devinet.c

Linux内核源代码 为压缩文件 是<<Linux内核>>一书中的源代码

				break;
			}
			ret = dev_change_flags(dev, ifr.ifr_flags);
			break;
	
		case SIOCSIFADDR:	/* Set interface address (and family) */
			if (inet_abc_len(sin->sin_addr.s_addr) < 0) {
				ret = -EINVAL;
				break;
			}

			if (!ifa) {
				if ((ifa = inet_alloc_ifa()) == NULL) {
					ret = -ENOBUFS;
					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 */
			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 */
			if (ifa->ifa_address != sin->sin_addr.s_addr) {
				if (inet_abc_len(sin->sin_addr.s_addr) < 0) {
					ret = -EINVAL;
					break;
				}
				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.
			 */
			if (bad_mask(sin->sin_addr.s_addr, 0)) {
				ret = -EINVAL;
				break;
			}

			if (ifa->ifa_mask != sin->sin_addr.s_addr) {
				inet_del_ifa(in_dev, ifap, 0);
				ifa->ifa_mask = sin->sin_addr.s_addr;
				ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask);
				inet_insert_ifa(ifa);
			}
			break;
	}
done:
	rtnl_unlock();
	dev_probe_unlock();
	return ret;

rarok:
	rtnl_unlock();
	dev_probe_unlock();
	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
		return -EFAULT;
	return 0;
}

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

	if (in_dev==NULL || (ifa=in_dev->ifa_list)==NULL)
		return 0;

	for ( ; ifa; ifa = ifa->ifa_next) {
		if (!buf) {
			done += sizeof(ifr);
			continue;
		}
		if (len < (int) sizeof(ifr))
			return done;
		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)))
			return -EFAULT;
		buf += sizeof(struct ifreq);
		len -= sizeof(struct ifreq);
		done += sizeof(struct ifreq);
	}
	return done;
}

u32 inet_select_addr(const struct net_device *dev, u32 dst, int scope)
{
	u32 addr = 0;
	struct in_device *in_dev;

	read_lock(&inetdev_lock);
	in_dev = __in_dev_get(dev);
	if (in_dev == NULL) {
		read_unlock(&inetdev_lock);
		return 0;
	}

	read_lock(&in_dev->lock);
	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);
	read_unlock(&in_dev->lock);
	read_unlock(&inetdev_lock);

	if (addr)
		return addr;

	/* 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);
	read_lock(&inetdev_lock);
	for (dev=dev_base; dev; dev=dev->next) {
		if ((in_dev=__in_dev_get(dev)) == NULL)
			continue;

		read_lock(&in_dev->lock);
		for_primary_ifa(in_dev) {
			if (ifa->ifa_scope != RT_SCOPE_LINK &&
			    ifa->ifa_scope <= scope) {
				read_unlock(&in_dev->lock);
				read_unlock(&inetdev_lock);
				read_unlock(&dev_base_lock);
				return ifa->ifa_local;
			}
		} endfor_ifa(in_dev);
		read_unlock(&in_dev->lock);
	}
	read_unlock(&inetdev_lock);
	read_unlock(&dev_base_lock);

	return 0;
}

/*
 *	Device notifier
 */

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

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

/* 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(dev);

	ASSERT_RTNL();

	if (in_dev == NULL)
		return NOTIFY_DONE;

	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 == &loopback_dev) {
			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:
		if (in_dev->ifa_list) {
			struct in_ifaddr *ifa;
			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
			/* Do not notify about label change, this event is
			   not interesting to applications using netlink.
			 */
		}
		break;
	}

	return NOTIFY_DONE;
}

struct notifier_block ip_netdev_notifier={
	inetdev_event,
	NULL,
	0
};

#ifdef CONFIG_RTNETLINK

static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
			    u32 pid, u32 seq, int event)
{
	struct ifaddrmsg *ifm;
	struct nlmsghdr  *nlh;
	unsigned char	 *b = skb->tail;

