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 * super.c 6 * 7 * load/unload driver, mount/dismount volumes 8 * 9 * Copyright (C) 2002, 2004 Oracle. All rights reserved. 10 */ 11 12#include <linux/module.h> 13#include <linux/fs.h> 14#include <linux/types.h> 15#include <linux/slab.h> 16#include <linux/highmem.h> 17#include <linux/init.h> 18#include <linux/random.h> 19#include <linux/statfs.h> 20#include <linux/moduleparam.h> 21#include <linux/blkdev.h> 22#include <linux/socket.h> 23#include <linux/inet.h> 24#include <linux/parser.h> 25#include <linux/crc32.h> 26#include <linux/debugfs.h> 27#include <linux/mount.h> 28#include <linux/seq_file.h> 29#include <linux/quotaops.h> 30#include <linux/cleancache.h> 31#include <linux/signal.h> 32 33#define CREATE_TRACE_POINTS 34#include "ocfs2_trace.h" 35 36#include <cluster/masklog.h> 37 38#include "ocfs2.h" 39 40/* this should be the only file to include a version 1 header */ 41#include "ocfs1_fs_compat.h" 42 43#include "alloc.h" 44#include "aops.h" 45#include "blockcheck.h" 46#include "dlmglue.h" 47#include "export.h" 48#include "extent_map.h" 49#include "heartbeat.h" 50#include "inode.h" 51#include "journal.h" 52#include "localalloc.h" 53#include "namei.h" 54#include "slot_map.h" 55#include "super.h" 56#include "sysfile.h" 57#include "uptodate.h" 58#include "xattr.h" 59#include "quota.h" 60#include "refcounttree.h" 61#include "suballoc.h" 62 63#include "buffer_head_io.h" 64#include "filecheck.h" 65 66static struct kmem_cache *ocfs2_inode_cachep; 67struct kmem_cache *ocfs2_dquot_cachep; 68struct kmem_cache *ocfs2_qf_chunk_cachep; 69 70static struct dentry *ocfs2_debugfs_root; 71 72MODULE_AUTHOR("Oracle"); 73MODULE_LICENSE("GPL"); 74MODULE_DESCRIPTION("OCFS2 cluster file system"); 75 76struct mount_options 77{ 78 unsigned long commit_interval; 79 unsigned long mount_opt; 80 unsigned int atime_quantum; 81 unsigned short slot; 82 int localalloc_opt; 83 unsigned int resv_level; 84 int dir_resv_level; 85 char cluster_stack[OCFS2_STACK_LABEL_LEN + 1]; 86}; 87 88static int ocfs2_parse_options(struct super_block *sb, char *options, 89 struct mount_options *mopt, 90 int is_remount); 91static int ocfs2_check_set_options(struct super_block *sb, 92 struct mount_options *options); 93static int ocfs2_show_options(struct seq_file *s, struct dentry *root); 94static void ocfs2_put_super(struct super_block *sb); 95static int ocfs2_mount_volume(struct super_block *sb); 96static int ocfs2_remount(struct super_block *sb, int *flags, char *data); 97static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err); 98static int ocfs2_initialize_mem_caches(void); 99static void ocfs2_free_mem_caches(void); 100static void ocfs2_delete_osb(struct ocfs2_super *osb); 101 102static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf); 103 104static int ocfs2_sync_fs(struct super_block *sb, int wait); 105 106static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb); 107static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb); 108static void ocfs2_release_system_inodes(struct ocfs2_super *osb); 109static int ocfs2_check_volume(struct ocfs2_super *osb); 110static int ocfs2_verify_volume(struct ocfs2_dinode *di, 111 struct buffer_head *bh, 112 u32 sectsize, 113 struct ocfs2_blockcheck_stats *stats); 114static int ocfs2_initialize_super(struct super_block *sb, 115 struct buffer_head *bh, 116 int sector_size, 117 struct ocfs2_blockcheck_stats *stats); 118static int ocfs2_get_sector(struct super_block *sb, 119 struct buffer_head **bh, 120 int block, 121 int sect_size); 122static struct inode *ocfs2_alloc_inode(struct super_block *sb); 123static void ocfs2_free_inode(struct inode *inode); 124static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend); 125static int ocfs2_enable_quotas(struct ocfs2_super *osb); 126static void ocfs2_disable_quotas(struct ocfs2_super *osb); 127 128static struct dquot **ocfs2_get_dquots(struct inode *inode) 129{ 130 return OCFS2_I(inode)->i_dquot; 131} 132 133static const struct super_operations ocfs2_sops = { 134 .statfs = ocfs2_statfs, 135 .alloc_inode = ocfs2_alloc_inode, 136 .free_inode = ocfs2_free_inode, 137 .drop_inode = ocfs2_drop_inode, 138 .evict_inode = ocfs2_evict_inode, 139 .sync_fs = ocfs2_sync_fs, 140 .put_super = ocfs2_put_super, 141 .remount_fs = ocfs2_remount, 142 .show_options = ocfs2_show_options, 143 .quota_read = ocfs2_quota_read, 144 .quota_write = ocfs2_quota_write, 145 .get_dquots = ocfs2_get_dquots, 146}; 147 148enum { 149 Opt_barrier, 150 Opt_err_panic, 151 Opt_err_ro, 152 Opt_intr, 153 Opt_nointr, 154 Opt_hb_none, 155 Opt_hb_local, 156 Opt_hb_global, 157 Opt_data_ordered, 158 Opt_data_writeback, 159 Opt_atime_quantum, 160 Opt_slot, 161 Opt_commit, 162 Opt_localalloc, 163 Opt_localflocks, 164 Opt_stack, 165 Opt_user_xattr, 166 Opt_nouser_xattr, 167 Opt_inode64, 168 Opt_acl, 169 Opt_noacl, 170 Opt_usrquota, 171 Opt_grpquota, 172 Opt_coherency_buffered, 173 Opt_coherency_full, 174 Opt_resv_level, 175 Opt_dir_resv_level, 176 Opt_journal_async_commit, 177 Opt_err_cont, 178 Opt_err, 179}; 180 181static const match_table_t tokens = { 182 {Opt_barrier, "barrier=%u"}, 183 {Opt_err_panic, "errors=panic"}, 184 {Opt_err_ro, "errors=remount-ro"}, 185 {Opt_intr, "intr"}, 186 {Opt_nointr, "nointr"}, 187 {Opt_hb_none, OCFS2_HB_NONE}, 188 {Opt_hb_local, OCFS2_HB_LOCAL}, 189 {Opt_hb_global, OCFS2_HB_GLOBAL}, 190 {Opt_data_ordered, "data=ordered"}, 191 {Opt_data_writeback, "data=writeback"}, 192 {Opt_atime_quantum, "atime_quantum=%u"}, 193 {Opt_slot, "preferred_slot=%u"}, 194 {Opt_commit, "commit=%u"}, 195 {Opt_localalloc, "localalloc=%d"}, 196 {Opt_localflocks, "localflocks"}, 197 {Opt_stack, "cluster_stack=%s"}, 198 {Opt_user_xattr, "user_xattr"}, 199 {Opt_nouser_xattr, "nouser_xattr"}, 200 {Opt_inode64, "inode64"}, 201 {Opt_acl, "acl"}, 202 {Opt_noacl, "noacl"}, 203 {Opt_usrquota, "usrquota"}, 204 {Opt_grpquota, "grpquota"}, 205 {Opt_coherency_buffered, "coherency=buffered"}, 206 {Opt_coherency_full, "coherency=full"}, 207 {Opt_resv_level, "resv_level=%u"}, 208 {Opt_dir_resv_level, "dir_resv_level=%u"}, 209 {Opt_journal_async_commit, "journal_async_commit"}, 210 {Opt_err_cont, "errors=continue"}, 211 {Opt_err, NULL} 212}; 213 214#ifdef CONFIG_DEBUG_FS 215static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) 216{ 217 struct ocfs2_cluster_connection *cconn = osb->cconn; 218 struct ocfs2_recovery_map *rm = osb->recovery_map; 219 struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan; 220 int i, out = 0; 221 unsigned long flags; 222 223 out += scnprintf(buf + out, len - out, 224 "%10s => Id: %-s Uuid: %-s Gen: 0x%X Label: %-s\n", 225 "Device", osb->dev_str, osb->uuid_str, 226 osb->fs_generation, osb->vol_label); 227 228 out += scnprintf(buf + out, len - out, 229 "%10s => State: %d Flags: 0x%lX\n", "Volume", 230 atomic_read(&osb->vol_state), osb->osb_flags); 231 232 out += scnprintf(buf + out, len - out, 233 "%10s => Block: %lu Cluster: %d\n", "Sizes", 234 osb->sb->s_blocksize, osb->s_clustersize); 235 236 out += scnprintf(buf + out, len - out, 237 "%10s => Compat: 0x%X Incompat: 0x%X " 238 "ROcompat: 0x%X\n", 239 "Features", osb->s_feature_compat, 240 osb->s_feature_incompat, osb->s_feature_ro_compat); 241 242 out += scnprintf(buf + out, len - out, 243 "%10s => Opts: 0x%lX AtimeQuanta: %u\n", "Mount", 244 osb->s_mount_opt, osb->s_atime_quantum); 245 246 if (cconn) { 247 out += scnprintf(buf + out, len - out, 248 "%10s => Stack: %s Name: %*s " 249 "Version: %d.%d\n", "Cluster", 250 (*osb->osb_cluster_stack == '\0' ? 251 "o2cb" : osb->osb_cluster_stack), 252 cconn->cc_namelen, cconn->cc_name, 253 cconn->cc_version.pv_major, 254 cconn->cc_version.pv_minor); 255 } 256 257 spin_lock_irqsave(&osb->dc_task_lock, flags); 258 out += scnprintf(buf + out, len - out, 259 "%10s => Pid: %d Count: %lu WakeSeq: %lu " 260 "WorkSeq: %lu\n", "DownCnvt", 261 (osb->dc_task ? task_pid_nr(osb->dc_task) : -1), 262 osb->blocked_lock_count, osb->dc_wake_sequence, 263 osb->dc_work_sequence); 264 spin_unlock_irqrestore(&osb->dc_task_lock, flags); 265 266 spin_lock(&osb->osb_lock); 267 out += scnprintf(buf + out, len - out, "%10s => Pid: %d Nodes:", 268 "Recovery", 269 (osb->recovery_thread_task ? 270 task_pid_nr(osb->recovery_thread_task) : -1)); 271 if (rm->rm_used == 0) 272 out += scnprintf(buf + out, len - out, " None\n"); 273 else { 274 for (i = 0; i < rm->rm_used; i++) 275 out += scnprintf(buf + out, len - out, " %d", 276 rm->rm_entries[i]); 277 out += scnprintf(buf + out, len - out, "\n"); 278 } 279 spin_unlock(&osb->osb_lock); 280 281 out += scnprintf(buf + out, len - out, 282 "%10s => Pid: %d Interval: %lu\n", "Commit", 283 (osb->commit_task ? task_pid_nr(osb->commit_task) : -1), 284 osb->osb_commit_interval); 285 286 out += scnprintf(buf + out, len - out, 287 "%10s => State: %d TxnId: %lu NumTxns: %d\n", 288 "Journal", osb->journal->j_state, 289 osb->journal->j_trans_id, 290 atomic_read(&osb->journal->j_num_trans)); 291 292 out += scnprintf(buf + out, len - out, 293 "%10s => GlobalAllocs: %d LocalAllocs: %d " 294 "SubAllocs: %d LAWinMoves: %d SAExtends: %d\n", 295 "Stats", 296 atomic_read(&osb->alloc_stats.bitmap_data), 297 atomic_read(&osb->alloc_stats.local_data), 298 atomic_read(&osb->alloc_stats.bg_allocs), 299 atomic_read(&osb->alloc_stats.moves), 300 atomic_read(&osb->alloc_stats.bg_extends)); 301 302 out += scnprintf(buf + out, len - out, 303 "%10s => State: %u Descriptor: %llu Size: %u bits " 304 "Default: %u bits\n", 305 "LocalAlloc", osb->local_alloc_state, 306 (unsigned long long)osb->la_last_gd, 307 osb->local_alloc_bits, osb->local_alloc_default_bits); 308 309 spin_lock(&osb->osb_lock); 310 out += scnprintf(buf + out, len - out, 311 "%10s => InodeSlot: %d StolenInodes: %d, " 312 "MetaSlot: %d StolenMeta: %d\n", "Steal", 313 osb->s_inode_steal_slot, 314 atomic_read(&osb->s_num_inodes_stolen), 315 osb->s_meta_steal_slot, 316 atomic_read(&osb->s_num_meta_stolen)); 317 spin_unlock(&osb->osb_lock); 318 319 out += scnprintf(buf + out, len - out, "OrphanScan => "); 320 out += scnprintf(buf + out, len - out, "Local: %u Global: %u ", 321 os->os_count, os->os_seqno); 322 out += scnprintf(buf + out, len - out, " Last Scan: "); 323 if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE) 324 out += scnprintf(buf + out, len - out, "Disabled\n"); 325 else 326 out += scnprintf(buf + out, len - out, "%lu seconds ago\n", 327 (unsigned long)(ktime_get_seconds() - os->os_scantime)); 328 329 out += scnprintf(buf + out, len - out, "%10s => %3s %10s\n", 330 "Slots", "Num", "RecoGen"); 331 for (i = 0; i < osb->max_slots; ++i) { 332 out += scnprintf(buf + out, len - out, 333 "%10s %c %3d %10d\n", 334 " ", 335 (i == osb->slot_num ? '*' : ' '), 336 i, osb->slot_recovery_generations[i]); 337 } 338 339 return out; 340} 341 342static int ocfs2_osb_debug_open(struct inode *inode, struct file *file) 343{ 344 struct ocfs2_super *osb = inode->i_private; 345 char *buf = NULL; 346 347 buf = kmalloc(PAGE_SIZE, GFP_KERNEL); 348 if (!buf) 349 goto bail; 350 351 i_size_write(inode, ocfs2_osb_dump(osb, buf, PAGE_SIZE)); 352 353 file->private_data = buf; 354 355 return 0; 356bail: 357 return -ENOMEM; 358} 359 360static int ocfs2_debug_release(struct inode *inode, struct file *file) 361{ 362 kfree(file->private_data); 363 return 0; 364} 365 366static ssize_t ocfs2_debug_read(struct file *file, char __user *buf, 367 size_t nbytes, loff_t *ppos) 368{ 369 return simple_read_from_buffer(buf, nbytes, ppos, file->private_data, 370 i_size_read(file->f_mapping->host)); 371} 372#else 373static int ocfs2_osb_debug_open(struct inode *inode, struct file *file) 374{ 375 return 0; 376} 377static int ocfs2_debug_release(struct inode *inode, struct file *file) 378{ 379 return 0; 380} 381static ssize_t ocfs2_debug_read(struct file *file, char __user *buf, 382 size_t nbytes, loff_t *ppos) 383{ 384 return 0; 385} 386#endif /* CONFIG_DEBUG_FS */ 387 388static const struct file_operations ocfs2_osb_debug_fops = { 389 .open = ocfs2_osb_debug_open, 390 .release = ocfs2_debug_release, 391 .read = ocfs2_debug_read, 392 .llseek = generic_file_llseek, 393}; 394 395static int ocfs2_sync_fs(struct super_block *sb, int wait) 396{ 397 int status; 398 tid_t target; 399 struct ocfs2_super *osb = OCFS2_SB(sb); 400 401 if (ocfs2_is_hard_readonly(osb)) 402 return -EROFS; 403 404 if (wait) { 405 status = ocfs2_flush_truncate_log(osb); 406 if (status < 0) 407 mlog_errno(status); 408 } else { 409 ocfs2_schedule_truncate_log_flush(osb, 0); 410 } 411 412 if (jbd2_journal_start_commit(osb->journal->j_journal, 413 &target)) { 414 if (wait) 415 jbd2_log_wait_commit(osb->journal->j_journal, 416 target); 417 } 418 return 0; 419} 420 421static int ocfs2_need_system_inode(struct ocfs2_super *osb, int ino) 422{ 423 if (!OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA) 424 && (ino == USER_QUOTA_SYSTEM_INODE 425 || ino == LOCAL_USER_QUOTA_SYSTEM_INODE)) 426 return 0; 427 if (!OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, OCFS2_FEATURE_RO_COMPAT_GRPQUOTA) 428 && (ino == GROUP_QUOTA_SYSTEM_INODE 429 || ino == LOCAL_GROUP_QUOTA_SYSTEM_INODE)) 430 return 0; 431 return 1; 432} 433 434static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb) 435{ 436 struct inode *new = NULL; 437 int status = 0; 438 int i; 439 440 new = ocfs2_iget(osb, osb->root_blkno, OCFS2_FI_FLAG_SYSFILE, 0); 441 if (IS_ERR(new)) { 442 status = PTR_ERR(new); 443 mlog_errno(status); 444 goto bail; 445 } 446 osb->root_inode = new; 447 448 new = ocfs2_iget(osb, osb->system_dir_blkno, OCFS2_FI_FLAG_SYSFILE, 0); 449 if (IS_ERR(new)) { 450 status = PTR_ERR(new); 451 mlog_errno(status); 452 goto bail; 453 } 454 osb->sys_root_inode = new; 455 456 for (i = OCFS2_FIRST_ONLINE_SYSTEM_INODE; 457 i <= OCFS2_LAST_GLOBAL_SYSTEM_INODE; i++) { 458 if (!ocfs2_need_system_inode(osb, i)) 459 continue; 460 new = ocfs2_get_system_file_inode(osb, i, osb->slot_num); 461 if (!new) { 462 ocfs2_release_system_inodes(osb); 463 status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL; 464 mlog_errno(status); 465 mlog(ML_ERROR, "Unable to load system inode %d, " 466 "possibly corrupt fs?", i); 467 goto bail; 468 } 469 // the array now has one ref, so drop this one 470 iput(new); 471 } 472 473bail: 474 if (status) 475 mlog_errno(status); 476 return status; 477} 478 479static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb) 480{ 481 struct inode *new = NULL; 482 int status = 0; 483 int i; 484 485 for (i = OCFS2_LAST_GLOBAL_SYSTEM_INODE + 1; 486 i < NUM_SYSTEM_INODES; 487 i++) { 488 if (!ocfs2_need_system_inode(osb, i)) 489 continue; 490 new = ocfs2_get_system_file_inode(osb, i, osb->slot_num); 491 if (!new) { 492 ocfs2_release_system_inodes(osb); 493 status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL; 494 mlog(ML_ERROR, "status=%d, sysfile=%d, slot=%d\n", 495 status, i, osb->slot_num); 496 goto bail; 497 } 498 /* the array now has one ref, so drop this one */ 499 iput(new); 500 } 501 502bail: 503 if (status) 504 mlog_errno(status); 505 return status; 506} 507 508static void ocfs2_release_system_inodes(struct ocfs2_super *osb) 509{ 510 int i; 511 struct inode *inode; 512 513 for (i = 0; i < NUM_GLOBAL_SYSTEM_INODES; i++) { 514 inode = osb->global_system_inodes[i]; 515 if (inode) { 516 iput(inode); 517 osb->global_system_inodes[i] = NULL; 518 } 519 } 520 521 inode = osb->sys_root_inode; 522 if (inode) { 523 iput(inode); 524 osb->sys_root_inode = NULL; 525 } 526 527 inode = osb->root_inode; 528 if (inode) { 529 iput(inode); 530 osb->root_inode = NULL; 531 } 532 533 if (!osb->local_system_inodes) 534 return; 535 536 for (i = 0; i < NUM_LOCAL_SYSTEM_INODES * osb->max_slots; i++) { 537 if (osb->local_system_inodes[i]) { 538 iput(osb->local_system_inodes[i]); 539 osb->local_system_inodes[i] = NULL; 540 } 541 } 542 543 kfree(osb->local_system_inodes); 544 osb->local_system_inodes = NULL; 545} 546 547/* We're allocating fs objects, use GFP_NOFS */ 548static struct inode *ocfs2_alloc_inode(struct super_block *sb) 549{ 550 struct ocfs2_inode_info *oi; 551 552 oi = kmem_cache_alloc(ocfs2_inode_cachep, GFP_NOFS); 553 if (!oi) 554 return NULL; 555 556 oi->i_sync_tid = 0; 557 oi->i_datasync_tid = 0; 558 memset(&oi->i_dquot, 0, sizeof(oi->i_dquot)); 559 560 jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode); 561 return &oi->vfs_inode; 562} 563 564static void ocfs2_free_inode(struct inode *inode) 565{ 566 kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode)); 567} 568 569static unsigned long long ocfs2_max_file_offset(unsigned int bbits, 570 unsigned int cbits) 571{ 572 unsigned int bytes = 1 << cbits; 573 unsigned int trim = bytes; 574 unsigned int bitshift = 32; 575 576 /* 577 * i_size and all block offsets in ocfs2 are always 64 bits 578 * wide. i_clusters is 32 bits, in cluster-sized units. So on 579 * 64 bit platforms, cluster size will be the limiting factor. 580 */ 581 582#if BITS_PER_LONG == 32 583 BUILD_BUG_ON(sizeof(sector_t) != 8); 584 /* 585 * We might be limited by page cache size. 586 */ 587 if (bytes > PAGE_SIZE) { 588 bytes = PAGE_SIZE; 589 trim = 1; 590 /* 591 * Shift by 31 here so that we don't get larger than 592 * MAX_LFS_FILESIZE 593 */ 594 bitshift = 31; 595 } 596#endif 597 598 /* 599 * Trim by a whole cluster when we can actually approach the 600 * on-disk limits. Otherwise we can overflow i_clusters when 601 * an extent start is at the max offset. 602 */ 603 return (((unsigned long long)bytes) << bitshift) - trim; 604} 605 606static int ocfs2_remount(struct super_block *sb, int *flags, char *data) 607{ 608 int incompat_features; 609 int ret = 0; 610 struct mount_options parsed_options; 611 struct ocfs2_super *osb = OCFS2_SB(sb); 612 u32 tmp; 613 614 sync_filesystem(sb); 615 616 if (!ocfs2_parse_options(sb, data, &parsed_options, 1) || 617 !ocfs2_check_set_options(sb, &parsed_options)) { 618 ret = -EINVAL; 619 goto out; 620 } 621 622 tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL | 623 OCFS2_MOUNT_HB_NONE; 624 if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) { 625 ret = -EINVAL; 626 mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n"); 627 goto out; 628 } 629 630 if ((osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) != 631 (parsed_options.mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) { 632 ret = -EINVAL; 633 mlog(ML_ERROR, "Cannot change data mode on remount\n"); 634 goto out; 635 } 636 637 /* Probably don't want this on remount; it might 638 * mess with other nodes */ 639 if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) && 640 (parsed_options.mount_opt & OCFS2_MOUNT_INODE64)) { 641 ret = -EINVAL; 642 mlog(ML_ERROR, "Cannot enable inode64 on remount\n"); 643 goto out; 644 } 645 646 /* We're going to/from readonly mode. */ 647 if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { 648 /* Disable quota accounting before remounting RO */ 649 if (*flags & SB_RDONLY) { 650 ret = ocfs2_susp_quotas(osb, 0); 651 if (ret < 0) 652 goto out; 653 } 654 /* Lock here so the check of HARD_RO and the potential 655 * setting of SOFT_RO is atomic. */ 656 spin_lock(&osb->osb_lock); 657 if (osb->osb_flags & OCFS2_OSB_HARD_RO) { 658 mlog(ML_ERROR, "Remount on readonly device is forbidden.\n"); 659 ret = -EROFS; 660 goto unlock_osb; 661 } 662 663 if (*flags & SB_RDONLY) { 664 sb->s_flags |= SB_RDONLY; 665 osb->osb_flags |= OCFS2_OSB_SOFT_RO; 666 } else { 667 if (osb->osb_flags & OCFS2_OSB_ERROR_FS) { 668 mlog(ML_ERROR, "Cannot remount RDWR " 669 "filesystem due to previous errors.