udp.c

嵌入式系统设计与实验教材二源码linux内核移植与编译

/*
 *	UDP over IPv6
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>	
 *
 *	Based on linux/ipv4/udp.c
 *
 *	$Id: udp.c,v 1.64 2001/09/01 00:31:50 davem Exp $
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *
 *	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/inet_common.h>

#include <net/checksum.h>

struct udp_mib udp_stats_in6[NR_CPUS*2];

/* 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)
{
	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++) {
			struct sock *sk;
			int size;

			sk = udp_hash[result & (UDP_HTABLE_SIZE - 1)];
			if (!sk) {
				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;
			do {
				if (++size >= best_size_so_far)
					goto next;
			} while ((sk = sk->next) != NULL);
			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 {
		struct sock *sk2;
		int addr_type = ipv6_addr_type(&sk->net_pinfo.af_inet6.rcv_saddr);

		for (sk2 = udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
		     sk2 != NULL;
		     sk2 = sk2->next) {
			if (sk2->num == snum &&
			    sk2 != sk &&
			    sk2->bound_dev_if == sk->bound_dev_if &&
			    (!sk2->rcv_saddr ||
			     addr_type == IPV6_ADDR_ANY ||
			     !ipv6_addr_cmp(&sk->net_pinfo.af_inet6.rcv_saddr,
					    &sk2->net_pinfo.af_inet6.rcv_saddr) ||
			     (addr_type == IPV6_ADDR_MAPPED &&
			      sk2->family == AF_INET &&
			      sk->rcv_saddr == sk2->rcv_saddr)) &&
			    (!sk2->reuse || !sk->reuse))
				goto fail;
		}
	}

	sk->num = snum;
	if (sk->pprev == NULL) {
		struct sock **skp = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
		if ((sk->next = *skp) != NULL)
			(*skp)->pprev = &sk->next;
		*skp = sk;
		sk->pprev = skp;
		sock_prot_inc_use(sk->prot);
		sock_hold(sk);
	}
	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->pprev) {
		if (sk->next)
			sk->next->pprev = sk->pprev;
		*sk->pprev = sk->next;
		sk->pprev = NULL;
		sk->num = 0;
		sock_prot_dec_use(sk->prot);
		__sock_put(sk);
	}
	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;
	unsigned short hnum = ntohs(dport);
	int badness = -1;

 	read_lock(&udp_hash_lock);
	for(sk = udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]; sk != NULL; sk = sk->next) {
		if((sk->num == hnum)		&&
		   (sk->family == PF_INET6)) {
			struct ipv6_pinfo *np = &sk->net_pinfo.af_inet6;
			int score = 0;
			if(sk->dport) {
				if(sk->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->bound_dev_if) {
				if(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;
}

/*
 *
 */

int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
	struct ipv6_pinfo      	*np = &sk->net_pinfo.af_inet6;
	struct in6_addr		*daddr;
	struct in6_addr		saddr;
	struct dst_entry	*dst;
	struct flowi		fl;
	struct ip6_flowlabel	*flowlabel = NULL;
	int			addr_type;
	int			err;

	if (usin->sin6_family == AF_INET) {
		err = udp_connect(sk, uaddr, addr_len);
		goto ipv4_connected;
	}

	if (addr_len < SIN6_LEN_RFC2133)
	  	return -EINVAL;

	if (usin->sin6_family != AF_INET6) 
	  	return -EAFNOSUPPORT;

	fl.fl6_flowlabel = 0;
	if (np->sndflow) {
		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
		}
	}

	addr_type = ipv6_addr_type(&usin->sin6_addr);

	if (addr_type == IPV6_ADDR_ANY) {
		/*
		 *	connect to self
		 */
		usin->sin6_addr.s6_addr[15] = 0x01;
	}

	daddr = &usin->sin6_addr;

	if (addr_type == IPV6_ADDR_MAPPED) {
		struct sockaddr_in sin;

		sin.sin_family = AF_INET;
		sin.sin_addr.s_addr = daddr->s6_addr32[3];
		sin.sin_port = usin->sin6_port;

		err = udp_connect(sk, (struct sockaddr*) &sin, sizeof(sin));

ipv4_connected:
		if (err < 0)
			return err;
		
		ipv6_addr_set(&np->daddr, 0, 0, 
			      __constant_htonl(0x0000ffff),
			      sk->daddr);

		if(ipv6_addr_any(&np->saddr)) {
			ipv6_addr_set(&np->saddr, 0, 0, 
				      __constant_htonl(0x0000ffff),
				      sk->saddr);
		}

		if(ipv6_addr_any(&np->rcv_saddr)) {
			ipv6_addr_set(&np->rcv_saddr, 0, 0, 
				      __constant_htonl(0x0000ffff),
				      sk->rcv_saddr);
		}
		return 0;
	}

	if (addr_type&IPV6_ADDR_LINKLOCAL) {
		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    usin->sin6_scope_id) {
			if (sk->bound_dev_if && sk->bound_dev_if != usin->sin6_scope_id) {
				fl6_sock_release(flowlabel);
				return -EINVAL;
			}
			sk->bound_dev_if = usin->sin6_scope_id;
		}

