summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_fsmap.c
blob: ae18ab86e608b5d9c23414d0b90cb369bf6e863f (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
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2017 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 */
#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_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_btree.h"
#include "xfs_rmap_btree.h"
#include "xfs_trace.h"
#include "xfs_rmap.h"
#include "xfs_alloc.h"
#include "xfs_bit.h"
#include <linux/fsmap.h>
#include "xfs_fsmap.h"
#include "xfs_refcount.h"
#include "xfs_refcount_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_rtbitmap.h"
#include "xfs_ag.h"

/* Convert an xfs_fsmap to an fsmap. */
static void
xfs_fsmap_from_internal(
	struct fsmap		*dest,
	struct xfs_fsmap	*src)
{
	dest->fmr_device = src->fmr_device;
	dest->fmr_flags = src->fmr_flags;
	dest->fmr_physical = BBTOB(src->fmr_physical);
	dest->fmr_owner = src->fmr_owner;
	dest->fmr_offset = BBTOB(src->fmr_offset);
	dest->fmr_length = BBTOB(src->fmr_length);
	dest->fmr_reserved[0] = 0;
	dest->fmr_reserved[1] = 0;
	dest->fmr_reserved[2] = 0;
}

/* Convert an fsmap to an xfs_fsmap. */
static void
xfs_fsmap_to_internal(
	struct xfs_fsmap	*dest,
	struct fsmap		*src)
{
	dest->fmr_device = src->fmr_device;
	dest->fmr_flags = src->fmr_flags;
	dest->fmr_physical = BTOBBT(src->fmr_physical);
	dest->fmr_owner = src->fmr_owner;
	dest->fmr_offset = BTOBBT(src->fmr_offset);
	dest->fmr_length = BTOBBT(src->fmr_length);
}

/* Convert an fsmap owner into an rmapbt owner. */
static int
xfs_fsmap_owner_to_rmap(
	struct xfs_rmap_irec	*dest,
	const struct xfs_fsmap	*src)
{
	if (!(src->fmr_flags & FMR_OF_SPECIAL_OWNER)) {
		dest->rm_owner = src->fmr_owner;
		return 0;
	}

	switch (src->fmr_owner) {
	case 0:			/* "lowest owner id possible" */
	case -1ULL:		/* "highest owner id possible" */
		dest->rm_owner = src->fmr_owner;
		break;
	case XFS_FMR_OWN_FREE:
		dest->rm_owner = XFS_RMAP_OWN_NULL;
		break;
	case XFS_FMR_OWN_UNKNOWN:
		dest->rm_owner = XFS_RMAP_OWN_UNKNOWN;
		break;
	case XFS_FMR_OWN_FS:
		dest->rm_owner = XFS_RMAP_OWN_FS;
		break;
	case XFS_FMR_OWN_LOG:
		dest->rm_owner = XFS_RMAP_OWN_LOG;
		break;
	case XFS_FMR_OWN_AG:
		dest->rm_owner = XFS_RMAP_OWN_AG;
		break;
	case XFS_FMR_OWN_INOBT:
		dest->rm_owner = XFS_RMAP_OWN_INOBT;
		break;
	case XFS_FMR_OWN_INODES:
		dest->rm_owner = XFS_RMAP_OWN_INODES;
		break;
	case XFS_FMR_OWN_REFC:
		dest->rm_owner = XFS_RMAP_OWN_REFC;
		break;
	case XFS_FMR_OWN_COW:
		dest->rm_owner = XFS_RMAP_OWN_COW;
		break;
	case XFS_FMR_OWN_DEFECTIVE:	/* not implemented */
		/* fall through */
	default:
		return -EINVAL;
	}
	return 0;
}

/* Convert an rmapbt owner into an fsmap owner. */
static int
xfs_fsmap_owner_from_rmap(
	struct xfs_fsmap		*dest,
	const struct xfs_rmap_irec	*src)
{
	dest->fmr_flags = 0;
	if (!XFS_RMAP_NON_INODE_OWNER(src->rm_owner)) {
		dest->fmr_owner = src->rm_owner;
		return 0;
	}
	dest->fmr_flags |= FMR_OF_SPECIAL_OWNER;

	switch (src->rm_owner) {
	case XFS_RMAP_OWN_FS:
		dest->fmr_owner = XFS_FMR_OWN_FS;
		break;
	case XFS_RMAP_OWN_LOG:
		dest->fmr_owner = XFS_FMR_OWN_LOG;
		break;
	case XFS_RMAP_OWN_AG:
		dest->fmr_owner = XFS_FMR_OWN_AG;
		break;
	case XFS_RMAP_OWN_INOBT:
		dest->fmr_owner = XFS_FMR_OWN_INOBT;
		break;
	case XFS_RMAP_OWN_INODES:
		dest->fmr_owner = XFS_FMR_OWN_INODES;
		break;
	case XFS_RMAP_OWN_REFC:
		dest->fmr_owner = XFS_FMR_OWN_REFC;
		break;
	case XFS_RMAP_OWN_COW:
		dest->fmr_owner = XFS_FMR_OWN_COW;
		break;
	case XFS_RMAP_OWN_NULL:	/* "free" */
		dest->fmr_owner = XFS_FMR_OWN_FREE;
		break;
	default:
		ASSERT(0);
		return -EFSCORRUPTED;
	}
	return 0;
}