\n"); 670 ret = -EROFS; 671 goto unlock_osb; 672 } 673 incompat_features = OCFS2_HAS_RO_COMPAT_FEATURE(sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP); 674 if (incompat_features) { 675 mlog(ML_ERROR, "Cannot remount RDWR because " 676 "of unsupported optional features " 677 "(%x).\n", incompat_features); 678 ret = -EINVAL; 679 goto unlock_osb; 680 } 681 sb->s_flags &= ~SB_RDONLY; 682 osb->osb_flags &= ~OCFS2_OSB_SOFT_RO; 683 } 684 trace_ocfs2_remount(sb->s_flags, osb->osb_flags, *flags); 685unlock_osb: 686 spin_unlock(&osb->osb_lock); 687 /* Enable quota accounting after remounting RW */ 688 if (!ret && !(*flags & SB_RDONLY)) { 689 if (sb_any_quota_suspended(sb)) 690 ret = ocfs2_susp_quotas(osb, 1); 691 else 692 ret = ocfs2_enable_quotas(osb); 693 if (ret < 0) { 694 /* Return back changes... */ 695 spin_lock(&osb->osb_lock); 696 sb->s_flags |= SB_RDONLY; 697 osb->osb_flags |= OCFS2_OSB_SOFT_RO; 698 spin_unlock(&osb->osb_lock); 699 goto out; 700 } 701 } 702 } 703 704 if (!ret) { 705 /* Only save off the new mount options in case of a successful 706 * remount. */ 707 osb->s_mount_opt = parsed_options.mount_opt; 708 osb->s_atime_quantum = parsed_options.atime_quantum; 709 osb->preferred_slot = parsed_options.slot; 710 if (parsed_options.commit_interval) 711 osb->osb_commit_interval = parsed_options.commit_interval; 712 713 if (!ocfs2_is_hard_readonly(osb)) 714 ocfs2_set_journal_params(osb); 715 716 sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | 717 ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? 718 SB_POSIXACL : 0); 719 } 720out: 721 return ret; 722} 723 724static int ocfs2_sb_probe(struct super_block *sb, 725 struct buffer_head **bh, 726 int *sector_size, 727 struct ocfs2_blockcheck_stats *stats) 728{ 729 int status, tmpstat; 730 struct ocfs1_vol_disk_hdr *hdr; 731 struct ocfs2_dinode *di; 732 int blksize; 733 734 *bh = NULL; 735 736 /* may be > 512 */ 737 *sector_size = bdev_logical_block_size(sb->s_bdev); 738 if (*sector_size > OCFS2_MAX_BLOCKSIZE) { 739 mlog(ML_ERROR, "Hardware sector size too large: %d (max=%d)\n", 740 *sector_size, OCFS2_MAX_BLOCKSIZE); 741 status = -EINVAL; 742 goto bail; 743 } 744 745 /* Can this really happen? */ 746 if (*sector_size < OCFS2_MIN_BLOCKSIZE) 747 *sector_size = OCFS2_MIN_BLOCKSIZE; 748 749 /* check block zero for old format */ 750 status = ocfs2_get_sector(sb, bh, 0, *sector_size); 751 if (status < 0) { 752 mlog_errno(status); 753 goto bail; 754 } 755 hdr = (struct ocfs1_vol_disk_hdr *) (*bh)->b_data; 756 if (hdr->major_version == OCFS1_MAJOR_VERSION) { 757 mlog(ML_ERROR, "incompatible version: %u.%u\n", 758 hdr->major_version, hdr->minor_version); 759 status = -EINVAL; 760 } 761 if (memcmp(hdr->signature, OCFS1_VOLUME_SIGNATURE, 762 strlen(OCFS1_VOLUME_SIGNATURE)) == 0) { 763 mlog(ML_ERROR, "incompatible volume signature: %8s\n", 764 hdr->signature); 765 status = -EINVAL; 766 } 767 brelse(*bh); 768 *bh = NULL; 769 if (status < 0) { 770 mlog(ML_ERROR, "This is an ocfs v1 filesystem which must be " 771 "upgraded before mounting with ocfs v2\n"); 772 goto bail; 773 } 774 775 /* 776 * Now check at magic offset for 512, 1024, 2048, 4096 777 * blocksizes. 4096 is the maximum blocksize because it is 778 * the minimum clustersize. 779 */ 780 status = -EINVAL; 781 for (blksize = *sector_size; 782 blksize <= OCFS2_MAX_BLOCKSIZE; 783 blksize <<= 1) { 784 tmpstat = ocfs2_get_sector(sb, bh, 785 OCFS2_SUPER_BLOCK_BLKNO, 786 blksize); 787 if (tmpstat < 0) { 788 status = tmpstat; 789 mlog_errno(status); 790 break; 791 } 792 di = (struct ocfs2_dinode *) (*bh)->b_data; 793 memset(stats, 0, sizeof(struct ocfs2_blockcheck_stats)); 794 spin_lock_init(&stats->b_lock); 795 tmpstat = ocfs2_verify_volume(di, *bh, blksize, stats); 796 if (tmpstat < 0) { 797 brelse(*bh); 798 *bh = NULL; 799 } 800 if (tmpstat != -EAGAIN) { 801 status = tmpstat; 802 break; 803 } 804 } 805 806bail: 807 return status; 808} 809 810static int ocfs2_verify_heartbeat(struct ocfs2_super *osb) 811{ 812 u32 hb_enabled = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL; 813 814 if (osb->s_mount_opt & hb_enabled) { 815 if (ocfs2_mount_local(osb)) { 816 mlog(ML_ERROR, "Cannot heartbeat on a locally " 817 "mounted device.\n"); 818 return -EINVAL; 819 } 820 if (ocfs2_userspace_stack(osb)) { 821 mlog(ML_ERROR, "Userspace stack expected, but " 822 "o2cb heartbeat arguments passed to mount\n"); 823 return -EINVAL; 824 } 825 if (((osb->s_mount_opt & OCFS2_MOUNT_HB_GLOBAL) && 826 !ocfs2_cluster_o2cb_global_heartbeat(osb)) || 827 ((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) && 828 ocfs2_cluster_o2cb_global_heartbeat(osb))) { 829 mlog(ML_ERROR, "Mismatching o2cb heartbeat modes\n"); 830 return -EINVAL; 831 } 832 } 833 834 if (!(osb->s_mount_opt & hb_enabled)) { 835 if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb) && 836 !ocfs2_userspace_stack(osb)) { 837 mlog(ML_ERROR, "Heartbeat has to be started to mount " 838 "a read-write clustered device.\n"); 839 return -EINVAL; 840 } 841 } 842 843 return 0; 844} 845 846/* 847 * If we're using a userspace stack, mount should have passed 848 * a name that matches the disk. If not, mount should not 849 * have passed a stack. 850 */ 851static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb, 852 struct mount_options *mopt) 853{ 854 if (!ocfs2_userspace_stack(osb) && mopt->cluster_stack[0]) { 855 mlog(ML_ERROR, 856 "cluster stack passed to mount, but this filesystem " 857 "does not support it\n"); 858 return -EINVAL; 859 } 860 861 if (ocfs2_userspace_stack(osb) && 862 strncmp(osb->osb_cluster_stack, mopt->cluster_stack, 863 OCFS2_STACK_LABEL_LEN)) { 864 mlog(ML_ERROR, 865 "cluster stack passed to mount (\"%s\") does not " 866 "match the filesystem (\"%s\")\n", 867 mopt->cluster_stack, 868 osb->osb_cluster_stack); 869 return -EINVAL; 870 } 871 872 return 0; 873} 874 875static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend) 876{ 877 int type; 878 struct super_block *sb = osb->sb; 879 unsigned int feature[OCFS2_MAXQUOTAS] = { 880 OCFS2_FEATURE_RO_COMPAT_USRQUOTA, 881 OCFS2_FEATURE_RO_COMPAT_GRPQUOTA}; 882 int status = 0; 883 884 for (type = 0; type < OCFS2_MAXQUOTAS; type++) { 885 if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type])) 886 continue; 887 if (unsuspend) 888 status = dquot_resume(sb, type); 889 else { 890 struct ocfs2_mem_dqinfo *oinfo; 891 892 /* Cancel periodic syncing before suspending */ 893 oinfo = sb_dqinfo(sb, type)->dqi_priv; 894 cancel_delayed_work_sync(&oinfo->dqi_sync_work); 895 status = dquot_suspend(sb, type); 896 } 897 if (status < 0) 898 break; 899 } 900 if (status < 0) 901 mlog(ML_ERROR, "Failed to suspend/unsuspend quotas on " 902 "remount (error = %d).\n", status); 903 return status; 904} 905 906static int ocfs2_enable_quotas(struct ocfs2_super *osb) 907{ 908 struct inode *inode[OCFS2_MAXQUOTAS] = { NULL, NULL }; 909 struct super_block *sb = osb->sb; 910 unsigned int feature[OCFS2_MAXQUOTAS] = { 911 OCFS2_FEATURE_RO_COMPAT_USRQUOTA, 912 OCFS2_FEATURE_RO_COMPAT_GRPQUOTA}; 913 unsigned int ino[OCFS2_MAXQUOTAS] = { 914 LOCAL_USER_QUOTA_SYSTEM_INODE, 915 LOCAL_GROUP_QUOTA_SYSTEM_INODE }; 916 int status; 917 int type; 918 919 sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NEGATIVE_USAGE; 920 for (type = 0; type < OCFS2_MAXQUOTAS; type++) { 921 if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type])) 922 continue; 923 inode[type] = ocfs2_get_system_file_inode(osb, ino[type], 924 osb->slot_num); 925 if (!inode[type]) { 926 status = -ENOENT; 927 goto out_quota_off; 928 } 929 status = dquot_load_quota_inode(inode[type], type, QFMT_OCFS2, 930 DQUOT_USAGE_ENABLED); 931 if (status < 0) 932 goto out_quota_off; 933 } 934 935 for (type = 0; type < OCFS2_MAXQUOTAS; type++) 936 iput(inode[type]); 937 return 0; 938out_quota_off: 939 ocfs2_disable_quotas(osb); 940 for (type = 0; type < OCFS2_MAXQUOTAS; type++) 941 iput(inode[type]); 942 mlog_errno(status); 943 return status; 944} 945 946static void ocfs2_disable_quotas(struct ocfs2_super *osb) 947{ 948 int type; 949 struct inode *inode; 950 struct super_block *sb = osb->sb; 951 struct ocfs2_mem_dqinfo *oinfo; 952 953 /* We mostly ignore errors in this function because there's not much 954 * we can do when we see them */ 955 for (type = 0; type < OCFS2_MAXQUOTAS; type++) { 956 if (!sb_has_quota_loaded(sb, type)) 957 continue; 958 if (!sb_has_quota_suspended(sb, type)) { 959 oinfo = sb_dqinfo(sb, type)->dqi_priv; 960 cancel_delayed_work_sync(&oinfo->dqi_sync_work); 961 } 962 inode = igrab(sb->s_dquot.files[type]); 963 /* Turn off quotas. This will remove all dquot structures from 964 * memory and so they will be automatically synced to global 965 * quota files */ 966 dquot_disable(sb, type, DQUOT_USAGE_ENABLED | 967 DQUOT_LIMITS_ENABLED); 968 if (!inode) 969 continue; 970 iput(inode); 971 } 972} 973 974static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) 975{ 976 struct dentry *root; 977 int status, sector_size; 978 struct mount_options parsed_options; 979 struct inode *inode = NULL; 980 struct ocfs2_super *osb = NULL; 981 struct buffer_head *bh = NULL; 982 char nodestr[12]; 983 struct ocfs2_blockcheck_stats stats; 984 985 trace_ocfs2_fill_super(sb, data, silent); 986 987 if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) { 988 status = -EINVAL; 989 goto out; 990 } 991 992 /* probe for superblock */ 993 status = ocfs2_sb_probe(sb, &bh, §or_size, &stats); 994 if (status < 0) { 995 mlog(ML_ERROR, "superblock probe failed!