aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/linux-2.6/xfs_super.c
blob: a1e3f3ea334b8b97db7d538b22427d7d2f6814be (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_clnt.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_alloc.h"
#include "xfs_dmapi.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_rw.h"
#include "xfs_acl.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
#include "xfs_vnodeops.h"
#include "xfs_vfsops.h"
#include "xfs_version.h"

#include <linux/namei.h>
#include <linux/init.h>
#include <linux/mount.h>
#include <linux/mempool.h>
#include <linux/writeback.h>
#include <linux/kthread.h>
#include <linux/freezer.h>

static struct quotactl_ops xfs_quotactl_operations;
static struct super_operations xfs_super_operations;
static kmem_zone_t *xfs_vnode_zone;
static kmem_zone_t *xfs_ioend_zone;
mempool_t *xfs_ioend_pool;

STATIC struct xfs_mount_args *
xfs_args_allocate(
	struct super_block	*sb,
	int			silent)
{
	struct xfs_mount_args	*args;

	args = kmem_zalloc(sizeof(struct xfs_mount_args), KM_SLEEP);
	args->logbufs = args->logbufsize = -1;
	strncpy(args->fsname, sb->s_id, MAXNAMELEN);

	/* Copy the already-parsed mount(2) flags we're interested in */
	if (sb->s_flags & MS_DIRSYNC)
		args->flags |= XFSMNT_DIRSYNC;
	if (sb->s_flags & MS_SYNCHRONOUS)
		args->flags |= XFSMNT_WSYNC;
	if (silent)
		args->flags |= XFSMNT_QUIET;
	args->flags |= XFSMNT_32BITINODES;

	return args;
}

__uint64_t
xfs_max_file_offset(
	unsigned int		blockshift)
{
	unsigned int		pagefactor = 1;
	unsigned int		bitshift = BITS_PER_LONG - 1;

	/* Figure out maximum filesize, on Linux this can depend on
	 * the filesystem blocksize (on 32 bit platforms).
	 * __block_prepare_write does this in an [unsigned] long...
	 *      page->index << (PAGE_CACHE_SHIFT - bbits)
	 * So, for page sized blocks (4K on 32 bit platforms),
	 * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
	 *      (((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
	 * but for smaller blocksizes it is less (bbits = log2 bsize).
	 * Note1: get_block_t takes a long (implicit cast from above)
	 * Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch
	 * can optionally convert the [unsigned] long from above into
	 * an [unsigned] long long.
	 */

#if BITS_PER_LONG == 32
# if defined(CONFIG_LBD)
	ASSERT(sizeof(sector_t) == 8);
	pagefactor = PAGE_CACHE_SIZE;
	bitshift = BITS_PER_LONG;
# else
	pagefactor = PAGE_CACHE_SIZE >> (PAGE_CACHE_SHIFT - blockshift);
# endif
#endif

	return (((__uint64_t)pagefactor) << bitshift) - 1;
}

STATIC_INLINE void
xfs_set_inodeops(
	struct inode		*inode)
{
	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &xfs_inode_operations;
		inode->i_fop = &xfs_file_operations;
		inode->i_mapping->a_ops = &xfs_address_space_operations;
		break;
	case S_IFDIR:
		inode->i_op = &xfs_dir_inode_operations;
		inode->i_fop = &xfs_dir_file_operations;
		break;
	case S_IFLNK:
		inode->i_op = &xfs_symlink_inode_operations;
		if (inode->i_blocks)
			inode->i_mapping->a_ops = &xfs_address_space_operations;
		break;
	default:
		inode->i_op = &xfs_inode_operations;
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
		break;
	}
}

