1// SPDX-License-Identifier: GPL-2.0-or-later 2/* -*- mode: c; c-basic-offset: 8; -*- 3 * vim: noexpandtab sw=8 ts=8 sts=0: 4 * 5 * suballoc.c 6 * 7 * metadata alloc and free 8 * Inspired by ext3 block groups. 9 * 10 * Copyright (C) 2002, 2004 Oracle. All rights reserved. 11 */ 12 13#include <linux/fs.h> 14#include <linux/types.h> 15#include <linux/slab.h> 16#include <linux/highmem.h> 17 18#include <cluster/masklog.h> 19 20#include "ocfs2.h" 21 22#include "alloc.h" 23#include "blockcheck.h" 24#include "dlmglue.h" 25#include "inode.h" 26#include "journal.h" 27#include "localalloc.h" 28#include "suballoc.h" 29#include "super.h" 30#include "sysfile.h" 31#include "uptodate.h" 32#include "ocfs2_trace.h" 33 34#include "buffer_head_io.h" 35 36#define NOT_ALLOC_NEW_GROUP 0 37#define ALLOC_NEW_GROUP 0x1 38#define ALLOC_GROUPS_FROM_GLOBAL 0x2 39 40#define OCFS2_MAX_TO_STEAL 1024 41 42struct ocfs2_suballoc_result { 43 u64 sr_bg_blkno; /* The bg we allocated from. Set 44 to 0 when a block group is 45 contiguous. */ 46 u64 sr_bg_stable_blkno; /* 47 * Doesn't change, always 48 * set to target block 49 * group descriptor 50 * block. 51 */ 52 u64 sr_blkno; /* The first allocated block */ 53 unsigned int sr_bit_offset; /* The bit in the bg */ 54 unsigned int sr_bits; /* How many bits we claimed */ 55}; 56 57static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res) 58{ 59 if (res->sr_blkno == 0) 60 return 0; 61 62 if (res->sr_bg_blkno) 63 return res->sr_bg_blkno; 64 65 return ocfs2_which_suballoc_group(res->sr_blkno, res->sr_bit_offset); 66} 67 68static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl); 69static int ocfs2_block_group_fill(handle_t *handle, 70 struct inode *alloc_inode, 71 struct buffer_head *bg_bh, 72 u64 group_blkno, 73 unsigned int group_clusters, 74 u16 my_chain, 75 struct ocfs2_chain_list *cl); 76static int ocfs2_block_group_alloc(struct ocfs2_super *osb, 77 struct inode *alloc_inode, 78 struct buffer_head *bh, 79 u64 max_block, 80 u64 *last_alloc_group, 81 int flags); 82 83static int ocfs2_cluster_group_search(struct inode *inode, 84 struct buffer_head *group_bh, 85 u32 bits_wanted, u32 min_bits, 86 u64 max_block, 87 struct ocfs2_suballoc_result *res); 88static int ocfs2_block_group_search(struct inode *inode, 89 struct buffer_head *group_bh, 90 u32 bits_wanted, u32 min_bits, 91 u64 max_block, 92 struct ocfs2_suballoc_result *res); 93static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, 94 handle_t *handle, 95 u32 bits_wanted, 96 u32 min_bits, 97 struct ocfs2_suballoc_result *res); 98static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, 99 int nr); 100static int ocfs2_relink_block_group(handle_t *handle, 101 struct inode *alloc_inode, 102 struct buffer_head *fe_bh, 103 struct buffer_head *bg_bh, 104 struct buffer_head *prev_bg_bh, 105 u16 chain); 106static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg, 107 u32 wanted); 108static inline u32 ocfs2_desc_bitmap_to_cluster_off(struct inode *inode, 109 u64 bg_blkno, 110 u16 bg_bit_off); 111static inline void ocfs2_block_to_cluster_group(struct inode *inode, 112 u64 data_blkno, 113 u64 *bg_blkno, 114 u16 *bg_bit_off); 115static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb, 116 u32 bits_wanted, u64 max_block, 117 int flags, 118 struct ocfs2_alloc_context **ac); 119 120void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac) 121{ 122 struct inode *inode = ac->ac_inode; 123 124 if (inode) { 125 if (ac->ac_which != OCFS2_AC_USE_LOCAL) 126 ocfs2_inode_unlock(inode, 1); 127 128 inode_unlock(inode); 129 130 iput(inode); 131 ac->ac_inode = NULL; 132 } 133 brelse(ac->ac_bh); 134 ac->ac_bh = NULL; 135 ac->ac_resv = NULL; 136 kfree(ac->ac_find_loc_priv); 137 ac->ac_find_loc_priv = NULL; 138} 139 140void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac) 141{ 142 ocfs2_free_ac_resource(ac); 143 kfree(ac); 144} 145 146static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl) 147{ 148 return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc); 149} 150 151#define do_error(fmt, ...) \ 152do { \ 153 if (resize) \ 154 mlog(ML_ERROR, fmt, ##__VA_ARGS__); \ 155 else \ 156 return ocfs2_error(sb, fmt, ##__VA_ARGS__); \ 157} while (0) 158 159static int ocfs2_validate_gd_self(struct super_block *sb, 160 struct buffer_head *bh, 161 int resize) 162{ 163 struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; 164 165 if (!OCFS2_IS_VALID_GROUP_DESC(gd)) { 166 do_error("Group descriptor #%llu has bad signature %.*s\n", 167 (unsigned long long)bh->b_blocknr, 7, 168 gd->bg_signature); 169 } 170 171 if (le64_to_cpu(gd->bg_blkno) != bh->b_blocknr) { 172 do_error("Group descriptor #%llu has an invalid bg_blkno of %llu\n", 173 (unsigned long long)bh->b_blocknr, 174 (unsigned long long)le64_to_cpu(gd->bg_blkno)); 175 } 176 177 if (le32_to_cpu(gd->bg_generation) != OCFS2_SB(sb)->fs_generation) { 178 do_error("Group descriptor #%llu has an invalid fs_generation of #%u\n", 179 (unsigned long long)bh->b_blocknr, 180 le32_to_cpu(gd->bg_generation)); 181 } 182 183 if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) { 184 do_error("Group descriptor #%llu has bit count %u but claims that %u are free\n", 185 (unsigned long long)bh->b_blocknr, 186 le16_to_cpu(gd->bg_bits), 187 le16_to_cpu(gd->bg_free_bits_count)); 188 } 189 190 if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) { 191 do_error("Group descriptor #%llu has bit count %u but max bitmap bits of %u\n", 192 (unsigned long long)bh->b_blocknr, 193 le16_to_cpu(gd->bg_bits), 194 8 * le16_to_cpu(gd->bg_size)); 195 } 196 197 return 0; 198} 199 200static int ocfs2_validate_gd_parent(struct super_block *sb, 201 struct ocfs2_dinode *di, 202 struct buffer_head *bh, 203 int resize) 204{ 205 unsigned int max_bits; 206 struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; 207 208 if (di->i_blkno != gd->bg_parent_dinode) { 209 do_error("Group descriptor #%llu has bad parent pointer (%llu, expected %llu)\n", 210 (unsigned long long)bh->b_blocknr, 211 (unsigned long long)le64_to_cpu(gd->bg_parent_dinode), 212 (unsigned long long)le64_to_cpu(di->i_blkno)); 213 } 214 215 max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc); 216 if (le16_to_cpu(gd->bg_bits) > max_bits) { 217 do_error("Group descriptor #%llu has bit count of %u\n", 218 (unsigned long long)bh->b_blocknr, 219 le16_to_cpu(gd->bg_bits)); 220 } 221 222 /* In resize, we may meet the case bg_chain == cl_next_free_rec. */ 223 if ((le16_to_cpu(gd->bg_chain) > 224 le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) || 225 ((le16_to_cpu(gd->bg_chain) == 226 le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) && !resize)) { 227 do_error("Group descriptor #%llu has bad chain %u\n", 228 (unsigned long long)bh->b_blocknr, 229 le16_to_cpu(gd->bg_chain)); 230 } 231 232 return 0; 233} 234 235#undef do_error 236 237/* 238 * This version only prints errors. It does not fail the filesystem, and 239 * exists only for resize. 240 */ 241int ocfs2_check_group_descriptor(struct super_block *sb, 242 struct ocfs2_dinode *di, 243 struct buffer_head *bh) 244{ 245 int rc; 246 struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; 247 248 BUG_ON(!buffer_uptodate(bh)); 249 250 /* 251 * If the ecc fails, we return the error but otherwise 252 * leave the filesystem running. We know any error is 253 * local to this block. 254 */ 255 rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &gd->bg_check); 256 if (rc) { 257 mlog(ML_ERROR, 258 "Checksum failed for group descriptor %llu\n", 259 (unsigned long long)bh->b_blocknr); 260 } else 261 rc = ocfs2_validate_gd_self(sb, bh, 1); 262 if (!rc) 263 rc = ocfs2_validate_gd_parent(sb, di, bh, 1); 264 265 return rc; 266} 267 268static int ocfs2_validate_group_descriptor(struct super_block *sb, 269 struct buffer_head *bh) 270{ 271 int rc; 272 struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; 273 274 trace_ocfs2_validate_group_descriptor( 275 (unsigned long long)bh->b_blocknr); 276 277 BUG_ON(!buffer_uptodate(bh)); 278 279 /* 280 * If the ecc fails, we return the error but otherwise 281 * leave the filesystem running. We know any error is 282 * local to this block. 283 */ 284 rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &gd->bg_check); 285 if (rc) 286 return rc; 287 288 /* 289 * Errors after here are fatal. 290 */ 291 292 return ocfs2_validate_gd_self(sb, bh, 0); 293} 294 295int ocfs2_read_group_descriptor(struct inode *inode, struct ocfs2_dinode *di, 296 u64 gd_blkno, struct buffer_head **bh) 297{ 298 int rc; 299 struct buffer_head *tmp = *bh; 300 301 rc = ocfs2_read_block(INODE_CACHE(inode), gd_blkno, &tmp, 302 ocfs2_validate_group_descriptor); 303 if (rc) 304 goto out; 305 306 rc = ocfs2_validate_gd_parent(inode->i_sb, di, tmp, 0); 307 if (rc) { 308 brelse(tmp); 309 goto out; 310 } 311 312 /* If ocfs2_read_block() got us a new bh, pass it up. */ 313 if (!