summaryrefslogtreecommitdiff
path: root/fs/xfs/linux-2.6/xfs_sync.c
blob: 594cd822d84de225755006321e5b97ebfe35cf70 (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.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_bmap_btree.h"
#include "xfs_inode.h"
#include "xfs_dinode.h"
#include "xfs_error.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_fsops.h"

#include <linux/kthread.h>
#include <linux/freezer.h>

/*
 * The inode lookup is done in batches to keep the amount of lock traffic and
 * radix tree lookups to a minimum. The batch size is a trade off between
 * lookup reduction and stack usage. This is in the reclaim path, so we can't
 * be too greedy.
 */
#define XFS_LOOKUP_BATCH	32

STATIC int
xfs_inode_ag_walk_grab(
	struct xfs_inode	*ip)
{
	struct inode		*inode = VFS_I(ip);

	ASSERT(rcu_read_lock_held());

	/*
	 * check for stale RCU freed inode
	 *
	 * If the inode has been reallocated, it doesn't matter if it's not in
	 * the AG we are walking - we are walking for writeback, so if it
	 * passes all the "valid inode" checks and is dirty, then we'll write
	 * it back anyway.  If it has been reallocated and still being
	 * initialised, the XFS_INEW check below will catch it.
	 */
	spin_lock(&ip->i_flags_lock);
	if (!ip->i_ino)
		goto out_unlock_noent;

	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
		goto out_unlock_noent;
	spin_unlock(&ip->i_flags_lock);

	/* nothing to sync during shutdown */
	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return EFSCORRUPTED;

	/* If we can't grab the inode, it must on it's way to reclaim. */
	if (!igrab(inode))
		return ENOENT;

	if (is_bad_inode(inode)) {
		IRELE(ip);
		return ENOENT;
	}

	/* inode is valid */
	return 0;

out_unlock_noent:
	spin_unlock(&ip->i_flags_lock);
	return ENOENT;
}

STATIC int
xfs_inode_ag_walk(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	int			(*execute)(struct xfs_inode *ip,
					   struct xfs_perag *pag, int flags),
	int			flags)
{
	uint32_t		first_index;
	int			last_error = 0;
	int			skipped;
	int			done;
	int			nr_found;

restart:
	done = 0;
	skipped = 0;
	first_index = 0;
	nr_found = 0;
	do {
		struct xfs_inode *batch[XFS_LOOKUP_BATCH];
		int		error = 0;
		int		i;

		rcu_read_lock();
		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
					(void **)batch, first_index,
					XFS_LOOKUP_BATCH);
		if (!nr_found) {
			rcu_read_unlock();
			break;
		}

		/*
		 * Grab the inodes before we drop the lock. if we found
		 * nothing, nr == 0 and the loop will be skipped.
		 */
		for (i = 0; i < nr_found; i++) {
			struct xfs_inode *ip = batch[i];

			if (done || xfs_inode_ag_walk_grab(ip))
				batch[i] = NULL;

			/*
			 * Update the index for the next lookup. Catch
			 * overflows into the next AG range which can occur if
			 * we have inodes in the last block of the AG and we
			 * are currently pointing to the last inode.
			 *
			 * Because we may see inodes that are from the wrong AG
			 * due to RCU freeing and reallocation, only update the
			 * index if it lies in this AG. It was a race that lead
			 * us to see this inode, so another lookup from the
			 * same index will not find it again.
			 */
			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
				continue;
			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
				done = 1;
		}

		/* unlock now we've grabbed the inodes. */
		rcu_read_unlock();

		for (i = 0; i < nr_found; i++) {
			if (!batch[i])
				continue;
			error = execute(batch[i], pag, flags);
			IRELE(batch[i]);
			if (error == EAGAIN) {
				skipped++;
				continue;
			}
			if (error && last_error != EFSCORRUPTED)
				last_error = error;
		}

		/* bail out if the filesystem is corrupted.  */
		if (error == EFSCORRUPTED)
			break;

	} while (nr_found && !done);

	if (skipped) {
		delay(1);
		goto restart;
	}
	return last_error;
}

int
xfs_inode_ag_iterator(
	struct xfs_mount	*mp,
	int			(*execute)(struct xfs_inode *ip,
					   struct xfs_perag *pag, int flags),
	int			flags)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;

	ag = 0;
	while ((pag = xfs_perag_get(mp, ag))) {
		ag = pag->pag_agno + 1;
		error = xfs_inode_ag_walk(mp, pag, execute, flags);
		xfs_perag_put(pag);
		if (error) {
			last_error = error;
			if (error == EFSCORRUPTED)
				break;
		}
	}
	return XFS_ERROR(last_error);
}