/* getfsmap query state */
struct xfs_getfsmap_info {
	struct xfs_fsmap_head	*head;
	struct fsmap		*fsmap_recs;	/* mapping records */
	struct xfs_buf		*agf_bp;	/* AGF, for refcount queries */
	struct xfs_perag	*pag;		/* AG info, if applicable */
	xfs_daddr_t		next_daddr;	/* next daddr we expect */
	/* daddr of low fsmap key when we're using the rtbitmap */
	xfs_daddr_t		low_daddr;
	xfs_daddr_t		end_daddr;	/* daddr of high fsmap key */
	u64			missing_owner;	/* owner of holes */
	u32			dev;		/* device id */
	/*
	 * Low rmap key for the query.  If low.rm_blockcount is nonzero, this
	 * is the second (or later) call to retrieve the recordset in pieces.
	 * xfs_getfsmap_rec_before_start will compare all records retrieved
	 * by the rmapbt query to filter out any records that start before
	 * the last record.
	 */
	struct xfs_rmap_irec	low;
	struct xfs_rmap_irec	high;		/* high rmap key */
	bool			last;		/* last extent? */
};

/* Associate a device with a getfsmap handler. */
struct xfs_getfsmap_dev {
	u32			dev;
	int			(*fn)(struct xfs_trans *tp,
				      const struct xfs_fsmap *keys,
				      struct xfs_getfsmap_info *info);
	sector_t		nr_sectors;
};

/* Compare two getfsmap device handlers. */
static int
xfs_getfsmap_dev_compare(
	const void			*p1,
	const void			*p2)
{
	const struct xfs_getfsmap_dev	*d1 = p1;
	const struct xfs_getfsmap_dev	*d2 = p2;

	return d1->dev - d2->dev;
}

/* Decide if this mapping is shared. */
STATIC int
xfs_getfsmap_is_shared(
	struct xfs_trans		*tp,
	struct xfs_getfsmap_info	*info,
	const struct xfs_rmap_irec	*rec,
	bool				*stat)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_btree_cur		*cur;
	xfs_agblock_t			fbno;
	xfs_extlen_t			flen;
	int				error;

	*stat = false;
	if (!xfs_has_reflink(mp))
		return 0;
	/* rt files will have no perag structure */
	if (!info->pag)
		return 0;

	/* Are there any shared blocks here? */
	flen = 0;
	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, info->pag);

	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
			rec->rm_blockcount, &fbno, &flen, false);

	xfs_btree_del_cursor(cur, error);
	if (error)
		return error;

	*stat = flen > 0;
	return 0;
}

static inline void
xfs_getfsmap_format(
	struct xfs_mount		*mp,
	struct xfs_fsmap		*xfm,
	struct xfs_getfsmap_info	*info)
{
	struct fsmap			*rec;

	trace_xfs_getfsmap_mapping(mp, xfm);

	rec = &info->fsmap_recs[info->head->fmh_entries++];
	xfs_fsmap_from_internal(rec, xfm);
}

static inline bool
xfs_getfsmap_rec_before_start(
	struct xfs_getfsmap_info	*info,
	const struct xfs_rmap_irec	*rec,
	xfs_daddr_t			rec_daddr)
{
	if (info->low_daddr != XFS_BUF_DADDR_NULL)
		return rec_daddr < info->low_daddr;
	if (info->low.rm_blockcount)
		return xfs_rmap_compare(rec, &info->low) < 0;
	return false;
}

/*
 * Format a reverse mapping for getfsmap, having translated rm_startblock
 * into the appropriate daddr units.  Pass in a nonzero @len_daddr if the
 * length could be larger than rm_blockcount in struct xfs_rmap_irec.
 */
STATIC int
xfs_getfsmap_helper(
	struct xfs_trans		*tp,
	struct xfs_getfsmap_info	*info,
	const struct xfs_rmap_irec	*rec,
	xfs_daddr_t			rec_daddr,
	xfs_daddr_t			len_daddr)
{
	struct xfs_fsmap		fmr;
	struct xfs_mount		*mp = tp->t_mountp;
	bool				shared;
	int				error;

	if (fatal_signal_pending(current))
		return -EINTR;

	if (len_daddr == 0)
		len_daddr = XFS_FSB_TO_BB(mp, rec->rm_blockcount);

