summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_defer.c
blob: 07d318b1f807a6c7e36a9f883bdf2d85a2b9628c (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
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2016 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_defer.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_log.h"
#include "xfs_rmap.h"
#include "xfs_refcount.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
#include "xfs_buf.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_trans_priv.h"

static struct kmem_cache	*xfs_defer_pending_cache;

/*
 * Deferred Operations in XFS
 *
 * Due to the way locking rules work in XFS, certain transactions (block
 * mapping and unmapping, typically) have permanent reservations so that
 * we can roll the transaction to adhere to AG locking order rules and
 * to unlock buffers between metadata updates.  Prior to rmap/reflink,
 * the mapping code had a mechanism to perform these deferrals for
 * extents that were going to be freed; this code makes that facility
 * more generic.
 *
 * When adding the reverse mapping and reflink features, it became
 * necessary to perform complex remapping multi-transactions to comply
 * with AG locking order rules, and to be able to spread a single
 * refcount update operation (an operation on an n-block extent can
 * update as many as n records!) among multiple transactions.  XFS can
 * roll a transaction to facilitate this, but using this facility
 * requires us to log "intent" items in case log recovery needs to
 * redo the operation, and to log "done" items to indicate that redo
 * is not necessary.
 *
 * Deferred work is tracked in xfs_defer_pending items.  Each pending
 * item tracks one type of deferred work.  Incoming work items (which
 * have not yet had an intent logged) are attached to a pending item
 * on the dop_intake list, where they wait for the caller to finish
 * the deferred operations.
 *
 * Finishing a set of deferred operations is an involved process.  To
 * start, we define "rolling a deferred-op transaction" as follows:
 *
 * > For each xfs_defer_pending item on the dop_intake list,
 *   - Sort the work items in AG order.  XFS locking
 *     order rules require us to lock buffers in AG order.
 *   - Create a log intent item for that type.
 *   - Attach it to the pending item.
 *   - Move the pending item from the dop_intake list to the
 *     dop_pending list.
 * > Roll the transaction.
 *
 * NOTE: To avoid exceeding the transaction reservation, we limit the
 * number of items that we attach to a given xfs_defer_pending.
 *
 * The actual finishing process looks like this:
 *
 * > For each xfs_defer_pending in the dop_pending list,
 *   - Roll the deferred-op transaction as above.
 *   - Create a log done item for that type, and attach it to the
 *     log intent item.
 *   - For each work item attached to the log intent item,
 *     * Perform the described action.
 *     * Attach the work item to the log done item.
 *     * If the result of doing the work was -EAGAIN, ->finish work
 *       wants a new transaction.  See the "Requesting a Fresh
 *       Transaction while Finishing Deferred Work" section below for
 *       details.
 *
 * The key here is that we must log an intent item for all pending
 * work items every time we roll the transaction, and that we must log
 * a done item as soon as the work is completed.  With this mechanism
 * we can perform complex remapping operations, chaining intent items
 * as needed.
 *
 * Requesting a Fresh Transaction while Finishing Deferred Work
 *
 * If ->finish_item decides that it needs a fresh transaction to
 * finish the work, it must ask its caller (xfs_defer_finish) for a
 * continuation.  The most likely cause of this circumstance are the
 * refcount adjust functions deciding that they've logged enough items
 * to be at risk of exceeding the transaction reservation.
 *
 * To get a fresh transaction, we want to log the existing log done
 * item to prevent the log intent item from replaying, immediately log
 * a new log intent item with the unfinished work items, roll the
 * transaction, and re-call ->finish_item wherever it left off.  The
 * log done item and the new log intent item must be in the same
 * transaction or atomicity cannot be guaranteed; defer_finish ensures
 * that this happens.
 *
 * This requires some coordination between ->finish_item and
 * defer_finish.  Upon deciding to request a new transaction,
 * ->finish_item should update the current work item to reflect the
 * unfinished work.  Next, it should reset the log done item's list
 * count to the number of items finished, and return -EAGAIN.
 * defer_finish sees the -EAGAIN, logs the new log intent item
 * with the remaining work items, and leaves the xfs_defer_pending
 * item at the head of the dop_work queue.  Then it rolls the
 * transaction and picks up processing where it left off.  It is
 * required that ->finish_item must be careful to leave enough
 * transaction reservation to fit the new log intent item.
 *
 * This is an example of remapping the extent (E, E+B) into file X at
 * offset A and dealing with the extent (C, C+B) already being mapped
 * there:
 * +-------------------------------------------------+
 * | Unmap file X startblock C offset A length B     | t0
 * | Intent to reduce refcount for extent (C, B)     |
 * | Intent to remove rmap (X, C, A, B)              |
 * | Intent to free extent (D, 1) (bmbt block)       |
 * | Intent to map (X, A, B) at startblock E         |
 * +-------------------------------------------------+
 * | Map file X startblock E offset A length B       | t1
 * | Done mapping (X, E, A, B)                       |
 * | Intent to increase refcount for extent (E, B)   |
 * | Intent to add rmap (X, E, A, B)                 |
 * +-------------------------------------------------+
 * | Reduce refcount for extent (C, B)               | t2
 * | Done reducing refcount for extent (C, 9)        |
 * | Intent to reduce refcount for extent (C+9, B-9) |
 * | (ran out of space after 9 refcount updates)     |
 * +-------------------------------------------------+
 * | Reduce refcount for extent (C+9, B+9)           | t3
 * | Done reducing refcount for extent (C+9, B-9)    |
 * | Increase refcount for extent (E, B)             |
 * | Done increasing refcount for extent (E, B)      |
 * | Intent to free extent (C, B)                    |
 * | Intent to free extent (F, 1) (refcountbt block) |
 * | Intent to remove rmap (F, 1, REFC)              |
 * +-------------------------------------------------+
 * | Remove rmap (X, C, A, B)                        | t4
 * | Done removing rmap (X, C, A, B)                 |
 * | Add rmap (X, E, A, B)                           |
 * | Done adding rmap (X, E, A, B)                   |
 * | Remove rmap (F, 1, REFC)                        |
 * | Done removing rmap (F, 1, REFC)                 |
 * +-------------------------------------------------+
 * | Free extent (C, B)                              | t5
 * | Done freeing extent (C, B)                      |
 * | Free extent (D, 1)                              |
 * | Done freeing extent (D, 1)                      |
 * | Free extent (F, 1)                              |
 * | Done freeing extent (F, 1)                      |
 * +-------------------------------------------------+
 *
 * If we should crash before t2 commits, log recovery replays
 * the following intent items:
 *
 * - Intent to reduce refcount for extent (C, B)
 * - Intent to remove rmap (X, C, A, B)
 * - Intent to free extent (D, 1) (bmbt block)
 * - Intent to increase refcount for extent (E, B)
 * - Intent to add rmap (X, E, A, B)
 *
 * In the process of recovering, it should also generate and take care
 * of these intent items:
 *
 * - Intent to free extent (C, B)
 * - Intent to free extent (F, 1) (refcountbt block)
 * - Intent to remove rmap (F, 1, REFC)
 *
 * Note that the continuation requested between t2 and t3 is likely to
 * reoccur.
 */
STATIC struct xfs_log_item *
xfs_defer_barrier_create_intent(
	struct xfs_trans		*tp,
	struct list_head		*items,
	unsigned int			count,
	bool				sort)
{
	return NULL;
}

