udp.c

Linux Kernel 2.6.9 for OMAP1710

/*
 *	UDP over IPv6
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>	
 *
 *	Based on linux/ipv4/udp.c
 *
 *	$Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 *      Kazunori MIYAZAWA @USAGI:       change process style to use ip6_append_data
 *      YOSHIFUJI Hideaki @USAGI:	convert /proc/net/udp6 to seq_file.
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <asm/uaccess.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/inet_common.h>

#include <net/ip6_checksum.h>
#include <net/xfrm.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>

DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6);

/* Grrr, addr_type already calculated by caller, but I don't want
 * to add some silly "cookie" argument to this method just for that.
 */
static int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
	struct sock *sk2;
	struct hlist_node *node;

	write_lock_bh(&udp_hash_lock);
	if (snum == 0) {
		int best_size_so_far, best, result, i;

		if (udp_port_rover > sysctl_local_port_range[1] ||
		    udp_port_rover < sysctl_local_port_range[0])
			udp_port_rover = sysctl_local_port_range[0];
		best_size_so_far = 32767;
		best = result = udp_port_rover;
		for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
			int size;
			struct hlist_head *list;

			list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)];
			if (hlist_empty(list)) {
				if (result > sysctl_local_port_range[1])
					result = sysctl_local_port_range[0] +
						((result - sysctl_local_port_range[0]) &
						 (UDP_HTABLE_SIZE - 1));
				goto gotit;
			}
			size = 0;
			sk_for_each(sk2, node, list)
				if (++size >= best_size_so_far)
					goto next;
			best_size_so_far = size;
			best = result;
		next:;
		}
		result = best;
		for(;; result += UDP_HTABLE_SIZE) {
			if (result > sysctl_local_port_range[1])
				result = sysctl_local_port_range[0]
					+ ((result - sysctl_local_port_range[0]) &
					   (UDP_HTABLE_SIZE - 1));
			if (!udp_lport_inuse(result))
				break;
		}
gotit:
		udp_port_rover = snum = result;
	} else {
		sk_for_each(sk2, node,
			    &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) {
			if (inet_sk(sk2)->num == snum &&
			    sk2 != sk &&
			    (!sk2->sk_bound_dev_if ||
			     !sk->sk_bound_dev_if ||
			     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
			    (!sk2->sk_reuse || !sk->sk_reuse) &&
			    ipv6_rcv_saddr_equal(sk, sk2))
				goto fail;
		}
	}

	inet_sk(sk)->num = snum;
	if (sk_unhashed(sk)) {
		sk_add_node(sk, &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]);
		sock_prot_inc_use(sk->sk_prot);
	}
	write_unlock_bh(&udp_hash_lock);
	return 0;

fail:
	write_unlock_bh(&udp_hash_lock);
	return 1;
}

static void udp_v6_hash(struct sock *sk)
{
	BUG();
}

static void udp_v6_unhash(struct sock *sk)
{
 	write_lock_bh(&udp_hash_lock);
	if (sk_del_node_init(sk)) {
		inet_sk(sk)->num = 0;
		sock_prot_dec_use(sk->sk_prot);
	}
	write_unlock_bh(&udp_hash_lock);
}

static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport,
				  struct in6_addr *daddr, u16 dport, int dif)
{
	struct sock *sk, *result = NULL;
	struct hlist_node *node;
	unsigned short hnum = ntohs(dport);
	int badness = -1;

 	read_lock(&udp_hash_lock);
	sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) {
		struct inet_opt *inet = inet_sk(sk);

		if (inet->num == hnum && sk->sk_family == PF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(sk);
			int score = 0;
			if (inet->dport) {
				if (inet->dport != sport)
					continue;
				score++;
			}
			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (ipv6_addr_cmp(&np->rcv_saddr, daddr))
					continue;
				score++;
			}
			if (!ipv6_addr_any(&np->daddr)) {
				if (ipv6_addr_cmp(&np->daddr, saddr))
					continue;
				score++;
			}
			if (sk->sk_bound_dev_if) {
				if (sk->sk_bound_dev_if != dif)
					continue;
				score++;
			}
			if(score == 4) {
				result = sk;
				break;
			} else if(score > badness) {
				result = sk;
				badness = score;
			}
		}
	}
	if (result)
		sock_hold(result);
 	read_unlock(&udp_hash_lock);
	return result;
}

/*
 *
 */

static void udpv6_close(struct sock *sk, long timeout)
{
	sk_common_release(sk);
}

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

static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, 
		  struct msghdr *msg, size_t len,
		  int noblock, int flags, int *addr_len)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
  	struct sk_buff *skb;
	size_t copied;
  	int err;

  	if (addr_len)
  		*addr_len=sizeof(struct sockaddr_in6);
  
	if (flags & MSG_ERRQUEUE)
		return ipv6_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 ((unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)))
			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 (msg->msg_name) {
		struct sockaddr_in6 *sin6;
	  
		sin6 = (struct sockaddr_in6 *) msg->msg_name;
		sin6->sin6_family = AF_INET6;
		sin6->sin6_port = skb->h.uh->source;
		sin6->sin6_flowinfo = 0;
		sin6->sin6_scope_id = 0;

		if (skb->protocol == htons(ETH_P_IP)) {
			struct inet_opt *inet = inet_sk(sk);

			ipv6_addr_set(&sin6->sin6_addr, 0, 0,
				      htonl(0xffff), skb->nh.iph->saddr);
			if (inet->cmsg_flags)
				ip_cmsg_recv(msg, skb);
		} else {
			ipv6_addr_copy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr);

			if (np->rxopt.all)
				datagram_recv_ctl(sk, msg, skb);
			if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
				sin6->sin6_scope_id = IP6CB(skb)->iif;
		}
  	}

