aboutsummaryrefslogtreecommitdiff
path: root/bfd/hash.c
blob: 6e60bedc05b67b40b844b7ed38f7251f9cc7cd7a (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
/* hash.c -- hash table routines for BFD
   Copyright (C) 1993-2023 Free Software Foundation, Inc.
   Written by Steve Chamberlain <sac@cygnus.com>

   This file is part of BFD, the Binary File Descriptor library.

   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 3 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will 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 to the Free Software
   Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston,
   MA 02110-1301, USA.  */

#include "sysdep.h"
#include "bfd.h"
#include "libbfd.h"
#include "objalloc.h"
#include "libiberty.h"

/*
SECTION
	Hash Tables

@cindex Hash tables
	BFD provides a simple set of hash table functions.  Routines
	are provided to initialize a hash table, to free a hash table,
	to look up a string in a hash table and optionally create an
	entry for it, and to traverse a hash table.  There is
	currently no routine to delete an string from a hash table.

	The basic hash table does not permit any data to be stored
	with a string.  However, a hash table is designed to present a
	base class from which other types of hash tables may be
	derived.  These derived types may store additional information
	with the string.  Hash tables were implemented in this way,
	rather than simply providing a data pointer in a hash table
	entry, because they were designed for use by the linker back
	ends.  The linker may create thousands of hash table entries,
	and the overhead of allocating private data and storing and
	following pointers becomes noticeable.

	The basic hash table code is in <<hash.c>>.

@menu
@* Creating and Freeing a Hash Table::
@* Looking Up or Entering a String::
@* Traversing a Hash Table::
@* Deriving a New Hash Table Type::
@end menu

INODE
Creating and Freeing a Hash Table, Looking Up or Entering a String, Hash Tables, Hash Tables
SUBSECTION
	Creating and freeing a hash table

@findex bfd_hash_table_init
@findex bfd_hash_table_init_n
	To create a hash table, create an instance of a <<struct
	bfd_hash_table>> (defined in <<bfd.h>>) and call
	<<bfd_hash_table_init>> (if you know approximately how many
	entries you will need, the function <<bfd_hash_table_init_n>>,
	which takes a @var{size} argument, may be used).
	<<bfd_hash_table_init>> returns <<FALSE>> if some sort of
	error occurs.

@findex bfd_hash_newfunc
	The function <<bfd_hash_table_init>> take as an argument a
	function to use to create new entries.  For a basic hash
	table, use the function <<bfd_hash_newfunc>>.  @xref{Deriving
	a New Hash Table Type}, for why you would want to use a
	different value for this argument.

@findex bfd_hash_allocate
	<<bfd_hash_table_init>> will create an objalloc which will be
	used to allocate new entries.  You may allocate memory on this
	objalloc using <<bfd_hash_allocate>>.

@findex bfd_hash_table_free
	Use <<bfd_hash_table_free>> to free up all the memory that has
	been allocated for a hash table.  This will not free up the
	<<struct bfd_hash_table>> itself, which you must provide.

@findex bfd_hash_set_default_size
	Use <<bfd_hash_set_default_size>> to set the default size of
	hash table to use.

INODE
Looking Up or Entering a String, Traversing a Hash Table, Creating and Freeing a Hash Table, Hash Tables
SUBSECTION
	Looking up or entering a string

@findex bfd_hash_lookup
	The function <<bfd_hash_lookup>> is used both to look up a
	string in the hash table and to create a new entry.

	If the @var{create} argument is <<FALSE>>, <<bfd_hash_lookup>>
	will look up a string.  If the string is found, it will
	returns a pointer to a <<struct bfd_hash_entry>>.  If the
	string is not found in the table <<bfd_hash_lookup>> will
	return <<NULL>>.  You should not modify any of the fields in
	the returns <<struct bfd_hash_entry>>.

	If the @var{create} argument is <<TRUE>>, the string will be
	entered into the hash table if it is not already there.
	Either way a pointer to a <<struct bfd_hash_entry>> will be
	returned, either to the existing structure or to a newly
	created one.  In this case, a <<NULL>> return means that an
	error occurred.

