summaryrefslogtreecommitdiff
path: root/net/ipv4/ipcomp.c
blob: 1f13cc507a47fc8ed2805ae65a1f9c47f9f1f489 (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
/*
 * IP Payload Compression Protocol (IPComp) - RFC3173.
 *
 * Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
 *
 * 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.
 *
 * Todo:
 *   - Tunable compression parameters.
 *   - Compression stats.
 *   - Adaptive compression.
 */
#include <linux/module.h>
#include <asm/scatterlist.h>
#include <asm/semaphore.h>
#include <linux/crypto.h>
#include <linux/pfkeyv2.h>
#include <linux/percpu.h>
#include <linux/smp.h>
#include <linux/list.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
#include <linux/mutex.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/icmp.h>
#include <net/ipcomp.h>
#include <net/protocol.h>

struct ipcomp_tfms {
	struct list_head list;
	struct crypto_comp **tfms;
	int users;
};

static DEFINE_MUTEX(ipcomp_resource_mutex);
static void **ipcomp_scratches;
static int ipcomp_scratch_users;
static LIST_HEAD(ipcomp_tfms_list);

static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
{
	struct ipcomp_data *ipcd = x->data;
	const int plen = skb->len;
	int dlen = IPCOMP_SCRATCH_SIZE;
	const u8 *start = skb->data;
	const int cpu = get_cpu();
	u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu);
	struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu);
	int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen);

	if (err)
		goto out;

	if (dlen < (plen + sizeof(struct ip_comp_hdr))) {
		err = -EINVAL;
		goto out;
	}

	err = pskb_expand_head(skb, 0, dlen - plen, GFP_ATOMIC);
	if (err)
		goto out;

	skb->truesize += dlen - plen;
	__skb_put(skb, dlen - plen);
	memcpy(skb->data, scratch, dlen);
out:
	put_cpu();
	return err;
}

static int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb)
{
	int err = -ENOMEM;
	struct iphdr *iph;
	struct ip_comp_hdr *ipch;

	if (skb_linearize_cow(skb))
		goto out;

	skb->ip_summed = CHECKSUM_NONE;

	/* Remove ipcomp header and decompress original payload */
	iph = ip_hdr(skb);
	ipch = (void *)skb->data;
	iph->protocol = ipch->nexthdr;
	skb->h.raw = skb->nh.raw + sizeof(*ipch);
	__skb_pull(skb, sizeof(*ipch));
	err = ipcomp_decompress(x, skb);

out:
	return err;
}

static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb)
{
	struct ipcomp_data *ipcd = x->data;
	const int ihlen = ip_hdrlen(skb);
	const int plen = skb->len - ihlen;
	int dlen = IPCOMP_SCRATCH_SIZE;
	u8 *start = skb->data + ihlen;
	const int cpu = get_cpu();
	u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu);
	struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu);
	int err = crypto_comp_compress(tfm, start, plen, scratch, &dlen);

	if (err)
		goto out;

	if ((dlen + sizeof(struct ip_comp_hdr)) >= plen) {
		err = -EMSGSIZE;
		goto out;
	}

	memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen);
	put_cpu();

	pskb_trim(skb, ihlen + dlen + sizeof(struct ip_comp_hdr));
	return 0;

out:
	put_cpu();
	return err;
}

static int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb)
{
	int err;
	struct ip_comp_hdr *ipch;
	struct ipcomp_data *ipcd = x->data;
	int hdr_len = 0;
	struct iphdr *iph = ip_hdr(skb);

	iph->tot_len = htons(skb->len);
	hdr_len = iph->ihl * 4;
	if ((skb->len - hdr_len) < ipcd->threshold) {
		/* Don't bother compressing */
		goto out_ok;
	}

	if (skb_linearize_cow(skb))
		goto out_ok;

	err = ipcomp_compress(x, skb);
	iph = ip_hdr(skb);

	if (err) {
		goto out_ok;
	}

	/* Install ipcomp header, convert into ipcomp datagram. */
	iph->tot_len = htons(skb->len);
	ipch = (struct ip_comp_hdr *)((char *)iph + iph->ihl * 4);
	ipch->nexthdr = iph->protocol;
	ipch->flags = 0;
	ipch->cpi = htons((u16 )ntohl(x->id.spi));
	iph->protocol = IPPROTO_COMP;
	ip_send_check(iph);
	return 0;