*bh) 314 *bh = tmp; 315 316out: 317 return rc; 318} 319 320static void ocfs2_bg_discontig_add_extent(struct ocfs2_super *osb, 321 struct ocfs2_group_desc *bg, 322 struct ocfs2_chain_list *cl, 323 u64 p_blkno, unsigned int clusters) 324{ 325 struct ocfs2_extent_list *el = &bg->bg_list; 326 struct ocfs2_extent_rec *rec; 327 328 BUG_ON(!ocfs2_supports_discontig_bg(osb)); 329 if (!el->l_next_free_rec) 330 el->l_count = cpu_to_le16(ocfs2_extent_recs_per_gd(osb->sb)); 331 rec = &el->l_recs[le16_to_cpu(el->l_next_free_rec)]; 332 rec->e_blkno = cpu_to_le64(p_blkno); 333 rec->e_cpos = cpu_to_le32(le16_to_cpu(bg->bg_bits) / 334 le16_to_cpu(cl->cl_bpc)); 335 rec->e_leaf_clusters = cpu_to_le16(clusters); 336 le16_add_cpu(&bg->bg_bits, clusters * le16_to_cpu(cl->cl_bpc)); 337 le16_add_cpu(&bg->bg_free_bits_count, 338 clusters * le16_to_cpu(cl->cl_bpc)); 339 le16_add_cpu(&el->l_next_free_rec, 1); 340} 341 342static int ocfs2_block_group_fill(handle_t *handle, 343 struct inode *alloc_inode, 344 struct buffer_head *bg_bh, 345 u64 group_blkno, 346 unsigned int group_clusters, 347 u16 my_chain, 348 struct ocfs2_chain_list *cl) 349{ 350 int status = 0; 351 struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb); 352 struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; 353 struct super_block * sb = alloc_inode->i_sb; 354 355 if (((unsigned long long) bg_bh->b_blocknr) != group_blkno) { 356 status = ocfs2_error(alloc_inode->i_sb, 357 "group block (%llu) != b_blocknr (%llu)\n", 358 (unsigned long long)group_blkno, 359 (unsigned long long) bg_bh->b_blocknr); 360 goto bail; 361 } 362 363 status = ocfs2_journal_access_gd(handle, 364 INODE_CACHE(alloc_inode), 365 bg_bh, 366 OCFS2_JOURNAL_ACCESS_CREATE); 367 if (status < 0) { 368 mlog_errno(status); 369 goto bail; 370 } 371 372 memset(bg, 0, sb->s_blocksize); 373 strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE); 374 bg->bg_generation = cpu_to_le32(osb->fs_generation); 375 bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1, 376 osb->s_feature_incompat)); 377 bg->bg_chain = cpu_to_le16(my_chain); 378 bg->bg_next_group = cl->cl_recs[my_chain].c_blkno; 379 bg->bg_parent_dinode = cpu_to_le64(OCFS2_I(alloc_inode)->ip_blkno); 380 bg->bg_blkno = cpu_to_le64(group_blkno); 381 if (group_clusters == le16_to_cpu(cl->cl_cpg)) 382 bg->bg_bits = cpu_to_le16(ocfs2_bits_per_group(cl)); 383 else 384 ocfs2_bg_discontig_add_extent(osb, bg, cl, group_blkno, 385 group_clusters); 386 387 /* set the 1st bit in the bitmap to account for the descriptor block */ 388 ocfs2_set_bit(0, (unsigned long *)bg->bg_bitmap); 389 bg->bg_free_bits_count = cpu_to_le16(le16_to_cpu(bg->bg_bits) - 1); 390 391 ocfs2_journal_dirty(handle, bg_bh); 392 393 /* There is no need to zero out or otherwise initialize the 394 * other blocks in a group - All valid FS metadata in a block 395 * group stores the superblock fs_generation value at 396 * allocation time. */ 397 398bail: 399 if (status) 400 mlog_errno(status); 401 return status; 402} 403 404static inline u16 ocfs2_find_smallest_chain(struct ocfs2_chain_list *cl) 405{ 406 u16 curr, best; 407 408 best = curr = 0; 409 while (curr < le16_to_cpu(cl->cl_count)) { 410 if (le32_to_cpu(cl->cl_recs[best].c_total) > 411 le32_to_cpu(cl->cl_recs[curr].c_total)) 412 best = curr; 413 curr++; 414 } 415 return best; 416} 417 418static struct buffer_head * 419ocfs2_block_group_alloc_contig(struct ocfs2_super *osb, handle_t *handle, 420 struct inode *alloc_inode, 421 struct ocfs2_alloc_context *ac, 422 struct ocfs2_chain_list *cl) 423{ 424 int status; 425 u32 bit_off, num_bits; 426 u64 bg_blkno; 427 struct buffer_head *bg_bh; 428 unsigned int alloc_rec = ocfs2_find_smallest_chain(cl); 429 430 status = ocfs2_claim_clusters(handle, ac, 431 le16_to_cpu(cl->cl_cpg), &bit_off, 432 &num_bits); 433 if (status < 0) { 434 if (status != -ENOSPC) 435 mlog_errno(status); 436 goto bail; 437 } 438 439 /* setup the group */ 440 bg_blkno = ocfs2_clusters_to_blocks(osb->sb, bit_off); 441 trace_ocfs2_block_group_alloc_contig( 442 (unsigned long long)bg_blkno, alloc_rec); 443 444 bg_bh = sb_getblk(osb->sb, bg_blkno); 445 if (!bg_bh) { 446 status = -ENOMEM; 447 mlog_errno(status); 448 goto bail; 449 } 450 ocfs2_set_new_buffer_uptodate(INODE_CACHE(alloc_inode), bg_bh); 451 452 status = ocfs2_block_group_fill(handle, alloc_inode, bg_bh, 453 bg_blkno, num_bits, alloc_rec, cl); 454 if (status < 0) { 455 brelse(bg_bh); 456 mlog_errno(status); 457 } 458 459bail: 460 return status ? ERR_PTR(status) : bg_bh; 461} 462 463static int ocfs2_block_group_claim_bits(struct ocfs2_super *osb, 464 handle_t *handle, 465 struct ocfs2_alloc_context *ac, 466 unsigned int min_bits, 467 u32 *bit_off, u32 *num_bits) 468{ 469 int status = 0; 470 471 while (min_bits) { 472 status = ocfs2_claim_clusters(handle, ac, min_bits, 473 bit_off, num_bits); 474 if (status != -ENOSPC) 475 break; 476 477 min_bits >>= 1; 478 } 479 480 return status; 481} 482 483static int ocfs2_block_group_grow_discontig(handle_t *handle, 484 struct inode *alloc_inode, 485 struct buffer_head *bg_bh, 486 struct ocfs2_alloc_context *ac, 487 struct ocfs2_chain_list *cl, 488 unsigned int min_bits) 489{ 490 int status; 491 struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb); 492 struct ocfs2_group_desc *bg = 493 (struct ocfs2_group_desc *)bg_bh->b_data; 494 unsigned int needed = le16_to_cpu(cl->cl_cpg) - 495 le16_to_cpu(bg->bg_bits) / le16_to_cpu(cl->cl_bpc); 496 u32 p_cpos, clusters; 497 u64 p_blkno; 498 struct ocfs2_extent_list *el = &bg->bg_list; 499 500 status = ocfs2_journal_access_gd(handle, 501 INODE_CACHE(alloc_inode), 502 bg_bh, 503 OCFS2_JOURNAL_ACCESS_CREATE); 504 if (status < 0) { 505 mlog_errno(status); 506 goto bail; 507 } 508 509 while ((needed > 0) && (le16_to_cpu(el->l_next_free_rec) < 510 le16_to_cpu(el->l_count))) { 511 if (min_bits > needed) 512 min_bits = needed; 513 status = ocfs2_block_group_claim_bits(osb, handle, ac, 514 min_bits, &p_cpos, 515 &clusters); 516 if (status < 0) { 517 if (status != -ENOSPC) 518 mlog_errno(status); 519 goto bail; 520 } 521 p_blkno = ocfs2_clusters_to_blocks(osb->sb, p_cpos); 522 ocfs2_bg_discontig_add_extent(osb, bg, cl, p_blkno, 523 clusters); 524 525 min_bits = clusters; 526 needed = le16_to_cpu(cl->cl_cpg) - 527 le16_to_cpu(bg->bg_bits) / le16_to_cpu(cl->cl_bpc); 528 } 529 530 if (needed > 0) { 531 /* 532 * We have used up all the extent rec but can't fill up 533 * the cpg. So bail out. 534 */ 535 status = -ENOSPC; 536 goto bail; 537 } 538 539 ocfs2_journal_dirty(handle, bg_bh); 540 541bail: 542 return status; 543} 544 545static void ocfs2_bg_alloc_cleanup(handle_t *handle, 546 struct ocfs2_alloc_context *cluster_ac, 547 struct inode *alloc_inode, 548 struct buffer_head *bg_bh) 549{ 550 int i, ret; 551 struct ocfs2_group_desc *bg; 552 struct ocfs2_extent_list *el; 553 struct ocfs2_extent_rec *rec; 554 555 if (!bg_bh) 556 return; 557 558 bg = (struct ocfs2_group_desc *)bg_bh->b_data; 559 el = &bg->bg_list; 560 for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) { 561 rec = &el->l_recs[i]; 562 ret = ocfs2_free_clusters(handle, cluster_ac->ac_inode, 563 cluster_ac->ac_bh, 564 le64_to_cpu(rec->e_blkno), 565 le16_to_cpu(rec->e_leaf_clusters)); 566 if (ret) 567 mlog_errno(ret); 568 /* Try all the clusters to free */ 569 } 570 571 ocfs2_remove_from_cache(INODE_CACHE(alloc_inode), bg_bh); 572 brelse(bg_bh); 573} 574 575static struct buffer_head * 576ocfs2_block_group_alloc_discontig(handle_t *handle, 577 struct inode *alloc_inode, 578 struct ocfs2_alloc_context *ac, 579 struct ocfs2_chain_list *cl) 580{ 581 int status; 582 u32 bit_off, num_bits; 583 u64 bg_blkno; 584 unsigned int min_bits = le16_to_cpu(cl->cl_cpg) >> 1; 585 struct buffer_head *bg_bh = NULL; 586 unsigned int alloc_rec = ocfs2_find_smallest_chain(cl); 587 struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb); 588 589 if (!ocfs2_supports_discontig_bg(osb)) { 590 status = -ENOSPC; 591 goto bail; 592 } 593 594 status = ocfs2_extend_trans(handle, 595 ocfs2_calc_bg_discontig_credits(osb->sb)); 596 if (status) { 597 mlog_errno(status); 598 goto bail; 599 } 600 601 /* 602 * We're going to be grabbing from multiple cluster groups. 603 * We don't have enough credits to relink them all, and the 604 * cluster groups will be staying in cache for the duration of 605 * this operation. 606 */ 607 ac->ac_disable_chain_relink = 1; 608 609 /* Claim the first region */ 610 status = ocfs2_block_group_claim_bits(osb, handle, ac, min_bits, 611 &bit_off, &num_bits); 612 if (status < 0) { 613 if (status != -ENOSPC) 614 mlog_errno(status); 615 goto bail; 616 } 617 min_bits = num_bits; 618 619 /* setup the group */ 620 bg_blkno = ocfs2_clusters_to_blocks(osb->sb, bit_off); 621 trace_ocfs2_block_group_alloc_discontig( 622 (unsigned long long)bg_blkno, alloc_rec); 623 624 bg_bh = sb_getblk(osb->sb, bg_blkno); 625 if (!bg_bh) { 626 status = -ENOMEM; 627 mlog_errno(status); 628 goto bail; 629 } 630 ocfs2_set_new_buffer_uptodate(INODE_CACHE(alloc_inode), bg_bh); 631 632 status = ocfs2_block_group_fill(handle, alloc_inode, bg_bh, 633 bg_blkno, num_bits, alloc_rec, cl); 634 if (status < 0) { 635 mlog_errno(status); 636 goto bail; 637 } 638 639 status = ocfs2_block_group_grow_discontig(handle, alloc_inode, 640 bg_bh, ac, cl, min_bits); 641 if (status) 642 mlog_errno(status); 643 644bail: 645 if (status) 646 ocfs2_bg_alloc_cleanup(handle, ac, alloc_inode, bg_bh); 647 return status ? ERR_PTR(status) : bg_bh; 648} 649 650/* 651 * We expect the block group allocator to already be locked. 652 */ 653static int ocfs2_block_group_alloc(struct ocfs2_super *osb, 654 struct inode *alloc_inode, 655 struct buffer_head *bh, 656 u64 max_block, 657 u64 *last_alloc_group, 658 int flags) 659{ 660 int status, credits; 661 struct ocfs2_dinode *fe = (struct ocfs2_dinode *) bh->b_data; 662 struct ocfs2_chain_list *cl; 663 struct ocfs2_alloc_context *ac = NULL; 664 handle_t *handle = NULL; 665 u16 alloc_rec; 666 struct buffer_head *bg_bh = NULL; 667 struct ocfs2_group_desc *bg; 668 669 BUG_ON(ocfs2_is_cluster_bitmap(alloc_inode)); 670 671 cl = &fe->id2.i_chain; 672 status = ocfs2_reserve_clusters_with_limit(osb, 673 le16_to_cpu(cl->cl_cpg), 674 max_block, flags, &ac); 675 if (status < 0) { 676 if (status != -ENOSPC) 677 mlog_errno(status); 678 goto bail; 679 } 680 681 credits = ocfs2_calc_group_alloc_credits(osb->sb, 682 le16_to_cpu(cl->cl_cpg)); 683 handle = ocfs2_start_trans(osb, credits); 684 if (IS_ERR(handle)) { 685 status = PTR_ERR(handle); 686 handle = NULL; 687 mlog_errno(status); 688 goto bail; 689 } 690 691 if (last_alloc_group && *last_alloc_group != 0) { 692 trace_ocfs2_block_group_alloc( 693 (unsigned long long)*last_alloc_group); 694 ac->ac_last_group = *last_alloc_group; 695 } 696 697 bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode, 698 ac, cl); 699 if (PTR_ERR(bg_bh) == -ENOSPC) 700 bg_bh = ocfs2_block_group_alloc_discontig(handle, 701 alloc_inode, 702 ac, cl); 703 if (IS_ERR(bg_bh)) { 704 status = PTR_ERR(bg_bh); 705 bg_bh = NULL; 706 if (status != -ENOSPC) 707 mlog_errno(status); 708 goto bail; 709 } 710 bg = (struct ocfs2_group_desc *) bg_bh->b_data; 711 712 status = ocfs2_journal_access_di(handle, INODE_CACHE(alloc_inode), 713 bh, OCFS2_JOURNAL_ACCESS_WRITE); 714 if (status < 0) { 715 mlog_errno(status); 716 goto bail; 717 } 718 719 alloc_rec = le16_to_cpu(bg->bg_chain); 720 le32_add_cpu(&cl->cl_recs[alloc_rec].c_free, 721 le16_to_cpu(bg->bg_free_bits_count)); 722 le32_add_cpu(&cl->cl_recs[alloc_rec].c_total, 723 le16_to_cpu(bg->bg_bits)); 724 cl->cl_recs[alloc_rec].c_blkno = bg->bg_blkno; 725 if (le16_to_cpu(cl->cl_next_free_rec) < le16_to_cpu(cl->cl_count)) 726 le16_add_cpu(&cl->cl_next_free_rec, 1); 727 728 le32_add_cpu(&fe->id1.bitmap1.i_used, le16_to_cpu(bg->bg_bits) - 729 le16_to_cpu(bg->bg_free_bits_count)); 730 le32_add_cpu(&fe->id1.bitmap1.i_total, le16_to_cpu(bg->bg_bits)); 