rtnetlink.c

linux 内核源代码

		atomic_inc(&skb->users);
	netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL);
	if (echo)
		err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
	return err;
}

int rtnl_unicast(struct sk_buff *skb, u32 pid)
{
	return nlmsg_unicast(rtnl, skb, pid);
}

int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group,
		struct nlmsghdr *nlh, gfp_t flags)
{
	int report = 0;

	if (nlh)
		report = nlmsg_report(nlh);

	return nlmsg_notify(rtnl, skb, pid, group, report, flags);
}

void rtnl_set_sk_err(u32 group, int error)
{
	netlink_set_err(rtnl, 0, group, error);
}

int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
{
	struct nlattr *mx;
	int i, valid = 0;

	mx = nla_nest_start(skb, RTA_METRICS);
	if (mx == NULL)
		return -ENOBUFS;

	for (i = 0; i < RTAX_MAX; i++) {
		if (metrics[i]) {
			valid++;
			NLA_PUT_U32(skb, i+1, metrics[i]);
		}
	}

	if (!valid) {
		nla_nest_cancel(skb, mx);
		return 0;
	}

	return nla_nest_end(skb, mx);

nla_put_failure:
	return nla_nest_cancel(skb, mx);
}

int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
		       u32 ts, u32 tsage, long expires, u32 error)
{
	struct rta_cacheinfo ci = {
		.rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse),
		.rta_used = dst->__use,
		.rta_clntref = atomic_read(&(dst->__refcnt)),
		.rta_error = error,
		.rta_id =  id,
		.rta_ts = ts,
		.rta_tsage = tsage,
	};

	if (expires)
		ci.rta_expires = jiffies_to_clock_t(expires);

	return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}

EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);

static void set_operstate(struct net_device *dev, unsigned char transition)
{
	unsigned char operstate = dev->operstate;

	switch(transition) {
	case IF_OPER_UP:
		if ((operstate == IF_OPER_DORMANT ||
		     operstate == IF_OPER_UNKNOWN) &&
		    !netif_dormant(dev))
			operstate = IF_OPER_UP;
		break;

	case IF_OPER_DORMANT:
		if (operstate == IF_OPER_UP ||
		    operstate == IF_OPER_UNKNOWN)
			operstate = IF_OPER_DORMANT;
		break;
	}

	if (dev->operstate != operstate) {
		write_lock_bh(&dev_base_lock);
		dev->operstate = operstate;
		write_unlock_bh(&dev_base_lock);
		netdev_state_change(dev);
	}
}

static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
				 struct net_device_stats *b)
{
	a->rx_packets = b->rx_packets;
	a->tx_packets = b->tx_packets;
	a->rx_bytes = b->rx_bytes;
	a->tx_bytes = b->tx_bytes;
	a->rx_errors = b->rx_errors;
	a->tx_errors = b->tx_errors;
	a->rx_dropped = b->rx_dropped;
	a->tx_dropped = b->tx_dropped;

	a->multicast = b->multicast;
	a->collisions = b->collisions;

	a->rx_length_errors = b->rx_length_errors;
	a->rx_over_errors = b->rx_over_errors;
	a->rx_crc_errors = b->rx_crc_errors;
	a->rx_frame_errors = b->rx_frame_errors;
	a->rx_fifo_errors = b->rx_fifo_errors;
	a->rx_missed_errors = b->rx_missed_errors;

	a->tx_aborted_errors = b->tx_aborted_errors;
	a->tx_carrier_errors = b->tx_carrier_errors;
	a->tx_fifo_errors = b->tx_fifo_errors;
	a->tx_heartbeat_errors = b->tx_heartbeat_errors;
	a->tx_window_errors = b->tx_window_errors;

	a->rx_compressed = b->rx_compressed;
	a->tx_compressed = b->tx_compressed;
};

static inline size_t if_nlmsg_size(const struct net_device *dev)
{
	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
	       + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
	       + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */
	       + nla_total_size(sizeof(struct rtnl_link_ifmap))
	       + nla_total_size(sizeof(struct rtnl_link_stats))
	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */
	       + nla_total_size(4) /* IFLA_TXQLEN */
	       + nla_total_size(4) /* IFLA_WEIGHT */
	       + nla_total_size(4) /* IFLA_MTU */
	       + nla_total_size(4) /* IFLA_LINK */
	       + nla_total_size(4) /* IFLA_MASTER */
	       + nla_total_size(1) /* IFLA_OPERSTATE */
	       + nla_total_size(1) /* IFLA_LINKMODE */
	       + rtnl_link_get_size(dev); /* IFLA_LINKINFO */
}

static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
			    int type, u32 pid, u32 seq, u32 change,
			    unsigned int flags)
{
	struct ifinfomsg *ifm;
	struct nlmsghdr *nlh;

