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 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771
|
/*
* Copyright (C) 2014 SUSE. 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.
*
* Authors: Mark Fasheh <mfasheh@suse.de>
*/
#include "kerncompat.h"
#include <stdio.h>
#include <stdlib.h>
#include <errno.h>
#include "kernel-lib/list.h"
#include "kernel-lib/rbtree.h"
#include "kernel-lib/rbtree_types.h"
#include "kernel-shared/accessors.h"
#include "kernel-shared/uapi/btrfs_tree.h"
#include "kernel-shared/ctree.h"
#include "kernel-shared/disk-io.h"
#include "kernel-shared/ulist.h"
#include "kernel-shared/extent_io.h"
#include "kernel-shared/transaction.h"
#include "kernel-shared/tree-checker.h"
#include "common/messages.h"
#include "common/rbtree-utils.h"
#include "check/repair.h"
#include "check/qgroup-verify.h"
static u64 *qgroup_item_count;
void qgroup_set_item_count_ptr(u64 *item_count_ptr)
{
qgroup_item_count = item_count_ptr;
}
/*#define QGROUP_VERIFY_DEBUG*/
static unsigned long tot_extents_scanned = 0;
static struct qgroup_count *find_count(u64 qgroupid);
struct qgroup_info {
u64 referenced;
u64 referenced_compressed;
u64 exclusive;
u64 exclusive_compressed;
};
struct qgroup_count {
u64 qgroupid;
int subvol_exists;
struct btrfs_disk_key key;
struct qgroup_info diskinfo;
struct qgroup_info info;
struct rb_node rb_node;
/* Parents when we are a child group */
struct list_head groups;
/*
* Children when we are a parent group (not currently used but
* maintained to mirror kernel handling of qgroups)
*/
struct list_head members;
u64 cur_refcnt;
struct list_head bad_list;
};
static struct counts_tree {
struct rb_root root;
unsigned int num_groups;
unsigned int rescan_running:1;
unsigned int qgroup_inconsist:1;
unsigned int simple:1;
u64 enable_gen;
u64 scan_progress;
} counts = { .root = RB_ROOT };
static LIST_HEAD(bad_qgroups);
static struct rb_root by_bytenr = RB_ROOT;
/*
* Glue structure to represent the relations between qgroups. Mirrored
* from kernel.
*/
struct btrfs_qgroup_list {
struct list_head next_group;
struct list_head next_member;
struct qgroup_count *group; /* Parent group */
struct qgroup_count *member;
};
/* Allow us to reset ref counts during accounting without zeroing each group. */
static u64 qgroup_seq = 1ULL;
static inline void update_cur_refcnt(struct qgroup_count *c)
{
if (c->cur_refcnt < qgroup_seq)
c->cur_refcnt = qgroup_seq;
c->cur_refcnt++;
}
static inline u64 group_get_cur_refcnt(struct qgroup_count *c)
{
if (c->cur_refcnt < qgroup_seq)
return 0;
return c->cur_refcnt - qgroup_seq;
}
static void inc_qgroup_seq(int root_count)
{
qgroup_seq += root_count + 1;
}
/*
* List of interior tree blocks. We walk this list after loading the
* extent tree to resolve implied refs. For each interior node we'll
* place a shared ref in the ref tree against each child object. This
* allows the shared ref resolving code to do the actual work later of
* finding roots to account against.
*
* An implied ref is when a tree block has refs on it that may not
* exist in any of its child nodes. Even though the refs might not
* exist further down the tree, the fact that our interior node has a
* ref means we need to account anything below it to all its roots.
*/
static struct ulist *tree_blocks = NULL; /* unode->val = bytenr, ->aux
* = tree_block pointer */
struct tree_block {
int level;
u64 num_bytes;
};
struct ref {
u64 bytenr;
u64 num_bytes;
u64 parent;
u64 root;
struct rb_node bytenr_node;
};
#ifdef QGROUP_VERIFY_DEBUG
static void print_ref(struct ref *ref)
{
printf("bytenr: %llu\t\tnum_bytes: %llu\t\t parent: %llu\t\t"
"root: %llu\n", ref->bytenr, ref->num_bytes,
ref->parent, ref->root);
}
static void print_all_refs(void)
{
unsigned long count = 0;
struct ref *ref;
struct rb_node *node;
node = rb_first(&by_bytenr);
while (node) {
ref = rb_entry(node, struct ref, bytenr_node);
print_ref(ref);
count++;
node = rb_next(node);
}
printf("%lu extents scanned with %lu refs in total.\n",
tot_extents_scanned, count);
}
#endif
/*
* Store by bytenr in rbtree
*
* The tree is sorted in ascending order by bytenr, then parent, then
* root. Since full refs have a parent == 0, those will come before
* shared refs.
*/
static int compare_ref(struct ref *orig, u64 bytenr, u64 root, u64 parent)
{
if (bytenr < orig->bytenr)
return -1;
if (bytenr > orig->bytenr)
return 1;
if (parent < orig->parent)
return -1;
if (parent > orig->parent)
return 1;
if (root < orig->root)
return -1;
if (root > orig->root)
return 1;
return 0;
}
/*
* insert a new ref into the tree. returns the existing ref entry
* if one is already there.
*/
static struct ref *insert_ref(struct ref *ref)
{
int ret;
struct rb_node **p = &by_bytenr.rb_node;
struct rb_node *parent = NULL;
struct ref *curr;
while (*p) {
parent = *p;
curr = rb_entry(parent, struct ref, bytenr_node);
ret = compare_ref(curr, ref->bytenr, ref->root, ref->parent);
if (ret < 0)
p = &(*p)->rb_left;
else if (ret > 0)
p = &(*p)->rb_right;
else
return curr;
}
rb_link_node(&ref->bytenr_node, parent, p);
rb_insert_color(&ref->bytenr_node, &by_bytenr);
return ref;
}
/*
* Partial search, returns the first ref with matching bytenr. Caller
* can walk forward from there.
