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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
|
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 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.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <stdio.h>
#include <stdlib.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <stdbool.h>
#include "kerncompat.h"
#include "kernel-shared/extent_io.h"
#include "kernel-lib/list.h"
#include "kernel-lib/raid56.h"
#include "kernel-lib/bitmap.h"
#include "kernel-shared/ctree.h"
#include "kernel-shared/volumes.h"
#include "kernel-shared/disk-io.h"
#include "common/utils.h"
#include "common/device-utils.h"
#include "common/internal.h"
static void free_extent_buffer_final(struct extent_buffer *eb);
void extent_buffer_init_cache(struct btrfs_fs_info *fs_info)
{
fs_info->max_cache_size = total_memory() / 4;
fs_info->cache_size = 0;
INIT_LIST_HEAD(&fs_info->lru);
}
void extent_buffer_free_cache(struct btrfs_fs_info *fs_info)
{
struct extent_buffer *eb;
while(!list_empty(&fs_info->lru)) {
eb = list_entry(fs_info->lru.next, struct extent_buffer, lru);
if (eb->refs) {
/*
* Reset extent buffer refs to 1, so the
* free_extent_buffer_nocache() can free it for sure.
*/
eb->refs = 1;
fprintf(stderr,
"extent buffer leak: start %llu len %u\n",
(unsigned long long)eb->start, eb->len);
free_extent_buffer_nocache(eb);
} else {
free_extent_buffer_final(eb);
}
}
free_extent_cache_tree(&fs_info->extent_cache);
fs_info->cache_size = 0;
}
void extent_io_tree_init(struct extent_io_tree *tree)
{
cache_tree_init(&tree->state);
cache_tree_init(&tree->cache);
INIT_LIST_HEAD(&tree->lru);
}
static struct extent_state *alloc_extent_state(void)
{
struct extent_state *state;
state = malloc(sizeof(*state));
if (!state)
return NULL;
state->cache_node.objectid = 0;
state->refs = 1;
state->state = 0;
state->xprivate = 0;
return state;
}
static void btrfs_free_extent_state(struct extent_state *state)
{
state->refs--;
BUG_ON(state->refs < 0);
if (state->refs == 0)
free(state);
}
static void free_extent_state_func(struct cache_extent *cache)
{
struct extent_state *es;
es = container_of(cache, struct extent_state, cache_node);
btrfs_free_extent_state(es);
}
void extent_io_tree_cleanup(struct extent_io_tree *tree)
{
struct extent_buffer *eb;
while(!list_empty(&tree->lru)) {
eb = list_entry(tree->lru.next, struct extent_buffer, lru);
if (eb->refs) {
/*
* Reset extent buffer refs to 1, so the
* free_extent_buffer_nocache() can free it for sure.
*/
eb->refs = 1;
fprintf(stderr,
"extent buffer leak: start %llu len %u\n",
(unsigned long long)eb->start, eb->len);
free_extent_buffer_nocache(eb);
} else {
free_extent_buffer_final(eb);
}
}
cache_tree_free_extents(&tree->state, free_extent_state_func);
}
static inline void update_extent_state(struct extent_state *state)
{
state->cache_node.start = state->start;
state->cache_node.size = state->end + 1 - state->start;
}
/*
* Utility function to look for merge candidates inside a given range.
* Any extents with matching state are merged together into a single
* extent in the tree. Extents with EXTENT_IO in their state field are
* not merged
*/
static int merge_state(struct extent_io_tree *tree,
struct extent_state *state)
{
struct extent_state *other;
struct cache_extent *other_node;
if (state->state & EXTENT_IOBITS)
return 0;
other_node = prev_cache_extent(&state->cache_node);
if (other_node) {
other = container_of(other_node, struct extent_state,
cache_node);
if (other->end == state->start - 1 &&
other->state == state->state) {
state->start = other->start;
update_extent_state(state);
remove_cache_extent(&tree->state, &other->cache_node);
btrfs_free_extent_state(other);
}
}
other_node = next_cache_extent(&state->cache_node);
if (other_node) {
other = container_of(other_node, struct extent_state,
cache_node);
if (other->start == state->end + 1 &&
other->state == state->state) {
other->start = state->start;
update_extent_state(other);
remove_cache_extent(&tree->state, &state->cache_node);
btrfs_free_extent_state(state);
}
}
return 0;
}
/*
* insert an extent_state struct into the tree. 'bits' are set on the
* struct before it is inserted.
