summaryrefslogtreecommitdiff
path: root/fs/fscache/object.c
blob: 3b0712213993de45941e141b033be0587b51c80c (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
/* FS-Cache object state machine handler
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * 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; either version
 * 2 of the License, or (at your option) any later version.
 *
 * See Documentation/filesystems/caching/object.txt for a description of the
 * object state machine and the in-kernel representations.
 */

#define FSCACHE_DEBUG_LEVEL COOKIE
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/prefetch.h>
#include "internal.h"

static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *, int);
static const struct fscache_state *fscache_kill_dependents(struct fscache_object *, int);
static const struct fscache_state *fscache_drop_object(struct fscache_object *, int);
static const struct fscache_state *fscache_initialise_object(struct fscache_object *, int);
static const struct fscache_state *fscache_invalidate_object(struct fscache_object *, int);
static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *, int);
static const struct fscache_state *fscache_kill_object(struct fscache_object *, int);
static const struct fscache_state *fscache_lookup_failure(struct fscache_object *, int);
static const struct fscache_state *fscache_look_up_object(struct fscache_object *, int);
static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
static const struct fscache_state *fscache_update_object(struct fscache_object *, int);

#define __STATE_NAME(n) fscache_osm_##n
#define STATE(n) (&__STATE_NAME(n))

/*
 * Define a work state.  Work states are execution states.  No event processing
 * is performed by them.  The function attached to a work state returns a
 * pointer indicating the next state to which the state machine should
 * transition.  Returning NO_TRANSIT repeats the current state, but goes back
 * to the scheduler first.
 */
#define WORK_STATE(n, sn, f) \
	const struct fscache_state __STATE_NAME(n) = {			\
		.name = #n,						\
		.short_name = sn,					\
		.work = f						\
	}

/*
 * Returns from work states.
 */
#define transit_to(state) ({ prefetch(&STATE(state)->work); STATE(state); })

#define NO_TRANSIT ((struct fscache_state *)NULL)

/*
 * Define a wait state.  Wait states are event processing states.  No execution
 * is performed by them.  Wait states are just tables of "if event X occurs,
 * clear it and transition to state Y".  The dispatcher returns to the
 * scheduler if none of the events in which the wait state has an interest are
 * currently pending.
 */
#define WAIT_STATE(n, sn, ...) \
	const struct fscache_state __STATE_NAME(n) = {			\
		.name = #n,						\
		.short_name = sn,					\
		.work = NULL,						\
		.transitions = { __VA_ARGS__, { 0, NULL } }		\
	}

#define TRANSIT_TO(state, emask) \
	{ .events = (emask), .transit_to = STATE(state) }

/*
 * The object state machine.
 */
static WORK_STATE(INIT_OBJECT,		"INIT", fscache_initialise_object);
static WORK_STATE(PARENT_READY,		"PRDY", fscache_parent_ready);
static WORK_STATE(ABORT_INIT,		"ABRT", fscache_abort_initialisation);
static WORK_STATE(LOOK_UP_OBJECT,	"LOOK", fscache_look_up_object);
static WORK_STATE(CREATE_OBJECT,	"CRTO", fscache_look_up_object);
static WORK_STATE(OBJECT_AVAILABLE,	"AVBL", fscache_object_available);
static WORK_STATE(JUMPSTART_DEPS,	"JUMP", fscache_jumpstart_dependents);

static WORK_STATE(INVALIDATE_OBJECT,	"INVL", fscache_invalidate_object);
static WORK_STATE(UPDATE_OBJECT,	"UPDT", fscache_update_object);

static WORK_STATE(LOOKUP_FAILURE,	"LCFL", fscache_lookup_failure);
static WORK_STATE(KILL_OBJECT,		"KILL", fscache_kill_object);
static WORK_STATE(KILL_DEPENDENTS,	"KDEP", fscache_kill_dependents);
static WORK_STATE(DROP_OBJECT,		"DROP", fscache_drop_object);
static WORK_STATE(OBJECT_DEAD,		"DEAD", (void*)2UL);

