File: malloc.c

package info (click to toggle)
mah-jong 1.8-1
  • links: PTS
  • area: main
  • in suites: lenny
  • size: 2,384 kB
  • ctags: 2,186
  • sloc: ansic: 26,312; perl: 393; makefile: 272; sh: 122
file content (5490 lines) | stat: -rw-r--r-- 181,123 bytes parent folder | download | duplicates (4)
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
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
/*
  This is a version (aka dlmalloc) of malloc/free/realloc written by
  Doug Lea and released to the public domain.  Use, modify, and
  redistribute this code without permission or acknowledgement in any
  way you wish.  Send questions, comments, complaints, performance
  data, etc to dl@cs.oswego.edu

* VERSION 2.7.2 Sat Aug 17 09:07:30 2002  Doug Lea  (dl at gee)

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

* Quickstart

  This library is all in one file to simplify the most common usage:
  ftp it, compile it (-O), and link it into another program. All
  of the compile-time options default to reasonable values for use on
  most unix platforms. Compile -DWIN32 for reasonable defaults on windows.
  You might later want to step through various compile-time and dynamic
  tuning options.

  For convenience, an include file for code using this malloc is at:
     ftp://gee.cs.oswego.edu/pub/misc/malloc-2.7.1.h
  You don't really need this .h file unless you call functions not
  defined in your system include files.  The .h file contains only the
  excerpts from this file needed for using this malloc on ANSI C/C++
  systems, so long as you haven't changed compile-time options about
  naming and tuning parameters.  If you do, then you can create your
  own malloc.h that does include all settings by cutting at the point
  indicated below.

* 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 malloc-intensive programs.

  The main properties of the algorithms are:
  * For large (>= 512 bytes) requests, it is a pure best-fit allocator,
    with ties normally decided via FIFO (i.e. least recently used).
  * For small (<= 64 bytes by default) requests, it is a caching
    allocator, that maintains pools of quickly recycled chunks.
  * In between, and for combinations of large and small requests, it does
    the best it can trying to meet both goals at once.
  * For very large requests (>= 128KB by default), it relies on system
    memory mapping facilities, if supported.

  For a longer but slightly out of date high-level description, see
     http://gee.cs.oswego.edu/dl/html/malloc.html

  You may already by default be using a C library containing a malloc
  that is  based on some version of this malloc (for example in
  linux). You might still want to use the one in this file in order to
  customize settings or to avoid overheads associated with library
  versions.

* Contents, described in more detail in "description of public routines" below.

  Standard (ANSI/SVID/...)  functions:
    malloc(size_t n);
    calloc(size_t n_elements, size_t element_size);
    free(Void_t* p);
    realloc(Void_t* p, size_t n);
    memalign(size_t alignment, size_t n);
    valloc(size_t n);
    mallinfo()
    mallopt(int parameter_number, int parameter_value)

  Additional functions:
    independent_calloc(size_t n_elements, size_t size, Void_t* chunks[]);
    independent_comalloc(size_t n_elements, size_t sizes[], Void_t* chunks[]);
    pvalloc(size_t n);
    cfree(Void_t* p);
    malloc_trim(size_t pad);
    malloc_usable_size(Void_t* p);
    malloc_stats();

* Vital statistics:

  Supported pointer representation:       4 or 8 bytes
  Supported size_t  representation:       4 or 8 bytes 
       Note that size_t is allowed to be 4 bytes even if pointers are 8.
       You can adjust this by defining INTERNAL_SIZE_T

  Alignment:                              2 * sizeof(size_t) (default)
       (i.e., 8 byte alignment with 4byte size_t). This suffices for
       nearly all current machines and C compilers. However, you can
       define MALLOC_ALIGNMENT to be wider than this if necessary.

  Minimum overhead per allocated chunk:   4 or 8 bytes
       Each malloced chunk has a hidden word of overhead 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.

       The maximum overhead wastage (i.e., number of extra bytes
       allocated than were requested in malloc) is less than or equal
       to the minimum size, except for requests >= mmap_threshold that
       are serviced via mmap(), where the worst case wastage is 2 *
       sizeof(size_t) bytes plus the remainder from a system page (the
       minimal mmap unit); typically 4096 or 8192 bytes.

  Maximum allocated size:  4-byte size_t: 2^32 minus about two pages 
                           8-byte size_t: 2^64 minus about two pages

       It is assumed that (possibly signed) size_t 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. The ISO C standard says that it must be
       unsigned, but a few systems are known not to adhere to this.
       Additionally, even when size_t is unsigned, sbrk (which is by
       default used to obtain memory from system) accepts signed
       arguments, and may not be able to handle size_t-wide arguments
       with negative sign bit.  Generally, values that would
       appear as negative after accounting for overhead and alignment
       are supported only via mmap(), which does not have this
       limitation.

       Requests for sizes outside the allowed range will perform an optional
       failure action and then return null. (Requests may also
       also fail because a system is out of memory.)

  Thread-safety: NOT thread-safe unless USE_MALLOC_LOCK defined

       When USE_MALLOC_LOCK is defined, wrappers are created to
       surround every public call with either a pthread mutex or
       a win32 spinlock (depending on WIN32). This is not
       especially fast, and can be a major bottleneck.
       It is designed only to provide minimal protection
       in concurrent environments, and to provide a basis for
       extensions.  If you are using malloc in a concurrent program,
       you would be far better off obtaining ptmalloc, which is
       derived from a version of this malloc, and is well-tuned for
       concurrent programs. (See http://www.malloc.de) Note that
       even when USE_MALLOC_LOCK is defined, you can can guarantee
       full thread-safety only if no threads acquire memory through 
       direct calls to MORECORE or other system-level allocators.

  Compliance: I believe it is compliant with the 1997 Single Unix Specification
       (See http://www.opennc.org). Also SVID/XPG, ANSI C, and probably 
       others as well.

* 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 also report using it in stand-alone embedded systems.

    The implementation is in straight, hand-tuned ANSI C.  It is not
    at all modular. (Sorry!)  It uses a lot of macros.  To be at all
    usable, this code should be compiled using an optimizing compiler
    (for example gcc -O3) that can simplify expressions and control
    paths. (FAQ: some macros import variables as arguments rather than
    declare locals because people reported that some debuggers
    otherwise get confused.)

    OPTION                     DEFAULT VALUE

    Compilation Environment options:

    __STD_C                    derived from C compiler defines
    WIN32                      NOT defined
    HAVE_MEMCPY                defined
    USE_MEMCPY                 1 if HAVE_MEMCPY is defined
    HAVE_MMAP                  defined as 1 
    MMAP_CLEARS                1
    HAVE_MREMAP                0 unless linux defined
    malloc_getpagesize         derived from system #includes, or 4096 if not
    HAVE_USR_INCLUDE_MALLOC_H  NOT defined
    LACKS_UNISTD_H             NOT defined unless WIN32
    LACKS_SYS_PARAM_H          NOT defined unless WIN32
    LACKS_SYS_MMAN_H           NOT defined unless WIN32
    LACKS_FCNTL_H              NOT defined

    Changing default word sizes:

    INTERNAL_SIZE_T            size_t
    MALLOC_ALIGNMENT           2 * sizeof(INTERNAL_SIZE_T)
    PTR_UINT                   unsigned long
    CHUNK_SIZE_T               unsigned long

    Configuration and functionality options:

    USE_DL_PREFIX              NOT defined
    USE_PUBLIC_MALLOC_WRAPPERS NOT defined
    USE_MALLOC_LOCK            NOT defined
    DEBUG                      NOT defined
    REALLOC_ZERO_BYTES_FREES   NOT defined
    MALLOC_FAILURE_ACTION      errno = ENOMEM, if __STD_C defined, else no-op
    TRIM_FASTBINS              0
    FIRST_SORTED_BIN_SIZE      512

    Options for customizing MORECORE:

    MORECORE                   sbrk
    MORECORE_CONTIGUOUS        1 
    MORECORE_CANNOT_TRIM       NOT defined
    MMAP_AS_MORECORE_SIZE      (1024 * 1024) 

    Tuning options that are also dynamically changeable via mallopt:

    DEFAULT_MXFAST             64
    DEFAULT_TRIM_THRESHOLD     256 * 1024
    DEFAULT_TOP_PAD            0
    DEFAULT_MMAP_THRESHOLD     256 * 1024
    DEFAULT_MMAP_MAX           65536

    There are several other #defined constants and macros that you
    probably don't want to touch unless you are extending or adapting malloc.
*/

/*
  WIN32 sets up defaults for MS environment and compilers.
  Otherwise defaults are for unix.
*/

/* #define WIN32 */

#ifdef WIN32

#define WIN32_LEAN_AND_MEAN
#include <windows.h>

/* Win32 doesn't supply or need the following headers */
/* #define LACKS_UNISTD_H */
/* #define LACKS_SYS_PARAM_H */
#define LACKS_SYS_MMAN_H

/* Use the supplied emulation of sbrk */
/* #define MORECORE sbrk */
/* #define MORECORE_CONTIGUOUS 1 */
/* #define MORECORE_FAILURE    ((void*)(-1)) */

/* Use the supplied emulation of mmap and munmap */
/* #define HAVE_MMAP 1 */
/* #define MUNMAP_FAILURE  (-1) */
/* #define MMAP_CLEARS 1 */

/* These values don't really matter in windows mmap emulation */
#define MAP_PRIVATE 1
#define MAP_ANONYMOUS 2
#define PROT_READ 1
#define PROT_WRITE 2

/* Emulation functions defined at the end of this file */

/* If USE_MALLOC_LOCK, use supplied critical-section-based lock functions */
#ifdef USE_MALLOC_LOCK
static int slwait(int *sl);
static int slrelease(int *sl);
#endif

static long getpagesize(void);
static long getregionsize(void);
static void *sbrk(long size);

static void vminfo (unsigned long*free, unsigned long*reserved, unsigned long*committed);
static int cpuinfo (int whole, unsigned long*kernel, unsigned long*user);

#endif

/*
  __STD_C should be nonzero if using ANSI-standard C compiler, a C++
  compiler, or a C compiler sufficiently close to ANSI to get away
  with it.
*/

#ifndef __STD_C
#if defined(__STDC__) || defined(_cplusplus)
#define __STD_C     1
#else
#define __STD_C     0
#endif 
#endif /*__STD_C*/


/*
  Void_t* is the pointer type that malloc should say it returns
*/

#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

/* define LACKS_UNISTD_H if your system does not have a <unistd.h>. */

/* #define  LACKS_UNISTD_H */

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

/* define LACKS_SYS_PARAM_H if your system does not have a <sys/param.h>. */

/* #define  LACKS_SYS_PARAM_H */


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


/*
  Debugging:

  Because freed chunks may be overwritten with bookkeeping 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.

  Setting DEBUG does NOT provide an automated mechanism for checking
  that all accesses to malloced memory stay within their
  bounds. However, there are several add-ons and adaptations of this
  or other mallocs available that do this.
*/

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

/*
  The unsigned integer type used for comparing any two chunk sizes.
  This should be at least as wide as size_t, but should not be signed.
*/

#ifndef CHUNK_SIZE_T
#define CHUNK_SIZE_T unsigned long
#endif

/* 
  The unsigned integer type used to hold addresses when they are are
  manipulated as integers. Except that it is not defined on all
  systems, intptr_t would suffice.
*/
#ifndef PTR_UINT
#define PTR_UINT unsigned long
#endif


/*
  INTERNAL_SIZE_T is the word-size used for internal bookkeeping
  of chunk sizes.

  The default version is the same as size_t.

  While not strictly necessary, it is best to define this as an
  unsigned type, even if size_t is a signed type. This may avoid some
  artificial size limitations on some systems.

  On a 64-bit machine, you may be able to reduce malloc overhead by
  defining INTERNAL_SIZE_T to be a 32 bit `unsigned int' at the
  expense of not being able to handle more than 2^32 of malloced
  space. If this limitation is acceptable, you are encouraged to set
  this unless you are on a platform requiring 16byte alignments. In
  this case the alignment requirements turn out to negate any
  potential advantages of decreasing size_t word size.

  Implementors: Beware of the possible combinations of:
     - INTERNAL_SIZE_T might be signed or unsigned, might be 32 or 64 bits,
       and might be the same width as int or as long
     - size_t might have different width and signedness as INTERNAL_SIZE_T
     - int and long might be 32 or 64 bits, and might be the same width
  To deal with this, most comparisons and difference computations
  among INTERNAL_SIZE_Ts should cast them to CHUNK_SIZE_T, being
  aware of the fact that casting an unsigned int to a wider long does
  not sign-extend. (This also makes checking for negative numbers
  awkward.) Some of these casts result in harmless compiler warnings
  on some systems.
*/

#ifndef INTERNAL_SIZE_T
#define INTERNAL_SIZE_T size_t
#endif

/* The corresponding word size */
#define SIZE_SZ                (sizeof(INTERNAL_SIZE_T))



/*
  MALLOC_ALIGNMENT is the minimum alignment for malloc'ed chunks.
  It must be a power of two at least 2 * SIZE_SZ, even on machines
  for which smaller alignments would suffice. It may be defined as
  larger than this though. Note however that code and data structures
  are optimized for the case of 8-byte alignment.
*/


#ifndef MALLOC_ALIGNMENT
#define MALLOC_ALIGNMENT       (2 * SIZE_SZ)
#endif

/* The corresponding bit mask value */
#define MALLOC_ALIGN_MASK      (MALLOC_ALIGNMENT - 1)



/*
  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 */

/*
  TRIM_FASTBINS controls whether free() of a very small chunk can
  immediately lead to trimming. Setting to true (1) can reduce memory
  footprint, but will almost always slow down programs that use a lot
  of small chunks.

  Define this only if you are willing to give up some speed to more
  aggressively reduce system-level memory footprint when releasing
  memory in programs that use many small chunks.  You can get
  essentially the same effect by setting MXFAST to 0, but this can
  lead to even greater slowdowns in programs using many small chunks.
  TRIM_FASTBINS is an in-between compile-time option, that disables
  only those chunks bordering topmost memory from being placed in
  fastbins.
*/

#ifndef TRIM_FASTBINS
#define TRIM_FASTBINS  0
#endif


/*
  USE_DL_PREFIX will prefix all public routines with the string 'dl'.
  This is necessary when you only want to use this malloc in one part 
  of a program, using your regular system malloc elsewhere.
*/

/* #define USE_DL_PREFIX */


/*
  USE_MALLOC_LOCK causes wrapper functions to surround each
  callable routine with pthread mutex lock/unlock.

  USE_MALLOC_LOCK forces USE_PUBLIC_MALLOC_WRAPPERS to be defined
*/


/* #define USE_MALLOC_LOCK */


/*
  If USE_PUBLIC_MALLOC_WRAPPERS is defined, every public routine is
  actually a wrapper function that first calls MALLOC_PREACTION, then
  calls the internal routine, and follows it with
  MALLOC_POSTACTION. This is needed for locking, but you can also use
  this, without USE_MALLOC_LOCK, for purposes of interception,
  instrumentation, etc. It is a sad fact that using wrappers often
  noticeably degrades performance of malloc-intensive programs.
*/

#ifdef USE_MALLOC_LOCK
#define USE_PUBLIC_MALLOC_WRAPPERS
#else
/* #define USE_PUBLIC_MALLOC_WRAPPERS */
#endif


/* 
   Two-phase name translation.
   All of the actual routines are given mangled names.
   When wrappers are used, they become the public callable versions.
   When DL_PREFIX is used, the callable names are prefixed.
*/

#ifndef USE_PUBLIC_MALLOC_WRAPPERS
#define cALLOc      public_cALLOc
#define fREe        public_fREe
#define cFREe       public_cFREe
#define mALLOc      public_mALLOc
#define mEMALIGn    public_mEMALIGn
#define rEALLOc     public_rEALLOc
#define vALLOc      public_vALLOc
#define pVALLOc     public_pVALLOc
#define mALLINFo    public_mALLINFo
#define mALLOPt     public_mALLOPt
#define mTRIm       public_mTRIm
#define mSTATs      public_mSTATs
#define mUSABLe     public_mUSABLe
#define iCALLOc     public_iCALLOc
#define iCOMALLOc   public_iCOMALLOc
#endif

#ifdef USE_DL_PREFIX
#define public_cALLOc    dlcalloc
#define public_fREe      dlfree
#define public_cFREe     dlcfree
#define public_mALLOc    dlmalloc
#define public_mEMALIGn  dlmemalign
#define public_rEALLOc   dlrealloc
#define public_vALLOc    dlvalloc
#define public_pVALLOc   dlpvalloc
#define public_mALLINFo  dlmallinfo
#define public_mALLOPt   dlmallopt
#define public_mTRIm     dlmalloc_trim
#define public_mSTATs    dlmalloc_stats
#define public_mUSABLe   dlmalloc_usable_size
#define public_iCALLOc   dlindependent_calloc
#define public_iCOMALLOc dlindependent_comalloc
#else /* USE_DL_PREFIX */
#define public_cALLOc    calloc
#define public_fREe      free
#define public_cFREe     cfree
#define public_mALLOc    malloc
#define public_mEMALIGn  memalign
#define public_rEALLOc   realloc
#define public_vALLOc    valloc
#define public_pVALLOc   pvalloc
#define public_mALLINFo  mallinfo
#define public_mALLOPt   mallopt
#define public_mTRIm     malloc_trim
#define public_mSTATs    malloc_stats
#define public_mUSABLe   malloc_usable_size
#define public_iCALLOc   independent_calloc
#define public_iCOMALLOc independent_comalloc
#endif /* USE_DL_PREFIX */


/*
  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 below.

  USE_MEMCPY should be defined as 1 if you actually want to
  have memset and memcpy called. People report that the macro
  versions are faster than libc versions on some systems.
  
  Even if USE_MEMCPY is set to 1, loops to copy/clear small chunks
  (of <= 36 bytes) are manually unrolled in realloc and calloc.
*/

#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))

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

/*
  MALLOC_FAILURE_ACTION is the action to take before "return 0" when
  malloc fails to be able to return memory, either because memory is
  exhausted or because of illegal arguments.
  
