1// SPDX-License-Identifier: GPL-2.0+ 2/* 3 * Copyright (C) 2016 Oracle. All Rights Reserved. 4 * Author: Darrick J. Wong <darrick.wong@oracle.com> 5 */ 6#include "xfs.h" 7#include "xfs_fs.h" 8#include "xfs_shared.h" 9#include "xfs_format.h" 10#include "xfs_log_format.h" 11#include "xfs_trans_resv.h" 12#include "xfs_mount.h" 13#include "xfs_defer.h" 14#include "xfs_btree.h" 15#include "xfs_bmap.h" 16#include "xfs_refcount_btree.h" 17#include "xfs_alloc.h" 18#include "xfs_errortag.h" 19#include "xfs_error.h" 20#include "xfs_trace.h" 21#include "xfs_trans.h" 22#include "xfs_bit.h" 23#include "xfs_refcount.h" 24#include "xfs_rmap.h" 25#include "xfs_ag.h" 26 27struct kmem_cache *xfs_refcount_intent_cache; 28 29/* Allowable refcount adjustment amounts. */ 30enum xfs_refc_adjust_op { 31 XFS_REFCOUNT_ADJUST_INCREASE = 1, 32 XFS_REFCOUNT_ADJUST_DECREASE = -1, 33 XFS_REFCOUNT_ADJUST_COW_ALLOC = 0, 34 XFS_REFCOUNT_ADJUST_COW_FREE = -1, 35}; 36 37STATIC int __xfs_refcount_cow_alloc(struct xfs_btree_cur *rcur, 38 xfs_agblock_t agbno, xfs_extlen_t aglen); 39STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur, 40 xfs_agblock_t agbno, xfs_extlen_t aglen); 41 42/* 43 * Look up the first record less than or equal to [bno, len] in the btree 44 * given by cur. 45 */ 46int 47xfs_refcount_lookup_le( 48 struct xfs_btree_cur *cur, 49 enum xfs_refc_domain domain, 50 xfs_agblock_t bno, 51 int *stat) 52{ 53 trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, 54 xfs_refcount_encode_startblock(bno, domain), 55 XFS_LOOKUP_LE); 56 cur->bc_rec.rc.rc_startblock = bno; 57 cur->bc_rec.rc.rc_blockcount = 0; 58 cur->bc_rec.rc.rc_domain = domain; 59 return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat); 60} 61 62/* 63 * Look up the first record greater than or equal to [bno, len] in the btree 64 * given by cur. 65 */ 66int 67xfs_refcount_lookup_ge( 68 struct xfs_btree_cur *cur, 69 enum xfs_refc_domain domain, 70 xfs_agblock_t bno, 71 int *stat) 72{ 73 trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, 74 xfs_refcount_encode_startblock(bno, domain), 75 XFS_LOOKUP_GE); 76 cur->bc_rec.rc.rc_startblock = bno; 77 cur->bc_rec.rc.rc_blockcount = 0; 78 cur->bc_rec.rc.rc_domain = domain; 79 return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); 80} 81 82/* 83 * Look up the first record equal to [bno, len] in the btree 84 * given by cur. 85 */ 86int 87xfs_refcount_lookup_eq( 88 struct xfs_btree_cur *cur, 89 enum xfs_refc_domain domain, 90 xfs_agblock_t bno, 91 int *stat) 92{ 93 trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, 94 xfs_refcount_encode_startblock(bno, domain), 95 XFS_LOOKUP_LE); 96 cur->bc_rec.rc.rc_startblock = bno; 97 cur->bc_rec.rc.rc_blockcount = 0; 98 cur->bc_rec.rc.rc_domain = domain; 99 return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); 100} 101 102/* Convert on-disk record to in-core format. */ 103void 104xfs_refcount_btrec_to_irec( 105 const union xfs_btree_rec *rec, 106 struct xfs_refcount_irec *irec) 107{ 108 uint32_t start; 109 110 start = be32_to_cpu(rec->refc.rc_startblock); 111 if (start & XFS_REFC_COWFLAG) { 112 start &= ~XFS_REFC_COWFLAG; 113 irec->rc_domain = XFS_REFC_DOMAIN_COW; 114 } else { 115 irec->rc_domain = XFS_REFC_DOMAIN_SHARED; 116 } 117 118 irec->rc_startblock = start; 119 irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount); 120 irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount); 121} 122 123/* Simple checks for refcount records. */ 124xfs_failaddr_t 125xfs_refcount_check_irec( 126 struct xfs_btree_cur *cur, 127 const struct xfs_refcount_irec *irec) 128{ 129 struct xfs_perag *pag = cur->bc_ag.pag; 130 131 if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) 132 return __this_address; 133 134 if (!xfs_refcount_check_domain(irec)) 135 return __this_address; 136 137 /* check for valid extent range, including overflow */ 138 if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) 139 return __this_address; 140 141 if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) 142 return __this_address; 143 144 return NULL; 145} 146 147static inline int 148xfs_refcount_complain_bad_rec( 149 struct xfs_btree_cur *cur, 150 xfs_failaddr_t fa, 151 const struct xfs_refcount_irec *irec) 152{ 153 struct xfs_mount *mp = cur->bc_mp; 154 155 xfs_warn(mp, 156 "Refcount BTree record corruption in AG %d detected at %pS!", 157 cur->bc_ag.pag->pag_agno, fa); 158 xfs_warn(mp, 159 "Start block 0x%x, block count 0x%x, references 0x%x", 160 irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); 161 return -EFSCORRUPTED; 162} 163 164/* 165 * Get the data from the pointed-to record. 166 */ 167int 168xfs_refcount_get_rec( 169 struct xfs_btree_cur *cur, 170 struct xfs_refcount_irec *irec, 171 int *stat) 172{ 173 union xfs_btree_rec *rec; 174 xfs_failaddr_t fa; 175 int error; 176 177 error = xfs_btree_get_rec(cur, &rec, stat); 178 if (error || !*stat) 179 return error; 180 181 xfs_refcount_btrec_to_irec(rec, irec); 182 fa = xfs_refcount_check_irec(cur, irec); 183 if (fa) 184 return xfs_refcount_complain_bad_rec(cur, fa, irec); 185 186 trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); 187 return 0; 188} 189 190/* 191 * Update the record referred to by cur to the value given 192 * by [bno, len, refcount]. 193 * This either works (return 0) or gets an EFSCORRUPTED error. 194 */ 195STATIC int 196xfs_refcount_update( 197 struct xfs_btree_cur *cur, 198 struct xfs_refcount_irec *irec) 199{ 200 union xfs_btree_rec rec; 201 uint32_t start; 202 int error; 203 204 trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); 205 206 start = xfs_refcount_encode_startblock(irec->rc_startblock, 207 irec->rc_domain); 208 rec.refc.rc_startblock = cpu_to_be32(start); 209 rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount); 210 rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount); 211 212 error = xfs_btree_update(cur, &rec); 213 if (error) 214 trace_xfs_refcount_update_error(cur->bc_mp, 215 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 216 return error; 217} 218 219/* 220 * Insert the record referred to by cur to the value given 221 * by [bno, len, refcount]. 222 * This either works (return 0) or gets an EFSCORRUPTED error. 223 */ 224int 225xfs_refcount_insert( 226 struct xfs_btree_cur *cur, 227 struct xfs_refcount_irec *irec, 228 int *i) 229{ 230 int error; 231 232 trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); 233 234 cur->bc_rec.rc.rc_startblock = irec->rc_startblock; 235 cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount; 236 cur->bc_rec.rc.rc_refcount = irec->rc_refcount; 237 cur->bc_rec.rc.rc_domain = irec->rc_domain; 238 239 error = xfs_btree_insert(cur, i); 240 if (error) 241 goto out_error; 242 if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) { 243 error = -EFSCORRUPTED; 244 goto out_error; 245 } 246 247out_error: 248 if (error) 249 trace_xfs_refcount_insert_error(cur->bc_mp, 250 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 251 return error; 252} 253 254/* 255 * Remove the record referred to by cur, then set the pointer to the spot 256 * where the record could be re-inserted, in case we want to increment or 257 * decrement the cursor. 258 * This either works (return 0) or gets an EFSCORRUPTED error. 