summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_buf_item.c
blob: 925ead22803a1dba76b18285524ef4a9925a1a46 (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_trans_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_log.h"


kmem_zone_t	*xfs_buf_item_zone;

static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_buf_log_item, bli_item);
}

STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);

static inline int
xfs_buf_log_format_size(
	struct xfs_buf_log_format *blfp)
{
	return offsetof(struct xfs_buf_log_format, blf_data_map) +
			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
}

/*
 * This returns the number of log iovecs needed to log the
 * given buf log item.
 *
 * It calculates this as 1 iovec for the buf log format structure
 * and 1 for each stretch of non-contiguous chunks to be logged.
 * Contiguous chunks are logged in a single iovec.
 *
 * If the XFS_BLI_STALE flag has been set, then log nothing.
 */
STATIC void
xfs_buf_item_size_segment(
	struct xfs_buf_log_item	*bip,
	struct xfs_buf_log_format *blfp,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_buf		*bp = bip->bli_buf;
	int			next_bit;
	int			last_bit;

	last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
	if (last_bit == -1)
		return;

	/*
	 * initial count for a dirty buffer is 2 vectors - the format structure
	 * and the first dirty region.
	 */
	*nvecs += 2;
	*nbytes += xfs_buf_log_format_size(blfp) + XFS_BLF_CHUNK;

	while (last_bit != -1) {
		/*
		 * This takes the bit number to start looking from and
		 * returns the next set bit from there.  It returns -1
		 * if there are no more bits set or the start bit is
		 * beyond the end of the bitmap.
		 */
		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
					last_bit + 1);
		/*
		 * If we run out of bits, leave the loop,
		 * else if we find a new set of bits bump the number of vecs,
		 * else keep scanning the current set of bits.
		 */
		if (next_bit == -1) {
			break;
		} else if (next_bit != last_bit + 1) {
			last_bit = next_bit;
			(*nvecs)++;
		} else if (xfs_buf_offset(bp, next_bit * XFS_BLF_CHUNK) !=
			   (xfs_buf_offset(bp, last_bit * XFS_BLF_CHUNK) +
			    XFS_BLF_CHUNK)) {
			last_bit = next_bit;
			(*nvecs)++;
		} else {
			last_bit++;
		}
		*nbytes += XFS_BLF_CHUNK;
	}
}

/*
 * This returns the number of log iovecs needed to log the given buf log item.
 *
 * It calculates this as 1 iovec for the buf log format structure and 1 for each
 * stretch of non-contiguous chunks to be logged.  Contiguous chunks are logged
 * in a single iovec.
 *
 * Discontiguous buffers need a format structure per region that that is being
 * logged. This makes the changes in the buffer appear to log recovery as though
 * they came from separate buffers, just like would occur if multiple buffers
 * were used instead of a single discontiguous buffer. This enables
 * discontiguous buffers to be in-memory constructs, completely transparent to
 * what ends up on disk.
 *
 * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
 * format structures.
 */
STATIC void
xfs_buf_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
	int			i;

	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	if (bip->bli_flags & XFS_BLI_STALE) {
		/*
		 * The buffer is stale, so all we need to log
		 * is the buf log format structure with the
		 * cancel flag in it.
		 */
		trace_xfs_buf_item_size_stale(bip);
		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
		*nvecs += bip->bli_format_count;
		for (i = 0; i < bip->bli_format_count; i++) {
			*nbytes += xfs_buf_log_format_size(&bip->bli_formats[i]);
		}
		return;
	}

	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);

	if (bip->bli_flags & XFS_BLI_ORDERED) {
		/*
		 * The buffer has been logged just to order it.
		 * It is not being included in the transaction
		 * commit, so no vectors are used at all.
		 */
		trace_xfs_buf_item_size_ordered(bip);
		*nvecs = XFS_LOG_VEC_ORDERED;
		return;
	}

