udp.c

Linux Kernel 2.6.9 for OMAP1710

		/*
		 * There are pending frames.
	 	 * The socket lock must be held while it's corked.
		 */
		lock_sock(sk);
		if (likely(up->pending)) {
			if (unlikely(up->pending != AF_INET)) {
				release_sock(sk);
				return -EINVAL;
			}
 			goto do_append_data;
		}
		release_sock(sk);
	}
	ulen += sizeof(struct udphdr);

	/*
	 *	Get and verify the address. 
	 */
	if (msg->msg_name) {
		struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
		if (msg->msg_namelen < sizeof(*usin))
			return -EINVAL;
		if (usin->sin_family != AF_INET) {
			if (usin->sin_family != AF_UNSPEC)
				return -EINVAL;
		}

		daddr = usin->sin_addr.s_addr;
		dport = usin->sin_port;
		if (dport == 0)
			return -EINVAL;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;
		daddr = inet->daddr;
		dport = inet->dport;
		/* Open fast path for connected socket.
		   Route will not be used, if at least one option is set.
		 */
		connected = 1;
  	}
	ipc.addr = inet->saddr;

	ipc.oif = sk->sk_bound_dev_if;
	if (msg->msg_controllen) {
		err = ip_cmsg_send(msg, &ipc);
		if (err)
			return err;
		if (ipc.opt)
			free = 1;
		connected = 0;
	}
	if (!ipc.opt)
		ipc.opt = inet->opt;

	saddr = ipc.addr;
	ipc.addr = faddr = daddr;

	if (ipc.opt && ipc.opt->srr) {
		if (!daddr)
			return -EINVAL;
		faddr = ipc.opt->faddr;
		connected = 0;
	}
	tos = RT_TOS(inet->tos);
	if (sk->sk_localroute || (msg->msg_flags & MSG_DONTROUTE) || 
	    (ipc.opt && ipc.opt->is_strictroute)) {
		tos |= RTO_ONLINK;
		connected = 0;
	}

	if (MULTICAST(daddr)) {
		if (!ipc.oif)
			ipc.oif = inet->mc_index;
		if (!saddr)
			saddr = inet->mc_addr;
		connected = 0;
	}

	if (connected)
		rt = (struct rtable*)sk_dst_check(sk, 0);

	if (rt == NULL) {
		struct flowi fl = { .oif = ipc.oif,
				    .nl_u = { .ip4_u =
					      { .daddr = faddr,
						.saddr = saddr,
						.tos = tos } },
				    .proto = IPPROTO_UDP,
				    .uli_u = { .ports =
					       { .sport = inet->sport,
						 .dport = dport } } };
		err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT));
		if (err)
			goto out;

		err = -EACCES;
		if ((rt->rt_flags & RTCF_BROADCAST) &&
		    !sock_flag(sk, SOCK_BROADCAST))
			goto out;
		if (connected)
			sk_dst_set(sk, dst_clone(&rt->u.dst));
	}

	if (msg->msg_flags&MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	saddr = rt->rt_src;
	if (!ipc.addr)
		daddr = ipc.addr = rt->rt_dst;

	lock_sock(sk);
	if (unlikely(up->pending)) {
		/* The socket is already corked while preparing it. */
		/* ... which is an evident application bug. --ANK */
		release_sock(sk);

		NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "udp cork app bug 2\n"));
		err = -EINVAL;
		goto out;
	}
	/*
	 *	Now cork the socket to pend data.
	 */
	inet->cork.fl.fl4_dst = daddr;
	inet->cork.fl.fl_ip_dport = dport;
	inet->cork.fl.fl4_src = saddr;
	inet->cork.fl.fl_ip_sport = inet->sport;
	up->pending = AF_INET;

do_append_data:
	up->len += ulen;
	err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, 
			sizeof(struct udphdr), &ipc, rt, 
			corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
	if (err)
		udp_flush_pending_frames(sk);
	else if (!corkreq)
		err = udp_push_pending_frames(sk, up);
	release_sock(sk);

out:
	ip_rt_put(rt);
	if (free)
		kfree(ipc.opt);
	if (!err) {
		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS);
		return len;
	}
	return err;

do_confirm:
	dst_confirm(&rt->u.dst);
	if (!(msg->msg_flags&MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto out;
}

int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags)
{
	struct udp_opt *up = udp_sk(sk);
	int ret;

	if (!up->pending) {
		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };

