summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_fsops.c
blob: ca3cf3f6239a579cf8f838bbe8dda65255ca6c30 (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
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
/*
 * Copyright (c) 2000-2005 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_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_error.h"
#include "xfs_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_rmap_btree.h"
#include "xfs_ialloc.h"
#include "xfs_fsops.h"
#include "xfs_itable.h"
#include "xfs_trans_space.h"
#include "xfs_rtalloc.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_filestream.h"
#include "xfs_rmap.h"
#include "xfs_ag_resv.h"

/*
 * File system operations
 */

static struct xfs_buf *
xfs_growfs_get_hdr_buf(
	struct xfs_mount	*mp,
	xfs_daddr_t		blkno,
	size_t			numblks,
	int			flags,
	const struct xfs_buf_ops *ops)
{
	struct xfs_buf		*bp;

	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
	if (!bp)
		return NULL;

	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
	bp->b_bn = blkno;
	bp->b_maps[0].bm_bn = blkno;
	bp->b_ops = ops;

	return bp;
}

struct aghdr_init_data {
	/* per ag data */
	xfs_agnumber_t		agno;		/* ag to init */
	xfs_extlen_t		agsize;		/* new AG size */
	struct list_head	buffer_list;	/* buffer writeback list */
	xfs_rfsblock_t		nfree;		/* cumulative new free space */

	/* per header data */
	xfs_daddr_t		daddr;		/* header location */
	size_t			numblks;	/* size of header */
	xfs_btnum_t		type;		/* type of btree root block */
};

/*
 * Generic btree root block init function
 */
static void
xfs_btroot_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno, 0);
}

/*
 * Alloc btree root block init functions
 */
static void
xfs_bnoroot_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_alloc_rec	*arec;

	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno, 0);
	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
	arec->ar_blockcount = cpu_to_be32(id->agsize -
					  be32_to_cpu(arec->ar_startblock));
}

static void
xfs_cntroot_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_alloc_rec	*arec;

	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno, 0);
	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
	arec->ar_blockcount = cpu_to_be32(id->agsize -
					  be32_to_cpu(arec->ar_startblock));
}

/*
 * Reverse map root block init
 */
static void
xfs_rmaproot_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
	struct xfs_rmap_rec	*rrec;

	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno, 0);

	/*
	 * mark the AG header regions as static metadata The BNO
	 * btree block is the first block after the headers, so
	 * it's location defines the size of region the static
	 * metadata consumes.
	 *
	 * Note: unlike mkfs, we never have to account for log
	 * space when growing the data regions
	 */
	rrec = XFS_RMAP_REC_ADDR(block, 1);
	rrec->rm_startblock = 0;
	rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
	rrec->rm_offset = 0;

	/* account freespace btree root blocks */
	rrec = XFS_RMAP_REC_ADDR(block, 2);
	rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
	rrec->rm_blockcount = cpu_to_be32(2);
	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
	rrec->rm_offset = 0;

	/* account inode btree root blocks */
	rrec = XFS_RMAP_REC_ADDR(block, 3);
	rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
	rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
					  XFS_IBT_BLOCK(mp));
	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
	rrec->rm_offset = 0;

	/* account for rmap btree root */
	rrec = XFS_RMAP_REC_ADDR(block, 4);
	rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
	rrec->rm_blockcount = cpu_to_be32(1);
	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
	rrec->rm_offset = 0;

	/* account for refc btree root */
	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
		rrec = XFS_RMAP_REC_ADDR(block, 5);
		rrec->rm_startblock = cpu_to_be32(xfs_refc_block(mp));
		rrec->rm_blockcount = cpu_to_be32(1);
		rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
		rrec->rm_offset = 0;
		be16_add_cpu(&block->bb_numrecs, 1);
	}
}

/*
 * Initialise new secondary superblocks with the pre-grow geometry, but mark
 * them as "in progress" so we know they haven't yet been activated. This will
 * get cleared when the update with the new geometry information is done after
 * changes to the primary are committed. This isn't strictly necessary, but we
 * get it for free with the delayed buffer write lists and it means we can tell
 * if a grow operation didn't complete properly after the fact.
 */
static void
xfs_sbblock_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);

	xfs_sb_to_disk(dsb, &mp->m_sb);
	dsb->sb_inprogress = 1;
}

static void
xfs_agfblock_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_agf		*agf = XFS_BUF_TO_AGF(bp);
	xfs_extlen_t		tmpsize;