*
* Leftmost refs will be full refs - this is used to our advantage
* when resolving roots.
*/
static struct ref *find_ref_bytenr(u64 bytenr)
{
struct rb_node *n = by_bytenr.rb_node;
struct ref *ref;
while (n) {
ref = rb_entry(n, struct ref, bytenr_node);
if (bytenr < ref->bytenr)
n = n->rb_left;
else if (bytenr > ref->bytenr)
n = n->rb_right;
else {
/* Walk to the left to find the first item */
struct rb_node *node_left = rb_prev(&ref->bytenr_node);
struct ref *ref_left;
while (node_left) {
ref_left = rb_entry(node_left, struct ref,
bytenr_node);
if (ref_left->bytenr != ref->bytenr)
break;
ref = ref_left;
node_left = rb_prev(node_left);
}
return ref;
}
}
return NULL;
}
static struct ref *find_ref(u64 bytenr, u64 root, u64 parent)
{
struct rb_node *n = by_bytenr.rb_node;
struct ref *ref;
int ret;
while (n) {
ref = rb_entry(n, struct ref, bytenr_node);
ret = compare_ref(ref, bytenr, root, parent);
if (ret < 0)
n = n->rb_left;
else if (ret > 0)
n = n->rb_right;
else
return ref;
}
return NULL;
}
static struct ref *alloc_ref(u64 bytenr, u64 root, u64 parent, u64 num_bytes)
{
struct ref *ref = find_ref(bytenr, root, parent);
BUG_ON(parent && root);
if (ref == NULL) {
ref = calloc(1, sizeof(*ref));
if (ref) {
ref->bytenr = bytenr;
ref->root = root;
ref->parent = parent;
ref->num_bytes = num_bytes;
insert_ref(ref);
}
}
return ref;
}
static void free_ref_node(struct rb_node *node)
{
struct ref *ref = rb_entry(node, struct ref, bytenr_node);
free(ref);
}
FREE_RB_BASED_TREE(ref, free_ref_node);
/*
* Resolves all the possible roots for the ref at parent.
*/
static int find_parent_roots(struct ulist *roots, u64 parent)
{
struct ref *ref;
struct rb_node *node;
int ret;
/*
* Search the rbtree for the first ref with bytenr == parent.
* Walk forward so long as bytenr == parent, adding resolved root ids.
* For each unresolved root, we recurse
*/
ref = find_ref_bytenr(parent);
if (!ref) {
error("bytenr ref not found for parent %llu", parent);
return -EIO;
}
node = &ref->bytenr_node;
if (ref->bytenr != parent) {
error("found bytenr ref does not match parent: %llu != %llu",
ref->bytenr, parent);
return -EIO;
}
{
/*
* Random sanity check, are we actually getting the
* leftmost node?
*/
struct rb_node *prev_node = rb_prev(&ref->bytenr_node);
struct ref *prev;
if (prev_node) {
prev = rb_entry(prev_node, struct ref, bytenr_node);
if (prev->bytenr == parent) {
error("unexpected: prev bytenr same as parent: %llu",
parent);
return -EIO;
}
}
}
do {
if (ref->root) {
if (is_fstree(ref->root)) {
ret = ulist_add(roots, ref->root, 0, 0);
if (ret < 0)
goto out;
}
} else if (ref->parent == ref->bytenr) {
/*
* Special loop case for tree reloc tree
*/
ref->root = BTRFS_TREE_RELOC_OBJECTID;
} else {
ret = find_parent_roots(roots, ref->parent);
if (ret < 0)
goto out;
}
node = rb_next(node);
if (node)
ref = rb_entry(node, struct ref, bytenr_node);
} while (node && ref->bytenr == parent);
ret = 0;
out:
return ret;
}
static int account_one_extent(struct ulist *roots, u64 bytenr, u64 num_bytes)
{
int ret;
u64 id, nr_roots, nr_refs;
struct qgroup_count *count;
struct ulist *local_counts = ulist_alloc(0);
struct ulist *tmp = ulist_alloc(0);
struct ulist_iterator uiter;
struct ulist_iterator tmp_uiter;
struct ulist_node *unode;
struct ulist_node *tmp_unode;
struct btrfs_qgroup_list *glist;
if (!local_counts || !tmp) {
ulist_free(local_counts);
ulist_free(tmp);
return ENOMEM;
}
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(roots, &uiter))) {
BUG_ON(unode->val == 0ULL);
/*
* For each root, find their corresponding tracking group and
* add it to our qgroups list.
*/
count = find_count(unode->val);
if (!count)
continue;
BUG_ON(!is_fstree(unode->val));
ret = ulist_add(local_counts, count->qgroupid, ptr_to_u64(count), 0);
if (ret < 0)
goto out;
/*
* Now we look for parents (and parents of those...). Use a tmp
* ulist here to avoid re-walking (and re-incrementing) our
* already added items on every loop iteration.
*/
ulist_reinit(tmp);
ret = ulist_add(tmp, count->qgroupid, ptr_to_u64(count), 0);
if (ret < 0)
goto out;
ULIST_ITER_INIT(&tmp_uiter);
while ((tmp_unode = ulist_next(tmp, &tmp_uiter))) {
/* Bump the refcount on a node every time we see it. */
count = u64_to_ptr(tmp_unode->aux);
update_cur_refcnt(count);
list_for_each_entry(glist, &count->groups, next_group) {
struct qgroup_count *parent;
parent = glist->group;
id = parent->qgroupid;
BUG_ON(!count);
ret = ulist_add(local_counts, id, ptr_to_u64(parent),
0);
if (ret < 0)
goto out;
ret = ulist_add(tmp, id, ptr_to_u64(parent),
0);
if (ret < 0)
goto out;
}
}
}
/*
* Now that we have gathered up and counted all the groups, we
* can add bytes for this ref.
