rtnetlink.c

linux 内核源代码

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Routing netlink socket interface: protocol independent part.
 *
 * Authors:	Alexey Kuznetsov, <[e-mail]>
 *
 *		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.
 *
 *	Fixes:
 *	Vitaly E. Lavrov		RTA_OK arithmetics was wrong.
 */

#include <linux/errno.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/if_addr.h>
#include <linux/nsproxy.h>

#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/string.h>

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/udp.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/fib_rules.h>
#include <net/rtnetlink.h>

struct rtnl_link
{
	rtnl_doit_func		doit;
	rtnl_dumpit_func	dumpit;
};

static DEFINE_MUTEX(rtnl_mutex);
static struct sock *rtnl;

void rtnl_lock(void)
{
	mutex_lock(&rtnl_mutex);
}

void __rtnl_unlock(void)
{
	mutex_unlock(&rtnl_mutex);
}

void rtnl_unlock(void)
{
	mutex_unlock(&rtnl_mutex);
	netdev_run_todo();
}

int rtnl_trylock(void)
{
	return mutex_trylock(&rtnl_mutex);
}

int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len)
{
	memset(tb, 0, sizeof(struct rtattr*)*maxattr);

	while (RTA_OK(rta, len)) {
		unsigned flavor = rta->rta_type;
		if (flavor && flavor <= maxattr)
			tb[flavor-1] = rta;
		rta = RTA_NEXT(rta, len);
	}
	return 0;
}

int __rtattr_parse_nested_compat(struct rtattr *tb[], int maxattr,
				 struct rtattr *rta, int len)
{
	if (RTA_PAYLOAD(rta) < len)
		return -1;
	if (RTA_PAYLOAD(rta) >= RTA_ALIGN(len) + sizeof(struct rtattr)) {
		rta = RTA_DATA(rta) + RTA_ALIGN(len);
		return rtattr_parse_nested(tb, maxattr, rta);
	}
	memset(tb, 0, sizeof(struct rtattr *) * maxattr);
	return 0;
}

static struct rtnl_link *rtnl_msg_handlers[NPROTO];

static inline int rtm_msgindex(int msgtype)
{
	int msgindex = msgtype - RTM_BASE;

	/*
	 * msgindex < 0 implies someone tried to register a netlink
	 * control code. msgindex >= RTM_NR_MSGTYPES may indicate that
	 * the message type has not been added to linux/rtnetlink.h
	 */
	BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES);

	return msgindex;
}

static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
{
	struct rtnl_link *tab;

	tab = rtnl_msg_handlers[protocol];
	if (tab == NULL || tab[msgindex].doit == NULL)
		tab = rtnl_msg_handlers[PF_UNSPEC];

	return tab ? tab[msgindex].doit : NULL;
}

static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
{
	struct rtnl_link *tab;

	tab = rtnl_msg_handlers[protocol];
	if (tab == NULL || tab[msgindex].dumpit == NULL)
		tab = rtnl_msg_handlers[PF_UNSPEC];

	return tab ? tab[msgindex].dumpit : NULL;
}

/**
 * __rtnl_register - Register a rtnetlink message type
 * @protocol: Protocol family or PF_UNSPEC
 * @msgtype: rtnetlink message type
 * @doit: Function pointer called for each request message
 * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
 *
 * Registers the specified function pointers (at least one of them has
 * to be non-NULL) to be called whenever a request message for the
 * specified protocol family and message type is received.
 *
 * The special protocol family PF_UNSPEC may be used to define fallback
 * function pointers for the case when no entry for the specific protocol
 * family exists.
 *
 * Returns 0 on success or a negative error code.
 */
int __rtnl_register(int protocol, int msgtype,
		    rtnl_doit_func doit, rtnl_dumpit_func dumpit)
{
	struct rtnl_link *tab;
	int msgindex;

	BUG_ON(protocol < 0 || protocol >= NPROTO);
	msgindex = rtm_msgindex(msgtype);

	tab = rtnl_msg_handlers[protocol];
	if (tab == NULL) {
		tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL);
		if (tab == NULL)
			return -ENOBUFS;

		rtnl_msg_handlers[protocol] = tab;
	}

	if (doit)
		tab[msgindex].doit = doit;

	if (dumpit)
		tab[msgindex].dumpit = dumpit;

	return 0;
}

EXPORT_SYMBOL_GPL(__rtnl_register);

