summaryrefslogtreecommitdiff
path: root/kernel/bpf/offload.c
blob: 8e93c47f0779617c7fca6158170f1b66dc100d66 (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
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
/*
 * Copyright (C) 2017-2018 Netronome Systems, Inc.
 *
 * This software is licensed under the GNU General License Version 2,
 * June 1991 as shown in the file COPYING in the top-level directory of this
 * source tree.
 *
 * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
 * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
 * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
 * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
 * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
 * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
 */

#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/bug.h>
#include <linux/kdev_t.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/printk.h>
#include <linux/proc_ns.h>
#include <linux/rhashtable.h>
#include <linux/rtnetlink.h>
#include <linux/rwsem.h>

/* Protects offdevs, members of bpf_offload_netdev and offload members
 * of all progs.
 * RTNL lock cannot be taken when holding this lock.
 */
static DECLARE_RWSEM(bpf_devs_lock);

struct bpf_offload_dev {
	struct list_head netdevs;
};

struct bpf_offload_netdev {
	struct rhash_head l;
	struct net_device *netdev;
	struct bpf_offload_dev *offdev;
	struct list_head progs;
	struct list_head maps;
	struct list_head offdev_netdevs;
};

static const struct rhashtable_params offdevs_params = {
	.nelem_hint		= 4,
	.key_len		= sizeof(struct net_device *),
	.key_offset		= offsetof(struct bpf_offload_netdev, netdev),
	.head_offset		= offsetof(struct bpf_offload_netdev, l),
	.automatic_shrinking	= true,
};

static struct rhashtable offdevs;
static bool offdevs_inited;

static int bpf_dev_offload_check(struct net_device *netdev)
{
	if (!netdev)
		return -EINVAL;
	if (!netdev->netdev_ops->ndo_bpf)
		return -EOPNOTSUPP;
	return 0;
}

static struct bpf_offload_netdev *
bpf_offload_find_netdev(struct net_device *netdev)
{
	lockdep_assert_held(&bpf_devs_lock);

	if (!offdevs_inited)
		return NULL;
	return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
}

int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
{
	struct bpf_offload_netdev *ondev;
	struct bpf_prog_offload *offload;
	int err;

	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
	    attr->prog_type != BPF_PROG_TYPE_XDP)
		return -EINVAL;

	if (attr->prog_flags)
		return -EINVAL;

	offload = kzalloc(sizeof(*offload), GFP_USER);
	if (!offload)
		return -ENOMEM;

	offload->prog = prog;

	offload->netdev = dev_get_by_index(current->nsproxy->net_ns,
					   attr->prog_ifindex);
	err = bpf_dev_offload_check(offload->netdev);
	if (err)
		goto err_maybe_put;

	down_write(&bpf_devs_lock);
	ondev = bpf_offload_find_netdev(offload->netdev);
	if (!ondev) {
		err = -EINVAL;
		goto err_unlock;
	}
	prog->aux->offload = offload;
	list_add_tail(&offload->offloads, &ondev->progs);
	dev_put(offload->netdev);
	up_write(&bpf_devs_lock);

	return 0;
err_unlock:
	up_write(&bpf_devs_lock);
err_maybe_put:
	if (offload->netdev)
		dev_put(offload->netdev);
	kfree(offload);
	return err;
}

static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
			     struct netdev_bpf *data)
{
	struct bpf_prog_offload *offload = prog->aux->offload;
	struct net_device *netdev;

	ASSERT_RTNL();

	if (!offload)
		return -ENODEV;
	netdev = offload->netdev;

	data->command = cmd;

	return netdev->netdev_ops->ndo_bpf(netdev, data);
}

int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
{
	struct netdev_bpf data = {};
	int err;

	data.verifier.prog = env->prog;

	rtnl_lock();
	err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data);
	if (err)
		goto exit_unlock;

	env->prog->aux->offload->dev_ops = data.verifier.ops;
	env->prog->aux->offload->dev_state = true;
exit_unlock:
	rtnl_unlock();
	return err;
}

int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
				 int insn_idx, int prev_insn_idx)
{
	struct bpf_prog_offload *offload;
	int ret = -ENODEV;

	down_read(&bpf_devs_lock);
	offload = env->prog->aux->offload;
	if (offload)
		ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
	up_read(&bpf_devs_lock);

	return ret;
}

int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
{
	struct bpf_prog_offload *offload;
	int ret = -ENODEV;

	down_read(&bpf_devs_lock);
	offload = env->prog->aux->offload;
	if (offload) {
		if (offload->dev_ops->finalize)
			ret = offload->dev_ops->finalize(env);
		else
			ret = 0;
	}
	up_read(&bpf_devs_lock);

	return ret;
}

static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
{
	struct bpf_prog_offload *offload = prog->aux->offload;
	struct netdev_bpf data = {};

	data.offload.prog = prog;

	if (offload->dev_state)
		WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));