		/* Call udp_sendmsg to specify destination address which
		 * sendpage interface can't pass.
		 * This will succeed only when the socket is connected.
		 */
		ret = udp_sendmsg(NULL, sk, &msg, 0);
		if (ret < 0)
			return ret;
	}

	lock_sock(sk);

	if (unlikely(!up->pending)) {
		release_sock(sk);

		NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "udp cork app bug 3\n"));
		return -EINVAL;
	}

	ret = ip_append_page(sk, page, offset, size, flags);
	if (ret == -EOPNOTSUPP) {
		release_sock(sk);
		return sock_no_sendpage(sk->sk_socket, page, offset,
					size, flags);
	}
	if (ret < 0) {
		udp_flush_pending_frames(sk);
		goto out;
	}

	up->len += size;
	if (!(up->corkflag || (flags&MSG_MORE)))
		ret = udp_push_pending_frames(sk, up);
	if (!ret)
		ret = size;
out:
	release_sock(sk);
	return ret;
}

/*
 *	IOCTL requests applicable to the UDP protocol
 */
 
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch(cmd) 
	{
		case SIOCOUTQ:
		{
			int amount = atomic_read(&sk->sk_wmem_alloc);
			return put_user(amount, (int __user *)arg);
		}

		case SIOCINQ:
		{
			struct sk_buff *skb;
			unsigned long amount;

			amount = 0;
			spin_lock_irq(&sk->sk_receive_queue.lock);
			skb = skb_peek(&sk->sk_receive_queue);
			if (skb != NULL) {
				/*
				 * We will only return the amount
				 * of this packet since that is all
				 * that will be read.
				 */
				amount = skb->len - sizeof(struct udphdr);
			}
			spin_unlock_irq(&sk->sk_receive_queue.lock);
			return put_user(amount, (int __user *)arg);
		}

		default:
			return -ENOIOCTLCMD;
	}
	return(0);
}

static __inline__ int __udp_checksum_complete(struct sk_buff *skb)
{
	return (unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
}

static __inline__ int udp_checksum_complete(struct sk_buff *skb)
{
	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
		__udp_checksum_complete(skb);
}

/*
 * 	This should be easy, if there is something there we
 * 	return it, otherwise we block.
 */

int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int noblock, int flags, int *addr_len)
{
	struct inet_opt *inet = inet_sk(sk);
  	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
  	struct sk_buff *skb;
  	int copied, err;

	/*
	 *	Check any passed addresses
	 */
	if (addr_len)
		*addr_len=sizeof(*sin);

	if (flags & MSG_ERRQUEUE)
		return ip_recv_error(sk, msg, len);

try_again:
	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;
  
  	copied = skb->len - sizeof(struct udphdr);
	if (copied > len) {
		copied = len;
		msg->msg_flags |= MSG_TRUNC;
	}

	if (skb->ip_summed==CHECKSUM_UNNECESSARY) {
		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
					      copied);
	} else if (msg->msg_flags&MSG_TRUNC) {
		if (__udp_checksum_complete(skb))
			goto csum_copy_err;
		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
					      copied);
	} else {
		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);

		if (err == -EINVAL)
			goto csum_copy_err;
	}

	if (err)
		goto out_free;

	sock_recv_timestamp(msg, sk, skb);

	/* Copy the address. */
	if (sin)
	{
		sin->sin_family = AF_INET;
		sin->sin_port = skb->h.uh->source;
		sin->sin_addr.s_addr = skb->nh.iph->saddr;
		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
  	}
	if (inet->cmsg_flags)
		ip_cmsg_recv(msg, skb);

	err = copied;
	if (flags & MSG_TRUNC)
		err = skb->len - sizeof(struct udphdr);
  
out_free:
  	skb_free_datagram(sk, skb);
out:
  	return err;

csum_copy_err:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS);