STATIC_INLINE void
xfs_revalidate_inode(
	xfs_mount_t		*mp,
	bhv_vnode_t		*vp,
	xfs_inode_t		*ip)
{
	struct inode		*inode = vn_to_inode(vp);

	inode->i_mode	= ip->i_d.di_mode;
	inode->i_nlink	= ip->i_d.di_nlink;
	inode->i_uid	= ip->i_d.di_uid;
	inode->i_gid	= ip->i_d.di_gid;

	switch (inode->i_mode & S_IFMT) {
	case S_IFBLK:
	case S_IFCHR:
		inode->i_rdev =
			MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
			      sysv_minor(ip->i_df.if_u2.if_rdev));
		break;
	default:
		inode->i_rdev = 0;
		break;
	}

	inode->i_generation = ip->i_d.di_gen;
	i_size_write(inode, ip->i_d.di_size);
	inode->i_blocks =
		XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
	inode->i_atime.tv_sec	= ip->i_d.di_atime.t_sec;
	inode->i_atime.tv_nsec	= ip->i_d.di_atime.t_nsec;
	inode->i_mtime.tv_sec	= ip->i_d.di_mtime.t_sec;
	inode->i_mtime.tv_nsec	= ip->i_d.di_mtime.t_nsec;
	inode->i_ctime.tv_sec	= ip->i_d.di_ctime.t_sec;
	inode->i_ctime.tv_nsec	= ip->i_d.di_ctime.t_nsec;
	if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
		inode->i_flags |= S_IMMUTABLE;
	else
		inode->i_flags &= ~S_IMMUTABLE;
	if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
		inode->i_flags |= S_APPEND;
	else
		inode->i_flags &= ~S_APPEND;
	if (ip->i_d.di_flags & XFS_DIFLAG_SYNC)
		inode->i_flags |= S_SYNC;
	else
		inode->i_flags &= ~S_SYNC;
	if (ip->i_d.di_flags & XFS_DIFLAG_NOATIME)
		inode->i_flags |= S_NOATIME;
	else
		inode->i_flags &= ~S_NOATIME;
	xfs_iflags_clear(ip, XFS_IMODIFIED);
}

void
xfs_initialize_vnode(
	struct xfs_mount	*mp,
	bhv_vnode_t		*vp,
	struct xfs_inode	*ip)
{
	struct inode		*inode = vn_to_inode(vp);

	if (!ip->i_vnode) {
		ip->i_vnode = vp;
		inode->i_private = ip;
	}

	/*
	 * We need to set the ops vectors, and unlock the inode, but if
	 * we have been called during the new inode create process, it is
	 * too early to fill in the Linux inode.  We will get called a
	 * second time once the inode is properly set up, and then we can
	 * finish our work.
	 */
	if (ip->i_d.di_mode != 0 && (inode->i_state & I_NEW)) {
		xfs_revalidate_inode(mp, vp, ip);
		xfs_set_inodeops(inode);

		xfs_iflags_clear(ip, XFS_INEW);
		barrier();

		unlock_new_inode(inode);
	}
}

int
xfs_blkdev_get(
	xfs_mount_t		*mp,
	const char		*name,
	struct block_device	**bdevp)
{
	int			error = 0;

	*bdevp = open_bdev_excl(name, 0, mp);
	if (IS_ERR(*bdevp)) {
		error = PTR_ERR(*bdevp);
		printk("XFS: Invalid device [%s], error=%d\n", name, error);
	}

	return -error;
}

void
xfs_blkdev_put(
	struct block_device	*bdev)
{
	if (bdev)
		close_bdev_excl(bdev);
}

/*
 * Try to write out the superblock using barriers.
 */
STATIC int
xfs_barrier_test(
	xfs_mount_t	*mp)
{
	xfs_buf_t	*sbp = xfs_getsb(mp, 0);
	int		error;

	XFS_BUF_UNDONE(sbp);
	XFS_BUF_UNREAD(sbp);
	XFS_BUF_UNDELAYWRITE(sbp);
	XFS_BUF_WRITE(sbp);
	XFS_BUF_UNASYNC(sbp);
	XFS_BUF_ORDERED(sbp);

	xfsbdstrat(mp, sbp);
	error = xfs_iowait(sbp);