  By default, sets errno if running on STD_C platform, else does nothing.  
*/

#ifndef MALLOC_FAILURE_ACTION
#if __STD_C
#define MALLOC_FAILURE_ACTION \
   errno = ENOMEM;

#else
#define MALLOC_FAILURE_ACTION
#endif
#endif

/*
  MORECORE-related declarations. By default, rely on sbrk
*/


#ifdef LACKS_UNISTD_H
#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
#if __STD_C
extern Void_t*     sbrk(ptrdiff_t);
#else
extern Void_t*     sbrk();
#endif
#endif
#endif

/*
  MORECORE is the name of the routine to call to obtain more memory
  from the system.  See below for general guidance on writing
  alternative MORECORE functions, as well as a version for WIN32 and a
  sample version for pre-OSX macos.
*/

#ifndef MORECORE
#define MORECORE sbrk
#endif

/*
  MORECORE_FAILURE is the value returned upon failure of MORECORE
  as well as mmap. Since it cannot be an otherwise valid memory address,
  and must reflect values of standard sys calls, you probably ought not
  try to redefine it.
*/

#ifndef MORECORE_FAILURE
#define MORECORE_FAILURE (-1)
#endif

/*
  If MORECORE_CONTIGUOUS is true, take advantage of fact that
  consecutive calls to MORECORE with positive arguments always return
  contiguous increasing addresses.  This is true of unix sbrk.  Even
  if not defined, when regions happen to be contiguous, malloc will
  permit allocations spanning regions obtained from different
  calls. But defining this when applicable enables some stronger
  consistency checks and space efficiencies. 
*/

#ifndef MORECORE_CONTIGUOUS
#define MORECORE_CONTIGUOUS 1
#endif

/*
  Define MORECORE_CANNOT_TRIM if your version of MORECORE
  cannot release space back to the system when given negative
  arguments. This is generally necessary only if you are using
  a hand-crafted MORECORE function that cannot handle negative arguments.
*/

/* #define MORECORE_CANNOT_TRIM */


/*
  Define HAVE_MMAP as true to optionally make malloc() use mmap() to
  allocate very large blocks.  These will be returned to the
  operating system immediately after a free(). Also, if mmap
  is available, it is used as a backup strategy in cases where
  MORECORE fails to provide space from system.

  This malloc is best tuned to work with mmap for large requests.
  If you do not have mmap, operations involving very large chunks (1MB
  or so) may be slower than you'd like.
*/

#ifndef HAVE_MMAP
  /* #define HAVE_MMAP 1 */
#endif

#if HAVE_MMAP
/* 
   Standard unix mmap using /dev/zero clears memory so calloc doesn't
   need to.
*/

#ifndef MMAP_CLEARS
#define MMAP_CLEARS 1
#endif

#else /* no mmap */
#ifndef MMAP_CLEARS
#define MMAP_CLEARS 0
#endif
#endif


/* 
   MMAP_AS_MORECORE_SIZE is the minimum mmap size argument to use if
   sbrk fails, and mmap is used as a backup (which is done only if
   HAVE_MMAP).  The value must be a multiple of page size.  This
   backup strategy generally applies only when systems have "holes" in
   address space, so sbrk cannot perform contiguous expansion, but
   there is still space available on system.  On systems for which
   this is known to be useful (i.e. most linux kernels), this occurs
   only when programs allocate huge amounts of memory.  Between this,
   and the fact that mmap regions tend to be limited, the size should
   be large, to avoid too many mmap calls and thus avoid running out
   of kernel resources.
*/

#ifndef MMAP_AS_MORECORE_SIZE
#define MMAP_AS_MORECORE_SIZE (1024 * 1024)
#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 linux
#define HAVE_MREMAP 1
#else
#define HAVE_MREMAP 0
#endif

#endif /* HAVE_MMAP */


/*
  The system page size. To the extent possible, this malloc manages
  memory from the system in page-size units.  Note that this value is
  cached during initialization into a field of malloc_state. So even
  if malloc_getpagesize is a function, it is only called once.

  The following mechanics for getpagesize were adapted from bsd/gnu
  getpagesize.h. If none of the system-probes here apply, a value of
  4096 is used, which should be OK: If they don't apply, then using
  the actual value probably doesn't impact performance.
*/


#ifndef malloc_getpagesize

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

#  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 /* use supplied emulation of getpagesize */
#        define malloc_getpagesize getpagesize() 
#      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 /* just guess */
#                define malloc_getpagesize (4096) 
#              endif
#            endif
#          endif
#        endif
#      endif
#    endif
#  endif
#endif

/*
  This version of malloc supports the standard SVID/XPG mallinfo
  routine that returns a struct containing usage properties and
  statistics. 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 that are not even meaningful in this version of
  malloc.  These fields are are instead filled by mallinfo() with
  other numbers that might 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.  The original SVID version of this struct,
  defined on most systems with mallinfo, declares all fields as
  ints. But some others define as unsigned long. If your system
  defines the fields using a type of different width than listed here,
  you must #include your system version and #define
  HAVE_USR_INCLUDE_MALLOC_H.
*/

/* #define HAVE_USR_INCLUDE_MALLOC_H */

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

/* SVID2/XPG mallinfo structure */

struct mallinfo {
  int arena;    /* non-mmapped space allocated from system */
  int ordblks;  /* number of free chunks */
  int smblks;   /* number of fastbin blocks */
  int hblks;    /* number of mmapped regions */
  int hblkhd;   /* space in mmapped regions */
  int usmblks;  /* maximum total allocated space */
  int fsmblks;  /* space available in freed fastbin blocks */
  int uordblks; /* total allocated space */
  int fordblks; /* total free space */
  int keepcost; /* top-most, releasable (via malloc_trim) space */
};

/*
  SVID/XPG defines four standard parameter numbers for mallopt,
  normally defined in malloc.h.  Only one of these (M_MXFAST) is used
  in this malloc. The others (M_NLBLKS, M_GRAIN, M_KEEP) don't apply,
  so setting them has no effect. But this malloc also supports other
  options in mallopt described below.
*/
#endif


/* ---------- description of public routines ------------ */

/*
  malloc(size_t n)
  Returns a pointer to a newly allocated chunk of at least n bytes, or null
  if no space is available. Additionally, on failure, errno is
  set to ENOMEM on ANSI C systems.

  If n is zero, malloc returns a minumum-sized chunk. (The minimum
  size is 16 bytes on most 32bit systems, and 24 or 32 bytes on 64bit
  systems.)  On most systems, size_t is an unsigned type, so calls
  with negative arguments are interpreted as requests for huge amounts
  of space, which will often fail. The maximum supported value of n
  differs across systems, but is in all cases less than the maximum
  representable value of a size_t.
*/
#if __STD_C
Void_t*  public_mALLOc(size_t);
#else
Void_t*  public_mALLOc();
#endif

/*
  free(Void_t* p)
  Releases the chunk of memory pointed to by p, that had been previously
  allocated using malloc or a related routine such as realloc.
  It has no effect if p is null. It can have arbitrary (i.e., bad!)
  effects if p has already been freed.

  Unless disabled (using mallopt), freeing very large spaces will
  when possible, automatically trigger operations that give
  back unused memory to the system, thus reducing program footprint.
*/
#if __STD_C
void     public_fREe(Void_t*);
#else
void     public_fREe();
#endif

/*
  calloc(size_t n_elements, size_t element_size);
  Returns a pointer to n_elements * element_size bytes, with all locations
  set to zero.
*/
#if __STD_C
Void_t*  public_cALLOc(size_t, size_t);
#else
Void_t*  public_cALLOc();
#endif

/*
  realloc(Void_t* p, size_t n)
  Returns 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. The algorithm
  prefers extending p when possible, otherwise it employs the
  equivalent of a malloc-copy-free sequence.

  If p is null, realloc is equivalent to malloc.  

  If space is not available, realloc returns null, errno is set (if on
  ANSI) and p is NOT freed.

  if n is for fewer bytes than already held by p, the newly unused
  space is lopped off and freed if possible.  Unless the #define
  REALLOC_ZERO_BYTES_FREES is set, realloc with a size argument of
  zero (re)allocates a minimum-sized chunk.

  Large chunks that were internally obtained via mmap will always
  be reallocated using malloc-copy-free sequences unless
  the system supports MREMAP (currently only linux).

  The old unix realloc convention of allowing the last-free'd chunk
  to be used as an argument to realloc is not supported.
*/
#if __STD_C
Void_t*  public_rEALLOc(Void_t*, size_t);
#else
Void_t*  public_rEALLOc();
#endif

/*
  memalign(size_t alignment, size_t n);
  Returns a pointer to a newly allocated chunk of n bytes, aligned
  in accord with the alignment argument.

  The alignment argument should be a power of two. If the argument is
  not a power of two, the nearest greater power is used.
  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*  public_mEMALIGn(size_t, size_t);
#else
Void_t*  public_mEMALIGn();
#endif

/*
  valloc(size_t n);
  Equivalent to memalign(pagesize, n), where pagesize is the page
  size of the system. If the pagesize is unknown, 4096 is used.
*/
#if __STD_C
Void_t*  public_vALLOc(size_t);
#else
Void_t*  public_vALLOc();
#endif



/*
  mallopt(int parameter_number, int parameter_value)
  Sets 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.  SVID/XPG/ANSI defines four standard param numbers for mallopt,
  normally defined in malloc.h.  Only one of these (M_MXFAST) is used
  in this malloc. The others (M_NLBLKS, M_GRAIN, M_KEEP) don't apply,
  so setting them has no effect. But this malloc also supports four
  other options in mallopt. See below for details.  Briefly, supported
  parameters are as follows (listed defaults are for "typical"
  configurations).

  Symbol            param #   default    allowed param values
  M_MXFAST          1         64         0-80  (0 disables fastbins)
  M_TRIM_THRESHOLD -1         256*1024   any   (-1U disables trimming)
  M_TOP_PAD        -2         0          any  
  M_MMAP_THRESHOLD -3         256*1024   any   (or 0 if no MMAP support)
  M_MMAP_MAX       -4         65536      any   (0 disables use of mmap)
*/
#if __STD_C
int      public_mALLOPt(int, int);
#else
int      public_mALLOPt();
#endif


/*
  mallinfo()
  Returns (by copy) a struct containing various summary statistics:

  arena:     current total non-mmapped bytes allocated from system 
  ordblks:   the number of free chunks 
  smblks:    the number of fastbin blocks (i.e., small chunks that
               have been freed but not use resused or consolidated)
  hblks:     current number of mmapped regions 
  hblkhd:    total bytes held in mmapped regions 
  usmblks:   the maximum total allocated space. This will be greater
                than current total if trimming has occurred.
  fsmblks:   total bytes held in fastbin blocks 
  uordblks:  current total allocated space (normal or mmapped)
  fordblks:  total free space 
  keepcost:  the maximum number of bytes that could ideally be released
               back to system via malloc_trim. ("ideally" means that
               it ignores page restrictions etc.)

  Because these fields are ints, but internal bookkeeping may
  be kept as longs, the reported values may wrap around zero and 
  thus be inaccurate.
*/
#if __STD_C
struct mallinfo public_mALLINFo(void);
#else
struct mallinfo public_mALLINFo();
#endif

/*
  independent_calloc(size_t n_elements, size_t element_size, Void_t* chunks[]);

  independent_calloc is similar to calloc, but instead of returning a
  single cleared space, it returns an array of pointers to n_elements
  independent elements that can hold contents of size elem_size, each
  of which starts out cleared, and can be independently freed,
  realloc'ed etc. The elements are guaranteed to be adjacently
  allocated (this is not guaranteed to occur with multiple callocs or
  mallocs), which may also improve cache locality in some
  applications.

  The "chunks" argument is optional (i.e., may be null, which is
  probably the most typical usage). If it is null, the returned array
  is itself dynamically allocated and should also be freed when it is
  no longer needed. Otherwise, the chunks array must be of at least
  n_elements in length. It is filled in with the pointers to the
  chunks.

  In either case, independent_calloc returns this pointer array, or
  null if the allocation failed.  If n_elements is zero and "chunks"
  is null, it returns a chunk representing an array with zero elements
  (which should be freed if not wanted).

  Each element must be individually freed when it is no longer
  needed. If you'd like to instead be able to free all at once, you
  should instead use regular calloc and assign pointers into this
  space to represent elements.  (In this case though, you cannot
  independently free elements.)
  
  independent_calloc simplifies and speeds up implementations of many
  kinds of pools.  It may also be useful when constructing large data
  structures that initially have a fixed number of fixed-sized nodes,
  but the number is not known at compile time, and some of the nodes
  may later need to be freed. For example:

  struct Node { int item; struct Node* next; };
  
  struct Node* build_list() {
    struct Node** pool;
    int n = read_number_of_nodes_needed();
    if (n <= 0) return 0;
    pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0);
    if (pool == 0) die(); 
    // organize into a linked list... 
    struct Node* first = pool[0];
    for (i = 0; i < n-1; ++i) 
      pool[i]->next = pool[i+1];
    free(pool);     // Can now free the array (or not, if it is needed later)
    return first;
  }
*/
#if __STD_C
Void_t** public_iCALLOc(size_t, size_t, Void_t**);
#else
Void_t** public_iCALLOc();
#endif

/*
  independent_comalloc(size_t n_elements, size_t sizes[], Void_t* chunks[]);

  independent_comalloc allocates, all at once, a set of n_elements
  chunks with sizes indicated in the "sizes" array.    It returns
  an array of pointers to these elements, each of which can be
  independently freed, realloc'ed etc. The elements are guaranteed to
  be adjacently allocated (this is not guaranteed to occur with
  multiple callocs or mallocs), which may also improve cache locality
  in some applications.

  The "chunks" argument is optional (i.e., may be null). If it is null
  the returned array is itself dynamically allocated and should also
  be freed when it is no longer needed. Otherwise, the chunks array
  must be of at least n_elements in length. It is filled in with the
  pointers to the chunks.

  In either case, independent_comalloc returns this pointer array, or
  null if the allocation failed.  If n_elements is zero and chunks is
  null, it returns a chunk representing an array with zero elements
  (which should be freed if not wanted).
  
  Each element must be individually freed when it is no longer
  needed. If you'd like to instead be able to free all at once, you
  should instead use a single regular malloc, and assign pointers at
  particular offsets in the aggregate space. (In this case though, you 
  cannot independently free elements.)

  independent_comallac differs from independent_calloc in that each
  element may have a different size, and also that it does not
  automatically clear elements.

  independent_comalloc can be used to speed up allocation in cases
  where several structs or objects must always be allocated at the
  same time.  For example:

  struct Head { ... }
  struct Foot { ... }

  void send_message(char* msg) {
    int msglen = strlen(msg);
    size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) };
    void* chunks[3];
    if (independent_comalloc(3, sizes, chunks) == 0)
      die();
    struct Head* head = (struct Head*)(chunks[0]);
    char*        body = (char*)(chunks[1]);
    struct Foot* foot = (struct Foot*)(chunks[2]);
    // ...
  }

  In general though, independent_comalloc is worth using only for
  larger values of n_elements. For small values, you probably won't
  detect enough difference from series of malloc calls to bother.

  Overuse of independent_comalloc can increase overall memory usage,
  since it cannot reuse existing noncontiguous small chunks that
  might be available for some of the elements.
*/
#if __STD_C
Void_t** public_iCOMALLOc(size_t, size_t*, Void_t**);
#else
Void_t** public_iCOMALLOc();
#endif


/*
  pvalloc(size_t n);
  Equivalent to valloc(minimum-page-that-holds(n)), that is,
  round up n to nearest pagesize.
 */
#if __STD_C
Void_t*  public_pVALLOc(size_t);
#else
Void_t*  public_pVALLOc();
#endif

/*
  cfree(Void_t* p);
  Equivalent to free(p).

  cfree is needed/defined on some systems that pair it with calloc,
  for odd historical reasons (such as: cfree is used in example 
  code in the first edition of K&R).
*/
#if __STD_C
void     public_cFREe(Void_t*);
#else
void     public_cFREe();
#endif

/*
  malloc_trim(size_t pad);

  If possible, 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.
  On systems that do not support "negative sbrks", it will always
  rreturn 0.
*/
#if __STD_C
int      public_mTRIm(size_t);
#else
int      public_mTRIm();
#endif

/*
  malloc_usable_size(Void_t* p);

  Returns the number of bytes you can actually use in
  an allocated chunk, which may be more than you requested (although
  often not) due to alignment and minimum size constraints.
  You can use this many bytes without worrying about
  overwriting other allocated objects. This is not a particularly great
  programming practice. malloc_usable_size can be more useful in
  debugging and assertions, for example:

  p = malloc(n);
  assert(malloc_usable_size(p) >= 256);

*/
#if __STD_C
size_t   public_mUSABLe(Void_t*);
#else
size_t   public_mUSABLe();
#endif

/*
  malloc_stats();
  Prints on stderr the amount of space obtained 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), 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. Because it includes
  alignment wastage as being in use, this figure may be greater than
  zero even when no user-level chunks are allocated.

  The reported current and maximum system memory can be inaccurate if
  a program makes other calls to system memory allocation functions
  (normally sbrk) outside of malloc.

  malloc_stats prints only the most commonly interesting statistics.
  More information can be obtained by calling mallinfo.

*/
#if __STD_C
void     public_mSTATs(void);
#else
void     public_mSTATs();
#endif

/* mallopt tuning options */

/*
  M_MXFAST is the maximum request size used for "fastbins", special bins
  that hold returned chunks without consolidating their spaces. This
  enables future requests for chunks of the same size to be handled
  very quickly, but can increase fragmentation, and thus increase the
  overall memory footprint of a program.

  This malloc manages fastbins very conservatively yet still
  efficiently, so fragmentation is rarely a problem for values less
  than or equal to the default.  The maximum supported value of MXFAST
  is 80. You wouldn't want it any higher than this anyway.  Fastbins
  are designed especially for use with many small structs, objects or
  strings -- the default handles structs/objects/arrays with sizes up
  to 16 4byte fields, or small strings representing words, tokens,
  etc. Using fastbins for larger objects normally worsens
  fragmentation without improving speed.

  M_MXFAST is set in REQUEST size units. It is internally used in
  chunksize units, which adds padding and alignment.  You can reduce
  M_MXFAST to 0 to disable all use of fastbins.  This causes the malloc
  algorithm to be a closer approximation of fifo-best-fit in all cases,
  not just for larger requests, but will generally cause it to be
  slower.
*/


/* M_MXFAST is a standard SVID/XPG tuning option, usually listed in malloc.h */
#ifndef M_MXFAST
#define M_MXFAST            1    
#endif

#ifndef DEFAULT_MXFAST
#define DEFAULT_MXFAST     64
#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 this much memory.

  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 trim value must be greater than page size to have any useful
  effect.  To disable trimming completely, you can set to 
  (unsigned long)(-1)

  Trim settings interact with fastbin (MXFAST) settings: Unless
  TRIM_FASTBINS is defined, automatic trimming never takes place upon
  freeing a chunk with size less than or equal to MXFAST. Trimming is
  instead delayed until subsequent freeing of larger chunks. However,
  you can still force an attempted trim by calling malloc_trim.

  Also, trimming is not generally possible in cases where
  the main arena is obtained via mmap.

