af_netlink.c

Linux Kernel 2.6.9 for OMAP1710

/*
 * 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)
 *
 */

#include <linux/config.h>
#include <linux/module.h>

#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/major.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/smp_lock.h>
#include <linux/notifier.h>
#include <linux/security.h>
#include <net/sock.h>
#include <net/scm.h>

#define Nprintk(a...)

#if defined(CONFIG_NETLINK_DEV) || defined(CONFIG_NETLINK_DEV_MODULE)
#define NL_EMULATE_DEV
#endif

struct netlink_opt
{
	u32			pid;
	unsigned		groups;
	u32			dst_pid;
	unsigned		dst_groups;
	unsigned long		state;
	int			(*handler)(int unit, struct sk_buff *skb);
	wait_queue_head_t	wait;
	struct netlink_callback	*cb;
	spinlock_t		cb_lock;
	void			(*data_ready)(struct sock *sk, int bytes);
};

#define nlk_sk(__sk) ((struct netlink_opt *)(__sk)->sk_protinfo)

static struct hlist_head nl_table[MAX_LINKS];
static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
static unsigned nl_nonroot[MAX_LINKS];

#ifdef NL_EMULATE_DEV
static struct socket *netlink_kernel[MAX_LINKS];
#endif

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

atomic_t netlink_sock_nr;

static rwlock_t nl_table_lock = RW_LOCK_UNLOCKED;
static atomic_t nl_table_users = ATOMIC_INIT(0);

static struct notifier_block *netlink_chain;

static void netlink_sock_destruct(struct sock *sk)
{
	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)->cb);

	kfree(nlk_sk(sk));

	atomic_dec(&netlink_sock_nr);
#ifdef NETLINK_REFCNT_DEBUG
	printk(KERN_DEBUG "NETLINK %p released, %d are still alive\n", sk, atomic_read(&netlink_sock_nr));
#endif
}

/* 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_bh(&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_bh(&nl_table_lock);
			schedule();
			write_lock_bh(&nl_table_lock);
		}

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

static __inline__ void netlink_table_ungrab(void)
{
	write_unlock_bh(&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(int protocol, u32 pid)
{
	struct sock *sk;
	struct hlist_node *node;

	read_lock(&nl_table_lock);
	sk_for_each(sk, node, &nl_table[protocol]) {
		if (nlk_sk(sk)->pid == pid) {
			sock_hold(sk);
			goto found;
		}
	}
	sk = NULL;
found:
	read_unlock(&nl_table_lock);
	return sk;
}

static struct proto_ops netlink_ops;

static int netlink_insert(struct sock *sk, u32 pid)
{
	int err = -EADDRINUSE;
	struct sock *osk;
	struct hlist_node *node;

	netlink_table_grab();
	sk_for_each(osk, node, &nl_table[sk->sk_protocol]) {
		if (nlk_sk(osk)->pid == pid)
			break;
	}
	if (!node) {
		err = -EBUSY;
		if (nlk_sk(sk)->pid == 0) {
			nlk_sk(sk)->pid = pid;
			sk_add_node(sk, &nl_table[sk->sk_protocol]);
			err = 0;
		}
	}
	netlink_table_ungrab();
	return err;
}

static void netlink_remove(struct sock *sk)
{
	netlink_table_grab();
	sk_del_node_init(sk);
	netlink_table_ungrab();
}

static int netlink_create(struct socket *sock, int protocol)
{
	struct sock *sk;
	struct netlink_opt *nlk;

	sock->state = SS_UNCONNECTED;

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

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

	sock->ops = &netlink_ops;

	sk = sk_alloc(PF_NETLINK, GFP_KERNEL, 1, NULL);
	if (!sk)
		return -ENOMEM;

	sock_init_data(sock,sk);
	sk_set_owner(sk, THIS_MODULE);

	nlk = sk->sk_protinfo = kmalloc(sizeof(*nlk), GFP_KERNEL);
	if (!nlk) {
		sk_free(sk);
		return -ENOMEM;
	}
	memset(nlk, 0, sizeof(*nlk));

	spin_lock_init(&nlk->cb_lock);
	init_waitqueue_head(&nlk->wait);
	sk->sk_destruct = netlink_sock_destruct;
	atomic_inc(&netlink_sock_nr);

	sk->sk_protocol = protocol;
	return 0;
}

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

	if (!sk)
		return 0;

