udp.c

linux 内核源代码

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		The User Datagram Protocol (UDP).
 *
 * Version:	$Id: udp.c,v 1.102 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Arnt Gulbrandsen, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *		Hirokazu Takahashi, <[e-mail]>
 *
 * Fixes:
 *		Alan Cox	:	verify_area() calls
 *		Alan Cox	: 	stopped close while in use off icmp
 *					messages. Not a fix but a botch that
 *					for udp at least is 'valid'.
 *		Alan Cox	:	Fixed icmp handling properly
 *		Alan Cox	: 	Correct error for oversized datagrams
 *		Alan Cox	:	Tidied select() semantics.
 *		Alan Cox	:	udp_err() fixed properly, also now
 *					select and read wake correctly on errors
 *		Alan Cox	:	udp_send verify_area moved to avoid mem leak
 *		Alan Cox	:	UDP can count its memory
 *		Alan Cox	:	send to an unknown connection causes
 *					an ECONNREFUSED off the icmp, but
 *					does NOT close.
 *		Alan Cox	:	Switched to new sk_buff handlers. No more backlog!
 *		Alan Cox	:	Using generic datagram code. Even smaller and the PEEK
 *					bug no longer crashes it.
 *		Fred Van Kempen	: 	Net2e support for sk->broadcast.
 *		Alan Cox	:	Uses skb_free_datagram
 *		Alan Cox	:	Added get/set sockopt support.
 *		Alan Cox	:	Broadcasting without option set returns EACCES.
 *		Alan Cox	:	No wakeup calls. Instead we now use the callbacks.
 *		Alan Cox	:	Use ip_tos and ip_ttl
 *		Alan Cox	:	SNMP Mibs
 *		Alan Cox	:	MSG_DONTROUTE, and 0.0.0.0 support.
 *		Matt Dillon	:	UDP length checks.
 *		Alan Cox	:	Smarter af_inet used properly.
 *		Alan Cox	:	Use new kernel side addressing.
 *		Alan Cox	:	Incorrect return on truncated datagram receive.
 *	Arnt Gulbrandsen 	:	New udp_send and stuff
 *		Alan Cox	:	Cache last socket
 *		Alan Cox	:	Route cache
 *		Jon Peatfield	:	Minor efficiency fix to sendto().
 *		Mike Shaver	:	RFC1122 checks.
 *		Alan Cox	:	Nonblocking error fix.
 *	Willy Konynenberg	:	Transparent proxying support.
 *		Mike McLagan	:	Routing by source
 *		David S. Miller	:	New socket lookup architecture.
 *					Last socket cache retained as it
 *					does have a high hit rate.
 *		Olaf Kirch	:	Don't linearise iovec on sendmsg.
 *		Andi Kleen	:	Some cleanups, cache destination entry
 *					for connect.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *		Melvin Smith	:	Check msg_name not msg_namelen in sendto(),
 *					return ENOTCONN for unconnected sockets (POSIX)
 *		Janos Farkas	:	don't deliver multi/broadcasts to a different
 *					bound-to-device socket
 *	Hirokazu Takahashi	:	HW checksumming for outgoing UDP
 *					datagrams.
 *	Hirokazu Takahashi	:	sendfile() on UDP works now.
 *		Arnaldo C. Melo :	convert /proc/net/udp to seq_file
 *	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.
 *	Derek Atkins <[e-mail]>: Add Encapulation Support
 *	James Chapman		:	Add L2TP encapsulation type.
 *
 *
 *		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 <asm/system.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/tcp_states.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include "udp_impl.h"

/*
 *	Snmp MIB for the UDP layer
 */

DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly;

struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);

static inline int __udp_lib_lport_inuse(__u16 num,
					const struct hlist_head udptable[])
{
	struct sock *sk;
	struct hlist_node *node;

	sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
		if (sk->sk_hash == num)
			return 1;
	return 0;
}

/**
 *  __udp_lib_get_port  -  UDP/-Lite port lookup for IPv4 and IPv6
 *
 *  @sk:          socket struct in question
 *  @snum:        port number to look up
 *  @udptable:    hash list table, must be of UDP_HTABLE_SIZE
 *  @saddr_comp:  AF-dependent comparison of bound local IP addresses
 */
int __udp_lib_get_port(struct sock *sk, unsigned short snum,
		       struct hlist_head udptable[],
		       int (*saddr_comp)(const struct sock *sk1,
					 const struct sock *sk2 )    )
{
	struct hlist_node *node;
	struct hlist_head *head;
	struct sock *sk2;
	int    error = 1;

	write_lock_bh(&udp_hash_lock);

	if (!snum) {
		int i, low, high, remaining;
		unsigned rover, best, best_size_so_far;

		inet_get_local_port_range(&low, &high);
		remaining = (high - low) + 1;

		best_size_so_far = UINT_MAX;
		best = rover = net_random() % remaining + low;

