aboutsummaryrefslogtreecommitdiff
path: root/lib/idr.c
blob: 00739aaf95a2717536957f9cb08413621417a2f8 (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
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
/*
 * 2002-10-18  written by Jim Houston jim.houston@ccur.com
 *	Copyright (C) 2002 by Concurrent Computer Corporation
 *	Distributed under the GNU GPL license version 2.
 *
 * Modified by George Anzinger to reuse immediately and to use
 * find bit instructions.  Also removed _irq on spinlocks.
 *
 * Modified by Nadia Derbey to make it RCU safe.
 *
 * Small id to pointer translation service.
 *
 * It uses a radix tree like structure as a sparse array indexed
 * by the id to obtain the pointer.  The bitmap makes allocating
 * a new id quick.
 *
 * You call it to allocate an id (an int) an associate with that id a
 * pointer or what ever, we treat it as a (void *).  You can pass this
 * id to a user for him to pass back at a later time.  You then pass
 * that id to this code and it returns your pointer.

 * You can release ids at any time. When all ids are released, most of
 * the memory is returned (we keep MAX_IDR_FREE) in a local pool so we
 * don't need to go to the memory "store" during an id allocate, just
 * so you don't need to be too concerned about locking and conflicts
 * with the slab allocator.
 */

#ifndef TEST                        // to test in user space...
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/export.h>
#endif
#include <linux/err.h>
#include <linux/string.h>
#include <linux/idr.h>
#include <linux/spinlock.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>

#define MAX_IDR_SHIFT		(sizeof(int) * 8 - 1)
#define MAX_IDR_BIT		(1U << MAX_IDR_SHIFT)

/* Leave the possibility of an incomplete final layer */
#define MAX_IDR_LEVEL ((MAX_IDR_SHIFT + IDR_BITS - 1) / IDR_BITS)

/* Number of id_layer structs to leave in free list */
#define MAX_IDR_FREE (MAX_IDR_LEVEL * 2)

static struct kmem_cache *idr_layer_cache;
static DEFINE_PER_CPU(struct idr_layer *, idr_preload_head);
static DEFINE_PER_CPU(int, idr_preload_cnt);
static DEFINE_SPINLOCK(simple_ida_lock);

/* the maximum ID which can be allocated given idr->layers */
static int idr_max(int layers)
{
	int bits = min_t(int, layers * IDR_BITS, MAX_IDR_SHIFT);

	return (1 << bits) - 1;
}

/*
 * Prefix mask for an idr_layer at @layer.  For layer 0, the prefix mask is
 * all bits except for the lower IDR_BITS.  For layer 1, 2 * IDR_BITS, and
 * so on.
 */
static int idr_layer_prefix_mask(int layer)
{
	return ~idr_max(layer + 1);
}

static struct idr_layer *get_from_free_list(struct idr *idp)
{
	struct idr_layer *p;
	unsigned long flags;

	spin_lock_irqsave(&idp->lock, flags);
	if ((p = idp->id_free)) {
		idp->id_free = p->ary[0];
		idp->id_free_cnt--;
		p->ary[0] = NULL;
	}
	spin_unlock_irqrestore(&idp->lock, flags);
	return(p);
}

/**
 * idr_layer_alloc - allocate a new idr_layer
 * @gfp_mask: allocation mask
 * @layer_idr: optional idr to allocate from
 *
 * If @layer_idr is %NULL, directly allocate one using @gfp_mask or fetch
 * one from the per-cpu preload buffer.  If @layer_idr is not %NULL, fetch
 * an idr_layer from @idr->id_free.
 *
 * @layer_idr is to maintain backward compatibility with the old alloc
 * interface - idr_pre_get() and idr_get_new*() - and will be removed
 * together with per-pool preload buffer.
 */
static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr)
{
	struct idr_layer *new;

	/* this is the old path, bypass to get_from_free_list() */
	if (layer_idr)
		return get_from_free_list(layer_idr);

	/* try to allocate directly from kmem_cache */
	new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
	if (new)
		return new;