	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
	agf->agf_seqno = cpu_to_be32(id->agno);
	agf->agf_length = cpu_to_be32(id->agsize);
	agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
	agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
	agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
	agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
		agf->agf_roots[XFS_BTNUM_RMAPi] =
					cpu_to_be32(XFS_RMAP_BLOCK(mp));
		agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
		agf->agf_rmap_blocks = cpu_to_be32(1);
	}

	agf->agf_flfirst = cpu_to_be32(1);
	agf->agf_fllast = 0;
	agf->agf_flcount = 0;
	tmpsize = id->agsize - mp->m_ag_prealloc_blocks;
	agf->agf_freeblks = cpu_to_be32(tmpsize);
	agf->agf_longest = cpu_to_be32(tmpsize);
	if (xfs_sb_version_hascrc(&mp->m_sb))
		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
		agf->agf_refcount_root = cpu_to_be32(
				xfs_refc_block(mp));
		agf->agf_refcount_level = cpu_to_be32(1);
		agf->agf_refcount_blocks = cpu_to_be32(1);
	}
}

static void
xfs_agflblock_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_agfl		*agfl = XFS_BUF_TO_AGFL(bp);
	__be32			*agfl_bno;
	int			bucket;

	if (xfs_sb_version_hascrc(&mp->m_sb)) {
		agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
		agfl->agfl_seqno = cpu_to_be32(id->agno);
		uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
	}

	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
	for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
		agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
}

static void
xfs_agiblock_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct aghdr_init_data	*id)
{
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(bp);
	int			bucket;

	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
	agi->agi_seqno = cpu_to_be32(id->agno);
	agi->agi_length = cpu_to_be32(id->agsize);
	agi->agi_count = 0;
	agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
	agi->agi_level = cpu_to_be32(1);
	agi->agi_freecount = 0;
	agi->agi_newino = cpu_to_be32(NULLAGINO);
	agi->agi_dirino = cpu_to_be32(NULLAGINO);
	if (xfs_sb_version_hascrc(&mp->m_sb))
		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
		agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
		agi->agi_free_level = cpu_to_be32(1);
	}
	for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
		agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
}

typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp,
				  struct aghdr_init_data *id);
static int
xfs_growfs_init_aghdr(
	struct xfs_mount	*mp,
	struct aghdr_init_data	*id,
	aghdr_init_work_f	work,
	const struct xfs_buf_ops *ops)

{
	struct xfs_buf		*bp;

	bp = xfs_growfs_get_hdr_buf(mp, id->daddr, id->numblks, 0, ops);
	if (!bp)
		return -ENOMEM;

	(*work)(mp, bp, id);

	xfs_buf_delwri_queue(bp, &id->buffer_list);
	xfs_buf_relse(bp);
	return 0;
}

struct xfs_aghdr_grow_data {
	xfs_daddr_t		daddr;
	size_t			numblks;
	const struct xfs_buf_ops *ops;
	aghdr_init_work_f	work;
	xfs_btnum_t		type;
	bool			need_init;
};

/*
 * Write new AG headers to disk. Non-transactional, but written
 * synchronously so they are completed prior to the growfs transaction
 * being logged.
 */
static int
xfs_grow_ag_headers(
	struct xfs_mount	*mp,
	struct aghdr_init_data	*id)