	/*
	 * Filter out records that start before our startpoint, if the
	 * caller requested that.
	 */
	if (xfs_getfsmap_rec_before_start(info, rec, rec_daddr)) {
		rec_daddr += len_daddr;
		if (info->next_daddr < rec_daddr)
			info->next_daddr = rec_daddr;
		return 0;
	}

	/*
	 * For an info->last query, we're looking for a gap between the last
	 * mapping emitted and the high key specified by userspace.  If the
	 * user's query spans less than 1 fsblock, then info->high and
	 * info->low will have the same rm_startblock, which causes rec_daddr
	 * and next_daddr to be the same.  Therefore, use the end_daddr that
	 * we calculated from userspace's high key to synthesize the record.
	 * Note that if the btree query found a mapping, there won't be a gap.
	 */
	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
		rec_daddr = info->end_daddr;

	/* Are we just counting mappings? */
	if (info->head->fmh_count == 0) {
		if (info->head->fmh_entries == UINT_MAX)
			return -ECANCELED;

		if (rec_daddr > info->next_daddr)
			info->head->fmh_entries++;

		if (info->last)
			return 0;

		info->head->fmh_entries++;

		rec_daddr += len_daddr;
		if (info->next_daddr < rec_daddr)
			info->next_daddr = rec_daddr;
		return 0;
	}

	/*
	 * If the record starts past the last physical block we saw,
	 * then we've found a gap.  Report the gap as being owned by
	 * whatever the caller specified is the missing owner.
	 */
	if (rec_daddr > info->next_daddr) {
		if (info->head->fmh_entries >= info->head->fmh_count)
			return -ECANCELED;

		fmr.fmr_device = info->dev;
		fmr.fmr_physical = info->next_daddr;
		fmr.fmr_owner = info->missing_owner;
		fmr.fmr_offset = 0;
		fmr.fmr_length = rec_daddr - info->next_daddr;
		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
		xfs_getfsmap_format(mp, &fmr, info);
	}

	if (info->last)
		goto out;

	/* Fill out the extent we found */
	if (info->head->fmh_entries >= info->head->fmh_count)
		return -ECANCELED;

	trace_xfs_fsmap_mapping(mp, info->dev,
			info->pag ? info->pag->pag_agno : NULLAGNUMBER, rec);

	fmr.fmr_device = info->dev;
	fmr.fmr_physical = rec_daddr;
	error = xfs_fsmap_owner_from_rmap(&fmr, rec);
	if (error)
		return error;
	fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset);
	fmr.fmr_length = len_daddr;
	if (rec->rm_flags & XFS_RMAP_UNWRITTEN)
		fmr.fmr_flags |= FMR_OF_PREALLOC;
	if (rec->rm_flags & XFS_RMAP_ATTR_FORK)
		fmr.fmr_flags |= FMR_OF_ATTR_FORK;
	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK)
		fmr.fmr_flags |= FMR_OF_EXTENT_MAP;
	if (fmr.fmr_flags == 0) {
		error = xfs_getfsmap_is_shared(tp, info, rec, &shared);
		if (error)
			return error;
		if (shared)
			fmr.fmr_flags |= FMR_OF_SHARED;
	}

	xfs_getfsmap_format(mp, &fmr, info);
out:
	rec_daddr += len_daddr;
	if (info->next_daddr < rec_daddr)
		info->next_daddr = rec_daddr;
	return 0;
}

/* Transform a rmapbt irec into a fsmap */
STATIC int
xfs_getfsmap_datadev_helper(
	struct xfs_btree_cur		*cur,
	const struct xfs_rmap_irec	*rec,
	void				*priv)
{
	struct xfs_mount		*mp = cur->bc_mp;
	struct xfs_getfsmap_info	*info = priv;
	xfs_fsblock_t			fsb;
	xfs_daddr_t			rec_daddr;

	fsb = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno, rec->rm_startblock);
	rec_daddr = XFS_FSB_TO_DADDR(mp, fsb);

	return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr, 0);
}

/* Transform a bnobt irec into a fsmap */
STATIC int
xfs_getfsmap_datadev_bnobt_helper(
	struct xfs_btree_cur		*cur,
	const struct xfs_alloc_rec_incore *rec,
	void				*priv)
{
	struct xfs_mount		*mp = cur->bc_mp;
	struct xfs_getfsmap_info	*info = priv;
	struct xfs_rmap_irec		irec;
	xfs_daddr_t			rec_daddr;

	rec_daddr = XFS_AGB_TO_DADDR(mp, cur->bc_ag.pag->pag_agno,
			rec->ar_startblock);