static WAIT_STATE(WAIT_FOR_INIT,	"?INI",
		  TRANSIT_TO(INIT_OBJECT,	1 << FSCACHE_OBJECT_EV_NEW_CHILD));

static WAIT_STATE(WAIT_FOR_PARENT,	"?PRN",
		  TRANSIT_TO(PARENT_READY,	1 << FSCACHE_OBJECT_EV_PARENT_READY));

static WAIT_STATE(WAIT_FOR_CMD,		"?CMD",
		  TRANSIT_TO(INVALIDATE_OBJECT,	1 << FSCACHE_OBJECT_EV_INVALIDATE),
		  TRANSIT_TO(UPDATE_OBJECT,	1 << FSCACHE_OBJECT_EV_UPDATE),
		  TRANSIT_TO(JUMPSTART_DEPS,	1 << FSCACHE_OBJECT_EV_NEW_CHILD));

static WAIT_STATE(WAIT_FOR_CLEARANCE,	"?CLR",
		  TRANSIT_TO(KILL_OBJECT,	1 << FSCACHE_OBJECT_EV_CLEARED));

/*
 * Out-of-band event transition tables.  These are for handling unexpected
 * events, such as an I/O error.  If an OOB event occurs, the state machine
 * clears and disables the event and forces a transition to the nominated work
 * state (acurrently executing work states will complete first).
 *
 * In such a situation, object->state remembers the state the machine should
 * have been in/gone to and returning NO_TRANSIT returns to that.
 */
static const struct fscache_transition fscache_osm_init_oob[] = {
	   TRANSIT_TO(ABORT_INIT,
		      (1 << FSCACHE_OBJECT_EV_ERROR) |
		      (1 << FSCACHE_OBJECT_EV_KILL)),
	   { 0, NULL }
};

static const struct fscache_transition fscache_osm_lookup_oob[] = {
	   TRANSIT_TO(LOOKUP_FAILURE,
		      (1 << FSCACHE_OBJECT_EV_ERROR) |
		      (1 << FSCACHE_OBJECT_EV_KILL)),
	   { 0, NULL }
};

static const struct fscache_transition fscache_osm_run_oob[] = {
	   TRANSIT_TO(KILL_OBJECT,
		      (1 << FSCACHE_OBJECT_EV_ERROR) |
		      (1 << FSCACHE_OBJECT_EV_KILL)),
	   { 0, NULL }
};

static int  fscache_get_object(struct fscache_object *);
static void fscache_put_object(struct fscache_object *);
static bool fscache_enqueue_dependents(struct fscache_object *, int);
static void fscache_dequeue_object(struct fscache_object *);

/*
 * we need to notify the parent when an op completes that we had outstanding
 * upon it
 */
static inline void fscache_done_parent_op(struct fscache_object *object)
{
	struct fscache_object *parent = object->parent;

	_enter("OBJ%x {OBJ%x,%x}",
	       object->debug_id, parent->debug_id, parent->n_ops);

	spin_lock_nested(&parent->lock, 1);
	parent->n_obj_ops--;
	parent->n_ops--;
	if (parent->n_ops == 0)
		fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
	spin_unlock(&parent->lock);
}

/*
 * Object state machine dispatcher.
 */
static void fscache_object_sm_dispatcher(struct fscache_object *object)
{
	const struct fscache_transition *t;
	const struct fscache_state *state, *new_state;
	unsigned long events, event_mask;
	int event = -1;

	ASSERT(object != NULL);

	_enter("{OBJ%x,%s,%lx}",
	       object->debug_id, object->state->name, object->events);

	event_mask = object->event_mask;
restart:
	object->event_mask = 0; /* Mask normal event handling */
	state = object->state;
restart_masked:
	events = object->events;

