summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_inode_item.c
blob: cd7803fda8b1be501af6d19d900d9d80bef5a391 (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
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#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_inode_item.h"
#include "xfs_trace.h"
#include "xfs_trans_priv.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_error.h"
#include "xfs_rtbitmap.h"

#include <linux/iversion.h>

struct kmem_cache	*xfs_ili_cache;		/* inode log item */

static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_inode_log_item, ili_item);
}

static uint64_t
xfs_inode_item_sort(
	struct xfs_log_item	*lip)
{
	return INODE_ITEM(lip)->ili_inode->i_ino;
}

/*
 * Prior to finally logging the inode, we have to ensure that all the
 * per-modification inode state changes are applied. This includes VFS inode
 * state updates, format conversions, verifier state synchronisation and
 * ensuring the inode buffer remains in memory whilst the inode is dirty.
 *
 * We have to be careful when we grab the inode cluster buffer due to lock
 * ordering constraints. The unlinked inode modifications (xfs_iunlink_item)
 * require AGI -> inode cluster buffer lock order. The inode cluster buffer is
 * not locked until ->precommit, so it happens after everything else has been
 * modified.
 *
 * Further, we have AGI -> AGF lock ordering, and with O_TMPFILE handling we
 * have AGI -> AGF -> iunlink item -> inode cluster buffer lock order. Hence we
 * cannot safely lock the inode cluster buffer in xfs_trans_log_inode() because
 * it can be called on a inode (e.g. via bumplink/droplink) before we take the
 * AGF lock modifying directory blocks.
 *
 * Rather than force a complete rework of all the transactions to call
 * xfs_trans_log_inode() once and once only at the end of every transaction, we
 * move the pinning of the inode cluster buffer to a ->precommit operation. This
 * matches how the xfs_iunlink_item locks the inode cluster buffer, and it
 * ensures that the inode cluster buffer locking is always done last in a
 * transaction. i.e. we ensure the lock order is always AGI -> AGF -> inode
 * cluster buffer.
 *
 * If we return the inode number as the precommit sort key then we'll also
 * guarantee that the order all inode cluster buffer locking is the same all the
 * inodes and unlink items in the transaction.
 */
static int
xfs_inode_item_precommit(
	struct xfs_trans	*tp,
	struct xfs_log_item	*lip)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	struct inode		*inode = VFS_I(ip);
	unsigned int		flags = iip->ili_dirty_flags;

	/*
	 * Don't bother with i_lock for the I_DIRTY_TIME check here, as races
	 * don't matter - we either will need an extra transaction in 24 hours
	 * to log the timestamps, or will clear already cleared fields in the
	 * worst case.
	 */
	if (inode->i_state & I_DIRTY_TIME) {
		spin_lock(&inode->i_lock);
		inode->i_state &= ~I_DIRTY_TIME;
		spin_unlock(&inode->i_lock);
	}

	/*
	 * If we're updating the inode core or the timestamps and it's possible
	 * to upgrade this inode to bigtime format, do so now.
	 */
	if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
	    xfs_has_bigtime(ip->i_mount) &&
	    !xfs_inode_has_bigtime(ip)) {
		ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME;
		flags |= XFS_ILOG_CORE;
	}

	/*
	 * Inode verifiers do not check that the extent size hint is an integer
	 * multiple of the rt extent size on a directory with both rtinherit
	 * and extszinherit flags set.  If we're logging a directory that is
	 * misconfigured in this way, clear the hint.
	 */
	if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
	    (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
	    xfs_extlen_to_rtxmod(ip->i_mount, ip->i_extsize) > 0) {
		ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
				   XFS_DIFLAG_EXTSZINHERIT);
		ip->i_extsize = 0;
		flags |= XFS_ILOG_CORE;
	}

	/*
	 * Record the specific change for fdatasync optimisation. This allows
	 * fdatasync to skip log forces for inodes that are only timestamp
	 * dirty. Once we've processed the XFS_ILOG_IVERSION flag, convert it
	 * to XFS_ILOG_CORE so that the actual on-disk dirty tracking
	 * (ili_fields) correctly tracks that the version has changed.
	 */
	spin_lock(&iip->ili_lock);
	iip->ili_fsync_fields |= (flags & ~XFS_ILOG_IVERSION);
	if (flags & XFS_ILOG_IVERSION)
		flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE);

	if (!iip->ili_item.li_buf) {
		struct xfs_buf	*bp;
		int		error;

		/*
		 * We hold the ILOCK here, so this inode is not going to be
		 * flushed while we are here. Further, because there is no
		 * buffer attached to the item, we know that there is no IO in
		 * progress, so nothing will clear the ili_fields while we read
		 * in the buffer. Hence we can safely drop the spin lock and
		 * read the buffer knowing that the state will not change from
		 * here.
		 */
		spin_unlock(&iip->ili_lock);
		error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp);
		if (error)
			return error;

