Blame view
kernel/bpf/syscall.c
18.9 KB
99c55f7d4
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 |
/* 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> |
251d00bf1
|
15 16 |
#include <linux/vmalloc.h> #include <linux/mmzone.h> |
99c55f7d4
|
17 |
#include <linux/anon_inodes.h> |
db20fd2b0
|
18 |
#include <linux/file.h> |
09756af46
|
19 20 |
#include <linux/license.h> #include <linux/filter.h> |
2541517c3
|
21 |
#include <linux/version.h> |
99c55f7d4
|
22 |
|
b121d1e74
|
23 |
DEFINE_PER_CPU(int, bpf_prog_active); |
1be7f75d1
|
24 |
int sysctl_unprivileged_bpf_disabled __read_mostly; |
99c55f7d4
|
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 |
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); } |
251d00bf1
|
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
void *bpf_map_area_alloc(size_t size) { /* We definitely need __GFP_NORETRY, so OOM killer doesn't * trigger under memory pressure as we really just want to * fail instead. */ const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc(size, GFP_USER | flags); if (area != NULL) return area; } return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags, PAGE_KERNEL); } void bpf_map_area_free(void *area) { kvfree(area); } |
6c9059817
|
73 74 75 76 77 78 79 80 81 82 83 84 |
int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); unsigned long memlock_limit, cur; memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; cur = atomic_long_read(&user->locked_vm); free_uid(user); if (cur + pages > memlock_limit) return -EPERM; return 0; } |
aaac3ba95
|
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 |
static int bpf_map_charge_memlock(struct bpf_map *map) { struct user_struct *user = get_current_user(); unsigned long memlock_limit; memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; atomic_long_add(map->pages, &user->locked_vm); if (atomic_long_read(&user->locked_vm) > memlock_limit) { atomic_long_sub(map->pages, &user->locked_vm); free_uid(user); return -EPERM; } map->user = user; return 0; } static void bpf_map_uncharge_memlock(struct bpf_map *map) { struct user_struct *user = map->user; atomic_long_sub(map->pages, &user->locked_vm); free_uid(user); } |
99c55f7d4
|
110 111 112 113 |
/* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); |
aaac3ba95
|
114 |
bpf_map_uncharge_memlock(map); |
99c55f7d4
|
115 116 117 |
/* implementation dependent freeing */ map->ops->map_free(map); } |
c9da161c6
|
118 119 120 121 122 123 124 |
static void bpf_map_put_uref(struct bpf_map *map) { if (atomic_dec_and_test(&map->usercnt)) { if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) bpf_fd_array_map_clear(map); } } |
99c55f7d4
|
125 126 127 128 129 130 131 132 133 134 |
/* 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); } } |
c9da161c6
|
135 |
void bpf_map_put_with_uref(struct bpf_map *map) |
99c55f7d4
|
136 |
{ |
c9da161c6
|
137 |
bpf_map_put_uref(map); |
99c55f7d4
|
138 |
bpf_map_put(map); |
c9da161c6
|
139 140 141 142 |
} static int bpf_map_release(struct inode *inode, struct file *filp) { |
61d1b6a42
|
143 144 145 146 147 148 |
struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); |
99c55f7d4
|
149 150 |
return 0; } |
f99bf205d
|
151 152 153 154 155 156 157 158 159 160 161 162 |
#ifdef CONFIG_PROC_FS static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_map *map = filp->private_data; seq_printf(m, "map_type:\t%u " "key_size:\t%u " "value_size:\t%u " |
322cea2f4
|
163 164 165 166 |
"max_entries:\t%u " "map_flags:\t%#x ", |
f99bf205d
|
167 168 169 |
map->map_type, map->key_size, map->value_size, |
322cea2f4
|
170 171 |
map->max_entries, map->map_flags); |
f99bf205d
|
172 173 |
} #endif |
99c55f7d4
|
174 |
static const struct file_operations bpf_map_fops = { |
f99bf205d
|
175 176 177 178 |
#ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, |
99c55f7d4
|
179 |
}; |
b2197755b
|
180 |
int bpf_map_new_fd(struct bpf_map *map) |
aa79781b6
|
181 182 183 184 |
{ return anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC); } |
99c55f7d4
|
185 186 187 188 189 190 191 |
/* 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 |
6c9059817
|
192 |
#define BPF_MAP_CREATE_LAST_FIELD map_flags |
99c55f7d4
|
193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
/* 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); |
c9da161c6
|
209 |
atomic_set(&map->usercnt, 1); |