731 le32_add_cpu(&fe->i_clusters, le16_to_cpu(cl->cl_cpg)); 732 733 ocfs2_journal_dirty(handle, bh); 734 735 spin_lock(&OCFS2_I(alloc_inode)->ip_lock); 736 OCFS2_I(alloc_inode)->ip_clusters = le32_to_cpu(fe->i_clusters); 737 fe->i_size = cpu_to_le64(ocfs2_clusters_to_bytes(alloc_inode->i_sb, 738 le32_to_cpu(fe->i_clusters))); 739 spin_unlock(&OCFS2_I(alloc_inode)->ip_lock); 740 i_size_write(alloc_inode, le64_to_cpu(fe->i_size)); 741 alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode); 742 ocfs2_update_inode_fsync_trans(handle, alloc_inode, 0); 743 744 status = 0; 745 746 /* save the new last alloc group so that the caller can cache it. */ 747 if (last_alloc_group) 748 *last_alloc_group = ac->ac_last_group; 749 750bail: 751 if (handle) 752 ocfs2_commit_trans(osb, handle); 753 754 if (ac) 755 ocfs2_free_alloc_context(ac); 756 757 brelse(bg_bh); 758 759 if (status) 760 mlog_errno(status); 761 return status; 762} 763 764static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb, 765 struct ocfs2_alloc_context *ac, 766 int type, 767 u32 slot, 768 u64 *last_alloc_group, 769 int flags) 770{ 771 int status; 772 u32 bits_wanted = ac->ac_bits_wanted; 773 struct inode *alloc_inode; 774 struct buffer_head *bh = NULL; 775 struct ocfs2_dinode *fe; 776 u32 free_bits; 777 778 alloc_inode = ocfs2_get_system_file_inode(osb, type, slot); 779 if (!alloc_inode) { 780 mlog_errno(-EINVAL); 781 return -EINVAL; 782 } 783 784 inode_lock(alloc_inode); 785 786 status = ocfs2_inode_lock(alloc_inode, &bh, 1); 787 if (status < 0) { 788 inode_unlock(alloc_inode); 789 iput(alloc_inode); 790 791 mlog_errno(status); 792 return status; 793 } 794 795 ac->ac_inode = alloc_inode; 796 ac->ac_alloc_slot = slot; 797 798 fe = (struct ocfs2_dinode *) bh->b_data; 799 800 /* The bh was validated by the inode read inside 801 * ocfs2_inode_lock(). Any corruption is a code bug. */ 802 BUG_ON(!OCFS2_IS_VALID_DINODE(fe)); 803 804 if (!(fe->i_flags & cpu_to_le32(OCFS2_CHAIN_FL))) { 805 status = ocfs2_error(alloc_inode->i_sb, 806 "Invalid chain allocator %llu\n", 807 (unsigned long long)le64_to_cpu(fe->i_blkno)); 808 goto bail; 809 } 810 811 free_bits = le32_to_cpu(fe->id1.bitmap1.i_total) - 812 le32_to_cpu(fe->id1.bitmap1.i_used); 813 814 if (bits_wanted > free_bits) { 815 /* cluster bitmap never grows */ 816 if (ocfs2_is_cluster_bitmap(alloc_inode)) { 817 trace_ocfs2_reserve_suballoc_bits_nospc(bits_wanted, 818 free_bits); 819 status = -ENOSPC; 820 goto bail; 821 } 822 823 if (!(flags & ALLOC_NEW_GROUP)) { 824 trace_ocfs2_reserve_suballoc_bits_no_new_group( 825 slot, bits_wanted, free_bits); 826 status = -ENOSPC; 827 goto bail; 828 } 829 830 status = ocfs2_block_group_alloc(osb, alloc_inode, bh, 831 ac->ac_max_block, 832 last_alloc_group, flags); 833 if (status < 0) { 834 if (status != -ENOSPC) 835 mlog_errno(status); 836 goto bail; 837 } 838 atomic_inc(&osb->alloc_stats.bg_extends); 839 840 /* You should never ask for this much metadata */ 841 BUG_ON(bits_wanted > 842 (le32_to_cpu(fe->id1.bitmap1.i_total) 843 - le32_to_cpu(fe->id1.bitmap1.i_used))); 844 } 845 846 get_bh(bh); 847 ac->ac_bh = bh; 848bail: 849 brelse(bh); 850 851 if (status) 852 mlog_errno(status); 853 return status; 854} 855 856static void ocfs2_init_inode_steal_slot(struct ocfs2_super *osb) 857{ 858 spin_lock(&osb->osb_lock); 859 osb->s_inode_steal_slot = OCFS2_INVALID_SLOT; 860 spin_unlock(&osb->osb_lock); 861 atomic_set(&osb->s_num_inodes_stolen, 0); 862} 863 864static void ocfs2_init_meta_steal_slot(struct ocfs2_super *osb) 865{ 866 spin_lock(&osb->osb_lock); 867 osb->s_meta_steal_slot = OCFS2_INVALID_SLOT; 868 spin_unlock(&osb->osb_lock); 869 atomic_set(&osb->s_num_meta_stolen, 0); 870} 871 872void ocfs2_init_steal_slots(struct ocfs2_super *osb) 873{ 874 ocfs2_init_inode_steal_slot(osb); 875 ocfs2_init_meta_steal_slot(osb); 876} 877 878static void __ocfs2_set_steal_slot(struct ocfs2_super *osb, int slot, int type) 879{ 880 spin_lock(&osb->osb_lock); 881 if (type == INODE_ALLOC_SYSTEM_INODE) 882 osb->s_inode_steal_slot = (u16)slot; 883 else if (type == EXTENT_ALLOC_SYSTEM_INODE) 884 osb->s_meta_steal_slot = (u16)slot; 885 spin_unlock(&osb->osb_lock); 886} 887 888static int __ocfs2_get_steal_slot(struct ocfs2_super *osb, int type) 889{ 890 int slot = OCFS2_INVALID_SLOT; 891 892 spin_lock(&osb->osb_lock); 893 if (type == INODE_ALLOC_SYSTEM_INODE) 894 slot = osb->s_inode_steal_slot; 895 else if (type == EXTENT_ALLOC_SYSTEM_INODE) 896 slot = osb->s_meta_steal_slot; 897 spin_unlock(&osb->osb_lock); 898 899 return slot; 900} 901 902static int ocfs2_get_inode_steal_slot(struct ocfs2_super *osb) 903{ 904 return __ocfs2_get_steal_slot(osb, INODE_ALLOC_SYSTEM_INODE); 905} 906 907static int ocfs2_get_meta_steal_slot(struct ocfs2_super *osb) 908{ 909 return __ocfs2_get_steal_slot(osb, EXTENT_ALLOC_SYSTEM_INODE); 910} 911 912static int ocfs2_steal_resource(struct ocfs2_super *osb, 913 struct ocfs2_alloc_context *ac, 914 int type) 915{ 916 int i, status = -ENOSPC; 917 int slot = __ocfs2_get_steal_slot(osb, type); 918 919 /* Start to steal resource from the first slot after ours. */ 920 if (slot == OCFS2_INVALID_SLOT) 921 slot = osb->slot_num + 1; 922 923 for (i = 0; i < osb->max_slots; i++, slot++) { 924 if (slot == osb->max_slots) 925 slot = 0; 926 927 if (slot == osb->slot_num) 928 continue; 929 930 status = ocfs2_reserve_suballoc_bits(osb, ac, 931 type, 932 (u32)slot, NULL, 933 NOT_ALLOC_NEW_GROUP); 934 if (status >= 0) { 935 __ocfs2_set_steal_slot(osb, slot, type); 936 break; 937 } 938 939 ocfs2_free_ac_resource(ac); 940 } 941 942 return status; 943} 944 945static int ocfs2_steal_inode(struct ocfs2_super *osb, 946 struct ocfs2_alloc_context *ac) 947{ 948 return ocfs2_steal_resource(osb, ac, INODE_ALLOC_SYSTEM_INODE); 949} 950 951static int ocfs2_steal_meta(struct ocfs2_super *osb, 952 struct ocfs2_alloc_context *ac) 953{ 954 return ocfs2_steal_resource(osb, ac, EXTENT_ALLOC_SYSTEM_INODE); 955} 956 957int ocfs2_reserve_new_metadata_blocks(struct ocfs2_super *osb, 958 int blocks, 959 struct ocfs2_alloc_context **ac) 960{ 961 int status; 962 int slot = ocfs2_get_meta_steal_slot(osb); 963 964 *ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL); 965 if (!(*ac)) { 966 status = -ENOMEM; 967 mlog_errno(status); 968 goto bail; 969 } 970 971 (*ac)->ac_bits_wanted = blocks; 972 (*ac)->ac_which = OCFS2_AC_USE_META; 973 (*ac)->ac_group_search = ocfs2_block_group_search; 974 975 if (slot != OCFS2_INVALID_SLOT && 976 atomic_read(&osb->s_num_meta_stolen) < OCFS2_MAX_TO_STEAL) 977 goto extent_steal; 978 979 atomic_set(&osb->s_num_meta_stolen, 0); 980 status = ocfs2_reserve_suballoc_bits(osb, (*ac), 981 EXTENT_ALLOC_SYSTEM_INODE, 982 (u32)osb->slot_num, NULL, 983 ALLOC_GROUPS_FROM_GLOBAL|ALLOC_NEW_GROUP); 984 985 986 if (status >= 0) { 987 status = 0; 988 if (slot != OCFS2_INVALID_SLOT) 989 ocfs2_init_meta_steal_slot(osb); 990 goto bail; 991 } else if (status < 0 && status != -ENOSPC) { 992 mlog_errno(status); 993 goto bail; 994 } 995 996 ocfs2_free_ac_resource(*ac); 997 998extent_steal: 999 status = ocfs2_steal_meta(osb, *ac); 1000 atomic_inc(&osb->s_num_meta_stolen); 1001 if (status < 0) { 1002 if (status != -ENOSPC) 1003 mlog_errno(status); 1004 goto bail; 1005 } 1006 1007 status = 0; 1008bail: 1009 if ((status < 0) && *ac) { 1010 ocfs2_free_alloc_context(*ac); 1011 *ac = NULL; 1012 } 1013 1014 if (status) 1015 mlog_errno(status); 1016 return status; 1017} 1018 1019int ocfs2_reserve_new_metadata(struct ocfs2_super *osb, 1020 struct ocfs2_extent_list *root_el, 1021 struct ocfs2_alloc_context **ac) 1022{ 1023 return ocfs2_reserve_new_metadata_blocks(osb, 1024 ocfs2_extend_meta_needed(root_el), 1025 ac); 1026} 1027 1028int ocfs2_reserve_new_inode(struct ocfs2_super *osb, 1029 struct ocfs2_alloc_context **ac) 1030{ 1031 int status; 1032 int slot = ocfs2_get_inode_steal_slot(osb); 1033 u64 alloc_group; 1034 1035 *ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL); 1036 if (!(*ac)) { 1037 status = -ENOMEM; 1038 mlog_errno(status); 1039 goto bail; 1040 } 1041 1042 (*ac)->ac_bits_wanted = 1; 1043 (*ac)->ac_which = OCFS2_AC_USE_INODE; 1044 1045 (*ac)->ac_group_search = ocfs2_block_group_search; 1046 1047 /* 1048 * stat(2) can't handle i_ino > 32bits, so we tell the 1049 * lower levels not to allocate us a block group past that 1050 * limit. The 'inode64' mount option avoids this behavior. 1051 */ 1052 if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64)) 1053 (*ac)->ac_max_block = (u32)~0U; 1054 1055 /* 1056 * slot is set when we successfully steal inode from other nodes. 1057 * It is reset in 3 places: 1058 * 1. when we flush the truncate log 1059 * 2. when we complete local alloc recovery. 1060 * 3. when we successfully allocate from our own slot. 1061 * After it is set, we will go on stealing inodes until we find the 1062 * need to check our slots to see whether there is some space for us. 1063 */ 1064 if (slot != OCFS2_INVALID_SLOT && 1065 atomic_read(&osb->s_num_inodes_stolen) < OCFS2_MAX_TO_STEAL) 1066 goto inode_steal; 1067 1068 atomic_set(&osb->s_num_inodes_stolen, 0); 1069 alloc_group = osb->osb_inode_alloc_group; 1070 status = ocfs2_reserve_suballoc_bits(osb, *ac, 1071 INODE_ALLOC_SYSTEM_INODE, 1072 (u32)osb->slot_num, 1073 &alloc_group, 1074 ALLOC_NEW_GROUP | 1075 ALLOC_GROUPS_FROM_GLOBAL); 1076 if (status >= 0) { 1077 status = 0; 1078 1079 spin_lock(&osb->osb_lock); 1080 osb->osb_inode_alloc_group = alloc_group; 1081 spin_unlock(&osb->osb_lock); 1082 trace_ocfs2_reserve_new_inode_new_group( 1083 (unsigned long long)alloc_group); 1084 1085 /* 1086 * Some inodes must be freed by us, so try to allocate 1087 * from our own next time. 1088 */ 1089 if (slot != OCFS2_INVALID_SLOT) 1090 ocfs2_init_inode_steal_slot(osb); 1091 goto bail; 1092 } else if (status < 0 && status != -ENOSPC) { 1093 mlog_errno(status); 1094 goto bail; 1095 } 1096 1097 ocfs2_free_ac_resource(*ac); 1098 1099inode_steal: 1100 status = ocfs2_steal_inode(osb, *ac); 1101 atomic_inc(&osb->s_num_inodes_stolen); 1102 if (status < 0) { 1103 if (status != -ENOSPC) 1104 mlog_errno(status); 1105 goto bail; 1106 } 1107 1108 status = 0; 1109bail: 1110 if ((status < 0) && *ac) { 1111 ocfs2_free_alloc_context(*ac); 1112 *ac = NULL; 1113 } 1114 1115 if (status) 1116 mlog_errno(status); 1117 return status; 1118} 1119 1120/* local alloc code has to do the same thing, so rather than do this 1121 * twice.. */ 1122int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb, 1123 struct ocfs2_alloc_context *ac) 1124{ 1125 int status; 1126 1127 ac->ac_which = OCFS2_AC_USE_MAIN; 1128 ac->ac_group_search = ocfs2_cluster_group_search; 1129 1130 status = ocfs2_reserve_suballoc_bits(osb, ac, 1131 GLOBAL_BITMAP_SYSTEM_INODE, 1132 OCFS2_INVALID_SLOT, NULL, 1133 ALLOC_NEW_GROUP); 1134 if (status < 0 && status != -ENOSPC) 1135 mlog_errno(status); 1136 1137 return status; 1138} 1139 1140/* Callers don't need to care which bitmap (local alloc or main) to 1141 * use so we figure it out for them, but unfortunately this clutters 1142 * things a bit. */ 1143static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb, 1144 u32 bits_wanted, u64 max_block, 1145 int flags, 1146 struct ocfs2_alloc_context **ac) 1147{ 1148 int status, ret = 0; 1149 int retried = 0; 1150 1151 *ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL); 1152 if (!