udp.c

linux 内核源代码

		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 -EAFNOSUPPORT;
		}

		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 (sock_flag(sk, SOCK_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 = sk->sk_protocol,
				    .uli_u = { .ports =
					       { .sport = inet->sport,
						 .dport = dport } } };
		security_sk_classify_flow(sk, &fl);
		err = ip_route_output_flow(&rt, &fl, sk, 1);
		if (err) {
			if (err == -ENETUNREACH)
				IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
			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);

		LIMIT_NETDEBUG(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;
	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
	err = ip_append_data(sk, 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);
	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
		up->pending = 0;
	release_sock(sk);

out:
	ip_rt_put(rt);
	if (free)
		kfree(ipc.opt);
	if (!err)
		return len;
	/*
	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
	 * ENOBUFS might not be good (it's not tunable per se), but otherwise
	 * we don't have a good statistic (IpOutDiscards but it can be too many
	 * things).  We could add another new stat but at least for now that
	 * seems like overkill.
	 */
	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
		UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
	}
	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_sock *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);

		LIMIT_NETDEBUG(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);
	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_bh(&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_bh(&sk->sk_receive_queue.lock);
		return put_user(amount, (int __user *)arg);
	}

	default:
		return -ENOIOCTLCMD;
	}

	return 0;
}

/*
 * 	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_sock *inet = inet_sk(sk);
	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
	struct sk_buff *skb;
	unsigned int ulen, copied;
	int err;
	int is_udplite = IS_UDPLITE(sk);

	/*
	 *	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;

	ulen = skb->len - sizeof(struct udphdr);
	copied = len;
	if (copied > ulen)
		copied = ulen;
	else if (copied < ulen)
		msg->msg_flags |= MSG_TRUNC;

	/*
	 * If checksum is needed at all, try to do it while copying the
	 * data.  If the data is truncated, or if we only want a partial
	 * coverage checksum (UDP-Lite), do it before the copy.
	 */

	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
		if (udp_lib_checksum_complete(skb))
			goto csum_copy_err;
	}

	if (skb_csum_unnecessary(skb))
		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 = udp_hdr(skb)->source;
		sin->sin_addr.s_addr = ip_hdr(skb)->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 = ulen;

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

csum_copy_err:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);

	skb_kill_datagram(sk, skb, flags);

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


int udp_disconnect(struct sock *sk, int flags)
{
	struct inet_sock *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;
}

/* 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.
 */
int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
	struct udp_sock *up = udp_sk(sk);
	int rc;

	/*
	 *	Charge it to the socket, dropping if the queue is full.
	 */
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto drop;
	nf_reset(skb);

	if (up->encap_type) {
		/*
		 * This is an encapsulation socket so pass the skb to
		 * the socket's udp_encap_rcv() hook. Otherwise, just
		 * fall through and pass this up the UDP socket.
		 * up->encap_rcv() returns the following value:
		 * =0 if skb was successfully passed to the encap
		 *    handler or was discarded by it.
		 * >0 if skb should be passed on to UDP.
		 * <0 if skb should be resubmitted as proto -N
		 */

		/* if we're overly short, let UDP handle it */
		if (skb->len > sizeof(struct udphdr) &&
		    up->encap_rcv != NULL) {
			int ret;

			ret = (*up->encap_rcv)(sk, skb);
			if (ret <= 0) {
				UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
				return -ret;
			}
		}

		/* FALLTHROUGH -- it's a UDP Packet */
	}

	/*
	 * 	UDP-Lite specific tests, ignored on UDP sockets
	 */
	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {

		/*
		 * MIB statistics other than incrementing the error count are
		 * disabled for the following two types of errors: these depend
		 * on the application settings, not on the functioning of the
		 * protocol stack as such.
		 *
		 * RFC 3828 here recommends (sec 3.3): "There should also be a
		 * way ... to ... at least let the receiving application block
		 * delivery of packets with coverage values less than a value
		 * provided by the application."
		 */
		if (up->pcrlen == 0) {          /* full coverage was set  */
			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage "
				"%d while full coverage %d requested\n",
				UDP_SKB_CB(skb)->cscov, skb->len);
			goto drop;
		}
		/* The next case involves violating the min. coverage requested
		 * by the receiver. This is subtle: if receiver wants x and x is
		 * greater than the buffersize/MTU then receiver will complain
		 * that it wants x while sender emits packets of smaller size y.
		 * Therefore the above ...()->partial_cov statement is essential.
		 */
		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
			LIMIT_NETDEBUG(KERN_WARNING
				"UDPLITE: coverage %d too small, need min %d\n",
				UDP_SKB_CB(skb)->cscov, up->pcrlen);
			goto drop;
		}
	}

	if (sk->sk_filter) {
		if (udp_lib_checksum_complete(skb))
			goto drop;
	}

	if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
		/* Note that an ENOMEM error is charged twice */
		if (rc == -ENOMEM)
			UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, up->pcflag);
		goto drop;
	}

	UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
	return 0;

drop:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag);
	kfree_skb(skb);
	return -1;
}

/*
 *	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 __udp4_lib_mcast_deliver(struct sk_buff *skb,
				    struct udphdr  *uh,
				    __be32 saddr, __be32 daddr,
				    struct hlist_head udptable[])
{
	struct sock *sk;
	int dif;

	read_lock(&udp_hash_lock);
	sk = sk_head(&udptable[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 inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
				 int proto)
{
	const struct iphdr *iph;
	int err;

	UDP_SKB_CB(skb)->partial_cov = 0;
	UDP_SKB_CB(skb)->cscov = skb->len;

	if (proto == IPPROTO_UDPLITE) {
		err = udplite_checksum_init(skb, uh);
		if (err)
			return err;
	}

	iph = ip_hdr(skb);
	if (uh->check == 0) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
	       if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
				      proto, skb->csum))
			skb->ip_summed = CHECKSUM_UNNECESSARY;
	}
	if (!skb_csum_unnecessary(skb))
		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,