		/* 1st pass: look for empty (or shortest) hash chain */
		for (i = 0; i < UDP_HTABLE_SIZE; i++) {
			int size = 0;

			head = &udptable[rover & (UDP_HTABLE_SIZE - 1)];
			if (hlist_empty(head))
				goto gotit;

			sk_for_each(sk2, node, head) {
				if (++size >= best_size_so_far)
					goto next;
			}
			best_size_so_far = size;
			best = rover;
		next:
			/* fold back if end of range */
			if (++rover > high)
				rover = low + ((rover - low)
					       & (UDP_HTABLE_SIZE - 1));


		}

		/* 2nd pass: find hole in shortest hash chain */
		rover = best;
		for (i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++) {
			if (! __udp_lib_lport_inuse(rover, udptable))
				goto gotit;
			rover += UDP_HTABLE_SIZE;
			if (rover > high)
				rover = low + ((rover - low)
					       & (UDP_HTABLE_SIZE - 1));
		}


		/* All ports in use! */
		goto fail;

gotit:
		snum = rover;
	} else {
		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];

		sk_for_each(sk2, node, head)
			if (sk2->sk_hash == snum                             &&
			    sk2 != sk                                        &&
			    (!sk2->sk_reuse        || !sk->sk_reuse)         &&
			    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
			     || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
			    (*saddr_comp)(sk, sk2)                             )
				goto fail;
	}

	inet_sk(sk)->num = snum;
	sk->sk_hash = snum;
	if (sk_unhashed(sk)) {
		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
		sk_add_node(sk, head);
		sock_prot_inc_use(sk->sk_prot);
	}
	error = 0;
fail:
	write_unlock_bh(&udp_hash_lock);
	return error;
}

int udp_get_port(struct sock *sk, unsigned short snum,
			int (*scmp)(const struct sock *, const struct sock *))
{
	return  __udp_lib_get_port(sk, snum, udp_hash, scmp);
}

int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
	struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);

	return 	( !ipv6_only_sock(sk2)  &&
		  (!inet1->rcv_saddr || !inet2->rcv_saddr ||
		   inet1->rcv_saddr == inet2->rcv_saddr      ));
}

static inline int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
	return udp_get_port(sk, snum, ipv4_rcv_saddr_equal);
}

/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
 * harder than this. -DaveM
 */
static struct sock *__udp4_lib_lookup(__be32 saddr, __be16 sport,
				      __be32 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 && !ipv6_only_sock(sk)) {
			int score = (sk->sk_family == PF_INET ? 1 : 0);
			if (inet->rcv_saddr) {
				if (inet->rcv_saddr != daddr)
					continue;
				score+=2;
			}
			if (inet->daddr) {
				if (inet->daddr != saddr)
					continue;
				score+=2;
			}
			if (inet->dport) {
				if (inet->dport != sport)
					continue;
				score+=2;
			}
			if (sk->sk_bound_dev_if) {
				if (sk->sk_bound_dev_if != dif)
					continue;
				score+=2;
			}
			if (score == 9) {
				result = sk;
				break;
			} else if (score > badness) {
				result = sk;
				badness = score;
			}
		}
	}
	if (result)
		sock_hold(result);
	read_unlock(&udp_hash_lock);
	return result;
}

static inline struct sock *udp_v4_mcast_next(struct sock *sk,
					     __be16 loc_port, __be32 loc_addr,
					     __be16 rmt_port, __be32 rmt_addr,
					     int dif)
{
	struct hlist_node *node;
	struct sock *s = sk;
	unsigned short hnum = ntohs(loc_port);