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

	spin_lock(&nlk->cb_lock);
	if (nlk->cb) {
		nlk->cb->done(nlk->cb);
		netlink_destroy_callback(nlk->cb);
		nlk->cb = NULL;
		__sock_put(sk);
	}
	spin_unlock(&nlk->cb_lock);

	/* OK. Socket is unlinked, and, therefore,
	   no new packets will arrive */

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

	skb_queue_purge(&sk->sk_write_queue);

	if (nlk->pid && !nlk->groups) {
		struct netlink_notify n = {
						.protocol = sk->sk_protocol,
						.pid = nlk->pid,
					  };
		notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n);
	}	
	
	sock_put(sk);
	return 0;
}

static int netlink_autobind(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct sock *osk;
	struct hlist_node *node;
	s32 pid = current->pid;
	int err;

retry:
	netlink_table_grab();
	sk_for_each(osk, node, &nl_table[sk->sk_protocol]) {
		if (nlk_sk(osk)->pid == pid) {
			/* Bind collision, search negative pid values. */
			if (pid > 0)
				pid = -4096;
			pid--;
			netlink_table_ungrab();
			goto retry;
		}
	}
	netlink_table_ungrab();

	err = netlink_insert(sk, pid);
	if (err == -EADDRINUSE)
		goto retry;
	nlk_sk(sk)->groups = 0;
	return 0;
}

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

static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	struct sock *sk = sock->sk;
	struct netlink_opt *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 && !netlink_capable(sock, NL_NONROOT_RECV))
		return -EPERM;

	if (nlk->pid) {
		if (nladdr->nl_pid != nlk->pid)
			return -EINVAL;
		nlk->groups = nladdr->nl_groups;
		return 0;
	}

	if (nladdr->nl_pid == 0) {
		err = netlink_autobind(sock);
		if (err == 0)
			nlk->groups = nladdr->nl_groups;
		return err;
	}

	err = netlink_insert(sk, nladdr->nl_pid);
	if (err == 0)
		nlk->groups = nladdr->nl_groups;
	return err;
}

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

	if (addr->sa_family == AF_UNSPEC) {
		sk->sk_state	= NETLINK_UNCONNECTED;
		nlk->dst_pid	= 0;
		nlk->dst_groups = 0;
		return 0;
	}
	if (addr->sa_family != AF_NETLINK)
		return -EINVAL;

	/* Only superuser is allowed to send multicasts */
	if (nladdr->nl_groups && !netlink_capable(sock, NL_NONROOT_SEND))
		return -EPERM;

	if (!nlk->pid)
		err = netlink_autobind(sock);

	if (err == 0) {
		sk->sk_state	= NETLINK_CONNECTED;
		nlk->dst_pid 	= nladdr->nl_pid;
		nlk->dst_groups = nladdr->nl_groups;
	}

	return err;
}

static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr_len, int peer)
{
	struct sock *sk = sock->sk;
	struct netlink_opt *nlk = nlk_sk(sk);
	struct sockaddr_nl *nladdr=(struct sockaddr_nl *)addr;
	
	nladdr->nl_family = AF_NETLINK;
	nladdr->nl_pad = 0;
	*addr_len = sizeof(*nladdr);

	if (peer) {
		nladdr->nl_pid = nlk->dst_pid;
		nladdr->nl_groups = nlk->dst_groups;
	} else {
		nladdr->nl_pid = nlk->pid;
		nladdr->nl_groups = nlk->groups;
	}
	return 0;
}

static void netlink_overrun(struct sock *sk)
{
	if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
		sk->sk_err = ENOBUFS;
		sk->sk_error_report(sk);
	}
}

struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
{
	int protocol = ssk->sk_protocol;
	struct sock *sock;
	struct netlink_opt *nlk;

	sock = netlink_lookup(protocol, pid);
	if (!sock)
		return ERR_PTR(-ECONNREFUSED);

	/* Don't bother queuing skb if kernel socket has no input function */
	nlk = nlk_sk(sock);
	if ((nlk->pid == 0 && !nlk->data_ready) ||
	    (sock->sk_state == NETLINK_CONNECTED &&
	     nlk->dst_pid != nlk_sk(ssk)->pid)) {
		sock_put(sock);
		return ERR_PTR(-ECONNREFUSED);
	}
	return sock;
}

struct sock *netlink_getsockbyfilp(struct file *filp)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct socket *socket;
	struct sock *sock;

	if (!inode->i_sock || !(socket = SOCKET_I(inode)))
		return ERR_PTR(-ENOTSOCK);

	sock = socket->sk;
	if (sock->sk_family != AF_NETLINK)
		return ERR_PTR(-EINVAL);

	sock_hold(sock);
	return sock;
}

/*
 * Attach a skb to a netlink socket.
 * The caller must hold a reference to the destination socket. On error, the
 * reference is dropped. The skb is not send to the destination, just all
 * all error checks are performed and memory in the queue is reserved.
 * Return values:
 * < 0: error. skb freed, reference to sock dropped.
 * 0: continue
 * 1: repeat lookup - reference dropped while waiting for socket memory.
 */
int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, long timeo)
{
	struct netlink_opt *nlk;

	nlk = nlk_sk(sk);

