about summary refs log tree commit diff
path: root/malloc/malloc.c
blob: fd8b52bfac00b1016669c91f0b56cbb4c4c419a1 (plain) (blame)
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
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
/* Malloc implementation for multiple threads without lock contention.
   Copyright (C) 1996-2023 Free Software Foundation, Inc.
   Copyright The GNU Toolchain Authors.
   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public License as
   published by the Free Software Foundation; either version 2.1 of the
   License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; see the file COPYING.LIB.  If
   not, see <https://www.gnu.org/licenses/>.  */

/*
  This is a version (aka ptmalloc2) of malloc/free/realloc written by
  Doug Lea and adapted to multiple threads/arenas by Wolfram Gloger.

  There have been substantial changes made after the integration into
  glibc in all parts of the code.  Do not look for much commonality
  with the ptmalloc2 version.

* Version ptmalloc2-20011215
  based on:
  VERSION 2.7.0 Sun Mar 11 14:14:06 2001  Doug Lea  (dl at gee)

* Quickstart

  In order to compile this implementation, a Makefile is provided with
  the ptmalloc2 distribution, which has pre-defined targets for some
  popular systems (e.g. "make posix" for Posix threads).  All that is
  typically required with regard to compiler flags is the selection of
  the thread package via defining one out of USE_PTHREADS, USE_THR or
  USE_SPROC.  Check the thread-m.h file for what effects this has.
  Many/most systems will additionally require USE_TSD_DATA_HACK to be
  defined, so this is the default for "make posix".

* 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* p);
    realloc(void* 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* chunks[]);
    independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]);
    pvalloc(size_t n);
    malloc_trim(size_t pad);
    malloc_usable_size(void* 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: thread-safe

  Compliance: I believe it is compliant with the 1997 Single Unix Specification
       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.
    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:

    HAVE_MREMAP                0

    Changing default word sizes:

    INTERNAL_SIZE_T            size_t

    Configuration and functionality options:

    USE_PUBLIC_MALLOC_WRAPPERS NOT defined
    USE_MALLOC_LOCK            NOT defined
    MALLOC_DEBUG               NOT defined
    REALLOC_ZERO_BYTES_FREES   1
    TRIM_FASTBINS              0

    Options for customizing MORECORE:

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

    Tuning options that are also dynamically changeable via mallopt:

    DEFAULT_MXFAST             64 (for 32bit), 128 (for 64bit)
    DEFAULT_TRIM_THRESHOLD     128 * 1024
    DEFAULT_TOP_PAD            0
    DEFAULT_MMAP_THRESHOLD     128 * 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.  */

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

#ifndef void
#define void      void
#endif /*void*/

#include <stddef.h>   /* for size_t */
#include <stdlib.h>   /* for getenv(), abort() */
#include <unistd.h>   /* for __libc_enable_secure */

#include <atomic.h>
#include <_itoa.h>
#include <bits/wordsize.h>
#include <sys/sysinfo.h>

#include <ldsodefs.h>

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

#include <shlib-compat.h>

/* For uintptr_t.  */
#include <stdint.h>

/* For va_arg, va_start, va_end.  */
#include <stdarg.h>

/* For MIN, MAX, powerof2.  */
#include <sys/param.h>

/* For ALIGN_UP et. al.  */
#include <libc-pointer-arith.h>

/* For DIAG_PUSH/POP_NEEDS_COMMENT et al.  */
#include <libc-diag.h>

/* For memory tagging.  */
#include <libc-mtag.h>

#include <malloc/malloc-internal.h>

/* For SINGLE_THREAD_P.  */
#include <sysdep-cancel.h>

#include <libc-internal.h>

/* For tcache double-free check.  */
#include <random-bits.h>
#include <sys/random.h>
#include <not-cancel.h>

/*
  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 -DMALLOC_DEBUG, 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 MALLOC_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 MALLOC_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 MALLOC_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.
*/

#ifndef MALLOC_DEBUG
#define MALLOC_DEBUG 0
#endif

#if USE_TCACHE
/* We want 64 entries.  This is an arbitrary limit, which tunables can reduce.  */
# define TCACHE_MAX_BINS		64
# define MAX_TCACHE_SIZE	tidx2usize (TCACHE_MAX_BINS-1)

/* Only used to pre-fill the tunables.  */
# define tidx2usize(idx)	(((size_t) idx) * MALLOC_ALIGNMENT + MINSIZE - SIZE_SZ)

/* When "x" is from chunksize().  */
# define csize2tidx(x) (((x) - MINSIZE + MALLOC_ALIGNMENT - 1) / MALLOC_ALIGNMENT)
/* When "x" is a user-provided size.  */
# define usize2tidx(x) csize2tidx (request2size (x))

/* With rounding and alignment, the bins are...
   idx 0   bytes 0..24 (64-bit) or 0..12 (32-bit)
   idx 1   bytes 25..40 or 13..20
   idx 2   bytes 41..56 or 21..28
   etc.  */

/* This is another arbitrary limit, which tunables can change.  Each
   tcache bin will hold at most this number of chunks.  */
# define TCACHE_FILL_COUNT 7

/* Maximum chunks in tcache bins for tunables.  This value must fit the range
   of tcache->counts[] entries, else they may overflow.  */
# define MAX_TCACHE_COUNT UINT16_MAX
#endif

/* Safe-Linking:
   Use randomness from ASLR (mmap_base) to protect single-linked lists
   of Fast-Bins and TCache.  That is, mask the "next" pointers of the
   lists' chunks, and also perform allocation alignment checks on them.
   This mechanism reduces the risk of pointer hijacking, as was done with
   Safe-Unlinking in the double-linked lists of Small-Bins.
   It assumes a minimum page size of 4096 bytes (12 bits).  Systems with
   larger pages provide less entropy, although the pointer mangling
   still works.  */
#define PROTECT_PTR(pos, ptr) \
  ((__typeof (ptr)) ((((size_t) pos) >> 12) ^ ((size_t) ptr)))
#define REVEAL_PTR(ptr)  PROTECT_PTR (&ptr, ptr)

/*
  The REALLOC_ZERO_BYTES_FREES macro controls the behavior of realloc (p, 0)
  when p is nonnull.  If the macro is nonzero, the realloc call returns NULL;
  otherwise, the call returns what malloc (0) would.  In either case,
  p is freed.  Glibc uses a nonzero REALLOC_ZERO_BYTES_FREES, which
  implements common historical practice.

  ISO C17 says the realloc call has implementation-defined behavior,
  and it might not even free p.
*/

#ifndef REALLOC_ZERO_BYTES_FREES
#define REALLOC_ZERO_BYTES_FREES 1
#endif

/*
  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

/* Definition for getting more memory from the OS.  */
#include "morecore.c"

#define MORECORE         (*__glibc_morecore)
#define MORECORE_FAILURE 0

/* Memory tagging.  */

/* Some systems support the concept of tagging (sometimes known as
   coloring) memory locations on a fine grained basis.  Each memory
   location is given a color (normally allocated randomly) and
   pointers are also colored.  When the pointer is dereferenced, the
   pointer's color is checked against the memory's color and if they
   differ the access is faulted (sometimes lazily).

   We use this in glibc by maintaining a single color for the malloc
   data structures that are interleaved with the user data and then
   assigning separate colors for each block allocation handed out.  In
   this way simple buffer overruns will be rapidly detected.  When
   memory is freed, the memory is recolored back to the glibc default
   so that simple use-after-free errors can also be detected.

   If memory is reallocated the buffer is recolored even if the
   address remains the same.  This has a performance impact, but
   guarantees that the old pointer cannot mistakenly be reused (code
   that compares old against new will see a mismatch and will then
   need to behave as though realloc moved the data to a new location).

   Internal API for memory tagging support.

   The aim is to keep the code for memory tagging support as close to
   the normal APIs in glibc as possible, so that if tagging is not
   enabled in the library, or is disabled at runtime then standard
   operations can continue to be used.  Support macros are used to do
   this:

   void *tag_new_zero_region (void *ptr, size_t size)

   Allocates a new tag, colors the memory with that tag, zeros the
   memory and returns a pointer that is correctly colored for that
   location.  The non-tagging version will simply call memset with 0.

   void *tag_region (void *ptr, size_t size)

   Color the region of memory pointed to by PTR and size SIZE with
   the color of PTR.  Returns the original pointer.

   void *tag_new_usable (void *ptr)

   Allocate a new random color and use it to color the user region of
   a chunk; this may include data from the subsequent chunk's header
   if tagging is sufficiently fine grained.  Returns PTR suitably
   recolored for accessing the memory there.

   void *tag_at (void *ptr)

   Read the current color of the memory at the address pointed to by
   PTR (ignoring it's current color) and return PTR recolored to that
   color.  PTR must be valid address in all other respects.  When
   tagging is not enabled, it simply returns the original pointer.
*/

#ifdef USE_MTAG
static bool mtag_enabled = false;
static int mtag_mmap_flags = 0;
#else
# define mtag_enabled false
# define mtag_mmap_flags 0
#endif

static __always_inline void *
tag_region (void *ptr, size_t size)
{
  if (__glibc_unlikely (mtag_enabled))
    return __libc_mtag_tag_region (ptr, size);
  return ptr;
}

static __always_inline void *
tag_new_zero_region (void *ptr, size_t size)
{
  if (__glibc_unlikely (mtag_enabled))
    return __libc_mtag_tag_zero_region (__libc_mtag_new_tag (ptr), size);
  return memset (ptr, 0, size);
}

/* Defined later.  */
static void *
tag_new_usable (void *ptr);

static __always_inline void *
tag_at (void *ptr)
{
  if (__glibc_unlikely (mtag_enabled))
    return __libc_mtag_address_get_tag (ptr);
  return ptr;
}

#include <string.h>

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


/*
  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 */

/*  MORECORE_CLEARS           (default 1)
     The degree to which the routine mapped to MORECORE zeroes out
     memory: never (0), only for newly allocated space (1) or always
     (2).  The distinction between (1) and (2) is necessary because on
     some systems, if the application first decrements and then
     increments the break value, the contents of the reallocated space
     are unspecified.
 */

#ifndef MORECORE_CLEARS
# define MORECORE_CLEARS 1
#endif


/*
   MMAP_AS_MORECORE_SIZE is the minimum mmap size argument to use if
   sbrk fails, and mmap is used as a backup.  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.
*/

#ifndef HAVE_MREMAP
#define HAVE_MREMAP 0
#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.
*/


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

#if IS_IN (libc)
/*
  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 minimum-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.
*/
void*  __libc_malloc(size_t);
libc_hidden_proto (__libc_malloc)

/*
  free(void* 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.
*/
void     __libc_free(void*);
libc_hidden_proto (__libc_free)

/*
  calloc(size_t n_elements, size_t element_size);
  Returns a pointer to n_elements * element_size bytes, with all locations
  set to zero.
*/
void*  __libc_calloc(size_t, size_t);

/*
  realloc(void* 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
  grown 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.
*/
void*  __libc_realloc(void*, size_t);
libc_hidden_proto (__libc_realloc)

/*
  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.
*/
void*  __libc_memalign(size_t, size_t);
libc_hidden_proto (__libc_memalign)

/*
  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.
*/
void*  __libc_valloc(size_t);



/*
  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:   always 0
  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.
*/
struct mallinfo2 __libc_mallinfo2(void);
libc_hidden_proto (__libc_mallinfo2)

struct mallinfo __libc_mallinfo(void);


/*
  pvalloc(size_t n);
  Equivalent to valloc(minimum-page-that-holds(n)), that is,
  round up n to nearest pagesize.
 */
void*  __libc_pvalloc(size_t);

/*
  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
  return 0.
*/
int      __malloc_trim(size_t);

/*
  malloc_usable_size(void* 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);

*/
size_t   __malloc_usable_size(void*);

/*
  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.

*/
void     __malloc_stats(void);

/*
  posix_memalign(void **memptr, size_t alignment, size_t size);

  POSIX wrapper like memalign(), checking for validity of size.
*/
int      __posix_memalign(void **, size_t, size_t);
#endif /* IS_IN (libc) */

/*
  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         128*1024   any   (-1U disables trimming)
  M_TOP_PAD        -2         0          any
  M_MMAP_THRESHOLD -3         128*1024   any   (or 0 if no MMAP support)
  M_MMAP_MAX       -4         65536      any   (0 disables use of mmap)
*/
int      __libc_mallopt(int, int);
#if IS_IN (libc)
libc_hidden_proto (__libc_mallopt)
#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 8 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 * SIZE_SZ / 4)
#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 It 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 (128 * 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

/*
  MMAP_THRESHOLD_MAX and _MIN are the bounds on the dynamically
  adjusted MMAP_THRESHOLD.
*/

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

#ifndef DEFAULT_MMAP_THRESHOLD_MAX
  /* For 32-bit platforms we cannot increase the maximum mmap
     threshold much because it is also the minimum value for the
     maximum heap size and its alignment.  Going above 512k (i.e., 1M
     for new heaps) wastes too much address space.  */
# if __WORDSIZE == 32
#  define DEFAULT_MMAP_THRESHOLD_MAX (512 * 1024)
# else
#  define DEFAULT_MMAP_THRESHOLD_MAX (4 * 1024 * 1024 * sizeof(long))
# endif
#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.


  Update in 2006:
  The above was written in 2001. Since then the world has changed a lot.
  Memory got bigger. Applications got bigger. The virtual address space
  layout in 32 bit linux changed.

  In the new situation, brk() and mmap space is shared and there are no
  artificial limits on brk size imposed by the kernel. What is more,
  applications have started using transient allocations larger than the
  128Kb as was imagined in 2001.

  The price for mmap is also high now; each time glibc mmaps from the
  kernel, the kernel is forced to zero out the memory it gives to the
  application. Zeroing memory is expensive and eats a lot of cache and
  memory bandwidth. This has nothing to do with the efficiency of the
  virtual memory system, by doing mmap the kernel just has no choice but
  to zero.

  In 2001, the kernel had a maximum size for brk() which was about 800
  megabytes on 32 bit x86, at that point brk() would hit the first
  mmaped shared libaries and couldn't expand anymore. With current 2.6
  kernels, the VA space layout is different and brk() and mmap
  both can span the entire heap at will.

  Rather than using a static threshold for the brk/mmap tradeoff,
  we are now using a simple dynamic one. The goal is still to avoid
  fragmentation. The old goals we kept are
  1) try to get the long lived large allocations to use mmap()
  2) really large allocations should always use mmap()
  and we're adding now:
  3) transient allocations should use brk() to avoid forcing the kernel
     having to zero memory over and over again

  The implementation works with a sliding threshold, which is by default
  limited to go between 128Kb and 32Mb (64Mb for 64 bitmachines) and starts
  out at 128Kb as per the 2001 default.

  This allows us to satisfy requirement 1) under the assumption that long
  lived allocations are made early in the process' lifespan, before it has
  started doing dynamic allocations of the same size (which will
  increase the threshold).

  The upperbound on the threshold satisfies requirement 2)

  The threshold goes up in value when the application frees memory that was
  allocated with the mmap allocator. The idea is that once the application
  starts freeing memory of a certain size, it's highly probable that this is
  a size the application uses for transient allocations. This estimator
  is there to satisfy the new third requirement.

*/

#define M_MMAP_THRESHOLD      -3

#ifndef DEFAULT_MMAP_THRESHOLD
#define DEFAULT_MMAP_THRESHOLD DEFAULT_MMAP_THRESHOLD_MIN
#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.
*/

#define M_MMAP_MAX             -4

#ifndef DEFAULT_MMAP_MAX
#define DEFAULT_MMAP_MAX       (65536)
#endif

#include <malloc.h>

#ifndef RETURN_ADDRESS
#define RETURN_ADDRESS(X_) (NULL)
#endif

/* Forward declarations.  */
struct malloc_chunk;
typedef struct malloc_chunk* mchunkptr;

/* Internal routines.  */

static void*  _int_malloc(mstate, size_t);
static void     _int_free(mstate, mchunkptr, int);
static void*  _int_realloc(mstate, mchunkptr, INTERNAL_SIZE_T,
			   INTERNAL_SIZE_T);
static void*  _int_memalign(mstate, size_t, size_t);
#if IS_IN (libc)
static void*  _mid_memalign(size_t, size_t, void *);
#endif

static void malloc_printerr(const char *str) __attribute__ ((noreturn));

static void munmap_chunk(mchunkptr p);
#if HAVE_MREMAP
static mchunkptr mremap_chunk(mchunkptr p, size_t new_size);
#endif

static size_t musable (void *mem);

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


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

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

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


/*
  -----------------------  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      mchunk_prev_size;  /* Size of previous chunk (if free).  */
  INTERNAL_SIZE_T      mchunk_size;       /* Size in bytes, including overhead. */

  struct malloc_chunk* fd;         /* double links -- used only if free. */
  struct malloc_chunk* bk;

  /* Only used for large blocks: pointer to next larger size.  */
  struct malloc_chunk* fd_nextsize; /* double links -- used only if free. */
  struct malloc_chunk* bk_nextsize;
};


/*
   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 unallocated (P clear)  |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of chunk, in bytes                     |A|M|P|
      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             User data starts here...                          .
	    .                                                               .
	    .             (malloc_usable_size() bytes)                      .
	    .                                                               |
nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             (size of chunk, but used for application data)    |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of next chunk, in bytes                |A|0|1|
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

    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 boundaries, 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, if unallocated (P clear)  |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    `head:' |             Size of chunk, in bytes                     |A|0|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                           |
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
	    |             Size of next chunk, in bytes                |A|0|0|
	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

    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.