*/
nr_roots = roots->nnodes;
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(local_counts, &uiter))) {
count = u64_to_ptr(unode->aux);
nr_refs = group_get_cur_refcnt(count);
if (nr_refs) {
count->info.referenced += num_bytes;
count->info.referenced_compressed += num_bytes;
if (nr_refs == nr_roots) {
count->info.exclusive += num_bytes;
count->info.exclusive_compressed += num_bytes;
}
}
#ifdef QGROUP_VERIFY_DEBUG
printf("account (%llu, %llu), qgroup %llu/%llu, rfer %llu,"
" excl %llu, refs %llu, roots %llu\n", bytenr, num_bytes,
btrfs_qgroup_level(count->qgroupid),
btrfs_qgroup_subvolid(count->qgroupid),
count->info.referenced, count->info.exclusive, nr_refs,
nr_roots);
#endif
}
inc_qgroup_seq(roots->nnodes);
ret = 0;
out:
ulist_free(local_counts);
ulist_free(tmp);
return ret;
}
static void print_subvol_info(u64 subvolid, u64 bytenr, u64 num_bytes,
struct ulist *roots);
/*
* Account each ref. Walk the refs, for each set of refs in a
* given bytenr:
*
* - add the roots for direct refs to the ref roots ulist
*
* - resolve all possible roots for shared refs, insert each
* of those into ref_roots ulist (this is a recursive process)
*
* - With all roots resolved we can account the ref - this is done in
* account_one_extent().
*/
static int account_all_refs(int do_qgroups, u64 search_subvol)
{
struct ref *ref;
struct rb_node *node;
u64 bytenr, num_bytes;
struct ulist *roots = ulist_alloc(0);
int ret;
node = rb_first(&by_bytenr);
while (node) {
ulist_reinit(roots);
ref = rb_entry(node, struct ref, bytenr_node);
/*
* Walk forward through the list of refs for this
* bytenr, adding roots to our ulist. If it's a full
* ref, then we have the easy case. Otherwise we need
* to search for roots.
*/
bytenr = ref->bytenr;
num_bytes = ref->num_bytes;
do {
BUG_ON(ref->bytenr != bytenr);
BUG_ON(ref->num_bytes != num_bytes);
if (ref->root) {
if (is_fstree(ref->root)) {
if (ulist_add(roots, ref->root, 0, 0) < 0)
goto enomem;
}
} else {
ret = find_parent_roots(roots, ref->parent);
if (ret < 0)
goto enomem;
}
/*
* When we leave this inner loop, node is set
* to next in our tree and will be turned into
* a ref object up top
*/
node = rb_next(node);
if (node)
ref = rb_entry(node, struct ref, bytenr_node);
} while (node && ref->bytenr == bytenr);
if (search_subvol)
print_subvol_info(search_subvol, bytenr, num_bytes,
roots);
if (!do_qgroups)
continue;
if (account_one_extent(roots, bytenr, num_bytes))
goto enomem;
}
ulist_free(roots);
return 0;
enomem:
error_msg(ERROR_MSG_MEMORY, "accounting for refs for qgroups");
return -ENOMEM;
}
static u64 resolve_one_root(u64 bytenr)
{
struct ref *ref = find_ref_bytenr(bytenr);
BUG_ON(ref == NULL);
if (ref->root)
return ref->root;
if (ref->parent == bytenr)
return BTRFS_TREE_RELOC_OBJECTID;
return resolve_one_root(ref->parent);
}
static inline struct tree_block *unode_tree_block(struct ulist_node *unode)
{
return u64_to_ptr(unode->aux);
}
static inline u64 unode_bytenr(struct ulist_node *unode)
{
return unode->val;
}
static int alloc_tree_block(u64 bytenr, u64 num_bytes, int level)
{
struct tree_block *block = calloc(1, sizeof(*block));
if (block) {
block->num_bytes = num_bytes;
block->level = level;
if (ulist_add(tree_blocks, bytenr, ptr_to_u64(block), 0) >= 0)
return 0;
free(block);
}
return -ENOMEM;
}
static void free_tree_blocks(void)
{
struct ulist_iterator uiter;
struct ulist_node *unode;
if (!tree_blocks)
return;
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(tree_blocks, &uiter)))
free(unode_tree_block(unode));
ulist_free(tree_blocks);
tree_blocks = NULL;
}
#ifdef QGROUP_VERIFY_DEBUG
static void print_tree_block(u64 bytenr, struct tree_block *block)
{
struct ref *ref;
struct rb_node *node;
printf("tree block: %llu\t\tlevel: %d\n", bytenr, block->level);
ref = find_ref_bytenr(bytenr);
node = &ref->bytenr_node;
do {
print_ref(ref);
node = rb_next(node);
if (node)
ref = rb_entry(node, struct ref, bytenr_node);
} while (node && ref->bytenr == bytenr);
printf("\n");
}
static void print_all_tree_blocks(void)
{
struct ulist_iterator uiter;
struct ulist_node *unode;
if (!tree_blocks)
return;
printf("Listing all found interior tree nodes:\n");
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(tree_blocks, &uiter)))
print_tree_block(unode_bytenr(unode), unode_tree_block(unode));
}
#endif
static int add_refs_for_leaf_items(struct extent_buffer *eb, u64 ref_parent)
{
int nr, i;
int extent_type;
u64 bytenr, num_bytes;
struct btrfs_key key;
struct btrfs_disk_key disk_key;
struct btrfs_file_extent_item *fi;
nr = btrfs_header_nritems(eb);
for (i = 0; i < nr; i++) {
btrfs_item_key(eb, &disk_key, i);
btrfs_disk_key_to_cpu(&key, &disk_key);
if (key.type != BTRFS_EXTENT_DATA_KEY)
continue;
fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item);
/* filter out: inline, disk_bytenr == 0, compressed?