	If the @var{create} argument is <<TRUE>>, and a new entry is
	created, the @var{copy} argument is used to decide whether to
	copy the string onto the hash table objalloc or not.  If
	@var{copy} is passed as <<FALSE>>, you must be careful not to
	deallocate or modify the string as long as the hash table
	exists.

INODE
Traversing a Hash Table, Deriving a New Hash Table Type, Looking Up or Entering a String, Hash Tables
SUBSECTION
	Traversing a hash table

@findex bfd_hash_traverse
	The function <<bfd_hash_traverse>> may be used to traverse a
	hash table, calling a function on each element.  The traversal
	is done in a random order.

	<<bfd_hash_traverse>> takes as arguments a function and a
	generic <<void *>> pointer.  The function is called with a
	hash table entry (a <<struct bfd_hash_entry *>>) and the
	generic pointer passed to <<bfd_hash_traverse>>.  The function
	must return a <<boolean>> value, which indicates whether to
	continue traversing the hash table.  If the function returns
	<<FALSE>>, <<bfd_hash_traverse>> will stop the traversal and
	return immediately.

INODE
Deriving a New Hash Table Type, , Traversing a Hash Table, Hash Tables
SUBSECTION
	Deriving a new hash table type

	Many uses of hash tables want to store additional information
	which each entry in the hash table.  Some also find it
	convenient to store additional information with the hash table
	itself.  This may be done using a derived hash table.

	Since C is not an object oriented language, creating a derived
	hash table requires sticking together some boilerplate
	routines with a few differences specific to the type of hash
	table you want to create.

	An example of a derived hash table is the linker hash table.
	The structures for this are defined in <<bfdlink.h>>.  The
	functions are in <<linker.c>>.

	You may also derive a hash table from an already derived hash
	table.  For example, the a.out linker backend code uses a hash
	table derived from the linker hash table.

@menu
@* Define the Derived Structures::
@* Write the Derived Creation Routine::
@* Write Other Derived Routines::
@end menu

INODE
Define the Derived Structures, Write the Derived Creation Routine, Deriving a New Hash Table Type, Deriving a New Hash Table Type
SUBSUBSECTION
	Define the derived structures

	You must define a structure for an entry in the hash table,
	and a structure for the hash table itself.

	The first field in the structure for an entry in the hash
	table must be of the type used for an entry in the hash table
	you are deriving from.  If you are deriving from a basic hash
	table this is <<struct bfd_hash_entry>>, which is defined in
	<<bfd.h>>.  The first field in the structure for the hash
	table itself must be of the type of the hash table you are
	deriving from itself.  If you are deriving from a basic hash
	table, this is <<struct bfd_hash_table>>.

	For example, the linker hash table defines <<struct
	bfd_link_hash_entry>> (in <<bfdlink.h>>).  The first field,
	<<root>>, is of type <<struct bfd_hash_entry>>.  Similarly,
	the first field in <<struct bfd_link_hash_table>>, <<table>>,
	is of type <<struct bfd_hash_table>>.

INODE
Write the Derived Creation Routine, Write Other Derived Routines, Define the Derived Structures, Deriving a New Hash Table Type
SUBSUBSECTION
	Write the derived creation routine

	You must write a routine which will create and initialize an
	entry in the hash table.  This routine is passed as the
	function argument to <<bfd_hash_table_init>>.

	In order to permit other hash tables to be derived from the
	hash table you are creating, this routine must be written in a
	standard way.

	The first argument to the creation routine is a pointer to a
	hash table entry.  This may be <<NULL>>, in which case the
	routine should allocate the right amount of space.  Otherwise
	the space has already been allocated by a hash table type
	derived from this one.

	After allocating space, the creation routine must call the
	creation routine of the hash table type it is derived from,
	passing in a pointer to the space it just allocated.  This
	will initialize any fields used by the base hash table.