	/*
	 * Clear all the flags we set and possible error state in the
	 * buffer.  We only did the write to try out whether barriers
	 * worked and shouldn't leave any traces in the superblock
	 * buffer.
	 */
	XFS_BUF_DONE(sbp);
	XFS_BUF_ERROR(sbp, 0);
	XFS_BUF_UNORDERED(sbp);

	xfs_buf_relse(sbp);
	return error;
}

void
xfs_mountfs_check_barriers(xfs_mount_t *mp)
{
	int error;

	if (mp->m_logdev_targp != mp->m_ddev_targp) {
		xfs_fs_cmn_err(CE_NOTE, mp,
		  "Disabling barriers, not supported with external log device");
		mp->m_flags &= ~XFS_MOUNT_BARRIER;
		return;
	}

	if (xfs_readonly_buftarg(mp->m_ddev_targp)) {
		xfs_fs_cmn_err(CE_NOTE, mp,
		  "Disabling barriers, underlying device is readonly");
		mp->m_flags &= ~XFS_MOUNT_BARRIER;
		return;
	}

	error = xfs_barrier_test(mp);
	if (error) {
		xfs_fs_cmn_err(CE_NOTE, mp,
		  "Disabling barriers, trial barrier write failed");
		mp->m_flags &= ~XFS_MOUNT_BARRIER;
		return;
	}
}

void
xfs_blkdev_issue_flush(
	xfs_buftarg_t		*buftarg)
{
	blkdev_issue_flush(buftarg->bt_bdev, NULL);
}

STATIC struct inode *
xfs_fs_alloc_inode(
	struct super_block	*sb)
{
	bhv_vnode_t		*vp;

	vp = kmem_zone_alloc(xfs_vnode_zone, KM_SLEEP);
	if (unlikely(!vp))
		return NULL;
	return vn_to_inode(vp);
}

STATIC void
xfs_fs_destroy_inode(
	struct inode		*inode)
{
	kmem_zone_free(xfs_vnode_zone, vn_from_inode(inode));
}

STATIC void
xfs_fs_inode_init_once(
	void			*vnode,
	kmem_zone_t		*zonep,
	unsigned long		flags)
{
	inode_init_once(vn_to_inode((bhv_vnode_t *)vnode));
}

STATIC int
xfs_init_zones(void)
{
	xfs_vnode_zone = kmem_zone_init_flags(sizeof(bhv_vnode_t), "xfs_vnode",
					KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
					KM_ZONE_SPREAD,
					xfs_fs_inode_init_once);
	if (!xfs_vnode_zone)
		goto out;

	xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
	if (!xfs_ioend_zone)
		goto out_destroy_vnode_zone;

	xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
						  xfs_ioend_zone);
	if (!xfs_ioend_pool)
		goto out_free_ioend_zone;
	return 0;

 out_free_ioend_zone:
	kmem_zone_destroy(xfs_ioend_zone);
 out_destroy_vnode_zone:
	kmem_zone_destroy(xfs_vnode_zone);
 out:
	return -ENOMEM;
}

STATIC void
xfs_destroy_zones(void)
{
	mempool_destroy(xfs_ioend_pool);
	kmem_zone_destroy(xfs_vnode_zone);
	kmem_zone_destroy(xfs_ioend_zone);
}

/*
 * Attempt to flush the inode, this will actually fail
 * if the inode is pinned, but we dirty the inode again
 * at the point when it is unpinned after a log write,
 * since this is when the inode itself becomes flushable.
 */
STATIC int
xfs_fs_write_inode(
	struct inode		*inode,
	int			sync)
{
	int			error = 0, flags = FLUSH_INODE;

	vn_trace_entry(XFS_I(inode), __FUNCTION__,
			(inst_t *)__return_address);
	if (sync) {
		filemap_fdatawait(inode->i_mapping);
		flags |= FLUSH_SYNC;
	}
	error = xfs_inode_flush(XFS_I(inode), flags);
	if (error == EAGAIN) {
		if (sync)
			error = xfs_inode_flush(XFS_I(inode),
						       flags | FLUSH_LOG);
		else
			error = 0;
	}

	return -error;
}

STATIC void
xfs_fs_clear_inode(
	struct inode		*inode)
{
	xfs_inode_t		*ip = XFS_I(inode);

