summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_trans.c
blob: c94e71f741b67032cd6d33f9c06786f36ebf1490 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
 * Copyright (C) 2010 Red Hat, 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_log_priv.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_extent_busy.h"
#include "xfs_quota.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_trace.h"
#include "xfs_error.h"
#include "xfs_defer.h"

kmem_zone_t	*xfs_trans_zone;

#if defined(CONFIG_TRACEPOINTS)
static void
xfs_trans_trace_reservations(
	struct xfs_mount	*mp)
{
	struct xfs_trans_res	resv;
	struct xfs_trans_res	*res;
	struct xfs_trans_res	*end_res;
	int			i;

	res = (struct xfs_trans_res *)M_RES(mp);
	end_res = (struct xfs_trans_res *)(M_RES(mp) + 1);
	for (i = 0; res < end_res; i++, res++)
		trace_xfs_trans_resv_calc(mp, i, res);
	xfs_log_get_max_trans_res(mp, &resv);
	trace_xfs_trans_resv_calc(mp, -1, &resv);
}
#else
# define xfs_trans_trace_reservations(mp)
#endif

/*
 * Initialize the precomputed transaction reservation values
 * in the mount structure.
 */
void
xfs_trans_init(
	struct xfs_mount	*mp)
{
	xfs_trans_resv_calc(mp, M_RES(mp));
	xfs_trans_trace_reservations(mp);
}

/*
 * Free the transaction structure.  If there is more clean up
 * to do when the structure is freed, add it here.
 */
STATIC void
xfs_trans_free(
	struct xfs_trans	*tp)
{
	xfs_extent_busy_sort(&tp->t_busy);
	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);

	trace_xfs_trans_free(tp, _RET_IP_);
	if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
		sb_end_intwrite(tp->t_mountp->m_super);
	xfs_trans_free_dqinfo(tp);
	kmem_cache_free(xfs_trans_zone, tp);
}

/*
 * This is called to create a new transaction which will share the
 * permanent log reservation of the given transaction.  The remaining
 * unused block and rt extent reservations are also inherited.  This
 * implies that the original transaction is no longer allowed to allocate
 * blocks.  Locks and log items, however, are no inherited.  They must
 * be added to the new transaction explicitly.
 */
STATIC struct xfs_trans *
xfs_trans_dup(
	struct xfs_trans	*tp)
{
	struct xfs_trans	*ntp;

	trace_xfs_trans_dup(tp, _RET_IP_);

	ntp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);

	/*
	 * Initialize the new transaction structure.
	 */
	ntp->t_magic = XFS_TRANS_HEADER_MAGIC;
	ntp->t_mountp = tp->t_mountp;
	INIT_LIST_HEAD(&ntp->t_items);
	INIT_LIST_HEAD(&ntp->t_busy);
	INIT_LIST_HEAD(&ntp->t_dfops);
	ntp->t_firstblock = NULLFSBLOCK;

	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
	ASSERT(tp->t_ticket != NULL);

	ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
		       (tp->t_flags & XFS_TRANS_RESERVE) |
		       (tp->t_flags & XFS_TRANS_NO_WRITECOUNT) |
		       (tp->t_flags & XFS_TRANS_RES_FDBLKS);
	/* We gave our writer reference to the new transaction */
	tp->t_flags |= XFS_TRANS_NO_WRITECOUNT;
	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);

	ASSERT(tp->t_blk_res >= tp->t_blk_res_used);
	ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
	tp->t_blk_res = tp->t_blk_res_used;

	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
	tp->t_rtx_res = tp->t_rtx_res_used;
	ntp->t_pflags = tp->t_pflags;

	/* move deferred ops over to the new tp */
	xfs_defer_move(ntp, tp);

	xfs_trans_dup_dqinfo(tp, ntp);
	return ntp;
}

/*
 * This is called to reserve free disk blocks and log space for the
 * given transaction.  This must be done before allocating any resources
 * within the transaction.
 *
 * This will return ENOSPC if there are not enough blocks available.
 * It will sleep waiting for available log space.
 * The only valid value for the flags parameter is XFS_RES_LOG_PERM, which
 * is used by long running transactions.  If any one of the reservations
 * fails then they will all be backed out.
 *
 * This does not do quota reservations. That typically is done by the
 * caller afterwards.
 */
static int
xfs_trans_reserve(
	struct xfs_trans	*tp,
	struct xfs_trans_res	*resp,
	uint			blocks,
	uint			rtextents)
{
	struct xfs_mount	*mp = tp->t_mountp;
	int			error = 0;
	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;