	/*
	 * the vector count is based on the number of buffer vectors we have
	 * dirty bits in. This will only be greater than one when we have a
	 * compound buffer with more than one segment dirty. Hence for compound
	 * buffers we need to track which segment the dirty bits correspond to,
	 * and when we move from one segment to the next increment the vector
	 * count for the extra buf log format structure that will need to be
	 * written.
	 */
	for (i = 0; i < bip->bli_format_count; i++) {
		xfs_buf_item_size_segment(bip, &bip->bli_formats[i],
					  nvecs, nbytes);
	}
	trace_xfs_buf_item_size(bip);
}

static inline void
xfs_buf_item_copy_iovec(
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp,
	struct xfs_buf		*bp,
	uint			offset,
	int			first_bit,
	uint			nbits)
{
	offset += first_bit * XFS_BLF_CHUNK;
	xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_BCHUNK,
			xfs_buf_offset(bp, offset),
			nbits * XFS_BLF_CHUNK);
}

static inline bool
xfs_buf_item_straddle(
	struct xfs_buf		*bp,
	uint			offset,
	int			next_bit,
	int			last_bit)
{
	return xfs_buf_offset(bp, offset + (next_bit << XFS_BLF_SHIFT)) !=
		(xfs_buf_offset(bp, offset + (last_bit << XFS_BLF_SHIFT)) +
		 XFS_BLF_CHUNK);
}

static void
xfs_buf_item_format_segment(
	struct xfs_buf_log_item	*bip,
	struct xfs_log_vec	*lv,
	struct xfs_log_iovec	**vecp,
	uint			offset,
	struct xfs_buf_log_format *blfp)
{
	struct xfs_buf	*bp = bip->bli_buf;
	uint		base_size;
	int		first_bit;
	int		last_bit;
	int		next_bit;
	uint		nbits;

	/* copy the flags across from the base format item */
	blfp->blf_flags = bip->__bli_format.blf_flags;

	/*
	 * Base size is the actual size of the ondisk structure - it reflects
	 * the actual size of the dirty bitmap rather than the size of the in
	 * memory structure.
	 */
	base_size = xfs_buf_log_format_size(blfp);

	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
	if (!(bip->bli_flags & XFS_BLI_STALE) && first_bit == -1) {
		/*
		 * If the map is not be dirty in the transaction, mark
		 * the size as zero and do not advance the vector pointer.
		 */
		return;
	}

	blfp = xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_BFORMAT, blfp, base_size);
	blfp->blf_size = 1;

	if (bip->bli_flags & XFS_BLI_STALE) {
		/*
		 * The buffer is stale, so all we need to log
		 * is the buf log format structure with the
		 * cancel flag in it.
		 */
		trace_xfs_buf_item_format_stale(bip);
		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
		return;
	}


	/*
	 * Fill in an iovec for each set of contiguous chunks.
	 */
	last_bit = first_bit;
	nbits = 1;
	for (;;) {
		/*
		 * This takes the bit number to start looking from and
		 * returns the next set bit from there.  It returns -1
		 * if there are no more bits set or the start bit is
		 * beyond the end of the bitmap.
		 */
		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
					(uint)last_bit + 1);
		/*
		 * If we run out of bits fill in the last iovec and get out of
		 * the loop.  Else if we start a new set of bits then fill in
		 * the iovec for the series we were looking at and start
		 * counting the bits in the new one.  Else we're still in the
		 * same set of bits so just keep counting and scanning.
		 */
		if (next_bit == -1) {
			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
						first_bit, nbits);
			blfp->blf_size++;
			break;
		} else if (next_bit != last_bit + 1 ||
		           xfs_buf_item_straddle(bp, offset, next_bit, last_bit)) {
			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
						first_bit, nbits);
			blfp->blf_size++;
			first_bit = next_bit;
			last_bit = next_bit;
			nbits = 1;
		} else {
			last_bit++;
			nbits++;
		}
	}
}

/*
 * This is called to fill in the vector of log iovecs for the
 * given log buf item.  It fills the first entry with a buf log
 * format structure, and the rest point to contiguous chunks
 * within the buffer.
 */
STATIC void
xfs_buf_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_vec	*lv)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
	struct xfs_buf		*bp = bip->bli_buf;
	struct xfs_log_iovec	*vecp = NULL;
	uint			offset = 0;
	int			i;

	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
	       (bip->bli_flags & XFS_BLI_STALE));

