summaryrefslogtreecommitdiffstats
path: root/net/ipv4/raw.c
blob: b3644f10dd156be619643059d793ca6178a66ff7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
/*
 * 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 1.3 1997/12/16 05:37:44 ralf Exp $
 *
 * Authors:	Ross Biro, <bir7@leland.Stanford.Edu>
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * 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/config.h> 
#include <asm/system.h>
#include <asm/uaccess.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/mroute.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/checksum.h>

#ifdef CONFIG_IP_MROUTE
struct sock *mroute_socket=NULL;
#endif

struct sock *raw_v4_htable[RAWV4_HTABLE_SIZE];

static void raw_v4_hash(struct sock *sk)
{
	struct sock **skp;
	int num = sk->num;

	num &= (RAWV4_HTABLE_SIZE - 1);
	skp = &raw_v4_htable[num];
	SOCKHASH_LOCK();
	sk->next = *skp;
	*skp = sk;
	sk->hashent = num;
	SOCKHASH_UNLOCK();
}

static void raw_v4_unhash(struct sock *sk)
{
	struct sock **skp;
	int num = sk->num;

	num &= (RAWV4_HTABLE_SIZE - 1);
	skp = &raw_v4_htable[num];

	SOCKHASH_LOCK();
	while(*skp != NULL) {
		if(*skp == sk) {
			*skp = sk->next;
			break;
		}
		skp = &((*skp)->next);
	}
	SOCKHASH_UNLOCK();
}

static void raw_v4_rehash(struct sock *sk)
{
	struct sock **skp;
	int num = sk->num;
	int oldnum = sk->hashent;

	num &= (RAWV4_HTABLE_SIZE - 1);
	skp = &raw_v4_htable[oldnum];

	SOCKHASH_LOCK();
	while(*skp != NULL) {
		if(*skp == sk) {
			*skp = sk->next;
			break;
		}
		skp = &((*skp)->next);
	}
	sk->next = raw_v4_htable[num];
	raw_v4_htable[num] = sk;
	sk->hashent = num;
	SOCKHASH_UNLOCK();
}

/* Grumble... icmp and ip_input want to get at this... */
struct sock *raw_v4_lookup(struct sock *sk, unsigned short num,
			   unsigned long raddr, unsigned long laddr, int dif)
{
	struct sock *s = sk;

	SOCKHASH_LOCK();
	for(s = sk; s; s = s->next) {
		if((s->num == num) 				&&
		   !(s->dead && (s->state == TCP_CLOSE))	&&
		   !(s->daddr && s->daddr != raddr) 		&&
		   !(s->rcv_saddr && s->rcv_saddr != laddr)	&&
		   !(s->bound_dev_if && s->bound_dev_if != dif))
			break; /* gotcha */
	}
	SOCKHASH_UNLOCK();
	return s;
}

/*
 *	Raw_err does not currently get called by the icmp module - FIXME:
 */
 
void raw_err (struct sock *sk, struct sk_buff *skb)
{
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;

	if (sk->ip_recverr && !sk->sock_readers) {
		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
		if (skb2 && sock_queue_err_skb(sk, skb2))
			kfree_skb(skb);
	}

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
		if (sk->ip_pmtudisc != IP_PMTUDISC_DONT) {
			sk->err = EMSGSIZE;
			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)
	{
		ip_statistics.IpInDiscards++;
		kfree_skb(skb);
		return -1;
	}

	ip_statistics.IpInDelivers++;
	return 0;
}

/*
 *	This should be the easiest of all, all we do is
 *	copy it into a buffer. All demultiplexing is done
 *	in ip.c
 */

int raw_rcv(struct sock *sk, struct sk_buff *skb)
{
	/* Now we need to copy this into memory. */
	skb_trim(skb, ntohs(skb->nh.iph->tot_len));
	
	skb->h.raw = skb->nh.raw;

	if (sk->sock_readers) {
		__skb_queue_tail(&sk->back_log, skb);
		return 0;
	}
	raw_rcv_skb(sk, skb);
	return 0;
}

struct rawfakehdr 
{
	struct  iovec *iov;
	u32	saddr;
};

/*
 *	Send a RAW IP packet.
 */

/*
 *	Callback support is trivial for SOCK_RAW
 */
  
static int raw_getfrag(const void *p, char *to, unsigned int offset, unsigned int fraglen)
{
	struct rawfakehdr *rfh = (struct rawfakehdr *) p;
	return memcpy_fromiovecend(to, rfh->iov, offset, fraglen);
}

