af_netlink.c

linux 内核源代码

	}
	siocb->scm->creds = *NETLINK_CREDS(skb);
	if (flags & MSG_TRUNC)
		copied = skb->len;
	skb_free_datagram(sk, skb);

	if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2)
		netlink_dump(sk);

	scm_recv(sock, msg, siocb->scm, flags);
out:
	netlink_rcv_wake(sk);
	return err ? : copied;
}

static void netlink_data_ready(struct sock *sk, int len)
{
	BUG();
}

/*
 *	We export these functions to other modules. They provide a
 *	complete set of kernel non-blocking support for message
 *	queueing.
 */

struct sock *
netlink_kernel_create(struct net *net, int unit, unsigned int groups,
		      void (*input)(struct sk_buff *skb),
		      struct mutex *cb_mutex, struct module *module)
{
	struct socket *sock;
	struct sock *sk;
	struct netlink_sock *nlk;
	unsigned long *listeners = NULL;

	BUG_ON(!nl_table);

	if (unit<0 || unit>=MAX_LINKS)
		return NULL;

	if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
		return NULL;

	if (__netlink_create(net, sock, cb_mutex, unit) < 0)
		goto out_sock_release;

	if (groups < 32)
		groups = 32;

	listeners = kzalloc(NLGRPSZ(groups), GFP_KERNEL);
	if (!listeners)
		goto out_sock_release;

	sk = sock->sk;
	sk->sk_data_ready = netlink_data_ready;
	if (input)
		nlk_sk(sk)->netlink_rcv = input;

	if (netlink_insert(sk, net, 0))
		goto out_sock_release;

	nlk = nlk_sk(sk);
	nlk->flags |= NETLINK_KERNEL_SOCKET;

	netlink_table_grab();
	if (!nl_table[unit].registered) {
		nl_table[unit].groups = groups;
		nl_table[unit].listeners = listeners;
		nl_table[unit].cb_mutex = cb_mutex;
		nl_table[unit].module = module;
		nl_table[unit].registered = 1;
	} else {
		kfree(listeners);
	}
	netlink_table_ungrab();

	return sk;

out_sock_release:
	kfree(listeners);
	sock_release(sock);
	return NULL;
}

/**
 * netlink_change_ngroups - change number of multicast groups
 *
 * This changes the number of multicast groups that are available
 * on a certain netlink family. Note that it is not possible to
 * change the number of groups to below 32. Also note that it does
 * not implicitly call netlink_clear_multicast_users() when the
 * number of groups is reduced.
 *
 * @sk: The kernel netlink socket, as returned by netlink_kernel_create().
 * @groups: The new number of groups.
 */
int netlink_change_ngroups(struct sock *sk, unsigned int groups)
{
	unsigned long *listeners, *old = NULL;
	struct netlink_table *tbl = &nl_table[sk->sk_protocol];
	int err = 0;

	if (groups < 32)
		groups = 32;

	netlink_table_grab();
	if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) {
		listeners = kzalloc(NLGRPSZ(groups), GFP_ATOMIC);
		if (!listeners) {
			err = -ENOMEM;
			goto out_ungrab;
		}
		old = tbl->listeners;
		memcpy(listeners, old, NLGRPSZ(tbl->groups));
		rcu_assign_pointer(tbl->listeners, listeners);
	}
	tbl->groups = groups;

 out_ungrab:
	netlink_table_ungrab();
	synchronize_rcu();
	kfree(old);
	return err;
}
EXPORT_SYMBOL(netlink_change_ngroups);

/**
 * netlink_clear_multicast_users - kick off multicast listeners
 *
 * This function removes all listeners from the given group.
 * @ksk: The kernel netlink socket, as returned by
 *	netlink_kernel_create().
 * @group: The multicast group to clear.
 */
void netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
{
	struct sock *sk;
	struct hlist_node *node;
	struct netlink_table *tbl = &nl_table[ksk->sk_protocol];

	netlink_table_grab();

	sk_for_each_bound(sk, node, &tbl->mc_list)
		netlink_update_socket_mc(nlk_sk(sk), group, 0);

	netlink_table_ungrab();
}
EXPORT_SYMBOL(netlink_clear_multicast_users);

void netlink_set_nonroot(int protocol, unsigned int flags)
{
	if ((unsigned int)protocol < MAX_LINKS)
		nl_table[protocol].nl_nonroot = flags;
}

static void netlink_destroy_callback(struct netlink_callback *cb)
{
	if (cb->skb)
		kfree_skb(cb->skb);
	kfree(cb);
}