    The A (NON_MAIN_ARENA) bit is cleared for chunks on the initial,
    main arena, described by the main_arena variable.  When additional
    threads are spawned, each thread receives its own arena (up to a
    configurable limit, after which arenas are reused for multiple
    threads), and the chunks in these arenas have the A bit set.  To
    find the arena for a chunk on such a non-main arena, heap_for_ptr
    performs a bit mask operation and indirection through the ar_ptr
    member of the per-heap header heap_info (see arena.c).

    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 three 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 M (IS_MMAPPED) set in their size fields.  Because they are
	allocated one-by-one, each must contain its own trailing size
	field.  If the M bit is set, the other bits are ignored
	(because mmapped chunks are neither in an arena, nor adjacent
	to a freed chunk).  The M bit is also used for chunks which
	originally came from a dumped heap via malloc_set_state in
	hooks.c.

     3. Chunks in fastbins are treated as allocated chunks from the
	point of view of the chunk allocator.  They are consolidated
	with their neighbors only in bulk, in malloc_consolidate.
*/

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

/* Conversion from malloc headers to user pointers, and back.  When
   using memory tagging the user data and the malloc data structure
   headers have distinct tags.  Converting fully from one to the other
   involves extracting the tag at the other address and creating a
   suitable pointer using it.  That can be quite expensive.  There are
   cases when the pointers are not dereferenced (for example only used
   for alignment check) so the tags are not relevant, and there are
   cases when user data is not tagged distinctly from malloc headers
   (user data is untagged because tagging is done late in malloc and
   early in free).  User memory tagging across internal interfaces:

      sysmalloc: Returns untagged memory.
      _int_malloc: Returns untagged memory.
      _int_free: Takes untagged memory.
      _int_memalign: Returns untagged memory.
      _int_memalign: Returns untagged memory.
      _mid_memalign: Returns tagged memory.
      _int_realloc: Takes and returns tagged memory.
*/

/* The chunk header is two SIZE_SZ elements, but this is used widely, so
   we define it here for clarity later.  */
#define CHUNK_HDR_SZ (2 * SIZE_SZ)

/* Convert a chunk address to a user mem pointer without correcting
   the tag.  */
#define chunk2mem(p) ((void*)((char*)(p) + CHUNK_HDR_SZ))

/* Convert a chunk address to a user mem pointer and extract the right tag.  */
#define chunk2mem_tag(p) ((void*)tag_at ((char*)(p) + CHUNK_HDR_SZ))

/* Convert a user mem pointer to a chunk address and extract the right tag.  */
#define mem2chunk(mem) ((mchunkptr)tag_at (((char*)(mem) - CHUNK_HDR_SZ)))

/* The smallest possible chunk */
#define MIN_CHUNK_SIZE        (offsetof(struct malloc_chunk, fd_nextsize))

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

#define MINSIZE  \
  (unsigned long)(((MIN_CHUNK_SIZE+MALLOC_ALIGN_MASK) & ~MALLOC_ALIGN_MASK))

/* Check if m has acceptable alignment */

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

#define misaligned_chunk(p) \
  ((uintptr_t)(MALLOC_ALIGNMENT == CHUNK_HDR_SZ ? (p) : chunk2mem (p)) \
   & MALLOC_ALIGN_MASK)

/* pad request bytes into a usable size -- internal version */
/* Note: This must be a macro that evaluates to a compile time constant
   if passed a literal constant.  */
#define request2size(req)                                         \
  (((req) + SIZE_SZ + MALLOC_ALIGN_MASK < MINSIZE)  ?             \
   MINSIZE :                                                      \
   ((req) + SIZE_SZ + MALLOC_ALIGN_MASK) & ~MALLOC_ALIGN_MASK)

/* Check if REQ overflows when padded and aligned and if the resulting
   value is less than PTRDIFF_T.  Returns the requested size or
   MINSIZE in case the value is less than MINSIZE, or 0 if any of the
   previous checks fail.  */
static inline size_t
checked_request2size (size_t req) __nonnull (1)
{
  if (__glibc_unlikely (req > PTRDIFF_MAX))
    return 0;

  /* When using tagged memory, we cannot share the end of the user
     block with the header for the next chunk, so ensure that we
     allocate blocks that are rounded up to the granule size.  Take
     care not to overflow from close to MAX_SIZE_T to a small
     number.  Ideally, this would be part of request2size(), but that
     must be a macro that produces a compile time constant if passed
     a constant literal.  */
  if (__glibc_unlikely (mtag_enabled))
    {
      /* Ensure this is not evaluated if !mtag_enabled, see gcc PR 99551.  */
      asm ("");

      req = (req + (__MTAG_GRANULE_SIZE - 1)) &
	    ~(size_t)(__MTAG_GRANULE_SIZE - 1);
    }

  return 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)->mchunk_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)->mchunk_size & IS_MMAPPED)


/* size field is or'ed with NON_MAIN_ARENA if the chunk was obtained
   from a non-main arena.  This is only set immediately before handing
   the chunk to the user, if necessary.  */
#define NON_MAIN_ARENA 0x4

/* Check for chunk from main arena.  */
#define chunk_main_arena(p) (((p)->mchunk_size & NON_MAIN_ARENA) == 0)

/* Mark a chunk as not being on the main arena.  */
#define set_non_main_arena(p) ((p)->mchunk_size |= NON_MAIN_ARENA)


/*
   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 | NON_MAIN_ARENA)

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

/* Like chunksize, but do not mask SIZE_BITS.  */
#define chunksize_nomask(p)         ((p)->mchunk_size)

/* Ptr to next physical malloc_chunk. */
#define next_chunk(p) ((mchunkptr) (((char *) (p)) + chunksize (p)))

/* Size of the chunk below P.  Only valid if !prev_inuse (P).  */
#define prev_size(p) ((p)->mchunk_prev_size)

/* Set the size of the chunk below P.  Only valid if !prev_inuse (P).  */
#define set_prev_size(p, sz) ((p)->mchunk_prev_size = (sz))

/* Ptr to previous physical malloc_chunk.  Only valid if !prev_inuse (P).  */
#define prev_chunk(p) ((mchunkptr) (((char *) (p)) - prev_size (p)))

/* 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)) + chunksize (p)))->mchunk_size) & PREV_INUSE)

/* set/clear chunk as being inuse without otherwise disturbing */
#define set_inuse(p)							      \
  ((mchunkptr) (((char *) (p)) + chunksize (p)))->mchunk_size |= PREV_INUSE

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


/* check/set/clear inuse bits in known places */
#define inuse_bit_at_offset(p, s)					      \
  (((mchunkptr) (((char *) (p)) + (s)))->mchunk_size & PREV_INUSE)

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

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


/* Set size at head, without disturbing its use bit */
#define set_head_size(p, s)  ((p)->mchunk_size = (((p)->mchunk_size & SIZE_BITS) | (s)))

/* Set size/use field */
#define set_head(p, s)       ((p)->mchunk_size = (s))

/* Set size at footer (only when chunk is not in use) */
#define set_foot(p, s)       (((mchunkptr) ((char *) (p) + (s)))->mchunk_prev_size = (s))

#pragma GCC poison mchunk_size
#pragma GCC poison mchunk_prev_size

/* This is the size of the real usable data in the chunk.  Not valid for
   dumped heap chunks.  */
#define memsize(p)                                                    \
  (__MTAG_GRANULE_SIZE > SIZE_SZ && __glibc_unlikely (mtag_enabled) ? \
    chunksize (p) - CHUNK_HDR_SZ :                                    \
    chunksize (p) - CHUNK_HDR_SZ + (chunk_is_mmapped (p) ? 0 : SIZE_SZ))

/* If memory tagging is enabled the layout changes to accommodate the granule
   size, this is wasteful for small allocations so not done by default.
   Both the chunk header and user data has to be granule aligned.  */
_Static_assert (__MTAG_GRANULE_SIZE <= CHUNK_HDR_SZ,
		"memory tagging is not supported with large granule.");

static __always_inline void *
tag_new_usable (void *ptr)
{
  if (__glibc_unlikely (mtag_enabled) && ptr)
    {
      mchunkptr cp = mem2chunk(ptr);
      ptr = __libc_mtag_tag_region (__libc_mtag_new_tag (ptr), memsize (cp));
    }
  return ptr;
}

/*
   -------------------- 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 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) * 2]))			      \
             - offsetof (struct malloc_chunk, fd))

/* 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)

/*
   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

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

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

    Bin 0 does not exist.  Bin 1 is the unordered list; if that would be
    a valid chunk size the small bins are bumped up one.
 */

#define NBINS             128
#define NSMALLBINS         64
#define SMALLBIN_WIDTH    MALLOC_ALIGNMENT
#define SMALLBIN_CORRECTION (MALLOC_ALIGNMENT > CHUNK_HDR_SZ)
#define MIN_LARGE_SIZE    ((NSMALLBINS - SMALLBIN_CORRECTION) * SMALLBIN_WIDTH)

#define in_smallbin_range(sz)  \
  ((unsigned long) (sz) < (unsigned long) MIN_LARGE_SIZE)

#define smallbin_index(sz) \
  ((SMALLBIN_WIDTH == 16 ? (((unsigned) (sz)) >> 4) : (((unsigned) (sz)) >> 3))\
   + SMALLBIN_CORRECTION)

#define largebin_index_32(sz)                                                \
  (((((unsigned long) (sz)) >> 6) <= 38) ?  56 + (((unsigned long) (sz)) >> 6) :\
   ((((unsigned long) (sz)) >> 9) <= 20) ?  91 + (((unsigned long) (sz)) >> 9) :\
   ((((unsigned long) (sz)) >> 12) <= 10) ? 110 + (((unsigned long) (sz)) >> 12) :\
   ((((unsigned long) (sz)) >> 15) <= 4) ? 119 + (((unsigned long) (sz)) >> 15) :\
   ((((unsigned long) (sz)) >> 18) <= 2) ? 124 + (((unsigned long) (sz)) >> 18) :\
   126)

#define largebin_index_32_big(sz)                                            \
  (((((unsigned long) (sz)) >> 6) <= 45) ?  49 + (((unsigned long) (sz)) >> 6) :\
   ((((unsigned long) (sz)) >> 9) <= 20) ?  91 + (((unsigned long) (sz)) >> 9) :\
   ((((unsigned long) (sz)) >> 12) <= 10) ? 110 + (((unsigned long) (sz)) >> 12) :\
   ((((unsigned long) (sz)) >> 15) <= 4) ? 119 + (((unsigned long) (sz)) >> 15) :\
   ((((unsigned long) (sz)) >> 18) <= 2) ? 124 + (((unsigned long) (sz)) >> 18) :\
   126)

// XXX It remains to be seen whether it is good to keep the widths of
// XXX the buckets the same or whether it should be scaled by a factor
// XXX of two as well.
#define largebin_index_64(sz)                                                \
  (((((unsigned long) (sz)) >> 6) <= 48) ?  48 + (((unsigned long) (sz)) >> 6) :\
   ((((unsigned long) (sz)) >> 9) <= 20) ?  91 + (((unsigned long) (sz)) >> 9) :\
   ((((unsigned long) (sz)) >> 12) <= 10) ? 110 + (((unsigned long) (sz)) >> 12) :\
   ((((unsigned long) (sz)) >> 15) <= 4) ? 119 + (((unsigned long) (sz)) >> 15) :\
   ((((unsigned long) (sz)) >> 18) <= 2) ? 124 + (((unsigned long) (sz)) >> 18) :\
   126)

#define largebin_index(sz) \
  (SIZE_SZ == 8 ? largebin_index_64 (sz)                                     \
   : MALLOC_ALIGNMENT == 16 ? largebin_index_32_big (sz)                     \
   : largebin_index_32 (sz))

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

/* Take a chunk off a bin list.  */
static void
unlink_chunk (mstate av, mchunkptr p)
{
  if (chunksize (p) != prev_size (next_chunk (p)))
    malloc_printerr ("corrupted size vs. prev_size");

  mchunkptr fd = p->fd;
  mchunkptr bk = p->bk;

  if (__builtin_expect (fd->bk != p || bk->fd != p, 0))
    malloc_printerr ("corrupted double-linked list");

  fd->bk = bk;
  bk->fd = fd;
  if (!in_smallbin_range (chunksize_nomask (p)) && p->fd_nextsize != NULL)
    {
      if (p->fd_nextsize->bk_nextsize != p
	  || p->bk_nextsize->fd_nextsize != p)
	malloc_printerr ("corrupted double-linked list (not small)");

      if (fd->fd_nextsize == NULL)
	{
	  if (p->fd_nextsize == p)
	    fd->fd_nextsize = fd->bk_nextsize = fd;
	  else
	    {
	      fd->fd_nextsize = p->fd_nextsize;
	      fd->bk_nextsize = p->bk_nextsize;
	      p->fd_nextsize->bk_nextsize = fd;
	      p->bk_nextsize->fd_nextsize = fd;
	    }
	}
      else
	{
	  p->fd_nextsize->bk_nextsize = p->bk_nextsize;
	  p->bk_nextsize->fd_nextsize = p->fd_nextsize;
	}
    }
}

/*
   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 NON_MAIN_ARENA flag is never set for unsorted chunks, so it
    does not have to be taken into account in size comparisons.
 */

/* 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;
#define fastbin(ar_ptr, idx) ((ar_ptr)->fastbinsY[idx])

/* offset 2 to use otherwise unindexable first 2 bins */
#define fastbin_index(sz) \
  ((((unsigned int) (sz)) >> (SIZE_SZ == 8 ? 4 : 3)) - 2)


/* The maximum fastbin request size we support */
#define MAX_FAST_SIZE     (80 * SIZE_SZ / 4)

#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 large chunks even
   if trimming is not used.
 */

#define FASTBIN_CONSOLIDATION_THRESHOLD  (65536UL)

/*
   NONCONTIGUOUS_BIT indicates that MORECORE does not return contiguous
   regions.  Otherwise, contiguity is exploited in merging together,
   when possible, results from consecutive MORECORE calls.