	/*
	 * If it is an inode buffer, transfer the in-memory state to the
	 * format flags and clear the in-memory state.
	 *
	 * For buffer based inode allocation, we do not transfer
	 * this state if the inode buffer allocation has not yet been committed
	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
	 * correct replay of the inode allocation.
	 *
	 * For icreate item based inode allocation, the buffers aren't written
	 * to the journal during allocation, and hence we should always tag the
	 * buffer as an inode buffer so that the correct unlinked list replay
	 * occurs during recovery.
	 */
	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
		if (xfs_sb_version_hascrc(&lip->li_mountp->m_sb) ||
		    !((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
		      xfs_log_item_in_current_chkpt(lip)))
			bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
	}

	if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) ==
							XFS_BLI_ORDERED) {
		/*
		 * The buffer has been logged just to order it.  It is not being
		 * included in the transaction commit, so don't format it.
		 */
		trace_xfs_buf_item_format_ordered(bip);
		return;
	}

	for (i = 0; i < bip->bli_format_count; i++) {
		xfs_buf_item_format_segment(bip, lv, &vecp, offset,
					    &bip->bli_formats[i]);
		offset += bp->b_maps[i].bm_len;
	}

	/*
	 * Check to make sure everything is consistent.
	 */
	trace_xfs_buf_item_format(bip);
}

/*
 * This is called to pin the buffer associated with the buf log item in memory
 * so it cannot be written out.
 *
 * We also always take a reference to the buffer log item here so that the bli
 * is held while the item is pinned in memory. This means that we can
 * unconditionally drop the reference count a transaction holds when the
 * transaction is completed.
 */
STATIC void
xfs_buf_item_pin(
	struct xfs_log_item	*lip)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);

	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
	       (bip->bli_flags & XFS_BLI_ORDERED) ||
	       (bip->bli_flags & XFS_BLI_STALE));

	trace_xfs_buf_item_pin(bip);

	atomic_inc(&bip->bli_refcount);
	atomic_inc(&bip->bli_buf->b_pin_count);
}

/*
 * This is called to unpin the buffer associated with the buf log
 * item which was previously pinned with a call to xfs_buf_item_pin().
 *
 * Also drop the reference to the buf item for the current transaction.
 * If the XFS_BLI_STALE flag is set and we are the last reference,
 * then free up the buf log item and unlock the buffer.
 *
 * If the remove flag is set we are called from uncommit in the
 * forced-shutdown path.  If that is true and the reference count on
 * the log item is going to drop to zero we need to free the item's
 * descriptor in the transaction.
 */
STATIC void
xfs_buf_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
	xfs_buf_t	*bp = bip->bli_buf;
	struct xfs_ail	*ailp = lip->li_ailp;
	int		stale = bip->bli_flags & XFS_BLI_STALE;
	int		freed;

	ASSERT(bp->b_fspriv == bip);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	trace_xfs_buf_item_unpin(bip);

	freed = atomic_dec_and_test(&bip->bli_refcount);

	if (atomic_dec_and_test(&bp->b_pin_count))
		wake_up_all(&bp->b_waiters);

	if (freed && stale) {
		ASSERT(bip->bli_flags & XFS_BLI_STALE);
		ASSERT(xfs_buf_islocked(bp));
		ASSERT(XFS_BUF_ISSTALE(bp));
		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);

		trace_xfs_buf_item_unpin_stale(bip);

		if (remove) {
			/*
			 * If we are in a transaction context, we have to
			 * remove the log item from the transaction as we are
			 * about to release our reference to the buffer.  If we
			 * don't, the unlock that occurs later in
			 * xfs_trans_uncommit() will try to reference the
			 * buffer which we no longer have a hold on.
			 */
			if (lip->li_desc)
				xfs_trans_del_item(lip);

			/*
			 * Since the transaction no longer refers to the buffer,
			 * the buffer should no longer refer to the transaction.
			 */
			bp->b_transp = NULL;
		}

