udp.c

Linux Kernel 2.6.9 for OMAP1710

			/* process the ESP packet */
			ret = xfrm4_rcv_encap(skb, up->encap_type);
			UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
			return -ret;
		}
		/* FALLTHROUGH -- it's a UDP Packet */
	}

	if (sk->sk_filter && skb->ip_summed != CHECKSUM_UNNECESSARY) {
		if (__udp_checksum_complete(skb)) {
			UDP_INC_STATS_BH(UDP_MIB_INERRORS);
			kfree_skb(skb);
			return -1;
		}
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	if (sock_queue_rcv_skb(sk,skb)<0) {
		UDP_INC_STATS_BH(UDP_MIB_INERRORS);
		kfree_skb(skb);
		return -1;
	}
	UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
	return 0;
}

/*
 *	Multicasts and broadcasts go to each listener.
 *
 *	Note: called only from the BH handler context,
 *	so we don't need to lock the hashes.
 */
static int udp_v4_mcast_deliver(struct sk_buff *skb, struct udphdr *uh,
				 u32 saddr, u32 daddr)
{
	struct sock *sk;
	int dif;

	read_lock(&udp_hash_lock);
	sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
	dif = skb->dev->ifindex;
	sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
	if (sk) {
		struct sock *sknext = NULL;

		do {
			struct sk_buff *skb1 = skb;

			sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
						   uh->source, saddr, dif);
			if(sknext)
				skb1 = skb_clone(skb, GFP_ATOMIC);

			if(skb1) {
				int ret = udp_queue_rcv_skb(sk, skb1);
				if (ret > 0)
					/* we should probably re-process instead
					 * of dropping packets here. */
					kfree_skb(skb1);
			}
			sk = sknext;
		} while(sknext);
	} else
		kfree_skb(skb);
	read_unlock(&udp_hash_lock);
	return 0;
}

/* Initialize UDP checksum. If exited with zero value (success),
 * CHECKSUM_UNNECESSARY means, that no more checks are required.
 * Otherwise, csum completion requires chacksumming packet body,
 * including udp header and folding it to skb->csum.
 */
static int udp_checksum_init(struct sk_buff *skb, struct udphdr *uh,
			     unsigned short ulen, u32 saddr, u32 daddr)
{
	if (uh->check == 0) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else if (skb->ip_summed == CHECKSUM_HW) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
		if (!udp_check(uh, ulen, saddr, daddr, skb->csum))
			return 0;
		NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "udp v4 hw csum failure.\n"));
		skb->ip_summed = CHECKSUM_NONE;
	}
	if (skb->ip_summed != CHECKSUM_UNNECESSARY)
		skb->csum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 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 udp_rcv(struct sk_buff *skb)
{
  	struct sock *sk;
  	struct udphdr *uh;
	unsigned short ulen;
	struct rtable *rt = (struct rtable*)skb->dst;
	u32 saddr = skb->nh.iph->saddr;
	u32 daddr = skb->nh.iph->daddr;
	int len = skb->len;

	/*
	 *	Validate the packet and the UDP length.
	 */
	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto no_header;

	uh = skb->h.uh;

	ulen = ntohs(uh->len);

	if (ulen > len || ulen < sizeof(*uh))
		goto short_packet;

	if (pskb_trim(skb, ulen))
		goto short_packet;

	if (udp_checksum_init(skb, uh, ulen, saddr, daddr) < 0)
		goto csum_error;

	if(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
		return udp_v4_mcast_deliver(skb, uh, saddr, daddr);

	sk = udp_v4_lookup(saddr, uh->source, daddr, uh->dest, skb->dev->ifindex);

	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 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;

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

	UDP_INC_STATS_BH(UDP_MIB_NOPORTS);
	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:
	NETDEBUG(if (net_ratelimit())
		printk(KERN_DEBUG "UDP: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
			NIPQUAD(saddr),
			ntohs(uh->source),
			ulen,
			len,
			NIPQUAD(daddr),
			ntohs(uh->dest)));
no_header:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS);
	kfree_skb(skb);
	return(0);

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

static 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
 */
static int udp_setsockopt(struct sock *sk, int level, int optname, 
			  char __user *optval, int optlen)
{
	struct udp_opt *up = udp_sk(sk);
	int val;
	int err = 0;

	if (level != SOL_UDP)
		return ip_setsockopt(sk, level, optname, optval, optlen);

	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);
			udp_push_pending_frames(sk, up);
			release_sock(sk);
		}
		break;
		
	case UDP_ENCAP:
		switch (val) {
		case 0:
		case UDP_ENCAP_ESPINUDP:
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			up->encap_type = val;
			break;
		default:
			err = -ENOPROTOOPT;
			break;
		}
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	};

	return err;
}

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

	if (level != SOL_UDP)
		return ip_getsockopt(sk, level, optname, optval, optlen);

	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;

	default:
		return -ENOPROTOOPT;
	};

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


struct proto udp_prot = {
 	.name =		"UDP",
	.close =	udp_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_v4_hash,
	.unhash =	udp_v4_unhash,
	.get_port =	udp_v4_get_port,
	.slab_obj_size = sizeof(struct udp_sock),
};

/* ------------------------------------------------------------------------ */
#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, &udp_hash[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(&udp_hash[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 = kmalloc(sizeof(*s), GFP_KERNEL);

	if (!s)
		goto out;
	memset(s, 0, sizeof(*s));
	s->family		= afinfo->family;
	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(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(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_opt *inet = inet_sk(sp);
	unsigned int dest = inet->daddr;
	unsigned int 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);
}

static 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,
	.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_port_rover);
EXPORT_SYMBOL(udp_prot);
EXPORT_SYMBOL(udp_sendmsg);

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