259 */ 260STATIC int 261xfs_refcount_delete( 262 struct xfs_btree_cur *cur, 263 int *i) 264{ 265 struct xfs_refcount_irec irec; 266 int found_rec; 267 int error; 268 269 error = xfs_refcount_get_rec(cur, &irec, &found_rec); 270 if (error) 271 goto out_error; 272 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 273 error = -EFSCORRUPTED; 274 goto out_error; 275 } 276 trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.pag->pag_agno, &irec); 277 error = xfs_btree_delete(cur, i); 278 if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) { 279 error = -EFSCORRUPTED; 280 goto out_error; 281 } 282 if (error) 283 goto out_error; 284 error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock, 285 &found_rec); 286out_error: 287 if (error) 288 trace_xfs_refcount_delete_error(cur->bc_mp, 289 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 290 return error; 291} 292 293/* 294 * Adjusting the Reference Count 295 * 296 * As stated elsewhere, the reference count btree (refcbt) stores 297 * >1 reference counts for extents of physical blocks. In this 298 * operation, we're either raising or lowering the reference count of 299 * some subrange stored in the tree: 300 * 301 * <------ adjustment range ------> 302 * ----+ +---+-----+ +--+--------+--------- 303 * 2 | | 3 | 4 | |17| 55 | 10 304 * ----+ +---+-----+ +--+--------+--------- 305 * X axis is physical blocks number; 306 * reference counts are the numbers inside the rectangles 307 * 308 * The first thing we need to do is to ensure that there are no 309 * refcount extents crossing either boundary of the range to be 310 * adjusted. For any extent that does cross a boundary, split it into 311 * two extents so that we can increment the refcount of one of the 312 * pieces later: 313 * 314 * <------ adjustment range ------> 315 * ----+ +---+-----+ +--+--------+----+---- 316 * 2 | | 3 | 2 | |17| 55 | 10 | 10 317 * ----+ +---+-----+ +--+--------+----+---- 318 * 319 * For this next step, let's assume that all the physical blocks in 320 * the adjustment range are mapped to a file and are therefore in use 321 * at least once. Therefore, we can infer that any gap in the 322 * refcount tree within the adjustment range represents a physical 323 * extent with refcount == 1: 324 * 325 * <------ adjustment range ------> 326 * ----+---+---+-----+-+--+--------+----+---- 327 * 2 |"1"| 3 | 2 |1|17| 55 | 10 | 10 328 * ----+---+---+-----+-+--+--------+----+---- 329 * ^ 330 * 331 * For each extent that falls within the interval range, figure out 332 * which extent is to the left or the right of that extent. Now we 333 * have a left, current, and right extent. If the new reference count 334 * of the center extent enables us to merge left, center, and right 335 * into one record covering all three, do so. If the center extent is 336 * at the left end of the range, abuts the left extent, and its new 337 * reference count matches the left extent's record, then merge them. 338 * If the center extent is at the right end of the range, abuts the 339 * right extent, and the reference counts match, merge those. In the 340 * example, we can left merge (assuming an increment operation): 341 * 342 * <------ adjustment range ------> 343 * --------+---+-----+-+--+--------+----+---- 344 * 2 | 3 | 2 |1|17| 55 | 10 | 10 345 * --------+---+-----+-+--+--------+----+---- 346 * ^ 347 * 348 * For all other extents within the range, adjust the reference count 349 * or delete it if the refcount falls below 2. If we were 350 * incrementing, the end result looks like this: 351 * 352 * <------ adjustment range ------> 353 * --------+---+-----+-+--+--------+----+---- 354 * 2 | 4 | 3 |2|18| 56 | 11 | 10 355 * --------+---+-----+-+--+--------+----+---- 356 * 357 * The result of a decrement operation looks as such: 358 * 359 * <------ adjustment range ------> 360 * ----+ +---+ +--+--------+----+---- 361 * 2 | | 2 | |16| 54 | 9 | 10 362 * ----+ +---+ +--+--------+----+---- 363 * DDDD 111111DD 364 * 365 * The blocks marked "D" are freed; the blocks marked "1" are only 366 * referenced once and therefore the record is removed from the 367 * refcount btree. 368 */ 369 370/* Next block after this extent. */ 371static inline xfs_agblock_t 372xfs_refc_next( 373 struct xfs_refcount_irec *rc) 374{ 375 return rc->rc_startblock + rc->rc_blockcount; 376} 377 378/* 379 * Split a refcount extent that crosses agbno. 380 */ 381STATIC int 382xfs_refcount_split_extent( 383 struct xfs_btree_cur *cur, 384 enum xfs_refc_domain domain, 385 xfs_agblock_t agbno, 386 bool *shape_changed) 387{ 388 struct xfs_refcount_irec rcext, tmp; 389 int found_rec; 390 int error; 391 392 *shape_changed = false; 393 error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec); 394 if (error) 395 goto out_error; 396 if (!found_rec) 397 return 0; 398 399 error = xfs_refcount_get_rec(cur, &rcext, &found_rec); 400 if (error) 401 goto out_error; 402 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 403 error = -EFSCORRUPTED; 404 goto out_error; 405 } 406 if (rcext.rc_domain != domain) 407 return 0; 408 if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno) 409 return 0; 410 411 *shape_changed = true; 412 trace_xfs_refcount_split_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, 413 &rcext, agbno); 414 415 /* Establish the right extent. */ 416 tmp = rcext; 417 tmp.rc_startblock = agbno; 418 tmp.rc_blockcount -= (agbno - rcext.rc_startblock); 419 error = xfs_refcount_update(cur, &tmp); 420 if (error) 421 goto out_error; 422 423 /* Insert the left extent. */ 424 tmp = rcext; 425 tmp.rc_blockcount = agbno - rcext.rc_startblock; 426 error = xfs_refcount_insert(cur, &tmp, &found_rec); 427 if (error) 428 goto out_error; 429 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 430 error = -EFSCORRUPTED; 431 goto out_error; 432 } 433 return error; 434 435out_error: 436 trace_xfs_refcount_split_extent_error(cur->bc_mp, 437 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 438 return error; 439} 440 441/* 442 * Merge the left, center, and right extents. 443 */ 444STATIC int 445xfs_refcount_merge_center_extents( 446 struct xfs_btree_cur *cur, 447 struct xfs_refcount_irec *left, 448 struct xfs_refcount_irec *center, 449 struct xfs_refcount_irec *right, 450 unsigned long long extlen, 451 xfs_extlen_t *aglen) 452{ 453 int error; 454 int found_rec; 455 456 trace_xfs_refcount_merge_center_extents(cur->bc_mp, 457 cur->bc_ag.pag->pag_agno, left, center, right); 458 459 ASSERT(left->rc_domain == center->rc_domain); 460 ASSERT(right->rc_domain == center->rc_domain); 461 462 /* 463 * Make sure the center and right extents are not in the btree. 464 * If the center extent was synthesized, the first delete call 465 * removes the right extent and we skip the second deletion. 466 * If center and right were in the btree, then the first delete 467 * call removes the center and the second one removes the right 468 * extent. 469 */ 470 error = xfs_refcount_lookup_ge(cur, center->rc_domain, 471 center->rc_startblock, &found_rec); 472 if (error) 473 goto out_error; 474 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 475 error = -EFSCORRUPTED; 476 goto out_error; 477 } 478 479 error = xfs_refcount_delete(cur, &found_rec); 480 if (error) 481 goto out_error; 482 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 483 error = -EFSCORRUPTED; 484 goto out_error; 485 } 486 487 if (center->rc_refcount > 1) { 488 error = xfs_refcount_delete(cur, &found_rec); 489 if (error) 490 goto out_error; 491 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 492 error = -EFSCORRUPTED; 493 goto out_error; 494 } 495 } 496 497 /* Enlarge the left extent. */ 498 error = xfs_refcount_lookup_le(cur, left->rc_domain, 499 left->rc_startblock, &found_rec); 500 if (error) 501 goto out_error; 502 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 503 error = -EFSCORRUPTED; 504 goto out_error; 505 } 506 507 left->rc_blockcount = extlen; 508 error = xfs_refcount_update(cur, left); 509 if (error) 510 goto out_error; 511 512 *aglen = 0; 513 return error; 514 515out_error: 516 trace_xfs_refcount_merge_center_extents_error(cur->bc_mp, 517 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 518 return error; 519} 520 521/* 522 * Merge with the left extent. 