STATIC int
xfs_sync_inode_data(
	struct xfs_inode	*ip,
	struct xfs_perag	*pag,
	int			flags)
{
	struct inode		*inode = VFS_I(ip);
	struct address_space *mapping = inode->i_mapping;
	int			error = 0;

	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
		goto out_wait;

	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
		if (flags & SYNC_TRYLOCK)
			goto out_wait;
		xfs_ilock(ip, XFS_IOLOCK_SHARED);
	}

	error = xfs_flush_pages(ip, 0, -1, (flags & SYNC_WAIT) ?
				0 : XBF_ASYNC, FI_NONE);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

 out_wait:
	if (flags & SYNC_WAIT)
		xfs_ioend_wait(ip);
	return error;
}

STATIC int
xfs_sync_inode_attr(
	struct xfs_inode	*ip,
	struct xfs_perag	*pag,
	int			flags)
{
	int			error = 0;

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	if (xfs_inode_clean(ip))
		goto out_unlock;
	if (!xfs_iflock_nowait(ip)) {
		if (!(flags & SYNC_WAIT))
			goto out_unlock;
		xfs_iflock(ip);
	}

	if (xfs_inode_clean(ip)) {
		xfs_ifunlock(ip);
		goto out_unlock;
	}

	error = xfs_iflush(ip, flags);

 out_unlock:
	xfs_iunlock(ip, XFS_ILOCK_SHARED);
	return error;
}

/*
 * Write out pagecache data for the whole filesystem.
 */
STATIC int
xfs_sync_data(
	struct xfs_mount	*mp,
	int			flags)
{
	int			error;

	ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);

	error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags);
	if (error)
		return XFS_ERROR(error);

	xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
	return 0;
}

/*
 * Write out inode metadata (attributes) for the whole filesystem.
 */
STATIC int
xfs_sync_attr(
	struct xfs_mount	*mp,
	int			flags)
{
	ASSERT((flags & ~SYNC_WAIT) == 0);

	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags);
}

STATIC int
xfs_sync_fsdata(
	struct xfs_mount	*mp)
{
	struct xfs_buf		*bp;

	/*
	 * If the buffer is pinned then push on the log so we won't get stuck
	 * waiting in the write for someone, maybe ourselves, to flush the log.
	 *
	 * Even though we just pushed the log above, we did not have the
	 * superblock buffer locked at that point so it can become pinned in
	 * between there and here.
	 */
	bp = xfs_getsb(mp, 0);
	if (XFS_BUF_ISPINNED(bp))
		xfs_log_force(mp, 0);

	return xfs_bwrite(mp, bp);
}

/*
 * When remounting a filesystem read-only or freezing the filesystem, we have
 * two phases to execute. This first phase is syncing the data before we
 * quiesce the filesystem, and the second is flushing all the inodes out after
 * we've waited for all the transactions created by the first phase to
 * complete. The second phase ensures that the inodes are written to their
 * location on disk rather than just existing in transactions in the log. This
 * means after a quiesce there is no log replay required to write the inodes to
 * disk (this is the main difference between a sync and a quiesce).
 */
/*
 * First stage of freeze - no writers will make progress now we are here,
 * so we flush delwri and delalloc buffers here, then wait for all I/O to
 * complete.  Data is frozen at that point. Metadata is not frozen,
 * transactions can still occur here so don't bother flushing the buftarg
 * because it'll just get dirty again.
 */
int
xfs_quiesce_data(
	struct xfs_mount	*mp)
{
	int			error, error2 = 0;

	/* push non-blocking */
	xfs_sync_data(mp, 0);
	xfs_qm_sync(mp, SYNC_TRYLOCK);

	/* push and block till complete */
	xfs_sync_data(mp, SYNC_WAIT);
	xfs_qm_sync(mp, SYNC_WAIT);

	/* write superblock and hoover up shutdown errors */
	error = xfs_sync_fsdata(mp);

	/* make sure all delwri buffers are written out */
	xfs_flush_buftarg(mp->m_ddev_targp, 1);

