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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Randomized tests for eBPF longest-prefix-match maps
*
* This program runs randomized tests against the lpm-bpf-map. It implements a
* "Trivial Longest Prefix Match" (tlpm) based on simple, linear, singly linked
* lists. The implementation should be pretty straightforward.
*
* Based on tlpm, this inserts randomized data into bpf-lpm-maps and verifies
* the trie-based bpf-map implementation behaves the same way as tlpm.
*/
#include <assert.h>
#include <errno.h>
#include <inttypes.h>
#include <linux/bpf.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <bpf/bpf.h>
#include "bpf_util.h"
struct tlpm_node {
struct tlpm_node *next;
size_t n_bits;
uint8_t key[];
};
static struct tlpm_node *tlpm_match(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits);
static struct tlpm_node *tlpm_add(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits)
{
struct tlpm_node *node;
size_t n;
n = (n_bits + 7) / 8;
/* 'overwrite' an equivalent entry if one already exists */
node = tlpm_match(list, key, n_bits);
if (node && node->n_bits == n_bits) {
memcpy(node->key, key, n);
return list;
}
/* add new entry with @key/@n_bits to @list and return new head */
node = malloc(sizeof(*node) + n);
assert(node);
node->next = list;
node->n_bits = n_bits;
memcpy(node->key, key, n);
return node;
}
static void tlpm_clear(struct tlpm_node *list)
{
struct tlpm_node *node;
/* free all entries in @list */
while ((node = list)) {
list = list->next;
free(node);
}
}
static struct tlpm_node *tlpm_match(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits)
{
struct tlpm_node *best = NULL;
size_t i;
/* Perform longest prefix-match on @key/@n_bits. That is, iterate all
* entries and match each prefix against @key. Remember the "best"
* entry we find (i.e., the longest prefix that matches) and return it
* to the caller when done.
*/
for ( ; list; list = list->next) {
for (i = 0; i < n_bits && i < list->n_bits; ++i) {
if ((key[i / 8] & (1 << (7 - i % 8))) !=
(list->key[i / 8] & (1 << (7 - i % 8))))
break;
}
if (i >= list->n_bits) {
if (!best || i > best->n_bits)
best = list;
}
}
return best;
}
static struct tlpm_node *tlpm_delete(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits)
{
struct tlpm_node *best = tlpm_match(list, key, n_bits);
struct tlpm_node *node;
if (!best || best->n_bits != n_bits)
return list;
if (best == list) {
node = best->next;
free(best);
return node;
}
for (node = list; node; node = node->next) {
if (node->next == best) {
node->next = best->next;
free(best);
return list;
}
}
/* should never get here */
assert(0);
return list;
}
static void test_lpm_basic(void)
{
struct tlpm_node *list = NULL, *t1, *t2;
/* very basic, static tests to verify tlpm works as expected */
assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
t1 = list = tlpm_add(list, (uint8_t[]){ 0xff }, 8);
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0x00 }, 16));
assert(!tlpm_match(list, (uint8_t[]){ 0x7f }, 8));
assert(!tlpm_match(list, (uint8_t[]){ 0xfe }, 8));
assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 7));
t2 = list = tlpm_add(list, (uint8_t[]){ 0xff, 0xff }, 16);
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
assert(t2 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15));
assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16));
list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16);
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8);
assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
tlpm_clear(list);
}
static void test_lpm_order(void)
{
struct tlpm_node *t1, *t2, *l1 = NULL, *l2 = NULL;
size_t i, j;
/* Verify the tlpm implementation works correctly regardless of the
* order of entries. Insert a random set of entries into @l1, and copy
* the same data in reverse order into @l2. Then verify a lookup of
* random keys will yield the same result in both sets.
