summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_log_cil.c
blob: 796e4464f809b143ede4dab5698a1bd0cb7db64b (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
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2010 Red Hat, Inc. All Rights Reserved.
 */

#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_shared.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_extent_busy.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_trace.h"

struct workqueue_struct *xfs_discard_wq;

/*
 * Allocate a new ticket. Failing to get a new ticket makes it really hard to
 * recover, so we don't allow failure here. Also, we allocate in a context that
 * we don't want to be issuing transactions from, so we need to tell the
 * allocation code this as well.
 *
 * We don't reserve any space for the ticket - we are going to steal whatever
 * space we require from transactions as they commit. To ensure we reserve all
 * the space required, we need to set the current reservation of the ticket to
 * zero so that we know to steal the initial transaction overhead from the
 * first transaction commit.
 */
static struct xlog_ticket *
xlog_cil_ticket_alloc(
	struct xlog	*log)
{
	struct xlog_ticket *tic;

	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0);

	/*
	 * set the current reservation to zero so we know to steal the basic
	 * transaction overhead reservation from the first transaction commit.
	 */
	tic->t_curr_res = 0;
	return tic;
}

/*
 * Unavoidable forward declaration - xlog_cil_push_work() calls
 * xlog_cil_ctx_alloc() itself.
 */
static void xlog_cil_push_work(struct work_struct *work);

static struct xfs_cil_ctx *
xlog_cil_ctx_alloc(void)
{
	struct xfs_cil_ctx	*ctx;

	ctx = kmem_zalloc(sizeof(*ctx), KM_NOFS);
	INIT_LIST_HEAD(&ctx->committing);
	INIT_LIST_HEAD(&ctx->busy_extents);
	INIT_WORK(&ctx->push_work, xlog_cil_push_work);
	return ctx;
}

static void
xlog_cil_ctx_switch(
	struct xfs_cil		*cil,
	struct xfs_cil_ctx	*ctx)
{
	ctx->sequence = ++cil->xc_current_sequence;
	ctx->cil = cil;
	cil->xc_ctx = ctx;
}

/*
 * After the first stage of log recovery is done, we know where the head and
 * tail of the log are. We need this log initialisation done before we can
 * initialise the first CIL checkpoint context.
 *
 * Here we allocate a log ticket to track space usage during a CIL push.  This
 * ticket is passed to xlog_write() directly so that we don't slowly leak log
 * space by failing to account for space used by log headers and additional
 * region headers for split regions.
 */
void
xlog_cil_init_post_recovery(
	struct xlog	*log)
{
	log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log);
	log->l_cilp->xc_ctx->sequence = 1;
}

static inline int
xlog_cil_iovec_space(
	uint	niovecs)
{
	return round_up((sizeof(struct xfs_log_vec) +
					niovecs * sizeof(struct xfs_log_iovec)),
			sizeof(uint64_t));
}

/*
 * shadow buffers can be large, so we need to use kvmalloc() here to ensure
 * success. Unfortunately, kvmalloc() only allows GFP_KERNEL contexts to fall
 * back to vmalloc, so we can't actually do anything useful with gfp flags to
 * control the kmalloc() behaviour within kvmalloc(). Hence kmalloc() will do
 * direct reclaim and compaction in the slow path, both of which are
 * horrendously expensive. We just want kmalloc to fail fast and fall back to
 * vmalloc if it can't get somethign straight away from the free lists or buddy
 * allocator. Hence we have to open code kvmalloc outselves here.
 *
 * Also, we are in memalloc_nofs_save task context here, so despite the use of
 * GFP_KERNEL here, we are actually going to be doing GFP_NOFS allocations. This
 * is actually the only way to make vmalloc() do GFP_NOFS allocations, so lets
 * just all pretend this is a GFP_KERNEL context operation....
 */
static inline void *
xlog_cil_kvmalloc(
	size_t		buf_size)
{
	gfp_t		flags = GFP_KERNEL;
	void		*p;

	flags &= ~__GFP_DIRECT_RECLAIM;
	flags |= __GFP_NOWARN | __GFP_NORETRY;
	do {
		p = kmalloc(buf_size, flags);
		if (!p)
			p = vmalloc(buf_size);
	} while (!p);

	return p;
}

/*
 * Allocate or pin log vector buffers for CIL insertion.
 *
 * The CIL currently uses disposable buffers for copying a snapshot of the
 * modified items into the log during a push. The biggest problem with this is
 * the requirement to allocate the disposable buffer during the commit if:
 *	a) does not exist; or
 *	b) it is too small
 *
 * If we do this allocation within xlog_cil_insert_format_items(), it is done
 * under the xc_ctx_lock, which means that a CIL push cannot occur during
 * the memory allocation. This means that we have a potential deadlock situation
 * under low memory conditions when we have lots of dirty metadata pinned in
 * the CIL and we need a CIL commit to occur to free memory.
 *
 * To avoid this, we need to move the memory allocation outside the
 * xc_ctx_lock, but because the log vector buffers are disposable, that opens
 * up a TOCTOU race condition w.r.t. the CIL committing and removing the log
 * vector buffers between the check and the formatting of the item into the
 * log vector buffer within the xc_ctx_lock.
 *
 * Because the log vector buffer needs to be unchanged during the CIL push
 * process, we cannot share the buffer between the transaction commit (which
 * modifies the buffer) and the CIL push context that is writing the changes
 * into the log. This means skipping preallocation of buffer space is
 * unreliable, but we most definitely do not want to be allocating and freeing
 * buffers unnecessarily during commits when overwrites can be done safely.
 *
 * The simplest solution to this problem is to allocate a shadow buffer when a
 * log item is committed for the second time, and then to only use this buffer
 * if necessary. The buffer can remain attached to the log item until such time
 * it is needed, and this is the buffer that is reallocated to match the size of
 * the incoming modification. Then during the formatting of the item we can swap
 * the active buffer with the new one if we can't reuse the existing buffer. We
 * don't free the old buffer as it may be reused on the next modification if
 * it's size is right, otherwise we'll free and reallocate it at that point.
 *
 * This function builds a vector for the changes in each log item in the
 * transaction. It then works out the length of the buffer needed for each log
 * item, allocates them and attaches the vector to the log item in preparation
 * for the formatting step which occurs under the xc_ctx_lock.
 *
 * While this means the memory footprint goes up, it avoids the repeated
 * alloc/free pattern that repeated modifications of an item would otherwise
 * cause, and hence minimises the CPU overhead of such behaviour.
 */
static void
xlog_cil_alloc_shadow_bufs(
	struct xlog		*log,
	struct xfs_trans	*tp)
{
	struct xfs_log_item	*lip;

	list_for_each_entry(lip, &tp->t_items, li_trans) {
		struct xfs_log_vec *lv;
		int	niovecs = 0;
		int	nbytes = 0;
		int	buf_size;
		bool	ordered = false;

