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
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
|
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
*/
/* Devmaps primary use is as a backend map for XDP BPF helper call
* bpf_redirect_map(). Because XDP is mostly concerned with performance we
* spent some effort to ensure the datapath with redirect maps does not use
* any locking. This is a quick note on the details.
*
* We have three possible paths to get into the devmap control plane bpf
* syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall
* will invoke an update, delete, or lookup operation. To ensure updates and
* deletes appear atomic from the datapath side xchg() is used to modify the
* netdev_map array. Then because the datapath does a lookup into the netdev_map
* array (read-only) from an RCU critical section we use call_rcu() to wait for
* an rcu grace period before free'ing the old data structures. This ensures the
* datapath always has a valid copy. However, the datapath does a "flush"
* operation that pushes any pending packets in the driver outside the RCU
* critical section. Each bpf_dtab_netdev tracks these pending operations using
* a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until
* this list is empty, indicating outstanding flush operations have completed.
*
* BPF syscalls may race with BPF program calls on any of the update, delete
* or lookup operations. As noted above the xchg() operation also keep the
* netdev_map consistent in this case. From the devmap side BPF programs
* calling into these operations are the same as multiple user space threads
* making system calls.
*
* Finally, any of the above may race with a netdev_unregister notifier. The
* unregister notifier must search for net devices in the map structure that
* contain a reference to the net device and remove them. This is a two step
* process (a) dereference the bpf_dtab_netdev object in netdev_map and (b)
* check to see if the ifindex is the same as the net_device being removed.
* When removing the dev a cmpxchg() is used to ensure the correct dev is
* removed, in the case of a concurrent update or delete operation it is
* possible that the initially referenced dev is no longer in the map. As the
* notifier hook walks the map we know that new dev references can not be
* added by the user because core infrastructure ensures dev_get_by_index()
* calls will fail at this point.
*
* The devmap_hash type is a map type which interprets keys as ifindexes and
* indexes these using a hashmap. This allows maps that use ifindex as key to be
* densely packed instead of having holes in the lookup array for unused
* ifindexes. The setup and packet enqueue/send code is shared between the two
* types of devmap; only the lookup and insertion is different.
*/
#include <linux/bpf.h>
#include <net/xdp.h>
#include <linux/filter.h>
#include <trace/events/xdp.h>
#define DEV_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
#define DEV_MAP_BULK_SIZE 16
struct bpf_dtab_netdev;
struct xdp_bulk_queue {
struct xdp_frame *q[DEV_MAP_BULK_SIZE];
struct list_head flush_node;
struct net_device *dev_rx;
struct bpf_dtab_netdev *obj;
unsigned int count;
};
struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
struct bpf_dtab *dtab;
struct xdp_bulk_queue __percpu *bulkq;
struct rcu_head rcu;
unsigned int idx; /* keep track of map index for tracepoint */
};
struct bpf_dtab {
struct bpf_map map;
struct bpf_dtab_netdev **netdev_map;
struct list_head __percpu *flush_list;
struct list_head list;
/* these are only used for DEVMAP_HASH type maps */
struct hlist_head *dev_index_head;
spinlock_t index_lock;
unsigned int items;
u32 n_buckets;
};
static DEFINE_SPINLOCK(dev_map_lock);
static LIST_HEAD(dev_map_list);
static struct hlist_head *dev_map_create_hash(unsigned int entries)
{
int i;
struct hlist_head *hash;
hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL);
if (hash != NULL)
for (i = 0; i < entries; i++)
INIT_HLIST_HEAD(&hash[i]);
return hash;
}
static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
{
int err, cpu;
u64 cost;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
return -EINVAL;
/* Lookup returns a pointer straight to dev->ifindex, so make sure the
* verifier prevents writes from the BPF side
*/
attr->map_flags |= BPF_F_RDONLY_PROG;
bpf_map_init_from_attr(&dtab->map, attr);
/* make sure page count doesn't overflow */
cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
cost += sizeof(struct list_head) * num_possible_cpus();
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
if (!dtab->n_buckets) /* Overflow check */
return -EINVAL;
cost += sizeof(struct hlist_head) * dtab->n_buckets;
}
/* if map size is larger than memlock limit, reject it */
err = bpf_map_charge_init(&dtab->map.memory, cost);
if (err)
return -EINVAL;
dtab->flush_list = alloc_percpu(struct list_head);
if (!dtab->flush_list)
goto free_charge;
for_each_possible_cpu(cpu)
INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu));
dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
sizeof(struct bpf_dtab_netdev *),
dtab->map.numa_node);
if (!dtab->netdev_map)
goto free_percpu;
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets);
if (!dtab->dev_index_head)
goto free_map_area;
spin_lock_init(&dtab->index_lock);
}
return 0;
free_map_area:
bpf_map_area_free(dtab->netdev_map);
free_percpu:
free_percpu(dtab->flush_list);
free_charge:
bpf_map_charge_finish(&dtab->map.memory);
return -ENOMEM;
}
static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
{
struct bpf_dtab *dtab;
int err;
if (!capable(CAP_NET_ADMIN))
return ERR_PTR(-EPERM);
dtab = kzalloc(sizeof(*dtab), GFP_USER);
if (!dtab)
return ERR_PTR(-ENOMEM);
err = dev_map_init_map(dtab, attr);
if (err) {
kfree(dtab);
return ERR_PTR(err);
}
spin_lock(&dev_map_lock);
list_add_tail_rcu(&dtab->list, &dev_map_list);
spin_unlock(&dev_map_lock);
return &dtab->map;
}
static void dev_map_free(struct bpf_map *map)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
int i, cpu;
/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding critical sections in
* these programs to complete. The rcu critical section only guarantees
* no further reads against netdev_map. It does __not__ ensure pending
* flush operations (if any) are complete.
*/
spin_lock(&dev_map_lock);
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
bpf_clear_redirect_map(map);
synchronize_rcu();
/* Make sure prior __dev_map_entry_free() have completed. */
rcu_barrier();
/* To ensure all pending flush operations have completed wait for flush
* list to empty on _all_ cpus.
* Because the above synchronize_rcu() ensures the map is disconnected
* from the program we can assume no new items will be added.
*/
for_each_online_cpu
|