* not if we can avoid it */
extent_type = btrfs_file_extent_type(eb, fi);
if (extent_type == BTRFS_FILE_EXTENT_INLINE)
continue;
bytenr = btrfs_file_extent_disk_bytenr(eb, fi);
if (!bytenr)
continue;
num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
if (alloc_ref(bytenr, 0, ref_parent, num_bytes) == NULL)
return ENOMEM;
}
return 0;
}
static int travel_tree(struct btrfs_fs_info *info, struct btrfs_root *root,
u64 bytenr, u64 num_bytes, u64 ref_parent)
{
int ret, nr, i;
struct extent_buffer *eb;
struct btrfs_tree_parent_check check = {
.owner_root = btrfs_root_id(root),
};
u64 new_bytenr;
u64 new_num_bytes;
// printf("travel_tree: bytenr: %llu\tnum_bytes: %llu\tref_parent: %llu\n",
// bytenr, num_bytes, ref_parent);
eb = read_tree_block(info, bytenr, &check);
if (!extent_buffer_uptodate(eb))
return -EIO;
ret = 0;
/* Don't add a ref for our starting tree block to itself */
if (bytenr != ref_parent) {
if (alloc_ref(bytenr, 0, ref_parent, num_bytes) == NULL)
return ENOMEM;
}
if (btrfs_is_leaf(eb)) {
ret = add_refs_for_leaf_items(eb, ref_parent);
goto out;
}
/*
* Interior nodes are tuples of (key, bytenr) where key is the
* leftmost key in the tree block pointed to by bytenr. We
* don't have to care about key here, just follow the bytenr
* pointer.
*/
nr = btrfs_header_nritems(eb);
for (i = 0; i < nr; i++) {
if (qgroup_item_count)
(*qgroup_item_count)++;
new_bytenr = btrfs_node_blockptr(eb, i);
new_num_bytes = info->nodesize;
ret = travel_tree(info, root, new_bytenr, new_num_bytes,
ref_parent);
}
out:
free_extent_buffer(eb);
return ret;
}
static int add_refs_for_implied(struct btrfs_fs_info *info, u64 bytenr,
struct tree_block *block)
{
int ret;
u64 root_id = resolve_one_root(bytenr);
struct btrfs_root *root;
struct btrfs_key key;
/* If this is a global tree skip it. */
if (!is_fstree(root_id))
return 0;
/* Tree reloc tree doesn't contribute qgroup, skip it */
if (root_id == BTRFS_TREE_RELOC_OBJECTID)
return 0;
key.objectid = root_id;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = (u64)-1;
/*
* XXX: Don't free the root object as we don't know whether it
* came off our fs_info struct or not.
*/
root = btrfs_read_fs_root(info, &key);
if (!root || IS_ERR(root))
return ENOENT;
ret = travel_tree(info, root, bytenr, block->num_bytes, bytenr);
if (ret)
return ret;
return 0;
}
/*
* Place shared refs in the ref tree for each child of an interior tree node.
*/
static int map_implied_refs(struct btrfs_fs_info *info)
{
int ret = 0;
struct ulist_iterator uiter;
struct ulist_node *unode;
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(tree_blocks, &uiter))) {
ret = add_refs_for_implied(info, unode_bytenr(unode),
unode_tree_block(unode));
if (ret)
goto out;
}
out:
return ret;
}
/*
* insert a new root into the tree. returns the existing root entry
* if one is already there. qgroupid is used
* as the key
*/
static int insert_count(struct qgroup_count *qc)
{
struct rb_node **p = &counts.root.rb_node;
struct rb_node *parent = NULL;
struct qgroup_count *curr;
while (*p) {
parent = *p;
curr = rb_entry(parent, struct qgroup_count, rb_node);
if (qc->qgroupid < curr->qgroupid)
p = &(*p)->rb_left;
else if (qc->qgroupid > curr->qgroupid)
p = &(*p)->rb_right;
else
return EEXIST;
}
counts.num_groups++;
rb_link_node(&qc->rb_node, parent, p);
rb_insert_color(&qc->rb_node, &counts.root);
return 0;
}
static struct qgroup_count *find_count(u64 qgroupid)
{
struct rb_node *n = counts.root.rb_node;
struct qgroup_count *count;
while (n) {
count = rb_entry(n, struct qgroup_count, rb_node);
if (qgroupid < count->qgroupid)
n = n->rb_left;
else if (qgroupid > count->qgroupid)
n = n->rb_right;
else
return count;
}
return NULL;
}
static struct qgroup_count *alloc_count(struct btrfs_disk_key *key,
struct extent_buffer *leaf,
struct btrfs_qgroup_info_item *disk)
{
struct qgroup_count *c = calloc(1, sizeof(*c));
struct qgroup_info *item;
if (c) {
c->qgroupid = btrfs_disk_key_offset(key);
c->key = *key;
item = &c->diskinfo;
item->referenced = btrfs_qgroup_info_rfer(leaf, disk);
item->referenced_compressed =
btrfs_qgroup_info_rfer_cmpr(leaf, disk);
item->exclusive = btrfs_qgroup_info_excl(leaf, disk);
item->exclusive_compressed =
btrfs_qgroup_info_excl_cmpr(leaf, disk);
INIT_LIST_HEAD(&c->groups);
INIT_LIST_HEAD(&c->members);
INIT_LIST_HEAD(&c->bad_list);
if (insert_count(c)) {
free(c);
c = NULL;
}
}
return c;
}
static int add_qgroup_relation(u64 memberid, u64 parentid)
{
struct qgroup_count *member;
struct qgroup_count *parent;
struct btrfs_qgroup_list *list;
if (memberid > parentid)
return 0;
member = find_count(memberid);
parent = find_count(parentid);
if (!member || !parent)
return -ENOENT;
list = calloc(1, sizeof(*list));
if (!list)
return -ENOMEM;
list->group = parent;
list->member = member;
list_add_tail(&list->next_group, &member->groups);
list_add_tail(&list->next_member, &parent->members);
return 0;
}
static void read_qgroup_status(struct btrfs_fs_info *info, struct extent_buffer *eb,
int slot, struct counts_tree *ct)
{
struct btrfs_qgroup_status_item *status_item;
u64 flags;
status_item = btrfs_item_ptr(eb, slot, struct btrfs_qgroup_status_item);
flags = btrfs_qgroup_status_flags(eb, status_item);
if (ct->simple == 1)
ct->enable_gen = btrfs_qgroup_status_enable_gen(eb, status_item);
/*
* Since qgroup_inconsist/rescan_running is just one bit,
* assign value directly won't work.