	/*
	 * Try to fetch one from the per-cpu preload buffer if in process
	 * context.  See idr_preload() for details.
	 */
	if (in_interrupt())
		return NULL;

	preempt_disable();
	new = __this_cpu_read(idr_preload_head);
	if (new) {
		__this_cpu_write(idr_preload_head, new->ary[0]);
		__this_cpu_dec(idr_preload_cnt);
		new->ary[0] = NULL;
	}
	preempt_enable();
	return new;
}

static void idr_layer_rcu_free(struct rcu_head *head)
{
	struct idr_layer *layer;

	layer = container_of(head, struct idr_layer, rcu_head);
	kmem_cache_free(idr_layer_cache, layer);
}

static inline void free_layer(struct idr *idr, struct idr_layer *p)
{
	if (idr->hint && idr->hint == p)
		RCU_INIT_POINTER(idr->hint, NULL);
	call_rcu(&p->rcu_head, idr_layer_rcu_free);
}

/* only called when idp->lock is held */
static void __move_to_free_list(struct idr *idp, struct idr_layer *p)
{
	p->ary[0] = idp->id_free;
	idp->id_free = p;
	idp->id_free_cnt++;
}

static void move_to_free_list(struct idr *idp, struct idr_layer *p)
{
	unsigned long flags;

	/*
	 * Depends on the return element being zeroed.
	 */
	spin_lock_irqsave(&idp->lock, flags);
	__move_to_free_list(idp, p);
	spin_unlock_irqrestore(&idp->lock, flags);
}

static void idr_mark_full(struct idr_layer **pa, int id)
{
	struct idr_layer *p = pa[0];
	int l = 0;

	__set_bit(id & IDR_MASK, p->bitmap);
	/*
	 * If this layer is full mark the bit in the layer above to
	 * show that this part of the radix tree is full.  This may
	 * complete the layer above and require walking up the radix
	 * tree.
	 */
	while (bitmap_full(p->bitmap, IDR_SIZE)) {
		if (!(p = pa[++l]))
			break;
		id = id >> IDR_BITS;
		__set_bit((id & IDR_MASK), p->bitmap);
	}
}

/**
 * idr_pre_get - reserve resources for idr allocation
 * @idp:	idr handle
 * @gfp_mask:	memory allocation flags
 *
 * This function should be called prior to calling the idr_get_new* functions.
 * It preallocates enough memory to satisfy the worst possible allocation. The
 * caller should pass in GFP_KERNEL if possible.  This of course requires that
 * no spinning locks be held.
 *
 * If the system is REALLY out of memory this function returns %0,
 * otherwise %1.
 */
int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
{
	while (idp->id_free_cnt < MAX_IDR_FREE) {
		struct idr_layer *new;
		new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
		if (new == NULL)
			return (0);
		move_to_free_list(idp, new);
	}
	return 1;
}
EXPORT_SYMBOL(idr_pre_get);

/**
 * sub_alloc - try to allocate an id without growing the tree depth
 * @idp: idr handle
 * @starting_id: id to start search at
 * @id: pointer to the allocated handle
 * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer
 * @gfp_mask: allocation mask for idr_layer_alloc()
 * @layer_idr: optional idr passed to idr_layer_alloc()
 *
 * Allocate an id in range [@starting_id, INT_MAX] from @idp without
 * growing its depth.  Returns
 *
 *  the allocated id >= 0 if successful,
 *  -EAGAIN if the tree needs to grow for allocation to succeed,
 *  -ENOSPC if the id space is exhausted,
 *  -ENOMEM if more idr_layers need to be allocated.
 */
static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa,
		     gfp_t gfp_mask, struct idr *layer_idr)
{
	int n, m, sh;
	struct idr_layer *p, *new;
	int l, id, oid;

	id = *starting_id;
 restart:
	p = idp->top;
	l = idp->layers;
	pa[l--] = NULL;
	while (1) {
		/*
		 * We run around this while until we reach the leaf node...
		 */
		n = (id >> (IDR_BITS*l)) & IDR_MASK;
		m = find_next_zero_bit(p->bitmap, IDR_SIZE, n);
		if (m == IDR_SIZE) {
			/* no space available go back to previous layer. */
			l++;
			oid = id;
			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;

			/* if already at the top layer, we need to grow */
			if (id >= 1 << (idp->layers * IDR_BITS)) {
				*starting_id = id;
				return -EAGAIN;
			}
			p = pa[l];
			BUG_ON(!p);

