xref: /kernel/linux/linux-5.10/fs/ocfs2/super.c (revision 8c2ecf20)
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, &sector_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