*/
ct->qgroup_inconsist = !!(flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT);
ct->rescan_running = !!(flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN);
ct->scan_progress = btrfs_qgroup_status_rescan(eb, status_item);
}
static int load_quota_info(struct btrfs_fs_info *info)
{
int ret;
struct btrfs_root *root = info->quota_root;
struct btrfs_root *tmproot;
struct btrfs_path path = { 0 };
struct btrfs_key key;
struct btrfs_key root_key;
struct btrfs_disk_key disk_key;
struct extent_buffer *leaf;
struct btrfs_qgroup_info_item *item;
struct qgroup_count *count;
int i, nr;
int search_relations = 0;
if (btrfs_fs_incompat(info, SIMPLE_QUOTA))
counts.simple = 1;
loop:
/*
* Do 2 passes, the first allocates group counts and reads status
* items. The 2nd pass picks up relation items and glues them to their
* respective count structures.
*/
key.objectid = search_relations ? 0 : BTRFS_QGROUP_RELATION_KEY;
key.type = 0;
key.offset = 0;
ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0) {
error("couldn't search slot: %d", ret);
goto out;
}
while (1) {
leaf = path.nodes[0];
nr = btrfs_header_nritems(leaf);
for(i = 0; i < nr; i++) {
btrfs_item_key(leaf, &disk_key, i);
btrfs_disk_key_to_cpu(&key, &disk_key);
if (search_relations) {
if (key.type == BTRFS_QGROUP_RELATION_KEY) {
ret = add_qgroup_relation(key.objectid,
key.offset);
if (ret) {
errno = -ret;
error(
"failed to add qgroup relation, member=%llu parent=%llu: %m",
key.objectid, key.offset);
goto out;
}
}
continue;
}
if (key.type == BTRFS_QGROUP_STATUS_KEY) {
read_qgroup_status(info, leaf, i, &counts);
continue;
}
/*
* At this point, we can ignore anything that
* isn't a qgroup info.
*/
if (key.type != BTRFS_QGROUP_INFO_KEY)
continue;
item = btrfs_item_ptr(leaf, i,
struct btrfs_qgroup_info_item);
count = alloc_count(&disk_key, leaf, item);
if (!count) {
ret = ENOMEM;
error_msg(ERROR_MSG_MEMORY, NULL);
goto out;
}
root_key.objectid = key.offset;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
tmproot = btrfs_read_fs_root_no_cache(info, &root_key);
if (tmproot && !IS_ERR(tmproot)) {
count->subvol_exists = 1;
btrfs_free_fs_root(tmproot);
}
}
ret = btrfs_next_leaf(root, &path);
if (ret != 0)
break;
}
ret = 0;
btrfs_release_path(&path);
if (!search_relations) {
search_relations = 1;
goto loop;
}
out:
return ret;
}
static int simple_quota_account_extent(struct btrfs_fs_info *info,
struct extent_buffer *leaf,
struct btrfs_key *key,
struct btrfs_extent_item *ei,
struct btrfs_extent_inline_ref *iref,
u64 bytenr, u64 num_bytes, int meta_item)
{
u64 generation;
int type;
u64 root;
struct ulist roots;
int ret;
struct extent_buffer *node_eb;
generation = btrfs_extent_generation(leaf, ei);
if (generation < counts.enable_gen)
return 0;
type = btrfs_extent_inline_ref_type(leaf, iref);
if (!meta_item) {
if (type == BTRFS_EXTENT_OWNER_REF_KEY) {
struct btrfs_extent_owner_ref *oref;
oref = (struct btrfs_extent_owner_ref *)(&iref->offset);
root = btrfs_extent_owner_ref_root_id(leaf, oref);
} else {
return 0;
}
} else {
struct btrfs_tree_parent_check check = { 0 };
check.owner_root = btrfs_root_id(btrfs_extent_root(info, key->objectid));
node_eb = read_tree_block(info, key->objectid, &check);
if (!extent_buffer_uptodate(node_eb))
return -EIO;
root = btrfs_header_owner(node_eb);
free_extent_buffer(node_eb);
}
if (!is_fstree(root))
return 0;
ulist_init(&roots);
ulist_add(&roots, root, 0, 0);
ret = account_one_extent(&roots, bytenr, num_bytes);
ulist_release(&roots);
return ret;
}
static int add_inline_refs(struct btrfs_fs_info *info,
struct extent_buffer *ei_leaf, int slot,
u64 bytenr, u64 num_bytes, int meta_item)
{
struct btrfs_extent_item *ei;
struct btrfs_extent_inline_ref *iref;
struct btrfs_extent_data_ref *dref;
struct btrfs_key key;
u64 flags, root_obj, offset, parent;
u32 item_size = btrfs_item_size(ei_leaf, slot);
int type;
unsigned long end;
unsigned long ptr;
ei = btrfs_item_ptr(ei_leaf, slot, struct btrfs_extent_item);
btrfs_item_key_to_cpu(ei_leaf, &key, slot);
flags = btrfs_extent_flags(ei_leaf, ei);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK && !meta_item) {
struct btrfs_tree_block_info *tbinfo;