		/* Skip items which aren't dirty in this transaction. */
		if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
			continue;

		/* get number of vecs and size of data to be stored */
		lip->li_ops->iop_size(lip, &niovecs, &nbytes);

		/*
		 * Ordered items need to be tracked but we do not wish to write
		 * them. We need a logvec to track the object, but we do not
		 * need an iovec or buffer to be allocated for copying data.
		 */
		if (niovecs == XFS_LOG_VEC_ORDERED) {
			ordered = true;
			niovecs = 0;
			nbytes = 0;
		}

		/*
		 * We 64-bit align the length of each iovec so that the start
		 * of the next one is naturally aligned.  We'll need to
		 * account for that slack space here. Then round nbytes up
		 * to 64-bit alignment so that the initial buffer alignment is
		 * easy to calculate and verify.
		 */
		nbytes += niovecs * sizeof(uint64_t);
		nbytes = round_up(nbytes, sizeof(uint64_t));

		/*
		 * The data buffer needs to start 64-bit aligned, so round up
		 * that space to ensure we can align it appropriately and not
		 * overrun the buffer.
		 */
		buf_size = nbytes + xlog_cil_iovec_space(niovecs);

		/*
		 * if we have no shadow buffer, or it is too small, we need to
		 * reallocate it.
		 */
		if (!lip->li_lv_shadow ||
		    buf_size > lip->li_lv_shadow->lv_size) {
			/*
			 * We free and allocate here as a realloc would copy
			 * unnecessary data. We don't use kvzalloc() for the
			 * same reason - we don't need to zero the data area in
			 * the buffer, only the log vector header and the iovec
			 * storage.
			 */
			kmem_free(lip->li_lv_shadow);
			lv = xlog_cil_kvmalloc(buf_size);

			memset(lv, 0, xlog_cil_iovec_space(niovecs));

			lv->lv_item = lip;
			lv->lv_size = buf_size;
			if (ordered)
				lv->lv_buf_len = XFS_LOG_VEC_ORDERED;
			else
				lv->lv_iovecp = (struct xfs_log_iovec *)&lv[1];
			lip->li_lv_shadow = lv;
		} else {
			/* same or smaller, optimise common overwrite case */
			lv = lip->li_lv_shadow;
			if (ordered)
				lv->lv_buf_len = XFS_LOG_VEC_ORDERED;
			else
				lv->lv_buf_len = 0;
			lv->lv_bytes = 0;
			lv->lv_next = NULL;
		}

		/* Ensure the lv is set up according to ->iop_size */
		lv->lv_niovecs = niovecs;

		/* The allocated data region lies beyond the iovec region */
		lv->lv_buf = (char *)lv + xlog_cil_iovec_space(niovecs);
	}

}

/*
 * Prepare the log item for insertion into the CIL. Calculate the difference in
 * log space and vectors it will consume, and if it is a new item pin it as
 * well.
 */
STATIC void
xfs_cil_prepare_item(
	struct xlog		*log,
	struct xfs_log_vec	*lv,
	struct xfs_log_vec	*old_lv,
	int			*diff_len,
	int			*diff_iovecs)
{
	/* Account for the new LV being passed in */
	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
		*diff_len += lv->lv_bytes;
		*diff_iovecs += lv->lv_niovecs;
	}

	/*
	 * If there is no old LV, this is the first time we've seen the item in
	 * this CIL context and so we need to pin it. If we are replacing the
	 * old_lv, then remove the space it accounts for and make it the shadow
	 * buffer for later freeing. In both cases we are now switching to the
	 * shadow buffer, so update the pointer to it appropriately.
	 */
	if (!old_lv) {
		if (lv->lv_item->li_ops->iop_pin)
			lv->lv_item->li_ops->iop_pin(lv->lv_item);
		lv->lv_item->li_lv_shadow = NULL;
	} else if (old_lv != lv) {
		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);

		*diff_len -= old_lv->lv_bytes;
		*diff_iovecs -= old_lv->lv_niovecs;
		lv->lv_item->li_lv_shadow = old_lv;
	}

	/* attach new log vector to log item */
	lv->lv_item->li_lv = lv;

	/*
	 * If this is the first time the item is being committed to the
	 * CIL, store the sequence number on the log item so we can
	 * tell in future commits whether this is the first checkpoint
	 * the item is being committed into.
	 */
	if (!lv->lv_item->li_seq)
		lv->lv_item->li_seq = log->l_cilp->xc_ctx->sequence;
}

/*
 * Format log item into a flat buffers
 *
 * For delayed logging, we need to hold a formatted buffer containing all the
 * changes on the log item. This enables us to relog the item in memory and
 * write it out asynchronously without needing to relock the object that was
 * modified at the time it gets written into the iclog.
 *
 * This function takes the prepared log vectors attached to each log item, and
 * formats the changes into the log vector buffer. The buffer it uses is
 * dependent on the current state of the vector in the CIL - the shadow lv is
 * guaranteed to be large enough for the current modification, but we will only
 * use that if we can't reuse the existing lv. If we can't reuse the existing
 * lv, then simple swap it out for the shadow lv. We don't free it - that is
 * done lazily either by th enext modification or the freeing of the log item.
 *
 * We don't set up region headers during this process; we simply copy the
 * regions into the flat buffer. We can do this because we still have to do a
 * formatting step to write the regions into the iclog buffer.  Writing the
 * ophdrs during the iclog write means that we can support splitting large
 * regions across iclog boundares without needing a change in the format of the
 * item/region encapsulation.
 *
 * Hence what we need to do now is change the rewrite the vector array to point
 * to the copied region inside the buffer we just allocated. This allows us to
 * format the regions into the iclog as though they are being formatted
 * directly out of the objects themselves.
 */
static void
xlog_cil_insert_format_items(
	struct xlog		*log,
	struct xfs_trans	*tp,
	int			*diff_len,
	int			*diff_iovecs)
{
	struct xfs_log_item	*lip;


	/* Bail out if we didn't find a log item.  */
	if (list_empty(&tp->t_items)) {
		ASSERT(0);
		return;
	}

	list_for_each_entry(lip, &tp->t_items, li_trans) {
		struct xfs_log_vec *lv;
		struct xfs_log_vec *old_lv = NULL;
		struct xfs_log_vec *shadow;
		bool	ordered = false;

		/* Skip items which aren't dirty in this transaction. */
		if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
			continue;

		/*
		 * The formatting size information is already attached to
		 * the shadow lv on the log item.
		 */
		shadow = lip->li_lv_shadow;
		if (shadow->lv_buf_len == XFS_LOG_VEC_ORDERED)
			ordered = true;