   The initial value comes from MORECORE_CONTIGUOUS, but is
   changed dynamically if mmap is ever used as an sbrk substitute.
 */

#define NONCONTIGUOUS_BIT     (2U)

#define contiguous(M)          (((M)->flags & NONCONTIGUOUS_BIT) == 0)
#define noncontiguous(M)       (((M)->flags & NONCONTIGUOUS_BIT) != 0)
#define set_noncontiguous(M)   ((M)->flags |= NONCONTIGUOUS_BIT)
#define set_contiguous(M)      ((M)->flags &= ~NONCONTIGUOUS_BIT)

/* Maximum size of memory handled in fastbins.  */
static uint8_t global_max_fast;

/*
   Set value of max_fast.
   Use impossibly small value if 0.
   Precondition: there are no existing fastbin chunks in the main arena.
   Since do_check_malloc_state () checks this, we call malloc_consolidate ()
   before changing max_fast.  Note other arenas will leak their fast bin
   entries if max_fast is reduced.
 */

#define set_max_fast(s) \
  global_max_fast = (((size_t) (s) <= MALLOC_ALIGN_MASK - SIZE_SZ)	\
                     ? MIN_CHUNK_SIZE / 2 : ((s + SIZE_SZ) & ~MALLOC_ALIGN_MASK))

static inline INTERNAL_SIZE_T
get_max_fast (void)
{
  /* Tell the GCC optimizers that global_max_fast is never larger
     than MAX_FAST_SIZE.  This avoids out-of-bounds array accesses in
     _int_malloc after constant propagation of the size parameter.
     (The code never executes because malloc preserves the
     global_max_fast invariant, but the optimizers may not recognize
     this.)  */
  if (global_max_fast > MAX_FAST_SIZE)
    __builtin_unreachable ();
  return global_max_fast;
}

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

/*
   have_fastchunks indicates that there are probably some fastbin chunks.
   It is set true on entering a chunk into any fastbin, and cleared early in
   malloc_consolidate.  The value is approximate since it may be set when there
   are no fastbin chunks, or it may be clear even if there are fastbin chunks
   available.  Given it's sole purpose is to reduce number of redundant calls to
   malloc_consolidate, it does not affect correctness.  As a result we can safely
   use relaxed atomic accesses.
 */


struct malloc_state
{
  /* Serialize access.  */
  __libc_lock_define (, mutex);

  /* Flags (formerly in max_fast).  */
  int flags;

  /* Set if the fastbin chunks contain recently inserted free blocks.  */
  /* Note this is a bool but not all targets support atomics on booleans.  */
  int have_fastchunks;

  /* Fastbins */
  mfastbinptr fastbinsY[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 - 2];

  /* Bitmap of bins */
  unsigned int binmap[BINMAPSIZE];

  /* Linked list */
  struct malloc_state *next;

  /* Linked list for free arenas.  Access to this field is serialized
     by free_list_lock in arena.c.  */
  struct malloc_state *next_free;

  /* Number of threads attached to this arena.  0 if the arena is on
     the free list.  Access to this field is serialized by
     free_list_lock in arena.c.  */
  INTERNAL_SIZE_T attached_threads;

  /* Memory allocated from the system in this arena.  */
  INTERNAL_SIZE_T system_mem;
  INTERNAL_SIZE_T max_system_mem;
};

struct malloc_par
{
  /* Tunable parameters */
  unsigned long trim_threshold;
  INTERNAL_SIZE_T top_pad;
  INTERNAL_SIZE_T mmap_threshold;
  INTERNAL_SIZE_T arena_test;
  INTERNAL_SIZE_T arena_max;

#if HAVE_TUNABLES
  /* Transparent Large Page support.  */
  INTERNAL_SIZE_T thp_pagesize;
  /* A value different than 0 means to align mmap allocation to hp_pagesize
     add hp_flags on flags.  */
  INTERNAL_SIZE_T hp_pagesize;
  int hp_flags;
#endif

  /* Memory map support */
  int n_mmaps;
  int n_mmaps_max;
  int max_n_mmaps;
  /* the mmap_threshold is dynamic, until the user sets
     it manually, at which point we need to disable any
     dynamic behavior. */
  int no_dyn_threshold;

  /* Statistics */
  INTERNAL_SIZE_T mmapped_mem;
  INTERNAL_SIZE_T max_mmapped_mem;

  /* First address handed out by MORECORE/sbrk.  */
  char *sbrk_base;

#if USE_TCACHE
  /* Maximum number of buckets to use.  */
  size_t tcache_bins;
  size_t tcache_max_bytes;
  /* Maximum number of chunks in each bucket.  */
  size_t tcache_count;
  /* Maximum number of chunks to remove from the unsorted list, which
     aren't used to prefill the cache.  */
  size_t tcache_unsorted_limit;
#endif
};

/* There are several instances of this struct ("arenas") in this
   malloc.  If you are adapting this malloc in a way that does NOT use
   a static or mmapped 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 main_arena =
{
  .mutex = _LIBC_LOCK_INITIALIZER,
  .next = &main_arena,
  .attached_threads = 1
};

/* There is only one instance of the malloc parameters.  */

static struct malloc_par mp_ =
{
  .top_pad = DEFAULT_TOP_PAD,
  .n_mmaps_max = DEFAULT_MMAP_MAX,
  .mmap_threshold = DEFAULT_MMAP_THRESHOLD,
  .trim_threshold = DEFAULT_TRIM_THRESHOLD,
#define NARENAS_FROM_NCORES(n) ((n) * (sizeof (long) == 4 ? 2 : 8))
  .arena_test = NARENAS_FROM_NCORES (1)
#if USE_TCACHE
  ,
  .tcache_count = TCACHE_FILL_COUNT,
  .tcache_bins = TCACHE_MAX_BINS,
  .tcache_max_bytes = tidx2usize (TCACHE_MAX_BINS-1),
  .tcache_unsorted_limit = 0 /* No limit.  */
#endif
};

/*
   Initialize a malloc_state struct.

   This is called from ptmalloc_init () or from _int_new_arena ()
   when creating a new arena.
 */

static void
malloc_init_state (mstate av)
{
  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;
    }

#if MORECORE_CONTIGUOUS
  if (av != &main_arena)
#endif
  set_noncontiguous (av);
  if (av == &main_arena)
    set_max_fast (DEFAULT_MXFAST);
  atomic_store_relaxed (&av->have_fastchunks, false);

  av->top = initial_top (av);
}

/*
   Other internal utilities operating on mstates
 */

static void *sysmalloc (INTERNAL_SIZE_T, mstate);
static int      systrim (size_t, mstate);
static void     malloc_consolidate (mstate);


/* -------------- Early definitions for debugging hooks ---------------- */

/* This function is called from the arena shutdown hook, to free the
   thread cache (if it exists).  */
static void tcache_thread_shutdown (void);

/* ------------------ Testing support ----------------------------------*/

static int perturb_byte;

static void
alloc_perturb (char *p, size_t n)
{
  if (__glibc_unlikely (perturb_byte))
    memset (p, perturb_byte ^ 0xff, n);
}

static void
free_perturb (char *p, size_t n)
{
  if (__glibc_unlikely (perturb_byte))
    memset (p, perturb_byte, n);
}



#include <stap-probe.h>

/* ----------- Routines dealing with transparent huge pages ----------- */

static inline void
madvise_thp (void *p, INTERNAL_SIZE_T size)
{
#if HAVE_TUNABLES && defined (MADV_HUGEPAGE)
  /* Do not consider areas smaller than a huge page or if the tunable is
     not active.  */
  if (mp_.thp_pagesize == 0 || size < mp_.thp_pagesize)
    return;

  /* Linux requires the input address to be page-aligned, and unaligned
     inputs happens only for initial data segment.  */
  if (__glibc_unlikely (!PTR_IS_ALIGNED (p, GLRO (dl_pagesize))))
    {
      void *q = PTR_ALIGN_DOWN (p, GLRO (dl_pagesize));
      size += PTR_DIFF (p, q);
      p = q;
    }

  __madvise (p, size, MADV_HUGEPAGE);
#endif
}

/* ------------------- Support for multiple arenas -------------------- */
#include "arena.c"

/*
   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 !MALLOC_DEBUG

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

#else

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

/*
   Properties of all chunks
 */

static void
do_check_chunk (mstate av, mchunkptr p)
{
  unsigned long 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->system_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 ((unsigned long) (sz) >= MINSIZE);
          /* top predecessor always marked inuse */
          assert (prev_inuse (p));
        }
    }
  else
    {
      /* 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 (((prev_size (p) + sz) & (GLRO (dl_pagesize) - 1)) == 0);
      /* mem is aligned */
      assert (aligned_OK (chunk2mem (p)));
    }
}

/*
   Properties of free chunks
 */

static void
do_check_free_chunk (mstate av, mchunkptr p)
{
  INTERNAL_SIZE_T sz = chunksize_nomask (p) & ~(PREV_INUSE | NON_MAIN_ARENA);
  mchunkptr next = chunk_at_offset (p, sz);

  do_check_chunk (av, p);

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

  /* Unless a special marker, must have OK fields */
  if ((unsigned long) (sz) >= MINSIZE)
    {
      assert ((sz & MALLOC_ALIGN_MASK) == 0);
      assert (aligned_OK (chunk2mem (p)));
      /* ... matching footer field */
      assert (prev_size (next_chunk (p)) == 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
 */

static void
do_check_inuse_chunk (mstate av, mchunkptr p)
{
  mchunkptr next;

  do_check_chunk (av, 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 (av, prv);
    }

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

/*
   Properties of chunks recycled from fastbins
 */

static void
do_check_remalloced_chunk (mstate av, mchunkptr p, INTERNAL_SIZE_T s)
{
  INTERNAL_SIZE_T sz = chunksize_nomask (p) & ~(PREV_INUSE | NON_MAIN_ARENA);

  if (!chunk_is_mmapped (p))
    {
      assert (av == arena_for_chunk (p));
      if (chunk_main_arena (p))
        assert (av == &main_arena);
      else
        assert (av != &main_arena);
    }

  do_check_inuse_chunk (av, p);

  /* Legal size ... */
  assert ((sz & MALLOC_ALIGN_MASK) == 0);
  assert ((unsigned long) (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
 */

static void
do_check_malloced_chunk (mstate av, mchunkptr p, INTERNAL_SIZE_T s)
{
  /* same as recycled case ... */
  do_check_remalloced_chunk (av, 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 `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)
{
  int i;
  mchunkptr p;
  mchunkptr q;
  mbinptr b;
  unsigned int idx;
  INTERNAL_SIZE_T size;
  unsigned long 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);

  /* Check the arena is initialized. */
  assert (av->top != 0);

  /* No memory has been allocated yet, so doing more tests is not possible.  */
  if (av->top == initial_top (av))
    return;

  /* pagesize is a power of 2 */
  assert (powerof2(GLRO (dl_pagesize)));

  /* A contiguous main_arena is consistent with sbrk_base.  */
  if (av == &main_arena && contiguous (av))
    assert ((char *) mp_.sbrk_base + av->system_mem ==
            (char *) av->top + chunksize (av->top));

  /* properties of fastbins */

  /* max_fast is in allowed range */
  assert ((get_max_fast () & ~1) <= request2size (MAX_FAST_SIZE));

  max_fast_bin = fastbin_index (get_max_fast ());

  for (i = 0; i < NFASTBINS; ++i)
    {
      p = fastbin (av, i);

      /* The following test can only be performed for the main arena.
         While mallopt calls malloc_consolidate to get rid of all fast
         bins (especially those larger than the new maximum) this does
         only happen for the main arena.  Trying to do this for any
         other arena would mean those arenas have to be locked and
         malloc_consolidate be called for them.  This is excessive.  And
         even if this is acceptable to somebody it still cannot solve
         the problem completely since if the arena is locked a
         concurrent malloc call might create a new arena which then
         could use the newly invalid fast bins.  */

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

      while (p != 0)
        {
	  if (__glibc_unlikely (misaligned_chunk (p)))
	    malloc_printerr ("do_check_malloc_state(): "
			     "unaligned fastbin chunk detected");
          /* each chunk claims to be inuse */
          do_check_inuse_chunk (av, p);
          total += chunksize (p);
          /* chunk belongs in this bin */
          assert (fastbin_index (chunksize (p)) == i);
	  p = REVEAL_PTR (p->fd);
        }
    }

  /* 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)
        {
          unsigned int binbit = get_binmap (av, i);
          int 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 (av, p);
          size = chunksize (p);
          total += size;
          if (i >= 2)
            {
              /* chunk belongs in bin */
              idx = bin_index (size);
              assert (idx == i);
              /* lists are sorted */
              assert (p->bk == b ||
                      (unsigned long) chunksize (p->bk) >= (unsigned long) chunksize (p));

              if (!in_smallbin_range (size))
                {
                  if (p->fd_nextsize != NULL)
                    {
                      if (p->fd_nextsize == p)
                        assert (p->bk_nextsize == p);
                      else
                        {
                          if (p->fd_nextsize == first (b))
                            assert (chunksize (p) < chunksize (p->fd_nextsize));
                          else
                            assert (chunksize (p) > chunksize (p->fd_nextsize));

                          if (p == first (b))
                            assert (chunksize (p) > chunksize (p->bk_nextsize));
                          else
                            assert (chunksize (p) < chunksize (p->bk_nextsize));
                        }
                    }
                  else
                    assert (p->bk_nextsize == NULL);
                }
            }
          else if (!in_smallbin_range (size))
            assert (p->fd_nextsize == NULL && p->bk_nextsize == NULL);
          /* chunk is followed by a legal chain of inuse chunks */
          for (q = next_chunk (p);
               (q != av->top && inuse (q) &&
                (unsigned long) (chunksize (q)) >= MINSIZE);
               q = next_chunk (q))
            do_check_inuse_chunk (av, q);
        }
    }

  /* top chunk is OK */
  check_chunk (av, av->top);
}
#endif


/* ----------------- Support for debugging hooks -------------------- */
#if IS_IN (libc)
#include "hooks.c"
#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.
 */

static void *
sysmalloc_mmap (INTERNAL_SIZE_T nb, size_t pagesize, int extra_flags, mstate av)
{
  long int size;

  /*
    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.

    See the front_misalign handling below, for glibc there is no need for
    further alignments unless we have have high alignment.
   */
  if (MALLOC_ALIGNMENT == CHUNK_HDR_SZ)
    size = ALIGN_UP (nb + SIZE_SZ, pagesize);
  else
    size = ALIGN_UP (nb + SIZE_SZ + MALLOC_ALIGN_MASK, pagesize);

  /* Don't try if size wraps around 0.  */
  if ((unsigned long) (size) <= (unsigned long) (nb))
    return MAP_FAILED;

  char *mm = (char *) MMAP (0, size,
			    mtag_mmap_flags | PROT_READ | PROT_WRITE,
			    extra_flags);
  if (mm == MAP_FAILED)
    return mm;

#ifdef MAP_HUGETLB
  if (!(extra_flags & MAP_HUGETLB))
    madvise_thp (mm, size);
#endif

  /*
    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().
   */

  INTERNAL_SIZE_T front_misalign; /* unusable bytes at front of new space */

  if (MALLOC_ALIGNMENT == CHUNK_HDR_SZ)
    {
      /* For glibc, chunk2mem increases the address by CHUNK_HDR_SZ and
	 MALLOC_ALIGN_MASK is CHUNK_HDR_SZ-1.  Each mmap'ed area is page
	 aligned and therefore definitely MALLOC_ALIGN_MASK-aligned.  */
      assert (((INTERNAL_SIZE_T) chunk2mem (mm) & MALLOC_ALIGN_MASK) == 0);
      front_misalign = 0;
    }
  else
    front_misalign = (INTERNAL_SIZE_T) chunk2mem (mm) & MALLOC_ALIGN_MASK;

  mchunkptr p;                    /* the allocated/returned chunk */

  if (front_misalign > 0)
    {
      ptrdiff_t correction = MALLOC_ALIGNMENT - front_misalign;
      p = (mchunkptr) (mm + correction);
      set_prev_size (p, correction);
      set_head (p, (size - correction) | IS_MMAPPED);
    }
  else
    {
      p = (mchunkptr) mm;
      set_prev_size (p, 0);
      set_head (p, size | IS_MMAPPED);
    }

  /* update statistics */
  int new = atomic_fetch_add_relaxed (&mp_.n_mmaps, 1) + 1;
  atomic_max (&mp_.max_n_mmaps, new);

  unsigned long sum;
  sum = atomic_fetch_add_relaxed (&mp_.mmapped_mem, size) + size;
  atomic_max (&mp_.max_mmapped_mem, sum);

  check_chunk (av, p);

  return chunk2mem (p);
}

/*
   Allocate memory using mmap() based on S and NB requested size, aligning to
   PAGESIZE if required.  The EXTRA_FLAGS is used on mmap() call.  If the call
   succeedes S is updated with the allocated size.  This is used as a fallback
   if MORECORE fails.
 */
static void *
sysmalloc_mmap_fallback (long int *s, INTERNAL_SIZE_T nb,
			 INTERNAL_SIZE_T old_size, size_t minsize,
			 size_t pagesize, int extra_flags, mstate av)
{
  long int size = *s;

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

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

  /* Don't try if size wraps around 0 */
  if ((unsigned long) (size) <= (unsigned long) (nb))
    return MORECORE_FAILURE;

  char *mbrk = (char *) (MMAP (0, size,
			       mtag_mmap_flags | PROT_READ | PROT_WRITE,
			       extra_flags));
  if (mbrk == MAP_FAILED)
    return MAP_FAILED;

#ifdef MAP_HUGETLB
  if (!(extra_flags & MAP_HUGETLB))
    madvise_thp (mbrk, size);
#endif

  /* 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);

  *s = size;
  return mbrk;
}

static void *
sysmalloc (INTERNAL_SIZE_T nb, mstate av)
{
  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 */
  unsigned long remainder_size;   /* its size */


  size_t pagesize = GLRO (dl_pagesize);
  bool tried_mmap = false;


  /*
     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 (av == NULL
      || ((unsigned long) (nb) >= (unsigned long) (mp_.mmap_threshold)
	  && (mp_.n_mmaps < mp_.n_mmaps_max)))
    {
      char *mm;
#if HAVE_TUNABLES
      if (mp_.hp_pagesize > 0 && nb >= mp_.hp_pagesize)
	{
	  /* There is no need to isse the THP madvise call if Huge Pages are
	     used directly.  */
	  mm = sysmalloc_mmap (nb, mp_.hp_pagesize, mp_.hp_flags, av);
	  if (mm != MAP_FAILED)
	    return mm;
	}
#endif
      mm = sysmalloc_mmap (nb, pagesize, 0, av);
      if (mm != MAP_FAILED)
	return mm;
      tried_mmap = true;
    }