{
	struct xfs_aghdr_grow_data aghdr_data[] = {
	{ /* SB */
		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_SB_DADDR),
		.numblks = XFS_FSS_TO_BB(mp, 1),
		.ops = &xfs_sb_buf_ops,
		.work = &xfs_sbblock_init,
		.need_init = true
	},
	{ /* AGF */
		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGF_DADDR(mp)),
		.numblks = XFS_FSS_TO_BB(mp, 1),
		.ops = &xfs_agf_buf_ops,
		.work = &xfs_agfblock_init,
		.need_init = true
	},
	{ /* AGFL */
		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGFL_DADDR(mp)),
		.numblks = XFS_FSS_TO_BB(mp, 1),
		.ops = &xfs_agfl_buf_ops,
		.work = &xfs_agflblock_init,
		.need_init = true
	},
	{ /* AGI */
		.daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGI_DADDR(mp)),
		.numblks = XFS_FSS_TO_BB(mp, 1),
		.ops = &xfs_agi_buf_ops,
		.work = &xfs_agiblock_init,
		.need_init = true
	},
	{ /* BNO root block */
		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_BNO_BLOCK(mp)),
		.numblks = BTOBB(mp->m_sb.sb_blocksize),
		.ops = &xfs_allocbt_buf_ops,
		.work = &xfs_bnoroot_init,
		.need_init = true
	},
	{ /* CNT root block */
		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
		.numblks = BTOBB(mp->m_sb.sb_blocksize),
		.ops = &xfs_allocbt_buf_ops,
		.work = &xfs_cntroot_init,
		.need_init = true
	},
	{ /* INO root block */
		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_IBT_BLOCK(mp)),
		.numblks = BTOBB(mp->m_sb.sb_blocksize),
		.ops = &xfs_inobt_buf_ops,
		.work = &xfs_btroot_init,
		.type = XFS_BTNUM_INO,
		.need_init = true
	},
	{ /* FINO root block */
		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_FIBT_BLOCK(mp)),
		.numblks = BTOBB(mp->m_sb.sb_blocksize),
		.ops = &xfs_inobt_buf_ops,
		.work = &xfs_btroot_init,
		.type = XFS_BTNUM_FINO,
		.need_init =  xfs_sb_version_hasfinobt(&mp->m_sb)
	},
	{ /* RMAP root block */
		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_RMAP_BLOCK(mp)),
		.numblks = BTOBB(mp->m_sb.sb_blocksize),
		.ops = &xfs_rmapbt_buf_ops,
		.work = &xfs_rmaproot_init,
		.need_init = xfs_sb_version_hasrmapbt(&mp->m_sb)
	},
	{ /* REFC root block */
		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, xfs_refc_block(mp)),
		.numblks = BTOBB(mp->m_sb.sb_blocksize),
		.ops = &xfs_refcountbt_buf_ops,
		.work = &xfs_btroot_init,
		.type = XFS_BTNUM_REFC,
		.need_init = xfs_sb_version_hasreflink(&mp->m_sb)
	},
	{ /* NULL terminating block */
		.daddr = XFS_BUF_DADDR_NULL,
	}
	};
	struct  xfs_aghdr_grow_data *dp;
	int			error = 0;

	/* Account for AG free space in new AG */
	id->nfree += id->agsize - mp->m_ag_prealloc_blocks;
	for (dp = &aghdr_data[0]; dp->daddr != XFS_BUF_DADDR_NULL; dp++) {
		if (!dp->need_init)
			continue;

		id->daddr = dp->daddr;
		id->numblks = dp->numblks;
		id->type = dp->type;
		error = xfs_growfs_init_aghdr(mp, id, dp->work, dp->ops);
		if (error)
			break;
	}
	return error;
}

static int
xfs_growfs_data_private(
	xfs_mount_t		*mp,		/* mount point for filesystem */
	xfs_growfs_data_t	*in)		/* growfs data input struct */
{
	xfs_agf_t		*agf;
	xfs_agi_t		*agi;
	xfs_buf_t		*bp;
	int			error;
	xfs_agnumber_t		nagcount;
	xfs_agnumber_t		nagimax = 0;
	xfs_rfsblock_t		nb, nb_mod;
	xfs_rfsblock_t		new;
	xfs_agnumber_t		oagcount;
	xfs_trans_t		*tp;
	LIST_HEAD		(buffer_list);
	struct aghdr_init_data	id = {};

	nb = in->newblocks;
	if (nb < mp->m_sb.sb_dblocks)
		return -EINVAL;
	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
		return error;
	error = xfs_buf_read_uncached(mp->m_ddev_targp,
				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
	if (error)
		return error;
	xfs_buf_relse(bp);

	new = nb;	/* use new as a temporary here */
	nb_mod = do_div(new, mp->m_sb.sb_agblocks);
	nagcount = new + (nb_mod != 0);
	if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
		nagcount--;
		nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
		if (nb < mp->m_sb.sb_dblocks)
			return -EINVAL;
	}
	new = nb - mp->m_sb.sb_dblocks;
	oagcount = mp->m_sb.sb_agcount;

	/* allocate the new per-ag structures */
	if (nagcount > oagcount) {
		error = xfs_initialize_perag(mp, nagcount, &nagimax);
		if (error)
			return error;
	}

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
			XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
	if (error)
		return error;