	irec.rm_startblock = rec->ar_startblock;
	irec.rm_blockcount = rec->ar_blockcount;
	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
	irec.rm_offset = 0;
	irec.rm_flags = 0;

	return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr, 0);
}

/* Set rmap flags based on the getfsmap flags */
static void
xfs_getfsmap_set_irec_flags(
	struct xfs_rmap_irec	*irec,
	const struct xfs_fsmap	*fmr)
{
	irec->rm_flags = 0;
	if (fmr->fmr_flags & FMR_OF_ATTR_FORK)
		irec->rm_flags |= XFS_RMAP_ATTR_FORK;
	if (fmr->fmr_flags & FMR_OF_EXTENT_MAP)
		irec->rm_flags |= XFS_RMAP_BMBT_BLOCK;
	if (fmr->fmr_flags & FMR_OF_PREALLOC)
		irec->rm_flags |= XFS_RMAP_UNWRITTEN;
}

static inline bool
rmap_not_shareable(struct xfs_mount *mp, const struct xfs_rmap_irec *r)
{
	if (!xfs_has_reflink(mp))
		return true;
	if (XFS_RMAP_NON_INODE_OWNER(r->rm_owner))
		return true;
	if (r->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
			   XFS_RMAP_UNWRITTEN))
		return true;
	return false;
}

/* Execute a getfsmap query against the regular data device. */
STATIC int
__xfs_getfsmap_datadev(
	struct xfs_trans		*tp,
	const struct xfs_fsmap		*keys,
	struct xfs_getfsmap_info	*info,
	int				(*query_fn)(struct xfs_trans *,
						    struct xfs_getfsmap_info *,
						    struct xfs_btree_cur **,
						    void *),
	void				*priv)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_perag		*pag;
	struct xfs_btree_cur		*bt_cur = NULL;
	xfs_fsblock_t			start_fsb;
	xfs_fsblock_t			end_fsb;
	xfs_agnumber_t			start_ag;
	xfs_agnumber_t			end_ag;
	uint64_t			eofs;
	int				error = 0;

	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
	if (keys[0].fmr_physical >= eofs)
		return 0;
	start_fsb = XFS_DADDR_TO_FSB(mp, keys[0].fmr_physical);
	end_fsb = XFS_DADDR_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));

	/*
	 * Convert the fsmap low/high keys to AG based keys.  Initialize
	 * low to the fsmap low key and max out the high key to the end
	 * of the AG.
	 */
	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
	if (error)
		return error;
	info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length);
	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);

	/* Adjust the low key if we are continuing from where we left off. */
	if (info->low.rm_blockcount == 0) {
		/* No previous record from which to continue */
	} else if (rmap_not_shareable(mp, &info->low)) {
		/* Last record seen was an unshareable extent */
		info->low.rm_owner = 0;
		info->low.rm_offset = 0;

		start_fsb += info->low.rm_blockcount;
		if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs)
			return 0;
	} else {
		/* Last record seen was a shareable file data extent */
		info->low.rm_offset += info->low.rm_blockcount;
	}
	info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb);

	info->high.rm_startblock = -1U;
	info->high.rm_owner = ULLONG_MAX;
	info->high.rm_offset = ULLONG_MAX;
	info->high.rm_blockcount = 0;
	info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;

	start_ag = XFS_FSB_TO_AGNO(mp, start_fsb);
	end_ag = XFS_FSB_TO_AGNO(mp, end_fsb);

	for_each_perag_range(mp, start_ag, end_ag, pag) {
		/*
		 * Set the AG high key from the fsmap high key if this
		 * is the last AG that we're querying.
		 */
		info->pag = pag;
		if (pag->pag_agno == end_ag) {
			info->high.rm_startblock = XFS_FSB_TO_AGBNO(mp,
					end_fsb);
			info->high.rm_offset = XFS_BB_TO_FSBT(mp,
					keys[1].fmr_offset);
			error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
			if (error)
				break;
			xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
		}

		if (bt_cur) {
			xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR);
			bt_cur = NULL;
			xfs_trans_brelse(tp, info->agf_bp);
			info->agf_bp = NULL;
		}

		error = xfs_alloc_read_agf(pag, tp, 0, &info->agf_bp);
		if (error)
			break;

		trace_xfs_fsmap_low_key(mp, info->dev, pag->pag_agno,
				&info->low);
		trace_xfs_fsmap_high_key(mp, info->dev, pag->pag_agno,
				&info->high);

		error = query_fn(tp, info, &bt_cur, priv);
		if (error)
			break;

		/*
		 * Set the AG low key to the start of the AG prior to
		 * moving on to the next AG.
		 */
		if (pag->pag_agno == start_ag)
			memset(&info->low, 0, sizeof(info->low));

