summaryrefslogtreecommitdiffstats
path: root/common/dlmalloc.src
blob: 12b85bb8302598df38119e1ae6c9c6c8ee905182 (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
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
/* ---------- To make a malloc.h, start cutting here ------------ */

/*
  A version of malloc/free/realloc written by Doug Lea and released to the
  public domain.  Send questions/comments/complaints/performance data
  to dl@cs.oswego.edu

* VERSION 2.6.6  Sun Mar  5 19:10:03 2000  Doug Lea  (dl at gee)

   Note: There may be an updated version of this malloc obtainable at
           ftp://g.oswego.edu/pub/misc/malloc.c
         Check before installing!

* Why use this malloc?

  This is not the fastest, most space-conserving, most portable, or
  most tunable malloc ever written. However it is among the fastest
  while also being among the most space-conserving, portable and tunable.
  Consistent balance across these factors results in a good general-purpose
  allocator. For a high-level description, see
     http://g.oswego.edu/dl/html/malloc.html

* Synopsis of public routines

  (Much fuller descriptions are contained in the program documentation below.)

  malloc(size_t n);
     Return a pointer to a newly allocated chunk of at least n bytes, or null
     if no space is available.
  free(Void_t* p);
     Release the chunk of memory pointed to by p, or no effect if p is null.
  realloc(Void_t* p, size_t n);
     Return a pointer to a chunk of size n that contains the same data
     as does chunk p up to the minimum of (n, p's size) bytes, or null
     if no space is available. The returned pointer may or may not be
     the same as p. If p is null, equivalent to malloc.  Unless the
     #define REALLOC_ZERO_BYTES_FREES below is set, realloc with a
     size argument of zero (re)allocates a minimum-sized chunk.
  memalign(size_t alignment, size_t n);
     Return a pointer to a newly allocated chunk of n bytes, aligned
     in accord with the alignment argument, which must be a power of
     two.
  valloc(size_t n);
     Equivalent to memalign(pagesize, n), where pagesize is the page
     size of the system (or as near to this as can be figured out from
     all the includes/defines below.)
  pvalloc(size_t n);
     Equivalent to valloc(minimum-page-that-holds(n)), that is,
     round up n to nearest pagesize.
  calloc(size_t unit, size_t quantity);
     Returns a pointer to quantity * unit bytes, with all locations
     set to zero.
  cfree(Void_t* p);
     Equivalent to free(p).
  malloc_trim(size_t pad);
     Release all but pad bytes of freed top-most memory back
     to the system. Return 1 if successful, else 0.
  malloc_usable_size(Void_t* p);
     Report the number usable allocated bytes associated with allocated
     chunk p. This may or may not report more bytes than were requested,
     due to alignment and minimum size constraints.
  malloc_stats();
     Prints brief summary statistics on stderr.
  mallinfo()
     Returns (by copy) a struct containing various summary statistics.
  mallopt(int parameter_number, int parameter_value)
     Changes one of the tunable parameters described below. Returns
     1 if successful in changing the parameter, else 0.

* Vital statistics:

  Alignment:                            8-byte
       8 byte alignment is currently hardwired into the design.  This
       seems to suffice for all current machines and C compilers.

  Assumed pointer representation:       4 or 8 bytes
       Code for 8-byte pointers is untested by me but has worked
       reliably by Wolfram Gloger, who contributed most of the
       changes supporting this.

  Assumed size_t  representation:       4 or 8 bytes
       Note that size_t is allowed to be 4 bytes even if pointers are 8.

  Minimum overhead per allocated chunk: 4 or 8 bytes
       Each malloced chunk has a hidden overhead of 4 bytes holding size
       and status information.

  Minimum allocated size: 4-byte ptrs:  16 bytes    (including 4 overhead)
                          8-byte ptrs:  24/32 bytes (including, 4/8 overhead)

       When a chunk is freed, 12 (for 4byte ptrs) or 20 (for 8 byte
       ptrs but 4 byte size) or 24 (for 8/8) additional bytes are
       needed; 4 (8) for a trailing size field
       and 8 (16) bytes for free list pointers. Thus, the minimum
       allocatable size is 16/24/32 bytes.

       Even a request for zero bytes (i.e., malloc(0)) returns a
       pointer to something of the minimum allocatable size.

  Maximum allocated size: 4-byte size_t: 2^31 -  8 bytes
                          8-byte size_t: 2^63 - 16 bytes

       It is assumed that (possibly signed) size_t bit values suffice to
       represent chunk sizes. `Possibly signed' is due to the fact
       that `size_t' may be defined on a system as either a signed or
       an unsigned type. To be conservative, values that would appear
       as negative numbers are avoided.
       Requests for sizes with a negative sign bit when the request
       size is treaded as a long will return null.

  Maximum overhead wastage per allocated chunk: normally 15 bytes

       Alignnment demands, plus the minimum allocatable size restriction
       make the normal worst-case wastage 15 bytes (i.e., up to 15
       more bytes will be allocated than were requested in malloc), with
       two exceptions:
         1. Because requests for zero bytes allocate non-zero space,
            the worst case wastage for a request of zero bytes is 24 bytes.
         2. For requests >= mmap_threshold that are serviced via
            mmap(), the worst case wastage is 8 bytes plus the remainder
            from a system page (the minimal mmap unit); typically 4096 bytes.

* Limitations

    Here are some features that are NOT currently supported

    * No user-definable hooks for callbacks and the like.
    * No automated mechanism for fully checking that all accesses
      to malloced memory stay within their bounds.
    * No support for compaction.

* Synopsis of compile-time options:

    People have reported using previous versions of this malloc on all
    versions of Unix, sometimes by tweaking some of the defines
    below. It has been tested most extensively on Solaris and
    Linux. It is also reported to work on WIN32 platforms.
    People have also reported adapting this malloc for use in
    stand-alone embedded systems.

    The implementation is in straight, hand-tuned ANSI C.  Among other
    consequences, it uses a lot of macros.  Because of this, to be at
    all usable, this code should be compiled using an optimizing compiler
    (for example gcc -O2) that can simplify expressions and control
    paths.

  __STD_C                  (default: derived from C compiler defines)
     Nonzero if using ANSI-standard C compiler, a C++ compiler, or
     a C compiler sufficiently close to ANSI to get away with it.
  DEBUG                    (default: NOT defined)
     Define to enable debugging. Adds fairly extensive assertion-based
     checking to help track down memory errors, but noticeably slows down
     execution.
  REALLOC_ZERO_BYTES_FREES (default: NOT defined)
     Define this if you think that realloc(p, 0) should be equivalent
     to free(p). Otherwise, since malloc returns a unique pointer for
     malloc(0), so does realloc(p, 0).
  HAVE_MEMCPY               (default: defined)
     Define if you are not otherwise using ANSI STD C, but still
     have memcpy and memset in your C library and want to use them.
     Otherwise, simple internal versions are supplied.
  USE_MEMCPY               (default: 1 if HAVE_MEMCPY is defined, 0 otherwise)
     Define as 1 if you want the C library versions of memset and
     memcpy called in realloc and calloc (otherwise macro versions are used).
     At least on some platforms, the simple macro versions usually
     outperform libc versions.
  HAVE_MMAP                 (default: defined as 1)
     Define to non-zero to optionally make malloc() use mmap() to
     allocate very large blocks.
  HAVE_MREMAP                 (default: defined as 0 unless Linux libc set)
     Define to non-zero to optionally make realloc() use mremap() to
     reallocate very large blocks.
  malloc_getpagesize        (default: derived from system #includes)
     Either a constant or routine call returning the system page size.
  HAVE_USR_INCLUDE_MALLOC_H (default: NOT defined)
     Optionally define if you are on a system with a /usr/include/malloc.h
     that declares struct mallinfo. It is not at all necessary to
     define this even if you do, but will ensure consistency.
  INTERNAL_SIZE_T           (default: size_t)
     Define to a 32-bit type (probably `unsigned int') if you are on a
     64-bit machine, yet do not want or need to allow malloc requests of
     greater than 2^31 to be handled. This saves space, especially for
     very small chunks.
  INTERNAL_LINUX_C_LIB      (default: NOT defined)
     Defined only when compiled as part of Linux libc.
     Also note that there is some odd internal name-mangling via defines
     (for example, internally, `malloc' is named `mALLOc') needed
     when compiling in this case. These look funny but don't otherwise
     affect anything.
  WIN32                     (default: undefined)
     Define this on MS win (95, nt) platforms to compile in sbrk emulation.
  LACKS_UNISTD_H            (default: undefined if not WIN32)
     Define this if your system does not have a <unistd.h>.
  LACKS_SYS_PARAM_H         (default: undefined if not WIN32)
     Define this if your system does not have a <sys/param.h>.
  MORECORE                  (default: sbrk)
     The name of the routine to call to obtain more memory from the system.
  MORECORE_FAILURE          (default: -1)
     The value returned upon failure of MORECORE.
  MORECORE_CLEARS           (default 1)
     True (1) if the routine mapped to MORECORE zeroes out memory (which
     holds for sbrk).
  DEFAULT_TRIM_THRESHOLD
  DEFAULT_TOP_PAD
  DEFAULT_MMAP_THRESHOLD
  DEFAULT_MMAP_MAX
     Default values of tunable parameters (described in detail below)
     controlling interaction with host system routines (sbrk, mmap, etc).
     These values may also be changed dynamically via mallopt(). The
     preset defaults are those that give best performance for typical
     programs/systems.
  USE_DL_PREFIX             (default: undefined)
     Prefix all public routines with the string 'dl'.  Useful to
     quickly avoid procedure declaration conflicts and linker symbol
     conflicts with existing memory allocation routines.


*/




/* Preliminaries */

#ifndef __STD_C
#ifdef __STDC__
#define __STD_C     1
#else
#if __cplusplus
#define __STD_C     1
#else
#define __STD_C     0
#endif /*__cplusplus*/
#endif /*__STDC__*/
#endif /*__STD_C*/

#ifndef Void_t
#if (__STD_C || defined(WIN32))
#define Void_t      void
#else
#define Void_t      char
#endif
#endif /*Void_t*/

#if __STD_C
#include <stddef.h>   /* for size_t */
#else
#include <sys/types.h>
#endif

#ifdef __cplusplus
extern "C" {
#endif

#include <stdio.h>    /* needed for malloc_stats */


/*
  Compile-time options
*/


/*
    Debugging:

    Because freed chunks may be overwritten with link fields, this
    malloc will often die when freed memory is overwritten by user
    programs.  This can be very effective (albeit in an annoying way)
    in helping track down dangling pointers.

    If you compile with -DDEBUG, a number of assertion checks are
    enabled that will catch more memory errors. You probably won't be
    able to make much sense of the actual assertion errors, but they
    should help you locate incorrectly overwritten memory.  The
    checking is fairly extensive, and will slow down execution
    noticeably. Calling malloc_stats or mallinfo with DEBUG set will
    attempt to check every non-mmapped allocated and free chunk in the
    course of computing the summmaries. (By nature, mmapped regions
    cannot be checked very much automatically.)

    Setting DEBUG may also be helpful if you are trying to modify
    this code. The assertions in the check routines spell out in more
    detail the assumptions and invariants underlying the algorithms.

*/

#if DEBUG
#include <assert.h>
#else
#define assert(x) ((void)0)
#endif


/*
  INTERNAL_SIZE_T is the word-size used for internal bookkeeping
  of chunk sizes. On a 64-bit machine, you can reduce malloc
  overhead by defining INTERNAL_SIZE_T to be a 32 bit `unsigned int'
  at the expense of not being able to handle requests greater than
  2^31. This limitation is hardly ever a concern; you are encouraged
  to set this. However, the default version is the same as size_t.
*/

#ifndef INTERNAL_SIZE_T
#define INTERNAL_SIZE_T size_t
#endif

/*
  REALLOC_ZERO_BYTES_FREES should be set if a call to
  realloc with zero bytes should be the same as a call to free.
  Some people think it should. Otherwise, since this malloc
  returns a unique pointer for malloc(0), so does realloc(p, 0).
*/


/*   #define REALLOC_ZERO_BYTES_FREES */


/*
  WIN32 causes an emulation of sbrk to be compiled in
  mmap-based options are not currently supported in WIN32.
*/

/* #define WIN32 */
#ifdef WIN32
#define MORECORE wsbrk
#define HAVE_MMAP 0

#define LACKS_UNISTD_H
#define LACKS_SYS_PARAM_H

/*
  Include 'windows.h' to get the necessary declarations for the
  Microsoft Visual C++ data structures and routines used in the 'sbrk'
  emulation.

  Define WIN32_LEAN_AND_MEAN so that only the essential Microsoft
  Visual C++ header files are included.
*/
#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#endif


/*
  HAVE_MEMCPY should be defined if you are not otherwise using
  ANSI STD C, but still have memcpy and memset in your C library
  and want to use them in calloc and realloc. Otherwise simple
  macro versions are defined here.

  USE_MEMCPY should be defined as 1 if you actually want to
  have memset and memcpy called. People report that the macro
  versions are often enough faster than libc versions on many
  systems that it is better to use them.

