af_unix.c

Linux Kernel 2.6.9 for OMAP1710

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

	wake_up_interruptible(&u->peer_wait);

	if (msg->msg_name)
		unix_copy_addr(msg, skb->sk);

	if (size > skb->len)
		size = skb->len;
	else if (size < skb->len)
		msg->msg_flags |= MSG_TRUNC;

	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size);
	if (err)
		goto out_free;

	if (!siocb->scm) {
		siocb->scm = &tmp_scm;
		memset(&tmp_scm, 0, sizeof(tmp_scm));
	}
	siocb->scm->creds = *UNIXCREDS(skb);

	if (!(flags & MSG_PEEK))
	{
		if (UNIXCB(skb).fp)
			unix_detach_fds(siocb->scm, skb);
	}
	else 
	{
		/* It is questionable: on PEEK we could:
		   - do not return fds - good, but too simple 8)
		   - return fds, and do not return them on read (old strategy,
		     apparently wrong)
		   - clone fds (I chose it for now, it is the most universal
		     solution)
		
	           POSIX 1003.1g does not actually define this clearly
	           at all. POSIX 1003.1g doesn't define a lot of things
	           clearly however!		     
		   
		*/
		if (UNIXCB(skb).fp)
			siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
	}
	err = size;

	scm_recv(sock, msg, siocb->scm, flags);

out_free:
	skb_free_datagram(sk,skb);
out:
	return err;
}

/*
 *	Sleep until data has arrive. But check for races..
 */
 
static long unix_stream_data_wait(struct sock * sk, long timeo)
{
	DEFINE_WAIT(wait);

	unix_state_rlock(sk);

	for (;;) {
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

		if (skb_queue_len(&sk->sk_receive_queue) ||
		    sk->sk_err ||
		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
		    signal_pending(current) ||
		    !timeo)
			break;

		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
		unix_state_runlock(sk);
		timeo = schedule_timeout(timeo);
		unix_state_rlock(sk);
		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	}

	finish_wait(sk->sk_sleep, &wait);
	unix_state_runlock(sk);
	return timeo;
}



static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size,
			       int flags)
{
	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
	struct scm_cookie tmp_scm;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr=msg->msg_name;
	int copied = 0;
	int check_creds = 0;
	int target;
	int err = 0;
	long timeo;

	err = -EINVAL;
	if (sk->sk_state != TCP_ESTABLISHED)
		goto out;

	err = -EOPNOTSUPP;
	if (flags&MSG_OOB)
		goto out;

	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);

	msg->msg_namelen = 0;

	/* Lock the socket to prevent queue disordering
	 * while sleeps in memcpy_tomsg
	 */

	if (!siocb->scm) {
		siocb->scm = &tmp_scm;
		memset(&tmp_scm, 0, sizeof(tmp_scm));
	}

	down(&u->readsem);

	do
	{
		int chunk;
		struct sk_buff *skb;

		skb = skb_dequeue(&sk->sk_receive_queue);
		if (skb==NULL)
		{
			if (copied >= target)
				break;

			/*
			 *	POSIX 1003.1g mandates this order.
			 */
			 
			if ((err = sock_error(sk)) != 0)
				break;
			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;
			err = -EAGAIN;
			if (!timeo)
				break;
			up(&u->readsem);

			timeo = unix_stream_data_wait(sk, timeo);

			if (signal_pending(current)) {
				err = sock_intr_errno(timeo);
				goto out;
			}
			down(&u->readsem);
			continue;
		}

		if (check_creds) {
			/* Never glue messages from different writers */
			if (memcmp(UNIXCREDS(skb), &siocb->scm->creds, sizeof(siocb->scm->creds)) != 0) {
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}
		} else {
			/* Copy credentials */
			siocb->scm->creds = *UNIXCREDS(skb);
			check_creds = 1;
		}