*/
static int insert_state(struct extent_io_tree *tree,
struct extent_state *state, u64 start, u64 end,
int bits)
{
int ret;
BUG_ON(end < start);
state->state |= bits;
state->start = start;
state->end = end;
update_extent_state(state);
ret = insert_cache_extent(&tree->state, &state->cache_node);
BUG_ON(ret);
merge_state(tree, state);
return 0;
}
/*
* split a given extent state struct in two, inserting the preallocated
* struct 'prealloc' as the newly created second half. 'split' indicates an
* offset inside 'orig' where it should be split.
*/
static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
struct extent_state *prealloc, u64 split)
{
int ret;
prealloc->start = orig->start;
prealloc->end = split - 1;
prealloc->state = orig->state;
update_extent_state(prealloc);
orig->start = split;
update_extent_state(orig);
ret = insert_cache_extent(&tree->state, &prealloc->cache_node);
BUG_ON(ret);
return 0;
}
/*
* clear some bits on a range in the tree.
*/
static int clear_state_bit(struct extent_io_tree *tree,
struct extent_state *state, int bits)
{
int ret = state->state & bits;
state->state &= ~bits;
if (state->state == 0) {
remove_cache_extent(&tree->state, &state->cache_node);
btrfs_free_extent_state(state);
} else {
merge_state(tree, state);
}
return ret;
}
/*
* extent_buffer_bitmap_set - set an area of a bitmap
* @eb: the extent buffer
* @start: offset of the bitmap item in the extent buffer
* @pos: bit number of the first bit
* @len: number of bits to set
*/
void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
unsigned long pos, unsigned long len)
{
u8 *p = (u8 *)eb->data + start + BIT_BYTE(pos);
const unsigned int size = pos + len;
int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
while (len >= bits_to_set) {
*p |= mask_to_set;
len -= bits_to_set;
bits_to_set = BITS_PER_BYTE;
mask_to_set = ~0;
p++;
}
if (len) {
mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
*p |= mask_to_set;
}
}
/*
* extent_buffer_bitmap_clear - clear an area of a bitmap
* @eb: the extent buffer
* @start: offset of the bitmap item in the extent buffer
* @pos: bit number of the first bit
* @len: number of bits to clear
*/
void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
unsigned long pos, unsigned long len)
{
u8 *p = (u8 *)eb->data + start + BIT_BYTE(pos);
const unsigned int size = pos + len;
int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
while (len >= bits_to_clear) {
*p &= ~mask_to_clear;
len -= bits_to_clear;
bits_to_clear = BITS_PER_BYTE;
mask_to_clear = ~0;
p++;
}
if (len) {
mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
*p &= ~mask_to_clear;
}
}
/*
* clear some bits on a range in the tree.
*/
int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, int bits)
{
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct cache_extent *node;
u64 last_end;
int err;
int set = 0;
again:
if (!prealloc) {
prealloc = alloc_extent_state();
if (!prealloc)
return -ENOMEM;
}
/*
* this search will find the extents that end after
* our range starts
*/
node = search_cache_extent(&tree->state, start);
if (!node)
goto out;
state = container_of(node, struct extent_state, cache_node);
if (state->start > end)
goto out;
last_end = state->end;
/*
* | ---- desired range ---- |
* | state | or
* | ------------- state -------------- |
*
* We need to split the extent we found, and may flip
* bits on second half.
*
* If the extent we found extends past our range, we
* just split and search again. It'll get split again
* the next time though.
*
* If the extent we found is inside our range, we clear
* the desired bit on it.
*/
if (state->start < start) {
err = split_state(tree, state, prealloc, start);
BUG_ON(err == -EEXIST);
prealloc = NULL;
if (err)
goto out;
if (state->end <= end) {
set |= clear_state_bit(tree, state, bits);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
} else {
start = state->start;
}
goto search_again;
}
/*
* | ---- desired range ---- |
* | state |
* We need to split the extent, and clear the bit
* on the first half
*/
if (state->start <= end && state->end > end) {
err = split_state(tree, state, prealloc, end + 1);
BUG_ON(err == -EEXIST);
set |= clear_state_bit(tree, prealloc, bits);
prealloc = NULL;
goto out;
}
start = state->end + 1;
set |= clear_state_bit(tree, state, bits);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
goto search_again;
out:
if (prealloc)
btrfs_free_extent_state(prealloc);
return set;
search_again:
if (start > end)
goto out;
goto again;
}
/*
* set some bits on a range in the tree.