*/

#define HAVE_MEMCPY

#ifndef USE_MEMCPY
#ifdef HAVE_MEMCPY
#define USE_MEMCPY 1
#else
#define USE_MEMCPY 0
#endif
#endif

#if (__STD_C || defined(HAVE_MEMCPY))

#if __STD_C
void* memset(void*, int, size_t);
void* memcpy(void*, const void*, size_t);
#else
#ifdef WIN32
// On Win32 platforms, 'memset()' and 'memcpy()' are already declared in
// 'windows.h'
#else
Void_t* memset();
Void_t* memcpy();
#endif
#endif
#endif

#if USE_MEMCPY

/* The following macros are only invoked with (2n+1)-multiples of
   INTERNAL_SIZE_T units, with a positive integer n. This is exploited
   for fast inline execution when n is small. */

#define MALLOC_ZERO(charp, nbytes)                                            \
do {                                                                          \
  INTERNAL_SIZE_T mzsz = (nbytes);                                            \
  if(mzsz <= 9*sizeof(mzsz)) {                                                \
    INTERNAL_SIZE_T* mz = (INTERNAL_SIZE_T*) (charp);                         \
    if(mzsz >= 5*sizeof(mzsz)) {     *mz++ = 0;                               \
                                     *mz++ = 0;                               \
      if(mzsz >= 7*sizeof(mzsz)) {   *mz++ = 0;                               \
                                     *mz++ = 0;                               \
        if(mzsz >= 9*sizeof(mzsz)) { *mz++ = 0;                               \
                                     *mz++ = 0; }}}                           \
                                     *mz++ = 0;                               \
                                     *mz++ = 0;                               \
                                     *mz   = 0;                               \
  } else memset((charp), 0, mzsz);                                            \
} while(0)

#define MALLOC_COPY(dest,src,nbytes)                                          \
do {                                                                          \
  INTERNAL_SIZE_T mcsz = (nbytes);                                            \
  if(mcsz <= 9*sizeof(mcsz)) {                                                \
    INTERNAL_SIZE_T* mcsrc = (INTERNAL_SIZE_T*) (src);                        \
    INTERNAL_SIZE_T* mcdst = (INTERNAL_SIZE_T*) (dest);                       \
    if(mcsz >= 5*sizeof(mcsz)) {     *mcdst++ = *mcsrc++;                     \
                                     *mcdst++ = *mcsrc++;                     \
      if(mcsz >= 7*sizeof(mcsz)) {   *mcdst++ = *mcsrc++;                     \
                                     *mcdst++ = *mcsrc++;                     \
        if(mcsz >= 9*sizeof(mcsz)) { *mcdst++ = *mcsrc++;                     \
                                     *mcdst++ = *mcsrc++; }}}                 \
                                     *mcdst++ = *mcsrc++;                     \
                                     *mcdst++ = *mcsrc++;                     \
                                     *mcdst   = *mcsrc  ;                     \
  } else memcpy(dest, src, mcsz);                                             \
} while(0)

#else /* !USE_MEMCPY */

/* Use Duff's device for good zeroing/copying performance. */

#define MALLOC_ZERO(charp, nbytes)                                            \
do {                                                                          \
  INTERNAL_SIZE_T* mzp = (INTERNAL_SIZE_T*)(charp);                           \
  long mctmp = (nbytes)/sizeof(INTERNAL_SIZE_T), mcn;                         \
  if (mctmp < 8) mcn = 0; else { mcn = (mctmp-1)/8; mctmp %= 8; }             \
  switch (mctmp) {                                                            \
    case 0: for(;;) { *mzp++ = 0;                                             \
    case 7:           *mzp++ = 0;                                             \
    case 6:           *mzp++ = 0;                                             \
    case 5:           *mzp++ = 0;                                             \
    case 4:           *mzp++ = 0;                                             \
    case 3:           *mzp++ = 0;                                             \
    case 2:           *mzp++ = 0;                                             \
    case 1:           *mzp++ = 0; if(mcn <= 0) break; mcn--; }                \
  }                                                                           \
} while(0)

#define MALLOC_COPY(dest,src,nbytes)                                          \
do {                                                                          \
  INTERNAL_SIZE_T* mcsrc = (INTERNAL_SIZE_T*) src;                            \
  INTERNAL_SIZE_T* mcdst = (INTERNAL_SIZE_T*) dest;                           \
  long mctmp = (nbytes)/sizeof(INTERNAL_SIZE_T), mcn;                         \
  if (mctmp < 8) mcn = 0; else { mcn = (mctmp-1)/8; mctmp %= 8; }             \
  switch (mctmp) {                                                            \
    case 0: for(;;) { *mcdst++ = *mcsrc++;                                    \
    case 7:           *mcdst++ = *mcsrc++;                                    \
    case 6:           *mcdst++ = *mcsrc++;                                    \
    case 5:           *mcdst++ = *mcsrc++;                                    \
    case 4:           *mcdst++ = *mcsrc++;                                    \
    case 3:           *mcdst++ = *mcsrc++;                                    \
    case 2:           *mcdst++ = *mcsrc++;                                    \
    case 1:           *mcdst++ = *mcsrc++; if(mcn <= 0) break; mcn--; }       \
  }                                                                           \
} while(0)

#endif


/*
  Define HAVE_MMAP to optionally make malloc() use mmap() to
  allocate very large blocks.  These will be returned to the
  operating system immediately after a free().
*/

#ifndef HAVE_MMAP
#define HAVE_MMAP 1
#endif

/*
  Define HAVE_MREMAP to make realloc() use mremap() to re-allocate
  large blocks.  This is currently only possible on Linux with
  kernel versions newer than 1.3.77.
*/

#ifndef HAVE_MREMAP
#ifdef INTERNAL_LINUX_C_LIB
#define HAVE_MREMAP 1
#else
#define HAVE_MREMAP 0
#endif
#endif

#if HAVE_MMAP

#include <unistd.h>
#include <fcntl.h>
#include <sys/mman.h>

#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON)
#define MAP_ANONYMOUS MAP_ANON
#endif

#endif /* HAVE_MMAP */

/*
  Access to system page size. To the extent possible, this malloc
  manages memory from the system in page-size units.

  The following mechanics for getpagesize were adapted from
  bsd/gnu getpagesize.h
*/

#ifndef LACKS_UNISTD_H
#  include <unistd.h>
#endif

#ifndef malloc_getpagesize
#  ifdef _SC_PAGESIZE         /* some SVR4 systems omit an underscore */
#    ifndef _SC_PAGE_SIZE
#      define _SC_PAGE_SIZE _SC_PAGESIZE
#    endif
#  endif
#  ifdef _SC_PAGE_SIZE
#    define malloc_getpagesize sysconf(_SC_PAGE_SIZE)
#  else
#    if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE)
       extern size_t getpagesize();
#      define malloc_getpagesize getpagesize()
#    else
#      ifdef WIN32
#        define malloc_getpagesize (4096) /* TBD: Use 'GetSystemInfo' instead */
#      else
#        ifndef LACKS_SYS_PARAM_H
#          include <sys/param.h>
#        endif
#        ifdef EXEC_PAGESIZE
#          define malloc_getpagesize EXEC_PAGESIZE
#        else
#          ifdef NBPG
#            ifndef CLSIZE
#              define malloc_getpagesize NBPG
#            else
#              define malloc_getpagesize (NBPG * CLSIZE)
#            endif
#          else
#            ifdef NBPC
#              define malloc_getpagesize NBPC
#            else
#              ifdef PAGESIZE
#                define malloc_getpagesize PAGESIZE
#              else
#                define malloc_getpagesize (4096) /* just guess */
#              endif
#            endif
#          endif
#        endif
#      endif
#    endif
#  endif
#endif



/*

  This version of malloc supports the standard SVID/XPG mallinfo
  routine that returns a struct containing the same kind of
  information you can get from malloc_stats. It should work on
  any SVID/XPG compliant system that has a /usr/include/malloc.h
  defining struct mallinfo. (If you'd like to install such a thing
  yourself, cut out the preliminary declarations as described above
  and below and save them in a malloc.h file. But there's no
  compelling reason to bother to do this.)

  The main declaration needed is the mallinfo struct that is returned
  (by-copy) by mallinfo().  The SVID/XPG malloinfo struct contains a
  bunch of fields, most of which are not even meaningful in this
  version of malloc. Some of these fields are are instead filled by
  mallinfo() with other numbers that might possibly be of interest.

  HAVE_USR_INCLUDE_MALLOC_H should be set if you have a
  /usr/include/malloc.h file that includes a declaration of struct
  mallinfo.  If so, it is included; else an SVID2/XPG2 compliant
  version is declared below.  These must be precisely the same for
  mallinfo() to work.

*/

/* #define HAVE_USR_INCLUDE_MALLOC_H */

#if HAVE_USR_INCLUDE_MALLOC_H
#include "/usr/include/malloc.h"
#else

/* SVID2/XPG mallinfo structure */

struct mallinfo {
  int arena;    /* total space allocated from system */
  int ordblks;  /* number of non-inuse chunks */
  int smblks;   /* unused -- always zero */
  int hblks;    /* number of mmapped regions */
  int hblkhd;   /* total space in mmapped regions */
  int usmblks;  /* unused -- always zero */
  int fsmblks;  /* unused -- always zero */
  int uordblks; /* total allocated space */
  int fordblks; /* total non-inuse space */
  int keepcost; /* top-most, releasable (via malloc_trim) space */
};

/* SVID2/XPG mallopt options */

#define M_MXFAST  1    /* UNUSED in this malloc */
#define M_NLBLKS  2    /* UNUSED in this malloc */
#define M_GRAIN   3    /* UNUSED in this malloc */
#define M_KEEP    4    /* UNUSED in this malloc */

#endif

/* mallopt options that actually do something */

#define M_TRIM_THRESHOLD    -1
#define M_TOP_PAD           -2
#define M_MMAP_THRESHOLD    -3
#define M_MMAP_MAX          -4



#ifndef DEFAULT_TRIM_THRESHOLD
#define DEFAULT_TRIM_THRESHOLD (128 * 1024)
#endif

/*
    M_TRIM_THRESHOLD is the maximum amount of unused top-most memory
      to keep before releasing via malloc_trim in free().

      Automatic trimming is mainly useful in long-lived programs.
      Because trimming via sbrk can be slow on some systems, and can
      sometimes be wasteful (in cases where programs immediately
      afterward allocate more large chunks) the value should be high
      enough so that your overall system performance would improve by
      releasing.

      The trim threshold and the mmap control parameters (see below)
      can be traded off with one another. Trimming and mmapping are
      two different ways of releasing unused memory back to the
      system. Between these two, it is often possible to keep
      system-level demands of a long-lived program down to a bare
      minimum. For example, in one test suite of sessions measuring
      the XF86 X server on Linux, using a trim threshold of 128K and a
      mmap threshold of 192K led to near-minimal long term resource
      consumption.

      If you are using this malloc in a long-lived program, it should
      pay to experiment with these values.  As a rough guide, you
      might set to a value close to the average size of a process
      (program) running on your system.  Releasing this much memory
      would allow such a process to run in memory.  Generally, it's
      worth it to tune for trimming rather tham memory mapping when a
      program undergoes phases where several large chunks are
      allocated and released in ways that can reuse each other's
      storage, perhaps mixed with phases where there are no such
      chunks at all.  And in well-behaved long-lived programs,
      controlling release of large blocks via trimming versus mapping
      is usually faster.

      However, in most programs, these parameters serve mainly as
      protection against the system-level effects of carrying around
      massive amounts of unneeded memory. Since frequent calls to
      sbrk, mmap, and munmap otherwise degrade performance, the default
      parameters are set to relatively high values that serve only as
      safeguards.

      The default trim value is high enough to cause trimming only in
      fairly extreme (by current memory consumption standards) cases.
      It must be greater than page size to have any useful effect.  To
      disable trimming completely, you can set to (unsigned long)(-1);


*/


#ifndef DEFAULT_TOP_PAD
#define DEFAULT_TOP_PAD        (0)
#endif

/*
    M_TOP_PAD is the amount of extra `padding' space to allocate or
      retain whenever sbrk is called. It is used in two ways internally:

      * When sbrk is called to extend the top of the arena to satisfy
        a new malloc request, this much padding is added to the sbrk
        request.

      * When malloc_trim is called automatically from free(),
        it is used as the `pad' argument.

      In both cases, the actual amount of padding is rounded
      so that the end of the arena is always a system page boundary.

      The main reason for using padding is to avoid calling sbrk so
      often. Having even a small pad greatly reduces the likelihood
      that nearly every malloc request during program start-up (or
      after trimming) will invoke sbrk, which needlessly wastes
      time.

      Automatic rounding-up to page-size units is normally sufficient
      to avoid measurable overhead, so the default is 0.  However, in
      systems where sbrk is relatively slow, it can pay to increase
      this value, at the expense of carrying around more memory than
      the program needs.

