aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_trans_ail.c
blob: 9bd1ee55ef6aa5eb2ee26e8b7ea3bf6f5dd2952f (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
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * Copyright (c) 2008 Dave Chinner
 * 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_types.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_trans_priv.h"
#include "xfs_error.h"

struct workqueue_struct	*xfs_ail_wq;	/* AIL workqueue */

#ifdef DEBUG
/*
 * Check that the list is sorted as it should be.
 */
STATIC void
xfs_ail_check(
	struct xfs_ail	*ailp,
	xfs_log_item_t	*lip)
{
	xfs_log_item_t	*prev_lip;

	if (list_empty(&ailp->xa_ail))
		return;

	/*
	 * Check the next and previous entries are valid.
	 */
	ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
	prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail);
	if (&prev_lip->li_ail != &ailp->xa_ail)
		ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);

	prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail);
	if (&prev_lip->li_ail != &ailp->xa_ail)
		ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0);


#ifdef XFS_TRANS_DEBUG
	/*
	 * Walk the list checking lsn ordering, and that every entry has the
	 * XFS_LI_IN_AIL flag set. This is really expensive, so only do it
	 * when specifically debugging the transaction subsystem.
	 */
	prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail);
	list_for_each_entry(lip, &ailp->xa_ail, li_ail) {
		if (&prev_lip->li_ail != &ailp->xa_ail)
			ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);
		ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
		prev_lip = lip;
	}
#endif /* XFS_TRANS_DEBUG */
}
#else /* !DEBUG */
#define	xfs_ail_check(a,l)
#endif /* DEBUG */

/*
 * Return a pointer to the first item in the AIL.  If the AIL is empty, then
 * return NULL.
 */
static xfs_log_item_t *
xfs_ail_min(
	struct xfs_ail  *ailp)
{
	if (list_empty(&ailp->xa_ail))
		return NULL;

	return list_first_entry(&ailp->xa_ail, xfs_log_item_t, li_ail);
}

 /*
 * Return a pointer to the last item in the AIL.  If the AIL is empty, then
 * return NULL.
 */
static xfs_log_item_t *
xfs_ail_max(
	struct xfs_ail  *ailp)
{
	if (list_empty(&ailp->xa_ail))
		return NULL;

	return list_entry(ailp->xa_ail.prev, xfs_log_item_t, li_ail);
}

/*
 * Return a pointer to the item which follows the given item in the AIL.  If
 * the given item is the last item in the list, then return NULL.
 */
static xfs_log_item_t *
xfs_ail_next(
	struct xfs_ail  *ailp,
	xfs_log_item_t  *lip)
{
	if (lip->li_ail.next == &ailp->xa_ail)
		return NULL;

	return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail);
}

/*
 * This is called by the log manager code to determine the LSN of the tail of
 * the log.  This is exactly the LSN of the first item in the AIL.  If the AIL
 * is empty, then this function returns 0.
 *
 * We need the AIL lock in order to get a coherent read of the lsn of the last
 * item in the AIL.
 */
xfs_lsn_t
xfs_ail_min_lsn(
	struct xfs_ail	*ailp)
{
	xfs_lsn_t	lsn = 0;
	xfs_log_item_t	*lip;

	spin_lock(&ailp->xa_lock);
	lip = xfs_ail_min(ailp);
	if (lip)
		lsn = lip->li_lsn;
	spin_unlock(&ailp->xa_lock);

	return lsn;
}

/*
 * Return the maximum lsn held in the AIL, or zero if the AIL is empty.
 */
static xfs_lsn_t
xfs_ail_max_lsn(
	struct xfs_ail  *ailp)
{
	xfs_lsn_t       lsn = 0;
	xfs_log_item_t  *lip;

	spin_lock(&ailp->xa_lock);
	lip = xfs_ail_max(ailp);
	if (lip)
		lsn = lip->li_lsn;
	spin_unlock(&ailp->xa_lock);

	return lsn;
}

/*
 * The cursor keeps track of where our current traversal is up to by tracking
 * the next item in the list for us. However, for this to be safe, removing an
 * object from the AIL needs to invalidate any cursor that points to it. hence
 * the traversal cursor needs to be linked to the struct xfs_ail so that
 * deletion can search all the active cursors for invalidation.
 */
STATIC void
xfs_trans_ail_cursor_init(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur)
{
	cur->item = NULL;
	list_add_tail(&cur->list, &ailp->xa_cursors);
}