			/* If we need to go up one layer, continue the
			 * loop; otherwise, restart from the top.
			 */
			sh = IDR_BITS * (l + 1);
			if (oid >> sh == id >> sh)
				continue;
			else
				goto restart;
		}
		if (m != n) {
			sh = IDR_BITS*l;
			id = ((id >> sh) ^ n ^ m) << sh;
		}
		if ((id >= MAX_IDR_BIT) || (id < 0))
			return -ENOSPC;
		if (l == 0)
			break;
		/*
		 * Create the layer below if it is missing.
		 */
		if (!p->ary[m]) {
			new = idr_layer_alloc(gfp_mask, layer_idr);
			if (!new)
				return -ENOMEM;
			new->layer = l-1;
			new->prefix = id & idr_layer_prefix_mask(new->layer);
			rcu_assign_pointer(p->ary[m], new);
			p->count++;
		}
		pa[l--] = p;
		p = p->ary[m];
	}

	pa[l] = p;
	return id;
}

static int idr_get_empty_slot(struct idr *idp, int starting_id,
			      struct idr_layer **pa, gfp_t gfp_mask,
			      struct idr *layer_idr)
{
	struct idr_layer *p, *new;
	int layers, v, id;
	unsigned long flags;

	id = starting_id;
build_up:
	p = idp->top;
	layers = idp->layers;
	if (unlikely(!p)) {
		if (!(p = idr_layer_alloc(gfp_mask, layer_idr)))
			return -ENOMEM;
		p->layer = 0;
		layers = 1;
	}
	/*
	 * Add a new layer to the top of the tree if the requested
	 * id is larger than the currently allocated space.
	 */
	while (id > idr_max(layers)) {
		layers++;
		if (!p->count) {
			/* special case: if the tree is currently empty,
			 * then we grow the tree by moving the top node
			 * upwards.
			 */
			p->layer++;
			WARN_ON_ONCE(p->prefix);
			continue;
		}
		if (!(new = idr_layer_alloc(gfp_mask, layer_idr))) {
			/*
			 * The allocation failed.  If we built part of
			 * the structure tear it down.
			 */
			spin_lock_irqsave(&idp->lock, flags);
			for (new = p; p && p != idp->top; new = p) {
				p = p->ary[0];
				new->ary[0] = NULL;
				new->count = 0;
				bitmap_clear(new->bitmap, 0, IDR_SIZE);
				__move_to_free_list(idp, new);
			}
			spin_unlock_irqrestore(&idp->lock, flags);
			return -ENOMEM;
		}
		new->ary[0] = p;
		new->count = 1;
		new->layer = layers-1;
		new->prefix = id & idr_layer_prefix_mask(new->layer);
		if (bitmap_full(p->bitmap, IDR_SIZE))
			__set_bit(0, new->bitmap);
		p = new;
	}
	rcu_assign_pointer(idp->top, p);
	idp->layers = layers;
	v = sub_alloc(idp, &id, pa, gfp_mask, layer_idr);
	if (v == -EAGAIN)
		goto build_up;
	return(v);
}

/*
 * @id and @pa are from a successful allocation from idr_get_empty_slot().
 * Install the user pointer @ptr and mark the slot full.
 */
static void idr_fill_slot(struct idr *idr, void *ptr, int id,
			  struct idr_layer **pa)
{
	/* update hint used for lookup, cleared from free_layer() */
	rcu_assign_pointer(idr->hint, pa[0]);

	rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], (struct idr_layer *)ptr);
	pa[0]->count++;
	idr_mark_full(pa, id);
}

/**
 * idr_get_new_above - allocate new idr entry above or equal to a start id
 * @idp: idr handle
 * @ptr: pointer you want associated with the id
 * @starting_id: id to start search at
 * @id: pointer to the allocated handle
 *
 * This is the allocate id function.  It should be called with any
 * required locks.
 *
 * If allocation from IDR's private freelist fails, idr_get_new_above() will
 * return %-EAGAIN.  The caller should retry the idr_pre_get() call to refill
 * IDR's preallocation and then retry the idr_get_new_above() call.
 *
 * If the idr is full idr_get_new_above() will return %-ENOSPC.
 *
 * @id returns a value in the range @starting_id ... %0x7fffffff
 */
int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
{
	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
	int rv;

	rv = idr_get_empty_slot(idp, starting_id, pa, 0, idp);
	if (rv < 0)
		return rv == -ENOMEM ? -EAGAIN : rv;

	idr_fill_slot(idp, ptr, rv, pa);
	*id = rv;
	return 0;
}
EXPORT_SYMBOL(idr_get_new_above);