STATIC void
xfs_defer_barrier_abort_intent(
	struct xfs_log_item		*intent)
{
	/* empty */
}

STATIC struct xfs_log_item *
xfs_defer_barrier_create_done(
	struct xfs_trans		*tp,
	struct xfs_log_item		*intent,
	unsigned int			count)
{
	return NULL;
}

STATIC int
xfs_defer_barrier_finish_item(
	struct xfs_trans		*tp,
	struct xfs_log_item		*done,
	struct list_head		*item,
	struct xfs_btree_cur		**state)
{
	ASSERT(0);
	return -EFSCORRUPTED;
}

STATIC void
xfs_defer_barrier_cancel_item(
	struct list_head		*item)
{
	ASSERT(0);
}

static const struct xfs_defer_op_type xfs_barrier_defer_type = {
	.max_items	= 1,
	.create_intent	= xfs_defer_barrier_create_intent,
	.abort_intent	= xfs_defer_barrier_abort_intent,
	.create_done	= xfs_defer_barrier_create_done,
	.finish_item	= xfs_defer_barrier_finish_item,
	.cancel_item	= xfs_defer_barrier_cancel_item,
};

/* Create a log intent done item for a log intent item. */
static inline void
xfs_defer_create_done(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp)
{
	struct xfs_log_item		*lip;

	/* If there is no log intent item, there can be no log done item. */
	if (!dfp->dfp_intent)
		return;

	/*
	 * Mark the transaction dirty, even on error. This ensures the
	 * transaction is aborted, which:
	 *
	 * 1.) releases the log intent item and frees the log done item
	 * 2.) shuts down the filesystem
	 */
	tp->t_flags |= XFS_TRANS_DIRTY;
	lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
	if (!lip)
		return;

	tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE;
	xfs_trans_add_item(tp, lip);
	set_bit(XFS_LI_DIRTY, &lip->li_flags);
	dfp->dfp_done = lip;
}