#ifdef NL_EMULATE_DEV
	if (nlk->handler)
		return 0;
#endif
	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
	    test_bit(0, &nlk->state)) {
		DECLARE_WAITQUEUE(wait, current);
		if (!timeo) {
			if (!nlk->pid)
				netlink_overrun(sk);
			sock_put(sk);
			kfree_skb(skb);
			return -EAGAIN;
		}

		__set_current_state(TASK_INTERRUPTIBLE);
		add_wait_queue(&nlk->wait, &wait);

		if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
		     test_bit(0, &nlk->state)) &&
		    !sock_flag(sk, SOCK_DEAD))
			timeo = schedule_timeout(timeo);

		__set_current_state(TASK_RUNNING);
		remove_wait_queue(&nlk->wait, &wait);
		sock_put(sk);

		if (signal_pending(current)) {
			kfree_skb(skb);
			return sock_intr_errno(timeo);
		}
		return 1;
	}
	skb_orphan(skb);
	skb_set_owner_r(skb, sk);
	return 0;
}

int netlink_sendskb(struct sock *sk, struct sk_buff *skb, int protocol)
{
	struct netlink_opt *nlk;
	int len = skb->len;

	nlk = nlk_sk(sk);
#ifdef NL_EMULATE_DEV
	if (nlk->handler) {
		skb_orphan(skb);
		len = nlk->handler(protocol, skb);
		sock_put(sk);
		return len;
	}
#endif

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

void netlink_detachskb(struct sock *sk, struct sk_buff *skb)
{
	kfree_skb(skb);
	sock_put(sk);
}

static inline void netlink_trim(struct sk_buff *skb, int allocation)
{
	int delta = skb->end - skb->tail;

	/* If the packet is charged to a socket, the modification
	 * of truesize below is illegal and will corrupt socket
	 * buffer accounting state.
	 */
	BUG_ON(skb->list != NULL);

	if (delta * 2 < skb->truesize)
		return;
	if (pskb_expand_head(skb, 0, -delta, allocation))
		return;
	skb->truesize -= delta;
}

int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 pid, int nonblock)
{
	struct sock *sk;
	int err;
	long timeo;

	netlink_trim(skb, gfp_any());

	timeo = sock_sndtimeo(ssk, nonblock);
retry:
	sk = netlink_getsockbypid(ssk, pid);
	if (IS_ERR(sk)) {
		kfree_skb(skb);
		return PTR_ERR(sk);
	}
	err = netlink_attachskb(sk, skb, nonblock, timeo);
	if (err == 1)
		goto retry;
	if (err)
		return err;

	return netlink_sendskb(sk, skb, ssk->sk_protocol);
}

static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
	struct netlink_opt *nlk = nlk_sk(sk);
#ifdef NL_EMULATE_DEV
	if (nlk->handler) {
		skb_orphan(skb);
		nlk->handler(sk->sk_protocol, skb);
		return 0;
	} else
#endif
	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
	    !test_bit(0, &nlk->state)) {
                skb_orphan(skb);
		skb_set_owner_r(skb, sk);
		skb_queue_tail(&sk->sk_receive_queue, skb);
		sk->sk_data_ready(sk, skb->len);
		return 0;
	}
	return -1;
}

int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
		      u32 group, int allocation)
{
	struct sock *sk;
	struct hlist_node *node;
	struct sk_buff *skb2 = NULL;
	int protocol = ssk->sk_protocol;
	int failure = 0, delivered = 0;

	netlink_trim(skb, allocation);

	/* While we sleep in clone, do not allow to change socket list */

	netlink_lock_table();

	sk_for_each(sk, node, &nl_table[protocol]) {
		struct netlink_opt *nlk = nlk_sk(sk);

		if (ssk == sk)
			continue;

		if (nlk->pid == pid || !(nlk->groups & group))
			continue;

		if (failure) {
			netlink_overrun(sk);
			continue;
		}