	/* Handle any out-of-band events (typically an error) */
	if (events & object->oob_event_mask) {
		_debug("{OBJ%x} oob %lx",
		       object->debug_id, events & object->oob_event_mask);
		for (t = object->oob_table; t->events; t++) {
			if (events & t->events) {
				state = t->transit_to;
				ASSERT(state->work != NULL);
				event = fls(events & t->events) - 1;
				__clear_bit(event, &object->oob_event_mask);
				clear_bit(event, &object->events);
				goto execute_work_state;
			}
		}
	}

	/* Wait states are just transition tables */
	if (!state->work) {
		if (events & event_mask) {
			for (t = state->transitions; t->events; t++) {
				if (events & t->events) {
					new_state = t->transit_to;
					event = fls(events & t->events) - 1;
					clear_bit(event, &object->events);
					_debug("{OBJ%x} ev %d: %s -> %s",
					       object->debug_id, event,
					       state->name, new_state->name);
					object->state = state = new_state;
					goto execute_work_state;
				}
			}

			/* The event mask didn't include all the tabled bits */
			BUG();
		}
		/* Randomly woke up */
		goto unmask_events;
	}

execute_work_state:
	_debug("{OBJ%x} exec %s", object->debug_id, state->name);

	new_state = state->work(object, event);
	event = -1;
	if (new_state == NO_TRANSIT) {
		_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
		fscache_enqueue_object(object);
		event_mask = object->oob_event_mask;
		goto unmask_events;
	}

	_debug("{OBJ%x} %s -> %s",
	       object->debug_id, state->name, new_state->name);
	object->state = state = new_state;

	if (state->work) {
		if (unlikely(state->work == ((void *)2UL))) {
			_leave(" [dead]");
			return;
		}
		goto restart_masked;
	}

	/* Transited to wait state */
	event_mask = object->oob_event_mask;
	for (t = state->transitions; t->events; t++)
		event_mask |= t->events;

unmask_events:
	object->event_mask = event_mask;
	smp_mb();
	events = object->events;
	if (events & event_mask)
		goto restart;
	_leave(" [msk %lx]", event_mask);
}

/*
 * execute an object
 */
static void fscache_object_work_func(struct work_struct *work)
{
	struct fscache_object *object =
		container_of(work, struct fscache_object, work);
	unsigned long start;

	_enter("{OBJ%x}", object->debug_id);

	start = jiffies;
	fscache_object_sm_dispatcher(object);
	fscache_hist(fscache_objs_histogram, start);
	fscache_put_object(object);
}

/**
 * fscache_object_init - Initialise a cache object description
 * @object: Object description
 * @cookie: Cookie object will be attached to
 * @cache: Cache in which backing object will be found
 *
 * Initialise a cache object description to its basic values.
 *
 * See Documentation/filesystems/caching/backend-api.txt for a complete
 * description.
 */
void fscache_object_init(struct fscache_object *object,
			 struct fscache_cookie *cookie,
			 struct fscache_cache *cache)
{
	const struct fscache_transition *t;

	atomic_inc(&cache->object_count);

	object->state = STATE(WAIT_FOR_INIT);
	object->oob_table = fscache_osm_init_oob;
	object->flags = 1 << FSCACHE_OBJECT_IS_LIVE;
	spin_lock_init(&object->lock);
	INIT_LIST_HEAD(&object->cache_link);
	INIT_HLIST_NODE(&object->cookie_link);
	INIT_WORK(&object->work, fscache_object_work_func);
	INIT_LIST_HEAD(&object->dependents);
	INIT_LIST_HEAD(&object->dep_link);
	INIT_LIST_HEAD(&object->pending_ops);
	object->n_children = 0;
	object->n_ops = object->n_in_progress = object->n_exclusive = 0;
	object->events = 0;
	object->store_limit = 0;
	object->store_limit_l = 0;
	object->cache = cache;
	object->cookie = cookie;
	object->parent = NULL;

	object->oob_event_mask = 0;
	for (t = object->oob_table; t->events; t++)
		object->oob_event_mask |= t->events;
	object->event_mask = object->oob_event_mask;
	for (t = object->state->transitions; t->events; t++)
		object->event_mask |= t->events;
}
EXPORT_SYMBOL(fscache_object_init);

