summaryrefslogtreecommitdiff
path: root/kernel/bpf/stackmap.c
blob: 57eeb1234b67e7dabd555e9562b0a0b59cd57abb (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
/* Copyright (c) 2016 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.
 */
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include <linux/elf.h>
#include <linux/pagemap.h>
#include "percpu_freelist.h"

#define STACK_CREATE_FLAG_MASK					\
	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\
	 BPF_F_STACK_BUILD_ID)

struct stack_map_bucket {
	struct pcpu_freelist_node fnode;
	u32 hash;
	u32 nr;
	u64 data[];
};

struct bpf_stack_map {
	struct bpf_map map;
	void *elems;
	struct pcpu_freelist freelist;
	u32 n_buckets;
	struct stack_map_bucket *buckets[];
};

static inline bool stack_map_use_build_id(struct bpf_map *map)
{
	return (map->map_flags & BPF_F_STACK_BUILD_ID);
}

static inline int stack_map_data_size(struct bpf_map *map)
{
	return stack_map_use_build_id(map) ?
		sizeof(struct bpf_stack_build_id) : sizeof(u64);
}

static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
{
	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
	int err;

	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,
					 smap->map.numa_node);
	if (!smap->elems)
		return -ENOMEM;

	err = pcpu_freelist_init(&smap->freelist);
	if (err)
		goto free_elems;

	pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
			       smap->map.max_entries);
	return 0;

free_elems:
	bpf_map_area_free(smap->elems);
	return err;
}

/* Called from syscall */
static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
{
	u32 value_size = attr->value_size;
	struct bpf_stack_map *smap;
	u64 cost, n_buckets;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return ERR_PTR(-EPERM);

	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
		return ERR_PTR(-EINVAL);

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    value_size < 8 || value_size % 8)
		return ERR_PTR(-EINVAL);

	BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64));
	if (attr->map_flags & BPF_F_STACK_BUILD_ID) {
		if (value_size % sizeof(struct bpf_stack_build_id) ||
		    value_size / sizeof(struct bpf_stack_build_id)
		    > sysctl_perf_event_max_stack)
			return ERR_PTR(-EINVAL);
	} else if (value_size / 8 > sysctl_perf_event_max_stack)
		return ERR_PTR(-EINVAL);

	/* hash table size must be power of 2 */
	n_buckets = roundup_pow_of_two(attr->max_entries);

	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
	if (cost >= U32_MAX - PAGE_SIZE)
		return ERR_PTR(-E2BIG);

	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
	if (!smap)
		return ERR_PTR(-ENOMEM);

	err = -E2BIG;
	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
	if (cost >= U32_MAX - PAGE_SIZE)
		goto free_smap;

	bpf_map_init_from_attr(&smap->map, attr);
	smap->map.value_size = value_size;
	smap->n_buckets = n_buckets;
	smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;

	err = bpf_map_precharge_memlock(smap->map.pages);
	if (err)
		goto free_smap;

	err = get_callchain_buffers(sysctl_perf_event_max_stack);
	if (err)
		goto free_smap;

	err = prealloc_elems_and_freelist(smap);
	if (err)
		goto put_buffers;

	return &smap->map;

put_buffers:
	put_callchain_buffers();
free_smap:
	bpf_map_area_free(smap);
	return ERR_PTR(err);
}

#define BPF_BUILD_ID 3
/*
 * Parse build id from the note segment. This logic can be shared between
 * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
 * identical.
 */
static inline int stack_map_parse_build_id(void *page_addr,
					   unsigned char *build_id,
					   void *note_start,
					   Elf32_Word note_size)
{
	Elf32_Word note_offs = 0, new_offs;

	/* check for overflow */
	if (note_start < page_addr || note_start + note_size < note_start)
		return -EINVAL;

	/* only supports note that fits in the first page */
	if (note_start + note_size > page_addr + PAGE_SIZE)
		return -EINVAL;

	while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);

		if (nhdr->n_type == BPF_BUILD_ID &&
		    nhdr->n_namesz == sizeof("GNU") &&
		    nhdr->n_descsz == BPF_BUILD_ID_SIZE) {
			memcpy(build_id,
			       note_start + note_offs +
			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
			       BPF_BUILD_ID_SIZE);
			return 0;
		}
		new_offs = note_offs + sizeof(Elf32_Nhdr) +
			ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
		if (new_offs <= note_offs)  /* overflow */
			break;
		note_offs = new_offs;
	}
	return -EINVAL;
}

