aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_log_cil.c
blob: 5eb51fc5eb844f2553e5a2d4711c9a32a74bdd18 (plain) (blame)
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
/*
 * Copyright (c) 2010 Red Hat, 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_log_format.h"
#include "xfs_shared.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_discard.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"

/*
 * 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,
				KM_SLEEP|KM_NOFS);
	tic->t_trans_type = XFS_TRANS_CHECKPOINT;

	/*
	 * 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;
}

/*
 * 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;
	log->l_cilp->xc_ctx->commit_lsn = xlog_assign_lsn(log->l_curr_cycle,
								log->l_curr_block);
}

STATIC int
xlog_cil_lv_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_vec	*lv)
{
	int	index;
	char	*ptr;

	/* format new vectors into array */
	lip->li_ops->iop_format(lip, lv->lv_iovecp);

	/* copy data into existing array */
	ptr = lv->lv_buf;
	for (index = 0; index < lv->lv_niovecs; index++) {
		struct xfs_log_iovec *vec = &lv->lv_iovecp[index];

		memcpy(ptr, vec->i_addr, vec->i_len);
		vec->i_addr = ptr;
		ptr += vec->i_len;
	}

	/*
	 * some size calculations for log vectors over-estimate, so the caller
	 * doesn't know the amount of space actually used by the item. Return
	 * the byte count to the caller so they can check and store it
	 * appropriately.
	 */
	return ptr - lv->lv_buf;
}

/*
 * 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_buf_len;
		*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 free it.
	 */
	if (!old_lv)
		lv->lv_item->li_ops->iop_pin(lv->lv_item);
	else if (old_lv != lv) {
		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);

		*diff_len -= old_lv->lv_buf_len;
		*diff_iovecs -= old_lv->lv_niovecs;
		kmem_free(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 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 formats the vector for the item into the buffer.
 * The buffer is then attached to the log item are then inserted into the
 * Committed Item List for tracking until the next checkpoint is written out.
 *
 * 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_desc *lidp;


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

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

		/* Skip items which aren't dirty in this transaction. */
		if (!(lidp->lid_flags & XFS_LID_DIRTY))
			continue;

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

		/* Skip items that do not have any vectors for writing */
		if (!niovecs)
			continue;

		/*
		 * 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;
		}

		/* grab the old item if it exists for reservation accounting */
		old_lv = lip->li_lv;

		/* calc buffer size */
		buf_size = sizeof(struct xfs_log_vec) + nbytes +
				niovecs * sizeof(struct xfs_log_iovec);

		/* compare to existing item size */
		if (lip->li_lv && buf_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_buf_len;

			/* Ensure the lv is set up according to ->iop_size */
			lv->lv_niovecs = niovecs;
			lv->lv_buf = (char *)lv + buf_size - nbytes;

			lv->lv_buf_len = xlog_cil_lv_item_format(lip, lv);
			goto insert;
		}

		/* allocate new data chunk */
		lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS);
		lv->lv_item = lip;
		lv->lv_size = buf_size;
		lv->lv_niovecs = niovecs;
		if (ordered) {
			/* track as an ordered logvec */
			ASSERT(lip->li_lv == NULL);
			lv->lv_buf_len = XFS_LOG_VEC_ORDERED;
			goto insert;
		}

		/* The allocated iovec region lies beyond the log vector. */
		lv->lv_iovecp = (struct xfs_log_iovec *)&lv[1];

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

		lv->lv_buf_len = xlog_cil_lv_item_format(lip, lv);
insert:
		ASSERT(lv->lv_buf_len <= nbytes);
		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_desc *lidp;
	int			len = 0;
	int			diff_iovecs = 0;
	int			iclog_space;

	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);

	/*
	 * 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.
	 */
	spin_lock(&cil->xc_cil_lock);
	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
		struct xfs_log_item	*lip = lidp->lid_item;