/*
 * Abort object initialisation before we start it.
 */
static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *object,
								int event)
{
	_enter("{OBJ%x},%d", object->debug_id, event);

	object->oob_event_mask = 0;
	fscache_dequeue_object(object);
	return transit_to(KILL_OBJECT);
}

/*
 * initialise an object
 * - check the specified object's parent to see if we can make use of it
 *   immediately to do a creation
 * - we may need to start the process of creating a parent and we need to wait
 *   for the parent's lookup and creation to complete if it's not there yet
 */
static const struct fscache_state *fscache_initialise_object(struct fscache_object *object,
							     int event)
{
	struct fscache_object *parent;
	bool success;

	_enter("{OBJ%x},%d", object->debug_id, event);

	ASSERT(list_empty(&object->dep_link));

	parent = object->parent;
	if (!parent) {
		_leave(" [no parent]");
		return transit_to(DROP_OBJECT);
	}

	_debug("parent: %s of:%lx", parent->state->name, parent->flags);

	if (fscache_object_is_dying(parent)) {
		_leave(" [bad parent]");
		return transit_to(DROP_OBJECT);
	}

	if (fscache_object_is_available(parent)) {
		_leave(" [ready]");
		return transit_to(PARENT_READY);
	}

	_debug("wait");

	spin_lock(&parent->lock);
	fscache_stat(&fscache_n_cop_grab_object);
	success = false;
	if (fscache_object_is_live(parent) &&
	    object->cache->ops->grab_object(object)) {
		list_add(&object->dep_link, &parent->dependents);
		success = true;
	}
	fscache_stat_d(&fscache_n_cop_grab_object);
	spin_unlock(&parent->lock);
	if (!success) {
		_leave(" [grab failed]");
		return transit_to(DROP_OBJECT);
	}

	/* fscache_acquire_non_index_cookie() uses this
	 * to wake the chain up */
	fscache_raise_event(parent, FSCACHE_OBJECT_EV_NEW_CHILD);
	_leave(" [wait]");
	return transit_to(WAIT_FOR_PARENT);
}

/*
 * Once the parent object is ready, we should kick off our lookup op.
 */
static const struct fscache_state *fscache_parent_ready(struct fscache_object *object,
							int event)
{
	struct fscache_object *parent = object->parent;

	_enter("{OBJ%x},%d", object->debug_id, event);

	ASSERT(parent != NULL);

	spin_lock(&parent->lock);
	parent->n_ops++;
	parent->n_obj_ops++;
	object->lookup_jif = jiffies;
	spin_unlock(&parent->lock);

	_leave("");
	return transit_to(LOOK_UP_OBJECT);
}

/*
 * look an object up in the cache from which it was allocated
 * - we hold an "access lock" on the parent object, so the parent object cannot
 *   be withdrawn by either party till we've finished
 */
static const struct fscache_state *fscache_look_up_object(struct fscache_object *object,
							  int event)
{
	struct fscache_cookie *cookie = object->cookie;
	struct fscache_object *parent = object->parent;
	int ret;

	_enter("{OBJ%x},%d", object->debug_id, event);

	object->oob_table = fscache_osm_lookup_oob;

	ASSERT(parent != NULL);
	ASSERTCMP(parent->n_ops, >, 0);
	ASSERTCMP(parent->n_obj_ops, >, 0);

	/* make sure the parent is still available */
	ASSERT(fscache_object_is_available(parent));

	if (fscache_object_is_dying(parent) ||
	    test_bit(FSCACHE_IOERROR, &object->cache->flags) ||
	    !fscache_use_cookie(object)) {
		_leave(" [unavailable]");
		return transit_to(LOOKUP_FAILURE);
	}