523 */ 524STATIC int 525xfs_refcount_merge_left_extent( 526 struct xfs_btree_cur *cur, 527 struct xfs_refcount_irec *left, 528 struct xfs_refcount_irec *cleft, 529 xfs_agblock_t *agbno, 530 xfs_extlen_t *aglen) 531{ 532 int error; 533 int found_rec; 534 535 trace_xfs_refcount_merge_left_extent(cur->bc_mp, 536 cur->bc_ag.pag->pag_agno, left, cleft); 537 538 ASSERT(left->rc_domain == cleft->rc_domain); 539 540 /* If the extent at agbno (cleft) wasn't synthesized, remove it. */ 541 if (cleft->rc_refcount > 1) { 542 error = xfs_refcount_lookup_le(cur, cleft->rc_domain, 543 cleft->rc_startblock, &found_rec); 544 if (error) 545 goto out_error; 546 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 547 error = -EFSCORRUPTED; 548 goto out_error; 549 } 550 551 error = xfs_refcount_delete(cur, &found_rec); 552 if (error) 553 goto out_error; 554 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 555 error = -EFSCORRUPTED; 556 goto out_error; 557 } 558 } 559 560 /* Enlarge the left extent. */ 561 error = xfs_refcount_lookup_le(cur, left->rc_domain, 562 left->rc_startblock, &found_rec); 563 if (error) 564 goto out_error; 565 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 566 error = -EFSCORRUPTED; 567 goto out_error; 568 } 569 570 left->rc_blockcount += cleft->rc_blockcount; 571 error = xfs_refcount_update(cur, left); 572 if (error) 573 goto out_error; 574 575 *agbno += cleft->rc_blockcount; 576 *aglen -= cleft->rc_blockcount; 577 return error; 578 579out_error: 580 trace_xfs_refcount_merge_left_extent_error(cur->bc_mp, 581 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 582 return error; 583} 584 585/* 586 * Merge with the right extent. 587 */ 588STATIC int 589xfs_refcount_merge_right_extent( 590 struct xfs_btree_cur *cur, 591 struct xfs_refcount_irec *right, 592 struct xfs_refcount_irec *cright, 593 xfs_extlen_t *aglen) 594{ 595 int error; 596 int found_rec; 597 598 trace_xfs_refcount_merge_right_extent(cur->bc_mp, 599 cur->bc_ag.pag->pag_agno, cright, right); 600 601 ASSERT(right->rc_domain == cright->rc_domain); 602 603 /* 604 * If the extent ending at agbno+aglen (cright) wasn't synthesized, 605 * remove it. 606 */ 607 if (cright->rc_refcount > 1) { 608 error = xfs_refcount_lookup_le(cur, cright->rc_domain, 609 cright->rc_startblock, &found_rec); 610 if (error) 611 goto out_error; 612 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 613 error = -EFSCORRUPTED; 614 goto out_error; 615 } 616 617 error = xfs_refcount_delete(cur, &found_rec); 618 if (error) 619 goto out_error; 620 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 621 error = -EFSCORRUPTED; 622 goto out_error; 623 } 624 } 625 626 /* Enlarge the right extent. */ 627 error = xfs_refcount_lookup_le(cur, right->rc_domain, 628 right->rc_startblock, &found_rec); 629 if (error) 630 goto out_error; 631 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 632 error = -EFSCORRUPTED; 633 goto out_error; 634 } 635 636 right->rc_startblock -= cright->rc_blockcount; 637 right->rc_blockcount += cright->rc_blockcount; 638 error = xfs_refcount_update(cur, right); 639 if (error) 640 goto out_error; 641 642 *aglen -= cright->rc_blockcount; 643 return error; 644 645out_error: 646 trace_xfs_refcount_merge_right_extent_error(cur->bc_mp, 647 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 648 return error; 649} 650 651/* 652 * Find the left extent and the one after it (cleft). This function assumes 653 * that we've already split any extent crossing agbno. 654 */ 655STATIC int 656xfs_refcount_find_left_extents( 657 struct xfs_btree_cur *cur, 658 struct xfs_refcount_irec *left, 659 struct xfs_refcount_irec *cleft, 660 enum xfs_refc_domain domain, 661 xfs_agblock_t agbno, 662 xfs_extlen_t aglen) 663{ 664 struct xfs_refcount_irec tmp; 665 int error; 666 int found_rec; 667 668 left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK; 669 error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec); 670 if (error) 671 goto out_error; 672 if (!found_rec) 673 return 0; 674 675 error = xfs_refcount_get_rec(cur, &tmp, &found_rec); 676 if (error) 677 goto out_error; 678 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 679 error = -EFSCORRUPTED; 680 goto out_error; 681 } 682 683 if (tmp.rc_domain != domain) 684 return 0; 685 if (xfs_refc_next(&tmp) != agbno) 686 return 0; 687 /* We have a left extent; retrieve (or invent) the next right one */ 688 *left = tmp; 689 690 error = xfs_btree_increment(cur, 0, &found_rec); 691 if (error) 692 goto out_error; 693 if (found_rec) { 694 error = xfs_refcount_get_rec(cur, &tmp, &found_rec); 695 if (error) 696 goto out_error; 697 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 698 error = -EFSCORRUPTED; 699 goto out_error; 700 } 701 702 if (tmp.rc_domain != domain) 703 goto not_found; 704 705 /* if tmp starts at the end of our range, just use that */ 706 if (tmp.rc_startblock == agbno) 707 *cleft = tmp; 708 else { 709 /* 710 * There's a gap in the refcntbt at the start of the 711 * range we're interested in (refcount == 1) so 712 * synthesize the implied extent and pass it back. 713 * We assume here that the agbno/aglen range was 714 * passed in from a data fork extent mapping and 715 * therefore is allocated to exactly one owner. 716 */ 717 cleft->rc_startblock = agbno; 718 cleft->rc_blockcount = min(aglen, 719 tmp.rc_startblock - agbno); 720 cleft->rc_refcount = 1; 721 cleft->rc_domain = domain; 722 } 723 } else { 724not_found: 725 /* 726 * No extents, so pretend that there's one covering the whole 727 * range. 728 */ 729 cleft->rc_startblock = agbno; 730 cleft->rc_blockcount = aglen; 731 cleft->rc_refcount = 1; 732 cleft->rc_domain = domain; 733 } 734 trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, 735 left, cleft, agbno); 736 return error; 737 738out_error: 739 trace_xfs_refcount_find_left_extent_error(cur->bc_mp, 740 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 741 return error; 742} 743 744/* 745 * Find the right extent and the one before it (cright). This function 746 * assumes that we've already split any extents crossing agbno + aglen. 747 */ 748STATIC int 749xfs_refcount_find_right_extents( 750 struct xfs_btree_cur *cur, 751 struct xfs_refcount_irec *right, 752 struct xfs_refcount_irec *cright, 753 enum xfs_refc_domain domain, 754 xfs_agblock_t agbno, 755 xfs_extlen_t aglen) 756{ 757 struct xfs_refcount_irec tmp; 758 int error; 759 int found_rec; 760 761 right->rc_startblock = cright->rc_startblock = NULLAGBLOCK; 762 error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec); 763 if (error) 764 goto out_error; 765 if (!found_rec) 766 return 0; 767 768 error = xfs_refcount_get_rec(cur, &tmp, &found_rec); 769 if (error) 770 goto out_error; 771 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 772 error = -EFSCORRUPTED; 773 goto out_error; 774 } 775 776 if (tmp.rc_domain != domain) 777 return 0; 778 if (tmp.rc_startblock != agbno + aglen) 779 return 0; 780 /* We have a right extent; retrieve (or invent) the next left one */ 781 *right = tmp; 782 783 error = xfs_btree_decrement(cur, 0, &found_rec); 784 if (error) 785 goto out_error; 786 if (found_rec) { 787 error = xfs_refcount_get_rec(cur, &tmp, &found_rec); 788 if (error) 789 goto out_error; 790 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 791 error = -EFSCORRUPTED; 792 goto out_error; 793 } 794 795 if (tmp.rc_domain != domain) 796 goto not_found; 797 798 /* if tmp ends at the end of our range, just use that */ 799 if (xfs_refc_next(&tmp) == agbno + aglen) 800 *cright = tmp; 801 else { 802 /* 803 * There's a gap in the refcntbt at the end of the 804 * range we're interested in (refcount == 1) so 805 * create the implied extent and pass it back. 806 * We assume here that the agbno/aglen range was 807 * passed in from a data fork extent mapping and 808 * therefore is allocated to exactly one owner. 