		/* Skip items which aren't dirty in this transaction. */
		if (!(lidp->lid_flags & XFS_LID_DIRTY))
			continue;

		list_move_tail(&lip->li_cil, &cil->xc_cil);
	}

	/* account for space used by new iovec headers  */
	len += diff_iovecs * sizeof(xlog_op_header_t);
	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->ticket->t_curr_res = ctx->ticket->t_unit_res;
		tp->t_ticket->t_curr_res -= ctx->ticket->t_unit_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)) {
		int hdrs;

		hdrs = (len + iclog_space - 1) / iclog_space;
		/* need to take into account split region headers, too */
		hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
		ctx->ticket->t_unit_res += hdrs;
		ctx->ticket->t_curr_res += hdrs;
		tp->t_ticket->t_curr_res -= hdrs;
		ASSERT(tp->t_ticket->t_curr_res >= len);
	}
	tp->t_ticket->t_curr_res -= len;
	ctx->space_used += len;

	spin_unlock(&cil->xc_cil_lock);
}

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;
	}
}

/*
 * 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(
	void	*args,
	int	abort)
{
	struct xfs_cil_ctx	*ctx = args;
	struct xfs_mount	*mp = ctx->cil->xc_log->l_mp;

	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,
			     (mp->m_flags & XFS_MOUNT_DISCARD) && !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)) {
		ASSERT(mp->m_flags & XFS_MOUNT_DISCARD);

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

	kmem_free(ctx);
}

/*
 * Push the Committed Item List to the log. If @push_seq flag is zero, then it
 * is a background flush and so we can chose to ignore it. Otherwise, if the
 * current sequence is the same as @push_seq we need to do a flush. If
 * @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.
 *
 * @push_seq is a value rather than a flag because that allows us to do an
 * unlocked check of the sequence number for a match. Hence we can allows 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 int
xlog_cil_push(
	struct xlog		*log)
{
	struct xfs_cil		*cil = log->l_cilp;
	struct xfs_log_vec	*lv;
	struct xfs_cil_ctx	*ctx;
	struct xfs_cil_ctx	*new_ctx;
	struct xlog_in_core	*commit_iclog;
	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		commit_lsn;
	xfs_lsn_t		push_seq;

	if (!cil)
		return 0;

	new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS);
	new_ctx->ticket = xlog_cil_ticket_alloc(log);

	down_write(&cil->xc_ctx_lock);
	ctx = cil->xc_ctx;

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

	/*
	 * 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;
	}
	spin_unlock(&cil->xc_push_lock);


	/* check for a previously pushed seqeunce */
	if (push_seq < cil->xc_ctx->sequence)
		goto out_skip;

	/*
	 * 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;
	}

	/*
	 * initialise the new context and attach it to the CIL. Then attach
	 * the current context to the CIL committing lsit so it can be found
	 * during log forces to extract the commit lsn of the sequence that
	 * needs to be forced.
	 */
	INIT_LIST_HEAD(&new_ctx->committing);
	INIT_LIST_HEAD(&new_ctx->busy_extents);
	new_ctx->sequence = ctx->sequence + 1;
	new_ctx->cil = cil;
	cil->xc_ctx = new_ctx;

	/*
	 * mirror the new sequence into the cil structure so that we can do
	 * unlocked checks against the current sequence in log forces without
	 * risking deferencing a freed context pointer.
	 */
	cil->xc_current_sequence = new_ctx->sequence;

	/*
	 * The switch is now done, 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.
	 */
	spin_lock(&cil->xc_push_lock);
	list_add(&ctx->committing, &cil->xc_committing);
	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;

	error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0);
	if (error)
		goto out_abort_free_ticket;

	/*
	 * now that we've written the checkpoint into the log, strictly
	 * order the commit records so replay will get them in the right order.
	 */
restart:
	spin_lock(&cil->xc_push_lock);
	list_for_each_entry(new_ctx, &cil->xc_committing, committing) {
		/*
		 * Higher sequences will wait for this one so skip them.
		 * Don't wait for own own sequence, either.
		 */
		if (new_ctx->sequence >= ctx->sequence)
			continue;
		if (!new_ctx->commit_lsn) {
			/*
			 * It is still being pushed! Wait for the push to
			 * complete, then start again from the beginning.
			 */
			xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock);
			goto restart;
		}
	}
	spin_unlock(&cil->xc_push_lock);

	/* xfs_log_done always frees the ticket on error. */
	commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, 0);
	if (commit_lsn == -1)
		goto out_abort;

	/* attach all the transactions w/ busy extents to iclog */
	ctx->log_cb.cb_func = xlog_cil_committed;
	ctx->log_cb.cb_arg = ctx;
	error = xfs_log_notify(log->l_mp, commit_iclog, &ctx->log_cb);
	if (error)
		goto out_abort;

