raw.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.
 *
 *		RAW - implementation of IP "raw" sockets.
 *
 * Version:	$Id: raw.c,v 1.64 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *
 * Fixes:
 *		Alan Cox	:	verify_area() fixed up
 *		Alan Cox	:	ICMP error handling
 *		Alan Cox	:	EMSGSIZE if you send too big a packet
 *		Alan Cox	: 	Now uses generic datagrams and shared
 *					skbuff library. No more peek crashes,
 *					no more backlogs
 *		Alan Cox	:	Checks sk->broadcast.
 *		Alan Cox	:	Uses skb_free_datagram/skb_copy_datagram
 *		Alan Cox	:	Raw passes ip options too
 *		Alan Cox	:	Setsocketopt added
 *		Alan Cox	:	Fixed error return for broadcasts
 *		Alan Cox	:	Removed wake_up calls
 *		Alan Cox	:	Use ttl/tos
 *		Alan Cox	:	Cleaned up old debugging
 *		Alan Cox	:	Use new kernel side addresses
 *	Arnt Gulbrandsen	:	Fixed MSG_DONTROUTE in raw sockets.
 *		Alan Cox	:	BSD style RAW socket demultiplexing.
 *		Alan Cox	:	Beginnings of mrouted support.
 *		Alan Cox	:	Added IP_HDRINCL option.
 *		Alan Cox	:	Skip broadcast check if BSDism set.
 *		David S. Miller	:	New socket lookup architecture.
 *
 *		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/types.h>
#include <asm/atomic.h>
#include <asm/byteorder.h>
#include <asm/current.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/aio.h>
#include <linux/kernel.h>
#include <linux/spinlock.h>
#include <linux/sockios.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/mroute.h>
#include <linux/netdevice.h>
#include <linux/in_route.h>
#include <linux/route.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/dst.h>
#include <net/sock.h>
#include <linux/gfp.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/snmp.h>
#include <net/tcp_states.h>
#include <net/inet_common.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

struct hlist_head raw_v4_htable[RAWV4_HTABLE_SIZE];
DEFINE_RWLOCK(raw_v4_lock);

static void raw_v4_hash(struct sock *sk)
{
	struct hlist_head *head = &raw_v4_htable[inet_sk(sk)->num &
						 (RAWV4_HTABLE_SIZE - 1)];

	write_lock_bh(&raw_v4_lock);
	sk_add_node(sk, head);
	sock_prot_inc_use(sk->sk_prot);
	write_unlock_bh(&raw_v4_lock);
}

static void raw_v4_unhash(struct sock *sk)
{
	write_lock_bh(&raw_v4_lock);
	if (sk_del_node_init(sk))
		sock_prot_dec_use(sk->sk_prot);
	write_unlock_bh(&raw_v4_lock);
}

struct sock *__raw_v4_lookup(struct sock *sk, unsigned short num,
			     __be32 raddr, __be32 laddr,
			     int dif)
{
	struct hlist_node *node;

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

		if (inet->num == num 					&&
		    !(inet->daddr && inet->daddr != raddr) 		&&
		    !(inet->rcv_saddr && inet->rcv_saddr != laddr)	&&
		    !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
			goto found; /* gotcha */
	}
	sk = NULL;
found:
	return sk;
}

/*
 *	0 - deliver
 *	1 - block
 */
static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb)
{
	int type;

	if (!pskb_may_pull(skb, sizeof(struct icmphdr)))
		return 1;

	type = icmp_hdr(skb)->type;
	if (type < 32) {
		__u32 data = raw_sk(sk)->filter.data;

		return ((1 << type) & data) != 0;
	}

	/* Do not block unknown ICMP types */
	return 0;
}

/* IP input processing comes here for RAW socket delivery.
 * Caller owns SKB, so we must make clones.
 *
 * RFC 1122: SHOULD pass TOS value up to the transport layer.
 * -> It does. And not only TOS, but all IP header.
 */
int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
{
	struct sock *sk;
	struct hlist_head *head;
	int delivered = 0;

	read_lock(&raw_v4_lock);
	head = &raw_v4_htable[hash];
	if (hlist_empty(head))
		goto out;
	sk = __raw_v4_lookup(__sk_head(head), iph->protocol,
			     iph->saddr, iph->daddr,
			     skb->dev->ifindex);

	while (sk) {
		delivered = 1;
		if (iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) {
			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);

			/* Not releasing hash table! */
			if (clone)
				raw_rcv(sk, clone);
		}
		sk = __raw_v4_lookup(sk_next(sk), iph->protocol,
				     iph->saddr, iph->daddr,
				     skb->dev->ifindex);
	}
out:
	read_unlock(&raw_v4_lock);
	return delivered;
}

void raw_err (struct sock *sk, struct sk_buff *skb, u32 info)
{
	struct inet_sock *inet = inet_sk(sk);
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	int err = 0;
	int harderr = 0;

	/* Report error on raw socket, if:
	   1. User requested ip_recverr.
	   2. Socket is connected (otherwise the error indication
	      is useless without ip_recverr and error is hard.
	 */
	if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED)
		return;