*/
int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, int bits)
{
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct cache_extent *node;
int err = 0;
u64 last_start;
u64 last_end;
again:
if (!prealloc) {
prealloc = alloc_extent_state();
if (!prealloc)
return -ENOMEM;
}
/*
* this search will find the extents that end after
* our range starts
*/
node = search_cache_extent(&tree->state, start);
if (!node) {
err = insert_state(tree, prealloc, start, end, bits);
BUG_ON(err == -EEXIST);
prealloc = NULL;
goto out;
}
state = container_of(node, struct extent_state, cache_node);
last_start = state->start;
last_end = state->end;
/*
* | ---- desired range ---- |
* | state |
*
* Just lock what we found and keep going
*/
if (state->start == start && state->end <= end) {
state->state |= bits;
merge_state(tree, state);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
goto search_again;
}
/*
* | ---- desired range ---- |
* | state |
* or
* | ------------- state -------------- |
*
* We need to split the extent we found, and may flip bits on
* second half.
*
* If the extent we found extends past our
* range, we just split and search again. It'll get split
* again the next time though.
*
* If the extent we found is inside our range, we set the
* desired bit on it.
*/
if (state->start < start) {
err = split_state(tree, state, prealloc, start);
BUG_ON(err == -EEXIST);
prealloc = NULL;
if (err)
goto out;
if (state->end <= end) {
state->state |= bits;
start = state->end + 1;
merge_state(tree, state);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
} else {
start = state->start;
}
goto search_again;
}
/*
* | ---- desired range ---- |
* | state | or | state |
*
* There's a hole, we need to insert something in it and
* ignore the extent we found.
*/
if (state->start > start) {
u64 this_end;
if (end < last_start)
this_end = end;
else
this_end = last_start -1;
err = insert_state(tree, prealloc, start, this_end,
bits);
BUG_ON(err == -EEXIST);
prealloc = NULL;
if (err)
goto out;
start = this_end + 1;
goto search_again;
}
/*
* | ---- desired range ---- |
* | ---------- state ---------- |
* We need to split the extent, and set the bit
* on the first half
*/
err = split_state(tree, state, prealloc, end + 1);
BUG_ON(err == -EEXIST);
state->state |= bits;
merge_state(tree, prealloc);
prealloc = NULL;
out:
if (prealloc)
btrfs_free_extent_state(prealloc);
return err;
search_again:
if (start > end)
goto out;
goto again;
}
int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end)
{
return set_extent_bits(tree, start, end, EXTENT_DIRTY);
}
int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end)
{
return clear_extent_bits(tree, start, end, EXTENT_DIRTY);
}
int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, int bits)
{
struct cache_extent *node;
struct extent_state *state;
int ret = 1;
/*
* this search will find all the extents that end after
* our range starts.
*/
node = search_cache_extent(&tree->state, start);
if (!node)
goto out;
while(1) {
state = container_of(node, struct extent_state, cache_node);
if (state->end >= start && (state->state & bits)) {
*start_ret = state->start;
*end_ret = state->end;
ret = 0;
break;
}
node = next_cache_extent(node);
if (!node)
break;
}
out:
return ret;
}
int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
int bits, int filled)
{
struct extent_state *state = NULL;
struct cache_extent *node;
int bitset = 0;
node = search_cache_extent(&tree->state, start);
while (node && start <= end) {
state = container_of(node, struct extent_state, cache_node);
if (filled && state->start > start) {
bitset = 0;
break;
}
if (state->start > end)
break;
if (state->state & bits) {
bitset = 1;
if (!filled)
break;
} else if (filled) {
bitset = 0;
break;
}
start = state->end + 1;
if (start > end)
break;
node = next_cache_extent(node);
if (!node) {
if (filled)
bitset = 0;
break;
}
}
return bitset;
}