99c55f7d4
|
210 |
|
aaac3ba95
|
211 212 |
err = bpf_map_charge_memlock(map); if (err) |
20b2b24f9
|
213 |
goto free_map_nouncharge; |
aaac3ba95
|
214 |
|
aa79781b6
|
215 |
err = bpf_map_new_fd(map); |
99c55f7d4
|
216 217 218 219 220 221 222 |
if (err < 0) /* failed to allocate fd */ goto free_map; return err; free_map: |
20b2b24f9
|
223 224 |
bpf_map_uncharge_memlock(map); free_map_nouncharge: |
99c55f7d4
|
225 226 227 |
map->ops->map_free(map); return err; } |
db20fd2b0
|
228 229 230 |
/* if error is returned, fd is released. * On success caller should complete fd access with matching fdput() */ |
c21012976
|
231 |
struct bpf_map *__bpf_map_get(struct fd f) |
db20fd2b0
|
232 |
{ |
db20fd2b0
|
233 234 |
if (!f.file) return ERR_PTR(-EBADF); |
db20fd2b0
|
235 236 237 238 |
if (f.file->f_op != &bpf_map_fops) { fdput(f); return ERR_PTR(-EINVAL); } |
c21012976
|
239 240 |
return f.file->private_data; } |
92117d844
|
241 242 243 244 |
/* prog's and map's refcnt limit */ #define BPF_MAX_REFCNT 32768 struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) |
c9da161c6
|
245 |
{ |
92117d844
|
246 247 248 249 |
if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) { atomic_dec(&map->refcnt); return ERR_PTR(-EBUSY); } |
c9da161c6
|
250 251 |
if (uref) atomic_inc(&map->usercnt); |
92117d844
|
252 |
return map; |
c9da161c6
|
253 254 255 |
} struct bpf_map *bpf_map_get_with_uref(u32 ufd) |
c21012976
|
256 257 258 259 260 261 262 |
{ struct fd f = fdget(ufd); struct bpf_map *map; map = __bpf_map_get(f); if (IS_ERR(map)) return map; |
92117d844
|
263 |
map = bpf_map_inc(map, true); |
c21012976
|
264 |
fdput(f); |
db20fd2b0
|
265 266 267 268 269 270 271 272 273 |
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; } |
b8cdc0517
|
274 275 276 277 |
int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; } |
db20fd2b0
|
278 279 280 281 282 283 284 285 |
/* 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; |
db20fd2b0
|
286 |
struct bpf_map *map; |
8ebe667c4
|
287 |
void *key, *value, *ptr; |
15a07b338
|
288 |
u32 value_size; |
592867bfa
|
289 |
struct fd f; |
db20fd2b0
|
290 291 292 293 |
int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; |
592867bfa
|
294 |
f = fdget(ufd); |
c21012976
|
295 |
map = __bpf_map_get(f); |
db20fd2b0
|
296 297 298 299 300 301 302 303 304 305 306 |
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; |
15a07b338
|
307 308 309 310 311 |
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; |
8ebe667c4
|
312 |
err = -ENOMEM; |
15a07b338
|
313 |
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); |
db20fd2b0
|
314 |
if (!value) |
8ebe667c4
|
315 |
goto free_key; |
15a07b338
|
316 317 318 319 |
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); |
557c0c6e7
|
320 321 |
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); |
15a07b338
|
322 323 324 325 326 327 328 329 |
} else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); if (ptr) memcpy(value, ptr, value_size); rcu_read_unlock(); err = ptr ? 0 : -ENOENT; } |
8ebe667c4
|
330 |
|
15a07b338
|
331 |
if (err) |
8ebe667c4
|
332 |
goto free_value; |
db20fd2b0
|
333 334 |
err = -EFAULT; |
15a07b338
|
335 |
if (copy_to_user(uvalue, value, value_size) != 0) |
8ebe667c4
|
336 |
goto free_value; |
db20fd2b0
|
337 338 |
err = 0; |
8ebe667c4
|
339 340 |
free_value: kfree(value); |
db20fd2b0
|
341 342 343 344 345 346 |
free_key: kfree(key); err_put: fdput(f); return err; } |
3274f5207
|
347 |
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags |
db20fd2b0
|
348 349 350 351 352 353 |
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; |
db20fd2b0
|
354 355 |
struct bpf_map *map; void *key, *value; |
15a07b338
|
356 |
u32 value_size; |
592867bfa
|
357 |
struct fd f; |
db20fd2b0
|
358 359 360 361 |
int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; |
592867bfa
|
362 |
f = fdget(ufd); |
c21012976
|
363 |
map = __bpf_map_get(f); |
db20fd2b0
|
364 365 366 367 368 369 370 371 372 373 374 |
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; |
15a07b338
|
375 376 377 378 379 |
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; |
db20fd2b0
|
380 |
err = -ENOMEM; |
15a07b338
|
381 |
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); |
db20fd2b0
|
382 383 384 385 |
if (!value) goto free_key; err = -EFAULT; |
15a07b338
|
386 |
if (copy_from_user(value, uvalue, value_size) != 0) |
