b.liu | e958203 | 2025-04-17 19:18:16 +0800 | [diff] [blame^] | 1 | // SPDX-License-Identifier: GPL-2.0 |
| 2 | /* |
| 3 | * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. |
| 4 | * All Rights Reserved. |
| 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_bit.h" |
| 13 | #include "xfs_mount.h" |
| 14 | #include "xfs_inode.h" |
| 15 | #include "xfs_trans.h" |
| 16 | #include "xfs_alloc.h" |
| 17 | #include "xfs_btree.h" |
| 18 | #include "xfs_bmap_btree.h" |
| 19 | #include "xfs_bmap.h" |
| 20 | #include "xfs_error.h" |
| 21 | #include "xfs_quota.h" |
| 22 | #include "xfs_trace.h" |
| 23 | #include "xfs_rmap.h" |
| 24 | |
| 25 | /* |
| 26 | * Convert on-disk form of btree root to in-memory form. |
| 27 | */ |
| 28 | void |
| 29 | xfs_bmdr_to_bmbt( |
| 30 | struct xfs_inode *ip, |
| 31 | xfs_bmdr_block_t *dblock, |
| 32 | int dblocklen, |
| 33 | struct xfs_btree_block *rblock, |
| 34 | int rblocklen) |
| 35 | { |
| 36 | struct xfs_mount *mp = ip->i_mount; |
| 37 | int dmxr; |
| 38 | xfs_bmbt_key_t *fkp; |
| 39 | __be64 *fpp; |
| 40 | xfs_bmbt_key_t *tkp; |
| 41 | __be64 *tpp; |
| 42 | |
| 43 | xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, |
| 44 | XFS_BTNUM_BMAP, 0, 0, ip->i_ino, |
| 45 | XFS_BTREE_LONG_PTRS); |
| 46 | rblock->bb_level = dblock->bb_level; |
| 47 | ASSERT(be16_to_cpu(rblock->bb_level) > 0); |
| 48 | rblock->bb_numrecs = dblock->bb_numrecs; |
| 49 | dmxr = xfs_bmdr_maxrecs(dblocklen, 0); |
| 50 | fkp = XFS_BMDR_KEY_ADDR(dblock, 1); |
| 51 | tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1); |
| 52 | fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr); |
| 53 | tpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen); |
| 54 | dmxr = be16_to_cpu(dblock->bb_numrecs); |
| 55 | memcpy(tkp, fkp, sizeof(*fkp) * dmxr); |
| 56 | memcpy(tpp, fpp, sizeof(*fpp) * dmxr); |
| 57 | } |
| 58 | |
| 59 | void |
| 60 | xfs_bmbt_disk_get_all( |
| 61 | struct xfs_bmbt_rec *rec, |
| 62 | struct xfs_bmbt_irec *irec) |
| 63 | { |
| 64 | uint64_t l0 = get_unaligned_be64(&rec->l0); |
| 65 | uint64_t l1 = get_unaligned_be64(&rec->l1); |
| 66 | |
| 67 | irec->br_startoff = (l0 & xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; |
| 68 | irec->br_startblock = ((l0 & xfs_mask64lo(9)) << 43) | (l1 >> 21); |
| 69 | irec->br_blockcount = l1 & xfs_mask64lo(21); |
| 70 | if (l0 >> (64 - BMBT_EXNTFLAG_BITLEN)) |
| 71 | irec->br_state = XFS_EXT_UNWRITTEN; |
| 72 | else |
| 73 | irec->br_state = XFS_EXT_NORM; |
| 74 | } |
| 75 | |
| 76 | /* |
| 77 | * Extract the blockcount field from an on disk bmap extent record. |
| 78 | */ |
| 79 | xfs_filblks_t |
| 80 | xfs_bmbt_disk_get_blockcount( |
| 81 | xfs_bmbt_rec_t *r) |
| 82 | { |
| 83 | return (xfs_filblks_t)(be64_to_cpu(r->l1) & xfs_mask64lo(21)); |
| 84 | } |
| 85 | |
| 86 | /* |
| 87 | * Extract the startoff field from a disk format bmap extent record. |
| 88 | */ |
| 89 | xfs_fileoff_t |
| 90 | xfs_bmbt_disk_get_startoff( |
| 91 | xfs_bmbt_rec_t *r) |
| 92 | { |
| 93 | return ((xfs_fileoff_t)be64_to_cpu(r->l0) & |
| 94 | xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; |
| 95 | } |
| 96 | |
| 97 | /* |
| 98 | * Set all the fields in a bmap extent record from the uncompressed form. |
| 99 | */ |
| 100 | void |
| 101 | xfs_bmbt_disk_set_all( |
| 102 | struct xfs_bmbt_rec *r, |