*/


#ifndef DEFAULT_MMAP_THRESHOLD
#define DEFAULT_MMAP_THRESHOLD (128 * 1024)
#endif

/*

    M_MMAP_THRESHOLD is the request size threshold for using mmap()
      to service a request. Requests of at least this size that cannot
      be allocated using already-existing space will be serviced via mmap.
      (If enough normal freed space already exists it is used instead.)

      Using mmap segregates relatively large chunks of memory so that
      they can be individually obtained and released from the host
      system. A request serviced through mmap is never reused by any
      other request (at least not directly; the system may just so
      happen to remap successive requests to the same locations).

      Segregating space in this way has the benefit that mmapped space
      can ALWAYS be individually released back to the system, which
      helps keep the system level memory demands of a long-lived
      program low. Mapped memory can never become `locked' between
      other chunks, as can happen with normally allocated chunks, which
      menas that even trimming via malloc_trim would not release them.

      However, it has the disadvantages that:

         1. The space cannot be reclaimed, consolidated, and then
            used to service later requests, as happens with normal chunks.
         2. It can lead to more wastage because of mmap page alignment
            requirements
         3. It causes malloc performance to be more dependent on host
            system memory management support routines which may vary in
            implementation quality and may impose arbitrary
            limitations. Generally, servicing a request via normal
            malloc steps is faster than going through a system's mmap.

      All together, these considerations should lead you to use mmap
      only for relatively large requests.


*/



#ifndef DEFAULT_MMAP_MAX
#if HAVE_MMAP
#define DEFAULT_MMAP_MAX       (64)
#else
#define DEFAULT_MMAP_MAX       (0)
#endif
#endif

/*
    M_MMAP_MAX is the maximum number of requests to simultaneously
      service using mmap. This parameter exists because:

         1. Some systems have a limited number of internal tables for
            use by mmap.
         2. In most systems, overreliance on mmap can degrade overall
            performance.
         3. If a program allocates many large regions, it is probably
            better off using normal sbrk-based allocation routines that
            can reclaim and reallocate normal heap memory. Using a
            small value allows transition into this mode after the
            first few allocations.

      Setting to 0 disables all use of mmap.  If HAVE_MMAP is not set,
      the default value is 0, and attempts to set it to non-zero values
      in mallopt will fail.
*/




/*
    USE_DL_PREFIX will prefix all public routines with the string 'dl'.
      Useful to quickly avoid procedure declaration conflicts and linker
      symbol conflicts with existing memory allocation routines.

*/

/* #define USE_DL_PREFIX */




/*

  Special defines for linux libc

  Except when compiled using these special defines for Linux libc
  using weak aliases, this malloc is NOT designed to work in
  multithreaded applications.  No semaphores or other concurrency
  control are provided to ensure that multiple malloc or free calls
  don't run at the same time, which could be disasterous. A single
  semaphore could be used across malloc, realloc, and free (which is
  essentially the effect of the linux weak alias approach). It would
  be hard to obtain finer granularity.

*/


#ifdef INTERNAL_LINUX_C_LIB

#if __STD_C

Void_t * __default_morecore_init (ptrdiff_t);
Void_t *(*__morecore)(ptrdiff_t) = __default_morecore_init;

#else

Void_t * __default_morecore_init ();
Void_t *(*__morecore)() = __default_morecore_init;

#endif

#define MORECORE (*__morecore)
#define MORECORE_FAILURE 0
#define MORECORE_CLEARS 1

#else /* INTERNAL_LINUX_C_LIB */

#if __STD_C
extern Void_t*     sbrk(ptrdiff_t);
#else
extern Void_t*     sbrk();
#endif

#ifndef MORECORE
#define MORECORE sbrk
#endif

#ifndef MORECORE_FAILURE
#define MORECORE_FAILURE -1
#endif

#ifndef MORECORE_CLEARS
#define MORECORE_CLEARS 1
#endif

#endif /* INTERNAL_LINUX_C_LIB */

#if defined(INTERNAL_LINUX_C_LIB) && defined(__ELF__)

#define cALLOc		__libc_calloc
#define fREe		__libc_free
#define mALLOc		__libc_malloc
#define mEMALIGn	__libc_memalign
#define rEALLOc		__libc_realloc
#define vALLOc		__libc_valloc
#define pvALLOc		__libc_pvalloc
#define mALLINFo	__libc_mallinfo
#define mALLOPt		__libc_mallopt

#pragma weak calloc = __libc_calloc
#pragma weak free = __libc_free
#pragma weak cfree = __libc_free
#pragma weak malloc = __libc_malloc
#pragma weak memalign = __libc_memalign
#pragma weak realloc = __libc_realloc
#pragma weak valloc = __libc_valloc
#pragma weak pvalloc = __libc_pvalloc
#pragma weak mallinfo = __libc_mallinfo
#pragma weak mallopt = __libc_mallopt

#else

#ifdef USE_DL_PREFIX
#define cALLOc		dlcalloc
#define fREe		dlfree
#define mALLOc		dlmalloc
#define mEMALIGn	dlmemalign
#define rEALLOc		dlrealloc
#define vALLOc		dlvalloc
#define pvALLOc		dlpvalloc
#define mALLINFo	dlmallinfo
#define mALLOPt		dlmallopt
#else /* USE_DL_PREFIX */
#define cALLOc		calloc
#define fREe		free
#define mALLOc		malloc
#define mEMALIGn	memalign
#define rEALLOc		realloc
#define vALLOc		valloc
#define pvALLOc		pvalloc
#define mALLINFo	mallinfo
#define mALLOPt		mallopt
#endif /* USE_DL_PREFIX */

#endif

/* Public routines */

#if __STD_C

Void_t* mALLOc(size_t);
void    fREe(Void_t*);
Void_t* rEALLOc(Void_t*, size_t);
Void_t* mEMALIGn(size_t, size_t);
Void_t* vALLOc(size_t);
Void_t* pvALLOc(size_t);
Void_t* cALLOc(size_t, size_t);
void    cfree(Void_t*);
int     malloc_trim(size_t);
size_t  malloc_usable_size(Void_t*);
void    malloc_stats();
int     mALLOPt(int, int);
struct mallinfo mALLINFo(void);
#else
Void_t* mALLOc();
void    fREe();
Void_t* rEALLOc();
Void_t* mEMALIGn();
Void_t* vALLOc();
Void_t* pvALLOc();
Void_t* cALLOc();
void    cfree();
int     malloc_trim();
size_t  malloc_usable_size();
void    malloc_stats();
int     mALLOPt();
struct mallinfo mALLINFo();
#endif


#ifdef __cplusplus
};  /* end of extern "C" */
#endif

/* ---------- To make a malloc.h, end cutting here ------------ */


/*
  Emulation of sbrk for WIN32
  All code within the ifdef WIN32 is untested by me.

  Thanks to Martin Fong and others for supplying this.
*/


#ifdef WIN32

#define AlignPage(add) (((add) + (malloc_getpagesize-1)) & \
~(malloc_getpagesize-1))
#define AlignPage64K(add) (((add) + (0x10000 - 1)) & ~(0x10000 - 1))

/* resrve 64MB to insure large contiguous space */
#define RESERVED_SIZE (1024*1024*64)
#define NEXT_SIZE (2048*1024)
#define TOP_MEMORY ((unsigned long)2*1024*1024*1024)

struct GmListElement;
typedef struct GmListElement GmListElement;

struct GmListElement
{
	GmListElement* next;
	void* base;
};

static GmListElement* head = 0;
static unsigned int gNextAddress = 0;
static unsigned int gAddressBase = 0;
static unsigned int gAllocatedSize = 0;

static
GmListElement* makeGmListElement (void* bas)
{
	GmListElement* this;
	this = (GmListElement*)(void*)LocalAlloc (0, sizeof (GmListElement));
	assert (this);
	if (this)
	{
		this->base = bas;
		this->next = head;
		head = this;
	}
	return this;
}

void gcleanup ()
{
	BOOL rval;
	assert ( (head == NULL) || (head->base == (void*)gAddressBase));
	if (gAddressBase && (gNextAddress - gAddressBase))
	{
		rval = VirtualFree ((void*)gAddressBase,
							gNextAddress - gAddressBase,
							MEM_DECOMMIT);
        assert (rval);
	}
	while (head)
	{
		GmListElement* next = head->next;
		rval = VirtualFree (head->base, 0, MEM_RELEASE);
		assert (rval);
		LocalFree (head);
		head = next;
	}
}

static
void* findRegion (void* start_address, unsigned long size)
{
	MEMORY_BASIC_INFORMATION info;
	if (size >= TOP_MEMORY) return NULL;

	while ((unsigned long)start_address + size < TOP_MEMORY)
	{
		VirtualQuery (start_address, &info, sizeof (info));
		if ((info.State == MEM_FREE) && (info.RegionSize >= size))
			return start_address;
		else
		{
			// Requested region is not available so see if the
			// next region is available.  Set 'start_address'
			// to the next region and call 'VirtualQuery()'
			// again.

			start_address = (char*)info.BaseAddress + info.RegionSize;

			// Make sure we start looking for the next region
			// on the *next* 64K boundary.  Otherwise, even if
			// the new region is free according to
			// 'VirtualQuery()', the subsequent call to
			// 'VirtualAlloc()' (which follows the call to
			// this routine in 'wsbrk()') will round *down*
			// the requested address to a 64K boundary which
			// we already know is an address in the
			// unavailable region.  Thus, the subsequent call
			// to 'VirtualAlloc()' will fail and bring us back
			// here, causing us to go into an infinite loop.

			start_address =
				(void *) AlignPage64K((unsigned long) start_address);
		}
	}
	return NULL;

}


void* wsbrk (long size)
{
	void* tmp;
	if (size > 0)
	{
		if (gAddressBase == 0)
		{
			gAllocatedSize = max (RESERVED_SIZE, AlignPage (size));
			gNextAddress = gAddressBase =
				(unsigned int)VirtualAlloc (NULL, gAllocatedSize,
											MEM_RESERVE, PAGE_NOACCESS);
		} else if (AlignPage (gNextAddress + size) > (gAddressBase +
gAllocatedSize))
		{
			long new_size = max (NEXT_SIZE, AlignPage (size));
			void* new_address = (void*)(gAddressBase+gAllocatedSize);
			do
			{
				new_address = findRegion (new_address, new_size);

				if (new_address == 0)
					return (void*)-1;

				gAddressBase = gNextAddress =
					(unsigned int)VirtualAlloc (new_address, new_size,
												MEM_RESERVE, PAGE_NOACCESS);
				// repeat in case of race condition
				// The region that we found has been snagged
				// by another thread
			}
			while (gAddressBase == 0);

			assert (new_address == (void*)gAddressBase);

			gAllocatedSize = new_size;

			if (!makeGmListElement ((void*)gAddressBase))
				return (void*)-1;
		}
		if ((size + gNextAddress) > AlignPage (gNextAddress))
		{
			void* res;
			res = VirtualAlloc ((void*)AlignPage (gNextAddress),
								(size + gNextAddress -
								 AlignPage (gNextAddress)),
								MEM_COMMIT, PAGE_READWRITE);
			if (res == 0)
				return (void*)-1;
		}
		tmp = (void*)gNextAddress;
		gNextAddress = (unsigned int)tmp + size;
		return tmp;
	}
	else if (size < 0)
	{
		unsigned int alignedGoal = AlignPage (gNextAddress + size);
		/* Trim by releasing the virtual memory */
		if (alignedGoal >= gAddressBase)
		{
			VirtualFree ((void*)alignedGoal, gNextAddress - alignedGoal,
						 MEM_DECOMMIT);
			gNextAddress = gNextAddress + size;
			return (void*)gNextAddress;
		}
		else
		{
			VirtualFree ((void*)gAddressBase, gNextAddress - gAddressBase,
						 MEM_DECOMMIT);
			gNextAddress = gAddressBase;
			return (void*)-1;
		}
	}
	else
	{
		return (void*)gNextAddress;
	}
}

#endif



/*
  Type declarations
*/


struct malloc_chunk
{
  INTERNAL_SIZE_T prev_size; /* Size of previous chunk (if free). */
  INTERNAL_SIZE_T size;      /* Size in bytes, including overhead. */
  struct malloc_chunk* fd;   /* double links -- used only if free. */
  struct malloc_chunk* bk;
};

typedef struct malloc_chunk* mchunkptr;

/*

   malloc_chunk details:

    (The following includes lightly edited explanations by Colin Plumb.)

    Chunks of memory are maintained using a `boundary tag' method as
    described in e.g., Knuth or Standish.  (See the paper by Paul
    Wilson ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a
    survey of such techniques.)  Sizes of free chunks are stored both
    in the front of each chunk and at the end.  This makes
    consolidating fragmented chunks into bigger chunks very fast.  The
    size fields also hold bits representing whether chunks are free or
    in use.