	/* Mark this thread as being in a transaction */
	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);

	/*
	 * Attempt to reserve the needed disk blocks by decrementing
	 * the number needed from the number available.  This will
	 * fail if the count would go below zero.
	 */
	if (blocks > 0) {
		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
		if (error != 0) {
			current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
			return -ENOSPC;
		}
		tp->t_blk_res += blocks;
	}

	/*
	 * Reserve the log space needed for this transaction.
	 */
	if (resp->tr_logres > 0) {
		bool	permanent = false;

		ASSERT(tp->t_log_res == 0 ||
		       tp->t_log_res == resp->tr_logres);
		ASSERT(tp->t_log_count == 0 ||
		       tp->t_log_count == resp->tr_logcount);

		if (resp->tr_logflags & XFS_TRANS_PERM_LOG_RES) {
			tp->t_flags |= XFS_TRANS_PERM_LOG_RES;
			permanent = true;
		} else {
			ASSERT(tp->t_ticket == NULL);
			ASSERT(!(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
		}

		if (tp->t_ticket != NULL) {
			ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES);
			error = xfs_log_regrant(mp, tp->t_ticket);
		} else {
			error = xfs_log_reserve(mp,
						resp->tr_logres,
						resp->tr_logcount,
						&tp->t_ticket, XFS_TRANSACTION,
						permanent);
		}

		if (error)
			goto undo_blocks;

		tp->t_log_res = resp->tr_logres;
		tp->t_log_count = resp->tr_logcount;
	}

	/*
	 * Attempt to reserve the needed realtime extents by decrementing
	 * the number needed from the number available.  This will
	 * fail if the count would go below zero.
	 */
	if (rtextents > 0) {
		error = xfs_mod_frextents(mp, -((int64_t)rtextents));
		if (error) {
			error = -ENOSPC;
			goto undo_log;
		}
		tp->t_rtx_res += rtextents;
	}

	return 0;

	/*
	 * Error cases jump to one of these labels to undo any
	 * reservations which have already been performed.
	 */
undo_log:
	if (resp->tr_logres > 0) {
		xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
		tp->t_ticket = NULL;
		tp->t_log_res = 0;
		tp->t_flags &= ~XFS_TRANS_PERM_LOG_RES;
	}

undo_blocks:
	if (blocks > 0) {
		xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
		tp->t_blk_res = 0;
	}

	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);

	return error;
}

int
xfs_trans_alloc(
	struct xfs_mount	*mp,
	struct xfs_trans_res	*resp,
	uint			blocks,
	uint			rtextents,
	uint			flags,
	struct xfs_trans	**tpp)
{
	struct xfs_trans	*tp;
	int			error;

	/*
	 * Allocate the handle before we do our freeze accounting and setting up
	 * GFP_NOFS allocation context so that we avoid lockdep false positives
	 * by doing GFP_KERNEL allocations inside sb_start_intwrite().
	 */
	tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
		sb_start_intwrite(mp->m_super);

	/*
	 * Zero-reservation ("empty") transactions can't modify anything, so
	 * they're allowed to run while we're frozen.
	 */
	WARN_ON(resp->tr_logres > 0 &&
		mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
	ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) ||
	       xfs_sb_version_haslazysbcount(&mp->m_sb));

	tp->t_magic = XFS_TRANS_HEADER_MAGIC;
	tp->t_flags = flags;
	tp->t_mountp = mp;
	INIT_LIST_HEAD(&tp->t_items);
	INIT_LIST_HEAD(&tp->t_busy);
	INIT_LIST_HEAD(&tp->t_dfops);
	tp->t_firstblock = NULLFSBLOCK;

	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
	if (error) {
		xfs_trans_cancel(tp);
		return error;
	}

	trace_xfs_trans_alloc(tp, _RET_IP_);