(*ac)) { 1153 status = -ENOMEM; 1154 mlog_errno(status); 1155 goto bail; 1156 } 1157 1158 (*ac)->ac_bits_wanted = bits_wanted; 1159 (*ac)->ac_max_block = max_block; 1160 1161 status = -ENOSPC; 1162 if (!(flags & ALLOC_GROUPS_FROM_GLOBAL) && 1163 ocfs2_alloc_should_use_local(osb, bits_wanted)) { 1164 status = ocfs2_reserve_local_alloc_bits(osb, 1165 bits_wanted, 1166 *ac); 1167 if ((status < 0) && (status != -ENOSPC)) { 1168 mlog_errno(status); 1169 goto bail; 1170 } 1171 } 1172 1173 if (status == -ENOSPC) { 1174retry: 1175 status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac); 1176 /* Retry if there is sufficient space cached in truncate log */ 1177 if (status == -ENOSPC && !retried) { 1178 retried = 1; 1179 ocfs2_inode_unlock((*ac)->ac_inode, 1); 1180 inode_unlock((*ac)->ac_inode); 1181 1182 ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted); 1183 if (ret == 1) { 1184 iput((*ac)->ac_inode); 1185 (*ac)->ac_inode = NULL; 1186 goto retry; 1187 } 1188 1189 if (ret < 0) 1190 mlog_errno(ret); 1191 1192 inode_lock((*ac)->ac_inode); 1193 ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1); 1194 if (ret < 0) { 1195 mlog_errno(ret); 1196 inode_unlock((*ac)->ac_inode); 1197 iput((*ac)->ac_inode); 1198 (*ac)->ac_inode = NULL; 1199 goto bail; 1200 } 1201 } 1202 if (status < 0) { 1203 if (status != -ENOSPC) 1204 mlog_errno(status); 1205 goto bail; 1206 } 1207 } 1208 1209 status = 0; 1210bail: 1211 if ((status < 0) && *ac) { 1212 ocfs2_free_alloc_context(*ac); 1213 *ac = NULL; 1214 } 1215 1216 if (status) 1217 mlog_errno(status); 1218 return status; 1219} 1220 1221int ocfs2_reserve_clusters(struct ocfs2_super *osb, 1222 u32 bits_wanted, 1223 struct ocfs2_alloc_context **ac) 1224{ 1225 return ocfs2_reserve_clusters_with_limit(osb, bits_wanted, 0, 1226 ALLOC_NEW_GROUP, ac); 1227} 1228 1229/* 1230 * More or less lifted from ext3. I'll leave their description below: 1231 * 1232 * "For ext3 allocations, we must not reuse any blocks which are 1233 * allocated in the bitmap buffer's "last committed data" copy. This 1234 * prevents deletes from freeing up the page for reuse until we have 1235 * committed the delete transaction. 1236 * 1237 * If we didn't do this, then deleting something and reallocating it as 1238 * data would allow the old block to be overwritten before the 1239 * transaction committed (because we force data to disk before commit). 1240 * This would lead to corruption if we crashed between overwriting the 1241 * data and committing the delete. 1242 * 1243 * @@@ We may want to make this allocation behaviour conditional on 1244 * data-writes at some point, and disable it for metadata allocations or 1245 * sync-data inodes." 1246 * 1247 * Note: OCFS2 already does this differently for metadata vs data 1248 * allocations, as those bitmaps are separate and undo access is never 1249 * called on a metadata group descriptor. 1250 */ 1251static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, 1252 int nr) 1253{ 1254 struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; 1255 struct journal_head *jh; 1256 int ret; 1257 1258 if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap)) 1259 return 0; 1260 1261 jh = jbd2_journal_grab_journal_head(bg_bh); 1262 if (!jh) 1263 return 1; 1264 1265 spin_lock(&jh->b_state_lock); 1266 bg = (struct ocfs2_group_desc *) jh->b_committed_data; 1267 if (bg) 1268 ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); 1269 else 1270 ret = 1; 1271 spin_unlock(&jh->b_state_lock); 1272 jbd2_journal_put_journal_head(jh); 1273 1274 return ret; 1275} 1276 1277static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, 1278 struct buffer_head *bg_bh, 1279 unsigned int bits_wanted, 1280 unsigned int total_bits, 1281 struct ocfs2_suballoc_result *res) 1282{ 1283 void *bitmap; 1284 u16 best_offset, best_size; 1285 int offset, start, found, status = 0; 1286 struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; 1287 1288 /* Callers got this descriptor from 1289 * ocfs2_read_group_descriptor(). Any corruption is a code bug. */ 1290 BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg)); 1291 1292 found = start = best_offset = best_size = 0; 1293 bitmap = bg->bg_bitmap; 1294 1295 while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) { 1296 if (offset == total_bits) 1297 break; 1298 1299 if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) { 1300 /* We found a zero, but we can't use it as it 1301 * hasn't been put to disk yet! */ 1302 found = 0; 1303 start = offset + 1; 1304 } else if (offset == start) { 1305 /* we found a zero */ 1306 found++; 1307 /* move start to the next bit to test */ 1308 start++; 1309 } else { 1310 /* got a zero after some ones */ 1311 found = 1; 1312 start = offset + 1; 1313 } 1314 if (found > best_size) { 1315 best_size = found; 1316 best_offset = start - found; 1317 } 1318 /* we got everything we needed */ 1319 if (found == bits_wanted) { 1320 /* mlog(0, "Found it all!\n"); */ 1321 break; 1322 } 1323 } 1324 1325 if (best_size) { 1326 res->sr_bit_offset = best_offset; 1327 res->sr_bits = best_size; 1328 } else { 1329 status = -ENOSPC; 1330 /* No error log here -- see the comment above 1331 * ocfs2_test_bg_bit_allocatable */ 1332 } 1333 1334 return status; 1335} 1336 1337int ocfs2_block_group_set_bits(handle_t *handle, 1338 struct inode *alloc_inode, 1339 struct ocfs2_group_desc *bg, 1340 struct buffer_head *group_bh, 1341 unsigned int bit_off, 1342 unsigned int num_bits) 1343{ 1344 int status; 1345 void *bitmap = bg->bg_bitmap; 1346 int journal_type = OCFS2_JOURNAL_ACCESS_WRITE; 1347 1348 /* All callers get the descriptor via 1349 * ocfs2_read_group_descriptor(). Any corruption is a code bug. */ 1350 BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg)); 1351 BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits); 1352 1353 trace_ocfs2_block_group_set_bits(bit_off, num_bits); 1354 1355 if (ocfs2_is_cluster_bitmap(alloc_inode)) 1356 journal_type = OCFS2_JOURNAL_ACCESS_UNDO; 1357 1358 status = ocfs2_journal_access_gd(handle, 1359 INODE_CACHE(alloc_inode), 1360 group_bh, 1361 journal_type); 1362 if (status < 0) { 1363 mlog_errno(status); 1364 goto bail; 1365 } 1366 1367 le16_add_cpu(&bg->bg_free_bits_count, -num_bits); 1368 if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) { 1369 return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n", 1370 (unsigned long long)le64_to_cpu(bg->bg_blkno), 1371 le16_to_cpu(bg->bg_bits), 1372 le16_to_cpu(bg->bg_free_bits_count), 1373 num_bits); 1374 } 1375 while(num_bits--) 1376 ocfs2_set_bit(bit_off++, bitmap); 1377 1378 ocfs2_journal_dirty(handle, group_bh); 1379 1380bail: 1381 return status; 1382} 1383 1384/* find the one with the most empty bits */ 1385static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl) 1386{ 1387 u16 curr, best; 1388 1389 BUG_ON(!cl->cl_next_free_rec); 1390 1391 best = curr = 0; 1392 while (curr < le16_to_cpu(cl->cl_next_free_rec)) { 1393 if (le32_to_cpu(cl->cl_recs[curr].c_free) > 1394 le32_to_cpu(cl->cl_recs[best].c_free)) 1395 best = curr; 1396 curr++; 1397 } 1398 1399 BUG_ON(best >= le16_to_cpu(cl->cl_next_free_rec)); 1400 return best; 1401} 1402 1403static int ocfs2_relink_block_group(handle_t *handle, 1404 struct inode *alloc_inode, 1405 struct buffer_head *fe_bh, 1406 struct buffer_head *bg_bh, 1407 struct buffer_head *prev_bg_bh, 1408 u16 chain) 1409{ 1410 int status; 1411 /* there is a really tiny chance the journal calls could fail, 1412 * but we wouldn't want inconsistent blocks in *any* case. */ 1413 u64 bg_ptr, prev_bg_ptr; 1414 struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data; 1415 struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; 1416 struct ocfs2_group_desc *prev_bg = (struct ocfs2_group_desc *) prev_bg_bh->b_data; 1417 1418 /* The caller got these descriptors from 1419 * ocfs2_read_group_descriptor(). Any corruption is a code bug. */ 1420 BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg)); 1421 BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(prev_bg)); 1422 1423 trace_ocfs2_relink_block_group( 1424 (unsigned long long)le64_to_cpu(fe->i_blkno), chain, 1425 (unsigned long long)le64_to_cpu(bg->bg_blkno), 1426 (unsigned long long)le64_to_cpu(prev_bg->bg_blkno)); 1427 1428 bg_ptr = le64_to_cpu(bg->bg_next_group); 1429 prev_bg_ptr = le64_to_cpu(prev_bg->bg_next_group); 1430 1431 status = ocfs2_journal_access_gd(handle, INODE_CACHE(alloc_inode), 1432 prev_bg_bh, 1433 OCFS2_JOURNAL_ACCESS_WRITE); 1434 if (status < 0) 1435 goto out; 1436 1437 prev_bg->bg_next_group = bg->bg_next_group; 1438 ocfs2_journal_dirty(handle, prev_bg_bh); 1439 1440 status = ocfs2_journal_access_gd(handle, INODE_CACHE(alloc_inode), 1441 bg_bh, OCFS2_JOURNAL_ACCESS_WRITE); 1442 if (status < 0) 1443 goto out_rollback_prev_bg; 1444 1445 bg->bg_next_group = fe->id2.i_chain.cl_recs[chain].c_blkno; 1446 ocfs2_journal_dirty(handle, bg_bh); 1447 1448 status = ocfs2_journal_access_di(handle, INODE_CACHE(alloc_inode), 1449 fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); 1450 if (status < 0) 1451 goto out_rollback_bg; 1452 1453 fe->id2.i_chain.cl_recs[chain].c_blkno = bg->bg_blkno; 1454 ocfs2_journal_dirty(handle, fe_bh); 1455 1456out: 1457 if (status < 0) 1458 mlog_errno(status); 1459 return status; 1460 1461out_rollback_bg: 1462 bg->bg_next_group = cpu_to_le64(bg_ptr); 1463out_rollback_prev_bg: 1464 prev_bg->bg_next_group = cpu_to_le64(prev_bg_ptr); 1465 goto out; 1466} 1467 1468static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg, 1469 u32 wanted) 1470{ 1471 return le16_to_cpu(bg->bg_free_bits_count) > wanted; 1472} 1473 1474/* return 0 on success, -ENOSPC to keep searching and any other < 0 1475 * value on error. */ 1476static int ocfs2_cluster_group_search(struct inode *inode, 1477 struct buffer_head *group_bh, 1478 u32 bits_wanted, u32 min_bits, 1479 u64 max_block, 1480 struct ocfs2_suballoc_result *res) 1481{ 1482 int search = -ENOSPC; 1483 int ret; 1484 u64 blkoff; 1485 struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *) group_bh->b_data; 1486 struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); 1487 unsigned int max_bits, gd_cluster_off; 1488 1489 BUG_ON(!ocfs2_is_cluster_bitmap(inode)); 1490 1491 if (gd->bg_free_bits_count) { 1492 max_bits = le16_to_cpu(gd->bg_bits); 1493 1494 /* Tail groups in cluster bitmaps which aren't cpg 1495 * aligned are prone to partial extension by a failed 1496 * fs resize. If the file system resize never got to 1497 * update the dinode cluster count, then we don't want 1498 * to trust any clusters past it, regardless of what 1499 * the group descriptor says. */ 1500 gd_cluster_off = ocfs2_blocks_to_clusters(inode->i_sb, 1501 le64_to_cpu(gd->bg_blkno)); 1502 if ((gd_cluster_off + max_bits) > 1503 OCFS2_I(inode)->ip_clusters) { 1504 max_bits = OCFS2_I(inode)->ip_clusters - gd_cluster_off; 1505 trace_ocfs2_cluster_group_search_wrong_max_bits( 1506 (unsigned long long)le64_to_cpu(gd->bg_blkno), 1507 le16_to_cpu(gd->bg_bits), 1508 OCFS2_I(inode)->ip_clusters, max_bits); 1509 } 1510 1511 ret = ocfs2_block_group_find_clear_bits(osb, 1512 group_bh, bits_wanted, 1513 max_bits, res); 1514 if (ret) 1515 return ret; 1516 1517 if (max_block) { 1518 blkoff = ocfs2_clusters_to_blocks(inode->i_sb, 1519 gd_cluster_off + 1520 res->sr_bit_offset + 1521 res->sr_bits); 1522 trace_ocfs2_cluster_group_search_max_block( 1523 (unsigned long long)blkoff, 1524 (unsigned long long)max_block); 1525 if (blkoff > max_block) 1526 return -ENOSPC; 1527 } 1528 1529 /* ocfs2_block_group_find_clear_bits() might 1530 * return success, but we still want to return 1531 * -ENOSPC unless it found the minimum number 1532 * of bits. */ 1533 if (min_bits <= res->sr_bits) 1534 search = 0; /* success */ 1535 else if (res->sr_bits) { 1536 /* 1537 * Don't show bits which we'll be returning 1538 * for allocation to the local alloc bitmap. 1539 */ 1540 ocfs2_local_alloc_seen_free_bits(osb, res->sr_bits); 1541 } 1542 } 1543 1544 return search; 1545} 1546 1547static int ocfs2_block_group_search(struct inode *inode, 1548 struct buffer_head *group_bh, 1549 u32 bits_wanted, u32 min_bits, 1550 u64 max_block, 1551 struct ocfs2_suballoc_result *res) 1552{ 1553 int ret = -ENOSPC; 1554 u64 blkoff; 1555 struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) group_bh->b_data; 1556 1557 BUG_ON(min_bits != 1); 1558 BUG_ON(ocfs2_is_cluster_bitmap(inode)); 1559 1560 if (bg->bg_free_bits_count) { 1561 ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), 1562 group_bh, bits_wanted, 1563 le16_to_cpu(bg->bg_bits), 1564 res); 1565 if (!ret && max_block) { 1566 blkoff = le64_to_cpu(bg->bg_blkno) + 1567 res->sr_bit_offset + res->sr_bits; 1568 trace_ocfs2_block_group_search_max_block( 1569 (unsigned long long)blkoff, 1570 (unsigned long long)max_block); 1571 if (blkoff > max_block) 1572 ret = -ENOSPC; 1573 } 1574 } 1575 1576 return ret; 1577} 1578 1579int ocfs2_alloc_dinode_update_counts(struct inode *inode, 1580 handle_t *handle, 1581 struct buffer_head *di_bh, 1582 u32 num_bits, 1583 u16 chain) 1584{ 1585 int ret; 1586 u32 tmp_used; 1587 struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; 1588 struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &di->id2.i_chain; 1589 1590 ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, 1591 OCFS2_JOURNAL_ACCESS_WRITE); 1592 if (ret < 0) { 1593 mlog_errno(ret); 1594 goto out; 1595 } 1596 1597 tmp_used = le32_to_cpu(di->id1.bitmap1.i_used); 1598 di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used); 1599 le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits); 1600 ocfs2_journal_dirty(handle, di_bh); 1601 1602out: 1603 return ret; 1604} 1605 1606void ocfs2_rollback_alloc_dinode_counts(struct inode *inode, 1607 struct buffer_head *di_bh, 1608 u32 num_bits, 1609 u16 chain) 1610{ 1611 u32 tmp_used; 1612 struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; 1613 struct ocfs2_chain_list *cl; 1614 1615 cl = (struct ocfs2_chain_list *)&di->id2.i_chain; 1616 tmp_used = le32_to_cpu(di->id1.bitmap1.i_used); 1617 di->id1.bitmap1.i_used = cpu_to_le32(tmp_used - num_bits); 1618 le32_add_cpu(&cl->cl_recs[chain].c_free, num_bits); 1619} 1620 1621static int ocfs2_bg_discontig_fix_by_rec(struct ocfs2_suballoc_result *res, 1622 struct ocfs2_extent_rec *rec, 1623 struct ocfs2_chain_list *cl) 1624{ 1625 unsigned int bpc = le16_to_cpu(cl->cl_bpc); 1626 unsigned int bitoff = le32_to_cpu(rec->e_cpos) * bpc; 1627 unsigned int bitcount = le16_to_cpu(rec->e_leaf_clusters) * bpc; 1628 1629 if (res->sr_bit_offset < bitoff) 1630 return 0; 1631 if (res->sr_bit_offset >= (bitoff + bitcount)) 1632 return 0; 1633 res->sr_blkno = le64_to_cpu(rec->e_blkno) + 1634 (res->sr_bit_offset - bitoff); 1635 if ((res->sr_bit_offset + res->sr_bits) > (bitoff + bitcount)) 1636 res->sr_bits = (bitoff + bitcount) - res->sr_bit_offset; 1637 return 1; 1638} 1639 1640static void ocfs2_bg_discontig_fix_result(struct ocfs2_alloc_context *ac, 1641 struct ocfs2_group_desc *bg, 1642 struct ocfs2_suballoc_result *res) 1643{ 1644 int i; 1645 u64 bg_blkno = res->sr_bg_blkno; /* Save off */ 1646 struct ocfs2_extent_rec *rec; 1647 struct ocfs2_dinode *di = (struct ocfs2_dinode *)ac->ac_bh->b_data; 1648 struct ocfs2_chain_list *cl = &di->id2.i_chain; 1649 1650 if (ocfs2_is_cluster_bitmap(ac->ac_inode)) { 1651 res->sr_blkno = 0; 1652 return; 1653 } 1654 1655 res->sr_blkno = res->sr_bg_blkno + res->sr_bit_offset; 1656 res->sr_bg_blkno = 0; /* Clear it for contig block groups */ 1657 if (!ocfs2_supports_discontig_bg(OCFS2_SB(ac->ac_inode->i_sb)) || 1658 !bg->bg_list.l_next_free_rec) 1659 return; 1660 1661 for (i = 0; i < le16_to_cpu(bg->bg_list.l_next_free_rec); i++) { 1662 rec = &bg->bg_list.l_recs[i]; 1663 if (ocfs2_bg_discontig_fix_by_rec(res, rec, cl)) { 1664 res->sr_bg_blkno = bg_blkno; /* Restore */ 1665 break; 1666 } 1667 } 1668} 1669 1670static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac, 1671 handle_t *handle, 1672 u32 bits_wanted, 1673 u32 min_bits, 1674 struct ocfs2_suballoc_result *res, 1675 u16 *bits_left) 1676{ 1677 int ret; 1678 struct buffer_head *group_bh = NULL; 1679 struct ocfs2_group_desc *gd; 1680 struct ocfs2_dinode *di = (struct ocfs2_dinode *)ac->ac_bh->b_data; 1681 struct inode *alloc_inode = ac->ac_inode; 1682 1683 ret = ocfs2_read_group_descriptor(alloc_inode, di, 1684 res->sr_bg_blkno, &group_bh); 1685 if (ret < 0) { 1686 mlog_errno(ret); 1687 return ret; 1688 } 1689 1690 gd = (struct ocfs2_group_desc *) group_bh->b_data; 1691 ret = ac->ac_group_search(alloc_inode, group_bh, bits_wanted, min_bits, 1692 ac->ac_max_block, res); 1693 if (ret < 0) { 1694 if (ret != -ENOSPC) 1695 mlog_errno(ret); 1696 goto out; 1697 } 1698 1699 if (!ret) 1700 ocfs2_bg_discontig_fix_result(ac, gd, res); 1701 1702 /* 1703 * sr_bg_blkno might have been changed by 1704 * ocfs2_bg_discontig_fix_result 1705 */ 1706 res->sr_bg_stable_blkno = group_bh->b_blocknr; 1707 1708 if (ac->ac_find_loc_only) 1709 goto out_loc_only; 1710 1711 ret = ocfs2_alloc_dinode_update_counts(alloc_inode, handle, ac->ac_bh, 1712 res->sr_bits, 1713 le16_to_cpu(gd->bg_chain)); 1714 if (ret < 0) { 1715 mlog_errno(ret); 1716 goto out; 1717 } 1718 1719 ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh, 1720 res->sr_bit_offset, res->sr_bits); 1721 if (ret < 0) { 1722 ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh, 1723 res->sr_bits, 1724 le16_to_cpu(gd->bg_chain)); 1725 mlog_errno(ret); 1726 } 1727 1728out_loc_only: 1729 *bits_left = le16_to_cpu(gd->bg_free_bits_count); 1730 1731out: 1732 brelse(group_bh); 1733 1734 return ret; 1735} 1736 1737static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, 1738 handle_t *handle, 1739 u32 bits_wanted, 1740 u32 min_bits, 1741 struct ocfs2_suballoc_result *res, 1742 u16 *bits_left) 1743{ 1744 int status; 1745 u16 chain; 1746 u64 next_group; 1747 struct inode *alloc_inode = ac->ac_inode; 1748 struct buffer_head *group_bh = NULL; 1749 struct buffer_head *prev_group_bh = NULL; 1750 struct ocfs2_dinode *fe = (struct ocfs2_dinode *) ac->ac_bh->b_data; 1751 struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &fe->id2.i_chain; 1752 struct ocfs2_group_desc *bg; 1753 1754 chain = ac->ac_chain; 1755 trace_ocfs2_search_chain_begin( 1756 (unsigned long long)OCFS2_I(alloc_inode)->ip_blkno, 1757 bits_wanted, chain); 1758 1759 status = ocfs2_read_group_descriptor(alloc_inode, fe, 1760 le64_to_cpu(cl->cl_recs[chain].c_blkno), 1761 &group_bh); 1762 if (status < 0) { 1763 mlog_errno(status); 1764 goto bail; 1765 } 1766 bg = (struct ocfs2_group_desc *) group_bh->b_data; 1767 1768 status = -ENOSPC; 1769 /* for now, the chain search is a bit simplistic. We just use 1770 * the 1st group with any empty bits. */ 1771 while ((status = ac->ac_group_search(alloc_inode, group_bh, 1772 bits_wanted, min_bits, 1773 ac->ac_max_block, 1774 res)) == -ENOSPC) { 1775 if (!bg->bg_next_group) 1776 break; 1777 1778 brelse(prev_group_bh); 1779 prev_group_bh = NULL; 1780 1781 next_group = le64_to_cpu(bg->bg_next_group); 1782 prev_group_bh = group_bh; 1783 group_bh = NULL; 1784 status = ocfs2_read_group_descriptor(alloc_inode, fe, 1785 next_group, &group_bh); 1786 if (status < 0) { 1787 mlog_errno(status); 1788 goto bail; 1789 } 1790 bg = (struct ocfs2_group_desc *) group_bh->b_data; 1791 } 1792 if (status < 0) { 1793 if (status != -ENOSPC) 1794 mlog_errno(status); 1795 goto bail; 1796 } 1797 1798 trace_ocfs2_search_chain_succ( 1799 (unsigned long long)le64_to_cpu(bg->bg_blkno), res->sr_bits); 1800 1801 res->sr_bg_blkno = le64_to_cpu(bg->bg_blkno); 1802 1803 BUG_ON(res->sr_bits == 0); 1804 if (!status) 1805 ocfs2_bg_discontig_fix_result(ac, bg, res); 1806 1807 /* 1808 * sr_bg_blkno might have been changed by 1809 * ocfs2_bg_discontig_fix_result 1810 */ 1811 res->sr_bg_stable_blkno = group_bh->b_blocknr; 1812 1813 /* 1814 * Keep track of previous block descriptor read. When 1815 * we find a target, if we have read more than X 1816 * number of descriptors, and the target is reasonably 1817 * empty, relink him to top of his chain. 