| 103 | struct xfs_bmbt_irec *s) |
| 104 | { |
| 105 | int extent_flag = (s->br_state != XFS_EXT_NORM); |
| 106 | |
| 107 | ASSERT(s->br_state == XFS_EXT_NORM || s->br_state == XFS_EXT_UNWRITTEN); |
| 108 | ASSERT(!(s->br_startoff & xfs_mask64hi(64-BMBT_STARTOFF_BITLEN))); |
| 109 | ASSERT(!(s->br_blockcount & xfs_mask64hi(64-BMBT_BLOCKCOUNT_BITLEN))); |
| 110 | ASSERT(!(s->br_startblock & xfs_mask64hi(64-BMBT_STARTBLOCK_BITLEN))); |
| 111 | |
| 112 | put_unaligned_be64( |
| 113 | ((xfs_bmbt_rec_base_t)extent_flag << 63) | |
| 114 | ((xfs_bmbt_rec_base_t)s->br_startoff << 9) | |
| 115 | ((xfs_bmbt_rec_base_t)s->br_startblock >> 43), &r->l0); |
| 116 | put_unaligned_be64( |
| 117 | ((xfs_bmbt_rec_base_t)s->br_startblock << 21) | |
| 118 | ((xfs_bmbt_rec_base_t)s->br_blockcount & |
| 119 | (xfs_bmbt_rec_base_t)xfs_mask64lo(21)), &r->l1); |
| 120 | } |
| 121 | |
| 122 | /* |
| 123 | * Convert in-memory form of btree root to on-disk form. |
| 124 | */ |
| 125 | void |
| 126 | xfs_bmbt_to_bmdr( |
| 127 | struct xfs_mount *mp, |
| 128 | struct xfs_btree_block *rblock, |
| 129 | int rblocklen, |
| 130 | xfs_bmdr_block_t *dblock, |
| 131 | int dblocklen) |
| 132 | { |
| 133 | int dmxr; |
| 134 | xfs_bmbt_key_t *fkp; |
| 135 | __be64 *fpp; |
| 136 | xfs_bmbt_key_t *tkp; |
| 137 | __be64 *tpp; |
| 138 | |
| 139 | if (xfs_sb_version_hascrc(&mp->m_sb)) { |
| 140 | ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_CRC_MAGIC)); |
| 141 | ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, |
| 142 | &mp->m_sb.sb_meta_uuid)); |
| 143 | ASSERT(rblock->bb_u.l.bb_blkno == |
| 144 | cpu_to_be64(XFS_BUF_DADDR_NULL)); |
| 145 | } else |
| 146 | ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_MAGIC)); |
| 147 | ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); |
| 148 | ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); |
| 149 | ASSERT(rblock->bb_level != 0); |
| 150 | dblock->bb_level = rblock->bb_level; |
| 151 | dblock->bb_numrecs = rblock->bb_numrecs; |
| 152 | dmxr = xfs_bmdr_maxrecs(dblocklen, 0); |
| 153 | fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1); |
| 154 | tkp = XFS_BMDR_KEY_ADDR(dblock, 1); |
| 155 | fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen); |
| 156 | tpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr); |
| 157 | dmxr = be16_to_cpu(dblock->bb_numrecs); |
| 158 | memcpy(tkp, fkp, sizeof(*fkp) * dmxr); |
| 159 | memcpy(tpp, fpp, sizeof(*fpp) * dmxr); |
| 160 | } |
| 161 | |
| 162 | STATIC struct xfs_btree_cur * |
| 163 | xfs_bmbt_dup_cursor( |
| 164 | struct xfs_btree_cur *cur) |
| 165 | { |
| 166 | struct xfs_btree_cur *new; |
| 167 | |
| 168 | new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp, |
| 169 | cur->bc_private.b.ip, cur->bc_private.b.whichfork); |
| 170 | |
| 171 | /* |
| 172 | * Copy the firstblock, dfops, and flags values, |
| 173 | * since init cursor doesn't get them. |
| 174 | */ |
| 175 | new->bc_private.b.flags = cur->bc_private.b.flags; |
| 176 | |
| 177 | return new; |
| 178 | } |
| 179 | |
| 180 | STATIC void |
| 181 | xfs_bmbt_update_cursor( |
| 182 | struct xfs_btree_cur *src, |
| 183 | struct xfs_btree_cur *dst) |
| 184 | { |
| 185 | ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) || |
| 186 | (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME)); |
