Free Electrons

Embedded Linux Experts

  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
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/bpf.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
#include <linux/filter.h>

static LIST_HEAD(bpf_map_types);

static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
	struct bpf_map_type_list *tl;
	struct bpf_map *map;

	list_for_each_entry(tl, &bpf_map_types, list_node) {
		if (tl->type == attr->map_type) {
			map = tl->ops->map_alloc(attr);
			if (IS_ERR(map))
				return map;
			map->ops = tl->ops;
			map->map_type = attr->map_type;
			return map;
		}
	}
	return ERR_PTR(-EINVAL);
}

/* boot time registration of different map implementations */
void bpf_register_map_type(struct bpf_map_type_list *tl)
{
	list_add(&tl->list_node, &bpf_map_types);
}

/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
	struct bpf_map *map = container_of(work, struct bpf_map, work);

	/* implementation dependent freeing */
	map->ops->map_free(map);
}

/* decrement map refcnt and schedule it for freeing via workqueue
 * (unrelying map implementation ops->map_free() might sleep)
 */
void bpf_map_put(struct bpf_map *map)
{
	if (atomic_dec_and_test(&map->refcnt)) {
		INIT_WORK(&map->work, bpf_map_free_deferred);
		schedule_work(&map->work);
	}
}

static int bpf_map_release(struct inode *inode, struct file *filp)
{
	struct bpf_map *map = filp->private_data;

	bpf_map_put(map);
	return 0;
}

static const struct file_operations bpf_map_fops = {
	.release = bpf_map_release,
};

/* helper macro to check that unused fields 'union bpf_attr' are zero */
#define CHECK_ATTR(CMD) \
	memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
		   sizeof(attr->CMD##_LAST_FIELD), 0, \
		   sizeof(*attr) - \
		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
		   sizeof(attr->CMD##_LAST_FIELD)) != NULL

#define BPF_MAP_CREATE_LAST_FIELD max_entries
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
	struct bpf_map *map;
	int err;

	err = CHECK_ATTR(BPF_MAP_CREATE);
	if (err)
		return -EINVAL;

	/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
	map = find_and_alloc_map(attr);
	if (IS_ERR(map))
		return PTR_ERR(map);

	atomic_set(&map->refcnt, 1);

	err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);

	if (err < 0)
		/* failed to allocate fd */
		goto free_map;

	return err;

free_map:
	map->ops->map_free(map);
	return err;
}

/* if error is returned, fd is released.
 * On success caller should complete fd access with matching fdput()
 */
struct bpf_map *bpf_map_get(struct fd f)
{
	struct bpf_map *map;

	if (!f.file)
		return ERR_PTR(-EBADF);

	if (f.file->f_op != &bpf_map_fops) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}

	map = f.file->private_data;

	return map;
}

/* helper to convert user pointers passed inside __aligned_u64 fields */
static void __user *u64_to_ptr(__u64 val)
{
	return (void __user *) (unsigned long) val;
}

/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value

static int map_lookup_elem(union bpf_attr *attr)
{
	void __user *ukey = u64_to_ptr(attr->key);
	void __user *uvalue = u64_to_ptr(attr->value);
	int ufd = attr->map_fd;
	struct fd f = fdget(ufd);
	struct bpf_map *map;
	void *key, *value, *ptr;
	int err;

	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
		return -EINVAL;

	map = bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	err = -ENOMEM;
	value = kmalloc(map->value_size, GFP_USER);
	if (!value)
		goto free_key;

	rcu_read_lock();
	ptr = map->ops->map_lookup_elem(map, key);
	if (ptr)
		memcpy(value, ptr, map->value_size);
	rcu_read_unlock();

	err = -ENOENT;
	if (!ptr)
		goto free_value;

	err = -EFAULT;
	if (copy_to_user(uvalue, value, map->value_size) != 0)
		goto free_value;

	err = 0;

free_value:
	kfree(value);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags

static int map_update_elem(union bpf_attr *attr)
{
	void __user *ukey = u64_to_ptr(attr->key);
	void __user *uvalue = u64_to_ptr(attr->value);
	int ufd = attr->map_fd;
	struct fd f = fdget(ufd);
	struct bpf_map *map;
	void *key, *value;
	int err;

	if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
		return -EINVAL;

	map = bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	err = -ENOMEM;
	value = kmalloc(map->value_size, GFP_USER);
	if (!value)
		goto free_key;

	err = -EFAULT;
	if (copy_from_user(value, uvalue, map->value_size) != 0)
		goto free_value;

