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
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
|
/*
* INETPEER - A storage for permanent information about peers
*
* This source is covered by the GNU GPL, the same as all kernel sources.
*
* Authors: Andrey V. Savochkin <saw@msu.ru>
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/random.h>
#include <linux/timer.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/net.h>
#include <linux/workqueue.h>
#include <net/ip.h>
#include <net/inetpeer.h>
#include <net/secure_seq.h>
/*
* Theory of operations.
* We keep one entry for each peer IP address. The nodes contains long-living
* information about the peer which doesn't depend on routes.
* At this moment this information consists only of ID field for the next
* outgoing IP packet. This field is incremented with each packet as encoded
* in inet_getid() function (include/net/inetpeer.h).
* At the moment of writing this notes identifier of IP packets is generated
* to be unpredictable using this code only for packets subjected
* (actually or potentially) to defragmentation. I.e. DF packets less than
* PMTU in size uses a constant ID and do not use this code (see
* ip_select_ident() in include/net/ip.h).
*
* Route cache entries hold references to our nodes.
* New cache entries get references via lookup by destination IP address in
* the avl tree. The reference is grabbed only when it's needed i.e. only
* when we try to output IP packet which needs an unpredictable ID (see
* __ip_select_ident() in net/ipv4/route.c).
* Nodes are removed only when reference counter goes to 0.
* When it's happened the node may be removed when a sufficient amount of
* time has been passed since its last use. The less-recently-used entry can
* also be removed if the pool is overloaded i.e. if the total amount of
* entries is greater-or-equal than the threshold.
*
* Node pool is organised as an AVL tree.
* Such an implementation has been chosen not just for fun. It's a way to
* prevent easy and efficient DoS attacks by creating hash collisions. A huge
* amount of long living nodes in a single hash slot would significantly delay
* lookups performed with disabled BHs.
*
* Serialisation issues.
* 1. Nodes may appear in the tree only with the pool lock held.
* 2. Nodes may disappear from the tree only with the pool lock held
* AND reference count being 0.
* 3. Global variable peer_total is modified under the pool lock.
* 4. struct inet_peer fields modification:
* avl_left, avl_right, avl_parent, avl_height: pool lock
* refcnt: atomically against modifications on other CPU;
* usually under some other lock to prevent node disappearing
* daddr: unchangeable
* ip_id_count: atomic value (no lock needed)
*/
static struct kmem_cache *peer_cachep __read_mostly;
static LIST_HEAD(gc_list);
static const int gc_delay = 60 * HZ;
static struct delayed_work gc_work;
static DEFINE_SPINLOCK(gc_lock);
#define node_height(x) x->avl_height
#define peer_avl_empty ((struct inet_peer *)&peer_fake_node)
#define peer_avl_empty_rcu ((struct inet_peer __rcu __force *)&peer_fake_node)
static const struct inet_peer peer_fake_node = {
.avl_left = peer_avl_empty_rcu,
.avl_right = peer_avl_empty_rcu,
.avl_height = 0
};
void inet_peer_base_init(struct inet_peer_base *bp)
{
bp->root = peer_avl_empty_rcu;
seqlock_init(&bp->lock);
bp->flush_seq = ~0U;
bp->total = 0;
}
EXPORT_SYMBOL_GPL(inet_peer_base_init);
static atomic_t v4_seq = ATOMIC_INIT(0);
static atomic_t v6_seq = ATOMIC_INIT(0);
static atomic_t *inetpeer_seq_ptr(int family)
{
return (family == AF_INET ? &v4_seq : &v6_seq);
}
static inline void flush_check(struct inet_peer_base *base, int family)
{
atomic_t *fp = inetpeer_seq_ptr(family);