/**
 * idr_preload - preload for idr_alloc()
 * @gfp_mask: allocation mask to use for preloading
 *
 * Preload per-cpu layer buffer for idr_alloc().  Can only be used from
 * process context and each idr_preload() invocation should be matched with
 * idr_preload_end().  Note that preemption is disabled while preloaded.
 *
 * The first idr_alloc() in the preloaded section can be treated as if it
 * were invoked with @gfp_mask used for preloading.  This allows using more
 * permissive allocation masks for idrs protected by spinlocks.
 *
 * For example, if idr_alloc() below fails, the failure can be treated as
 * if idr_alloc() were called with GFP_KERNEL rather than GFP_NOWAIT.
 *
 *	idr_preload(GFP_KERNEL);
 *	spin_lock(lock);
 *
 *	id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT);
 *
 *	spin_unlock(lock);
 *	idr_preload_end();
 *	if (id < 0)
 *		error;
 */
void idr_preload(gfp_t gfp_mask)
{
	/*
	 * Consuming preload buffer from non-process context breaks preload
	 * allocation guarantee.  Disallow usage from those contexts.
	 */
	WARN_ON_ONCE(in_interrupt());
	might_sleep_if(gfp_mask & __GFP_WAIT);

	preempt_disable();

	/*
	 * idr_alloc() is likely to succeed w/o full idr_layer buffer and
	 * return value from idr_alloc() needs to be checked for failure
	 * anyway.  Silently give up if allocation fails.  The caller can
	 * treat failures from idr_alloc() as if idr_alloc() were called
	 * with @gfp_mask which should be enough.
	 */
	while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) {
		struct idr_layer *new;

		preempt_enable();
		new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
		preempt_disable();
		if (!new)
			break;

		/* link the new one to per-cpu preload list */
		new->ary[0] = __this_cpu_read(idr_preload_head);
		__this_cpu_write(idr_preload_head, new);
		__this_cpu_inc(idr_preload_cnt);
	}
}
EXPORT_SYMBOL(idr_preload);

/**
 * idr_alloc - allocate new idr entry
 * @idr: the (initialized) idr
 * @ptr: pointer to be associated with the new id
 * @start: the minimum id (inclusive)
 * @end: the maximum id (exclusive, <= 0 for max)
 * @gfp_mask: memory allocation flags
 *
 * Allocate an id in [start, end) and associate it with @ptr.  If no ID is
 * available in the specified range, returns -ENOSPC.  On memory allocation
 * failure, returns -ENOMEM.
 *
 * Note that @end is treated as max when <= 0.  This is to always allow
 * using @start + N as @end as long as N is inside integer range.
 *
 * The user is responsible for exclusively synchronizing all operations
 * which may modify @idr.  However, read-only accesses such as idr_find()
 * or iteration can be performed under RCU read lock provided the user
 * destroys @ptr in RCU-safe way after removal from idr.
 */
int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask)
{
	int max = end > 0 ? end - 1 : INT_MAX;	/* inclusive upper limit */
	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
	int id;

	might_sleep_if(gfp_mask & __GFP_WAIT);

	/* sanity checks */
	if (WARN_ON_ONCE(start < 0))
		return -EINVAL;
	if (unlikely(max < start))
		return -ENOSPC;

	/* allocate id */
	id = idr_get_empty_slot(idr, start, pa, gfp_mask, NULL);
	if (unlikely(id < 0))
		return id;
	if (unlikely(id > max))
		return -ENOSPC;

	idr_fill_slot(idr, ptr, id, pa);
	return id;
}
EXPORT_SYMBOL_GPL(idr_alloc);

static void idr_remove_warning(int id)
{
	printk(KERN_WARNING
		"idr_remove called for id=%d which is not allocated.\n", id);
	dump_stack();
}

static void sub_remove(struct idr *idp, int shift, int id)
{
	struct idr_layer *p = idp->top;
	struct idr_layer **pa[MAX_IDR_LEVEL + 1];
	struct idr_layer ***paa = &pa[0];
	struct idr_layer *to_free;
	int n;

	*paa = NULL;
	*++paa = &idp->top;

	while ((shift > 0) && p) {
		n = (id >> shift) & IDR_MASK;
		__clear_bit(n, p->bitmap);
		*++paa = &p->ary[n];
		p = p->ary[n];
		shift -= IDR_BITS;
	}
	n = id & IDR_MASK;
	if (likely(p != NULL && test_bit(n, p->bitmap))) {
		__clear_bit(n, p->bitmap);
		rcu_assign_pointer(p->ary[n], NULL);
		to_free = NULL;
		while(*paa && ! --((**paa)->count)){
			if (to_free)
				free_layer(idp, to_free);
			to_free = **paa;
			**paa-- = NULL;
		}
		if (!*paa)
			idp->layers = 0;
		if (to_free)
			free_layer(idp, to_free);
	} else
		idr_remove_warning(id);
}