	*tpp = tp;
	return 0;
}

/*
 * Create an empty transaction with no reservation.  This is a defensive
 * mechanism for routines that query metadata without actually modifying them --
 * if the metadata being queried is somehow cross-linked (think a btree block
 * pointer that points higher in the tree), we risk deadlock.  However, blocks
 * grabbed as part of a transaction can be re-grabbed.  The verifiers will
 * notice the corrupt block and the operation will fail back to userspace
 * without deadlocking.
 *
 * Note the zero-length reservation; this transaction MUST be cancelled without
 * any dirty data.
 *
 * Callers should obtain freeze protection to avoid a conflict with fs freezing
 * where we can be grabbing buffers at the same time that freeze is trying to
 * drain the buffer LRU list.
 */
int
xfs_trans_alloc_empty(
	struct xfs_mount		*mp,
	struct xfs_trans		**tpp)
{
	struct xfs_trans_res		resv = {0};

	return xfs_trans_alloc(mp, &resv, 0, 0, XFS_TRANS_NO_WRITECOUNT, tpp);
}

/*
 * Record the indicated change to the given field for application
 * to the file system's superblock when the transaction commits.
 * For now, just store the change in the transaction structure.
 *
 * Mark the transaction structure to indicate that the superblock
 * needs to be updated before committing.
 *
 * Because we may not be keeping track of allocated/free inodes and
 * used filesystem blocks in the superblock, we do not mark the
 * superblock dirty in this transaction if we modify these fields.
 * We still need to update the transaction deltas so that they get
 * applied to the incore superblock, but we don't want them to
 * cause the superblock to get locked and logged if these are the
 * only fields in the superblock that the transaction modifies.
 */
void
xfs_trans_mod_sb(
	xfs_trans_t	*tp,
	uint		field,
	int64_t		delta)
{
	uint32_t	flags = (XFS_TRANS_DIRTY|XFS_TRANS_SB_DIRTY);
	xfs_mount_t	*mp = tp->t_mountp;

	switch (field) {
	case XFS_TRANS_SB_ICOUNT:
		tp->t_icount_delta += delta;
		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
			flags &= ~XFS_TRANS_SB_DIRTY;
		break;
	case XFS_TRANS_SB_IFREE:
		tp->t_ifree_delta += delta;
		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
			flags &= ~XFS_TRANS_SB_DIRTY;
		break;
	case XFS_TRANS_SB_FDBLOCKS:
		/*
		 * Track the number of blocks allocated in the transaction.
		 * Make sure it does not exceed the number reserved. If so,
		 * shutdown as this can lead to accounting inconsistency.
		 */
		if (delta < 0) {
			tp->t_blk_res_used += (uint)-delta;
			if (tp->t_blk_res_used > tp->t_blk_res)
				xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
		} else if (delta > 0 && (tp->t_flags & XFS_TRANS_RES_FDBLKS)) {
			int64_t	blkres_delta;