/*
 * Get the next item in the traversal and advance the cursor.  If the cursor
 * was invalidated (indicated by a lip of 1), restart the traversal.
 */
struct xfs_log_item *
xfs_trans_ail_cursor_next(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur)
{
	struct xfs_log_item	*lip = cur->item;

	if ((__psint_t)lip & 1)
		lip = xfs_ail_min(ailp);
	if (lip)
		cur->item = xfs_ail_next(ailp, lip);
	return lip;
}

/*
 * When the traversal is complete, we need to remove the cursor from the list
 * of traversing cursors.
 */
void
xfs_trans_ail_cursor_done(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur)
{
	cur->item = NULL;
	list_del_init(&cur->list);
}

/*
 * Invalidate any cursor that is pointing to this item. This is called when an
 * item is removed from the AIL. Any cursor pointing to this object is now
 * invalid and the traversal needs to be terminated so it doesn't reference a
 * freed object. We set the low bit of the cursor item pointer so we can
 * distinguish between an invalidation and the end of the list when getting the
 * next item from the cursor.
 */
STATIC void
xfs_trans_ail_cursor_clear(
	struct xfs_ail		*ailp,
	struct xfs_log_item	*lip)
{
	struct xfs_ail_cursor	*cur;

	list_for_each_entry(cur, &ailp->xa_cursors, list) {
		if (cur->item == lip)
			cur->item = (struct xfs_log_item *)
					((__psint_t)cur->item | 1);
	}
}

/*
 * Find the first item in the AIL with the given @lsn by searching in ascending
 * LSN order and initialise the cursor to point to the next item for a
 * ascending traversal.  Pass a @lsn of zero to initialise the cursor to the
 * first item in the AIL. Returns NULL if the list is empty.
 */
xfs_log_item_t *
xfs_trans_ail_cursor_first(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur,
	xfs_lsn_t		lsn)
{
	xfs_log_item_t		*lip;

	xfs_trans_ail_cursor_init(ailp, cur);

	if (lsn == 0) {
		lip = xfs_ail_min(ailp);
		goto out;
	}

	list_for_each_entry(lip, &ailp->xa_ail, li_ail) {
		if (XFS_LSN_CMP(lip->li_lsn, lsn) >= 0)
			goto out;
	}
	return NULL;

out:
	if (lip)
		cur->item = xfs_ail_next(ailp, lip);
	return lip;
}

static struct xfs_log_item *
__xfs_trans_ail_cursor_last(
	struct xfs_ail		*ailp,
	xfs_lsn_t		lsn)
{
	xfs_log_item_t		*lip;

	list_for_each_entry_reverse(lip, &ailp->xa_ail, li_ail) {
		if (XFS_LSN_CMP(lip->li_lsn, lsn) <= 0)
			return lip;
	}
	return NULL;
}

/*
 * Find the last item in the AIL with the given @lsn by searching in descending
 * LSN order and initialise the cursor to point to that item.  If there is no
 * item with the value of @lsn, then it sets the cursor to the last item with an
 * LSN lower than @lsn.  Returns NULL if the list is empty.
 */
struct xfs_log_item *
xfs_trans_ail_cursor_last(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur,
	xfs_lsn_t		lsn)
{
	xfs_trans_ail_cursor_init(ailp, cur);
	cur->item = __xfs_trans_ail_cursor_last(ailp, lsn);
	return cur->item;
}

/*
 * Splice the log item list into the AIL at the given LSN. We splice to the
 * tail of the given LSN to maintain insert order for push traversals. The
 * cursor is optional, allowing repeated updates to the same LSN to avoid
 * repeated traversals.  This should not be called with an empty list.
 */
static void
xfs_ail_splice(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur,
	struct list_head	*list,
	xfs_lsn_t		lsn)
{
	struct xfs_log_item	*lip;

	ASSERT(!list_empty(list));

	/*
	 * Use the cursor to determine the insertion point if one is
	 * provided.  If not, or if the one we got is not valid,
	 * find the place in the AIL where the items belong.
	 */
	lip = cur ? cur->item : NULL;
	if (!lip || (__psint_t) lip & 1)
		lip = __xfs_trans_ail_cursor_last(ailp, lsn);