/*
 * It looks a bit ugly.
 * It would be better to create kernel thread.
 */

static int netlink_dump(struct sock *sk)
{
	struct netlink_sock *nlk = nlk_sk(sk);
	struct netlink_callback *cb;
	struct sk_buff *skb;
	struct nlmsghdr *nlh;
	int len, err = -ENOBUFS;

	skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL);
	if (!skb)
		goto errout;

	mutex_lock(nlk->cb_mutex);

	cb = nlk->cb;
	if (cb == NULL) {
		err = -EINVAL;
		goto errout_skb;
	}

	len = cb->dump(skb, cb);

	if (len > 0) {
		mutex_unlock(nlk->cb_mutex);
		skb_queue_tail(&sk->sk_receive_queue, skb);
		sk->sk_data_ready(sk, len);
		return 0;
	}

	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);
	if (!nlh)
		goto errout_skb;

	memcpy(nlmsg_data(nlh), &len, sizeof(len));

	skb_queue_tail(&sk->sk_receive_queue, skb);
	sk->sk_data_ready(sk, skb->len);

	if (cb->done)
		cb->done(cb);
	nlk->cb = NULL;
	mutex_unlock(nlk->cb_mutex);

	netlink_destroy_callback(cb);
	return 0;

errout_skb:
	mutex_unlock(nlk->cb_mutex);
	kfree_skb(skb);
errout:
	return err;
}

int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
		       struct nlmsghdr *nlh,
		       int (*dump)(struct sk_buff *skb, struct netlink_callback*),
		       int (*done)(struct netlink_callback*))
{
	struct netlink_callback *cb;
	struct sock *sk;
	struct netlink_sock *nlk;

	cb = kzalloc(sizeof(*cb), GFP_KERNEL);
	if (cb == NULL)
		return -ENOBUFS;

	cb->dump = dump;
	cb->done = done;
	cb->nlh = nlh;
	atomic_inc(&skb->users);
	cb->skb = skb;

	sk = netlink_lookup(ssk->sk_net, ssk->sk_protocol, NETLINK_CB(skb).pid);
	if (sk == NULL) {
		netlink_destroy_callback(cb);
		return -ECONNREFUSED;
	}
	nlk = nlk_sk(sk);
	/* A dump is in progress... */
	mutex_lock(nlk->cb_mutex);
	if (nlk->cb) {
		mutex_unlock(nlk->cb_mutex);
		netlink_destroy_callback(cb);
		sock_put(sk);
		return -EBUSY;
	}
	nlk->cb = cb;
	mutex_unlock(nlk->cb_mutex);

	netlink_dump(sk);
	sock_put(sk);

	/* We successfully started a dump, by returning -EINTR we
	 * signal not to send ACK even if it was requested.
	 */
	return -EINTR;
}

void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
{
	struct sk_buff *skb;
	struct nlmsghdr *rep;
	struct nlmsgerr *errmsg;
	size_t payload = sizeof(*errmsg);

	/* error messages get the original request appened */
	if (err)
		payload += nlmsg_len(nlh);

	skb = nlmsg_new(payload, GFP_KERNEL);
	if (!skb) {
		struct sock *sk;

		sk = netlink_lookup(in_skb->sk->sk_net,
				    in_skb->sk->sk_protocol,
				    NETLINK_CB(in_skb).pid);
		if (sk) {
			sk->sk_err = ENOBUFS;
			sk->sk_error_report(sk);
			sock_put(sk);
		}
		return;
	}

	rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
			  NLMSG_ERROR, sizeof(struct nlmsgerr), 0);
	errmsg = nlmsg_data(rep);
	errmsg->error = err;
	memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh));
	netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
}

int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
						     struct nlmsghdr *))
{
	struct nlmsghdr *nlh;
	int err;

	while (skb->len >= nlmsg_total_size(0)) {
		int msglen;

		nlh = nlmsg_hdr(skb);
		err = 0;

		if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
			return 0;

