udp.c

linux 内核源代码

					       skb->len, proto, 0);
	/* Probably, we should checksum udp header (it should be in cache
	 * in any case) and data in tiny packets (< rx copybreak).
	 */

	return 0;
}

/*
 *	All we need to do is get the socket, and then do a checksum.
 */

int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
		   int proto)
{
	struct sock *sk;
	struct udphdr *uh = udp_hdr(skb);
	unsigned short ulen;
	struct rtable *rt = (struct rtable*)skb->dst;
	__be32 saddr = ip_hdr(skb)->saddr;
	__be32 daddr = ip_hdr(skb)->daddr;

	/*
	 *  Validate the packet.
	 */
	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto drop;		/* No space for header. */

	ulen = ntohs(uh->len);
	if (ulen > skb->len)
		goto short_packet;

	if (proto == IPPROTO_UDP) {
		/* UDP validates ulen. */
		if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
			goto short_packet;
		uh = udp_hdr(skb);
	}

	if (udp4_csum_init(skb, uh, proto))
		goto csum_error;

	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
		return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);

	sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
			       inet_iif(skb), udptable);

	if (sk != NULL) {
		int ret = udp_queue_rcv_skb(sk, skb);
		sock_put(sk);

		/* a return value > 0 means to resubmit the input, but
		 * it wants the return to be -protocol, or 0
		 */
		if (ret > 0)
			return -ret;
		return 0;
	}

	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto drop;
	nf_reset(skb);

	/* No socket. Drop packet silently, if checksum is wrong */
	if (udp_lib_checksum_complete(skb))
		goto csum_error;

	UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

	/*
	 * Hmm.  We got an UDP packet to a port to which we
	 * don't wanna listen.  Ignore it.
	 */
	kfree_skb(skb);
	return 0;

short_packet:
	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
		       NIPQUAD(saddr),
		       ntohs(uh->source),
		       ulen,
		       skb->len,
		       NIPQUAD(daddr),
		       ntohs(uh->dest));
	goto drop;

csum_error:
	/*
	 * RFC1122: OK.  Discards the bad packet silently (as far as
	 * the network is concerned, anyway) as per 4.1.3.4 (MUST).
	 */
	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
		       NIPQUAD(saddr),
		       ntohs(uh->source),
		       NIPQUAD(daddr),
		       ntohs(uh->dest),
		       ulen);
drop:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
	kfree_skb(skb);
	return 0;
}

int udp_rcv(struct sk_buff *skb)
{
	return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
}

int udp_destroy_sock(struct sock *sk)
{
	lock_sock(sk);
	udp_flush_pending_frames(sk);
	release_sock(sk);
	return 0;
}

/*
 *	Socket option code for UDP
 */
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
		       char __user *optval, int optlen,
		       int (*push_pending_frames)(struct sock *))
{
	struct udp_sock *up = udp_sk(sk);
	int val;
	int err = 0;

	if (optlen<sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	switch (optname) {
	case UDP_CORK:
		if (val != 0) {
			up->corkflag = 1;
		} else {
			up->corkflag = 0;
			lock_sock(sk);
			(*push_pending_frames)(sk);
			release_sock(sk);
		}
		break;

	case UDP_ENCAP:
		switch (val) {
		case 0:
		case UDP_ENCAP_ESPINUDP:
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			up->encap_rcv = xfrm4_udp_encap_rcv;
			/* FALLTHROUGH */
		case UDP_ENCAP_L2TPINUDP:
			up->encap_type = val;
			break;
		default:
			err = -ENOPROTOOPT;
			break;
		}
		break;

	/*
	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
	 */
	/* The sender sets actual checksum coverage length via this option.
	 * The case coverage > packet length is handled by send module. */
	case UDPLITE_SEND_CSCOV:
		if (!up->pcflag)         /* Disable the option on UDP sockets */
			return -ENOPROTOOPT;
		if (val != 0 && val < 8) /* Illegal coverage: use default (8) */
			val = 8;
		up->pcslen = val;
		up->pcflag |= UDPLITE_SEND_CC;
		break;