/*
 * Ensure there's a log intent item associated with this deferred work item if
 * the operation must be restarted on crash.  Returns 1 if there's a log item;
 * 0 if there isn't; or a negative errno.
 */
static int
xfs_defer_create_intent(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp,
	bool				sort)
{
	struct xfs_log_item		*lip;

	if (dfp->dfp_intent)
		return 1;

	lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count,
			sort);
	if (!lip)
		return 0;
	if (IS_ERR(lip))
		return PTR_ERR(lip);

	tp->t_flags |= XFS_TRANS_DIRTY;
	xfs_trans_add_item(tp, lip);
	set_bit(XFS_LI_DIRTY, &lip->li_flags);
	dfp->dfp_intent = lip;
	return 1;
}

/*
 * For each pending item in the intake list, log its intent item and the
 * associated extents, then add the entire intake list to the end of
 * the pending list.
 *
 * Returns 1 if at least one log item was associated with the deferred work;
 * 0 if there are no log items; or a negative errno.
 */
static int
xfs_defer_create_intents(
	struct xfs_trans		*tp)
{
	struct xfs_defer_pending	*dfp;
	int				ret = 0;

	list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
		int			ret2;

		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
		ret2 = xfs_defer_create_intent(tp, dfp, true);
		if (ret2 < 0)
			return ret2;
		ret |= ret2;
	}
	return ret;
}

static inline void
xfs_defer_pending_abort(
	struct xfs_mount		*mp,
	struct xfs_defer_pending	*dfp)
{
	trace_xfs_defer_pending_abort(mp, dfp);

	if (dfp->dfp_intent && !dfp->dfp_done) {
		dfp->dfp_ops->abort_intent(dfp->dfp_intent);
		dfp->dfp_intent = NULL;
	}
}

static inline void
xfs_defer_pending_cancel_work(
	struct xfs_mount		*mp,
	struct xfs_defer_pending	*dfp)
{
	struct list_head		*pwi;
	struct list_head		*n;

	trace_xfs_defer_cancel_list(mp, dfp);

	list_del(&dfp->dfp_list);
	list_for_each_safe(pwi, n, &dfp->dfp_work) {
		list_del(pwi);
		dfp->dfp_count--;
		trace_xfs_defer_cancel_item(mp, dfp, pwi);
		dfp->dfp_ops->cancel_item(pwi);
	}
	ASSERT(dfp->dfp_count == 0);
	kmem_cache_free(xfs_defer_pending_cache, dfp);
}

STATIC void
xfs_defer_pending_abort_list(
	struct xfs_mount		*mp,
	struct list_head		*dop_list)
{
	struct xfs_defer_pending	*dfp;

	/* Abort intent items that don't have a done item. */
	list_for_each_entry(dfp, dop_list, dfp_list)
		xfs_defer_pending_abort(mp, dfp);
}

/* Abort all the intents that were committed. */
STATIC void
xfs_defer_trans_abort(
	struct xfs_trans		*tp,
	struct list_head		*dop_pending)
{
	trace_xfs_defer_trans_abort(tp, _RET_IP_);
	xfs_defer_pending_abort_list(tp->t_mountp, dop_pending);
}

/*
 * Capture resources that the caller said not to release ("held") when the
 * transaction commits.  Caller is responsible for zero-initializing @dres.
 */
static int
xfs_defer_save_resources(
	struct xfs_defer_resources	*dres,
	struct xfs_trans		*tp)
{
	struct xfs_buf_log_item		*bli;
	struct xfs_inode_log_item	*ili;
	struct xfs_log_item		*lip;

	BUILD_BUG_ON(NBBY * sizeof(dres->dr_ordered) < XFS_DEFER_OPS_NR_BUFS);

	list_for_each_entry(lip, &tp->t_items, li_trans) {
		switch (lip->li_type) {
		case XFS_LI_BUF:
			bli = container_of(lip, struct xfs_buf_log_item,
					   bli_item);
			if (bli->bli_flags & XFS_BLI_HOLD) {
				if (dres->dr_bufs >= XFS_DEFER_OPS_NR_BUFS) {
					ASSERT(0);
					return -EFSCORRUPTED;
				}
				if (bli->bli_flags & XFS_BLI_ORDERED)
					dres->dr_ordered |=
							(1U << dres->dr_bufs);
				else
					xfs_trans_dirty_buf(tp, bli->bli_buf);
				dres->dr_bp[dres->dr_bufs++] = bli->bli_buf;
			}
			break;
		case XFS_LI_INODE:
			ili = container_of(lip, struct xfs_inode_log_item,
					   ili_item);
			if (ili->ili_lock_flags == 0) {
				if (dres->dr_inos >= XFS_DEFER_OPS_NR_INODES) {
					ASSERT(0);
					return -EFSCORRUPTED;
				}
				xfs_trans_log_inode(tp, ili->ili_inode,
						    XFS_ILOG_CORE);
				dres->dr_ip[dres->dr_inos++] = ili->ili_inode;
			}
			break;
		default:
			break;
		}
	}

	return 0;
}

/* Attach the held resources to the transaction. */
static void
xfs_defer_restore_resources(
	struct xfs_trans		*tp,
	struct xfs_defer_resources	*dres)
{
	unsigned short			i;