		/* Only requests are handled by the kernel */
		if (!(nlh->nlmsg_flags & NLM_F_REQUEST))
			goto ack;

		/* Skip control messages */
		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
			goto ack;

		err = cb(skb, nlh);
		if (err == -EINTR)
			goto skip;

ack:
		if (nlh->nlmsg_flags & NLM_F_ACK || err)
			netlink_ack(skb, nlh, err);

skip:
	        msglen = NLMSG_ALIGN(nlh->nlmsg_len);
		if (msglen > skb->len)
			msglen = skb->len;
		skb_pull(skb, msglen);
	}

	return 0;
}

/**
 * nlmsg_notify - send a notification netlink message
 * @sk: netlink socket to use
 * @skb: notification message
 * @pid: destination netlink pid for reports or 0
 * @group: destination multicast group or 0
 * @report: 1 to report back, 0 to disable
 * @flags: allocation flags
 */
int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid,
		 unsigned int group, int report, gfp_t flags)
{
	int err = 0;

	if (group) {
		int exclude_pid = 0;

		if (report) {
			atomic_inc(&skb->users);
			exclude_pid = pid;
		}

		/* errors reported via destination sk->sk_err */
		nlmsg_multicast(sk, skb, exclude_pid, group, flags);
	}

	if (report)
		err = nlmsg_unicast(sk, skb, pid);

	return err;
}

#ifdef CONFIG_PROC_FS
struct nl_seq_iter {
	struct net *net;
	int link;
	int hash_idx;
};

static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
{
	struct nl_seq_iter *iter = seq->private;
	int i, j;
	struct sock *s;
	struct hlist_node *node;
	loff_t off = 0;

	for (i=0; i<MAX_LINKS; i++) {
		struct nl_pid_hash *hash = &nl_table[i].hash;

		for (j = 0; j <= hash->mask; j++) {
			sk_for_each(s, node, &hash->table[j]) {
				if (iter->net != s->sk_net)
					continue;
				if (off == pos) {
					iter->link = i;
					iter->hash_idx = j;
					return s;
				}
				++off;
			}
		}
	}
	return NULL;
}

static void *netlink_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&nl_table_lock);
	return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}

static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *s;
	struct nl_seq_iter *iter;
	int i, j;

	++*pos;

	if (v == SEQ_START_TOKEN)
		return netlink_seq_socket_idx(seq, 0);

	iter = seq->private;
	s = v;
	do {
		s = sk_next(s);
	} while (s && (iter->net != s->sk_net));
	if (s)
		return s;

	i = iter->link;
	j = iter->hash_idx + 1;

	do {
		struct nl_pid_hash *hash = &nl_table[i].hash;

		for (; j <= hash->mask; j++) {
			s = sk_head(&hash->table[j]);
			while (s && (iter->net != s->sk_net))
				s = sk_next(s);
			if (s) {
				iter->link = i;
				iter->hash_idx = j;
				return s;
			}
		}

		j = 0;
	} while (++i < MAX_LINKS);

	return NULL;
}

static void netlink_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&nl_table_lock);
}


static int netlink_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_puts(seq,
			 "sk       Eth Pid    Groups   "
			 "Rmem     Wmem     Dump     Locks\n");
	else {
		struct sock *s = v;
		struct netlink_sock *nlk = nlk_sk(s);

		seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %d\n",
			   s,
			   s->sk_protocol,
			   nlk->pid,
			   nlk->groups ? (u32)nlk->groups[0] : 0,
			   atomic_read(&s->sk_rmem_alloc),
			   atomic_read(&s->sk_wmem_alloc),
			   nlk->cb,
			   atomic_read(&s->sk_refcnt)
			);

	}
	return 0;
}

static const struct seq_operations netlink_seq_ops = {
	.start  = netlink_seq_start,
	.next   = netlink_seq_next,
	.stop   = netlink_seq_stop,
	.show   = netlink_seq_show,
};


static int netlink_seq_open(struct inode *inode, struct file *file)
{
	struct nl_seq_iter *iter;

	iter = __seq_open_private(file, &netlink_seq_ops, sizeof(*iter));
	if (!iter)
		return -ENOMEM;

	iter->net = get_proc_net(inode);
	if (!iter->net) {
		seq_release_private(inode, file);
		return -ENXIO;
	}

	return 0;
}

static int netlink_seq_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct nl_seq_iter *iter = seq->private;
	put_net(iter->net);
	return seq_release_private(inode, file);
}

static const struct file_operations netlink_seq_fops = {
	.owner		= THIS_MODULE,
	.open		= netlink_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= netlink_seq_release,
};