    An allocated chunk looks like this:


    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Size of previous chunk, if allocated            | |
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Size of chunk, in bytes                         |P|
      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             User data starts here...                          .
            .                                                               .
            .             (malloc_usable_space() bytes)                     .
            .                                                               |
nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Size of chunk                                     |
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+


    Where "chunk" is the front of the chunk for the purpose of most of
    the malloc code, but "mem" is the pointer that is returned to the
    user.  "Nextchunk" is the beginning of the next contiguous chunk.

    Chunks always begin on even word boundries, so the mem portion
    (which is returned to the user) is also on an even word boundary, and
    thus double-word aligned.

    Free chunks are stored in circular doubly-linked lists, and look like this:

    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Size of previous chunk                            |
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    `head:' |             Size of chunk, in bytes                         |P|
      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Forward pointer to next chunk in list             |
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Back pointer to previous chunk in list            |
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
            |             Unused space (may be 0 bytes long)                .
            .                                                               .
            .                                                               |
nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    `foot:' |             Size of chunk, in bytes                           |
            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

    The P (PREV_INUSE) bit, stored in the unused low-order bit of the
    chunk size (which is always a multiple of two words), is an in-use
    bit for the *previous* chunk.  If that bit is *clear*, then the
    word before the current chunk size contains the previous chunk
    size, and can be used to find the front of the previous chunk.
    (The very first chunk allocated always has this bit set,
    preventing access to non-existent (or non-owned) memory.)

    Note that the `foot' of the current chunk is actually represented
    as the prev_size of the NEXT chunk. (This makes it easier to
    deal with alignments etc).

    The two exceptions to all this are

     1. The special chunk `top', which doesn't bother using the
        trailing size field since there is no
        next contiguous chunk that would have to index off it. (After
        initialization, `top' is forced to always exist.  If it would
        become less than MINSIZE bytes long, it is replenished via
        malloc_extend_top.)

     2. Chunks allocated via mmap, which have the second-lowest-order
        bit (IS_MMAPPED) set in their size fields.  Because they are
        never merged or traversed from any other chunk, they have no
        foot size or inuse information.

    Available chunks are kept in any of several places (all declared below):

    * `av': An array of chunks serving as bin headers for consolidated
       chunks. Each bin is doubly linked.  The bins are approximately
       proportionally (log) spaced.  There are a lot of these bins
       (128). This may look excessive, but works very well in
       practice.  All procedures maintain the invariant that no
       consolidated chunk physically borders another one. Chunks in
       bins are kept in size order, with ties going to the
       approximately least recently used chunk.

       The chunks in each bin are maintained in decreasing sorted order by
       size.  This is irrelevant for the small bins, which all contain
       the same-sized chunks, but facilitates best-fit allocation for
       larger chunks. (These lists are just sequential. Keeping them in
       order almost never requires enough traversal to warrant using
       fancier ordered data structures.)  Chunks of the same size are
       linked with the most recently freed at the front, and allocations
       are taken from the back.  This results in LRU or FIFO allocation
       order, which tends to give each chunk an equal opportunity to be
       consolidated with adjacent freed chunks, resulting in larger free
       chunks and less fragmentation.

    * `top': The top-most available chunk (i.e., the one bordering the
       end of available memory) is treated specially. It is never
       included in any bin, is used only if no other chunk is
       available, and is released back to the system if it is very
       large (see M_TRIM_THRESHOLD).

    * `last_remainder': A bin holding only the remainder of the
       most recently split (non-top) chunk. This bin is checked
       before other non-fitting chunks, so as to provide better
       locality for runs of sequentially allocated chunks.

    *  Implicitly, through the host system's memory mapping tables.
       If supported, requests greater than a threshold are usually
       serviced via calls to mmap, and then later released via munmap.

*/






/*  sizes, alignments */

#define SIZE_SZ                (sizeof(INTERNAL_SIZE_T))
#define MALLOC_ALIGNMENT       (SIZE_SZ + SIZE_SZ)
#define MALLOC_ALIGN_MASK      (MALLOC_ALIGNMENT - 1)
#define MINSIZE                (sizeof(struct malloc_chunk))

/* conversion from malloc headers to user pointers, and back */

#define chunk2mem(p)   ((Void_t*)((char*)(p) + 2*SIZE_SZ))
#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - 2*SIZE_SZ))

/* pad request bytes into a usable size */

#define request2size(req) \
 (((long)((req) + (SIZE_SZ + MALLOC_ALIGN_MASK)) < \
  (long)(MINSIZE + MALLOC_ALIGN_MASK)) ? MINSIZE : \
   (((req) + (SIZE_SZ + MALLOC_ALIGN_MASK)) & ~(MALLOC_ALIGN_MASK)))

/* Check if m has acceptable alignment */

#define aligned_OK(m)    (((unsigned long)((m)) & (MALLOC_ALIGN_MASK)) == 0)




/*
  Physical chunk operations
*/


/* size field is or'ed with PREV_INUSE when previous adjacent chunk in use */

#define PREV_INUSE 0x1

/* size field is or'ed with IS_MMAPPED if the chunk was obtained with mmap() */

#define IS_MMAPPED 0x2

/* Bits to mask off when extracting size */

#define SIZE_BITS (PREV_INUSE|IS_MMAPPED)


/* Ptr to next physical malloc_chunk. */

#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->size & ~PREV_INUSE) ))

/* Ptr to previous physical malloc_chunk */

#define prev_chunk(p)\
   ((mchunkptr)( ((char*)(p)) - ((p)->prev_size) ))


/* Treat space at ptr + offset as a chunk */

#define chunk_at_offset(p, s)  ((mchunkptr)(((char*)(p)) + (s)))




/*
  Dealing with use bits
*/

/* extract p's inuse bit */

#define inuse(p)\
((((mchunkptr)(((char*)(p))+((p)->size & ~PREV_INUSE)))->size) & PREV_INUSE)

/* extract inuse bit of previous chunk */

#define prev_inuse(p)  ((p)->size & PREV_INUSE)

/* check for mmap()'ed chunk */

#define chunk_is_mmapped(p) ((p)->size & IS_MMAPPED)

/* set/clear chunk as in use without otherwise disturbing */

#define set_inuse(p)\
((mchunkptr)(((char*)(p)) + ((p)->size & ~PREV_INUSE)))->size |= PREV_INUSE

#define clear_inuse(p)\
((mchunkptr)(((char*)(p)) + ((p)->size & ~PREV_INUSE)))->size &= ~(PREV_INUSE)

/* check/set/clear inuse bits in known places */

#define inuse_bit_at_offset(p, s)\
 (((mchunkptr)(((char*)(p)) + (s)))->size & PREV_INUSE)

#define set_inuse_bit_at_offset(p, s)\
 (((mchunkptr)(((char*)(p)) + (s)))->size |= PREV_INUSE)

#define clear_inuse_bit_at_offset(p, s)\
 (((mchunkptr)(((char*)(p)) + (s)))->size &= ~(PREV_INUSE))




/*
  Dealing with size fields
*/

/* Get size, ignoring use bits */

#define chunksize(p)          ((p)->size & ~(SIZE_BITS))

/* Set size at head, without disturbing its use bit */

#define set_head_size(p, s)   ((p)->size = (((p)->size & PREV_INUSE) | (s)))

/* Set size/use ignoring previous bits in header */

#define set_head(p, s)        ((p)->size = (s))

/* Set size at footer (only when chunk is not in use) */

#define set_foot(p, s)   (((mchunkptr)((char*)(p) + (s)))->prev_size = (s))





/*
   Bins

    The bins, `av_' are an array of pairs of pointers serving as the
    heads of (initially empty) doubly-linked lists of chunks, laid out
    in a way so that each pair can be treated as if it were in a
    malloc_chunk. (This way, the fd/bk offsets for linking bin heads
    and chunks are the same).

    Bins for sizes < 512 bytes contain chunks of all the same size, spaced
    8 bytes apart. Larger bins are approximately logarithmically
    spaced. (See the table below.) The `av_' array is never mentioned
    directly in the code, but instead via bin access macros.

    Bin layout:

    64 bins of size       8
    32 bins of size      64
    16 bins of size     512
     8 bins of size    4096
     4 bins of size   32768
     2 bins of size  262144
     1 bin  of size what's left

    There is actually a little bit of slop in the numbers in bin_index
    for the sake of speed. This makes no difference elsewhere.

    The special chunks `top' and `last_remainder' get their own bins,
    (this is implemented via yet more trickery with the av_ array),
    although `top' is never properly linked to its bin since it is
    always handled specially.

*/

#define NAV             128   /* number of bins */

typedef struct malloc_chunk* mbinptr;

/* access macros */

#define bin_at(i)      ((mbinptr)((char*)&(av_[2*(i) + 2]) - 2*SIZE_SZ))
#define next_bin(b)    ((mbinptr)((char*)(b) + 2 * sizeof(mbinptr)))
#define prev_bin(b)    ((mbinptr)((char*)(b) - 2 * sizeof(mbinptr)))

/*
   The first 2 bins are never indexed. The corresponding av_ cells are instead
   used for bookkeeping. This is not to save space, but to simplify
   indexing, maintain locality, and avoid some initialization tests.
*/

#define top            (bin_at(0)->fd)   /* The topmost chunk */
#define last_remainder (bin_at(1))       /* remainder from last split */


/*
   Because top initially points to its own bin with initial
   zero size, thus forcing extension on the first malloc request,
   we avoid having any special code in malloc to check whether
   it even exists yet. But we still need to in malloc_extend_top.
*/

#define initial_top    ((mchunkptr)(bin_at(0)))

/* Helper macro to initialize bins */

#define IAV(i)  bin_at(i), bin_at(i)

static mbinptr av_[NAV * 2 + 2] = {
 0, 0,
 IAV(0),   IAV(1),   IAV(2),   IAV(3),   IAV(4),   IAV(5),   IAV(6),   IAV(7),
 IAV(8),   IAV(9),   IAV(10),  IAV(11),  IAV(12),  IAV(13),  IAV(14),  IAV(15),
 IAV(16),  IAV(17),  IAV(18),  IAV(19),  IAV(20),  IAV(21),  IAV(22),  IAV(23),
 IAV(24),  IAV(25),  IAV(26),  IAV(27),  IAV(28),  IAV(29),  IAV(30),  IAV(31),
 IAV(32),  IAV(33),  IAV(34),  IAV(35),  IAV(36),  IAV(37),  IAV(38),  IAV(39),
 IAV(40),  IAV(41),  IAV(42),  IAV(43),  IAV(44),  IAV(45),  IAV(46),  IAV(47),
 IAV(48),  IAV(49),  IAV(50),  IAV(51),  IAV(52),  IAV(53),  IAV(54),  IAV(55),
 IAV(56),  IAV(57),  IAV(58),  IAV(59),  IAV(60),  IAV(61),  IAV(62),  IAV(63),
 IAV(64),  IAV(65),  IAV(66),  IAV(67),  IAV(68),  IAV(69),  IAV(70),  IAV(71),
 IAV(72),  IAV(73),  IAV(74),  IAV(75),  IAV(76),  IAV(77),  IAV(78),  IAV(79),
 IAV(80),  IAV(81),  IAV(82),  IAV(83),  IAV(84),  IAV(85),  IAV(86),  IAV(87),
 IAV(88),  IAV(89),  IAV(90),  IAV(91),  IAV(92),  IAV(93),  IAV(94),  IAV(95),
 IAV(96),  IAV(97),  IAV(98),  IAV(99),  IAV(100), IAV(101), IAV(102), IAV(103),
 IAV(104), IAV(105), IAV(106), IAV(107), IAV(108), IAV(109), IAV(110), IAV(111),
 IAV(112), IAV(113), IAV(114), IAV(115), IAV(116), IAV(117), IAV(118), IAV(119),
 IAV(120), IAV(121), IAV(122), IAV(123), IAV(124), IAV(125), IAV(126), IAV(127)
};



/* field-extraction macros */

#define first(b) ((b)->fd)
#define last(b)  ((b)->bk)

/*
  Indexing into bins
*/

#define bin_index(sz)                                                          \
(((((unsigned long)(sz)) >> 9) ==    0) ?       (((unsigned long)(sz)) >>  3): \
 ((((unsigned long)(sz)) >> 9) <=    4) ?  56 + (((unsigned long)(sz)) >>  6): \
 ((((unsigned long)(sz)) >> 9) <=   20) ?  91 + (((unsigned long)(sz)) >>  9): \
 ((((unsigned long)(sz)) >> 9) <=   84) ? 110 + (((unsigned long)(sz)) >> 12): \
 ((((unsigned long)(sz)) >> 9) <=  340) ? 119 + (((unsigned long)(sz)) >> 15): \
 ((((unsigned long)(sz)) >> 9) <= 1364) ? 124 + (((unsigned long)(sz)) >> 18): \
                                          126)
/*
  bins for chunks < 512 are all spaced 8 bytes apart, and hold
  identically sized chunks. This is exploited in malloc.
*/

#define MAX_SMALLBIN         63
#define MAX_SMALLBIN_SIZE   512
#define SMALLBIN_WIDTH        8

#define smallbin_index(sz)  (((unsigned long)(sz)) >> 3)

/*
   Requests are `small' if both the corresponding and the next bin are small
*/