		/*
		 * We need an explicit buffer reference for the log item but
		 * don't want the buffer to remain attached to the transaction.
		 * Hold the buffer but release the transaction reference once
		 * we've attached the inode log item to the buffer log item
		 * list.
		 */
		xfs_buf_hold(bp);
		spin_lock(&iip->ili_lock);
		iip->ili_item.li_buf = bp;
		bp->b_flags |= _XBF_INODES;
		list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list);
		xfs_trans_brelse(tp, bp);
	}

	/*
	 * Always OR in the bits from the ili_last_fields field.  This is to
	 * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines
	 * in the eventual clearing of the ili_fields bits.  See the big comment
	 * in xfs_iflush() for an explanation of this coordination mechanism.
	 */
	iip->ili_fields |= (flags | iip->ili_last_fields);
	spin_unlock(&iip->ili_lock);

	/*
	 * We are done with the log item transaction dirty state, so clear it so
	 * that it doesn't pollute future transactions.
	 */
	iip->ili_dirty_flags = 0;
	return 0;
}

/*
 * The logged size of an inode fork is always the current size of the inode
 * fork. This means that when an inode fork is relogged, the size of the logged
 * region is determined by the current state, not the combination of the
 * previously logged state + the current state. This is different relogging
 * behaviour to most other log items which will retain the size of the
 * previously logged changes when smaller regions are relogged.
 *
 * Hence operations that remove data from the inode fork (e.g. shortform
 * dir/attr remove, extent form extent removal, etc), the size of the relogged
 * inode gets -smaller- rather than stays the same size as the previously logged
 * size and this can result in the committing transaction reducing the amount of
 * space being consumed by the CIL.
 */
STATIC void
xfs_inode_item_data_fork_size(
	struct xfs_inode_log_item *iip,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_inode	*ip = iip->ili_inode;

	switch (ip->i_df.if_format) {
	case XFS_DINODE_FMT_EXTENTS:
		if ((iip->ili_fields & XFS_ILOG_DEXT) &&
		    ip->i_df.if_nextents > 0 &&
		    ip->i_df.if_bytes > 0) {
			/* worst case, doesn't subtract delalloc extents */
			*nbytes += xfs_inode_data_fork_size(ip);
			*nvecs += 1;
		}
		break;
	case XFS_DINODE_FMT_BTREE:
		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
		    ip->i_df.if_broot_bytes > 0) {
			*nbytes += ip->i_df.if_broot_bytes;
			*nvecs += 1;
		}
		break;
	case XFS_DINODE_FMT_LOCAL:
		if ((iip->ili_fields & XFS_ILOG_DDATA) &&
		    ip->i_df.if_bytes > 0) {
			*nbytes += xlog_calc_iovec_len(ip->i_df.if_bytes);
			*nvecs += 1;
		}
		break;

	case XFS_DINODE_FMT_DEV:
		break;
	default:
		ASSERT(0);
		break;
	}
}

STATIC void
xfs_inode_item_attr_fork_size(
	struct xfs_inode_log_item *iip,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_inode	*ip = iip->ili_inode;

	switch (ip->i_af.if_format) {
	case XFS_DINODE_FMT_EXTENTS:
		if ((iip->ili_fields & XFS_ILOG_AEXT) &&
		    ip->i_af.if_nextents > 0 &&
		    ip->i_af.if_bytes > 0) {
			/* worst case, doesn't subtract unused space */
			*nbytes += xfs_inode_attr_fork_size(ip);
			*nvecs += 1;
		}
		break;
	case XFS_DINODE_FMT_BTREE:
		if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
		    ip->i_af.if_broot_bytes > 0) {
			*nbytes += ip->i_af.if_broot_bytes;
			*nvecs += 1;
		}
		break;
	case XFS_DINODE_FMT_LOCAL:
		if ((iip->ili_fields & XFS_ILOG_ADATA) &&
		    ip->i_af.if_bytes > 0) {
			*nbytes += xlog_calc_iovec_len(ip->i_af.if_bytes);
			*nvecs += 1;
		}
		break;
	default:
		ASSERT(0);
		break;
	}
}

/*
 * This returns the number of iovecs needed to log the given inode item.
 *
 * We need one iovec for the inode log format structure, one for the
 * inode core, and possibly one for the inode data/extents/b-tree root
 * and one for the inode attribute data/extents/b-tree root.
 */
STATIC void
xfs_inode_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;