#endif

int netlink_register_notifier(struct notifier_block *nb)
{
	return atomic_notifier_chain_register(&netlink_chain, nb);
}

int netlink_unregister_notifier(struct notifier_block *nb)
{
	return atomic_notifier_chain_unregister(&netlink_chain, nb);
}

static const struct proto_ops netlink_ops = {
	.family =	PF_NETLINK,
	.owner =	THIS_MODULE,
	.release =	netlink_release,
	.bind =		netlink_bind,
	.connect =	netlink_connect,
	.socketpair =	sock_no_socketpair,
	.accept =	sock_no_accept,
	.getname =	netlink_getname,
	.poll =		datagram_poll,
	.ioctl =	sock_no_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	sock_no_shutdown,
	.setsockopt =	netlink_setsockopt,
	.getsockopt =	netlink_getsockopt,
	.sendmsg =	netlink_sendmsg,
	.recvmsg =	netlink_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

static struct net_proto_family netlink_family_ops = {
	.family = PF_NETLINK,
	.create = netlink_create,
	.owner	= THIS_MODULE,	/* for consistency 8) */
};

static int __net_init netlink_net_init(struct net *net)
{
#ifdef CONFIG_PROC_FS
	if (!proc_net_fops_create(net, "netlink", 0, &netlink_seq_fops))
		return -ENOMEM;
#endif
	return 0;
}

static void __net_exit netlink_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
	proc_net_remove(net, "netlink");
#endif
}

static struct pernet_operations __net_initdata netlink_net_ops = {
	.init = netlink_net_init,
	.exit = netlink_net_exit,
};

static int __init netlink_proto_init(void)
{
	struct sk_buff *dummy_skb;
	int i;
	unsigned long limit;
	unsigned int order;
	int err = proto_register(&netlink_proto, 0);

	if (err != 0)
		goto out;

	BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof(dummy_skb->cb));

	nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL);
	if (!nl_table)
		goto panic;

	if (num_physpages >= (128 * 1024))
		limit = num_physpages >> (21 - PAGE_SHIFT);
	else
		limit = num_physpages >> (23 - PAGE_SHIFT);

	order = get_bitmask_order(limit) - 1 + PAGE_SHIFT;
	limit = (1UL << order) / sizeof(struct hlist_head);
	order = get_bitmask_order(min(limit, (unsigned long)UINT_MAX)) - 1;

	for (i = 0; i < MAX_LINKS; i++) {
		struct nl_pid_hash *hash = &nl_table[i].hash;

		hash->table = nl_pid_hash_alloc(1 * sizeof(*hash->table));
		if (!hash->table) {
			while (i-- > 0)
				nl_pid_hash_free(nl_table[i].hash.table,
						 1 * sizeof(*hash->table));
			kfree(nl_table);
			goto panic;
		}
		memset(hash->table, 0, 1 * sizeof(*hash->table));
		hash->max_shift = order;
		hash->shift = 0;
		hash->mask = 0;
		hash->rehash_time = jiffies;
	}

	sock_register(&netlink_family_ops);
	register_pernet_subsys(&netlink_net_ops);
	/* The netlink device handler may be needed early. */
	rtnetlink_init();
out:
	return err;
panic:
	panic("netlink_init: Cannot allocate nl_table\n");
}

core_initcall(netlink_proto_init);

EXPORT_SYMBOL(netlink_ack);
EXPORT_SYMBOL(netlink_rcv_skb);
EXPORT_SYMBOL(netlink_broadcast);
EXPORT_SYMBOL(netlink_dump_start);
EXPORT_SYMBOL(netlink_kernel_create);
EXPORT_SYMBOL(netlink_register_notifier);
EXPORT_SYMBOL(netlink_set_nonroot);
EXPORT_SYMBOL(netlink_unicast);
EXPORT_SYMBOL(netlink_unregister_notifier);
EXPORT_SYMBOL(nlmsg_notify);