809 */ 810 cright->rc_startblock = max(agbno, xfs_refc_next(&tmp)); 811 cright->rc_blockcount = right->rc_startblock - 812 cright->rc_startblock; 813 cright->rc_refcount = 1; 814 cright->rc_domain = domain; 815 } 816 } else { 817not_found: 818 /* 819 * No extents, so pretend that there's one covering the whole 820 * range. 821 */ 822 cright->rc_startblock = agbno; 823 cright->rc_blockcount = aglen; 824 cright->rc_refcount = 1; 825 cright->rc_domain = domain; 826 } 827 trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, 828 cright, right, agbno + aglen); 829 return error; 830 831out_error: 832 trace_xfs_refcount_find_right_extent_error(cur->bc_mp, 833 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 834 return error; 835} 836 837/* Is this extent valid? */ 838static inline bool 839xfs_refc_valid( 840 const struct xfs_refcount_irec *rc) 841{ 842 return rc->rc_startblock != NULLAGBLOCK; 843} 844 845static inline xfs_nlink_t 846xfs_refc_merge_refcount( 847 const struct xfs_refcount_irec *irec, 848 enum xfs_refc_adjust_op adjust) 849{ 850 /* Once a record hits MAXREFCOUNT, it is pinned there forever */ 851 if (irec->rc_refcount == MAXREFCOUNT) 852 return MAXREFCOUNT; 853 return irec->rc_refcount + adjust; 854} 855 856static inline bool 857xfs_refc_want_merge_center( 858 const struct xfs_refcount_irec *left, 859 const struct xfs_refcount_irec *cleft, 860 const struct xfs_refcount_irec *cright, 861 const struct xfs_refcount_irec *right, 862 bool cleft_is_cright, 863 enum xfs_refc_adjust_op adjust, 864 unsigned long long *ulenp) 865{ 866 unsigned long long ulen = left->rc_blockcount; 867 xfs_nlink_t new_refcount; 868 869 /* 870 * To merge with a center record, both shoulder records must be 871 * adjacent to the record we want to adjust. This is only true if 872 * find_left and find_right made all four records valid. 873 */ 874 if (!xfs_refc_valid(left) || !xfs_refc_valid(right) || 875 !xfs_refc_valid(cleft) || !xfs_refc_valid(cright)) 876 return false; 877 878 /* There must only be one record for the entire range. */ 879 if (!cleft_is_cright) 880 return false; 881 882 /* The shoulder record refcounts must match the new refcount. */ 883 new_refcount = xfs_refc_merge_refcount(cleft, adjust); 884 if (left->rc_refcount != new_refcount) 885 return false; 886 if (right->rc_refcount != new_refcount) 887 return false; 888 889 /* 890 * The new record cannot exceed the max length. ulen is a ULL as the 891 * individual record block counts can be up to (u32 - 1) in length 892 * hence we need to catch u32 addition overflows here. 893 */ 894 ulen += cleft->rc_blockcount + right->rc_blockcount; 895 if (ulen >= MAXREFCEXTLEN) 896 return false; 897 898 *ulenp = ulen; 899 return true; 900} 901 902static inline bool 903xfs_refc_want_merge_left( 904 const struct xfs_refcount_irec *left, 905 const struct xfs_refcount_irec *cleft, 906 enum xfs_refc_adjust_op adjust) 907{ 908 unsigned long long ulen = left->rc_blockcount; 909 xfs_nlink_t new_refcount; 910 911 /* 912 * For a left merge, the left shoulder record must be adjacent to the 913 * start of the range. If this is true, find_left made left and cleft 914 * contain valid contents. 915 */ 916 if (!xfs_refc_valid(left) || !xfs_refc_valid(cleft)) 917 return false; 918 919 /* Left shoulder record refcount must match the new refcount. */ 920 new_refcount = xfs_refc_merge_refcount(cleft, adjust); 921 if (left->rc_refcount != new_refcount) 922 return false; 923 924 /* 925 * The new record cannot exceed the max length. ulen is a ULL as the 926 * individual record block counts can be up to (u32 - 1) in length 927 * hence we need to catch u32 addition overflows here. 928 */ 929 ulen += cleft->rc_blockcount; 930 if (ulen >= MAXREFCEXTLEN) 931 return false; 932 933 return true; 934} 935 936static inline bool 937xfs_refc_want_merge_right( 938 const struct xfs_refcount_irec *cright, 939 const struct xfs_refcount_irec *right, 940 enum xfs_refc_adjust_op adjust) 941{ 942 unsigned long long ulen = right->rc_blockcount; 943 xfs_nlink_t new_refcount; 944 945 /* 946 * For a right merge, the right shoulder record must be adjacent to the 947 * end of the range. If this is true, find_right made cright and right 948 * contain valid contents. 949 */ 950 if (!xfs_refc_valid(right) || !xfs_refc_valid(cright)) 951 return false; 952 953 /* Right shoulder record refcount must match the new refcount. */ 954 new_refcount = xfs_refc_merge_refcount(cright, adjust); 955 if (right->rc_refcount != new_refcount) 956 return false; 957 958 /* 959 * The new record cannot exceed the max length. ulen is a ULL as the 960 * individual record block counts can be up to (u32 - 1) in length 961 * hence we need to catch u32 addition overflows here. 962 */ 963 ulen += cright->rc_blockcount; 964 if (ulen >= MAXREFCEXTLEN) 965 return false; 966 967 return true; 968} 969 970/* 971 * Try to merge with any extents on the boundaries of the adjustment range. 972 */ 973STATIC int 974xfs_refcount_merge_extents( 975 struct xfs_btree_cur *cur, 976 enum xfs_refc_domain domain, 977 xfs_agblock_t *agbno, 978 xfs_extlen_t *aglen, 979 enum xfs_refc_adjust_op adjust, 980 bool *shape_changed) 981{ 982 struct xfs_refcount_irec left = {0}, cleft = {0}; 983 struct xfs_refcount_irec cright = {0}, right = {0}; 984 int error; 985 unsigned long long ulen; 986 bool cequal; 987 988 *shape_changed = false; 989 /* 990 * Find the extent just below agbno [left], just above agbno [cleft], 991 * just below (agbno + aglen) [cright], and just above (agbno + aglen) 992 * [right]. 993 */ 994 error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain, 995 *agbno, *aglen); 996 if (error) 997 return error; 998 error = xfs_refcount_find_right_extents(cur, &right, &cright, domain, 999 *agbno, *aglen); 1000 if (error) 1001 return error; 1002 1003 /* No left or right extent to merge; exit. */ 1004 if (!xfs_refc_valid(&left) && !xfs_refc_valid(&right)) 1005 return 0; 1006 1007 cequal = (cleft.rc_startblock == cright.rc_startblock) && 1008 (cleft.rc_blockcount == cright.rc_blockcount); 1009 1010 /* Try to merge left, cleft, and right. cleft must == cright. */ 1011 if (xfs_refc_want_merge_center(&left, &cleft, &cright, &right, cequal, 1012 adjust, &ulen)) { 1013 *shape_changed = true; 1014 return xfs_refcount_merge_center_extents(cur, &left, &cleft, 1015 &right, ulen, aglen); 1016 } 1017 1018 /* Try to merge left and cleft. */ 1019 if (xfs_refc_want_merge_left(&left, &cleft, adjust)) { 1020 *shape_changed = true; 1021 error = xfs_refcount_merge_left_extent(cur, &left, &cleft, 1022 agbno, aglen); 1023 if (error) 1024 return error; 1025 1026 /* 1027 * If we just merged left + cleft and cleft == cright, 1028 * we no longer have a cright to merge with right. We're done. 1029 */ 1030 if (cequal) 1031 return 0; 1032 } 1033 1034 /* Try to merge cright and right. */ 1035 if (xfs_refc_want_merge_right(&cright, &right, adjust)) { 1036 *shape_changed = true; 1037 return xfs_refcount_merge_right_extent(cur, &right, &cright, 1038 aglen); 1039 } 1040 1041 return 0; 1042} 1043 1044/* 1045 * XXX: This is a pretty hand-wavy estimate. The penalty for guessing 1046 * true incorrectly is a shutdown FS; the penalty for guessing false 1047 * incorrectly is more transaction rolls than might be necessary. 