| 187 | |
| 188 | dst->bc_private.b.allocated += src->bc_private.b.allocated; |
| 189 | dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock; |
| 190 | |
| 191 | src->bc_private.b.allocated = 0; |
| 192 | } |
| 193 | |
| 194 | STATIC int |
| 195 | xfs_bmbt_alloc_block( |
| 196 | struct xfs_btree_cur *cur, |
| 197 | union xfs_btree_ptr *start, |
| 198 | union xfs_btree_ptr *new, |
| 199 | int *stat) |
| 200 | { |
| 201 | xfs_alloc_arg_t args; /* block allocation args */ |
| 202 | int error; /* error return value */ |
| 203 | |
| 204 | memset(&args, 0, sizeof(args)); |
| 205 | args.tp = cur->bc_tp; |
| 206 | args.mp = cur->bc_mp; |
| 207 | args.fsbno = cur->bc_tp->t_firstblock; |
| 208 | xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino, |
| 209 | cur->bc_private.b.whichfork); |
| 210 | |
| 211 | if (args.fsbno == NULLFSBLOCK) { |
| 212 | args.fsbno = be64_to_cpu(start->l); |
| 213 | args.type = XFS_ALLOCTYPE_START_BNO; |
| 214 | /* |
| 215 | * Make sure there is sufficient room left in the AG to |
| 216 | * complete a full tree split for an extent insert. If |
| 217 | * we are converting the middle part of an extent then |
| 218 | * we may need space for two tree splits. |
| 219 | * |
| 220 | * We are relying on the caller to make the correct block |
| 221 | * reservation for this operation to succeed. If the |
| 222 | * reservation amount is insufficient then we may fail a |
| 223 | * block allocation here and corrupt the filesystem. |
| 224 | */ |
| 225 | args.minleft = args.tp->t_blk_res; |
| 226 | } else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) { |
| 227 | args.type = XFS_ALLOCTYPE_START_BNO; |
| 228 | } else { |
| 229 | args.type = XFS_ALLOCTYPE_NEAR_BNO; |
| 230 | } |
| 231 | |
| 232 | args.minlen = args.maxlen = args.prod = 1; |
| 233 | args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL; |
| 234 | if (!args.wasdel && args.tp->t_blk_res == 0) { |
| 235 | error = -ENOSPC; |
| 236 | goto error0; |
| 237 | } |
| 238 | error = xfs_alloc_vextent(&args); |
| 239 | if (error) |
| 240 | goto error0; |
| 241 | |
| 242 | if (args.fsbno == NULLFSBLOCK && args.minleft) { |
| 243 | /* |
| 244 | * Could not find an AG with enough free space to satisfy |
| 245 | * a full btree split. Try again and if |
| 246 | * successful activate the lowspace algorithm. |
| 247 | */ |
| 248 | args.fsbno = 0; |
| 249 | args.type = XFS_ALLOCTYPE_FIRST_AG; |
| 250 | error = xfs_alloc_vextent(&args); |
| 251 | if (error) |
| 252 | goto error0; |
| 253 | cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE; |
| 254 | } |
| 255 | if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { |
| 256 | *stat = 0; |
| 257 | return 0; |
| 258 | } |
| 259 | |
| 260 | ASSERT(args.len == 1); |
| 261 | cur->bc_tp->t_firstblock = args.fsbno; |
| 262 | cur->bc_private.b.allocated++; |
| 263 | cur->bc_private.b.ip->i_d.di_nblocks++; |
| 264 | xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE); |
| 265 | xfs_trans_mod_dquot_byino(args.tp, cur->bc_private.b.ip, |
| 266 | XFS_TRANS_DQ_BCOUNT, 1L); |
| 267 | |
| 268 | new->l = cpu_to_be64(args.fsbno); |
| 269 | |
| 270 | *stat = 1; |
| 271 | return 0; |
| 272 | |
| 273 | error0: |
| 274 | return error; |
| 275 | } |
| 276 | |
| 277 | STATIC int |
| 278 | xfs_bmbt_free_block( |
| 279 | struct xfs_btree_cur *cur, |