	/* Rejoin the joined inodes. */
	for (i = 0; i < dres->dr_inos; i++)
		xfs_trans_ijoin(tp, dres->dr_ip[i], 0);

	/* Rejoin the buffers and dirty them so the log moves forward. */
	for (i = 0; i < dres->dr_bufs; i++) {
		xfs_trans_bjoin(tp, dres->dr_bp[i]);
		if (dres->dr_ordered & (1U << i))
			xfs_trans_ordered_buf(tp, dres->dr_bp[i]);
		xfs_trans_bhold(tp, dres->dr_bp[i]);
	}
}

/* Roll a transaction so we can do some deferred op processing. */
STATIC int
xfs_defer_trans_roll(
	struct xfs_trans		**tpp)
{
	struct xfs_defer_resources	dres = { };
	int				error;

	error = xfs_defer_save_resources(&dres, *tpp);
	if (error)
		return error;

	trace_xfs_defer_trans_roll(*tpp, _RET_IP_);

	/*
	 * Roll the transaction.  Rolling always given a new transaction (even
	 * if committing the old one fails!) to hand back to the caller, so we
	 * join the held resources to the new transaction so that we always
	 * return with the held resources joined to @tpp, no matter what
	 * happened.
	 */
	error = xfs_trans_roll(tpp);

	xfs_defer_restore_resources(*tpp, &dres);

	if (error)
		trace_xfs_defer_trans_roll_error(*tpp, error);
	return error;
}

/*
 * Free up any items left in the list.
 */
static void
xfs_defer_cancel_list(
	struct xfs_mount		*mp,
	struct list_head		*dop_list)
{
	struct xfs_defer_pending	*dfp;
	struct xfs_defer_pending	*pli;

	/*
	 * Free the pending items.  Caller should already have arranged
	 * for the intent items to be released.
	 */
	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list)
		xfs_defer_pending_cancel_work(mp, dfp);
}

static inline void
xfs_defer_relog_intent(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp)
{
	struct xfs_log_item		*lip;

	xfs_defer_create_done(tp, dfp);

	lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
	if (lip) {
		xfs_trans_add_item(tp, lip);
		set_bit(XFS_LI_DIRTY, &lip->li_flags);
	}
	dfp->dfp_done = NULL;
	dfp->dfp_intent = lip;
}

/*
 * Prevent a log intent item from pinning the tail of the log by logging a
 * done item to release the intent item; and then log a new intent item.
 * The caller should provide a fresh transaction and roll it after we're done.
 */
static void
xfs_defer_relog(
	struct xfs_trans		**tpp,
	struct list_head		*dfops)
{
	struct xlog			*log = (*tpp)->t_mountp->m_log;
	struct xfs_defer_pending	*dfp;
	xfs_lsn_t			threshold_lsn = NULLCOMMITLSN;


	ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES);

	list_for_each_entry(dfp, dfops, dfp_list) {
		/*
		 * If the log intent item for this deferred op is not a part of
		 * the current log checkpoint, relog the intent item to keep
		 * the log tail moving forward.  We're ok with this being racy
		 * because an incorrect decision means we'll be a little slower
		 * at pushing the tail.
		 */
		if (dfp->dfp_intent == NULL ||
		    xfs_log_item_in_current_chkpt(dfp->dfp_intent))
			continue;

		/*
		 * Figure out where we need the tail to be in order to maintain
		 * the minimum required free space in the log.  Only sample
		 * the log threshold once per call.
		 */
		if (threshold_lsn == NULLCOMMITLSN) {
			threshold_lsn = xlog_grant_push_threshold(log, 0);
			if (threshold_lsn == NULLCOMMITLSN)
				break;
		}
		if (XFS_LSN_CMP(dfp->dfp_intent->li_lsn, threshold_lsn) >= 0)
			continue;

		trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);

		xfs_defer_relog_intent(*tpp, dfp);
	}
}

/*
 * Log an intent-done item for the first pending intent, and finish the work
 * items.
 */
int
xfs_defer_finish_one(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp)
{
	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
	struct xfs_btree_cur		*state = NULL;
	struct list_head		*li, *n;
	int				error;

	trace_xfs_defer_pending_finish(tp->t_mountp, dfp);

	xfs_defer_create_done(tp, dfp);
	list_for_each_safe(li, n, &dfp->dfp_work) {
		list_del(li);
		dfp->dfp_count--;
		trace_xfs_defer_finish_item(tp->t_mountp, dfp, li);
		error = ops->finish_item(tp, dfp->dfp_done, li, &state);
		if (error == -EAGAIN) {
			int		ret;

