summaryrefslogtreecommitdiff
path: root/kernel/bpf/arraymap.c
blob: 7c25426d3cf5699ffde545ee9a8d5e254f16f517 (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
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016,2017 Facebook
 *
 * 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/err.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
#include <linux/perf_event.h>

#include "map_in_map.h"

#define ARRAY_CREATE_FLAG_MASK \
	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)

static void bpf_array_free_percpu(struct bpf_array *array)
{
	int i;

	for (i = 0; i < array->map.max_entries; i++)
		free_percpu(array->pptrs[i]);
}

static int bpf_array_alloc_percpu(struct bpf_array *array)
{
	void __percpu *ptr;
	int i;

	for (i = 0; i < array->map.max_entries; i++) {
		ptr = __alloc_percpu_gfp(array->elem_size, 8,
					 GFP_USER | __GFP_NOWARN);
		if (!ptr) {
			bpf_array_free_percpu(array);
			return -ENOMEM;
		}
		array->pptrs[i] = ptr;
	}

	return 0;
}

/* Called from syscall */
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
	int numa_node = bpf_map_attr_numa_node(attr);
	struct bpf_array *array;
	u64 array_size;
	u32 elem_size;

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    attr->value_size == 0 ||
	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
	    (percpu && numa_node != NUMA_NO_NODE))
		return ERR_PTR(-EINVAL);

	if (attr->value_size > KMALLOC_MAX_SIZE)
		/* if value_size is bigger, the user space won't be able to
		 * access the elements.
		 */
		return ERR_PTR(-E2BIG);

	elem_size = round_up(attr->value_size, 8);

	array_size = sizeof(*array);
	if (percpu)
		array_size += (u64) attr->max_entries * sizeof(void *);
	else
		array_size += (u64) attr->max_entries * elem_size;

	/* make sure there is no u32 overflow later in round_up() */
	if (array_size >= U32_MAX - PAGE_SIZE)
		return ERR_PTR(-ENOMEM);

	/* allocate all map elements and zero-initialize them */
	array = bpf_map_area_alloc(array_size, numa_node);
	if (!array)
		return ERR_PTR(-ENOMEM);

	/* copy mandatory map attributes */
	array->map.map_type = attr->map_type;
	array->map.key_size = attr->key_size;
	array->map.value_size = attr->value_size;
	array->map.max_entries = attr->max_entries;
	array->map.map_flags = attr->map_flags;
	array->map.numa_node = numa_node;
	array->elem_size = elem_size;

	if (!percpu)
		goto out;

	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();

	if (array_size >= U32_MAX - PAGE_SIZE ||
	    bpf_array_alloc_percpu(array)) {
		bpf_map_area_free(array);
		return ERR_PTR(-ENOMEM);
	}
out:
	array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;

	return &array->map;
}

/* Called from syscall or from eBPF program */
static void *array_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;

	if (unlikely(index >= array->map.max_entries))
		return NULL;

	return array->value + array->elem_size * index;
}

/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
	struct bpf_insn *insn = insn_buf;
	u32 elem_size = round_up(map->value_size, 8);
	const int ret = BPF_REG_0;
	const int map_ptr = BPF_REG_1;
	const int index = BPF_REG_2;

	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);

	if (is_power_of_2(elem_size)) {
		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
	} else {
		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
	}
	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
	*insn++ = BPF_MOV64_IMM(ret, 0);
	return insn - insn_buf;
}

/* Called from eBPF program */
static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;

	if (unlikely(index >= array->map.max_entries))
		return NULL;

	return this_cpu_ptr(array->pptrs[index]);
}

int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;
	void __percpu *pptr;
	int cpu, off = 0;
	u32 size;

	if (unlikely(index >= array->map.max_entries))
		return -ENOENT;

	/* per_cpu areas are zero-filled and bpf programs can only
	 * access 'value_size' of them, so copying rounded areas
	 * will not leak any kernel data
	 */
	size = round_up(map->value_size, 8);
	rcu_read_lock();
	pptr = array->pptrs[index];
	for_each_possible_cpu(cpu) {
		bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
		off += size;
	}
	rcu_read_unlock();
	return 0;
}

/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = key ? *(u32 *)key : U32_MAX;
	u32 *next = (u32 *)next_key;

	if (index >= array->map.max_entries) {
		*next = 0;
		return 0;
	}

	if (index == array->map.max_entries - 1)
		return -ENOENT;

	*next = index + 1;
	return 0;
}

/* Called from syscall or from eBPF program */
static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
				 u64 map_flags)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;

	if (unlikely(map_flags > BPF_EXIST))
		/* unknown flags */
		return -EINVAL;

	if (unlikely(index >= array->map.max_entries))
		/* all elements were pre-allocated, cannot insert a new one */
		return -E2BIG;

	if (unlikely(map_flags == BPF_NOEXIST))
		/* all elements already exist */
		return -EEXIST;