  /* There are no usable arenas and mmap also failed.  */
  if (av == NULL)
    return 0;

  /* 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) ||
          ((unsigned long) (old_size) >= MINSIZE &&
           prev_inuse (old_top) &&
           ((unsigned long) old_end & (pagesize - 1)) == 0));

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


  if (av != &main_arena)
    {
      heap_info *old_heap, *heap;
      size_t old_heap_size;

      /* First try to extend the current heap. */
      old_heap = heap_for_ptr (old_top);
      old_heap_size = old_heap->size;
      if ((long) (MINSIZE + nb - old_size) > 0
          && grow_heap (old_heap, MINSIZE + nb - old_size) == 0)
        {
          av->system_mem += old_heap->size - old_heap_size;
          set_head (old_top, (((char *) old_heap + old_heap->size) - (char *) old_top)
                    | PREV_INUSE);
        }
      else if ((heap = new_heap (nb + (MINSIZE + sizeof (*heap)), mp_.top_pad)))
        {
          /* Use a newly allocated heap.  */
          heap->ar_ptr = av;
          heap->prev = old_heap;
          av->system_mem += heap->size;
          /* Set up the new top.  */
          top (av) = chunk_at_offset (heap, sizeof (*heap));
          set_head (top (av), (heap->size - sizeof (*heap)) | PREV_INUSE);

          /* Setup fencepost and free the old top chunk with a multiple of
             MALLOC_ALIGNMENT in size. */
          /* The fencepost takes at least MINSIZE bytes, because it might
             become the top chunk again later.  Note that a footer is set
             up, too, although the chunk is marked in use. */
          old_size = (old_size - MINSIZE) & ~MALLOC_ALIGN_MASK;
          set_head (chunk_at_offset (old_top, old_size + CHUNK_HDR_SZ),
		    0 | PREV_INUSE);
          if (old_size >= MINSIZE)
            {
              set_head (chunk_at_offset (old_top, old_size),
			CHUNK_HDR_SZ | PREV_INUSE);
              set_foot (chunk_at_offset (old_top, old_size), CHUNK_HDR_SZ);
              set_head (old_top, old_size | PREV_INUSE | NON_MAIN_ARENA);
              _int_free (av, old_top, 1);
            }
          else
            {
              set_head (old_top, (old_size + CHUNK_HDR_SZ) | PREV_INUSE);
              set_foot (old_top, (old_size + CHUNK_HDR_SZ));
            }
        }
      else if (!tried_mmap)
	{
	  /* We can at least try to use to mmap memory.  If new_heap fails
	     it is unlikely that trying to allocate huge pages will
	     succeed.  */
	  char *mm = sysmalloc_mmap (nb, pagesize, 0, av);
	  if (mm != MAP_FAILED)
	    return mm;
	}
    }
  else     /* av == main_arena */


    { /* Request enough space for nb + pad + overhead */
      size = nb + mp_.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 or huge 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.
       */

#if HAVE_TUNABLES && defined (MADV_HUGEPAGE)
      /* Defined in brk.c.  */
      extern void *__curbrk;
      if (__glibc_unlikely (mp_.thp_pagesize != 0))
	{
	  uintptr_t top = ALIGN_UP ((uintptr_t) __curbrk + size,
				    mp_.thp_pagesize);
	  size = top - (uintptr_t) __curbrk;
	}
      else
#endif
	size = ALIGN_UP (size, GLRO(dl_pagesize));

      /*
         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 (brk != (char *) (MORECORE_FAILURE))
	    madvise_thp (brk, size);
          LIBC_PROBE (memory_sbrk_more, 2, brk, size);
        }

      if (brk == (char *) (MORECORE_FAILURE))
        {
          /*
             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.
           */

	  char *mbrk = MAP_FAILED;
#if HAVE_TUNABLES
	  if (mp_.hp_pagesize > 0)
	    mbrk = sysmalloc_mmap_fallback (&size, nb, old_size,
					    mp_.hp_pagesize, mp_.hp_pagesize,
					    mp_.hp_flags, av);
#endif
	  if (mbrk == MAP_FAILED)
	    mbrk = sysmalloc_mmap_fallback (&size, nb, old_size, pagesize,
					    MMAP_AS_MORECORE_SIZE, 0, av);
	  if (mbrk != MAP_FAILED)
	    {
	      /* We do not need, and cannot use, another sbrk call to find end */
	      brk = mbrk;
	      snd_brk = brk + size;
	    }
        }

      if (brk != (char *) (MORECORE_FAILURE))
        {
          if (mp_.sbrk_base == 0)
            mp_.sbrk_base = brk;
          av->system_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);

          else if (contiguous (av) && old_size && brk < old_end)
	    /* Oops!  Someone else killed our space..  Can't touch anything.  */
	    malloc_printerr ("break adjusted to free malloc space");

          /*
             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;

              /* handle contiguous cases */
              if (contiguous (av))
                {
                  /* Count foreign sbrk as system_mem.  */
                  if (old_size)
                    av->system_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 += (ALIGN_UP (end_misalign, pagesize)) - end_misalign;

                  assert (correction >= 0);
                  snd_brk = (char *) (MORECORE (correction));

                  /*
                     If can't allocate correction, try to at least find out current
                     brk.  It might be enough to proceed without failing.

                     Note that if second sbrk did NOT fail, we assume that space
                     is contiguous with first sbrk. This is a safe assumption unless
                     program is multithreaded but doesn't use locks and a foreign sbrk
                     occurred between our first and second calls.
                   */

                  if (snd_brk == (char *) (MORECORE_FAILURE))
                    {
                      correction = 0;
                      snd_brk = (char *) (MORECORE (0));
                    }
		  else
		    madvise_thp (snd_brk, correction);
                }

              /* handle non-contiguous cases */
              else
                {
                  if (MALLOC_ALIGNMENT == CHUNK_HDR_SZ)
                    /* MORECORE/mmap must correctly align */
                    assert (((unsigned long) chunk2mem (brk) & MALLOC_ALIGN_MASK) == 0);
                  else
                    {
                      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.
                           */

                          aligned_brk += MALLOC_ALIGNMENT - front_misalign;
                        }
                    }

                  /* Find out current end of memory */
                  if (snd_brk == (char *) (MORECORE_FAILURE))
                    {
                      snd_brk = (char *) (MORECORE (0));
                    }
                }

              /* 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->system_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 - 2 * CHUNK_HDR_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.
                       */
		      set_head (chunk_at_offset (old_top, old_size),
				CHUNK_HDR_SZ | PREV_INUSE);
		      set_head (chunk_at_offset (old_top,
						 old_size + CHUNK_HDR_SZ),
				CHUNK_HDR_SZ | PREV_INUSE);

                      /* If possible, release the rest. */
                      if (old_size >= MINSIZE)
                        {
                          _int_free (av, old_top, 1);
                        }
                    }
                }
            }
        }
    } /* if (av !=  &main_arena) */

  if ((unsigned long) av->system_mem > (unsigned long) (av->max_system_mem))
    av->max_system_mem = av->system_mem;
  check_malloc_state (av);

  /* finally, do the allocation */
  p = av->top;
  size = chunksize (p);

  /* check that one of the above allocation paths succeeded */
  if ((unsigned long) (size) >= (unsigned long) (nb + MINSIZE))
    {
      remainder_size = size - nb;
      remainder = chunk_at_offset (p, nb);
      av->top = remainder;
      set_head (p, nb | PREV_INUSE | (av != &main_arena ? NON_MAIN_ARENA : 0));
      set_head (remainder, remainder_size | PREV_INUSE);
      check_malloced_chunk (av, p, nb);
      return chunk2mem (p);
    }

  /* catch all failure paths */
  __set_errno (ENOMEM);
  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.
 */

static int
systrim (size_t pad, mstate av)
{
  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 */
  long top_area;

  top_size = chunksize (av->top);

  top_area = top_size - MINSIZE - 1;
  if (top_area <= pad)
    return 0;

  /* Release in pagesize units and round down to the nearest page.  */
#if HAVE_TUNABLES && defined (MADV_HUGEPAGE)
  if (__glibc_unlikely (mp_.thp_pagesize != 0))
    extra = ALIGN_DOWN (top_area - pad, mp_.thp_pagesize);
  else
#endif
    extra = ALIGN_DOWN (top_area - pad, GLRO(dl_pagesize));

  if (extra == 0)
    return 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));

      LIBC_PROBE (memory_sbrk_less, 2, new_brk, extra);

      if (new_brk != (char *) MORECORE_FAILURE)
        {
          released = (long) (current_brk - new_brk);

          if (released != 0)
            {
              /* Success. Adjust top. */
              av->system_mem -= released;
              set_head (av->top, (top_size - released) | PREV_INUSE);
              check_malloc_state (av);
              return 1;
            }
        }
    }
  return 0;
}

static void
munmap_chunk (mchunkptr p)
{
  size_t pagesize = GLRO (dl_pagesize);
  INTERNAL_SIZE_T size = chunksize (p);

  assert (chunk_is_mmapped (p));

  uintptr_t mem = (uintptr_t) chunk2mem (p);
  uintptr_t block = (uintptr_t) p - prev_size (p);
  size_t total_size = prev_size (p) + size;
  /* Unfortunately we have to do the compilers job by hand here.  Normally
     we would test BLOCK and TOTAL-SIZE separately for compliance with the
     page size.  But gcc does not recognize the optimization possibility
     (in the moment at least) so we combine the two values into one before
     the bit test.  */
  if (__glibc_unlikely ((block | total_size) & (pagesize - 1)) != 0
      || __glibc_unlikely (!powerof2 (mem & (pagesize - 1))))
    malloc_printerr ("munmap_chunk(): invalid pointer");

  atomic_fetch_add_relaxed (&mp_.n_mmaps, -1);
  atomic_fetch_add_relaxed (&mp_.mmapped_mem, -total_size);

  /* If munmap failed the process virtual memory address space is in a
     bad shape.  Just leave the block hanging around, the process will
     terminate shortly anyway since not much can be done.  */
  __munmap ((char *) block, total_size);
}

#if HAVE_MREMAP

static mchunkptr
mremap_chunk (mchunkptr p, size_t new_size)
{
  size_t pagesize = GLRO (dl_pagesize);
  INTERNAL_SIZE_T offset = prev_size (p);
  INTERNAL_SIZE_T size = chunksize (p);
  char *cp;

  assert (chunk_is_mmapped (p));

  uintptr_t block = (uintptr_t) p - offset;
  uintptr_t mem = (uintptr_t) chunk2mem(p);
  size_t total_size = offset + size;
  if (__glibc_unlikely ((block | total_size) & (pagesize - 1)) != 0
      || __glibc_unlikely (!powerof2 (mem & (pagesize - 1))))
    malloc_printerr("mremap_chunk(): invalid pointer");

  /* Note the extra SIZE_SZ overhead as in mmap_chunk(). */
  new_size = ALIGN_UP (new_size + offset + SIZE_SZ, pagesize);

  /* No need to remap if the number of pages does not change.  */
  if (total_size == new_size)
    return p;

  cp = (char *) __mremap ((char *) block, total_size, new_size,
                          MREMAP_MAYMOVE);

  if (cp == MAP_FAILED)
    return 0;

  madvise_thp (cp, new_size);

  p = (mchunkptr) (cp + offset);

  assert (aligned_OK (chunk2mem (p)));

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

  INTERNAL_SIZE_T new;
  new = atomic_fetch_add_relaxed (&mp_.mmapped_mem, new_size - size - offset)
        + new_size - size - offset;
  atomic_max (&mp_.max_mmapped_mem, new);
  return p;
}
#endif /* HAVE_MREMAP */

/*------------------------ Public wrappers. --------------------------------*/

#if USE_TCACHE

/* We overlay this structure on the user-data portion of a chunk when
   the chunk is stored in the per-thread cache.  */
typedef struct tcache_entry
{
  struct tcache_entry *next;
  /* This field exists to detect double frees.  */
  uintptr_t key;
} tcache_entry;

/* There is one of these for each thread, which contains the
   per-thread cache (hence "tcache_perthread_struct").  Keeping
   overall size low is mildly important.  Note that COUNTS and ENTRIES
   are redundant (we could have just counted the linked list each
   time), this is for performance reasons.  */
typedef struct tcache_perthread_struct
{
  uint16_t counts[TCACHE_MAX_BINS];
  tcache_entry *entries[TCACHE_MAX_BINS];
} tcache_perthread_struct;

static __thread bool tcache_shutting_down = false;
static __thread tcache_perthread_struct *tcache = NULL;

/* Process-wide key to try and catch a double-free in the same thread.  */
static uintptr_t tcache_key;

/* The value of tcache_key does not really have to be a cryptographically
   secure random number.  It only needs to be arbitrary enough so that it does
   not collide with values present in applications.  If a collision does happen
   consistently enough, it could cause a degradation in performance since the
   entire list is checked to check if the block indeed has been freed the
   second time.  The odds of this happening are exceedingly low though, about 1
   in 2^wordsize.  There is probably a higher chance of the performance
   degradation being due to a double free where the first free happened in a
   different thread; that's a case this check does not cover.  */
static void
tcache_key_initialize (void)
{
  if (__getrandom_nocancel (&tcache_key, sizeof(tcache_key), GRND_NONBLOCK)
      != sizeof (tcache_key))
    {
      tcache_key = random_bits ();
#if __WORDSIZE == 64
      tcache_key = (tcache_key << 32) | random_bits ();
#endif
    }
}

/* Caller must ensure that we know tc_idx is valid and there's room
   for more chunks.  */
static __always_inline void
tcache_put (mchunkptr chunk, size_t tc_idx)
{
  tcache_entry *e = (tcache_entry *) chunk2mem (chunk);

  /* Mark this chunk as "in the tcache" so the test in _int_free will
     detect a double free.  */
  e->key = tcache_key;

  e->next = PROTECT_PTR (&e->next, tcache->entries[tc_idx]);
  tcache->entries[tc_idx] = e;
  ++(tcache->counts[tc_idx]);
}

/* Caller must ensure that we know tc_idx is valid and there's
   available chunks to remove.  */
static __always_inline void *
tcache_get (size_t tc_idx)
{
  tcache_entry *e = tcache->entries[tc_idx];
  if (__glibc_unlikely (!aligned_OK (e)))
    malloc_printerr ("malloc(): unaligned tcache chunk detected");
  tcache->entries[tc_idx] = REVEAL_PTR (e->next);
  --(tcache->counts[tc_idx]);
  e->key = 0;
  return (void *) e;
}

static void
tcache_thread_shutdown (void)
{
  int i;
  tcache_perthread_struct *tcache_tmp = tcache;

  tcache_shutting_down = true;

  if (!tcache)
    return;

  /* Disable the tcache and prevent it from being reinitialized.  */
  tcache = NULL;

  /* Free all of the entries and the tcache itself back to the arena
     heap for coalescing.  */
  for (i = 0; i < TCACHE_MAX_BINS; ++i)
    {
      while (tcache_tmp->entries[i])
	{
	  tcache_entry *e = tcache_tmp->entries[i];
	  if (__glibc_unlikely (!aligned_OK (e)))
	    malloc_printerr ("tcache_thread_shutdown(): "
			     "unaligned tcache chunk detected");
	  tcache_tmp->entries[i] = REVEAL_PTR (e->next);
	  __libc_free (e);
	}
    }

  __libc_free (tcache_tmp);
}

static void
tcache_init(void)
{
  mstate ar_ptr;
  void *victim = 0;
  const size_t bytes = sizeof (tcache_perthread_struct);

  if (tcache_shutting_down)
    return;

  arena_get (ar_ptr, bytes);
  victim = _int_malloc (ar_ptr, bytes);
  if (!victim && ar_ptr != NULL)
    {
      ar_ptr = arena_get_retry (ar_ptr, bytes);
      victim = _int_malloc (ar_ptr, bytes);
    }


  if (ar_ptr != NULL)
    __libc_lock_unlock (ar_ptr->mutex);

  /* In a low memory situation, we may not be able to allocate memory
     - in which case, we just keep trying later.  However, we
     typically do this very early, so either there is sufficient
     memory, or there isn't enough memory to do non-trivial
     allocations anyway.  */
  if (victim)
    {
      tcache = (tcache_perthread_struct *) victim;
      memset (tcache, 0, sizeof (tcache_perthread_struct));
    }

}

# define MAYBE_INIT_TCACHE() \
  if (__glibc_unlikely (tcache == NULL)) \
    tcache_init();

#else  /* !USE_TCACHE */
# define MAYBE_INIT_TCACHE()

static void
tcache_thread_shutdown (void)
{
  /* Nothing to do if there is no thread cache.  */
}