/**
 * idr_remove - remove the given id and free its slot
 * @idp: idr handle
 * @id: unique key
 */
void idr_remove(struct idr *idp, int id)
{
	struct idr_layer *p;
	struct idr_layer *to_free;

	if (id < 0)
		return;

	sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
	if (idp->top && idp->top->count == 1 && (idp->layers > 1) &&
	    idp->top->ary[0]) {
		/*
		 * Single child at leftmost slot: we can shrink the tree.
		 * This level is not needed anymore since when layers are
		 * inserted, they are inserted at the top of the existing
		 * tree.
		 */
		to_free = idp->top;
		p = idp->top->ary[0];
		rcu_assign_pointer(idp->top, p);
		--idp->layers;
		to_free->count = 0;
		bitmap_clear(to_free->bitmap, 0, IDR_SIZE);
		free_layer(idp, to_free);
	}
	while (idp->id_free_cnt >= MAX_IDR_FREE) {
		p = get_from_free_list(idp);
		/*
		 * Note: we don't call the rcu callback here, since the only
		 * layers that fall into the freelist are those that have been
		 * preallocated.
		 */
		kmem_cache_free(idr_layer_cache, p);
	}
	return;
}
EXPORT_SYMBOL(idr_remove);

void __idr_remove_all(struct idr *idp)
{
	int n, id, max;
	int bt_mask;
	struct idr_layer *p;
	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
	struct idr_layer **paa = &pa[0];

	n = idp->layers * IDR_BITS;
	p = idp->top;
	rcu_assign_pointer(idp->top, NULL);
	max = idr_max(idp->layers);

	id = 0;
	while (id >= 0 && id <= max) {
		while (n > IDR_BITS && p) {
			n -= IDR_BITS;
			*paa++ = p;
			p = p->ary[(id >> n) & IDR_MASK];
		}

		bt_mask = id;
		id += 1 << n;
		/* Get the highest bit that the above add changed from 0->1. */
		while (n < fls(id ^ bt_mask)) {
			if (p)
				free_layer(idp, p);
			n += IDR_BITS;
			p = *--paa;
		}
	}
	idp->layers = 0;
}
EXPORT_SYMBOL(__idr_remove_all);

/**
 * idr_destroy - release all cached layers within an idr tree
 * @idp: idr handle
 *
 * Free all id mappings and all idp_layers.  After this function, @idp is
 * completely unused and can be freed / recycled.  The caller is
 * responsible for ensuring that no one else accesses @idp during or after
 * idr_destroy().
 *
 * A typical clean-up sequence for objects stored in an idr tree will use
 * idr_for_each() to free all objects, if necessay, then idr_destroy() to
 * free up the id mappings and cached idr_layers.
 */
void idr_destroy(struct idr *idp)
{
	__idr_remove_all(idp);

	while (idp->id_free_cnt) {
		struct idr_layer *p = get_from_free_list(idp);
		kmem_cache_free(idr_layer_cache, p);
	}
}
EXPORT_SYMBOL(idr_destroy);

void *idr_find_slowpath(struct idr *idp, int id)
{
	int n;
	struct idr_layer *p;

	if (id < 0)
		return NULL;

	p = rcu_dereference_raw(idp->top);
	if (!p)
		return NULL;
	n = (p->layer+1) * IDR_BITS;

	if (id > idr_max(p->layer + 1))
		return NULL;
	BUG_ON(n == 0);

	while (n > 0 && p) {
		n -= IDR_BITS;
		BUG_ON(n != p->layer*IDR_BITS);
		p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
	}
	return((void *)p);
}
EXPORT_SYMBOL(idr_find_slowpath);