out_ok:
	if (x->props.mode == XFRM_MODE_TUNNEL)
		ip_send_check(iph);
	return 0;
}

static void ipcomp4_err(struct sk_buff *skb, u32 info)
{
	__be32 spi;
	struct iphdr *iph = (struct iphdr *)skb->data;
	struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
	struct xfrm_state *x;

	if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH ||
	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
		return;

	spi = htonl(ntohs(ipch->cpi));
	x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr,
			      spi, IPPROTO_COMP, AF_INET);
	if (!x)
		return;
	NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%u.%u.%u.%u\n",
		 spi, NIPQUAD(iph->daddr));
	xfrm_state_put(x);
}

/* We always hold one tunnel user reference to indicate a tunnel */
static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
{
	struct xfrm_state *t;
	u8 mode = XFRM_MODE_TUNNEL;

	t = xfrm_state_alloc();
	if (t == NULL)
		goto out;

	t->id.proto = IPPROTO_IPIP;
	t->id.spi = x->props.saddr.a4;
	t->id.daddr.a4 = x->id.daddr.a4;
	memcpy(&t->sel, &x->sel, sizeof(t->sel));
	t->props.family = AF_INET;
	if (x->props.mode == XFRM_MODE_BEET)
		mode = x->props.mode;
	t->props.mode = mode;
	t->props.saddr.a4 = x->props.saddr.a4;
	t->props.flags = x->props.flags;

	if (xfrm_init_state(t))
		goto error;

	atomic_set(&t->tunnel_users, 1);
out:
	return t;

error:
	t->km.state = XFRM_STATE_DEAD;
	xfrm_state_put(t);
	t = NULL;
	goto out;
}

/*
 * Must be protected by xfrm_cfg_mutex.  State and tunnel user references are
 * always incremented on success.
 */
static int ipcomp_tunnel_attach(struct xfrm_state *x)
{
	int err = 0;
	struct xfrm_state *t;

	t = xfrm_state_lookup((xfrm_address_t *)&x->id.daddr.a4,
			      x->props.saddr.a4, IPPROTO_IPIP, AF_INET);
	if (!t) {
		t = ipcomp_tunnel_create(x);
		if (!t) {
			err = -EINVAL;
			goto out;
		}
		xfrm_state_insert(t);
		xfrm_state_hold(t);
	}
	x->tunnel = t;
	atomic_inc(&t->tunnel_users);
out:
	return err;
}

static void ipcomp_free_scratches(void)
{
	int i;
	void **scratches;

	if (--ipcomp_scratch_users)
		return;

	scratches = ipcomp_scratches;
	if (!scratches)
		return;

	for_each_possible_cpu(i)
		vfree(*per_cpu_ptr(scratches, i));

	free_percpu(scratches);
}

static void **ipcomp_alloc_scratches(void)
{
	int i;
	void **scratches;

	if (ipcomp_scratch_users++)
		return ipcomp_scratches;

	scratches = alloc_percpu(void *);
	if (!scratches)
		return NULL;

	ipcomp_scratches = scratches;

	for_each_possible_cpu(i) {
		void *scratch = vmalloc(IPCOMP_SCRATCH_SIZE);
		if (!scratch)
			return NULL;
		*per_cpu_ptr(scratches, i) = scratch;
	}

	return scratches;
}

static void ipcomp_free_tfms(struct crypto_comp **tfms)
{
	struct ipcomp_tfms *pos;
	int cpu;

	list_for_each_entry(pos, &ipcomp_tfms_list, list) {
		if (pos->tfms == tfms)
			break;
	}

	BUG_TRAP(pos);

	if (--pos->users)
		return;

	list_del(&pos->list);
	kfree(pos);

	if (!tfms)
		return;

	for_each_possible_cpu(cpu) {
		struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu);
		crypto_free_comp(tfm);
	}
	free_percpu(tfms);
}

static struct crypto_comp **ipcomp_alloc_tfms(const char *alg_name)
{
	struct ipcomp_tfms *pos;
	struct crypto_comp **tfms;
	int cpu;