	/* The receiver specifies a minimum checksum coverage value. To make
	 * sense, this should be set to at least 8 (as done below). If zero is
	 * used, this again means full checksum coverage.                     */
	case UDPLITE_RECV_CSCOV:
		if (!up->pcflag)         /* Disable the option on UDP sockets */
			return -ENOPROTOOPT;
		if (val != 0 && val < 8) /* Avoid silly minimal values.       */
			val = 8;
		up->pcrlen = val;
		up->pcflag |= UDPLITE_RECV_CC;
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	}

	return err;
}

int udp_setsockopt(struct sock *sk, int level, int optname,
		   char __user *optval, int optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
					  udp_push_pending_frames);
	return ip_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
int compat_udp_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
					  udp_push_pending_frames);
	return compat_ip_setsockopt(sk, level, optname, optval, optlen);
}
#endif

int udp_lib_getsockopt(struct sock *sk, int level, int optname,
		       char __user *optval, int __user *optlen)
{
	struct udp_sock *up = udp_sk(sk);
	int val, len;

	if (get_user(len,optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(int));

	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case UDP_CORK:
		val = up->corkflag;
		break;

	case UDP_ENCAP:
		val = up->encap_type;
		break;

	/* The following two cannot be changed on UDP sockets, the return is
	 * always 0 (which corresponds to the full checksum coverage of UDP). */
	case UDPLITE_SEND_CSCOV:
		val = up->pcslen;
		break;

	case UDPLITE_RECV_CSCOV:
		val = up->pcrlen;
		break;

	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val,len))
		return -EFAULT;
	return 0;
}

int udp_getsockopt(struct sock *sk, int level, int optname,
		   char __user *optval, int __user *optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
	return ip_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
int compat_udp_getsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, int __user *optlen)
{
	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
	return compat_ip_getsockopt(sk, level, optname, optval, optlen);
}
#endif
/**
 * 	udp_poll - wait for a UDP event.
 *	@file - file struct
 *	@sock - socket
 *	@wait - poll table
 *
 *	This is same as datagram poll, except for the special case of
 *	blocking sockets. If application is using a blocking fd
 *	and a packet with checksum error is in the queue;
 *	then it could get return from select indicating data available
 *	but then block when reading it. Add special case code
 *	to work around these arguably broken applications.
 */
unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	unsigned int mask = datagram_poll(file, sock, wait);
	struct sock *sk = sock->sk;
	int 	is_lite = IS_UDPLITE(sk);

	/* Check for false positives due to checksum errors */
	if ( (mask & POLLRDNORM) &&
	     !(file->f_flags & O_NONBLOCK) &&
	     !(sk->sk_shutdown & RCV_SHUTDOWN)){
		struct sk_buff_head *rcvq = &sk->sk_receive_queue;
		struct sk_buff *skb;

		spin_lock_bh(&rcvq->lock);
		while ((skb = skb_peek(rcvq)) != NULL &&
		       udp_lib_checksum_complete(skb)) {
			UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
			__skb_unlink(skb, rcvq);
			kfree_skb(skb);
		}
		spin_unlock_bh(&rcvq->lock);

		/* nothing to see, move along */
		if (skb == NULL)
			mask &= ~(POLLIN | POLLRDNORM);
	}

	return mask;

}

DEFINE_PROTO_INUSE(udp)

struct proto udp_prot = {
	.name		   = "UDP",
	.owner		   = THIS_MODULE,
	.close		   = udp_lib_close,
	.connect	   = ip4_datagram_connect,
	.disconnect	   = udp_disconnect,
	.ioctl		   = udp_ioctl,
	.destroy	   = udp_destroy_sock,
	.setsockopt	   = udp_setsockopt,
	.getsockopt	   = udp_getsockopt,
	.sendmsg	   = udp_sendmsg,
	.recvmsg	   = udp_recvmsg,
	.sendpage	   = udp_sendpage,
	.backlog_rcv	   = udp_queue_rcv_skb,
	.hash		   = udp_lib_hash,
	.unhash		   = udp_lib_unhash,
	.get_port	   = udp_v4_get_port,
	.obj_size	   = sizeof(struct udp_sock),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_udp_setsockopt,
	.compat_getsockopt = compat_udp_getsockopt,
#endif
	REF_PROTO_INUSE(udp)
};

/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS

static struct sock *udp_get_first(struct seq_file *seq)
{
	struct sock *sk;
	struct udp_iter_state *state = seq->private;

	for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
		struct hlist_node *node;
		sk_for_each(sk, node, state->hashtable + state->bucket) {
			if (sk->sk_family == state->family)
				goto found;
		}
	}
	sk = NULL;
found:
	return sk;
}

static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
	struct udp_iter_state *state = seq->private;

	do {
		sk = sk_next(sk);
try_again:
		;
	} while (sk && sk->sk_family != state->family);

	if (!sk && ++state->bucket < UDP_HTABLE_SIZE) {
		sk = sk_head(state->hashtable + state->bucket);
		goto try_again;
	}
	return sk;
}

static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
{
	struct sock *sk = udp_get_first(seq);

	if (sk)
		while (pos && (sk = udp_get_next(seq, sk)) != NULL)
			--pos;
	return pos ? NULL : sk;
}

static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&udp_hash_lock);
	return *pos ? udp_get_idx(seq, *pos-1) : (void *)1;
}

static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *sk;

	if (v == (void *)1)
		sk = udp_get_idx(seq, 0);
	else
		sk = udp_get_next(seq, v);