#define is_small_request(nb) (nb < MAX_SMALLBIN_SIZE - SMALLBIN_WIDTH)



/*
    To help compensate for the large number of bins, a one-level index
    structure is used for bin-by-bin searching.  `binblocks' is a
    one-word bitvector recording whether groups of BINBLOCKWIDTH bins
    have any (possibly) non-empty bins, so they can be skipped over
    all at once during during traversals. The bits are NOT always
    cleared as soon as all bins in a block are empty, but instead only
    when all are noticed to be empty during traversal in malloc.
*/

#define BINBLOCKWIDTH     4   /* bins per block */

#define binblocks      (bin_at(0)->size) /* bitvector of nonempty blocks */

/* bin<->block macros */

#define idx2binblock(ix)    ((unsigned)1 << (ix / BINBLOCKWIDTH))
#define mark_binblock(ii)   (binblocks |= idx2binblock(ii))
#define clear_binblock(ii)  (binblocks &= ~(idx2binblock(ii)))





/*  Other static bookkeeping data */

/* variables holding tunable values */

static unsigned long trim_threshold   = DEFAULT_TRIM_THRESHOLD;
static unsigned long top_pad          = DEFAULT_TOP_PAD;
static unsigned int  n_mmaps_max      = DEFAULT_MMAP_MAX;
static unsigned long mmap_threshold   = DEFAULT_MMAP_THRESHOLD;

/* The first value returned from sbrk */
static char* sbrk_base = (char*)(-1);

/* The maximum memory obtained from system via sbrk */
static unsigned long max_sbrked_mem = 0;

/* The maximum via either sbrk or mmap */
static unsigned long max_total_mem = 0;

/* internal working copy of mallinfo */
static struct mallinfo current_mallinfo = {  0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };

/* The total memory obtained from system via sbrk */
#define sbrked_mem  (current_mallinfo.arena)

/* Tracking mmaps */

static unsigned int n_mmaps = 0;
static unsigned int max_n_mmaps = 0;
static unsigned long mmapped_mem = 0;
static unsigned long max_mmapped_mem = 0;



/*
  Debugging support
*/

#if DEBUG


/*
  These routines make a number of assertions about the states
  of data structures that should be true at all times. If any
  are not true, it's very likely that a user program has somehow
  trashed memory. (It's also possible that there is a coding error
  in malloc. In which case, please report it!)
*/

#if __STD_C
static void do_check_chunk(mchunkptr p)
#else
static void do_check_chunk(p) mchunkptr p;
#endif
{
  INTERNAL_SIZE_T sz = p->size & ~PREV_INUSE;

  /* No checkable chunk is mmapped */
  assert(!chunk_is_mmapped(p));

  /* Check for legal address ... */
  assert((char*)p >= sbrk_base);
  if (p != top)
    assert((char*)p + sz <= (char*)top);
  else
    assert((char*)p + sz <= sbrk_base + sbrked_mem);

}


#if __STD_C
static void do_check_free_chunk(mchunkptr p)
#else
static void do_check_free_chunk(p) mchunkptr p;
#endif
{
  INTERNAL_SIZE_T sz = p->size & ~PREV_INUSE;
  mchunkptr next = chunk_at_offset(p, sz);

  do_check_chunk(p);

  /* Check whether it claims to be free ... */
  assert(!inuse(p));

  /* Unless a special marker, must have OK fields */
  if ((long)sz >= (long)MINSIZE)
  {
    assert((sz & MALLOC_ALIGN_MASK) == 0);
    assert(aligned_OK(chunk2mem(p)));
    /* ... matching footer field */
    assert(next->prev_size == sz);
    /* ... and is fully consolidated */
    assert(prev_inuse(p));
    assert (next == top || inuse(next));

    /* ... and has minimally sane links */
    assert(p->fd->bk == p);
    assert(p->bk->fd == p);
  }
  else /* markers are always of size SIZE_SZ */
    assert(sz == SIZE_SZ);
}

#if __STD_C
static void do_check_inuse_chunk(mchunkptr p)
#else
static void do_check_inuse_chunk(p) mchunkptr p;
#endif
{
  mchunkptr next = next_chunk(p);
  do_check_chunk(p);

  /* Check whether it claims to be in use ... */
  assert(inuse(p));

  /* ... and is surrounded by OK chunks.
    Since more things can be checked with free chunks than inuse ones,
    if an inuse chunk borders them and debug is on, it's worth doing them.
  */
  if (!prev_inuse(p))
  {
    mchunkptr prv = prev_chunk(p);
    assert(next_chunk(prv) == p);
    do_check_free_chunk(prv);
  }
  if (next == top)
  {
    assert(prev_inuse(next));
    assert(chunksize(next) >= MINSIZE);
  }
  else if (!inuse(next))
    do_check_free_chunk(next);

}

#if __STD_C
static void do_check_malloced_chunk(mchunkptr p, INTERNAL_SIZE_T s)
#else
static void do_check_malloced_chunk(p, s) mchunkptr p; INTERNAL_SIZE_T s;
#endif
{
  INTERNAL_SIZE_T sz = p->size & ~PREV_INUSE;
  long room = sz - s;

  do_check_inuse_chunk(p);

  /* Legal size ... */
  assert((long)sz >= (long)MINSIZE);
  assert((sz & MALLOC_ALIGN_MASK) == 0);
  assert(room >= 0);
  assert(room < (long)MINSIZE);

  /* ... and alignment */
  assert(aligned_OK(chunk2mem(p)));


  /* ... and was allocated at front of an available chunk */
  assert(prev_inuse(p));

}


#define check_free_chunk(P)  do_check_free_chunk(P)
#define check_inuse_chunk(P) do_check_inuse_chunk(P)
#define check_chunk(P) do_check_chunk(P)
#define check_malloced_chunk(P,N) do_check_malloced_chunk(P,N)
#else
#define check_free_chunk(P)
#define check_inuse_chunk(P)
#define check_chunk(P)
#define check_malloced_chunk(P,N)
#endif



/*
  Macro-based internal utilities
*/


/*
  Linking chunks in bin lists.
  Call these only with variables, not arbitrary expressions, as arguments.
*/

/*
  Place chunk p of size s in its bin, in size order,
  putting it ahead of others of same size.
*/


#define frontlink(P, S, IDX, BK, FD)                                          \
{                                                                             \
  if (S < MAX_SMALLBIN_SIZE)                                                  \
  {                                                                           \
    IDX = smallbin_index(S);                                                  \
    mark_binblock(IDX);                                                       \
    BK = bin_at(IDX);                                                         \
    FD = BK->fd;                                                              \
    P->bk = BK;                                                               \
    P->fd = FD;                                                               \
    FD->bk = BK->fd = P;                                                      \
  }                                                                           \
  else                                                                        \
  {                                                                           \
    IDX = bin_index(S);                                                       \
    BK = bin_at(IDX);                                                         \
    FD = BK->fd;                                                              \
    if (FD == BK) mark_binblock(IDX);                                         \
    else                                                                      \
    {                                                                         \
      while (FD != BK && S < chunksize(FD)) FD = FD->fd;                      \
      BK = FD->bk;                                                            \
    }                                                                         \
    P->bk = BK;                                                               \
    P->fd = FD;                                                               \
    FD->bk = BK->fd = P;                                                      \
  }                                                                           \
}


/* take a chunk off a list */

#define unlink(P, BK, FD)                                                     \
{                                                                             \
  BK = P->bk;                                                                 \
  FD = P->fd;                                                                 \
  FD->bk = BK;                                                                \
  BK->fd = FD;                                                                \
}                                                                             \

/* Place p as the last remainder */

#define link_last_remainder(P)                                                \
{                                                                             \
  last_remainder->fd = last_remainder->bk =  P;                               \
  P->fd = P->bk = last_remainder;                                             \
}

/* Clear the last_remainder bin */

#define clear_last_remainder \
  (last_remainder->fd = last_remainder->bk = last_remainder)






/* Routines dealing with mmap(). */

#if HAVE_MMAP

#if __STD_C
static mchunkptr mmap_chunk(size_t size)
#else
static mchunkptr mmap_chunk(size) size_t size;
#endif
{
  size_t page_mask = malloc_getpagesize - 1;
  mchunkptr p;

#ifndef MAP_ANONYMOUS
  static int fd = -1;
#endif

  if(n_mmaps >= n_mmaps_max) return 0; /* too many regions */

  /* For mmapped chunks, the overhead is one SIZE_SZ unit larger, because
   * there is no following chunk whose prev_size field could be used.
   */
  size = (size + SIZE_SZ + page_mask) & ~page_mask;

#ifdef MAP_ANONYMOUS
  p = (mchunkptr)mmap(0, size, PROT_READ|PROT_WRITE,
		      MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
#else /* !MAP_ANONYMOUS */
  if (fd < 0)
  {
    fd = open("/dev/zero", O_RDWR);
    if(fd < 0) return 0;
  }
  p = (mchunkptr)mmap(0, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
#endif

  if(p == (mchunkptr)-1) return 0;

  n_mmaps++;
  if (n_mmaps > max_n_mmaps) max_n_mmaps = n_mmaps;

  /* We demand that eight bytes into a page must be 8-byte aligned. */
  assert(aligned_OK(chunk2mem(p)));

  /* The offset to the start of the mmapped region is stored
   * in the prev_size field of the chunk; normally it is zero,
   * but that can be changed in memalign().
   */
  p->prev_size = 0;
  set_head(p, size|IS_MMAPPED);

  mmapped_mem += size;
  if ((unsigned long)mmapped_mem > (unsigned long)max_mmapped_mem)
    max_mmapped_mem = mmapped_mem;
  if ((unsigned long)(mmapped_mem + sbrked_mem) > (unsigned long)max_total_mem)
    max_total_mem = mmapped_mem + sbrked_mem;
  return p;
}

#if __STD_C
static void munmap_chunk(mchunkptr p)
#else
static void munmap_chunk(p) mchunkptr p;
#endif
{
  INTERNAL_SIZE_T size = chunksize(p);
  int ret;

  assert (chunk_is_mmapped(p));
  assert(! ((char*)p >= sbrk_base && (char*)p < sbrk_base + sbrked_mem));
  assert((n_mmaps > 0));
  assert(((p->prev_size + size) & (malloc_getpagesize-1)) == 0);

  n_mmaps--;
  mmapped_mem -= (size + p->prev_size);

  ret = munmap((char *)p - p->prev_size, size + p->prev_size);

  /* munmap returns non-zero on failure */
  assert(ret == 0);
}

#if HAVE_MREMAP

#if __STD_C
static mchunkptr mremap_chunk(mchunkptr p, size_t new_size)
#else
static mchunkptr mremap_chunk(p, new_size) mchunkptr p; size_t new_size;
#endif
{
  size_t page_mask = malloc_getpagesize - 1;
  INTERNAL_SIZE_T offset = p->prev_size;
  INTERNAL_SIZE_T size = chunksize(p);
  char *cp;

  assert (chunk_is_mmapped(p));
  assert(! ((char*)p >= sbrk_base && (char*)p < sbrk_base + sbrked_mem));
  assert((n_mmaps > 0));
  assert(((size + offset) & (malloc_getpagesize-1)) == 0);

  /* Note the extra SIZE_SZ overhead as in mmap_chunk(). */
  new_size = (new_size + offset + SIZE_SZ + page_mask) & ~page_mask;

  cp = (char *)mremap((char *)p - offset, size + offset, new_size, 1);

  if (cp == (char *)-1) return 0;

  p = (mchunkptr)(cp + offset);

  assert(aligned_OK(chunk2mem(p)));

  assert((p->prev_size == offset));
  set_head(p, (new_size - offset)|IS_MMAPPED);

  mmapped_mem -= size + offset;
  mmapped_mem += new_size;
  if ((unsigned long)mmapped_mem > (unsigned long)max_mmapped_mem)
    max_mmapped_mem = mmapped_mem;
  if ((unsigned long)(mmapped_mem + sbrked_mem) > (unsigned long)max_total_mem)
    max_total_mem = mmapped_mem + sbrked_mem;
  return p;
}

#endif /* HAVE_MREMAP */

#endif /* HAVE_MMAP */




/*
  Extend the top-most chunk by obtaining memory from system.
  Main interface to sbrk (but see also malloc_trim).
*/

#if __STD_C
static void malloc_extend_top(INTERNAL_SIZE_T nb)
#else
static void malloc_extend_top(nb) INTERNAL_SIZE_T nb;
#endif
{
  char*     brk;                  /* return value from sbrk */
  INTERNAL_SIZE_T front_misalign; /* unusable bytes at front of sbrked space */
  INTERNAL_SIZE_T correction;     /* bytes for 2nd sbrk call */
  char*     new_brk;              /* return of 2nd sbrk call */
  INTERNAL_SIZE_T top_size;       /* new size of top chunk */

  mchunkptr old_top     = top;  /* Record state of old top */
  INTERNAL_SIZE_T old_top_size = chunksize(old_top);
  char*     old_end      = (char*)(chunk_at_offset(old_top, old_top_size));