db20fd2b0
|
387 |
goto free_value; |
b121d1e74
|
388 389 390 391 392 |
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from * inside bpf map update or delete otherwise deadlocks are possible */ preempt_disable(); __this_cpu_inc(bpf_prog_active); |
15a07b338
|
393 394 395 396 |
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); |
d056a7887
|
397 |
} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || |
4ed8ec521
|
398 399 |
map->map_type == BPF_MAP_TYPE_PROG_ARRAY || map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) { |
d056a7887
|
400 401 402 403 |
rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, attr->flags); rcu_read_unlock(); |
15a07b338
|
404 405 406 407 408 |
} else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); rcu_read_unlock(); } |
b121d1e74
|
409 410 |
__this_cpu_dec(bpf_prog_active); preempt_enable(); |
db20fd2b0
|
411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
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; |
db20fd2b0
|
427 |
struct bpf_map *map; |
592867bfa
|
428 |
struct fd f; |
db20fd2b0
|
429 430 431 432 433 |
void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; |
592867bfa
|
434 |
f = fdget(ufd); |
c21012976
|
435 |
map = __bpf_map_get(f); |
db20fd2b0
|
436 437 438 439 440 441 442 443 444 445 446 |
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; |
b121d1e74
|
447 448 |
preempt_disable(); __this_cpu_inc(bpf_prog_active); |
db20fd2b0
|
449 450 451 |
rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); |
b121d1e74
|
452 453 |
__this_cpu_dec(bpf_prog_active); preempt_enable(); |
db20fd2b0
|
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 |
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; |
db20fd2b0
|
470 471 |
struct bpf_map *map; void *key, *next_key; |
592867bfa
|
472 |
struct fd f; |
db20fd2b0
|
473 474 475 476 |
int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; |
592867bfa
|
477 |
f = fdget(ufd); |
c21012976
|
478 |
map = __bpf_map_get(f); |
db20fd2b0
|
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 |
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; } |
09756af46
|
516 517 518 519 520 521 522 523 524 |
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; |
24701ecea
|
525 |
prog->type = type; |
09756af46
|
526 527 528 |
return 0; } } |
24701ecea
|
529 |
|
09756af46
|
530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 |
return -EINVAL; } void bpf_register_prog_type(struct bpf_prog_type_list *tl) { list_add(&tl->list_node, &bpf_prog_types); } /* 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); } |
aaac3ba95
|
548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 |
static int bpf_prog_charge_memlock(struct bpf_prog *prog) { struct user_struct *user = get_current_user(); unsigned long memlock_limit; memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; atomic_long_add(prog->pages, &user->locked_vm); if (atomic_long_read(&user->locked_vm) > memlock_limit) { atomic_long_sub(prog->pages, &user->locked_vm); free_uid(user); return -EPERM; } prog->aux->user = user; return 0; } static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) { struct user_struct *user = prog->aux->user; atomic_long_sub(prog->pages, &user->locked_vm); free_uid(user); } |
1aacde3d2
|
572 |
static void __bpf_prog_put_rcu(struct rcu_head *rcu) |
abf2e7d6e
|
573 574 575 576 |
{ struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); free_used_maps(aux); |
aaac3ba95
|
577 |
bpf_prog_uncharge_memlock(aux->prog); |
abf2e7d6e
|
578 579 |
bpf_prog_free(aux->prog); } |
09756af46
|
580 581 |
void bpf_prog_put(struct bpf_prog *prog) { |
e9d8afa90
|
582 |
if (atomic_dec_and_test(&prog->aux->refcnt)) |
1aacde3d2
|
583 |
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); |
09756af46
|
584 |
} |
e2e9b6541
|
585 |
EXPORT_SYMBOL_GPL(bpf_prog_put); |
09756af46
|
586 587 588 589 |
static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; |
1aacde3d2
|
590 |
bpf_prog_put(prog); |
09756af46
|
591 592 593 594 595 596 |
return 0; } static const struct file_operations bpf_prog_fops = { .release = bpf_prog_release, }; |
b2197755b
|
597 |
int bpf_prog_new_fd(struct bpf_prog *prog) |
aa79781b6
|
598 599 600 601 |
{ return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } |
113214be7
|
602 |
static struct bpf_prog *____bpf_prog_get(struct fd f) |
09756af46
|