		/* Skip items that do not have any vectors for writing */
		if (!shadow->lv_niovecs && !ordered)
			continue;

		/* compare to existing item size */
		old_lv = lip->li_lv;
		if (lip->li_lv && shadow->lv_size <= lip->li_lv->lv_size) {
			/* same or smaller, optimise common overwrite case */
			lv = lip->li_lv;
			lv->lv_next = NULL;

			if (ordered)
				goto insert;

			/*
			 * set the item up as though it is a new insertion so
			 * that the space reservation accounting is correct.
			 */
			*diff_iovecs -= lv->lv_niovecs;
			*diff_len -= lv->lv_bytes;

			/* Ensure the lv is set up according to ->iop_size */
			lv->lv_niovecs = shadow->lv_niovecs;

			/* reset the lv buffer information for new formatting */
			lv->lv_buf_len = 0;
			lv->lv_bytes = 0;
			lv->lv_buf = (char *)lv +
					xlog_cil_iovec_space(lv->lv_niovecs);
		} else {
			/* switch to shadow buffer! */
			lv = shadow;
			lv->lv_item = lip;
			if (ordered) {
				/* track as an ordered logvec */
				ASSERT(lip->li_lv == NULL);
				goto insert;
			}
		}

		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
		lip->li_ops->iop_format(lip, lv);
insert:
		xfs_cil_prepare_item(log, lv, old_lv, diff_len, diff_iovecs);
	}
}

/*
 * Insert the log items into the CIL and calculate the difference in space
 * consumed by the item. Add the space to the checkpoint ticket and calculate
 * if the change requires additional log metadata. If it does, take that space
 * as well. Remove the amount of space we added to the checkpoint ticket from
 * the current transaction ticket so that the accounting works out correctly.
 */
static void
xlog_cil_insert_items(
	struct xlog		*log,
	struct xfs_trans	*tp)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
	struct xfs_log_item	*lip;
	int			len = 0;
	int			diff_iovecs = 0;
	int			iclog_space;
	int			iovhdr_res = 0, split_res = 0, ctx_res = 0;

	ASSERT(tp);

	/*
	 * We can do this safely because the context can't checkpoint until we
	 * are done so it doesn't matter exactly how we update the CIL.
	 */
	xlog_cil_insert_format_items(log, tp, &len, &diff_iovecs);

	spin_lock(&cil->xc_cil_lock);

	/* account for space used by new iovec headers  */
	iovhdr_res = diff_iovecs * sizeof(xlog_op_header_t);
	len += iovhdr_res;
	ctx->nvecs += diff_iovecs;

	/* attach the transaction to the CIL if it has any busy extents */
	if (!list_empty(&tp->t_busy))
		list_splice_init(&tp->t_busy, &ctx->busy_extents);

	/*
	 * Now transfer enough transaction reservation to the context ticket
	 * for the checkpoint. The context ticket is special - the unit
	 * reservation has to grow as well as the current reservation as we
	 * steal from tickets so we can correctly determine the space used
	 * during the transaction commit.
	 */
	if (ctx->ticket->t_curr_res == 0) {
		ctx_res = ctx->ticket->t_unit_res;
		ctx->ticket->t_curr_res = ctx_res;
		tp->t_ticket->t_curr_res -= ctx_res;
	}

	/* do we need space for more log record headers? */
	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
	if (len > 0 && (ctx->space_used / iclog_space !=
				(ctx->space_used + len) / iclog_space)) {
		split_res = (len + iclog_space - 1) / iclog_space;
		/* need to take into account split region headers, too */
		split_res *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
		ctx->ticket->t_unit_res += split_res;
		ctx->ticket->t_curr_res += split_res;
		tp->t_ticket->t_curr_res -= split_res;
		ASSERT(tp->t_ticket->t_curr_res >= len);
	}
	tp->t_ticket->t_curr_res -= len;
	ctx->space_used += len;

	/*
	 * If we've overrun the reservation, dump the tx details before we move
	 * the log items. Shutdown is imminent...
	 */
	if (WARN_ON(tp->t_ticket->t_curr_res < 0)) {
		xfs_warn(log->l_mp, "Transaction log reservation overrun:");
		xfs_warn(log->l_mp,
			 "  log items: %d bytes (iov hdrs: %d bytes)",
			 len, iovhdr_res);
		xfs_warn(log->l_mp, "  split region headers: %d bytes",
			 split_res);
		xfs_warn(log->l_mp, "  ctx ticket: %d bytes", ctx_res);
		xlog_print_trans(tp);
	}

	/*
	 * Now (re-)position everything modified at the tail of the CIL.
	 * We do this here so we only need to take the CIL lock once during
	 * the transaction commit.
	 */
	list_for_each_entry(lip, &tp->t_items, li_trans) {

		/* Skip items which aren't dirty in this transaction. */
		if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
			continue;

		/*
		 * Only move the item if it isn't already at the tail. This is
		 * to prevent a transient list_empty() state when reinserting
		 * an item that is already the only item in the CIL.
		 */
		if (!list_is_last(&lip->li_cil, &cil->xc_cil))
			list_move_tail(&lip->li_cil, &cil->xc_cil);
	}

	spin_unlock(&cil->xc_cil_lock);

	if (tp->t_ticket->t_curr_res < 0)
		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
}

static void
xlog_cil_free_logvec(
	struct xfs_log_vec	*log_vector)
{
	struct xfs_log_vec	*lv;

	for (lv = log_vector; lv; ) {
		struct xfs_log_vec *next = lv->lv_next;
		kmem_free(lv);
		lv = next;
	}
}

static void
xlog_discard_endio_work(
	struct work_struct	*work)
{
	struct xfs_cil_ctx	*ctx =
		container_of(work, struct xfs_cil_ctx, discard_endio_work);
	struct xfs_mount	*mp = ctx->cil->xc_log->l_mp;

	xfs_extent_busy_clear(mp, &ctx->busy_extents, false);
	kmem_free(ctx);
}

/*
 * Queue up the actual completion to a thread to avoid IRQ-safe locking for
 * pagb_lock.  Note that we need a unbounded workqueue, otherwise we might
 * get the execution delayed up to 30 seconds for weird reasons.
 */
static void
xlog_discard_endio(
	struct bio		*bio)
{
	struct xfs_cil_ctx	*ctx = bio->bi_private;

	INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work);
	queue_work(xfs_discard_wq, &ctx->discard_endio_work);
	bio_put(bio);
}

static void
xlog_discard_busy_extents(
	struct xfs_mount	*mp,
	struct xfs_cil_ctx	*ctx)
{
	struct list_head	*list = &ctx->busy_extents;
	struct xfs_extent_busy	*busyp;
	struct bio		*bio = NULL;
	struct blk_plug		plug;
	int			error = 0;