\n"); 996 goto out; 997 } 998 999 status = ocfs2_initialize_super(sb, bh, sector_size, &stats); 1000 brelse(bh); 1001 bh = NULL; 1002 if (status < 0) 1003 goto out; 1004 1005 osb = OCFS2_SB(sb); 1006 1007 if (!ocfs2_check_set_options(sb, &parsed_options)) { 1008 status = -EINVAL; 1009 goto out_super; 1010 } 1011 osb->s_mount_opt = parsed_options.mount_opt; 1012 osb->s_atime_quantum = parsed_options.atime_quantum; 1013 osb->preferred_slot = parsed_options.slot; 1014 osb->osb_commit_interval = parsed_options.commit_interval; 1015 1016 ocfs2_la_set_sizes(osb, parsed_options.localalloc_opt); 1017 osb->osb_resv_level = parsed_options.resv_level; 1018 osb->osb_dir_resv_level = parsed_options.resv_level; 1019 if (parsed_options.dir_resv_level == -1) 1020 osb->osb_dir_resv_level = parsed_options.resv_level; 1021 else 1022 osb->osb_dir_resv_level = parsed_options.dir_resv_level; 1023 1024 status = ocfs2_verify_userspace_stack(osb, &parsed_options); 1025 if (status) 1026 goto out_super; 1027 1028 sb->s_magic = OCFS2_SUPER_MAGIC; 1029 1030 sb->s_flags = (sb->s_flags & ~(SB_POSIXACL | SB_NOSEC)) | 1031 ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0); 1032 1033 /* Hard readonly mode only if: bdev_read_only, SB_RDONLY, 1034 * heartbeat=none */ 1035 if (bdev_read_only(sb->s_bdev)) { 1036 if (!sb_rdonly(sb)) { 1037 status = -EACCES; 1038 mlog(ML_ERROR, "Readonly device detected but readonly " 1039 "mount was not specified.\n"); 1040 goto out_super; 1041 } 1042 1043 /* You should not be able to start a local heartbeat 1044 * on a readonly device. */ 1045 if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) { 1046 status = -EROFS; 1047 mlog(ML_ERROR, "Local heartbeat specified on readonly " 1048 "device.\n"); 1049 goto out_super; 1050 } 1051 1052 status = ocfs2_check_journals_nolocks(osb); 1053 if (status < 0) { 1054 if (status == -EROFS) 1055 mlog(ML_ERROR, "Recovery required on readonly " 1056 "file system, but write access is " 1057 "unavailable.\n"); 1058 goto out_super; 1059 } 1060 1061 ocfs2_set_ro_flag(osb, 1); 1062 1063 printk(KERN_NOTICE "ocfs2: Readonly device (%s) detected. " 1064 "Cluster services will not be used for this mount. " 1065 "Recovery will be skipped.\n", osb->dev_str); 1066 } 1067 1068 if (!ocfs2_is_hard_readonly(osb)) { 1069 if (sb_rdonly(sb)) 1070 ocfs2_set_ro_flag(osb, 0); 1071 } 1072 1073 status = ocfs2_verify_heartbeat(osb); 1074 if (status < 0) 1075 goto out_super; 1076 1077 osb->osb_debug_root = debugfs_create_dir(osb->uuid_str, 1078 ocfs2_debugfs_root); 1079 1080 debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root, 1081 osb, &ocfs2_osb_debug_fops); 1082 1083 if (ocfs2_meta_ecc(osb)) 1084 ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats, 1085 osb->osb_debug_root); 1086 1087 status = ocfs2_mount_volume(sb); 1088 if (status < 0) 1089 goto out_debugfs; 1090 1091 if (osb->root_inode) 1092 inode = igrab(osb->root_inode); 1093 1094 if (!inode) { 1095 status = -EIO; 1096 goto out_dismount; 1097 } 1098 1099 osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL, 1100 &ocfs2_kset->kobj); 1101 if (!osb->osb_dev_kset) { 1102 status = -ENOMEM; 1103 mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id); 1104 goto out_dismount; 1105 } 1106 1107 /* Create filecheck sysfs related directories/files at 1108 * /sys/fs/ocfs2/<devname>/filecheck */ 1109 if (ocfs2_filecheck_create_sysfs(osb)) { 1110 status = -ENOMEM; 1111 mlog(ML_ERROR, "Unable to create filecheck sysfs directory at " 1112 "/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id); 1113 goto out_dismount; 1114 } 1115 1116 root = d_make_root(inode); 1117 if (!root) { 1118 status = -ENOMEM; 1119 goto out_dismount; 1120 } 1121 1122 sb->s_root = root; 1123 1124 ocfs2_complete_mount_recovery(osb); 1125 1126 if (ocfs2_mount_local(osb)) 1127 snprintf(nodestr, sizeof(nodestr), "local"); 1128 else 1129 snprintf(nodestr, sizeof(nodestr), "%u", osb->node_num); 1130 1131 printk(KERN_INFO "ocfs2: Mounting device (%s) on (node %s, slot %d) " 1132 "with %s data mode.\n", 1133 osb->dev_str, nodestr, osb->slot_num, 1134 osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" : 1135 "ordered"); 1136 1137 atomic_set(&osb->vol_state, VOLUME_MOUNTED); 1138 wake_up(&osb->osb_mount_event); 1139 1140 /* Now we can initialize quotas because we can afford to wait 1141 * for cluster locks recovery now. That also means that truncation 1142 * log recovery can happen but that waits for proper quota setup */ 1143 if (!sb_rdonly(sb)) { 1144 status = ocfs2_enable_quotas(osb); 1145 if (status < 0) { 1146 /* We have to err-out specially here because 1147 * s_root is already set */ 1148 mlog_errno(status); 1149 atomic_set(&osb->vol_state, VOLUME_DISABLED); 1150 wake_up(&osb->osb_mount_event); 1151 return status; 1152 } 1153 } 1154 1155 ocfs2_complete_quota_recovery(osb); 1156 1157 /* Now we wake up again for processes waiting for quotas */ 1158 atomic_set(&osb->vol_state, VOLUME_MOUNTED_QUOTAS); 1159 wake_up(&osb->osb_mount_event); 1160 1161 /* Start this when the mount is almost sure of being successful */ 1162 ocfs2_orphan_scan_start(osb); 1163 1164 return status; 1165 1166out_dismount: 1167 atomic_set(&osb->vol_state, VOLUME_DISABLED); 1168 wake_up(&osb->osb_mount_event); 1169 ocfs2_free_replay_slots(osb); 1170 ocfs2_dismount_volume(sb, 1); 1171 goto out; 1172 1173out_debugfs: 1174 debugfs_remove_recursive(osb->osb_debug_root); 1175out_super: 1176 ocfs2_release_system_inodes(osb); 1177 kfree(osb->recovery_map); 1178 ocfs2_delete_osb(osb); 1179 kfree(osb); 1180out: 1181 mlog_errno(status); 1182 1183 return status; 1184} 1185 1186static struct dentry *ocfs2_mount(struct file_system_type *fs_type, 1187 int flags, 1188 const char *dev_name, 1189 void *data) 1190{ 1191 return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super); 1192} 1193 1194static struct file_system_type ocfs2_fs_type = { 1195 .owner = THIS_MODULE, 1196 .name = "ocfs2", 1197 .mount = ocfs2_mount, 1198 .kill_sb = kill_block_super, 1199 .fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE, 1200 .next = NULL 1201}; 1202MODULE_ALIAS_FS("ocfs2"); 1203 1204static int ocfs2_check_set_options(struct super_block *sb, 1205 struct mount_options *options) 1206{ 1207 if (options->mount_opt & OCFS2_MOUNT_USRQUOTA && 1208 !OCFS2_HAS_RO_COMPAT_FEATURE(sb, 1209 OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) { 1210 mlog(ML_ERROR, "User quotas were requested, but this " 1211 "filesystem does not have the feature enabled.\n"); 1212 return 0; 1213 } 1214 if (options->mount_opt & OCFS2_MOUNT_GRPQUOTA && 1215 !OCFS2_HAS_RO_COMPAT_FEATURE(sb, 1216 OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) { 1217 mlog(ML_ERROR, "Group quotas were requested, but this " 1218 "filesystem does not have the feature enabled.\n"); 1219 return 0; 1220 } 1221 if (options->mount_opt & OCFS2_MOUNT_POSIX_ACL && 1222 !OCFS2_HAS_INCOMPAT_FEATURE(sb, OCFS2_FEATURE_INCOMPAT_XATTR)) { 1223 mlog(ML_ERROR, "ACL support requested but extended attributes " 1224 "feature is not enabled\n"); 1225 return 0; 1226 } 1227 /* No ACL setting specified? Use XATTR feature... */ 1228 if (!(options->mount_opt & (OCFS2_MOUNT_POSIX_ACL | 1229 OCFS2_MOUNT_NO_POSIX_ACL))) { 1230 if (OCFS2_HAS_INCOMPAT_FEATURE(sb, OCFS2_FEATURE_INCOMPAT_XATTR)) 1231 options->mount_opt |= OCFS2_MOUNT_POSIX_ACL; 1232 else 1233 options->mount_opt |= OCFS2_MOUNT_NO_POSIX_ACL; 1234 } 1235 return 1; 1236} 1237 1238static int ocfs2_parse_options(struct super_block *sb, 1239 char *options, 1240 struct mount_options *mopt, 1241 int is_remount) 1242{ 1243 int status, user_stack = 0; 1244 char *p; 1245 u32 tmp; 1246 int token, option; 1247 substring_t args[MAX_OPT_ARGS]; 1248 1249 trace_ocfs2_parse_options(is_remount, options ? options : "(none)"); 1250 1251 mopt->commit_interval = 0; 1252 mopt->mount_opt = OCFS2_MOUNT_NOINTR; 1253 mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM; 1254 mopt->slot = OCFS2_INVALID_SLOT; 1255 mopt->localalloc_opt = -1; 1256 mopt->cluster_stack[0] = '\0'; 1257 mopt->resv_level = OCFS2_DEFAULT_RESV_LEVEL; 1258 mopt->dir_resv_level = -1; 1259 1260 if (!options) { 1261 status = 1; 1262 goto bail; 1263 } 1264 1265 while ((p = strsep(&options, ",")) != NULL) { 1266 if (!*p) 1267 continue; 1268 1269 token = match_token(p, tokens, args); 1270 switch (token) { 1271 case Opt_hb_local: 1272 mopt->mount_opt |= OCFS2_MOUNT_HB_LOCAL; 1273 break; 1274 case Opt_hb_none: 1275 mopt->mount_opt |= OCFS2_MOUNT_HB_NONE; 1276 break; 1277 case Opt_hb_global: 1278 mopt->mount_opt |= OCFS2_MOUNT_HB_GLOBAL; 1279 break; 1280 case Opt_barrier: 1281 if (match_int(&args[0], &option)) { 1282 status = 0; 1283 goto bail; 1284 } 1285 if (option) 1286 mopt->mount_opt |= OCFS2_MOUNT_BARRIER; 1287 else 1288 mopt->mount_opt &= ~OCFS2_MOUNT_BARRIER; 1289 break; 1290 case Opt_intr: 1291 mopt->mount_opt &= ~OCFS2_MOUNT_NOINTR; 1292 break; 1293 case Opt_nointr: 1294 mopt->mount_opt |= OCFS2_MOUNT_NOINTR; 1295 break; 1296 case Opt_err_panic: 1297 mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT; 1298 mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS; 1299 mopt->mount_opt |= OCFS2_MOUNT_ERRORS_PANIC; 1300 break; 1301 case Opt_err_ro: 1302 mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT; 1303 mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC; 1304 mopt->mount_opt |= OCFS2_MOUNT_ERRORS_ROFS; 1305 break; 1306 case Opt_err_cont: 1307 mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS; 1308 mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC; 1309 mopt->mount_opt |= OCFS2_MOUNT_ERRORS_CONT; 1310 break; 1311 case Opt_data_ordered: 1312 mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK; 1313 break; 1314 case Opt_data_writeback: 1315 mopt->mount_opt |= OCFS2_MOUNT_DATA_WRITEBACK; 1316 break; 1317 case Opt_user_xattr: 1318 mopt->mount_opt &= ~OCFS2_MOUNT_NOUSERXATTR; 1319 break; 1320 case Opt_nouser_xattr: 1321 mopt->mount_opt |= OCFS2_MOUNT_NOUSERXATTR; 1322 break; 1323 case Opt_atime_quantum: 1324 if (match_int(&args[0], &option)) { 1325 status = 0; 1326 goto bail; 1327 } 1328 if (option >= 0) 1329 mopt->atime_quantum = option; 1330 break; 1331 case Opt_slot: 1332 if (match_int(&args[0], &option)) { 1333 status = 0; 1334 goto bail; 1335 } 1336 if (option) 1337 mopt->slot = (u16)option; 1338 break; 1339 case Opt_commit: 1340 if (match_int(&args[0], &option)) { 1341 status = 0; 1342 goto bail; 1343 } 1344 if (option < 0) 1345 return 0; 1346 if (option == 0) 1347 option = JBD2_DEFAULT_MAX_COMMIT_AGE; 1348 mopt->commit_interval = HZ * option; 1349 break; 1350 case Opt_localalloc: 1351 if (match_int(&args[0], &option)) { 1352 status = 0; 1353 goto bail; 1354 } 1355 if (option >= 0) 1356 mopt->localalloc_opt = option; 1357 break; 1358 case Opt_localflocks: 1359 /* 1360 * Changing this during remount could race 1361 * flock() requests, or "unbalance" existing 1362 * ones (e.g., a lock is taken in one mode but 1363 * dropped in the other). If users care enough 1364 * to flip locking modes during remount, we 1365 * could add a "local" flag to individual 1366 * flock structures for proper tracking of 1367 * state. 