	/*
	 * ip can be null when xfs_iget_core calls xfs_idestroy if we
	 * find an inode with di_mode == 0 but without IGET_CREATE set.
	 */
	if (ip) {
		vn_trace_entry(ip, __FUNCTION__, (inst_t *)__return_address);

		XFS_STATS_INC(vn_rele);
		XFS_STATS_INC(vn_remove);
		XFS_STATS_INC(vn_reclaim);
		XFS_STATS_DEC(vn_active);

		xfs_inactive(ip);
		xfs_iflags_clear(ip, XFS_IMODIFIED);
		if (xfs_reclaim(ip))
			panic("%s: cannot reclaim 0x%p\n", __FUNCTION__, inode);
	}

	ASSERT(XFS_I(inode) == NULL);
}

/*
 * Enqueue a work item to be picked up by the vfs xfssyncd thread.
 * Doing this has two advantages:
 * - It saves on stack space, which is tight in certain situations
 * - It can be used (with care) as a mechanism to avoid deadlocks.
 * Flushing while allocating in a full filesystem requires both.
 */
STATIC void
xfs_syncd_queue_work(
	struct xfs_mount *mp,
	void		*data,
	void		(*syncer)(struct xfs_mount *, void *))
{
	struct bhv_vfs_sync_work *work;

	work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
	INIT_LIST_HEAD(&work->w_list);
	work->w_syncer = syncer;
	work->w_data = data;
	work->w_mount = mp;
	spin_lock(&mp->m_sync_lock);
	list_add_tail(&work->w_list, &mp->m_sync_list);
	spin_unlock(&mp->m_sync_lock);
	wake_up_process(mp->m_sync_task);
}

/*
 * Flush delayed allocate data, attempting to free up reserved space
 * from existing allocations.  At this point a new allocation attempt
 * has failed with ENOSPC and we are in the process of scratching our
 * heads, looking about for more room...
 */
STATIC void
xfs_flush_inode_work(
	struct xfs_mount *mp,
	void		*arg)
{
	struct inode	*inode = arg;
	filemap_flush(inode->i_mapping);
	iput(inode);
}

void
xfs_flush_inode(
	xfs_inode_t	*ip)
{
	struct inode	*inode = ip->i_vnode;

	igrab(inode);
	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
	delay(msecs_to_jiffies(500));
}

/*
 * This is the "bigger hammer" version of xfs_flush_inode_work...
 * (IOW, "If at first you don't succeed, use a Bigger Hammer").
 */
STATIC void
xfs_flush_device_work(
	struct xfs_mount *mp,
	void		*arg)
{
	struct inode	*inode = arg;
	sync_blockdev(mp->m_super->s_bdev);
	iput(inode);
}

void
xfs_flush_device(
	xfs_inode_t	*ip)
{
	struct inode	*inode = vn_to_inode(XFS_ITOV(ip));

	igrab(inode);
	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
	delay(msecs_to_jiffies(500));
	xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
}

STATIC void
xfs_sync_worker(
	struct xfs_mount *mp,
	void		*unused)
{
	int		error;

	if (!(mp->m_flags & XFS_MOUNT_RDONLY))
		error = xfs_sync(mp, SYNC_FSDATA | SYNC_BDFLUSH | SYNC_ATTR |
				     SYNC_REFCACHE | SYNC_SUPER);
	mp->m_sync_seq++;
	wake_up(&mp->m_wait_single_sync_task);
}