	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm));
	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)
		RTA_PUT(skb, IFA_ADDRESS, 4, &ifa->ifa_address);
	if (ifa->ifa_local)
		RTA_PUT(skb, IFA_LOCAL, 4, &ifa->ifa_local);
	if (ifa->ifa_broadcast)
		RTA_PUT(skb, IFA_BROADCAST, 4, &ifa->ifa_broadcast);
	if (ifa->ifa_anycast)
		RTA_PUT(skb, IFA_ANYCAST, 4, &ifa->ifa_anycast);
	if (ifa->ifa_label[0])
		RTA_PUT(skb, IFA_LABEL, IFNAMSIZ, &ifa->ifa_label);
	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
	int idx, ip_idx;
	int s_idx, s_ip_idx;
	struct net_device *dev;
	struct in_device *in_dev;
	struct in_ifaddr *ifa;

	s_idx = cb->args[0];
	s_ip_idx = ip_idx = cb->args[1];
	read_lock(&dev_base_lock);
	for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) {
		if (idx < s_idx)
			continue;
		if (idx > s_idx)
			s_ip_idx = 0;
		read_lock(&inetdev_lock);
		if ((in_dev = __in_dev_get(dev)) == NULL) {
			read_unlock(&inetdev_lock);
			continue;
		}
		read_lock(&in_dev->lock);
		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) <= 0) {
				read_unlock(&in_dev->lock);
				read_unlock(&inetdev_lock);
				goto done;
			}
		}
		read_unlock(&in_dev->lock);
		read_unlock(&inetdev_lock);
	}

done:
	read_unlock(&dev_base_lock);
	cb->args[0] = idx;
	cb->args[1] = ip_idx;

	return skb->len;
}

static void rtmsg_ifa(int event, struct in_ifaddr * ifa)
{
	struct sk_buff *skb;
	int size = NLMSG_SPACE(sizeof(struct ifaddrmsg)+128);

	skb = alloc_skb(size, GFP_KERNEL);
	if (!skb) {
		netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, ENOBUFS);
		return;
	}
	if (inet_fill_ifaddr(skb, ifa, 0, 0, event) < 0) {
		kfree_skb(skb);
		netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, EINVAL);
		return;
	}
	NETLINK_CB(skb).dst_groups = RTMGRP_IPV4_IFADDR;
	netlink_broadcast(rtnl, skb, 0, RTMGRP_IPV4_IFADDR, GFP_KERNEL);
}


static struct rtnetlink_link inet_rtnetlink_table[RTM_MAX-RTM_BASE+1] =
{
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},

	{ inet_rtm_newaddr,	NULL,			},
	{ inet_rtm_deladdr,	NULL,			},
	{ NULL,			inet_dump_ifaddr,	},
	{ NULL,			NULL,			},

	{ inet_rtm_newroute,	NULL,			},
	{ inet_rtm_delroute,	NULL,			},
	{ inet_rtm_getroute,	inet_dump_fib,		},
	{ NULL,			NULL,			},

	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},

#ifdef CONFIG_IP_MULTIPLE_TABLES
	{ inet_rtm_newrule,	NULL,			},
	{ inet_rtm_delrule,	NULL,			},
	{ NULL,			inet_dump_rules,	},
	{ NULL,			NULL,			},
#else
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
	{ NULL,			NULL,			},
#endif
};

#endif /* CONFIG_RTNETLINK */


#ifdef CONFIG_SYSCTL

void inet_forward_change()
{
	struct net_device *dev;
	int on = ipv4_devconf.forwarding;

	ipv4_devconf.accept_redirects = !on;
	ipv4_devconf_dflt.forwarding = on;

	read_lock(&dev_base_lock);
	for (dev = dev_base; dev; dev = dev->next) {
		struct in_device *in_dev;
		read_lock(&inetdev_lock);
		in_dev = __in_dev_get(dev);
		if (in_dev)
			in_dev->cnf.forwarding = on;
		read_unlock(&inetdev_lock);
	}
	read_unlock(&dev_base_lock);

	rt_cache_flush(0);
}

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

	ret = proc_dointvec(ctl, write, filp, buffer, lenp);

