af_netlink.c

linux 内核源代码

/*
 * NETLINK      Kernel-user communication protocol.
 *
 * 		Authors:	Alan Cox <[e-mail]>
 * 				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.
 *
 * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith
 *                               added netlink_proto_exit
 * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <[e-mail]>
 * 				 use nlk_sk, as sk->protinfo is on a diet 8)
 * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <[e-mail]>
 * 				 - inc module use count of module that owns
 * 				   the kernel socket in case userspace opens
 * 				   socket of same protocol
 * 				 - remove all module support, since netlink is
 * 				   mandatory if CONFIG_NET=y these days
 */

#include <linux/module.h>

#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/security.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <linux/audit.h>
#include <linux/selinux.h>
#include <linux/mutex.h>

#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/scm.h>
#include <net/netlink.h>

#define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))

struct netlink_sock {
	/* struct sock has to be the first member of netlink_sock */
	struct sock		sk;
	u32			pid;
	u32			dst_pid;
	u32			dst_group;
	u32			flags;
	u32			subscriptions;
	u32			ngroups;
	unsigned long		*groups;
	unsigned long		state;
	wait_queue_head_t	wait;
	struct netlink_callback	*cb;
	struct mutex		*cb_mutex;
	struct mutex		cb_def_mutex;
	void			(*netlink_rcv)(struct sk_buff *skb);
	struct module		*module;
};

#define NETLINK_KERNEL_SOCKET	0x1
#define NETLINK_RECV_PKTINFO	0x2

static inline struct netlink_sock *nlk_sk(struct sock *sk)
{
	return container_of(sk, struct netlink_sock, sk);
}

static inline int netlink_is_kernel(struct sock *sk)
{
	return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
}

struct nl_pid_hash {
	struct hlist_head *table;
	unsigned long rehash_time;

	unsigned int mask;
	unsigned int shift;

	unsigned int entries;
	unsigned int max_shift;

	u32 rnd;
};

struct netlink_table {
	struct nl_pid_hash hash;
	struct hlist_head mc_list;
	unsigned long *listeners;
	unsigned int nl_nonroot;
	unsigned int groups;
	struct mutex *cb_mutex;
	struct module *module;
	int registered;
};

static struct netlink_table *nl_table;

static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);

static int netlink_dump(struct sock *sk);
static void netlink_destroy_callback(struct netlink_callback *cb);

static DEFINE_RWLOCK(nl_table_lock);
static atomic_t nl_table_users = ATOMIC_INIT(0);

static ATOMIC_NOTIFIER_HEAD(netlink_chain);

static u32 netlink_group_mask(u32 group)
{
	return group ? 1 << (group - 1) : 0;
}

static struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
{
	return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask];
}

static void netlink_sock_destruct(struct sock *sk)
{
	struct netlink_sock *nlk = nlk_sk(sk);

	if (nlk->cb) {
		if (nlk->cb->done)
			nlk->cb->done(nlk->cb);
		netlink_destroy_callback(nlk->cb);
	}

	skb_queue_purge(&sk->sk_receive_queue);

	if (!sock_flag(sk, SOCK_DEAD)) {
		printk("Freeing alive netlink socket %p\n", sk);
		return;
	}
	BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
	BUG_TRAP(!nlk_sk(sk)->groups);
}

/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on SMP.
 * Look, when several writers sleep and reader wakes them up, all but one
 * immediately hit write lock and grab all the cpus. Exclusive sleep solves
 * this, _but_ remember, it adds useless work on UP machines.
 */

static void netlink_table_grab(void)
{
	write_lock_irq(&nl_table_lock);

	if (atomic_read(&nl_table_users)) {
		DECLARE_WAITQUEUE(wait, current);

		add_wait_queue_exclusive(&nl_table_wait, &wait);
		for(;;) {
			set_current_state(TASK_UNINTERRUPTIBLE);
			if (atomic_read(&nl_table_users) == 0)
				break;
			write_unlock_irq(&nl_table_lock);
			schedule();
			write_lock_irq(&nl_table_lock);
		}