	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
		memcpy(this_cpu_ptr(array->pptrs[index]),
		       value, map->value_size);
	else
		memcpy(array->value + array->elem_size * index,
		       value, map->value_size);
	return 0;
}

int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
			    u64 map_flags)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;
	void __percpu *pptr;
	int cpu, off = 0;
	u32 size;

	if (unlikely(map_flags > BPF_EXIST))
		/* unknown flags */
		return -EINVAL;

	if (unlikely(index >= array->map.max_entries))
		/* all elements were pre-allocated, cannot insert a new one */
		return -E2BIG;

	if (unlikely(map_flags == BPF_NOEXIST))
		/* all elements already exist */
		return -EEXIST;

	/* the user space will provide round_up(value_size, 8) bytes that
	 * will be copied into per-cpu area. bpf programs can only access
	 * value_size of it. During lookup the same extra bytes will be
	 * returned or zeros which were zero-filled by percpu_alloc,
	 * so no kernel data leaks possible
	 */
	size = round_up(map->value_size, 8);
	rcu_read_lock();
	pptr = array->pptrs[index];
	for_each_possible_cpu(cpu) {
		bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
		off += size;
	}
	rcu_read_unlock();
	return 0;
}

/* Called from syscall or from eBPF program */
static int array_map_delete_elem(struct bpf_map *map, void *key)
{
	return -EINVAL;
}

/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);

	/* 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 programs to complete
	 * and free the array
	 */
	synchronize_rcu();

	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
		bpf_array_free_percpu(array);

	bpf_map_area_free(array);
}

const struct bpf_map_ops array_map_ops = {
	.map_alloc = array_map_alloc,
	.map_free = array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = array_map_lookup_elem,
	.map_update_elem = array_map_update_elem,
	.map_delete_elem = array_map_delete_elem,
	.map_gen_lookup = array_map_gen_lookup,
};

const struct bpf_map_ops percpu_array_map_ops = {
	.map_alloc = array_map_alloc,
	.map_free = array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = percpu_array_map_lookup_elem,
	.map_update_elem = array_map_update_elem,
	.map_delete_elem = array_map_delete_elem,
};

static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
{
	/* only file descriptors can be stored in this type of map */
	if (attr->value_size != sizeof(u32))
		return ERR_PTR(-EINVAL);
	return array_map_alloc(attr);
}

static void fd_array_map_free(struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	int i;

	synchronize_rcu();

	/* make sure it's empty */
	for (i = 0; i < array->map.max_entries; i++)
		BUG_ON(array->ptrs[i] != NULL);

	bpf_map_area_free(array);
}

static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
{
	return NULL;
}

/* only called from syscall */
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
{
	void **elem, *ptr;
	int ret =  0;

	if (!map->ops->map_fd_sys_lookup_elem)
		return -ENOTSUPP;

	rcu_read_lock();
	elem = array_map_lookup_elem(map, key);
	if (elem && (ptr = READ_ONCE(*elem)))
		*value = map->ops->map_fd_sys_lookup_elem(ptr);
	else
		ret = -ENOENT;
	rcu_read_unlock();

	return ret;
}

/* only called from syscall */
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
				 void *key, void *value, u64 map_flags)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	void *new_ptr, *old_ptr;
	u32 index = *(u32 *)key, ufd;

	if (map_flags != BPF_ANY)
		return -EINVAL;

	if (index >= array->map.max_entries)
		return -E2BIG;

	ufd = *(u32 *)value;
	new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
	if (IS_ERR(new_ptr))
		return PTR_ERR(new_ptr);

	old_ptr = xchg(array->ptrs + index, new_ptr);
	if (old_ptr)
		map->ops->map_fd_put_ptr(old_ptr);

	return 0;
}

static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	void *old_ptr;
	u32 index = *(u32 *)key;

	if (index >= array->map.max_entries)
		return -E2BIG;

	old_ptr = xchg(array->ptrs + index, NULL);
	if (old_ptr) {
		map->ops->map_fd_put_ptr(old_ptr);
		return 0;
	} else {
		return -ENOENT;
	}
}

static void *prog_fd_array_get_ptr(struct bpf_map *map,
				   struct file *map_file, int fd)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct bpf_prog *prog = bpf_prog_get(fd);

	if (IS_ERR(prog))
		return prog;

	if (!bpf_prog_array_compatible(array, prog)) {
		bpf_prog_put(prog);
		return ERR_PTR(-EINVAL);
	}

	return prog;
}

static void prog_fd_array_put_ptr(void *ptr)
{
	bpf_prog_put(ptr);
}

static u32 prog_fd_array_sys_lookup_elem(void *ptr)
{
	return ((struct bpf_prog *)ptr)->aux->id;
}