	*nvecs += 2;
	*nbytes += sizeof(struct xfs_inode_log_format) +
		   xfs_log_dinode_size(ip->i_mount);

	xfs_inode_item_data_fork_size(iip, nvecs, nbytes);
	if (xfs_inode_has_attr_fork(ip))
		xfs_inode_item_attr_fork_size(iip, nvecs, nbytes);
}

STATIC void
xfs_inode_item_format_data_fork(
	struct xfs_inode_log_item *iip,
	struct xfs_inode_log_format *ilf,
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp)
{
	struct xfs_inode	*ip = iip->ili_inode;
	size_t			data_bytes;

	switch (ip->i_df.if_format) {
	case XFS_DINODE_FMT_EXTENTS:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | XFS_ILOG_DEV);

		if ((iip->ili_fields & XFS_ILOG_DEXT) &&
		    ip->i_df.if_nextents > 0 &&
		    ip->i_df.if_bytes > 0) {
			struct xfs_bmbt_rec *p;

			ASSERT(xfs_iext_count(&ip->i_df) > 0);

			p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT);
			data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK);
			xlog_finish_iovec(lv, *vecp, data_bytes);

			ASSERT(data_bytes <= ip->i_df.if_bytes);

			ilf->ilf_dsize = data_bytes;
			ilf->ilf_size++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_DEXT;
		}
		break;
	case XFS_DINODE_FMT_BTREE:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV);

		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
		    ip->i_df.if_broot_bytes > 0) {
			ASSERT(ip->i_df.if_broot != NULL);
			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IBROOT,
					ip->i_df.if_broot,
					ip->i_df.if_broot_bytes);
			ilf->ilf_dsize = ip->i_df.if_broot_bytes;
			ilf->ilf_size++;
		} else {
			ASSERT(!(iip->ili_fields &
				 XFS_ILOG_DBROOT));
			iip->ili_fields &= ~XFS_ILOG_DBROOT;
		}
		break;
	case XFS_DINODE_FMT_LOCAL:
		iip->ili_fields &=
			~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | XFS_ILOG_DEV);
		if ((iip->ili_fields & XFS_ILOG_DDATA) &&
		    ip->i_df.if_bytes > 0) {
			ASSERT(ip->i_df.if_u1.if_data != NULL);
			ASSERT(ip->i_disk_size > 0);
			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
					ip->i_df.if_u1.if_data,
					ip->i_df.if_bytes);
			ilf->ilf_dsize = (unsigned)ip->i_df.if_bytes;
			ilf->ilf_size++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_DDATA;
		}
		break;
	case XFS_DINODE_FMT_DEV:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | XFS_ILOG_DEXT);
		if (iip->ili_fields & XFS_ILOG_DEV)
			ilf->ilf_u.ilfu_rdev = sysv_encode_dev(VFS_I(ip)->i_rdev);
		break;
	default:
		ASSERT(0);
		break;
	}
}

STATIC void
xfs_inode_item_format_attr_fork(
	struct xfs_inode_log_item *iip,
	struct xfs_inode_log_format *ilf,
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp)
{
	struct xfs_inode	*ip = iip->ili_inode;
	size_t			data_bytes;

	switch (ip->i_af.if_format) {
	case XFS_DINODE_FMT_EXTENTS:
		iip->ili_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT);

		if ((iip->ili_fields & XFS_ILOG_AEXT) &&
		    ip->i_af.if_nextents > 0 &&
		    ip->i_af.if_bytes > 0) {
			struct xfs_bmbt_rec *p;

			ASSERT(xfs_iext_count(&ip->i_af) ==
				ip->i_af.if_nextents);

			p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_EXT);
			data_bytes = xfs_iextents_copy(ip, p, XFS_ATTR_FORK);
			xlog_finish_iovec(lv, *vecp, data_bytes);

			ilf->ilf_asize = data_bytes;
			ilf->ilf_size++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_AEXT;
		}
		break;
	case XFS_DINODE_FMT_BTREE:
		iip->ili_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_AEXT);

		if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
		    ip->i_af.if_broot_bytes > 0) {
			ASSERT(ip->i_af.if_broot != NULL);

			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_BROOT,
					ip->i_af.if_broot,
					ip->i_af.if_broot_bytes);
			ilf->ilf_asize = ip->i_af.if_broot_bytes;
			ilf->ilf_size++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_ABROOT;
		}
		break;
	case XFS_DINODE_FMT_LOCAL:
		iip->ili_fields &=
			~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT);

		if ((iip->ili_fields & XFS_ILOG_ADATA) &&
		    ip->i_af.if_bytes > 0) {
			ASSERT(ip->i_af.if_u1.if_data != NULL);
			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
					ip->i_af.if_u1.if_data,
					ip->i_af.if_bytes);
			ilf->ilf_asize = (unsigned)ip->i_af.if_bytes;
			ilf->ilf_size++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_ADATA;
		}
		break;
	default:
		ASSERT(0);
		break;
	}
}