	/*
	 * If a cursor is provided, we know we're processing the AIL
	 * in lsn order, and future items to be spliced in will
	 * follow the last one being inserted now.  Update the
	 * cursor to point to that last item, now while we have a
	 * reliable pointer to it.
	 */
	if (cur)
		cur->item = list_entry(list->prev, struct xfs_log_item, li_ail);

	/*
	 * Finally perform the splice.  Unless the AIL was empty,
	 * lip points to the item in the AIL _after_ which the new
	 * items should go.  If lip is null the AIL was empty, so
	 * the new items go at the head of the AIL.
	 */
	if (lip)
		list_splice(list, &lip->li_ail);
	else
		list_splice(list, &ailp->xa_ail);
}

/*
 * Delete the given item from the AIL.  Return a pointer to the item.
 */
static void
xfs_ail_delete(
	struct xfs_ail  *ailp,
	xfs_log_item_t  *lip)
{
	xfs_ail_check(ailp, lip);
	list_del(&lip->li_ail);
	xfs_trans_ail_cursor_clear(ailp, lip);
}

/*
 * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself
 * to run at a later time if there is more work to do to complete the push.
 */
STATIC void
xfs_ail_worker(
	struct work_struct	*work)
{
	struct xfs_ail		*ailp = container_of(to_delayed_work(work),
					struct xfs_ail, xa_work);
	xfs_mount_t		*mp = ailp->xa_mount;
	struct xfs_ail_cursor	cur;
	xfs_log_item_t		*lip;
	xfs_lsn_t		lsn;
	xfs_lsn_t		target;
	long			tout = 10;
	int			flush_log = 0;
	int			stuck = 0;
	int			count = 0;
	int			push_xfsbufd = 0;

	spin_lock(&ailp->xa_lock);
	target = ailp->xa_target;
	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
	if (!lip || XFS_FORCED_SHUTDOWN(mp)) {
		/*
		 * AIL is empty or our push has reached the end.
		 */
		xfs_trans_ail_cursor_done(ailp, &cur);
		spin_unlock(&ailp->xa_lock);
		goto out_done;
	}

	XFS_STATS_INC(xs_push_ail);

	/*
	 * While the item we are looking at is below the given threshold
	 * try to flush it out. We'd like not to stop until we've at least
	 * tried to push on everything in the AIL with an LSN less than
	 * the given threshold.
	 *
	 * However, we will stop after a certain number of pushes and wait
	 * for a reduced timeout to fire before pushing further. This
	 * prevents use from spinning when we can't do anything or there is
	 * lots of contention on the AIL lists.
	 */
	lsn = lip->li_lsn;
	while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
		int	lock_result;
		/*
		 * If we can lock the item without sleeping, unlock the AIL
		 * lock and flush the item.  Then re-grab the AIL lock so we
		 * can look for the next item on the AIL. List changes are
		 * handled by the AIL lookup functions internally
		 *
		 * If we can't lock the item, either its holder will flush it
		 * or it is already being flushed or it is being relogged.  In
		 * any of these case it is being taken care of and we can just
		 * skip to the next item in the list.
		 */
		lock_result = IOP_TRYLOCK(lip);
		spin_unlock(&ailp->xa_lock);
		switch (lock_result) {
		case XFS_ITEM_SUCCESS:
			XFS_STATS_INC(xs_push_ail_success);
			IOP_PUSH(lip);
			ailp->xa_last_pushed_lsn = lsn;
			break;

		case XFS_ITEM_PUSHBUF:
			XFS_STATS_INC(xs_push_ail_pushbuf);
			IOP_PUSHBUF(lip);
			ailp->xa_last_pushed_lsn = lsn;
			push_xfsbufd = 1;
			break;

		case XFS_ITEM_PINNED:
			XFS_STATS_INC(xs_push_ail_pinned);
			stuck++;
			flush_log = 1;
			break;

		case XFS_ITEM_LOCKED:
			XFS_STATS_INC(xs_push_ail_locked);
			stuck++;
			break;

		default:
			ASSERT(0);
			break;
		}

		spin_lock(&ailp->xa_lock);
		/* should we bother continuing? */
		if (XFS_FORCED_SHUTDOWN(mp))
			break;
		ASSERT(mp->m_log);

		count++;