	Finally the creation routine must initialize any local fields
	for the new hash table type.

	Here is a boilerplate example of a creation routine.
	@var{function_name} is the name of the routine.
	@var{entry_type} is the type of an entry in the hash table you
	are creating.  @var{base_newfunc} is the name of the creation
	routine of the hash table type your hash table is derived
	from.

EXAMPLE

.struct bfd_hash_entry *
.@var{function_name} (struct bfd_hash_entry *entry,
.		      struct bfd_hash_table *table,
.		      const char *string)
.{
.  struct @var{entry_type} *ret = (@var{entry_type} *) entry;
.
. {* Allocate the structure if it has not already been allocated by a
.    derived class.  *}
.  if (ret == NULL)
.    {
.      ret = bfd_hash_allocate (table, sizeof (* ret));
.      if (ret == NULL)
.	 return NULL;
.    }
.
. {* Call the allocation method of the base class.  *}
.  ret = ((@var{entry_type} *)
.	  @var{base_newfunc} ((struct bfd_hash_entry *) ret, table, string));
.
. {* Initialize the local fields here.  *}
.
.  return (struct bfd_hash_entry *) ret;
.}

DESCRIPTION
	The creation routine for the linker hash table, which is in
	<<linker.c>>, looks just like this example.
	@var{function_name} is <<_bfd_link_hash_newfunc>>.
	@var{entry_type} is <<struct bfd_link_hash_entry>>.
	@var{base_newfunc} is <<bfd_hash_newfunc>>, the creation
	routine for a basic hash table.

	<<_bfd_link_hash_newfunc>> also initializes the local fields
	in a linker hash table entry: <<type>>, <<written>> and
	<<next>>.

INODE
Write Other Derived Routines, , Write the Derived Creation Routine, Deriving a New Hash Table Type
SUBSUBSECTION
	Write other derived routines

	You will want to write other routines for your new hash table,
	as well.

	You will want an initialization routine which calls the
	initialization routine of the hash table you are deriving from
	and initializes any other local fields.  For the linker hash
	table, this is <<_bfd_link_hash_table_init>> in <<linker.c>>.

	You will want a lookup routine which calls the lookup routine
	of the hash table you are deriving from and casts the result.
	The linker hash table uses <<bfd_link_hash_lookup>> in
	<<linker.c>> (this actually takes an additional argument which
	it uses to decide how to return the looked up value).

	You may want a traversal routine.  This should just call the
	traversal routine of the hash table you are deriving from with
	appropriate casts.  The linker hash table uses
	<<bfd_link_hash_traverse>> in <<linker.c>>.

	These routines may simply be defined as macros.  For example,
	the a.out backend linker hash table, which is derived from the
	linker hash table, uses macros for the lookup and traversal
	routines.  These are <<aout_link_hash_lookup>> and
	<<aout_link_hash_traverse>> in aoutx.h.
*/

/* The default number of entries to use when creating a hash table.  */
#define DEFAULT_SIZE 4051

/* The following function returns a nearest prime number which is
   greater than N, and near a power of two.  Copied from libiberty.
   Returns zero for ridiculously large N to signify an error.  */

static unsigned long
higher_prime_number (unsigned long n)
{
  /* These are primes that are near, but slightly smaller than, a
     power of two.  */
  static const unsigned long primes[] =
    {
      (unsigned long) 31,
      (unsigned long) 61,
      (unsigned long) 127,
      (unsigned long) 251,
      (unsigned long) 509,
      (unsigned long) 1021,
      (unsigned long) 2039,
      (unsigned long) 4093,
      (unsigned long) 8191,
      (unsigned long) 16381,
      (unsigned long) 32749,
      (unsigned long) 65521,
      (unsigned long) 131071,
      (unsigned long) 262139,
      (unsigned long) 524287,
      (unsigned long) 1048573,
      (unsigned long) 2097143,
      (unsigned long) 4194301,
      (unsigned long) 8388593,
      (unsigned long) 16777213,
      (unsigned long) 33554393,
      (unsigned long) 67108859,
      (unsigned long) 134217689,
      (unsigned long) 268435399,
      (unsigned long) 536870909,
      (unsigned long) 1073741789,
      (unsigned long) 2147483647,
					/* 4294967291L */
      ((unsigned long) 2147483647) + ((unsigned long) 2147483644),
  };