#endif /* !USE_TCACHE  */

#if IS_IN (libc)
void *
__libc_malloc (size_t bytes)
{
  mstate ar_ptr;
  void *victim;

  _Static_assert (PTRDIFF_MAX <= SIZE_MAX / 2,
                  "PTRDIFF_MAX is not more than half of SIZE_MAX");

  if (!__malloc_initialized)
    ptmalloc_init ();
#if USE_TCACHE
  /* int_free also calls request2size, be careful to not pad twice.  */
  size_t tbytes = checked_request2size (bytes);
  if (tbytes == 0)
    {
      __set_errno (ENOMEM);
      return NULL;
    }
  size_t tc_idx = csize2tidx (tbytes);

  MAYBE_INIT_TCACHE ();

  DIAG_PUSH_NEEDS_COMMENT;
  if (tc_idx < mp_.tcache_bins
      && tcache
      && tcache->counts[tc_idx] > 0)
    {
      victim = tcache_get (tc_idx);
      return tag_new_usable (victim);
    }
  DIAG_POP_NEEDS_COMMENT;
#endif

  if (SINGLE_THREAD_P)
    {
      victim = tag_new_usable (_int_malloc (&main_arena, bytes));
      assert (!victim || chunk_is_mmapped (mem2chunk (victim)) ||
	      &main_arena == arena_for_chunk (mem2chunk (victim)));
      return victim;
    }

  arena_get (ar_ptr, bytes);

  victim = _int_malloc (ar_ptr, bytes);
  /* Retry with another arena only if we were able to find a usable arena
     before.  */
  if (!victim && ar_ptr != NULL)
    {
      LIBC_PROBE (memory_malloc_retry, 1, bytes);
      ar_ptr = arena_get_retry (ar_ptr, bytes);
      victim = _int_malloc (ar_ptr, bytes);
    }

  if (ar_ptr != NULL)
    __libc_lock_unlock (ar_ptr->mutex);

  victim = tag_new_usable (victim);

  assert (!victim || chunk_is_mmapped (mem2chunk (victim)) ||
          ar_ptr == arena_for_chunk (mem2chunk (victim)));
  return victim;
}
libc_hidden_def (__libc_malloc)

void
__libc_free (void *mem)
{
  mstate ar_ptr;
  mchunkptr p;                          /* chunk corresponding to mem */

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

  /* Quickly check that the freed pointer matches the tag for the memory.
     This gives a useful double-free detection.  */
  if (__glibc_unlikely (mtag_enabled))
    *(volatile char *)mem;

  int err = errno;

  p = mem2chunk (mem);

  if (chunk_is_mmapped (p))                       /* release mmapped memory. */
    {
      /* See if the dynamic brk/mmap threshold needs adjusting.
	 Dumped fake mmapped chunks do not affect the threshold.  */
      if (!mp_.no_dyn_threshold
          && chunksize_nomask (p) > mp_.mmap_threshold
          && chunksize_nomask (p) <= DEFAULT_MMAP_THRESHOLD_MAX)
        {
          mp_.mmap_threshold = chunksize (p);
          mp_.trim_threshold = 2 * mp_.mmap_threshold;
          LIBC_PROBE (memory_mallopt_free_dyn_thresholds, 2,
                      mp_.mmap_threshold, mp_.trim_threshold);
        }
      munmap_chunk (p);
    }
  else
    {
      MAYBE_INIT_TCACHE ();

      /* Mark the chunk as belonging to the library again.  */
      (void)tag_region (chunk2mem (p), memsize (p));

      ar_ptr = arena_for_chunk (p);
      _int_free (ar_ptr, p, 0);
    }

  __set_errno (err);
}
libc_hidden_def (__libc_free)

void *
__libc_realloc (void *oldmem, size_t bytes)
{
  mstate ar_ptr;
  INTERNAL_SIZE_T nb;         /* padded request size */

  void *newp;             /* chunk to return */

  if (!__malloc_initialized)
    ptmalloc_init ();

#if REALLOC_ZERO_BYTES_FREES
  if (bytes == 0 && oldmem != NULL)
    {
      __libc_free (oldmem); return 0;
    }
#endif

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

  /* Perform a quick check to ensure that the pointer's tag matches the
     memory's tag.  */
  if (__glibc_unlikely (mtag_enabled))
    *(volatile char*) oldmem;

  /* Return the chunk as is whenever possible, i.e. there's enough usable space
     but not so much that we end up fragmenting the block.  We use the trim
     threshold as the heuristic to decide the latter.  */
  size_t usable = musable (oldmem);
  if (bytes <= usable
      && (unsigned long) (usable - bytes) <= mp_.trim_threshold)
    return oldmem;

  /* chunk corresponding to oldmem */
  const mchunkptr oldp = mem2chunk (oldmem);
  /* its size */
  const INTERNAL_SIZE_T oldsize = chunksize (oldp);

  if (chunk_is_mmapped (oldp))
    ar_ptr = NULL;
  else
    {
      MAYBE_INIT_TCACHE ();
      ar_ptr = arena_for_chunk (oldp);
    }

  /* Little security check which won't hurt performance: the allocator
     never wrapps around at the end of the address space.  Therefore
     we can exclude some size values which might appear here by
     accident or by "design" from some intruder.  */
  if ((__builtin_expect ((uintptr_t) oldp > (uintptr_t) -oldsize, 0)
       || __builtin_expect (misaligned_chunk (oldp), 0)))
      malloc_printerr ("realloc(): invalid pointer");

  nb = checked_request2size (bytes);
  if (nb == 0)
    {
      __set_errno (ENOMEM);
      return NULL;
    }

  if (chunk_is_mmapped (oldp))
    {
      void *newmem;

#if HAVE_MREMAP
      newp = mremap_chunk (oldp, nb);
      if (newp)
	{
	  void *newmem = chunk2mem_tag (newp);
	  /* Give the new block a different tag.  This helps to ensure
	     that stale handles to the previous mapping are not
	     reused.  There's a performance hit for both us and the
	     caller for doing this, so we might want to
	     reconsider.  */
	  return tag_new_usable (newmem);
	}
#endif
      /* Note the extra SIZE_SZ overhead. */
      if (oldsize - SIZE_SZ >= nb)
        return oldmem;                         /* do nothing */

      /* Must alloc, copy, free. */
      newmem = __libc_malloc (bytes);
      if (newmem == 0)
        return 0;              /* propagate failure */

      memcpy (newmem, oldmem, oldsize - CHUNK_HDR_SZ);
      munmap_chunk (oldp);
      return newmem;
    }

  if (SINGLE_THREAD_P)
    {
      newp = _int_realloc (ar_ptr, oldp, oldsize, nb);
      assert (!newp || chunk_is_mmapped (mem2chunk (newp)) ||
	      ar_ptr == arena_for_chunk (mem2chunk (newp)));

      return newp;
    }

  __libc_lock_lock (ar_ptr->mutex);

  newp = _int_realloc (ar_ptr, oldp, oldsize, nb);

  __libc_lock_unlock (ar_ptr->mutex);
  assert (!newp || chunk_is_mmapped (mem2chunk (newp)) ||
          ar_ptr == arena_for_chunk (mem2chunk (newp)));

  if (newp == NULL)
    {
      /* Try harder to allocate memory in other arenas.  */
      LIBC_PROBE (memory_realloc_retry, 2, bytes, oldmem);
      newp = __libc_malloc (bytes);
      if (newp != NULL)
        {
	  size_t sz = memsize (oldp);
	  memcpy (newp, oldmem, sz);
	  (void) tag_region (chunk2mem (oldp), sz);
          _int_free (ar_ptr, oldp, 0);
        }
    }

  return newp;
}
libc_hidden_def (__libc_realloc)

void *
__libc_memalign (size_t alignment, size_t bytes)
{
  if (!__malloc_initialized)
    ptmalloc_init ();

  void *address = RETURN_ADDRESS (0);
  return _mid_memalign (alignment, bytes, address);
}

static void *
_mid_memalign (size_t alignment, size_t bytes, void *address)
{
  mstate ar_ptr;
  void *p;

  /* If we need less alignment than we give anyway, just relay to malloc.  */
  if (alignment <= MALLOC_ALIGNMENT)
    return __libc_malloc (bytes);

  /* Otherwise, ensure that it is at least a minimum chunk size */
  if (alignment < MINSIZE)
    alignment = MINSIZE;

  /* If the alignment is greater than SIZE_MAX / 2 + 1 it cannot be a
     power of 2 and will cause overflow in the check below.  */
  if (alignment > SIZE_MAX / 2 + 1)
    {
      __set_errno (EINVAL);
      return 0;
    }


  /* Make sure alignment is power of 2.  */
  if (!powerof2 (alignment))
    {
      size_t a = MALLOC_ALIGNMENT * 2;
      while (a < alignment)
        a <<= 1;
      alignment = a;
    }

  if (SINGLE_THREAD_P)
    {
      p = _int_memalign (&main_arena, alignment, bytes);
      assert (!p || chunk_is_mmapped (mem2chunk (p)) ||
	      &main_arena == arena_for_chunk (mem2chunk (p)));
      return tag_new_usable (p);
    }

  arena_get (ar_ptr, bytes + alignment + MINSIZE);

  p = _int_memalign (ar_ptr, alignment, bytes);
  if (!p && ar_ptr != NULL)
    {
      LIBC_PROBE (memory_memalign_retry, 2, bytes, alignment);
      ar_ptr = arena_get_retry (ar_ptr, bytes);
      p = _int_memalign (ar_ptr, alignment, bytes);
    }

  if (ar_ptr != NULL)
    __libc_lock_unlock (ar_ptr->mutex);

  assert (!p || chunk_is_mmapped (mem2chunk (p)) ||
          ar_ptr == arena_for_chunk (mem2chunk (p)));
  return tag_new_usable (p);
}
/* For ISO C11.  */
weak_alias (__libc_memalign, aligned_alloc)
libc_hidden_def (__libc_memalign)

void *
__libc_valloc (size_t bytes)
{
  if (!__malloc_initialized)
    ptmalloc_init ();

  void *address = RETURN_ADDRESS (0);
  size_t pagesize = GLRO (dl_pagesize);
  return _mid_memalign (pagesize, bytes, address);
}

void *
__libc_pvalloc (size_t bytes)
{
  if (!__malloc_initialized)
    ptmalloc_init ();

  void *address = RETURN_ADDRESS (0);
  size_t pagesize = GLRO (dl_pagesize);
  size_t rounded_bytes;
  /* ALIGN_UP with overflow check.  */
  if (__glibc_unlikely (__builtin_add_overflow (bytes,
						pagesize - 1,
						&rounded_bytes)))
    {
      __set_errno (ENOMEM);
      return 0;
    }
  rounded_bytes = rounded_bytes & -(pagesize - 1);

  return _mid_memalign (pagesize, rounded_bytes, address);
}

void *
__libc_calloc (size_t n, size_t elem_size)
{
  mstate av;
  mchunkptr oldtop;
  INTERNAL_SIZE_T sz, oldtopsize;
  void *mem;
  unsigned long clearsize;
  unsigned long nclears;
  INTERNAL_SIZE_T *d;
  ptrdiff_t bytes;

  if (__glibc_unlikely (__builtin_mul_overflow (n, elem_size, &bytes)))
    {
       __set_errno (ENOMEM);
       return NULL;
    }

  sz = bytes;

  if (!__malloc_initialized)
    ptmalloc_init ();

  MAYBE_INIT_TCACHE ();

  if (SINGLE_THREAD_P)
    av = &main_arena;
  else
    arena_get (av, sz);

  if (av)
    {
      /* Check if we hand out the top chunk, in which case there may be no
	 need to clear. */
#if MORECORE_CLEARS
      oldtop = top (av);
      oldtopsize = chunksize (top (av));
# if MORECORE_CLEARS < 2
      /* Only newly allocated memory is guaranteed to be cleared.  */
      if (av == &main_arena &&
	  oldtopsize < mp_.sbrk_base + av->max_system_mem - (char *) oldtop)
	oldtopsize = (mp_.sbrk_base + av->max_system_mem - (char *) oldtop);
# endif
      if (av != &main_arena)
	{
	  heap_info *heap = heap_for_ptr (oldtop);
	  if (oldtopsize < (char *) heap + heap->mprotect_size - (char *) oldtop)
	    oldtopsize = (char *) heap + heap->mprotect_size - (char *) oldtop;
	}
#endif
    }
  else
    {
      /* No usable arenas.  */
      oldtop = 0;
      oldtopsize = 0;
    }
  mem = _int_malloc (av, sz);

  assert (!mem || chunk_is_mmapped (mem2chunk (mem)) ||
          av == arena_for_chunk (mem2chunk (mem)));

  if (!SINGLE_THREAD_P)
    {
      if (mem == 0 && av != NULL)
	{
	  LIBC_PROBE (memory_calloc_retry, 1, sz);
	  av = arena_get_retry (av, sz);
	  mem = _int_malloc (av, sz);
	}

      if (av != NULL)
	__libc_lock_unlock (av->mutex);
    }

  /* Allocation failed even after a retry.  */
  if (mem == 0)
    return 0;

  mchunkptr p = mem2chunk (mem);

  /* If we are using memory tagging, then we need to set the tags
     regardless of MORECORE_CLEARS, so we zero the whole block while
     doing so.  */
  if (__glibc_unlikely (mtag_enabled))
    return tag_new_zero_region (mem, memsize (p));

  INTERNAL_SIZE_T csz = chunksize (p);

  /* Two optional cases in which clearing not necessary */
  if (chunk_is_mmapped (p))
    {
      if (__builtin_expect (perturb_byte, 0))
        return memset (mem, 0, sz);

      return mem;
    }

#if MORECORE_CLEARS
  if (perturb_byte == 0 && (p == oldtop && csz > oldtopsize))
    {
      /* clear only the bytes from non-freshly-sbrked memory */
      csz = oldtopsize;
    }
#endif

  /* 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 = csz - SIZE_SZ;
  nclears = clearsize / sizeof (INTERNAL_SIZE_T);
  assert (nclears >= 3);

  if (nclears > 9)
    return memset (d, 0, 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;
                }
            }
        }
    }

  return mem;
}
#endif /* IS_IN (libc) */

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

static void *
_int_malloc (mstate av, size_t bytes)
{
  INTERNAL_SIZE_T nb;               /* normalized request size */
  unsigned int idx;                 /* associated bin index */
  mbinptr bin;                      /* associated bin */

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

  mchunkptr remainder;              /* remainder from a split */
  unsigned long 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 */

#if USE_TCACHE
  size_t tcache_unsorted_count;	    /* count of unsorted chunks processed */
#endif

  /*
     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 returns false for request sizes
     that are so large that they wrap around zero when padded and
     aligned.
   */

  nb = checked_request2size (bytes);
  if (nb == 0)
    {
      __set_errno (ENOMEM);
      return NULL;
    }

  /* There are no usable arenas.  Fall back to sysmalloc to get a chunk from
     mmap.  */
  if (__glibc_unlikely (av == NULL))
    {
      void *p = sysmalloc (nb, av);
      if (p != NULL)
	alloc_perturb (p, bytes);
      return p;
    }

  /*
     If the size qualifies as a fastbin, first check corresponding bin.
     This code is safe to execute even if av is not yet initialized, so we
     can try it without checking, which saves some time on this fast path.
   */

#define REMOVE_FB(fb, victim, pp)			\
  do							\
    {							\
      victim = pp;					\
      if (victim == NULL)				\
	break;						\
      pp = REVEAL_PTR (victim->fd);                                     \
      if (__glibc_unlikely (pp != NULL && misaligned_chunk (pp)))       \
	malloc_printerr ("malloc(): unaligned fastbin chunk detected"); \
    }							\
  while ((pp = catomic_compare_and_exchange_val_acq (fb, pp, victim)) \
	 != victim);					\

  if ((unsigned long) (nb) <= (unsigned long) (get_max_fast ()))
    {
      idx = fastbin_index (nb);
      mfastbinptr *fb = &fastbin (av, idx);
      mchunkptr pp;
      victim = *fb;

      if (victim != NULL)
	{
	  if (__glibc_unlikely (misaligned_chunk (victim)))
	    malloc_printerr ("malloc(): unaligned fastbin chunk detected 2");

	  if (SINGLE_THREAD_P)
	    *fb = REVEAL_PTR (victim->fd);
	  else
	    REMOVE_FB (fb, pp, victim);
	  if (__glibc_likely (victim != NULL))
	    {
	      size_t victim_idx = fastbin_index (chunksize (victim));
	      if (__builtin_expect (victim_idx != idx, 0))
		malloc_printerr ("malloc(): memory corruption (fast)");
	      check_remalloced_chunk (av, victim, nb);
#if USE_TCACHE
	      /* While we're here, if we see other chunks of the same size,
		 stash them in the tcache.  */
	      size_t tc_idx = csize2tidx (nb);
	      if (tcache && tc_idx < mp_.tcache_bins)
		{
		  mchunkptr tc_victim;