/*
 * Convert an incore timestamp to a log timestamp.  Note that the log format
 * specifies host endian format!
 */
static inline xfs_log_timestamp_t
xfs_inode_to_log_dinode_ts(
	struct xfs_inode		*ip,
	const struct timespec64		tv)
{
	struct xfs_log_legacy_timestamp	*lits;
	xfs_log_timestamp_t		its;

	if (xfs_inode_has_bigtime(ip))
		return xfs_inode_encode_bigtime(tv);

	lits = (struct xfs_log_legacy_timestamp *)&its;
	lits->t_sec = tv.tv_sec;
	lits->t_nsec = tv.tv_nsec;

	return its;
}

/*
 * The legacy DMAPI fields are only present in the on-disk and in-log inodes,
 * but not in the in-memory one.  But we are guaranteed to have an inode buffer
 * in memory when logging an inode, so we can just copy it from the on-disk
 * inode to the in-log inode here so that recovery of file system with these
 * fields set to non-zero values doesn't lose them.  For all other cases we zero
 * the fields.
 */
static void
xfs_copy_dm_fields_to_log_dinode(
	struct xfs_inode	*ip,
	struct xfs_log_dinode	*to)
{
	struct xfs_dinode	*dip;

	dip = xfs_buf_offset(ip->i_itemp->ili_item.li_buf,
			     ip->i_imap.im_boffset);

	if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) {
		to->di_dmevmask = be32_to_cpu(dip->di_dmevmask);
		to->di_dmstate = be16_to_cpu(dip->di_dmstate);
	} else {
		to->di_dmevmask = 0;
		to->di_dmstate = 0;
	}
}

static inline void
xfs_inode_to_log_dinode_iext_counters(
	struct xfs_inode	*ip,
	struct xfs_log_dinode	*to)
{
	if (xfs_inode_has_large_extent_counts(ip)) {
		to->di_big_nextents = xfs_ifork_nextents(&ip->i_df);
		to->di_big_anextents = xfs_ifork_nextents(&ip->i_af);
		to->di_nrext64_pad = 0;
	} else {
		to->di_nextents = xfs_ifork_nextents(&ip->i_df);
		to->di_anextents = xfs_ifork_nextents(&ip->i_af);
	}
}

static void
xfs_inode_to_log_dinode(
	struct xfs_inode	*ip,
	struct xfs_log_dinode	*to,
	xfs_lsn_t		lsn)
{
	struct inode		*inode = VFS_I(ip);

	to->di_magic = XFS_DINODE_MAGIC;
	to->di_format = xfs_ifork_format(&ip->i_df);
	to->di_uid = i_uid_read(inode);
	to->di_gid = i_gid_read(inode);
	to->di_projid_lo = ip->i_projid & 0xffff;
	to->di_projid_hi = ip->i_projid >> 16;

	memset(to->di_pad3, 0, sizeof(to->di_pad3));
	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode_get_atime(inode));
	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode_get_mtime(inode));
	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode_get_ctime(inode));
	to->di_nlink = inode->i_nlink;
	to->di_gen = inode->i_generation;
	to->di_mode = inode->i_mode;

	to->di_size = ip->i_disk_size;
	to->di_nblocks = ip->i_nblocks;
	to->di_extsize = ip->i_extsize;
	to->di_forkoff = ip->i_forkoff;
	to->di_aformat = xfs_ifork_format(&ip->i_af);
	to->di_flags = ip->i_diflags;

	xfs_copy_dm_fields_to_log_dinode(ip, to);

	/* log a dummy value to ensure log structure is fully initialised */
	to->di_next_unlinked = NULLAGINO;

	if (xfs_has_v3inodes(ip->i_mount)) {
		to->di_version = 3;
		to->di_changecount = inode_peek_iversion(inode);
		to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime);
		to->di_flags2 = ip->i_diflags2;
		to->di_cowextsize = ip->i_cowextsize;
		to->di_ino = ip->i_ino;
		to->di_lsn = lsn;
		memset(to->di_pad2, 0, sizeof(to->di_pad2));
		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
		to->di_v3_pad = 0;
	} else {
		to->di_version = 2;
		to->di_flushiter = ip->i_flushiter;
		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
	}

	xfs_inode_to_log_dinode_iext_counters(ip, to);
}

/*
 * Format the inode core. Current timestamp data is only in the VFS inode
 * fields, so we need to grab them from there. Hence rather than just copying
 * the XFS inode core structure, format the fields directly into the iovec.
 */
static void
xfs_inode_item_format_core(
	struct xfs_inode	*ip,
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp)
{
	struct xfs_log_dinode	*dic;

	dic = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_ICORE);
	xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn);
	xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_mount));
}