| 280 | struct xfs_buf *bp) |
| 281 | { |
| 282 | struct xfs_mount *mp = cur->bc_mp; |
| 283 | struct xfs_inode *ip = cur->bc_private.b.ip; |
| 284 | struct xfs_trans *tp = cur->bc_tp; |
| 285 | xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp)); |
| 286 | struct xfs_owner_info oinfo; |
| 287 | |
| 288 | xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork); |
| 289 | xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo); |
| 290 | ip->i_d.di_nblocks--; |
| 291 | |
| 292 | xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); |
| 293 | xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); |
| 294 | return 0; |
| 295 | } |
| 296 | |
| 297 | STATIC int |
| 298 | xfs_bmbt_get_minrecs( |
| 299 | struct xfs_btree_cur *cur, |
| 300 | int level) |
| 301 | { |
| 302 | if (level == cur->bc_nlevels - 1) { |
| 303 | struct xfs_ifork *ifp; |
| 304 | |
| 305 | ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, |
| 306 | cur->bc_private.b.whichfork); |
| 307 | |
| 308 | return xfs_bmbt_maxrecs(cur->bc_mp, |
| 309 | ifp->if_broot_bytes, level == 0) / 2; |
| 310 | } |
| 311 | |
| 312 | return cur->bc_mp->m_bmap_dmnr[level != 0]; |
| 313 | } |
| 314 | |
| 315 | int |
| 316 | xfs_bmbt_get_maxrecs( |
| 317 | struct xfs_btree_cur *cur, |
| 318 | int level) |
| 319 | { |
| 320 | if (level == cur->bc_nlevels - 1) { |
| 321 | struct xfs_ifork *ifp; |
| 322 | |
| 323 | ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, |
| 324 | cur->bc_private.b.whichfork); |
| 325 | |
| 326 | return xfs_bmbt_maxrecs(cur->bc_mp, |
| 327 | ifp->if_broot_bytes, level == 0); |
| 328 | } |
| 329 | |
| 330 | return cur->bc_mp->m_bmap_dmxr[level != 0]; |
| 331 | |
| 332 | } |
| 333 | |
| 334 | /* |
| 335 | * Get the maximum records we could store in the on-disk format. |
| 336 | * |
| 337 | * For non-root nodes this is equivalent to xfs_bmbt_get_maxrecs, but |
| 338 | * for the root node this checks the available space in the dinode fork |
| 339 | * so that we can resize the in-memory buffer to match it. After a |
| 340 | * resize to the maximum size this function returns the same value |
| 341 | * as xfs_bmbt_get_maxrecs for the root node, too. |
| 342 | */ |
| 343 | STATIC int |
| 344 | xfs_bmbt_get_dmaxrecs( |
| 345 | struct xfs_btree_cur *cur, |
| 346 | int level) |
| 347 | { |
| 348 | if (level != cur->bc_nlevels - 1) |
| 349 | return cur->bc_mp->m_bmap_dmxr[level != 0]; |
| 350 | return xfs_bmdr_maxrecs(cur->bc_private.b.forksize, level == 0); |
| 351 | } |
| 352 | |
| 353 | STATIC void |
| 354 | xfs_bmbt_init_key_from_rec( |
| 355 | union xfs_btree_key *key, |
| 356 | union xfs_btree_rec *rec) |
| 357 | { |
| 358 | key->bmbt.br_startoff = |
| 359 | cpu_to_be64(xfs_bmbt_disk_get_startoff(&rec->bmbt)); |
| 360 | } |
| 361 | |
| 362 | STATIC void |
| 363 | xfs_bmbt_init_high_key_from_rec( |
| 364 | union xfs_btree_key *key, |
| 365 | union xfs_btree_rec *rec) |
| 366 | { |
| 367 | key->bmbt.br_startoff = cpu_to_be64( |
| 368 | xfs_bmbt_disk_get_startoff(&rec->bmbt) + |
| 369 | xfs_bmbt_disk_get_blockcount(&rec->bmbt) - 1); |
| 370 | } |
| 371 | |
| 372 | STATIC void |
| 373 | xfs_bmbt_init_rec_from_cur( |
| 374 | struct xfs_btree_cur *cur, |
| 375 | union xfs_btree_rec *rec) |
| 376 | { |
| 377 | xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b); |
