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
66 static struct kmem_cache *ocfs2_inode_cachep;
67 struct kmem_cache *ocfs2_dquot_cachep;
68 struct kmem_cache *ocfs2_qf_chunk_cachep;
69
70 static struct dentry *ocfs2_debugfs_root;
71
72 MODULE_AUTHOR("Oracle");
73 MODULE_LICENSE("GPL");
74 MODULE_DESCRIPTION("OCFS2 cluster file system");
75
76 struct 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
88 static int ocfs2_parse_options(struct super_block *sb, char *options,
89 struct mount_options *mopt,
90 int is_remount);
91 static int ocfs2_check_set_options(struct super_block *sb,
92 struct mount_options *options);
93 static int ocfs2_show_options(struct seq_file *s, struct dentry *root);
94 static void ocfs2_put_super(struct super_block *sb);
95 static int ocfs2_mount_volume(struct super_block *sb);
96 static int ocfs2_remount(struct super_block *sb, int *flags, char *data);
97 static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err);
98 static int ocfs2_initialize_mem_caches(void);
99 static void ocfs2_free_mem_caches(void);
100 static void ocfs2_delete_osb(struct ocfs2_super *osb);
101
102 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf);
103
104 static int ocfs2_sync_fs(struct super_block *sb, int wait);
105
106 static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb);
107 static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb);
108 static void ocfs2_release_system_inodes(struct ocfs2_super *osb);
109 static int ocfs2_check_volume(struct ocfs2_super *osb);
110 static int ocfs2_verify_volume(struct ocfs2_dinode *di,
111 struct buffer_head *bh,
112 u32 sectsize,
113 struct ocfs2_blockcheck_stats *stats);
114 static int ocfs2_initialize_super(struct super_block *sb,
115 struct buffer_head *bh,
116 int sector_size,
117 struct ocfs2_blockcheck_stats *stats);
118 static int ocfs2_get_sector(struct super_block *sb,
119 struct buffer_head **bh,
120 int block,
121 int sect_size);
122 static struct inode *ocfs2_alloc_inode(struct super_block *sb);
123 static void ocfs2_free_inode(struct inode *inode);
124 static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend);
125 static int ocfs2_enable_quotas(struct ocfs2_super *osb);
126 static void ocfs2_disable_quotas(struct ocfs2_super *osb);
127
ocfs2_get_dquots(struct inode *inode)128 static struct dquot **ocfs2_get_dquots(struct inode *inode)
129 {
130 return OCFS2_I(inode)->i_dquot;
131 }
132
133 static 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
148 enum {
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
181 static 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
ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)215 static 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
ocfs2_osb_debug_open(struct inode *inode, struct file *file)342 static 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;
356 bail:
357 return -ENOMEM;
358 }
359
ocfs2_debug_release(struct inode *inode, struct file *file)360 static int ocfs2_debug_release(struct inode *inode, struct file *file)
361 {
362 kfree(file->private_data);
363 return 0;
364 }
365
ocfs2_debug_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)366 static 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
ocfs2_osb_debug_open(struct inode *inode, struct file *file)373 static int ocfs2_osb_debug_open(struct inode *inode, struct file *file)
374 {
375 return 0;
376 }
ocfs2_debug_release(struct inode *inode, struct file *file)377 static int ocfs2_debug_release(struct inode *inode, struct file *file)
378 {
379 return 0;
380 }
ocfs2_debug_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)381 static 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
388 static 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
ocfs2_sync_fs(struct super_block *sb, int wait)395 static 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
ocfs2_need_system_inode(struct ocfs2_super *osb, int ino)421 static 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
ocfs2_init_global_system_inodes(struct ocfs2_super *osb)434 static 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
473 bail:
474 if (status)
475 mlog_errno(status);
476 return status;
477 }
478
ocfs2_init_local_system_inodes(struct ocfs2_super *osb)479 static 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
502 bail:
503 if (status)
504 mlog_errno(status);
505 return status;
506 }
507
ocfs2_release_system_inodes(struct ocfs2_super *osb)508 static 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 */
ocfs2_alloc_inode(struct super_block *sb)548 static 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
ocfs2_free_inode(struct inode *inode)564 static void ocfs2_free_inode(struct inode *inode)
565 {
566 kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode));
567 }
568
ocfs2_max_file_offset(unsigned int bbits, unsigned int cbits)569 static 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
ocfs2_remount(struct super_block *sb, int *flags, char *data)606 static 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);
685 unlock_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 }
720 out:
721 return ret;
722 }
723
ocfs2_sb_probe(struct super_block *sb, struct buffer_head **bh, int *sector_size, struct ocfs2_blockcheck_stats *stats)724 static 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
806 bail:
807 return status;
808 }
809