STATIC int
xfssyncd(
	void			*arg)
{
	struct xfs_mount	*mp = arg;
	long			timeleft;
	bhv_vfs_sync_work_t	*work, *n;
	LIST_HEAD		(tmp);

	set_freezable();
	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
	for (;;) {
		timeleft = schedule_timeout_interruptible(timeleft);
		/* swsusp */
		try_to_freeze();
		if (kthread_should_stop() && list_empty(&mp->m_sync_list))
			break;

		spin_lock(&mp->m_sync_lock);
		/*
		 * We can get woken by laptop mode, to do a sync -
		 * that's the (only!) case where the list would be
		 * empty with time remaining.
		 */
		if (!timeleft || list_empty(&mp->m_sync_list)) {
			if (!timeleft)
				timeleft = xfs_syncd_centisecs *
							msecs_to_jiffies(10);
			INIT_LIST_HEAD(&mp->m_sync_work.w_list);
			list_add_tail(&mp->m_sync_work.w_list,
					&mp->m_sync_list);
		}
		list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
			list_move(&work->w_list, &tmp);
		spin_unlock(&mp->m_sync_lock);

		list_for_each_entry_safe(work, n, &tmp, w_list) {
			(*work->w_syncer)(mp, work->w_data);
			list_del(&work->w_list);
			if (work == &mp->m_sync_work)
				continue;
			kmem_free(work, sizeof(struct bhv_vfs_sync_work));
		}
	}

	return 0;
}

STATIC void
xfs_fs_put_super(
	struct super_block	*sb)
{
	struct xfs_mount	*mp = XFS_M(sb);
	int			error;

	kthread_stop(mp->m_sync_task);

	xfs_sync(mp, SYNC_ATTR | SYNC_DELWRI);
	error = xfs_unmount(mp, 0, NULL);
	if (error)
		printk("XFS: unmount got error=%d\n", error);
}

STATIC void
xfs_fs_write_super(
	struct super_block	*sb)
{
	if (!(sb->s_flags & MS_RDONLY))
		xfs_sync(XFS_M(sb), SYNC_FSDATA);
	sb->s_dirt = 0;
}

STATIC int
xfs_fs_sync_super(
	struct super_block	*sb,
	int			wait)
{
	struct xfs_mount	*mp = XFS_M(sb);
	int			error;
	int			flags;

	if (unlikely(sb->s_frozen == SB_FREEZE_WRITE)) {
		/*
		 * First stage of freeze - no more writers will make progress
		 * now we are here, so we flush delwri and delalloc buffers
		 * here, then wait for all I/O to complete.  Data is frozen at
		 * that point. Metadata is not frozen, transactions can still
		 * occur here so don't bother flushing the buftarg (i.e
		 * SYNC_QUIESCE) because it'll just get dirty again.
		 */
		flags = SYNC_DATA_QUIESCE;
	} else
		flags = SYNC_FSDATA | (wait ? SYNC_WAIT : 0);

	error = xfs_sync(mp, flags);
	sb->s_dirt = 0;

	if (unlikely(laptop_mode)) {
		int	prev_sync_seq = mp->m_sync_seq;

		/*
		 * The disk must be active because we're syncing.
		 * We schedule xfssyncd now (now that the disk is
		 * active) instead of later (when it might not be).
		 */
		wake_up_process(mp->m_sync_task);
		/*
		 * We have to wait for the sync iteration to complete.
		 * If we don't, the disk activity caused by the sync
		 * will come after the sync is completed, and that
		 * triggers another sync from laptop mode.
		 */
		wait_event(mp->m_wait_single_sync_task,
				mp->m_sync_seq != prev_sync_seq);
	}

	return -error;
}

STATIC int
xfs_fs_statfs(
	struct dentry		*dentry,
	struct kstatfs		*statp)
{
	return -xfs_statvfs(XFS_M(dentry->d_sb), statp,
				vn_from_inode(dentry->d_inode));
}