	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:
	/* 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 (flags & MSG_DONTWAIT) {
		UDP6_INC_STATS_USER(UDP_MIB_INERRORS);
		return -EAGAIN;
	}
	goto try_again;
}

static void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	       int type, int code, int offset, __u32 info)
{
	struct ipv6_pinfo *np;
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	struct net_device *dev = skb->dev;
	struct in6_addr *saddr = &hdr->saddr;
	struct in6_addr *daddr = &hdr->daddr;
	struct udphdr *uh = (struct udphdr*)(skb->data+offset);
	struct sock *sk;
	int err;

	sk = udp_v6_lookup(daddr, uh->dest, saddr, uh->source, dev->ifindex);
   
	if (sk == NULL)
		return;

	np = inet6_sk(sk);

	if (!icmpv6_err_convert(type, code, &err) && !np->recverr)
		goto out;

	if (sk->sk_state != TCP_ESTABLISHED && !np->recverr)
		goto out;

	if (np->recverr)
		ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));

	sk->sk_err = err;
	sk->sk_error_report(sk);
out:
	sock_put(sk);
}

static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
		kfree_skb(skb);
		return -1;
	}

	if (skb->ip_summed != CHECKSUM_UNNECESSARY) {
		if ((unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) {
			UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
			kfree_skb(skb);
			return 0;
		}
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	if (sock_queue_rcv_skb(sk,skb)<0) {
		UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
		kfree_skb(skb);
		return 0;
	}
	UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
	return 0;
}

static struct sock *udp_v6_mcast_next(struct sock *sk,
				      u16 loc_port, struct in6_addr *loc_addr,
				      u16 rmt_port, struct in6_addr *rmt_addr,
				      int dif)
{
	struct hlist_node *node;
	struct sock *s = sk;
	unsigned short num = ntohs(loc_port);

	sk_for_each_from(s, node) {
		struct inet_opt *inet = inet_sk(s);

		if (inet->num == num && s->sk_family == PF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(s);
			if (inet->dport) {
				if (inet->dport != rmt_port)
					continue;
			}
			if (!ipv6_addr_any(&np->daddr) &&
			    ipv6_addr_cmp(&np->daddr, rmt_addr))
				continue;

			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
				continue;

			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (!ipv6_addr_cmp(&np->rcv_saddr, loc_addr))
					return s;
				continue;
			}
			if(!inet6_mc_check(s, loc_addr, rmt_addr))
				continue;
			return s;
		}
	}
	return NULL;
}

/*
 * Note: called only from the BH handler context,
 * so we don't need to lock the hashes.
 */
static void udpv6_mcast_deliver(struct udphdr *uh,
				struct in6_addr *saddr, struct in6_addr *daddr,
				struct sk_buff *skb)
{
	struct sock *sk, *sk2;
	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_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
	if (!sk) {
		kfree_skb(skb);
		goto out;
	}

	sk2 = sk;
	while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr,
					uh->source, saddr, dif))) {
		struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
		if (buff)
			udpv6_queue_rcv_skb(sk2, buff);
	}
	udpv6_queue_rcv_skb(sk, skb);
out:
	read_unlock(&udp_hash_lock);
}

static int udpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
{
	struct sk_buff *skb = *pskb;
	struct sock *sk;
  	struct udphdr *uh;
	struct net_device *dev = skb->dev;
	struct in6_addr *saddr, *daddr;
	u32 ulen = 0;

	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto short_packet;

	saddr = &skb->nh.ipv6h->saddr;
	daddr = &skb->nh.ipv6h->daddr;
	uh = skb->h.uh;

	ulen = ntohs(uh->len);

	/* Check for jumbo payload */
	if (ulen == 0)
		ulen = skb->len;

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

	if (uh->check == 0) {
		/* RFC 2460 section 8.1 says that we SHOULD log
		   this error. Well, it is reasonable.
		 */
		LIMIT_NETDEBUG(
			printk(KERN_INFO "IPv6: udp checksum is 0\n"));
		goto discard;
	}

	if (ulen < skb->len) {
		if (__pskb_trim(skb, ulen))
			goto discard;
		saddr = &skb->nh.ipv6h->saddr;
		daddr = &skb->nh.ipv6h->daddr;
		uh = skb->h.uh;
	}

	if (skb->ip_summed==CHECKSUM_HW) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
		if (csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum)) {
			LIMIT_NETDEBUG(printk(KERN_DEBUG "udp v6 hw csum failure.\n"));
			skb->ip_summed = CHECKSUM_NONE;
		}
	}
	if (skb->ip_summed != CHECKSUM_UNNECESSARY)
		skb->csum = ~csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, 0);

	/* 
	 *	Multicast receive code 
	 */
	if (ipv6_addr_is_multicast(daddr)) {
		udpv6_mcast_deliver(uh, saddr, daddr, skb);
		return 0;
	}

	/* Unicast */

	/* 
	 * check socket cache ... must talk to Alan about his plans
	 * for sock caches... i'll skip this for now.
	 */
	sk = udp_v6_lookup(saddr, uh->source, daddr, uh->dest, dev->ifindex);

	if (sk == NULL) {
		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto discard;

		if (skb->ip_summed != CHECKSUM_UNNECESSARY &&
		    (unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)))
			goto discard;
		UDP6_INC_STATS_BH(UDP_MIB_NOPORTS);

		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);

		kfree_skb(skb);
		return(0);
	}
	
	/* deliver */
	
	udpv6_queue_rcv_skb(sk, skb);
	sock_put(sk);
	return(0);