			/*
			 * Caller wants a fresh transaction; put the work item
			 * back on the list and log a new log intent item to
			 * replace the old one.  See "Requesting a Fresh
			 * Transaction while Finishing Deferred Work" above.
			 */
			list_add(li, &dfp->dfp_work);
			dfp->dfp_count++;
			dfp->dfp_done = NULL;
			dfp->dfp_intent = NULL;
			ret = xfs_defer_create_intent(tp, dfp, false);
			if (ret < 0)
				error = ret;
		}

		if (error)
			goto out;
	}

	/* Done with the dfp, free it. */
	list_del(&dfp->dfp_list);
	kmem_cache_free(xfs_defer_pending_cache, dfp);
out:
	if (ops->finish_cleanup)
		ops->finish_cleanup(tp, state, error);
	return error;
}

/* Move all paused deferred work from @tp to @paused_list. */
static void
xfs_defer_isolate_paused(
	struct xfs_trans		*tp,
	struct list_head		*paused_list)
{
	struct xfs_defer_pending	*dfp;
	struct xfs_defer_pending	*pli;

	list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) {
		if (!(dfp->dfp_flags & XFS_DEFER_PAUSED))
			continue;

		list_move_tail(&dfp->dfp_list, paused_list);
		trace_xfs_defer_isolate_paused(tp->t_mountp, dfp);
	}
}

/*
 * Finish all the pending work.  This involves logging intent items for
 * any work items that wandered in since the last transaction roll (if
 * one has even happened), rolling the transaction, and finishing the
 * work items in the first item on the logged-and-pending list.
 *
 * If an inode is provided, relog it to the new transaction.
 */
int
xfs_defer_finish_noroll(
	struct xfs_trans		**tp)
{
	struct xfs_defer_pending	*dfp = NULL;
	int				error = 0;
	LIST_HEAD(dop_pending);
	LIST_HEAD(dop_paused);

	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);

	trace_xfs_defer_finish(*tp, _RET_IP_);

	/* Until we run out of pending work to finish... */
	while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) {
		/*
		 * Deferred items that are created in the process of finishing
		 * other deferred work items should be queued at the head of
		 * the pending list, which puts them ahead of the deferred work
		 * that was created by the caller.  This keeps the number of
		 * pending work items to a minimum, which decreases the amount
		 * of time that any one intent item can stick around in memory,
		 * pinning the log tail.
		 */
		int has_intents = xfs_defer_create_intents(*tp);

		xfs_defer_isolate_paused(*tp, &dop_paused);

		list_splice_init(&(*tp)->t_dfops, &dop_pending);

		if (has_intents < 0) {
			error = has_intents;
			goto out_shutdown;
		}
		if (has_intents || dfp) {
			error = xfs_defer_trans_roll(tp);
			if (error)
				goto out_shutdown;

			/* Relog intent items to keep the log moving. */
			xfs_defer_relog(tp, &dop_pending);
			xfs_defer_relog(tp, &dop_paused);

			if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
				error = xfs_defer_trans_roll(tp);
				if (error)
					goto out_shutdown;
			}
		}

		dfp = list_first_entry_or_null(&dop_pending,
				struct xfs_defer_pending, dfp_list);
		if (!dfp)
			break;
		error = xfs_defer_finish_one(*tp, dfp);
		if (error && error != -EAGAIN)
			goto out_shutdown;
	}

	/* Requeue the paused items in the outgoing transaction. */
	list_splice_tail_init(&dop_paused, &(*tp)->t_dfops);

	trace_xfs_defer_finish_done(*tp, _RET_IP_);
	return 0;

out_shutdown:
	list_splice_tail_init(&dop_paused, &dop_pending);
	xfs_defer_trans_abort(*tp, &dop_pending);
	xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
	trace_xfs_defer_finish_error(*tp, error);
	xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending);
	xfs_defer_cancel(*tp);
	return error;
}

int
xfs_defer_finish(
	struct xfs_trans	**tp)
{
#ifdef DEBUG
	struct xfs_defer_pending *dfp;
#endif
	int			error;

	/*
	 * Finish and roll the transaction once more to avoid returning to the
	 * caller with a dirty transaction.
	 */
	error = xfs_defer_finish_noroll(tp);
	if (error)
		return error;
	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
		error = xfs_defer_trans_roll(tp);
		if (error) {
			xfs_force_shutdown((*tp)->t_mountp,
					   SHUTDOWN_CORRUPT_INCORE);
			return error;
		}
	}