/*
 *	IPPROTO_RAW needs extra work.
 */
 
static int raw_getrawfrag(const void *p, char *to, unsigned int offset, unsigned int fraglen)
{
	struct rawfakehdr *rfh = (struct rawfakehdr *) p;

	if (memcpy_fromiovecend(to, rfh->iov, offset, fraglen))
		return -EFAULT;

	if (offset==0) {
		struct iphdr *iph = (struct iphdr *)to;
		if (!iph->saddr)
			iph->saddr = rfh->saddr;
		iph->check=0;
		iph->tot_len=htons(fraglen);	/* This is right as you can't frag
						   RAW packets */
		/*
	 	 *	Deliberate breach of modularity to keep 
	 	 *	ip_build_xmit clean (well less messy).
		 */
		if (!iph->id)
			iph->id = htons(ip_id_count++);
		iph->check=ip_fast_csum((unsigned char *)iph, iph->ihl);
	}
	return 0;
}

static int raw_sendmsg(struct sock *sk, struct msghdr *msg, int len)
{
	struct ipcm_cookie ipc;
	struct rawfakehdr rfh;
	struct rtable *rt = NULL;
	int free = 0;
	u32 daddr;
	u8  tos;
	int err;

	/* This check is ONLY to check for arithmetic overflow
	   on integer(!) len. Not more! Real check will be made
	   in ip_build_xmit --ANK

	   BTW socket.c -> af_*.c -> ... make multiple
	   invalid conversions size_t -> int. We MUST repair it f.e.
	   by replacing all of them with size_t and revise all
	   the places sort of len += sizeof(struct iphdr)
	   If len was ULONG_MAX-10 it would be cathastrophe  --ANK
	 */

	if (len < 0 || len > 0xFFFF)
		return -EMSGSIZE;

	/*
	 *	Check the flags.
	 */

	if (msg->msg_flags & MSG_OOB)		/* Mirror BSD error message compatibility */
		return -EOPNOTSUPP;
			 
	if (msg->msg_flags & ~(MSG_DONTROUTE|MSG_DONTWAIT))
		return(-EINVAL);

	/*
	 *	Get and verify the address. 
	 */

	if (msg->msg_namelen) {
		struct sockaddr_in *usin = (struct sockaddr_in*)msg->msg_name;
		if (msg->msg_namelen < sizeof(*usin))
			return(-EINVAL);
		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);
			if (usin->sin_family)
				return -EINVAL;
		}
		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 {
		if (sk->state != TCP_ESTABLISHED) 
			return(-EINVAL);
		daddr = sk->daddr;
	}

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

	if (msg->msg_controllen) {
		int tmp = ip_cmsg_send(msg, &ipc);
		if (tmp)
			return tmp;
		if (ipc.opt)
			free=1;
	}

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

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

	if (ipc.opt) {
		err = -EINVAL;
		/* Linux does not mangle headers on raw sockets,
		 * so that IP options + IP_HDRINCL is non-sense.
		 */
		if (sk->ip_hdrincl)
			goto done;
		if (ipc.opt->srr) {
			if (!daddr)
				goto done;
			daddr = ipc.opt->faddr;
		}
	}
	tos = RT_TOS(sk->ip_tos) | sk->localroute;
	if (msg->msg_flags&MSG_DONTROUTE)
		tos |= RTO_ONLINK;

	if (MULTICAST(daddr)) {
		if (!ipc.oif)
			ipc.oif = sk->ip_mc_index;
		if (!rfh.saddr)
			rfh.saddr = sk->ip_mc_addr;
	}

	err = ip_route_output(&rt, daddr, rfh.saddr, tos, ipc.oif);

	if (err)
		goto done;

	err = -EACCES;
	if (rt->rt_flags&RTCF_BROADCAST && !sk->broadcast)
		goto done;

	rfh.iov = msg->msg_iov;
	rfh.saddr = rt->rt_src;
	if (!ipc.addr)
		ipc.addr = rt->rt_dst;
	err=ip_build_xmit(sk, sk->ip_hdrincl ? raw_getrawfrag : raw_getfrag,
			  &rfh, len, &ipc, rt, msg->msg_flags);

done:
	if (free)
		kfree(ipc.opt);
	ip_rt_put(rt);

	return err<0 ? err : len;
}

static void raw_close(struct sock *sk, unsigned long timeout)
{
	sk->state = TCP_CLOSE;
	ip_ra_control(sk, 0, NULL);
	sk->dead=1;
	destroy_sock(sk);
}

/* This gets rid of all the nasties in af_inet. -DaveM */
static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
	int chk_addr_ret;

	if((sk->state != TCP_CLOSE) || (addr_len < sizeof(struct sockaddr_in)))
		return -EINVAL;
	chk_addr_ret = inet_addr_type(addr->sin_addr.s_addr);
	if(addr->sin_addr.s_addr != 0 && chk_addr_ret != RTN_LOCAL &&
	   chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) {
#ifdef CONFIG_IP_TRANSPARENT_PROXY
		/* Superuser may bind to any address to allow transparent proxying. */
		if(chk_addr_ret != RTN_UNICAST || !suser())
#endif
			return -EADDRNOTAVAIL;
	}
	sk->rcv_saddr = sk->saddr = addr->sin_addr.s_addr;
	if(chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		sk->saddr = 0;  /* Use device */
	dst_release(xchg(&sk->dst_cache, NULL));
	return 0;
}