static struct extent_buffer *__alloc_extent_buffer(struct btrfs_fs_info *info,
u64 bytenr, u32 blocksize)
{
struct extent_buffer *eb;
eb = calloc(1, sizeof(struct extent_buffer) + blocksize);
if (!eb)
return NULL;
eb->start = bytenr;
eb->len = blocksize;
eb->refs = 1;
eb->flags = 0;
eb->cache_node.start = bytenr;
eb->cache_node.size = blocksize;
eb->fs_info = info;
INIT_LIST_HEAD(&eb->recow);
INIT_LIST_HEAD(&eb->lru);
memset_extent_buffer(eb, 0, 0, blocksize);
return eb;
}
struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
{
struct extent_buffer *new;
new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
if (!new)
return NULL;
copy_extent_buffer(new, src, 0, 0, src->len);
new->flags |= EXTENT_BUFFER_DUMMY;
return new;
}
static void free_extent_buffer_final(struct extent_buffer *eb)
{
BUG_ON(eb->refs);
list_del_init(&eb->lru);
if (!(eb->flags & EXTENT_BUFFER_DUMMY)) {
remove_cache_extent(&eb->fs_info->extent_cache, &eb->cache_node);
BUG_ON(eb->fs_info->cache_size < eb->len);
eb->fs_info->cache_size -= eb->len;
}
free(eb);
}
static void free_extent_buffer_internal(struct extent_buffer *eb, bool free_now)
{
if (!eb || IS_ERR(eb))
return;
eb->refs--;
BUG_ON(eb->refs < 0);
if (eb->refs == 0) {
if (eb->flags & EXTENT_BUFFER_DIRTY) {
warning(
"dirty eb leak (aborted trans): start %llu len %u",
eb->start, eb->len);
}
list_del_init(&eb->recow);
if (eb->flags & EXTENT_BUFFER_DUMMY || free_now)
free_extent_buffer_final(eb);
}
}
void free_extent_buffer(struct extent_buffer *eb)
{
free_extent_buffer_internal(eb, 0);
}
void free_extent_buffer_nocache(struct extent_buffer *eb)
{
free_extent_buffer_internal(eb, 1);
}
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 bytenr, u32 blocksize)
{
struct extent_buffer *eb = NULL;
struct cache_extent *cache;
cache = lookup_cache_extent(&fs_info->extent_cache, bytenr, blocksize);
if (cache && cache->start == bytenr &&
cache->size == blocksize) {
eb = container_of(cache, struct extent_buffer, cache_node);
list_move_tail(&eb->lru, &fs_info->lru);
eb->refs++;
}
return eb;
}
struct extent_buffer *find_first_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
{
struct extent_buffer *eb = NULL;
struct cache_extent *cache;
cache = search_cache_extent(&fs_info->extent_cache, start);
if (cache) {
eb = container_of(cache, struct extent_buffer, cache_node);
list_move_tail(&eb->lru, &fs_info->lru);
eb->refs++;
}
return eb;
}
static void trim_extent_buffer_cache(struct btrfs_fs_info *fs_info)
{
struct extent_buffer *eb, *tmp;
list_for_each_entry_safe(eb, tmp, &fs_info->lru, lru) {
if (eb->refs == 0)
free_extent_buffer_final(eb);
if (fs_info->cache_size <= ((fs_info->max_cache_size * 9) / 10))
break;
}
}
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 bytenr, u32 blocksize)
{
struct extent_buffer *eb;
struct cache_extent *cache;
cache = lookup_cache_extent(&fs_info->extent_cache, bytenr, blocksize);
if (cache && cache->start == bytenr &&
cache->size == blocksize) {
eb = container_of(cache, struct extent_buffer, cache_node);
list_move_tail(&eb->lru, &fs_info->lru);
eb->refs++;
} else {
int ret;
if (cache) {
eb = container_of(cache, struct extent_buffer,
cache_node);
free_extent_buffer(eb);
}
eb = __alloc_extent_buffer(fs_info, bytenr, blocksize);
if (!eb)
return NULL;
ret = insert_cache_extent(&fs_info->extent_cache, &eb->cache_node);
if (ret) {
free(eb);
return NULL;
}
list_add_tail(&eb->lru, &fs_info->lru);
fs_info->cache_size += blocksize;
if (fs_info->cache_size >= fs_info->max_cache_size)
trim_extent_buffer_cache(fs_info);
}
return eb;
}
/*
* Allocate a dummy extent buffer which won't be inserted into extent buffer
* cache.
*
* This mostly allows super block read write using existing eb infrastructure
* without pulluting the eb cache.
*
* This is especially important to avoid injecting eb->start == SZ_64K, as
* fuzzed image could have invalid tree bytenr covers super block range,
* and cause ref count underflow.