		/*
		 * If we get called here because of an IO error, we may
		 * or may not have the item on the AIL. xfs_trans_ail_delete()
		 * will take care of that situation.
		 * xfs_trans_ail_delete() drops the AIL lock.
		 */
		if (bip->bli_flags & XFS_BLI_STALE_INODE) {
			xfs_buf_do_callbacks(bp);
			bp->b_fspriv = NULL;
			bp->b_iodone = NULL;
		} else {
			spin_lock(&ailp->xa_lock);
			xfs_trans_ail_delete(ailp, lip, SHUTDOWN_LOG_IO_ERROR);
			xfs_buf_item_relse(bp);
			ASSERT(bp->b_fspriv == NULL);
		}
		xfs_buf_relse(bp);
	} else if (freed && remove) {
		/*
		 * There are currently two references to the buffer - the active
		 * LRU reference and the buf log item. What we are about to do
		 * here - simulate a failed IO completion - requires 3
		 * references.
		 *
		 * The LRU reference is removed by the xfs_buf_stale() call. The
		 * buf item reference is removed by the xfs_buf_iodone()
		 * callback that is run by xfs_buf_do_callbacks() during ioend
		 * processing (via the bp->b_iodone callback), and then finally
		 * the ioend processing will drop the IO reference if the buffer
		 * is marked XBF_ASYNC.
		 *
		 * Hence we need to take an additional reference here so that IO
		 * completion processing doesn't free the buffer prematurely.
		 */
		xfs_buf_lock(bp);
		xfs_buf_hold(bp);
		bp->b_flags |= XBF_ASYNC;
		xfs_buf_ioerror(bp, -EIO);
		XFS_BUF_UNDONE(bp);
		xfs_buf_stale(bp);
		xfs_buf_ioend(bp);
	}
}

/*
 * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
 * seconds so as to not spam logs too much on repeated detection of the same
 * buffer being bad..
 */

static DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);

STATIC uint
xfs_buf_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
	struct xfs_buf		*bp = bip->bli_buf;
	uint			rval = XFS_ITEM_SUCCESS;

	if (xfs_buf_ispinned(bp))
		return XFS_ITEM_PINNED;
	if (!xfs_buf_trylock(bp)) {
		/*
		 * If we have just raced with a buffer being pinned and it has
		 * been marked stale, we could end up stalling until someone else
		 * issues a log force to unpin the stale buffer. Check for the
		 * race condition here so xfsaild recognizes the buffer is pinned
		 * and queues a log force to move it along.
		 */
		if (xfs_buf_ispinned(bp))
			return XFS_ITEM_PINNED;
		return XFS_ITEM_LOCKED;
	}

	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));

	trace_xfs_buf_item_push(bip);

	/* has a previous flush failed due to IO errors? */
	if ((bp->b_flags & XBF_WRITE_FAIL) &&
	    ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
		xfs_warn(bp->b_target->bt_mount,
"Detected failing async write on buffer block 0x%llx. Retrying async write.",
			 (long long)bp->b_bn);
	}

	if (!xfs_buf_delwri_queue(bp, buffer_list))
		rval = XFS_ITEM_FLUSHING;
	xfs_buf_unlock(bp);
	return rval;
}

/*
 * Release the buffer associated with the buf log item.  If there is no dirty
 * logged data associated with the buffer recorded in the buf log item, then
 * free the buf log item and remove the reference to it in the buffer.
 *
 * This call ignores the recursion count.  It is only called when the buffer
 * should REALLY be unlocked, regardless of the recursion count.
 *
 * We unconditionally drop the transaction's reference to the log item. If the
 * item was logged, then another reference was taken when it was pinned, so we
 * can safely drop the transaction reference now.  This also allows us to avoid
 * potential races with the unpin code freeing the bli by not referencing the
 * bli after we've dropped the reference count.
 *
 * If the XFS_BLI_HOLD flag is set in the buf log item, then free the log item
 * if necessary but do not unlock the buffer.  This is for support of
 * xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't
 * free the item.
 */
STATIC void
xfs_buf_item_unlock(
	struct xfs_log_item	*lip)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
	struct xfs_buf		*bp = bip->bli_buf;
	bool			clean;
	bool			aborted;
	int			flags;

	/* Clear the buffer's association with this transaction. */
	bp->b_transp = NULL;

	/*
	 * If this is a transaction abort, don't return early.  Instead, allow
	 * the brelse to happen.  Normally it would be done for stale
	 * (cancelled) buffers at unpin time, but we'll never go through the
	 * pin/unpin cycle if we abort inside commit.
	 */
	aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false;
	/*
	 * Before possibly freeing the buf item, copy the per-transaction state
	 * so we can reference it safely later after clearing it from the
	 * buffer log item.
	 */
	flags = bip->bli_flags;
	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);