		/*
		 * If this is the last AG, report any gap at the end of it
		 * before we drop the reference to the perag when the loop
		 * terminates.
		 */
		if (pag->pag_agno == end_ag) {
			info->last = true;
			error = query_fn(tp, info, &bt_cur, priv);
			if (error)
				break;
		}
		info->pag = NULL;
	}

	if (bt_cur)
		xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR :
							 XFS_BTREE_NOERROR);
	if (info->agf_bp) {
		xfs_trans_brelse(tp, info->agf_bp);
		info->agf_bp = NULL;
	}
	if (info->pag) {
		xfs_perag_rele(info->pag);
		info->pag = NULL;
	} else if (pag) {
		/* loop termination case */
		xfs_perag_rele(pag);
	}

	return error;
}

/* Actually query the rmap btree. */
STATIC int
xfs_getfsmap_datadev_rmapbt_query(
	struct xfs_trans		*tp,
	struct xfs_getfsmap_info	*info,
	struct xfs_btree_cur		**curpp,
	void				*priv)
{
	/* Report any gap at the end of the last AG. */
	if (info->last)
		return xfs_getfsmap_datadev_helper(*curpp, &info->high, info);

	/* Allocate cursor for this AG and query_range it. */
	*curpp = xfs_rmapbt_init_cursor(tp->t_mountp, tp, info->agf_bp,
			info->pag);
	return xfs_rmap_query_range(*curpp, &info->low, &info->high,
			xfs_getfsmap_datadev_helper, info);
}

/* Execute a getfsmap query against the regular data device rmapbt. */
STATIC int
xfs_getfsmap_datadev_rmapbt(
	struct xfs_trans		*tp,
	const struct xfs_fsmap		*keys,
	struct xfs_getfsmap_info	*info)
{
	info->missing_owner = XFS_FMR_OWN_FREE;
	return __xfs_getfsmap_datadev(tp, keys, info,
			xfs_getfsmap_datadev_rmapbt_query, NULL);
}

/* Actually query the bno btree. */
STATIC int
xfs_getfsmap_datadev_bnobt_query(
	struct xfs_trans		*tp,
	struct xfs_getfsmap_info	*info,
	struct xfs_btree_cur		**curpp,
	void				*priv)
{
	struct xfs_alloc_rec_incore	*key = priv;

	/* Report any gap at the end of the last AG. */
	if (info->last)
		return xfs_getfsmap_datadev_bnobt_helper(*curpp, &key[1], info);

	/* Allocate cursor for this AG and query_range it. */
	*curpp = xfs_bnobt_init_cursor(tp->t_mountp, tp, info->agf_bp,
			info->pag);
	key->ar_startblock = info->low.rm_startblock;
	key[1].ar_startblock = info->high.rm_startblock;
	return xfs_alloc_query_range(*curpp, key, &key[1],
			xfs_getfsmap_datadev_bnobt_helper, info);
}

/* Execute a getfsmap query against the regular data device's bnobt. */
STATIC int
xfs_getfsmap_datadev_bnobt(
	struct xfs_trans		*tp,
	const struct xfs_fsmap		*keys,
	struct xfs_getfsmap_info	*info)
{
	struct xfs_alloc_rec_incore	akeys[2];

	memset(akeys, 0, sizeof(akeys));
	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
	return __xfs_getfsmap_datadev(tp, keys, info,
			xfs_getfsmap_datadev_bnobt_query, &akeys[0]);
}

/* Execute a getfsmap query against the log device. */
STATIC int
xfs_getfsmap_logdev(
	struct xfs_trans		*tp,
	const struct xfs_fsmap		*keys,
	struct xfs_getfsmap_info	*info)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_rmap_irec		rmap;
	xfs_daddr_t			rec_daddr, len_daddr;
	xfs_fsblock_t			start_fsb, end_fsb;
	uint64_t			eofs;

	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
	if (keys[0].fmr_physical >= eofs)
		return 0;
	start_fsb = XFS_BB_TO_FSBT(mp,
				keys[0].fmr_physical + keys[0].fmr_length);
	end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));

	/* Adjust the low key if we are continuing from where we left off. */
	if (keys[0].fmr_length > 0)
		info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb);

	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb);
	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb);

	if (start_fsb > 0)
		return 0;

	/* Fabricate an rmap entry for the external log device. */
	rmap.rm_startblock = 0;
	rmap.rm_blockcount = mp->m_sb.sb_logblocks;
	rmap.rm_owner = XFS_RMAP_OWN_LOG;
	rmap.rm_offset = 0;
	rmap.rm_flags = 0;

	rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock);
	len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount);
	return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr);
}