/* decrement refcnt of all bpf_progs that are stored in this map */
void bpf_fd_array_map_clear(struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	int i;

	for (i = 0; i < array->map.max_entries; i++)
		fd_array_map_delete_elem(map, &i);
}

const struct bpf_map_ops prog_array_map_ops = {
	.map_alloc = fd_array_map_alloc,
	.map_free = fd_array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = fd_array_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = prog_fd_array_get_ptr,
	.map_fd_put_ptr = prog_fd_array_put_ptr,
	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
};

static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
						   struct file *map_file)
{
	struct bpf_event_entry *ee;

	ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
	if (ee) {
		ee->event = perf_file->private_data;
		ee->perf_file = perf_file;
		ee->map_file = map_file;
	}

	return ee;
}

static void __bpf_event_entry_free(struct rcu_head *rcu)
{
	struct bpf_event_entry *ee;

	ee = container_of(rcu, struct bpf_event_entry, rcu);
	fput(ee->perf_file);
	kfree(ee);
}

static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
{
	call_rcu(&ee->rcu, __bpf_event_entry_free);
}

static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
					 struct file *map_file, int fd)
{
	struct bpf_event_entry *ee;
	struct perf_event *event;
	struct file *perf_file;
	u64 value;

	perf_file = perf_event_get(fd);
	if (IS_ERR(perf_file))
		return perf_file;

	ee = ERR_PTR(-EOPNOTSUPP);
	event = perf_file->private_data;
	if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
		goto err_out;

	ee = bpf_event_entry_gen(perf_file, map_file);
	if (ee)
		return ee;
	ee = ERR_PTR(-ENOMEM);
err_out:
	fput(perf_file);
	return ee;
}

static void perf_event_fd_array_put_ptr(void *ptr)
{
	bpf_event_entry_free_rcu(ptr);
}

static void perf_event_fd_array_release(struct bpf_map *map,
					struct file *map_file)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct bpf_event_entry *ee;
	int i;

	rcu_read_lock();
	for (i = 0; i < array->map.max_entries; i++) {
		ee = READ_ONCE(array->ptrs[i]);
		if (ee && ee->map_file == map_file)
			fd_array_map_delete_elem(map, &i);
	}
	rcu_read_unlock();
}

const struct bpf_map_ops perf_event_array_map_ops = {
	.map_alloc = fd_array_map_alloc,
	.map_free = fd_array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = fd_array_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
	.map_release = perf_event_fd_array_release,
};

#ifdef CONFIG_CGROUPS
static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
				     struct file *map_file /* not used */,
				     int fd)
{
	return cgroup_get_from_fd(fd);
}

static void cgroup_fd_array_put_ptr(void *ptr)
{
	/* cgroup_put free cgrp after a rcu grace period */
	cgroup_put(ptr);
}

static void cgroup_fd_array_free(struct bpf_map *map)
{
	bpf_fd_array_map_clear(map);
	fd_array_map_free(map);
}

const struct bpf_map_ops cgroup_array_map_ops = {
	.map_alloc = fd_array_map_alloc,
	.map_free = cgroup_fd_array_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = fd_array_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
};
#endif

static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
{
	struct bpf_map *map, *inner_map_meta;

	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
	if (IS_ERR(inner_map_meta))
		return inner_map_meta;

	map = fd_array_map_alloc(attr);
	if (IS_ERR(map)) {
		bpf_map_meta_free(inner_map_meta);
		return map;
	}

	map->inner_map_meta = inner_map_meta;

	return map;
}

static void array_of_map_free(struct bpf_map *map)
{
	/* map->inner_map_meta is only accessed by syscall which
	 * is protected by fdget/fdput.
	 */
	bpf_map_meta_free(map->inner_map_meta);
	bpf_fd_array_map_clear(map);
	fd_array_map_free(map);
}

static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_map **inner_map = array_map_lookup_elem(map, key);

	if (!inner_map)
		return NULL;

	return READ_ONCE(*inner_map);
}

static u32 array_of_map_gen_lookup(struct bpf_map *map,
				   struct bpf_insn *insn_buf)
{
	u32 elem_size = round_up(map->value_size, 8);
	struct bpf_insn *insn = insn_buf;
	const int ret = BPF_REG_0;
	const int map_ptr = BPF_REG_1;
	const int index = BPF_REG_2;

	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
	if (is_power_of_2(elem_size))
		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
	else
		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
	*insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
	*insn++ = BPF_MOV64_IMM(ret, 0);

	return insn - insn_buf;
}

const struct bpf_map_ops array_of_maps_map_ops = {
	.map_alloc = array_of_map_alloc,
	.map_free = array_of_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = array_of_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = bpf_map_fd_get_ptr,
	.map_fd_put_ptr = bpf_map_fd_put_ptr,
	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
	.map_gen_lookup = array_of_map_gen_lookup,
};