	/*
	 * If the buf item is marked stale, then don't do anything.  We'll
	 * unlock the buffer and free the buf item when the buffer is unpinned
	 * for the last time.
	 */
	if (flags & XFS_BLI_STALE) {
		trace_xfs_buf_item_unlock_stale(bip);
		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
		if (!aborted) {
			atomic_dec(&bip->bli_refcount);
			return;
		}
	}

	trace_xfs_buf_item_unlock(bip);

	/*
	 * If the buf item isn't tracking any data, free it, otherwise drop the
	 * reference we hold to it. If we are aborting the transaction, this may
	 * be the only reference to the buf item, so we free it anyway
	 * regardless of whether it is dirty or not. A dirty abort implies a
	 * shutdown, anyway.
	 *
	 * Ordered buffers are dirty but may have no recorded changes, so ensure
	 * we only release clean items here.
	 */
	clean = (flags & XFS_BLI_DIRTY) ? false : true;
	if (clean) {
		int i;
		for (i = 0; i < bip->bli_format_count; i++) {
			if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
				     bip->bli_formats[i].blf_map_size)) {
				clean = false;
				break;
			}
		}
	}

	/*
	 * Clean buffers, by definition, cannot be in the AIL. However, aborted
	 * buffers may be dirty and hence in the AIL. Therefore if we are
	 * aborting a buffer and we've just taken the last refernce away, we
	 * have to check if it is in the AIL before freeing it. We need to free
	 * it in this case, because an aborted transaction has already shut the
	 * filesystem down and this is the last chance we will have to do so.
	 */
	if (atomic_dec_and_test(&bip->bli_refcount)) {
		if (clean)
			xfs_buf_item_relse(bp);
		else if (aborted) {
			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
			if (lip->li_flags & XFS_LI_IN_AIL) {
				spin_lock(&lip->li_ailp->xa_lock);
				xfs_trans_ail_delete(lip->li_ailp, lip,
						     SHUTDOWN_LOG_IO_ERROR);
			}
			xfs_buf_item_relse(bp);
		}
	}

	if (!(flags & XFS_BLI_HOLD))
		xfs_buf_relse(bp);
}

/*
 * This is called to find out where the oldest active copy of the
 * buf log item in the on disk log resides now that the last log
 * write of it completed at the given lsn.
 * We always re-log all the dirty data in a buffer, so usually the
 * latest copy in the on disk log is the only one that matters.  For
 * those cases we simply return the given lsn.
 *
 * The one exception to this is for buffers full of newly allocated
 * inodes.  These buffers are only relogged with the XFS_BLI_INODE_BUF
 * flag set, indicating that only the di_next_unlinked fields from the
 * inodes in the buffers will be replayed during recovery.  If the
 * original newly allocated inode images have not yet been flushed
 * when the buffer is so relogged, then we need to make sure that we
 * keep the old images in the 'active' portion of the log.  We do this
 * by returning the original lsn of that transaction here rather than
 * the current one.
 */
STATIC xfs_lsn_t
xfs_buf_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);

	trace_xfs_buf_item_committed(bip);

	if ((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) && lip->li_lsn != 0)
		return lip->li_lsn;
	return lsn;
}

STATIC void
xfs_buf_item_committing(
	struct xfs_log_item	*lip,
	xfs_lsn_t		commit_lsn)
{
}

/*
 * This is the ops vector shared by all buf log items.
 */
static const struct xfs_item_ops xfs_buf_item_ops = {
	.iop_size	= xfs_buf_item_size,
	.iop_format	= xfs_buf_item_format,
	.iop_pin	= xfs_buf_item_pin,
	.iop_unpin	= xfs_buf_item_unpin,
	.iop_unlock	= xfs_buf_item_unlock,
	.iop_committed	= xfs_buf_item_committed,
	.iop_push	= xfs_buf_item_push,
	.iop_committing = xfs_buf_item_committing
};

STATIC int
xfs_buf_item_get_format(
	struct xfs_buf_log_item	*bip,
	int			count)
{
	ASSERT(bip->bli_formats == NULL);
	bip->bli_format_count = count;

	if (count == 1) {
		bip->bli_formats = &bip->__bli_format;
		return 0;
	}

	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
				KM_SLEEP);
	if (!bip->bli_formats)
		return -ENOMEM;
	return 0;
}