  /* Pad request with top_pad plus minimal overhead */

  INTERNAL_SIZE_T    sbrk_size     = nb + top_pad + MINSIZE;
  unsigned long pagesz    = malloc_getpagesize;

  /* If not the first time through, round to preserve page boundary */
  /* Otherwise, we need to correct to a page size below anyway. */
  /* (We also correct below if an intervening foreign sbrk call.) */

  if (sbrk_base != (char*)(-1))
    sbrk_size = (sbrk_size + (pagesz - 1)) & ~(pagesz - 1);

  brk = (char*)(MORECORE (sbrk_size));

  /* Fail if sbrk failed or if a foreign sbrk call killed our space */
  if (brk == (char*)(MORECORE_FAILURE) ||
      (brk < old_end && old_top != initial_top))
    return;

  sbrked_mem += sbrk_size;

  if (brk == old_end) /* can just add bytes to current top */
  {
    top_size = sbrk_size + old_top_size;
    set_head(top, top_size | PREV_INUSE);
  }
  else
  {
    if (sbrk_base == (char*)(-1))  /* First time through. Record base */
      sbrk_base = brk;
    else  /* Someone else called sbrk().  Count those bytes as sbrked_mem. */
      sbrked_mem += brk - (char*)old_end;

    /* Guarantee alignment of first new chunk made from this space */
    front_misalign = (unsigned long)chunk2mem(brk) & MALLOC_ALIGN_MASK;
    if (front_misalign > 0)
    {
      correction = (MALLOC_ALIGNMENT) - front_misalign;
      brk += correction;
    }
    else
      correction = 0;

    /* Guarantee the next brk will be at a page boundary */

    correction += ((((unsigned long)(brk + sbrk_size))+(pagesz-1)) &
                   ~(pagesz - 1)) - ((unsigned long)(brk + sbrk_size));

    /* Allocate correction */
    new_brk = (char*)(MORECORE (correction));
    if (new_brk == (char*)(MORECORE_FAILURE)) return;

    sbrked_mem += correction;

    top = (mchunkptr)brk;
    top_size = new_brk - brk + correction;
    set_head(top, top_size | PREV_INUSE);

    if (old_top != initial_top)
    {

      /* There must have been an intervening foreign sbrk call. */
      /* A double fencepost is necessary to prevent consolidation */

      /* If not enough space to do this, then user did something very wrong */
      if (old_top_size < MINSIZE)
      {
        set_head(top, PREV_INUSE); /* will force null return from malloc */
        return;
      }

      /* Also keep size a multiple of MALLOC_ALIGNMENT */
      old_top_size = (old_top_size - 3*SIZE_SZ) & ~MALLOC_ALIGN_MASK;
      set_head_size(old_top, old_top_size);
      chunk_at_offset(old_top, old_top_size          )->size =
        SIZE_SZ|PREV_INUSE;
      chunk_at_offset(old_top, old_top_size + SIZE_SZ)->size =
        SIZE_SZ|PREV_INUSE;
      /* If possible, release the rest. */
      if (old_top_size >= MINSIZE)
        fREe(chunk2mem(old_top));
    }
  }

  if ((unsigned long)sbrked_mem > (unsigned long)max_sbrked_mem)
    max_sbrked_mem = sbrked_mem;
  if ((unsigned long)(mmapped_mem + sbrked_mem) > (unsigned long)max_total_mem)
    max_total_mem = mmapped_mem + sbrked_mem;

  /* We always land on a page boundary */
  assert(((unsigned long)((char*)top + top_size) & (pagesz - 1)) == 0);
}




/* Main public routines */


/*
  Malloc Algorthim:

    The requested size is first converted into a usable form, `nb'.
    This currently means to add 4 bytes overhead plus possibly more to
    obtain 8-byte alignment and/or to obtain a size of at least
    MINSIZE (currently 16 bytes), the smallest allocatable size.
    (All fits are considered `exact' if they are within MINSIZE bytes.)

    From there, the first successful of the following steps is taken:

      1. The bin corresponding to the request size is scanned, and if
         a chunk of exactly the right size is found, it is taken.

      2. The most recently remaindered chunk is used if it is big
         enough.  This is a form of (roving) first fit, used only in
         the absence of exact fits. Runs of consecutive requests use
         the remainder of the chunk used for the previous such request
         whenever possible. This limited use of a first-fit style
         allocation strategy tends to give contiguous chunks
         coextensive lifetimes, which improves locality and can reduce
         fragmentation in the long run.

      3. Other bins are scanned in increasing size order, using a
         chunk big enough to fulfill the request, and splitting off
         any remainder.  This search is strictly by best-fit; i.e.,
         the smallest (with ties going to approximately the least
         recently used) chunk that fits is selected.

      4. If large enough, the chunk bordering the end of memory
         (`top') is split off. (This use of `top' is in accord with
         the best-fit search rule.  In effect, `top' is treated as
         larger (and thus less well fitting) than any other available
         chunk since it can be extended to be as large as necessary
         (up to system limitations).

      5. If the request size meets the mmap threshold and the
         system supports mmap, and there are few enough currently
         allocated mmapped regions, and a call to mmap succeeds,
         the request is allocated via direct memory mapping.

      6. Otherwise, the top of memory is extended by
         obtaining more space from the system (normally using sbrk,
         but definable to anything else via the MORECORE macro).
         Memory is gathered from the system (in system page-sized
         units) in a way that allows chunks obtained across different
         sbrk calls to be consolidated, but does not require
         contiguous memory. Thus, it should be safe to intersperse
         mallocs with other sbrk calls.


      All allocations are made from the the `lowest' part of any found
      chunk. (The implementation invariant is that prev_inuse is
      always true of any allocated chunk; i.e., that each allocated
      chunk borders either a previously allocated and still in-use chunk,
      or the base of its memory arena.)

*/

#if __STD_C
Void_t* mALLOc(size_t bytes)
#else
Void_t* mALLOc(bytes) size_t bytes;
#endif
{
  mchunkptr victim;                  /* inspected/selected chunk */
  INTERNAL_SIZE_T victim_size;       /* its size */
  int       idx;                     /* index for bin traversal */
  mbinptr   bin;                     /* associated bin */
  mchunkptr remainder;               /* remainder from a split */
  long      remainder_size;          /* its size */
  int       remainder_index;         /* its bin index */
  unsigned long block;               /* block traverser bit */
  int       startidx;                /* first bin of a traversed block */
  mchunkptr fwd;                     /* misc temp for linking */
  mchunkptr bck;                     /* misc temp for linking */
  mbinptr q;                         /* misc temp */

  INTERNAL_SIZE_T nb;

  if ((long)bytes < 0) return 0;

  nb = request2size(bytes);  /* padded request size; */

  /* Check for exact match in a bin */

  if (is_small_request(nb))  /* Faster version for small requests */
  {
    idx = smallbin_index(nb);

    /* No traversal or size check necessary for small bins.  */

    q = bin_at(idx);
    victim = last(q);

    /* Also scan the next one, since it would have a remainder < MINSIZE */
    if (victim == q)
    {
      q = next_bin(q);
      victim = last(q);
    }
    if (victim != q)
    {
      victim_size = chunksize(victim);
      unlink(victim, bck, fwd);
      set_inuse_bit_at_offset(victim, victim_size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }

    idx += 2; /* Set for bin scan below. We've already scanned 2 bins. */

  }
  else
  {
    idx = bin_index(nb);
    bin = bin_at(idx);

    for (victim = last(bin); victim != bin; victim = victim->bk)
    {
      victim_size = chunksize(victim);
      remainder_size = victim_size - nb;

      if (remainder_size >= (long)MINSIZE) /* too big */
      {
        --idx; /* adjust to rescan below after checking last remainder */
        break;
      }

      else if (remainder_size >= 0) /* exact fit */
      {
        unlink(victim, bck, fwd);
        set_inuse_bit_at_offset(victim, victim_size);
        check_malloced_chunk(victim, nb);
        return chunk2mem(victim);
      }
    }

    ++idx;

  }

  /* Try to use the last split-off remainder */

  if ( (victim = last_remainder->fd) != last_remainder)
  {
    victim_size = chunksize(victim);
    remainder_size = victim_size - nb;

    if (remainder_size >= (long)MINSIZE) /* re-split */
    {
      remainder = chunk_at_offset(victim, nb);
      set_head(victim, nb | PREV_INUSE);
      link_last_remainder(remainder);
      set_head(remainder, remainder_size | PREV_INUSE);
      set_foot(remainder, remainder_size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }

    clear_last_remainder;

    if (remainder_size >= 0)  /* exhaust */
    {
      set_inuse_bit_at_offset(victim, victim_size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }

    /* Else place in bin */

    frontlink(victim, victim_size, remainder_index, bck, fwd);
  }

  /*
     If there are any possibly nonempty big-enough blocks,
     search for best fitting chunk by scanning bins in blockwidth units.
  */

  if ( (block = idx2binblock(idx)) <= binblocks)
  {

    /* Get to the first marked block */

    if ( (block & binblocks) == 0)
    {
      /* force to an even block boundary */
      idx = (idx & ~(BINBLOCKWIDTH - 1)) + BINBLOCKWIDTH;
      block <<= 1;
      while ((block & binblocks) == 0)
      {
        idx += BINBLOCKWIDTH;
        block <<= 1;
      }
    }

    /* For each possibly nonempty block ... */
    for (;;)
    {
      startidx = idx;          /* (track incomplete blocks) */
      q = bin = bin_at(idx);

      /* For each bin in this block ... */
      do
      {
        /* Find and use first big enough chunk ... */

        for (victim = last(bin); victim != bin; victim = victim->bk)
        {
          victim_size = chunksize(victim);
          remainder_size = victim_size - nb;

          if (remainder_size >= (long)MINSIZE) /* split */
          {
            remainder = chunk_at_offset(victim, nb);
            set_head(victim, nb | PREV_INUSE);
            unlink(victim, bck, fwd);
            link_last_remainder(remainder);
            set_head(remainder, remainder_size | PREV_INUSE);
            set_foot(remainder, remainder_size);
            check_malloced_chunk(victim, nb);
            return chunk2mem(victim);
          }

          else if (remainder_size >= 0)  /* take */
          {
            set_inuse_bit_at_offset(victim, victim_size);
            unlink(victim, bck, fwd);
            check_malloced_chunk(victim, nb);
            return chunk2mem(victim);
          }

        }

       bin = next_bin(bin);

      } while ((++idx & (BINBLOCKWIDTH - 1)) != 0);

      /* Clear out the block bit. */

      do   /* Possibly backtrack to try to clear a partial block */
      {
        if ((startidx & (BINBLOCKWIDTH - 1)) == 0)
        {
          binblocks &= ~block;
          break;
        }
        --startidx;
       q = prev_bin(q);
      } while (first(q) == q);

      /* Get to the next possibly nonempty block */

      if ( (block <<= 1) <= binblocks && (block != 0) )
      {
        while ((block & binblocks) == 0)
        {
          idx += BINBLOCKWIDTH;
          block <<= 1;
        }
      }
      else
        break;
    }
  }


  /* Try to use top chunk */

  /* Require that there be a remainder, ensuring top always exists  */
  if ( (remainder_size = chunksize(top) - nb) < (long)MINSIZE)
  {

#if HAVE_MMAP
    /* If big and would otherwise need to extend, try to use mmap instead */
    if ((unsigned long)nb >= (unsigned long)mmap_threshold &&
        (victim = mmap_chunk(nb)) != 0)
      return chunk2mem(victim);
#endif

    /* Try to extend */
    malloc_extend_top(nb);
    if ( (remainder_size = chunksize(top) - nb) < (long)MINSIZE)
      return 0; /* propagate failure */
  }

  victim = top;
  set_head(victim, nb | PREV_INUSE);
  top = chunk_at_offset(victim, nb);
  set_head(top, remainder_size | PREV_INUSE);
  check_malloced_chunk(victim, nb);
  return chunk2mem(victim);

}




/*

  free() algorithm :

    cases:

       1. free(0) has no effect.

       2. If the chunk was allocated via mmap, it is release via munmap().

       3. If a returned chunk borders the current high end of memory,
          it is consolidated into the top, and if the total unused
          topmost memory exceeds the trim threshold, malloc_trim is
          called.

       4. Other chunks are consolidated as they arrive, and
          placed in corresponding bins. (This includes the case of
          consolidating with the current `last_remainder').