	ASSERT(xfs_has_discard(mp));

	blk_start_plug(&plug);
	list_for_each_entry(busyp, list, list) {
		trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
					 busyp->length);

		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
				XFS_FSB_TO_BB(mp, busyp->length),
				GFP_NOFS, 0, &bio);
		if (error && error != -EOPNOTSUPP) {
			xfs_info(mp,
	 "discard failed for extent [0x%llx,%u], error %d",
				 (unsigned long long)busyp->bno,
				 busyp->length,
				 error);
			break;
		}
	}

	if (bio) {
		bio->bi_private = ctx;
		bio->bi_end_io = xlog_discard_endio;
		submit_bio(bio);
	} else {
		xlog_discard_endio_work(&ctx->discard_endio_work);
	}
	blk_finish_plug(&plug);
}

/*
 * Mark all items committed and clear busy extents. We free the log vector
 * chains in a separate pass so that we unpin the log items as quickly as
 * possible.
 */
static void
xlog_cil_committed(
	struct xfs_cil_ctx	*ctx)
{
	struct xfs_mount	*mp = ctx->cil->xc_log->l_mp;
	bool			abort = xlog_is_shutdown(ctx->cil->xc_log);

	/*
	 * If the I/O failed, we're aborting the commit and already shutdown.
	 * Wake any commit waiters before aborting the log items so we don't
	 * block async log pushers on callbacks. Async log pushers explicitly do
	 * not wait on log force completion because they may be holding locks
	 * required to unpin items.
	 */
	if (abort) {
		spin_lock(&ctx->cil->xc_push_lock);
		wake_up_all(&ctx->cil->xc_start_wait);
		wake_up_all(&ctx->cil->xc_commit_wait);
		spin_unlock(&ctx->cil->xc_push_lock);
	}

	xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, ctx->lv_chain,
					ctx->start_lsn, abort);

	xfs_extent_busy_sort(&ctx->busy_extents);
	xfs_extent_busy_clear(mp, &ctx->busy_extents,
			      xfs_has_discard(mp) && !abort);

	spin_lock(&ctx->cil->xc_push_lock);
	list_del(&ctx->committing);
	spin_unlock(&ctx->cil->xc_push_lock);

	xlog_cil_free_logvec(ctx->lv_chain);

	if (!list_empty(&ctx->busy_extents))
		xlog_discard_busy_extents(mp, ctx);
	else
		kmem_free(ctx);
}

void
xlog_cil_process_committed(
	struct list_head	*list)
{
	struct xfs_cil_ctx	*ctx;

	while ((ctx = list_first_entry_or_null(list,
			struct xfs_cil_ctx, iclog_entry))) {
		list_del(&ctx->iclog_entry);
		xlog_cil_committed(ctx);
	}
}

/*
* Record the LSN of the iclog we were just granted space to start writing into.
* If the context doesn't have a start_lsn recorded, then this iclog will
* contain the start record for the checkpoint. Otherwise this write contains
* the commit record for the checkpoint.
*/
void
xlog_cil_set_ctx_write_state(
	struct xfs_cil_ctx	*ctx,
	struct xlog_in_core	*iclog)
{
	struct xfs_cil		*cil = ctx->cil;
	xfs_lsn_t		lsn = be64_to_cpu(iclog->ic_header.h_lsn);

	ASSERT(!ctx->commit_lsn);
	if (!ctx->start_lsn) {
		spin_lock(&cil->xc_push_lock);
		/*
		 * The LSN we need to pass to the log items on transaction
		 * commit is the LSN reported by the first log vector write, not
		 * the commit lsn. If we use the commit record lsn then we can
		 * move the tail beyond the grant write head.
		 */
		ctx->start_lsn = lsn;
		wake_up_all(&cil->xc_start_wait);
		spin_unlock(&cil->xc_push_lock);
		return;
	}

	/*
	 * Take a reference to the iclog for the context so that we still hold
	 * it when xlog_write is done and has released it. This means the
	 * context controls when the iclog is released for IO.
	 */
	atomic_inc(&iclog->ic_refcnt);

	/*
	 * xlog_state_get_iclog_space() guarantees there is enough space in the
	 * iclog for an entire commit record, so we can attach the context
	 * callbacks now.  This needs to be done before we make the commit_lsn
	 * visible to waiters so that checkpoints with commit records in the
	 * same iclog order their IO completion callbacks in the same order that
	 * the commit records appear in the iclog.
	 */
	spin_lock(&cil->xc_log->l_icloglock);
	list_add_tail(&ctx->iclog_entry, &iclog->ic_callbacks);
	spin_unlock(&cil->xc_log->l_icloglock);

	/*
	 * Now we can record the commit LSN and wake anyone waiting for this
	 * sequence to have the ordered commit record assigned to a physical
	 * location in the log.
	 */
	spin_lock(&cil->xc_push_lock);
	ctx->commit_iclog = iclog;
	ctx->commit_lsn = lsn;
	wake_up_all(&cil->xc_commit_wait);
	spin_unlock(&cil->xc_push_lock);
}


/*
 * Ensure that the order of log writes follows checkpoint sequence order. This
 * relies on the context LSN being zero until the log write has guaranteed the
 * LSN that the log write will start at via xlog_state_get_iclog_space().
 */
enum _record_type {
	_START_RECORD,
	_COMMIT_RECORD,
};

static int
xlog_cil_order_write(
	struct xfs_cil		*cil,
	xfs_csn_t		sequence,
	enum _record_type	record)
{
	struct xfs_cil_ctx	*ctx;

restart:
	spin_lock(&cil->xc_push_lock);
	list_for_each_entry(ctx, &cil->xc_committing, committing) {
		/*
		 * Avoid getting stuck in this loop because we were woken by the
		 * shutdown, but then went back to sleep once already in the
		 * shutdown state.
		 */
		if (xlog_is_shutdown(cil->xc_log)) {
			spin_unlock(&cil->xc_push_lock);
			return -EIO;
		}

		/*
		 * Higher sequences will wait for this one so skip them.
		 * Don't wait for our own sequence, either.
		 */
		if (ctx->sequence >= sequence)
			continue;

		/* Wait until the LSN for the record has been recorded. */
		switch (record) {
		case _START_RECORD:
			if (!ctx->start_lsn) {
				xlog_wait(&cil->xc_start_wait, &cil->xc_push_lock);
				goto restart;
			}
			break;
		case _COMMIT_RECORD:
			if (!ctx->commit_lsn) {
				xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock);
				goto restart;
			}
			break;
		}
	}
	spin_unlock(&cil->xc_push_lock);
	return 0;
}

