forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxfs_icache.c
1331 lines (1170 loc) · 33.9 KB
/
xfs_icache.c
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
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_inum.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_bmap_util.h"
#include <linux/kthread.h>
#include <linux/freezer.h>
STATIC void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp,
struct xfs_perag *pag, struct xfs_inode *ip);
/*
* Allocate and initialise an xfs_inode.
*/
struct xfs_inode *
xfs_inode_alloc(
struct xfs_mount *mp,
xfs_ino_t ino)
{
struct xfs_inode *ip;
/*
* if this didn't occur in transactions, we could use
* KM_MAYFAIL and return NULL here on ENOMEM. Set the
* code up to do this anyway.
*/
ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
if (!ip)
return NULL;
if (inode_init_always(mp->m_super, VFS_I(ip))) {
kmem_zone_free(xfs_inode_zone, ip);
return NULL;
}
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(!xfs_isiflocked(ip));
ASSERT(ip->i_ino == 0);
mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
/* initialise the xfs inode */
ip->i_ino = ino;
ip->i_mount = mp;
memset(&ip->i_imap, 0, sizeof(struct xfs_imap));
ip->i_afp = NULL;
memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
ip->i_flags = 0;
ip->i_delayed_blks = 0;
memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
return ip;
}
STATIC void
xfs_inode_free_callback(
struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
struct xfs_inode *ip = XFS_I(inode);
kmem_zone_free(xfs_inode_zone, ip);
}
void
xfs_inode_free(
struct xfs_inode *ip)
{
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
xfs_idestroy_fork(ip, XFS_DATA_FORK);
break;
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
if (ip->i_itemp) {
ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL));
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
/*
* Because we use RCU freeing we need to ensure the inode always
* appears to be reclaimed with an invalid inode number when in the
* free state. The ip->i_flags_lock provides the barrier against lookup
* races.
*/
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!xfs_isiflocked(ip));
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}
/*
* Check the validity of the inode we just found it the cache
*/
static int
xfs_iget_cache_hit(
struct xfs_perag *pag,
struct xfs_inode *ip,
xfs_ino_t ino,
int flags,
int lock_flags) __releases(RCU)
{
struct inode *inode = VFS_I(ip);
struct xfs_mount *mp = ip->i_mount;
int error;
/*
* check for re-use of an inode within an RCU grace period due to the
* radix tree nodes not being updated yet. We monitor for this by
* setting the inode number to zero before freeing the inode structure.
* If the inode has been reallocated and set up, then the inode number
* will not match, so check for that, too.
*/
spin_lock(&ip->i_flags_lock);
if (ip->i_ino != ino) {
trace_xfs_iget_skip(ip);
XFS_STATS_INC(xs_ig_frecycle);
error = EAGAIN;
goto out_error;
}
/*
* If we are racing with another cache hit that is currently
* instantiating this inode or currently recycling it out of
* reclaimabe state, wait for the initialisation to complete
* before continuing.
*
* XXX(hch): eventually we should do something equivalent to
* wait_on_inode to wait for these flags to be cleared
* instead of polling for it.
*/
if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) {
trace_xfs_iget_skip(ip);
XFS_STATS_INC(xs_ig_frecycle);
error = EAGAIN;
goto out_error;
}
/*
* If lookup is racing with unlink return an error immediately.
*/
if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
error = ENOENT;
goto out_error;
}
/*
* If IRECLAIMABLE is set, we've torn down the VFS inode already.
* Need to carefully get it back into useable state.
*/
if (ip->i_flags & XFS_IRECLAIMABLE) {
trace_xfs_iget_reclaim(ip);
/*
* We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
* from stomping over us while we recycle the inode. We can't
* clear the radix tree reclaimable tag yet as it requires
* pag_ici_lock to be held exclusive.
*/
ip->i_flags |= XFS_IRECLAIM;
spin_unlock(&ip->i_flags_lock);
rcu_read_unlock();
error = -inode_init_always(mp->m_super, inode);
if (error) {
/*
* Re-initializing the inode failed, and we are in deep
* trouble. Try to re-add it to the reclaim list.
*/
rcu_read_lock();
spin_lock(&ip->i_flags_lock);
ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
trace_xfs_iget_reclaim_fail(ip);
goto out_error;
}
spin_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
/*
* Clear the per-lifetime state in the inode as we are now
* effectively a new inode and need to return to the initial
* state before reuse occurs.