ocfs2_verify_heartbeat(struct ocfs2_super *osb)810 static 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 */
ocfs2_verify_userspace_stack(struct ocfs2_super *osb, struct mount_options *mopt)851 static 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
ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend)875 static 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
ocfs2_enable_quotas(struct ocfs2_super *osb)906 static 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;
938 out_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
ocfs2_disable_quotas(struct ocfs2_super *osb)946 static 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
ocfs2_fill_super(struct super_block *sb, void *data, int silent)974 static 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
1166 out_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
1173 out_debugfs:
1174 debugfs_remove_recursive(osb->osb_debug_root);
1175 out_super:
1176 ocfs2_release_system_inodes(osb);
1177 kfree(osb->recovery_map);
1178 ocfs2_delete_osb(osb);
1179 kfree(osb);
1180 out:
1181 mlog_errno(status);
1182
1183 return status;
1184 }
1185
ocfs2_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data)1186 static 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
1194 static 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 };
1202 MODULE_ALIAS_FS("ocfs2");
1203
ocfs2_check_set_options(struct super_block *sb, struct mount_options *options)1204 static 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
ocfs2_parse_options(struct super_block *sb, char *options, struct mount_options *mopt, int is_remount)1238 static 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
1471 bail:
1472 return status;
1473 }
1474
ocfs2_show_options(struct seq_file *s, struct dentry *root)1475 static 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
ocfs2_init(void)1562 static 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);
1586 out3:
1587 debugfs_remove(ocfs2_debugfs_root);
1588 ocfs2_free_mem_caches();
1589 out2:
1590 exit_ocfs2_uptodate_cache();
1591 out1:
1592 mlog_errno(status);
1593 return status;
1594 }
1595
ocfs2_exit(void)1596 static 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
ocfs2_put_super(struct super_block *sb)1609 static 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
ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)1617 static 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;
1669 bail:
1670 iput(inode);
1671
1672 if (status)
1673 mlog_errno(status);
1674
1675 return status;
1676 }
1677
ocfs2_inode_init_once(void *data)1678 static 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
ocfs2_initialize_mem_caches(void)1709 static 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
ocfs2_free_mem_caches(void)1739 static 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
ocfs2_get_sector(struct super_block *sb, struct buffer_head **bh, int block, int sect_size)1756 static 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
ocfs2_mount_volume(struct super_block *sb)1787 static 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
1841 out_check_volume:
1842 ocfs2_free_replay_slots(osb);
1843 out_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);
1850 out_super_lock:
1851 ocfs2_super_unlock(osb, 1);
1852 out_dlm:
1853 ocfs2_dlm_shutdown(osb, 0);
1854 out:
1855 return status;
1856 }
1857
ocfs2_dismount_volume(struct super_block *sb, int mnt_err)1858 static 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
ocfs2_setup_osb_uuid(struct ocfs2_super *osb, const unsigned char *uuid, unsigned uuid_bytes)1951 static 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(). */
ocfs2_journal_addressable(struct ocfs2_super *osb)1978 static 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
ocfs2_initialize_super(struct super_block *sb, struct buffer_head *bh, int sector_size, struct ocfs2_blockcheck_stats *stats)2005 static 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
2317 bail:
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 */
ocfs2_verify_volume(struct ocfs2_dinode *di, struct buffer_head *bh, u32 blksz, struct ocfs2_blockcheck_stats *stats)2326 static 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
2386 out:
2387 if (status && status != -EAGAIN)
2388 mlog_errno(status);
2389 return status;
2390 }
2391
ocfs2_check_volume(struct ocfs2_super *osb)2392 static 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
2485 finally:
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 */
ocfs2_delete_osb(struct ocfs2_super *osb)2499 static 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 */
ocfs2_handle_error(struct super_block *sb)2530 static 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
__ocfs2_error(struct super_block *sb, const char *function, const char *fmt, ...)2558 int __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. */
__ocfs2_abort(struct super_block *sb, const char *function, const char *fmt, ...)2581 void __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 */
ocfs2_block_signals(sigset_t *oldset)2617 void 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
ocfs2_unblock_signals(sigset_t *oldset)2627 void ocfs2_unblock_signals(sigset_t *oldset)
2628 {
2629 int rc = sigprocmask(SIG_SETMASK, oldset, NULL);
2630 BUG_ON(rc);
2631 }
2632
2633 module_init(ocfs2_init);
2634 module_exit(ocfs2_exit);
2635