1368 */ 1369 if (!is_remount) 1370 mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS; 1371 break; 1372 case Opt_stack: 1373 /* Check both that the option we were passed 1374 * is of the right length and that it is a proper 1375 * string of the right length. 1376 */ 1377 if (((args[0].to - args[0].from) != 1378 OCFS2_STACK_LABEL_LEN) || 1379 (strnlen(args[0].from, 1380 OCFS2_STACK_LABEL_LEN) != 1381 OCFS2_STACK_LABEL_LEN)) { 1382 mlog(ML_ERROR, 1383 "Invalid cluster_stack option\n"); 1384 status = 0; 1385 goto bail; 1386 } 1387 memcpy(mopt->cluster_stack, args[0].from, 1388 OCFS2_STACK_LABEL_LEN); 1389 mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0'; 1390 /* 1391 * Open code the memcmp here as we don't have 1392 * an osb to pass to 1393 * ocfs2_userspace_stack(). 1394 */ 1395 if (memcmp(mopt->cluster_stack, 1396 OCFS2_CLASSIC_CLUSTER_STACK, 1397 OCFS2_STACK_LABEL_LEN)) 1398 user_stack = 1; 1399 break; 1400 case Opt_inode64: 1401 mopt->mount_opt |= OCFS2_MOUNT_INODE64; 1402 break; 1403 case Opt_usrquota: 1404 mopt->mount_opt |= OCFS2_MOUNT_USRQUOTA; 1405 break; 1406 case Opt_grpquota: 1407 mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA; 1408 break; 1409 case Opt_coherency_buffered: 1410 mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED; 1411 break; 1412 case Opt_coherency_full: 1413 mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED; 1414 break; 1415 case Opt_acl: 1416 mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL; 1417 mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL; 1418 break; 1419 case Opt_noacl: 1420 mopt->mount_opt |= OCFS2_MOUNT_NO_POSIX_ACL; 1421 mopt->mount_opt &= ~OCFS2_MOUNT_POSIX_ACL; 1422 break; 1423 case Opt_resv_level: 1424 if (is_remount) 1425 break; 1426 if (match_int(&args[0], &option)) { 1427 status = 0; 1428 goto bail; 1429 } 1430 if (option >= OCFS2_MIN_RESV_LEVEL && 1431 option < OCFS2_MAX_RESV_LEVEL) 1432 mopt->resv_level = option; 1433 break; 1434 case Opt_dir_resv_level: 1435 if (is_remount) 1436 break; 1437 if (match_int(&args[0], &option)) { 1438 status = 0; 1439 goto bail; 1440 } 1441 if (option >= OCFS2_MIN_RESV_LEVEL && 1442 option < OCFS2_MAX_RESV_LEVEL) 1443 mopt->dir_resv_level = option; 1444 break; 1445 case Opt_journal_async_commit: 1446 mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT; 1447 break; 1448 default: 1449 mlog(ML_ERROR, 1450 "Unrecognized mount option \"%s\" " 1451 "or missing value\n", p); 1452 status = 0; 1453 goto bail; 1454 } 1455 } 1456 1457 if (user_stack == 0) { 1458 /* Ensure only one heartbeat mode */ 1459 tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL | 1460 OCFS2_MOUNT_HB_GLOBAL | 1461 OCFS2_MOUNT_HB_NONE); 1462 if (hweight32(tmp) != 1) { 1463 mlog(ML_ERROR, "Invalid heartbeat mount options\n"); 1464 status = 0; 1465 goto bail; 1466 } 1467 } 1468 1469 status = 1; 1470 1471bail: 1472 return status; 1473} 1474 1475static int ocfs2_show_options(struct seq_file *s, struct dentry *root) 1476{ 1477 struct ocfs2_super *osb = OCFS2_SB(root->d_sb); 1478 unsigned long opts = osb->s_mount_opt; 1479 unsigned int local_alloc_megs; 1480 1481 if (opts & (OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL)) { 1482 seq_printf(s, ",_netdev"); 1483 if (opts & OCFS2_MOUNT_HB_LOCAL) 1484 seq_printf(s, ",%s", OCFS2_HB_LOCAL); 1485 else 1486 seq_printf(s, ",%s", OCFS2_HB_GLOBAL); 1487 } else 1488 seq_printf(s, ",%s", OCFS2_HB_NONE); 1489 1490 if (opts & OCFS2_MOUNT_NOINTR) 1491 seq_printf(s, ",nointr"); 1492 1493 if (opts & OCFS2_MOUNT_DATA_WRITEBACK) 1494 seq_printf(s, ",data=writeback"); 1495 else 1496 seq_printf(s, ",data=ordered"); 1497 1498 if (opts & OCFS2_MOUNT_BARRIER) 1499 seq_printf(s, ",barrier=1"); 1500 1501 if (opts & OCFS2_MOUNT_ERRORS_PANIC) 1502 seq_printf(s, ",errors=panic"); 1503 else if (opts & OCFS2_MOUNT_ERRORS_CONT) 1504 seq_printf(s, ",errors=continue"); 1505 else 1506 seq_printf(s, ",errors=remount-ro"); 1507 1508 if (osb->preferred_slot != OCFS2_INVALID_SLOT) 1509 seq_printf(s, ",preferred_slot=%d", osb->preferred_slot); 1510 1511 seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum); 1512 1513 if (osb->osb_commit_interval) 1514 seq_printf(s, ",commit=%u", 1515 (unsigned) (osb->osb_commit_interval / HZ)); 1516 1517 local_alloc_megs = osb->local_alloc_bits >> (20 - osb->s_clustersize_bits); 1518 if (local_alloc_megs != ocfs2_la_default_mb(osb)) 1519 seq_printf(s, ",localalloc=%d", local_alloc_megs); 1520 1521 if (opts & OCFS2_MOUNT_LOCALFLOCKS) 1522 seq_printf(s, ",localflocks,"); 1523 1524 if (osb->osb_cluster_stack[0]) 1525 seq_show_option_n(s, "cluster_stack", osb->osb_cluster_stack, 1526 OCFS2_STACK_LABEL_LEN); 1527 if (opts & OCFS2_MOUNT_USRQUOTA) 1528 seq_printf(s, ",usrquota"); 1529 if (opts & OCFS2_MOUNT_GRPQUOTA) 1530 seq_printf(s, ",grpquota"); 1531 1532 if (opts & OCFS2_MOUNT_COHERENCY_BUFFERED) 1533 seq_printf(s, ",coherency=buffered"); 1534 else 1535 seq_printf(s, ",coherency=full"); 1536 1537 if (opts & OCFS2_MOUNT_NOUSERXATTR) 1538 seq_printf(s, ",nouser_xattr"); 1539 else 1540 seq_printf(s, ",user_xattr"); 1541 1542 if (opts & OCFS2_MOUNT_INODE64) 1543 seq_printf(s, ",inode64"); 1544 1545 if (opts & OCFS2_MOUNT_POSIX_ACL) 1546 seq_printf(s, ",acl"); 1547 else 1548 seq_printf(s, ",noacl"); 1549 1550 if (osb->osb_resv_level != OCFS2_DEFAULT_RESV_LEVEL) 1551 seq_printf(s, ",resv_level=%d", osb->osb_resv_level); 1552 1553 if (osb->osb_dir_resv_level != osb->osb_resv_level) 1554 seq_printf(s, ",dir_resv_level=%d", osb->osb_resv_level); 1555 1556 if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) 1557 seq_printf(s, ",journal_async_commit"); 1558 1559 return 0; 1560} 1561 1562static int __init ocfs2_init(void) 1563{ 1564 int status; 1565 1566 status = init_ocfs2_uptodate_cache(); 1567 if (status < 0) 1568 goto out1; 1569 1570 status = ocfs2_initialize_mem_caches(); 1571 if (status < 0) 1572 goto out2; 1573 1574 ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL); 1575 1576 ocfs2_set_locking_protocol(); 1577 1578 status = register_quota_format(&ocfs2_quota_format); 1579 if (status < 0) 1580 goto out3; 1581 status = register_filesystem(&ocfs2_fs_type); 1582 if (!status) 1583 return 0; 1584 1585 unregister_quota_format(&ocfs2_quota_format); 1586out3: 1587 debugfs_remove(ocfs2_debugfs_root); 1588 ocfs2_free_mem_caches(); 1589out2: 1590 exit_ocfs2_uptodate_cache(); 1591out1: 1592 mlog_errno(status); 1593 return status; 1594} 1595 1596static void __exit ocfs2_exit(void) 1597{ 1598 unregister_quota_format(&ocfs2_quota_format); 1599 1600 debugfs_remove(ocfs2_debugfs_root); 1601 1602 ocfs2_free_mem_caches(); 1603 1604 unregister_filesystem(&ocfs2_fs_type); 1605 1606 exit_ocfs2_uptodate_cache(); 1607} 1608 1609static void ocfs2_put_super(struct super_block *sb) 1610{ 1611 trace_ocfs2_put_super(sb); 1612 1613 ocfs2_sync_blockdev(sb); 1614 ocfs2_dismount_volume(sb, 0); 1615} 1616 1617static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf) 1618{ 1619 struct ocfs2_super *osb; 1620 u32 numbits, freebits; 1621 int status; 1622 struct ocfs2_dinode *bm_lock; 1623 struct buffer_head *bh = NULL; 1624 struct inode *inode = NULL; 1625 1626 trace_ocfs2_statfs(dentry->d_sb, buf); 1627 1628 osb = OCFS2_SB(dentry->d_sb); 1629 1630 inode = ocfs2_get_system_file_inode(osb, 1631 GLOBAL_BITMAP_SYSTEM_INODE, 1632 OCFS2_INVALID_SLOT); 1633 if (!inode) { 1634 mlog(ML_ERROR, "failed to get bitmap inode\n"); 1635 status = -EIO; 1636 goto bail; 1637 } 1638 1639 status = ocfs2_inode_lock(inode, &bh, 0); 1640 if (status < 0) { 1641 mlog_errno(status); 1642 goto bail; 1643 } 1644 1645 bm_lock = (struct ocfs2_dinode *) bh->b_data; 1646 1647 numbits = le32_to_cpu(bm_lock->id1.bitmap1.i_total); 1648 freebits = numbits - le32_to_cpu(bm_lock->id1.bitmap1.i_used); 1649 1650 buf->f_type = OCFS2_SUPER_MAGIC; 1651 buf->f_bsize = dentry->d_sb->s_blocksize; 1652 buf->f_namelen = OCFS2_MAX_FILENAME_LEN; 1653 buf->f_blocks = ((sector_t) numbits) * 1654 (osb->s_clustersize >> osb->sb->s_blocksize_bits); 1655 buf->f_bfree = ((sector_t) freebits) * 1656 (osb->s_clustersize >> osb->sb->s_blocksize_bits); 1657 buf->f_bavail = buf->f_bfree; 1658 buf->f_files = numbits; 1659 buf->f_ffree = freebits; 1660 buf->f_fsid.val[0] = crc32_le(0, osb->uuid_str, OCFS2_VOL_UUID_LEN) 1661 & 0xFFFFFFFFUL; 1662 buf->f_fsid.val[1] = crc32_le(0, osb->uuid_str + OCFS2_VOL_UUID_LEN, 1663 OCFS2_VOL_UUID_LEN) & 0xFFFFFFFFUL; 1664 1665 brelse(bh); 1666 1667 ocfs2_inode_unlock(inode, 0); 1668 status = 0; 1669bail: 1670 iput(inode); 1671 1672 if (status) 1673 mlog_errno(status); 1674 1675 return status; 1676} 1677 1678static void ocfs2_inode_init_once(void *data) 1679{ 1680 struct ocfs2_inode_info *oi = data; 1681 1682 oi->ip_flags = 0; 1683 oi->ip_open_count = 0; 1684 spin_lock_init(&oi->ip_lock); 1685 ocfs2_extent_map_init(&oi->vfs_inode); 1686 INIT_LIST_HEAD(&oi->ip_io_markers); 1687 INIT_LIST_HEAD(&oi->ip_unwritten_list); 1688 oi->ip_dir_start_lookup = 0; 1689 init_rwsem(&oi->ip_alloc_sem); 1690 init_rwsem(&oi->ip_xattr_sem); 1691 mutex_init(&oi->ip_io_mutex); 1692 1693 oi->ip_blkno = 0ULL; 1694 oi->ip_clusters = 0; 1695 oi->ip_next_orphan = NULL; 1696 1697 ocfs2_resv_init_once(&oi->ip_la_data_resv); 1698 1699 ocfs2_lock_res_init_once(&oi->ip_rw_lockres); 1700 ocfs2_lock_res_init_once(&oi->ip_inode_lockres); 1701 ocfs2_lock_res_init_once(&oi->ip_open_lockres); 1702 1703 ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode), 1704 &ocfs2_inode_caching_ops); 1705 1706 inode_init_once(&oi->vfs_inode); 1707} 1708 1709static int ocfs2_initialize_mem_caches(void) 1710{ 1711 ocfs2_inode_cachep = kmem_cache_create("ocfs2_inode_cache", 1712 sizeof(struct ocfs2_inode_info), 1713 0, 1714 (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| 1715 SLAB_MEM_SPREAD|SLAB_ACCOUNT), 1716 ocfs2_inode_init_once); 1717 ocfs2_dquot_cachep = kmem_cache_create("ocfs2_dquot_cache", 1718 sizeof(struct ocfs2_dquot), 1719 0, 1720 (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| 1721 SLAB_MEM_SPREAD), 1722 NULL); 1723 ocfs2_qf_chunk_cachep = kmem_cache_create("ocfs2_qf_chunk_cache", 1724 sizeof(struct ocfs2_quota_chunk), 1725 0, 1726 (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), 1727 NULL); 1728 if (!ocfs2_inode_cachep || !ocfs2_dquot_cachep || 1729 !ocfs2_qf_chunk_cachep) { 1730 kmem_cache_destroy(ocfs2_inode_cachep); 1731 kmem_cache_destroy(ocfs2_dquot_cachep); 1732 kmem_cache_destroy(ocfs2_qf_chunk_cachep); 1733 return -ENOMEM; 1734 } 1735 1736 return 0; 1737} 1738 1739static void ocfs2_free_mem_caches(void) 1740{ 1741 /* 1742 * Make sure all delayed rcu free inodes are flushed before we 1743 * destroy cache. 1744 */ 1745 rcu_barrier(); 1746 kmem_cache_destroy(ocfs2_inode_cachep); 1747 ocfs2_inode_cachep = NULL; 1748 1749 kmem_cache_destroy(ocfs2_dquot_cachep); 1750 ocfs2_dquot_cachep = NULL; 1751 1752 kmem_cache_destroy(ocfs2_qf_chunk_cachep); 1753 ocfs2_qf_chunk_cachep = NULL; 1754} 1755 1756static int ocfs2_get_sector(struct super_block *sb, 1757 struct buffer_head **bh, 1758 int block, 1759 int sect_size) 1760{ 1761 if (!sb_set_blocksize(sb, sect_size)) { 1762 mlog(ML_ERROR, "unable to set blocksize\n"); 1763 return -EIO; 1764 } 1765 1766 *bh = sb_getblk(sb, block); 1767 if (!*bh) { 1768 mlog_errno(-ENOMEM); 1769 return -ENOMEM; 1770 } 1771 lock_buffer(*bh); 1772 if (!buffer_dirty(*bh)) 1773 clear_buffer_uptodate(*bh); 1774 unlock_buffer(*bh); 1775 ll_rw_block(REQ_OP_READ, 0, 1, bh); 1776 wait_on_buffer(*bh); 1777 if (!buffer_uptodate(*bh)) { 1778 mlog_errno(-EIO); 1779 brelse(*bh); 1780 *bh = NULL; 1781 return -EIO; 1782 } 1783 1784 return 0; 1785} 1786 1787static int ocfs2_mount_volume(struct super_block *sb) 1788{ 1789 int status = 0; 1790 struct ocfs2_super *osb = OCFS2_SB(sb); 1791 1792 if (ocfs2_is_hard_readonly(osb)) 1793 goto out; 1794 1795 mutex_init(&osb->obs_trim_fs_mutex); 1796 1797 status = ocfs2_dlm_init(osb); 1798 if (status < 0) { 1799 mlog_errno(status); 1800 if (status == -EBADR && ocfs2_userspace_stack(osb)) 1801 mlog(ML_ERROR, "couldn't mount because cluster name on" 1802 " disk does not match the running cluster name.\n"); 1803 goto out; 1804 } 1805 1806 status = ocfs2_super_lock(osb, 1); 1807 if (status < 0) { 1808 mlog_errno(status); 1809 goto out_dlm; 1810 } 1811 1812 /* This will load up the node map and add ourselves to it. */ 1813 status = ocfs2_find_slot(osb); 1814 if (status < 0) { 1815 mlog_errno(status); 1816 goto out_super_lock; 1817 } 1818 1819 /* load all node-local system inodes */ 1820 status = ocfs2_init_local_system_inodes(osb); 1821 if (status < 0) { 1822 mlog_errno(status); 1823 goto out_super_lock; 1824 } 1825 1826 status = ocfs2_check_volume(osb); 1827 if (status < 0) { 1828 mlog_errno(status); 1829 goto out_system_inodes; 1830 } 1831 1832 status = ocfs2_truncate_log_init(osb); 1833 if (status < 0) { 1834 mlog_errno(status); 1835 goto out_check_volume; 1836 } 1837 1838 ocfs2_super_unlock(osb, 1); 1839 return 0; 1840 1841out_check_volume: 1842 ocfs2_free_replay_slots(osb); 1843out_system_inodes: 1844 if (osb->local_alloc_state == OCFS2_LA_ENABLED) 1845 ocfs2_shutdown_local_alloc(osb); 1846 ocfs2_release_system_inodes(osb); 1847 /* before journal shutdown, we should release slot_info */ 1848 ocfs2_free_slot_info(osb); 1849 ocfs2_journal_shutdown(osb); 1850out_super_lock: 1851 ocfs2_super_unlock(osb, 1); 1852out_dlm: 1853 ocfs2_dlm_shutdown(osb, 0); 1854out: 1855 return status; 1856} 1857 1858static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) 1859{ 1860 int tmp, hangup_needed = 0; 1861 struct ocfs2_super *osb = NULL; 1862 char nodestr[12]; 1863 1864 trace_ocfs2_dismount_volume(sb); 1865 1866 BUG_ON(!sb); 1867 osb = OCFS2_SB(sb); 1868 BUG_ON(!osb); 1869 1870 /* Remove file check sysfs related directores/files, 1871 * and wait for the pending file check operations */ 1872 ocfs2_filecheck_remove_sysfs(osb); 1873 1874 kset_unregister(osb->osb_dev_kset); 1875 1876 /* Orphan scan should be stopped as early as possible */ 1877 ocfs2_orphan_scan_stop(osb); 1878 1879 ocfs2_disable_quotas(osb); 1880 1881 /* All dquots should be freed by now */ 1882 WARN_ON(!llist_empty(&osb->dquot_drop_list)); 1883 /* Wait for worker to be done with the work structure in osb */ 1884 cancel_work_sync(&osb->dquot_drop_work); 1885 1886 ocfs2_shutdown_local_alloc(osb); 1887 1888 ocfs2_truncate_log_shutdown(osb); 1889 1890 /* This will disable recovery and flush any recovery work. */ 1891 ocfs2_recovery_exit(osb); 1892 1893 ocfs2_journal_shutdown(osb); 1894 1895 ocfs2_sync_blockdev(sb); 1896 1897 ocfs2_purge_refcount_trees(osb); 1898 1899 /* No cluster connection means we've failed during mount, so skip 1900 * all the steps which depended on that to complete. */ 1901 if (osb->cconn) { 1902 tmp = ocfs2_super_lock(osb, 1); 1903 if (tmp < 0) { 1904 mlog_errno(tmp); 1905 return; 1906 } 1907 } 1908 1909 if (osb->slot_num != OCFS2_INVALID_SLOT) 1910 ocfs2_put_slot(osb); 1911 1912 if (osb->cconn) 1913 ocfs2_super_unlock(osb, 1); 1914 1915 ocfs2_release_system_inodes(osb); 1916 1917 /* 1918 * If we're dismounting due to mount error, mount.ocfs2 will clean 1919 * up heartbeat. If we're a local mount, there is no heartbeat. 1920 * If we failed before we got a uuid_str yet, we can't stop 1921 * heartbeat. Otherwise, do it. 1922 */ 1923 if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str && 1924 !ocfs2_is_hard_readonly(osb)) 1925 hangup_needed = 1; 1926 1927 ocfs2_dlm_shutdown(osb, hangup_needed); 1928 1929 ocfs2_blockcheck_stats_debugfs_remove(&osb->osb_ecc_stats); 1930 debugfs_remove_recursive(osb->osb_debug_root); 1931 1932 if (hangup_needed) 1933 ocfs2_cluster_hangup(osb->uuid_str, strlen(osb->uuid_str)); 1934 1935 atomic_set(&osb->vol_state, VOLUME_DISMOUNTED); 1936 1937 if (ocfs2_mount_local(osb)) 1938 snprintf(nodestr, sizeof(nodestr), "local"); 1939 else 1940 snprintf(nodestr, sizeof(nodestr), "%u", osb->node_num); 1941 1942 printk(KERN_INFO "ocfs2: Unmounting device (%s) on (node %s)\n", 1943 osb->dev_str, nodestr); 1944 1945 ocfs2_delete_osb(osb); 1946 kfree(osb); 1947 sb->s_dev = 0; 1948 sb->s_fs_info = NULL; 1949} 1950 1951static int ocfs2_setup_osb_uuid(struct ocfs2_super *osb, const unsigned char *uuid, 1952 unsigned uuid_bytes) 1953{ 1954 int i, ret; 1955 char *ptr; 1956 1957 BUG_ON(uuid_bytes != OCFS2_VOL_UUID_LEN); 1958 1959 osb->uuid_str = kzalloc(OCFS2_VOL_UUID_LEN * 2 + 1, GFP_KERNEL); 1960 if (osb->uuid_str == NULL) 1961 return -ENOMEM; 1962 1963 for (i = 0, ptr = osb->uuid_str; i < OCFS2_VOL_UUID_LEN; i++) { 1964 /* print with null */ 1965 ret = snprintf(ptr, 3, "%02X", uuid[i]); 1966 if (ret != 2) /* drop super cleans up */ 1967 return -EINVAL; 1968 /* then only advance past the last char */ 1969 ptr += 2; 1970 } 1971 1972 return 0; 1973} 1974 1975/* Make sure entire volume is addressable by our journal. Requires 1976 osb_clusters_at_boot to be valid and for the journal to have been 1977 initialized by ocfs2_journal_init(). */ 1978static int ocfs2_journal_addressable(struct ocfs2_super *osb) 1979{ 1980 int status = 0; 1981 u64 max_block = 1982 ocfs2_clusters_to_blocks(osb->sb, 1983 osb->osb_clusters_at_boot) - 1; 1984 1985 /* 32-bit block number is always OK. */ 1986 if (max_block <= (u32)~0ULL) 1987 goto out; 1988 1989 /* Volume is "huge", so see if our journal is new enough to 1990 support it. */ 1991 if (!