1818 * 1819 * We've read 0 extra blocks and only send one more to 1820 * the transaction, yet the next guy to search has a 1821 * much easier time. 1822 * 1823 * Do this *after* figuring out how many bits we're taking out 1824 * of our target group. 1825 */ 1826 if (!ac->ac_disable_chain_relink && 1827 (prev_group_bh) && 1828 (ocfs2_block_group_reasonably_empty(bg, res->sr_bits))) { 1829 status = ocfs2_relink_block_group(handle, alloc_inode, 1830 ac->ac_bh, group_bh, 1831 prev_group_bh, chain); 1832 if (status < 0) { 1833 mlog_errno(status); 1834 goto bail; 1835 } 1836 } 1837 1838 if (ac->ac_find_loc_only) 1839 goto out_loc_only; 1840 1841 status = ocfs2_alloc_dinode_update_counts(alloc_inode, handle, 1842 ac->ac_bh, res->sr_bits, 1843 chain); 1844 if (status) { 1845 mlog_errno(status); 1846 goto bail; 1847 } 1848 1849 status = ocfs2_block_group_set_bits(handle, 1850 alloc_inode, 1851 bg, 1852 group_bh, 1853 res->sr_bit_offset, 1854 res->sr_bits); 1855 if (status < 0) { 1856 ocfs2_rollback_alloc_dinode_counts(alloc_inode, 1857 ac->ac_bh, res->sr_bits, chain); 1858 mlog_errno(status); 1859 goto bail; 1860 } 1861 1862 trace_ocfs2_search_chain_end( 1863 (unsigned long long)le64_to_cpu(fe->i_blkno), 1864 res->sr_bits); 1865 1866out_loc_only: 1867 *bits_left = le16_to_cpu(bg->bg_free_bits_count); 1868bail: 1869 brelse(group_bh); 1870 brelse(prev_group_bh); 1871 1872 if (status) 1873 mlog_errno(status); 1874 return status; 1875} 1876 1877/* will give out up to bits_wanted contiguous bits. */ 1878static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, 1879 handle_t *handle, 1880 u32 bits_wanted, 1881 u32 min_bits, 1882 struct ocfs2_suballoc_result *res) 1883{ 1884 int status; 1885 u16 victim, i; 1886 u16 bits_left = 0; 1887 u64 hint = ac->ac_last_group; 1888 struct ocfs2_chain_list *cl; 1889 struct ocfs2_dinode *fe; 1890 1891 BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted); 1892 BUG_ON(bits_wanted > (ac->ac_bits_wanted - ac->ac_bits_given)); 1893 BUG_ON(!ac->ac_bh); 1894 1895 fe = (struct ocfs2_dinode *) ac->ac_bh->b_data; 1896 1897 /* The bh was validated by the inode read during 1898 * ocfs2_reserve_suballoc_bits(). Any corruption is a code bug. */ 1899 BUG_ON(!OCFS2_IS_VALID_DINODE(fe)); 1900 1901 if (le32_to_cpu(fe->id1.bitmap1.i_used) >= 1902 le32_to_cpu(fe->id1.bitmap1.i_total)) { 1903 status = ocfs2_error(ac->ac_inode->i_sb, 1904 "Chain allocator dinode %llu has %u used bits but only %u total\n", 1905 (unsigned long long)le64_to_cpu(fe->i_blkno), 1906 le32_to_cpu(fe->id1.bitmap1.i_used), 1907 le32_to_cpu(fe->id1.bitmap1.i_total)); 1908 goto bail; 1909 } 1910 1911 res->sr_bg_blkno = hint; 1912 if (res->sr_bg_blkno) { 1913 /* Attempt to short-circuit the usual search mechanism 1914 * by jumping straight to the most recently used 1915 * allocation group. This helps us maintain some 1916 * contiguousness across allocations. */ 1917 status = ocfs2_search_one_group(ac, handle, bits_wanted, 1918 min_bits, res, &bits_left); 1919 if (!status) 1920 goto set_hint; 1921 if (status < 0 && status != -ENOSPC) { 1922 mlog_errno(status); 1923 goto bail; 1924 } 1925 } 1926 1927 cl = (struct ocfs2_chain_list *) &fe->id2.i_chain; 1928 1929 victim = ocfs2_find_victim_chain(cl); 1930 ac->ac_chain = victim; 1931 1932 status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, 1933 res, &bits_left); 1934 if (!status) { 1935 if (ocfs2_is_cluster_bitmap(ac->ac_inode)) 1936 hint = res->sr_bg_blkno; 1937 else 1938 hint = ocfs2_group_from_res(res); 1939 goto set_hint; 1940 } 1941 if (status < 0 && status != -ENOSPC) { 1942 mlog_errno(status); 1943 goto bail; 1944 } 1945 1946 trace_ocfs2_claim_suballoc_bits(victim); 1947 1948 /* If we didn't pick a good victim, then just default to 1949 * searching each chain in order. Don't allow chain relinking 1950 * because we only calculate enough journal credits for one 1951 * relink per alloc. */ 1952 ac->ac_disable_chain_relink = 1; 1953 for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) { 1954 if (i == victim) 1955 continue; 1956 if (!cl->cl_recs[i].c_free) 1957 continue; 1958 1959 ac->ac_chain = i; 1960 status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, 1961 res, &bits_left); 1962 if (!status) { 1963 hint = ocfs2_group_from_res(res); 1964 break; 1965 } 1966 if (status < 0 && status != -ENOSPC) { 1967 mlog_errno(status); 1968 goto bail; 1969 } 1970 } 1971 1972set_hint: 1973 if (status != -ENOSPC) { 1974 /* If the next search of this group is not likely to 1975 * yield a suitable extent, then we reset the last 1976 * group hint so as to not waste a disk read */ 1977 if (bits_left < min_bits) 1978 ac->ac_last_group = 0; 1979 else 1980 ac->ac_last_group = hint; 1981 } 1982 1983bail: 1984 if (status) 1985 mlog_errno(status); 1986 return status; 1987} 1988 1989int ocfs2_claim_metadata(handle_t *handle, 1990 struct ocfs2_alloc_context *ac, 1991 u32 bits_wanted, 1992 u64 *suballoc_loc, 1993 u16 *suballoc_bit_start, 1994 unsigned int *num_bits, 1995 u64 *blkno_start) 1996{ 1997 int status; 1998 struct ocfs2_suballoc_result res = { .sr_blkno = 0, }; 1999 2000 BUG_ON(!ac); 2001 BUG_ON(ac->ac_bits_wanted < (ac->ac_bits_given + bits_wanted)); 2002 BUG_ON(ac->ac_which != OCFS2_AC_USE_META); 2003 2004 status = ocfs2_claim_suballoc_bits(ac, 2005 handle, 2006 bits_wanted, 2007 1, 2008 &res); 2009 if (status < 0) { 2010 mlog_errno(status); 2011 goto bail; 2012 } 2013 atomic_inc(&OCFS2_SB(ac->ac_inode->i_sb)->alloc_stats.bg_allocs); 2014 2015 *suballoc_loc = res.sr_bg_blkno; 2016 *suballoc_bit_start = res.sr_bit_offset; 2017 *blkno_start = res.sr_blkno; 2018 ac->ac_bits_given += res.sr_bits; 2019 *num_bits = res.sr_bits; 2020 status = 0; 2021bail: 2022 if (status) 2023 mlog_errno(status); 2024 return status; 2025} 2026 2027static void ocfs2_init_inode_ac_group(struct inode *dir, 2028 struct buffer_head *parent_di_bh, 2029 struct ocfs2_alloc_context *ac) 2030{ 2031 struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_di_bh->b_data; 2032 /* 2033 * Try to allocate inodes from some specific group. 2034 * 2035 * If the parent dir has recorded the last group used in allocation, 2036 * cool, use it. Otherwise if we try to allocate new inode from the 2037 * same slot the parent dir belongs to, use the same chunk. 2038 * 2039 * We are very careful here to avoid the mistake of setting 2040 * ac_last_group to a group descriptor from a different (unlocked) slot. 2041 */ 2042 if (OCFS2_I(dir)->ip_last_used_group && 2043 OCFS2_I(dir)->ip_last_used_slot == ac->ac_alloc_slot) 2044 ac->ac_last_group = OCFS2_I(dir)->ip_last_used_group; 2045 else if (le16_to_cpu(di->i_suballoc_slot) == ac->ac_alloc_slot) { 2046 if (di->i_suballoc_loc) 2047 ac->ac_last_group = le64_to_cpu(di->i_suballoc_loc); 2048 else 2049 ac->ac_last_group = ocfs2_which_suballoc_group( 2050 le64_to_cpu(di->i_blkno), 2051 le16_to_cpu(di->i_suballoc_bit)); 2052 } 2053} 2054 2055static inline void ocfs2_save_inode_ac_group(struct inode *dir, 2056 struct ocfs2_alloc_context *ac) 2057{ 2058 OCFS2_I(dir)->ip_last_used_group = ac->ac_last_group; 2059 OCFS2_I(dir)->ip_last_used_slot = ac->ac_alloc_slot; 2060} 2061 2062int ocfs2_find_new_inode_loc(struct inode *dir, 2063 struct buffer_head *parent_fe_bh, 2064 struct ocfs2_alloc_context *ac, 2065 u64 *fe_blkno) 2066{ 2067 int ret; 2068 handle_t *handle = NULL; 2069 struct ocfs2_suballoc_result *res; 2070 2071 BUG_ON(!ac); 2072 BUG_ON(ac->ac_bits_given != 0); 2073 BUG_ON(ac->ac_bits_wanted != 1); 2074 BUG_ON(ac->ac_which != OCFS2_AC_USE_INODE); 2075 2076 res = kzalloc(sizeof(*res), GFP_NOFS); 2077 if (res == NULL) { 2078 ret = -ENOMEM; 2079 mlog_errno(ret); 2080 goto out; 2081 } 2082 2083 ocfs2_init_inode_ac_group(dir, parent_fe_bh, ac); 2084 2085 /* 2086 * The handle started here is for chain relink. Alternatively, 2087 * we could just disable relink for these calls. 2088 */ 2089 handle = ocfs2_start_trans(OCFS2_SB(dir->i_sb), OCFS2_SUBALLOC_ALLOC); 2090 if (IS_ERR(handle)) { 2091 ret = PTR_ERR(handle); 2092 handle = NULL; 2093 mlog_errno(ret); 2094 goto out; 2095 } 2096 2097 /* 2098 * This will instruct ocfs2_claim_suballoc_bits and 2099 * ocfs2_search_one_group to search but save actual allocation 2100 * for later. 2101 */ 2102 ac->ac_find_loc_only = 1; 2103 2104 ret = ocfs2_claim_suballoc_bits(ac, handle, 1, 1, res); 2105 if (ret < 0) { 2106 mlog_errno(ret); 2107 goto out; 2108 } 2109 2110 ac->ac_find_loc_priv = res; 2111 *fe_blkno = res->sr_blkno; 2112 ocfs2_update_inode_fsync_trans(handle, dir, 0); 2113out: 2114 if (handle) 2115 ocfs2_commit_trans(OCFS2_SB(dir->i_sb), handle); 2116 2117 if (ret) 2118 kfree(res); 2119 2120 return ret; 2121} 2122 2123int ocfs2_claim_new_inode_at_loc(handle_t *handle, 2124 struct inode *dir, 2125 struct ocfs2_alloc_context *ac, 2126 u64 *suballoc_loc, 2127 u16 *suballoc_bit, 2128 u64 di_blkno) 2129{ 2130 int ret; 2131 u16 chain; 2132 struct ocfs2_suballoc_result *res = ac->ac_find_loc_priv; 2133 struct buffer_head *bg_bh = NULL; 2134 struct ocfs2_group_desc *bg; 2135 struct ocfs2_dinode *di = (struct ocfs2_dinode *) ac->ac_bh->b_data; 2136 2137 /* 2138 * Since di_blkno is being passed back in, we check for any 2139 * inconsistencies which may have happened between 2140 * calls. These are code bugs as di_blkno is not expected to 2141 * change once returned from ocfs2_find_new_inode_loc() 2142 */ 2143 BUG_ON(res->sr_blkno != di_blkno); 2144 2145 ret = ocfs2_read_group_descriptor(ac->ac_inode, di, 2146 res->sr_bg_stable_blkno, &bg_bh); 2147 if (ret) { 2148 mlog_errno(ret); 2149 goto out; 2150 } 2151 2152 bg = (struct ocfs2_group_desc *) bg_bh->b_data; 2153 chain = le16_to_cpu(bg->bg_chain); 2154 2155 ret = ocfs2_alloc_dinode_update_counts(ac->ac_inode, handle, 2156 ac->ac_bh, res->sr_bits, 2157 chain); 2158 if (ret) { 2159 mlog_errno(ret); 2160 goto out; 2161 } 2162 2163 ret = ocfs2_block_group_set_bits(handle, 2164 ac->ac_inode, 2165 bg, 2166 bg_bh, 2167 res->sr_bit_offset, 2168 res->sr_bits); 2169 if (ret < 0) { 2170 ocfs2_rollback_alloc_dinode_counts(ac->ac_inode, 2171 ac->ac_bh, res->sr_bits, chain); 2172 mlog_errno(ret); 2173 goto out; 2174 } 2175 2176 trace_ocfs2_claim_new_inode_at_loc((unsigned long long)di_blkno, 2177 res->sr_bits); 2178 2179 atomic_inc(&OCFS2_SB(ac->ac_inode->i_sb)->alloc_stats.bg_allocs); 2180 2181 BUG_ON(res->sr_bits != 1); 2182 2183 *suballoc_loc = res->sr_bg_blkno; 2184 *suballoc_bit = res->sr_bit_offset; 2185 ac->ac_bits_given++; 2186 ocfs2_save_inode_ac_group(dir, ac); 2187 2188out: 2189 brelse(bg_bh); 2190 2191 return ret; 2192} 2193 2194int ocfs2_claim_new_inode(handle_t *handle, 2195 struct inode *dir, 2196 struct buffer_head *parent_fe_bh, 2197 struct ocfs2_alloc_context *ac, 2198 u64 *suballoc_loc, 2199 u16 *suballoc_bit, 2200 u64 *fe_blkno) 2201{ 2202 int status; 2203 struct ocfs2_suballoc_result res; 2204 2205 BUG_ON(!ac); 2206 BUG_ON(ac->ac_bits_given != 0); 2207 BUG_ON(ac->ac_bits_wanted != 1); 2208 BUG_ON(ac->ac_which != OCFS2_AC_USE_INODE); 2209 2210 ocfs2_init_inode_ac_group(dir, parent_fe_bh, ac); 2211 2212 status = ocfs2_claim_suballoc_bits(ac, 2213 handle, 2214 1, 2215 1, 2216 &res); 2217 if (status < 0) { 2218 mlog_errno(status); 2219 goto bail; 2220 } 2221 atomic_inc(&OCFS2_SB(ac->ac_inode->i_sb)->alloc_stats.bg_allocs); 2222 2223 BUG_ON(res.sr_bits != 1); 2224 2225 *suballoc_loc = res.sr_bg_blkno; 2226 *suballoc_bit = res.sr_bit_offset; 2227 *fe_blkno = res.sr_blkno; 2228 ac->ac_bits_given++; 2229 ocfs2_save_inode_ac_group(dir, ac); 2230 status = 0; 2231bail: 2232 if (status) 2233 mlog_errno(status); 2234 return status; 2235} 2236 2237/* translate a group desc. blkno and it's bitmap offset into 2238 * disk cluster offset. */ 2239static inline u32 ocfs2_desc_bitmap_to_cluster_off(struct inode *inode, 2240 u64 bg_blkno, 2241 u16 bg_bit_off) 2242{ 2243 struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); 2244 u32 cluster = 0; 2245 2246 BUG_ON(!ocfs2_is_cluster_bitmap(inode)); 2247 2248 if (bg_blkno != osb->first_cluster_group_blkno) 2249 cluster = ocfs2_blocks_to_clusters(inode->i_sb, bg_blkno); 2250 cluster += (u32) bg_bit_off; 2251 return cluster; 2252} 2253 2254/* given a cluster offset, calculate which block group it belongs to 2255 * and return that block offset. */ 2256u64 ocfs2_which_cluster_group(struct inode *inode, u32 cluster) 2257{ 2258 struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); 2259 u32 group_no; 2260 2261 BUG_ON(!ocfs2_is_cluster_bitmap(inode)); 2262 2263 group_no = cluster / osb->bitmap_cpg; 2264 if (!group_no) 2265 return osb->first_cluster_group_blkno; 2266 return ocfs2_clusters_to_blocks(inode->i_sb, 2267 group_no * osb->bitmap_cpg); 2268} 2269 2270/* given the block number of a cluster start, calculate which cluster 2271 * group and descriptor bitmap offset that corresponds to. */ 2272static inline void ocfs2_block_to_cluster_group(struct inode *inode, 2273 u64 data_blkno, 2274 u64 *bg_blkno, 2275 u16 *bg_bit_off) 2276{ 2277 struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); 2278 u32 data_cluster = ocfs2_blocks_to_clusters(osb->sb, data_blkno); 2279 2280 BUG_ON(!ocfs2_is_cluster_bitmap(inode)); 2281 2282 *bg_blkno = ocfs2_which_cluster_group(inode, 2283 data_cluster); 2284 2285 if (*bg_blkno == osb->first_cluster_group_blkno) 2286 *bg_bit_off = (u16) data_cluster; 2287 else 2288 *bg_bit_off = (u16) ocfs2_blocks_to_clusters(osb->sb, 2289 data_blkno - *bg_blkno); 2290} 2291 2292/* 2293 * min_bits - minimum contiguous chunk from this total allocation we 2294 * can handle. set to what we asked for originally for a full 2295 * contig. allocation, set to '1' to indicate we can deal with extents 2296 * of any size. 2297 */ 2298int __ocfs2_claim_clusters(handle_t *handle, 2299 struct ocfs2_alloc_context *ac, 2300 u32 min_clusters, 2301 u32 max_clusters, 2302 u32 *cluster_start, 2303 u32 *num_clusters) 2304{ 2305 int status; 2306 unsigned int bits_wanted = max_clusters; 2307 struct ocfs2_suballoc_result res = { .sr_blkno = 0, }; 2308 struct ocfs2_super *osb = OCFS2_SB(ac->ac_inode->i_sb); 2309 2310 BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted); 2311 2312 BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL 2313 && ac->ac_which != OCFS2_AC_USE_MAIN); 2314 2315 if (ac->ac_which == OCFS2_AC_USE_LOCAL) { 2316 WARN_ON(min_clusters > 1); 2317 2318 status = ocfs2_claim_local_alloc_bits(osb, 2319 handle, 2320 ac, 2321 bits_wanted, 2322 cluster_start, 2323 num_clusters); 2324 if (!status) 2325 atomic_inc(&osb->alloc_stats.local_data); 2326 } else { 2327 if (min_clusters > (osb->bitmap_cpg - 1)) { 2328 /* The only paths asking for contiguousness 2329 * should know about this already. */ 2330 mlog(ML_ERROR, "minimum allocation requested %u exceeds " 2331 "group bitmap size %u!\n", min_clusters, 2332 osb->bitmap_cpg); 2333 status = -ENOSPC; 2334 goto bail; 2335 } 2336 /* clamp the current request down to a realistic size. */ 2337 if (bits_wanted > (osb->bitmap_cpg - 1)) 2338 bits_wanted = osb->bitmap_cpg - 1; 2339 2340 status = ocfs2_claim_suballoc_bits(ac, 2341 handle, 2342 bits_wanted, 2343 min_clusters, 2344 &res); 2345 if (!status) { 2346 BUG_ON(res.sr_blkno); /* cluster alloc can't set */ 2347 *cluster_start = 2348 ocfs2_desc_bitmap_to_cluster_off(ac->ac_inode, 2349 res.sr_bg_blkno, 2350 res.sr_bit_offset); 2351 atomic_inc(&osb->alloc_stats.bitmap_data); 2352 *num_clusters = res.sr_bits; 2353 } 2354 } 2355 if (status < 0) { 2356 if (status != -ENOSPC) 2357 mlog_errno(status); 2358 goto bail; 2359 } 2360 2361 ac->ac_bits_given += *num_clusters; 2362 2363bail: 2364 if (status) 2365 mlog_errno(status); 2366 return status; 2367} 2368 2369int ocfs2_claim_clusters(handle_t *handle, 2370 struct ocfs2_alloc_context *ac, 2371 u32 min_clusters, 2372 u32 *cluster_start, 2373 u32 *num_clusters) 2374{ 2375 unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given; 2376 2377 return __ocfs2_claim_clusters(handle, ac, min_clusters, 2378 bits_wanted, cluster_start, num_clusters); 2379} 2380 2381static int ocfs2_block_group_clear_bits(handle_t *handle, 2382 struct inode *alloc_inode, 2383 struct ocfs2_group_desc *bg, 2384 struct buffer_head *group_bh, 2385 unsigned int bit_off, 2386 unsigned int num_bits, 2387 void (*undo_fn)(unsigned int bit, 2388 unsigned long *bmap)) 2389{ 2390 int status; 2391 unsigned int tmp; 2392 struct ocfs2_group_desc *undo_bg = NULL; 2393 struct journal_head *jh; 2394 2395 /* The caller got this descriptor from 2396 * ocfs2_read_group_descriptor(). Any corruption is a code bug. */ 2397 BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg)); 2398 2399 trace_ocfs2_block_group_clear_bits(bit_off, num_bits); 2400 2401 BUG_ON(undo_fn && !ocfs2_is_cluster_bitmap(alloc_inode)); 2402 status = ocfs2_journal_access_gd(handle, INODE_CACHE(alloc_inode), 2403 group_bh, 2404 undo_fn ? 2405 OCFS2_JOURNAL_ACCESS_UNDO : 2406 OCFS2_JOURNAL_ACCESS_WRITE); 2407 if (status < 0) { 2408 mlog_errno(status); 2409 goto bail; 2410 } 2411 2412 jh = bh2jh(group_bh); 2413 if (undo_fn) { 2414 spin_lock(&jh->b_state_lock); 2415 undo_bg = (struct ocfs2_group_desc *) jh->b_committed_data; 2416 BUG_ON(!undo_bg); 2417 } 2418 2419 tmp = num_bits; 2420 while(tmp--) { 2421 ocfs2_clear_bit((bit_off + tmp), 2422 (unsigned long *) bg->bg_bitmap); 2423 if (undo_fn) 2424 undo_fn(bit_off + tmp, 2425 (unsigned long *) undo_bg->bg_bitmap); 2426 } 2427 le16_add_cpu(&bg->bg_free_bits_count, num_bits); 2428 if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) { 2429 if (undo_fn) 2430 spin_unlock(&jh->b_state_lock); 2431 return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n", 2432 (unsigned long long)le64_to_cpu(bg->bg_blkno), 2433 le16_to_cpu(bg->bg_bits), 2434 le16_to_cpu(bg->bg_free_bits_count), 2435 num_bits); 2436 } 2437 2438 if (undo_fn) 2439 spin_unlock(&jh->b_state_lock); 2440 2441 ocfs2_journal_dirty(handle, group_bh); 2442bail: 2443 return status; 2444} 2445 2446/* 2447 * expects the suballoc inode to already be locked. 2448 */ 2449static int _ocfs2_free_suballoc_bits(handle_t *handle, 2450 struct inode *alloc_inode, 2451 struct buffer_head *alloc_bh, 2452 unsigned int start_bit, 2453 u64 bg_blkno, 2454 unsigned int count, 2455 void (*undo_fn)(unsigned int bit, 2456 unsigned long *bitmap)) 2457{ 2458 int status = 0; 2459 u32 tmp_used; 2460 struct ocfs2_dinode *fe = (struct ocfs2_dinode *) alloc_bh->b_data; 2461 struct ocfs2_chain_list *cl = &fe->id2.i_chain; 2462 struct buffer_head *group_bh = NULL; 2463 struct ocfs2_group_desc *group; 2464 2465 /* The alloc_bh comes from ocfs2_free_dinode() or 2466 * ocfs2_free_clusters(). The callers have all locked the 2467 * allocator and gotten alloc_bh from the lock call. This 2468 * validates the dinode buffer. Any corruption that has happened 2469 * is a code bug. */ 2470 BUG_ON(!OCFS2_IS_VALID_DINODE(fe)); 2471 BUG_ON((count + start_bit) > ocfs2_bits_per_group(cl)); 2472 2473 trace_ocfs2_free_suballoc_bits( 2474 (unsigned long long)OCFS2_I(alloc_inode)->ip_blkno, 2475 (unsigned long long)bg_blkno, 2476 start_bit, count); 2477 2478 status = ocfs2_read_group_descriptor(alloc_inode, fe, bg_blkno, 2479 &group_bh); 2480 if (status < 0) { 2481 mlog_errno(status); 2482 goto bail; 2483 } 2484 group = (struct ocfs2_group_desc *) group_bh->b_data; 2485 2486 BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits)); 2487 2488 status = ocfs2_block_group_clear_bits(handle, alloc_inode, 2489 group, group_bh, 2490 start_bit, count, undo_fn); 2491 if (status < 0) { 2492 mlog_errno(status); 2493 goto bail; 2494 } 2495 2496 status = ocfs2_journal_access_di(handle, INODE_CACHE(alloc_inode), 2497 alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); 2498 if (status < 0) { 2499 mlog_errno(status); 2500 ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh, 2501 start_bit, count); 2502 goto bail; 2503 } 2504 2505 le32_add_cpu(&cl->cl_recs[le16_to_cpu(group->bg_chain)].c_free, 2506 count); 2507 tmp_used = le32_to_cpu(fe->id1.bitmap1.i_used); 2508 fe->id1.bitmap1.i_used = cpu_to_le32(tmp_used - count); 2509 ocfs2_journal_dirty(handle, alloc_bh); 2510 2511bail: 2512 brelse(group_bh); 2513 return status; 2514} 2515 2516int ocfs2_free_suballoc_bits(handle_t *handle, 2517 struct inode *alloc_inode, 2518 struct buffer_head *alloc_bh, 2519 unsigned int start_bit, 2520 u64 bg_blkno, 2521 unsigned int count) 2522{ 2523 return _ocfs2_free_suballoc_bits(handle, alloc_inode, alloc_bh, 2524 start_bit, bg_blkno, count, NULL); 2525} 2526 2527int ocfs2_free_dinode(handle_t *handle, 2528 struct inode *inode_alloc_inode, 2529 struct buffer_head *inode_alloc_bh, 2530 struct ocfs2_dinode *di) 2531{ 2532 u64 blk = le64_to_cpu(di->i_blkno); 2533 u16 bit = le16_to_cpu(di->i_suballoc_bit); 2534 u64 bg_blkno = ocfs2_which_suballoc_group(blk, bit); 2535 2536 if (di->i_suballoc_loc) 2537 bg_blkno = le64_to_cpu(di->i_suballoc_loc); 2538 return ocfs2_free_suballoc_bits(handle, inode_alloc_inode, 2539 inode_alloc_bh, bit, bg_blkno, 1); 2540} 2541 2542static int _ocfs2_free_clusters(handle_t *handle, 2543 struct inode *bitmap_inode, 2544 struct buffer_head *bitmap_bh, 2545 u64 start_blk, 2546 unsigned int num_clusters, 2547 void (*undo_fn)(unsigned int bit, 2548 unsigned long *bitmap)) 2549{ 2550 int status; 2551 u16 bg_start_bit; 2552 u64 bg_blkno; 2553 2554 /* You can't ever have a contiguous set of clusters 2555 * bigger than a block group bitmap so we never have to worry 2556 * about looping on them. 2557 * This is expensive. We can safely remove once this stuff has 2558 * gotten tested really well. */ 2559 BUG_ON(start_blk != ocfs2_clusters_to_blocks(bitmap_inode->i_sb, 2560 ocfs2_blocks_to_clusters(bitmap_inode->i_sb, 2561 start_blk))); 2562 2563 2564 ocfs2_block_to_cluster_group(bitmap_inode, start_blk, &bg_blkno, 2565 &bg_start_bit); 2566 2567 trace_ocfs2_free_clusters((unsigned long long)bg_blkno, 2568 (unsigned long long)start_blk, 2569 bg_start_bit, num_clusters); 2570 2571 status = _ocfs2_free_suballoc_bits(handle, bitmap_inode, bitmap_bh, 2572 bg_start_bit, bg_blkno, 2573 num_clusters, undo_fn); 2574 if (status < 0) { 2575 mlog_errno(status); 2576 goto out; 2577 } 2578 2579 ocfs2_local_alloc_seen_free_bits(OCFS2_SB(bitmap_inode->i_sb), 2580 num_clusters); 2581 2582out: 2583 return status; 2584} 2585 2586int ocfs2_free_clusters(handle_t *handle, 2587 struct inode *bitmap_inode, 2588 struct buffer_head *bitmap_bh, 2589 u64 start_blk, 2590 unsigned int num_clusters) 2591{ 2592 return _ocfs2_free_clusters(handle, bitmap_inode, bitmap_bh, 2593 start_blk, num_clusters, 2594 _ocfs2_set_bit); 2595} 2596 2597/* 2598 * Give never-used clusters back to the global bitmap. We don't need 2599 * to protect these bits in the undo buffer. 2600 */ 2601int ocfs2_release_clusters(handle_t *handle, 2602 struct inode *bitmap_inode, 2603 struct buffer_head *bitmap_bh, 2604 u64 start_blk, 2605 unsigned int num_clusters) 2606{ 2607 return _ocfs2_free_clusters(handle, bitmap_inode, bitmap_bh, 2608 start_blk, num_clusters, 2609 _ocfs2_clear_bit); 2610} 2611 2612/* 2613 * For a given allocation, determine which allocators will need to be 2614 * accessed, and lock them, reserving the appropriate number of bits. 2615 * 2616 * Sparse file systems call this from ocfs2_write_begin_nolock() 2617 * and ocfs2_allocate_unwritten_extents(). 2618 * 2619 * File systems which don't support holes call this from 2620 * ocfs2_extend_allocation(). 2621 */ 2622int ocfs2_lock_allocators(struct inode *inode, 2623 struct ocfs2_extent_tree *et, 2624 u32 clusters_to_add, u32 extents_to_split, 2625 struct ocfs2_alloc_context **data_ac, 2626 struct ocfs2_alloc_context **meta_ac) 2627{ 2628 int ret = 0, num_free_extents; 2629 unsigned int max_recs_needed = clusters_to_add + 2 * extents_to_split; 2630 struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); 2631 2632 *meta_ac = NULL; 2633 if (data_ac) 2634 *data_ac = NULL; 2635 2636 BUG_ON(clusters_to_add != 0 && data_ac == NULL); 2637 2638 num_free_extents = ocfs2_num_free_extents(et); 2639 if (num_free_extents < 0) { 2640 ret = num_free_extents; 2641 mlog_errno(ret); 2642 goto out; 2643 } 2644 2645 /* 2646 * Sparse allocation file systems need to be more conservative 2647 * with reserving room for expansion - the actual allocation 2648 * happens while we've got a journal handle open so re-taking 2649 * a cluster lock (because we ran out of room for another 2650 * extent) will violate ordering rules. 2651 * 2652 * Most of the time we'll only be seeing this 1 cluster at a time 2653 * anyway. 2654 * 2655 * Always lock for any unwritten extents - we might want to 2656 * add blocks during a split. 2657 */ 2658 if (!num_free_extents || 2659 (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed)) { 2660 ret = ocfs2_reserve_new_metadata(osb, et->et_root_el, meta_ac); 2661 if (ret < 0) { 2662 if (ret != -ENOSPC) 2663 mlog_errno(ret); 2664 goto out; 2665 } 2666 } 2667 2668 if (clusters_to_add == 0) 2669 goto out; 2670 2671 ret = ocfs2_reserve_clusters(osb, clusters_to_add, data_ac); 2672 if (ret < 0) { 2673 if (ret != -ENOSPC) 2674 mlog_errno(ret); 2675 goto out; 2676 } 2677 2678out: 2679 if (ret) { 2680 if (*meta_ac) { 2681 ocfs2_free_alloc_context(*meta_ac); 2682 *meta_ac = NULL; 2683 } 2684 2685 /* 2686 * We cannot have an error and a non null *data_ac. 2687 */ 2688 } 2689 2690 return ret; 2691} 2692 2693/* 2694 * Read the inode specified by blkno to get suballoc_slot and 2695 * suballoc_bit. 2696 */ 2697static int ocfs2_get_suballoc_slot_bit(struct ocfs2_super *osb, u64 blkno, 2698 u16 *suballoc_slot, u64 *group_blkno, 2699 u16 *suballoc_bit) 2700{ 2701 int status; 2702 struct buffer_head *inode_bh = NULL; 2703 struct ocfs2_dinode *inode_fe; 2704 2705 trace_ocfs2_get_suballoc_slot_bit((unsigned long long)blkno); 2706 2707 /* dirty read disk */ 2708 status = ocfs2_read_blocks_sync(osb, blkno, 1, &inode_bh); 2709 if (status < 0) { 2710 mlog(ML_ERROR, "read block %llu failed %d\n", 2711 (unsigned long long)blkno, status); 2712 goto bail; 2713 } 2714 2715 inode_fe = (struct ocfs2_dinode *) inode_bh->b_data; 2716 if (!OCFS2_IS_VALID_DINODE(inode_fe)) { 2717 mlog(ML_ERROR, "invalid inode %llu requested\n", 2718 (unsigned long long)blkno); 2719 status = -EINVAL; 2720 goto bail; 2721 } 2722 2723 if (le16_to_cpu(inode_fe->i_suballoc_slot) != (u16)OCFS2_INVALID_SLOT && 2724 (u32)le16_to_cpu(inode_fe->i_suballoc_slot) > osb->max_slots - 1) { 2725 mlog(ML_ERROR, "inode %llu has invalid suballoc slot %u\n", 2726 (unsigned long long)blkno, 2727 (u32)le16_to_cpu(inode_fe->i_suballoc_slot)); 2728 status = -EINVAL; 2729 goto bail; 2730 } 2731 2732 if (suballoc_slot) 2733 *suballoc_slot = le16_to_cpu(inode_fe->i_suballoc_slot); 2734 if (suballoc_bit) 2735 *suballoc_bit = le16_to_cpu(inode_fe->i_suballoc_bit); 2736 if (group_blkno) 2737 *group_blkno = le64_to_cpu(inode_fe->i_suballoc_loc); 2738 2739bail: 2740 brelse(inode_bh); 2741 2742 if (status) 2743 mlog_errno(status); 2744 return status; 2745} 2746 2747/* 2748 * test whether bit is SET in allocator bitmap or not. on success, 0 2749 * is returned and *res is 1 for SET; 0 otherwise. when fails, errno 2750 * is returned and *res is meaningless. Call this after you have 2751 * cluster locked against suballoc, or you may get a result based on 2752 * non-up2date contents 2753 */ 2754static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb, 2755 struct inode *suballoc, 2756 struct buffer_head *alloc_bh, 2757 u64 group_blkno, u64 blkno, 2758 u16 bit, int *res) 2759{ 2760 struct ocfs2_dinode *alloc_di; 2761 struct ocfs2_group_desc *group; 2762 struct buffer_head *group_bh = NULL; 2763 u64 bg_blkno; 2764 int status; 2765 2766 trace_ocfs2_test_suballoc_bit((unsigned long long)blkno, 2767 (unsigned int)bit); 2768 2769 alloc_di = (struct ocfs2_dinode *)alloc_bh->b_data; 2770 if ((bit + 1) > ocfs2_bits_per_group(&alloc_di->id2.i_chain)) { 2771 mlog(ML_ERROR, "suballoc bit %u out of range of %u\n", 2772 (unsigned int)bit, 2773 ocfs2_bits_per_group(&alloc_di->id2.i_chain)); 2774 status = -EINVAL; 2775 goto bail; 2776 } 2777 2778 bg_blkno = group_blkno ? group_blkno : 2779 ocfs2_which_suballoc_group(blkno, bit); 2780 status = ocfs2_read_group_descriptor(suballoc, alloc_di, bg_blkno, 2781 &group_bh); 2782 if (status < 0) { 2783 mlog(ML_ERROR, "read group %llu failed %d\n", 2784 (unsigned long long)bg_blkno, status); 2785 goto bail; 2786 } 2787 2788 group = (struct ocfs2_group_desc *) group_bh->b_data; 2789 *res = ocfs2_test_bit(bit, (unsigned long *)group->bg_bitmap); 2790 2791bail: 2792 brelse(group_bh); 2793 2794 if (status) 2795 mlog_errno(status); 2796 return status; 2797} 2798 2799/* 2800 * Test if the bit representing this inode (blkno) is set in the 2801 * suballocator. 2802 * 2803 * On success, 0 is returned and *res is 1 for SET; 0 otherwise. 2804 * 2805 * In the event of failure, a negative value is returned and *res is 2806 * meaningless. 2807 * 2808 * Callers must make sure to hold nfs_sync_lock to prevent 2809 * ocfs2_delete_inode() on another node from accessing the same 2810 * suballocator concurrently. 2811 */ 2812int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) 2813{ 2814 int status; 2815 u64 group_blkno = 0; 2816 u16 suballoc_bit = 0, suballoc_slot = 0; 2817 struct inode *inode_alloc_inode; 2818 struct buffer_head *alloc_bh = NULL; 2819 2820 trace_ocfs2_test_inode_bit((unsigned long long)blkno); 2821 2822 status = ocfs2_get_suballoc_slot_bit(osb, blkno, &suballoc_slot, 2823 &group_blkno, &suballoc_bit); 2824 if (status < 0) { 2825 mlog(ML_ERROR, "get alloc slot and bit failed %d\n", status); 2826 goto bail; 2827 } 2828 2829 if (suballoc_slot == (u16)OCFS2_INVALID_SLOT) 2830 inode_alloc_inode = ocfs2_get_system_file_inode(osb, 2831 GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot); 2832 else 2833 inode_alloc_inode = ocfs2_get_system_file_inode(osb, 2834 INODE_ALLOC_SYSTEM_INODE, suballoc_slot); 2835 if (!inode_alloc_inode) { 2836 /* the error code could be inaccurate, but we are not able to 2837 * get the correct one. */ 2838 status = -EINVAL; 2839 mlog(ML_ERROR, "unable to get alloc inode in slot %u\n", 2840 (u32)suballoc_slot); 2841 goto bail; 2842 } 2843 2844 inode_lock(inode_alloc_inode); 2845 status = ocfs2_inode_lock(inode_alloc_inode, &alloc_bh, 0); 2846 if (status < 0) { 2847 inode_unlock(inode_alloc_inode); 2848 iput(inode_alloc_inode); 2849 mlog(ML_ERROR, "lock on alloc inode on slot %u failed %d\n", 2850 (u32)suballoc_slot, status); 2851 goto bail; 2852 } 2853 2854 status = ocfs2_test_suballoc_bit(osb, inode_alloc_inode, alloc_bh, 2855 group_blkno, blkno, suballoc_bit, res); 2856 if (status < 0) 2857 mlog(ML_ERROR, "test suballoc bit failed %d\n", status); 2858 2859 ocfs2_inode_unlock(inode_alloc_inode, 0); 2860 inode_unlock(inode_alloc_inode); 2861 2862 iput(inode_alloc_inode); 2863 brelse(alloc_bh); 2864bail: 2865 if (status) 2866 mlog_errno(status); 2867 return status; 2868} 2869