summaryrefslogtreecommitdiff
path: root/net/ipv4/inet_fragment.c
blob: a5ec5d9567931d03cfa3fbe1a370857ed8dc3b3d (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
/*
 * inet fragments management
 *
 *		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.
 *
 * 		Authors:	Pavel Emelyanov <xemul@openvz.org>
 *				Started as consolidation of ipv4/ip_fragment.c,
 *				ipv6/reassembly. and ipv6 nf conntrack reassembly
 */

#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/random.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <linux/rhashtable.h>

#include <net/sock.h>
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/ipv6.h>

/* Use skb->cb to track consecutive/adjacent fragments coming at
 * the end of the queue. Nodes in the rb-tree queue will
 * contain "runs" of one or more adjacent fragments.
 *
 * Invariants:
 * - next_frag is NULL at the tail of a "run";
 * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
 */
struct ipfrag_skb_cb {
	union {
		struct inet_skb_parm	h4;
		struct inet6_skb_parm	h6;
	};
	struct sk_buff		*next_frag;
	int			frag_run_len;
};

#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))

static void fragcb_clear(struct sk_buff *skb)
{
	RB_CLEAR_NODE(&skb->rbnode);
	FRAG_CB(skb)->next_frag = NULL;
	FRAG_CB(skb)->frag_run_len = skb->len;
}

/* Append skb to the last "run". */
static void fragrun_append_to_last(struct inet_frag_queue *q,
				   struct sk_buff *skb)
{
	fragcb_clear(skb);

	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
	FRAG_CB(q->fragments_tail)->next_frag = skb;
	q->fragments_tail = skb;
}

/* Create a new "run" with the skb. */
static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb)
{
	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
	fragcb_clear(skb);

	if (q->last_run_head)
		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
			     &q->last_run_head->rbnode.rb_right);
	else
		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
	rb_insert_color(&skb->rbnode, &q->rb_fragments);

	q->fragments_tail = skb;
	q->last_run_head = skb;
}

/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
 * Value : 0xff if frame should be dropped.
 *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
 */
const u8 ip_frag_ecn_table[16] = {
	/* at least one fragment had CE, and others ECT_0 or ECT_1 */
	[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0]			= INET_ECN_CE,
	[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1]			= INET_ECN_CE,
	[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1]	= INET_ECN_CE,

	/* invalid combinations : drop frame */
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
};
EXPORT_SYMBOL(ip_frag_ecn_table);

int inet_frags_init(struct inet_frags *f)
{
	f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
					    NULL);
	if (!f->frags_cachep)
		return -ENOMEM;

	return 0;
}
EXPORT_SYMBOL(inet_frags_init);

void inet_frags_fini(struct inet_frags *f)
{
	/* We must wait that all inet_frag_destroy_rcu() have completed. */
	rcu_barrier();

	kmem_cache_destroy(f->frags_cachep);
	f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);

static void inet_frags_free_cb(void *ptr, void *arg)
{
	struct inet_frag_queue *fq = ptr;

	/* If we can not cancel the timer, it means this frag_queue
	 * is already disappearing, we have nothing to do.
	 * Otherwise, we own a refcount until the end of this function.
	 */
	if (!del_timer(&fq->timer))
		return;

	spin_lock_bh(&fq->lock);
	if (!(fq->flags & INET_FRAG_COMPLETE)) {
		fq->flags |= INET_FRAG_COMPLETE;
		refcount_dec(&fq->refcnt);
	}
	spin_unlock_bh(&fq->lock);

	inet_frag_put(fq);
}

void fqdir_exit(struct fqdir *fqdir)
{
	fqdir->high_thresh = 0; /* prevent creation of new frags */

	rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
}
EXPORT_SYMBOL(fqdir_exit);

void inet_frag_kill(struct inet_frag_queue *fq)
{
	if (del_timer(&fq->timer))
		refcount_dec(&fq->refcnt);

	if (!(fq->flags & INET_FRAG_COMPLETE)) {
		struct fqdir *fqdir = fq->fqdir;

		fq->flags |= INET_FRAG_COMPLETE;
		rhashtable_remove_fast(&fqdir->rhashtable, &fq->node, fqdir->f->rhash_params);
		refcount_dec(&fq->refcnt);
	}
}
EXPORT_SYMBOL(inet_frag_kill);

static void inet_frag_destroy_rcu(struct rcu_head *head)
{
	struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
						 rcu);
	struct inet_frags *f = q->fqdir->f;

	if (f->destructor)
		f->destructor(q);
	kmem_cache_free(f->frags_cachep, q);
}

unsigned int inet_frag_rbtree_purge(struct rb_root *root)
{
	struct rb_node *p = rb_first(root);
	unsigned int sum = 0;

	while (p) {
		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);

		p = rb_next(p);
		rb_erase(&skb->rbnode, root);
		while (skb) {
			struct sk_buff *next = FRAG_CB(skb)->next_frag;

			sum += skb->truesize;
			kfree_skb(skb);
			skb = next;
		}
	}
	return sum;
}
EXPORT_SYMBOL(inet_frag_rbtree_purge);

void inet_frag_destroy(struct inet_frag_queue *q)
{
	struct fqdir *fqdir;
	unsigned int sum, sum_truesize = 0;
	struct inet_frags *f;

	WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
	WARN_ON(del_timer(&q->timer) != 0);

	/* Release all fragment data. */
	fqdir = q->fqdir;
	f = fqdir->f;
	sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments);
	sum = sum_truesize + f->qsize;

	call_rcu(&q->rcu, inet_frag_destroy_rcu);

	sub_frag_mem_limit(fqdir, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);

static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir,
					       struct inet_frags *f,
					       void *arg)
{
	struct inet_frag_queue *q;

	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
	if (!q)
		return NULL;

	q->fqdir = fqdir;
	f->constructor(q, arg);
	add_frag_mem_limit(fqdir, f->qsize);

	timer_setup(&q->timer, f->frag_expire, 0);
	spin_lock_init(&q->lock);
	refcount_set(&q->refcnt, 3);

	return q;
}

static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir,
						void *arg,
						struct inet_frag_queue **prev)
{
	struct inet_frags *f = fqdir->f;
	struct inet_frag_queue *q;

	q = inet_frag_alloc(fqdir, f, arg);
	if (!q) {
		*prev = ERR_PTR(-ENOMEM);
		return NULL;
	}
	mod_timer(&q->timer, jiffies + fqdir->timeout);

	*prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key,
						 &q->node, f->rhash_params);
	if (*prev) {
		q->flags |= INET_FRAG_COMPLETE;
		inet_frag_kill(q);
		inet_frag_destroy(q);
		return NULL;
	}
	return q;
}

/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key)
{
	struct inet_frag_queue *fq = NULL, *prev;

	if (!fqdir->high_thresh || frag_mem_limit(fqdir) > fqdir->high_thresh)
		return NULL;

	rcu_read_lock();

	prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params);
	if (!prev)
		fq = inet_frag_create(fqdir, key, &prev);
	if (prev && !IS_ERR(prev)) {
		fq = prev;
		if (!refcount_inc_not_zero(&fq->refcnt))
			fq = NULL;
	}
	rcu_read_unlock();
	return fq;
}
EXPORT_SYMBOL(inet_frag_find);

int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
			   int offset, int end)
{
	struct sk_buff *last = q->fragments_tail;

	/* RFC5722, Section 4, amended by Errata ID : 3089
	 *                          When reassembling an IPv6 datagram, if
	 *   one or more its constituent fragments is determined to be an
	 *   overlapping fragment, the entire datagram (and any constituent
	 *   fragments) MUST be silently discarded.
	 *
	 * Duplicates, however, should be ignored (i.e. skb dropped, but the
	 * queue/fragments kept for later reassembly).
	 */
	if (!last)
		fragrun_create(q, skb);  /* First fragment. */
	else if (last->ip_defrag_offset + last->len < end) {
		/* This is the common case: skb goes to the end. */
		/* Detect and discard overlaps. */
		if (offset < last->ip_defrag_offset + last->len)
			return IPFRAG_OVERLAP;
		if (offset == last->ip_defrag_offset + last->len)
			fragrun_append_to_last(q, skb);
		else
			fragrun_create(q, skb);
	} else {
		/* Binary search. Note that skb can become the first fragment,
		 * but not the last (covered above).
		 */
		struct rb_node **rbn, *parent;

		rbn = &q->rb_fragments.rb_node;
		do {
			struct sk_buff *curr;
			int curr_run_end;

			parent = *rbn;
			curr = rb_to_skb(parent);
			curr_run_end = curr->ip_defrag_offset +
					FRAG_CB(curr)->frag_run_len;
			if (end <= curr->ip_defrag_offset)
				rbn = &parent->rb_left;
			else if (offset >= curr_run_end)
				rbn = &parent->rb_right;
			else if (offset >= curr->ip_defrag_offset &&
				 end <= curr_run_end)
				return IPFRAG_DUP;
			else
				return IPFRAG_OVERLAP;
		} while (*rbn);
		/* Here we have parent properly set, and rbn pointing to
		 * one of its NULL left/right children. Insert skb.
		 */
		fragcb_clear(skb);
		rb_link_node(&skb->rbnode, parent, rbn);
		rb_insert_color(&skb->rbnode, &q->rb_fragments);
	}