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

	if (inet->recverr) {
		struct iphdr *iph = (struct iphdr*)skb->data;
		u8 *payload = skb->data + (iph->ihl << 2);

		if (inet->hdrincl)
			payload = skb->data;
		ip_icmp_error(sk, skb, err, 0, info, payload);
	}

	if (inet->recverr || harderr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	}
}

static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
{
	/* Charge it to the socket. */

	if (sock_queue_rcv_skb(sk, skb) < 0) {
		/* FIXME: increment a raw drops counter here */
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	return NET_RX_SUCCESS;
}

int raw_rcv(struct sock *sk, struct sk_buff *skb)
{
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
		kfree_skb(skb);
		return NET_RX_DROP;
	}
	nf_reset(skb);

	skb_push(skb, skb->data - skb_network_header(skb));

	raw_rcv_skb(sk, skb);
	return 0;
}

static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
			struct rtable *rt,
			unsigned int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	int hh_len;
	struct iphdr *iph;
	struct sk_buff *skb;
	unsigned int iphlen;
	int err;

	if (length > rt->u.dst.dev->mtu) {
		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport,
			       rt->u.dst.dev->mtu);
		return -EMSGSIZE;
	}
	if (flags&MSG_PROBE)
		goto out;

	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);

	skb = sock_alloc_send_skb(sk, length+hh_len+15,
				  flags&MSG_DONTWAIT, &err);
	if (skb == NULL)
		goto error;
	skb_reserve(skb, hh_len);

	skb->priority = sk->sk_priority;
	skb->dst = dst_clone(&rt->u.dst);

	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	skb_put(skb, length);

	skb->ip_summed = CHECKSUM_NONE;

	skb->transport_header = skb->network_header;
	err = memcpy_fromiovecend((void *)iph, from, 0, length);
	if (err)
		goto error_fault;

	/* We don't modify invalid header */
	iphlen = iph->ihl * 4;
	if (iphlen >= sizeof(*iph) && iphlen <= length) {
		if (!iph->saddr)
			iph->saddr = rt->rt_src;
		iph->check   = 0;
		iph->tot_len = htons(length);
		if (!iph->id)
			ip_select_ident(iph, &rt->u.dst, NULL);

		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
	}
	if (iph->protocol == IPPROTO_ICMP)
		icmp_out_count(((struct icmphdr *)
			skb_transport_header(skb))->type);

	err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
		      dst_output);
	if (err > 0)
		err = inet->recverr ? net_xmit_errno(err) : 0;
	if (err)
		goto error;
out:
	return 0;

error_fault:
	err = -EFAULT;
	kfree_skb(skb);
error:
	IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
	return err;
}

static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
{
	struct iovec *iov;
	u8 __user *type = NULL;
	u8 __user *code = NULL;
	int probed = 0;
	unsigned int i;

	if (!msg->msg_iov)
		return 0;

	for (i = 0; i < msg->msg_iovlen; i++) {
		iov = &msg->msg_iov[i];
		if (!iov)
			continue;

		switch (fl->proto) {
		case IPPROTO_ICMP:
			/* check if one-byte field is readable or not. */
			if (iov->iov_base && iov->iov_len < 1)
				break;

			if (!type) {
				type = iov->iov_base;
				/* check if code field is readable or not. */
				if (iov->iov_len > 1)
					code = type + 1;
			} else if (!code)
				code = iov->iov_base;

			if (type && code) {
				if (get_user(fl->fl_icmp_type, type) ||
				    get_user(fl->fl_icmp_code, code))
					return -EFAULT;
				probed = 1;
			}
			break;
		default:
			probed = 1;
			break;
		}
		if (probed)
			break;
	}
	return 0;
}

static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		       size_t len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipcm_cookie ipc;
	struct rtable *rt = NULL;
	int free = 0;
	__be32 daddr;
	__be32 saddr;
	u8  tos;
	int err;

	err = -EMSGSIZE;
	if (len > 0xFFFF)
		goto out;

	/*
	 *	Check the flags.
	 */

	err = -EOPNOTSUPP;
	if (msg->msg_flags & MSG_OOB)	/* Mirror BSD error message */
		goto out;               /* compatibility */

	/*
	 *	Get and verify the address.
	 */

	if (msg->msg_namelen) {
		struct sockaddr_in *usin = (struct sockaddr_in*)msg->msg_name;
		err = -EINVAL;
		if (msg->msg_namelen < sizeof(*usin))
			goto out;
		if (usin->sin_family != AF_INET) {
			static int complained;
			if (!complained++)
				printk(KERN_INFO "%s forgot to set AF_INET in "
						 "raw sendmsg. Fix it!\n",
						 current->comm);
			err = -EAFNOSUPPORT;
			if (usin->sin_family)
				goto out;
		}
		daddr = usin->sin_addr.s_addr;
		/* ANK: I did not forget to get protocol from port field.
		 * I just do not know, who uses this weirdness.
		 * IP_HDRINCL is much more convenient.
		 */
	} else {
		err = -EDESTADDRREQ;
		if (sk->sk_state != TCP_ESTABLISHED)
			goto out;
		daddr = inet->daddr;
	}

	ipc.addr = inet->saddr;
	ipc.opt = NULL;
	ipc.oif = sk->sk_bound_dev_if;

	if (msg->msg_controllen) {
		err = ip_cmsg_send(msg, &ipc);
		if (err)
			goto out;
		if (ipc.opt)
			free = 1;
	}

	saddr = ipc.addr;
	ipc.addr = daddr;

	if (!ipc.opt)
		ipc.opt = inet->opt;

	if (ipc.opt) {
		err = -EINVAL;
		/* Linux does not mangle headers on raw sockets,
		 * so that IP options + IP_HDRINCL is non-sense.
		 */
		if (inet->hdrincl)
			goto done;
		if (ipc.opt->srr) {