	_debug("LOOKUP \"%s\" in \"%s\"",
	       cookie->def->name, object->cache->tag->name);

	fscache_stat(&fscache_n_object_lookups);
	fscache_stat(&fscache_n_cop_lookup_object);
	ret = object->cache->ops->lookup_object(object);
	fscache_stat_d(&fscache_n_cop_lookup_object);

	fscache_unuse_cookie(object);

	if (ret == -ETIMEDOUT) {
		/* probably stuck behind another object, so move this one to
		 * the back of the queue */
		fscache_stat(&fscache_n_object_lookups_timed_out);
		_leave(" [timeout]");
		return NO_TRANSIT;
	}

	if (ret < 0) {
		_leave(" [error]");
		return transit_to(LOOKUP_FAILURE);
	}

	_leave(" [ok]");
	return transit_to(OBJECT_AVAILABLE);
}

/**
 * fscache_object_lookup_negative - Note negative cookie lookup
 * @object: Object pointing to cookie to mark
 *
 * Note negative lookup, permitting those waiting to read data from an already
 * existing backing object to continue as there's no data for them to read.
 */
void fscache_object_lookup_negative(struct fscache_object *object)
{
	struct fscache_cookie *cookie = object->cookie;

	_enter("{OBJ%x,%s}", object->debug_id, object->state->name);

	if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
		fscache_stat(&fscache_n_object_lookups_negative);

		/* Allow write requests to begin stacking up and read requests to begin
		 * returning ENODATA.
		 */
		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);

		_debug("wake up lookup %p", &cookie->flags);
		clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
	}
	_leave("");
}
EXPORT_SYMBOL(fscache_object_lookup_negative);

/**
 * fscache_obtained_object - Note successful object lookup or creation
 * @object: Object pointing to cookie to mark
 *
 * Note successful lookup and/or creation, permitting those waiting to write
 * data to a backing object to continue.
 *
 * Note that after calling this, an object's cookie may be relinquished by the
 * netfs, and so must be accessed with object lock held.
 */
void fscache_obtained_object(struct fscache_object *object)
{
	struct fscache_cookie *cookie = object->cookie;

	_enter("{OBJ%x,%s}", object->debug_id, object->state->name);

	/* if we were still looking up, then we must have a positive lookup
	 * result, in which case there may be data available */
	if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
		fscache_stat(&fscache_n_object_lookups_positive);

		/* We do (presumably) have data */
		clear_bit_unlock(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);

		/* Allow write requests to begin stacking up and read requests
		 * to begin shovelling data.
		 */
		clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
	} else {
		fscache_stat(&fscache_n_object_created);
	}

	set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags);
	_leave("");
}
EXPORT_SYMBOL(fscache_obtained_object);

/*
 * handle an object that has just become available
 */
static const struct fscache_state *fscache_object_available(struct fscache_object *object,
							    int event)
{
	_enter("{OBJ%x},%d", object->debug_id, event);

	object->oob_table = fscache_osm_run_oob;

	spin_lock(&object->lock);

	fscache_done_parent_op(object);
	if (object->n_in_progress == 0) {
		if (object->n_ops > 0) {
			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
			fscache_start_operations(object);
		} else {
			ASSERT(list_empty(&object->pending_ops));
		}
	}
	spin_unlock(&object->lock);

	fscache_stat(&fscache_n_cop_lookup_complete);
	object->cache->ops->lookup_complete(object);
	fscache_stat_d(&fscache_n_cop_lookup_complete);

	fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif);
	fscache_stat(&fscache_n_object_avail);

	_leave("");
	return transit_to(JUMPSTART_DEPS);
}

/*
 * Wake up this object's dependent objects now that we've become available.
 */
static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *object,
								int event)
{
	_enter("{OBJ%x},%d", object->debug_id, event);

	if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_PARENT_READY))
		return NO_TRANSIT; /* Not finished; requeue */
	return transit_to(WAIT_FOR_CMD);
}

/*
 * Handle lookup or creation failute.
 */
static const struct fscache_state *fscache_lookup_failure(struct fscache_object *object,
							  int event)
{
	struct fscache_cookie *cookie;