#ifdef CONFIG_XFS_RT
/* Transform a rtbitmap "record" into a fsmap */
STATIC int
xfs_getfsmap_rtdev_rtbitmap_helper(
	struct xfs_mount		*mp,
	struct xfs_trans		*tp,
	const struct xfs_rtalloc_rec	*rec,
	void				*priv)
{
	struct xfs_getfsmap_info	*info = priv;
	struct xfs_rmap_irec		irec;
	xfs_rtblock_t			rtbno;
	xfs_daddr_t			rec_daddr, len_daddr;

	rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
	rec_daddr = XFS_FSB_TO_BB(mp, rtbno);
	irec.rm_startblock = rtbno;

	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
	len_daddr = XFS_FSB_TO_BB(mp, rtbno);
	irec.rm_blockcount = rtbno;

	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
	irec.rm_offset = 0;
	irec.rm_flags = 0;

	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr);
}

/* Execute a getfsmap query against the realtime device rtbitmap. */
STATIC int
xfs_getfsmap_rtdev_rtbitmap(
	struct xfs_trans		*tp,
	const struct xfs_fsmap		*keys,
	struct xfs_getfsmap_info	*info)
{

	struct xfs_rtalloc_rec		ahigh = { 0 };
	struct xfs_mount		*mp = tp->t_mountp;
	xfs_rtblock_t			start_rtb;
	xfs_rtblock_t			end_rtb;
	xfs_rtxnum_t			high;
	uint64_t			eofs;
	int				error;

	eofs = XFS_FSB_TO_BB(mp, xfs_rtx_to_rtb(mp, mp->m_sb.sb_rextents));
	if (keys[0].fmr_physical >= eofs)
		return 0;
	start_rtb = XFS_BB_TO_FSBT(mp,
				keys[0].fmr_physical + keys[0].fmr_length);
	end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));

	info->missing_owner = XFS_FMR_OWN_UNKNOWN;

	/* Adjust the low key if we are continuing from where we left off. */
	if (keys[0].fmr_length > 0) {
		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
		if (info->low_daddr >= eofs)
			return 0;
	}

	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb);
	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb);

	xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);

	/*
	 * Set up query parameters to return free rtextents covering the range
	 * we want.
	 */
	high = xfs_rtb_to_rtxup(mp, end_rtb);
	error = xfs_rtalloc_query_range(mp, tp, xfs_rtb_to_rtx(mp, start_rtb),
			high, xfs_getfsmap_rtdev_rtbitmap_helper, info);
	if (error)
		goto err;

	/*
	 * Report any gaps at the end of the rtbitmap by simulating a null
	 * rmap starting at the block after the end of the query range.
	 */
	info->last = true;
	ahigh.ar_startext = min(mp->m_sb.sb_rextents, high);

	error = xfs_getfsmap_rtdev_rtbitmap_helper(mp, tp, &ahigh, info);
	if (error)
		goto err;
err:
	xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
	return error;
}
#endif /* CONFIG_XFS_RT */

/* Do we recognize the device? */
STATIC bool
xfs_getfsmap_is_valid_device(
	struct xfs_mount	*mp,
	struct xfs_fsmap	*fm)
{
	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
	    fm->fmr_device == new_encode_dev(mp->m_ddev_targp->bt_dev))
		return true;
	if (mp->m_logdev_targp &&
	    fm->fmr_device == new_encode_dev(mp->m_logdev_targp->bt_dev))
		return true;
	if (mp->m_rtdev_targp &&
	    fm->fmr_device == new_encode_dev(mp->m_rtdev_targp->bt_dev))
		return true;
	return false;
}

/* Ensure that the low key is less than the high key. */
STATIC bool
xfs_getfsmap_check_keys(
	struct xfs_fsmap		*low_key,
	struct xfs_fsmap		*high_key)
{
	if (low_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) {
		if (low_key->fmr_offset)
			return false;
	}
	if (high_key->fmr_flags != -1U &&
	    (high_key->fmr_flags & (FMR_OF_SPECIAL_OWNER |
				    FMR_OF_EXTENT_MAP))) {
		if (high_key->fmr_offset && high_key->fmr_offset != -1ULL)
			return false;
	}
	if (high_key->fmr_length && high_key->fmr_length != -1ULL)
		return false;

	if (low_key->fmr_device > high_key->fmr_device)
		return false;
	if (low_key->fmr_device < high_key->fmr_device)
		return true;

	if (low_key->fmr_physical > high_key->fmr_physical)
		return false;
	if (low_key->fmr_physical < high_key->fmr_physical)
		return true;

	if (low_key->fmr_owner > high_key->fmr_owner)
		return false;
	if (low_key->fmr_owner < high_key->fmr_owner)
		return true;

	if (low_key->fmr_offset > high_key->fmr_offset)
		return false;
	if (low_key->fmr_offset < high_key->fmr_offset)
		return true;

	return false;
}

/*
 * There are only two devices if we didn't configure RT devices at build time.
 */
#ifdef CONFIG_XFS_RT
#define XFS_GETFSMAP_DEVS	3
#else
#define XFS_GETFSMAP_DEVS	2
#endif /* CONFIG_XFS_RT */

