fib_frontend.c

linux 内核源代码

};

static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh,
			     struct fib_config *cfg)
{
	struct nlattr *attr;
	int err, remaining;
	struct rtmsg *rtm;

	err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy);
	if (err < 0)
		goto errout;

	memset(cfg, 0, sizeof(*cfg));

	rtm = nlmsg_data(nlh);
	cfg->fc_dst_len = rtm->rtm_dst_len;
	cfg->fc_tos = rtm->rtm_tos;
	cfg->fc_table = rtm->rtm_table;
	cfg->fc_protocol = rtm->rtm_protocol;
	cfg->fc_scope = rtm->rtm_scope;
	cfg->fc_type = rtm->rtm_type;
	cfg->fc_flags = rtm->rtm_flags;
	cfg->fc_nlflags = nlh->nlmsg_flags;

	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
	cfg->fc_nlinfo.nlh = nlh;

	if (cfg->fc_type > RTN_MAX) {
		err = -EINVAL;
		goto errout;
	}

	nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
		switch (nla_type(attr)) {
		case RTA_DST:
			cfg->fc_dst = nla_get_be32(attr);
			break;
		case RTA_OIF:
			cfg->fc_oif = nla_get_u32(attr);
			break;
		case RTA_GATEWAY:
			cfg->fc_gw = nla_get_be32(attr);
			break;
		case RTA_PRIORITY:
			cfg->fc_priority = nla_get_u32(attr);
			break;
		case RTA_PREFSRC:
			cfg->fc_prefsrc = nla_get_be32(attr);
			break;
		case RTA_METRICS:
			cfg->fc_mx = nla_data(attr);
			cfg->fc_mx_len = nla_len(attr);
			break;
		case RTA_MULTIPATH:
			cfg->fc_mp = nla_data(attr);
			cfg->fc_mp_len = nla_len(attr);
			break;
		case RTA_FLOW:
			cfg->fc_flow = nla_get_u32(attr);
			break;
		case RTA_TABLE:
			cfg->fc_table = nla_get_u32(attr);
			break;
		}
	}

	return 0;
errout:
	return err;
}

static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct fib_config cfg;
	struct fib_table *tb;
	int err;

	err = rtm_to_fib_config(skb, nlh, &cfg);
	if (err < 0)
		goto errout;

	tb = fib_get_table(cfg.fc_table);
	if (tb == NULL) {
		err = -ESRCH;
		goto errout;
	}

	err = tb->tb_delete(tb, &cfg);
errout:
	return err;
}

static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct fib_config cfg;
	struct fib_table *tb;
	int err;

	err = rtm_to_fib_config(skb, nlh, &cfg);
	if (err < 0)
		goto errout;

	tb = fib_new_table(cfg.fc_table);
	if (tb == NULL) {
		err = -ENOBUFS;
		goto errout;
	}

	err = tb->tb_insert(tb, &cfg);
errout:
	return err;
}

static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
	unsigned int h, s_h;
	unsigned int e = 0, s_e;
	struct fib_table *tb;
	struct hlist_node *node;
	int dumped = 0;

	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
		return ip_rt_dump(skb, cb);

	s_h = cb->args[0];
	s_e = cb->args[1];

	for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
		e = 0;
		hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) {
			if (e < s_e)
				goto next;
			if (dumped)
				memset(&cb->args[2], 0, sizeof(cb->args) -
						 2 * sizeof(cb->args[0]));
			if (tb->tb_dump(tb, skb, cb) < 0)
				goto out;
			dumped = 1;
next:
			e++;
		}
	}
out:
	cb->args[1] = e;
	cb->args[0] = h;

	return skb->len;
}

/* Prepare and feed intra-kernel routing request.
   Really, it should be netlink message, but :-( netlink
   can be not configured, so that we feed it directly
   to fib engine. It is legal, because all events occur
   only when netlink is already locked.
 */