  Note that the trick some people use of mallocing a huge space and
  then freeing it at program startup, in an attempt to reserve system
  memory, doesn't have the intended effect under automatic trimming,
  since that memory will immediately be returned to the system.
*/

#define M_TRIM_THRESHOLD       -1

#ifndef DEFAULT_TRIM_THRESHOLD
#define DEFAULT_TRIM_THRESHOLD (256 * 1024)
#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.
*/

#define M_TOP_PAD              -2

#ifndef DEFAULT_TOP_PAD
#define DEFAULT_TOP_PAD        (0)
#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 benefits that:

   1. 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. 
   2. Mapped memory can never become `locked' between
      other chunks, as can happen with normally allocated chunks, which
      means that even trimming via malloc_trim would not release them.
   3. On some systems with "holes" in address spaces, mmap can obtain
      memory that sbrk cannot.

  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.

  The advantages of mmap nearly always outweigh disadvantages for
  "large" chunks, but the value of "large" varies across systems.  The
  default is an empirically derived value that works well in most
  systems.
*/

#define M_MMAP_THRESHOLD      -3

#ifndef DEFAULT_MMAP_THRESHOLD
#define DEFAULT_MMAP_THRESHOLD (256 * 1024)
#endif

/*
  M_MMAP_MAX is the maximum number of requests to simultaneously
  service using mmap. This parameter exists because
. Some systems have a limited number of internal tables for
  use by mmap, and using more than a few of them may degrade
  performance.

  The default is set to a value that serves only as a safeguard.
  Setting to 0 disables use of mmap for servicing large requests.  If
  HAVE_MMAP is not set, the default value is 0, and attempts to set it
  to non-zero values in mallopt will fail.
*/

#define M_MMAP_MAX             -4

#ifndef DEFAULT_MMAP_MAX
#if HAVE_MMAP
#define DEFAULT_MMAP_MAX       (65536)
#else
#define DEFAULT_MMAP_MAX       (0)
#endif
#endif

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

/* 
  ========================================================================
  To make a fully customizable malloc.h header file, cut everything
  above this line, put into file malloc.h, edit to suit, and #include it 
  on the next line, as well as in programs that use this malloc.
  ========================================================================
*/

/* #include "malloc.h" */

/* --------------------- public wrappers ---------------------- */

#ifdef USE_PUBLIC_MALLOC_WRAPPERS

/* Declare all routines as internal */
#if __STD_C
static Void_t*  mALLOc(size_t);
static void     fREe(Void_t*);
static Void_t*  rEALLOc(Void_t*, size_t);
static Void_t*  mEMALIGn(size_t, size_t);
static Void_t*  vALLOc(size_t);
static Void_t*  pVALLOc(size_t);
static Void_t*  cALLOc(size_t, size_t);
static Void_t** iCALLOc(size_t, size_t, Void_t**);
static Void_t** iCOMALLOc(size_t, size_t*, Void_t**);
static void     cFREe(Void_t*);
static int      mTRIm(size_t);
static size_t   mUSABLe(Void_t*);
static void     mSTATs();
static int      mALLOPt(int, int);
static struct mallinfo mALLINFo(void);
#else
static Void_t*  mALLOc();
static void     fREe();
static Void_t*  rEALLOc();
static Void_t*  mEMALIGn();
static Void_t*  vALLOc();
static Void_t*  pVALLOc();
static Void_t*  cALLOc();
static Void_t** iCALLOc();
static Void_t** iCOMALLOc();
static void     cFREe();
static int      mTRIm();
static size_t   mUSABLe();
static void     mSTATs();
static int      mALLOPt();
static struct mallinfo mALLINFo();
#endif

/*
  MALLOC_PREACTION and MALLOC_POSTACTION should be
  defined to return 0 on success, and nonzero on failure.
  The return value of MALLOC_POSTACTION is currently ignored
  in wrapper functions since there is no reasonable default
  action to take on failure.
*/


#ifdef USE_MALLOC_LOCK

#ifdef WIN32

static int mALLOC_MUTEx;
#define MALLOC_PREACTION   slwait(&mALLOC_MUTEx)
#define MALLOC_POSTACTION  slrelease(&mALLOC_MUTEx)

#else

#include <pthread.h>

static pthread_mutex_t mALLOC_MUTEx = PTHREAD_MUTEX_INITIALIZER;

#define MALLOC_PREACTION   pthread_mutex_lock(&mALLOC_MUTEx)
#define MALLOC_POSTACTION  pthread_mutex_unlock(&mALLOC_MUTEx)

#endif /* USE_MALLOC_LOCK */

#else

/* Substitute anything you like for these */

#define MALLOC_PREACTION   (0)
#define MALLOC_POSTACTION  (0)

#endif

Void_t* public_mALLOc(size_t bytes) {
  Void_t* m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = mALLOc(bytes);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

void public_fREe(Void_t* m) {
  if (MALLOC_PREACTION != 0) {
    return;
  }
  fREe(m);
  if (MALLOC_POSTACTION != 0) {
  }
}

Void_t* public_rEALLOc(Void_t* m, size_t bytes) {
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = rEALLOc(m, bytes);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

Void_t* public_mEMALIGn(size_t alignment, size_t bytes) {
  Void_t* m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = mEMALIGn(alignment, bytes);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

Void_t* public_vALLOc(size_t bytes) {
  Void_t* m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = vALLOc(bytes);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

Void_t* public_pVALLOc(size_t bytes) {
  Void_t* m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = pVALLOc(bytes);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

Void_t* public_cALLOc(size_t n, size_t elem_size) {
  Void_t* m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = cALLOc(n, elem_size);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}


Void_t** public_iCALLOc(size_t n, size_t elem_size, Void_t** chunks) {
  Void_t** m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = iCALLOc(n, elem_size, chunks);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

Void_t** public_iCOMALLOc(size_t n, size_t sizes[], Void_t** chunks) {
  Void_t** m;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  m = iCOMALLOc(n, sizes, chunks);
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

void public_cFREe(Void_t* m) {
  if (MALLOC_PREACTION != 0) {
    return;
  }
  cFREe(m);
  if (MALLOC_POSTACTION != 0) {
  }
}

int public_mTRIm(size_t s) {
  int result;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  result = mTRIm(s);
  if (MALLOC_POSTACTION != 0) {
  }
  return result;
}

size_t public_mUSABLe(Void_t* m) {
  size_t result;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  result = mUSABLe(m);
  if (MALLOC_POSTACTION != 0) {
  }
  return result;
}

void public_mSTATs() {
  if (MALLOC_PREACTION != 0) {
    return;
  }
  mSTATs();
  if (MALLOC_POSTACTION != 0) {
  }
}

struct mallinfo public_mALLINFo() {
  struct mallinfo m;
  if (MALLOC_PREACTION != 0) {
    struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
    return nm;
  }
  m = mALLINFo();
  if (MALLOC_POSTACTION != 0) {
  }
  return m;
}

int public_mALLOPt(int p, int v) {
  int result;
  if (MALLOC_PREACTION != 0) {
    return 0;
  }
  result = mALLOPt(p, v);
  if (MALLOC_POSTACTION != 0) {
  }
  return result;
}

#endif



/* ------------- Optional versions of memcopy ---------------- */


#if USE_MEMCPY

/* 
  Note: memcpy is ONLY invoked with non-overlapping regions,
  so the (usually slower) memmove is not needed.
*/

#define MALLOC_COPY(dest, src, nbytes)  memcpy(dest, src, nbytes)
#define MALLOC_ZERO(dest, nbytes)       memset(dest, 0,   nbytes)

#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);                           \
  CHUNK_SIZE_T  mctmp = (nbytes)/sizeof(INTERNAL_SIZE_T);                     \
  long 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;                           \
  CHUNK_SIZE_T  mctmp = (nbytes)/sizeof(INTERNAL_SIZE_T);                     \
  long 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

/* ------------------ MMAP support ------------------  */


#if HAVE_MMAP

#ifndef LACKS_FCNTL_H
#include <fcntl.h>
#endif

#ifndef LACKS_SYS_MMAN_H
#include <sys/mman.h>
#endif

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

/* 
   Nearly all versions of mmap support MAP_ANONYMOUS, 
   so the following is unlikely to be needed, but is
   supplied just in case.
*/

#ifndef MAP_ANONYMOUS

static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */

#define MMAP(addr, size, prot, flags) ((dev_zero_fd < 0) ? \
 (dev_zero_fd = open("/dev/zero", O_RDWR), \
  mmap((addr), (size), (prot), (flags), dev_zero_fd, 0)) : \
   mmap((addr), (size), (prot), (flags), dev_zero_fd, 0))

#else

#define MMAP(addr, size, prot, flags) \
 (mmap((addr), (size), (prot), (flags)|MAP_ANONYMOUS, -1, 0))

#endif


#endif /* HAVE_MMAP */


/*
  -----------------------  Chunk representations -----------------------
*/


/*
  This struct declaration is misleading (but accurate and necessary).
  It declares a "view" into memory allowing access to necessary
  fields at known offsets from a given base. See explanation below.
*/

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 at least 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. If
    prev_inuse is set for any given chunk, then you CANNOT determine
    the size of the previous chunk, and might even get a memory
    addressing fault when trying to do so.

    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 but can be very confusing when trying
    to extend or adapt this code.

    The two exceptions to all this are

     1. The special chunk `top' 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.

     2. Chunks allocated via mmap, which have the second-lowest-order
        bit (IS_MMAPPED) set in their size fields.  Because they are
        allocated one-by-one, each must contain its own trailing size field.

*/

/*
  ---------- Size and alignment checks and conversions ----------
*/

/* 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))

/* The smallest possible chunk */
#define MIN_CHUNK_SIZE        (sizeof(struct malloc_chunk))

/* The smallest size we can malloc is an aligned minimal chunk */

#define MINSIZE  \
  (CHUNK_SIZE_T)(((MIN_CHUNK_SIZE+MALLOC_ALIGN_MASK) & ~MALLOC_ALIGN_MASK))

/* Check if m has acceptable alignment */

#define aligned_OK(m)  (((PTR_UINT)((m)) & (MALLOC_ALIGN_MASK)) == 0)


/* 
   Check if a request is so large that it would wrap around zero when
   padded and aligned. To simplify some other code, the bound is made
   low enough so that adding MINSIZE will also not wrap around sero.
*/

#define REQUEST_OUT_OF_RANGE(req)                                 \
  ((CHUNK_SIZE_T)(req) >=                                        \
   (CHUNK_SIZE_T)(INTERNAL_SIZE_T)(-2 * MINSIZE))    

/* pad request bytes into a usable size -- internal version */

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

/*  Same, except also perform argument check */

#define checked_request2size(req, sz)                             \
  if (REQUEST_OUT_OF_RANGE(req)) {                                \
    MALLOC_FAILURE_ACTION;                                        \
    return 0;                                                     \
  }                                                               \
  (sz) = request2size(req);                                              

/*
  --------------- Physical chunk operations ---------------
*/


/* size field is or'ed with PREV_INUSE when previous adjacent chunk in use */
#define PREV_INUSE 0x1

/* extract inuse bit of previous chunk */
#define prev_inuse(p)       ((p)->size & PREV_INUSE)


/* size field is or'ed with IS_MMAPPED if the chunk was obtained with mmap() */
#define IS_MMAPPED 0x2

/* check for mmap()'ed chunk */
#define chunk_is_mmapped(p) ((p)->size & IS_MMAPPED)

/* 
  Bits to mask off when extracting size 

  Note: IS_MMAPPED is intentionally not masked off from size field in
  macros for which mmapped chunks should never be seen. This should
  cause helpful core dumps to occur if it is tried by accident by
  people extending or adapting this malloc.
*/
#define SIZE_BITS (PREV_INUSE|IS_MMAPPED)

/* Get size, ignoring use bits */
#define chunksize(p)         ((p)->size & ~(SIZE_BITS))


/* 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)))

/* extract p's inuse bit */
#define inuse(p)\
((((mchunkptr)(((char*)(p))+((p)->size & ~PREV_INUSE)))->size) & PREV_INUSE)

/* set/clear chunk as being inuse 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))


/* 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 field */
#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))


/*
  -------------------- Internal data structures --------------------

   All internal state is held in an instance of malloc_state defined
   below. There are no other static variables, except in two optional
   cases: 
   * If USE_MALLOC_LOCK is defined, the mALLOC_MUTEx declared above. 
   * If HAVE_MMAP is true, but mmap doesn't support
     MAP_ANONYMOUS, a dummy file descriptor for mmap.

   Beware of lots of tricks that minimize the total bookkeeping space
   requirements. The result is a little over 1K bytes (for 4byte
   pointers and size_t.)
*/

/*
  Bins

    An array of bin headers for free 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.  Most bins hold sizes that are
    unusual as malloc request sizes, but are more usual for fragments
    and consolidated sets of chunks, which is what these bins hold, so
    they can be found quickly.  All procedures maintain the invariant
    that no consolidated chunk physically borders another one, so each
    chunk in a list is known to be preceeded and followed by either
    inuse chunks or the ends of memory.

    Chunks in bins are kept in size order, with ties going to the
    approximately least recently used chunk. Ordering isn't needed
    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 (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.

    To simplify use in double-linked lists, each bin header acts
    as a malloc_chunk. This avoids special-casing for headers.
    But to conserve space and improve locality, we allocate
    only the fd/bk pointers of bins, and then use repositioning tricks
    to treat these as the fields of a malloc_chunk*.  
*/

typedef struct malloc_chunk* mbinptr;

/* addressing -- note that bin_at(0) does not exist */
#define bin_at(m, i) ((mbinptr)((char*)&((m)->bins[(i)<<1]) - (SIZE_SZ<<1)))

/* analog of ++bin */
#define next_bin(b)  ((mbinptr)((char*)(b) + (sizeof(mchunkptr)<<1)))

/* Reminders about list directionality within bins */
#define first(b)     ((b)->fd)
#define last(b)      ((b)->bk)

/* Take a chunk off a bin list */
#define unlink(P, BK, FD) {                                            \
  FD = P->fd;                                                          \
  BK = P->bk;                                                          \
  FD->bk = BK;                                                         \
  BK->fd = FD;                                                         \
}

/*
  Indexing

    Bins for sizes < 512 bytes contain chunks of all the same size, spaced
    8 bytes apart. Larger bins are approximately logarithmically spaced:

    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

    The bins top out around 1MB because we expect to service large
    requests via mmap.
*/

#define NBINS              96
#define NSMALLBINS         32
#define SMALLBIN_WIDTH      8
#define MIN_LARGE_SIZE    256

#define in_smallbin_range(sz)  \
  ((CHUNK_SIZE_T)(sz) < (CHUNK_SIZE_T)MIN_LARGE_SIZE)

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

/*
  Compute index for size. We expect this to be inlined when
  compiled with optimization, else not, which works out well.
*/
static int largebin_index(unsigned int sz) {
  unsigned int  x = sz >> SMALLBIN_WIDTH; 
  unsigned int m;            /* bit position of highest set bit of m */

  if (x >= 0x10000) return NBINS-1;

  /* On intel, use BSRL instruction to find highest bit */
#if defined(__GNUC__) && defined(i386)

  __asm__("bsrl %1,%0\n\t"
          : "=r" (m) 
          : "g"  (x));

#else
  {
    /*
      Based on branch-free nlz algorithm in chapter 5 of Henry
      S. Warren Jr's book "Hacker's Delight".
    */

    unsigned int n = ((x - 0x100) >> 16) & 8;
    x <<= n; 
    m = ((x - 0x1000) >> 16) & 4;
    n += m; 
    x <<= m; 
    m = ((x - 0x4000) >> 16) & 2;
    n += m; 
    x = (x << m) >> 14;
    m = 13 - n + (x & ~(x>>1));
  }
#endif

  /* Use next 2 bits to create finer-granularity bins */
  return NSMALLBINS + (m << 2) + ((sz >> (m + 6)) & 3);
}

#define bin_index(sz) \
 ((in_smallbin_range(sz)) ? smallbin_index(sz) : largebin_index(sz))

/*
  FIRST_SORTED_BIN_SIZE is the chunk size corresponding to the
  first bin that is maintained in sorted order. This must
  be the smallest size corresponding to a given bin.

  Normally, this should be MIN_LARGE_SIZE. But you can weaken
  best fit guarantees to sometimes speed up malloc by increasing value.
  Doing this means that malloc may choose a chunk that is 
  non-best-fitting by up to the width of the bin.

  Some useful cutoff values:
      512 - all bins sorted
     2560 - leaves bins <=     64 bytes wide unsorted  
    12288 - leaves bins <=    512 bytes wide unsorted
    65536 - leaves bins <=   4096 bytes wide unsorted
   262144 - leaves bins <=  32768 bytes wide unsorted
       -1 - no bins sorted (not recommended!)
*/

#define FIRST_SORTED_BIN_SIZE MIN_LARGE_SIZE 
/* #define FIRST_SORTED_BIN_SIZE 65536 */

/*
  Unsorted chunks

    All remainders from chunk splits, as well as all returned chunks,
    are first placed in the "unsorted" bin. They are then placed
    in regular bins after malloc gives them ONE chance to be used before
    binning. So, basically, the unsorted_chunks list acts as a queue,
    with chunks being placed on it in free (and malloc_consolidate),
    and taken off (to be either used or placed in bins) in malloc.
*/

/* The otherwise unindexable 1-bin is used to hold unsorted chunks. */
#define unsorted_chunks(M)          (bin_at(M, 1))

/*
  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).  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 do so when getting memory from system, so we make
    initial_top treat the bin as a legal but unusable chunk during the
    interval between initialization and the first call to
    sYSMALLOc. (This is somewhat delicate, since it relies on
    the 2 preceding words to be zero during this interval as well.)
*/

/* Conveniently, the unsorted bin can be used as dummy top on first call */
#define initial_top(M)              (unsorted_chunks(M))

/*
  Binmap

    To help compensate for the large number of bins, a one-level index
    structure is used for bin-by-bin searching.  `binmap' is a
    bitvector recording whether bins are definitely empty so they can
    be skipped over during during traversals.  The bits are NOT always
    cleared as soon as bins are empty, but instead only
    when they are noticed to be empty during traversal in malloc.
*/

/* Conservatively use 32 bits per map word, even if on 64bit system */
#define BINMAPSHIFT      5
#define BITSPERMAP       (1U << BINMAPSHIFT)
#define BINMAPSIZE       (NBINS / BITSPERMAP)

#define idx2block(i)     ((i) >> BINMAPSHIFT)
#define idx2bit(i)       ((1U << ((i) & ((1U << BINMAPSHIFT)-1))))

#define mark_bin(m,i)    ((m)->binmap[idx2block(i)] |=  idx2bit(i))
#define unmark_bin(m,i)  ((m)->binmap[idx2block(i)] &= ~(idx2bit(i)))
#define get_binmap(m,i)  ((m)->binmap[idx2block(i)] &   idx2bit(i))

/*
  Fastbins

    An array of lists holding recently freed small chunks.  Fastbins
    are not doubly linked.  It is faster to single-link them, and
    since chunks are never removed from the middles of these lists,
    double linking is not necessary. Also, unlike regular bins, they
    are not even processed in FIFO order (they use faster LIFO) since
    ordering doesn't much matter in the transient contexts in which
    fastbins are normally used.