/*
 * Write out the log vector change now attached to the CIL context. This will
 * write a start record that needs to be strictly ordered in ascending CIL
 * sequence order so that log recovery will always use in-order start LSNs when
 * replaying checkpoints.
 */
static int
xlog_cil_write_chain(
	struct xfs_cil_ctx	*ctx,
	struct xfs_log_vec	*chain)
{
	struct xlog		*log = ctx->cil->xc_log;
	int			error;

	error = xlog_cil_order_write(ctx->cil, ctx->sequence, _START_RECORD);
	if (error)
		return error;
	return xlog_write(log, ctx, chain, ctx->ticket, XLOG_START_TRANS);
}

/*
 * Write out the commit record of a checkpoint transaction to close off a
 * running log write. These commit records are strictly ordered in ascending CIL
 * sequence order so that log recovery will always replay the checkpoints in the
 * correct order.
 */
static int
xlog_cil_write_commit_record(
	struct xfs_cil_ctx	*ctx)
{
	struct xlog		*log = ctx->cil->xc_log;
	struct xfs_log_iovec	reg = {
		.i_addr = NULL,
		.i_len = 0,
		.i_type = XLOG_REG_TYPE_COMMIT,
	};
	struct xfs_log_vec	vec = {
		.lv_niovecs = 1,
		.lv_iovecp = &reg,
	};
	int			error;

	if (xlog_is_shutdown(log))
		return -EIO;

	error = xlog_cil_order_write(ctx->cil, ctx->sequence, _COMMIT_RECORD);
	if (error)
		return error;

	error = xlog_write(log, ctx, &vec, ctx->ticket, XLOG_COMMIT_TRANS);
	if (error)
		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
	return error;
}

/*
 * Push the Committed Item List to the log.
 *
 * If the current sequence is the same as xc_push_seq we need to do a flush. If
 * xc_push_seq is less than the current sequence, then it has already been
 * flushed and we don't need to do anything - the caller will wait for it to
 * complete if necessary.
 *
 * xc_push_seq is checked unlocked against the sequence number for a match.
 * Hence we can allow log forces to run racily and not issue pushes for the
 * same sequence twice.  If we get a race between multiple pushes for the same
 * sequence they will block on the first one and then abort, hence avoiding
 * needless pushes.
 */
static void
xlog_cil_push_work(
	struct work_struct	*work)
{
	struct xfs_cil_ctx	*ctx =
		container_of(work, struct xfs_cil_ctx, push_work);
	struct xfs_cil		*cil = ctx->cil;
	struct xlog		*log = cil->xc_log;
	struct xfs_log_vec	*lv;
	struct xfs_cil_ctx	*new_ctx;
	struct xlog_ticket	*tic;
	int			num_iovecs;
	int			error = 0;
	struct xfs_trans_header thdr;
	struct xfs_log_iovec	lhdr;
	struct xfs_log_vec	lvhdr = { NULL };
	xfs_lsn_t		preflush_tail_lsn;
	xfs_csn_t		push_seq;
	struct bio		bio;
	DECLARE_COMPLETION_ONSTACK(bdev_flush);
	bool			push_commit_stable;

	new_ctx = xlog_cil_ctx_alloc();
	new_ctx->ticket = xlog_cil_ticket_alloc(log);

	down_write(&cil->xc_ctx_lock);

	spin_lock(&cil->xc_push_lock);
	push_seq = cil->xc_push_seq;
	ASSERT(push_seq <= ctx->sequence);
	push_commit_stable = cil->xc_push_commit_stable;
	cil->xc_push_commit_stable = false;

	/*
	 * As we are about to switch to a new, empty CIL context, we no longer
	 * need to throttle tasks on CIL space overruns. Wake any waiters that
	 * the hard push throttle may have caught so they can start committing
	 * to the new context. The ctx->xc_push_lock provides the serialisation
	 * necessary for safely using the lockless waitqueue_active() check in
	 * this context.
	 */
	if (waitqueue_active(&cil->xc_push_wait))
		wake_up_all(&cil->xc_push_wait);

	/*
	 * Check if we've anything to push. If there is nothing, then we don't
	 * move on to a new sequence number and so we have to be able to push
	 * this sequence again later.
	 */
	if (list_empty(&cil->xc_cil)) {
		cil->xc_push_seq = 0;
		spin_unlock(&cil->xc_push_lock);
		goto out_skip;
	}


	/* check for a previously pushed sequence */
	if (push_seq < ctx->sequence) {
		spin_unlock(&cil->xc_push_lock);
		goto out_skip;
	}

	/*
	 * We are now going to push this context, so add it to the committing
	 * list before we do anything else. This ensures that anyone waiting on
	 * this push can easily detect the difference between a "push in
	 * progress" and "CIL is empty, nothing to do".
	 *
	 * IOWs, a wait loop can now check for:
	 *	the current sequence not being found on the committing list;
	 *	an empty CIL; and
	 *	an unchanged sequence number
	 * to detect a push that had nothing to do and therefore does not need
	 * waiting on. If the CIL is not empty, we get put on the committing
	 * list before emptying the CIL and bumping the sequence number. Hence
	 * an empty CIL and an unchanged sequence number means we jumped out
	 * above after doing nothing.
	 *
	 * Hence the waiter will either find the commit sequence on the
	 * committing list or the sequence number will be unchanged and the CIL
	 * still dirty. In that latter case, the push has not yet started, and
	 * so the waiter will have to continue trying to check the CIL
	 * committing list until it is found. In extreme cases of delay, the
	 * sequence may fully commit between the attempts the wait makes to wait
	 * on the commit sequence.
	 */
	list_add(&ctx->committing, &cil->xc_committing);
	spin_unlock(&cil->xc_push_lock);

	/*
	 * The CIL is stable at this point - nothing new will be added to it
	 * because we hold the flush lock exclusively. Hence we can now issue
	 * a cache flush to ensure all the completed metadata in the journal we
	 * are about to overwrite is on stable storage.
	 *
	 * Because we are issuing this cache flush before we've written the
	 * tail lsn to the iclog, we can have metadata IO completions move the
	 * tail forwards between the completion of this flush and the iclog
	 * being written. In this case, we need to re-issue the cache flush
	 * before the iclog write. To detect whether the log tail moves, sample
	 * the tail LSN *before* we issue the flush.
	 */
	preflush_tail_lsn = atomic64_read(&log->l_tail_lsn);
	xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
				&bdev_flush);