*/
for (i = 0; i < (1 << 12); ++i)
l1 = tlpm_add(l1, (uint8_t[]){
rand() % 0xff,
rand() % 0xff,
}, rand() % 16 + 1);
for (t1 = l1; t1; t1 = t1->next)
l2 = tlpm_add(l2, t1->key, t1->n_bits);
for (i = 0; i < (1 << 8); ++i) {
uint8_t key[] = { rand() % 0xff, rand() % 0xff };
t1 = tlpm_match(l1, key, 16);
t2 = tlpm_match(l2, key, 16);
assert(!t1 == !t2);
if (t1) {
assert(t1->n_bits == t2->n_bits);
for (j = 0; j < t1->n_bits; ++j)
assert((t1->key[j / 8] & (1 << (7 - j % 8))) ==
(t2->key[j / 8] & (1 << (7 - j % 8))));
}
}
tlpm_clear(l1);
tlpm_clear(l2);
}
static void test_lpm_map(int keysize)
{
size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
struct tlpm_node *t, *list = NULL;
struct bpf_lpm_trie_key *key;
uint8_t *data, *value;
int r, map;
/* Compare behavior of tlpm vs. bpf-lpm. Create a randomized set of
* prefixes and insert it into both tlpm and bpf-lpm. Then run some
* randomized lookups and verify both maps return the same result.
*/
n_matches = 0;
n_matches_after_delete = 0;
n_nodes = 1 << 8;
n_lookups = 1 << 16;
data = alloca(keysize);
memset(data, 0, keysize);
value = alloca(keysize + 1);
memset(value, 0, keysize + 1);
key = alloca(sizeof(*key) + keysize);
memset(key, 0, sizeof(*key) + keysize);
map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
sizeof(*key) + keysize,
keysize + 1,
4096,
BPF_F_NO_PREALLOC);
assert(map >= 0);
for (i = 0; i < n_nodes; ++i) {
for (j = 0; j < keysize; ++j)
value[j] = rand() & 0xff;
value[keysize] = rand() % (8 * keysize + 1);
list = tlpm_add(list, value, value[keysize]);
key->prefixlen = value[keysize];
memcpy(key->data, value, keysize);
r = bpf_map_update_elem(map, key, value, 0);
assert(!r);
}
for (i = 0; i < n_lookups; ++i) {
for (j = 0; j < keysize; ++j)
data[j] = rand() & 0xff;
t = tlpm_match(list, data, 8 * keysize);
key->prefixlen = 8 * keysize;
memcpy(key->data, data, keysize);
r = bpf_map_lookup_elem(map, key, value);
assert(!r || errno == ENOENT);
assert(!t == !!r);
if (t) {
++n_matches;
assert(t->n_bits == value[keysize]);
for (j = 0; j < t->n_bits; ++j)
assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
(value[j / 8] & (1 << (7 - j % 8))));
}
}
/* Remove the first half of the elements in the tlpm and the
* corresponding nodes from the bpf-lpm. Then run the same
* large number of random lookups in both and make sure they match.
* Note: we need to count the number of nodes actually inserted
* since there may have been duplicates.
*/
for (i = 0, t = list; t; i++, t = t->next)
;
for (j = 0; j < i / 2; ++j) {
key->prefixlen = list->n_bits;
memcpy(key->data, list->key, keysize);
r = bpf_map_delete_elem(map, key);
assert(!r);
list = tlpm_delete(list, list->key, list->n_bits);
assert(list);
}
for (i = 0; i < n_lookups; ++i) {
for (j = 0; j < keysize; ++j)
data[j] = rand() & 0xff;
t = tlpm_match(list, data, 8 * keysize);
key->prefixlen = 8 * keysize;
memcpy(key->data, data, keysize);
r = bpf_map_lookup_elem(map, key, value);
assert(!r || errno == ENOENT);
assert(!t == !!r);
if (t) {
++n_matches_after_delete;
assert(t->n_bits == value[keysize]);
for (j = 0; j < t->n_bits; ++j)
assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
(value[j / 8] & (1 << (7 - j % 8))));
}
}
close(map);
tlpm_clear(list);
/* With 255 random nodes in the map, we are pretty likely to match
* something on every lookup. For statistics, use this:
*
* printf(" nodes: %zu\n"
* " lookups: %zu\n"
* " matches: %zu\n"
* "matches(delete): %zu\n",
* n_nodes, n_lookups, n_matches, n_matches_after_delete);
*/
}
/* Test the implementation with some 'real world' examples */
static void test_lpm_ipaddr(void)
{
struct bpf_lpm_trie_key *key_ipv4;
struct bpf_lpm_trie_key *key_ipv6;
size_t key_size_ipv4;
size_t key_size_ipv6;
int map_fd_ipv4;
int map_fd_ipv6;
__u64 value;
key_size_ipv4 = sizeof(*key_ipv4) + sizeof(__u32);
key_size_ipv6 = sizeof(*key_ipv6) + sizeof(__u32) * 4;
key_ipv4 = alloca(key_size_ipv4);
key_ipv6 = alloca(key_size_ipv6);
map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