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

int raw_recvmsg(struct sock *sk, struct msghdr *msg, int len,
		int noblock, int flags,int *addr_len)
{
	int copied=0;
	struct sk_buff *skb;
	int err;
	struct sockaddr_in *sin=(struct sockaddr_in *)msg->msg_name;

	if (flags & MSG_OOB)
		return -EOPNOTSUPP;
		
	if (sk->shutdown & RCV_SHUTDOWN) 
		return(0);

	if (addr_len)
		*addr_len=sizeof(*sin);

	if (sk->ip_recverr && (skb = skb_dequeue(&sk->error_queue)) != NULL) {
		err = sock_error(sk);
		if (msg->msg_controllen == 0) {
			skb_free_datagram(sk, skb);
			return err;
		}
		put_cmsg(msg, SOL_IP, IP_RECVERR, skb->len, skb->data);
		skb_free_datagram(sk, skb);
		return 0;
	}

	skb=skb_recv_datagram(sk,flags,noblock,&err);
	if(skb==NULL)
 		return err;

	copied = skb->len;
	if (len < copied)
	{
		msg->msg_flags |= MSG_TRUNC;
		copied = len;
	}
	
	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	if (err)
		goto done;

	sk->stamp=skb->stamp;

	/* Copy the address. */
	if (sin) {
		sin->sin_family = AF_INET;
		sin->sin_addr.s_addr = skb->nh.iph->saddr;
	}
	if (sk->ip_cmsg_flags)
		ip_cmsg_recv(msg, skb);
done:
	skb_free_datagram(sk, skb);
	return (err ? : copied);
}

static int raw_init(struct sock *sk)
{
	struct raw_opt *tp = &(sk->tp_pinfo.tp_raw4);
	if (sk->num == IPPROTO_ICMP) {
		memset(&tp->filter, 0, sizeof(tp->filter));

		/* By default block ECHO and TIMESTAMP requests */

		set_bit(ICMP_ECHO, &tp->filter);
		set_bit(ICMP_TIMESTAMP, &tp->filter);
	}
	return 0;
}

static int raw_seticmpfilter(struct sock *sk, char *optval, int optlen)
{
	if (optlen > sizeof(struct icmp_filter))
		optlen = sizeof(struct icmp_filter);
	if (copy_from_user(&sk->tp_pinfo.tp_raw4.filter, optval, optlen))
		return -EFAULT;
	return 0;
}

static int raw_geticmpfilter(struct sock *sk, char *optval, int *optlen)
{
	int len;

	if (get_user(len,optlen))
		return -EFAULT;
	if (len > sizeof(struct icmp_filter))
		len = sizeof(struct icmp_filter);
	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &sk->tp_pinfo.tp_raw4.filter, len))
		return -EFAULT;
	return 0;
}

static int raw_setsockopt(struct sock *sk, int level, int optname, 
			  char *optval, int optlen)
{
	if (level != SOL_RAW)
		return ip_setsockopt(sk, level, optname, optval, optlen);

	switch (optname) {
	case ICMP_FILTER:
		if (sk->num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		return raw_seticmpfilter(sk, optval, optlen);
	};

	return -ENOPROTOOPT;
}

static int raw_getsockopt(struct sock *sk, int level, int optname, 
			  char *optval, int *optlen)
{
	if (level != SOL_RAW)
		return ip_getsockopt(sk, level, optname, optval, optlen);

	switch (optname) {
	case ICMP_FILTER:
		if (sk->num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		return raw_geticmpfilter(sk, optval, optlen);
	};

	return -ENOPROTOOPT;
}

struct proto raw_prot = {
	(struct sock *)&raw_prot,	/* sklist_next */
	(struct sock *)&raw_prot,	/* sklist_prev */
	raw_close,			/* close */
	udp_connect,			/* connect */
	NULL,				/* accept */
	NULL,				/* retransmit */
	NULL,				/* write_wakeup */
	NULL,				/* read_wakeup */
	datagram_poll,			/* poll */
#ifdef CONFIG_IP_MROUTE
	ipmr_ioctl,			/* ioctl */
#else
	NULL,				/* ioctl */
#endif
	raw_init,			/* init */
	NULL,				/* destroy */
	NULL,				/* shutdown */
	raw_setsockopt,			/* setsockopt */
	raw_getsockopt,			/* getsockopt */
	raw_sendmsg,			/* sendmsg */
	raw_recvmsg,			/* recvmsg */
	raw_bind,			/* bind */
	raw_rcv_skb,			/* backlog_rcv */
	raw_v4_hash,			/* hash */
	raw_v4_unhash,			/* unhash */
	raw_v4_rehash,			/* rehash */
	NULL,				/* good_socknum */
	NULL,				/* verify_bind */
	128,				/* max_header */
	0,				/* retransmits */
	"RAW",				/* name */
	0,				/* inuse */
	0				/* highestinuse */
};