	/*
	 * Pull all the log vectors off the items in the CIL, and remove the
	 * items from the CIL. We don't need the CIL lock here because it's only
	 * needed on the transaction commit side which is currently locked out
	 * by the flush lock.
	 */
	lv = NULL;
	num_iovecs = 0;
	while (!list_empty(&cil->xc_cil)) {
		struct xfs_log_item	*item;

		item = list_first_entry(&cil->xc_cil,
					struct xfs_log_item, li_cil);
		list_del_init(&item->li_cil);
		if (!ctx->lv_chain)
			ctx->lv_chain = item->li_lv;
		else
			lv->lv_next = item->li_lv;
		lv = item->li_lv;
		item->li_lv = NULL;
		num_iovecs += lv->lv_niovecs;
	}

	/*
	 * Switch the contexts so we can drop the context lock and move out
	 * of a shared context. We can't just go straight to the commit record,
	 * though - we need to synchronise with previous and future commits so
	 * that the commit records are correctly ordered in the log to ensure
	 * that we process items during log IO completion in the correct order.
	 *
	 * For example, if we get an EFI in one checkpoint and the EFD in the
	 * next (e.g. due to log forces), we do not want the checkpoint with
	 * the EFD to be committed before the checkpoint with the EFI.  Hence
	 * we must strictly order the commit records of the checkpoints so
	 * that: a) the checkpoint callbacks are attached to the iclogs in the
	 * correct order; and b) the checkpoints are replayed in correct order
	 * in log recovery.
	 *
	 * Hence we need to add this context to the committing context list so
	 * that higher sequences will wait for us to write out a commit record
	 * before they do.
	 *
	 * xfs_log_force_seq requires us to mirror the new sequence into the cil
	 * structure atomically with the addition of this sequence to the
	 * committing list. This also ensures that we can do unlocked checks
	 * against the current sequence in log forces without risking
	 * deferencing a freed context pointer.
	 */
	spin_lock(&cil->xc_push_lock);
	xlog_cil_ctx_switch(cil, new_ctx);
	spin_unlock(&cil->xc_push_lock);
	up_write(&cil->xc_ctx_lock);

	/*
	 * Build a checkpoint transaction header and write it to the log to
	 * begin the transaction. We need to account for the space used by the
	 * transaction header here as it is not accounted for in xlog_write().
	 *
	 * The LSN we need to pass to the log items on transaction commit is
	 * the LSN reported by the first log vector write. If we use the commit
	 * record lsn then we can move the tail beyond the grant write head.
	 */
	tic = ctx->ticket;
	thdr.th_magic = XFS_TRANS_HEADER_MAGIC;
	thdr.th_type = XFS_TRANS_CHECKPOINT;
	thdr.th_tid = tic->t_tid;
	thdr.th_num_items = num_iovecs;
	lhdr.i_addr = &thdr;
	lhdr.i_len = sizeof(xfs_trans_header_t);
	lhdr.i_type = XLOG_REG_TYPE_TRANSHDR;
	tic->t_curr_res -= lhdr.i_len + sizeof(xlog_op_header_t);

	lvhdr.lv_niovecs = 1;
	lvhdr.lv_iovecp = &lhdr;
	lvhdr.lv_next = ctx->lv_chain;

	/*
	 * Before we format and submit the first iclog, we have to ensure that
	 * the metadata writeback ordering cache flush is complete.
	 */
	wait_for_completion(&bdev_flush);

	error = xlog_cil_write_chain(ctx, &lvhdr);
	if (error)
		goto out_abort_free_ticket;

	error = xlog_cil_write_commit_record(ctx);
	if (error)
		goto out_abort_free_ticket;

	xfs_log_ticket_ungrant(log, tic);

	/*
	 * If the checkpoint spans multiple iclogs, wait for all previous iclogs
	 * to complete before we submit the commit_iclog. We can't use state
	 * checks for this - ACTIVE can be either a past completed iclog or a
	 * future iclog being filled, while WANT_SYNC through SYNC_DONE can be a
	 * past or future iclog awaiting IO or ordered IO completion to be run.
	 * In the latter case, if it's a future iclog and we wait on it, the we
	 * will hang because it won't get processed through to ic_force_wait
	 * wakeup until this commit_iclog is written to disk.  Hence we use the
	 * iclog header lsn and compare it to the commit lsn to determine if we
	 * need to wait on iclogs or not.
	 */
	spin_lock(&log->l_icloglock);
	if (ctx->start_lsn != ctx->commit_lsn) {
		xfs_lsn_t	plsn;

		plsn = be64_to_cpu(ctx->commit_iclog->ic_prev->ic_header.h_lsn);
		if (plsn && XFS_LSN_CMP(plsn, ctx->commit_lsn) < 0) {
			/*
			 * Waiting on ic_force_wait orders the completion of
			 * iclogs older than ic_prev. Hence we only need to wait
			 * on the most recent older iclog here.
			 */
			xlog_wait_on_iclog(ctx->commit_iclog->ic_prev);
			spin_lock(&log->l_icloglock);
		}

		/*
		 * We need to issue a pre-flush so that the ordering for this
		 * checkpoint is correctly preserved down to stable storage.
		 */
		ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
	}

	/*
	 * The commit iclog must be written to stable storage to guarantee
	 * journal IO vs metadata writeback IO is correctly ordered on stable
	 * storage.
	 *
	 * If the push caller needs the commit to be immediately stable and the
	 * commit_iclog is not yet marked as XLOG_STATE_WANT_SYNC to indicate it
	 * will be written when released, switch it's state to WANT_SYNC right
	 * now.
	 */
	ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA;
	if (push_commit_stable &&
	    ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE)
		xlog_state_switch_iclogs(log, ctx->commit_iclog, 0);
	xlog_state_release_iclog(log, ctx->commit_iclog, preflush_tail_lsn);

	/* Not safe to reference ctx now! */

	spin_unlock(&log->l_icloglock);
	return;

out_skip:
	up_write(&cil->xc_ctx_lock);
	xfs_log_ticket_put(new_ctx->ticket);
	kmem_free(new_ctx);
	return;

out_abort_free_ticket:
	xfs_log_ticket_ungrant(log, tic);
	ASSERT(xlog_is_shutdown(log));
	if (!ctx->commit_iclog) {
		xlog_cil_committed(ctx);
		return;
	}
	spin_lock(&log->l_icloglock);
	xlog_state_release_iclog(log, ctx->commit_iclog, 0);
	/* Not safe to reference ctx now! */
	spin_unlock(&log->l_icloglock);
}

/*
 * We need to push CIL every so often so we don't cache more than we can fit in
 * the log. The limit really is that a checkpoint can't be more than half the
 * log (the current checkpoint is not allowed to overwrite the previous
 * checkpoint), but commit latency and memory usage limit this to a smaller
 * size.
 */
static void
xlog_cil_push_background(
	struct xlog	*log) __releases(cil->xc_ctx_lock)
{
	struct xfs_cil	*cil = log->l_cilp;