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

	ifm = nlmsg_data(nlh);
	ifm->ifi_family = AF_UNSPEC;
	ifm->__ifi_pad = 0;
	ifm->ifi_type = dev->type;
	ifm->ifi_index = dev->ifindex;
	ifm->ifi_flags = dev_get_flags(dev);
	ifm->ifi_change = change;

	NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name);
	NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len);
	NLA_PUT_U8(skb, IFLA_OPERSTATE,
		   netif_running(dev) ? dev->operstate : IF_OPER_DOWN);
	NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode);
	NLA_PUT_U32(skb, IFLA_MTU, dev->mtu);

	if (dev->ifindex != dev->iflink)
		NLA_PUT_U32(skb, IFLA_LINK, dev->iflink);

	if (dev->master)
		NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex);

	if (dev->qdisc_sleeping)
		NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc_sleeping->ops->id);

	if (1) {
		struct rtnl_link_ifmap map = {
			.mem_start   = dev->mem_start,
			.mem_end     = dev->mem_end,
			.base_addr   = dev->base_addr,
			.irq         = dev->irq,
			.dma         = dev->dma,
			.port        = dev->if_port,
		};
		NLA_PUT(skb, IFLA_MAP, sizeof(map), &map);
	}

	if (dev->addr_len) {
		NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr);
		NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast);
	}

	if (dev->get_stats) {
		struct net_device_stats *stats = dev->get_stats(dev);
		if (stats) {
			struct nlattr *attr;

			attr = nla_reserve(skb, IFLA_STATS,
					   sizeof(struct rtnl_link_stats));
			if (attr == NULL)
				goto nla_put_failure;

			copy_rtnl_link_stats(nla_data(attr), stats);
		}
	}

	if (dev->rtnl_link_ops) {
		if (rtnl_link_fill(skb, dev) < 0)
			goto nla_put_failure;
	}

	return nlmsg_end(skb, nlh);

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

static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = skb->sk->sk_net;
	int idx;
	int s_idx = cb->args[0];
	struct net_device *dev;

	idx = 0;
	for_each_netdev(net, dev) {
		if (idx < s_idx)
			goto cont;
		if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
				     NETLINK_CB(cb->skb).pid,
				     cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0)
			break;
cont:
		idx++;
	}
	cb->args[0] = idx;

	return skb->len;
}

const struct nla_policy ifla_policy[IFLA_MAX+1] = {
	[IFLA_IFNAME]		= { .type = NLA_STRING, .len = IFNAMSIZ-1 },
	[IFLA_ADDRESS]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
	[IFLA_BROADCAST]	= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
	[IFLA_MAP]		= { .len = sizeof(struct rtnl_link_ifmap) },
	[IFLA_MTU]		= { .type = NLA_U32 },
	[IFLA_TXQLEN]		= { .type = NLA_U32 },
	[IFLA_WEIGHT]		= { .type = NLA_U32 },
	[IFLA_OPERSTATE]	= { .type = NLA_U8 },
	[IFLA_LINKMODE]		= { .type = NLA_U8 },
	[IFLA_NET_NS_PID]	= { .type = NLA_U32 },
};

static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
	[IFLA_INFO_KIND]	= { .type = NLA_STRING },
	[IFLA_INFO_DATA]	= { .type = NLA_NESTED },
};

static struct net *get_net_ns_by_pid(pid_t pid)
{
	struct task_struct *tsk;
	struct net *net;