*/
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
u64 bytenr, u32 blocksize)
{
struct extent_buffer *ret;
ret = __alloc_extent_buffer(fs_info, bytenr, blocksize);
if (!ret)
return NULL;
ret->flags |= EXTENT_BUFFER_DUMMY;
return ret;
}
static int read_raid56(struct btrfs_fs_info *fs_info, void *buf, u64 logical,
u64 len, int mirror, struct btrfs_multi_bio *multi,
u64 *raid_map)
{
const int tolerance = (multi->type & BTRFS_RAID_RAID6 ? 2 : 1);
const int num_stripes = multi->num_stripes;
const u64 full_stripe_start = raid_map[0];
void **pointers = NULL;
unsigned long *failed_stripe_bitmap = NULL;
int failed_a = -1;
int failed_b = -1;
int i;
int ret;
/* Only read repair should go this path */
ASSERT(mirror > 1);
ASSERT(raid_map);
/* The read length should be inside one stripe */
ASSERT(len <= BTRFS_STRIPE_LEN);
pointers = calloc(num_stripes, sizeof(void *));
if (!pointers) {
ret = -ENOMEM;
goto out;
}
/* Allocate memory for the full stripe */
for (i = 0; i < num_stripes; i++) {
pointers[i] = malloc(BTRFS_STRIPE_LEN);
if (!pointers[i]) {
ret = -ENOMEM;
goto out;
}
}
failed_stripe_bitmap = bitmap_zalloc(num_stripes);
if (!failed_stripe_bitmap) {
ret = -ENOMEM;
goto out;
}
/*
* Read the full stripe.
*
* The stripes in @multi is not rotated, thus can be used to read from
* disk directly.
*/
for (i = 0; i < num_stripes; i++) {
ret = btrfs_pread(multi->stripes[i].dev->fd, pointers[i],
BTRFS_STRIPE_LEN, multi->stripes[i].physical,
fs_info->zoned);
if (ret < BTRFS_STRIPE_LEN)
set_bit(i, failed_stripe_bitmap);
}
/*
* Get the failed index.
*
* Since we're reading using mirror_num > 1 already, it means the data
* stripe where @logical lies in is definitely corrupted.
*/
set_bit((logical - full_stripe_start) / BTRFS_STRIPE_LEN, failed_stripe_bitmap);
/*
* For RAID6, we don't have good way to exhaust all the combinations,
* so here we can only go through the map to see if we have missing devices.
*
* If we only have one failed stripe (marked by above set_bit()), then
* we have no better idea, fallback to use P corruption.
*/
if (multi->type & BTRFS_BLOCK_GROUP_RAID6 &&
bitmap_weight(failed_stripe_bitmap, num_stripes) < 2)
set_bit(num_stripes - 2, failed_stripe_bitmap);
/* Damaged beyond repair already. */
if (bitmap_weight(failed_stripe_bitmap, num_stripes) > tolerance) {
ret = -EIO;
goto out;
}
for_each_set_bit(i, failed_stripe_bitmap, num_stripes) {
if (failed_a < 0)
failed_a = i;
else if (failed_b < 0)
failed_b = i;
}
/* Rebuild the full stripe */
ret = raid56_recov(num_stripes, BTRFS_STRIPE_LEN, multi->type,
failed_a, failed_b, pointers);
ASSERT(ret == 0);
/* Now copy the data back to original buf */
memcpy(buf, pointers[failed_a] + (logical - full_stripe_start) %
BTRFS_STRIPE_LEN, len);
ret = 0;
out:
free(failed_stripe_bitmap);
for (i = 0; i < num_stripes; i++)
free(pointers[i]);
free(pointers);
return ret;
}
int read_data_from_disk(struct btrfs_fs_info *info, void *buf, u64 logical,
u64 *len, int mirror)
{
struct btrfs_multi_bio *multi = NULL;
struct btrfs_device *device;
u64 read_len = *len;
u64 *raid_map = NULL;
int ret;
ret = btrfs_map_block(info, READ, logical, &read_len, &multi, mirror,
&raid_map);
if (ret) {
fprintf(stderr, "Couldn't map the block %llu\n", logical);
return -EIO;
}
read_len = min(*len, read_len);
/* We need to rebuild from P/Q */
if (mirror > 1 && multi->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
ret = read_raid56(info, buf, logical, read_len, mirror, multi,
raid_map);
free(multi);
free(raid_map);
*len = read_len;
return ret;
}
free(raid_map);
device = multi->stripes[0].dev;
if (device->fd <= 0) {
kfree(multi);
return -EIO;
}
ret = btrfs_pread(device->fd, buf, read_len,
multi->stripes[0].physical, info->zoned);
kfree(multi);
if (ret < 0) {
fprintf(stderr, "Error reading %llu, %d\n", logical,
ret);
return ret;
}
if (ret != read_len) {
fprintf(stderr,
"Short read for %llu, read %d, read_len %llu\n",
logical, ret, read_len);
return -EIO;
}
*len = read_len;
return 0;
}
/*
* Write the data in @buf to logical bytenr @offset.