		  /* While bin not empty and tcache not full, copy chunks.  */
		  while (tcache->counts[tc_idx] < mp_.tcache_count
			 && (tc_victim = *fb) != NULL)
		    {
		      if (__glibc_unlikely (misaligned_chunk (tc_victim)))
			malloc_printerr ("malloc(): unaligned fastbin chunk detected 3");
		      if (SINGLE_THREAD_P)
			*fb = REVEAL_PTR (tc_victim->fd);
		      else
			{
			  REMOVE_FB (fb, pp, tc_victim);
			  if (__glibc_unlikely (tc_victim == NULL))
			    break;
			}
		      tcache_put (tc_victim, tc_idx);
		    }
		}
#endif
	      void *p = chunk2mem (victim);
	      alloc_perturb (p, bytes);
	      return p;
	    }
	}
    }

  /*
     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;
	  if (__glibc_unlikely (bck->fd != victim))
	    malloc_printerr ("malloc(): smallbin double linked list corrupted");
          set_inuse_bit_at_offset (victim, nb);
          bin->bk = bck;
          bck->fd = bin;

          if (av != &main_arena)
	    set_non_main_arena (victim);
          check_malloced_chunk (av, victim, nb);
#if USE_TCACHE
	  /* While we're here, if we see other chunks of the same size,
	     stash them in the tcache.  */
	  size_t tc_idx = csize2tidx (nb);
	  if (tcache && tc_idx < mp_.tcache_bins)
	    {
	      mchunkptr tc_victim;

	      /* While bin not empty and tcache not full, copy chunks over.  */
	      while (tcache->counts[tc_idx] < mp_.tcache_count
		     && (tc_victim = last (bin)) != bin)
		{
		  if (tc_victim != 0)
		    {
		      bck = tc_victim->bk;
		      set_inuse_bit_at_offset (tc_victim, nb);
		      if (av != &main_arena)
			set_non_main_arena (tc_victim);
		      bin->bk = bck;
		      bck->fd = bin;

		      tcache_put (tc_victim, tc_idx);
	            }
		}
	    }
#endif
          void *p = chunk2mem (victim);
          alloc_perturb (p, bytes);
          return p;
        }
    }

  /*
     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 (atomic_load_relaxed (&av->have_fastchunks))
        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.

     The outer loop here is needed because we might not realize until
     near the end of malloc that we should have consolidated, so must
     do so and retry. This happens at most once, and only when we would
     otherwise need to expand memory to service a "small" request.
   */

#if USE_TCACHE
  INTERNAL_SIZE_T tcache_nb = 0;
  size_t tc_idx = csize2tidx (nb);
  if (tcache && tc_idx < mp_.tcache_bins)
    tcache_nb = nb;
  int return_cached = 0;

  tcache_unsorted_count = 0;
#endif

  for (;; )
    {
      int iters = 0;
      while ((victim = unsorted_chunks (av)->bk) != unsorted_chunks (av))
        {
          bck = victim->bk;
          size = chunksize (victim);
          mchunkptr next = chunk_at_offset (victim, size);

          if (__glibc_unlikely (size <= CHUNK_HDR_SZ)
              || __glibc_unlikely (size > av->system_mem))
            malloc_printerr ("malloc(): invalid size (unsorted)");
          if (__glibc_unlikely (chunksize_nomask (next) < CHUNK_HDR_SZ)
              || __glibc_unlikely (chunksize_nomask (next) > av->system_mem))
            malloc_printerr ("malloc(): invalid next size (unsorted)");
          if (__glibc_unlikely ((prev_size (next) & ~(SIZE_BITS)) != size))
            malloc_printerr ("malloc(): mismatching next->prev_size (unsorted)");
          if (__glibc_unlikely (bck->fd != victim)
              || __glibc_unlikely (victim->fd != unsorted_chunks (av)))
            malloc_printerr ("malloc(): unsorted double linked list corrupted");
          if (__glibc_unlikely (prev_inuse (next)))
            malloc_printerr ("malloc(): invalid next->prev_inuse (unsorted)");

          /*
             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 &&
              (unsigned long) (size) > (unsigned long) (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);
              if (!in_smallbin_range (remainder_size))
                {
                  remainder->fd_nextsize = NULL;
                  remainder->bk_nextsize = NULL;
                }

              set_head (victim, nb | PREV_INUSE |
                        (av != &main_arena ? NON_MAIN_ARENA : 0));
              set_head (remainder, remainder_size | PREV_INUSE);
              set_foot (remainder, remainder_size);

              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }

          /* remove from unsorted list */
          if (__glibc_unlikely (bck->fd != victim))
            malloc_printerr ("malloc(): corrupted unsorted chunks 3");
          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);
              if (av != &main_arena)
		set_non_main_arena (victim);
#if USE_TCACHE
	      /* Fill cache first, return to user only if cache fills.
		 We may return one of these chunks later.  */
	      if (tcache_nb
		  && tcache->counts[tc_idx] < mp_.tcache_count)
		{
		  tcache_put (victim, tc_idx);
		  return_cached = 1;
		  continue;
		}
	      else
		{
#endif
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
#if USE_TCACHE
		}
#endif
            }

          /* 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;

              /* maintain large bins in sorted order */
              if (fwd != bck)
                {
                  /* Or with inuse bit to speed comparisons */
                  size |= PREV_INUSE;
                  /* if smaller than smallest, bypass loop below */
                  assert (chunk_main_arena (bck->bk));
                  if ((unsigned long) (size)
		      < (unsigned long) chunksize_nomask (bck->bk))
                    {
                      fwd = bck;
                      bck = bck->bk;

                      victim->fd_nextsize = fwd->fd;
                      victim->bk_nextsize = fwd->fd->bk_nextsize;
                      fwd->fd->bk_nextsize = victim->bk_nextsize->fd_nextsize = victim;
                    }
                  else
                    {
                      assert (chunk_main_arena (fwd));
                      while ((unsigned long) size < chunksize_nomask (fwd))
                        {
                          fwd = fwd->fd_nextsize;
			  assert (chunk_main_arena (fwd));
                        }

                      if ((unsigned long) size
			  == (unsigned long) chunksize_nomask (fwd))
                        /* Always insert in the second position.  */
                        fwd = fwd->fd;
                      else
                        {
                          victim->fd_nextsize = fwd;
                          victim->bk_nextsize = fwd->bk_nextsize;
                          if (__glibc_unlikely (fwd->bk_nextsize->fd_nextsize != fwd))
                            malloc_printerr ("malloc(): largebin double linked list corrupted (nextsize)");
                          fwd->bk_nextsize = victim;
                          victim->bk_nextsize->fd_nextsize = victim;
                        }
                      bck = fwd->bk;
                      if (bck->fd != fwd)
                        malloc_printerr ("malloc(): largebin double linked list corrupted (bk)");
                    }
                }
              else
                victim->fd_nextsize = victim->bk_nextsize = victim;
            }

          mark_bin (av, victim_index);
          victim->bk = bck;
          victim->fd = fwd;
          fwd->bk = victim;
          bck->fd = victim;

#if USE_TCACHE
      /* If we've processed as many chunks as we're allowed while
	 filling the cache, return one of the cached ones.  */
      ++tcache_unsorted_count;
      if (return_cached
	  && mp_.tcache_unsorted_limit > 0
	  && tcache_unsorted_count > mp_.tcache_unsorted_limit)
	{
	  return tcache_get (tc_idx);
	}
#endif

#define MAX_ITERS       10000
          if (++iters >= MAX_ITERS)
            break;
        }

#if USE_TCACHE
      /* If all the small chunks we found ended up cached, return one now.  */
      if (return_cached)
	{
	  return tcache_get (tc_idx);
	}
#endif

      /*
         If a large request, scan through the chunks of current bin in
         sorted order to find smallest that fits.  Use the skip list for this.
       */

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

          /* skip scan if empty or largest chunk is too small */
          if ((victim = first (bin)) != bin
	      && (unsigned long) chunksize_nomask (victim)
	        >= (unsigned long) (nb))
            {
              victim = victim->bk_nextsize;
              while (((unsigned long) (size = chunksize (victim)) <
                      (unsigned long) (nb)))
                victim = victim->bk_nextsize;

              /* Avoid removing the first entry for a size so that the skip
                 list does not have to be rerouted.  */
              if (victim != last (bin)
		  && chunksize_nomask (victim)
		    == chunksize_nomask (victim->fd))
                victim = victim->fd;

              remainder_size = size - nb;
              unlink_chunk (av, victim);

              /* Exhaust */
              if (remainder_size < MINSIZE)
                {
                  set_inuse_bit_at_offset (victim, size);
                  if (av != &main_arena)
		    set_non_main_arena (victim);
                }
              /* Split */
              else
                {
                  remainder = chunk_at_offset (victim, nb);
                  /* We cannot assume the unsorted list is empty and therefore
                     have to perform a complete insert here.  */
                  bck = unsorted_chunks (av);
                  fwd = bck->fd;
		  if (__glibc_unlikely (fwd->bk != bck))
		    malloc_printerr ("malloc(): corrupted unsorted chunks");
                  remainder->bk = bck;
                  remainder->fd = fwd;
                  bck->fd = remainder;
                  fwd->bk = remainder;
                  if (!in_smallbin_range (remainder_size))
                    {
                      remainder->fd_nextsize = NULL;
                      remainder->bk_nextsize = NULL;
                    }
                  set_head (victim, nb | PREV_INUSE |
                            (av != &main_arena ? NON_MAIN_ARENA : 0));
                  set_head (remainder, remainder_size | PREV_INUSE);
                  set_foot (remainder, remainder_size);
                }
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }
        }

      /*
         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.
         The particular case of skipping all bins during warm-up phases
         when no chunks have been returned yet is faster than it might look.
       */

      ++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 ((unsigned long) (size) >= (unsigned long) (nb));

              remainder_size = size - nb;

              /* unlink */
              unlink_chunk (av, victim);

              /* Exhaust */
              if (remainder_size < MINSIZE)
                {
                  set_inuse_bit_at_offset (victim, size);
                  if (av != &main_arena)
		    set_non_main_arena (victim);
                }

              /* Split */
              else
                {
                  remainder = chunk_at_offset (victim, nb);

                  /* We cannot assume the unsorted list is empty and therefore
                     have to perform a complete insert here.  */
                  bck = unsorted_chunks (av);
                  fwd = bck->fd;
		  if (__glibc_unlikely (fwd->bk != bck))
		    malloc_printerr ("malloc(): corrupted unsorted chunks 2");
                  remainder->bk = bck;
                  remainder->fd = fwd;
                  bck->fd = remainder;
                  fwd->bk = remainder;

                  /* advertise as last remainder */
                  if (in_smallbin_range (nb))
                    av->last_remainder = remainder;
                  if (!in_smallbin_range (remainder_size))
                    {
                      remainder->fd_nextsize = NULL;
                      remainder->bk_nextsize = NULL;
                    }
                  set_head (victim, nb | PREV_INUSE |
                            (av != &main_arena ? NON_MAIN_ARENA : 0));
                  set_head (remainder, remainder_size | PREV_INUSE);
                  set_foot (remainder, remainder_size);
                }
              check_malloced_chunk (av, victim, nb);
              void *p = chunk2mem (victim);
              alloc_perturb (p, bytes);
              return p;
            }
        }

    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
         exhausted 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 (__glibc_unlikely (size > av->system_mem))
        malloc_printerr ("malloc(): corrupted top size");

      if ((unsigned long) (size) >= (unsigned long) (nb + MINSIZE))
        {
          remainder_size = size - nb;
          remainder = chunk_at_offset (victim, nb);
          av->top = remainder;
          set_head (victim, nb | PREV_INUSE |
                    (av != &main_arena ? NON_MAIN_ARENA : 0));
          set_head (remainder, remainder_size | PREV_INUSE);

          check_malloced_chunk (av, victim, nb);
          void *p = chunk2mem (victim);
          alloc_perturb (p, bytes);
          return p;
        }

      /* When we are using atomic ops to free fast chunks we can get
         here for all block sizes.  */
      else if (atomic_load_relaxed (&av->have_fastchunks))
        {
          malloc_consolidate (av);
          /* restore original bin index */
          if (in_smallbin_range (nb))
            idx = smallbin_index (nb);
          else
            idx = largebin_index (nb);
        }

      /*
         Otherwise, relay to handle system-dependent cases
       */
      else
        {
          void *p = sysmalloc (nb, av);
          if (p != NULL)
            alloc_perturb (p, bytes);
          return p;
        }
    }
}

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

static void
_int_free (mstate av, mchunkptr p, int have_lock)
{
  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 */

  size = chunksize (p);

  /* Little security check which won't hurt performance: the
     allocator never wrapps around at the end of the address space.
     Therefore we can exclude some size values which might appear
     here by accident or by "design" from some intruder.  */
  if (__builtin_expect ((uintptr_t) p > (uintptr_t) -size, 0)
      || __builtin_expect (misaligned_chunk (p), 0))
    malloc_printerr ("free(): invalid pointer");
  /* We know that each chunk is at least MINSIZE bytes in size or a
     multiple of MALLOC_ALIGNMENT.  */
  if (__glibc_unlikely (size < MINSIZE || !aligned_OK (size)))
    malloc_printerr ("free(): invalid size");

  check_inuse_chunk(av, p);

#if USE_TCACHE
  {
    size_t tc_idx = csize2tidx (size);
    if (tcache != NULL && tc_idx < mp_.tcache_bins)
      {
	/* Check to see if it's already in the tcache.  */
	tcache_entry *e = (tcache_entry *) chunk2mem (p);

	/* This test succeeds on double free.  However, we don't 100%
	   trust it (it also matches random payload data at a 1 in
	   2^<size_t> chance), so verify it's not an unlikely
	   coincidence before aborting.  */
	if (__glibc_unlikely (e->key == tcache_key))
	  {
	    tcache_entry *tmp;
	    size_t cnt = 0;
	    LIBC_PROBE (memory_tcache_double_free, 2, e, tc_idx);
	    for (tmp = tcache->entries[tc_idx];
		 tmp;
		 tmp = REVEAL_PTR (tmp->next), ++cnt)
	      {
		if (cnt >= mp_.tcache_count)
		  malloc_printerr ("free(): too many chunks detected in tcache");
		if (__glibc_unlikely (!aligned_OK (tmp)))
		  malloc_printerr ("free(): unaligned chunk detected in tcache 2");
		if (tmp == e)
		  malloc_printerr ("free(): double free detected in tcache 2");
		/* If we get here, it was a coincidence.  We've wasted a
		   few cycles, but don't abort.  */
	      }
	  }

	if (tcache->counts[tc_idx] < mp_.tcache_count)
	  {
	    tcache_put (p, tc_idx);
	    return;
	  }
      }
  }
#endif

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

  if ((unsigned long)(size) <= (unsigned long)(get_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
      ) {

    if (__builtin_expect (chunksize_nomask (chunk_at_offset (p, size))
			  <= CHUNK_HDR_SZ, 0)
	|| __builtin_expect (chunksize (chunk_at_offset (p, size))
			     >= av->system_mem, 0))
      {
	bool fail = true;
	/* We might not have a lock at this point and concurrent modifications
	   of system_mem might result in a false positive.  Redo the test after
	   getting the lock.  */
	if (!have_lock)
	  {
	    __libc_lock_lock (av->mutex);
	    fail = (chunksize_nomask (chunk_at_offset (p, size)) <= CHUNK_HDR_SZ
		    || chunksize (chunk_at_offset (p, size)) >= av->system_mem);
	    __libc_lock_unlock (av->mutex);
	  }

	if (fail)
	  malloc_printerr ("free(): invalid next size (fast)");
      }

    free_perturb (chunk2mem(p), size - CHUNK_HDR_SZ);

    atomic_store_relaxed (&av->have_fastchunks, true);
    unsigned int idx = fastbin_index(size);
    fb = &fastbin (av, idx);

    /* Atomically link P to its fastbin: P->FD = *FB; *FB = P;  */
    mchunkptr old = *fb, old2;

    if (SINGLE_THREAD_P)
      {
	/* Check that the top of the bin is not the record we are going to
	   add (i.e., double free).  */
	if (__builtin_expect (old == p, 0))
	  malloc_printerr ("double free or corruption (fasttop)");
	p->fd = PROTECT_PTR (&p->fd, old);
	*fb = p;
      }
    else
      do
	{
	  /* Check that the top of the bin is not the record we are going to
	     add (i.e., double free).  */
	  if (__builtin_expect (old == p, 0))
	    malloc_printerr ("double free or corruption (fasttop)");
	  old2 = old;
	  p->fd = PROTECT_PTR (&p->fd, old);
	}
      while ((old = catomic_compare_and_exchange_val_rel (fb, p, old2))
	     != old2);