/*
 * This is called to fill in the vector of log iovecs for the given inode
 * log item.  It fills the first item with an inode log format structure,
 * the second with the on-disk inode structure, and a possible third and/or
 * fourth with the inode data/extents/b-tree root and inode attributes
 * data/extents/b-tree root.
 *
 * Note: Always use the 64 bit inode log format structure so we don't
 * leave an uninitialised hole in the format item on 64 bit systems. Log
 * recovery on 32 bit systems handles this just fine, so there's no reason
 * for not using an initialising the properly padded structure all the time.
 */
STATIC void
xfs_inode_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_vec	*lv)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	struct xfs_log_iovec	*vecp = NULL;
	struct xfs_inode_log_format *ilf;

	ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT);
	ilf->ilf_type = XFS_LI_INODE;
	ilf->ilf_ino = ip->i_ino;
	ilf->ilf_blkno = ip->i_imap.im_blkno;
	ilf->ilf_len = ip->i_imap.im_len;
	ilf->ilf_boffset = ip->i_imap.im_boffset;
	ilf->ilf_fields = XFS_ILOG_CORE;
	ilf->ilf_size = 2; /* format + core */

	/*
	 * make sure we don't leak uninitialised data into the log in the case
	 * when we don't log every field in the inode.
	 */
	ilf->ilf_dsize = 0;
	ilf->ilf_asize = 0;
	ilf->ilf_pad = 0;
	memset(&ilf->ilf_u, 0, sizeof(ilf->ilf_u));

	xlog_finish_iovec(lv, vecp, sizeof(*ilf));

	xfs_inode_item_format_core(ip, lv, &vecp);
	xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
	if (xfs_inode_has_attr_fork(ip)) {
		xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp);
	} else {
		iip->ili_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT);
	}

	/* update the format with the exact fields we actually logged */
	ilf->ilf_fields |= (iip->ili_fields & ~XFS_ILOG_TIMESTAMP);
}

/*
 * This is called to pin the inode associated with the inode log
 * item in memory so it cannot be written out.
 */
STATIC void
xfs_inode_item_pin(
	struct xfs_log_item	*lip)
{
	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
	ASSERT(lip->li_buf);

	trace_xfs_inode_pin(ip, _RET_IP_);
	atomic_inc(&ip->i_pincount);
}


/*
 * This is called to unpin the inode associated with the inode log
 * item which was previously pinned with a call to xfs_inode_item_pin().
 *
 * Also wake up anyone in xfs_iunpin_wait() if the count goes to 0.
 *
 * Note that unpin can race with inode cluster buffer freeing marking the buffer
 * stale. In that case, flush completions are run from the buffer unpin call,
 * which may happen before the inode is unpinned. If we lose the race, there
 * will be no buffer attached to the log item, but the inode will be marked
 * XFS_ISTALE.
 */
STATIC void
xfs_inode_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{
	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;

	trace_xfs_inode_unpin(ip, _RET_IP_);
	ASSERT(lip->li_buf || xfs_iflags_test(ip, XFS_ISTALE));
	ASSERT(atomic_read(&ip->i_pincount) > 0);
	if (atomic_dec_and_test(&ip->i_pincount))
		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
}

STATIC uint
xfs_inode_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
		__releases(&lip->li_ailp->ail_lock)
		__acquires(&lip->li_ailp->ail_lock)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	struct xfs_buf		*bp = lip->li_buf;
	uint			rval = XFS_ITEM_SUCCESS;
	int			error;

	if (!bp || (ip->i_flags & XFS_ISTALE)) {
		/*
		 * Inode item/buffer is being aborted due to cluster
		 * buffer deletion. Trigger a log force to have that operation
		 * completed and items removed from the AIL before the next push
		 * attempt.
		 */
		return XFS_ITEM_PINNED;
	}

	if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp))
		return XFS_ITEM_PINNED;

	if (xfs_iflags_test(ip, XFS_IFLUSHING))
		return XFS_ITEM_FLUSHING;

	if (!xfs_buf_trylock(bp))
		return XFS_ITEM_LOCKED;

	spin_unlock(&lip->li_ailp->ail_lock);

	/*
	 * We need to hold a reference for flushing the cluster buffer as it may
	 * fail the buffer without IO submission. In which case, we better get a
	 * reference for that completion because otherwise we don't get a
	 * reference for IO until we queue the buffer for delwri submission.
	 */
	xfs_buf_hold(bp);
	error = xfs_iflush_cluster(bp);
	if (!error) {
		if (!xfs_buf_delwri_queue(bp, buffer_list))
			rval = XFS_ITEM_FLUSHING;
		xfs_buf_relse(bp);
	} else {
		/*
		 * Release the buffer if we were unable to flush anything. On
		 * any other error, the buffer has already been released.
		 */
		if (error == -EAGAIN)
			xfs_buf_relse(bp);
		rval = XFS_ITEM_LOCKED;
	}

	spin_lock(&lip->li_ailp->ail_lock);
	return rval;
}

/*
 * Unlock the inode associated with the inode log item.
 */
STATIC void
xfs_inode_item_release(
	struct xfs_log_item	*lip)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	unsigned short		lock_flags;