| 378 | } |
| 379 | |
| 380 | STATIC void |
| 381 | xfs_bmbt_init_ptr_from_cur( |
| 382 | struct xfs_btree_cur *cur, |
| 383 | union xfs_btree_ptr *ptr) |
| 384 | { |
| 385 | ptr->l = 0; |
| 386 | } |
| 387 | |
| 388 | STATIC int64_t |
| 389 | xfs_bmbt_key_diff( |
| 390 | struct xfs_btree_cur *cur, |
| 391 | union xfs_btree_key *key) |
| 392 | { |
| 393 | return (int64_t)be64_to_cpu(key->bmbt.br_startoff) - |
| 394 | cur->bc_rec.b.br_startoff; |
| 395 | } |
| 396 | |
| 397 | STATIC int64_t |
| 398 | xfs_bmbt_diff_two_keys( |
| 399 | struct xfs_btree_cur *cur, |
| 400 | union xfs_btree_key *k1, |
| 401 | union xfs_btree_key *k2) |
| 402 | { |
| 403 | uint64_t a = be64_to_cpu(k1->bmbt.br_startoff); |
| 404 | uint64_t b = be64_to_cpu(k2->bmbt.br_startoff); |
| 405 | |
| 406 | /* |
| 407 | * Note: This routine previously casted a and b to int64 and subtracted |
| 408 | * them to generate a result. This lead to problems if b was the |
| 409 | * "maximum" key value (all ones) being signed incorrectly, hence this |
| 410 | * somewhat less efficient version. |
| 411 | */ |
| 412 | if (a > b) |
| 413 | return 1; |
| 414 | if (b > a) |
| 415 | return -1; |
| 416 | return 0; |
| 417 | } |
| 418 | |
| 419 | static xfs_failaddr_t |
| 420 | xfs_bmbt_verify( |
| 421 | struct xfs_buf *bp) |
| 422 | { |
| 423 | struct xfs_mount *mp = bp->b_mount; |
| 424 | struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); |
| 425 | xfs_failaddr_t fa; |
| 426 | unsigned int level; |
| 427 | |
| 428 | if (!xfs_verify_magic(bp, block->bb_magic)) |
| 429 | return __this_address; |
| 430 | |
| 431 | if (xfs_sb_version_hascrc(&mp->m_sb)) { |
| 432 | /* |
| 433 | * XXX: need a better way of verifying the owner here. Right now |
| 434 | * just make sure there has been one set. |
| 435 | */ |
| 436 | fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); |
| 437 | if (fa) |
| 438 | return fa; |
| 439 | } |
| 440 | |
| 441 | /* |
| 442 | * numrecs and level verification. |
| 443 | * |
| 444 | * We don't know what fork we belong to, so just verify that the level |
| 445 | * is less than the maximum of the two. Later checks will be more |
| 446 | * precise. |
| 447 | */ |
| 448 | level = be16_to_cpu(block->bb_level); |
| 449 | if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1])) |
| 450 | return __this_address; |
| 451 | |
| 452 | return xfs_btree_lblock_verify(bp, mp->m_bmap_dmxr[level != 0]); |
| 453 | } |
| 454 | |
| 455 | static void |
| 456 | xfs_bmbt_read_verify( |
| 457 | struct xfs_buf *bp) |
| 458 | { |
| 459 | xfs_failaddr_t fa; |
| 460 | |
| 461 | if (!xfs_btree_lblock_verify_crc(bp)) |
| 462 | xfs_verifier_error(bp, -EFSBADCRC, __this_address); |
| 463 | else { |
| 464 | fa = xfs_bmbt_verify(bp); |
| 465 | if (fa) |
| 466 | xfs_verifier_error(bp, -EFSCORRUPTED, fa); |
| 467 | } |
| 468 | |
| 469 | if (bp->b_error) |
| 470 | trace_xfs_btree_corrupt(bp, _RET_IP_); |
| 471 | } |
| 472 | |
| 473 | static void |
| 474 | xfs_bmbt_write_verify( |
| 475 | struct xfs_buf *bp) |
| 476 | { |
| 477 | xfs_failaddr_t fa; |
| 478 | |
| 479 | fa = xfs_bmbt_verify(bp); |
| 480 | if (fa) { |
| 481 | trace_xfs_btree_corrupt(bp, _RET_IP_); |
| 482 | xfs_verifier_error(bp, -EFSCORRUPTED, fa); |
| 483 | return; |
| 484 | } |
| 485 | xfs_btree_lblock_calc_crc(bp); |
| 486 | } |
| 487 | |