/*
 * Get filesystem's extents as described in head, and format for output. Fills
 * in the supplied records array until there are no more reverse mappings to
 * return or head.fmh_entries == head.fmh_count.  In the second case, this
 * function returns -ECANCELED to indicate that more records would have been
 * returned.
 *
 * Key to Confusion
 * ----------------
 * There are multiple levels of keys and counters at work here:
 * xfs_fsmap_head.fmh_keys	-- low and high fsmap keys passed in;
 *				   these reflect fs-wide sector addrs.
 * dkeys			-- fmh_keys used to query each device;
 *				   these are fmh_keys but w/ the low key
 *				   bumped up by fmr_length.
 * xfs_getfsmap_info.next_daddr	-- next disk addr we expect to see; this
 *				   is how we detect gaps in the fsmap
				   records and report them.
 * xfs_getfsmap_info.low/high	-- per-AG low/high keys computed from
 *				   dkeys; used to query the metadata.
 */
STATIC int
xfs_getfsmap(
	struct xfs_mount		*mp,
	struct xfs_fsmap_head		*head,
	struct fsmap			*fsmap_recs)
{
	struct xfs_trans		*tp = NULL;
	struct xfs_fsmap		dkeys[2];	/* per-dev keys */
	struct xfs_getfsmap_dev		handlers[XFS_GETFSMAP_DEVS];
	struct xfs_getfsmap_info	info = { NULL };
	bool				use_rmap;
	int				i;
	int				error = 0;

	if (head->fmh_iflags & ~FMH_IF_VALID)
		return -EINVAL;
	if (!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[0]) ||
	    !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1]))
		return -EINVAL;
	if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1]))
		return -EINVAL;

	use_rmap = xfs_has_rmapbt(mp) &&
		   has_capability_noaudit(current, CAP_SYS_ADMIN);
	head->fmh_entries = 0;

	/* Set up our device handlers. */
	memset(handlers, 0, sizeof(handlers));
	handlers[0].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
	handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
	if (use_rmap)
		handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
	else
		handlers[0].fn = xfs_getfsmap_datadev_bnobt;
	if (mp->m_logdev_targp != mp->m_ddev_targp) {
		handlers[1].nr_sectors = XFS_FSB_TO_BB(mp,
						       mp->m_sb.sb_logblocks);
		handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
		handlers[1].fn = xfs_getfsmap_logdev;
	}
#ifdef CONFIG_XFS_RT
	if (mp->m_rtdev_targp) {
		handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
		handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
	}
#endif /* CONFIG_XFS_RT */

	xfs_sort(handlers, XFS_GETFSMAP_DEVS, sizeof(struct xfs_getfsmap_dev),
			xfs_getfsmap_dev_compare);

	/*
	 * To continue where we left off, we allow userspace to use the
	 * last mapping from a previous call as the low key of the next.
	 * This is identified by a non-zero length in the low key. We
	 * have to increment the low key in this scenario to ensure we
	 * don't return the same mapping again, and instead return the
	 * very next mapping.
	 *
	 * If the low key mapping refers to file data, the same physical
	 * blocks could be mapped to several other files/offsets.
	 * According to rmapbt record ordering, the minimal next
	 * possible record for the block range is the next starting
	 * offset in the same inode. Therefore, each fsmap backend bumps
	 * the file offset to continue the search appropriately.  For
	 * all other low key mapping types (attr blocks, metadata), each
	 * fsmap backend bumps the physical offset as there can be no
	 * other mapping for the same physical block range.
	 */
	dkeys[0] = head->fmh_keys[0];
	memset(&dkeys[1], 0xFF, sizeof(struct xfs_fsmap));

	info.next_daddr = head->fmh_keys[0].fmr_physical +
			  head->fmh_keys[0].fmr_length;
	info.end_daddr = XFS_BUF_DADDR_NULL;
	info.fsmap_recs = fsmap_recs;
	info.head = head;

	/* For each device we support... */
	for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
		/* Is this device within the range the user asked for? */
		if (!handlers[i].fn)
			continue;
		if (head->fmh_keys[0].fmr_device > handlers[i].dev)
			continue;
		if (head->fmh_keys[1].fmr_device < handlers[i].dev)
			break;