		__set_current_state(TASK_RUNNING);
		remove_wait_queue(&nl_table_wait, &wait);
	}
}

static __inline__ void netlink_table_ungrab(void)
{
	write_unlock_irq(&nl_table_lock);
	wake_up(&nl_table_wait);
}

static __inline__ void
netlink_lock_table(void)
{
	/* read_lock() synchronizes us to netlink_table_grab */

	read_lock(&nl_table_lock);
	atomic_inc(&nl_table_users);
	read_unlock(&nl_table_lock);
}

static __inline__ void
netlink_unlock_table(void)
{
	if (atomic_dec_and_test(&nl_table_users))
		wake_up(&nl_table_wait);
}

static __inline__ struct sock *netlink_lookup(struct net *net, int protocol, u32 pid)
{
	struct nl_pid_hash *hash = &nl_table[protocol].hash;
	struct hlist_head *head;
	struct sock *sk;
	struct hlist_node *node;

	read_lock(&nl_table_lock);
	head = nl_pid_hashfn(hash, pid);
	sk_for_each(sk, node, head) {
		if ((sk->sk_net == net) && (nlk_sk(sk)->pid == pid)) {
			sock_hold(sk);
			goto found;
		}
	}
	sk = NULL;
found:
	read_unlock(&nl_table_lock);
	return sk;
}

static inline struct hlist_head *nl_pid_hash_alloc(size_t size)
{
	if (size <= PAGE_SIZE)
		return kmalloc(size, GFP_ATOMIC);
	else
		return (struct hlist_head *)
			__get_free_pages(GFP_ATOMIC, get_order(size));
}

static inline void nl_pid_hash_free(struct hlist_head *table, size_t size)
{
	if (size <= PAGE_SIZE)
		kfree(table);
	else
		free_pages((unsigned long)table, get_order(size));
}

static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow)
{
	unsigned int omask, mask, shift;
	size_t osize, size;
	struct hlist_head *otable, *table;
	int i;

	omask = mask = hash->mask;
	osize = size = (mask + 1) * sizeof(*table);
	shift = hash->shift;

	if (grow) {
		if (++shift > hash->max_shift)
			return 0;
		mask = mask * 2 + 1;
		size *= 2;
	}

	table = nl_pid_hash_alloc(size);
	if (!table)
		return 0;

	memset(table, 0, size);
	otable = hash->table;
	hash->table = table;
	hash->mask = mask;
	hash->shift = shift;
	get_random_bytes(&hash->rnd, sizeof(hash->rnd));

	for (i = 0; i <= omask; i++) {
		struct sock *sk;
		struct hlist_node *node, *tmp;

		sk_for_each_safe(sk, node, tmp, &otable[i])
			__sk_add_node(sk, nl_pid_hashfn(hash, nlk_sk(sk)->pid));
	}

	nl_pid_hash_free(otable, osize);
	hash->rehash_time = jiffies + 10 * 60 * HZ;
	return 1;
}

static inline int nl_pid_hash_dilute(struct nl_pid_hash *hash, int len)
{
	int avg = hash->entries >> hash->shift;

	if (unlikely(avg > 1) && nl_pid_hash_rehash(hash, 1))
		return 1;

	if (unlikely(len > avg) && time_after(jiffies, hash->rehash_time)) {
		nl_pid_hash_rehash(hash, 0);
		return 1;
	}

	return 0;
}

static const struct proto_ops netlink_ops;

static void
netlink_update_listeners(struct sock *sk)
{
	struct netlink_table *tbl = &nl_table[sk->sk_protocol];
	struct hlist_node *node;
	unsigned long mask;
	unsigned int i;

	for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
		mask = 0;
		sk_for_each_bound(sk, node, &tbl->mc_list) {
			if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
				mask |= nlk_sk(sk)->groups[i];
		}
		tbl->listeners[i] = mask;
	}
	/* this function is only called with the netlink table "grabbed", which
	 * makes sure updates are visible before bind or setsockopt return. */
}

static int netlink_insert(struct sock *sk, struct net *net, u32 pid)
{
	struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
	struct hlist_head *head;
	int err = -EADDRINUSE;
	struct sock *osk;
	struct hlist_node *node;
	int len;