	/* Clear queue. */
	if (flags&MSG_PEEK) {
		int clear = 0;
		spin_lock_irq(&sk->sk_receive_queue.lock);
		if (skb == skb_peek(&sk->sk_receive_queue)) {
			__skb_unlink(skb, &sk->sk_receive_queue);
			clear = 1;
		}
		spin_unlock_irq(&sk->sk_receive_queue.lock);
		if (clear)
			kfree_skb(skb);
	}

	skb_free_datagram(sk, skb);

	if (noblock)
		return -EAGAIN;	
	goto try_again;
}


int udp_disconnect(struct sock *sk, int flags)
{
	struct inet_opt *inet = inet_sk(sk);
	/*
	 *	1003.1g - break association.
	 */
	 
	sk->sk_state = TCP_CLOSE;
	inet->daddr = 0;
	inet->dport = 0;
	sk->sk_bound_dev_if = 0;
	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
		sk->sk_prot->unhash(sk);
		inet->sport = 0;
	}
	sk_dst_reset(sk);
	return 0;
}

static void udp_close(struct sock *sk, long timeout)
{
	sk_common_release(sk);
}

/* return:
 * 	1  if the the UDP system should process it
 *	0  if we should drop this packet
 * 	-1 if it should get processed by xfrm4_rcv_encap
 */
static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
{
#ifndef CONFIG_XFRM
	return 1; 
#else
	struct udp_opt *up = udp_sk(sk);
  	struct udphdr *uh = skb->h.uh;
	struct iphdr *iph;
	int iphlen, len;
  
	__u8 *udpdata = (__u8 *)uh + sizeof(struct udphdr);
	__u32 *udpdata32 = (__u32 *)udpdata;
	__u16 encap_type = up->encap_type;

	/* if we're overly short, let UDP handle it */
	if (udpdata > skb->tail)
		return 1;

	/* if this is not encapsulated socket, then just return now */
	if (!encap_type)
		return 1;

	len = skb->tail - udpdata;

	switch (encap_type) {
	default:
	case UDP_ENCAP_ESPINUDP:
		/* Check if this is a keepalive packet.  If so, eat it. */
		if (len == 1 && udpdata[0] == 0xff) {
			return 0;
		} else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0 ) {
			/* ESP Packet without Non-ESP header */
			len = sizeof(struct udphdr);
		} else
			/* Must be an IKE packet.. pass it through */
			return 1;
		break;
	case UDP_ENCAP_ESPINUDP_NON_IKE:
		/* Check if this is a keepalive packet.  If so, eat it. */
		if (len == 1 && udpdata[0] == 0xff) {
			return 0;
		} else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
			   udpdata32[0] == 0 && udpdata32[1] == 0) {
			
			/* ESP Packet with Non-IKE marker */
			len = sizeof(struct udphdr) + 2 * sizeof(u32);
		} else
			/* Must be an IKE packet.. pass it through */
			return 1;
		break;
	}

	/* At this point we are sure that this is an ESPinUDP packet,
	 * so we need to remove 'len' bytes from the packet (the UDP
	 * header and optional ESP marker bytes) and then modify the
	 * protocol to ESP, and then call into the transform receiver.
	 */

	/* Now we can update and verify the packet length... */
	iph = skb->nh.iph;
	iphlen = iph->ihl << 2;
	iph->tot_len = htons(ntohs(iph->tot_len) - len);
	if (skb->len < iphlen + len) {
		/* packet is too small!?! */
		return 0;
	}

	/* pull the data buffer up to the ESP header and set the
	 * transport header to point to ESP.  Keep UDP on the stack
	 * for later.
	 */
	skb->h.raw = skb_pull(skb, len);

	/* modify the protocol (it's ESP!) */
	iph->protocol = IPPROTO_ESP;

	/* and let the caller know to send this into the ESP processor... */
	return -1;
#endif
}

/* returns:
 *  -1: error
 *   0: success
 *  >0: "udp encap" protocol resubmission
 *
 * Note that in the success and error cases, the skb is assumed to
 * have either been requeued or freed.
 */
static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
	struct udp_opt *up = udp_sk(sk);

	/*
	 *	Charge it to the socket, dropping if the queue is full.
	 */
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
		kfree_skb(skb);
		return -1;
	}

	if (up->encap_type) {
		/*
		 * This is an encapsulation socket, so let's see if this is
		 * an encapsulated packet.
		 * If it's a keepalive packet, then just eat it.
		 * If it's an encapsulateed packet, then pass it to the
		 * IPsec xfrm input and return the response
		 * appropriately.  Otherwise, just fall through and
		 * pass this up the UDP socket.
		 */
		int ret;

		ret = udp_encap_rcv(sk, skb);
		if (ret == 0) {
			/* Eat the packet .. */
			kfree_skb(skb);
			return 0;
		}
		if (ret < 0) {