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
|
/*
* 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;
refcount_set(&f->refcnt, 1);
init_completion(&f->completion);
return 0;
}
EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
if (refcount_dec_and_test(&f->refcnt))
complete(&f->completion);
wait_for_completion(&f->completion);
kmem_cache_destroy(f->frags_cachep);
f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);
/* called from rhashtable_free_and_destroy() at netns_frags dismantle */
static void inet_frags_free_cb(void *ptr, void *arg)
{
struct inet_frag_queue *fq = ptr;
int count;
count = del_timer_sync(&fq->timer) ? 1 : 0;
spin_lock_bh(&fq->lock);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
fq->flags |= INET_FRAG_COMPLETE;
count++;
} else if (fq->flags & INET_FRAG_HASH_DEAD) {
count++;
}
spin_unlock_bh(&fq->lock);
if (refcount_sub_and_test(count, &fq->refcnt))
inet_frag_destroy(fq);
}
static void fqdir_rwork_fn(struct work_struct *work)
{
struct fqdir *fqdir = container_of(to_rcu_work(work),
struct fqdir, destroy_rwork);
struct inet_frags *f = fqdir->f;
rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
/* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu)
* have completed, since they need to dereference fqdir.
* Would it not be nice to have kfree_rcu_barrier() ? :)
*/
rcu_barrier();
if (refcount_dec_and_test(&f->refcnt))
complete(&f->completion);
kfree(fqdir);
}
int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
{
struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL);
int res;
if (!fqdir)
return -ENOMEM;
fqdir->f = f;
fqdir->net = net;
res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params);
if (res < 0) {
kfree(fqdir);
return res;
}
refcount_inc(&f->refcnt);
*fqdirp = fqdir;
return 0;
}
EXPORT_SYMBOL(fqdir_init);
void fqdir_exit(struct fqdir *fqdir)
{
fqdir->high_thresh = 0; /* prevent creation of new frags */
fqdir->dead = true;
/* call_rcu is supposed to provide memory barrier semantics,
* separating the setting of fqdir->dead with the destruction
* work. This implicit barrier is paired with inet_frag_kill().
*/
INIT_RCU_WORK(&fqdir->destroy_rwork, fqdir_rwork_fn);
queue_rcu_work(system_wq, &fqdir->destroy_rwork);
}
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;
rcu_read_lock();
/* The RCU read lock provides a memory barrier
* guaranteeing that if fqdir->dead is false then
* the hash table destruction will not start until
* after we unlock. Paired with inet_frags_exit_net().
*/
if (!fqdir->dead) {
rhashtable_remove_fast(&fqdir->rhashtable, &fq->node,
fqdir->f->rhash_params);
refcount_dec(&fq->refcnt);
} else {
fq->flags |= INET_FRAG_HASH_DEAD;
}
rcu_read_unlock();
}
}
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
|