	_enter("{OBJ%x},%d", object->debug_id, event);

	object->oob_event_mask = 0;

	fscache_stat(&fscache_n_cop_lookup_complete);
	object->cache->ops->lookup_complete(object);
	fscache_stat_d(&fscache_n_cop_lookup_complete);

	cookie = object->cookie;
	set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);

	fscache_done_parent_op(object);
	return transit_to(KILL_OBJECT);
}

/*
 * Wait for completion of all active operations on this object and the death of
 * all child objects of this object.
 */
static const struct fscache_state *fscache_kill_object(struct fscache_object *object,
						       int event)
{
	_enter("{OBJ%x,%d,%d},%d",
	       object->debug_id, object->n_ops, object->n_children, event);

	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
	object->oob_event_mask = 0;

	if (list_empty(&object->dependents) &&
	    object->n_ops == 0 &&
	    object->n_children == 0)
		return transit_to(DROP_OBJECT);

	if (object->n_in_progress == 0) {
		spin_lock(&object->lock);
		if (object->n_ops > 0 && object->n_in_progress == 0)
			fscache_start_operations(object);
		spin_unlock(&object->lock);
	}

	if (!list_empty(&object->dependents))
		return transit_to(KILL_DEPENDENTS);

	return transit_to(WAIT_FOR_CLEARANCE);
}

/*
 * Kill dependent objects.
 */
static const struct fscache_state *fscache_kill_dependents(struct fscache_object *object,
							   int event)
{
	_enter("{OBJ%x},%d", object->debug_id, event);

	if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_KILL))
		return NO_TRANSIT; /* Not finished */
	return transit_to(WAIT_FOR_CLEARANCE);
}

/*
 * Drop an object's attachments
 */
static const struct fscache_state *fscache_drop_object(struct fscache_object *object,
						       int event)
{
	struct fscache_object *parent = object->parent;
	struct fscache_cookie *cookie = object->cookie;
	struct fscache_cache *cache = object->cache;
	bool awaken = false;

	_enter("{OBJ%x,%d},%d", object->debug_id, object->n_children, event);

	ASSERT(cookie != NULL);
	ASSERT(!hlist_unhashed(&object->cookie_link));

	/* Make sure the cookie no longer points here and that the netfs isn't
	 * waiting for us.
	 */
	spin_lock(&cookie->lock);
	hlist_del_init(&object->cookie_link);
	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
		awaken = true;
	spin_unlock(&cookie->lock);

	if (awaken)
		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);

	/* Prevent a race with our last child, which has to signal EV_CLEARED
	 * before dropping our spinlock.
	 */
	spin_lock(&object->lock);
	spin_unlock(&object->lock);

	/* Discard from the cache's collection of objects */
	spin_lock(&cache->object_list_lock);
	list_del_init(&object->cache_link);
	spin_unlock(&cache->object_list_lock);

	fscache_stat(&fscache_n_cop_drop_object);
	cache->ops->drop_object(object);
	fscache_stat_d(&fscache_n_cop_drop_object);

	/* The parent object wants to know when all it dependents have gone */
	if (parent) {
		_debug("release parent OBJ%x {%d}",
		       parent->debug_id, parent->n_children);

		spin_lock(&parent->lock);
		parent->n_children--;
		if (parent->n_children == 0)
			fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
		spin_unlock(&parent->lock);
		object->parent = NULL;
	}

	/* this just shifts the object release to the work processor */
	fscache_put_object(object);
	fscache_stat(&fscache_n_object_dead);

	_leave("");
	return transit_to(OBJECT_DEAD);
}

/*
 * get a ref on an object
 */
static int fscache_get_object(struct fscache_object *object)
{
	int ret;

	fscache_stat(&fscache_n_cop_grab_object);
	ret = object->cache->ops->grab_object(object) ? 0 : -EAGAIN;
	fscache_stat_d(&fscache_n_cop_grab_object);
	return ret;
}