| 488 | const struct xfs_buf_ops xfs_bmbt_buf_ops = { |
| 489 | .name = "xfs_bmbt", |
| 490 | .magic = { cpu_to_be32(XFS_BMAP_MAGIC), |
| 491 | cpu_to_be32(XFS_BMAP_CRC_MAGIC) }, |
| 492 | .verify_read = xfs_bmbt_read_verify, |
| 493 | .verify_write = xfs_bmbt_write_verify, |
| 494 | .verify_struct = xfs_bmbt_verify, |
| 495 | }; |
| 496 | |
| 497 | |
| 498 | STATIC int |
| 499 | xfs_bmbt_keys_inorder( |
| 500 | struct xfs_btree_cur *cur, |
| 501 | union xfs_btree_key *k1, |
| 502 | union xfs_btree_key *k2) |
| 503 | { |
| 504 | return be64_to_cpu(k1->bmbt.br_startoff) < |
| 505 | be64_to_cpu(k2->bmbt.br_startoff); |
| 506 | } |
| 507 | |
| 508 | STATIC int |
| 509 | xfs_bmbt_recs_inorder( |
| 510 | struct xfs_btree_cur *cur, |
| 511 | union xfs_btree_rec *r1, |
| 512 | union xfs_btree_rec *r2) |
| 513 | { |
| 514 | return xfs_bmbt_disk_get_startoff(&r1->bmbt) + |
| 515 | xfs_bmbt_disk_get_blockcount(&r1->bmbt) <= |
| 516 | xfs_bmbt_disk_get_startoff(&r2->bmbt); |
| 517 | } |
| 518 | |
| 519 | static const struct xfs_btree_ops xfs_bmbt_ops = { |
| 520 | .rec_len = sizeof(xfs_bmbt_rec_t), |
| 521 | .key_len = sizeof(xfs_bmbt_key_t), |
| 522 | |
| 523 | .dup_cursor = xfs_bmbt_dup_cursor, |
| 524 | .update_cursor = xfs_bmbt_update_cursor, |
| 525 | .alloc_block = xfs_bmbt_alloc_block, |
| 526 | .free_block = xfs_bmbt_free_block, |
| 527 | .get_maxrecs = xfs_bmbt_get_maxrecs, |
| 528 | .get_minrecs = xfs_bmbt_get_minrecs, |
| 529 | .get_dmaxrecs = xfs_bmbt_get_dmaxrecs, |
| 530 | .init_key_from_rec = xfs_bmbt_init_key_from_rec, |
| 531 | .init_high_key_from_rec = xfs_bmbt_init_high_key_from_rec, |
| 532 | .init_rec_from_cur = xfs_bmbt_init_rec_from_cur, |
| 533 | .init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur, |
| 534 | .key_diff = xfs_bmbt_key_diff, |
| 535 | .diff_two_keys = xfs_bmbt_diff_two_keys, |
| 536 | .buf_ops = &xfs_bmbt_buf_ops, |
| 537 | .keys_inorder = xfs_bmbt_keys_inorder, |
| 538 | .recs_inorder = xfs_bmbt_recs_inorder, |
| 539 | }; |
| 540 | |
| 541 | /* |
| 542 | * Allocate a new bmap btree cursor. |
| 543 | */ |
| 544 | struct xfs_btree_cur * /* new bmap btree cursor */ |
| 545 | xfs_bmbt_init_cursor( |
| 546 | struct xfs_mount *mp, /* file system mount point */ |
| 547 | struct xfs_trans *tp, /* transaction pointer */ |
| 548 | struct xfs_inode *ip, /* inode owning the btree */ |
| 549 | int whichfork) /* data or attr fork */ |
| 550 | { |
| 551 | struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); |
| 552 | struct xfs_btree_cur *cur; |
| 553 | ASSERT(whichfork != XFS_COW_FORK); |
| 554 | |
| 555 | cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS); |
| 556 | |
| 557 | cur->bc_tp = tp; |
| 558 | cur->bc_mp = mp; |
| 559 | cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1; |
| 560 | cur->bc_btnum = XFS_BTNUM_BMAP; |
| 561 | cur->bc_blocklog = mp->m_sb.sb_blocklog; |
| 562 | cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2); |
| 563 | |
| 564 | cur->bc_ops = &xfs_bmbt_ops; |
| 565 | cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE; |
| 566 | if (xfs_sb_version_hascrc(&mp->m_sb)) |
| 567 | cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; |
| 568 | |
| 569 | cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork); |
| 570 | cur->bc_private.b.ip = ip; |
| 571 | cur->bc_private.b.allocated = 0; |