    /* Check that size of fastbin chunk at the top is the same as
       size of the chunk that we are adding.  We can dereference OLD
       only if we have the lock, otherwise it might have already been
       allocated again.  */
    if (have_lock && old != NULL
	&& __builtin_expect (fastbin_index (chunksize (old)) != idx, 0))
      malloc_printerr ("invalid fastbin entry (free)");
  }

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

  else if (!chunk_is_mmapped(p)) {

    /* If we're single-threaded, don't lock the arena.  */
    if (SINGLE_THREAD_P)
      have_lock = true;

    if (!have_lock)
      __libc_lock_lock (av->mutex);

    nextchunk = chunk_at_offset(p, size);

    /* Lightweight tests: check whether the block is already the
       top block.  */
    if (__glibc_unlikely (p == av->top))
      malloc_printerr ("double free or corruption (top)");
    /* Or whether the next chunk is beyond the boundaries of the arena.  */
    if (__builtin_expect (contiguous (av)
			  && (char *) nextchunk
			  >= ((char *) av->top + chunksize(av->top)), 0))
	malloc_printerr ("double free or corruption (out)");
    /* Or whether the block is actually not marked used.  */
    if (__glibc_unlikely (!prev_inuse(nextchunk)))
      malloc_printerr ("double free or corruption (!prev)");

    nextsize = chunksize(nextchunk);
    if (__builtin_expect (chunksize_nomask (nextchunk) <= CHUNK_HDR_SZ, 0)
	|| __builtin_expect (nextsize >= av->system_mem, 0))
      malloc_printerr ("free(): invalid next size (normal)");

    free_perturb (chunk2mem(p), size - CHUNK_HDR_SZ);

    /* consolidate backward */
    if (!prev_inuse(p)) {
      prevsize = prev_size (p);
      size += prevsize;
      p = chunk_at_offset(p, -((long) prevsize));
      if (__glibc_unlikely (chunksize(p) != prevsize))
        malloc_printerr ("corrupted size vs. prev_size while consolidating");
      unlink_chunk (av, p);
    }

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

      /* consolidate forward */
      if (!nextinuse) {
	unlink_chunk (av, nextchunk);
	size += nextsize;
      } else
	clear_inuse_bit_at_offset(nextchunk, 0);

      /*
	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;
      if (__glibc_unlikely (fwd->bk != bck))
	malloc_printerr ("free(): corrupted unsorted chunks");
      p->fd = fwd;
      p->bk = bck;
      if (!in_smallbin_range(size))
	{
	  p->fd_nextsize = NULL;
	  p->bk_nextsize = NULL;
	}
      bck->fd = p;
      fwd->bk = p;

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

      check_free_chunk(av, 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(av, 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 ((unsigned long)(size) >= FASTBIN_CONSOLIDATION_THRESHOLD) {
      if (atomic_load_relaxed (&av->have_fastchunks))
	malloc_consolidate(av);

      if (av == &main_arena) {
#ifndef MORECORE_CANNOT_TRIM
	if ((unsigned long)(chunksize(av->top)) >=
	    (unsigned long)(mp_.trim_threshold))
	  systrim(mp_.top_pad, av);
#endif
      } else {
	/* Always try heap_trim(), even if the top chunk is not
	   large, because the corresponding heap might go away.  */
	heap_info *heap = heap_for_ptr(top(av));

	assert(heap->ar_ptr == av);
	heap_trim(heap, mp_.top_pad);
      }
    }

    if (!have_lock)
      __libc_lock_unlock (av->mutex);
  }
  /*
    If the chunk was allocated via mmap, release via munmap().
  */

  else {
    munmap_chunk (p);
  }
}

/*
  ------------------------- 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.
*/

static void malloc_consolidate(mstate av)
{
  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;

  atomic_store_relaxed (&av->have_fastchunks, false);

  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 = &fastbin (av, NFASTBINS - 1);
  fb = &fastbin (av, 0);
  do {
    p = atomic_exchange_acquire (fb, NULL);
    if (p != 0) {
      do {
	{
	  if (__glibc_unlikely (misaligned_chunk (p)))
	    malloc_printerr ("malloc_consolidate(): "
			     "unaligned fastbin chunk detected");

	  unsigned int idx = fastbin_index (chunksize (p));
	  if ((&fastbin (av, idx)) != fb)
	    malloc_printerr ("malloc_consolidate(): invalid chunk size");
	}

	check_inuse_chunk(av, p);
	nextp = REVEAL_PTR (p->fd);

	/* Slightly streamlined version of consolidation code in free() */
	size = chunksize (p);
	nextchunk = chunk_at_offset(p, size);
	nextsize = chunksize(nextchunk);

	if (!prev_inuse(p)) {
	  prevsize = prev_size (p);
	  size += prevsize;
	  p = chunk_at_offset(p, -((long) prevsize));
	  if (__glibc_unlikely (chunksize(p) != prevsize))
	    malloc_printerr ("corrupted size vs. prev_size in fastbins");
	  unlink_chunk (av, p);
	}

	if (nextchunk != av->top) {
	  nextinuse = inuse_bit_at_offset(nextchunk, nextsize);

	  if (!nextinuse) {
	    size += nextsize;
	    unlink_chunk (av, nextchunk);
	  } else
	    clear_inuse_bit_at_offset(nextchunk, 0);

	  first_unsorted = unsorted_bin->fd;
	  unsorted_bin->fd = p;
	  first_unsorted->bk = p;

	  if (!in_smallbin_range (size)) {
	    p->fd_nextsize = NULL;
	    p->bk_nextsize = NULL;
	  }

	  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);
}

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

static void *
_int_realloc (mstate av, mchunkptr oldp, INTERNAL_SIZE_T oldsize,
	     INTERNAL_SIZE_T nb)
{
  mchunkptr        newp;            /* chunk to return */
  INTERNAL_SIZE_T  newsize;         /* its size */
  void*          newmem;          /* corresponding user mem */

  mchunkptr        next;            /* next contiguous chunk after oldp */

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

  /* oldmem size */
  if (__builtin_expect (chunksize_nomask (oldp) <= CHUNK_HDR_SZ, 0)
      || __builtin_expect (oldsize >= av->system_mem, 0)
      || __builtin_expect (oldsize != chunksize (oldp), 0))
    malloc_printerr ("realloc(): invalid old size");

  check_inuse_chunk (av, oldp);

  /* All callers already filter out mmap'ed chunks.  */
  assert (!chunk_is_mmapped (oldp));

  next = chunk_at_offset (oldp, oldsize);
  INTERNAL_SIZE_T nextsize = chunksize (next);
  if (__builtin_expect (chunksize_nomask (next) <= CHUNK_HDR_SZ, 0)
      || __builtin_expect (nextsize >= av->system_mem, 0))
    malloc_printerr ("realloc(): invalid next size");

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

  else
    {
      /* Try to expand forward into top */
      if (next == av->top &&
          (unsigned long) (newsize = oldsize + nextsize) >=
          (unsigned long) (nb + MINSIZE))
        {
          set_head_size (oldp, nb | (av != &main_arena ? NON_MAIN_ARENA : 0));
          av->top = chunk_at_offset (oldp, nb);
          set_head (av->top, (newsize - nb) | PREV_INUSE);
          check_inuse_chunk (av, oldp);
          return tag_new_usable (chunk2mem (oldp));
        }

      /* Try to expand forward into next chunk;  split off remainder below */
      else if (next != av->top &&
               !inuse (next) &&
               (unsigned long) (newsize = oldsize + nextsize) >=
               (unsigned long) (nb))
        {
          newp = oldp;
          unlink_chunk (av, next);
        }

      /* allocate, copy, free */
      else
        {
          newmem = _int_malloc (av, 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
            {
	      void *oldmem = chunk2mem (oldp);
	      size_t sz = memsize (oldp);
	      (void) tag_region (oldmem, sz);
	      newmem = tag_new_usable (newmem);
	      memcpy (newmem, oldmem, sz);
	      _int_free (av, oldp, 1);
	      check_inuse_chunk (av, newp);
	      return newmem;
            }
        }
    }

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

  assert ((unsigned long) (newsize) >= (unsigned long) (nb));

  remainder_size = newsize - nb;

  if (remainder_size < MINSIZE)   /* not enough extra to split off */
    {
      set_head_size (newp, newsize | (av != &main_arena ? NON_MAIN_ARENA : 0));
      set_inuse_bit_at_offset (newp, newsize);
    }
  else   /* split remainder */
    {
      remainder = chunk_at_offset (newp, nb);
      /* Clear any user-space tags before writing the header.  */
      remainder = tag_region (remainder, remainder_size);
      set_head_size (newp, nb | (av != &main_arena ? NON_MAIN_ARENA : 0));
      set_head (remainder, remainder_size | PREV_INUSE |
                (av != &main_arena ? NON_MAIN_ARENA : 0));
      /* Mark remainder as inuse so free() won't complain */
      set_inuse_bit_at_offset (remainder, remainder_size);
      _int_free (av, remainder, 1);
    }

  check_inuse_chunk (av, newp);
  return tag_new_usable (chunk2mem (newp));
}

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

static void *
_int_memalign (mstate av, size_t alignment, size_t bytes)
{
  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 */
  unsigned long remainder_size;   /* its size */
  INTERNAL_SIZE_T size;



  nb = checked_request2size (bytes);
  if (nb == 0)
    {
      __set_errno (ENOMEM);
      return NULL;
    }

  /*
     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 *) (_int_malloc (av, nb + alignment + MINSIZE));

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

  p = mem2chunk (m);

  if ((((unsigned long) (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 (((unsigned long) (m + alignment - 1)) &
                                - ((signed long) alignment));
      if ((unsigned long) (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))
        {
          set_prev_size (newp, prev_size (p) + leadsize);
          set_head (newp, newsize | IS_MMAPPED);
          return chunk2mem (newp);
        }

      /* Otherwise, give back leader, use the rest */
      set_head (newp, newsize | PREV_INUSE |
                (av != &main_arena ? NON_MAIN_ARENA : 0));
      set_inuse_bit_at_offset (newp, newsize);
      set_head_size (p, leadsize | (av != &main_arena ? NON_MAIN_ARENA : 0));
      _int_free (av, p, 1);
      p = newp;

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

  /* Also give back spare room at the end */
  if (!chunk_is_mmapped (p))
    {
      size = chunksize (p);
      if ((unsigned long) (size) > (unsigned long) (nb + MINSIZE))
        {
          remainder_size = size - nb;
          remainder = chunk_at_offset (p, nb);
          set_head (remainder, remainder_size | PREV_INUSE |
                    (av != &main_arena ? NON_MAIN_ARENA : 0));
          set_head_size (p, nb);
          _int_free (av, remainder, 1);
        }
    }

  check_inuse_chunk (av, p);
  return chunk2mem (p);
}


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

static int
mtrim (mstate av, size_t pad)
{
  /* Ensure all blocks are consolidated.  */
  malloc_consolidate (av);

  const size_t ps = GLRO (dl_pagesize);
  int psindex = bin_index (ps);
  const size_t psm1 = ps - 1;

  int result = 0;
  for (int i = 1; i < NBINS; ++i)
    if (i == 1 || i >= psindex)
      {
        mbinptr bin = bin_at (av, i);

        for (mchunkptr p = last (bin); p != bin; p = p->bk)
          {
            INTERNAL_SIZE_T size = chunksize (p);

            if (size > psm1 + sizeof (struct malloc_chunk))
              {
                /* See whether the chunk contains at least one unused page.  */
                char *paligned_mem = (char *) (((uintptr_t) p
                                                + sizeof (struct malloc_chunk)
                                                + psm1) & ~psm1);

                assert ((char *) chunk2mem (p) + 2 * CHUNK_HDR_SZ
			<= paligned_mem);
                assert ((char *) p + size > paligned_mem);

                /* This is the size we could potentially free.  */
                size -= paligned_mem - (char *) p;

                if (size > psm1)
                  {
#if MALLOC_DEBUG
                    /* When debugging we simulate destroying the memory
                       content.  */
                    memset (paligned_mem, 0x89, size & ~psm1);
#endif
                    __madvise (paligned_mem, size & ~psm1, MADV_DONTNEED);

                    result = 1;
                  }
              }
          }
      }

#ifndef MORECORE_CANNOT_TRIM
  return result | (av == &main_arena ? systrim (pad, av) : 0);

#else
  return result;
#endif
}


int
__malloc_trim (size_t s)
{
  int result = 0;

  if (!__malloc_initialized)
    ptmalloc_init ();

  mstate ar_ptr = &main_arena;
  do
    {
      __libc_lock_lock (ar_ptr->mutex);
      result |= mtrim (ar_ptr, s);
      __libc_lock_unlock (ar_ptr->mutex);

      ar_ptr = ar_ptr->next;
    }
  while (ar_ptr != &main_arena);

  return result;
}


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

static size_t
musable (void *mem)
{
  mchunkptr p = mem2chunk (mem);

  if (chunk_is_mmapped (p))
    return chunksize (p) - CHUNK_HDR_SZ;
  else if (inuse (p))
    return memsize (p);

  return 0;
}

#if IS_IN (libc)
size_t
__malloc_usable_size (void *m)
{
  if (m == NULL)
    return 0;
  return musable (m);
}
#endif

/*
   ------------------------------ mallinfo ------------------------------
   Accumulate malloc statistics for arena AV into M.
 */
static void
int_mallinfo (mstate av, struct mallinfo2 *m)
{
  size_t i;
  mbinptr b;
  mchunkptr p;
  INTERNAL_SIZE_T avail;
  INTERNAL_SIZE_T fastavail;
  int nblocks;
  int nfastblocks;

  check_malloc_state (av);

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

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

  for (i = 0; i < NFASTBINS; ++i)
    {
      for (p = fastbin (av, i);
	   p != 0;
	   p = REVEAL_PTR (p->fd))
        {
	  if (__glibc_unlikely (misaligned_chunk (p)))
	    malloc_printerr ("int_mallinfo(): "
			     "unaligned fastbin chunk detected");
          ++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);
        }
    }

  m->smblks += nfastblocks;
  m->ordblks += nblocks;
  m->fordblks += avail;
  m->uordblks += av->system_mem - avail;
  m->arena += av->system_mem;
  m->fsmblks += fastavail;
  if (av == &main_arena)
    {
      m->hblks = mp_.n_mmaps;
      m->hblkhd = mp_.mmapped_mem;
      m->usmblks = 0;
      m->keepcost = chunksize (av->top);
    }
}


struct mallinfo2
__libc_mallinfo2 (void)
{
  struct mallinfo2 m;
  mstate ar_ptr;

  if (!__malloc_initialized)
    ptmalloc_init ();

  memset (&m, 0, sizeof (m));
  ar_ptr = &main_arena;
  do
    {
      __libc_lock_lock (ar_ptr->mutex);
      int_mallinfo (ar_ptr, &m);
      __libc_lock_unlock (ar_ptr->mutex);

      ar_ptr = ar_ptr->next;
    }
  while (ar_ptr != &main_arena);

  return m;
}
libc_hidden_def (__libc_mallinfo2)

struct mallinfo
__libc_mallinfo (void)
{
  struct mallinfo m;
  struct mallinfo2 m2 = __libc_mallinfo2 ();

  m.arena = m2.arena;
  m.ordblks = m2.ordblks;
  m.smblks = m2.smblks;
  m.hblks = m2.hblks;
  m.hblkhd = m2.hblkhd;
  m.usmblks = m2.usmblks;
  m.fsmblks = m2.fsmblks;
  m.uordblks = m2.uordblks;
  m.fordblks = m2.fordblks;
  m.keepcost = m2.keepcost;

  return m;
}


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

void
__malloc_stats (void)
{
  int i;
  mstate ar_ptr;
  unsigned int in_use_b = mp_.mmapped_mem, system_b = in_use_b;

  if (!__malloc_initialized)
    ptmalloc_init ();
  _IO_flockfile (stderr);
  int old_flags2 = stderr->_flags2;
  stderr->_flags2 |= _IO_FLAGS2_NOTCANCEL;
  for (i = 0, ar_ptr = &main_arena;; i++)
    {
      struct mallinfo2 mi;

      memset (&mi, 0, sizeof (mi));
      __libc_lock_lock (ar_ptr->mutex);
      int_mallinfo (ar_ptr, &mi);
      fprintf (stderr, "Arena %d:\n", i);
      fprintf (stderr, "system bytes     = %10u\n", (unsigned int) mi.arena);
      fprintf (stderr, "in use bytes     = %10u\n", (unsigned int) mi.uordblks);
#if MALLOC_DEBUG > 1
      if (i > 0)
        dump_heap (heap_for_ptr (top (ar_ptr)));
#endif
      system_b += mi.arena;
      in_use_b += mi.uordblks;
      __libc_lock_unlock (ar_ptr->mutex);
      ar_ptr = ar_ptr->next;
      if (ar_ptr == &main_arena)
        break;
    }
  fprintf (stderr, "Total (incl. mmap):\n");
  fprintf (stderr, "system bytes     = %10u\n", system_b);
  fprintf (stderr, "in use bytes     = %10u\n", in_use_b);
  fprintf (stderr, "max mmap regions = %10u\n", (unsigned int) mp_.max_n_mmaps);
  fprintf (stderr, "max mmap bytes   = %10lu\n",
           (unsigned long) mp_.max_mmapped_mem);
  stderr->_flags2 = old_flags2;
  _IO_funlockfile (stderr);
}