STATIC int
xfs_fs_remount(
	struct super_block	*sb,
	int			*flags,
	char			*options)
{
	struct xfs_mount	*mp = XFS_M(sb);
	struct xfs_mount_args	*args = xfs_args_allocate(sb, 0);
	int			error;

	error = xfs_parseargs(mp, options, args, 1);
	if (!error)
		error = xfs_mntupdate(mp, flags, args);
	kmem_free(args, sizeof(*args));
	return -error;
}

STATIC void
xfs_fs_lockfs(
	struct super_block	*sb)
{
	xfs_freeze(XFS_M(sb));
}

STATIC int
xfs_fs_show_options(
	struct seq_file		*m,
	struct vfsmount		*mnt)
{
	return -xfs_showargs(XFS_M(mnt->mnt_sb), m);
}

STATIC int
xfs_fs_quotasync(
	struct super_block	*sb,
	int			type)
{
	return -XFS_QM_QUOTACTL(XFS_M(sb), Q_XQUOTASYNC, 0, NULL);
}

STATIC int
xfs_fs_getxstate(
	struct super_block	*sb,
	struct fs_quota_stat	*fqs)
{
	return -XFS_QM_QUOTACTL(XFS_M(sb), Q_XGETQSTAT, 0, (caddr_t)fqs);
}

STATIC int
xfs_fs_setxstate(
	struct super_block	*sb,
	unsigned int		flags,
	int			op)
{
	return -XFS_QM_QUOTACTL(XFS_M(sb), op, 0, (caddr_t)&flags);
}

STATIC int
xfs_fs_getxquota(
	struct super_block	*sb,
	int			type,
	qid_t			id,
	struct fs_disk_quota	*fdq)
{
	return -XFS_QM_QUOTACTL(XFS_M(sb),
				 (type == USRQUOTA) ? Q_XGETQUOTA :
				  ((type == GRPQUOTA) ? Q_XGETGQUOTA :
				   Q_XGETPQUOTA), id, (caddr_t)fdq);
}

STATIC int
xfs_fs_setxquota(
	struct super_block	*sb,
	int			type,
	qid_t			id,
	struct fs_disk_quota	*fdq)
{
	return -XFS_QM_QUOTACTL(XFS_M(sb),
				 (type == USRQUOTA) ? Q_XSETQLIM :
				  ((type == GRPQUOTA) ? Q_XSETGQLIM :
				   Q_XSETPQLIM), id, (caddr_t)fdq);
}

STATIC int
xfs_fs_fill_super(
	struct super_block	*sb,
	void			*data,
	int			silent)
{
	struct inode		*rootvp;
	struct xfs_mount	*mp = NULL;
	struct xfs_mount_args	*args = xfs_args_allocate(sb, silent);
	struct kstatfs		statvfs;
	int			error;

	mp = xfs_mount_init();

	INIT_LIST_HEAD(&mp->m_sync_list);
	spin_lock_init(&mp->m_sync_lock);
	init_waitqueue_head(&mp->m_wait_single_sync_task);

	mp->m_super = sb;
	sb->s_fs_info = mp;

	if (sb->s_flags & MS_RDONLY)
		mp->m_flags |= XFS_MOUNT_RDONLY;

	error = xfs_parseargs(mp, (char *)data, args, 0);
	if (error)
		goto fail_vfsop;

	sb_min_blocksize(sb, BBSIZE);
	sb->s_export_op = &xfs_export_operations;
	sb->s_qcop = &xfs_quotactl_operations;
	sb->s_op = &xfs_super_operations;

	error = xfs_mount(mp, args, NULL);
	if (error)
		goto fail_vfsop;

	error = xfs_statvfs(mp, &statvfs, NULL);
	if (error)
		goto fail_unmount;

	sb->s_dirt = 1;
	sb->s_magic = statvfs.f_type;
	sb->s_blocksize = statvfs.f_bsize;
	sb->s_blocksize_bits = ffs(statvfs.f_bsize) - 1;
	sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
	sb->s_time_gran = 1;
	set_posix_acl_flag(sb);