	/* Lookup the network namespace */
	net = ERR_PTR(-ESRCH);
	rcu_read_lock();
	tsk = find_task_by_vpid(pid);
	if (tsk) {
		struct nsproxy *nsproxy;
		nsproxy = task_nsproxy(tsk);
		if (nsproxy)
			net = get_net(nsproxy->net_ns);
	}
	rcu_read_unlock();
	return net;
}

static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
		      struct nlattr **tb, char *ifname, int modified)
{
	int send_addr_notify = 0;
	int err;

	if (tb[IFLA_NET_NS_PID]) {
		struct net *net;
		net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID]));
		if (IS_ERR(net)) {
			err = PTR_ERR(net);
			goto errout;
		}
		err = dev_change_net_namespace(dev, net, ifname);
		put_net(net);
		if (err)
			goto errout;
		modified = 1;
	}

	if (tb[IFLA_MAP]) {
		struct rtnl_link_ifmap *u_map;
		struct ifmap k_map;

		if (!dev->set_config) {
			err = -EOPNOTSUPP;
			goto errout;
		}

		if (!netif_device_present(dev)) {
			err = -ENODEV;
			goto errout;
		}

		u_map = nla_data(tb[IFLA_MAP]);
		k_map.mem_start = (unsigned long) u_map->mem_start;
		k_map.mem_end = (unsigned long) u_map->mem_end;
		k_map.base_addr = (unsigned short) u_map->base_addr;
		k_map.irq = (unsigned char) u_map->irq;
		k_map.dma = (unsigned char) u_map->dma;
		k_map.port = (unsigned char) u_map->port;

		err = dev->set_config(dev, &k_map);
		if (err < 0)
			goto errout;

		modified = 1;
	}

	if (tb[IFLA_ADDRESS]) {
		struct sockaddr *sa;
		int len;

		if (!dev->set_mac_address) {
			err = -EOPNOTSUPP;
			goto errout;
		}

		if (!netif_device_present(dev)) {
			err = -ENODEV;
			goto errout;
		}

		len = sizeof(sa_family_t) + dev->addr_len;
		sa = kmalloc(len, GFP_KERNEL);
		if (!sa) {
			err = -ENOMEM;
			goto errout;
		}
		sa->sa_family = dev->type;
		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
		       dev->addr_len);
		err = dev->set_mac_address(dev, sa);
		kfree(sa);
		if (err)
			goto errout;
		send_addr_notify = 1;
		modified = 1;
	}

	if (tb[IFLA_MTU]) {
		err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
		if (err < 0)
			goto errout;
		modified = 1;
	}

	/*
	 * Interface selected by interface index but interface
	 * name provided implies that a name change has been
	 * requested.
	 */
	if (ifm->ifi_index > 0 && ifname[0]) {
		err = dev_change_name(dev, ifname);
		if (err < 0)
			goto errout;
		modified = 1;
	}

	if (tb[IFLA_BROADCAST]) {
		nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len);
		send_addr_notify = 1;
	}

	if (ifm->ifi_flags || ifm->ifi_change) {
		unsigned int flags = ifm->ifi_flags;

		/* bugwards compatibility: ifi_change == 0 is treated as ~0 */
		if (ifm->ifi_change)
			flags = (flags & ifm->ifi_change) |
				(dev->flags & ~ifm->ifi_change);
		dev_change_flags(dev, flags);
	}

	if (tb[IFLA_TXQLEN])
		dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);

	if (tb[IFLA_OPERSTATE])
		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));

	if (tb[IFLA_LINKMODE]) {
		write_lock_bh(&dev_base_lock);
		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
		write_unlock_bh(&dev_base_lock);
	}

	err = 0;

errout:
	if (err < 0 && modified && net_ratelimit())
		printk(KERN_WARNING "A link change request failed with "
		       "some changes comitted already. Interface %s may "
		       "have been left with an inconsistent configuration, "
		       "please check.\n", dev->name);

	if (send_addr_notify)
		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
	return err;
}

static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net *net = skb->sk->sk_net;
	struct ifinfomsg *ifm;
	struct net_device *dev;
	int err;
	struct nlattr *tb[IFLA_MAX+1];
	char ifname[IFNAMSIZ];

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
	if (err < 0)
		goto errout;

	if (tb[IFLA_IFNAME])
		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
	else
		ifname[0] = '\0';

	err = -EINVAL;
	ifm = nlmsg_data(nlh);
	if (ifm->ifi_index > 0)
		dev = dev_get_by_index(net, ifm->ifi_index);
	else if (tb[IFLA_IFNAME])
		dev = dev_get_by_name(net, ifname);
	else
		goto errout;

	if (dev == NULL) {
		err = -ENODEV;
		goto errout;
	}

	if (tb[IFLA_ADDRESS] &&
	    nla_len(tb[IFLA_ADDRESS]) < dev->addr_len)