/*
 * Discard a ref on an object
 */
static void fscache_put_object(struct fscache_object *object)
{
	fscache_stat(&fscache_n_cop_put_object);
	object->cache->ops->put_object(object);
	fscache_stat_d(&fscache_n_cop_put_object);
}

/**
 * fscache_object_destroy - Note that a cache object is about to be destroyed
 * @object: The object to be destroyed
 *
 * Note the imminent destruction and deallocation of a cache object record.
 */
void fscache_object_destroy(struct fscache_object *object)
{
	fscache_objlist_remove(object);

	/* We can get rid of the cookie now */
	fscache_cookie_put(object->cookie);
	object->cookie = NULL;
}
EXPORT_SYMBOL(fscache_object_destroy);

/*
 * enqueue an object for metadata-type processing
 */
void fscache_enqueue_object(struct fscache_object *object)
{
	_enter("{OBJ%x}", object->debug_id);

	if (fscache_get_object(object) >= 0) {
		wait_queue_head_t *cong_wq =
			&get_cpu_var(fscache_object_cong_wait);

		if (queue_work(fscache_object_wq, &object->work)) {
			if (fscache_object_congested())
				wake_up(cong_wq);
		} else
			fscache_put_object(object);

		put_cpu_var(fscache_object_cong_wait);
	}
}

/**
 * fscache_object_sleep_till_congested - Sleep until object wq is congested
 * @timeoutp: Scheduler sleep timeout
 *
 * Allow an object handler to sleep until the object workqueue is congested.
 *
 * The caller must set up a wake up event before calling this and must have set
 * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
 * condition before calling this function as no test is made here.
 *
 * %true is returned if the object wq is congested, %false otherwise.
 */
bool fscache_object_sleep_till_congested(signed long *timeoutp)
{
	wait_queue_head_t *cong_wq = this_cpu_ptr(&fscache_object_cong_wait);
	DEFINE_WAIT(wait);

	if (fscache_object_congested())
		return true;

	add_wait_queue_exclusive(cong_wq, &wait);
	if (!fscache_object_congested())
		*timeoutp = schedule_timeout(*timeoutp);
	finish_wait(cong_wq, &wait);

	return fscache_object_congested();
}
EXPORT_SYMBOL_GPL(fscache_object_sleep_till_congested);

/*
 * Enqueue the dependents of an object for metadata-type processing.
 *
 * If we don't manage to finish the list before the scheduler wants to run
 * again then return false immediately.  We return true if the list was
 * cleared.
 */
static bool fscache_enqueue_dependents(struct fscache_object *object, int event)
{
	struct fscache_object *dep;
	bool ret = true;

	_enter("{OBJ%x}", object->debug_id);

	if (list_empty(&object->dependents))
		return true;

	spin_lock(&object->lock);

	while (!list_empty(&object->dependents)) {
		dep = list_entry(object->dependents.next,
				 struct fscache_object, dep_link);
		list_del_init(&dep->dep_link);

		fscache_raise_event(dep, event);
		fscache_put_object(dep);

		if (!list_empty(&object->dependents) && need_resched()) {
			ret = false;
			break;
		}
	}

	spin_unlock(&object->lock);
	return ret;
}

/*
 * remove an object from whatever queue it's waiting on
 */
static void fscache_dequeue_object(struct fscache_object *object)
{
	_enter("{OBJ%x}", object->debug_id);

	if (!list_empty(&object->dep_link)) {
		spin_lock(&object->parent->lock);
		list_del_init(&object->dep_link);
		spin_unlock(&object->parent->lock);
	}

	_leave("");
}

/**
 * fscache_check_aux - Ask the netfs whether an object on disk is still valid
 * @object: The object to ask about
 * @data: The auxiliary data for the object
 * @datalen: The size of the auxiliary data
 *
 * This function consults the netfs about the coherency state of an object.
 * The caller must be holding a ref on cookie->n_active (held by
 * fscache_look_up_object() on behalf of the cache backend during object lookup
 * and creation).
 */
enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
					const void *data, uint16_t datalen)
{
	enum fscache_checkaux result;

	if (!object->cookie->def->check_aux) {
		fscache_stat(&fscache_n_checkaux_none);
		return FSCACHE_CHECKAUX_OKAY;
	}

	result = object->cookie->def->check_aux(object->cookie->netfs_data,
						data, datalen);
	switch (result) {
		/* entry okay as is */
	case FSCACHE_CHECKAUX_OKAY:
		fscache_stat(&fscache_n_checkaux_okay);
		break;