	/* mark the log as covered if needed */
	if (xfs_log_need_covered(mp))
		error2 = xfs_fs_log_dummy(mp);

	/* flush data-only devices */
	if (mp->m_rtdev_targp)
		XFS_bflush(mp->m_rtdev_targp);

	return error ? error : error2;
}

STATIC void
xfs_quiesce_fs(
	struct xfs_mount	*mp)
{
	int	count = 0, pincount;

	xfs_reclaim_inodes(mp, 0);
	xfs_flush_buftarg(mp->m_ddev_targp, 0);

	/*
	 * This loop must run at least twice.  The first instance of the loop
	 * will flush most meta data but that will generate more meta data
	 * (typically directory updates).  Which then must be flushed and
	 * logged before we can write the unmount record. We also so sync
	 * reclaim of inodes to catch any that the above delwri flush skipped.
	 */
	do {
		xfs_reclaim_inodes(mp, SYNC_WAIT);
		xfs_sync_attr(mp, SYNC_WAIT);
		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
		if (!pincount) {
			delay(50);
			count++;
		}
	} while (count < 2);
}

/*
 * Second stage of a quiesce. The data is already synced, now we have to take
 * care of the metadata. New transactions are already blocked, so we need to
 * wait for any remaining transactions to drain out before proceding.
 */
void
xfs_quiesce_attr(
	struct xfs_mount	*mp)
{
	int	error = 0;

	/* wait for all modifications to complete */
	while (atomic_read(&mp->m_active_trans) > 0)
		delay(100);

	/* flush inodes and push all remaining buffers out to disk */
	xfs_quiesce_fs(mp);

	/*
	 * Just warn here till VFS can correctly support
	 * read-only remount without racing.
	 */
	WARN_ON(atomic_read(&mp->m_active_trans) != 0);

	/* Push the superblock and write an unmount record */
	error = xfs_log_sbcount(mp, 1);
	if (error)
		xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
				"Frozen image may not be consistent.");
	xfs_log_unmount_write(mp);
	xfs_unmountfs_writesb(mp);
}

/*
 * Enqueue a work item to be picked up by the vfs xfssyncd thread.
 * Doing this has two advantages:
 * - It saves on stack space, which is tight in certain situations
 * - It can be used (with care) as a mechanism to avoid deadlocks.
 * Flushing while allocating in a full filesystem requires both.
 */
STATIC void
xfs_syncd_queue_work(
	struct xfs_mount *mp,
	void		*data,
	void		(*syncer)(struct xfs_mount *, void *),
	struct completion *completion)
{
	struct xfs_sync_work *work;

	work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP);
	INIT_LIST_HEAD(&work->w_list);
	work->w_syncer = syncer;
	work->w_data = data;
	work->w_mount = mp;
	work->w_completion = completion;
	spin_lock(&mp->m_sync_lock);
	list_add_tail(&work->w_list, &mp->m_sync_list);
	spin_unlock(&mp->m_sync_lock);
	wake_up_process(mp->m_sync_task);
}

/*
 * Flush delayed allocate data, attempting to free up reserved space
 * from existing allocations.  At this point a new allocation attempt
 * has failed with ENOSPC and we are in the process of scratching our
 * heads, looking about for more room...
 */
STATIC void
xfs_flush_inodes_work(
	struct xfs_mount *mp,
	void		*arg)
{
	struct inode	*inode = arg;
	xfs_sync_data(mp, SYNC_TRYLOCK);
	xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT);
	iput(inode);
}

void
xfs_flush_inodes(
	xfs_inode_t	*ip)
{
	struct inode	*inode = VFS_I(ip);
	DECLARE_COMPLETION_ONSTACK(completion);

	igrab(inode);
	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion);
	wait_for_completion(&completion);
	xfs_log_force(ip->i_mount, XFS_LOG_SYNC);
}

/*
 * Every sync period we need to unpin all items, reclaim inodes and sync
 * disk quotas.  We might need to cover the log to indicate that the
 * filesystem is idle and not frozen.
 */
STATIC void
xfs_sync_worker(
	struct xfs_mount *mp,
	void		*unused)
{
	int		error;

	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
		/* dgc: errors ignored here */
		if (mp->m_super->s_frozen == SB_UNFROZEN &&
		    xfs_log_need_covered(mp))
			error = xfs_fs_log_dummy(mp);
		else
			xfs_log_force(mp, 0);
		xfs_reclaim_inodes(mp, 0);
		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
	}
	mp->m_sync_seq++;
	wake_up(&mp->m_wait_single_sync_task);
}