/*
   ------------------------------ mallopt ------------------------------
 */
static __always_inline int
do_set_trim_threshold (size_t value)
{
  LIBC_PROBE (memory_mallopt_trim_threshold, 3, value, mp_.trim_threshold,
	      mp_.no_dyn_threshold);
  mp_.trim_threshold = value;
  mp_.no_dyn_threshold = 1;
  return 1;
}

static __always_inline int
do_set_top_pad (size_t value)
{
  LIBC_PROBE (memory_mallopt_top_pad, 3, value, mp_.top_pad,
	      mp_.no_dyn_threshold);
  mp_.top_pad = value;
  mp_.no_dyn_threshold = 1;
  return 1;
}

static __always_inline int
do_set_mmap_threshold (size_t value)
{
  LIBC_PROBE (memory_mallopt_mmap_threshold, 3, value, mp_.mmap_threshold,
	      mp_.no_dyn_threshold);
  mp_.mmap_threshold = value;
  mp_.no_dyn_threshold = 1;
  return 1;
}

static __always_inline int
do_set_mmaps_max (int32_t value)
{
  LIBC_PROBE (memory_mallopt_mmap_max, 3, value, mp_.n_mmaps_max,
	      mp_.no_dyn_threshold);
  mp_.n_mmaps_max = value;
  mp_.no_dyn_threshold = 1;
  return 1;
}

static __always_inline int
do_set_mallopt_check (int32_t value)
{
  return 1;
}

static __always_inline int
do_set_perturb_byte (int32_t value)
{
  LIBC_PROBE (memory_mallopt_perturb, 2, value, perturb_byte);
  perturb_byte = value;
  return 1;
}

static __always_inline int
do_set_arena_test (size_t value)
{
  LIBC_PROBE (memory_mallopt_arena_test, 2, value, mp_.arena_test);
  mp_.arena_test = value;
  return 1;
}

static __always_inline int
do_set_arena_max (size_t value)
{
  LIBC_PROBE (memory_mallopt_arena_max, 2, value, mp_.arena_max);
  mp_.arena_max = value;
  return 1;
}

#if USE_TCACHE
static __always_inline int
do_set_tcache_max (size_t value)
{
  if (value <= MAX_TCACHE_SIZE)
    {
      LIBC_PROBE (memory_tunable_tcache_max_bytes, 2, value, mp_.tcache_max_bytes);
      mp_.tcache_max_bytes = value;
      mp_.tcache_bins = csize2tidx (request2size(value)) + 1;
      return 1;
    }
  return 0;
}

static __always_inline int
do_set_tcache_count (size_t value)
{
  if (value <= MAX_TCACHE_COUNT)
    {
      LIBC_PROBE (memory_tunable_tcache_count, 2, value, mp_.tcache_count);
      mp_.tcache_count = value;
      return 1;
    }
  return 0;
}

static __always_inline int
do_set_tcache_unsorted_limit (size_t value)
{
  LIBC_PROBE (memory_tunable_tcache_unsorted_limit, 2, value, mp_.tcache_unsorted_limit);
  mp_.tcache_unsorted_limit = value;
  return 1;
}
#endif

static __always_inline int
do_set_mxfast (size_t value)
{
  if (value <= MAX_FAST_SIZE)
    {
      LIBC_PROBE (memory_mallopt_mxfast, 2, value, get_max_fast ());
      set_max_fast (value);
      return 1;
    }
  return 0;
}

#if HAVE_TUNABLES
static __always_inline int
do_set_hugetlb (size_t value)
{
  if (value == 1)
    {
      enum malloc_thp_mode_t thp_mode = __malloc_thp_mode ();
      /*
	 Only enable THP madvise usage if system does support it and
	 has 'madvise' mode.  Otherwise the madvise() call is wasteful.
       */
      if (thp_mode == malloc_thp_mode_madvise)
	mp_.thp_pagesize = __malloc_default_thp_pagesize ();
    }
  else if (value >= 2)
    __malloc_hugepage_config (value == 2 ? 0 : value, &mp_.hp_pagesize,
			      &mp_.hp_flags);
  return 0;
}
#endif

int
__libc_mallopt (int param_number, int value)
{
  mstate av = &main_arena;
  int res = 1;

  if (!__malloc_initialized)
    ptmalloc_init ();
  __libc_lock_lock (av->mutex);

  LIBC_PROBE (memory_mallopt, 2, param_number, value);

  /* We must consolidate main arena before changing max_fast
     (see definition of set_max_fast).  */
  malloc_consolidate (av);

  /* Many of these helper functions take a size_t.  We do not worry
     about overflow here, because negative int values will wrap to
     very large size_t values and the helpers have sufficient range
     checking for such conversions.  Many of these helpers are also
     used by the tunables macros in arena.c.  */

  switch (param_number)
    {
    case M_MXFAST:
      res = do_set_mxfast (value);
      break;

    case M_TRIM_THRESHOLD:
      res = do_set_trim_threshold (value);
      break;

    case M_TOP_PAD:
      res = do_set_top_pad (value);
      break;

    case M_MMAP_THRESHOLD:
      res = do_set_mmap_threshold (value);
      break;

    case M_MMAP_MAX:
      res = do_set_mmaps_max (value);
      break;

    case M_CHECK_ACTION:
      res = do_set_mallopt_check (value);
      break;

    case M_PERTURB:
      res = do_set_perturb_byte (value);
      break;

    case M_ARENA_TEST:
      if (value > 0)
	res = do_set_arena_test (value);
      break;

    case M_ARENA_MAX:
      if (value > 0)
	res = do_set_arena_max (value);
      break;
    }
  __libc_lock_unlock (av->mutex);
  return res;
}
libc_hidden_def (__libc_mallopt)


/*
   -------------------- 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, 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.

   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 *) ((((unsigned long) 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;
      }
   }

 */


/* Helper code.  */

extern char **__libc_argv attribute_hidden;

static void
malloc_printerr (const char *str)
{
#if IS_IN (libc)
  __libc_message ("%s\n", str);
#else
  __libc_fatal (str);
#endif
  __builtin_unreachable ();
}

#if IS_IN (libc)
/* We need a wrapper function for one of the additions of POSIX.  */
int
__posix_memalign (void **memptr, size_t alignment, size_t size)
{
  void *mem;

  if (!__malloc_initialized)
    ptmalloc_init ();

  /* Test whether the SIZE argument is valid.  It must be a power of
     two multiple of sizeof (void *).  */
  if (alignment % sizeof (void *) != 0
      || !powerof2 (alignment / sizeof (void *))
      || alignment == 0)
    return EINVAL;


  void *address = RETURN_ADDRESS (0);
  mem = _mid_memalign (alignment, size, address);

  if (mem != NULL)
    {
      *memptr = mem;
      return 0;
    }

  return ENOMEM;
}
weak_alias (__posix_memalign, posix_memalign)
#endif


int
__malloc_info (int options, FILE *fp)
{
  /* For now, at least.  */
  if (options != 0)
    return EINVAL;

  int n = 0;
  size_t total_nblocks = 0;
  size_t total_nfastblocks = 0;
  size_t total_avail = 0;
  size_t total_fastavail = 0;
  size_t total_system = 0;
  size_t total_max_system = 0;
  size_t total_aspace = 0;
  size_t total_aspace_mprotect = 0;



  if (!__malloc_initialized)
    ptmalloc_init ();

  fputs ("<malloc version=\"1\">\n", fp);

  /* Iterate over all arenas currently in use.  */
  mstate ar_ptr = &main_arena;
  do
    {
      fprintf (fp, "<heap nr=\"%d\">\n<sizes>\n", n++);

      size_t nblocks = 0;
      size_t nfastblocks = 0;
      size_t avail = 0;
      size_t fastavail = 0;
      struct
      {
	size_t from;
	size_t to;
	size_t total;
	size_t count;
      } sizes[NFASTBINS + NBINS - 1];
#define nsizes (sizeof (sizes) / sizeof (sizes[0]))

      __libc_lock_lock (ar_ptr->mutex);

      /* Account for top chunk.  The top-most available chunk is
	 treated specially and is never in any bin. See "initial_top"
	 comments.  */
      avail = chunksize (ar_ptr->top);
      nblocks = 1;  /* Top always exists.  */

      for (size_t i = 0; i < NFASTBINS; ++i)
	{
	  mchunkptr p = fastbin (ar_ptr, i);
	  if (p != NULL)
	    {
	      size_t nthissize = 0;
	      size_t thissize = chunksize (p);

	      while (p != NULL)
		{
		  if (__glibc_unlikely (misaligned_chunk (p)))
		    malloc_printerr ("__malloc_info(): "
				     "unaligned fastbin chunk detected");
		  ++nthissize;
		  p = REVEAL_PTR (p->fd);
		}

	      fastavail += nthissize * thissize;
	      nfastblocks += nthissize;
	      sizes[i].from = thissize - (MALLOC_ALIGNMENT - 1);
	      sizes[i].to = thissize;
	      sizes[i].count = nthissize;
	    }
	  else
	    sizes[i].from = sizes[i].to = sizes[i].count = 0;

	  sizes[i].total = sizes[i].count * sizes[i].to;
	}


      mbinptr bin;
      struct malloc_chunk *r;

      for (size_t i = 1; i < NBINS; ++i)
	{
	  bin = bin_at (ar_ptr, i);
	  r = bin->fd;
	  sizes[NFASTBINS - 1 + i].from = ~((size_t) 0);
	  sizes[NFASTBINS - 1 + i].to = sizes[NFASTBINS - 1 + i].total
					  = sizes[NFASTBINS - 1 + i].count = 0;

	  if (r != NULL)
	    while (r != bin)
	      {
		size_t r_size = chunksize_nomask (r);
		++sizes[NFASTBINS - 1 + i].count;
		sizes[NFASTBINS - 1 + i].total += r_size;
		sizes[NFASTBINS - 1 + i].from
		  = MIN (sizes[NFASTBINS - 1 + i].from, r_size);
		sizes[NFASTBINS - 1 + i].to = MAX (sizes[NFASTBINS - 1 + i].to,
						   r_size);

		r = r->fd;
	      }

	  if (sizes[NFASTBINS - 1 + i].count == 0)
	    sizes[NFASTBINS - 1 + i].from = 0;
	  nblocks += sizes[NFASTBINS - 1 + i].count;
	  avail += sizes[NFASTBINS - 1 + i].total;
	}

      size_t heap_size = 0;
      size_t heap_mprotect_size = 0;
      size_t heap_count = 0;
      if (ar_ptr != &main_arena)
	{
	  /* Iterate over the arena heaps from back to front.  */
	  heap_info *heap = heap_for_ptr (top (ar_ptr));
	  do
	    {
	      heap_size += heap->size;
	      heap_mprotect_size += heap->mprotect_size;
	      heap = heap->prev;
	      ++heap_count;
	    }
	  while (heap != NULL);
	}

      __libc_lock_unlock (ar_ptr->mutex);

      total_nfastblocks += nfastblocks;
      total_fastavail += fastavail;

      total_nblocks += nblocks;
      total_avail += avail;

      for (size_t i = 0; i < nsizes; ++i)
	if (sizes[i].count != 0 && i != NFASTBINS)
	  fprintf (fp, "\
  <size from=\"%zu\" to=\"%zu\" total=\"%zu\" count=\"%zu\"/>\n",
		   sizes[i].from, sizes[i].to, sizes[i].total, sizes[i].count);

      if (sizes[NFASTBINS].count != 0)
	fprintf (fp, "\
  <unsorted from=\"%zu\" to=\"%zu\" total=\"%zu\" count=\"%zu\"/>\n",
		 sizes[NFASTBINS].from, sizes[NFASTBINS].to,
		 sizes[NFASTBINS].total, sizes[NFASTBINS].count);

      total_system += ar_ptr->system_mem;
      total_max_system += ar_ptr->max_system_mem;

      fprintf (fp,
	       "</sizes>\n<total type=\"fast\" count=\"%zu\" size=\"%zu\"/>\n"
	       "<total type=\"rest\" count=\"%zu\" size=\"%zu\"/>\n"
	       "<system type=\"current\" size=\"%zu\"/>\n"
	       "<system type=\"max\" size=\"%zu\"/>\n",
	       nfastblocks, fastavail, nblocks, avail,
	       ar_ptr->system_mem, ar_ptr->max_system_mem);

      if (ar_ptr != &main_arena)
	{
	  fprintf (fp,
		   "<aspace type=\"total\" size=\"%zu\"/>\n"
		   "<aspace type=\"mprotect\" size=\"%zu\"/>\n"
		   "<aspace type=\"subheaps\" size=\"%zu\"/>\n",
		   heap_size, heap_mprotect_size, heap_count);
	  total_aspace += heap_size;
	  total_aspace_mprotect += heap_mprotect_size;
	}
      else
	{
	  fprintf (fp,
		   "<aspace type=\"total\" size=\"%zu\"/>\n"
		   "<aspace type=\"mprotect\" size=\"%zu\"/>\n",
		   ar_ptr->system_mem, ar_ptr->system_mem);
	  total_aspace += ar_ptr->system_mem;
	  total_aspace_mprotect += ar_ptr->system_mem;
	}

      fputs ("</heap>\n", fp);
      ar_ptr = ar_ptr->next;
    }
  while (ar_ptr != &main_arena);

  fprintf (fp,
	   "<total type=\"fast\" count=\"%zu\" size=\"%zu\"/>\n"
	   "<total type=\"rest\" count=\"%zu\" size=\"%zu\"/>\n"
	   "<total type=\"mmap\" count=\"%d\" size=\"%zu\"/>\n"
	   "<system type=\"current\" size=\"%zu\"/>\n"
	   "<system type=\"max\" size=\"%zu\"/>\n"
	   "<aspace type=\"total\" size=\"%zu\"/>\n"
	   "<aspace type=\"mprotect\" size=\"%zu\"/>\n"
	   "</malloc>\n",
	   total_nfastblocks, total_fastavail, total_nblocks, total_avail,
	   mp_.n_mmaps, mp_.mmapped_mem,
	   total_system, total_max_system,
	   total_aspace, total_aspace_mprotect);

  return 0;
}
#if IS_IN (libc)
weak_alias (__malloc_info, malloc_info)

strong_alias (__libc_calloc, __calloc) weak_alias (__libc_calloc, calloc)
strong_alias (__libc_free, __free) strong_alias (__libc_free, free)
strong_alias (__libc_malloc, __malloc) strong_alias (__libc_malloc, malloc)
strong_alias (__libc_memalign, __memalign)
weak_alias (__libc_memalign, memalign)
strong_alias (__libc_realloc, __realloc) strong_alias (__libc_realloc, realloc)
strong_alias (__libc_valloc, __valloc) weak_alias (__libc_valloc, valloc)
strong_alias (__libc_pvalloc, __pvalloc) weak_alias (__libc_pvalloc, pvalloc)
strong_alias (__libc_mallinfo, __mallinfo)
weak_alias (__libc_mallinfo, mallinfo)
strong_alias (__libc_mallinfo2, __mallinfo2)
weak_alias (__libc_mallinfo2, mallinfo2)
strong_alias (__libc_mallopt, __mallopt) weak_alias (__libc_mallopt, mallopt)

weak_alias (__malloc_stats, malloc_stats)
weak_alias (__malloc_usable_size, malloc_usable_size)
weak_alias (__malloc_trim, malloc_trim)
#endif

#if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_26)
compat_symbol (libc, __libc_free, cfree, GLIBC_2_0);
#endif

/* ------------------------------------------------------------
   History:

   [see ftp://g.oswego.edu/pub/misc/malloc.c for the history of dlmalloc]

 */
/*
 * Local variables:
 * c-basic-offset: 2
 * End:
 */