	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
	bpf_prog_free_id(prog, true);

	list_del_init(&offload->offloads);
	kfree(offload);
	prog->aux->offload = NULL;
}

void bpf_prog_offload_destroy(struct bpf_prog *prog)
{
	rtnl_lock();
	down_write(&bpf_devs_lock);
	if (prog->aux->offload)
		__bpf_prog_offload_destroy(prog);
	up_write(&bpf_devs_lock);
	rtnl_unlock();
}

static int bpf_prog_offload_translate(struct bpf_prog *prog)
{
	struct netdev_bpf data = {};
	int ret;

	data.offload.prog = prog;

	rtnl_lock();
	ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
	rtnl_unlock();

	return ret;
}

static unsigned int bpf_prog_warn_on_exec(const void *ctx,
					  const struct bpf_insn *insn)
{
	WARN(1, "attempt to execute device eBPF program on the host!");
	return 0;
}

int bpf_prog_offload_compile(struct bpf_prog *prog)
{
	prog->bpf_func = bpf_prog_warn_on_exec;

	return bpf_prog_offload_translate(prog);
}

struct ns_get_path_bpf_prog_args {
	struct bpf_prog *prog;
	struct bpf_prog_info *info;
};

static struct ns_common *bpf_prog_offload_info_fill_ns(void *private_data)
{
	struct ns_get_path_bpf_prog_args *args = private_data;
	struct bpf_prog_aux *aux = args->prog->aux;
	struct ns_common *ns;
	struct net *net;

	rtnl_lock();
	down_read(&bpf_devs_lock);

	if (aux->offload) {
		args->info->ifindex = aux->offload->netdev->ifindex;
		net = dev_net(aux->offload->netdev);
		get_net(net);
		ns = &net->ns;
	} else {
		args->info->ifindex = 0;
		ns = NULL;
	}

	up_read(&bpf_devs_lock);
	rtnl_unlock();

	return ns;
}

int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
			       struct bpf_prog *prog)
{
	struct ns_get_path_bpf_prog_args args = {
		.prog	= prog,
		.info	= info,
	};
	struct bpf_prog_aux *aux = prog->aux;
	struct inode *ns_inode;
	struct path ns_path;
	char __user *uinsns;
	void *res;
	u32 ulen;

	res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args);
	if (IS_ERR(res)) {
		if (!info->ifindex)
			return -ENODEV;
		return PTR_ERR(res);
	}

	down_read(&bpf_devs_lock);

	if (!aux->offload) {
		up_read(&bpf_devs_lock);
		return -ENODEV;
	}

	ulen = info->jited_prog_len;
	info->jited_prog_len = aux->offload->jited_len;
	if (info->jited_prog_len & ulen) {
		uinsns = u64_to_user_ptr(info->jited_prog_insns);
		ulen = min_t(u32, info->jited_prog_len, ulen);
		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {
			up_read(&bpf_devs_lock);
			return -EFAULT;
		}
	}

	up_read(&bpf_devs_lock);

	ns_inode = ns_path.dentry->d_inode;
	info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev);
	info->netns_ino = ns_inode->i_ino;
	path_put(&ns_path);

	return 0;
}

const struct bpf_prog_ops bpf_offload_prog_ops = {
};

static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
			       enum bpf_netdev_command cmd)
{
	struct netdev_bpf data = {};
	struct net_device *netdev;