    Chunks in fastbins keep their inuse bit set, so they cannot
    be consolidated with other free chunks. malloc_consolidate
    releases all chunks in fastbins and consolidates them with
    other free chunks. 
*/

typedef struct malloc_chunk* mfastbinptr;

/* offset 2 to use otherwise unindexable first 2 bins */
#define fastbin_index(sz)        ((((unsigned int)(sz)) >> 3) - 2)

/* The maximum fastbin request size we support */
#define MAX_FAST_SIZE     80

#define NFASTBINS  (fastbin_index(request2size(MAX_FAST_SIZE))+1)

/*
  FASTBIN_CONSOLIDATION_THRESHOLD is the size of a chunk in free()
  that triggers automatic consolidation of possibly-surrounding
  fastbin chunks. This is a heuristic, so the exact value should not
  matter too much. It is defined at half the default trim threshold as a
  compromise heuristic to only attempt consolidation if it is likely
  to lead to trimming. However, it is not dynamically tunable, since
  consolidation reduces fragmentation surrounding loarge chunks even 
  if trimming is not used.
*/

#define FASTBIN_CONSOLIDATION_THRESHOLD  \
  ((unsigned long)(DEFAULT_TRIM_THRESHOLD) >> 1)

/*
  Since the lowest 2 bits in max_fast don't matter in size comparisons, 
  they are used as flags.
*/

/*
  ANYCHUNKS_BIT held in max_fast indicates that there may be any
  freed chunks at all. It is set true when entering a chunk into any
  bin.
*/

#define ANYCHUNKS_BIT        (1U)

#define have_anychunks(M)     (((M)->max_fast &  ANYCHUNKS_BIT))
#define set_anychunks(M)      ((M)->max_fast |=  ANYCHUNKS_BIT)
#define clear_anychunks(M)    ((M)->max_fast &= ~ANYCHUNKS_BIT)

/*
  FASTCHUNKS_BIT held in max_fast indicates that there are probably
  some fastbin chunks. It is set true on entering a chunk into any
  fastbin, and cleared only in malloc_consolidate.
*/

#define FASTCHUNKS_BIT        (2U)

#define have_fastchunks(M)   (((M)->max_fast &  FASTCHUNKS_BIT))
#define set_fastchunks(M)    ((M)->max_fast |=  (FASTCHUNKS_BIT|ANYCHUNKS_BIT))
#define clear_fastchunks(M)  ((M)->max_fast &= ~(FASTCHUNKS_BIT))

/* 
   Set value of max_fast. 
   Use impossibly small value if 0.
*/

#define set_max_fast(M, s) \
  (M)->max_fast = (((s) == 0)? SMALLBIN_WIDTH: request2size(s)) | \
  ((M)->max_fast &  (FASTCHUNKS_BIT|ANYCHUNKS_BIT))

#define get_max_fast(M) \
  ((M)->max_fast & ~(FASTCHUNKS_BIT | ANYCHUNKS_BIT))


/*
  morecore_properties is a status word holding dynamically discovered
  or controlled properties of the morecore function
*/

#define MORECORE_CONTIGUOUS_BIT  (1U)

#define contiguous(M) \
        (((M)->morecore_properties &  MORECORE_CONTIGUOUS_BIT))
#define noncontiguous(M) \
        (((M)->morecore_properties &  MORECORE_CONTIGUOUS_BIT) == 0)
#define set_contiguous(M) \
        ((M)->morecore_properties |=  MORECORE_CONTIGUOUS_BIT)
#define set_noncontiguous(M) \
        ((M)->morecore_properties &= ~MORECORE_CONTIGUOUS_BIT)


/*
   ----------- Internal state representation and initialization -----------
*/

struct malloc_state {

  /* The maximum chunk size to be eligible for fastbin */
  INTERNAL_SIZE_T  max_fast;   /* low 2 bits used as flags */

  /* Fastbins */
  mfastbinptr      fastbins[NFASTBINS];

  /* Base of the topmost chunk -- not otherwise kept in a bin */
  mchunkptr        top;

  /* The remainder from the most recent split of a small request */
  mchunkptr        last_remainder;

  /* Normal bins packed as described above */
  mchunkptr        bins[NBINS * 2];

  /* Bitmap of bins. Trailing zero map handles cases of largest binned size */
  unsigned int     binmap[BINMAPSIZE+1];

  /* Tunable parameters */
  CHUNK_SIZE_T     trim_threshold;
  INTERNAL_SIZE_T  top_pad;
  INTERNAL_SIZE_T  mmap_threshold;

  /* Memory map support */
  int              n_mmaps;
  int              n_mmaps_max;
  int              max_n_mmaps;

  /* Cache malloc_getpagesize */
  unsigned int     pagesize;    

  /* Track properties of MORECORE */
  unsigned int     morecore_properties;

  /* Statistics */
  INTERNAL_SIZE_T  mmapped_mem;
  INTERNAL_SIZE_T  sbrked_mem;
  INTERNAL_SIZE_T  max_sbrked_mem;
  INTERNAL_SIZE_T  max_mmapped_mem;
  INTERNAL_SIZE_T  max_total_mem;
};

typedef struct malloc_state *mstate;

/* 
   There is exactly one instance of this struct in this malloc.
   If you are adapting this malloc in a way that does NOT use a static
   malloc_state, you MUST explicitly zero-fill it before using. This
   malloc relies on the property that malloc_state is initialized to
   all zeroes (as is true of C statics).
*/

static struct malloc_state av_;  /* never directly referenced */

/*
   All uses of av_ are via get_malloc_state().
   At most one "call" to get_malloc_state is made per invocation of
   the public versions of malloc and free, but other routines
   that in turn invoke malloc and/or free may call more then once. 
   Also, it is called in check* routines if DEBUG is set.
*/

#define get_malloc_state() (&(av_))

/*
  Initialize a malloc_state struct.

  This is called only from within malloc_consolidate, which needs
  be called in the same contexts anyway.  It is never called directly
  outside of malloc_consolidate because some optimizing compilers try
  to inline it at all call points, which turns out not to be an
  optimization at all. (Inlining it in malloc_consolidate is fine though.)
*/

#if __STD_C
static void malloc_init_state(mstate av)
#else
static void malloc_init_state(av) mstate av;
#endif
{
  int     i;
  mbinptr bin;
  
  /* Establish circular links for normal bins */
  for (i = 1; i < NBINS; ++i) { 
    bin = bin_at(av,i);
    bin->fd = bin->bk = bin;
  }

  av->top_pad        = DEFAULT_TOP_PAD;
  av->n_mmaps_max    = DEFAULT_MMAP_MAX;
  av->mmap_threshold = DEFAULT_MMAP_THRESHOLD;
  av->trim_threshold = DEFAULT_TRIM_THRESHOLD;

#if MORECORE_CONTIGUOUS
  set_contiguous(av);
#else
  set_noncontiguous(av);
#endif


  set_max_fast(av, DEFAULT_MXFAST);

  av->top            = initial_top(av);
  av->pagesize       = malloc_getpagesize;
}

/* 
   Other internal utilities operating on mstates
*/

#if __STD_C
static Void_t*  sYSMALLOc(INTERNAL_SIZE_T, mstate);
static int      sYSTRIm(size_t, mstate);
static void     malloc_consolidate(mstate);
static Void_t** iALLOc(size_t, size_t*, int, Void_t**);
#else
static Void_t*  sYSMALLOc();
static int      sYSTRIm();
static void     malloc_consolidate();
static Void_t** iALLOc();
#endif

/*
  Debugging support

  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 ! DEBUG

#define check_chunk(P)
#define check_free_chunk(P)
#define check_inuse_chunk(P)
#define check_remalloced_chunk(P,N)
#define check_malloced_chunk(P,N)
#define check_malloc_state()

#else
#define check_chunk(P)              do_check_chunk(P)
#define check_free_chunk(P)         do_check_free_chunk(P)
#define check_inuse_chunk(P)        do_check_inuse_chunk(P)
#define check_remalloced_chunk(P,N) do_check_remalloced_chunk(P,N)
#define check_malloced_chunk(P,N)   do_check_malloced_chunk(P,N)
#define check_malloc_state()        do_check_malloc_state()

/*
  Properties of all chunks
*/

#if __STD_C
static void do_check_chunk(mchunkptr p)
#else
static void do_check_chunk(p) mchunkptr p;
#endif
{
  mstate av = get_malloc_state();
  CHUNK_SIZE_T  sz = chunksize(p);
  /* min and max possible addresses assuming contiguous allocation */
  char* max_address = (char*)(av->top) + chunksize(av->top);
  char* min_address = max_address - av->sbrked_mem;

  if (!chunk_is_mmapped(p)) {
    
    /* Has legal address ... */
    if (p != av->top) {
      if (contiguous(av)) {
        assert(((char*)p) >= min_address);
        assert(((char*)p + sz) <= ((char*)(av->top)));
      }
    }
    else {
      /* top size is always at least MINSIZE */
      assert((CHUNK_SIZE_T)(sz) >= MINSIZE);
      /* top predecessor always marked inuse */
      assert(prev_inuse(p));
    }
      
  }
  else {
#if HAVE_MMAP
    /* address is outside main heap  */
    if (contiguous(av) && av->top != initial_top(av)) {
      assert(((char*)p) < min_address || ((char*)p) > max_address);
    }
    /* chunk is page-aligned */
    assert(((p->prev_size + sz) & (av->pagesize-1)) == 0);
    /* mem is aligned */
    assert(aligned_OK(chunk2mem(p)));
#else
    /* force an appropriate assert violation if debug set */
    assert(!chunk_is_mmapped(p));
#endif
  }
}

/*
  Properties of free chunks
*/

#if __STD_C
static void do_check_free_chunk(mchunkptr p)
#else
static void do_check_free_chunk(p) mchunkptr p;
#endif
{
  mstate av = get_malloc_state();

  INTERNAL_SIZE_T sz = p->size & ~PREV_INUSE;
  mchunkptr next = chunk_at_offset(p, sz);

  do_check_chunk(p);

  /* Chunk must claim to be free ... */
  assert(!inuse(p));
  assert (!chunk_is_mmapped(p));

  /* Unless a special marker, must have OK fields */
  if ((CHUNK_SIZE_T)(sz) >= 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 == av->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);
}

/*
  Properties of inuse chunks
*/

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

  if (chunk_is_mmapped(p))
    return; /* mmapped chunks have no next/prev */

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

  next = next_chunk(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))  {
    /* Note that we cannot even look at prev unless it is not inuse */
    mchunkptr prv = prev_chunk(p);
    assert(next_chunk(prv) == p);
    do_check_free_chunk(prv);
  }

  if (next == av->top) {
    assert(prev_inuse(next));
    assert(chunksize(next) >= MINSIZE);
  }
  else if (!inuse(next))
    do_check_free_chunk(next);
}

/*
  Properties of chunks recycled from fastbins
*/

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

  do_check_inuse_chunk(p);

  /* Legal size ... */
  assert((sz & MALLOC_ALIGN_MASK) == 0);
  assert((CHUNK_SIZE_T)(sz) >= MINSIZE);
  /* ... and alignment */
  assert(aligned_OK(chunk2mem(p)));
  /* chunk is less than MINSIZE more than request */
  assert((long)(sz) - (long)(s) >= 0);
  assert((long)(sz) - (long)(s + MINSIZE) < 0);
}

/*
  Properties of nonrecycled chunks at the point they are malloced
*/

#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
{
  /* same as recycled case ... */
  do_check_remalloced_chunk(p, s);

  /*
    ... plus,  must obey implementation invariant 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. This is ensured
    by making all allocations from the the `lowest' part of any found
    chunk.  This does not necessarily hold however for chunks
    recycled via fastbins.
  */

  assert(prev_inuse(p));
}


/*
  Properties of malloc_state.

  This may be useful for debugging malloc, as well as detecting user
  programmer errors that somehow write into malloc_state.

  If you are extending or experimenting with this malloc, you can
  probably figure out how to hack this routine to print out or
  display chunk addresses, sizes, bins, and other instrumentation.
*/

static void do_check_malloc_state()
{
  mstate av = get_malloc_state();
  int i;
  mchunkptr p;
  mchunkptr q;
  mbinptr b;
  unsigned int binbit;
  int empty;
  unsigned int idx;
  INTERNAL_SIZE_T size;
  CHUNK_SIZE_T  total = 0;
  int max_fast_bin;

  /* internal size_t must be no wider than pointer type */
  assert(sizeof(INTERNAL_SIZE_T) <= sizeof(char*));

  /* alignment is a power of 2 */
  assert((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-1)) == 0);

  /* cannot run remaining checks until fully initialized */
  if (av->top == 0 || av->top == initial_top(av))
    return;

  /* pagesize is a power of 2 */
  assert((av->pagesize & (av->pagesize-1)) == 0);

  /* properties of fastbins */

  /* max_fast is in allowed range */
  assert(get_max_fast(av) <= request2size(MAX_FAST_SIZE));

  max_fast_bin = fastbin_index(av->max_fast);

  for (i = 0; i < NFASTBINS; ++i) {
    p = av->fastbins[i];

    /* all bins past max_fast are empty */
    if (i > max_fast_bin)
      assert(p == 0);

    while (p != 0) {
      /* each chunk claims to be inuse */
      do_check_inuse_chunk(p);
      total += chunksize(p);
      /* chunk belongs in this bin */
      assert(fastbin_index(chunksize(p)) == i);
      p = p->fd;
    }
  }

  if (total != 0)
    assert(have_fastchunks(av));
  else if (!have_fastchunks(av))
    assert(total == 0);

  /* check normal bins */
  for (i = 1; i < NBINS; ++i) {
    b = bin_at(av,i);

    /* binmap is accurate (except for bin 1 == unsorted_chunks) */
    if (i >= 2) {
      binbit = get_binmap(av,i);
      empty = last(b) == b;
      if (!binbit)
        assert(empty);
      else if (!empty)
        assert(binbit);
    }

    for (p = last(b); p != b; p = p->bk) {
      /* each chunk claims to be free */
      do_check_free_chunk(p);
      size = chunksize(p);
      total += size;
      if (i >= 2) {
        /* chunk belongs in bin */
        idx = bin_index(size);
        assert(idx == i);
        /* lists are sorted */
        if ((CHUNK_SIZE_T) size >= (CHUNK_SIZE_T)(FIRST_SORTED_BIN_SIZE)) {
          assert(p->bk == b || 
                 (CHUNK_SIZE_T)chunksize(p->bk) >= 
                 (CHUNK_SIZE_T)chunksize(p));
        }
      }
      /* chunk is followed by a legal chain of inuse chunks */
      for (q = next_chunk(p);
           (q != av->top && inuse(q) && 
             (CHUNK_SIZE_T)(chunksize(q)) >= MINSIZE);
           q = next_chunk(q))
        do_check_inuse_chunk(q);
    }
  }

  /* top chunk is OK */
  check_chunk(av->top);

  /* sanity checks for statistics */

  assert(total <= (CHUNK_SIZE_T)(av->max_total_mem));
  assert(av->n_mmaps >= 0);
  assert(av->n_mmaps <= av->max_n_mmaps);

  assert((CHUNK_SIZE_T)(av->sbrked_mem) <=
         (CHUNK_SIZE_T)(av->max_sbrked_mem));

  assert((CHUNK_SIZE_T)(av->mmapped_mem) <=
         (CHUNK_SIZE_T)(av->max_mmapped_mem));

  assert((CHUNK_SIZE_T)(av->max_total_mem) >=
         (CHUNK_SIZE_T)(av->mmapped_mem) + (CHUNK_SIZE_T)(av->sbrked_mem));
}
#endif


/* ----------- Routines dealing with system allocation -------------- */

/*
  sysmalloc handles malloc cases requiring more memory from the system.
  On entry, it is assumed that av->top does not have enough
  space to service request for nb bytes, thus requiring that av->top
  be extended or replaced.
*/

#if __STD_C
static Void_t* sYSMALLOc(INTERNAL_SIZE_T nb, mstate av)
#else
static Void_t* sYSMALLOc(nb, av) INTERNAL_SIZE_T nb; mstate av;
#endif
{
  mchunkptr       old_top;        /* incoming value of av->top */
  INTERNAL_SIZE_T old_size;       /* its size */
  char*           old_end;        /* its end address */

  long            size;           /* arg to first MORECORE or mmap call */
  char*           brk;            /* return value from MORECORE */

  long            correction;     /* arg to 2nd MORECORE call */
  char*           snd_brk;        /* 2nd return val */

  INTERNAL_SIZE_T front_misalign; /* unusable bytes at front of new space */
  INTERNAL_SIZE_T end_misalign;   /* partial page left at end of new space */
  char*           aligned_brk;    /* aligned offset into brk */

  mchunkptr       p;              /* the allocated/returned chunk */
  mchunkptr       remainder;      /* remainder from allocation */
  CHUNK_SIZE_T    remainder_size; /* its size */

  CHUNK_SIZE_T    sum;            /* for updating stats */

  size_t          pagemask  = av->pagesize - 1;

  /*
    If there is space available in fastbins, consolidate and retry
    malloc from scratch rather than getting memory from system.  This
    can occur only if nb is in smallbin range so we didn't consolidate
    upon entry to malloc. It is much easier to handle this case here
    than in malloc proper.
  */

  if (have_fastchunks(av)) {
    assert(in_smallbin_range(nb));
    malloc_consolidate(av);
    return mALLOc(nb - MALLOC_ALIGN_MASK);
  }


#if HAVE_MMAP

  /*
    If have mmap, and the request size meets the mmap threshold, and
    the system supports mmap, and there are few enough currently
    allocated mmapped regions, try to directly map this request
    rather than expanding top.
  */

  if ((CHUNK_SIZE_T)(nb) >= (CHUNK_SIZE_T)(av->mmap_threshold) &&
      (av->n_mmaps < av->n_mmaps_max)) {

    char* mm;             /* return value from mmap call*/

    /*
      Round up size to nearest page.  For mmapped chunks, the overhead
      is one SIZE_SZ unit larger than for normal chunks, because there
      is no following chunk whose prev_size field could be used.
    */
    size = (nb + SIZE_SZ + MALLOC_ALIGN_MASK + pagemask) & ~pagemask;