(OCFS2_HAS_COMPAT_FEATURE(osb->sb, 1992 OCFS2_FEATURE_COMPAT_JBD2_SB) && 1993 jbd2_journal_check_used_features(osb->journal->j_journal, 0, 0, 1994 JBD2_FEATURE_INCOMPAT_64BIT))) { 1995 mlog(ML_ERROR, "The journal cannot address the entire volume. " 1996 "Enable the 'block64' journal option with tunefs.ocfs2"); 1997 status = -EFBIG; 1998 goto out; 1999 } 2000 2001 out: 2002 return status; 2003} 2004 2005static int ocfs2_initialize_super(struct super_block *sb, 2006 struct buffer_head *bh, 2007 int sector_size, 2008 struct ocfs2_blockcheck_stats *stats) 2009{ 2010 int status; 2011 int i, cbits, bbits; 2012 struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data; 2013 struct inode *inode = NULL; 2014 struct ocfs2_journal *journal; 2015 struct ocfs2_super *osb; 2016 u64 total_blocks; 2017 2018 osb = kzalloc(sizeof(struct ocfs2_super), GFP_KERNEL); 2019 if (!osb) { 2020 status = -ENOMEM; 2021 mlog_errno(status); 2022 goto bail; 2023 } 2024 2025 sb->s_fs_info = osb; 2026 sb->s_op = &ocfs2_sops; 2027 sb->s_d_op = &ocfs2_dentry_ops; 2028 sb->s_export_op = &ocfs2_export_ops; 2029 sb->s_qcop = &dquot_quotactl_sysfile_ops; 2030 sb->dq_op = &ocfs2_quota_operations; 2031 sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; 2032 sb->s_xattr = ocfs2_xattr_handlers; 2033 sb->s_time_gran = 1; 2034 sb->s_flags |= SB_NOATIME; 2035 /* this is needed to support O_LARGEFILE */ 2036 cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits); 2037 bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); 2038 sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits); 2039 memcpy(&sb->s_uuid, di->id2.i_super.s_uuid, 2040 sizeof(di->id2.i_super.s_uuid)); 2041 2042 osb->osb_dx_mask = (1 << (cbits - bbits)) - 1; 2043 2044 for (i = 0; i < 3; i++) 2045 osb->osb_dx_seed[i] = le32_to_cpu(di->id2.i_super.s_dx_seed[i]); 2046 osb->osb_dx_seed[3] = le32_to_cpu(di->id2.i_super.s_uuid_hash); 2047 2048 osb->sb = sb; 2049 osb->s_sectsize_bits = blksize_bits(sector_size); 2050 BUG_ON(!osb->s_sectsize_bits); 2051 2052 spin_lock_init(&osb->dc_task_lock); 2053 init_waitqueue_head(&osb->dc_event); 2054 osb->dc_work_sequence = 0; 2055 osb->dc_wake_sequence = 0; 2056 INIT_LIST_HEAD(&osb->blocked_lock_list); 2057 osb->blocked_lock_count = 0; 2058 spin_lock_init(&osb->osb_lock); 2059 spin_lock_init(&osb->osb_xattr_lock); 2060 ocfs2_init_steal_slots(osb); 2061 2062 mutex_init(&osb->system_file_mutex); 2063 2064 atomic_set(&osb->alloc_stats.moves, 0); 2065 atomic_set(&osb->alloc_stats.local_data, 0); 2066 atomic_set(&osb->alloc_stats.bitmap_data, 0); 2067 atomic_set(&osb->alloc_stats.bg_allocs, 0); 2068 atomic_set(&osb->alloc_stats.bg_extends, 0); 2069 2070 /* Copy the blockcheck stats from the superblock probe */ 2071 osb->osb_ecc_stats = *stats; 2072 2073 ocfs2_init_node_maps(osb); 2074 2075 snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u", 2076 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); 2077 2078 osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots); 2079 if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) { 2080 mlog(ML_ERROR, "Invalid number of node slots (%u)\n", 2081 osb->max_slots); 2082 status = -EINVAL; 2083 goto bail; 2084 } 2085 2086 ocfs2_orphan_scan_init(osb); 2087 2088 status = ocfs2_recovery_init(osb); 2089 if (status) { 2090 mlog(ML_ERROR, "Unable to initialize recovery state\n"); 2091 mlog_errno(status); 2092 goto bail; 2093 } 2094 2095 init_waitqueue_head(&osb->checkpoint_event); 2096 2097 osb->s_atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM; 2098 2099 osb->slot_num = OCFS2_INVALID_SLOT; 2100 2101 osb->s_xattr_inline_size = le16_to_cpu( 2102 di->id2.i_super.s_xattr_inline_size); 2103 2104 osb->local_alloc_state = OCFS2_LA_UNUSED; 2105 osb->local_alloc_bh = NULL; 2106 INIT_DELAYED_WORK(&osb->la_enable_wq, ocfs2_la_enable_worker); 2107 2108 init_waitqueue_head(&osb->osb_mount_event); 2109 2110 status = ocfs2_resmap_init(osb, &osb->osb_la_resmap); 2111 if (status) { 2112 mlog_errno(status); 2113 goto bail; 2114 } 2115 2116 osb->vol_label = kmalloc(OCFS2_MAX_VOL_LABEL_LEN, GFP_KERNEL); 2117 if (!osb->vol_label) { 2118 mlog(ML_ERROR, "unable to alloc vol label\n"); 2119 status = -ENOMEM; 2120 goto bail; 2121 } 2122 2123 osb->slot_recovery_generations = 2124 kcalloc(osb->max_slots, sizeof(*osb->slot_recovery_generations), 2125 GFP_KERNEL); 2126 if (!osb->slot_recovery_generations) { 2127 status = -ENOMEM; 2128 mlog_errno(status); 2129 goto bail; 2130 } 2131 2132 init_waitqueue_head(&osb->osb_wipe_event); 2133 osb->osb_orphan_wipes = kcalloc(osb->max_slots, 2134 sizeof(*osb->osb_orphan_wipes), 2135 GFP_KERNEL); 2136 if (!osb->osb_orphan_wipes) { 2137 status = -ENOMEM; 2138 mlog_errno(status); 2139 goto bail; 2140 } 2141 2142 osb->osb_rf_lock_tree = RB_ROOT; 2143 2144 osb->s_feature_compat = 2145 le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_compat); 2146 osb->s_feature_ro_compat = 2147 le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_ro_compat); 2148 osb->s_feature_incompat = 2149 le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_incompat); 2150 2151 if ((i = OCFS2_HAS_INCOMPAT_FEATURE(osb->sb, ~OCFS2_FEATURE_INCOMPAT_SUPP))) { 2152 mlog(ML_ERROR, "couldn't mount because of unsupported " 2153 "optional features (%x).\n", i); 2154 status = -EINVAL; 2155 goto bail; 2156 } 2157 if (!sb_rdonly(osb->sb) && (i = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP))) { 2158 mlog(ML_ERROR, "couldn't mount RDWR because of " 2159 "unsupported optional features (%x).\n", i); 2160 status = -EINVAL; 2161 goto bail; 2162 } 2163 2164 if (ocfs2_clusterinfo_valid(osb)) { 2165 /* 2166 * ci_stack and ci_cluster in ocfs2_cluster_info may not be null 2167 * terminated, so make sure no overflow happens here by using 2168 * memcpy. Destination strings will always be null terminated 2169 * because osb is allocated using kzalloc. 2170 */ 2171 osb->osb_stackflags = 2172 OCFS2_RAW_SB(di)->s_cluster_info.ci_stackflags; 2173 memcpy(osb->osb_cluster_stack, 2174 OCFS2_RAW_SB(di)->s_cluster_info.ci_stack, 2175 OCFS2_STACK_LABEL_LEN); 2176 if (strlen(osb->osb_cluster_stack) != OCFS2_STACK_LABEL_LEN) { 2177 mlog(ML_ERROR, 2178 "couldn't mount because of an invalid " 2179 "cluster stack label (%s) \n", 2180 osb->osb_cluster_stack); 2181 status = -EINVAL; 2182 goto bail; 2183 } 2184 memcpy(osb->osb_cluster_name, 2185 OCFS2_RAW_SB(di)->s_cluster_info.ci_cluster, 2186 OCFS2_CLUSTER_NAME_LEN); 2187 } else { 2188 /* The empty string is identical with classic tools that 2189 * don't know about s_cluster_info. */ 2190 osb->osb_cluster_stack[0] = '\0'; 2191 } 2192 2193 get_random_bytes(&osb->s_next_generation, sizeof(u32)); 2194 2195 /* FIXME 2196 * This should be done in ocfs2_journal_init(), but unknown 2197 * ordering issues will cause the filesystem to crash. 2198 * If anyone wants to figure out what part of the code 2199 * refers to osb->journal before ocfs2_journal_init() is run, 2200 * be my guest. 2201 */ 2202 /* initialize our journal structure */ 2203 2204 journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL); 2205 if (!journal) { 2206 mlog(ML_ERROR, "unable to alloc journal\n"); 2207 status = -ENOMEM; 2208 goto bail; 2209 } 2210 osb->journal = journal; 2211 journal->j_osb = osb; 2212 2213 atomic_set(&journal->j_num_trans, 0); 2214 init_rwsem(&journal->j_trans_barrier); 2215 init_waitqueue_head(&journal->j_checkpointed); 2216 spin_lock_init(&journal->j_lock); 2217 journal->j_trans_id = (unsigned long) 1; 2218 INIT_LIST_HEAD(&journal->j_la_cleanups); 2219 INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery); 2220 journal->j_state = OCFS2_JOURNAL_FREE; 2221 2222 INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs); 2223 init_llist_head(&osb->dquot_drop_list); 2224 2225 /* get some pseudo constants for clustersize bits */ 2226 osb->s_clustersize_bits = 2227 le32_to_cpu(di->id2.i_super.s_clustersize_bits); 2228 osb->s_clustersize = 1 << osb->s_clustersize_bits; 2229 2230 if (osb->s_clustersize < OCFS2_MIN_CLUSTERSIZE || 2231 osb->s_clustersize > OCFS2_MAX_CLUSTERSIZE) { 2232 mlog(ML_ERROR, "Volume has invalid cluster size (%d)\n", 2233 osb->s_clustersize); 2234 status = -EINVAL; 2235 goto bail; 2236 } 2237 2238 total_blocks = ocfs2_clusters_to_blocks(osb->sb, 2239 le32_to_cpu(di->i_clusters)); 2240 2241 status = generic_check_addressable(osb->sb->s_blocksize_bits, 2242 total_blocks); 2243 if (status) { 2244 mlog(ML_ERROR, "Volume too large " 2245 "to mount safely on this system"); 2246 status = -EFBIG; 2247 goto bail; 2248 } 2249 2250 if (ocfs2_setup_osb_uuid(osb, di->id2.i_super.s_uuid, 2251 sizeof(di->id2.i_super.s_uuid))) { 2252 mlog(ML_ERROR, "Out of memory trying to setup our uuid.\n"); 2253 status = -ENOMEM; 2254 goto bail; 2255 } 2256 2257 strlcpy(osb->vol_label, di->id2.i_super.s_label, 2258 OCFS2_MAX_VOL_LABEL_LEN); 2259 osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno); 2260 osb->system_dir_blkno = le64_to_cpu(di->id2.i_super.s_system_dir_blkno); 2261 osb->first_cluster_group_blkno = 2262 le64_to_cpu(di->id2.i_super.s_first_cluster_group); 2263 osb->fs_generation = le32_to_cpu(di->i_fs_generation); 2264 osb->uuid_hash = le32_to_cpu(di->id2.i_super.s_uuid_hash); 2265 trace_ocfs2_initialize_super(osb->vol_label, osb->uuid_str, 2266 (unsigned long long)osb->root_blkno, 2267 (unsigned long long)osb->system_dir_blkno, 2268 osb->s_clustersize_bits); 2269 2270 osb->osb_dlm_debug = ocfs2_new_dlm_debug(); 2271 if (!osb->osb_dlm_debug) { 2272 status = -ENOMEM; 2273 mlog_errno(status); 2274 goto bail; 2275 } 2276 2277 atomic_set(&osb->vol_state, VOLUME_INIT); 2278 2279 /* load root, system_dir, and all global system inodes */ 2280 status = ocfs2_init_global_system_inodes(osb); 2281 if (status < 0) { 2282 mlog_errno(status); 2283 goto bail; 2284 } 2285 2286 /* 2287 * global bitmap 2288 */ 2289 inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, 2290 OCFS2_INVALID_SLOT); 2291 if (!inode) { 2292 status = -EINVAL; 2293 mlog_errno(status); 2294 goto bail; 2295 } 2296 2297 osb->bitmap_blkno = OCFS2_I(inode)->ip_blkno; 2298 osb->osb_clusters_at_boot = OCFS2_I(inode)->ip_clusters; 2299 iput(inode); 2300 2301 osb->bitmap_cpg = ocfs2_group_bitmap_size(sb, 0, 2302 osb->s_feature_incompat) * 8; 2303 2304 status = ocfs2_init_slot_info(osb); 2305 if (status < 0) { 2306 mlog_errno(status); 2307 goto bail; 2308 } 2309 cleancache_init_shared_fs(sb); 2310 2311 osb->ocfs2_wq = alloc_ordered_workqueue("ocfs2_wq", WQ_MEM_RECLAIM); 2312 if (!osb->ocfs2_wq) { 2313 status = -ENOMEM; 2314 mlog_errno(status); 2315 } 2316 2317bail: 2318 return status; 2319} 2320 2321/* 2322 * will return: -EAGAIN if it is ok to keep searching for superblocks 2323 * -EINVAL if there is a bad superblock 2324 * 0 on success 2325 */ 2326static int ocfs2_verify_volume(struct ocfs2_dinode *di, 2327 struct buffer_head *bh, 2328 u32 blksz, 2329 struct ocfs2_blockcheck_stats *stats) 2330{ 2331 int status = -EAGAIN; 2332 2333 if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE, 2334 strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) { 2335 /* We have to do a raw check of the feature here */ 2336 if (le32_to_cpu(di->id2.i_super.s_feature_incompat) & 2337 OCFS2_FEATURE_INCOMPAT_META_ECC) { 2338 status = ocfs2_block_check_validate(bh->b_data, 2339 bh->b_size, 2340 &di->i_check, 2341 stats); 2342 if (status) 2343 goto out; 2344 } 2345 status = -EINVAL; 2346 if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) { 2347 mlog(ML_ERROR, "found superblock with incorrect block " 2348 "size: found %u, should be %u\n", 2349 1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits), 2350 blksz); 2351 } else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) != 2352 OCFS2_MAJOR_REV_LEVEL || 2353 le16_to_cpu(di->id2.i_super.s_minor_rev_level) != 2354 OCFS2_MINOR_REV_LEVEL) { 2355 mlog(ML_ERROR, "found superblock with bad version: " 2356 "found %u.