STATIC int
xfssyncd(
	void			*arg)
{
	struct xfs_mount	*mp = arg;
	long			timeleft;
	xfs_sync_work_t		*work, *n;
	LIST_HEAD		(tmp);

	set_freezable();
	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
	for (;;) {
		if (list_empty(&mp->m_sync_list))
			timeleft = schedule_timeout_interruptible(timeleft);
		/* swsusp */
		try_to_freeze();
		if (kthread_should_stop() && list_empty(&mp->m_sync_list))
			break;

		spin_lock(&mp->m_sync_lock);
		/*
		 * We can get woken by laptop mode, to do a sync -
		 * that's the (only!) case where the list would be
		 * empty with time remaining.
		 */
		if (!timeleft || list_empty(&mp->m_sync_list)) {
			if (!timeleft)
				timeleft = xfs_syncd_centisecs *
							msecs_to_jiffies(10);
			INIT_LIST_HEAD(&mp->m_sync_work.w_list);
			list_add_tail(&mp->m_sync_work.w_list,
					&mp->m_sync_list);
		}
		list_splice_init(&mp->m_sync_list, &tmp);
		spin_unlock(&mp->m_sync_lock);

		list_for_each_entry_safe(work, n, &tmp, w_list) {
			(*work->w_syncer)(mp, work->w_data);
			list_del(&work->w_list);
			if (work == &mp->m_sync_work)
				continue;
			if (work->w_completion)
				complete(work->w_completion);
			kmem_free(work);
		}
	}

	return 0;
}

int
xfs_syncd_init(
	struct xfs_mount	*mp)
{
	mp->m_sync_work.w_syncer = xfs_sync_worker;
	mp->m_sync_work.w_mount = mp;
	mp->m_sync_work.w_completion = NULL;
	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd/%s", mp->m_fsname);
	if (IS_ERR(mp->m_sync_task))
		return -PTR_ERR(mp->m_sync_task);
	return 0;
}

void
xfs_syncd_stop(
	struct xfs_mount	*mp)
{
	kthread_stop(mp->m_sync_task);
}

void
__xfs_inode_set_reclaim_tag(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip)
{
	radix_tree_tag_set(&pag->pag_ici_root,
			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
			   XFS_ICI_RECLAIM_TAG);

	if (!pag->pag_ici_reclaimable) {
		/* propagate the reclaim tag up into the perag radix tree */
		spin_lock(&ip->i_mount->m_perag_lock);
		radix_tree_tag_set(&ip->i_mount->m_perag_tree,
				XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
				XFS_ICI_RECLAIM_TAG);
		spin_unlock(&ip->i_mount->m_perag_lock);
		trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
							-1, _RET_IP_);
	}
	pag->pag_ici_reclaimable++;
}

/*
 * We set the inode flag atomically with the radix tree tag.
 * Once we get tag lookups on the radix tree, this inode flag
 * can go away.
 */
void
xfs_inode_set_reclaim_tag(
	xfs_inode_t	*ip)
{
	struct xfs_mount *mp = ip->i_mount;
	struct xfs_perag *pag;

	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
	spin_lock(&pag->pag_ici_lock);
	spin_lock(&ip->i_flags_lock);
	__xfs_inode_set_reclaim_tag(pag, ip);
	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
	spin_unlock(&ip->i_flags_lock);
	spin_unlock(&pag->pag_ici_lock);
	xfs_perag_put(pag);
}

STATIC void
__xfs_inode_clear_reclaim(
	xfs_perag_t	*pag,
	xfs_inode_t	*ip)
{
	pag->pag_ici_reclaimable--;
	if (!pag->pag_ici_reclaimable) {
		/* clear the reclaim tag from the perag radix tree */
		spin_lock(&ip->i_mount->m_perag_lock);
		radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
				XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
				XFS_ICI_RECLAIM_TAG);
		spin_unlock(&ip->i_mount->m_perag_lock);
		trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno,
							-1, _RET_IP_);
	}
}

void
__xfs_inode_clear_reclaim_tag(
	xfs_mount_t	*mp,
	xfs_perag_t	*pag,
	xfs_inode_t	*ip)
{
	radix_tree_tag_clear(&pag->pag_ici_root,
			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
	__xfs_inode_clear_reclaim(pag, ip);
}