			/*
			 * Return freed blocks directly to the reservation
			 * instead of the global pool, being careful not to
			 * overflow the trans counter. This is used to preserve
			 * reservation across chains of transaction rolls that
			 * repeatedly free and allocate blocks.
			 */
			blkres_delta = min_t(int64_t, delta,
					     UINT_MAX - tp->t_blk_res);
			tp->t_blk_res += blkres_delta;
			delta -= blkres_delta;
		}
		tp->t_fdblocks_delta += delta;
		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
			flags &= ~XFS_TRANS_SB_DIRTY;
		break;
	case XFS_TRANS_SB_RES_FDBLOCKS:
		/*
		 * The allocation has already been applied to the
		 * in-core superblock's counter.  This should only
		 * be applied to the on-disk superblock.
		 */
		tp->t_res_fdblocks_delta += delta;
		if (xfs_sb_version_haslazysbcount(&mp->m_sb))
			flags &= ~XFS_TRANS_SB_DIRTY;
		break;
	case XFS_TRANS_SB_FREXTENTS:
		/*
		 * Track the number of blocks allocated in the
		 * transaction.  Make sure it does not exceed the
		 * number reserved.
		 */
		if (delta < 0) {
			tp->t_rtx_res_used += (uint)-delta;
			ASSERT(tp->t_rtx_res_used <= tp->t_rtx_res);
		}
		tp->t_frextents_delta += delta;
		break;
	case XFS_TRANS_SB_RES_FREXTENTS:
		/*
		 * The allocation has already been applied to the
		 * in-core superblock's counter.  This should only
		 * be applied to the on-disk superblock.
		 */
		ASSERT(delta < 0);
		tp->t_res_frextents_delta += delta;
		break;
	case XFS_TRANS_SB_DBLOCKS:
		ASSERT(delta > 0);
		tp->t_dblocks_delta += delta;
		break;
	case XFS_TRANS_SB_AGCOUNT:
		ASSERT(delta > 0);
		tp->t_agcount_delta += delta;
		break;
	case XFS_TRANS_SB_IMAXPCT:
		tp->t_imaxpct_delta += delta;
		break;
	case XFS_TRANS_SB_REXTSIZE:
		tp->t_rextsize_delta += delta;
		break;
	case XFS_TRANS_SB_RBMBLOCKS:
		tp->t_rbmblocks_delta += delta;
		break;
	case XFS_TRANS_SB_RBLOCKS:
		tp->t_rblocks_delta += delta;
		break;
	case XFS_TRANS_SB_REXTENTS:
		tp->t_rextents_delta += delta;
		break;
	case XFS_TRANS_SB_REXTSLOG:
		tp->t_rextslog_delta += delta;
		break;
	default:
		ASSERT(0);
		return;
	}

	tp->t_flags |= flags;
}

/*
 * xfs_trans_apply_sb_deltas() is called from the commit code
 * to bring the superblock buffer into the current transaction
 * and modify it as requested by earlier calls to xfs_trans_mod_sb().
 *
 * For now we just look at each field allowed to change and change
 * it if necessary.
 */
STATIC void
xfs_trans_apply_sb_deltas(
	xfs_trans_t	*tp)
{
	xfs_dsb_t	*sbp;
	xfs_buf_t	*bp;
	int		whole = 0;

	bp = xfs_trans_getsb(tp);
	sbp = bp->b_addr;

	/*
	 * Check that superblock mods match the mods made to AGF counters.
	 */
	ASSERT((tp->t_fdblocks_delta + tp->t_res_fdblocks_delta) ==
	       (tp->t_ag_freeblks_delta + tp->t_ag_flist_delta +
		tp->t_ag_btree_delta));

	/*
	 * Only update the superblock counters if we are logging them
	 */
	if (!xfs_sb_version_haslazysbcount(&(tp->t_mountp->m_sb))) {
		if (tp->t_icount_delta)
			be64_add_cpu(&sbp->sb_icount, tp->t_icount_delta);
		if (tp->t_ifree_delta)
			be64_add_cpu(&sbp->sb_ifree, tp->t_ifree_delta);
		if (tp->t_fdblocks_delta)
			be64_add_cpu(&sbp->sb_fdblocks, tp->t_fdblocks_delta);
		if (tp->t_res_fdblocks_delta)
			be64_add_cpu(&sbp->sb_fdblocks, tp->t_res_fdblocks_delta);
	}

	if (tp->t_frextents_delta)
		be64_add_cpu(&sbp->sb_frextents, tp->t_frextents_delta);
	if (tp->t_res_frextents_delta)
		be64_add_cpu(&sbp->sb_frextents, tp->t_res_frextents_delta);

	if (tp->t_dblocks_delta) {
		be64_add_cpu(&sbp->sb_dblocks, tp->t_dblocks_delta);
		whole = 1;
	}
	if (tp->t_agcount_delta) {
		be32_add_cpu(&sbp->sb_agcount, tp->t_agcount_delta);
		whole = 1;
	}
	if (tp->t_imaxpct_delta) {
		sbp->sb_imax_pct += tp->t_imaxpct_delta;
		whole = 1;
	}
	if (tp->t_rextsize_delta) {
		be32_add_cpu(&sbp->sb_rextsize, tp->t_rextsize_delta);
		whole = 1;
	}
	if (tp->t_rbmblocks_delta) {
		be32_add_cpu(&sbp->sb_rbmblocks, tp->t_rbmblocks_delta);
		whole = 1;
	}
	if (tp->t_rblocks_delta) {
		be64_add_cpu(&sbp->sb_rblocks, tp->t_rblocks_delta);
		whole = 1;
	}
	if (tp->t_rextents_delta) {
		be64_add_cpu(&sbp->sb_rextents, tp->t_rextents_delta);
		whole = 1;
	}
	if (tp->t_rextslog_delta) {
		sbp->sb_rextslog += tp->t_rextslog_delta;
		whole = 1;
	}