603 |
{ |
09756af46
|
604 605 |
if (!f.file) return ERR_PTR(-EBADF); |
09756af46
|
606 607 608 609 |
if (f.file->f_op != &bpf_prog_fops) { fdput(f); return ERR_PTR(-EINVAL); } |
c21012976
|
610 |
return f.file->private_data; |
09756af46
|
611 |
} |
59d3656d5
|
612 |
struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) |
92117d844
|
613 |
{ |
59d3656d5
|
614 615 |
if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { atomic_sub(i, &prog->aux->refcnt); |
92117d844
|
616 617 618 619 |
return ERR_PTR(-EBUSY); } return prog; } |
59d3656d5
|
620 621 622 623 624 625 |
EXPORT_SYMBOL_GPL(bpf_prog_add); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) { return bpf_prog_add(prog, 1); } |
92117d844
|
626 |
|
113214be7
|
627 |
static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) |
09756af46
|
628 629 630 |
{ struct fd f = fdget(ufd); struct bpf_prog *prog; |
113214be7
|
631 |
prog = ____bpf_prog_get(f); |
09756af46
|
632 633 |
if (IS_ERR(prog)) return prog; |
113214be7
|
634 635 636 637 |
if (type && prog->type != *type) { prog = ERR_PTR(-EINVAL); goto out; } |
09756af46
|
638 |
|
92117d844
|
639 |
prog = bpf_prog_inc(prog); |
113214be7
|
640 |
out: |
09756af46
|
641 642 643 |
fdput(f); return prog; } |
113214be7
|
644 645 646 647 648 649 650 651 652 653 654 |
struct bpf_prog *bpf_prog_get(u32 ufd) { return __bpf_prog_get(ufd, NULL); } struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { return __bpf_prog_get(ufd, &type); } EXPORT_SYMBOL_GPL(bpf_prog_get_type); |
09756af46
|
655 656 |
/* last field in 'union bpf_attr' used by this command */ |
2541517c3
|
657 |
#define BPF_PROG_LOAD_LAST_FIELD kern_version |
09756af46
|
658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 |
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; |
2541517c3
|
681 682 683 |
if (type == BPF_PROG_TYPE_KPROBE && attr->kern_version != LINUX_VERSION_CODE) return -EINVAL; |
1be7f75d1
|
684 685 |
if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN)) return -EPERM; |
09756af46
|
686 687 688 689 |
/* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) return -ENOMEM; |
aaac3ba95
|
690 691 692 |
err = bpf_prog_charge_memlock(prog); if (err) goto free_prog_nouncharge; |
09756af46
|
693 694 695 696 697 698 699 700 |
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; |
a91263d52
|
701 |
prog->jited = 0; |
09756af46
|
702 703 |
atomic_set(&prog->aux->refcnt, 1); |
a91263d52
|
704 |
prog->gpl_compatible = is_gpl ? 1 : 0; |
09756af46
|
705 706 707 708 709 710 711 |
/* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) goto free_prog; /* run eBPF verifier */ |
9bac3d6d5
|
712 |
err = bpf_check(&prog, attr); |
09756af46
|
713 714 715 716 |
if (err < 0) goto free_used_maps; /* eBPF program is ready to be JITed */ |
d1c55ab5e
|
717 |
prog = bpf_prog_select_runtime(prog, &err); |
04fd61ab3
|
718 719 |
if (err < 0) goto free_used_maps; |
09756af46
|
720 |
|
aa79781b6
|
721 |
err = bpf_prog_new_fd(prog); |
09756af46
|
722 723 724 725 726 727 728 729 730 |
if (err < 0) /* failed to allocate fd */ goto free_used_maps; return err; free_used_maps: free_used_maps(prog->aux); free_prog: |
aaac3ba95
|
731 732 |
bpf_prog_uncharge_memlock(prog); free_prog_nouncharge: |
09756af46
|
733 734 735 |
bpf_prog_free(prog); return err; } |
b2197755b
|
736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 |
#define BPF_OBJ_LAST_FIELD bpf_fd static int bpf_obj_pin(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_OBJ)) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) return -EINVAL; return bpf_obj_get_user(u64_to_ptr(attr->pathname)); } |
99c55f7d4
|
753 754 755 756 |
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; int err; |
1be7f75d1
|
757 |
if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled) |
99c55f7d4
|
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 |
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; |
db20fd2b0
|
797 798 799 800 801 802 803 804 805 806 807 808 |
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; |
09756af46
|
809 810 811 |
case BPF_PROG_LOAD: err = bpf_prog_load(&attr); break; |
b2197755b
|
812 813 814 815 816 817 |
case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); break; case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; |
99c55f7d4
|
818 819 820 821 822 823 824 |
default: err = -EINVAL; break; } return err; } |