	ASSERT_RTNL();

	data.command = cmd;
	data.offmap = offmap;
	/* Caller must make sure netdev is valid */
	netdev = offmap->netdev;

	return netdev->netdev_ops->ndo_bpf(netdev, &data);
}

struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
	struct net *net = current->nsproxy->net_ns;
	struct bpf_offload_netdev *ondev;
	struct bpf_offloaded_map *offmap;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return ERR_PTR(-EPERM);
	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
	    attr->map_type != BPF_MAP_TYPE_HASH)
		return ERR_PTR(-EINVAL);

	offmap = kzalloc(sizeof(*offmap), GFP_USER);
	if (!offmap)
		return ERR_PTR(-ENOMEM);

	bpf_map_init_from_attr(&offmap->map, attr);

	rtnl_lock();
	down_write(&bpf_devs_lock);
	offmap->netdev = __dev_get_by_index(net, attr->map_ifindex);
	err = bpf_dev_offload_check(offmap->netdev);
	if (err)
		goto err_unlock;

	ondev = bpf_offload_find_netdev(offmap->netdev);
	if (!ondev) {
		err = -EINVAL;
		goto err_unlock;
	}

	err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
	if (err)
		goto err_unlock;

	list_add_tail(&offmap->offloads, &ondev->maps);
	up_write(&bpf_devs_lock);
	rtnl_unlock();

	return &offmap->map;

err_unlock:
	up_write(&bpf_devs_lock);
	rtnl_unlock();
	kfree(offmap);
	return ERR_PTR(err);
}

static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
{
	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
	bpf_map_free_id(&offmap->map, true);
	list_del_init(&offmap->offloads);
	offmap->netdev = NULL;
}

void bpf_map_offload_map_free(struct bpf_map *map)
{
	struct bpf_offloaded_map *offmap = map_to_offmap(map);

	rtnl_lock();
	down_write(&bpf_devs_lock);
	if (offmap->netdev)
		__bpf_map_offload_destroy(offmap);
	up_write(&bpf_devs_lock);
	rtnl_unlock();

	kfree(offmap);
}

int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value)
{
	struct bpf_offloaded_map *offmap = map_to_offmap(map);
	int ret = -ENODEV;

	down_read(&bpf_devs_lock);
	if (offmap->netdev)
		ret = offmap->dev_ops->map_lookup_elem(offmap, key, value);
	up_read(&bpf_devs_lock);

	return ret;
}

int bpf_map_offload_update_elem(struct bpf_map *map,
				void *key, void *value, u64 flags)
{
	struct bpf_offloaded_map *offmap = map_to_offmap(map);
	int ret = -ENODEV;

	if (unlikely(flags > BPF_EXIST))
		return -EINVAL;

	down_read(&bpf_devs_lock);
	if (offmap->netdev)
		ret = offmap->dev_ops->map_update_elem(offmap, key, value,
						       flags);
	up_read(&bpf_devs_lock);

	return ret;
}

int bpf_map_offload_delete_elem(struct bpf_map *map, void *key)
{
	struct bpf_offloaded_map *offmap = map_to_offmap(map);
	int ret = -ENODEV;

	down_read(&bpf_devs_lock);
	if (offmap->netdev)
		ret = offmap->dev_ops->map_delete_elem(offmap, key);
	up_read(&bpf_devs_lock);

	return ret;
}

int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct bpf_offloaded_map *offmap = map_to_offmap(map);
	int ret = -ENODEV;

	down_read(&bpf_devs_lock);
	if (offmap->netdev)
		ret = offmap->dev_ops->map_get_next_key(offmap, key, next_key);
	up_read(&bpf_devs_lock);

	return ret;
}

struct ns_get_path_bpf_map_args {
	struct bpf_offloaded_map *offmap;
	struct bpf_map_info *info;
};

static struct ns_common *bpf_map_offload_info_fill_ns(void *private_data)
{
	struct ns_get_path_bpf_map_args *args = private_data;
	struct ns_common *ns;
	struct net *net;

	rtnl_lock();
	down_read(&bpf_devs_lock);

	if (args->offmap->netdev) {
		args->info->ifindex = args->offmap->netdev->ifindex;
		net = dev_net(args->offmap->netdev);
		get_net(net);
		ns = &net->ns;
	} else {
		args->info->ifindex = 0;
		ns = NULL;
	}

	up_read(&bpf_devs_lock);
	rtnl_unlock();

	return ns;
}

int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
{
	struct ns_get_path_bpf_map_args args = {
		.offmap	= map_to_offmap(map),
		.info	= info,
	};
	struct inode *ns_inode;
	struct path ns_path;
	void *res;