	/*
	 * Write new AG headers to disk. Non-transactional, but need to be
	 * written and completed prior to the growfs transaction being logged.
	 * To do this, we use a delayed write buffer list and wait for
	 * submission and IO completion of the list as a whole. This allows the
	 * IO subsystem to merge all the AG headers in a single AG into a single
	 * IO and hide most of the latency of the IO from us.
	 *
	 * This also means that if we get an error whilst building the buffer
	 * list to write, we can cancel the entire list without having written
	 * anything.
	 */
	INIT_LIST_HEAD(&id.buffer_list);
	for (id.agno = nagcount - 1;
	     id.agno >= oagcount;
	     id.agno--, new -= id.agsize) {

		if (id.agno == nagcount - 1)
			id.agsize = nb -
				(id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
		else
			id.agsize = mp->m_sb.sb_agblocks;

		error = xfs_grow_ag_headers(mp, &id);
		if (error) {
			xfs_buf_delwri_cancel(&id.buffer_list);
			goto out_trans_cancel;
		}
	}
	error = xfs_buf_delwri_submit(&id.buffer_list);
	if (error)
		goto out_trans_cancel;

	xfs_trans_agblocks_delta(tp, id.nfree);

	/*
	 * There are new blocks in the old last a.g.
	 */
	if (new) {
		struct xfs_owner_info	oinfo;

		/*
		 * Change the agi length.
		 */
		error = xfs_ialloc_read_agi(mp, tp, id.agno, &bp);
		if (error)
			goto out_trans_cancel;

		ASSERT(bp);
		agi = XFS_BUF_TO_AGI(bp);
		be32_add_cpu(&agi->agi_length, new);
		ASSERT(nagcount == oagcount ||
		       be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
		xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);

		/*
		 * Change agf length.
		 */
		error = xfs_alloc_read_agf(mp, tp, id.agno, 0, &bp);
		if (error)
			goto out_trans_cancel;

		ASSERT(bp);
		agf = XFS_BUF_TO_AGF(bp);
		be32_add_cpu(&agf->agf_length, new);
		ASSERT(be32_to_cpu(agf->agf_length) ==
		       be32_to_cpu(agi->agi_length));

		xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);

		/*
		 * Free the new space.
		 *
		 * XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
		 * this doesn't actually exist in the rmap btree.
		 */
		xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
		error = xfs_rmap_free(tp, bp, id.agno,
				be32_to_cpu(agf->agf_length) - new,
				new, &oinfo);
		if (error)
			goto out_trans_cancel;
		error = xfs_free_extent(tp,
				XFS_AGB_TO_FSB(mp, id.agno,
					be32_to_cpu(agf->agf_length) - new),
				new, &oinfo, XFS_AG_RESV_NONE);
		if (error)
			goto out_trans_cancel;
	}

	/*
	 * Update changed superblock fields transactionally. These are not
	 * seen by the rest of the world until the transaction commit applies
	 * them atomically to the superblock.
	 */
	if (nagcount > oagcount)
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
	if (nb > mp->m_sb.sb_dblocks)
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
				 nb - mp->m_sb.sb_dblocks);
	if (id.nfree)
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
	xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp);
	if (error)
		return error;

	/* New allocation groups fully initialized, so update mount struct */
	if (nagimax)
		mp->m_maxagi = nagimax;
	xfs_set_low_space_thresholds(mp);
	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);

	/*
	 * If we expanded the last AG, free the per-AG reservation
	 * so we can reinitialize it with the new size.
	 */
	if (new) {
		struct xfs_perag	*pag;

		pag = xfs_perag_get(mp, id.agno);
		error = xfs_ag_resv_free(pag);
		xfs_perag_put(pag);
		if (error)
			return error;
	}