  const unsigned long *low = &primes[0];
  const unsigned long *high = &primes[sizeof (primes) / sizeof (primes[0])];

  while (low != high)
    {
      const unsigned long *mid = low + (high - low) / 2;
      if (n >= *mid)
	low = mid + 1;
      else
	high = mid;
    }

  if (n >= *low)
    return 0;

  return *low;
}

static unsigned long bfd_default_hash_table_size = DEFAULT_SIZE;

/* Create a new hash table, given a number of entries.  */

bool
bfd_hash_table_init_n (struct bfd_hash_table *table,
		       struct bfd_hash_entry *(*newfunc) (struct bfd_hash_entry *,
							  struct bfd_hash_table *,
							  const char *),
		       unsigned int entsize,
		       unsigned int size)
{
  unsigned long alloc;

  alloc = size;
  alloc *= sizeof (struct bfd_hash_entry *);
  if (alloc / sizeof (struct bfd_hash_entry *) != size)
    {
      bfd_set_error (bfd_error_no_memory);
      return false;
    }

  table->memory = (void *) objalloc_create ();
  if (table->memory == NULL)
    {
      bfd_set_error (bfd_error_no_memory);
      return false;
    }
  table->table = (struct bfd_hash_entry **)
      objalloc_alloc ((struct objalloc *) table->memory, alloc);
  if (table->table == NULL)
    {
      bfd_hash_table_free (table);
      bfd_set_error (bfd_error_no_memory);
      return false;
    }
  memset ((void *) table->table, 0, alloc);
  table->size = size;
  table->entsize = entsize;
  table->count = 0;
  table->frozen = 0;
  table->newfunc = newfunc;
  return true;
}

/* Create a new hash table with the default number of entries.  */

bool
bfd_hash_table_init (struct bfd_hash_table *table,
		     struct bfd_hash_entry *(*newfunc) (struct bfd_hash_entry *,
							struct bfd_hash_table *,
							const char *),
		     unsigned int entsize)
{
  return bfd_hash_table_init_n (table, newfunc, entsize,
				bfd_default_hash_table_size);
}

/* Free a hash table.  */

void
bfd_hash_table_free (struct bfd_hash_table *table)
{
  objalloc_free ((struct objalloc *) table->memory);
  table->memory = NULL;
}

static inline unsigned long
bfd_hash_hash (const char *string, unsigned int *lenp)
{
  const unsigned char *s;
  unsigned long hash;
  unsigned int len;
  unsigned int c;

  BFD_ASSERT (string != NULL);
  hash = 0;
  len = 0;
  s = (const unsigned char *) string;
  while ((c = *s++) != '\0')
    {
      hash += c + (c << 17);
      hash ^= hash >> 2;
    }
  len = (s - (const unsigned char *) string) - 1;
  hash += len + (len << 17);
  hash ^= hash >> 2;
  if (lenp != NULL)
    *lenp = len;
  return hash;
}

/* Look up a string in a hash table.  */

struct bfd_hash_entry *
bfd_hash_lookup (struct bfd_hash_table *table,
		 const char *string,
		 bool create,
		 bool copy)
{
  unsigned long hash;
  struct bfd_hash_entry *hashp;
  unsigned int len;
  unsigned int _index;

  hash = bfd_hash_hash (string, &len);
  _index = hash % table->size;
  for (hashp = table->table[_index];
       hashp != NULL;
       hashp = hashp->next)
    {
      if (hashp->hash == hash
	  && strcmp (hashp->string, string) == 0)
	return hashp;
    }

  if (! create)
    return NULL;

  if (copy)
    {
      char *new_string;