    /* Don't try if size wraps around 0 */
    if ((CHUNK_SIZE_T)(size) > (CHUNK_SIZE_T)(nb)) {

      mm = (char*)(MMAP(0, size, PROT_READ|PROT_WRITE, MAP_PRIVATE));
      
      if (mm != (char*)(MORECORE_FAILURE)) {
        
        /*
          The offset to the start of the mmapped region is stored
          in the prev_size field of the chunk. This allows us to adjust
          returned start address to meet alignment requirements here 
          and in memalign(), and still be able to compute proper
          address argument for later munmap in free() and realloc().
        */
        
        front_misalign = (INTERNAL_SIZE_T)chunk2mem(mm) & MALLOC_ALIGN_MASK;
        if (front_misalign > 0) {
          correction = MALLOC_ALIGNMENT - front_misalign;
          p = (mchunkptr)(mm + correction);
          p->prev_size = correction;
          set_head(p, (size - correction) |IS_MMAPPED);
        }
        else {
          p = (mchunkptr)mm;
          p->prev_size = 0;
          set_head(p, size|IS_MMAPPED);
        }
        
        /* update statistics */
        
        if (++av->n_mmaps > av->max_n_mmaps) 
          av->max_n_mmaps = av->n_mmaps;
        
        sum = av->mmapped_mem += size;
        if (sum > (CHUNK_SIZE_T)(av->max_mmapped_mem)) 
          av->max_mmapped_mem = sum;
        sum += av->sbrked_mem;
        if (sum > (CHUNK_SIZE_T)(av->max_total_mem)) 
          av->max_total_mem = sum;

        check_chunk(p);
        
        return chunk2mem(p);
      }
    }
  }
#endif

  /* Record incoming configuration of top */

  old_top  = av->top;
  old_size = chunksize(old_top);
  old_end  = (char*)(chunk_at_offset(old_top, old_size));

  brk = snd_brk = (char*)(MORECORE_FAILURE); 

  /* 
     If not the first time through, we require old_size to be
     at least MINSIZE and to have prev_inuse set.
  */

  assert((old_top == initial_top(av) && old_size == 0) || 
         ((CHUNK_SIZE_T) (old_size) >= MINSIZE &&
          prev_inuse(old_top)));

  /* Precondition: not enough current space to satisfy nb request */
  assert((CHUNK_SIZE_T)(old_size) < (CHUNK_SIZE_T)(nb + MINSIZE));

  /* Precondition: all fastbins are consolidated */
  assert(!have_fastchunks(av));


  /* Request enough space for nb + pad + overhead */

  size = nb + av->top_pad + MINSIZE;

  /*
    If contiguous, we can subtract out existing space that we hope to
    combine with new space. We add it back later only if
    we don't actually get contiguous space.
  */

  if (contiguous(av))
    size -= old_size;

  /*
    Round to a multiple of page size.
    If MORECORE is not contiguous, this ensures that we only call it
    with whole-page arguments.  And if MORECORE is contiguous and
    this is not first time through, this preserves page-alignment of
    previous calls. Otherwise, we correct to page-align below.
  */

  size = (size + pagemask) & ~pagemask;

  /*
    Don't try to call MORECORE if argument is so big as to appear
    negative. Note that since mmap takes size_t arg, it may succeed
    below even if we cannot call MORECORE.
  */

  if (size > 0) 
    brk = (char*)(MORECORE(size));

  /*
    If have mmap, try using it as a backup when MORECORE fails or
    cannot be used. This is worth doing on systems that have "holes" in
    address space, so sbrk cannot extend to give contiguous space, but
    space is available elsewhere.  Note that we ignore mmap max count
    and threshold limits, since the space will not be used as a
    segregated mmap region.
  */

#if HAVE_MMAP
  if (brk == (char*)(MORECORE_FAILURE)) {

    /* Cannot merge with old top, so add its size back in */
    if (contiguous(av))
      size = (size + old_size + pagemask) & ~pagemask;

    /* If we are relying on mmap as backup, then use larger units */
    if ((CHUNK_SIZE_T)(size) < (CHUNK_SIZE_T)(MMAP_AS_MORECORE_SIZE))
      size = MMAP_AS_MORECORE_SIZE;

    /* Don't try if size wraps around 0 */
    if ((CHUNK_SIZE_T)(size) > (CHUNK_SIZE_T)(nb)) {

      brk = (char*)(MMAP(0, size, PROT_READ|PROT_WRITE, MAP_PRIVATE));
      
      if (brk != (char*)(MORECORE_FAILURE)) {
        
        /* We do not need, and cannot use, another sbrk call to find end */
        snd_brk = brk + size;
        
        /* 
           Record that we no longer have a contiguous sbrk region. 
           After the first time mmap is used as backup, we do not
           ever rely on contiguous space since this could incorrectly
           bridge regions.
        */
        set_noncontiguous(av);
      }
    }
  }
#endif

  if (brk != (char*)(MORECORE_FAILURE)) {
    av->sbrked_mem += size;

    /*
      If MORECORE extends previous space, we can likewise extend top size.
    */
    
    if (brk == old_end && snd_brk == (char*)(MORECORE_FAILURE)) {
      set_head(old_top, (size + old_size) | PREV_INUSE);
    }

    /*
      Otherwise, make adjustments:
      
      * If the first time through or noncontiguous, we need to call sbrk
        just to find out where the end of memory lies.

      * We need to ensure that all returned chunks from malloc will meet
        MALLOC_ALIGNMENT

      * If there was an intervening foreign sbrk, we need to adjust sbrk
        request size to account for fact that we will not be able to
        combine new space with existing space in old_top.

      * Almost all systems internally allocate whole pages at a time, in
        which case we might as well use the whole last page of request.
        So we allocate enough more memory to hit a page boundary now,
        which in turn causes future contiguous calls to page-align.
    */
    
    else {
      front_misalign = 0;
      end_misalign = 0;
      correction = 0;
      aligned_brk = brk;

      /*
        If MORECORE returns an address lower than we have seen before,
        we know it isn't really contiguous.  This and some subsequent
        checks help cope with non-conforming MORECORE functions and
        the presence of "foreign" calls to MORECORE from outside of
        malloc or by other threads.  We cannot guarantee to detect
        these in all cases, but cope with the ones we do detect.
      */
      if (contiguous(av) && old_size != 0 && brk < old_end) {
        set_noncontiguous(av);
      }
      
      /* handle contiguous cases */
      if (contiguous(av)) { 

        /* 
           We can tolerate forward non-contiguities here (usually due
           to foreign calls) but treat them as part of our space for
           stats reporting.
        */
        if (old_size != 0) 
          av->sbrked_mem += brk - old_end;
        
        /* Guarantee alignment of first new chunk made from this space */

        front_misalign = (INTERNAL_SIZE_T)chunk2mem(brk) & MALLOC_ALIGN_MASK;
        if (front_misalign > 0) {

          /*
            Skip over some bytes to arrive at an aligned position.
            We don't need to specially mark these wasted front bytes.
            They will never be accessed anyway because
            prev_inuse of av->top (and any chunk created from its start)
            is always true after initialization.
          */

          correction = MALLOC_ALIGNMENT - front_misalign;
          aligned_brk += correction;
        }
        
        /*
          If this isn't adjacent to existing space, then we will not
          be able to merge with old_top space, so must add to 2nd request.
        */
        
        correction += old_size;
        
        /* Extend the end address to hit a page boundary */
        end_misalign = (INTERNAL_SIZE_T)(brk + size + correction);
        correction += ((end_misalign + pagemask) & ~pagemask) - end_misalign;
        
        assert(correction >= 0);
        snd_brk = (char*)(MORECORE(correction));
        
        if (snd_brk == (char*)(MORECORE_FAILURE)) {
          /*
            If can't allocate correction, try to at least find out current
            brk.  It might be enough to proceed without failing.
          */
          correction = 0;
          snd_brk = (char*)(MORECORE(0));
        }
        else if (snd_brk < brk) {
          /*
            If the second call gives noncontiguous space even though
            it says it won't, the only course of action is to ignore
            results of second call, and conservatively estimate where
            the first call left us. Also set noncontiguous, so this
            won't happen again, leaving at most one hole.
            
            Note that this check is intrinsically incomplete.  Because
            MORECORE is allowed to give more space than we ask for,
            there is no reliable way to detect a noncontiguity
            producing a forward gap for the second call.
          */
          snd_brk = brk + size;
          correction = 0;
          set_noncontiguous(av);
        }

      }
      
      /* handle non-contiguous cases */
      else { 
        /* MORECORE/mmap must correctly align */
        assert(aligned_OK(chunk2mem(brk)));
        
        /* Find out current end of memory */
        if (snd_brk == (char*)(MORECORE_FAILURE)) {
          snd_brk = (char*)(MORECORE(0));
          av->sbrked_mem += snd_brk - brk - size;
        }
      }
      
      /* Adjust top based on results of second sbrk */
      if (snd_brk != (char*)(MORECORE_FAILURE)) {
        av->top = (mchunkptr)aligned_brk;
        set_head(av->top, (snd_brk - aligned_brk + correction) | PREV_INUSE);
        av->sbrked_mem += correction;
     
        /*
          If not the first time through, we either have a
          gap due to foreign sbrk or a non-contiguous region.  Insert a
          double fencepost at old_top to prevent consolidation with space
          we don't own. These fenceposts are artificial chunks that are
          marked as inuse and are in any case too small to use.  We need
          two to make sizes and alignments work out.
        */
   
        if (old_size != 0) {
          /* 
             Shrink old_top to insert fenceposts, keeping size a
             multiple of MALLOC_ALIGNMENT. We know there is at least
             enough space in old_top to do this.
          */
          old_size = (old_size - 3*SIZE_SZ) & ~MALLOC_ALIGN_MASK;
          set_head(old_top, old_size | PREV_INUSE);
          
          /*
            Note that the following assignments completely overwrite
            old_top when old_size was previously MINSIZE.  This is
            intentional. We need the fencepost, even if old_top otherwise gets
            lost.
          */
          chunk_at_offset(old_top, old_size          )->size =
            SIZE_SZ|PREV_INUSE;

          chunk_at_offset(old_top, old_size + SIZE_SZ)->size =
            SIZE_SZ|PREV_INUSE;

          /* 
             If possible, release the rest, suppressing trimming.
          */
          if (old_size >= MINSIZE) {
            INTERNAL_SIZE_T tt = av->trim_threshold;
            av->trim_threshold = (INTERNAL_SIZE_T)(-1);
            fREe(chunk2mem(old_top));
            av->trim_threshold = tt;
          }
        }
      }
    }
    
    /* Update statistics */
    sum = av->sbrked_mem;
    if (sum > (CHUNK_SIZE_T)(av->max_sbrked_mem))
      av->max_sbrked_mem = sum;
    
    sum += av->mmapped_mem;
    if (sum > (CHUNK_SIZE_T)(av->max_total_mem))
      av->max_total_mem = sum;

    check_malloc_state();
    
    /* finally, do the allocation */

    p = av->top;
    size = chunksize(p);
    
    /* check that one of the above allocation paths succeeded */
    if ((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb + MINSIZE)) {
      remainder_size = size - nb;
      remainder = chunk_at_offset(p, nb);
      av->top = remainder;
      set_head(p, nb | PREV_INUSE);
      set_head(remainder, remainder_size | PREV_INUSE);
      check_malloced_chunk(p, nb);
      return chunk2mem(p);
    }

  }

  /* catch all failure paths */
  MALLOC_FAILURE_ACTION;
  return 0;
}




/*
  sYSTRIm is an inverse of sorts to sYSMALLOc.  It gives memory back
  to the system (via negative arguments to sbrk) if there is unused
  memory at the `high' end of the malloc pool. It is called
  automatically by free() when top space exceeds the trim
  threshold. It is also called by the public malloc_trim routine.  It
  returns 1 if it actually released any memory, else 0.
*/

#if __STD_C
static int sYSTRIm(size_t pad, mstate av)
#else
static int sYSTRIm(pad, av) size_t pad; mstate av;
#endif
{
  long  top_size;        /* Amount of top-most memory */
  long  extra;           /* Amount to release */
  long  released;        /* Amount actually released */
  char* current_brk;     /* address returned by pre-check sbrk call */
  char* new_brk;         /* address returned by post-check sbrk call */
  size_t pagesz;

  pagesz = av->pagesize;
  top_size = chunksize(av->top);
  
  /* Release in pagesize units, keeping at least one page */
  extra = ((top_size - pad - MINSIZE + (pagesz-1)) / pagesz - 1) * pagesz;
  
  if (extra > 0) {
    
    /*
      Only proceed if end of memory is where we last set it.
      This avoids problems if there were foreign sbrk calls.
    */
    current_brk = (char*)(MORECORE(0));
    if (current_brk == (char*)(av->top) + top_size) {
      
      /*
        Attempt to release memory. We ignore MORECORE return value,
        and instead call again to find out where new end of memory is.
        This avoids problems if first call releases less than we asked,
        of if failure somehow altered brk value. (We could still
        encounter problems if it altered brk in some very bad way,
        but the only thing we can do is adjust anyway, which will cause
        some downstream failure.)
      */
      
      MORECORE(-extra);
      new_brk = (char*)(MORECORE(0));
      
      if (new_brk != (char*)MORECORE_FAILURE) {
        released = (long)(current_brk - new_brk);
        
        if (released != 0) {
          /* Success. Adjust top. */
          av->sbrked_mem -= released;
          set_head(av->top, (top_size - released) | PREV_INUSE);
          check_malloc_state();
          return 1;
        }
      }
    }
  }
  return 0;
}

/*
  ------------------------------ malloc ------------------------------
*/


#if __STD_C
Void_t* mALLOc(size_t bytes)
#else
  Void_t* mALLOc(bytes) size_t bytes;
#endif
{
  mstate av = get_malloc_state();

  INTERNAL_SIZE_T nb;               /* normalized request size */
  unsigned int    idx;              /* associated bin index */
  mbinptr         bin;              /* associated bin */
  mfastbinptr*    fb;               /* associated fastbin */

  mchunkptr       victim;           /* inspected/selected chunk */
  INTERNAL_SIZE_T size;             /* its size */
  int             victim_index;     /* its bin index */

  mchunkptr       remainder;        /* remainder from a split */
  CHUNK_SIZE_T    remainder_size;   /* its size */

  unsigned int    block;            /* bit map traverser */
  unsigned int    bit;              /* bit map traverser */
  unsigned int    map;              /* current word of binmap */

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

  /*
    Convert request size to internal form by adding SIZE_SZ bytes
    overhead plus possibly more to obtain necessary alignment and/or
    to obtain a size of at least MINSIZE, the smallest allocatable
    size. Also, checked_request2size traps (returning 0) request sizes
    that are so large that they wrap around zero when padded and
    aligned.
  */

  checked_request2size(bytes, nb);

  /*
    Bypass search if no frees yet
   */
  if (!have_anychunks(av)) {
    if (av->max_fast == 0) /* initialization check */
      malloc_consolidate(av);
    goto use_top;
  }

  /*
    If the size qualifies as a fastbin, first check corresponding bin.
  */

  if ((CHUNK_SIZE_T)(nb) <= (CHUNK_SIZE_T)(av->max_fast)) { 
    fb = &(av->fastbins[(fastbin_index(nb))]);
    if ( (victim = *fb) != 0) {
      *fb = victim->fd;
      check_remalloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
  }

  /*
    If a small request, check regular bin.  Since these "smallbins"
    hold one size each, no searching within bins is necessary.
    (For a large request, we need to wait until unsorted chunks are
    processed to find best fit. But for small ones, fits are exact
    anyway, so we can check now, which is faster.)
  */

  if (in_smallbin_range(nb)) {
    idx = smallbin_index(nb);
    bin = bin_at(av,idx);

    if ( (victim = last(bin)) != bin) {
      bck = victim->bk;
      set_inuse_bit_at_offset(victim, nb);
      bin->bk = bck;
      bck->fd = bin;
      
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
  }

  /* 
     If this is a large request, consolidate fastbins before continuing.
     While it might look excessive to kill all fastbins before
     even seeing if there is space available, this avoids
     fragmentation problems normally associated with fastbins.
     Also, in practice, programs tend to have runs of either small or
     large requests, but less often mixtures, so consolidation is not 
     invoked all that often in most programs. And the programs that
     it is called frequently in otherwise tend to fragment.
  */

  else {
    idx = largebin_index(nb);
    if (have_fastchunks(av)) 
      malloc_consolidate(av);
  }

  /*
    Process recently freed or remaindered chunks, taking one only if
    it is exact fit, or, if this a small request, the chunk is remainder from
    the most recent non-exact fit.  Place other traversed chunks in
    bins.  Note that this step is the only place in any routine where
    chunks are placed in bins.
  */
    
  while ( (victim = unsorted_chunks(av)->bk) != unsorted_chunks(av)) {
    bck = victim->bk;
    size = chunksize(victim);
    
    /* 
       If a small request, try to use last remainder if it is the
       only chunk in unsorted bin.  This helps promote locality for
       runs of consecutive small requests. This is the only
       exception to best-fit, and applies only when there is
       no exact fit for a small chunk.
    */
    
    if (in_smallbin_range(nb) && 
        bck == unsorted_chunks(av) &&
        victim == av->last_remainder &&
        (CHUNK_SIZE_T)(size) > (CHUNK_SIZE_T)(nb + MINSIZE)) {
      
      /* split and reattach remainder */
      remainder_size = size - nb;
      remainder = chunk_at_offset(victim, nb);
      unsorted_chunks(av)->bk = unsorted_chunks(av)->fd = remainder;
      av->last_remainder = remainder; 
      remainder->bk = remainder->fd = unsorted_chunks(av);
      
      set_head(victim, nb | PREV_INUSE);
      set_head(remainder, remainder_size | PREV_INUSE);
      set_foot(remainder, remainder_size);
      
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
    
    /* remove from unsorted list */
    unsorted_chunks(av)->bk = bck;
    bck->fd = unsorted_chunks(av);
    
    /* Take now instead of binning if exact fit */
    
    if (size == nb) {
      set_inuse_bit_at_offset(victim, size);
      check_malloced_chunk(victim, nb);
      return chunk2mem(victim);
    }
    
    /* place chunk in bin */
    
    if (in_smallbin_range(size)) {
      victim_index = smallbin_index(size);
      bck = bin_at(av, victim_index);
      fwd = bck->fd;
    }
    else {
      victim_index = largebin_index(size);
      bck = bin_at(av, victim_index);
      fwd = bck->fd;
      
      if (fwd != bck) {
        /* if smaller than smallest, place first */
        if ((CHUNK_SIZE_T)(size) < (CHUNK_SIZE_T)(bck->bk->size)) {
          fwd = bck;
          bck = bck->bk;
        }
        else if ((CHUNK_SIZE_T)(size) >= 
                 (CHUNK_SIZE_T)(FIRST_SORTED_BIN_SIZE)) {
          
          /* maintain large bins in sorted order */
          size |= PREV_INUSE; /* Or with inuse bit to speed comparisons */
          while ((CHUNK_SIZE_T)(size) < (CHUNK_SIZE_T)(fwd->size)) 
            fwd = fwd->fd;
          bck = fwd->bk;
        }
      }
    }
      
    mark_bin(av, victim_index);
    victim->bk = bck;
    victim->fd = fwd;
    fwd->bk = victim;
    bck->fd = victim;
  }
  
  /*
    If a large request, scan through the chunks of current bin to
    find one that fits.  (This will be the smallest that fits unless
    FIRST_SORTED_BIN_SIZE has been changed from default.)  This is
    the only step where an unbounded number of chunks might be
    scanned without doing anything useful with them. However the
    lists tend to be short.
  */
  
  if (!in_smallbin_range(nb)) {
    bin = bin_at(av, idx);
    
    for (victim = last(bin); victim != bin; victim = victim->bk) {
      size = chunksize(victim);
      
      if ((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb)) {
        remainder_size = size - nb;
        unlink(victim, bck, fwd);
        
        /* Exhaust */
        if (remainder_size < MINSIZE)  {
          set_inuse_bit_at_offset(victim, size);
          check_malloced_chunk(victim, nb);
          return chunk2mem(victim);
        }
        /* Split */
        else {
          remainder = chunk_at_offset(victim, nb);
          unsorted_chunks(av)->bk = unsorted_chunks(av)->fd = remainder;
          remainder->bk = remainder->fd = unsorted_chunks(av);
          set_head(victim, nb | PREV_INUSE);
          set_head(remainder, remainder_size | PREV_INUSE);
          set_foot(remainder, remainder_size);
          check_malloced_chunk(victim, nb);
          return chunk2mem(victim);
        } 
      }
    }    
  }

  /*
    Search for a chunk by scanning bins, starting with next largest
    bin. 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.
    