	/* This can be any valid CPU ID so we don't need locking. */
	cpu = raw_smp_processor_id();

	list_for_each_entry(pos, &ipcomp_tfms_list, list) {
		struct crypto_comp *tfm;

		tfms = pos->tfms;
		tfm = *per_cpu_ptr(tfms, cpu);

		if (!strcmp(crypto_comp_name(tfm), alg_name)) {
			pos->users++;
			return tfms;
		}
	}

	pos = kmalloc(sizeof(*pos), GFP_KERNEL);
	if (!pos)
		return NULL;

	pos->users = 1;
	INIT_LIST_HEAD(&pos->list);
	list_add(&pos->list, &ipcomp_tfms_list);

	pos->tfms = tfms = alloc_percpu(struct crypto_comp *);
	if (!tfms)
		goto error;

	for_each_possible_cpu(cpu) {
		struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0,
							    CRYPTO_ALG_ASYNC);
		if (!tfm)
			goto error;
		*per_cpu_ptr(tfms, cpu) = tfm;
	}

	return tfms;

error:
	ipcomp_free_tfms(tfms);
	return NULL;
}

static void ipcomp_free_data(struct ipcomp_data *ipcd)
{
	if (ipcd->tfms)
		ipcomp_free_tfms(ipcd->tfms);
	ipcomp_free_scratches();
}

static void ipcomp_destroy(struct xfrm_state *x)
{
	struct ipcomp_data *ipcd = x->data;
	if (!ipcd)
		return;
	xfrm_state_delete_tunnel(x);
	mutex_lock(&ipcomp_resource_mutex);
	ipcomp_free_data(ipcd);
	mutex_unlock(&ipcomp_resource_mutex);
	kfree(ipcd);
}

static int ipcomp_init_state(struct xfrm_state *x)
{
	int err;
	struct ipcomp_data *ipcd;
	struct xfrm_algo_desc *calg_desc;

	err = -EINVAL;
	if (!x->calg)
		goto out;

	if (x->encap)
		goto out;

	err = -ENOMEM;
	ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL);
	if (!ipcd)
		goto out;

	x->props.header_len = 0;
	if (x->props.mode == XFRM_MODE_TUNNEL)
		x->props.header_len += sizeof(struct iphdr);

	mutex_lock(&ipcomp_resource_mutex);
	if (!ipcomp_alloc_scratches())
		goto error;

	ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name);
	if (!ipcd->tfms)
		goto error;
	mutex_unlock(&ipcomp_resource_mutex);

	if (x->props.mode == XFRM_MODE_TUNNEL) {
		err = ipcomp_tunnel_attach(x);
		if (err)
			goto error_tunnel;
	}

	calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0);
	BUG_ON(!calg_desc);
	ipcd->threshold = calg_desc->uinfo.comp.threshold;
	x->data = ipcd;
	err = 0;
out:
	return err;

error_tunnel:
	mutex_lock(&ipcomp_resource_mutex);
error:
	ipcomp_free_data(ipcd);
	mutex_unlock(&ipcomp_resource_mutex);
	kfree(ipcd);
	goto out;
}

static struct xfrm_type ipcomp_type = {
	.description	= "IPCOMP4",
	.owner		= THIS_MODULE,
	.proto	     	= IPPROTO_COMP,
	.init_state	= ipcomp_init_state,
	.destructor	= ipcomp_destroy,
	.input		= ipcomp_input,
	.output		= ipcomp_output
};

static struct net_protocol ipcomp4_protocol = {
	.handler	=	xfrm4_rcv,
	.err_handler	=	ipcomp4_err,
	.no_policy	=	1,
};

static int __init ipcomp4_init(void)
{
	if (xfrm_register_type(&ipcomp_type, AF_INET) < 0) {
		printk(KERN_INFO "ipcomp init: can't add xfrm type\n");
		return -EAGAIN;
	}
	if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) {
		printk(KERN_INFO "ipcomp init: can't add protocol\n");
		xfrm_unregister_type(&ipcomp_type, AF_INET);
		return -EAGAIN;
	}
	return 0;
}

static void __exit ipcomp4_fini(void)
{
	if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0)
		printk(KERN_INFO "ip ipcomp close: can't remove protocol\n");
	if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0)
		printk(KERN_INFO "ip ipcomp close: can't remove xfrm type\n");
}

module_init(ipcomp4_init);
module_exit(ipcomp4_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");