/**
 * idr_for_each - iterate through all stored pointers
 * @idp: idr handle
 * @fn: function to be called for each pointer
 * @data: data passed back to callback function
 *
 * Iterate over the pointers registered with the given idr.  The
 * callback function will be called for each pointer currently
 * registered, passing the id, the pointer and the data pointer passed
 * to this function.  It is not safe to modify the idr tree while in
 * the callback, so functions such as idr_get_new and idr_remove are
 * not allowed.
 *
 * We check the return of @fn each time. If it returns anything other
 * than %0, we break out and return that value.
 *
 * The caller must serialize idr_for_each() vs idr_get_new() and idr_remove().
 */
int idr_for_each(struct idr *idp,
		 int (*fn)(int id, void *p, void *data), void *data)
{
	int n, id, max, error = 0;
	struct idr_layer *p;
	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
	struct idr_layer **paa = &pa[0];

	n = idp->layers * IDR_BITS;
	p = rcu_dereference_raw(idp->top);
	max = idr_max(idp->layers);

	id = 0;
	while (id >= 0 && id <= max) {
		while (n > 0 && p) {
			n -= IDR_BITS;
			*paa++ = p;
			p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
		}

		if (p) {
			error = fn(id, (void *)p, data);
			if (error)
				break;
		}

		id += 1 << n;
		while (n < fls(id)) {
			n += IDR_BITS;
			p = *--paa;
		}
	}

	return error;
}
EXPORT_SYMBOL(idr_for_each);

/**
 * idr_get_next - lookup next object of id to given id.
 * @idp: idr handle
 * @nextidp:  pointer to lookup key
 *
 * Returns pointer to registered object with id, which is next number to
 * given id. After being looked up, *@nextidp will be updated for the next
 * iteration.
 *
 * This function can be called under rcu_read_lock(), given that the leaf
 * pointers lifetimes are correctly managed.
 */
void *idr_get_next(struct idr *idp, int *nextidp)
{
	struct idr_layer *p, *pa[MAX_IDR_LEVEL + 1];
	struct idr_layer **paa = &pa[0];
	int id = *nextidp;
	int n, max;

	/* find first ent */
	p = rcu_dereference_raw(idp->top);
	if (!p)
		return NULL;
	n = (p->layer + 1) * IDR_BITS;
	max = idr_max(p->layer + 1);

	while (id >= 0 && id <= max) {
		while (n > 0 && p) {
			n -= IDR_BITS;
			*paa++ = p;
			p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
		}

		if (p) {
			*nextidp = id;
			return p;
		}

		/*
		 * Proceed to the next layer at the current level.  Unlike
		 * idr_for_each(), @id isn't guaranteed to be aligned to
		 * layer boundary at this point and adding 1 << n may
		 * incorrectly skip IDs.  Make sure we jump to the
		 * beginning of the next layer using round_up().
		 */
		id = round_up(id + 1, 1 << n);
		while (n < fls(id)) {
			n += IDR_BITS;
			p = *--paa;
		}
	}
	return NULL;
}
EXPORT_SYMBOL(idr_get_next);


/**
 * idr_replace - replace pointer for given id
 * @idp: idr handle
 * @ptr: pointer you want associated with the id
 * @id: lookup key
 *
 * Replace the pointer registered with an id and return the old value.
 * A %-ENOENT return indicates that @id was not found.
 * A %-EINVAL return indicates that @id was not within valid constraints.
 *
 * The caller must serialize with writers.
 */
void *idr_replace(struct idr *idp, void *ptr, int id)
{
	int n;
	struct idr_layer *p, *old_p;

	if (id < 0)
		return ERR_PTR(-EINVAL);

	p = idp->top;
	if (!p)
		return ERR_PTR(-EINVAL);

	n = (p->layer+1) * IDR_BITS;

	if (id >= (1 << n))
		return ERR_PTR(-EINVAL);

	n -= IDR_BITS;
	while ((n > 0) && p) {
		p = p->ary[(id >> n) & IDR_MASK];
		n -= IDR_BITS;
	}

	n = id & IDR_MASK;
	if (unlikely(p == NULL || !test_bit(n, p->bitmap)))
		return ERR_PTR(-ENOENT);

	old_p = p->ary[n];
	rcu_assign_pointer(p->ary[n], ptr);

	return old_p;
}
EXPORT_SYMBOL(idr_replace);

void __init idr_init_cache(void)
{
	idr_layer_cache = kmem_cache_create("idr_layer_cache",
				sizeof(struct idr_layer), 0, SLAB_PANIC, NULL);
}

/**
 * idr_init - initialize idr handle
 * @idp:	idr handle
 *
 * This function is use to set up the handle (@idp) that you will pass
 * to the rest of the functions.
 */
void idr_init(struct idr *idp)
{
	memset(idp, 0, sizeof(struct idr));
	spin_lock_init(&idp->lock);
}
EXPORT_SYMBOL(idr_init);