      new_string = (char *) objalloc_alloc ((struct objalloc *) table->memory,
					    len + 1);
      if (!new_string)
	{
	  bfd_set_error (bfd_error_no_memory);
	  return NULL;
	}
      memcpy (new_string, string, len + 1);
      string = new_string;
    }

  return bfd_hash_insert (table, string, hash);
}

/* Insert an entry in a hash table.  */

struct bfd_hash_entry *
bfd_hash_insert (struct bfd_hash_table *table,
		 const char *string,
		 unsigned long hash)
{
  struct bfd_hash_entry *hashp;
  unsigned int _index;

  hashp = (*table->newfunc) (NULL, table, string);
  if (hashp == NULL)
    return NULL;
  hashp->string = string;
  hashp->hash = hash;
  _index = hash % table->size;
  hashp->next = table->table[_index];
  table->table[_index] = hashp;
  table->count++;

  if (!table->frozen && table->count > table->size * 3 / 4)
    {
      unsigned long newsize = higher_prime_number (table->size);
      struct bfd_hash_entry **newtable;
      unsigned int hi;
      unsigned long alloc = newsize * sizeof (struct bfd_hash_entry *);

      /* If we can't find a higher prime, or we can't possibly alloc
	 that much memory, don't try to grow the table.  */
      if (newsize == 0 || alloc / sizeof (struct bfd_hash_entry *) != newsize)
	{
	  table->frozen = 1;
	  return hashp;
	}

      newtable = ((struct bfd_hash_entry **)
		  objalloc_alloc ((struct objalloc *) table->memory, alloc));
      if (newtable == NULL)
	{
	  table->frozen = 1;
	  return hashp;
	}
      memset (newtable, 0, alloc);

      for (hi = 0; hi < table->size; hi ++)
	while (table->table[hi])
	  {
	    struct bfd_hash_entry *chain = table->table[hi];
	    struct bfd_hash_entry *chain_end = chain;

	    while (chain_end->next && chain_end->next->hash == chain->hash)
	      chain_end = chain_end->next;

	    table->table[hi] = chain_end->next;
	    _index = chain->hash % newsize;
	    chain_end->next = newtable[_index];
	    newtable[_index] = chain;
	  }
      table->table = newtable;
      table->size = newsize;
    }

  return hashp;
}

/* Rename an entry in a hash table.  */

void
bfd_hash_rename (struct bfd_hash_table *table,
		 const char *string,
		 struct bfd_hash_entry *ent)
{
  unsigned int _index;
  struct bfd_hash_entry **pph;

  _index = ent->hash % table->size;
  for (pph = &table->table[_index]; *pph != NULL; pph = &(*pph)->next)
    if (*pph == ent)
      break;
  if (*pph == NULL)
    abort ();

  *pph = ent->next;
  ent->string = string;
  ent->hash = bfd_hash_hash (string, NULL);
  _index = ent->hash % table->size;
  ent->next = table->table[_index];
  table->table[_index] = ent;
}

/* Replace an entry in a hash table.  */

void
bfd_hash_replace (struct bfd_hash_table *table,
		  struct bfd_hash_entry *old,
		  struct bfd_hash_entry *nw)
{
  unsigned int _index;
  struct bfd_hash_entry **pph;

  _index = old->hash % table->size;
  for (pph = &table->table[_index];
       (*pph) != NULL;
       pph = &(*pph)->next)
    {
      if (*pph == old)
	{
	  *pph = nw;
	  return;
	}
    }

  abort ();
}

/* Allocate space in a hash table.  */

void *
bfd_hash_allocate (struct bfd_hash_table *table,
		   unsigned int size)
{
  void * ret;

  ret = objalloc_alloc ((struct objalloc *) table->memory, size);
  if (ret == NULL && size != 0)
    bfd_set_error (bfd_error_no_memory);
  return ret;
}