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

		if (s->sk_hash != hnum					||
		    (inet->daddr && inet->daddr != rmt_addr)		||
		    (inet->dport != rmt_port && inet->dport)		||
		    (inet->rcv_saddr && inet->rcv_saddr != loc_addr)	||
		    ipv6_only_sock(s)					||
		    (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
			continue;
		if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
			continue;
		goto found;
	}
	s = NULL;
found:
	return s;
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.
 * Header points to the ip header of the error packet. We move
 * on past this. Then (as it used to claim before adjustment)
 * header points to the first 8 bytes of the udp header.  We need
 * to find the appropriate port.
 */

void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[])
{
	struct inet_sock *inet;
	struct iphdr *iph = (struct iphdr*)skb->data;
	struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	struct sock *sk;
	int harderr;
	int err;

	sk = __udp4_lib_lookup(iph->daddr, uh->dest, iph->saddr, uh->source,
			       skb->dev->ifindex, udptable		    );
	if (sk == NULL) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;	/* No socket for error */
	}

	err = 0;
	harderr = 0;
	inet = inet_sk(sk);

	switch (type) {
	default:
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	case ICMP_SOURCE_QUENCH:
		goto out;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		harderr = 1;
		break;
	case ICMP_DEST_UNREACH:
		if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
			if (inet->pmtudisc != IP_PMTUDISC_DONT) {
				err = EMSGSIZE;
				harderr = 1;
				break;
			}
			goto out;
		}
		err = EHOSTUNREACH;
		if (code <= NR_ICMP_UNREACH) {
			harderr = icmp_err_convert[code].fatal;
			err = icmp_err_convert[code].errno;
		}
		break;
	}

	/*
	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
	 *	4.1.3.3.
	 */
	if (!inet->recverr) {
		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
			goto out;
	} else {
		ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1));
	}
	sk->sk_err = err;
	sk->sk_error_report(sk);
out:
	sock_put(sk);
}

void udp_err(struct sk_buff *skb, u32 info)
{
	return __udp4_lib_err(skb, info, udp_hash);
}

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

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

/**
 * 	udp4_hwcsum_outgoing  -  handle outgoing HW checksumming
 * 	@sk: 	socket we are sending on
 * 	@skb: 	sk_buff containing the filled-in UDP header
 * 	        (checksum field must be zeroed out)
 */
static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
				 __be32 src, __be32 dst, int len      )
{
	unsigned int offset;
	struct udphdr *uh = udp_hdr(skb);
	__wsum csum = 0;

	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		/*
		 * Only one fragment on the socket.
		 */
		skb->csum_start = skb_transport_header(skb) - skb->head;
		skb->csum_offset = offsetof(struct udphdr, check);
		uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0);
	} else {
		/*
		 * HW-checksum won't work as there are two or more
		 * fragments on the socket so that all csums of sk_buffs
		 * should be together
		 */
		offset = skb_transport_offset(skb);
		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);

		skb->ip_summed = CHECKSUM_NONE;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			csum = csum_add(csum, skb->csum);
		}

		uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
		if (uh->check == 0)
			uh->check = CSUM_MANGLED_0;
	}
}

/*
 * Push out all pending data as one UDP datagram. Socket is locked.
 */
static int udp_push_pending_frames(struct sock *sk)
{
	struct udp_sock  *up = udp_sk(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct flowi *fl = &inet->cork.fl;
	struct sk_buff *skb;
	struct udphdr *uh;
	int err = 0;
	__wsum csum = 0;

	/* Grab the skbuff where UDP header space exists. */
	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	/*
	 * Create a UDP header
	 */
	uh = udp_hdr(skb);
	uh->source = fl->fl_ip_sport;
	uh->dest = fl->fl_ip_dport;
	uh->len = htons(up->len);
	uh->check = 0;

	if (up->pcflag)  				 /*     UDP-Lite      */
		csum  = udplite_csum_outgoing(sk, skb);

	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */

		skb->ip_summed = CHECKSUM_NONE;
		goto send;

	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */

		udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len);
		goto send;

	} else						 /*   `normal' UDP    */
		csum = udp_csum_outgoing(sk, skb);

	/* add protocol-dependent pseudo-header */
	uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len,
				      sk->sk_protocol, csum             );
	if (uh->check == 0)
		uh->check = CSUM_MANGLED_0;

send:
	err = ip_push_pending_frames(sk);
out:
	up->len = 0;
	up->pending = 0;
	if (!err)
		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag);
	return err;
}

int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct udp_sock *up = udp_sk(sk);
	int ulen = len;
	struct ipcm_cookie ipc;
	struct rtable *rt = NULL;
	int free = 0;
	int connected = 0;
	__be32 daddr, faddr, saddr;
	__be16 dport;
	u8  tos;
	int err, is_udplite = up->pcflag;
	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);

	if (len > 0xFFFF)
		return -EMSGSIZE;

	/*
	 *	Check the flags.
	 */

	if (msg->msg_flags&MSG_OOB)	/* Mirror BSD error message compatibility */
		return -EOPNOTSUPP;

	ipc.opt = NULL;

	if (up->pending) {
		/*
		 * There are pending frames.
		 * The socket lock must be held while it's corked.
		 */