| 572 | cur->bc_private.b.flags = 0; |
| 573 | cur->bc_private.b.whichfork = whichfork; |
| 574 | |
| 575 | return cur; |
| 576 | } |
| 577 | |
| 578 | /* |
| 579 | * Calculate number of records in a bmap btree block. |
| 580 | */ |
| 581 | int |
| 582 | xfs_bmbt_maxrecs( |
| 583 | struct xfs_mount *mp, |
| 584 | int blocklen, |
| 585 | int leaf) |
| 586 | { |
| 587 | blocklen -= XFS_BMBT_BLOCK_LEN(mp); |
| 588 | |
| 589 | if (leaf) |
| 590 | return blocklen / sizeof(xfs_bmbt_rec_t); |
| 591 | return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t)); |
| 592 | } |
| 593 | |
| 594 | /* |
| 595 | * Calculate number of records in a bmap btree inode root. |
| 596 | */ |
| 597 | int |
| 598 | xfs_bmdr_maxrecs( |
| 599 | int blocklen, |
| 600 | int leaf) |
| 601 | { |
| 602 | blocklen -= sizeof(xfs_bmdr_block_t); |
| 603 | |
| 604 | if (leaf) |
| 605 | return blocklen / sizeof(xfs_bmdr_rec_t); |
| 606 | return blocklen / (sizeof(xfs_bmdr_key_t) + sizeof(xfs_bmdr_ptr_t)); |
| 607 | } |
| 608 | |
| 609 | /* |
| 610 | * Change the owner of a btree format fork fo the inode passed in. Change it to |
| 611 | * the owner of that is passed in so that we can change owners before or after |
| 612 | * we switch forks between inodes. The operation that the caller is doing will |
| 613 | * determine whether is needs to change owner before or after the switch. |
| 614 | * |
| 615 | * For demand paged transactional modification, the fork switch should be done |
| 616 | * after reading in all the blocks, modifying them and pinning them in the |
| 617 | * transaction. For modification when the buffers are already pinned in memory, |
| 618 | * the fork switch can be done before changing the owner as we won't need to |
| 619 | * validate the owner until the btree buffers are unpinned and writes can occur |
| 620 | * again. |
| 621 | * |
| 622 | * For recovery based ownership change, there is no transactional context and |
| 623 | * so a buffer list must be supplied so that we can record the buffers that we |
| 624 | * modified for the caller to issue IO on. |
| 625 | */ |
| 626 | int |
| 627 | xfs_bmbt_change_owner( |
| 628 | struct xfs_trans *tp, |
| 629 | struct xfs_inode *ip, |
| 630 | int whichfork, |
| 631 | xfs_ino_t new_owner, |
| 632 | struct list_head *buffer_list) |
| 633 | { |
| 634 | struct xfs_btree_cur *cur; |
| 635 | int error; |
| 636 | |
| 637 | ASSERT(tp || buffer_list); |
| 638 | ASSERT(!(tp && buffer_list)); |
| 639 | if (whichfork == XFS_DATA_FORK) |
| 640 | ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_BTREE); |
| 641 | else |
| 642 | ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE); |
| 643 | |
| 644 | cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork); |
| 645 | if (!cur) |
| 646 | return -ENOMEM; |
| 647 | cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER; |
| 648 | |
| 649 | error = xfs_btree_change_owner(cur, new_owner, buffer_list); |
| 650 | xfs_btree_del_cursor(cur, error); |
| 651 | return error; |
| 652 | } |
| 653 | |
| 654 | /* Calculate the bmap btree size for some records. */ |
| 655 | unsigned long long |
| 656 | xfs_bmbt_calc_size( |
| 657 | struct xfs_mount *mp, |
| 658 | unsigned long long len) |
| 659 | { |
| 660 | return xfs_btree_calc_size(mp->m_bmap_dmnr, len); |
| 661 | } |