static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
{
	struct fib_table *tb;
	struct fib_config cfg = {
		.fc_protocol = RTPROT_KERNEL,
		.fc_type = type,
		.fc_dst = dst,
		.fc_dst_len = dst_len,
		.fc_prefsrc = ifa->ifa_local,
		.fc_oif = ifa->ifa_dev->dev->ifindex,
		.fc_nlflags = NLM_F_CREATE | NLM_F_APPEND,
	};

	if (type == RTN_UNICAST)
		tb = fib_new_table(RT_TABLE_MAIN);
	else
		tb = fib_new_table(RT_TABLE_LOCAL);

	if (tb == NULL)
		return;

	cfg.fc_table = tb->tb_id;

	if (type != RTN_LOCAL)
		cfg.fc_scope = RT_SCOPE_LINK;
	else
		cfg.fc_scope = RT_SCOPE_HOST;

	if (cmd == RTM_NEWROUTE)
		tb->tb_insert(tb, &cfg);
	else
		tb->tb_delete(tb, &cfg);
}

void fib_add_ifaddr(struct in_ifaddr *ifa)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;
	struct in_ifaddr *prim = ifa;
	__be32 mask = ifa->ifa_mask;
	__be32 addr = ifa->ifa_local;
	__be32 prefix = ifa->ifa_address&mask;

	if (ifa->ifa_flags&IFA_F_SECONDARY) {
		prim = inet_ifa_byprefix(in_dev, prefix, mask);
		if (prim == NULL) {
			printk(KERN_DEBUG "fib_add_ifaddr: bug: prim == NULL\n");
			return;
		}
	}

	fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim);

	if (!(dev->flags&IFF_UP))
		return;

	/* Add broadcast address, if it is explicitly assigned. */
	if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
		fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);

	if (!ZERONET(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) &&
	    (prefix != addr || ifa->ifa_prefixlen < 32)) {
		fib_magic(RTM_NEWROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL :
			  RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim);

		/* Add network specific broadcasts, when it takes a sense */
		if (ifa->ifa_prefixlen < 31) {
			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim);
			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix|~mask, 32, prim);
		}
	}
}

static void fib_del_ifaddr(struct in_ifaddr *ifa)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;
	struct in_ifaddr *ifa1;
	struct in_ifaddr *prim = ifa;
	__be32 brd = ifa->ifa_address|~ifa->ifa_mask;
	__be32 any = ifa->ifa_address&ifa->ifa_mask;
#define LOCAL_OK	1
#define BRD_OK		2
#define BRD0_OK		4
#define BRD1_OK		8
	unsigned ok = 0;

	if (!(ifa->ifa_flags&IFA_F_SECONDARY))
		fib_magic(RTM_DELROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL :
			  RTN_UNICAST, any, ifa->ifa_prefixlen, prim);
	else {
		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
		if (prim == NULL) {
			printk(KERN_DEBUG "fib_del_ifaddr: bug: prim == NULL\n");
			return;
		}
	}

	/* Deletion is more complicated than add.
	   We should take care of not to delete too much :-)

	   Scan address list to be sure that addresses are really gone.
	 */

	for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
		if (ifa->ifa_local == ifa1->ifa_local)
			ok |= LOCAL_OK;
		if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
			ok |= BRD_OK;
		if (brd == ifa1->ifa_broadcast)
			ok |= BRD1_OK;
		if (any == ifa1->ifa_broadcast)
			ok |= BRD0_OK;
	}

	if (!(ok&BRD_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
	if (!(ok&BRD1_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
	if (!(ok&BRD0_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
	if (!(ok&LOCAL_OK)) {
		fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);

		/* Check, that this local address finally disappeared. */
		if (inet_addr_type(ifa->ifa_local) != RTN_LOCAL) {
			/* And the last, but not the least thing.
			   We must flush stray FIB entries.