1048 * Be conservative here. 1049 */ 1050static bool 1051xfs_refcount_still_have_space( 1052 struct xfs_btree_cur *cur) 1053{ 1054 unsigned long overhead; 1055 1056 /* 1057 * Worst case estimate: full splits of the free space and rmap btrees 1058 * to handle each of the shape changes to the refcount btree. 1059 */ 1060 overhead = xfs_allocfree_block_count(cur->bc_mp, 1061 cur->bc_ag.refc.shape_changes); 1062 overhead += cur->bc_mp->m_refc_maxlevels; 1063 overhead *= cur->bc_mp->m_sb.sb_blocksize; 1064 1065 /* 1066 * Only allow 2 refcount extent updates per transaction if the 1067 * refcount continue update "error" has been injected. 1068 */ 1069 if (cur->bc_ag.refc.nr_ops > 2 && 1070 XFS_TEST_ERROR(false, cur->bc_mp, 1071 XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE)) 1072 return false; 1073 1074 if (cur->bc_ag.refc.nr_ops == 0) 1075 return true; 1076 else if (overhead > cur->bc_tp->t_log_res) 1077 return false; 1078 return cur->bc_tp->t_log_res - overhead > 1079 cur->bc_ag.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; 1080} 1081 1082/* 1083 * Adjust the refcounts of middle extents. At this point we should have 1084 * split extents that crossed the adjustment range; merged with adjacent 1085 * extents; and updated agbno/aglen to reflect the merges. Therefore, 1086 * all we have to do is update the extents inside [agbno, agbno + aglen]. 1087 */ 1088STATIC int 1089xfs_refcount_adjust_extents( 1090 struct xfs_btree_cur *cur, 1091 xfs_agblock_t *agbno, 1092 xfs_extlen_t *aglen, 1093 enum xfs_refc_adjust_op adj) 1094{ 1095 struct xfs_refcount_irec ext, tmp; 1096 int error; 1097 int found_rec, found_tmp; 1098 xfs_fsblock_t fsbno; 1099 1100 /* Merging did all the work already. */ 1101 if (*aglen == 0) 1102 return 0; 1103 1104 error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno, 1105 &found_rec); 1106 if (error) 1107 goto out_error; 1108 1109 while (*aglen > 0 && xfs_refcount_still_have_space(cur)) { 1110 error = xfs_refcount_get_rec(cur, &ext, &found_rec); 1111 if (error) 1112 goto out_error; 1113 if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { 1114 ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; 1115 ext.rc_blockcount = 0; 1116 ext.rc_refcount = 0; 1117 ext.rc_domain = XFS_REFC_DOMAIN_SHARED; 1118 } 1119 1120 /* 1121 * Deal with a hole in the refcount tree; if a file maps to 1122 * these blocks and there's no refcountbt record, pretend that 1123 * there is one with refcount == 1. 1124 */ 1125 if (ext.rc_startblock != *agbno) { 1126 tmp.rc_startblock = *agbno; 1127 tmp.rc_blockcount = min(*aglen, 1128 ext.rc_startblock - *agbno); 1129 tmp.rc_refcount = 1 + adj; 1130 tmp.rc_domain = XFS_REFC_DOMAIN_SHARED; 1131 1132 trace_xfs_refcount_modify_extent(cur->bc_mp, 1133 cur->bc_ag.pag->pag_agno, &tmp); 1134 1135 /* 1136 * Either cover the hole (increment) or 1137 * delete the range (decrement). 1138 */ 1139 cur->bc_ag.refc.nr_ops++; 1140 if (tmp.rc_refcount) { 1141 error = xfs_refcount_insert(cur, &tmp, 1142 &found_tmp); 1143 if (error) 1144 goto out_error; 1145 if (XFS_IS_CORRUPT(cur->bc_mp, 1146 found_tmp != 1)) { 1147 error = -EFSCORRUPTED; 1148 goto out_error; 1149 } 1150 } else { 1151 fsbno = XFS_AGB_TO_FSB(cur->bc_mp, 1152 cur->bc_ag.pag->pag_agno, 1153 tmp.rc_startblock); 1154 error = xfs_free_extent_later(cur->bc_tp, fsbno, 1155 tmp.rc_blockcount, NULL, 1156 XFS_AG_RESV_NONE); 1157 if (error) 1158 goto out_error; 1159 } 1160 1161 (*agbno) += tmp.rc_blockcount; 1162 (*aglen) -= tmp.rc_blockcount; 1163 1164 /* Stop if there's nothing left to modify */ 1165 if (*aglen == 0 || !xfs_refcount_still_have_space(cur)) 1166 break; 1167 1168 /* Move the cursor to the start of ext. */ 1169 error = xfs_refcount_lookup_ge(cur, 1170 XFS_REFC_DOMAIN_SHARED, *agbno, 1171 &found_rec); 1172 if (error) 1173 goto out_error; 1174 } 1175 1176 /* 1177 * A previous step trimmed agbno/aglen such that the end of the 1178 * range would not be in the middle of the record. If this is 1179 * no longer the case, something is seriously wrong with the 1180 * btree. Make sure we never feed the synthesized record into 1181 * the processing loop below. 1182 */ 1183 if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) || 1184 XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) { 1185 error = -EFSCORRUPTED; 1186 goto out_error; 1187 } 1188 1189 /* 1190 * Adjust the reference count and either update the tree 1191 * (incr) or free the blocks (decr). 1192 */ 1193 if (ext.rc_refcount == MAXREFCOUNT) 1194 goto skip; 1195 ext.rc_refcount += adj; 1196 trace_xfs_refcount_modify_extent(cur->bc_mp, 1197 cur->bc_ag.pag->pag_agno, &ext); 1198 cur->bc_ag.refc.nr_ops++; 1199 if (ext.rc_refcount > 1) { 1200 error = xfs_refcount_update(cur, &ext); 1201 if (error) 1202 goto out_error; 1203 } else if (ext.rc_refcount == 1) { 1204 error = xfs_refcount_delete(cur, &found_rec); 1205 if (error) 1206 goto out_error; 1207 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 1208 error = -EFSCORRUPTED; 1209 goto out_error; 1210 } 1211 goto advloop; 1212 } else { 1213 fsbno = XFS_AGB_TO_FSB(cur->bc_mp, 1214 cur->bc_ag.pag->pag_agno, 1215 ext.rc_startblock); 1216 error = xfs_free_extent_later(cur->bc_tp, fsbno, 1217 ext.rc_blockcount, NULL, 1218 XFS_AG_RESV_NONE); 1219 if (error) 1220 goto out_error; 1221 } 1222 1223skip: 1224 error = xfs_btree_increment(cur, 0, &found_rec); 1225 if (error) 1226 goto out_error; 1227 1228advloop: 1229 (*agbno) += ext.rc_blockcount; 1230 (*aglen) -= ext.rc_blockcount; 1231 } 1232 1233 return error; 1234out_error: 1235 trace_xfs_refcount_modify_extent_error(cur->bc_mp, 1236 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 1237 return error; 1238} 1239 1240/* Adjust the reference count of a range of AG blocks. */ 1241STATIC int 1242xfs_refcount_adjust( 1243 struct xfs_btree_cur *cur, 1244 xfs_agblock_t *agbno, 1245 xfs_extlen_t *aglen, 1246 enum xfs_refc_adjust_op adj) 1247{ 1248 bool shape_changed; 1249 int shape_changes = 0; 1250 int error; 1251 1252 if (adj == XFS_REFCOUNT_ADJUST_INCREASE) 1253 trace_xfs_refcount_increase(cur->bc_mp, 1254 cur->bc_ag.pag->pag_agno, *agbno, *aglen); 1255 else 1256 trace_xfs_refcount_decrease(cur->bc_mp, 1257 cur->bc_ag.pag->pag_agno, *agbno, *aglen); 1258 1259 /* 1260 * Ensure that no rcextents cross the boundary of the adjustment range. 1261 */ 1262 error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, 1263 *agbno, &shape_changed); 1264 if (error) 1265 goto out_error; 1266 if (shape_changed) 1267 shape_changes++; 1268 1269 error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, 1270 *agbno + *aglen, &shape_changed); 1271 if (error) 1272 goto out_error; 1273 if (shape_changed) 1274 shape_changes++; 1275 1276 /* 1277 * Try to merge with the left or right extents of the range. 1278 */ 1279 error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED, 1280 agbno, aglen, adj, &shape_changed); 1281 if (error) 1282 goto out_error; 1283 if (shape_changed) 1284 shape_changes++; 1285 if (shape_changes) 1286 cur->bc_ag.refc.shape_changes++; 1287 1288 /* Now that we've taken care of the ends, adjust the middle extents */ 1289 error = xfs_refcount_adjust_extents(cur, agbno, aglen, adj); 1290 if (error) 1291 goto out_error; 1292 1293 return 0; 1294 1295out_error: 1296 trace_xfs_refcount_adjust_error(cur->bc_mp, cur->bc_ag.pag->pag_agno, 1297 error, _RET_IP_); 1298 return error; 1299} 1300 1301/* Clean up after calling xfs_refcount_finish_one. */ 1302void 1303xfs_refcount_finish_one_cleanup( 1304 struct xfs_trans *tp, 1305 struct xfs_btree_cur *rcur, 1306 int error) 1307{ 1308 struct xfs_buf *agbp; 1309 1310 if (rcur == NULL) 1311 return; 1312 agbp = rcur->bc_ag.agbp; 1313 xfs_btree_del_cursor(rcur, error); 1314 if (error) 1315 xfs_trans_brelse(tp, agbp); 1316} 1317 1318/* 1319 * Set up a continuation a deferred refcount operation by updating the intent. 