		/*
		 * If this device number matches the high key, we have
		 * to pass the high key to the handler to limit the
		 * query results.  If the device number exceeds the
		 * low key, zero out the low key so that we get
		 * everything from the beginning.
		 */
		if (handlers[i].dev == head->fmh_keys[1].fmr_device) {
			dkeys[1] = head->fmh_keys[1];
			info.end_daddr = min(handlers[i].nr_sectors - 1,
					     dkeys[1].fmr_physical);
		}
		if (handlers[i].dev > head->fmh_keys[0].fmr_device)
			memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));

		/*
		 * Grab an empty transaction so that we can use its recursive
		 * buffer locking abilities to detect cycles in the rmapbt
		 * without deadlocking.
		 */
		error = xfs_trans_alloc_empty(mp, &tp);
		if (error)
			break;

		info.dev = handlers[i].dev;
		info.last = false;
		info.pag = NULL;
		info.low_daddr = XFS_BUF_DADDR_NULL;
		info.low.rm_blockcount = 0;
		error = handlers[i].fn(tp, dkeys, &info);
		if (error)
			break;
		xfs_trans_cancel(tp);
		tp = NULL;
		info.next_daddr = 0;
	}

	if (tp)
		xfs_trans_cancel(tp);
	head->fmh_oflags = FMH_OF_DEV_T;
	return error;
}

int
xfs_ioc_getfsmap(
	struct xfs_inode	*ip,
	struct fsmap_head	__user *arg)
{
	struct xfs_fsmap_head	xhead = {0};
	struct fsmap_head	head;
	struct fsmap		*recs;
	unsigned int		count;
	__u32			last_flags = 0;
	bool			done = false;
	int			error;

	if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
		return -EFAULT;
	if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
	    memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
		       sizeof(head.fmh_keys[0].fmr_reserved)) ||
	    memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
		       sizeof(head.fmh_keys[1].fmr_reserved)))
		return -EINVAL;

	/*
	 * Use an internal memory buffer so that we don't have to copy fsmap
	 * data to userspace while holding locks.  Start by trying to allocate
	 * up to 128k for the buffer, but fall back to a single page if needed.
	 */
	count = min_t(unsigned int, head.fmh_count,
			131072 / sizeof(struct fsmap));
	recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL);
	if (!recs) {
		count = min_t(unsigned int, head.fmh_count,
				PAGE_SIZE / sizeof(struct fsmap));
		recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL);
		if (!recs)
			return -ENOMEM;
	}

	xhead.fmh_iflags = head.fmh_iflags;
	xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]);
	xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]);

	trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
	trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]);

	head.fmh_entries = 0;
	do {
		struct fsmap __user	*user_recs;
		struct fsmap		*last_rec;

		user_recs = &arg->fmh_recs[head.fmh_entries];
		xhead.fmh_entries = 0;
		xhead.fmh_count = min_t(unsigned int, count,
					head.fmh_count - head.fmh_entries);

		/* Run query, record how many entries we got. */
		error = xfs_getfsmap(ip->i_mount, &xhead, recs);
		switch (error) {
		case 0:
			/*
			 * There are no more records in the result set.  Copy
			 * whatever we got to userspace and break out.
			 */
			done = true;
			break;
		case -ECANCELED:
			/*
			 * The internal memory buffer is full.  Copy whatever
			 * records we got to userspace and go again if we have
			 * not yet filled the userspace buffer.
			 */
			error = 0;
			break;
		default:
			goto out_free;
		}
		head.fmh_entries += xhead.fmh_entries;
		head.fmh_oflags = xhead.fmh_oflags;

		/*
		 * If the caller wanted a record count or there aren't any
		 * new records to return, we're done.
		 */
		if (head.fmh_count == 0 || xhead.fmh_entries == 0)
			break;

		/* Copy all the records we got out to userspace. */
		if (copy_to_user(user_recs, recs,
				 xhead.fmh_entries * sizeof(struct fsmap))) {
			error = -EFAULT;
			goto out_free;
		}

		/* Remember the last record flags we copied to userspace. */
		last_rec = &recs[xhead.fmh_entries - 1];
		last_flags = last_rec->fmr_flags;

		/* Set up the low key for the next iteration. */
		xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec);
		trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
	} while (!done && head.fmh_entries < head.fmh_count);

	/*
	 * If there are no more records in the query result set and we're not
	 * in counting mode, mark the last record returned with the LAST flag.
	 */
	if (done && head.fmh_count > 0 && head.fmh_entries > 0) {
		struct fsmap __user	*user_rec;

		last_flags |= FMR_OF_LAST;
		user_rec = &arg->fmh_recs[head.fmh_entries - 1];

		if (copy_to_user(&user_rec->fmr_flags, &last_flags,
					sizeof(last_flags))) {
			error = -EFAULT;
			goto out_free;
		}
	}

	/* copy back header */
	if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) {
		error = -EFAULT;
		goto out_free;
	}

out_free:
	kvfree(recs);
	return error;
}