/* Base method for creating a new hash table entry.  */

struct bfd_hash_entry *
bfd_hash_newfunc (struct bfd_hash_entry *entry,
		  struct bfd_hash_table *table,
		  const char *string ATTRIBUTE_UNUSED)
{
  if (entry == NULL)
    entry = (struct bfd_hash_entry *) bfd_hash_allocate (table,
							 sizeof (* entry));
  return entry;
}

/* Traverse a hash table.  */

void
bfd_hash_traverse (struct bfd_hash_table *table,
		   bool (*func) (struct bfd_hash_entry *, void *),
		   void * info)
{
  unsigned int i;

  table->frozen = 1;
  for (i = 0; i < table->size; i++)
    {
      struct bfd_hash_entry *p;

      for (p = table->table[i]; p != NULL; p = p->next)
	if (! (*func) (p, info))
	  goto out;
    }
 out:
  table->frozen = 0;
}

unsigned long
bfd_hash_set_default_size (unsigned long hash_size)
{
  /* These silly_size values result in around 1G and 32M of memory
     being allocated for the table of pointers.  Note that the number
     of elements allocated will be almost twice the size of any power
     of two chosen here.  */
  unsigned long silly_size = sizeof (size_t) > 4 ? 0x4000000 : 0x400000;
  if (hash_size > silly_size)
    hash_size = silly_size;
  else if (hash_size != 0)
    hash_size--;
  hash_size = higher_prime_number (hash_size);
  BFD_ASSERT (hash_size != 0);
  bfd_default_hash_table_size = hash_size;
  return bfd_default_hash_table_size;
}

/* A few different object file formats (a.out, COFF, ELF) use a string
   table.  These functions support adding strings to a string table,
   returning the byte offset, and writing out the table.

   Possible improvements:
   + look for strings matching trailing substrings of other strings
   + better data structures?  balanced trees?
   + look at reducing memory use elsewhere -- maybe if we didn't have
     to construct the entire symbol table at once, we could get by
     with smaller amounts of VM?  (What effect does that have on the
     string table reductions?)  */

/* An entry in the strtab hash table.  */

struct strtab_hash_entry
{
  struct bfd_hash_entry root;
  /* Index in string table.  */
  bfd_size_type index;
  /* Next string in strtab.  */
  struct strtab_hash_entry *next;
};

/* The strtab hash table.  */

struct bfd_strtab_hash
{
  struct bfd_hash_table table;
  /* Size of strtab--also next available index.  */
  bfd_size_type size;
  /* First string in strtab.  */
  struct strtab_hash_entry *first;
  /* Last string in strtab.  */
  struct strtab_hash_entry *last;
  /* Whether to precede strings with a two or four byte length,
     as in the XCOFF .debug section.  */
  char length_field_size;
};


/* Routine to create an entry in a strtab.  */

static struct bfd_hash_entry *
strtab_hash_newfunc (struct bfd_hash_entry *entry,
		     struct bfd_hash_table *table,
		     const char *string)
{
  struct strtab_hash_entry *ret = (struct strtab_hash_entry *) entry;

  /* Allocate the structure if it has not already been allocated by a
     subclass.  */
  if (ret == NULL)
    ret = (struct strtab_hash_entry *) bfd_hash_allocate (table,
							  sizeof (* ret));
  if (ret == NULL)
    return NULL;

  /* Call the allocation method of the superclass.  */
  ret = (struct strtab_hash_entry *)
	 bfd_hash_newfunc ((struct bfd_hash_entry *) ret, table, string);

  if (ret)
    {
      /* Initialize the local fields.  */
      ret->index = (bfd_size_type) -1;
      ret->next = NULL;
    }

  return (struct bfd_hash_entry *) ret;
}

/* Look up an entry in an strtab.  */

#define strtab_hash_lookup(t, string, create, copy) \
  ((struct strtab_hash_entry *) \
   bfd_hash_lookup (&(t)->table, (string), (create), (copy)))