1320 * Checks to make sure we're not going to run off the end of the AG. 1321 */ 1322static inline int 1323xfs_refcount_continue_op( 1324 struct xfs_btree_cur *cur, 1325 struct xfs_refcount_intent *ri, 1326 xfs_agblock_t new_agbno) 1327{ 1328 struct xfs_mount *mp = cur->bc_mp; 1329 struct xfs_perag *pag = cur->bc_ag.pag; 1330 1331 if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, 1332 ri->ri_blockcount))) 1333 return -EFSCORRUPTED; 1334 1335 ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); 1336 1337 ASSERT(xfs_verify_fsbext(mp, ri->ri_startblock, ri->ri_blockcount)); 1338 ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, ri->ri_startblock)); 1339 1340 return 0; 1341} 1342 1343/* 1344 * Process one of the deferred refcount operations. We pass back the 1345 * btree cursor to maintain our lock on the btree between calls. 1346 * This saves time and eliminates a buffer deadlock between the 1347 * superblock and the AGF because we'll always grab them in the same 1348 * order. 1349 */ 1350int 1351xfs_refcount_finish_one( 1352 struct xfs_trans *tp, 1353 struct xfs_refcount_intent *ri, 1354 struct xfs_btree_cur **pcur) 1355{ 1356 struct xfs_mount *mp = tp->t_mountp; 1357 struct xfs_btree_cur *rcur; 1358 struct xfs_buf *agbp = NULL; 1359 int error = 0; 1360 xfs_agblock_t bno; 1361 unsigned long nr_ops = 0; 1362 int shape_changes = 0; 1363 1364 bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock); 1365 1366 trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock), 1367 ri->ri_type, XFS_FSB_TO_AGBNO(mp, ri->ri_startblock), 1368 ri->ri_blockcount); 1369 1370 if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) 1371 return -EIO; 1372 1373 /* 1374 * If we haven't gotten a cursor or the cursor AG doesn't match 1375 * the startblock, get one now. 1376 */ 1377 rcur = *pcur; 1378 if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) { 1379 nr_ops = rcur->bc_ag.refc.nr_ops; 1380 shape_changes = rcur->bc_ag.refc.shape_changes; 1381 xfs_refcount_finish_one_cleanup(tp, rcur, 0); 1382 rcur = NULL; 1383 *pcur = NULL; 1384 } 1385 if (rcur == NULL) { 1386 error = xfs_alloc_read_agf(ri->ri_pag, tp, 1387 XFS_ALLOC_FLAG_FREEING, &agbp); 1388 if (error) 1389 return error; 1390 1391 rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, ri->ri_pag); 1392 rcur->bc_ag.refc.nr_ops = nr_ops; 1393 rcur->bc_ag.refc.shape_changes = shape_changes; 1394 } 1395 *pcur = rcur; 1396 1397 switch (ri->ri_type) { 1398 case XFS_REFCOUNT_INCREASE: 1399 error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, 1400 XFS_REFCOUNT_ADJUST_INCREASE); 1401 if (error) 1402 return error; 1403 if (ri->ri_blockcount > 0) 1404 error = xfs_refcount_continue_op(rcur, ri, bno); 1405 break; 1406 case XFS_REFCOUNT_DECREASE: 1407 error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, 1408 XFS_REFCOUNT_ADJUST_DECREASE); 1409 if (error) 1410 return error; 1411 if (ri->ri_blockcount > 0) 1412 error = xfs_refcount_continue_op(rcur, ri, bno); 1413 break; 1414 case XFS_REFCOUNT_ALLOC_COW: 1415 error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); 1416 if (error) 1417 return error; 1418 ri->ri_blockcount = 0; 1419 break; 1420 case XFS_REFCOUNT_FREE_COW: 1421 error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); 1422 if (error) 1423 return error; 1424 ri->ri_blockcount = 0; 1425 break; 1426 default: 1427 ASSERT(0); 1428 return -EFSCORRUPTED; 1429 } 1430 if (!error && ri->ri_blockcount > 0) 1431 trace_xfs_refcount_finish_one_leftover(mp, ri->ri_pag->pag_agno, 1432 ri->ri_type, bno, ri->ri_blockcount); 1433 return error; 1434} 1435 1436/* 1437 * Record a refcount intent for later processing. 1438 */ 1439static void 1440__xfs_refcount_add( 1441 struct xfs_trans *tp, 1442 enum xfs_refcount_intent_type type, 1443 xfs_fsblock_t startblock, 1444 xfs_extlen_t blockcount) 1445{ 1446 struct xfs_refcount_intent *ri; 1447 1448 trace_xfs_refcount_defer(tp->t_mountp, 1449 XFS_FSB_TO_AGNO(tp->t_mountp, startblock), 1450 type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), 1451 blockcount); 1452 1453 ri = kmem_cache_alloc(xfs_refcount_intent_cache, 1454 GFP_NOFS | __GFP_NOFAIL); 1455 INIT_LIST_HEAD(&ri->ri_list); 1456 ri->ri_type = type; 1457 ri->ri_startblock = startblock; 1458 ri->ri_blockcount = blockcount; 1459 1460 xfs_refcount_update_get_group(tp->t_mountp, ri); 1461 xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list); 1462} 1463 1464/* 1465 * Increase the reference count of the blocks backing a file's extent. 1466 */ 1467void 1468xfs_refcount_increase_extent( 1469 struct xfs_trans *tp, 1470 struct xfs_bmbt_irec *PREV) 1471{ 1472 if (!xfs_has_reflink(tp->t_mountp)) 1473 return; 1474 1475 __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, PREV->br_startblock, 1476 PREV->br_blockcount); 1477} 1478 1479/* 1480 * Decrease the reference count of the blocks backing a file's extent. 1481 */ 1482void 1483xfs_refcount_decrease_extent( 1484 struct xfs_trans *tp, 1485 struct xfs_bmbt_irec *PREV) 1486{ 1487 if (!xfs_has_reflink(tp->t_mountp)) 1488 return; 1489 1490 __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, PREV->br_startblock, 1491 PREV->br_blockcount); 1492} 1493 1494/* 1495 * Given an AG extent, find the lowest-numbered run of shared blocks 1496 * within that range and return the range in fbno/flen. If 1497 * find_end_of_shared is set, return the longest contiguous extent of 1498 * shared blocks; if not, just return the first extent we find. If no 1499 * shared blocks are found, fbno and flen will be set to NULLAGBLOCK 1500 * and 0, respectively. 1501 */ 1502int 1503xfs_refcount_find_shared( 1504 struct xfs_btree_cur *cur, 1505 xfs_agblock_t agbno, 1506 xfs_extlen_t aglen, 1507 xfs_agblock_t *fbno, 1508 xfs_extlen_t *flen, 1509 bool find_end_of_shared) 1510{ 1511 struct xfs_refcount_irec tmp; 1512 int i; 1513 int have; 1514 int error; 1515 1516 trace_xfs_refcount_find_shared(cur->bc_mp, cur->bc_ag.pag->pag_agno, 1517 agbno, aglen); 1518 1519 /* By default, skip the whole range */ 1520 *fbno = NULLAGBLOCK; 1521 *flen = 0; 1522 1523 /* Try to find a refcount extent that crosses the start */ 1524 error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno, 1525 &have); 1526 if (error) 1527 goto out_error; 1528 if (!have) { 1529 /* No left extent, look at the next one */ 1530 error = xfs_btree_increment(cur, 0, &have); 1531 if (error) 1532 goto out_error; 1533 if (!have) 1534 goto done; 1535 } 1536 error = xfs_refcount_get_rec(cur, &tmp, &i); 1537 if (error) 1538 goto out_error; 1539 if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { 1540 error = -EFSCORRUPTED; 1541 goto out_error; 1542 } 1543 if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) 1544 goto done; 1545 1546 /* If the extent ends before the start, look at the next one */ 1547 if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) { 1548 error = xfs_btree_increment(cur, 0, &have); 1549 if (error) 1550 goto out_error; 1551 if (!have) 1552 goto done; 1553 error = xfs_refcount_get_rec(cur, &tmp, &i); 1554 if (error) 1555 goto out_error; 1556 if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { 1557 error = -EFSCORRUPTED; 1558 goto out_error; 1559 } 1560 if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) 1561 goto done; 1562 } 1563 1564 /* If the extent starts after the range we want, bail out */ 1565 if (tmp.rc_startblock >= agbno + aglen) 1566 goto done; 1567 1568 /* We found the start of a shared extent! */ 1569 if (tmp.rc_startblock < agbno) { 1570 tmp.rc_blockcount -= (agbno - tmp.rc_startblock); 1571 tmp.rc_startblock = agbno; 1572 } 1573 1574 *fbno = tmp.rc_startblock; 1575 *flen = min(tmp.rc_blockcount, agbno + aglen - *fbno); 1576 if (!find_end_of_shared) 1577 goto done; 1578 1579 /* Otherwise, find the end of this shared extent */ 1580 while (*fbno + *flen < agbno + aglen) { 1581 error = xfs_btree_increment(cur, 0, &have); 1582 if (error) 1583 goto out_error; 1584 if (!have) 1585 break; 1586 error = xfs_refcount_get_rec(cur, &tmp, &i); 1587 if (error) 1588 goto out_error; 1589 if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { 1590 error = -EFSCORRUPTED; 1591 goto out_error; 1592 } 1593 if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED || 1594 tmp.rc_startblock >= agbno + aglen || 1595 tmp.rc_startblock != *fbno + *flen) 1596 break; 1597 *flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno); 1598 } 1599 1600done: 1601 trace_xfs_refcount_find_shared_result(cur->bc_mp, 1602 cur->bc_ag.pag->pag_agno, *fbno, *flen); 1603 1604out_error: 1605 if (error) 1606 trace_xfs_refcount_find_shared_error(cur->bc_mp, 1607 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 1608 return error; 1609} 1610 1611/* 1612 * Recovering CoW Blocks After a Crash 1613 * 1614 * Due to the way that the copy on write mechanism works, there's a window of 1615 * opportunity in which we can lose track of allocated blocks during a crash. 1616 * Because CoW uses delayed allocation in the in-core CoW fork, writeback 1617 * causes blocks to be allocated and stored in the CoW fork. The blocks are 1618 * no longer in the free space btree but are not otherwise recorded anywhere 1619 * until the write completes and the blocks are mapped into the file. A crash 1620 * in between allocation and remapping results in the replacement blocks being 1621 * lost. This situation is exacerbated by the CoW extent size hint because 1622 * allocations can hang around for long time. 1623 * 1624 * However, there is a place where we can record these allocations before they 1625 * become mappings -- the reference count btree. The btree does not record 1626 * extents with refcount == 1, so we can record allocations with a refcount of 1627 * 1. Blocks being used for CoW writeout cannot be shared, so there should be 1628 * no conflict with shared block records. These mappings should be created 1629 * when we allocate blocks to the CoW fork and deleted when they're removed 1630 * from the CoW fork. 1631 * 1632 * Minor nit: records for in-progress CoW allocations and records for shared 1633 * extents must never be merged, to preserve the property that (except for CoW 1634 * allocations) there are no refcount btree entries with refcount == 1. The 1635 * only time this could potentially happen is when unsharing a block that's 1636 * adjacent to CoW allocations, so we must be careful to avoid this. 1637 * 1638 * At mount time we recover lost CoW allocations by searching the refcount 1639 * btree for these refcount == 1 mappings. These represent CoW allocations 1640 * that were in progress at the time the filesystem went down, so we can free 1641 * them to get the space back. 1642 * 1643 * This mechanism is superior to creating EFIs for unmapped CoW extents for 1644 * several reasons -- first, EFIs pin the tail of the log and would have to be 1645 * periodically relogged to avoid filling up the log. Second, CoW completions 1646 * will have to file an EFD and create new EFIs for whatever remains in the 1647 * CoW fork; this partially takes care of (1) but extent-size reservations 1648 * will have to periodically relog even if there's no writeout in progress. 1649 * This can happen if the CoW extent size hint is set, which you really want. 1650 * Third, EFIs cannot currently be automatically relogged into newer 1651 * transactions to advance the log tail. Fourth, stuffing the log full of 1652 * EFIs places an upper bound on the number of CoW allocations that can be 1653 * held filesystem-wide at any given time. Recording them in the refcount 1654 * btree doesn't require us to maintain any state in memory and doesn't pin 1655 * the log. 1656 */ 1657/* 1658 * Adjust the refcounts of CoW allocations. These allocations are "magic" 1659 * in that they're not referenced anywhere else in the filesystem, so we 1660 * stash them in the refcount btree with a refcount of 1 until either file 1661 * remapping (or CoW cancellation) happens. 1662 */ 1663STATIC int 1664xfs_refcount_adjust_cow_extents( 1665 struct xfs_btree_cur *cur, 1666 xfs_agblock_t agbno, 1667 xfs_extlen_t aglen, 1668 enum xfs_refc_adjust_op adj) 1669{ 1670 struct xfs_refcount_irec ext, tmp; 1671 int error; 1672 int found_rec, found_tmp; 1673 1674 if (aglen == 0) 1675 return 0; 1676 1677 /* Find any overlapping refcount records */ 1678 error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno, 1679 &found_rec); 1680 if (error) 1681 goto out_error; 1682 error = xfs_refcount_get_rec(cur, &ext, &found_rec); 1683 if (error) 1684 goto out_error; 1685 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec && 1686 ext.rc_domain != XFS_REFC_DOMAIN_COW)) { 1687 error = -EFSCORRUPTED; 1688 goto out_error; 1689 } 1690 if (!found_rec) { 1691 ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; 1692 ext.rc_blockcount = 0; 1693 ext.rc_refcount = 0; 1694 ext.rc_domain = XFS_REFC_DOMAIN_COW; 1695 } 1696 1697 switch (adj) { 1698 case XFS_REFCOUNT_ADJUST_COW_ALLOC: 1699 /* Adding a CoW reservation, there should be nothing here. */ 1700 if (XFS_IS_CORRUPT(cur->bc_mp, 1701 agbno + aglen > ext.rc_startblock)) { 1702 error = -EFSCORRUPTED; 1703 goto out_error; 1704 } 1705 1706 tmp.rc_startblock = agbno; 1707 tmp.rc_blockcount = aglen; 1708 tmp.rc_refcount = 1; 1709 tmp.rc_domain = XFS_REFC_DOMAIN_COW; 1710 1711 trace_xfs_refcount_modify_extent(cur->bc_mp, 1712 cur->bc_ag.pag->pag_agno, &tmp); 1713 1714 error = xfs_refcount_insert(cur, &tmp, 1715 &found_tmp); 1716 if (error) 1717 goto out_error; 1718 if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) { 1719 error = -EFSCORRUPTED; 1720 goto out_error; 1721 } 1722 break; 1723 case XFS_REFCOUNT_ADJUST_COW_FREE: 1724 /* Removing a CoW reservation, there should be one extent. */ 1725 if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) { 1726 error = -EFSCORRUPTED; 1727 goto out_error; 1728 } 1729 if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) { 1730 error = -EFSCORRUPTED; 1731 goto out_error; 1732 } 1733 if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) { 1734 error = -EFSCORRUPTED; 1735 goto out_error; 1736 } 1737 1738 ext.rc_refcount = 0; 1739 trace_xfs_refcount_modify_extent(cur->bc_mp, 1740 cur->bc_ag.pag->pag_agno, &ext); 1741 error = xfs_refcount_delete(cur, &found_rec); 1742 if (error) 1743 goto out_error; 1744 if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { 1745 error = -EFSCORRUPTED; 1746 goto out_error; 1747 } 1748 break; 1749 default: 1750 ASSERT(0); 1751 } 1752 1753 return error; 1754out_error: 1755 trace_xfs_refcount_modify_extent_error(cur->bc_mp, 1756 cur->bc_ag.pag->pag_agno, error, _RET_IP_); 1757 return error; 1758} 1759 1760/* 1761 * Add or remove refcount btree entries for CoW reservations. 1762 */ 1763STATIC int 1764xfs_refcount_adjust_cow( 1765 struct xfs_btree_cur *cur, 1766 xfs_agblock_t agbno, 1767 xfs_extlen_t aglen, 1768 enum xfs_refc_adjust_op adj) 1769{ 1770 bool shape_changed; 1771 int error; 1772 1773 /* 1774 * Ensure that no rcextents cross the boundary of the adjustment range. 1775 */ 1776 error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, 1777 agbno, &shape_changed); 1778 if (error) 1779 goto out_error; 1780 1781 error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, 1782 agbno + aglen, &shape_changed); 1783 if (error) 1784 goto out_error; 1785 1786 /* 1787 * Try to merge with the left or right extents of the range. 