	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
	if (whole)
		/*
		 * Log the whole thing, the fields are noncontiguous.
		 */
		xfs_trans_log_buf(tp, bp, 0, sizeof(xfs_dsb_t) - 1);
	else
		/*
		 * Since all the modifiable fields are contiguous, we
		 * can get away with this.
		 */
		xfs_trans_log_buf(tp, bp, offsetof(xfs_dsb_t, sb_icount),
				  offsetof(xfs_dsb_t, sb_frextents) +
				  sizeof(sbp->sb_frextents) - 1);
}

/*
 * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations and
 * apply superblock counter changes to the in-core superblock.  The
 * t_res_fdblocks_delta and t_res_frextents_delta fields are explicitly NOT
 * applied to the in-core superblock.  The idea is that that has already been
 * done.
 *
 * If we are not logging superblock counters, then the inode allocated/free and
 * used block counts are not updated in the on disk superblock. In this case,
 * XFS_TRANS_SB_DIRTY will not be set when the transaction is updated but we
 * still need to update the incore superblock with the changes.
 *
 * Deltas for the inode count are +/-64, hence we use a large batch size of 128
 * so we don't need to take the counter lock on every update.
 */
#define XFS_ICOUNT_BATCH	128

void
xfs_trans_unreserve_and_mod_sb(
	struct xfs_trans	*tp)
{
	struct xfs_mount	*mp = tp->t_mountp;
	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
	int64_t			blkdelta = 0;
	int64_t			rtxdelta = 0;
	int64_t			idelta = 0;
	int64_t			ifreedelta = 0;
	int			error;

	/* calculate deltas */
	if (tp->t_blk_res > 0)
		blkdelta = tp->t_blk_res;
	if ((tp->t_fdblocks_delta != 0) &&
	    (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
	     (tp->t_flags & XFS_TRANS_SB_DIRTY)))
	        blkdelta += tp->t_fdblocks_delta;

	if (tp->t_rtx_res > 0)
		rtxdelta = tp->t_rtx_res;
	if ((tp->t_frextents_delta != 0) &&
	    (tp->t_flags & XFS_TRANS_SB_DIRTY))
		rtxdelta += tp->t_frextents_delta;

	if (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
	     (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
		idelta = tp->t_icount_delta;
		ifreedelta = tp->t_ifree_delta;
	}

	/* apply the per-cpu counters */
	if (blkdelta) {
		error = xfs_mod_fdblocks(mp, blkdelta, rsvd);
		ASSERT(!error);
	}

	if (idelta) {
		percpu_counter_add_batch(&mp->m_icount, idelta,
					 XFS_ICOUNT_BATCH);
		if (idelta < 0)
			ASSERT(__percpu_counter_compare(&mp->m_icount, 0,
							XFS_ICOUNT_BATCH) >= 0);
	}

	if (ifreedelta) {
		percpu_counter_add(&mp->m_ifree, ifreedelta);
		if (ifreedelta < 0)
			ASSERT(percpu_counter_compare(&mp->m_ifree, 0) >= 0);
	}

	if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY))
		return;

	/* apply remaining deltas */
	spin_lock(&mp->m_sb_lock);
	mp->m_sb.sb_frextents += rtxdelta;
	mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
	mp->m_sb.sb_agcount += tp->t_agcount_delta;
	mp->m_sb.sb_imax_pct += tp->t_imaxpct_delta;
	mp->m_sb.sb_rextsize += tp->t_rextsize_delta;
	mp->m_sb.sb_rbmblocks += tp->t_rbmblocks_delta;
	mp->m_sb.sb_rblocks += tp->t_rblocks_delta;
	mp->m_sb.sb_rextents += tp->t_rextents_delta;
	mp->m_sb.sb_rextslog += tp->t_rextslog_delta;
	spin_unlock(&mp->m_sb_lock);