/*
 * Grab the inode for reclaim exclusively.
 * Return 0 if we grabbed it, non-zero otherwise.
 */
STATIC int
xfs_reclaim_inode_grab(
	struct xfs_inode	*ip,
	int			flags)
{
	ASSERT(rcu_read_lock_held());

	/* quick check for stale RCU freed inode */
	if (!ip->i_ino)
		return 1;

	/*
	 * do some unlocked checks first to avoid unnecessary lock traffic.
	 * The first is a flush lock check, the second is a already in reclaim
	 * check. Only do these checks if we are not going to block on locks.
	 */
	if ((flags & SYNC_TRYLOCK) &&
	    (!ip->i_flush.done || __xfs_iflags_test(ip, XFS_IRECLAIM))) {
		return 1;
	}

	/*
	 * The radix tree lock here protects a thread in xfs_iget from racing
	 * with us starting reclaim on the inode.  Once we have the
	 * XFS_IRECLAIM flag set it will not touch us.
	 *
	 * Due to RCU lookup, we may find inodes that have been freed and only
	 * have XFS_IRECLAIM set.  Indeed, we may see reallocated inodes that
	 * aren't candidates for reclaim at all, so we must check the
	 * XFS_IRECLAIMABLE is set first before proceeding to reclaim.
	 */
	spin_lock(&ip->i_flags_lock);
	if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) ||
	    __xfs_iflags_test(ip, XFS_IRECLAIM)) {
		/* not a reclaim candidate. */
		spin_unlock(&ip->i_flags_lock);
		return 1;
	}
	__xfs_iflags_set(ip, XFS_IRECLAIM);
	spin_unlock(&ip->i_flags_lock);
	return 0;
}

/*
 * Inodes in different states need to be treated differently, and the return
 * value of xfs_iflush is not sufficient to get this right. The following table
 * lists the inode states and the reclaim actions necessary for non-blocking
 * reclaim:
 *
 *
 *	inode state	     iflush ret		required action
 *      ---------------      ----------         ---------------
 *	bad			-		reclaim
 *	shutdown		EIO		unpin and reclaim
 *	clean, unpinned		0		reclaim
 *	stale, unpinned		0		reclaim
 *	clean, pinned(*)	0		requeue
 *	stale, pinned		EAGAIN		requeue
 *	dirty, delwri ok	0		requeue
 *	dirty, delwri blocked	EAGAIN		requeue
 *	dirty, sync flush	0		reclaim
 *
 * (*) dgc: I don't think the clean, pinned state is possible but it gets
 * handled anyway given the order of checks implemented.
 *
 * As can be seen from the table, the return value of xfs_iflush() is not
 * sufficient to correctly decide the reclaim action here. The checks in
 * xfs_iflush() might look like duplicates, but they are not.
 *
 * Also, because we get the flush lock first, we know that any inode that has
 * been flushed delwri has had the flush completed by the time we check that
 * the inode is clean. The clean inode check needs to be done before flushing
 * the inode delwri otherwise we would loop forever requeuing clean inodes as
 * we cannot tell apart a successful delwri flush and a clean inode from the
 * return value of xfs_iflush().
 *
 * Note that because the inode is flushed delayed write by background
 * writeback, the flush lock may already be held here and waiting on it can
 * result in very long latencies. Hence for sync reclaims, where we wait on the
 * flush lock, the caller should push out delayed write inodes first before
 * trying to reclaim them to minimise the amount of time spent waiting. For
 * background relaim, we just requeue the inode for the next pass.
 *
 * Hence the order of actions after gaining the locks should be:
 *	bad		=> reclaim
 *	shutdown	=> unpin and reclaim
 *	pinned, delwri	=> requeue
 *	pinned, sync	=> unpin
 *	stale		=> reclaim
 *	clean		=> reclaim
 *	dirty, delwri	=> flush and requeue
 *	dirty, sync	=> flush, wait and reclaim
 */
STATIC int
xfs_reclaim_inode(
	struct xfs_inode	*ip,
	struct xfs_perag	*pag,
	int			sync_mode)
{
	int	error;

restart:
	error = 0;
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	if (!xfs_iflock_nowait(ip)) {
		if (!(sync_mode & SYNC_WAIT))
			goto out;
		xfs_iflock(ip);
	}

	if (is_bad_inode(VFS_I(ip)))
		goto reclaim;
	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
		xfs_iunpin_wait(ip);
		goto reclaim;
	}
	if (xfs_ipincount(ip)) {
		if (!(sync_mode & SYNC_WAIT)) {
			xfs_ifunlock(ip);
			goto out;
		}
		xfs_iunpin_wait(ip);
	}
	if (xfs_iflags_test(ip, XFS_ISTALE))
		goto reclaim;
	if (xfs_inode_clean(ip))
		goto reclaim;