	/* eBPF program that use maps are running under rcu_read_lock(),
	 * therefore all map accessors rely on this fact, so do the same here
	 */
	rcu_read_lock();
	err = map->ops->map_update_elem(map, key, value, attr->flags);
	rcu_read_unlock();

free_value:
	kfree(value);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

#define BPF_MAP_DELETE_ELEM_LAST_FIELD key

static int map_delete_elem(union bpf_attr *attr)
{
	void __user *ukey = u64_to_ptr(attr->key);
	int ufd = attr->map_fd;
	struct fd f = fdget(ufd);
	struct bpf_map *map;
	void *key;
	int err;

	if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
		return -EINVAL;

	map = bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	rcu_read_lock();
	err = map->ops->map_delete_elem(map, key);
	rcu_read_unlock();

free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key

static int map_get_next_key(union bpf_attr *attr)
{
	void __user *ukey = u64_to_ptr(attr->key);
	void __user *unext_key = u64_to_ptr(attr->next_key);
	int ufd = attr->map_fd;
	struct fd f = fdget(ufd);
	struct bpf_map *map;
	void *key, *next_key;
	int err;

	if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
		return -EINVAL;

	map = bpf_map_get(f);
	if (IS_ERR(map))
		return PTR_ERR(map);

	err = -ENOMEM;
	key = kmalloc(map->key_size, GFP_USER);
	if (!key)
		goto err_put;

	err = -EFAULT;
	if (copy_from_user(key, ukey, map->key_size) != 0)
		goto free_key;

	err = -ENOMEM;
	next_key = kmalloc(map->key_size, GFP_USER);
	if (!next_key)
		goto free_key;

	rcu_read_lock();
	err = map->ops->map_get_next_key(map, key, next_key);
	rcu_read_unlock();
	if (err)
		goto free_next_key;

	err = -EFAULT;
	if (copy_to_user(unext_key, next_key, map->key_size) != 0)
		goto free_next_key;

	err = 0;

free_next_key:
	kfree(next_key);
free_key:
	kfree(key);
err_put:
	fdput(f);
	return err;
}

static LIST_HEAD(bpf_prog_types);

static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
	struct bpf_prog_type_list *tl;

	list_for_each_entry(tl, &bpf_prog_types, list_node) {
		if (tl->type == type) {
			prog->aux->ops = tl->ops;
			prog->aux->prog_type = type;
			return 0;
		}
	}
	return -EINVAL;
}

void bpf_register_prog_type(struct bpf_prog_type_list *tl)
{
	list_add(&tl->list_node, &bpf_prog_types);
}

/* fixup insn->imm field of bpf_call instructions:
 * if (insn->imm == BPF_FUNC_map_lookup_elem)
 *      insn->imm = bpf_map_lookup_elem - __bpf_call_base;
 * else if (insn->imm == BPF_FUNC_map_update_elem)
 *      insn->imm = bpf_map_update_elem - __bpf_call_base;
 * else ...
 *
 * this function is called after eBPF program passed verification
 */
static void fixup_bpf_calls(struct bpf_prog *prog)
{
	const struct bpf_func_proto *fn;
	int i;

	for (i = 0; i < prog->len; i++) {
		struct bpf_insn *insn = &prog->insnsi[i];

		if (insn->code == (BPF_JMP | BPF_CALL)) {
			/* we reach here when program has bpf_call instructions
			 * and it passed bpf_check(), means that
			 * ops->get_func_proto must have been supplied, check it
			 */
			BUG_ON(!prog->aux->ops->get_func_proto);

			fn = prog->aux->ops->get_func_proto(insn->imm);
			/* all functions that have prototype and verifier allowed
			 * programs to call them, must be real in-kernel functions
			 */
			BUG_ON(!fn->func);
			insn->imm = fn->func - __bpf_call_base;
		}
	}
}