		/*
		 * Are there too many items we can't do anything with?
		 * If we we are skipping too many items because we can't flush
		 * them or they are already being flushed, we back off and
		 * given them time to complete whatever operation is being
		 * done. i.e. remove pressure from the AIL while we can't make
		 * progress so traversals don't slow down further inserts and
		 * removals to/from the AIL.
		 *
		 * The value of 100 is an arbitrary magic number based on
		 * observation.
		 */
		if (stuck > 100)
			break;

		lip = xfs_trans_ail_cursor_next(ailp, &cur);
		if (lip == NULL)
			break;
		lsn = lip->li_lsn;
	}
	xfs_trans_ail_cursor_done(ailp, &cur);
	spin_unlock(&ailp->xa_lock);

	if (flush_log) {
		/*
		 * If something we need to push out was pinned, then
		 * push out the log so it will become unpinned and
		 * move forward in the AIL.
		 */
		XFS_STATS_INC(xs_push_ail_flush);
		xfs_log_force(mp, 0);
	}

	if (push_xfsbufd) {
		/* we've got delayed write buffers to flush */
		wake_up_process(mp->m_ddev_targp->bt_task);
	}

	/* assume we have more work to do in a short while */
out_done:
	if (!count) {
		/* We're past our target or empty, so idle */
		ailp->xa_last_pushed_lsn = 0;

		/*
		 * We clear the XFS_AIL_PUSHING_BIT first before checking
		 * whether the target has changed. If the target has changed,
		 * this pushes the requeue race directly onto the result of the
		 * atomic test/set bit, so we are guaranteed that either the
		 * the pusher that changed the target or ourselves will requeue
		 * the work (but not both).
		 */
		clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags);
		smp_rmb();
		if (XFS_LSN_CMP(ailp->xa_target, target) == 0 ||
		    test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
			return;

		tout = 50;
	} else if (XFS_LSN_CMP(lsn, target) >= 0) {
		/*
		 * We reached the target so wait a bit longer for I/O to
		 * complete and remove pushed items from the AIL before we
		 * start the next scan from the start of the AIL.
		 */
		tout = 50;
		ailp->xa_last_pushed_lsn = 0;
	} else if ((stuck * 100) / count > 90) {
		/*
		 * Either there is a lot of contention on the AIL or we
		 * are stuck due to operations in progress. "Stuck" in this
		 * case is defined as >90% of the items we tried to push
		 * were stuck.
		 *
		 * Backoff a bit more to allow some I/O to complete before
		 * continuing from where we were.
		 */
		tout = 20;
	}

	/* There is more to do, requeue us.  */
	queue_delayed_work(xfs_syncd_wq, &ailp->xa_work,
					msecs_to_jiffies(tout));
}

/*
 * This routine is called to move the tail of the AIL forward.  It does this by
 * trying to flush items in the AIL whose lsns are below the given
 * threshold_lsn.
 *
 * The push is run asynchronously in a workqueue, which means the caller needs
 * to handle waiting on the async flush for space to become available.
 * We don't want to interrupt any push that is in progress, hence we only queue
 * work if we set the pushing bit approriately.
 *
 * We do this unlocked - we only need to know whether there is anything in the
 * AIL at the time we are called. We don't need to access the contents of
 * any of the objects, so the lock is not needed.
 */
void
xfs_ail_push(
	struct xfs_ail	*ailp,
	xfs_lsn_t	threshold_lsn)
{
	xfs_log_item_t	*lip;

	lip = xfs_ail_min(ailp);
	if (!lip || XFS_FORCED_SHUTDOWN(ailp->xa_mount) ||
	    XFS_LSN_CMP(threshold_lsn, ailp->xa_target) <= 0)
		return;

	/*
	 * Ensure that the new target is noticed in push code before it clears
	 * the XFS_AIL_PUSHING_BIT.
	 */
	smp_wmb();
	xfs_trans_ail_copy_lsn(ailp, &ailp->xa_target, &threshold_lsn);
	if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
		queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0);
}