	/*
	 * Now we have an inode that needs flushing.
	 *
	 * We do a nonblocking flush here even if we are doing a SYNC_WAIT
	 * reclaim as we can deadlock with inode cluster removal.
	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
	 * ip->i_lock, and we are doing the exact opposite here. As a result,
	 * doing a blocking xfs_itobp() to get the cluster buffer will result
	 * in an ABBA deadlock with xfs_ifree_cluster().
	 *
	 * As xfs_ifree_cluser() must gather all inodes that are active in the
	 * cache to mark them stale, if we hit this case we don't actually want
	 * to do IO here - we want the inode marked stale so we can simply
	 * reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
	 * just unlock the inode, back off and try again. Hopefully the next
	 * pass through will see the stale flag set on the inode.
	 */
	error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
	if (sync_mode & SYNC_WAIT) {
		if (error == EAGAIN) {
			xfs_iunlock(ip, XFS_ILOCK_EXCL);
			/* backoff longer than in xfs_ifree_cluster */
			delay(2);
			goto restart;
		}
		xfs_iflock(ip);
		goto reclaim;
	}

	/*
	 * When we have to flush an inode but don't have SYNC_WAIT set, we
	 * flush the inode out using a delwri buffer and wait for the next
	 * call into reclaim to find it in a clean state instead of waiting for
	 * it now. We also don't return errors here - if the error is transient
	 * then the next reclaim pass will flush the inode, and if the error
	 * is permanent then the next sync reclaim will reclaim the inode and
	 * pass on the error.
	 */
	if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
		xfs_warn(ip->i_mount,
			"inode 0x%llx background reclaim flush failed with %d",
			(long long)ip->i_ino, error);
	}
out:
	xfs_iflags_clear(ip, XFS_IRECLAIM);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	/*
	 * We could return EAGAIN here to make reclaim rescan the inode tree in
	 * a short while. However, this just burns CPU time scanning the tree
	 * waiting for IO to complete and xfssyncd never goes back to the idle
	 * state. Instead, return 0 to let the next scheduled background reclaim
	 * attempt to reclaim the inode again.
	 */
	return 0;

reclaim:
	xfs_ifunlock(ip);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	XFS_STATS_INC(xs_ig_reclaims);
	/*
	 * Remove the inode from the per-AG radix tree.
	 *
	 * Because radix_tree_delete won't complain even if the item was never
	 * added to the tree assert that it's been there before to catch
	 * problems with the inode life time early on.
	 */
	spin_lock(&pag->pag_ici_lock);
	if (!radix_tree_delete(&pag->pag_ici_root,
				XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
		ASSERT(0);
	__xfs_inode_clear_reclaim(pag, ip);
	spin_unlock(&pag->pag_ici_lock);

	/*
	 * Here we do an (almost) spurious inode lock in order to coordinate
	 * with inode cache radix tree lookups.  This is because the lookup
	 * can reference the inodes in the cache without taking references.
	 *
	 * We make that OK here by ensuring that we wait until the inode is
	 * unlocked after the lookup before we go ahead and free it.  We get
	 * both the ilock and the iolock because the code may need to drop the
	 * ilock one but will still hold the iolock.
	 */
	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_qm_dqdetach(ip);
	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);

	xfs_inode_free(ip);
	return error;