	/*
	 * Reserve AG metadata blocks. ENOSPC here does not mean there was a
	 * growfs failure, just that there still isn't space for new user data
	 * after the grow has been run.
	 */
	error = xfs_fs_reserve_ag_blocks(mp);
	if (error == -ENOSPC)
		error = 0;
	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	return error;
}

static int
xfs_growfs_log_private(
	xfs_mount_t		*mp,	/* mount point for filesystem */
	xfs_growfs_log_t	*in)	/* growfs log input struct */
{
	xfs_extlen_t		nb;

	nb = in->newblocks;
	if (nb < XFS_MIN_LOG_BLOCKS || nb < XFS_B_TO_FSB(mp, XFS_MIN_LOG_BYTES))
		return -EINVAL;
	if (nb == mp->m_sb.sb_logblocks &&
	    in->isint == (mp->m_sb.sb_logstart != 0))
		return -EINVAL;
	/*
	 * Moving the log is hard, need new interfaces to sync
	 * the log first, hold off all activity while moving it.
	 * Can have shorter or longer log in the same space,
	 * or transform internal to external log or vice versa.
	 */
	return -ENOSYS;
}

static int
xfs_growfs_imaxpct(
	struct xfs_mount	*mp,
	__u32			imaxpct)
{
	struct xfs_trans	*tp;
	int			dpct;
	int			error;

	if (imaxpct > 100)
		return -EINVAL;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
			XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
	if (error)
		return error;

	dpct = imaxpct - mp->m_sb.sb_imax_pct;
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
	xfs_trans_set_sync(tp);
	return xfs_trans_commit(tp);
}

/*
 * After a grow operation, we need to update all the secondary superblocks
 * to match the new state of the primary. Because we are completely overwriting
 * all the existing fields in the secondary superblock buffers, there is no need
 * to read them in from disk. Just get a new buffer, stamp it and write it.
 *
 * The sb buffers need to be cached here so that we serialise against scrub
 * scanning secondary superblocks, but we don't want to keep it in memory once
 * it is written so we mark it as a one-shot buffer.
 */
static int
xfs_growfs_update_superblocks(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	int			saved_error = 0;
	int			error = 0;
	LIST_HEAD		(buffer_list);

	/* update secondary superblocks. */
	for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) {
		struct xfs_buf		*bp;

		bp = xfs_buf_get(mp->m_ddev_targp,
				 XFS_AG_DADDR(mp, agno, XFS_SB_DADDR),
				 XFS_FSS_TO_BB(mp, 1), 0);
		/*
		 * If we get an error reading or writing alternate superblocks,
		 * continue.  xfs_repair chooses the "best" superblock based
		 * on most matches; if we break early, we'll leave more
		 * superblocks un-updated than updated, and xfs_repair may
		 * pick them over the properly-updated primary.
		 */
		if (!bp) {
			xfs_warn(mp,
		"error allocating secondary superblock for ag %d",
				agno);
			if (!saved_error)
				saved_error = -ENOMEM;
			continue;
		}

		bp->b_ops = &xfs_sb_buf_ops;
		xfs_buf_oneshot(bp);
		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
		xfs_buf_delwri_queue(bp, &buffer_list);
		xfs_buf_relse(bp);

		/* don't hold too many buffers at once */
		if (agno % 16)
			continue;

		error = xfs_buf_delwri_submit(&buffer_list);
		if (error) {
			xfs_warn(mp,
		"write error %d updating a secondary superblock near ag %d",
				error, agno);
			if (!saved_error)
				saved_error = error;
			continue;
		}
	}
	error = xfs_buf_delwri_submit(&buffer_list);
	if (error) {
		xfs_warn(mp,
		"write error %d updating a secondary superblock near ag %d",
			error, agno);
	}

	return saved_error ? saved_error : error;
}

/*
 * protected versions of growfs function acquire and release locks on the mount
 * point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
 * XFS_IOC_FSGROWFSRT
 */
int
xfs_growfs_data(
	struct xfs_mount	*mp,
	struct xfs_growfs_data	*in)
{
	int			error = 0;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!mutex_trylock(&mp->m_growlock))
		return -EWOULDBLOCK;

	/* update imaxpct separately to the physical grow of the filesystem */
	if (in->imaxpct != mp->m_sb.sb_imax_pct) {
		error = xfs_growfs_imaxpct(mp, in->imaxpct);
		if (error)
			goto out_error;
	}

	if (in->newblocks != mp->m_sb.sb_dblocks) {
		error = xfs_growfs_data_private(mp, in);
		if (error)
			goto out_error;
	}

	/* Post growfs calculations needed to reflect new state in operations */
	if (mp->m_sb.sb_imax_pct) {
		uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
		do_div(icount, 100);
		mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
	} else
		mp->m_maxicount = 0;