tbinfo = (struct btrfs_tree_block_info *)(ei + 1);
iref = (struct btrfs_extent_inline_ref *)(tbinfo + 1);
} else {
iref = (struct btrfs_extent_inline_ref *)(ei + 1);
}
if (counts.simple) {
int ret = simple_quota_account_extent(info, ei_leaf, &key, ei, iref,
bytenr, num_bytes, meta_item);
if (ret)
error("squota account extent error: %d", ret);
return ret;
}
ptr = (unsigned long)iref;
end = (unsigned long)ei + item_size;
while (ptr < end) {
iref = (struct btrfs_extent_inline_ref *)ptr;
parent = root_obj = 0;
offset = btrfs_extent_inline_ref_offset(ei_leaf, iref);
type = btrfs_extent_inline_ref_type(ei_leaf, iref);
switch (type) {
case BTRFS_TREE_BLOCK_REF_KEY:
root_obj = offset;
break;
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
root_obj = btrfs_extent_data_ref_root(ei_leaf, dref);
break;
case BTRFS_SHARED_DATA_REF_KEY:
case BTRFS_SHARED_BLOCK_REF_KEY:
parent = offset;
break;
default:
error("unexpected iref type %d", type);
return 1;
}
if (alloc_ref(bytenr, root_obj, parent, num_bytes) == NULL)
return ENOMEM;
ptr += btrfs_extent_inline_ref_size(type);
}
return 0;
}
static int add_keyed_ref(struct btrfs_fs_info *info,
struct btrfs_key *key,
struct extent_buffer *leaf, int slot,
u64 bytenr, u64 num_bytes)
{
u64 root_obj = 0, parent = 0;
struct btrfs_extent_data_ref *dref;
switch(key->type) {
case BTRFS_TREE_BLOCK_REF_KEY:
root_obj = key->offset;
break;
case BTRFS_EXTENT_DATA_REF_KEY:
dref = btrfs_item_ptr(leaf, slot, struct btrfs_extent_data_ref);
root_obj = btrfs_extent_data_ref_root(leaf, dref);
break;
case BTRFS_SHARED_DATA_REF_KEY:
case BTRFS_SHARED_BLOCK_REF_KEY:
parent = key->offset;
break;
default:
return 1;
}
if (alloc_ref(bytenr, root_obj, parent, num_bytes) == NULL)
return ENOMEM;
return 0;
}
/*
* return value of 0 indicates leaf or not meta data. The code that
* calls this does not need to make a distinction between the two as
* it is only concerned with intermediate blocks which will always
* have level > 0.
*/
static int get_tree_block_level(struct btrfs_key *key,
struct extent_buffer *ei_leaf,
int slot)
{
int level = 0;
int meta_key = key->type == BTRFS_METADATA_ITEM_KEY;
u64 flags;
struct btrfs_extent_item *ei;
ei = btrfs_item_ptr(ei_leaf, slot, struct btrfs_extent_item);
flags = btrfs_extent_flags(ei_leaf, ei);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK && !meta_key) {
struct btrfs_tree_block_info *tbinfo;
tbinfo = (struct btrfs_tree_block_info *)(ei + 1);
level = btrfs_tree_block_level(ei_leaf, tbinfo);
} else if (meta_key) {
/* skinny metadata */
level = (int)key->offset;
}
return level;
}
/*
* Walk the extent tree, allocating a ref item for every ref and
* storing it in the bytenr tree.
*/
static int scan_extents(struct btrfs_fs_info *info,
u64 start, u64 end)
{
int ret, i, nr, level;
struct btrfs_root *root = btrfs_extent_root(info, start);
struct btrfs_key key;
struct btrfs_path path = { 0 };
struct btrfs_disk_key disk_key;
struct extent_buffer *leaf;
u64 bytenr = 0, num_bytes = 0;
key.objectid = start;
key.type = 0;
key.offset = 0;
ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0) {
error("couldn't search slot: %d", ret);
goto out;
}
path.reada = READA_BACK;
while (1) {
leaf = path.nodes[0];
nr = btrfs_header_nritems(leaf);
for(i = 0; i < nr; i++) {
btrfs_item_key(leaf, &disk_key, i);
btrfs_disk_key_to_cpu(&key, &disk_key);
if (key.objectid < start)
continue;
if (key.objectid > end)
goto done;
if (key.type == BTRFS_EXTENT_ITEM_KEY ||
key.type == BTRFS_METADATA_ITEM_KEY) {
int meta = 0;
tot_extents_scanned++;
bytenr = key.objectid;
num_bytes = key.offset;
if (key.type == BTRFS_METADATA_ITEM_KEY) {
num_bytes = info->nodesize;
meta = 1;
}
ret = add_inline_refs(info, leaf, i, bytenr,
num_bytes, meta);
if (ret)
goto out;
level = get_tree_block_level(&key, leaf, i);
if (level) {
if (alloc_tree_block(bytenr, num_bytes,
level))
return ENOMEM;
}
continue;
}
if (key.type > BTRFS_SHARED_DATA_REF_KEY)
continue;
if (key.type < BTRFS_TREE_BLOCK_REF_KEY)
continue;
/*
* Keyed refs should come after their extent
* item in the tree. As a result, the value of
* bytenr and num_bytes should be unchanged
* from the above block that catches the
* original extent item.