STATIC void
xfs_buf_item_free_format(
	struct xfs_buf_log_item	*bip)
{
	if (bip->bli_formats != &bip->__bli_format) {
		kmem_free(bip->bli_formats);
		bip->bli_formats = NULL;
	}
}

/*
 * Allocate a new buf log item to go with the given buffer.
 * Set the buffer's b_fsprivate field to point to the new
 * buf log item.  If there are other item's attached to the
 * buffer (see xfs_buf_attach_iodone() below), then put the
 * buf log item at the front.
 */
void
xfs_buf_item_init(
	xfs_buf_t	*bp,
	xfs_mount_t	*mp)
{
	xfs_log_item_t		*lip = bp->b_fspriv;
	xfs_buf_log_item_t	*bip;
	int			chunks;
	int			map_size;
	int			error;
	int			i;

	/*
	 * Check to see if there is already a buf log item for
	 * this buffer.  If there is, it is guaranteed to be
	 * the first.  If we do already have one, there is
	 * nothing to do here so return.
	 */
	ASSERT(bp->b_target->bt_mount == mp);
	if (lip != NULL && lip->li_type == XFS_LI_BUF)
		return;

	bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
	xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
	bip->bli_buf = bp;
	xfs_buf_hold(bp);

	/*
	 * chunks is the number of XFS_BLF_CHUNK size pieces the buffer
	 * can be divided into. Make sure not to truncate any pieces.
	 * map_size is the size of the bitmap needed to describe the
	 * chunks of the buffer.
	 *
	 * Discontiguous buffer support follows the layout of the underlying
	 * buffer. This makes the implementation as simple as possible.
	 */
	error = xfs_buf_item_get_format(bip, bp->b_map_count);
	ASSERT(error == 0);

	for (i = 0; i < bip->bli_format_count; i++) {
		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
				      XFS_BLF_CHUNK);
		map_size = DIV_ROUND_UP(chunks, NBWORD);

		bip->bli_formats[i].blf_type = XFS_LI_BUF;
		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
		bip->bli_formats[i].blf_map_size = map_size;
	}

	/*
	 * Put the buf item into the list of items attached to the
	 * buffer at the front.
	 */
	if (bp->b_fspriv)
		bip->bli_item.li_bio_list = bp->b_fspriv;
	bp->b_fspriv = bip;
}


/*
 * Mark bytes first through last inclusive as dirty in the buf
 * item's bitmap.
 */
static void
xfs_buf_item_log_segment(
	uint			first,
	uint			last,
	uint			*map)
{
	uint		first_bit;
	uint		last_bit;
	uint		bits_to_set;
	uint		bits_set;
	uint		word_num;
	uint		*wordp;
	uint		bit;
	uint		end_bit;
	uint		mask;

	/*
	 * Convert byte offsets to bit numbers.
	 */
	first_bit = first >> XFS_BLF_SHIFT;
	last_bit = last >> XFS_BLF_SHIFT;

	/*
	 * Calculate the total number of bits to be set.
	 */
	bits_to_set = last_bit - first_bit + 1;

	/*
	 * Get a pointer to the first word in the bitmap
	 * to set a bit in.
	 */
	word_num = first_bit >> BIT_TO_WORD_SHIFT;
	wordp = &map[word_num];

	/*
	 * Calculate the starting bit in the first word.
	 */
	bit = first_bit & (uint)(NBWORD - 1);

	/*
	 * First set any bits in the first word of our range.
	 * If it starts at bit 0 of the word, it will be
	 * set below rather than here.  That is what the variable
	 * bit tells us. The variable bits_set tracks the number
	 * of bits that have been set so far.  End_bit is the number
	 * of the last bit to be set in this word plus one.
	 */
	if (bit) {
		end_bit = MIN(bit + bits_to_set, (uint)NBWORD);
		mask = ((1 << (end_bit - bit)) - 1) << bit;
		*wordp |= mask;
		wordp++;
		bits_set = end_bit - bit;
	} else {
		bits_set = 0;
	}

	/*
	 * Now set bits a whole word at a time that are between
	 * first_bit and last_bit.
	 */
	while ((bits_to_set - bits_set) >= NBWORD) {
		*wordp |= 0xffffffff;
		bits_set += NBWORD;
		wordp++;
	}