    The bitmap avoids needing to check that most blocks are nonempty.
  */
    
  ++idx;
  bin = bin_at(av,idx);
  block = idx2block(idx);
  map = av->binmap[block];
  bit = idx2bit(idx);
  
  for (;;) {
    
    /* Skip rest of block if there are no more set bits in this block.  */
    if (bit > map || bit == 0) {
      do {
        if (++block >= BINMAPSIZE)  /* out of bins */
          goto use_top;
      } while ( (map = av->binmap[block]) == 0);
      
      bin = bin_at(av, (block << BINMAPSHIFT));
      bit = 1;
    }
    
    /* Advance to bin with set bit. There must be one. */
    while ((bit & map) == 0) {
      bin = next_bin(bin);
      bit <<= 1;
      assert(bit != 0);
    }
    
    /* Inspect the bin. It is likely to be non-empty */
    victim = last(bin);
    
    /*  If a false alarm (empty bin), clear the bit. */
    if (victim == bin) {
      av->binmap[block] = map &= ~bit; /* Write through */
      bin = next_bin(bin);
      bit <<= 1;
    }
    
    else {
      size = chunksize(victim);
      
      /*  We know the first chunk in this bin is big enough to use. */
      assert((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb));
      
      remainder_size = size - nb;
      
      /* unlink */
      bck = victim->bk;
      bin->bk = bck;
      bck->fd = bin;
      
      /* Exhaust */
      if (remainder_size < MINSIZE) {
        set_inuse_bit_at_offset(victim, size);
        check_malloced_chunk(victim, nb);
        return chunk2mem(victim);
      }
      
      /* Split */
      else {
        remainder = chunk_at_offset(victim, nb);
        
        unsorted_chunks(av)->bk = unsorted_chunks(av)->fd = remainder;
        remainder->bk = remainder->fd = unsorted_chunks(av);
        /* advertise as last remainder */
        if (in_smallbin_range(nb)) 
          av->last_remainder = remainder; 
        
        set_head(victim, nb | PREV_INUSE);
        set_head(remainder, remainder_size | PREV_INUSE);
        set_foot(remainder, remainder_size);
        check_malloced_chunk(victim, nb);
        return chunk2mem(victim);
      }
    }
  }

  use_top:    
  /*
    If large enough, split off the chunk bordering the end of memory
    (held in av->top). Note that this is in accord with the best-fit
    search rule.  In effect, av->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).
    
    We require that av->top always exists (i.e., has size >=
    MINSIZE) after initialization, so if it would otherwise be
    exhuasted by current request, it is replenished. (The main
    reason for ensuring it exists is that we may need MINSIZE space
    to put in fenceposts in sysmalloc.)
  */
  
  victim = av->top;
  size = chunksize(victim);
  
  if ((CHUNK_SIZE_T)(size) >= (CHUNK_SIZE_T)(nb + MINSIZE)) {
    remainder_size = size - nb;
    remainder = chunk_at_offset(victim, nb);
    av->top = remainder;
    set_head(victim, nb | PREV_INUSE);
    set_head(remainder, remainder_size | PREV_INUSE);
    
    check_malloced_chunk(victim, nb);
    return chunk2mem(victim);
  }
  
  /* 
     If no space in top, relay to handle system-dependent cases 
  */
  return sYSMALLOc(nb, av);    
}

/*
  ------------------------------ free ------------------------------
*/

#if __STD_C
void fREe(Void_t* mem)
#else
void fREe(mem) Void_t* mem;
#endif
{
  mstate av = get_malloc_state();

  mchunkptr       p;           /* chunk corresponding to mem */
  INTERNAL_SIZE_T size;        /* its size */
  mfastbinptr*    fb;          /* associated fastbin */
  mchunkptr       nextchunk;   /* next contiguous chunk */
  INTERNAL_SIZE_T nextsize;    /* its size */
  int             nextinuse;   /* true if nextchunk is used */
  INTERNAL_SIZE_T prevsize;    /* size of previous contiguous chunk */
  mchunkptr       bck;         /* misc temp for linking */
  mchunkptr       fwd;         /* misc temp for linking */

  /* free(0) has no effect */
  if (mem != 0) {
    p = mem2chunk(mem);
    size = chunksize(p);

    check_inuse_chunk(p);

    /*
      If eligible, place chunk on a fastbin so it can be found
      and used quickly in malloc.
    */

    if ((CHUNK_SIZE_T)(size) <= (CHUNK_SIZE_T)(av->max_fast)

#if TRIM_FASTBINS
        /* 
           If TRIM_FASTBINS set, don't place chunks
           bordering top into fastbins
        */
        && (chunk_at_offset(p, size) != av->top)
#endif
        ) {

      set_fastchunks(av);
      fb = &(av->fastbins[fastbin_index(size)]);
      p->fd = *fb;
      *fb = p;
    }

    /*
       Consolidate other non-mmapped chunks as they arrive.
    */

    else if (!chunk_is_mmapped(p)) {
      set_anychunks(av);

      nextchunk = chunk_at_offset(p, size);
      nextsize = chunksize(nextchunk);

      /* consolidate backward */
      if (!prev_inuse(p)) {
        prevsize = p->prev_size;
        size += prevsize;
        p = chunk_at_offset(p, -((long) prevsize));
        unlink(p, bck, fwd);
      }

      if (nextchunk != av->top) {
        /* get and clear inuse bit */
        nextinuse = inuse_bit_at_offset(nextchunk, nextsize);
        set_head(nextchunk, nextsize);

        /* consolidate forward */
        if (!nextinuse) {
          unlink(nextchunk, bck, fwd);
          size += nextsize;
        }

        /*
          Place the chunk in unsorted chunk list. Chunks are
          not placed into regular bins until after they have
          been given one chance to be used in malloc.
        */

        bck = unsorted_chunks(av);
        fwd = bck->fd;
        p->bk = bck;
        p->fd = fwd;
        bck->fd = p;
        fwd->bk = p;

        set_head(p, size | PREV_INUSE);
        set_foot(p, size);
        
        check_free_chunk(p);
      }

      /*
         If the chunk borders the current high end of memory,
         consolidate into top
      */

      else {
        size += nextsize;
        set_head(p, size | PREV_INUSE);
        av->top = p;
        check_chunk(p);
      }

      /*
        If freeing a large space, consolidate possibly-surrounding
        chunks. Then, if the total unused topmost memory exceeds trim
        threshold, ask malloc_trim to reduce top.

        Unless max_fast is 0, we don't know if there are fastbins
        bordering top, so we cannot tell for sure whether threshold
        has been reached unless fastbins are consolidated.  But we
        don't want to consolidate on each free.  As a compromise,
        consolidation is performed if FASTBIN_CONSOLIDATION_THRESHOLD
        is reached.
      */

      if ((CHUNK_SIZE_T)(size) >= FASTBIN_CONSOLIDATION_THRESHOLD) { 
        if (have_fastchunks(av)) 
          malloc_consolidate(av);

#ifndef MORECORE_CANNOT_TRIM        
        if ((CHUNK_SIZE_T)(chunksize(av->top)) >= 
            (CHUNK_SIZE_T)(av->trim_threshold))
          sYSTRIm(av->top_pad, av);
#endif
      }

    }
    /*
      If the chunk was allocated via mmap, release via munmap()
      Note that if HAVE_MMAP is false but chunk_is_mmapped is
      true, then user must have overwritten memory. There's nothing
      we can do to catch this error unless DEBUG is set, in which case
      check_inuse_chunk (above) will have triggered error.
    */

    else {
#if HAVE_MMAP
      int ret;
      INTERNAL_SIZE_T offset = p->prev_size;
      av->n_mmaps--;
      av->mmapped_mem -= (size + offset);
      ret = munmap((char*)p - offset, size + offset);
      /* munmap returns non-zero on failure */
      assert(ret == 0);
#endif
    }
  }
}

/*
  ------------------------- malloc_consolidate -------------------------

  malloc_consolidate is a specialized version of free() that tears
  down chunks held in fastbins.  Free itself cannot be used for this
  purpose since, among other things, it might place chunks back onto
  fastbins.  So, instead, we need to use a minor variant of the same
  code.
  
  Also, because this routine needs to be called the first time through
  malloc anyway, it turns out to be the perfect place to trigger
  initialization code.
*/

#if __STD_C
static void malloc_consolidate(mstate av)
#else
static void malloc_consolidate(av) mstate av;
#endif
{
  mfastbinptr*    fb;                 /* current fastbin being consolidated */
  mfastbinptr*    maxfb;              /* last fastbin (for loop control) */
  mchunkptr       p;                  /* current chunk being consolidated */
  mchunkptr       nextp;              /* next chunk to consolidate */
  mchunkptr       unsorted_bin;       /* bin header */
  mchunkptr       first_unsorted;     /* chunk to link to */

  /* These have same use as in free() */
  mchunkptr       nextchunk;
  INTERNAL_SIZE_T size;
  INTERNAL_SIZE_T nextsize;
  INTERNAL_SIZE_T prevsize;
  int             nextinuse;
  mchunkptr       bck;
  mchunkptr       fwd;

  /*
    If max_fast is 0, we know that av hasn't
    yet been initialized, in which case do so below
  */

  if (av->max_fast != 0) {
    clear_fastchunks(av);

    unsorted_bin = unsorted_chunks(av);

    /*
      Remove each chunk from fast bin and consolidate it, placing it
      then in unsorted bin. Among other reasons for doing this,
      placing in unsorted bin avoids needing to calculate actual bins
      until malloc is sure that chunks aren't immediately going to be
      reused anyway.
    */
    
    maxfb = &(av->fastbins[fastbin_index(av->max_fast)]);
    fb = &(av->fastbins[0]);
    do {
      if ( (p = *fb) != 0) {
        *fb = 0;
        
        do {
          check_inuse_chunk(p);
          nextp = p->fd;
          
          /* Slightly streamlined version of consolidation code in free() */
          size = p->size & ~PREV_INUSE;
          nextchunk = chunk_at_offset(p, size);
          nextsize = chunksize(nextchunk);
          
          if (!prev_inuse(p)) {
            prevsize = p->prev_size;
            size += prevsize;
            p = chunk_at_offset(p, -((long) prevsize));
            unlink(p, bck, fwd);
          }
          
          if (nextchunk != av->top) {
            nextinuse = inuse_bit_at_offset(nextchunk, nextsize);
            set_head(nextchunk, nextsize);
            
            if (!nextinuse) {
              size += nextsize;
              unlink(nextchunk, bck, fwd);
            }
            
            first_unsorted = unsorted_bin->fd;
            unsorted_bin->fd = p;
            first_unsorted->bk = p;
            
            set_head(p, size | PREV_INUSE);
            p->bk = unsorted_bin;
            p->fd = first_unsorted;
            set_foot(p, size);
          }
          
          else {
            size += nextsize;
            set_head(p, size | PREV_INUSE);
            av->top = p;
          }
          
        } while ( (p = nextp) != 0);
        
      }
    } while (fb++ != maxfb);
  }
  else {
    malloc_init_state(av);
    check_malloc_state();
  }
}

/*
  ------------------------------ realloc ------------------------------
*/


#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
{
  mstate av = get_malloc_state();

  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 */

  mchunkptr        remainder;       /* extra space at end of newp */
  CHUNK_SIZE_T     remainder_size;  /* its size */

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

  CHUNK_SIZE_T     copysize;        /* bytes to copy */
  unsigned int     ncopies;         /* INTERNAL_SIZE_T words to copy */
  INTERNAL_SIZE_T* s;               /* copy source */ 
  INTERNAL_SIZE_T* d;               /* copy destination */


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

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

  checked_request2size(bytes, nb);

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

  check_inuse_chunk(oldp);

  if (!chunk_is_mmapped(oldp)) {

    if ((CHUNK_SIZE_T)(oldsize) >= (CHUNK_SIZE_T)(nb)) {
      /* already big enough; split below */
      newp = oldp;
      newsize = oldsize;
    }

    else {
      next = chunk_at_offset(oldp, oldsize);

      /* Try to expand forward into top */
      if (next == av->top &&
          (CHUNK_SIZE_T)(newsize = oldsize + chunksize(next)) >=
          (CHUNK_SIZE_T)(nb + MINSIZE)) {
        set_head_size(oldp, nb);
        av->top = chunk_at_offset(oldp, nb);
        set_head(av->top, (newsize - nb) | PREV_INUSE);
        return chunk2mem(oldp);
      }
      
      /* Try to expand forward into next chunk;  split off remainder below */
      else if (next != av->top && 
               !inuse(next) &&
               (CHUNK_SIZE_T)(newsize = oldsize + chunksize(next)) >=
               (CHUNK_SIZE_T)(nb)) {
        newp = oldp;
        unlink(next, bck, fwd);
      }

      /* allocate, copy, free */
      else {
        newmem = mALLOc(nb - MALLOC_ALIGN_MASK);
        if (newmem == 0)
          return 0; /* propagate failure */
      
        newp = mem2chunk(newmem);
        newsize = chunksize(newp);
        
        /*
          Avoid copy if newp is next chunk after oldp.
        */
        if (newp == next) {
          newsize += oldsize;
          newp = oldp;
        }
        else {
          /*
            Unroll copy of <= 36 bytes (72 if 8byte sizes)
            We know that contents have an odd number of
            INTERNAL_SIZE_T-sized words; minimally 3.
          */
          
          copysize = oldsize - SIZE_SZ;
          s = (INTERNAL_SIZE_T*)(oldmem);
          d = (INTERNAL_SIZE_T*)(newmem);
          ncopies = copysize / sizeof(INTERNAL_SIZE_T);
          assert(ncopies >= 3);
          
          if (ncopies > 9)
            MALLOC_COPY(d, s, copysize);
          
          else {
            *(d+0) = *(s+0);
            *(d+1) = *(s+1);
            *(d+2) = *(s+2);
            if (ncopies > 4) {
              *(d+3) = *(s+3);
              *(d+4) = *(s+4);
              if (ncopies > 6) {
                *(d+5) = *(s+5);
                *(d+6) = *(s+6);
                if (ncopies > 8) {
                  *(d+7) = *(s+7);
                  *(d+8) = *(s+8);
                }
              }
            }
          }
          
          fREe(oldmem);
          check_inuse_chunk(newp);
          return chunk2mem(newp);
        }
      }
    }

    /* If possible, free extra space in old or extended chunk */

    assert((CHUNK_SIZE_T)(newsize) >= (CHUNK_SIZE_T)(nb));

    remainder_size = newsize - nb;

    if (remainder_size < MINSIZE) { /* not enough extra to split off */
      set_head_size(newp, newsize);
      set_inuse_bit_at_offset(newp, newsize);
    }
    else { /* split remainder */
      remainder = chunk_at_offset(newp, nb);
      set_head_size(newp, nb);
      set_head(remainder, remainder_size | PREV_INUSE);
      /* Mark remainder as inuse so free() won't complain */
      set_inuse_bit_at_offset(remainder, remainder_size);
      fREe(chunk2mem(remainder)); 
    }

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

  /*
    Handle mmap cases
  */

  else {
#if HAVE_MMAP

#if HAVE_MREMAP
    INTERNAL_SIZE_T offset = oldp->prev_size;
    size_t pagemask = av->pagesize - 1;
    char *cp;
    CHUNK_SIZE_T  sum;
    
    /* Note the extra SIZE_SZ overhead */
    newsize = (nb + offset + SIZE_SZ + pagemask) & ~pagemask;

    /* don't need to remap if still within same page */
    if (oldsize == newsize - offset) 
      return oldmem;

    cp = (char*)mremap((char*)oldp - offset, oldsize + offset, newsize, 1);
    
    if (cp != (char*)MORECORE_FAILURE) {

      newp = (mchunkptr)(cp + offset);
      set_head(newp, (newsize - offset)|IS_MMAPPED);
      
      assert(aligned_OK(chunk2mem(newp)));
      assert((newp->prev_size == offset));
      
      /* update statistics */
      sum = av->mmapped_mem += newsize - oldsize;
      if (sum > (CHUNK_SIZE_T)(av->max_mmapped_mem)) 
        av->max_mmapped_mem = sum;
      sum += av->sbrked_mem;
      if (sum > (CHUNK_SIZE_T)(av->max_total_mem)) 
        av->max_total_mem = sum;
      
      return chunk2mem(newp);
    }
#endif

    /* Note the extra SIZE_SZ overhead. */
    if ((CHUNK_SIZE_T)(oldsize) >= (CHUNK_SIZE_T)(nb + SIZE_SZ)) 
      newmem = oldmem; /* do nothing */
    else {
      /* Must alloc, copy, free. */
      newmem = mALLOc(nb - MALLOC_ALIGN_MASK);
      if (newmem != 0) {
        MALLOC_COPY(newmem, oldmem, oldsize - 2*SIZE_SZ);
        fREe(oldmem);
      }
    }
    return newmem;