/**
 * rtnl_register - Register a rtnetlink message type
 *
 * Identical to __rtnl_register() but panics on failure. This is useful
 * as failure of this function is very unlikely, it can only happen due
 * to lack of memory when allocating the chain to store all message
 * handlers for a protocol. Meant for use in init functions where lack
 * of memory implies no sense in continueing.
 */
void rtnl_register(int protocol, int msgtype,
		   rtnl_doit_func doit, rtnl_dumpit_func dumpit)
{
	if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0)
		panic("Unable to register rtnetlink message handler, "
		      "protocol = %d, message type = %d\n",
		      protocol, msgtype);
}

EXPORT_SYMBOL_GPL(rtnl_register);

/**
 * rtnl_unregister - Unregister a rtnetlink message type
 * @protocol: Protocol family or PF_UNSPEC
 * @msgtype: rtnetlink message type
 *
 * Returns 0 on success or a negative error code.
 */
int rtnl_unregister(int protocol, int msgtype)
{
	int msgindex;

	BUG_ON(protocol < 0 || protocol >= NPROTO);
	msgindex = rtm_msgindex(msgtype);

	if (rtnl_msg_handlers[protocol] == NULL)
		return -ENOENT;

	rtnl_msg_handlers[protocol][msgindex].doit = NULL;
	rtnl_msg_handlers[protocol][msgindex].dumpit = NULL;

	return 0;
}

EXPORT_SYMBOL_GPL(rtnl_unregister);

/**
 * rtnl_unregister_all - Unregister all rtnetlink message type of a protocol
 * @protocol : Protocol family or PF_UNSPEC
 *
 * Identical to calling rtnl_unregster() for all registered message types
 * of a certain protocol family.
 */
void rtnl_unregister_all(int protocol)
{
	BUG_ON(protocol < 0 || protocol >= NPROTO);

	kfree(rtnl_msg_handlers[protocol]);
	rtnl_msg_handlers[protocol] = NULL;
}

EXPORT_SYMBOL_GPL(rtnl_unregister_all);

static LIST_HEAD(link_ops);

/**
 * __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
 * @ops: struct rtnl_link_ops * to register
 *
 * The caller must hold the rtnl_mutex. This function should be used
 * by drivers that create devices during module initialization. It
 * must be called before registering the devices.
 *
 * Returns 0 on success or a negative error code.
 */
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
	if (!ops->dellink)
		ops->dellink = unregister_netdevice;

	list_add_tail(&ops->list, &link_ops);
	return 0;
}

EXPORT_SYMBOL_GPL(__rtnl_link_register);

/**
 * rtnl_link_register - Register rtnl_link_ops with rtnetlink.
 * @ops: struct rtnl_link_ops * to register
 *
 * Returns 0 on success or a negative error code.
 */
int rtnl_link_register(struct rtnl_link_ops *ops)
{
	int err;

	rtnl_lock();
	err = __rtnl_link_register(ops);
	rtnl_unlock();
	return err;
}

EXPORT_SYMBOL_GPL(rtnl_link_register);

/**
 * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
 * @ops: struct rtnl_link_ops * to unregister
 *
 * The caller must hold the rtnl_mutex.
 */
void __rtnl_link_unregister(struct rtnl_link_ops *ops)
{
	struct net_device *dev, *n;
	struct net *net;

	for_each_net(net) {
restart:
		for_each_netdev_safe(net, dev, n) {
			if (dev->rtnl_link_ops == ops) {
				ops->dellink(dev);
				goto restart;
			}
		}
	}
	list_del(&ops->list);
}

EXPORT_SYMBOL_GPL(__rtnl_link_unregister);

/**
 * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
 * @ops: struct rtnl_link_ops * to unregister
 */
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
	rtnl_lock();
	__rtnl_link_unregister(ops);
	rtnl_unlock();
}