	/* Reset LOWMODE now that we've finished all the dfops. */
#ifdef DEBUG
	list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list)
		ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
#endif
	(*tp)->t_flags &= ~XFS_TRANS_LOWMODE;
	return 0;
}

void
xfs_defer_cancel(
	struct xfs_trans	*tp)
{
	struct xfs_mount	*mp = tp->t_mountp;

	trace_xfs_defer_cancel(tp, _RET_IP_);
	xfs_defer_trans_abort(tp, &tp->t_dfops);
	xfs_defer_cancel_list(mp, &tp->t_dfops);
}

/*
 * Return the last pending work item attached to this transaction if it matches
 * the deferred op type.
 */
static inline struct xfs_defer_pending *
xfs_defer_find_last(
	struct xfs_trans		*tp,
	const struct xfs_defer_op_type	*ops)
{
	struct xfs_defer_pending	*dfp = NULL;

	/* No dfops at all? */
	if (list_empty(&tp->t_dfops))
		return NULL;

	dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending,
			dfp_list);

	/* Wrong type? */
	if (dfp->dfp_ops != ops)
		return NULL;
	return dfp;
}

/*
 * Decide if we can add a deferred work item to the last dfops item attached
 * to the transaction.
 */
static inline bool
xfs_defer_can_append(
	struct xfs_defer_pending	*dfp,
	const struct xfs_defer_op_type	*ops)
{
	/* Already logged? */
	if (dfp->dfp_intent)
		return false;

	/* Paused items cannot absorb more work */
	if (dfp->dfp_flags & XFS_DEFER_PAUSED)
		return NULL;

	/* Already full? */
	if (ops->max_items && dfp->dfp_count >= ops->max_items)
		return false;

	return true;
}

/* Create a new pending item at the end of the transaction list. */
static inline struct xfs_defer_pending *
xfs_defer_alloc(
	struct xfs_trans		*tp,
	const struct xfs_defer_op_type	*ops)
{
	struct xfs_defer_pending	*dfp;

	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
			GFP_NOFS | __GFP_NOFAIL);
	dfp->dfp_ops = ops;
	INIT_LIST_HEAD(&dfp->dfp_work);
	list_add_tail(&dfp->dfp_list, &tp->t_dfops);

	return dfp;
}

/* Add an item for later deferred processing. */
struct xfs_defer_pending *
xfs_defer_add(
	struct xfs_trans		*tp,
	struct list_head		*li,
	const struct xfs_defer_op_type	*ops)
{
	struct xfs_defer_pending	*dfp = NULL;

	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);

	dfp = xfs_defer_find_last(tp, ops);
	if (!dfp || !xfs_defer_can_append(dfp, ops))
		dfp = xfs_defer_alloc(tp, ops);

	xfs_defer_add_item(dfp, li);
	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
	return dfp;
}

/*
 * Add a defer ops barrier to force two otherwise adjacent deferred work items
 * to be tracked separately and have separate log items.
 */
void
xfs_defer_add_barrier(
	struct xfs_trans		*tp)
{
	struct xfs_defer_pending	*dfp;

	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);

	/* If the last defer op added was a barrier, we're done. */
	dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type);
	if (dfp)
		return;

	xfs_defer_alloc(tp, &xfs_barrier_defer_type);

	trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
}

/*
 * Create a pending deferred work item to replay the recovered intent item
 * and add it to the list.
 */
void
xfs_defer_start_recovery(
	struct xfs_log_item		*lip,
	struct list_head		*r_dfops,
	const struct xfs_defer_op_type	*ops)
{
	struct xfs_defer_pending	*dfp;

	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
			GFP_NOFS | __GFP_NOFAIL);
	dfp->dfp_ops = ops;
	dfp->dfp_intent = lip;
	INIT_LIST_HEAD(&dfp->dfp_work);
	list_add_tail(&dfp->dfp_list, r_dfops);
}

/*
 * Cancel a deferred work item created to recover a log intent item.  @dfp
 * will be freed after this function returns.
 */
void
xfs_defer_cancel_recovery(
	struct xfs_mount		*mp,
	struct xfs_defer_pending	*dfp)
{
	xfs_defer_pending_abort(mp, dfp);
	xfs_defer_pending_cancel_work(mp, dfp);
}

/* Replay the deferred work item created from a recovered log intent item. */
int
xfs_defer_finish_recovery(
	struct xfs_mount		*mp,
	struct xfs_defer_pending	*dfp,
	struct list_head		*capture_list)
{
	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
	int				error;

	/* dfp is freed by recover_work and must not be accessed afterwards */
	error = ops->recover_work(dfp, capture_list);
	if (error)
		trace_xlog_intent_recovery_failed(mp, ops, error);
	return error;
}