*/


#if __STD_C
void fREe(Void_t* mem)
#else
void fREe(mem) Void_t* mem;
#endif
{
  mchunkptr p;         /* chunk corresponding to mem */
  INTERNAL_SIZE_T hd;  /* its head field */
  INTERNAL_SIZE_T sz;  /* its size */
  int       idx;       /* its bin index */
  mchunkptr next;      /* next contiguous chunk */
  INTERNAL_SIZE_T nextsz; /* its size */
  INTERNAL_SIZE_T prevsz; /* size of previous contiguous chunk */
  mchunkptr bck;       /* misc temp for linking */
  mchunkptr fwd;       /* misc temp for linking */
  int       islr;      /* track whether merging with last_remainder */

  if (mem == 0)                              /* free(0) has no effect */
    return;

  p = mem2chunk(mem);
  hd = p->size;

#if HAVE_MMAP
  if (hd & IS_MMAPPED)                       /* release mmapped memory. */
  {
    munmap_chunk(p);
    return;
  }
#endif

  check_inuse_chunk(p);

  sz = hd & ~PREV_INUSE;
  next = chunk_at_offset(p, sz);
  nextsz = chunksize(next);

  if (next == top)                            /* merge with top */
  {
    sz += nextsz;

    if (!(hd & PREV_INUSE))                    /* consolidate backward */
    {
      prevsz = p->prev_size;
      p = chunk_at_offset(p, -((long) prevsz));
      sz += prevsz;
      unlink(p, bck, fwd);
    }

    set_head(p, sz | PREV_INUSE);
    top = p;
    if ((unsigned long)(sz) >= (unsigned long)trim_threshold)
      malloc_trim(top_pad);
    return;
  }

  set_head(next, nextsz);                    /* clear inuse bit */

  islr = 0;

  if (!(hd & PREV_INUSE))                    /* consolidate backward */
  {
    prevsz = p->prev_size;
    p = chunk_at_offset(p, -((long) prevsz));
    sz += prevsz;

    if (p->fd == last_remainder)             /* keep as last_remainder */
      islr = 1;
    else
      unlink(p, bck, fwd);
  }

  if (!(inuse_bit_at_offset(next, nextsz)))   /* consolidate forward */
  {
    sz += nextsz;

    if (!islr && next->fd == last_remainder)  /* re-insert last_remainder */
    {
      islr = 1;
      link_last_remainder(p);
    }
    else
      unlink(next, bck, fwd);
  }


  set_head(p, sz | PREV_INUSE);
  set_foot(p, sz);
  if (!islr)
    frontlink(p, sz, idx, bck, fwd);
}





/*

  Realloc algorithm:

    Chunks that were obtained via mmap cannot be extended or shrunk
    unless HAVE_MREMAP is defined, in which case mremap is used.
    Otherwise, if their reallocation is for additional space, they are
    copied.  If for less, they are just left alone.

    Otherwise, if the reallocation is for additional space, and the
    chunk can be extended, it is, else a malloc-copy-free sequence is
    taken.  There are several different ways that a chunk could be
    extended. All are tried:

       * Extending forward into following adjacent free chunk.
       * Shifting backwards, joining preceding adjacent space
       * Both shifting backwards and extending forward.
       * Extending into newly sbrked space

    Unless the #define REALLOC_ZERO_BYTES_FREES is set, realloc with a
    size argument of zero (re)allocates a minimum-sized chunk.

    If the reallocation is for less space, and the new request is for
    a `small' (<512 bytes) size, then the newly unused space is lopped
    off and freed.

    The old unix realloc convention of allowing the last-free'd chunk
    to be used as an argument to realloc is no longer supported.
    I don't know of any programs still relying on this feature,
    and allowing it would also allow too many other incorrect
    usages of realloc to be sensible.


*/


#if __STD_C
Void_t* rEALLOc(Void_t* oldmem, size_t bytes)
#else
Void_t* rEALLOc(oldmem, bytes) Void_t* oldmem; size_t bytes;
#endif
{
  INTERNAL_SIZE_T    nb;      /* padded request size */

  mchunkptr oldp;             /* chunk corresponding to oldmem */
  INTERNAL_SIZE_T    oldsize; /* its size */

  mchunkptr newp;             /* chunk to return */
  INTERNAL_SIZE_T    newsize; /* its size */
  Void_t*   newmem;           /* corresponding user mem */

  mchunkptr next;             /* next contiguous chunk after oldp */
  INTERNAL_SIZE_T  nextsize;  /* its size */

  mchunkptr prev;             /* previous contiguous chunk before oldp */
  INTERNAL_SIZE_T  prevsize;  /* its size */

  mchunkptr remainder;        /* holds split off extra space from newp */
  INTERNAL_SIZE_T  remainder_size;   /* its size */

  mchunkptr bck;              /* misc temp for linking */
  mchunkptr fwd;              /* misc temp for linking */

#ifdef REALLOC_ZERO_BYTES_FREES
  if (bytes == 0) { fREe(oldmem); return 0; }
#endif

  if ((long)bytes < 0) return 0;

  /* realloc of null is supposed to be same as malloc */
  if (oldmem == 0) return mALLOc(bytes);

  newp    = oldp    = mem2chunk(oldmem);
  newsize = oldsize = chunksize(oldp);


  nb = request2size(bytes);

#if HAVE_MMAP
  if (chunk_is_mmapped(oldp))
  {
#if HAVE_MREMAP
    newp = mremap_chunk(oldp, nb);
    if(newp) return chunk2mem(newp);
#endif
    /* Note the extra SIZE_SZ overhead. */
    if(oldsize - SIZE_SZ >= nb) return oldmem; /* do nothing */
    /* Must alloc, copy, free. */
    newmem = mALLOc(bytes);
    if (newmem == 0) return 0; /* propagate failure */
    MALLOC_COPY(newmem, oldmem, oldsize - 2*SIZE_SZ);
    munmap_chunk(oldp);
    return newmem;
  }
#endif

  check_inuse_chunk(oldp);

  if ((long)(oldsize) < (long)(nb))
  {

    /* Try expanding forward */

    next = chunk_at_offset(oldp, oldsize);
    if (next == top || !inuse(next))
    {
      nextsize = chunksize(next);

      /* Forward into top only if a remainder */
      if (next == top)
      {
        if ((long)(nextsize + newsize) >= (long)(nb + MINSIZE))
        {
          newsize += nextsize;
          top = chunk_at_offset(oldp, nb);
          set_head(top, (newsize - nb) | PREV_INUSE);
          set_head_size(oldp, nb);
          return chunk2mem(oldp);
        }
      }

      /* Forward into next chunk */
      else if (((long)(nextsize + newsize) >= (long)(nb)))
      {
        unlink(next, bck, fwd);
        newsize  += nextsize;
        goto split;
      }
    }
    else
    {
      next = 0;
      nextsize = 0;
    }

    /* Try shifting backwards. */

    if (!prev_inuse(oldp))
    {
      prev = prev_chunk(oldp);
      prevsize = chunksize(prev);

      /* try forward + backward first to save a later consolidation */

      if (next != 0)
      {
        /* into top */
        if (next == top)
        {
          if ((long)(nextsize + prevsize + newsize) >= (long)(nb + MINSIZE))
          {
            unlink(prev, bck, fwd);
            newp = prev;
            newsize += prevsize + nextsize;
            newmem = chunk2mem(newp);
            MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
            top = chunk_at_offset(newp, nb);
            set_head(top, (newsize - nb) | PREV_INUSE);
            set_head_size(newp, nb);
            return newmem;
          }
        }

        /* into next chunk */
        else if (((long)(nextsize + prevsize + newsize) >= (long)(nb)))
        {
          unlink(next, bck, fwd);
          unlink(prev, bck, fwd);
          newp = prev;
          newsize += nextsize + prevsize;
          newmem = chunk2mem(newp);
          MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
          goto split;
        }
      }

      /* backward only */
      if (prev != 0 && (long)(prevsize + newsize) >= (long)nb)
      {
        unlink(prev, bck, fwd);
        newp = prev;
        newsize += prevsize;
        newmem = chunk2mem(newp);
        MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
        goto split;
      }
    }

    /* Must allocate */

    newmem = mALLOc (bytes);

    if (newmem == 0)  /* propagate failure */
      return 0;

    /* Avoid copy if newp is next chunk after oldp. */
    /* (This can only happen when new chunk is sbrk'ed.) */

    if ( (newp = mem2chunk(newmem)) == next_chunk(oldp))
    {
      newsize += chunksize(newp);
      newp = oldp;
      goto split;
    }

    /* Otherwise copy, free, and exit */
    MALLOC_COPY(newmem, oldmem, oldsize - SIZE_SZ);
    fREe(oldmem);
    return newmem;
  }


 split:  /* split off extra room in old or expanded chunk */

  if (newsize - nb >= MINSIZE) /* split off remainder */
  {
    remainder = chunk_at_offset(newp, nb);
    remainder_size = newsize - nb;
    set_head_size(newp, nb);
    set_head(remainder, remainder_size | PREV_INUSE);
    set_inuse_bit_at_offset(remainder, remainder_size);
    fREe(chunk2mem(remainder)); /* let free() deal with it */
  }
  else
  {
    set_head_size(newp, newsize);
    set_inuse_bit_at_offset(newp, newsize);
  }

  check_inuse_chunk(newp);
  return chunk2mem(newp);
}




/*

  memalign algorithm:

    memalign requests more than enough space from malloc, finds a spot
    within that chunk that meets the alignment request, and then
    possibly frees the leading and trailing space.

    The alignment argument must be a power of two. This property is not
    checked by memalign, so misuse may result in random runtime errors.

    8-byte alignment is guaranteed by normal malloc calls, so don't
    bother calling memalign with an argument of 8 or less.

    Overreliance on memalign is a sure way to fragment space.

*/


#if __STD_C
Void_t* mEMALIGn(size_t alignment, size_t bytes)
#else
Void_t* mEMALIGn(alignment, bytes) size_t alignment; size_t bytes;
#endif
{
  INTERNAL_SIZE_T    nb;      /* padded  request size */
  char*     m;                /* memory returned by malloc call */
  mchunkptr p;                /* corresponding chunk */
  char*     brk;              /* alignment point within p */
  mchunkptr newp;             /* chunk to return */
  INTERNAL_SIZE_T  newsize;   /* its size */
  INTERNAL_SIZE_T  leadsize;  /* leading space befor alignment point */
  mchunkptr remainder;        /* spare room at end to split off */
  long      remainder_size;   /* its size */

  if ((long)bytes < 0) return 0;

  /* If need less alignment than we give anyway, just relay to malloc */

  if (alignment <= MALLOC_ALIGNMENT) return mALLOc(bytes);

  /* Otherwise, ensure that it is at least a minimum chunk size */

  if (alignment <  MINSIZE) alignment = MINSIZE;

  /* Call malloc with worst case padding to hit alignment. */

  nb = request2size(bytes);
  m  = (char*)(mALLOc(nb + alignment + MINSIZE));

  if (m == 0) return 0; /* propagate failure */

  p = mem2chunk(m);

  if ((((unsigned long)(m)) % alignment) == 0) /* aligned */
  {
#if HAVE_MMAP
    if(chunk_is_mmapped(p))
      return chunk2mem(p); /* nothing more to do */
#endif
  }
  else /* misaligned */
  {
    /*
      Find an aligned spot inside chunk.
      Since we need to give back leading space in a chunk of at
      least MINSIZE, if the first calculation places us at
      a spot with less than MINSIZE leader, we can move to the
      next aligned spot -- we've allocated enough total room so that
      this is always possible.
    */

    brk = (char*)mem2chunk(((unsigned long)(m + alignment - 1)) & -((signed) alignment));
    if ((long)(brk - (char*)(p)) < MINSIZE) brk = brk + alignment;

    newp = (mchunkptr)brk;
    leadsize = brk - (char*)(p);
    newsize = chunksize(p) - leadsize;

#if HAVE_MMAP
    if(chunk_is_mmapped(p))
    {
      newp->prev_size = p->prev_size + leadsize;
      set_head(newp, newsize|IS_MMAPPED);
      return chunk2mem(newp);
    }
#endif

    /* give back leader, use the rest */

    set_head(newp, newsize | PREV_INUSE);
    set_inuse_bit_at_offset(newp, newsize);
    set_head_size(p, leadsize);
    fREe(chunk2mem(p));
    p = newp;

    assert (newsize >= nb && (((unsigned long)(chunk2mem(p))) % alignment) == 0);
  }

  /* Also give back spare room at the end */

  remainder_size = chunksize(p) - nb;

  if (remainder_size >= (long)MINSIZE)
  {
    remainder = chunk_at_offset(p, nb);
    set_head(remainder, remainder_size | PREV_INUSE);
    set_head_size(p, nb);
    fREe(chunk2mem(remainder));
  }

  check_inuse_chunk(p);
  return chunk2mem(p);

}




/*
    valloc just invokes memalign with alignment argument equal
    to the page size of the system (or as near to this as can
    be figured out from all the includes/defines above.)
*/

#if __STD_C
Void_t* vALLOc(size_t bytes)
#else
Void_t* vALLOc(bytes) size_t bytes;
#endif
{
  return mEMALIGn (malloc_getpagesize, bytes);
}

/*
  pvalloc just invokes valloc for the nearest pagesize
  that will accommodate request
*/


#if __STD_C
Void_t* pvALLOc(size_t bytes)
#else
Void_t* pvALLOc(bytes) size_t bytes;
#endif
{
  size_t pagesize = malloc_getpagesize;
  return mEMALIGn (pagesize, (bytes + pagesize - 1) & ~(pagesize - 1));
}

/*

  calloc calls malloc, then zeroes out the allocated chunk.