	/*
	 * Finally, set any bits left to be set in one last partial word.
	 */
	end_bit = bits_to_set - bits_set;
	if (end_bit) {
		mask = (1 << end_bit) - 1;
		*wordp |= mask;
	}
}

/*
 * Mark bytes first through last inclusive as dirty in the buf
 * item's bitmap.
 */
void
xfs_buf_item_log(
	xfs_buf_log_item_t	*bip,
	uint			first,
	uint			last)
{
	int			i;
	uint			start;
	uint			end;
	struct xfs_buf		*bp = bip->bli_buf;

	/*
	 * walk each buffer segment and mark them dirty appropriately.
	 */
	start = 0;
	for (i = 0; i < bip->bli_format_count; i++) {
		if (start > last)
			break;
		end = start + BBTOB(bp->b_maps[i].bm_len);
		if (first > end) {
			start += BBTOB(bp->b_maps[i].bm_len);
			continue;
		}
		if (first < start)
			first = start;
		if (end > last)
			end = last;

		xfs_buf_item_log_segment(first, end,
					 &bip->bli_formats[i].blf_data_map[0]);

		start += bp->b_maps[i].bm_len;
	}
}


/*
 * Return 1 if the buffer has been logged or ordered in a transaction (at any
 * point, not just the current transaction) and 0 if not.
 */
uint
xfs_buf_item_dirty(
	xfs_buf_log_item_t	*bip)
{
	return (bip->bli_flags & XFS_BLI_DIRTY);
}

STATIC void
xfs_buf_item_free(
	xfs_buf_log_item_t	*bip)
{
	xfs_buf_item_free_format(bip);
	kmem_zone_free(xfs_buf_item_zone, bip);
}

/*
 * This is called when the buf log item is no longer needed.  It should
 * free the buf log item associated with the given buffer and clear
 * the buffer's pointer to the buf log item.  If there are no more
 * items in the list, clear the b_iodone field of the buffer (see
 * xfs_buf_attach_iodone() below).
 */
void
xfs_buf_item_relse(
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip = bp->b_fspriv;

	trace_xfs_buf_item_relse(bp, _RET_IP_);
	ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));

	bp->b_fspriv = bip->bli_item.li_bio_list;
	if (bp->b_fspriv == NULL)
		bp->b_iodone = NULL;

	xfs_buf_rele(bp);
	xfs_buf_item_free(bip);
}


/*
 * Add the given log item with its callback to the list of callbacks
 * to be called when the buffer's I/O completes.  If it is not set
 * already, set the buffer's b_iodone() routine to be
 * xfs_buf_iodone_callbacks() and link the log item into the list of
 * items rooted at b_fsprivate.  Items are always added as the second
 * entry in the list if there is a first, because the buf item code
 * assumes that the buf log item is first.
 */
void
xfs_buf_attach_iodone(
	xfs_buf_t	*bp,
	void		(*cb)(xfs_buf_t *, xfs_log_item_t *),
	xfs_log_item_t	*lip)
{
	xfs_log_item_t	*head_lip;

	ASSERT(xfs_buf_islocked(bp));

	lip->li_cb = cb;
	head_lip = bp->b_fspriv;
	if (head_lip) {
		lip->li_bio_list = head_lip->li_bio_list;
		head_lip->li_bio_list = lip;
	} else {
		bp->b_fspriv = lip;
	}

	ASSERT(bp->b_iodone == NULL ||
	       bp->b_iodone == xfs_buf_iodone_callbacks);
	bp->b_iodone = xfs_buf_iodone_callbacks;
}

/*
 * We can have many callbacks on a buffer. Running the callbacks individually
 * can cause a lot of contention on the AIL lock, so we allow for a single
 * callback to be able to scan the remaining lip->li_bio_list for other items
 * of the same type and callback to be processed in the first call.
 *
 * As a result, the loop walking the callback list below will also modify the
 * list. it removes the first item from the list and then runs the callback.
 * The loop then restarts from the new head of the list. This allows the
 * callback to scan and modify the list attached to the buffer and we don't
 * have to care about maintaining a next item pointer.
 */
STATIC void
xfs_buf_do_callbacks(
	struct xfs_buf		*bp)
{
	struct xfs_log_item	*lip;

	while ((lip = bp->b_fspriv) != NULL) {
		bp->b_fspriv = lip->li_bio_list;
		ASSERT(lip->li_cb != NULL);
		/*
		 * Clear the next pointer so we don't have any
		 * confusion if the item is added to another buf.
		 * Don't touch the log item after calling its
		 * callback, because it could have freed itself.
		 */
		lip->li_bio_list = NULL;
		lip->li_cb(bp, lip);
	}
}