	if (write && *valp != val) {
		if (valp == &ipv4_devconf.forwarding)
			inet_forward_change();
		else if (valp != &ipv4_devconf_dflt.forwarding)
			rt_cache_flush(0);
	}

        return ret;
}

static struct devinet_sysctl_table
{
	struct ctl_table_header *sysctl_header;
	ctl_table devinet_vars[13];
	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 = {
	NULL,
	{{NET_IPV4_CONF_FORWARDING, "forwarding",
         &ipv4_devconf.forwarding, sizeof(int), 0644, NULL,
         &devinet_sysctl_forward},
	{NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding",
         &ipv4_devconf.mc_forwarding, sizeof(int), 0444, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects",
         &ipv4_devconf.accept_redirects, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects",
         &ipv4_devconf.secure_redirects, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_SHARED_MEDIA, "shared_media",
         &ipv4_devconf.shared_media, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_RP_FILTER, "rp_filter",
         &ipv4_devconf.rp_filter, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects",
         &ipv4_devconf.send_redirects, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route",
         &ipv4_devconf.accept_source_route, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_PROXY_ARP, "proxy_arp",
         &ipv4_devconf.proxy_arp, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay",
         &ipv4_devconf.bootp_relay, sizeof(int), 0644, NULL,
         &proc_dointvec},
        {NET_IPV4_CONF_LOG_MARTIANS, "log_martians",
         &ipv4_devconf.log_martians, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_CONF_TAG, "tag",
	 &ipv4_devconf.tag, sizeof(int), 0644, NULL,
	 &proc_dointvec},
	 {0}},

	{{NET_PROTO_CONF_ALL, "all", NULL, 0, 0555, devinet_sysctl.devinet_vars},{0}},
	{{NET_IPV4_CONF, "conf", NULL, 0, 0555, devinet_sysctl.devinet_dev},{0}},
	{{NET_IPV4, "ipv4", NULL, 0, 0555, devinet_sysctl.devinet_conf_dir},{0}},
	{{CTL_NET, "net", NULL, 0, 0555, devinet_sysctl.devinet_proto_dir},{0}}
};

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;

	t = kmalloc(sizeof(*t), GFP_KERNEL);
	if (t == NULL)
		return;
	memcpy(t, &devinet_sysctl, sizeof(*t));
	for (i=0; i<sizeof(t->devinet_vars)/sizeof(t->devinet_vars[0])-1; i++) {
		t->devinet_vars[i].data += (char*)p - (char*)&ipv4_devconf;
		t->devinet_vars[i].de = NULL;
	}
	if (dev) {
		t->devinet_dev[0].procname = dev->name;
		t->devinet_dev[0].ctl_name = dev->ifindex;
	} else {
		t->devinet_dev[0].procname = "default";
		t->devinet_dev[0].ctl_name = NET_PROTO_CONF_DEFAULT;
	}
	t->devinet_dev[0].child = t->devinet_vars;
	t->devinet_dev[0].de = NULL;
	t->devinet_conf_dir[0].child = t->devinet_dev;
	t->devinet_conf_dir[0].de = NULL;
	t->devinet_proto_dir[0].child = t->devinet_conf_dir;
	t->devinet_proto_dir[0].de = NULL;
	t->devinet_root_dir[0].child = t->devinet_proto_dir;
	t->devinet_root_dir[0].de = NULL;

	t->sysctl_header = register_sysctl_table(t->devinet_root_dir, 0);
	if (t->sysctl_header == NULL)
		kfree(t);
	else
		p->sysctl = t;
}

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);
	}
}
#endif

void __init devinet_init(void)
{
	register_gifconf(PF_INET, inet_gifconf);
	register_netdevice_notifier(&ip_netdev_notifier);
#ifdef CONFIG_RTNETLINK
	rtnetlink_links[PF_INET] = inet_rtnetlink_table;
#endif
#ifdef CONFIG_SYSCTL
	devinet_sysctl.sysctl_header =
		register_sysctl_table(devinet_sysctl.devinet_root_dir, 0);
	devinet_sysctl_register(NULL, &ipv4_devconf_dflt);
#endif
}