#else 
    /* If !HAVE_MMAP, but chunk_is_mmapped, user must have overwritten mem */
    check_malloc_state();
    MALLOC_FAILURE_ACTION;
    return 0;
#endif
  }
}

/*
  ------------------------------ memalign ------------------------------
*/

#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 before alignment point */
  mchunkptr       remainder;      /* spare room at end to split off */
  CHUNK_SIZE_T    remainder_size; /* its size */
  INTERNAL_SIZE_T size;

  /* 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;

  /* Make sure alignment is power of 2 (in case MINSIZE is not).  */
  if ((alignment & (alignment - 1)) != 0) {
    size_t a = MALLOC_ALIGNMENT * 2;
    while ((CHUNK_SIZE_T)a < (CHUNK_SIZE_T)alignment) a <<= 1;
    alignment = a;
  }

  checked_request2size(bytes, nb);

  /*
    Strategy: find a spot within that chunk that meets the alignment
    request, and then possibly free the leading and trailing space.
  */


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

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

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

  p = mem2chunk(m);

  if ((((PTR_UINT)(m)) % alignment) != 0) { /* 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((PTR_UINT)(((PTR_UINT)(m + alignment - 1)) &
                           -((signed long) alignment)));
    if ((CHUNK_SIZE_T)(brk - (char*)(p)) < MINSIZE)
      brk += alignment;

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

    /* For mmapped chunks, just adjust offset */
    if (chunk_is_mmapped(p)) {
      newp->prev_size = p->prev_size + leadsize;
      set_head(newp, newsize|IS_MMAPPED);
      return chunk2mem(newp);
    }

    /* Otherwise, 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 &&
            (((PTR_UINT)(chunk2mem(p))) % alignment) == 0);
  }

  /* Also give back spare room at the end */
  if (!chunk_is_mmapped(p)) {
    size = chunksize(p);
    if ((CHUNK_SIZE_T)(size) > (CHUNK_SIZE_T)(nb + MINSIZE)) {
      remainder_size = size - nb;
      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);
}

/*
  ------------------------------ calloc ------------------------------
*/

#if __STD_C
Void_t* cALLOc(size_t n_elements, size_t elem_size)
#else
Void_t* cALLOc(n_elements, elem_size) size_t n_elements; size_t elem_size;
#endif
{
  mchunkptr p;
  CHUNK_SIZE_T  clearsize;
  CHUNK_SIZE_T  nclears;
  INTERNAL_SIZE_T* d;

  Void_t* mem = mALLOc(n_elements * elem_size);

  if (mem != 0) {
    p = mem2chunk(mem);

    if (!chunk_is_mmapped(p))
    {  
      /*
        Unroll clear of <= 36 bytes (72 if 8byte sizes)
        We know that contents have an odd number of
        INTERNAL_SIZE_T-sized words; minimally 3.
      */

      d = (INTERNAL_SIZE_T*)mem;
      clearsize = chunksize(p) - SIZE_SZ;
      nclears = clearsize / sizeof(INTERNAL_SIZE_T);
      assert(nclears >= 3);

      if (nclears > 9)
        MALLOC_ZERO(d, clearsize);

      else {
        *(d+0) = 0;
        *(d+1) = 0;
        *(d+2) = 0;
        if (nclears > 4) {
          *(d+3) = 0;
          *(d+4) = 0;
          if (nclears > 6) {
            *(d+5) = 0;
            *(d+6) = 0;
            if (nclears > 8) {
              *(d+7) = 0;
              *(d+8) = 0;
            }
          }
        }
      }
    }
#if ! MMAP_CLEARS
    else
    {
      d = (INTERNAL_SIZE_T*)mem;
      /*
        Note the additional SIZE_SZ
      */
      clearsize = chunksize(p) - 2*SIZE_SZ;
      MALLOC_ZERO(d, clearsize);
    }
#endif
  }
  return mem;
}

/*
  ------------------------------ cfree ------------------------------
*/

#if __STD_C
void cFREe(Void_t *mem)
#else
void cFREe(mem) Void_t *mem;
#endif
{
  fREe(mem);
}

/*
  ------------------------- independent_calloc -------------------------
*/

#if __STD_C
Void_t** iCALLOc(size_t n_elements, size_t elem_size, Void_t* chunks[])
#else
Void_t** iCALLOc(n_elements, elem_size, chunks) size_t n_elements; size_t elem_size; Void_t* chunks[];
#endif
{
  size_t sz = elem_size; /* serves as 1-element array */
  /* opts arg of 3 means all elements are same size, and should be cleared */
  return iALLOc(n_elements, &sz, 3, chunks);
}

/*
  ------------------------- independent_comalloc -------------------------
*/

#if __STD_C
Void_t** iCOMALLOc(size_t n_elements, size_t sizes[], Void_t* chunks[])
#else
Void_t** iCOMALLOc(n_elements, sizes, chunks) size_t n_elements; size_t sizes[]; Void_t* chunks[];
#endif
{
  return iALLOc(n_elements, sizes, 0, chunks);
}


/*
  ------------------------------ ialloc ------------------------------
  ialloc provides common support for independent_X routines, handling all of
  the combinations that can result.

  The opts arg has:
    bit 0 set if all elements are same size (using sizes[0])
    bit 1 set if elements should be zeroed
*/


#if __STD_C
static Void_t** iALLOc(size_t n_elements, 
                       size_t* sizes,  
                       int opts,
                       Void_t* chunks[])
#else
static Void_t** iALLOc(n_elements, sizes, opts, chunks) size_t n_elements; size_t* sizes; int opts; Void_t* chunks[];
#endif
{
  mstate av = get_malloc_state();
  INTERNAL_SIZE_T element_size;   /* chunksize of each element, if all same */
  INTERNAL_SIZE_T contents_size;  /* total size of elements */
  INTERNAL_SIZE_T array_size;     /* request size of pointer array */
  Void_t*         mem;            /* malloced aggregate space */
  mchunkptr       p;              /* corresponding chunk */
  INTERNAL_SIZE_T remainder_size; /* remaining bytes while splitting */
  Void_t**        marray;         /* either "chunks" or malloced ptr array */
  mchunkptr       array_chunk;    /* chunk for malloced ptr array */
  int             mmx;            /* to disable mmap */
  INTERNAL_SIZE_T size;           
  size_t          i;

  /* Ensure initialization */
  if (av->max_fast == 0) malloc_consolidate(av);

  /* compute array length, if needed */
  if (chunks != 0) {
    if (n_elements == 0)
      return chunks; /* nothing to do */
    marray = chunks;
    array_size = 0;
  }
  else {
    /* if empty req, must still return chunk representing empty array */
    if (n_elements == 0) 
      return (Void_t**) mALLOc(0);
    marray = 0;
    array_size = request2size(n_elements * (sizeof(Void_t*)));
  }

  /* compute total element size */
  if (opts & 0x1) { /* all-same-size */
    element_size = request2size(*sizes);
    contents_size = n_elements * element_size;
  }
  else { /* add up all the sizes */
    element_size = 0;
    contents_size = 0;
    for (i = 0; i != n_elements; ++i) 
      contents_size += request2size(sizes[i]);     
  }

  /* subtract out alignment bytes from total to minimize overallocation */
  size = contents_size + array_size - MALLOC_ALIGN_MASK;
  
  /* 
     Allocate the aggregate chunk.
     But first disable mmap so malloc won't use it, since
     we would not be able to later free/realloc space internal
     to a segregated mmap region.
 */
  mmx = av->n_mmaps_max;   /* disable mmap */
  av->n_mmaps_max = 0;
  mem = mALLOc(size);
  av->n_mmaps_max = mmx;   /* reset mmap */
  if (mem == 0) 
    return 0;

  p = mem2chunk(mem);
  assert(!chunk_is_mmapped(p)); 
  remainder_size = chunksize(p);

  if (opts & 0x2) {       /* optionally clear the elements */
    MALLOC_ZERO(mem, remainder_size - SIZE_SZ - array_size);
  }

  /* If not provided, allocate the pointer array as final part of chunk */
  if (marray == 0) {
    array_chunk = chunk_at_offset(p, contents_size);
    marray = (Void_t**) (chunk2mem(array_chunk));
    set_head(array_chunk, (remainder_size - contents_size) | PREV_INUSE);
    remainder_size = contents_size;
  }

  /* split out elements */
  for (i = 0; ; ++i) {
    marray[i] = chunk2mem(p);
    if (i != n_elements-1) {
      if (element_size != 0) 
        size = element_size;
      else
        size = request2size(sizes[i]);          
      remainder_size -= size;
      set_head(p, size | PREV_INUSE);
      p = chunk_at_offset(p, size);
    }
    else { /* the final element absorbs any overallocation slop */
      set_head(p, remainder_size | PREV_INUSE);
      break;
    }
  }

#if DEBUG
  if (marray != chunks) {
    /* final element must have exactly exhausted chunk */
    if (element_size != 0) 
      assert(remainder_size == element_size);
    else
      assert(remainder_size == request2size(sizes[i]));
    check_inuse_chunk(mem2chunk(marray));
  }

  for (i = 0; i != n_elements; ++i)
    check_inuse_chunk(mem2chunk(marray[i]));
#endif

  return marray;
}


/*
  ------------------------------ valloc ------------------------------
*/

#if __STD_C
Void_t* vALLOc(size_t bytes)
#else
Void_t* vALLOc(bytes) size_t bytes;
#endif
{
  /* Ensure initialization */
  mstate av = get_malloc_state();
  if (av->max_fast == 0) malloc_consolidate(av);
  return mEMALIGn(av->pagesize, bytes);
}

/*
  ------------------------------ pvalloc ------------------------------
*/


#if __STD_C
Void_t* pVALLOc(size_t bytes)
#else
Void_t* pVALLOc(bytes) size_t bytes;
#endif
{
  mstate av = get_malloc_state();
  size_t pagesz;

  /* Ensure initialization */
  if (av->max_fast == 0) malloc_consolidate(av);
  pagesz = av->pagesize;
  return mEMALIGn(pagesz, (bytes + pagesz - 1) & ~(pagesz - 1));
}
   

/*
  ------------------------------ malloc_trim ------------------------------
*/

#if __STD_C
int mTRIm(size_t pad)
#else
int mTRIm(pad) size_t pad;
#endif
{
  mstate av = get_malloc_state();
  /* Ensure initialization/consolidation */
  malloc_consolidate(av);

#ifndef MORECORE_CANNOT_TRIM        
  return sYSTRIm(pad, av);
#else
  return 0;
#endif
}


/*
  ------------------------- malloc_usable_size -------------------------
*/

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

/*
  ------------------------------ mallinfo ------------------------------
*/

struct mallinfo mALLINFo()
{
  mstate av = get_malloc_state();
  struct mallinfo mi;
  int i;
  mbinptr b;
  mchunkptr p;
  INTERNAL_SIZE_T avail;
  INTERNAL_SIZE_T fastavail;
  int nblocks;
  int nfastblocks;

  /* Ensure initialization */
  if (av->top == 0)  malloc_consolidate(av);

  check_malloc_state();

  /* Account for top */
  avail = chunksize(av->top);
  nblocks = 1;  /* top always exists */

  /* traverse fastbins */
  nfastblocks = 0;
  fastavail = 0;

  for (i = 0; i < (int)NFASTBINS; ++i) {
    for (p = av->fastbins[i]; p != 0; p = p->fd) {
      ++nfastblocks;
      fastavail += chunksize(p);
    }
  }

  avail += fastavail;

  /* traverse regular bins */
  for (i = 1; i < NBINS; ++i) {
    b = bin_at(av, i);
    for (p = last(b); p != b; p = p->bk) {
      ++nblocks;
      avail += chunksize(p);
    }
  }

  mi.smblks = nfastblocks;
  mi.ordblks = nblocks;
  mi.fordblks = avail;
  mi.uordblks = av->sbrked_mem - avail;
  mi.arena = av->sbrked_mem;
  mi.hblks = av->n_mmaps;
  mi.hblkhd = av->mmapped_mem;
  mi.fsmblks = fastavail;
  mi.keepcost = chunksize(av->top);
  mi.usmblks = av->max_total_mem;
  return mi;
}

/*
  ------------------------------ malloc_stats ------------------------------
*/

void mSTATs(void)
{
  struct mallinfo mi = mALLINFo();

#ifdef WIN32
  {
    CHUNK_SIZE_T  free, reserved, committed;
    vminfo (&free, &reserved, &committed);
    fprintf(stderr, "free bytes       = %10lu\n", 
            free);
    fprintf(stderr, "reserved bytes   = %10lu\n", 
            reserved);
    fprintf(stderr, "committed bytes  = %10lu\n", 
            committed);
  }
#endif


  fprintf(stderr, "max system bytes = %10lu\n",
          (CHUNK_SIZE_T)(mi.usmblks));
  fprintf(stderr, "system bytes     = %10lu\n",
          (CHUNK_SIZE_T)(mi.arena + mi.hblkhd));
  fprintf(stderr, "in use bytes     = %10lu\n",
          (CHUNK_SIZE_T)(mi.uordblks + mi.hblkhd));

#ifdef WIN32 
  {
    CHUNK_SIZE_T  kernel, user;
    if (cpuinfo (TRUE, &kernel, &user)) {
      fprintf(stderr, "kernel ms        = %10lu\n", 
              kernel);
      fprintf(stderr, "user ms          = %10lu\n", 
              user);
    }
  }
#endif
}


/*
  ------------------------------ mallopt ------------------------------
*/

#if __STD_C
int mALLOPt(int param_number, int value)
#else
int mALLOPt(param_number, value) int param_number; int value;
#endif
{
  mstate av = get_malloc_state();
  /* Ensure initialization/consolidation */
  malloc_consolidate(av);

  switch(param_number) {
  case M_MXFAST:
    if (value >= 0 && value <= MAX_FAST_SIZE) {
      set_max_fast(av, value);
      return 1;
    }
    else
      return 0;

  case M_TRIM_THRESHOLD:
    av->trim_threshold = value;
    return 1;

  case M_TOP_PAD:
    av->top_pad = value;
    return 1;

  case M_MMAP_THRESHOLD:
    av->mmap_threshold = value;
    return 1;

  case M_MMAP_MAX:
#if !HAVE_MMAP
    if (value != 0)
      return 0;
#endif
    av->n_mmaps_max = value;
    return 1;

  default:
    return 0;
  }
}


/* 
  -------------------- Alternative MORECORE functions --------------------
*/


/*
  General Requirements for MORECORE.

  The MORECORE function must have the following properties:

  If MORECORE_CONTIGUOUS is false:

    * MORECORE must allocate in multiples of pagesize. It will
      only be called with arguments that are multiples of pagesize.

    * MORECORE(0) must return an address that is at least 
      MALLOC_ALIGNMENT aligned. (Page-aligning always suffices.)

  else (i.e. If MORECORE_CONTIGUOUS is true):

    * Consecutive calls to MORECORE with positive arguments
      return increasing addresses, indicating that space has been
      contiguously extended. 

    * MORECORE need not allocate in multiples of pagesize.
      Calls to MORECORE need not have args of multiples of pagesize.

    * MORECORE need not page-align.

  In either case:

    * MORECORE may allocate more memory than requested. (Or even less,
      but this will generally result in a malloc failure.)

    * MORECORE must not allocate memory when given argument zero, but
      instead return one past the end address of memory from previous
      nonzero call. This malloc does NOT call MORECORE(0)
      until at least one call with positive arguments is made, so
      the initial value returned is not important.

    * Even though consecutive calls to MORECORE need not return contiguous
      addresses, it must be OK for malloc'ed chunks to span multiple
      regions in those cases where they do happen to be contiguous.

    * MORECORE need not handle negative arguments -- it may instead
      just return MORECORE_FAILURE when given negative arguments.
      Negative arguments are always multiples of pagesize. MORECORE
      must not misinterpret negative args as large positive unsigned
      args. You can suppress all such calls from even occurring by defining
      MORECORE_CANNOT_TRIM,

  There is some variation across systems about the type of the
  argument to sbrk/MORECORE. If size_t is unsigned, then it cannot
  actually be size_t, because sbrk supports negative args, so it is
  normally the signed type of the same width as size_t (sometimes
  declared as "intptr_t", and sometimes "ptrdiff_t").  It doesn't much
  matter though. Internally, we use "long" as arguments, which should
  work across all reasonable possibilities.

  Additionally, if MORECORE ever returns failure for a positive
  request, and HAVE_MMAP is true, then mmap is used as a noncontiguous
  system allocator. This is a useful backup strategy for systems with
  holes in address spaces -- in this case sbrk cannot contiguously
  expand the heap, but mmap may be able to map noncontiguous space.

  If you'd like mmap to ALWAYS be used, you can define MORECORE to be
  a function that always returns MORECORE_FAILURE.

  Malloc only has limited ability to detect failures of MORECORE
  to supply contiguous space when it says it can. In particular,
  multithreaded programs that do not use locks may result in
  rece conditions across calls to MORECORE that result in gaps
  that cannot be detected as such, and subsequent corruption.

  If you are using this malloc with something other than sbrk (or its
  emulation) to supply memory regions, you probably want to set
  MORECORE_CONTIGUOUS as false.  As an example, here is a custom
  allocator kindly contributed for pre-OSX macOS.  It uses virtually
  but not necessarily physically contiguous non-paged memory (locked
  in, present and won't get swapped out).  You can use it by
  uncommenting this section, adding some #includes, and setting up the
  appropriate defines above:

      #define MORECORE osMoreCore
      #define MORECORE_CONTIGUOUS 0

  There is also a shutdown routine that should somehow be called for
  cleanup upon program exit.