	netlink_table_grab();
	head = nl_pid_hashfn(hash, pid);
	len = 0;
	sk_for_each(osk, node, head) {
		if ((osk->sk_net == net) && (nlk_sk(osk)->pid == pid))
			break;
		len++;
	}
	if (node)
		goto err;

	err = -EBUSY;
	if (nlk_sk(sk)->pid)
		goto err;

	err = -ENOMEM;
	if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX))
		goto err;

	if (len && nl_pid_hash_dilute(hash, len))
		head = nl_pid_hashfn(hash, pid);
	hash->entries++;
	nlk_sk(sk)->pid = pid;
	sk_add_node(sk, head);
	err = 0;

err:
	netlink_table_ungrab();
	return err;
}

static void netlink_remove(struct sock *sk)
{
	netlink_table_grab();
	if (sk_del_node_init(sk))
		nl_table[sk->sk_protocol].hash.entries--;
	if (nlk_sk(sk)->subscriptions)
		__sk_del_bind_node(sk);
	netlink_table_ungrab();
}

static struct proto netlink_proto = {
	.name	  = "NETLINK",
	.owner	  = THIS_MODULE,
	.obj_size = sizeof(struct netlink_sock),
};

static int __netlink_create(struct net *net, struct socket *sock,
			    struct mutex *cb_mutex, int protocol)
{
	struct sock *sk;
	struct netlink_sock *nlk;

	sock->ops = &netlink_ops;

	sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto);
	if (!sk)
		return -ENOMEM;

	sock_init_data(sock, sk);

	nlk = nlk_sk(sk);
	if (cb_mutex)
		nlk->cb_mutex = cb_mutex;
	else {
		nlk->cb_mutex = &nlk->cb_def_mutex;
		mutex_init(nlk->cb_mutex);
	}
	init_waitqueue_head(&nlk->wait);

	sk->sk_destruct = netlink_sock_destruct;
	sk->sk_protocol = protocol;
	return 0;
}

static int netlink_create(struct net *net, struct socket *sock, int protocol)
{
	struct module *module = NULL;
	struct mutex *cb_mutex;
	struct netlink_sock *nlk;
	int err = 0;

	sock->state = SS_UNCONNECTED;

	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
		return -ESOCKTNOSUPPORT;

	if (protocol<0 || protocol >= MAX_LINKS)
		return -EPROTONOSUPPORT;

	netlink_lock_table();
#ifdef CONFIG_KMOD
	if (!nl_table[protocol].registered) {
		netlink_unlock_table();
		request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol);
		netlink_lock_table();
	}
#endif
	if (nl_table[protocol].registered &&
	    try_module_get(nl_table[protocol].module))
		module = nl_table[protocol].module;
	cb_mutex = nl_table[protocol].cb_mutex;
	netlink_unlock_table();

	if ((err = __netlink_create(net, sock, cb_mutex, protocol)) < 0)
		goto out_module;

	nlk = nlk_sk(sock->sk);
	nlk->module = module;
out:
	return err;

out_module:
	module_put(module);
	goto out;
}

static int netlink_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct netlink_sock *nlk;

	if (!sk)
		return 0;

	netlink_remove(sk);
	sock_orphan(sk);
	nlk = nlk_sk(sk);

	/*
	 * OK. Socket is unlinked, any packets that arrive now
	 * will be purged.
	 */

	sock->sk = NULL;
	wake_up_interruptible_all(&nlk->wait);

	skb_queue_purge(&sk->sk_write_queue);

	if (nlk->pid && !nlk->subscriptions) {
		struct netlink_notify n = {
						.net = sk->sk_net,
						.protocol = sk->sk_protocol,
						.pid = nlk->pid,
					  };
		atomic_notifier_call_chain(&netlink_chain,
				NETLINK_URELEASE, &n);
	}

	module_put(nlk->module);