%u, should be %u.%u\n", 2357 le16_to_cpu(di->id2.i_super.s_major_rev_level), 2358 le16_to_cpu(di->id2.i_super.s_minor_rev_level), 2359 OCFS2_MAJOR_REV_LEVEL, 2360 OCFS2_MINOR_REV_LEVEL); 2361 } else if (bh->b_blocknr != le64_to_cpu(di->i_blkno)) { 2362 mlog(ML_ERROR, "bad block number on superblock: " 2363 "found %llu, should be %llu\n", 2364 (unsigned long long)le64_to_cpu(di->i_blkno), 2365 (unsigned long long)bh->b_blocknr); 2366 } else if (le32_to_cpu(di->id2.i_super.s_clustersize_bits) < 12 || 2367 le32_to_cpu(di->id2.i_super.s_clustersize_bits) > 20) { 2368 mlog(ML_ERROR, "bad cluster size found: %u\n", 2369 1 << le32_to_cpu(di->id2.i_super.s_clustersize_bits)); 2370 } else if (!le64_to_cpu(di->id2.i_super.s_root_blkno)) { 2371 mlog(ML_ERROR, "bad root_blkno: 0\n"); 2372 } else if (!le64_to_cpu(di->id2.i_super.s_system_dir_blkno)) { 2373 mlog(ML_ERROR, "bad system_dir_blkno: 0\n"); 2374 } else if (le16_to_cpu(di->id2.i_super.s_max_slots) > OCFS2_MAX_SLOTS) { 2375 mlog(ML_ERROR, 2376 "Superblock slots found greater than file system " 2377 "maximum: found %u, max %u\n", 2378 le16_to_cpu(di->id2.i_super.s_max_slots), 2379 OCFS2_MAX_SLOTS); 2380 } else { 2381 /* found it! */ 2382 status = 0; 2383 } 2384 } 2385 2386out: 2387 if (status && status != -EAGAIN) 2388 mlog_errno(status); 2389 return status; 2390} 2391 2392static int ocfs2_check_volume(struct ocfs2_super *osb) 2393{ 2394 int status; 2395 int dirty; 2396 int local; 2397 struct ocfs2_dinode *local_alloc = NULL; /* only used if we 2398 * recover 2399 * ourselves. */ 2400 2401 /* Init our journal object. */ 2402 status = ocfs2_journal_init(osb->journal, &dirty); 2403 if (status < 0) { 2404 mlog(ML_ERROR, "Could not initialize journal!\n"); 2405 goto finally; 2406 } 2407 2408 /* Now that journal has been initialized, check to make sure 2409 entire volume is addressable. */ 2410 status = ocfs2_journal_addressable(osb); 2411 if (status) 2412 goto finally; 2413 2414 /* If the journal was unmounted cleanly then we don't want to 2415 * recover anything. Otherwise, journal_load will do that 2416 * dirty work for us :) */ 2417 if (!dirty) { 2418 status = ocfs2_journal_wipe(osb->journal, 0); 2419 if (status < 0) { 2420 mlog_errno(status); 2421 goto finally; 2422 } 2423 } else { 2424 printk(KERN_NOTICE "ocfs2: File system on device (%s) was not " 2425 "unmounted cleanly, recovering it.\n", osb->dev_str); 2426 } 2427 2428 local = ocfs2_mount_local(osb); 2429 2430 /* will play back anything left in the journal. */ 2431 status = ocfs2_journal_load(osb->journal, local, dirty); 2432 if (status < 0) { 2433 mlog(ML_ERROR, "ocfs2 journal load failed! %d\n", status); 2434 goto finally; 2435 } 2436 2437 if (osb->s_mount_opt & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) 2438 jbd2_journal_set_features(osb->journal->j_journal, 2439 JBD2_FEATURE_COMPAT_CHECKSUM, 0, 2440 JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); 2441 else 2442 jbd2_journal_clear_features(osb->journal->j_journal, 2443 JBD2_FEATURE_COMPAT_CHECKSUM, 0, 2444 JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); 2445 2446 if (dirty) { 2447 /* recover my local alloc if we didn't unmount cleanly. */ 2448 status = ocfs2_begin_local_alloc_recovery(osb, 2449 osb->slot_num, 2450 &local_alloc); 2451 if (status < 0) { 2452 mlog_errno(status); 2453 goto finally; 2454 } 2455 /* we complete the recovery process after we've marked 2456 * ourselves as mounted. */ 2457 } 2458 2459 status = ocfs2_load_local_alloc(osb); 2460 if (status < 0) { 2461 mlog_errno(status); 2462 goto finally; 2463 } 2464 2465 if (dirty) { 2466 /* Recovery will be completed after we've mounted the 2467 * rest of the volume. */ 2468 osb->local_alloc_copy = local_alloc; 2469 local_alloc = NULL; 2470 } 2471 2472 /* go through each journal, trylock it and if you get the 2473 * lock, and it's marked as dirty, set the bit in the recover 2474 * map and launch a recovery thread for it. */ 2475 status = ocfs2_mark_dead_nodes(osb); 2476 if (status < 0) { 2477 mlog_errno(status); 2478 goto finally; 2479 } 2480 2481 status = ocfs2_compute_replay_slots(osb); 2482 if (status < 0) 2483 mlog_errno(status); 2484 2485finally: 2486 kfree(local_alloc); 2487 2488 if (status) 2489 mlog_errno(status); 2490 return status; 2491} 2492 2493/* 2494 * The routine gets called from dismount or close whenever a dismount on 2495 * volume is requested and the osb open count becomes 1. 2496 * It will remove the osb from the global list and also free up all the 2497 * initialized resources and fileobject. 2498 */ 2499static void ocfs2_delete_osb(struct ocfs2_super *osb) 2500{ 2501 /* This function assumes that the caller has the main osb resource */ 2502 2503 /* ocfs2_initializer_super have already created this workqueue */ 2504 if (osb->ocfs2_wq) 2505 destroy_workqueue(osb->ocfs2_wq); 2506 2507 ocfs2_free_slot_info(osb); 2508 2509 kfree(osb->osb_orphan_wipes); 2510 kfree(osb->slot_recovery_generations); 2511 /* FIXME 2512 * This belongs in journal shutdown, but because we have to 2513 * allocate osb->journal at the start of ocfs2_initialize_osb(), 2514 * we free it here. 2515 */ 2516 kfree(osb->journal); 2517 kfree(osb->local_alloc_copy); 2518 kfree(osb->uuid_str); 2519 kfree(osb->vol_label); 2520 ocfs2_put_dlm_debug(osb->osb_dlm_debug); 2521 memset(osb, 0, sizeof(struct ocfs2_super)); 2522} 2523 2524/* Depending on the mount option passed, perform one of the following: 2525 * Put OCFS2 into a readonly state (default) 2526 * Return EIO so that only the process errs 2527 * Fix the error as if fsck.ocfs2 -y 2528 * panic 2529 */ 2530static int ocfs2_handle_error(struct super_block *sb) 2531{ 2532 struct ocfs2_super *osb = OCFS2_SB(sb); 2533 int rv = 0; 2534 2535 ocfs2_set_osb_flag(osb, OCFS2_OSB_ERROR_FS); 2536 pr_crit("On-disk corruption discovered. " 2537 "Please run fsck.ocfs2 once the filesystem is unmounted.\n"); 2538 2539 if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_PANIC) { 2540 panic("OCFS2: (device %s): panic forced after error\n", 2541 sb->s_id); 2542 } else if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_CONT) { 2543 pr_crit("OCFS2: Returning error to the calling process.\n"); 2544 rv = -EIO; 2545 } else { /* default option */ 2546 rv = -EROFS; 2547 if (sb_rdonly(sb) && (ocfs2_is_soft_readonly(osb) || ocfs2_is_hard_readonly(osb))) 2548 return rv; 2549 2550 pr_crit("OCFS2: File system is now read-only.\n"); 2551 sb->s_flags |= SB_RDONLY; 2552 ocfs2_set_ro_flag(osb, 0); 2553 } 2554 2555 return rv; 2556} 2557 2558int __ocfs2_error(struct super_block *sb, const char *function, 2559 const char *fmt, ...) 2560{ 2561 struct va_format vaf; 2562 va_list args; 2563 2564 va_start(args, fmt); 2565 vaf.fmt = fmt; 2566 vaf.va = &args; 2567 2568 /* Not using mlog here because we want to show the actual 2569 * function the error came from. */ 2570 printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV", 2571 sb->s_id, function, &vaf); 2572 2573 va_end(args); 2574 2575 return ocfs2_handle_error(sb); 2576} 2577 2578/* Handle critical errors. This is intentionally more drastic than 2579 * ocfs2_handle_error, so we only use for things like journal errors, 2580 * etc. */ 2581void __ocfs2_abort(struct super_block *sb, const char *function, 2582 const char *fmt, ...) 2583{ 2584 struct va_format vaf; 2585 va_list args; 2586 2587 va_start(args, fmt); 2588 2589 vaf.fmt = fmt; 2590 vaf.va = &args; 2591 2592 printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV", 2593 sb->s_id, function, &vaf); 2594 2595 va_end(args); 2596 2597 /* We don't have the cluster support yet to go straight to 2598 * hard readonly in here. Until then, we want to keep 2599 * ocfs2_abort() so that we can at least mark critical 2600 * errors. 2601 * 2602 * TODO: This should abort the journal and alert other nodes 2603 * that our slot needs recovery. */ 2604 2605 /* Force a panic(). This stinks, but it's better than letting 2606 * things continue without having a proper hard readonly 2607 * here. */ 2608 if (!ocfs2_mount_local(OCFS2_SB(sb))) 2609 OCFS2_SB(sb)->s_mount_opt |= OCFS2_MOUNT_ERRORS_PANIC; 2610 ocfs2_handle_error(sb); 2611} 2612 2613/* 2614 * Void signal blockers, because in-kernel sigprocmask() only fails 2615 * when SIG_* is wrong. 2616 */ 2617void ocfs2_block_signals(sigset_t *oldset) 2618{ 2619 int rc; 2620 sigset_t blocked; 2621 2622 sigfillset(&blocked); 2623 rc = sigprocmask(SIG_BLOCK, &blocked, oldset); 2624 BUG_ON(rc); 2625} 2626 2627void ocfs2_unblock_signals(sigset_t *oldset) 2628{ 2629 int rc = sigprocmask(SIG_SETMASK, oldset, NULL); 2630 BUG_ON(rc); 2631} 2632 2633module_init(ocfs2_init); 2634module_exit(ocfs2_exit); 2635