/*
 * Push out all items in the AIL immediately
 */
void
xfs_ail_push_all(
	struct xfs_ail  *ailp)
{
	xfs_lsn_t       threshold_lsn = xfs_ail_max_lsn(ailp);

	if (threshold_lsn)
		xfs_ail_push(ailp, threshold_lsn);
}

/*
 * This is to be called when an item is unlocked that may have
 * been in the AIL.  It will wake up the first member of the AIL
 * wait list if this item's unlocking might allow it to progress.
 * If the item is in the AIL, then we need to get the AIL lock
 * while doing our checking so we don't race with someone going
 * to sleep waiting for this event in xfs_trans_push_ail().
 */
void
xfs_trans_unlocked_item(
	struct xfs_ail	*ailp,
	xfs_log_item_t	*lip)
{
	xfs_log_item_t	*min_lip;

	/*
	 * If we're forcibly shutting down, we may have
	 * unlocked log items arbitrarily. The last thing
	 * we want to do is to move the tail of the log
	 * over some potentially valid data.
	 */
	if (!(lip->li_flags & XFS_LI_IN_AIL) ||
	    XFS_FORCED_SHUTDOWN(ailp->xa_mount)) {
		return;
	}

	/*
	 * This is the one case where we can call into xfs_ail_min()
	 * without holding the AIL lock because we only care about the
	 * case where we are at the tail of the AIL.  If the object isn't
	 * at the tail, it doesn't matter what result we get back.  This
	 * is slightly racy because since we were just unlocked, we could
	 * go to sleep between the call to xfs_ail_min and the call to
	 * xfs_log_move_tail, have someone else lock us, commit to us disk,
	 * move us out of the tail of the AIL, and then we wake up.  However,
	 * the call to xfs_log_move_tail() doesn't do anything if there's
	 * not enough free space to wake people up so we're safe calling it.
	 */
	min_lip = xfs_ail_min(ailp);

	if (min_lip == lip)
		xfs_log_move_tail(ailp->xa_mount, 1);
}	/* xfs_trans_unlocked_item */

/*
 * xfs_trans_ail_update - bulk AIL insertion operation.
 *
 * @xfs_trans_ail_update takes an array of log items that all need to be
 * positioned at the same LSN in the AIL. If an item is not in the AIL, it will
 * be added.  Otherwise, it will be repositioned  by removing it and re-adding
 * it to the AIL. If we move the first item in the AIL, update the log tail to
 * match the new minimum LSN in the AIL.
 *
 * This function takes the AIL lock once to execute the update operations on
 * all the items in the array, and as such should not be called with the AIL
 * lock held. As a result, once we have the AIL lock, we need to check each log
 * item LSN to confirm it needs to be moved forward in the AIL.
 *
 * To optimise the insert operation, we delete all the items from the AIL in
 * the first pass, moving them into a temporary list, then splice the temporary
 * list into the correct position in the AIL. This avoids needing to do an
 * insert operation on every item.
 *
 * This function must be called with the AIL lock held.  The lock is dropped
 * before returning.
 */
void
xfs_trans_ail_update_bulk(
	struct xfs_ail		*ailp,
	struct xfs_ail_cursor	*cur,
	struct xfs_log_item	**log_items,
	int			nr_items,
	xfs_lsn_t		lsn) __releases(ailp->xa_lock)
{
	xfs_log_item_t		*mlip;
	xfs_lsn_t		tail_lsn;
	int			mlip_changed = 0;
	int			i;
	LIST_HEAD(tmp);

	ASSERT(nr_items > 0);		/* Not required, but true. */
	mlip = xfs_ail_min(ailp);

	for (i = 0; i < nr_items; i++) {
		struct xfs_log_item *lip = log_items[i];
		if (lip->li_flags & XFS_LI_IN_AIL) {
			/* check if we really need to move the item */
			if (XFS_LSN_CMP(lsn, lip->li_lsn) <= 0)
				continue;

			xfs_ail_delete(ailp, lip);
			if (mlip == lip)
				mlip_changed = 1;
		} else {
			lip->li_flags |= XFS_LI_IN_AIL;
		}
		lip->li_lsn = lsn;
		list_add(&lip->li_ail, &tmp);
	}

	if (!list_empty(&tmp))
		xfs_ail_splice(ailp, cur, &tmp, lsn);

	if (!mlip_changed) {
		spin_unlock(&ailp->xa_lock);
		return;
	}

	/*
	 * It is not safe to access mlip after the AIL lock is dropped, so we
	 * must get a copy of li_lsn before we do so.  This is especially
	 * important on 32-bit platforms where accessing and updating 64-bit
	 * values like li_lsn is not atomic.
	 */
	mlip = xfs_ail_min(ailp);
	tail_lsn = mlip->li_lsn;
	spin_unlock(&ailp->xa_lock);
	xfs_log_move_tail(ailp->xa_mount, tail_lsn);
}

