udp.c

linux 内核源代码

/*
 *	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/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.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 <linux/skbuff.h>
#include <asm/uaccess.h>

#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/raw.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>

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

DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;

static inline int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
	return udp_get_port(sk, snum, ipv6_rcv_saddr_equal);
}

static struct sock *__udp6_lib_lookup(struct in6_addr *saddr, __be16 sport,
				      struct in6_addr *daddr, __be16 dport,
				      int dif, struct hlist_head udptable[])
{
	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, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
		struct inet_sock *inet = inet_sk(sk);

		if (sk->sk_hash == 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_equal(&np->rcv_saddr, daddr))
					continue;
				score++;
			}
			if (!ipv6_addr_any(&np->daddr)) {
				if (!ipv6_addr_equal(&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;
}

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

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 inet_sock *inet = inet_sk(sk);
	struct sk_buff *skb;
	unsigned int ulen, copied;
	int err;
	int is_udplite = IS_UDPLITE(sk);

	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;

	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 (msg->msg_name) {
		struct sockaddr_in6 *sin6;

		sin6 = (struct sockaddr_in6 *) msg->msg_name;
		sin6->sin6_family = AF_INET6;
		sin6->sin6_port = udp_hdr(skb)->source;
		sin6->sin6_flowinfo = 0;
		sin6->sin6_scope_id = 0;

		if (skb->protocol == htons(ETH_P_IP))
			ipv6_addr_set(&sin6->sin6_addr, 0, 0,
				      htonl(0xffff), ip_hdr(skb)->saddr);
		else {
			ipv6_addr_copy(&sin6->sin6_addr,
				       &ipv6_hdr(skb)->saddr);
			if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
				sin6->sin6_scope_id = IP6CB(skb)->iif;
		}

	}
	if (skb->protocol == htons(ETH_P_IP)) {
		if (inet->cmsg_flags)
			ip_cmsg_recv(msg, skb);
	} else {
		if (np->rxopt.all)
			datagram_recv_ctl(sk, msg, skb);
	}

	err = copied;
	if (flags & MSG_TRUNC)
		err = ulen;

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

csum_copy_err:
	UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
	skb_kill_datagram(sk, skb, flags);

	if (flags & MSG_DONTWAIT)
		return -EAGAIN;
	goto try_again;
}

void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		    int type, int code, int offset, __be32 info,
		    struct hlist_head udptable[]                    )
{
	struct ipv6_pinfo *np;
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	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 = __udp6_lib_lookup(daddr, uh->dest,
			       saddr, uh->source, inet6_iif(skb), udptable);
	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__ void udpv6_err(struct sk_buff *skb,
				 struct inet6_skb_parm *opt, int type,
				 int code, int offset, __be32 info     )
{
	return __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash);
}

int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
	struct udp_sock *up = udp_sk(sk);
	int rc;

	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
		goto drop;

	/*
	 * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
	 */
	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {

		if (up->pcrlen == 0) {          /* full coverage was set  */
			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage"
				" %d while full coverage %d requested\n",
				UDP_SKB_CB(skb)->cscov, skb->len);
			goto drop;
		}
		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: 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)
			UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, up->pcflag);
		goto drop;
	}
	UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
	return 0;
drop:
	UDP6_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag);
	kfree_skb(skb);
	return -1;
}

static struct sock *udp_v6_mcast_next(struct sock *sk,
				      __be16 loc_port, struct in6_addr *loc_addr,
				      __be16 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_sock *inet = inet_sk(s);

		if (s->sk_hash == 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_equal(&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_equal(&np->rcv_saddr, loc_addr))
					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 int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr,
			   struct in6_addr *daddr, struct hlist_head udptable[])
{
	struct sock *sk, *sk2;
	const struct udphdr *uh = udp_hdr(skb);
	int dif;

	read_lock(&udp_hash_lock);
	sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
	dif = inet6_iif(skb);
	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);
	return 0;
}

static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
				 int proto)
{
	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;
	}

	if (uh->check == 0) {
		/* RFC 2460 section 8.1 says that we SHOULD log
		   this error. Well, it is reasonable.
		 */
		LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
		return 1;
	}
	if (skb->ip_summed == CHECKSUM_COMPLETE &&
	    !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
			     skb->len, proto, skb->csum))
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (!skb_csum_unnecessary(skb))
		skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
							 &ipv6_hdr(skb)->daddr,
							 skb->len, proto, 0));

	return 0;
}

int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
		   int proto)
{
	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 = &ipv6_hdr(skb)->saddr;
	daddr = &ipv6_hdr(skb)->daddr;
	uh = udp_hdr(skb);

	ulen = ntohs(uh->len);
	if (ulen > skb->len)
		goto short_packet;

	if (proto == IPPROTO_UDP) {
		/* UDP validates ulen. */

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

		if (ulen < sizeof(*uh))
			goto short_packet;

		if (ulen < skb->len) {
			if (pskb_trim_rcsum(skb, ulen))
				goto short_packet;
			saddr = &ipv6_hdr(skb)->saddr;
			daddr = &ipv6_hdr(skb)->daddr;
			uh = udp_hdr(skb);
		}
	}

	if (udp6_csum_init(skb, uh, proto))
		goto discard;

	/*
	 *	Multicast receive code
	 */
	if (ipv6_addr_is_multicast(daddr))
		return __udp6_lib_mcast_deliver(skb, saddr, daddr, udptable);

	/* Unicast */

	/*
	 * check socket cache ... must talk to Alan about his plans
	 * for sock caches... i'll skip this for now.
	 */
	sk = __udp6_lib_lookup(saddr, uh->source,
			       daddr, uh->dest, inet6_iif(skb), udptable);

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

		if (udp_lib_checksum_complete(skb))
			goto discard;
		UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);

		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;

short_packet:
	LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n",
		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
		       ulen, skb->len);

discard:
	UDP6_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
	kfree_skb(skb);
	return 0;
}

static __inline__ int udpv6_rcv(struct sk_buff *skb)
{
	return __udp6_lib_rcv(skb, udp_hash, IPPROTO_UDP);
}

/*
 * Throw away all pending data and cancel the corking. Socket is locked.
 */
static void udp_v6_flush_pending_frames(struct sock *sk)
{
	struct udp_sock *up = udp_sk(sk);

	if (up->pending) {
		up->len = 0;