	error = xfs_root(mp, &rootvp);
	if (error)
		goto fail_unmount;

	sb->s_root = d_alloc_root(vn_to_inode(rootvp));
	if (!sb->s_root) {
		error = ENOMEM;
		goto fail_vnrele;
	}
	if (is_bad_inode(sb->s_root->d_inode)) {
		error = EINVAL;
		goto fail_vnrele;
	}

	mp->m_sync_work.w_syncer = xfs_sync_worker;
	mp->m_sync_work.w_mount = mp;
	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
	if (IS_ERR(mp->m_sync_task)) {
		error = -PTR_ERR(mp->m_sync_task);
		goto fail_vnrele;
	}

	vn_trace_exit(XFS_I(sb->s_root->d_inode), __FUNCTION__,
			(inst_t *)__return_address);

	kmem_free(args, sizeof(*args));
	return 0;

fail_vnrele:
	if (sb->s_root) {
		dput(sb->s_root);
		sb->s_root = NULL;
	} else {
		VN_RELE(rootvp);
	}

fail_unmount:
	xfs_unmount(mp, 0, NULL);

fail_vfsop:
	kmem_free(args, sizeof(*args));
	return -error;
}

STATIC int
xfs_fs_get_sb(
	struct file_system_type	*fs_type,
	int			flags,
	const char		*dev_name,
	void			*data,
	struct vfsmount		*mnt)
{
	return get_sb_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super,
			   mnt);
}

static struct super_operations xfs_super_operations = {
	.alloc_inode		= xfs_fs_alloc_inode,
	.destroy_inode		= xfs_fs_destroy_inode,
	.write_inode		= xfs_fs_write_inode,
	.clear_inode		= xfs_fs_clear_inode,
	.put_super		= xfs_fs_put_super,
	.write_super		= xfs_fs_write_super,
	.sync_fs		= xfs_fs_sync_super,
	.write_super_lockfs	= xfs_fs_lockfs,
	.statfs			= xfs_fs_statfs,
	.remount_fs		= xfs_fs_remount,
	.show_options		= xfs_fs_show_options,
};

static struct quotactl_ops xfs_quotactl_operations = {
	.quota_sync		= xfs_fs_quotasync,
	.get_xstate		= xfs_fs_getxstate,
	.set_xstate		= xfs_fs_setxstate,
	.get_xquota		= xfs_fs_getxquota,
	.set_xquota		= xfs_fs_setxquota,
};

static struct file_system_type xfs_fs_type = {
	.owner			= THIS_MODULE,
	.name			= "xfs",
	.get_sb			= xfs_fs_get_sb,
	.kill_sb		= kill_block_super,
	.fs_flags		= FS_REQUIRES_DEV,
};


STATIC int __init
init_xfs_fs( void )
{
	int			error;
	static char		message[] __initdata = KERN_INFO \
		XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled\n";

	printk(message);

	ktrace_init(64);

	error = xfs_init_zones();
	if (error < 0)
		goto undo_zones;

	error = xfs_buf_init();
	if (error < 0)
		goto undo_buffers;

	vn_init();
	xfs_init();
	uuid_init();
	vfs_initquota();

	error = register_filesystem(&xfs_fs_type);
	if (error)
		goto undo_register;
	return 0;

undo_register:
	xfs_buf_terminate();

undo_buffers:
	xfs_destroy_zones();

undo_zones:
	return error;
}

STATIC void __exit
exit_xfs_fs( void )
{
	vfs_exitquota();
	unregister_filesystem(&xfs_fs_type);
	xfs_cleanup();
	xfs_buf_terminate();
	xfs_destroy_zones();
	ktrace_uninit();
}

module_init(init_xfs_fs);
module_exit(exit_xfs_fs);

MODULE_AUTHOR("Silicon Graphics, Inc.");
MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled");
MODULE_LICENSE("GPL");