*
* Such data will be written to all mirrors and RAID56 P/Q will also be
* properly handled.
*/
int write_data_to_disk(struct btrfs_fs_info *info, void *buf, u64 offset,
u64 bytes)
{
struct btrfs_multi_bio *multi = NULL;
struct btrfs_device *device;
u64 bytes_left = bytes;
u64 this_len;
u64 total_write = 0;
u64 *raid_map = NULL;
u64 dev_bytenr;
int dev_nr;
int ret = 0;
while (bytes_left > 0) {
this_len = bytes_left;
dev_nr = 0;
ret = btrfs_map_block(info, WRITE, offset, &this_len, &multi,
0, &raid_map);
if (ret) {
fprintf(stderr, "Couldn't map the block %llu\n",
offset);
return -EIO;
}
if (raid_map) {
struct extent_buffer *eb;
u64 stripe_len = this_len;
this_len = min(this_len, bytes_left);
this_len = min(this_len, (u64)info->nodesize);
eb = malloc(sizeof(struct extent_buffer) + this_len);
if (!eb) {
error_msg(ERROR_MSG_MEMORY, "extent buffer");
ret = -ENOMEM;
goto out;
}
memset(eb, 0, sizeof(struct extent_buffer) + this_len);
eb->start = offset;
eb->len = this_len;
memcpy(eb->data, buf + total_write, this_len);
ret = write_raid56_with_parity(info, eb, multi,
stripe_len, raid_map);
BUG_ON(ret < 0);
free(eb);
kfree(raid_map);
raid_map = NULL;
} else while (dev_nr < multi->num_stripes) {
device = multi->stripes[dev_nr].dev;
if (device->fd <= 0) {
kfree(multi);
return -EIO;
}
dev_bytenr = multi->stripes[dev_nr].physical;
this_len = min(this_len, bytes_left);
dev_nr++;
device->total_ios++;
ret = btrfs_pwrite(device->fd, buf + total_write,
this_len, dev_bytenr, info->zoned);
if (ret != this_len) {
if (ret < 0) {
fprintf(stderr, "Error writing to "
"device %d\n", errno);
ret = -errno;
kfree(multi);
return ret;
} else {
fprintf(stderr, "Short write\n");
kfree(multi);
return -EIO;
}
}
}
BUG_ON(bytes_left < this_len);
bytes_left -= this_len;
offset += this_len;
total_write += this_len;
kfree(multi);
multi = NULL;
}
return 0;
out:
kfree(raid_map);
return ret;
}
int set_extent_buffer_dirty(struct extent_buffer *eb)
{
struct extent_io_tree *tree = &eb->fs_info->dirty_buffers;
if (!(eb->flags & EXTENT_BUFFER_DIRTY)) {
eb->flags |= EXTENT_BUFFER_DIRTY;
set_extent_dirty(tree, eb->start, eb->start + eb->len - 1);
extent_buffer_get(eb);
}
return 0;
}
int clear_extent_buffer_dirty(struct extent_buffer *eb)
{
struct extent_io_tree *tree = &eb->fs_info->dirty_buffers;
if (eb->flags & EXTENT_BUFFER_DIRTY) {
eb->flags &= ~EXTENT_BUFFER_DIRTY;
clear_extent_dirty(tree, eb->start, eb->start + eb->len - 1);
free_extent_buffer(eb);
}
return 0;
}
int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
unsigned long start, unsigned long len)
{
return memcmp(eb->data + start, ptrv, len);
}
void read_extent_buffer(const struct extent_buffer *eb, void *dst,
unsigned long start, unsigned long len)
{
memcpy(dst, eb->data + start, len);
}
void write_extent_buffer(const struct extent_buffer *eb, const void *src,
unsigned long start, unsigned long len)
{
memcpy((void *)eb->data + start, src, len);
}
void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len)
{
memcpy(dst->data + dst_offset, src->data + src_offset, len);
}
void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
unsigned long src_offset, unsigned long len)
{
memmove(dst->data + dst_offset, dst->data + src_offset, len);
}
void memset_extent_buffer(struct extent_buffer *eb, char c,
unsigned long start, unsigned long len)
{
memset(eb->data + start, c, len);
}
int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
unsigned long nr)
{
return le_test_bit(nr, (u8 *)eb->data + start);
}
|