*/

#if __STD_C
Void_t* cALLOc(size_t n, size_t elem_size)
#else
Void_t* cALLOc(n, elem_size) size_t n; size_t elem_size;
#endif
{
  mchunkptr p;
  INTERNAL_SIZE_T csz;

  INTERNAL_SIZE_T sz = n * elem_size;


  /* check if expand_top called, in which case don't need to clear */
#if MORECORE_CLEARS
  mchunkptr oldtop = top;
  INTERNAL_SIZE_T oldtopsize = chunksize(top);
#endif
  Void_t* mem = mALLOc (sz);

  if ((long)n < 0) return 0;

  if (mem == 0)
    return 0;
  else
  {
    p = mem2chunk(mem);

    /* Two optional cases in which clearing not necessary */


#if HAVE_MMAP
    if (chunk_is_mmapped(p)) return mem;
#endif

    csz = chunksize(p);

#if MORECORE_CLEARS
    if (p == oldtop && csz > oldtopsize)
    {
      /* clear only the bytes from non-freshly-sbrked memory */
      csz = oldtopsize;
    }
#endif

    MALLOC_ZERO(mem, csz - SIZE_SZ);
    return mem;
  }
}

/*

  cfree just calls free. It is needed/defined on some systems
  that pair it with calloc, presumably for odd historical reasons.

*/

#if !defined(INTERNAL_LINUX_C_LIB) || !defined(__ELF__)
#if __STD_C
void cfree(Void_t *mem)
#else
void cfree(mem) Void_t *mem;
#endif
{
  fREe(mem);
}
#endif



/*

    Malloc_trim gives memory back to the system (via negative
    arguments to sbrk) if there is unused memory at the `high' end of
    the malloc pool. You can call this after freeing large blocks of
    memory to potentially reduce the system-level memory requirements
    of a program. However, it cannot guarantee to reduce memory. Under
    some allocation patterns, some large free blocks of memory will be
    locked between two used chunks, so they cannot be given back to
    the system.

    The `pad' argument to malloc_trim represents the amount of free
    trailing space to leave untrimmed. If this argument is zero,
    only the minimum amount of memory to maintain internal data
    structures will be left (one page or less). Non-zero arguments
    can be supplied to maintain enough trailing space to service
    future expected allocations without having to re-obtain memory
    from the system.

    Malloc_trim returns 1 if it actually released any memory, else 0.

*/

#if __STD_C
int malloc_trim(size_t pad)
#else
int malloc_trim(pad) size_t pad;
#endif
{
  long  top_size;        /* Amount of top-most memory */
  long  extra;           /* Amount to release */
  char* current_brk;     /* address returned by pre-check sbrk call */
  char* new_brk;         /* address returned by negative sbrk call */

  unsigned long pagesz = malloc_getpagesize;

  top_size = chunksize(top);
  extra = ((top_size - pad - MINSIZE + (pagesz-1)) / pagesz - 1) * pagesz;

  if (extra < (long)pagesz)  /* Not enough memory to release */
    return 0;

  else
  {
    /* Test to make sure no one else called sbrk */
    current_brk = (char*)(MORECORE (0));
    if (current_brk != (char*)(top) + top_size)
      return 0;     /* Apparently we don't own memory; must fail */

    else
    {
      new_brk = (char*)(MORECORE (-extra));

      if (new_brk == (char*)(MORECORE_FAILURE)) /* sbrk failed? */
      {
        /* Try to figure out what we have */
        current_brk = (char*)(MORECORE (0));
        top_size = current_brk - (char*)top;
        if (top_size >= (long)MINSIZE) /* if not, we are very very dead! */
        {
          sbrked_mem = current_brk - sbrk_base;
          set_head(top, top_size | PREV_INUSE);
        }
        check_chunk(top);
        return 0;
      }

      else
      {
        /* Success. Adjust top accordingly. */
        set_head(top, (top_size - extra) | PREV_INUSE);
        sbrked_mem -= extra;
        check_chunk(top);
        return 1;
      }
    }
  }
}



/*
  malloc_usable_size:

    This routine tells you how many bytes you can actually use in an
    allocated chunk, which may be more than you requested (although
    often not). You can use this many bytes without worrying about
    overwriting other allocated objects. Not a particularly great
    programming practice, but still sometimes useful.

*/

#if __STD_C
size_t malloc_usable_size(Void_t* mem)
#else
size_t malloc_usable_size(mem) Void_t* mem;
#endif
{
  mchunkptr p;
  if (mem == 0)
    return 0;
  else
  {
    p = mem2chunk(mem);
    if(!chunk_is_mmapped(p))
    {
      if (!inuse(p)) return 0;
      check_inuse_chunk(p);
      return chunksize(p) - SIZE_SZ;
    }
    return chunksize(p) - 2*SIZE_SZ;
  }
}




/* Utility to update current_mallinfo for malloc_stats and mallinfo() */

static void malloc_update_mallinfo()
{
  int i;
  mbinptr b;
  mchunkptr p;
#if DEBUG
  mchunkptr q;
#endif

  INTERNAL_SIZE_T avail = chunksize(top);
  int   navail = ((long)(avail) >= (long)MINSIZE)? 1 : 0;

  for (i = 1; i < NAV; ++i)
  {
    b = bin_at(i);
    for (p = last(b); p != b; p = p->bk)
    {
#if DEBUG
      check_free_chunk(p);
      for (q = next_chunk(p);
           q < top && inuse(q) && (long)(chunksize(q)) >= (long)MINSIZE;
           q = next_chunk(q))
        check_inuse_chunk(q);
#endif
      avail += chunksize(p);
      navail++;
    }
  }

  current_mallinfo.ordblks = navail;
  current_mallinfo.uordblks = sbrked_mem - avail;
  current_mallinfo.fordblks = avail;
  current_mallinfo.hblks = n_mmaps;
  current_mallinfo.hblkhd = mmapped_mem;
  current_mallinfo.keepcost = chunksize(top);

}



/*

  malloc_stats:

    Prints on stderr the amount of space obtain from the system (both
    via sbrk and mmap), the maximum amount (which may be more than
    current if malloc_trim and/or munmap got called), the maximum
    number of simultaneous mmap regions used, and the current number
    of bytes allocated via malloc (or realloc, etc) but not yet
    freed. (Note that this is the number of bytes allocated, not the
    number requested. It will be larger than the number requested
    because of alignment and bookkeeping overhead.)

*/

void malloc_stats()
{
  malloc_update_mallinfo();
  fprintf(stderr, "max system bytes = %10u\n",
          (unsigned int)(max_total_mem));
  fprintf(stderr, "system bytes     = %10u\n",
          (unsigned int)(sbrked_mem + mmapped_mem));
  fprintf(stderr, "in use bytes     = %10u\n",
          (unsigned int)(current_mallinfo.uordblks + mmapped_mem));
#if HAVE_MMAP
  fprintf(stderr, "max mmap regions = %10u\n",
          (unsigned int)max_n_mmaps);
#endif
}

/*
  mallinfo returns a copy of updated current mallinfo.
*/

struct mallinfo mALLINFo()
{
  malloc_update_mallinfo();
  return current_mallinfo;
}




/*
  mallopt:

    mallopt is the general SVID/XPG interface to tunable parameters.
    The format is to provide a (parameter-number, parameter-value) pair.
    mallopt then sets the corresponding parameter to the argument
    value if it can (i.e., so long as the value is meaningful),
    and returns 1 if successful else 0.

    See descriptions of tunable parameters above.

*/

#if __STD_C
int mALLOPt(int param_number, int value)
#else
int mALLOPt(param_number, value) int param_number; int value;
#endif
{
  switch(param_number)
  {
    case M_TRIM_THRESHOLD:
      trim_threshold = value; return 1;
    case M_TOP_PAD:
      top_pad = value; return 1;
    case M_MMAP_THRESHOLD:
      mmap_threshold = value; return 1;
    case M_MMAP_MAX:
#if HAVE_MMAP
      n_mmaps_max = value; return 1;
#else
      if (value != 0) return 0; else  n_mmaps_max = value; return 1;
#endif

    default:
      return 0;
  }
}

/*

History:

    V2.6.6 Sun Dec  5 07:42:19 1999  Doug Lea  (dl at gee)
      * return null for negative arguments
      * Added Several WIN32 cleanups from Martin C. Fong <mcfong@yahoo.com>
         * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h'
          (e.g. WIN32 platforms)
         * Cleanup up header file inclusion for WIN32 platforms
         * Cleanup code to avoid Microsoft Visual C++ compiler complaints
         * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing
           memory allocation routines
         * Set 'malloc_getpagesize' for WIN32 platforms (needs more work)
         * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to
	   usage of 'assert' in non-WIN32 code
         * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to
           avoid infinite loop
      * Always call 'fREe()' rather than 'free()'

    V2.6.5 Wed Jun 17 15:57:31 1998  Doug Lea  (dl at gee)
      * Fixed ordering problem with boundary-stamping

    V2.6.3 Sun May 19 08:17:58 1996  Doug Lea  (dl at gee)
      * Added pvalloc, as recommended by H.J. Liu
      * Added 64bit pointer support mainly from Wolfram Gloger
      * Added anonymously donated WIN32 sbrk emulation
      * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen
      * malloc_extend_top: fix mask error that caused wastage after
        foreign sbrks
      * Add linux mremap support code from HJ Liu

    V2.6.2 Tue Dec  5 06:52:55 1995  Doug Lea  (dl at gee)
      * Integrated most documentation with the code.
      * Add support for mmap, with help from
        Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
      * Use last_remainder in more cases.
      * Pack bins using idea from  colin@nyx10.cs.du.edu
      * Use ordered bins instead of best-fit threshhold
      * Eliminate block-local decls to simplify tracing and debugging.
      * Support another case of realloc via move into top
      * Fix error occuring when initial sbrk_base not word-aligned.
      * Rely on page size for units instead of SBRK_UNIT to
        avoid surprises about sbrk alignment conventions.
      * Add mallinfo, mallopt. Thanks to Raymond Nijssen
        (raymond@es.ele.tue.nl) for the suggestion.
      * Add `pad' argument to malloc_trim and top_pad mallopt parameter.
      * More precautions for cases where other routines call sbrk,
        courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
      * Added macros etc., allowing use in linux libc from
        H.J. Lu (hjl@gnu.ai.mit.edu)
      * Inverted this history list

    V2.6.1 Sat Dec  2 14:10:57 1995  Doug Lea  (dl at gee)
      * Re-tuned and fixed to behave more nicely with V2.6.0 changes.
      * Removed all preallocation code since under current scheme
        the work required to undo bad preallocations exceeds
        the work saved in good cases for most test programs.
      * No longer use return list or unconsolidated bins since
        no scheme using them consistently outperforms those that don't
        given above changes.
      * Use best fit for very large chunks to prevent some worst-cases.
      * Added some support for debugging

    V2.6.0 Sat Nov  4 07:05:23 1995  Doug Lea  (dl at gee)
      * Removed footers when chunks are in use. Thanks to
        Paul Wilson (wilson@cs.texas.edu) for the suggestion.

    V2.5.4 Wed Nov  1 07:54:51 1995  Doug Lea  (dl at gee)
      * Added malloc_trim, with help from Wolfram Gloger
        (wmglo@Dent.MED.Uni-Muenchen.DE).

    V2.5.3 Tue Apr 26 10:16:01 1994  Doug Lea  (dl at g)

    V2.5.2 Tue Apr  5 16:20:40 1994  Doug Lea  (dl at g)
      * realloc: try to expand in both directions
      * malloc: swap order of clean-bin strategy;
      * realloc: only conditionally expand backwards
      * Try not to scavenge used bins
      * Use bin counts as a guide to preallocation
      * Occasionally bin return list chunks in first scan
      * Add a few optimizations from colin@nyx10.cs.du.edu

    V2.5.1 Sat Aug 14 15:40:43 1993  Doug Lea  (dl at g)
      * faster bin computation & slightly different binning
      * merged all consolidations to one part of malloc proper
         (eliminating old malloc_find_space & malloc_clean_bin)
      * Scan 2 returns chunks (not just 1)
      * Propagate failure in realloc if malloc returns 0
      * Add stuff to allow compilation on non-ANSI compilers
          from kpv@research.att.com

    V2.5 Sat Aug  7 07:41:59 1993  Doug Lea  (dl at g.oswego.edu)
      * removed potential for odd address access in prev_chunk
      * removed dependency on getpagesize.h
      * misc cosmetics and a bit more internal documentation
      * anticosmetics: mangled names in macros to evade debugger strangeness
      * tested on sparc, hp-700, dec-mips, rs6000
          with gcc & native cc (hp, dec only) allowing
          Detlefs & Zorn comparison study (in SIGPLAN Notices.)

    Trial version Fri Aug 28 13:14:29 1992  Doug Lea  (dl at g.oswego.edu)
      * Based loosely on libg++-1.2X malloc. (It retains some of the overall
         structure of old version,  but most details differ.)

*/