	skb->ip_defrag_offset = offset;

	return IPFRAG_OK;
}
EXPORT_SYMBOL(inet_frag_queue_insert);

void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
			      struct sk_buff *parent)
{
	struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
	struct sk_buff **nextp;
	int delta;

	if (head != skb) {
		fp = skb_clone(skb, GFP_ATOMIC);
		if (!fp)
			return NULL;
		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
		if (RB_EMPTY_NODE(&skb->rbnode))
			FRAG_CB(parent)->next_frag = fp;
		else
			rb_replace_node(&skb->rbnode, &fp->rbnode,
					&q->rb_fragments);
		if (q->fragments_tail == skb)
			q->fragments_tail = fp;
		skb_morph(skb, head);
		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
		rb_replace_node(&head->rbnode, &skb->rbnode,
				&q->rb_fragments);
		consume_skb(head);
		head = skb;
	}
	WARN_ON(head->ip_defrag_offset != 0);

	delta = -head->truesize;

	/* Head of list must not be cloned. */
	if (skb_unclone(head, GFP_ATOMIC))
		return NULL;

	delta += head->truesize;
	if (delta)
		add_frag_mem_limit(q->fqdir, delta);

	/* If the first fragment is fragmented itself, we split
	 * it to two chunks: the first with data and paged part
	 * and the second, holding only fragments.
	 */
	if (skb_has_frag_list(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		clone = alloc_skb(0, GFP_ATOMIC);
		if (!clone)
			return NULL;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_frag_list_init(head);
		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
		clone->data_len = head->data_len - plen;
		clone->len = clone->data_len;
		head->truesize += clone->truesize;
		clone->csum = 0;
		clone->ip_summed = head->ip_summed;
		add_frag_mem_limit(q->fqdir, clone->truesize);
		skb_shinfo(head)->frag_list = clone;
		nextp = &clone->next;
	} else {
		nextp = &skb_shinfo(head)->frag_list;
	}

	return nextp;
}
EXPORT_SYMBOL(inet_frag_reasm_prepare);

void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
			    void *reasm_data)
{
	struct sk_buff **nextp = (struct sk_buff **)reasm_data;
	struct rb_node *rbn;
	struct sk_buff *fp;

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

	/* Traverse the tree in order, to build frag_list. */
	fp = FRAG_CB(head)->next_frag;
	rbn = rb_next(&head->rbnode);
	rb_erase(&head->rbnode, &q->rb_fragments);
	while (rbn || fp) {
		/* fp points to the next sk_buff in the current run;
		 * rbn points to the next run.
		 */
		/* Go through the current run. */
		while (fp) {
			*nextp = fp;
			nextp = &fp->next;
			fp->prev = NULL;
			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
			fp->sk = NULL;
			head->data_len += fp->len;
			head->len += fp->len;
			if (head->ip_summed != fp->ip_summed)
				head->ip_summed = CHECKSUM_NONE;
			else if (head->ip_summed == CHECKSUM_COMPLETE)
				head->csum = csum_add(head->csum, fp->csum);
			head->truesize += fp->truesize;
			fp = FRAG_CB(fp)->next_frag;
		}
		/* Move to the next run. */
		if (rbn) {
			struct rb_node *rbnext = rb_next(rbn);

			fp = rb_to_skb(rbn);
			rb_erase(rbn, &q->rb_fragments);
			rbn = rbnext;
		}
	}
	sub_frag_mem_limit(q->fqdir, head->truesize);

	*nextp = NULL;
	skb_mark_not_on_list(head);
	head->prev = NULL;
	head->tstamp = q->stamp;
}
EXPORT_SYMBOL(inet_frag_reasm_finish);

struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q)
{
	struct sk_buff *head, *skb;

	head = skb_rb_first(&q->rb_fragments);
	if (!head)
		return NULL;
	skb = FRAG_CB(head)->next_frag;
	if (skb)
		rb_replace_node(&head->rbnode, &skb->rbnode,
				&q->rb_fragments);
	else
		rb_erase(&head->rbnode, &q->rb_fragments);
	memset(&head->rbnode, 0, sizeof(head->rbnode));
	barrier();

	if (head == q->fragments_tail)
		q->fragments_tail = NULL;

	sub_frag_mem_limit(q->fqdir, head->truesize);

	return head;
}
EXPORT_SYMBOL(inet_frag_pull_head);