	/* Update secondary superblocks now the physical grow has completed */
	error = xfs_growfs_update_superblocks(mp);

out_error:
	/*
	 * Increment the generation unconditionally, the error could be from
	 * updating the secondary superblocks, in which case the new size
	 * is live already.
	 */
	mp->m_generation++;
	mutex_unlock(&mp->m_growlock);
	return error;
}

int
xfs_growfs_log(
	xfs_mount_t		*mp,
	xfs_growfs_log_t	*in)
{
	int error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!mutex_trylock(&mp->m_growlock))
		return -EWOULDBLOCK;
	error = xfs_growfs_log_private(mp, in);
	mutex_unlock(&mp->m_growlock);
	return error;
}

/*
 * exported through ioctl XFS_IOC_FSCOUNTS
 */

int
xfs_fs_counts(
	xfs_mount_t		*mp,
	xfs_fsop_counts_t	*cnt)
{
	cnt->allocino = percpu_counter_read_positive(&mp->m_icount);
	cnt->freeino = percpu_counter_read_positive(&mp->m_ifree);
	cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
						mp->m_alloc_set_aside;

	spin_lock(&mp->m_sb_lock);
	cnt->freertx = mp->m_sb.sb_frextents;
	spin_unlock(&mp->m_sb_lock);
	return 0;
}

/*
 * exported through ioctl XFS_IOC_SET_RESBLKS & XFS_IOC_GET_RESBLKS
 *
 * xfs_reserve_blocks is called to set m_resblks
 * in the in-core mount table. The number of unused reserved blocks
 * is kept in m_resblks_avail.
 *
 * Reserve the requested number of blocks if available. Otherwise return
 * as many as possible to satisfy the request. The actual number
 * reserved are returned in outval
 *
 * A null inval pointer indicates that only the current reserved blocks
 * available  should  be returned no settings are changed.
 */

int
xfs_reserve_blocks(
	xfs_mount_t             *mp,
	uint64_t              *inval,
	xfs_fsop_resblks_t      *outval)
{
	int64_t			lcounter, delta;
	int64_t			fdblks_delta = 0;
	uint64_t		request;
	int64_t			free;
	int			error = 0;

	/* If inval is null, report current values and return */
	if (inval == (uint64_t *)NULL) {
		if (!outval)
			return -EINVAL;
		outval->resblks = mp->m_resblks;
		outval->resblks_avail = mp->m_resblks_avail;
		return 0;
	}

	request = *inval;

	/*
	 * With per-cpu counters, this becomes an interesting problem. we need
	 * to work out if we are freeing or allocation blocks first, then we can
	 * do the modification as necessary.
	 *
	 * We do this under the m_sb_lock so that if we are near ENOSPC, we will
	 * hold out any changes while we work out what to do. This means that
	 * the amount of free space can change while we do this, so we need to
	 * retry if we end up trying to reserve more space than is available.
	 */
	spin_lock(&mp->m_sb_lock);

	/*
	 * If our previous reservation was larger than the current value,
	 * then move any unused blocks back to the free pool. Modify the resblks
	 * counters directly since we shouldn't have any problems unreserving
	 * space.
	 */
	if (mp->m_resblks > request) {
		lcounter = mp->m_resblks_avail - request;
		if (lcounter  > 0) {		/* release unused blocks */
			fdblks_delta = lcounter;
			mp->m_resblks_avail -= lcounter;
		}
		mp->m_resblks = request;
		if (fdblks_delta) {
			spin_unlock(&mp->m_sb_lock);
			error = xfs_mod_fdblocks(mp, fdblks_delta, 0);
			spin_lock(&mp->m_sb_lock);
		}

		goto out;
	}

	/*
	 * If the request is larger than the current reservation, reserve the
	 * blocks before we update the reserve counters. Sample m_fdblocks and
	 * perform a partial reservation if the request exceeds free space.
	 */
	error = -ENOSPC;
	do {
		free = percpu_counter_sum(&mp->m_fdblocks) -
						mp->m_alloc_set_aside;
		if (!free)
			break;

		delta = request - mp->m_resblks;
		lcounter = free - delta;
		if (lcounter < 0)
			/* We can't satisfy the request, just get what we can */
			fdblks_delta = free;
		else
			fdblks_delta = delta;