			   First of all, we scan fib_info list searching
			   for stray nexthop entries, then ignite fib_flush.
			*/
			if (fib_sync_down(ifa->ifa_local, NULL, 0))
				fib_flush();
		}
	}
#undef LOCAL_OK
#undef BRD_OK
#undef BRD0_OK
#undef BRD1_OK
}

static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb )
{

	struct fib_result       res;
	struct flowi            fl = { .mark = frn->fl_mark,
				       .nl_u = { .ip4_u = { .daddr = frn->fl_addr,
							    .tos = frn->fl_tos,
							    .scope = frn->fl_scope } } };

#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r = NULL;
#endif

	frn->err = -ENOENT;
	if (tb) {
		local_bh_disable();

		frn->tb_id = tb->tb_id;
		frn->err = tb->tb_lookup(tb, &fl, &res);

		if (!frn->err) {
			frn->prefixlen = res.prefixlen;
			frn->nh_sel = res.nh_sel;
			frn->type = res.type;
			frn->scope = res.scope;
			fib_res_put(&res);
		}
		local_bh_enable();
	}
}

static void nl_fib_input(struct sk_buff *skb)
{
	struct fib_result_nl *frn;
	struct nlmsghdr *nlh;
	struct fib_table *tb;
	u32 pid;

	nlh = nlmsg_hdr(skb);
	if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len ||
	    nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn)))
		return;

	skb = skb_clone(skb, GFP_KERNEL);
	if (skb == NULL)
		return;
	nlh = nlmsg_hdr(skb);

	frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
	tb = fib_get_table(frn->tb_id_in);

	nl_fib_lookup(frn, tb);

	pid = NETLINK_CB(skb).pid;       /* pid of sending process */
	NETLINK_CB(skb).pid = 0;         /* from kernel */
	NETLINK_CB(skb).dst_group = 0;  /* unicast */
	netlink_unicast(fibnl, skb, pid, MSG_DONTWAIT);
}

static void nl_fib_lookup_init(void)
{
	fibnl = netlink_kernel_create(&init_net, NETLINK_FIB_LOOKUP, 0,
				      nl_fib_input, NULL, THIS_MODULE);
}

static void fib_disable_ip(struct net_device *dev, int force)
{
	if (fib_sync_down(0, dev, force))
		fib_flush();
	rt_cache_flush(0);
	arp_ifdown(dev);
}

static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct in_ifaddr *ifa = (struct in_ifaddr*)ptr;

	switch (event) {
	case NETDEV_UP:
		fib_add_ifaddr(ifa);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		fib_sync_up(ifa->ifa_dev->dev);
#endif
		rt_cache_flush(-1);
		break;
	case NETDEV_DOWN:
		fib_del_ifaddr(ifa);
		if (ifa->ifa_dev->ifa_list == NULL) {
			/* Last address was deleted from this interface.
			   Disable IP.
			 */
			fib_disable_ip(ifa->ifa_dev->dev, 1);
		} else {
			rt_cache_flush(-1);
		}
		break;
	}
	return NOTIFY_DONE;
}

static int fib_netdev_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;

	if (event == NETDEV_UNREGISTER) {
		fib_disable_ip(dev, 2);
		return NOTIFY_DONE;
	}

	if (!in_dev)
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_UP:
		for_ifa(in_dev) {
			fib_add_ifaddr(ifa);
		} endfor_ifa(in_dev);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		fib_sync_up(dev);
#endif
		rt_cache_flush(-1);
		break;
	case NETDEV_DOWN:
		fib_disable_ip(dev, 0);
		break;
	case NETDEV_CHANGEMTU:
	case NETDEV_CHANGE:
		rt_cache_flush(0);
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block fib_inetaddr_notifier = {
	.notifier_call =fib_inetaddr_event,
};

static struct notifier_block fib_netdev_notifier = {
	.notifier_call =fib_netdev_event,
};

void __init ip_fib_init(void)
{
	unsigned int i;

	for (i = 0; i < FIB_TABLE_HASHSZ; i++)
		INIT_HLIST_HEAD(&fib_table_hash[i]);

	fib4_rules_init();

	register_netdevice_notifier(&fib_netdev_notifier);
	register_inetaddr_notifier(&fib_inetaddr_notifier);
	nl_fib_lookup_init();

	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL);
	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL);
	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib);
}

EXPORT_SYMBOL(inet_addr_type);
EXPORT_SYMBOL(ip_dev_find);