	++*pos;
	return sk;
}

static void udp_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&udp_hash_lock);
}

static int udp_seq_open(struct inode *inode, struct file *file)
{
	struct udp_seq_afinfo *afinfo = PDE(inode)->data;
	struct seq_file *seq;
	int rc = -ENOMEM;
	struct udp_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL);

	if (!s)
		goto out;
	s->family		= afinfo->family;
	s->hashtable		= afinfo->hashtable;
	s->seq_ops.start	= udp_seq_start;
	s->seq_ops.next		= udp_seq_next;
	s->seq_ops.show		= afinfo->seq_show;
	s->seq_ops.stop		= udp_seq_stop;

	rc = seq_open(file, &s->seq_ops);
	if (rc)
		goto out_kfree;

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

/* ------------------------------------------------------------------------ */
int udp_proc_register(struct udp_seq_afinfo *afinfo)
{
	struct proc_dir_entry *p;
	int rc = 0;

	if (!afinfo)
		return -EINVAL;
	afinfo->seq_fops->owner		= afinfo->owner;
	afinfo->seq_fops->open		= udp_seq_open;
	afinfo->seq_fops->read		= seq_read;
	afinfo->seq_fops->llseek	= seq_lseek;
	afinfo->seq_fops->release	= seq_release_private;

	p = proc_net_fops_create(&init_net, afinfo->name, S_IRUGO, afinfo->seq_fops);
	if (p)
		p->data = afinfo;
	else
		rc = -ENOMEM;
	return rc;
}

void udp_proc_unregister(struct udp_seq_afinfo *afinfo)
{
	if (!afinfo)
		return;
	proc_net_remove(&init_net, afinfo->name);
	memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
}

/* ------------------------------------------------------------------------ */
static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket)
{
	struct inet_sock *inet = inet_sk(sp);
	__be32 dest = inet->daddr;
	__be32 src  = inet->rcv_saddr;
	__u16 destp	  = ntohs(inet->dport);
	__u16 srcp	  = ntohs(inet->sport);

	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
		bucket, src, srcp, dest, destp, sp->sk_state,
		atomic_read(&sp->sk_wmem_alloc),
		atomic_read(&sp->sk_rmem_alloc),
		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
		atomic_read(&sp->sk_refcnt), sp);
}

int udp4_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "%-127s\n",
			   "  sl  local_address rem_address   st tx_queue "
			   "rx_queue tr tm->when retrnsmt   uid  timeout "
			   "inode");
	else {
		char tmpbuf[129];
		struct udp_iter_state *state = seq->private;

		udp4_format_sock(v, tmpbuf, state->bucket);
		seq_printf(seq, "%-127s\n", tmpbuf);
	}
	return 0;
}

/* ------------------------------------------------------------------------ */
static struct file_operations udp4_seq_fops;
static struct udp_seq_afinfo udp4_seq_afinfo = {
	.owner		= THIS_MODULE,
	.name		= "udp",
	.family		= AF_INET,
	.hashtable	= udp_hash,
	.seq_show	= udp4_seq_show,
	.seq_fops	= &udp4_seq_fops,
};

int __init udp4_proc_init(void)
{
	return udp_proc_register(&udp4_seq_afinfo);
}

void udp4_proc_exit(void)
{
	udp_proc_unregister(&udp4_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */

EXPORT_SYMBOL(udp_disconnect);
EXPORT_SYMBOL(udp_hash);
EXPORT_SYMBOL(udp_hash_lock);
EXPORT_SYMBOL(udp_ioctl);
EXPORT_SYMBOL(udp_get_port);
EXPORT_SYMBOL(udp_prot);
EXPORT_SYMBOL(udp_sendmsg);
EXPORT_SYMBOL(udp_lib_getsockopt);
EXPORT_SYMBOL(udp_lib_setsockopt);
EXPORT_SYMBOL(udp_poll);

#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(udp_proc_register);
EXPORT_SYMBOL(udp_proc_unregister);
#endif