/* Create a new strtab.  */

struct bfd_strtab_hash *
_bfd_stringtab_init (void)
{
  struct bfd_strtab_hash *table;
  size_t amt = sizeof (* table);

  table = (struct bfd_strtab_hash *) bfd_malloc (amt);
  if (table == NULL)
    return NULL;

  if (!bfd_hash_table_init (&table->table, strtab_hash_newfunc,
			    sizeof (struct strtab_hash_entry)))
    {
      free (table);
      return NULL;
    }

  table->size = 0;
  table->first = NULL;
  table->last = NULL;
  table->length_field_size = 0;

  return table;
}

/* Create a new strtab in which the strings are output in the format
   used in the XCOFF .debug section: a two byte length precedes each
   string.  */

struct bfd_strtab_hash *
_bfd_xcoff_stringtab_init (bool isxcoff64)
{
  struct bfd_strtab_hash *ret;

  ret = _bfd_stringtab_init ();
  if (ret != NULL)
    ret->length_field_size = isxcoff64 ? 4 : 2;
  return ret;
}

/* Free a strtab.  */

void
_bfd_stringtab_free (struct bfd_strtab_hash *table)
{
  bfd_hash_table_free (&table->table);
  free (table);
}

/* Get the index of a string in a strtab, adding it if it is not
   already present.  If HASH is FALSE, we don't really use the hash
   table, and we don't eliminate duplicate strings.  If COPY is true
   then store a copy of STR if creating a new entry.  */

bfd_size_type
_bfd_stringtab_add (struct bfd_strtab_hash *tab,
		    const char *str,
		    bool hash,
		    bool copy)
{
  struct strtab_hash_entry *entry;

  if (hash)
    {
      entry = strtab_hash_lookup (tab, str, true, copy);
      if (entry == NULL)
	return (bfd_size_type) -1;
    }
  else
    {
      entry = (struct strtab_hash_entry *) bfd_hash_allocate (&tab->table,
							      sizeof (* entry));
      if (entry == NULL)
	return (bfd_size_type) -1;
      if (! copy)
	entry->root.string = str;
      else
	{
	  size_t len = strlen (str) + 1;
	  char *n;

	  n = (char *) bfd_hash_allocate (&tab->table, len);
	  if (n == NULL)
	    return (bfd_size_type) -1;
	  memcpy (n, str, len);
	  entry->root.string = n;
	}
      entry->index = (bfd_size_type) -1;
      entry->next = NULL;
    }

  if (entry->index == (bfd_size_type) -1)
    {
      entry->index = tab->size;
      tab->size += strlen (str) + 1;
      entry->index += tab->length_field_size;
      tab->size += tab->length_field_size;
      if (tab->first == NULL)
	tab->first = entry;
      else
	tab->last->next = entry;
      tab->last = entry;
    }

  return entry->index;
}

/* Get the number of bytes in a strtab.  */

bfd_size_type
_bfd_stringtab_size (struct bfd_strtab_hash *tab)
{
  return tab->size;
}

/* Write out a strtab.  ABFD must already be at the right location in
   the file.  */

bool
_bfd_stringtab_emit (bfd *abfd, struct bfd_strtab_hash *tab)
{
  struct strtab_hash_entry *entry;

  for (entry = tab->first; entry != NULL; entry = entry->next)
    {
      const char *str;
      size_t len;

      str = entry->root.string;
      len = strlen (str) + 1;

      if (tab->length_field_size == 4)
	{
	  bfd_byte buf[4];

	  /* The output length includes the null byte.  */
	  bfd_put_32 (abfd, (bfd_vma) len, buf);
	  if (bfd_bwrite ((void *) buf, (bfd_size_type) 4, abfd) != 4)
	    return false;
	}
      else if (tab->length_field_size == 2)
	{
	  bfd_byte buf[2];

	  /* The output length includes the null byte.  */
	  bfd_put_16 (abfd, (bfd_vma) len, buf);
	  if (bfd_bwrite ((void *) buf, (bfd_size_type) 2, abfd) != 2)
	    return false;
	}

      if (bfd_bwrite ((void *) str, (bfd_size_type) len, abfd) != len)
	return false;
    }

  return true;
}