/*
 * xfs_trans_ail_delete_bulk - remove multiple log items from the AIL
 *
 * @xfs_trans_ail_delete_bulk takes an array of log items that all need to
 * removed from the AIL. The caller is already holding the AIL lock, and done
 * all the checks necessary to ensure the items passed in via @log_items are
 * ready for deletion. This includes checking that the items are in the AIL.
 *
 * For each log item to be removed, unlink it  from the AIL, clear the IN_AIL
 * flag from the item and reset the item's lsn to 0. If we remove the first
 * item in the AIL, update the log tail to match the new minimum LSN in the
 * AIL.
 *
 * This function will not drop the AIL lock until all items are removed from
 * the AIL to minimise the amount of lock traffic on the AIL. This does not
 * greatly increase the AIL hold time, but does significantly reduce the amount
 * of traffic on the lock, especially during IO completion.
 *
 * This function must be called with the AIL lock held.  The lock is dropped
 * before returning.
 */
void
xfs_trans_ail_delete_bulk(
	struct xfs_ail		*ailp,
	struct xfs_log_item	**log_items,
	int			nr_items) __releases(ailp->xa_lock)
{
	xfs_log_item_t		*mlip;
	xfs_lsn_t		tail_lsn;
	int			mlip_changed = 0;
	int			i;

	mlip = xfs_ail_min(ailp);

	for (i = 0; i < nr_items; i++) {
		struct xfs_log_item *lip = log_items[i];
		if (!(lip->li_flags & XFS_LI_IN_AIL)) {
			struct xfs_mount	*mp = ailp->xa_mount;

			spin_unlock(&ailp->xa_lock);
			if (!XFS_FORCED_SHUTDOWN(mp)) {
				xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
		"%s: attempting to delete a log item that is not in the AIL",
						__func__);
				xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
			}
			return;
		}

		xfs_ail_delete(ailp, lip);
		lip->li_flags &= ~XFS_LI_IN_AIL;
		lip->li_lsn = 0;
		if (mlip == lip)
			mlip_changed = 1;
	}

	if (!mlip_changed) {
		spin_unlock(&ailp->xa_lock);
		return;
	}

	/*
	 * It is not safe to access mlip after the AIL lock is dropped, so we
	 * must get a copy of li_lsn before we do so.  This is especially
	 * important on 32-bit platforms where accessing and updating 64-bit
	 * values like li_lsn is not atomic. It is possible we've emptied the
	 * AIL here, so if that is the case, pass an LSN of 0 to the tail move.
	 */
	mlip = xfs_ail_min(ailp);
	tail_lsn = mlip ? mlip->li_lsn : 0;
	spin_unlock(&ailp->xa_lock);
	xfs_log_move_tail(ailp->xa_mount, tail_lsn);
}

/*
 * The active item list (AIL) is a doubly linked list of log
 * items sorted by ascending lsn.  The base of the list is
 * a forw/back pointer pair embedded in the xfs mount structure.
 * The base is initialized with both pointers pointing to the
 * base.  This case always needs to be distinguished, because
 * the base has no lsn to look at.  We almost always insert
 * at the end of the list, so on inserts we search from the
 * end of the list to find where the new item belongs.
 */

/*
 * Initialize the doubly linked list to point only to itself.
 */
int
xfs_trans_ail_init(
	xfs_mount_t	*mp)
{
	struct xfs_ail	*ailp;

	ailp = kmem_zalloc(sizeof(struct xfs_ail), KM_MAYFAIL);
	if (!ailp)
		return ENOMEM;

	ailp->xa_mount = mp;
	INIT_LIST_HEAD(&ailp->xa_ail);
	INIT_LIST_HEAD(&ailp->xa_cursors);
	spin_lock_init(&ailp->xa_lock);
	INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker);
	mp->m_ail = ailp;
	return 0;
}

void
xfs_trans_ail_destroy(
	xfs_mount_t	*mp)
{
	struct xfs_ail	*ailp = mp->m_ail;

	cancel_delayed_work_sync(&ailp->xa_work);
	kmem_free(ailp);
}