1788 */ 1789 error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno, 1790 &aglen, adj, &shape_changed); 1791 if (error) 1792 goto out_error; 1793 1794 /* Now that we've taken care of the ends, adjust the middle extents */ 1795 error = xfs_refcount_adjust_cow_extents(cur, agbno, aglen, adj); 1796 if (error) 1797 goto out_error; 1798 1799 return 0; 1800 1801out_error: 1802 trace_xfs_refcount_adjust_cow_error(cur->bc_mp, cur->bc_ag.pag->pag_agno, 1803 error, _RET_IP_); 1804 return error; 1805} 1806 1807/* 1808 * Record a CoW allocation in the refcount btree. 1809 */ 1810STATIC int 1811__xfs_refcount_cow_alloc( 1812 struct xfs_btree_cur *rcur, 1813 xfs_agblock_t agbno, 1814 xfs_extlen_t aglen) 1815{ 1816 trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, 1817 agbno, aglen); 1818 1819 /* Add refcount btree reservation */ 1820 return xfs_refcount_adjust_cow(rcur, agbno, aglen, 1821 XFS_REFCOUNT_ADJUST_COW_ALLOC); 1822} 1823 1824/* 1825 * Remove a CoW allocation from the refcount btree. 1826 */ 1827STATIC int 1828__xfs_refcount_cow_free( 1829 struct xfs_btree_cur *rcur, 1830 xfs_agblock_t agbno, 1831 xfs_extlen_t aglen) 1832{ 1833 trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, 1834 agbno, aglen); 1835 1836 /* Remove refcount btree reservation */ 1837 return xfs_refcount_adjust_cow(rcur, agbno, aglen, 1838 XFS_REFCOUNT_ADJUST_COW_FREE); 1839} 1840 1841/* Record a CoW staging extent in the refcount btree. */ 1842void 1843xfs_refcount_alloc_cow_extent( 1844 struct xfs_trans *tp, 1845 xfs_fsblock_t fsb, 1846 xfs_extlen_t len) 1847{ 1848 struct xfs_mount *mp = tp->t_mountp; 1849 1850 if (!xfs_has_reflink(mp)) 1851 return; 1852 1853 __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len); 1854 1855 /* Add rmap entry */ 1856 xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), 1857 XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); 1858} 1859 1860/* Forget a CoW staging event in the refcount btree. */ 1861void 1862xfs_refcount_free_cow_extent( 1863 struct xfs_trans *tp, 1864 xfs_fsblock_t fsb, 1865 xfs_extlen_t len) 1866{ 1867 struct xfs_mount *mp = tp->t_mountp; 1868 1869 if (!xfs_has_reflink(mp)) 1870 return; 1871 1872 /* Remove rmap entry */ 1873 xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), 1874 XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); 1875 __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len); 1876} 1877 1878struct xfs_refcount_recovery { 1879 struct list_head rr_list; 1880 struct xfs_refcount_irec rr_rrec; 1881}; 1882 1883/* Stuff an extent on the recovery list. */ 1884STATIC int 1885xfs_refcount_recover_extent( 1886 struct xfs_btree_cur *cur, 1887 const union xfs_btree_rec *rec, 1888 void *priv) 1889{ 1890 struct list_head *debris = priv; 1891 struct xfs_refcount_recovery *rr; 1892 1893 if (XFS_IS_CORRUPT(cur->bc_mp, 1894 be32_to_cpu(rec->refc.rc_refcount) != 1)) 1895 return -EFSCORRUPTED; 1896 1897 rr = kmalloc(sizeof(struct xfs_refcount_recovery), 1898 GFP_KERNEL | __GFP_NOFAIL); 1899 INIT_LIST_HEAD(&rr->rr_list); 1900 xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); 1901 1902 if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL || 1903 XFS_IS_CORRUPT(cur->bc_mp, 1904 rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { 1905 kfree(rr); 1906 return -EFSCORRUPTED; 1907 } 1908 1909 list_add_tail(&rr->rr_list, debris); 1910 return 0; 1911} 1912 1913/* Find and remove leftover CoW reservations. */ 1914int 1915xfs_refcount_recover_cow_leftovers( 1916 struct xfs_mount *mp, 1917 struct xfs_perag *pag) 1918{ 1919 struct xfs_trans *tp; 1920 struct xfs_btree_cur *cur; 1921 struct xfs_buf *agbp; 1922 struct xfs_refcount_recovery *rr, *n; 1923 struct list_head debris; 1924 union xfs_btree_irec low = { 1925 .rc.rc_domain = XFS_REFC_DOMAIN_COW, 1926 }; 1927 union xfs_btree_irec high = { 1928 .rc.rc_domain = XFS_REFC_DOMAIN_COW, 1929 .rc.rc_startblock = -1U, 1930 }; 1931 xfs_fsblock_t fsb; 1932 int error; 1933 1934 /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ 1935 BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); 1936 if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) 1937 return -EOPNOTSUPP; 1938 1939 INIT_LIST_HEAD(&debris); 1940 1941 /* 1942 * In this first part, we use an empty transaction to gather up 1943 * all the leftover CoW extents so that we can subsequently 1944 * delete them. The empty transaction is used to avoid 1945 * a buffer lock deadlock if there happens to be a loop in the 1946 * refcountbt because we're allowed to re-grab a buffer that is 1947 * already attached to our transaction. When we're done 1948 * recording the CoW debris we cancel the (empty) transaction 1949 * and everything goes away cleanly. 1950 */ 1951 error = xfs_trans_alloc_empty(mp, &tp); 1952 if (error) 1953 return error; 1954 1955 error = xfs_alloc_read_agf(pag, tp, 0, &agbp); 1956 if (error) 1957 goto out_trans; 1958 cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); 1959 1960 /* Find all the leftover CoW staging extents. */ 1961 error = xfs_btree_query_range(cur, &low, &high, 1962 xfs_refcount_recover_extent, &debris); 1963 xfs_btree_del_cursor(cur, error); 1964 xfs_trans_brelse(tp, agbp); 1965 xfs_trans_cancel(tp); 1966 if (error) 1967 goto out_free; 1968 1969 /* Now iterate the list to free the leftovers */ 1970 list_for_each_entry_safe(rr, n, &debris, rr_list) { 1971 /* Set up transaction. */ 1972 error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp); 1973 if (error) 1974 goto out_free; 1975 1976 trace_xfs_refcount_recover_extent(mp, pag->pag_agno, 1977 &rr->rr_rrec); 1978 1979 /* Free the orphan record */ 1980 fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, 1981 rr->rr_rrec.rc_startblock); 1982 xfs_refcount_free_cow_extent(tp, fsb, 1983 rr->rr_rrec.rc_blockcount); 1984 1985 /* Free the block. */ 1986 error = xfs_free_extent_later(tp, fsb, 1987 rr->rr_rrec.rc_blockcount, NULL, 1988 XFS_AG_RESV_NONE); 1989 if (error) 1990 goto out_trans; 1991 1992 error = xfs_trans_commit(tp); 1993 if (error) 1994 goto out_free; 1995 1996 list_del(&rr->rr_list); 1997 kfree(rr); 1998 } 1999 2000 return error; 2001out_trans: 2002 xfs_trans_cancel(tp); 2003out_free: 2004 /* Free the leftover list */ 2005 list_for_each_entry_safe(rr, n, &debris, rr_list) { 2006 list_del(&rr->rr_list); 2007 kfree(rr); 2008 } 2009 return error; 2010} 2011 2012/* 2013 * Scan part of the keyspace of the refcount records and tell us if the area 2014 * has no records, is fully mapped by records, or is partially filled. 2015 */ 2016int 2017xfs_refcount_has_records( 2018 struct xfs_btree_cur *cur, 2019 enum xfs_refc_domain domain, 2020 xfs_agblock_t bno, 2021 xfs_extlen_t len, 2022 enum xbtree_recpacking *outcome) 2023{ 2024 union xfs_btree_irec low; 2025 union xfs_btree_irec high; 2026 2027 memset(&low, 0, sizeof(low)); 2028 low.rc.rc_startblock = bno; 2029 memset(&high, 0xFF, sizeof(high)); 2030 high.rc.rc_startblock = bno + len - 1; 2031 low.rc.rc_domain = high.rc.rc_domain = domain; 2032 2033 return xfs_btree_has_records(cur, &low, &high, NULL, outcome); 2034} 2035 2036int __init 2037xfs_refcount_intent_init_cache(void) 2038{ 2039 xfs_refcount_intent_cache = kmem_cache_create("xfs_refc_intent", 2040 sizeof(struct xfs_refcount_intent), 2041 0, 0, NULL); 2042 2043 return xfs_refcount_intent_cache != NULL ? 0 : -ENOMEM; 2044} 2045 2046void 2047xfs_refcount_intent_destroy_cache(void) 2048{ 2049 kmem_cache_destroy(xfs_refcount_intent_cache); 2050 xfs_refcount_intent_cache = NULL; 2051} 2052