	/*
	 * The cil won't be empty because we are called while holding the
	 * context lock so whatever we added to the CIL will still be there
	 */
	ASSERT(!list_empty(&cil->xc_cil));

	/*
	 * Don't do a background push if we haven't used up all the
	 * space available yet.
	 */
	if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) {
		up_read(&cil->xc_ctx_lock);
		return;
	}

	spin_lock(&cil->xc_push_lock);
	if (cil->xc_push_seq < cil->xc_current_sequence) {
		cil->xc_push_seq = cil->xc_current_sequence;
		queue_work(cil->xc_push_wq, &cil->xc_ctx->push_work);
	}

	/*
	 * Drop the context lock now, we can't hold that if we need to sleep
	 * because we are over the blocking threshold. The push_lock is still
	 * held, so blocking threshold sleep/wakeup is still correctly
	 * serialised here.
	 */
	up_read(&cil->xc_ctx_lock);

	/*
	 * If we are well over the space limit, throttle the work that is being
	 * done until the push work on this context has begun. Enforce the hard
	 * throttle on all transaction commits once it has been activated, even
	 * if the committing transactions have resulted in the space usage
	 * dipping back down under the hard limit.
	 *
	 * The ctx->xc_push_lock provides the serialisation necessary for safely
	 * using the lockless waitqueue_active() check in this context.
	 */
	if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log) ||
	    waitqueue_active(&cil->xc_push_wait)) {
		trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket);
		ASSERT(cil->xc_ctx->space_used < log->l_logsize);
		xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock);
		return;
	}

	spin_unlock(&cil->xc_push_lock);

}

/*
 * xlog_cil_push_now() is used to trigger an immediate CIL push to the sequence
 * number that is passed. When it returns, the work will be queued for
 * @push_seq, but it won't be completed.
 *
 * If the caller is performing a synchronous force, we will flush the workqueue
 * to get previously queued work moving to minimise the wait time they will
 * undergo waiting for all outstanding pushes to complete. The caller is
 * expected to do the required waiting for push_seq to complete.
 *
 * If the caller is performing an async push, we need to ensure that the
 * checkpoint is fully flushed out of the iclogs when we finish the push. If we
 * don't do this, then the commit record may remain sitting in memory in an
 * ACTIVE iclog. This then requires another full log force to push to disk,
 * which defeats the purpose of having an async, non-blocking CIL force
 * mechanism. Hence in this case we need to pass a flag to the push work to
 * indicate it needs to flush the commit record itself.
 */
static void
xlog_cil_push_now(
	struct xlog	*log,
	xfs_lsn_t	push_seq,
	bool		async)
{
	struct xfs_cil	*cil = log->l_cilp;

	if (!cil)
		return;

	ASSERT(push_seq && push_seq <= cil->xc_current_sequence);

	/* start on any pending background push to minimise wait time on it */
	if (!async)
		flush_workqueue(cil->xc_push_wq);

	spin_lock(&cil->xc_push_lock);

	/*
	 * If this is an async flush request, we always need to set the
	 * xc_push_commit_stable flag even if something else has already queued
	 * a push. The flush caller is asking for the CIL to be on stable
	 * storage when the next push completes, so regardless of who has queued
	 * the push, the flush requires stable semantics from it.
	 */
	cil->xc_push_commit_stable = async;

	/*
	 * If the CIL is empty or we've already pushed the sequence then
	 * there's no more work that we need to do.
	 */
	if (list_empty(&cil->xc_cil) || push_seq <= cil->xc_push_seq) {
		spin_unlock(&cil->xc_push_lock);
		return;
	}

	cil->xc_push_seq = push_seq;
	queue_work(cil->xc_push_wq, &cil->xc_ctx->push_work);
	spin_unlock(&cil->xc_push_lock);
}

bool
xlog_cil_empty(
	struct xlog	*log)
{
	struct xfs_cil	*cil = log->l_cilp;
	bool		empty = false;

	spin_lock(&cil->xc_push_lock);
	if (list_empty(&cil->xc_cil))
		empty = true;
	spin_unlock(&cil->xc_push_lock);
	return empty;
}

/*
 * Commit a transaction with the given vector to the Committed Item List.
 *
 * To do this, we need to format the item, pin it in memory if required and
 * account for the space used by the transaction. Once we have done that we
 * need to release the unused reservation for the transaction, attach the
 * transaction to the checkpoint context so we carry the busy extents through
 * to checkpoint completion, and then unlock all the items in the transaction.
 *
 * Called with the context lock already held in read mode to lock out
 * background commit, returns without it held once background commits are
 * allowed again.
 */
void
xlog_cil_commit(
	struct xlog		*log,
	struct xfs_trans	*tp,
	xfs_csn_t		*commit_seq,
	bool			regrant)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_log_item	*lip, *next;

	/*
	 * Do all necessary memory allocation before we lock the CIL.
	 * This ensures the allocation does not deadlock with a CIL
	 * push in memory reclaim (e.g. from kswapd).
	 */
	xlog_cil_alloc_shadow_bufs(log, tp);

	/* lock out background commit */
	down_read(&cil->xc_ctx_lock);

	xlog_cil_insert_items(log, tp);

	if (regrant && !xlog_is_shutdown(log))
		xfs_log_ticket_regrant(log, tp->t_ticket);
	else
		xfs_log_ticket_ungrant(log, tp->t_ticket);
	tp->t_ticket = NULL;
	xfs_trans_unreserve_and_mod_sb(tp);

	/*
	 * Once all the items of the transaction have been copied to the CIL,
	 * the items can be unlocked and possibly freed.
	 *
	 * This needs to be done before we drop the CIL context lock because we
	 * have to update state in the log items and unlock them before they go
	 * to disk. If we don't, then the CIL checkpoint can race with us and
	 * we can run checkpoint completion before we've updated and unlocked
	 * the log items. This affects (at least) processing of stale buffers,
	 * inodes and EFIs.
	 */
	trace_xfs_trans_commit_items(tp, _RET_IP_);
	list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
		xfs_trans_del_item(lip);
		if (lip->li_ops->iop_committing)
			lip->li_ops->iop_committing(lip, cil->xc_ctx->sequence);
	}
	if (commit_seq)
		*commit_seq = cil->xc_ctx->sequence;

	/* xlog_cil_push_background() releases cil->xc_ctx_lock */
	xlog_cil_push_background(log);
}