	ASSERT(ip->i_itemp != NULL);
	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

	lock_flags = iip->ili_lock_flags;
	iip->ili_lock_flags = 0;
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
}

/*
 * This is called to find out where the oldest active copy of the inode log
 * item in the on disk log resides now that the last log write of it completed
 * at the given lsn.  Since we always re-log all dirty data in an inode, the
 * latest copy in the on disk log is the only one that matters.  Therefore,
 * simply return the given lsn.
 *
 * If the inode has been marked stale because the cluster is being freed, we
 * don't want to (re-)insert this inode into the AIL. There is a race condition
 * where the cluster buffer may be unpinned before the inode is inserted into
 * the AIL during transaction committed processing. If the buffer is unpinned
 * before the inode item has been committed and inserted, then it is possible
 * for the buffer to be written and IO completes before the inode is inserted
 * into the AIL. In that case, we'd be inserting a clean, stale inode into the
 * AIL which will never get removed. It will, however, get reclaimed which
 * triggers an assert in xfs_inode_free() complaining about freein an inode
 * still in the AIL.
 *
 * To avoid this, just unpin the inode directly and return a LSN of -1 so the
 * transaction committed code knows that it does not need to do any further
 * processing on the item.
 */
STATIC xfs_lsn_t
xfs_inode_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;

	if (xfs_iflags_test(ip, XFS_ISTALE)) {
		xfs_inode_item_unpin(lip, 0);
		return -1;
	}
	return lsn;
}

STATIC void
xfs_inode_item_committing(
	struct xfs_log_item	*lip,
	xfs_csn_t		seq)
{
	INODE_ITEM(lip)->ili_commit_seq = seq;
	return xfs_inode_item_release(lip);
}

static const struct xfs_item_ops xfs_inode_item_ops = {
	.iop_sort	= xfs_inode_item_sort,
	.iop_precommit	= xfs_inode_item_precommit,
	.iop_size	= xfs_inode_item_size,
	.iop_format	= xfs_inode_item_format,
	.iop_pin	= xfs_inode_item_pin,
	.iop_unpin	= xfs_inode_item_unpin,
	.iop_release	= xfs_inode_item_release,
	.iop_committed	= xfs_inode_item_committed,
	.iop_push	= xfs_inode_item_push,
	.iop_committing	= xfs_inode_item_committing,
};


/*
 * Initialize the inode log item for a newly allocated (in-core) inode.
 */
void
xfs_inode_item_init(
	struct xfs_inode	*ip,
	struct xfs_mount	*mp)
{
	struct xfs_inode_log_item *iip;

	ASSERT(ip->i_itemp == NULL);
	iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_cache,
					      GFP_KERNEL | __GFP_NOFAIL);

	iip->ili_inode = ip;
	spin_lock_init(&iip->ili_lock);
	xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE,
						&xfs_inode_item_ops);
}

/*
 * Free the inode log item and any memory hanging off of it.
 */
void
xfs_inode_item_destroy(
	struct xfs_inode	*ip)
{
	struct xfs_inode_log_item *iip = ip->i_itemp;

	ASSERT(iip->ili_item.li_buf == NULL);

	ip->i_itemp = NULL;
	kmem_free(iip->ili_item.li_lv_shadow);
	kmem_cache_free(xfs_ili_cache, iip);
}


/*
 * We only want to pull the item from the AIL if it is actually there
 * and its location in the log has not changed since we started the
 * flush.  Thus, we only bother if the inode's lsn has not changed.
 */
static void
xfs_iflush_ail_updates(
	struct xfs_ail		*ailp,
	struct list_head	*list)
{
	struct xfs_log_item	*lip;
	xfs_lsn_t		tail_lsn = 0;

	/* this is an opencoded batch version of xfs_trans_ail_delete */
	spin_lock(&ailp->ail_lock);
	list_for_each_entry(lip, list, li_bio_list) {
		xfs_lsn_t	lsn;

		clear_bit(XFS_LI_FAILED, &lip->li_flags);
		if (INODE_ITEM(lip)->ili_flush_lsn != lip->li_lsn)
			continue;