		/* Connect to link-local address requires an interface */
		if (sk->bound_dev_if == 0)
			return -EINVAL;
	}

	ipv6_addr_copy(&np->daddr, daddr);
	np->flow_label = fl.fl6_flowlabel;

	sk->dport = usin->sin6_port;

	/*
	 *	Check for a route to destination an obtain the
	 *	destination cache for it.
	 */

	fl.proto = IPPROTO_UDP;
	fl.fl6_dst = &np->daddr;
	fl.fl6_src = &saddr;
	fl.oif = sk->bound_dev_if;
	fl.uli_u.ports.dport = sk->dport;
	fl.uli_u.ports.sport = sk->sport;

	if (flowlabel) {
		if (flowlabel->opt && flowlabel->opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt;
			fl.fl6_dst = rt0->addr;
		}
	} else if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
		fl.fl6_dst = rt0->addr;
	}

	dst = ip6_route_output(sk, &fl);

	if ((err = dst->error) != 0) {
		dst_release(dst);
		fl6_sock_release(flowlabel);
		return err;
	}

	ip6_dst_store(sk, dst, fl.fl6_dst);

	/* get the source adddress used in the apropriate device */

	err = ipv6_get_saddr(dst, daddr, &saddr);

	if (err == 0) {
		if(ipv6_addr_any(&np->saddr))
			ipv6_addr_copy(&np->saddr, &saddr);

		if(ipv6_addr_any(&np->rcv_saddr)) {
			ipv6_addr_copy(&np->rcv_saddr, &saddr);
			sk->rcv_saddr = LOOPBACK4_IPV6;
		}
		sk->state = TCP_ESTABLISHED;
	}
	fl6_sock_release(flowlabel);

	return err;
}

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

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

int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, int len,
		  int noblock, int flags, int *addr_len)
{
  	struct sk_buff *skb;
  	int copied, err;

  	if (addr_len)
  		*addr_len=sizeof(struct sockaddr_in6);
  
	if (flags & MSG_ERRQUEUE)
		return ipv6_recv_error(sk, msg, len);

	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 == __constant_htons(ETH_P_IP)) {
			ipv6_addr_set(&sin6->sin6_addr, 0, 0,
				      __constant_htonl(0xffff), skb->nh.iph->saddr);
			if (sk->protinfo.af_inet.cmsg_flags)
				ip_cmsg_recv(msg, skb);
		} else {
			memcpy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr,
			       sizeof(struct in6_addr));

			if (sk->net_pinfo.af_inet6.rxopt.all)
				datagram_recv_ctl(sk, msg, skb);
			if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) {
				struct inet6_skb_parm *opt = (struct inet6_skb_parm *) skb->cb;
				sin6->sin6_scope_id = opt->iif;
			}
		}
  	}
	err = copied;

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->receive_queue.lock);
		if (skb == skb_peek(&sk->receive_queue)) {
			__skb_unlink(skb, &sk->receive_queue);
			clear = 1;
		}
		spin_unlock_irq(&sk->receive_queue.lock);
		if (clear)
			kfree_skb(skb);
	}

	/* Error for blocking case is chosen to masquerade
	   as some normal condition.
	 */
	err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH;
	UDP6_INC_STATS_USER(UdpInErrors);
	goto out_free;
}

void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	       int type, int code, int offset, __u32 info)
{
	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;

	if (!icmpv6_err_convert(type, code, &err) &&
	    !sk->net_pinfo.af_inet6.recverr)
		goto out;

	if (sk->state!=TCP_ESTABLISHED &&
	    !sk->net_pinfo.af_inet6.recverr)
		goto out;

	if (sk->net_pinfo.af_inet6.recverr)
		ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));

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

static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
#if defined(CONFIG_FILTER)
	if (sk->filter && skb->ip_summed != CHECKSUM_UNNECESSARY) {
		if ((unsigned short)csum_fold(csum_partial(skb->h.raw, skb->len, skb->csum))) {
			UDP6_INC_STATS_BH(UdpInErrors);
			IP6_INC_STATS_BH(Ip6InDiscards);
			kfree_skb(skb);
			return 0;
		}
		skb->ip_summed = CHECKSUM_UNNECESSARY;