/* Parse build ID from 32-bit ELF */
static int stack_map_get_build_id_32(void *page_addr,
				     unsigned char *build_id)
{
	Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
	Elf32_Phdr *phdr;
	int i;

	/* only supports phdr that fits in one page */
	if (ehdr->e_phnum >
	    (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
		return -EINVAL;

	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));

	for (i = 0; i < ehdr->e_phnum; ++i)
		if (phdr[i].p_type == PT_NOTE)
			return stack_map_parse_build_id(page_addr, build_id,
					page_addr + phdr[i].p_offset,
					phdr[i].p_filesz);
	return -EINVAL;
}

/* Parse build ID from 64-bit ELF */
static int stack_map_get_build_id_64(void *page_addr,
				     unsigned char *build_id)
{
	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
	Elf64_Phdr *phdr;
	int i;

	/* only supports phdr that fits in one page */
	if (ehdr->e_phnum >
	    (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
		return -EINVAL;

	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));

	for (i = 0; i < ehdr->e_phnum; ++i)
		if (phdr[i].p_type == PT_NOTE)
			return stack_map_parse_build_id(page_addr, build_id,
					page_addr + phdr[i].p_offset,
					phdr[i].p_filesz);
	return -EINVAL;
}

/* Parse build ID of ELF file mapped to vma */
static int stack_map_get_build_id(struct vm_area_struct *vma,
				  unsigned char *build_id)
{
	Elf32_Ehdr *ehdr;
	struct page *page;
	void *page_addr;
	int ret;

	/* only works for page backed storage  */
	if (!vma->vm_file)
		return -EINVAL;

	page = find_get_page(vma->vm_file->f_mapping, 0);
	if (!page)
		return -EFAULT;	/* page not mapped */

	ret = -EINVAL;
	page_addr = page_address(page);
	ehdr = (Elf32_Ehdr *)page_addr;

	/* compare magic x7f "ELF" */
	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
		goto out;

	/* only support executable file and shared object file */
	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN)
		goto out;

	if (ehdr->e_ident[EI_CLASS] == ELFCLASS32)
		ret = stack_map_get_build_id_32(page_addr, build_id);
	else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64)
		ret = stack_map_get_build_id_64(page_addr, build_id);
out:
	put_page(page);
	return ret;
}

static void stack_map_get_build_id_offset(struct bpf_map *map,
					  struct stack_map_bucket *bucket,
					  u64 *ips, u32 trace_nr, bool user)
{
	int i;
	struct vm_area_struct *vma;
	struct bpf_stack_build_id *id_offs;

	bucket->nr = trace_nr;
	id_offs = (struct bpf_stack_build_id *)bucket->data;

	/*
	 * We cannot do up_read() in nmi context, so build_id lookup is
	 * only supported for non-nmi events. If at some point, it is
	 * possible to run find_vma() without taking the semaphore, we
	 * would like to allow build_id lookup in nmi context.
	 *
	 * Same fallback is used for kernel stack (!user) on a stackmap
	 * with build_id.
	 */
	if (!user || !current || !current->mm || in_nmi() ||
	    down_read_trylock(&current->mm->mmap_sem) == 0) {
		/* cannot access current->mm, fall back to ips */
		for (i = 0; i < trace_nr; i++) {
			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
			id_offs[i].ip = ips[i];
		}
		return;
	}

	for (i = 0; i < trace_nr; i++) {
		vma = find_vma(current->mm, ips[i]);
		if (!vma || stack_map_get_build_id(vma, id_offs[i].build_id)) {
			/* per entry fall back to ips */
			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
			id_offs[i].ip = ips[i];
			continue;
		}
		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
			- vma->vm_start;
		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
	}
	up_read(&current->mm->mmap_sem);
}

BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
	   u64, flags)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
	struct perf_callchain_entry *trace;
	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
	u32 max_depth = map->value_size / stack_map_data_size(map);
	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
	u32 hash, id, trace_nr, trace_len;
	bool user = flags & BPF_F_USER_STACK;
	bool kernel = !user;
	u64 *ips;
	bool hash_matches;

	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
		return -EINVAL;

	trace = get_perf_callchain(regs, init_nr, kernel, user,
				   sysctl_perf_event_max_stack, false, false);

	if (unlikely(!trace))
		/* couldn't fetch the stack trace */
		return -EFAULT;