		/*
		 * dgc: Not sure how this happens, but it happens very
		 * occassionaly via generic/388.  xfs_iflush_abort() also
		 * silently handles this same "under writeback but not in AIL at
		 * shutdown" condition via xfs_trans_ail_delete().
		 */
		if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) {
			ASSERT(xlog_is_shutdown(lip->li_log));
			continue;
		}

		lsn = xfs_ail_delete_one(ailp, lip);
		if (!tail_lsn && lsn)
			tail_lsn = lsn;
	}
	xfs_ail_update_finish(ailp, tail_lsn);
}

/*
 * Walk the list of inodes that have completed their IOs. If they are clean
 * remove them from the list and dissociate them from the buffer. Buffers that
 * are still dirty remain linked to the buffer and on the list. Caller must
 * handle them appropriately.
 */
static void
xfs_iflush_finish(
	struct xfs_buf		*bp,
	struct list_head	*list)
{
	struct xfs_log_item	*lip, *n;

	list_for_each_entry_safe(lip, n, list, li_bio_list) {
		struct xfs_inode_log_item *iip = INODE_ITEM(lip);
		bool	drop_buffer = false;

		spin_lock(&iip->ili_lock);

		/*
		 * Remove the reference to the cluster buffer if the inode is
		 * clean in memory and drop the buffer reference once we've
		 * dropped the locks we hold.
		 */
		ASSERT(iip->ili_item.li_buf == bp);
		if (!iip->ili_fields) {
			iip->ili_item.li_buf = NULL;
			list_del_init(&lip->li_bio_list);
			drop_buffer = true;
		}
		iip->ili_last_fields = 0;
		iip->ili_flush_lsn = 0;
		spin_unlock(&iip->ili_lock);
		xfs_iflags_clear(iip->ili_inode, XFS_IFLUSHING);
		if (drop_buffer)
			xfs_buf_rele(bp);
	}
}

/*
 * Inode buffer IO completion routine.  It is responsible for removing inodes
 * attached to the buffer from the AIL if they have not been re-logged and
 * completing the inode flush.
 */
void
xfs_buf_inode_iodone(
	struct xfs_buf		*bp)
{
	struct xfs_log_item	*lip, *n;
	LIST_HEAD(flushed_inodes);
	LIST_HEAD(ail_updates);

	/*
	 * Pull the attached inodes from the buffer one at a time and take the
	 * appropriate action on them.
	 */
	list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) {
		struct xfs_inode_log_item *iip = INODE_ITEM(lip);

		if (xfs_iflags_test(iip->ili_inode, XFS_ISTALE)) {
			xfs_iflush_abort(iip->ili_inode);
			continue;
		}
		if (!iip->ili_last_fields)
			continue;

		/* Do an unlocked check for needing the AIL lock. */
		if (iip->ili_flush_lsn == lip->li_lsn ||
		    test_bit(XFS_LI_FAILED, &lip->li_flags))
			list_move_tail(&lip->li_bio_list, &ail_updates);
		else
			list_move_tail(&lip->li_bio_list, &flushed_inodes);
	}

	if (!list_empty(&ail_updates)) {
		xfs_iflush_ail_updates(bp->b_mount->m_ail, &ail_updates);
		list_splice_tail(&ail_updates, &flushed_inodes);
	}

	xfs_iflush_finish(bp, &flushed_inodes);
	if (!list_empty(&flushed_inodes))
		list_splice_tail(&flushed_inodes, &bp->b_li_list);
}

void
xfs_buf_inode_io_fail(
	struct xfs_buf		*bp)
{
	struct xfs_log_item	*lip;

	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
		set_bit(XFS_LI_FAILED, &lip->li_flags);
}

/*
 * Clear the inode logging fields so no more flushes are attempted.  If we are
 * on a buffer list, it is now safe to remove it because the buffer is
 * guaranteed to be locked. The caller will drop the reference to the buffer
 * the log item held.
 */
static void
xfs_iflush_abort_clean(
	struct xfs_inode_log_item *iip)
{
	iip->ili_last_fields = 0;
	iip->ili_fields = 0;
	iip->ili_fsync_fields = 0;
	iip->ili_flush_lsn = 0;
	iip->ili_item.li_buf = NULL;
	list_del_init(&iip->ili_item.li_bio_list);
}

/*
 * Abort flushing the inode from a context holding the cluster buffer locked.
 *
 * This is the normal runtime method of aborting writeback of an inode that is
 * attached to a cluster buffer. It occurs when the inode and the backing
 * cluster buffer have been freed (i.e. inode is XFS_ISTALE), or when cluster
 * flushing or buffer IO completion encounters a log shutdown situation.
 *
 * If we need to abort inode writeback and we don't already hold the buffer
 * locked, call xfs_iflush_shutdown_abort() instead as this should only ever be
 * necessary in a shutdown situation.
 */
void
xfs_iflush_abort(
	struct xfs_inode	*ip)
{
	struct xfs_inode_log_item *iip = ip->i_itemp;
	struct xfs_buf		*bp;

	if (!iip) {
		/* clean inode, nothing to do */
		xfs_iflags_clear(ip, XFS_IFLUSHING);
		return;
	}