		/*
		 * We'll either succeed in getting space from the free block
		 * count or we'll get an ENOSPC. If we get a ENOSPC, it means
		 * things changed while we were calculating fdblks_delta and so
		 * we should try again to see if there is anything left to
		 * reserve.
		 *
		 * Don't set the reserved flag here - we don't want to reserve
		 * the extra reserve blocks from the reserve.....
		 */
		spin_unlock(&mp->m_sb_lock);
		error = xfs_mod_fdblocks(mp, -fdblks_delta, 0);
		spin_lock(&mp->m_sb_lock);
	} while (error == -ENOSPC);

	/*
	 * Update the reserve counters if blocks have been successfully
	 * allocated.
	 */
	if (!error && fdblks_delta) {
		mp->m_resblks += fdblks_delta;
		mp->m_resblks_avail += fdblks_delta;
	}

out:
	if (outval) {
		outval->resblks = mp->m_resblks;
		outval->resblks_avail = mp->m_resblks_avail;
	}

	spin_unlock(&mp->m_sb_lock);
	return error;
}

int
xfs_fs_goingdown(
	xfs_mount_t	*mp,
	uint32_t	inflags)
{
	switch (inflags) {
	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
		struct super_block *sb = freeze_bdev(mp->m_super->s_bdev);

		if (sb && !IS_ERR(sb)) {
			xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
			thaw_bdev(sb->s_bdev, sb);
		}

		break;
	}
	case XFS_FSOP_GOING_FLAGS_LOGFLUSH:
		xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
		break;
	case XFS_FSOP_GOING_FLAGS_NOLOGFLUSH:
		xfs_force_shutdown(mp,
				SHUTDOWN_FORCE_UMOUNT | SHUTDOWN_LOG_IO_ERROR);
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

/*
 * Force a shutdown of the filesystem instantly while keeping the filesystem
 * consistent. We don't do an unmount here; just shutdown the shop, make sure
 * that absolutely nothing persistent happens to this filesystem after this
 * point.
 */
void
xfs_do_force_shutdown(
	xfs_mount_t	*mp,
	int		flags,
	char		*fname,
	int		lnnum)
{
	int		logerror;

	logerror = flags & SHUTDOWN_LOG_IO_ERROR;

	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
		xfs_notice(mp,
	"%s(0x%x) called from line %d of file %s.  Return address = "PTR_FMT,
			__func__, flags, lnnum, fname, __return_address);
	}
	/*
	 * No need to duplicate efforts.
	 */
	if (XFS_FORCED_SHUTDOWN(mp) && !logerror)
		return;

	/*
	 * This flags XFS_MOUNT_FS_SHUTDOWN, makes sure that we don't
	 * queue up anybody new on the log reservations, and wakes up
	 * everybody who's sleeping on log reservations to tell them
	 * the bad news.
	 */
	if (xfs_log_force_umount(mp, logerror))
		return;

	if (flags & SHUTDOWN_CORRUPT_INCORE) {
		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
    "Corruption of in-memory data detected.  Shutting down filesystem");
		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
			xfs_stack_trace();
	} else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
		if (logerror) {
			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
		"Log I/O Error Detected.  Shutting down filesystem");
		} else if (flags & SHUTDOWN_DEVICE_REQ) {
			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
		"All device paths lost.  Shutting down filesystem");
		} else if (!(flags & SHUTDOWN_REMOTE_REQ)) {
			xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
		"I/O Error Detected. Shutting down filesystem");
		}
	}
	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
		xfs_alert(mp,
	"Please umount the filesystem and rectify the problem(s)");
	}
}

/*
 * Reserve free space for per-AG metadata.
 */
int
xfs_fs_reserve_ag_blocks(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	struct xfs_perag	*pag;
	int			error = 0;
	int			err2;

	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
		pag = xfs_perag_get(mp, agno);
		err2 = xfs_ag_resv_init(pag);
		xfs_perag_put(pag);
		if (err2 && !error)
			error = err2;
	}

	if (error && error != -ENOSPC) {
		xfs_warn(mp,
	"Error %d reserving per-AG metadata reserve pool.", error);
		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
	}

	return error;
}

/*
 * Free space reserved for per-AG metadata.
 */
int
xfs_fs_unreserve_ag_blocks(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	struct xfs_perag	*pag;
	int			error = 0;
	int			err2;

	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
		pag = xfs_perag_get(mp, agno);
		err2 = xfs_ag_resv_free(pag);
		xfs_perag_put(pag);
		if (err2 && !error)
			error = err2;
	}

	if (error)
		xfs_warn(mp,
	"Error %d freeing per-AG metadata reserve pool.", error);

	return error;
}