*/
BUG_ON(key.objectid != bytenr);
ret = add_keyed_ref(info, &key, leaf, i, bytenr,
num_bytes);
if (ret)
goto out;
}
ret = btrfs_next_leaf(root, &path);
if (ret != 0) {
if (ret < 0) {
error("next leaf failed: %d", ret);
goto out;
}
break;
}
}
done:
ret = 0;
out:
btrfs_release_path(&path);
return ret;
}
static void print_fields(u64 bytes, u64 bytes_compressed, char *prefix,
char *type)
{
printf("%s\t\t%s %llu %s compressed %llu\n",
prefix, type, bytes, type, bytes_compressed);
}
static void print_fields_signed(long long bytes,
long long bytes_compressed,
char *prefix, char *type)
{
printf("%s\t\t%s %lld %s compressed %lld\n",
prefix, type, bytes, type, bytes_compressed);
}
static inline int qgroup_printable(struct qgroup_count *c)
{
return !!(c->subvol_exists || btrfs_qgroup_level(c->qgroupid));
}
static int report_qgroup_difference(struct qgroup_count *count, int verbose)
{
int is_different;
struct qgroup_info *info = &count->info;
struct qgroup_info *disk = &count->diskinfo;
long long excl_diff = info->exclusive - disk->exclusive;
long long ref_diff = info->referenced - disk->referenced;
is_different = excl_diff || ref_diff;
if (verbose || (is_different && qgroup_printable(count))) {
printf("Counts for qgroup id: %u/%llu %s\n",
btrfs_qgroup_level(count->qgroupid),
btrfs_qgroup_subvolid(count->qgroupid),
is_different ? "are different" : "");
print_fields(info->referenced, info->referenced_compressed,
"our:", "referenced");
print_fields(disk->referenced, disk->referenced_compressed,
"disk:", "referenced");
if (ref_diff)
print_fields_signed(ref_diff, ref_diff,
"diff:", "referenced");
print_fields(info->exclusive, info->exclusive_compressed,
"our:", "exclusive");
print_fields(disk->exclusive, disk->exclusive_compressed,
"disk:", "exclusive");
if (excl_diff)
print_fields_signed(excl_diff, excl_diff,
"diff:", "exclusive");
}
return is_different;
}
/*
* Report qgroups errors
* @all: if set, all qgroup will be checked and reported even already
* inconsistent or under rescan.
*/
void report_qgroups(int all)
{
struct rb_node *node;
struct qgroup_count *c;
if (!opt_check_repair && counts.rescan_running) {
if (all) {
printf(
"Qgroup rescan is running, a difference in qgroup counts is expected\n");
} else {
printf(
"Qgroup rescan is running, qgroups will not be printed.\n");
return;
}
}
/*
* It's possible that rescan hasn't been initialized yet.
*/
if (counts.qgroup_inconsist && !counts.rescan_running)
printf(
"Rescan hasn't been initialzied, a difference in qgroup accounting is expected\n");
node = rb_first(&counts.root);
while (node) {
c = rb_entry(node, struct qgroup_count, rb_node);
report_qgroup_difference(c, all);
node = rb_next(node);
}
}
void free_qgroup_counts(void)
{
struct rb_node *node;
struct qgroup_count *c;
struct btrfs_qgroup_list *glist, *tmpglist;
node = rb_first(&counts.root);
while (node) {
c = rb_entry(node, struct qgroup_count, rb_node);
list_del(&c->bad_list);
list_for_each_entry_safe(glist, tmpglist, &c->groups,
next_group) {
list_del(&glist->next_group);
list_del(&glist->next_member);
free(glist);
}
list_for_each_entry_safe(glist, tmpglist, &c->members,
next_group) {
list_del(&glist->next_group);
list_del(&glist->next_member);
free(glist);
}
node = rb_next(node);
rb_erase(&c->rb_node, &counts.root);
free(c);
}
}
static bool is_bad_qgroup(struct qgroup_count *count)
{
struct qgroup_info *info = &count->info;
struct qgroup_info *disk = &count->diskinfo;
s64 excl_diff = info->exclusive - disk->exclusive;
s64 ref_diff = info->referenced - disk->referenced;
return (excl_diff || ref_diff);
}
/*
* Verify all qgroup numbers.
*
* Return <0 for fatal errors (e.g. ENOMEM or failed to read quota tree)
* Return 0 if all qgroup numbers are correct or no need to check (under rescan)
* Return >0 if qgroup numbers are inconsistent.
*/
int qgroup_verify_all(struct btrfs_fs_info *info)
{
struct rb_node *n;
int ret;
bool found_err = false;
bool skip_err = false;
struct rb_node *node;
if (!info->quota_enabled)
return 0;
tree_blocks = ulist_alloc(0);
if (!tree_blocks) {
error_msg(ERROR_MSG_MEMORY, "allocate ulist");
return ENOMEM;
}
ret = load_quota_info(info);
if (ret) {
error("loading qgroups from disk: %d", ret);
goto out;
}
if (counts.rescan_running)
skip_err = true;
if (counts.qgroup_inconsist && !counts.rescan_running &&
counts.rescan_running == 0)
skip_err = true;
/*
* Put all extent refs into our rbtree
*/
for (n = rb_first(&info->block_group_cache_tree); n; n = rb_next(n)) {
struct btrfs_block_group *bg;
bg = rb_entry(n, struct btrfs_block_group, cache_node);
ret = scan_extents(info, bg->start,
bg->start + bg->length - 1);
if (ret) {
error("while scanning extent tree: %d", ret);
goto out;
}
}
/*
* As in the kernel, simple qgroup accounting is done locally per extent,
* so we don't need to resolve backrefs to find which subvol an extent
* is accounted to.
*/
if (counts.simple)
goto check;
ret = map_implied_refs(info);
if (ret) {
error("while mapping refs: %d", ret);
goto out;
}
ret = account_all_refs(1, 0);
check:
/*
* Do the correctness check here, so for callers who don't want
* verbose report can skip calling report_qgroups()
*/
node = rb_first(&counts.root);
while (node) {
struct qgroup_count *c;
c = rb_entry(node, struct qgroup_count, rb_node);
if (is_bad_qgroup(c)) {
list_add_tail(&c->bad_list, &bad_qgroups);
found_err = true;
}
node = rb_next(node);
}
out:
/*
* Don't free the qgroup count records as they will be walked
* later via the print function.