if (unlikely(base->flush_seq != atomic_read(fp))) {
inetpeer_invalidate_tree(base);
base->flush_seq = atomic_read(fp);
}
}
void inetpeer_invalidate_family(int family)
{
atomic_t *fp = inetpeer_seq_ptr(family);
atomic_inc(fp);
}
#define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
/* Exported for sysctl_net_ipv4. */
int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more
* aggressively at this stage */
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
static void inetpeer_gc_worker(struct work_struct *work)
{
struct inet_peer *p, *n, *c;
LIST_HEAD(list);
spin_lock_bh(&gc_lock);
list_replace_init(&gc_list, &list);
spin_unlock_bh(&gc_lock);
if (list_empty(&list))
return;
list_for_each_entry_safe(p, n, &list, gc_list) {
if (need_resched())
cond_resched();
c = rcu_dereference_protected(p->avl_left, 1);
if (c != peer_avl_empty) {
list_add_tail(&c->gc_list, &list);
p->avl_left = peer_avl_empty_rcu;
}
c = rcu_dereference_protected(p->avl_right, 1);
if (c != peer_avl_empty) {
list_add_tail(&c->gc_list, &list);
p->avl_right = peer_avl_empty_rcu;
}
n = list_entry(p->gc_list.next, struct inet_peer, gc_list);
if (!atomic_read(&p->refcnt)) {
list_del(&p->gc_list);
kmem_cache_free(peer_cachep, p);
}
}
if (list_empty(&list))
return;
spin_lock_bh(&gc_lock);
list_splice(&list, &gc_list);
spin_unlock_bh(&gc_lock);
schedule_delayed_work(&gc_work, gc_delay);
}
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
{
struct sysinfo si;
/* Use the straight interface to information about memory. */
si_meminfo(&si);
/* The values below were suggested by Alexey Kuznetsov
* <kuznet@ms2.inr.ac.ru>. I don't have any opinion about the values
* myself. --SAW
*/
if (si.totalram <= (32768*1024)/PAGE_SIZE)
inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */
if (si.totalram <= (16384*1024)/PAGE_SIZE)
inet_peer_threshold >>= 1; /* about 512KB */
if (si.totalram <= (8192*1024)/PAGE_SIZE)
inet_peer_threshold >>= 2; /* about 128KB */
peer_cachep = kmem_cache_create("inet_peer_cache",
sizeof(struct inet_peer),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
NULL);
INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker);
}
static int addr_compare(const struct inetpeer_addr *a,
const struct inetpeer_addr *b)
{
int i, n = (a->family == AF_INET ? 1 : 4);
for (i = 0; i < n; i++) {
if (a->addr.a6[i] == b->addr.a6[i])
continue;
if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i])
return -1;
return 1;
}
return 0;
}
#define rcu_deref_locked(X, BASE) \
rcu_dereference_protected(X, lockdep_is_held(&(BASE)->lock.lock))
/*
* Called with local BH disabled and the pool lock held.
*/
#define lookup(_daddr, _stack, _base) \
({ \
struct inet_peer *u; \
struct inet_peer __rcu **v; \
\
stackptr = _stack; \
*stackptr++ = &_base->root; \
for (u = rcu_deref_locked(_base->root, _base); \
u != peer_avl_empty; ) { \
int cmp = addr_compare(_daddr, &u->daddr); \
if (cmp == 0) \
break; \
if (cmp == -1) \
v = &u->avl_left; \
else \
v = &u->avl_right; \
*stackptr++ = v; \
u = rcu_deref_locked(*v, _base); \
} \
u; \
})
/*
* Called with rcu_read_lock()
* Because we hold no lock against a writer, its quite possible we fall
* in an endless loop.
* But every pointer we follow is guaranteed to be valid thanks to RCU.
* We exit from this function if number of links exceeds PEER_MAXDEPTH
*/
static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
struct inet_peer_base *base)
{
struct inet_peer *u = rcu_dereference(base->root);
int count = 0;
while (u != peer_avl_empty) {
int cmp = addr_compare(daddr, &u->daddr);
if (cmp == 0) {
/* Before taking a reference, check if this entry was
* deleted (refcnt=-1)
*/
if (!atomic_add_unless(&u->refcnt, 1, -1))
u = NULL;
return u;
}
if (cmp == -1)
u = rcu_dereference(u
|