	/*
	 * Debug checks outside of the spinlock so they don't lock up the
	 * machine if they fail.
	 */
	ASSERT(mp->m_sb.sb_imax_pct >= 0);
	ASSERT(mp->m_sb.sb_rextslog >= 0);
	return;
}

/* Add the given log item to the transaction's list of log items. */
void
xfs_trans_add_item(
	struct xfs_trans	*tp,
	struct xfs_log_item	*lip)
{
	ASSERT(lip->li_mountp == tp->t_mountp);
	ASSERT(lip->li_ailp == tp->t_mountp->m_ail);
	ASSERT(list_empty(&lip->li_trans));
	ASSERT(!test_bit(XFS_LI_DIRTY, &lip->li_flags));

	list_add_tail(&lip->li_trans, &tp->t_items);
	trace_xfs_trans_add_item(tp, _RET_IP_);
}

/*
 * Unlink the log item from the transaction. the log item is no longer
 * considered dirty in this transaction, as the linked transaction has
 * finished, either by abort or commit completion.
 */
void
xfs_trans_del_item(
	struct xfs_log_item	*lip)
{
	clear_bit(XFS_LI_DIRTY, &lip->li_flags);
	list_del_init(&lip->li_trans);
}

/* Detach and unlock all of the items in a transaction */
static void
xfs_trans_free_items(
	struct xfs_trans	*tp,
	bool			abort)
{
	struct xfs_log_item	*lip, *next;

	trace_xfs_trans_free_items(tp, _RET_IP_);

	list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
		xfs_trans_del_item(lip);
		if (abort)
			set_bit(XFS_LI_ABORTED, &lip->li_flags);
		if (lip->li_ops->iop_release)
			lip->li_ops->iop_release(lip);
	}
}

static inline void
xfs_log_item_batch_insert(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur,
	struct xfs_log_item	**log_items,
	int			nr_items,
	xfs_lsn_t		commit_lsn)
{
	int	i;

	spin_lock(&ailp->ail_lock);
	/* xfs_trans_ail_update_bulk drops ailp->ail_lock */
	xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn);

	for (i = 0; i < nr_items; i++) {
		struct xfs_log_item *lip = log_items[i];

		if (lip->li_ops->iop_unpin)
			lip->li_ops->iop_unpin(lip, 0);
	}
}

/*
 * Bulk operation version of xfs_trans_committed that takes a log vector of
 * items to insert into the AIL. This uses bulk AIL insertion techniques to
 * minimise lock traffic.
 *
 * If we are called with the aborted flag set, it is because a log write during
 * a CIL checkpoint commit has failed. In this case, all the items in the
 * checkpoint have already gone through iop_committed and iop_committing, which
 * means that checkpoint commit abort handling is treated exactly the same
 * as an iclog write error even though we haven't started any IO yet. Hence in
 * this case all we need to do is iop_committed processing, followed by an
 * iop_unpin(aborted) call.
 *
 * The AIL cursor is used to optimise the insert process. If commit_lsn is not
 * at the end of the AIL, the insert cursor avoids the need to walk
 * the AIL to find the insertion point on every xfs_log_item_batch_insert()
 * call. This saves a lot of needless list walking and is a net win, even
 * though it slightly increases that amount of AIL lock traffic to set it up
 * and tear it down.
 */
void
xfs_trans_committed_bulk(
	struct xfs_ail		*ailp,
	struct xfs_log_vec	*log_vector,
	xfs_lsn_t		commit_lsn,
	bool			aborted)
{
#define LOG_ITEM_BATCH_SIZE	32
	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
	struct xfs_log_vec	*lv;
	struct xfs_ail_cursor	cur;
	int			i = 0;

	spin_lock(&ailp->ail_lock);
	xfs_trans_ail_cursor_last(ailp, &cur, commit_lsn);
	spin_unlock(&ailp->ail_lock);

	/* unpin all the log items */
	for (lv = log_vector; lv; lv = lv->lv_next ) {
		struct xfs_log_item	*lip = lv->lv_item;
		xfs_lsn_t		item_lsn;

		if (aborted)
			set_bit(XFS_LI_ABORTED, &lip->li_flags);

		if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
			lip->li_ops->iop_release(lip);
			continue;
		}

		if (lip->li_ops->iop_committed)
			item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
		else
			item_lsn = commit_lsn;