/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
	int i;

	for (i = 0; i < aux->used_map_cnt; i++)
		bpf_map_put(aux->used_maps[i]);

	kfree(aux->used_maps);
}

void bpf_prog_put(struct bpf_prog *prog)
{
	if (atomic_dec_and_test(&prog->aux->refcnt)) {
		free_used_maps(prog->aux);
		bpf_prog_free(prog);
	}
}

static int bpf_prog_release(struct inode *inode, struct file *filp)
{
	struct bpf_prog *prog = filp->private_data;

	bpf_prog_put(prog);
	return 0;
}

static const struct file_operations bpf_prog_fops = {
        .release = bpf_prog_release,
};

static struct bpf_prog *get_prog(struct fd f)
{
	struct bpf_prog *prog;

	if (!f.file)
		return ERR_PTR(-EBADF);

	if (f.file->f_op != &bpf_prog_fops) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}

	prog = f.file->private_data;

	return prog;
}

/* called by sockets/tracing/seccomp before attaching program to an event
 * pairs with bpf_prog_put()
 */
struct bpf_prog *bpf_prog_get(u32 ufd)
{
	struct fd f = fdget(ufd);
	struct bpf_prog *prog;

	prog = get_prog(f);

	if (IS_ERR(prog))
		return prog;

	atomic_inc(&prog->aux->refcnt);
	fdput(f);
	return prog;
}

/* last field in 'union bpf_attr' used by this command */
#define	BPF_PROG_LOAD_LAST_FIELD log_buf

static int bpf_prog_load(union bpf_attr *attr)
{
	enum bpf_prog_type type = attr->prog_type;
	struct bpf_prog *prog;
	int err;
	char license[128];
	bool is_gpl;

	if (CHECK_ATTR(BPF_PROG_LOAD))
		return -EINVAL;

	/* copy eBPF program license from user space */
	if (strncpy_from_user(license, u64_to_ptr(attr->license),
			      sizeof(license) - 1) < 0)
		return -EFAULT;
	license[sizeof(license) - 1] = 0;

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
	is_gpl = license_is_gpl_compatible(license);

	if (attr->insn_cnt >= BPF_MAXINSNS)
		return -EINVAL;

	/* plain bpf_prog allocation */
	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
	if (!prog)
		return -ENOMEM;

	prog->len = attr->insn_cnt;

	err = -EFAULT;
	if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
			   prog->len * sizeof(struct bpf_insn)) != 0)
		goto free_prog;

	prog->orig_prog = NULL;
	prog->jited = false;

	atomic_set(&prog->aux->refcnt, 1);
	prog->aux->is_gpl_compatible = is_gpl;

	/* find program type: socket_filter vs tracing_filter */
	err = find_prog_type(type, prog);
	if (err < 0)
		goto free_prog;

	/* run eBPF verifier */
	err = bpf_check(prog, attr);

	if (err < 0)
		goto free_used_maps;

	/* fixup BPF_CALL->imm field */
	fixup_bpf_calls(prog);

	/* eBPF program is ready to be JITed */
	bpf_prog_select_runtime(prog);

	err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);

	if (err < 0)
		/* failed to allocate fd */
		goto free_used_maps;

	return err;

free_used_maps:
	free_used_maps(prog->aux);
free_prog:
	bpf_prog_free(prog);
	return err;
}

SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
	union bpf_attr attr = {};
	int err;

	/* the syscall is limited to root temporarily. This restriction will be
	 * lifted when security audit is clean. Note that eBPF+tracing must have
	 * this restriction, since it may pass kernel data to user space
	 */
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!access_ok(VERIFY_READ, uattr, 1))
		return -EFAULT;

	if (size > PAGE_SIZE)	/* silly large */
		return -E2BIG;

	/* If we're handed a bigger struct than we know of,
	 * ensure all the unknown bits are 0 - i.e. new
	 * user-space does not rely on any kernel feature
	 * extensions we dont know about yet.
	 */
	if (size > sizeof(attr)) {
		unsigned char __user *addr;
		unsigned char __user *end;
		unsigned char val;

		addr = (void __user *)uattr + sizeof(attr);
		end  = (void __user *)uattr + size;

		for (; addr < end; addr++) {
			err = get_user(val, addr);
			if (err)
				return err;
			if (val)
				return -E2BIG;
		}
		size = sizeof(attr);
	}

	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
	if (copy_from_user(&attr, uattr, size) != 0)
		return -EFAULT;

	switch (cmd) {
	case BPF_MAP_CREATE:
		err = map_create(&attr);
		break;
	case BPF_MAP_LOOKUP_ELEM:
		err = map_lookup_elem(&attr);
		break;
	case BPF_MAP_UPDATE_ELEM:
		err = map_update_elem(&attr);
		break;
	case BPF_MAP_DELETE_ELEM:
		err = map_delete_elem(&attr);
		break;
	case BPF_MAP_GET_NEXT_KEY:
		err = map_get_next_key(&attr);
		break;
	case BPF_PROG_LOAD:
		err = bpf_prog_load(&attr);
		break;
	default:
		err = -EINVAL;
		break;
	}

	return err;
}