		/* Copy address just once */
		if (sunaddr)
		{
			unix_copy_addr(msg, skb->sk);
			sunaddr = NULL;
		}

		chunk = min_t(unsigned int, skb->len, size);
		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
			skb_queue_head(&sk->sk_receive_queue, skb);
			if (copied == 0)
				copied = -EFAULT;
			break;
		}
		copied += chunk;
		size -= chunk;

		/* Mark read part of skb as used */
		if (!(flags & MSG_PEEK))
		{
			skb_pull(skb, chunk);

			if (UNIXCB(skb).fp)
				unix_detach_fds(siocb->scm, skb);

			/* put the skb back if we didn't use it up.. */
			if (skb->len)
			{
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}

			kfree_skb(skb);

			if (siocb->scm->fp)
				break;
		}
		else
		{
			/* It is questionable, see note in unix_dgram_recvmsg.
			 */
			if (UNIXCB(skb).fp)
				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);

			/* put message back and return */
			skb_queue_head(&sk->sk_receive_queue, skb);
			break;
		}
	} while (size);

	up(&u->readsem);
	scm_recv(sock, msg, siocb->scm, flags);
out:
	return copied ? : err;
}

static int unix_shutdown(struct socket *sock, int mode)
{
	struct sock *sk = sock->sk;
	struct sock *other;

	mode = (mode+1)&(RCV_SHUTDOWN|SEND_SHUTDOWN);

	if (mode) {
		unix_state_wlock(sk);
		sk->sk_shutdown |= mode;
		other=unix_peer(sk);
		if (other)
			sock_hold(other);
		unix_state_wunlock(sk);
		sk->sk_state_change(sk);

		if (other &&
			(sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {

			int peer_mode = 0;

			if (mode&RCV_SHUTDOWN)
				peer_mode |= SEND_SHUTDOWN;
			if (mode&SEND_SHUTDOWN)
				peer_mode |= RCV_SHUTDOWN;
			unix_state_wlock(other);
			other->sk_shutdown |= peer_mode;
			unix_state_wunlock(other);
			other->sk_state_change(other);
			read_lock(&other->sk_callback_lock);
			if (peer_mode == SHUTDOWN_MASK)
				sk_wake_async(other,1,POLL_HUP);
			else if (peer_mode & RCV_SHUTDOWN)
				sk_wake_async(other,1,POLL_IN);
			read_unlock(&other->sk_callback_lock);
		}
		if (other)
			sock_put(other);
	}
	return 0;
}

static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	long amount=0;
	int err;

	switch(cmd)
	{
		case SIOCOUTQ:
			amount = atomic_read(&sk->sk_wmem_alloc);
			err = put_user(amount, (int __user *)arg);
			break;
		case SIOCINQ:
		{
			struct sk_buff *skb;
			if (sk->sk_state == TCP_LISTEN) {
				err = -EINVAL;
				break;
			}

			spin_lock(&sk->sk_receive_queue.lock);
			skb = skb_peek(&sk->sk_receive_queue);
			if (skb)
				amount=skb->len;
			spin_unlock(&sk->sk_receive_queue.lock);
			err = put_user(amount, (int __user *)arg);
			break;
		}

		default:
			err = dev_ioctl(cmd, (void __user *)arg);
			break;
	}
	return err;
}

static unsigned int unix_poll(struct file * file, struct socket *sock, poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask;

	poll_wait(file, sk->sk_sleep, wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err)
		mask |= POLLERR;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sk->sk_shutdown & RCV_SHUTDOWN))
		mask |= POLLIN | POLLRDNORM;

	/* Connection-based need to check for termination and startup */
	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && sk->sk_state == TCP_CLOSE)
		mask |= POLLHUP;