/*
 * This is the iodone() function for buffers which have had callbacks
 * attached to them by xfs_buf_attach_iodone().  It should remove each
 * log item from the buffer's list and call the callback of each in turn.
 * When done, the buffer's fsprivate field is set to NULL and the buffer
 * is unlocked with a call to iodone().
 */
void
xfs_buf_iodone_callbacks(
	struct xfs_buf		*bp)
{
	struct xfs_log_item	*lip = bp->b_fspriv;
	struct xfs_mount	*mp = lip->li_mountp;
	static ulong		lasttime;
	static xfs_buftarg_t	*lasttarg;

	if (likely(!bp->b_error))
		goto do_callbacks;

	/*
	 * If we've already decided to shutdown the filesystem because of
	 * I/O errors, there's no point in giving this a retry.
	 */
	if (XFS_FORCED_SHUTDOWN(mp)) {
		xfs_buf_stale(bp);
		XFS_BUF_DONE(bp);
		trace_xfs_buf_item_iodone(bp, _RET_IP_);
		goto do_callbacks;
	}

	if (bp->b_target != lasttarg ||
	    time_after(jiffies, (lasttime + 5*HZ))) {
		lasttime = jiffies;
		xfs_buf_ioerror_alert(bp, __func__);
	}
	lasttarg = bp->b_target;

	/*
	 * If the write was asynchronous then no one will be looking for the
	 * error.  Clear the error state and write the buffer out again.
	 *
	 * XXX: This helps against transient write errors, but we need to find
	 * a way to shut the filesystem down if the writes keep failing.
	 *
	 * In practice we'll shut the filesystem down soon as non-transient
	 * errors tend to affect the whole device and a failing log write
	 * will make us give up.  But we really ought to do better here.
	 */
	if (XFS_BUF_ISASYNC(bp)) {
		ASSERT(bp->b_iodone != NULL);

		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);

		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */

		if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
			bp->b_flags |= XBF_WRITE | XBF_ASYNC |
				       XBF_DONE | XBF_WRITE_FAIL;
			xfs_buf_submit(bp);
		} else {
			xfs_buf_relse(bp);
		}

		return;
	}

	/*
	 * If the write of the buffer was synchronous, we want to make
	 * sure to return the error to the caller of xfs_bwrite().
	 */
	xfs_buf_stale(bp);
	XFS_BUF_DONE(bp);

	trace_xfs_buf_error_relse(bp, _RET_IP_);

do_callbacks:
	xfs_buf_do_callbacks(bp);
	bp->b_fspriv = NULL;
	bp->b_iodone = NULL;
	xfs_buf_ioend(bp);
}

/*
 * This is the iodone() function for buffers which have been
 * logged.  It is called when they are eventually flushed out.
 * It should remove the buf item from the AIL, and free the buf item.
 * It is called by xfs_buf_iodone_callbacks() above which will take
 * care of cleaning up the buffer itself.
 */
void
xfs_buf_iodone(
	struct xfs_buf		*bp,
	struct xfs_log_item	*lip)
{
	struct xfs_ail		*ailp = lip->li_ailp;

	ASSERT(BUF_ITEM(lip)->bli_buf == bp);

	xfs_buf_rele(bp);

	/*
	 * If we are forcibly shutting down, this may well be
	 * off the AIL already. That's because we simulate the
	 * log-committed callbacks to unpin these buffers. Or we may never
	 * have put this item on AIL because of the transaction was
	 * aborted forcibly. xfs_trans_ail_delete() takes care of these.
	 *
	 * Either way, AIL is useless if we're forcing a shutdown.
	 */
	spin_lock(&ailp->xa_lock);
	xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
	xfs_buf_item_free(BUF_ITEM(lip));
}