	/*
	 * Remove the inode item from the AIL before we clear its internal
	 * state. Whilst the inode is in the AIL, it should have a valid buffer
	 * pointer for push operations to access - it is only safe to remove the
	 * inode from the buffer once it has been removed from the AIL.
	 *
	 * We also clear the failed bit before removing the item from the AIL
	 * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer
	 * references the inode item owns and needs to hold until we've fully
	 * aborted the inode log item and detached it from the buffer.
	 */
	clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags);
	xfs_trans_ail_delete(&iip->ili_item, 0);

	/*
	 * Grab the inode buffer so can we release the reference the inode log
	 * item holds on it.
	 */
	spin_lock(&iip->ili_lock);
	bp = iip->ili_item.li_buf;
	xfs_iflush_abort_clean(iip);
	spin_unlock(&iip->ili_lock);

	xfs_iflags_clear(ip, XFS_IFLUSHING);
	if (bp)
		xfs_buf_rele(bp);
}

/*
 * Abort an inode flush in the case of a shutdown filesystem. This can be called
 * from anywhere with just an inode reference and does not require holding the
 * inode cluster buffer locked. If the inode is attached to a cluster buffer,
 * it will grab and lock it safely, then abort the inode flush.
 */
void
xfs_iflush_shutdown_abort(
	struct xfs_inode	*ip)
{
	struct xfs_inode_log_item *iip = ip->i_itemp;
	struct xfs_buf		*bp;

	if (!iip) {
		/* clean inode, nothing to do */
		xfs_iflags_clear(ip, XFS_IFLUSHING);
		return;
	}

	spin_lock(&iip->ili_lock);
	bp = iip->ili_item.li_buf;
	if (!bp) {
		spin_unlock(&iip->ili_lock);
		xfs_iflush_abort(ip);
		return;
	}

	/*
	 * We have to take a reference to the buffer so that it doesn't get
	 * freed when we drop the ili_lock and then wait to lock the buffer.
	 * We'll clean up the extra reference after we pick up the ili_lock
	 * again.
	 */
	xfs_buf_hold(bp);
	spin_unlock(&iip->ili_lock);
	xfs_buf_lock(bp);

	spin_lock(&iip->ili_lock);
	if (!iip->ili_item.li_buf) {
		/*
		 * Raced with another removal, hold the only reference
		 * to bp now. Inode should not be in the AIL now, so just clean
		 * up and return;
		 */
		ASSERT(list_empty(&iip->ili_item.li_bio_list));
		ASSERT(!test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags));
		xfs_iflush_abort_clean(iip);
		spin_unlock(&iip->ili_lock);
		xfs_iflags_clear(ip, XFS_IFLUSHING);
		xfs_buf_relse(bp);
		return;
	}

	/*
	 * Got two references to bp. The first will get dropped by
	 * xfs_iflush_abort() when the item is removed from the buffer list, but
	 * we can't drop our reference until _abort() returns because we have to
	 * unlock the buffer as well. Hence we abort and then unlock and release
	 * our reference to the buffer.
	 */
	ASSERT(iip->ili_item.li_buf == bp);
	spin_unlock(&iip->ili_lock);
	xfs_iflush_abort(ip);
	xfs_buf_relse(bp);
}


/*
 * convert an xfs_inode_log_format struct from the old 32 bit version
 * (which can have different field alignments) to the native 64 bit version
 */
int
xfs_inode_item_format_convert(
	struct xfs_log_iovec		*buf,
	struct xfs_inode_log_format	*in_f)
{
	struct xfs_inode_log_format_32	*in_f32 = buf->i_addr;

	if (buf->i_len != sizeof(*in_f32)) {
		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
		return -EFSCORRUPTED;
	}

	in_f->ilf_type = in_f32->ilf_type;
	in_f->ilf_size = in_f32->ilf_size;
	in_f->ilf_fields = in_f32->ilf_fields;
	in_f->ilf_asize = in_f32->ilf_asize;
	in_f->ilf_dsize = in_f32->ilf_dsize;
	in_f->ilf_ino = in_f32->ilf_ino;
	memcpy(&in_f->ilf_u, &in_f32->ilf_u, sizeof(in_f->ilf_u));
	in_f->ilf_blkno = in_f32->ilf_blkno;
	in_f->ilf_len = in_f32->ilf_len;
	in_f->ilf_boffset = in_f32->ilf_boffset;
	return 0;
}