	/*
	 * we set writable also when the other side has shut down the
	 * connection. This prevents stuck sockets.
	 */
	if (unix_writable(sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;

	return mask;
}


#ifdef CONFIG_PROC_FS
static struct sock *unix_seq_idx(int *iter, loff_t pos)
{
	loff_t off = 0;
	struct sock *s;

	for (s = first_unix_socket(iter); s; s = next_unix_socket(iter, s)) {
		if (off == pos) 
			return s;
		++off;
	}
	return NULL;
}


static void *unix_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&unix_table_lock);
	return *pos ? unix_seq_idx(seq->private, *pos - 1) : ((void *) 1);
}

static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;

	if (v == (void *)1) 
		return first_unix_socket(seq->private);
	return next_unix_socket(seq->private, v);
}

static void unix_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&unix_table_lock);
}

static int unix_seq_show(struct seq_file *seq, void *v)
{
	
	if (v == (void *)1)
		seq_puts(seq, "Num       RefCount Protocol Flags    Type St "
			 "Inode Path\n");
	else {
		struct sock *s = v;
		struct unix_sock *u = unix_sk(s);
		unix_state_rlock(s);

		seq_printf(seq, "%p: %08X %08X %08X %04X %02X %5lu",
			s,
			atomic_read(&s->sk_refcnt),
			0,
			s->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0,
			s->sk_type,
			s->sk_socket ?
			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTED : SS_UNCONNECTED) :
			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
			sock_i_ino(s));

		if (u->addr) {
			int i, len;
			seq_putc(seq, ' ');

			i = 0;
			len = u->addr->len - sizeof(short);
			if (!UNIX_ABSTRACT(s))
				len--;
			else {
				seq_putc(seq, '@');
				i++;
			}
			for ( ; i < len; i++)
				seq_putc(seq, u->addr->name->sun_path[i]);
		}
		unix_state_runlock(s);
		seq_putc(seq, '\n');
	}

	return 0;
}

static struct seq_operations unix_seq_ops = {
	.start  = unix_seq_start,
	.next   = unix_seq_next,
	.stop   = unix_seq_stop,
	.show   = unix_seq_show,
};


static int unix_seq_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	int rc = -ENOMEM;
	int *iter = kmalloc(sizeof(int), GFP_KERNEL);

	if (!iter)
		goto out;

	rc = seq_open(file, &unix_seq_ops);
	if (rc)
		goto out_kfree;

	seq	     = file->private_data;
	seq->private = iter;
	*iter = 0;
out:
	return rc;
out_kfree:
	kfree(iter);
	goto out;
}

static struct file_operations unix_seq_fops = {
	.owner		= THIS_MODULE,
	.open		= unix_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

#endif

static struct net_proto_family unix_family_ops = {
	.family = PF_UNIX,
	.create = unix_create,
	.owner	= THIS_MODULE,
};

#ifdef CONFIG_SYSCTL
extern void unix_sysctl_register(void);
extern void unix_sysctl_unregister(void);
#else
static inline void unix_sysctl_register(void) {}
static inline void unix_sysctl_unregister(void) {}
#endif

static int __init af_unix_init(void)
{
	struct sk_buff *dummy_skb;

	if (sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb)) {
		printk(KERN_CRIT "%s: panic\n", __FUNCTION__);
		return -1;
	}
        /* allocate our sock slab cache */
        unix_sk_cachep = kmem_cache_create("unix_sock",
					   sizeof(struct unix_sock), 0,
					   SLAB_HWCACHE_ALIGN, NULL, NULL);
        if (!unix_sk_cachep)
                printk(KERN_CRIT
                        "af_unix_init: Cannot create unix_sock SLAB cache!\n");

	sock_register(&unix_family_ops);
#ifdef CONFIG_PROC_FS
	proc_net_fops_create("unix", 0, &unix_seq_fops);
#endif
	unix_sysctl_register();
	return 0;
}

static void __exit af_unix_exit(void)
{
	sock_unregister(PF_UNIX);
	unix_sysctl_unregister();
	proc_net_remove("unix");
	kmem_cache_destroy(unix_sk_cachep);
}

module_init(af_unix_init);
module_exit(af_unix_exit);

MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_UNIX);