/**
 * DOC: IDA description
 * IDA - IDR based ID allocator
 *
 * This is id allocator without id -> pointer translation.  Memory
 * usage is much lower than full blown idr because each id only
 * occupies a bit.  ida uses a custom leaf node which contains
 * IDA_BITMAP_BITS slots.
 *
 * 2007-04-25  written by Tejun Heo <htejun@gmail.com>
 */

static void free_bitmap(struct ida *ida, struct ida_bitmap *bitmap)
{
	unsigned long flags;

	if (!ida->free_bitmap) {
		spin_lock_irqsave(&ida->idr.lock, flags);
		if (!ida->free_bitmap) {
			ida->free_bitmap = bitmap;
			bitmap = NULL;
		}
		spin_unlock_irqrestore(&ida->idr.lock, flags);
	}

	kfree(bitmap);
}

/**
 * ida_pre_get - reserve resources for ida allocation
 * @ida:	ida handle
 * @gfp_mask:	memory allocation flag
 *
 * This function should be called prior to locking and calling the
 * following function.  It preallocates enough memory to satisfy the
 * worst possible allocation.
 *
 * If the system is REALLY out of memory this function returns %0,
 * otherwise %1.
 */
int ida_pre_get(struct ida *ida, gfp_t gfp_mask)
{
	/* allocate idr_layers */
	if (!idr_pre_get(&ida->idr, gfp_mask))
		return 0;

	/* allocate free_bitmap */
	if (!ida->free_bitmap) {
		struct ida_bitmap *bitmap;

		bitmap = kmalloc(sizeof(struct ida_bitmap), gfp_mask);
		if (!bitmap)
			return 0;

		free_bitmap(ida, bitmap);
	}

	return 1;
}
EXPORT_SYMBOL(ida_pre_get);

/**
 * ida_get_new_above - allocate new ID above or equal to a start id
 * @ida:	ida handle
 * @starting_id: id to start search at
 * @p_id:	pointer to the allocated handle
 *
 * Allocate new ID above or equal to @starting_id.  It should be called
 * with any required locks.
 *
 * If memory is required, it will return %-EAGAIN, you should unlock
 * and go back to the ida_pre_get() call.  If the ida is full, it will
 * return %-ENOSPC.
 *
 * @p_id returns a value in the range @starting_id ... %0x7fffffff.
 */
int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
{
	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
	struct ida_bitmap *bitmap;
	unsigned long flags;
	int idr_id = starting_id / IDA_BITMAP_BITS;
	int offset = starting_id % IDA_BITMAP_BITS;
	int t, id;

 restart:
	/* get vacant slot */
	t = idr_get_empty_slot(&ida->idr, idr_id, pa, 0, &ida->idr);
	if (t < 0)
		return t == -ENOMEM ? -EAGAIN : t;

	if (t * IDA_BITMAP_BITS >= MAX_IDR_BIT)
		return -ENOSPC;

	if (t != idr_id)
		offset = 0;
	idr_id = t;

	/* if bitmap isn't there, create a new one */
	bitmap = (void *)pa[0]->ary[idr_id & IDR_MASK];
	if (!bitmap) {
		spin_lock_irqsave(&ida->idr.lock, flags);
		bitmap = ida->free_bitmap;
		ida->free_bitmap = NULL;
		spin_unlock_irqrestore(&ida->idr.lock, flags);

		if (!bitmap)
			return -EAGAIN;

		memset(bitmap, 0, sizeof(struct ida_bitmap));
		rcu_assign_pointer(pa[0]->ary[idr_id & IDR_MASK],
				(void *)bitmap);
		pa[0]->count++;
	}

	/* lookup for empty slot */
	t = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, offset);
	if (t == IDA_BITMAP_BITS) {
		/* no empty slot after offset, continue to the next chunk */
		idr_id++;
		offset = 0;
		goto restart;
	}

	id = idr_id * IDA_BITMAP_BITS + t;
	if (id >= MAX_IDR_BIT)
		return -ENOSPC;

	__set_bit(t, bitmap->bitmap);
	if (++bitmap->nr_busy == IDA_BITMAP_BITS)
		idr_mark_full(pa, idr_id);

	*p_id = id;