	/*
	 * now the checkpoint commit is complete and we've attached the
	 * callbacks to the iclog we can assign the commit LSN to the context
	 * and wake up anyone who is waiting for the commit to complete.
	 */
	spin_lock(&cil->xc_push_lock);
	ctx->commit_lsn = commit_lsn;
	wake_up_all(&cil->xc_commit_wait);
	spin_unlock(&cil->xc_push_lock);

	/* release the hounds! */
	return xfs_log_release_iclog(log->l_mp, commit_iclog);

out_skip:
	up_write(&cil->xc_ctx_lock);
	xfs_log_ticket_put(new_ctx->ticket);
	kmem_free(new_ctx);
	return 0;

out_abort_free_ticket:
	xfs_log_ticket_put(tic);
out_abort:
	xlog_cil_committed(ctx, XFS_LI_ABORTED);
	return XFS_ERROR(EIO);
}

static void
xlog_cil_push_work(
	struct work_struct	*work)
{
	struct xfs_cil		*cil = container_of(work, struct xfs_cil,
							xc_push_work);
	xlog_cil_push(cil->xc_log);
}

/*
 * 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)
{
	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))
		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(log->l_mp->m_cil_workqueue, &cil->xc_push_work);
	}
	spin_unlock(&cil->xc_push_lock);

}

static void
xlog_cil_push_foreground(
	struct xlog	*log,
	xfs_lsn_t	push_seq)
{
	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 */
	flush_work(&cil->xc_push_work);

	/*
	 * If the CIL is empty or we've already pushed the sequence then
	 * there's no work we need to do.
	 */
	spin_lock(&cil->xc_push_lock);
	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;
	spin_unlock(&cil->xc_push_lock);

	/* do the push now */
	xlog_cil_push(log);
}

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.
 */
int
xfs_log_commit_cil(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_lsn_t		*commit_lsn,
	int			flags)
{
	struct xlog		*log = mp->m_log;
	struct xfs_cil		*cil = log->l_cilp;
	int			log_flags = 0;

	if (flags & XFS_TRANS_RELEASE_LOG_RES)
		log_flags = XFS_LOG_REL_PERM_RESERV;

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

	xlog_cil_insert_items(log, tp);

	/* check we didn't blow the reservation */
	if (tp->t_ticket->t_curr_res < 0)
		xlog_print_tic_res(mp, tp->t_ticket);

	tp->t_commit_lsn = cil->xc_ctx->sequence;
	if (commit_lsn)
		*commit_lsn = tp->t_commit_lsn;

	xfs_log_done(mp, tp->t_ticket, NULL, log_flags);
	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 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.
	 */
	xfs_trans_free_items(tp, tp->t_commit_lsn, 0);

	xlog_cil_push_background(log);

	up_read(&cil->xc_ctx_lock);
	return 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_lsn(
	struct xlog	*log,
	xfs_lsn_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);

	/*
	 * 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.
	 */
	xlog_cil_push_foreground(log, sequence);

	/*
	 * 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.
	 */
restart:
	spin_lock(&cil->xc_push_lock);
	list_for_each_entry(ctx, &cil->xc_committing, committing) {
		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.
			 */
			xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock);
			goto restart;
		}
		if (ctx->sequence != sequence)
			continue;
		/* found it! */
		commit_lsn = ctx->commit_lsn;
	}
	spin_unlock(&cil->xc_push_lock);
	return commit_lsn;
}

/*
 * 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_ctx *ctx;

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

	ctx = lip->li_mountp->m_log->l_cilp->xc_ctx;

	/*
	 * 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.
	 */
	if (XFS_LSN_CMP(lip->li_seq, ctx->sequence) != 0)
		return false;
	return true;
}

/*
 * 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_SLEEP|KM_MAYFAIL);
	if (!cil)
		return ENOMEM;

	ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL);
	if (!ctx) {
		kmem_free(cil);
		return ENOMEM;
	}

	INIT_WORK(&cil->xc_push_work, xlog_cil_push_work);
	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_rwsem(&cil->xc_ctx_lock);
	init_waitqueue_head(&cil->xc_commit_wait);

	INIT_LIST_HEAD(&ctx->committing);
	INIT_LIST_HEAD(&ctx->busy_extents);
	ctx->sequence = 1;
	ctx->cil = cil;
	cil->xc_ctx = ctx;
	cil->xc_current_sequence = ctx->sequence;

	cil->xc_log = log;
	log->l_cilp = cil;
	return 0;
}

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));
	kmem_free(log->l_cilp);
}