key_size_ipv4, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd_ipv4 >= 0);
map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
key_size_ipv6, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd_ipv6 >= 0);
/* Fill data some IPv4 and IPv6 address ranges */
value = 1;
key_ipv4->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 2;
key_ipv4->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 3;
key_ipv4->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 5;
key_ipv4->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 4;
key_ipv4->prefixlen = 23;
inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 0xdeadbeef;
key_ipv6->prefixlen = 64;
inet_pton(AF_INET6, "2a00:1450:4001:814::200e", key_ipv6->data);
assert(bpf_map_update_elem(map_fd_ipv6, key_ipv6, &value, 0) == 0);
/* Set tprefixlen to maximum for lookups */
key_ipv4->prefixlen = 32;
key_ipv6->prefixlen = 128;
/* Test some lookups that should come back with a value */
inet_pton(AF_INET, "192.168.128.23", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0);
assert(value == 3);
inet_pton(AF_INET, "192.168.0.1", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0);
assert(value == 2);
inet_pton(AF_INET6, "2a00:1450:4001:814::", key_ipv6->data);
assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0);
assert(value == 0xdeadbeef);
inet_pton(AF_INET6, "2a00:1450:4001:814::1", key_ipv6->data);
assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0);
assert(value == 0xdeadbeef);
/* Test some lookups that should not match any entry */
inet_pton(AF_INET, "10.0.0.1", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 &&
errno == ENOENT);
inet_pton(AF_INET, "11.11.11.11", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 &&
errno == ENOENT);
inet_pton(AF_INET6, "2a00:ffff::", key_ipv6->data);
assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == -1 &&
errno == ENOENT);
close(map_fd_ipv4);
close(map_fd_ipv6);
}
static void test_lpm_delete(void)
{
struct bpf_lpm_trie_key *key;
size_t key_size;
int map_fd;
__u64 value;
key_size = sizeof(*key) + sizeof(__u32);
key = alloca(key_size);
map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
key_size, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd >= 0);
/* Add nodes:
* 192.168.0.0/16 (1)
* 192.168.0.0/24 (2)
* 192.168.128.0/24 (3)
* 192.168.1.0/24 (4)
*
* (1)
* / \
* (IM) (3)
* / \
* (2) (4)
*/
value = 1;
key->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
value = 2;
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
value = 3;
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
value = 4;
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
/* remove non-existent node */
key->prefixlen = 32;
inet_pton(AF_INET, "10.0.0.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
errno == ENOENT);
/* assert initial lookup */
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.0.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 2);
/* remove leaf node */
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.0.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 1);
/* remove leaf (and intermediary) node */
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.1.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 1);
/* remove root node */
key->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.128.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 3);
/* remove last node */
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.128.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
errno == ENOENT);
close(map_fd);
}
int main(void)
{
struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY };
int i, ret;
/* we want predictable, pseudo random tests */
srand(0xf00ba1);
/* allow unlimited locked memory */
ret = setrlimit(RLIMIT_MEMLOCK, &limit);
if (ret < 0)
perror("Unable to lift memlock rlimit");
test_lpm_basic();
test_lpm_order();
/* Test with 8, 16, 24, 32, ... 128 bit prefix length */
for (i = 1; i <= 16; ++i)
test_lpm_map(i);
test_lpm_ipaddr();
test_lpm_delete();
printf("test_lpm: OK\n");
return 0;
}
|