*/
ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
ip->i_flags |= XFS_INEW;
__xfs_inode_clear_reclaim_tag(mp, pag, ip);
inode->i_state = I_NEW;
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
spin_unlock(&ip->i_flags_lock);
spin_unlock(&pag->pag_ici_lock);
} else {
/* If the VFS inode is being torn down, pause and try again. */
if (!igrab(inode)) {
trace_xfs_iget_skip(ip);
error = EAGAIN;
goto out_error;
}
/* We've got a live one. */
spin_unlock(&ip->i_flags_lock);
rcu_read_unlock();
trace_xfs_iget_hit(ip);
}
if (lock_flags != 0)
xfs_ilock(ip, lock_flags);
xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
XFS_STATS_INC(xs_ig_found);
return 0;
out_error:
spin_unlock(&ip->i_flags_lock);
rcu_read_unlock();
return error;
}
static int
xfs_iget_cache_miss(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_trans_t *tp,
xfs_ino_t ino,
struct xfs_inode **ipp,
int flags,
int lock_flags)
{
struct xfs_inode *ip;
int error;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
int iflags;
ip = xfs_inode_alloc(mp, ino);
if (!ip)
return ENOMEM;
error = xfs_iread(mp, tp, ip, flags);
if (error)
goto out_destroy;
trace_xfs_iget_miss(ip);
if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = ENOENT;
goto out_destroy;
}
/*
* Preload the radix tree so we can insert safely under the
* write spinlock. Note that we cannot sleep inside the preload
* region. Since we can be called from transaction context, don't
* recurse into the file system.
*/
if (radix_tree_preload(GFP_NOFS)) {
error = EAGAIN;
goto out_destroy;
}
/*
* Because the inode hasn't been added to the radix-tree yet it can't
* be found by another thread, so we can do the non-sleeping lock here.
*/
if (lock_flags) {
if (!xfs_ilock_nowait(ip, lock_flags))
BUG();
}
/*
* These values must be set before inserting the inode into the radix
* tree as the moment it is inserted a concurrent lookup (allowed by the
* RCU locking mechanism) can find it and that lookup must see that this
* is an inode currently under construction (i.e. that XFS_INEW is set).
* The ip->i_flags_lock that protects the XFS_INEW flag forms the
* memory barrier that ensures this detection works correctly at lookup
* time.
*/
iflags = XFS_INEW;
if (flags & XFS_IGET_DONTCACHE)
iflags |= XFS_IDONTCACHE;
ip->i_udquot = NULL;
ip->i_gdquot = NULL;
ip->i_pdquot = NULL;
xfs_iflags_set(ip, iflags);
/* insert the new inode */
spin_lock(&pag->pag_ici_lock);
error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
if (unlikely(error)) {
WARN_ON(error != -EEXIST);
XFS_STATS_INC(xs_ig_dup);
error = EAGAIN;
goto out_preload_end;
}
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
*ipp = ip;
return 0;
out_preload_end:
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
/*
* Look up an inode by number in the given file system.
* The inode is looked up in the cache held in each AG.
* If the inode is found in the cache, initialise the vfs inode
* if necessary.
*
* If it is not in core, read it in from the file system's device,
* add it to the cache and initialise the vfs inode.
*
* The inode is locked according to the value of the lock_flags parameter.
* This flag parameter indicates how and if the inode's IO lock and inode lock
* should be taken.
*
* mp -- the mount point structure for the current file system. It points
* to the inode hash table.
* tp -- a pointer to the current transaction if there is one. This is
* simply passed through to the xfs_iread() call.
* ino -- the number of the inode desired. This is the unique identifier
* within the file system for the inode being requested.
* lock_flags -- flags indicating how to lock the inode. See the comment
* for xfs_ilock() for a list of valid values.
*/
int
xfs_iget(
xfs_mount_t *mp,
xfs_trans_t *tp,
xfs_ino_t ino,
uint flags,
uint lock_flags,
xfs_inode_t **ipp)
{
xfs_inode_t *ip;
int error;
xfs_perag_t *pag;
xfs_agino_t agino;
/*
* xfs_reclaim_inode() uses the ILOCK to ensure an inode
* doesn't get freed while it's being referenced during a
* radix tree traversal here. It assumes this function
* aqcuires only the ILOCK (and therefore it has no need to
* involve the IOLOCK in this synchronization).
*/
ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
/* reject inode numbers outside existing AGs */
if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
return EINVAL;
/* get the perag structure and ensure that it's inode capable */
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
agino = XFS_INO_TO_AGINO(mp, ino);
again:
error = 0;
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root, agino);
if (ip) {
error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
if (error)
goto out_error_or_again;
} else {
rcu_read_unlock();
XFS_STATS_INC(xs_ig_missed);
error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
flags, lock_flags);
if (error)
goto out_error_or_again;
}
xfs_perag_put(pag);
*ipp = ip;
/*
* If we have a real type for an on-disk inode, we can set ops(&unlock)
* now. If it's a new inode being created, xfs_ialloc will handle it.