	/* Each leaf node can handle nearly a thousand slots and the
	 * whole idea of ida is to have small memory foot print.
	 * Throw away extra resources one by one after each successful
	 * allocation.
	 */
	if (ida->idr.id_free_cnt || ida->free_bitmap) {
		struct idr_layer *p = get_from_free_list(&ida->idr);
		if (p)
			kmem_cache_free(idr_layer_cache, p);
	}

	return 0;
}
EXPORT_SYMBOL(ida_get_new_above);

/**
 * ida_remove - remove the given ID
 * @ida:	ida handle
 * @id:		ID to free
 */
void ida_remove(struct ida *ida, int id)
{
	struct idr_layer *p = ida->idr.top;
	int shift = (ida->idr.layers - 1) * IDR_BITS;
	int idr_id = id / IDA_BITMAP_BITS;
	int offset = id % IDA_BITMAP_BITS;
	int n;
	struct ida_bitmap *bitmap;

	/* clear full bits while looking up the leaf idr_layer */
	while ((shift > 0) && p) {
		n = (idr_id >> shift) & IDR_MASK;
		__clear_bit(n, p->bitmap);
		p = p->ary[n];
		shift -= IDR_BITS;
	}

	if (p == NULL)
		goto err;

	n = idr_id & IDR_MASK;
	__clear_bit(n, p->bitmap);

	bitmap = (void *)p->ary[n];
	if (!test_bit(offset, bitmap->bitmap))
		goto err;

	/* update bitmap and remove it if empty */
	__clear_bit(offset, bitmap->bitmap);
	if (--bitmap->nr_busy == 0) {
		__set_bit(n, p->bitmap);	/* to please idr_remove() */
		idr_remove(&ida->idr, idr_id);
		free_bitmap(ida, bitmap);
	}

	return;

 err:
	printk(KERN_WARNING
	       "ida_remove called for id=%d which is not allocated.\n", id);
}
EXPORT_SYMBOL(ida_remove);

/**
 * ida_destroy - release all cached layers within an ida tree
 * @ida:		ida handle
 */
void ida_destroy(struct ida *ida)
{
	idr_destroy(&ida->idr);
	kfree(ida->free_bitmap);
}
EXPORT_SYMBOL(ida_destroy);

/**
 * ida_simple_get - get a new id.
 * @ida: the (initialized) ida.
 * @start: the minimum id (inclusive, < 0x8000000)
 * @end: the maximum id (exclusive, < 0x8000000 or 0)
 * @gfp_mask: memory allocation flags
 *
 * Allocates an id in the range start <= id < end, or returns -ENOSPC.
 * On memory allocation failure, returns -ENOMEM.
 *
 * Use ida_simple_remove() to get rid of an id.
 */
int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
		   gfp_t gfp_mask)
{
	int ret, id;
	unsigned int max;
	unsigned long flags;

	BUG_ON((int)start < 0);
	BUG_ON((int)end < 0);

	if (end == 0)
		max = 0x80000000;
	else {
		BUG_ON(end < start);
		max = end - 1;
	}

again:
	if (!ida_pre_get(ida, gfp_mask))
		return -ENOMEM;

	spin_lock_irqsave(&simple_ida_lock, flags);
	ret = ida_get_new_above(ida, start, &id);
	if (!ret) {
		if (id > max) {
			ida_remove(ida, id);
			ret = -ENOSPC;
		} else {
			ret = id;
		}
	}
	spin_unlock_irqrestore(&simple_ida_lock, flags);

	if (unlikely(ret == -EAGAIN))
		goto again;

	return ret;
}
EXPORT_SYMBOL(ida_simple_get);

/**
 * ida_simple_remove - remove an allocated id.
 * @ida: the (initialized) ida.
 * @id: the id returned by ida_simple_get.
 */
void ida_simple_remove(struct ida *ida, unsigned int id)
{
	unsigned long flags;

	BUG_ON((int)id < 0);
	spin_lock_irqsave(&simple_ida_lock, flags);
	ida_remove(ida, id);
	spin_unlock_irqrestore(&simple_ida_lock, flags);
}
EXPORT_SYMBOL(ida_simple_remove);

/**
 * ida_init - initialize ida handle
 * @ida:	ida handle
 *
 * This function is use to set up the handle (@ida) that you will pass
 * to the rest of the functions.
 */
void ida_init(struct ida *ida)
{
	memset(ida, 0, sizeof(struct ida));
	idr_init(&ida->idr);

}
EXPORT_SYMBOL(ida_init);