		/* item_lsn of -1 means the item needs no further processing */
		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
			continue;

		/*
		 * if we are aborting the operation, no point in inserting the
		 * object into the AIL as we are in a shutdown situation.
		 */
		if (aborted) {
			ASSERT(XFS_FORCED_SHUTDOWN(ailp->ail_mount));
			if (lip->li_ops->iop_unpin)
				lip->li_ops->iop_unpin(lip, 1);
			continue;
		}

		if (item_lsn != commit_lsn) {

			/*
			 * Not a bulk update option due to unusual item_lsn.
			 * Push into AIL immediately, rechecking the lsn once
			 * we have the ail lock. Then unpin the item. This does
			 * not affect the AIL cursor the bulk insert path is
			 * using.
			 */
			spin_lock(&ailp->ail_lock);
			if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0)
				xfs_trans_ail_update(ailp, lip, item_lsn);
			else
				spin_unlock(&ailp->ail_lock);
			if (lip->li_ops->iop_unpin)
				lip->li_ops->iop_unpin(lip, 0);
			continue;
		}

		/* Item is a candidate for bulk AIL insert.  */
		log_items[i++] = lv->lv_item;
		if (i >= LOG_ITEM_BATCH_SIZE) {
			xfs_log_item_batch_insert(ailp, &cur, log_items,
					LOG_ITEM_BATCH_SIZE, commit_lsn);
			i = 0;
		}
	}

	/* make sure we insert the remainder! */
	if (i)
		xfs_log_item_batch_insert(ailp, &cur, log_items, i, commit_lsn);

	spin_lock(&ailp->ail_lock);
	xfs_trans_ail_cursor_done(&cur);
	spin_unlock(&ailp->ail_lock);
}

/*
 * Commit the given transaction to the log.
 *
 * XFS disk error handling mechanism is not based on a typical
 * transaction abort mechanism. Logically after the filesystem
 * gets marked 'SHUTDOWN', we can't let any new transactions
 * be durable - ie. committed to disk - because some metadata might
 * be inconsistent. In such cases, this returns an error, and the
 * caller may assume that all locked objects joined to the transaction
 * have already been unlocked as if the commit had succeeded.
 * Do not reference the transaction structure after this call.
 */
static int
__xfs_trans_commit(
	struct xfs_trans	*tp,
	bool			regrant)
{
	struct xfs_mount	*mp = tp->t_mountp;
	xfs_lsn_t		commit_lsn = -1;
	int			error = 0;
	int			sync = tp->t_flags & XFS_TRANS_SYNC;

	trace_xfs_trans_commit(tp, _RET_IP_);

	/*
	 * Finish deferred items on final commit. Only permanent transactions
	 * should ever have deferred ops.
	 */
	WARN_ON_ONCE(!list_empty(&tp->t_dfops) &&
		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
		error = xfs_defer_finish_noroll(&tp);
		if (error)
			goto out_unreserve;
	}

	/*
	 * If there is nothing to be logged by the transaction,
	 * then unlock all of the items associated with the
	 * transaction and free the transaction structure.
	 * Also make sure to return any reserved blocks to
	 * the free pool.
	 */
	if (!(tp->t_flags & XFS_TRANS_DIRTY))
		goto out_unreserve;

	if (XFS_FORCED_SHUTDOWN(mp)) {
		error = -EIO;
		goto out_unreserve;
	}

	ASSERT(tp->t_ticket != NULL);

	/*
	 * If we need to update the superblock, then do it now.
	 */
	if (tp->t_flags & XFS_TRANS_SB_DIRTY)
		xfs_trans_apply_sb_deltas(tp);
	xfs_trans_apply_dquot_deltas(tp);

	xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);

	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
	xfs_trans_free(tp);

	/*
	 * If the transaction needs to be synchronous, then force the
	 * log out now and wait for it.
	 */
	if (sync) {
		error = xfs_log_force_lsn(mp, commit_lsn, XFS_LOG_SYNC, NULL);
		XFS_STATS_INC(mp, xs_trans_sync);
	} else {
		XFS_STATS_INC(mp, xs_trans_async);
	}

	return error;

out_unreserve:
	xfs_trans_unreserve_and_mod_sb(tp);