/*
 * Move deferred ops from one transaction to another and reset the source to
 * initial state. This is primarily used to carry state forward across
 * transaction rolls with pending dfops.
 */
void
xfs_defer_move(
	struct xfs_trans	*dtp,
	struct xfs_trans	*stp)
{
	list_splice_init(&stp->t_dfops, &dtp->t_dfops);

	/*
	 * Low free space mode was historically controlled by a dfops field.
	 * This meant that low mode state potentially carried across multiple
	 * transaction rolls. Transfer low mode on a dfops move to preserve
	 * that behavior.
	 */
	dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);
	stp->t_flags &= ~XFS_TRANS_LOWMODE;
}

/*
 * Prepare a chain of fresh deferred ops work items to be completed later.  Log
 * recovery requires the ability to put off until later the actual finishing
 * work so that it can process unfinished items recovered from the log in
 * correct order.
 *
 * Create and log intent items for all the work that we're capturing so that we
 * can be assured that the items will get replayed if the system goes down
 * before log recovery gets a chance to finish the work it put off.  The entire
 * deferred ops state is transferred to the capture structure and the
 * transaction is then ready for the caller to commit it.  If there are no
 * intent items to capture, this function returns NULL.
 *
 * If capture_ip is not NULL, the capture structure will obtain an extra
 * reference to the inode.
 */
static struct xfs_defer_capture *
xfs_defer_ops_capture(
	struct xfs_trans		*tp)
{
	struct xfs_defer_capture	*dfc;
	unsigned short			i;
	int				error;

	if (list_empty(&tp->t_dfops))
		return NULL;

	error = xfs_defer_create_intents(tp);
	if (error < 0)
		return ERR_PTR(error);

	/* Create an object to capture the defer ops. */
	dfc = kzalloc(sizeof(*dfc), GFP_NOFS | __GFP_NOFAIL);
	INIT_LIST_HEAD(&dfc->dfc_list);
	INIT_LIST_HEAD(&dfc->dfc_dfops);

	/* Move the dfops chain and transaction state to the capture struct. */
	list_splice_init(&tp->t_dfops, &dfc->dfc_dfops);
	dfc->dfc_tpflags = tp->t_flags & XFS_TRANS_LOWMODE;
	tp->t_flags &= ~XFS_TRANS_LOWMODE;

	/* Capture the remaining block reservations along with the dfops. */
	dfc->dfc_blkres = tp->t_blk_res - tp->t_blk_res_used;
	dfc->dfc_rtxres = tp->t_rtx_res - tp->t_rtx_res_used;

	/* Preserve the log reservation size. */
	dfc->dfc_logres = tp->t_log_res;

	error = xfs_defer_save_resources(&dfc->dfc_held, tp);
	if (error) {
		/*
		 * Resource capture should never fail, but if it does, we
		 * still have to shut down the log and release things
		 * properly.
		 */
		xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE);
	}

	/*
	 * Grab extra references to the inodes and buffers because callers are
	 * expected to release their held references after we commit the
	 * transaction.
	 */
	for (i = 0; i < dfc->dfc_held.dr_inos; i++) {
		ASSERT(xfs_isilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL));
		ihold(VFS_I(dfc->dfc_held.dr_ip[i]));
	}

	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
		xfs_buf_hold(dfc->dfc_held.dr_bp[i]);

	return dfc;
}

/* Release all resources that we used to capture deferred ops. */
void
xfs_defer_ops_capture_abort(
	struct xfs_mount		*mp,
	struct xfs_defer_capture	*dfc)
{
	unsigned short			i;

	xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops);
	xfs_defer_cancel_list(mp, &dfc->dfc_dfops);

	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
		xfs_buf_relse(dfc->dfc_held.dr_bp[i]);

	for (i = 0; i < dfc->dfc_held.dr_inos; i++)
		xfs_irele(dfc->dfc_held.dr_ip[i]);

	kmem_free(dfc);
}

/*
 * Capture any deferred ops and commit the transaction.  This is the last step
 * needed to finish a log intent item that we recovered from the log.  If any
 * of the deferred ops operate on an inode, the caller must pass in that inode
 * so that the reference can be transferred to the capture structure.  The
 * caller must hold ILOCK_EXCL on the inode, and must unlock it before calling
 * xfs_defer_ops_continue.
 */
int
xfs_defer_ops_capture_and_commit(
	struct xfs_trans		*tp,
	struct list_head		*capture_list)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_defer_capture	*dfc;
	int				error;

	/* If we don't capture anything, commit transaction and exit. */
	dfc = xfs_defer_ops_capture(tp);
	if (IS_ERR(dfc)) {
		xfs_trans_cancel(tp);
		return PTR_ERR(dfc);
	}
	if (!dfc)
		return xfs_trans_commit(tp);