/*
 * Flush the CIL to stable storage but don't wait for it to complete. This
 * requires the CIL push to ensure the commit record for the push hits the disk,
 * but otherwise is no different to a push done from a log force.
 */
void
xlog_cil_flush(
	struct xlog	*log)
{
	xfs_csn_t	seq = log->l_cilp->xc_current_sequence;

	trace_xfs_log_force(log->l_mp, seq, _RET_IP_);
	xlog_cil_push_now(log, seq, true);

	/*
	 * If the CIL is empty, make sure that any previous checkpoint that may
	 * still be in an active iclog is pushed to stable storage.
	 */
	if (list_empty(&log->l_cilp->xc_cil))
		xfs_log_force(log->l_mp, 0);
}

/*
 * Conditionally push the CIL based on the sequence passed in.
 *
 * We only need to push if we haven't already pushed the sequence number given.
 * Hence the only time we will trigger a push here is if the push sequence is
 * the same as the current context.
 *
 * We return the current commit lsn to allow the callers to determine if a
 * iclog flush is necessary following this call.
 */
xfs_lsn_t
xlog_cil_force_seq(
	struct xlog	*log,
	xfs_csn_t	sequence)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_cil_ctx	*ctx;
	xfs_lsn_t		commit_lsn = NULLCOMMITLSN;

	ASSERT(sequence <= cil->xc_current_sequence);

	if (!sequence)
		sequence = cil->xc_current_sequence;
	trace_xfs_log_force(log->l_mp, sequence, _RET_IP_);

	/*
	 * check to see if we need to force out the current context.
	 * xlog_cil_push() handles racing pushes for the same sequence,
	 * so no need to deal with it here.
	 */
restart:
	xlog_cil_push_now(log, sequence, false);

	/*
	 * See if we can find a previous sequence still committing.
	 * We need to wait for all previous sequence commits to complete
	 * before allowing the force of push_seq to go ahead. Hence block
	 * on commits for those as well.
	 */
	spin_lock(&cil->xc_push_lock);
	list_for_each_entry(ctx, &cil->xc_committing, committing) {
		/*
		 * Avoid getting stuck in this loop because we were woken by the
		 * shutdown, but then went back to sleep once already in the
		 * shutdown state.
		 */
		if (xlog_is_shutdown(log))
			goto out_shutdown;
		if (ctx->sequence > sequence)
			continue;
		if (!ctx->commit_lsn) {
			/*
			 * It is still being pushed! Wait for the push to
			 * complete, then start again from the beginning.
			 */
			XFS_STATS_INC(log->l_mp, xs_log_force_sleep);
			xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock);
			goto restart;
		}
		if (ctx->sequence != sequence)
			continue;
		/* found it! */
		commit_lsn = ctx->commit_lsn;
	}

	/*
	 * The call to xlog_cil_push_now() executes the push in the background.
	 * Hence by the time we have got here it our sequence may not have been
	 * pushed yet. This is true if the current sequence still matches the
	 * push sequence after the above wait loop and the CIL still contains
	 * dirty objects. This is guaranteed by the push code first adding the
	 * context to the committing list before emptying the CIL.
	 *
	 * Hence if we don't find the context in the committing list and the
	 * current sequence number is unchanged then the CIL contents are
	 * significant.  If the CIL is empty, if means there was nothing to push
	 * and that means there is nothing to wait for. If the CIL is not empty,
	 * it means we haven't yet started the push, because if it had started
	 * we would have found the context on the committing list.
	 */
	if (sequence == cil->xc_current_sequence &&
	    !list_empty(&cil->xc_cil)) {
		spin_unlock(&cil->xc_push_lock);
		goto restart;
	}

	spin_unlock(&cil->xc_push_lock);
	return commit_lsn;

	/*
	 * We detected a shutdown in progress. We need to trigger the log force
	 * to pass through it's iclog state machine error handling, even though
	 * we are already in a shutdown state. Hence we can't return
	 * NULLCOMMITLSN here as that has special meaning to log forces (i.e.
	 * LSN is already stable), so we return a zero LSN instead.
	 */
out_shutdown:
	spin_unlock(&cil->xc_push_lock);
	return 0;
}

/*
 * Check if the current log item was first committed in this sequence.
 * We can't rely on just the log item being in the CIL, we have to check
 * the recorded commit sequence number.
 *
 * Note: for this to be used in a non-racy manner, it has to be called with
 * CIL flushing locked out. As a result, it should only be used during the
 * transaction commit process when deciding what to format into the item.
 */
bool
xfs_log_item_in_current_chkpt(
	struct xfs_log_item	*lip)
{
	struct xfs_cil		*cil = lip->li_log->l_cilp;

	if (list_empty(&lip->li_cil))
		return false;

	/*
	 * li_seq is written on the first commit of a log item to record the
	 * first checkpoint it is written to. Hence if it is different to the
	 * current sequence, we're in a new checkpoint.
	 */
	return lip->li_seq == READ_ONCE(cil->xc_current_sequence);
}

/*
 * Perform initial CIL structure initialisation.
 */
int
xlog_cil_init(
	struct xlog	*log)
{
	struct xfs_cil	*cil;
	struct xfs_cil_ctx *ctx;

	cil = kmem_zalloc(sizeof(*cil), KM_MAYFAIL);
	if (!cil)
		return -ENOMEM;
	/*
	 * Limit the CIL pipeline depth to 4 concurrent works to bound the
	 * concurrency the log spinlocks will be exposed to.
	 */
	cil->xc_push_wq = alloc_workqueue("xfs-cil/%s",
			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_UNBOUND),
			4, log->l_mp->m_super->s_id);
	if (!cil->xc_push_wq)
		goto out_destroy_cil;

	INIT_LIST_HEAD(&cil->xc_cil);
	INIT_LIST_HEAD(&cil->xc_committing);
	spin_lock_init(&cil->xc_cil_lock);
	spin_lock_init(&cil->xc_push_lock);
	init_waitqueue_head(&cil->xc_push_wait);
	init_rwsem(&cil->xc_ctx_lock);
	init_waitqueue_head(&cil->xc_start_wait);
	init_waitqueue_head(&cil->xc_commit_wait);
	cil->xc_log = log;
	log->l_cilp = cil;

	ctx = xlog_cil_ctx_alloc();
	xlog_cil_ctx_switch(cil, ctx);

	return 0;

out_destroy_cil:
	kmem_free(cil);
	return -ENOMEM;
}

void
xlog_cil_destroy(
	struct xlog	*log)
{
	if (log->l_cilp->xc_ctx) {
		if (log->l_cilp->xc_ctx->ticket)
			xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket);
		kmem_free(log->l_cilp->xc_ctx);
	}

	ASSERT(list_empty(&log->l_cilp->xc_cil));
	destroy_workqueue(log->l_cilp->xc_push_wq);
	kmem_free(log->l_cilp);
}