		/* entry requires update */
	case FSCACHE_CHECKAUX_NEEDS_UPDATE:
		fscache_stat(&fscache_n_checkaux_update);
		break;

		/* entry requires deletion */
	case FSCACHE_CHECKAUX_OBSOLETE:
		fscache_stat(&fscache_n_checkaux_obsolete);
		break;

	default:
		BUG();
	}

	return result;
}
EXPORT_SYMBOL(fscache_check_aux);

/*
 * Asynchronously invalidate an object.
 */
static const struct fscache_state *_fscache_invalidate_object(struct fscache_object *object,
							      int event)
{
	struct fscache_operation *op;
	struct fscache_cookie *cookie = object->cookie;

	_enter("{OBJ%x},%d", object->debug_id, event);

	/* We're going to need the cookie.  If the cookie is not available then
	 * retire the object instead.
	 */
	if (!fscache_use_cookie(object)) {
		ASSERT(object->cookie->stores.rnode == NULL);
		set_bit(FSCACHE_COOKIE_RETIRED, &cookie->flags);
		_leave(" [no cookie]");
		return transit_to(KILL_OBJECT);
	}

	/* Reject any new read/write ops and abort any that are pending. */
	fscache_invalidate_writes(cookie);
	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
	fscache_cancel_all_ops(object);

	/* Now we have to wait for in-progress reads and writes */
	op = kzalloc(sizeof(*op), GFP_KERNEL);
	if (!op)
		goto nomem;

	fscache_operation_init(op, object->cache->ops->invalidate_object, NULL);
	op->flags = FSCACHE_OP_ASYNC |
		(1 << FSCACHE_OP_EXCLUSIVE) |
		(1 << FSCACHE_OP_UNUSE_COOKIE);

	spin_lock(&cookie->lock);
	if (fscache_submit_exclusive_op(object, op) < 0)
		goto submit_op_failed;
	spin_unlock(&cookie->lock);
	fscache_put_operation(op);

	/* Once we've completed the invalidation, we know there will be no data
	 * stored in the cache and thus we can reinstate the data-check-skip
	 * optimisation.
	 */
	set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);

	/* We can allow read and write requests to come in once again.  They'll
	 * queue up behind our exclusive invalidation operation.
	 */
	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
	_leave(" [ok]");
	return transit_to(UPDATE_OBJECT);

nomem:
	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
	fscache_unuse_cookie(object);
	_leave(" [ENOMEM]");
	return transit_to(KILL_OBJECT);

submit_op_failed:
	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
	spin_unlock(&cookie->lock);
	kfree(op);
	_leave(" [EIO]");
	return transit_to(KILL_OBJECT);
}

static const struct fscache_state *fscache_invalidate_object(struct fscache_object *object,
							     int event)
{
	const struct fscache_state *s;

	fscache_stat(&fscache_n_invalidates_run);
	fscache_stat(&fscache_n_cop_invalidate_object);
	s = _fscache_invalidate_object(object, event);
	fscache_stat_d(&fscache_n_cop_invalidate_object);
	return s;
}

/*
 * Asynchronously update an object.
 */
static const struct fscache_state *fscache_update_object(struct fscache_object *object,
							 int event)
{
	_enter("{OBJ%x},%d", object->debug_id, event);

	fscache_stat(&fscache_n_updates_run);
	fscache_stat(&fscache_n_cop_update_object);
	object->cache->ops->update_object(object);
	fscache_stat_d(&fscache_n_cop_update_object);

	_leave("");
	return transit_to(WAIT_FOR_CMD);
}