	/*
	 * It is indeed possible for the transaction to be not dirty but
	 * the dqinfo portion to be.  All that means is that we have some
	 * (non-persistent) quota reservations that need to be unreserved.
	 */
	xfs_trans_unreserve_and_mod_dquots(tp);
	if (tp->t_ticket) {
		if (regrant && !XLOG_FORCED_SHUTDOWN(mp->m_log))
			xfs_log_ticket_regrant(mp->m_log, tp->t_ticket);
		else
			xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
		tp->t_ticket = NULL;
	}
	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
	xfs_trans_free_items(tp, !!error);
	xfs_trans_free(tp);

	XFS_STATS_INC(mp, xs_trans_empty);
	return error;
}

int
xfs_trans_commit(
	struct xfs_trans	*tp)
{
	return __xfs_trans_commit(tp, false);
}

/*
 * Unlock all of the transaction's items and free the transaction.
 * The transaction must not have modified any of its items, because
 * there is no way to restore them to their previous state.
 *
 * If the transaction has made a log reservation, make sure to release
 * it as well.
 */
void
xfs_trans_cancel(
	struct xfs_trans	*tp)
{
	struct xfs_mount	*mp = tp->t_mountp;
	bool			dirty = (tp->t_flags & XFS_TRANS_DIRTY);

	trace_xfs_trans_cancel(tp, _RET_IP_);

	if (tp->t_flags & XFS_TRANS_PERM_LOG_RES)
		xfs_defer_cancel(tp);

	/*
	 * See if the caller is relying on us to shut down the
	 * filesystem.  This happens in paths where we detect
	 * corruption and decide to give up.
	 */
	if (dirty && !XFS_FORCED_SHUTDOWN(mp)) {
		XFS_ERROR_REPORT("xfs_trans_cancel", XFS_ERRLEVEL_LOW, mp);
		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
	}
#ifdef DEBUG
	if (!dirty && !XFS_FORCED_SHUTDOWN(mp)) {
		struct xfs_log_item *lip;

		list_for_each_entry(lip, &tp->t_items, li_trans)
			ASSERT(!xlog_item_is_intent_done(lip));
	}
#endif
	xfs_trans_unreserve_and_mod_sb(tp);
	xfs_trans_unreserve_and_mod_dquots(tp);

	if (tp->t_ticket) {
		xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
		tp->t_ticket = NULL;
	}

	/* mark this thread as no longer being in a transaction */
	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);

	xfs_trans_free_items(tp, dirty);
	xfs_trans_free(tp);
}

/*
 * Roll from one trans in the sequence of PERMANENT transactions to
 * the next: permanent transactions are only flushed out when
 * committed with xfs_trans_commit(), but we still want as soon
 * as possible to let chunks of it go to the log. So we commit the
 * chunk we've been working on and get a new transaction to continue.
 */
int
xfs_trans_roll(
	struct xfs_trans	**tpp)
{
	struct xfs_trans	*trans = *tpp;
	struct xfs_trans_res	tres;
	int			error;

	trace_xfs_trans_roll(trans, _RET_IP_);

	/*
	 * Copy the critical parameters from one trans to the next.
	 */
	tres.tr_logres = trans->t_log_res;
	tres.tr_logcount = trans->t_log_count;

	*tpp = xfs_trans_dup(trans);

	/*
	 * Commit the current transaction.
	 * If this commit failed, then it'd just unlock those items that
	 * are not marked ihold. That also means that a filesystem shutdown
	 * is in progress. The caller takes the responsibility to cancel
	 * the duplicate transaction that gets returned.
	 */
	error = __xfs_trans_commit(trans, true);
	if (error)
		return error;

	/*
	 * Reserve space in the log for the next transaction.
	 * This also pushes items in the "AIL", the list of logged items,
	 * out to disk if they are taking up space at the tail of the log
	 * that we want to use.  This requires that either nothing be locked
	 * across this call, or that anything that is locked be logged in
	 * the prior and the next transactions.
	 */
	tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
	return xfs_trans_reserve(*tpp, &tres, 0, 0);
}