}

/*
 * Walk the AGs and reclaim the inodes in them. Even if the filesystem is
 * corrupted, we still want to try to reclaim all the inodes. If we don't,
 * then a shut down during filesystem unmount reclaim walk leak all the
 * unreclaimed inodes.
 */
int
xfs_reclaim_inodes_ag(
	struct xfs_mount	*mp,
	int			flags,
	int			*nr_to_scan)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;
	int			trylock = flags & SYNC_TRYLOCK;
	int			skipped;

restart:
	ag = 0;
	skipped = 0;
	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
		unsigned long	first_index = 0;
		int		done = 0;
		int		nr_found = 0;

		ag = pag->pag_agno + 1;

		if (trylock) {
			if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
				skipped++;
				xfs_perag_put(pag);
				continue;
			}
			first_index = pag->pag_ici_reclaim_cursor;
		} else
			mutex_lock(&pag->pag_ici_reclaim_lock);

		do {
			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
			int	i;

			rcu_read_lock();
			nr_found = radix_tree_gang_lookup_tag(
					&pag->pag_ici_root,
					(void **)batch, first_index,
					XFS_LOOKUP_BATCH,
					XFS_ICI_RECLAIM_TAG);
			if (!nr_found) {
				rcu_read_unlock();
				break;
			}

			/*
			 * Grab the inodes before we drop the lock. if we found
			 * nothing, nr == 0 and the loop will be skipped.
			 */
			for (i = 0; i < nr_found; i++) {
				struct xfs_inode *ip = batch[i];

				if (done || xfs_reclaim_inode_grab(ip, flags))
					batch[i] = NULL;

				/*
				 * Update the index for the next lookup. Catch
				 * overflows into the next AG range which can
				 * occur if we have inodes in the last block of
				 * the AG and we are currently pointing to the
				 * last inode.
				 *
				 * Because we may see inodes that are from the
				 * wrong AG due to RCU freeing and
				 * reallocation, only update the index if it
				 * lies in this AG. It was a race that lead us
				 * to see this inode, so another lookup from
				 * the same index will not find it again.
				 */
				if (XFS_INO_TO_AGNO(mp, ip->i_ino) !=
								pag->pag_agno)
					continue;
				first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
				if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
					done = 1;
			}

			/* unlock now we've grabbed the inodes. */
			rcu_read_unlock();

			for (i = 0; i < nr_found; i++) {
				if (!batch[i])
					continue;
				error = xfs_reclaim_inode(batch[i], pag, flags);
				if (error && last_error != EFSCORRUPTED)
					last_error = error;
			}

			*nr_to_scan -= XFS_LOOKUP_BATCH;

		} while (nr_found && !done && *nr_to_scan > 0);

		if (trylock && !done)
			pag->pag_ici_reclaim_cursor = first_index;
		else
			pag->pag_ici_reclaim_cursor = 0;
		mutex_unlock(&pag->pag_ici_reclaim_lock);
		xfs_perag_put(pag);
	}

	/*
	 * if we skipped any AG, and we still have scan count remaining, do
	 * another pass this time using blocking reclaim semantics (i.e
	 * waiting on the reclaim locks and ignoring the reclaim cursors). This
	 * ensure that when we get more reclaimers than AGs we block rather
	 * than spin trying to execute reclaim.
	 */
	if (trylock && skipped && *nr_to_scan > 0) {
		trylock = 0;
		goto restart;
	}
	return XFS_ERROR(last_error);
}

int
xfs_reclaim_inodes(
	xfs_mount_t	*mp,
	int		mode)
{
	int		nr_to_scan = INT_MAX;

	return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan);
}

/*
 * Shrinker infrastructure.
 */
static int
xfs_reclaim_inode_shrink(
	struct shrinker	*shrink,
	int		nr_to_scan,
	gfp_t		gfp_mask)
{
	struct xfs_mount *mp;
	struct xfs_perag *pag;
	xfs_agnumber_t	ag;
	int		reclaimable;

	mp = container_of(shrink, struct xfs_mount, m_inode_shrink);
	if (nr_to_scan) {
		if (!(gfp_mask & __GFP_FS))
			return -1;

		xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK, &nr_to_scan);
		/* terminate if we don't exhaust the scan */
		if (nr_to_scan > 0)
			return -1;
       }

	reclaimable = 0;
	ag = 0;
	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
		ag = pag->pag_agno + 1;
		reclaimable += pag->pag_ici_reclaimable;
		xfs_perag_put(pag);
	}
	return reclaimable;
}

void
xfs_inode_shrinker_register(
	struct xfs_mount	*mp)
{
	mp->m_inode_shrink.shrink = xfs_reclaim_inode_shrink;
	mp->m_inode_shrink.seeks = DEFAULT_SEEKS;
	register_shrinker(&mp->m_inode_shrink);
}

void
xfs_inode_shrinker_unregister(
	struct xfs_mount	*mp)
{
	unregister_shrinker(&mp->m_inode_shrink);
}