  #define MAX_POOL_ENTRIES 100
  #define MINIMUM_MORECORE_SIZE  (64 * 1024)
  static int next_os_pool;
  void *our_os_pools[MAX_POOL_ENTRIES];

  void *osMoreCore(int size)
  {
    void *ptr = 0;
    static void *sbrk_top = 0;

    if (size > 0)
    {
      if (size < MINIMUM_MORECORE_SIZE)
         size = MINIMUM_MORECORE_SIZE;
      if (CurrentExecutionLevel() == kTaskLevel)
         ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0);
      if (ptr == 0)
      {
        return (void *) MORECORE_FAILURE;
      }
      // save ptrs so they can be freed during cleanup
      our_os_pools[next_os_pool] = ptr;
      next_os_pool++;
      ptr = (void *) ((((CHUNK_SIZE_T) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK);
      sbrk_top = (char *) ptr + size;
      return ptr;
    }
    else if (size < 0)
    {
      // we don't currently support shrink behavior
      return (void *) MORECORE_FAILURE;
    }
    else
    {
      return sbrk_top;
    }
  }

  // cleanup any allocated memory pools
  // called as last thing before shutting down driver

  void osCleanupMem(void)
  {
    void **ptr;

    for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++)
      if (*ptr)
      {
         PoolDeallocate(*ptr);
         *ptr = 0;
      }
  }

*/


/* 
  -------------------------------------------------------------- 

  Emulation of sbrk for win32. 
  Donated by J. Walter <Walter@GeNeSys-e.de>.
  For additional information about this code, and malloc on Win32, see 
     http://www.genesys-e.de/jwalter/
*/


#ifdef WIN32

#ifdef _DEBUG
/* #define TRACE */
#endif

/* Support for USE_MALLOC_LOCK */
#ifdef USE_MALLOC_LOCK

/* Wait for spin lock */
static int slwait (int *sl) {
    while (InterlockedCompareExchange ((void **) sl, (void *) 1, (void *) 0) != 0) 
	    Sleep (0);
    return 0;
}

/* Release spin lock */
static int slrelease (int *sl) {
    InterlockedExchange (sl, 0);
    return 0;
}

#ifdef NEEDED
/* Spin lock for emulation code */
static int g_sl;
#endif

#endif /* USE_MALLOC_LOCK */

/* getpagesize for windows */
static long getpagesize (void) {
    static long g_pagesize = 0;
    if (! g_pagesize) {
        SYSTEM_INFO system_info;
        GetSystemInfo (&system_info);
        g_pagesize = system_info.dwPageSize;
    }
    return g_pagesize;
}
static long getregionsize (void) {
    static long g_regionsize = 0;
    if (! g_regionsize) {
        SYSTEM_INFO system_info;
        GetSystemInfo (&system_info);
        g_regionsize = system_info.dwAllocationGranularity;
    }
    return g_regionsize;
}

/* A region list entry */
typedef struct _region_list_entry {
    void *top_allocated;
    void *top_committed;
    void *top_reserved;
    long reserve_size;
    struct _region_list_entry *previous;
} region_list_entry;

/* Allocate and link a region entry in the region list */
static int region_list_append (region_list_entry **last, void *base_reserved, long reserve_size) {
    region_list_entry *next = HeapAlloc (GetProcessHeap (), 0, sizeof (region_list_entry));
    if (! next)
        return FALSE;
    next->top_allocated = (char *) base_reserved;
    next->top_committed = (char *) base_reserved;
    next->top_reserved = (char *) base_reserved + reserve_size;
    next->reserve_size = reserve_size;
    next->previous = *last;
    *last = next;
    return TRUE;
}
/* Free and unlink the last region entry from the region list */
static int region_list_remove (region_list_entry **last) {
    region_list_entry *previous = (*last)->previous;
    if (! HeapFree (GetProcessHeap (), sizeof (region_list_entry), *last))
        return FALSE;
    *last = previous;
    return TRUE;
}

#define CEIL(size,to)	(((size)+(to)-1)&~((to)-1))
#define FLOOR(size,to)	((size)&~((to)-1))

#define SBRK_SCALE  0
/* #define SBRK_SCALE  1 */
/* #define SBRK_SCALE  2 */
/* #define SBRK_SCALE  4  */

/* sbrk for windows */
static void *sbrk (long size) {
    static long g_pagesize, g_my_pagesize;
    static long g_regionsize, g_my_regionsize;
    static region_list_entry *g_last;
    void *result = (void *) MORECORE_FAILURE;
#ifdef TRACE
    printf ("sbrk %d\n", size);
#endif
#if defined (USE_MALLOC_LOCK) && defined (NEEDED)
    /* Wait for spin lock */
    slwait (&g_sl);
#endif
    /* First time initialization */
    if (! g_pagesize) {
        g_pagesize = getpagesize ();
        g_my_pagesize = g_pagesize << SBRK_SCALE;
    }
    if (! g_regionsize) {
        g_regionsize = getregionsize ();
        g_my_regionsize = g_regionsize << SBRK_SCALE;
    }
    if (! g_last) {
        if (! region_list_append (&g_last, 0, 0)) 
           goto sbrk_exit;
    }
    /* Assert invariants */
    assert (g_last);
    assert ((char *) g_last->top_reserved - g_last->reserve_size <= (char *) g_last->top_allocated &&
            g_last->top_allocated <= g_last->top_committed);
    assert ((char *) g_last->top_reserved - g_last->reserve_size <= (char *) g_last->top_committed &&
            g_last->top_committed <= g_last->top_reserved &&
            (unsigned) g_last->top_committed % g_pagesize == 0);
    assert ((unsigned) g_last->top_reserved % g_regionsize == 0);
    assert ((unsigned) g_last->reserve_size % g_regionsize == 0);
    /* Allocation requested? */
    if (size >= 0) {
        /* Allocation size is the requested size */
        long allocate_size = size;
        /* Compute the size to commit */
        long to_commit = (char *) g_last->top_allocated + allocate_size - (char *) g_last->top_committed;
        /* Do we reach the commit limit? */
        if (to_commit > 0) {
            /* Round size to commit */
            long commit_size = CEIL (to_commit, g_my_pagesize);
            /* Compute the size to reserve */
            long to_reserve = (char *) g_last->top_committed + commit_size - (char *) g_last->top_reserved;
            /* Do we reach the reserve limit? */
            if (to_reserve > 0) {
                /* Compute the remaining size to commit in the current region */
                long remaining_commit_size = (char *) g_last->top_reserved - (char *) g_last->top_committed;
                if (remaining_commit_size > 0) {
                    /* Assert preconditions */
                    assert ((unsigned) g_last->top_committed % g_pagesize == 0);
                    assert (0 < remaining_commit_size && remaining_commit_size % g_pagesize == 0); {
                        /* Commit this */
                        void *base_committed = VirtualAlloc (g_last->top_committed, remaining_commit_size,
							                                 MEM_COMMIT, PAGE_READWRITE);
                        /* Check returned pointer for consistency */
                        if (base_committed != g_last->top_committed)
                            goto sbrk_exit;
                        /* Assert postconditions */
                        assert ((unsigned) base_committed % g_pagesize == 0);
#ifdef TRACE
                        printf ("Commit %p %d\n", base_committed, remaining_commit_size);
#endif
                        /* Adjust the regions commit top */
                        g_last->top_committed = (char *) base_committed + remaining_commit_size;
                    }
                } {
                    /* Now we are going to search and reserve. */
                    int contiguous = -1;
                    int found = FALSE;
                    MEMORY_BASIC_INFORMATION memory_info;
                    void *base_reserved;
                    long reserve_size;
                    do {
                        /* Assume contiguous memory */
                        contiguous = TRUE;
                        /* Round size to reserve */
                        reserve_size = CEIL (to_reserve, g_my_regionsize);
                        /* Start with the current region's top */
                        memory_info.BaseAddress = g_last->top_reserved;
                        /* Assert preconditions */
                        assert ((unsigned) memory_info.BaseAddress % g_pagesize == 0);
                        assert (0 < reserve_size && reserve_size % g_regionsize == 0);
                        while (VirtualQuery (memory_info.BaseAddress, &memory_info, sizeof (memory_info))) {
                            /* Assert postconditions */
                            assert ((unsigned) memory_info.BaseAddress % g_pagesize == 0);
#ifdef TRACE
                            printf ("Query %p %d %s\n", memory_info.BaseAddress, memory_info.RegionSize, 
                                    memory_info.State == MEM_FREE ? "FREE": 
                                    (memory_info.State == MEM_RESERVE ? "RESERVED":
                                     (memory_info.State == MEM_COMMIT ? "COMMITTED": "?")));
#endif
                            /* Region is free, well aligned and big enough: we are done */
                            if (memory_info.State == MEM_FREE &&
                                (unsigned) memory_info.BaseAddress % g_regionsize == 0 &&
                                memory_info.RegionSize >= (unsigned) reserve_size) {
                                found = TRUE;
                                break;
                            }
                            /* From now on we can't get contiguous memory! */
                            contiguous = FALSE;
                            /* Recompute size to reserve */
                            reserve_size = CEIL (allocate_size, g_my_regionsize);
                            memory_info.BaseAddress = (char *) memory_info.BaseAddress + memory_info.RegionSize;
                            /* Assert preconditions */
                            assert ((unsigned) memory_info.BaseAddress % g_pagesize == 0);
                            assert (0 < reserve_size && reserve_size % g_regionsize == 0);
                        }
                        /* Search failed? */
                        if (! found) 
                            goto sbrk_exit;
                        /* Assert preconditions */
                        assert ((unsigned) memory_info.BaseAddress % g_regionsize == 0);
                        assert (0 < reserve_size && reserve_size % g_regionsize == 0);
                        /* Try to reserve this */
                        base_reserved = VirtualAlloc (memory_info.BaseAddress, reserve_size, 
					                                  MEM_RESERVE, PAGE_NOACCESS);
                        if (! base_reserved) {
                            int rc = GetLastError ();
                            if (rc != ERROR_INVALID_ADDRESS) 
                                goto sbrk_exit;
                        }
                        /* A null pointer signals (hopefully) a race condition with another thread. */
                        /* In this case, we try again. */
                    } while (! base_reserved);
                    /* Check returned pointer for consistency */
                    if (memory_info.BaseAddress && base_reserved != memory_info.BaseAddress)
                        goto sbrk_exit;
                    /* Assert postconditions */
                    assert ((unsigned) base_reserved % g_regionsize == 0);
#ifdef TRACE
                    printf ("Reserve %p %d\n", base_reserved, reserve_size);
#endif
                    /* Did we get contiguous memory? */
                    if (contiguous) {
                        long start_size = (char *) g_last->top_committed - (char *) g_last->top_allocated;
                        /* Adjust allocation size */
                        allocate_size -= start_size;
                        /* Adjust the regions allocation top */
                        g_last->top_allocated = g_last->top_committed;
                        /* Recompute the size to commit */
                        to_commit = (char *) g_last->top_allocated + allocate_size - (char *) g_last->top_committed;
                        /* Round size to commit */
                        commit_size = CEIL (to_commit, g_my_pagesize);
                    } 
                    /* Append the new region to the list */
                    if (! region_list_append (&g_last, base_reserved, reserve_size))
                        goto sbrk_exit;
                    /* Didn't we get contiguous memory? */
                    if (! contiguous) {
                        /* Recompute the size to commit */
                        to_commit = (char *) g_last->top_allocated + allocate_size - (char *) g_last->top_committed;
                        /* Round size to commit */
                        commit_size = CEIL (to_commit, g_my_pagesize);
                    }
                }
            } 
            /* Assert preconditions */
            assert ((unsigned) g_last->top_committed % g_pagesize == 0);
            assert (0 < commit_size && commit_size % g_pagesize == 0); {
                /* Commit this */
                void *base_committed = VirtualAlloc (g_last->top_committed, commit_size, 
				    			                     MEM_COMMIT, PAGE_READWRITE);
                /* Check returned pointer for consistency */
                if (base_committed != g_last->top_committed)
                    goto sbrk_exit;
                /* Assert postconditions */
                assert ((unsigned) base_committed % g_pagesize == 0);
#ifdef TRACE
                printf ("Commit %p %d\n", base_committed, commit_size);
#endif
                /* Adjust the regions commit top */
                g_last->top_committed = (char *) base_committed + commit_size;
            }
        } 
        /* Adjust the regions allocation top */
        g_last->top_allocated = (char *) g_last->top_allocated + allocate_size;
        result = (char *) g_last->top_allocated - size;
    /* Deallocation requested? */
    } else if (size < 0) {
        long deallocate_size = - size;
        /* As long as we have a region to release */
        while ((char *) g_last->top_allocated - deallocate_size < (char *) g_last->top_reserved - g_last->reserve_size) {
            /* Get the size to release */
            long release_size = g_last->reserve_size;
            /* Get the base address */
            void *base_reserved = (char *) g_last->top_reserved - release_size;
            /* Assert preconditions */
            assert ((unsigned) base_reserved % g_regionsize == 0); 
            assert (0 < release_size && release_size % g_regionsize == 0); {
                /* Release this */
                int rc = VirtualFree (base_reserved, 0, 
                                      MEM_RELEASE);
                /* Check returned code for consistency */
                if (! rc)
                    goto sbrk_exit;
#ifdef TRACE
                printf ("Release %p %d\n", base_reserved, release_size);
#endif
            }
            /* Adjust deallocation size */
            deallocate_size -= (char *) g_last->top_allocated - (char *) base_reserved;
            /* Remove the old region from the list */
            if (! region_list_remove (&g_last))
                goto sbrk_exit;
        } {
            /* Compute the size to decommit */
            long to_decommit = (char *) g_last->top_committed - ((char *) g_last->top_allocated - deallocate_size);
            if (to_decommit >= g_my_pagesize) {
                /* Compute the size to decommit */
                long decommit_size = FLOOR (to_decommit, g_my_pagesize);
                /*  Compute the base address */
                void *base_committed = (char *) g_last->top_committed - decommit_size;
                /* Assert preconditions */
                assert ((unsigned) base_committed % g_pagesize == 0);
                assert (0 < decommit_size && decommit_size % g_pagesize == 0); {
                    /* Decommit this */
                    int rc = VirtualFree ((char *) base_committed, decommit_size, 
                                          MEM_DECOMMIT);
                    /* Check returned code for consistency */
                    if (! rc)
                        goto sbrk_exit;
#ifdef TRACE
                    printf ("Decommit %p %d\n", base_committed, decommit_size);
#endif
                }
                /* Adjust deallocation size and regions commit and allocate top */
                deallocate_size -= (char *) g_last->top_allocated - (char *) base_committed;
                g_last->top_committed = base_committed;
                g_last->top_allocated = base_committed;
            }
        }
        /* Adjust regions allocate top */
        g_last->top_allocated = (char *) g_last->top_allocated - deallocate_size;
        /* Check for underflow */
        if ((char *) g_last->top_reserved - g_last->reserve_size > (char *) g_last->top_allocated ||
            g_last->top_allocated > g_last->top_committed) {
            /* Adjust regions allocate top */
            g_last->top_allocated = (char *) g_last->top_reserved - g_last->reserve_size;
            goto sbrk_exit;
        }
        result = g_last->top_allocated;
    }
    /* Assert invariants */
    assert (g_last);
    assert ((char *) g_last->top_reserved - g_last->reserve_size <= (char *) g_last->top_allocated &&
            g_last->top_allocated <= g_last->top_committed);
    assert ((char *) g_last->top_reserved - g_last->reserve_size <= (char *) g_last->top_committed &&
            g_last->top_committed <= g_last->top_reserved &&
            (unsigned) g_last->top_committed % g_pagesize == 0);
    assert ((unsigned) g_last->top_reserved % g_regionsize == 0);
    assert ((unsigned) g_last->reserve_size % g_regionsize == 0);

sbrk_exit:
#if defined (USE_MALLOC_LOCK) && defined (NEEDED)
    /* Release spin lock */
    slrelease (&g_sl);
#endif
    return result;
}

static void vminfo (CHUNK_SIZE_T  *free, CHUNK_SIZE_T  *reserved, CHUNK_SIZE_T  *committed) {
    MEMORY_BASIC_INFORMATION memory_info;
    memory_info.BaseAddress = 0;
    *free = *reserved = *committed = 0;
    while (VirtualQuery (memory_info.BaseAddress, &memory_info, sizeof (memory_info))) {
        switch (memory_info.State) {
        case MEM_FREE:
            *free += memory_info.RegionSize;
            break;
        case MEM_RESERVE:
            *reserved += memory_info.RegionSize;
            break;
        case MEM_COMMIT:
            *committed += memory_info.RegionSize;
            break;
        }
        memory_info.BaseAddress = (char *) memory_info.BaseAddress + memory_info.RegionSize;
    }
}

static int cpuinfo (int whole, CHUNK_SIZE_T  *kernel, CHUNK_SIZE_T  *user) {
    if (whole) {
        __int64 creation64, exit64, kernel64, user64;
        int rc = GetProcessTimes (GetCurrentProcess (), 
                                  (FILETIME *) &creation64,  
                                  (FILETIME *) &exit64, 
                                  (FILETIME *) &kernel64, 
                                  (FILETIME *) &user64);
        if (! rc) {
            *kernel = 0;
            *user = 0;
            return FALSE;
        } 
        *kernel = (CHUNK_SIZE_T) (kernel64 / 10000);
        *user = (CHUNK_SIZE_T) (user64 / 10000);
        return TRUE;
    } else {
        __int64 creation64, exit64, kernel64, user64;
        int rc = GetThreadTimes (GetCurrentThread (), 
                                 (FILETIME *) &creation64,  
                                 (FILETIME *) &exit64, 
                                 (FILETIME *) &kernel64, 
                                 (FILETIME *) &user64);
        if (! rc) {
            *kernel = 0;
            *user = 0;
            return FALSE;
        } 
        *kernel = (CHUNK_SIZE_T) (kernel64 / 10000);
        *user = (CHUNK_SIZE_T) (user64 / 10000);
        return TRUE;
    }
}

#endif /* WIN32 */

/* ------------------------------------------------------------
History:
    V2.7.2 Sat Aug 17 09:07:30 2002  Doug Lea  (dl at gee)
      * Fix malloc_state bitmap array misdeclaration

    V2.7.1 Thu Jul 25 10:58:03 2002  Doug Lea  (dl at gee)
      * Allow tuning of FIRST_SORTED_BIN_SIZE
      * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte.
      * Better detection and support for non-contiguousness of MORECORE. 
        Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger
      * Bypass most of malloc if no frees. Thanks To Emery Berger.
      * Fix freeing of old top non-contiguous chunk im sysmalloc.
      * Raised default trim and map thresholds to 256K.
      * Fix mmap-related #defines. Thanks to Lubos Lunak.
      * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield.
      * Branch-free bin calculation
      * Default trim and mmap thresholds now 256K.

    V2.7.0 Sun Mar 11 14:14:06 2001  Doug Lea  (dl at gee)
      * Introduce independent_comalloc and independent_calloc.
        Thanks to Michael Pachos for motivation and help.
      * Make optional .h file available
      * Allow > 2GB requests on 32bit systems.
      * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>.
        Thanks also to Andreas Mueller <a.mueller at paradatec.de>,
        and Anonymous.
      * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for 
        helping test this.)
      * memalign: check alignment arg
      * realloc: don't try to shift chunks backwards, since this
        leads to  more fragmentation in some programs and doesn't
        seem to help in any others.
      * Collect all cases in malloc requiring system memory into sYSMALLOc
      * Use mmap as backup to sbrk
      * Place all internal state in malloc_state
      * Introduce fastbins (although similar to 2.5.1)
      * Many minor tunings and cosmetic improvements
      * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK 
      * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS
        Thanks to Tony E. Bennett <tbennett@nvidia.com> and others.
      * Include errno.h to support default failure action.

    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 at yahoo.com>
         * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h'
          (e.g. WIN32 platforms)
         * Cleanup 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.)

*/