EXPORT_SYMBOL_GPL(rtnl_link_unregister);

static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
{
	const struct rtnl_link_ops *ops;

	list_for_each_entry(ops, &link_ops, list) {
		if (!strcmp(ops->kind, kind))
			return ops;
	}
	return NULL;
}

static size_t rtnl_link_get_size(const struct net_device *dev)
{
	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
	size_t size;

	if (!ops)
		return 0;

	size = nlmsg_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */
	       nlmsg_total_size(strlen(ops->kind) + 1);	 /* IFLA_INFO_KIND */

	if (ops->get_size)
		/* IFLA_INFO_DATA + nested data */
		size += nlmsg_total_size(sizeof(struct nlattr)) +
			ops->get_size(dev);

	if (ops->get_xstats_size)
		size += ops->get_xstats_size(dev);	/* IFLA_INFO_XSTATS */

	return size;
}

static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
{
	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
	struct nlattr *linkinfo, *data;
	int err = -EMSGSIZE;

	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
	if (linkinfo == NULL)
		goto out;

	if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
		goto err_cancel_link;
	if (ops->fill_xstats) {
		err = ops->fill_xstats(skb, dev);
		if (err < 0)
			goto err_cancel_link;
	}
	if (ops->fill_info) {
		data = nla_nest_start(skb, IFLA_INFO_DATA);
		if (data == NULL)
			goto err_cancel_link;
		err = ops->fill_info(skb, dev);
		if (err < 0)
			goto err_cancel_data;
		nla_nest_end(skb, data);
	}

	nla_nest_end(skb, linkinfo);
	return 0;

err_cancel_data:
	nla_nest_cancel(skb, data);
err_cancel_link:
	nla_nest_cancel(skb, linkinfo);
out:
	return err;
}

static const int rtm_min[RTM_NR_FAMILIES] =
{
	[RTM_FAM(RTM_NEWLINK)]      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
	[RTM_FAM(RTM_NEWADDR)]      = NLMSG_LENGTH(sizeof(struct ifaddrmsg)),
	[RTM_FAM(RTM_NEWROUTE)]     = NLMSG_LENGTH(sizeof(struct rtmsg)),
	[RTM_FAM(RTM_NEWRULE)]      = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)),
	[RTM_FAM(RTM_NEWQDISC)]     = NLMSG_LENGTH(sizeof(struct tcmsg)),
	[RTM_FAM(RTM_NEWTCLASS)]    = NLMSG_LENGTH(sizeof(struct tcmsg)),
	[RTM_FAM(RTM_NEWTFILTER)]   = NLMSG_LENGTH(sizeof(struct tcmsg)),
	[RTM_FAM(RTM_NEWACTION)]    = NLMSG_LENGTH(sizeof(struct tcamsg)),
	[RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
	[RTM_FAM(RTM_GETANYCAST)]   = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
};

static const int rta_max[RTM_NR_FAMILIES] =
{
	[RTM_FAM(RTM_NEWLINK)]      = IFLA_MAX,
	[RTM_FAM(RTM_NEWADDR)]      = IFA_MAX,
	[RTM_FAM(RTM_NEWROUTE)]     = RTA_MAX,
	[RTM_FAM(RTM_NEWRULE)]      = FRA_MAX,
	[RTM_FAM(RTM_NEWQDISC)]     = TCA_MAX,
	[RTM_FAM(RTM_NEWTCLASS)]    = TCA_MAX,
	[RTM_FAM(RTM_NEWTFILTER)]   = TCA_MAX,
	[RTM_FAM(RTM_NEWACTION)]    = TCAA_MAX,
};

void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
{
	struct rtattr *rta;
	int size = RTA_LENGTH(attrlen);

	rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size));
	rta->rta_type = attrtype;
	rta->rta_len = size;
	memcpy(RTA_DATA(rta), data, attrlen);
	memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size);
}

size_t rtattr_strlcpy(char *dest, const struct rtattr *rta, size_t size)
{
	size_t ret = RTA_PAYLOAD(rta);
	char *src = RTA_DATA(rta);

	if (ret > 0 && src[ret - 1] == '\0')
		ret--;
	if (size > 0) {
		size_t len = (ret >= size) ? size - 1 : ret;
		memset(dest, 0, size);
		memcpy(dest, src, len);
	}
	return ret;
}

int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo)
{
	int err = 0;

	NETLINK_CB(skb).dst_group = group;
	if (echo)