	netlink_table_grab();
	if (netlink_is_kernel(sk)) {
		kfree(nl_table[sk->sk_protocol].listeners);
		nl_table[sk->sk_protocol].module = NULL;
		nl_table[sk->sk_protocol].registered = 0;
	} else if (nlk->subscriptions)
		netlink_update_listeners(sk);
	netlink_table_ungrab();

	kfree(nlk->groups);
	nlk->groups = NULL;

	sock_put(sk);
	return 0;
}

static int netlink_autobind(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct net *net = sk->sk_net;
	struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
	struct hlist_head *head;
	struct sock *osk;
	struct hlist_node *node;
	s32 pid = current->tgid;
	int err;
	static s32 rover = -4097;

retry:
	cond_resched();
	netlink_table_grab();
	head = nl_pid_hashfn(hash, pid);
	sk_for_each(osk, node, head) {
		if ((osk->sk_net != net))
			continue;
		if (nlk_sk(osk)->pid == pid) {
			/* Bind collision, search negative pid values. */
			pid = rover--;
			if (rover > -4097)
				rover = -4097;
			netlink_table_ungrab();
			goto retry;
		}
	}
	netlink_table_ungrab();

	err = netlink_insert(sk, net, pid);
	if (err == -EADDRINUSE)
		goto retry;

	/* If 2 threads race to autobind, that is fine.  */
	if (err == -EBUSY)
		err = 0;

	return err;
}

static inline int netlink_capable(struct socket *sock, unsigned int flag)
{
	return (nl_table[sock->sk->sk_protocol].nl_nonroot & flag) ||
	       capable(CAP_NET_ADMIN);
}

static void
netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions)
{
	struct netlink_sock *nlk = nlk_sk(sk);

	if (nlk->subscriptions && !subscriptions)
		__sk_del_bind_node(sk);
	else if (!nlk->subscriptions && subscriptions)
		sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list);
	nlk->subscriptions = subscriptions;
}

static int netlink_realloc_groups(struct sock *sk)
{
	struct netlink_sock *nlk = nlk_sk(sk);
	unsigned int groups;
	unsigned long *new_groups;
	int err = 0;

	netlink_table_grab();

	groups = nl_table[sk->sk_protocol].groups;
	if (!nl_table[sk->sk_protocol].registered) {
		err = -ENOENT;
		goto out_unlock;
	}

	if (nlk->ngroups >= groups)
		goto out_unlock;

	new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC);
	if (new_groups == NULL) {
		err = -ENOMEM;
		goto out_unlock;
	}
	memset((char*)new_groups + NLGRPSZ(nlk->ngroups), 0,
	       NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));

	nlk->groups = new_groups;
	nlk->ngroups = groups;
 out_unlock:
	netlink_table_ungrab();
	return err;
}

static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	struct sock *sk = sock->sk;
	struct net *net = sk->sk_net;
	struct netlink_sock *nlk = nlk_sk(sk);
	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
	int err;

	if (nladdr->nl_family != AF_NETLINK)
		return -EINVAL;

	/* Only superuser is allowed to listen multicasts */
	if (nladdr->nl_groups) {
		if (!netlink_capable(sock, NL_NONROOT_RECV))
			return -EPERM;
		err = netlink_realloc_groups(sk);
		if (err)
			return err;
	}

	if (nlk->pid) {
		if (nladdr->nl_pid != nlk->pid)
			return -EINVAL;
	} else {
		err = nladdr->nl_pid ?
			netlink_insert(sk, net, nladdr->nl_pid) :
			netlink_autobind(sock);
		if (err)
			return err;
	}

	if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
		return 0;

	netlink_table_grab();
	netlink_update_subscriptions(sk, nlk->subscriptions +
					 hweight32(nladdr->nl_groups) -
					 hweight32(nlk->groups[0]));
	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
	netlink_update_listeners(sk);
	netlink_table_ungrab();

	return 0;
}

static int netlink_connect(struct socket *sock, struct sockaddr *addr,
			   int alen, int flags)
{
	int err = 0;
	struct sock *sk = sock->sk;
	struct netlink_sock *nlk = nlk_sk(sk);
	struct sockaddr_nl *nladdr=(struct sockaddr_nl*)addr;