	/* Commit the transaction and add the capture structure to the list. */
	error = xfs_trans_commit(tp);
	if (error) {
		xfs_defer_ops_capture_abort(mp, dfc);
		return error;
	}

	list_add_tail(&dfc->dfc_list, capture_list);
	return 0;
}

/*
 * Attach a chain of captured deferred ops to a new transaction and free the
 * capture structure.  If an inode was captured, it will be passed back to the
 * caller with ILOCK_EXCL held and joined to the transaction with lockflags==0.
 * The caller now owns the inode reference.
 */
void
xfs_defer_ops_continue(
	struct xfs_defer_capture	*dfc,
	struct xfs_trans		*tp,
	struct xfs_defer_resources	*dres)
{
	unsigned int			i;

	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
	ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));

	/* Lock the captured resources to the new transaction. */
	if (dfc->dfc_held.dr_inos == 2)
		xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL,
				    dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL);
	else if (dfc->dfc_held.dr_inos == 1)
		xfs_ilock(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL);

	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
		xfs_buf_lock(dfc->dfc_held.dr_bp[i]);

	/* Join the captured resources to the new transaction. */
	xfs_defer_restore_resources(tp, &dfc->dfc_held);
	memcpy(dres, &dfc->dfc_held, sizeof(struct xfs_defer_resources));
	dres->dr_bufs = 0;

	/* Move captured dfops chain and state to the transaction. */
	list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
	tp->t_flags |= dfc->dfc_tpflags;

	kmem_free(dfc);
}

/* Release the resources captured and continued during recovery. */
void
xfs_defer_resources_rele(
	struct xfs_defer_resources	*dres)
{
	unsigned short			i;

	for (i = 0; i < dres->dr_inos; i++) {
		xfs_iunlock(dres->dr_ip[i], XFS_ILOCK_EXCL);
		xfs_irele(dres->dr_ip[i]);
		dres->dr_ip[i] = NULL;
	}

	for (i = 0; i < dres->dr_bufs; i++) {
		xfs_buf_relse(dres->dr_bp[i]);
		dres->dr_bp[i] = NULL;
	}

	dres->dr_inos = 0;
	dres->dr_bufs = 0;
	dres->dr_ordered = 0;
}

static inline int __init
xfs_defer_init_cache(void)
{
	xfs_defer_pending_cache = kmem_cache_create("xfs_defer_pending",
			sizeof(struct xfs_defer_pending),
			0, 0, NULL);

	return xfs_defer_pending_cache != NULL ? 0 : -ENOMEM;
}

static inline void
xfs_defer_destroy_cache(void)
{
	kmem_cache_destroy(xfs_defer_pending_cache);
	xfs_defer_pending_cache = NULL;
}

/* Set up caches for deferred work items. */
int __init
xfs_defer_init_item_caches(void)
{
	int				error;

	error = xfs_defer_init_cache();
	if (error)
		return error;
	error = xfs_rmap_intent_init_cache();
	if (error)
		goto err;
	error = xfs_refcount_intent_init_cache();
	if (error)
		goto err;
	error = xfs_bmap_intent_init_cache();
	if (error)
		goto err;
	error = xfs_extfree_intent_init_cache();
	if (error)
		goto err;
	error = xfs_attr_intent_init_cache();
	if (error)
		goto err;
	return 0;
err:
	xfs_defer_destroy_item_caches();
	return error;
}

/* Destroy all the deferred work item caches, if they've been allocated. */
void
xfs_defer_destroy_item_caches(void)
{
	xfs_attr_intent_destroy_cache();
	xfs_extfree_intent_destroy_cache();
	xfs_bmap_intent_destroy_cache();
	xfs_refcount_intent_destroy_cache();
	xfs_rmap_intent_destroy_cache();
	xfs_defer_destroy_cache();
}

/*
 * Mark a deferred work item so that it will be requeued indefinitely without
 * being finished.  Caller must ensure there are no data dependencies on this
 * work item in the meantime.
 */
void
xfs_defer_item_pause(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp)
{
	ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED));

	dfp->dfp_flags |= XFS_DEFER_PAUSED;

	trace_xfs_defer_item_pause(tp->t_mountp, dfp);
}

/*
 * Release a paused deferred work item so that it will be finished during the
 * next transaction roll.
 */
void
xfs_defer_item_unpause(
	struct xfs_trans		*tp,
	struct xfs_defer_pending	*dfp)
{
	ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);

	dfp->dfp_flags &= ~XFS_DEFER_PAUSED;

	trace_xfs_defer_item_unpause(tp->t_mountp, dfp);
}