	res = ns_get_path_cb(&ns_path, bpf_map_offload_info_fill_ns, &args);
	if (IS_ERR(res)) {
		if (!info->ifindex)
			return -ENODEV;
		return PTR_ERR(res);
	}

	ns_inode = ns_path.dentry->d_inode;
	info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev);
	info->netns_ino = ns_inode->i_ino;
	path_put(&ns_path);

	return 0;
}

static bool __bpf_offload_dev_match(struct bpf_prog *prog,
				    struct net_device *netdev)
{
	struct bpf_offload_netdev *ondev1, *ondev2;
	struct bpf_prog_offload *offload;

	if (!bpf_prog_is_dev_bound(prog->aux))
		return false;

	offload = prog->aux->offload;
	if (!offload)
		return false;
	if (offload->netdev == netdev)
		return true;

	ondev1 = bpf_offload_find_netdev(offload->netdev);
	ondev2 = bpf_offload_find_netdev(netdev);

	return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev;
}

bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
{
	bool ret;

	down_read(&bpf_devs_lock);
	ret = __bpf_offload_dev_match(prog, netdev);
	up_read(&bpf_devs_lock);

	return ret;
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_match);

bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
{
	struct bpf_offloaded_map *offmap;
	bool ret;

	if (!bpf_map_is_dev_bound(map))
		return bpf_map_offload_neutral(map);
	offmap = map_to_offmap(map);

	down_read(&bpf_devs_lock);
	ret = __bpf_offload_dev_match(prog, offmap->netdev);
	up_read(&bpf_devs_lock);

	return ret;
}

int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
				    struct net_device *netdev)
{
	struct bpf_offload_netdev *ondev;
	int err;

	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
	if (!ondev)
		return -ENOMEM;

	ondev->netdev = netdev;
	ondev->offdev = offdev;
	INIT_LIST_HEAD(&ondev->progs);
	INIT_LIST_HEAD(&ondev->maps);

	down_write(&bpf_devs_lock);
	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
	if (err) {
		netdev_warn(netdev, "failed to register for BPF offload\n");
		goto err_unlock_free;
	}

	list_add(&ondev->offdev_netdevs, &offdev->netdevs);
	up_write(&bpf_devs_lock);
	return 0;

err_unlock_free:
	up_write(&bpf_devs_lock);
	kfree(ondev);
	return err;
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);

void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
				       struct net_device *netdev)
{
	struct bpf_offload_netdev *ondev, *altdev;
	struct bpf_offloaded_map *offmap, *mtmp;
	struct bpf_prog_offload *offload, *ptmp;

	ASSERT_RTNL();

	down_write(&bpf_devs_lock);
	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
	if (WARN_ON(!ondev))
		goto unlock;

	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
	list_del(&ondev->offdev_netdevs);

	/* Try to move the objects to another netdev of the device */
	altdev = list_first_entry_or_null(&offdev->netdevs,
					  struct bpf_offload_netdev,
					  offdev_netdevs);
	if (altdev) {
		list_for_each_entry(offload, &ondev->progs, offloads)
			offload->netdev = altdev->netdev;
		list_splice_init(&ondev->progs, &altdev->progs);

		list_for_each_entry(offmap, &ondev->maps, offloads)
			offmap->netdev = altdev->netdev;
		list_splice_init(&ondev->maps, &altdev->maps);
	} else {
		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
			__bpf_prog_offload_destroy(offload->prog);
		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
			__bpf_map_offload_destroy(offmap);
	}

	WARN_ON(!list_empty(&ondev->progs));
	WARN_ON(!list_empty(&ondev->maps));
	kfree(ondev);
unlock:
	up_write(&bpf_devs_lock);
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);

struct bpf_offload_dev *bpf_offload_dev_create(void)
{
	struct bpf_offload_dev *offdev;
	int err;

	down_write(&bpf_devs_lock);
	if (!offdevs_inited) {
		err = rhashtable_init(&offdevs, &offdevs_params);
		if (err)
			return ERR_PTR(err);
		offdevs_inited = true;
	}
	up_write(&bpf_devs_lock);

	offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
	if (!offdev)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&offdev->netdevs);

	return offdev;
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_create);

void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
{
	WARN_ON(!list_empty(&offdev->netdevs));
	kfree(offdev);
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);