*/
free_tree_blocks();
free_ref_tree(&by_bytenr);
if (!ret && !skip_err && found_err)
ret = 1;
return ret;
}
static void __print_subvol_info(u64 bytenr, u64 num_bytes, struct ulist *roots)
{
int n = roots->nnodes;
struct ulist_iterator uiter;
struct ulist_node *unode;
printf("%llu\t%llu\t%d\t", bytenr, num_bytes, n);
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(roots, &uiter))) {
printf("%llu ", unode->val);
}
printf("\n");
}
static void print_subvol_info(u64 subvolid, u64 bytenr, u64 num_bytes,
struct ulist *roots)
{
struct ulist_iterator uiter;
struct ulist_node *unode;
ULIST_ITER_INIT(&uiter);
while ((unode = ulist_next(roots, &uiter))) {
BUG_ON(unode->val == 0ULL);
if (unode->val == subvolid) {
__print_subvol_info(bytenr, num_bytes, roots);
return;
}
}
}
int print_extent_state(struct btrfs_fs_info *info, u64 subvol)
{
struct rb_node *n;
int ret;
tree_blocks = ulist_alloc(0);
if (!tree_blocks) {
error_msg(ERROR_MSG_MEMORY, "allocate ulist");
return ENOMEM;
}
/*
* Put all extent refs into our rbtree
*/
for (n = rb_first(&info->block_group_cache_tree); n; n = rb_next(n)) {
struct btrfs_block_group *bg;
bg = rb_entry(n, struct btrfs_block_group, cache_node);
ret = scan_extents(info, bg->start,
bg->start + bg->length - 1);
if (ret) {
error("while scanning extent tree: %d", ret);
goto out;
}
}
ret = map_implied_refs(info);
if (ret) {
error("while mapping refs: %d", ret);
goto out;
}
printf("Offset\t\tLen\tRoot Refs\tRoots\n");
ret = account_all_refs(0, subvol);
out:
free_tree_blocks();
free_ref_tree(&by_bytenr);
return ret;
}
static int repair_qgroup_info(struct btrfs_fs_info *info,
struct qgroup_count *count, bool silent)
{
int ret;
struct btrfs_root *root = info->quota_root;
struct btrfs_trans_handle *trans;
struct btrfs_path path = { 0 };
struct btrfs_qgroup_info_item *info_item;
struct btrfs_key key;
if (!silent)
printf("Repair qgroup %u/%llu\n",
btrfs_qgroup_level(count->qgroupid),
btrfs_qgroup_subvolid(count->qgroupid));
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans))
return PTR_ERR(trans);
key.objectid = 0;
key.type = BTRFS_QGROUP_INFO_KEY;
key.offset = count->qgroupid;
ret = btrfs_search_slot(trans, root, &key, &path, 0, 1);
if (ret) {
error("could not find disk item for qgroup %u/%llu",
btrfs_qgroup_level(count->qgroupid),
btrfs_qgroup_subvolid(count->qgroupid));
if (ret > 0)
ret = -ENOENT;
goto out;
}
info_item = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_qgroup_info_item);
btrfs_set_qgroup_info_generation(path.nodes[0], info_item,
trans->transid);
btrfs_set_qgroup_info_rfer(path.nodes[0], info_item,
count->info.referenced);
btrfs_set_qgroup_info_rfer_cmpr(path.nodes[0], info_item,
count->info.referenced_compressed);
btrfs_set_qgroup_info_excl(path.nodes[0], info_item,
count->info.exclusive);
btrfs_set_qgroup_info_excl_cmpr(path.nodes[0], info_item,
count->info.exclusive_compressed);
btrfs_mark_buffer_dirty(path.nodes[0]);
out:
btrfs_commit_transaction(trans, root);
btrfs_release_path(&path);
return ret;
}
static int repair_qgroup_status(struct btrfs_fs_info *info, bool silent)
{
int ret;
struct btrfs_root *root = info->quota_root;
struct btrfs_trans_handle *trans;
struct btrfs_path path = { 0 };
struct btrfs_key key;
struct btrfs_qgroup_status_item *status_item;
bool simple = btrfs_fs_incompat(info, SIMPLE_QUOTA);
u64 flags = BTRFS_QGROUP_STATUS_FLAG_ON;
if (!silent)
printf("Repair qgroup status item\n");
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans))
return PTR_ERR(trans);
key.objectid = 0;
key.type = BTRFS_QGROUP_STATUS_KEY;
key.offset = 0;
ret = btrfs_search_slot(trans, root, &key, &path, 0, 1);
if (ret) {
error("could not find qgroup status item");
if (ret > 0)
ret = -ENOENT;
goto out;
}
status_item = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_qgroup_status_item);
if (simple)
flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
btrfs_set_qgroup_status_flags(path.nodes[0], status_item, flags);
btrfs_set_qgroup_status_rescan(path.nodes[0], status_item, 0);
btrfs_set_qgroup_status_generation(path.nodes[0], status_item,
trans->transid);
btrfs_set_qgroup_status_version(path.nodes[0], status_item,
BTRFS_QGROUP_STATUS_VERSION);
btrfs_mark_buffer_dirty(path.nodes[0]);
out:
btrfs_commit_transaction(trans, root);
btrfs_release_path(&path);
return ret;
}
int repair_qgroups(struct btrfs_fs_info *info, int *repaired, bool silent)
{
int ret = 0;
struct qgroup_count *count, *tmpcount;
*repaired = 0;
if (info->readonly)
return 0;
list_for_each_entry_safe(count, tmpcount, &bad_qgroups, bad_list) {
ret = repair_qgroup_info(info, count, silent);
if (ret) {
goto out;
}
(*repaired)++;
list_del_init(&count->bad_list);
}
/*
* Do this step last as we want the latest transaction id on
* our qgroup status to avoid a (useless) warning after
* mount.
*/
if (*repaired || counts.qgroup_inconsist || counts.rescan_running) {
ret = repair_qgroup_status(info, silent);
if (ret)
goto out;
(*repaired)++;
}
out:
return ret;
}
|