*/
if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
xfs_setup_inode(ip);
return 0;
out_error_or_again:
if (error == EAGAIN) {
delay(1);
goto again;
}
xfs_perag_put(pag);
return error;
}
/*
* 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;
/* 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,
void *args),
int flags,
void *args,
int tag)
{
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();
if (tag == -1)
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void **)batch, first_index,
XFS_LOOKUP_BATCH);
else
nr_found = radix_tree_gang_lookup_tag(
&pag->pag_ici_root,
(void **) batch, first_index,
XFS_LOOKUP_BATCH, 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_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, args);
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;
cond_resched();
} while (nr_found && !done);
if (skipped) {
delay(1);
goto restart;
}
return last_error;
}
/*
* Background scanning to trim post-EOF preallocated space. This is queued
* based on the 'speculative_prealloc_lifetime' tunable (5m by default).
*/
STATIC void
xfs_queue_eofblocks(
struct xfs_mount *mp)
{
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_EOFBLOCKS_TAG))
queue_delayed_work(mp->m_eofblocks_workqueue,
&mp->m_eofblocks_work,
msecs_to_jiffies(xfs_eofb_secs * 1000));
rcu_read_unlock();
}
void
xfs_eofblocks_worker(
struct work_struct *work)
{
struct xfs_mount *mp = container_of(to_delayed_work(work),
struct xfs_mount, m_eofblocks_work);
xfs_icache_free_eofblocks(mp, NULL);
xfs_queue_eofblocks(mp);
}
int
xfs_inode_ag_iterator(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags,
void *args),
int flags,
void *args)
{
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, args, -1);
xfs_perag_put(pag);
if (error) {
last_error = error;
if (error == EFSCORRUPTED)
break;
}
}
return XFS_ERROR(last_error);
}
int
xfs_inode_ag_iterator_tag(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags,
void *args),
int flags,
void *args,
int tag)
{
struct xfs_perag *pag;
int error = 0;
int last_error = 0;
xfs_agnumber_t ag;
ag = 0;
while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
ag = pag->pag_agno + 1;
error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
xfs_perag_put(pag);
if (error) {
last_error = error;
if (error == EFSCORRUPTED)
break;
}
}
return XFS_ERROR(last_error);
}
/*
* Queue a new inode reclaim pass if there are reclaimable inodes and there
* isn't a reclaim pass already in progress. By default it runs every 5s based
* on the xfs periodic sync default of 30s. Perhaps this should have it's own
* tunable, but that can be done if this method proves to be ineffective or too
* aggressive.
*/
static void
xfs_reclaim_work_queue(
struct xfs_mount *mp)
{
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
}
rcu_read_unlock();
}
/*
* This is a fast pass over the inode cache to try to get reclaim moving on as
* many inodes as possible in a short period of time. It kicks itself every few
* seconds, as well as being kicked by the inode cache shrinker when memory
* goes low. It scans as quickly as possible avoiding locked inodes or those
* already being flushed, and once done schedules a future pass.
*/
void
xfs_reclaim_worker(
struct work_struct *work)
{
struct xfs_mount *mp = container_of(to_delayed_work(work),
struct xfs_mount, m_reclaim_work);
xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
xfs_reclaim_work_queue(mp);
}
static 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);
/* schedule periodic background inode reclaim */
xfs_reclaim_work_queue(ip->i_mount);
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_);
}
}
STATIC 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;
/*
* If we are asked for non-blocking operation, do unlocked checks to
* see if the inode already is being flushed or in reclaim to avoid
* lock traffic.
*/
if ((flags & SYNC_TRYLOCK) &&
__xfs_iflags_test(ip, XFS_IFLOCK | 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. The following
* table lists the inode states and the reclaim actions necessary:
*
* 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, async - requeue
* dirty, sync 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* 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.
*
* Note that because the inode is flushed delayed write by AIL pushing, 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 the AIL first before trying to reclaim inodes to
* minimise the amount of time spent waiting. For background relaim, we only
* bother to reclaim clean inodes anyway.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, async => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, async => requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
struct xfs_buf *bp = NULL;
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 (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
xfs_iflush_abort(ip, false);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
/*
* Never flush out dirty data during non-blocking reclaim, as it would
* just contend with AIL pushing trying to do the same job.
*/
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
/*
* Now we have an inode that needs flushing.
*
* Note that xfs_iflush will never block on the inode buffer lock, as
* 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_imap_to_bp() to get the cluster buffer would
* 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 here, 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, &bp);
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
if (!error) {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
xfs_iflock(ip);
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.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
return error;
out_ifunlock:
xfs_ifunlock(ip);
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);