	/* get_perf_callchain() guarantees that trace->nr >= init_nr
	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
	 */
	trace_nr = trace->nr - init_nr;

	if (trace_nr <= skip)
		/* skipping more than usable stack trace */
		return -EFAULT;

	trace_nr -= skip;
	trace_len = trace_nr * sizeof(u64);
	ips = trace->ip + skip + init_nr;
	hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
	id = hash & (smap->n_buckets - 1);
	bucket = READ_ONCE(smap->buckets[id]);

	hash_matches = bucket && bucket->hash == hash;
	/* fast cmp */
	if (hash_matches && flags & BPF_F_FAST_STACK_CMP)
		return id;

	if (stack_map_use_build_id(map)) {
		/* for build_id+offset, pop a bucket before slow cmp */
		new_bucket = (struct stack_map_bucket *)
			pcpu_freelist_pop(&smap->freelist);
		if (unlikely(!new_bucket))
			return -ENOMEM;
		stack_map_get_build_id_offset(map, new_bucket, ips,
					      trace_nr, user);
		trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
		if (hash_matches && bucket->nr == trace_nr &&
		    memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
			pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
			return id;
		}
		if (bucket && !(flags & BPF_F_REUSE_STACKID)) {
			pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
			return -EEXIST;
		}
	} else {
		if (hash_matches && bucket->nr == trace_nr &&
		    memcmp(bucket->data, ips, trace_len) == 0)
			return id;
		if (bucket && !(flags & BPF_F_REUSE_STACKID))
			return -EEXIST;

		new_bucket = (struct stack_map_bucket *)
			pcpu_freelist_pop(&smap->freelist);
		if (unlikely(!new_bucket))
			return -ENOMEM;
		memcpy(new_bucket->data, ips, trace_len);
	}

	new_bucket->hash = hash;
	new_bucket->nr = trace_nr;

	old_bucket = xchg(&smap->buckets[id], new_bucket);
	if (old_bucket)
		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
	return id;
}

const struct bpf_func_proto bpf_get_stackid_proto = {
	.func		= bpf_get_stackid,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

/* Called from eBPF program */
static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
{
	return NULL;
}

/* Called from syscall */
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
	struct stack_map_bucket *bucket, *old_bucket;
	u32 id = *(u32 *)key, trace_len;

	if (unlikely(id >= smap->n_buckets))
		return -ENOENT;

	bucket = xchg(&smap->buckets[id], NULL);
	if (!bucket)
		return -ENOENT;

	trace_len = bucket->nr * stack_map_data_size(map);
	memcpy(value, bucket->data, trace_len);
	memset(value + trace_len, 0, map->value_size - trace_len);

	old_bucket = xchg(&smap->buckets[id], bucket);
	if (old_bucket)
		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
	return 0;
}

static int stack_map_get_next_key(struct bpf_map *map, void *key,
				  void *next_key)
{
	struct bpf_stack_map *smap = container_of(map,
						  struct bpf_stack_map, map);
	u32 id;

	WARN_ON_ONCE(!rcu_read_lock_held());

	if (!key) {
		id = 0;
	} else {
		id = *(u32 *)key;
		if (id >= smap->n_buckets || !smap->buckets[id])
			id = 0;
		else
			id++;
	}

	while (id < smap->n_buckets && !smap->buckets[id])
		id++;

	if (id >= smap->n_buckets)
		return -ENOENT;

	*(u32 *)next_key = id;
	return 0;
}

static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
				 u64 map_flags)
{
	return -EINVAL;
}

/* Called from syscall or from eBPF program */
static int stack_map_delete_elem(struct bpf_map *map, void *key)
{
	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
	struct stack_map_bucket *old_bucket;
	u32 id = *(u32 *)key;

	if (unlikely(id >= smap->n_buckets))
		return -E2BIG;

	old_bucket = xchg(&smap->buckets[id], NULL);
	if (old_bucket) {
		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
		return 0;
	} else {
		return -ENOENT;
	}
}

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

	/* wait for bpf programs to complete before freeing stack map */
	synchronize_rcu();

	bpf_map_area_free(smap->elems);
	pcpu_freelist_destroy(&smap->freelist);
	bpf_map_area_free(smap);
	put_callchain_buffers();
}

const struct bpf_map_ops stack_map_ops = {
	.map_alloc = stack_map_alloc,
	.map_free = stack_map_free,
	.map_get_next_key = stack_map_get_next_key,
	.map_lookup_elem = stack_map_lookup_elem,
	.map_update_elem = stack_map_update_elem,
	.map_delete_elem = stack_map_delete_elem,
};