summaryrefslogtreecommitdiff
path: root/mm/vmalloc.c
blob: d33894d7b27a1d1a1c42b3982d65b08108cf1c58 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 1993  Linus Torvalds
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
 *  Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
 *  Numa awareness, Christoph Lameter, SGI, June 2005
 *  Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019
 */

#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/set_memory.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/llist.h>
#include <linux/bitops.h>
#include <linux/rbtree_augmented.h>
#include <linux/overflow.h>
#include <linux/pgtable.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>

#include "internal.h"
#include "pgalloc-track.h"

#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
static bool __ro_after_init vmap_allow_huge = true;

static int __init set_nohugevmalloc(char *str)
{
	vmap_allow_huge = false;
	return 0;
}
early_param("nohugevmalloc", set_nohugevmalloc);
#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
static const bool vmap_allow_huge = false;
#endif	/* CONFIG_HAVE_ARCH_HUGE_VMALLOC */

bool is_vmalloc_addr(const void *x)
{
	unsigned long addr = (unsigned long)x;

	return addr >= VMALLOC_START && addr < VMALLOC_END;
}
EXPORT_SYMBOL(is_vmalloc_addr);

struct vfree_deferred {
	struct llist_head list;
	struct work_struct wq;
};
static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);

static void __vunmap(const void *, int);

static void free_work(struct work_struct *w)
{
	struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
	struct llist_node *t, *llnode;

	llist_for_each_safe(llnode, t, llist_del_all(&p->list))
		__vunmap((void *)llnode, 1);
}

/*** Page table manipulation functions ***/
static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			pgtbl_mod_mask *mask)
{
	pte_t *pte;
	u64 pfn;

	pfn = phys_addr >> PAGE_SHIFT;
	pte = pte_alloc_kernel_track(pmd, addr, mask);
	if (!pte)
		return -ENOMEM;
	do {
		BUG_ON(!pte_none(*pte));
		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	*mask |= PGTBL_PTE_MODIFIED;
	return 0;
}

static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	if (max_page_shift < PMD_SHIFT)
		return 0;

	if (!arch_vmap_pmd_supported(prot))
		return 0;

	if ((end - addr) != PMD_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, PMD_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
		return 0;

	if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
		return 0;

	return pmd_set_huge(pmd, phys_addr, prot);
}

static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);

		if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
					max_page_shift)) {
			*mask |= PGTBL_PMD_MODIFIED;
			continue;
		}

		if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
			return -ENOMEM;
	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
	return 0;
}

static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	if (max_page_shift < PUD_SHIFT)
		return 0;

	if (!arch_vmap_pud_supported(prot))
		return 0;

	if ((end - addr) != PUD_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, PUD_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
		return 0;

	if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
		return 0;

	return pud_set_huge(pud, phys_addr, prot);
}

static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);

		if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
					max_page_shift)) {
			*mask |= PGTBL_PUD_MODIFIED;
			continue;
		}

		if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
					max_page_shift, mask))
			return -ENOMEM;
	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
	return 0;
}

static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	if (max_page_shift < P4D_SHIFT)
		return 0;

	if (!arch_vmap_p4d_supported(prot))
		return 0;

	if ((end - addr) != P4D_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, P4D_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
		return 0;

	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
		return 0;

	return p4d_set_huge(p4d, phys_addr, prot);
}

static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
	if (!p4d)
		return -ENOMEM;
	do {
		next = p4d_addr_end(addr, end);

		if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
					max_page_shift)) {
			*mask |= PGTBL_P4D_MODIFIED;
			continue;
		}

		if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
					max_page_shift, mask))
			return -ENOMEM;
	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
	return 0;
}

static int vmap_range_noflush(unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	pgd_t *pgd;
	unsigned long start;
	unsigned long next;
	int err;
	pgtbl_mod_mask mask = 0;

	might_sleep();
	BUG_ON(addr >= end);

	start = addr;
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
					max_page_shift, &mask);
		if (err)
			break;
	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);

	return err;
}

int vmap_range(unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	int err;

	err = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift);
	flush_cache_vmap(addr, end);

	return err;
}

static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	pte_t *pte;

	pte = pte_offset_kernel(pmd, addr);
	do {
		pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte);
		WARN_ON(!pte_none(ptent) && !pte_present(ptent));
	} while (pte++, addr += PAGE_SIZE, addr != end);
	*mask |= PGTBL_PTE_MODIFIED;
}

static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;
	int cleared;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);

		cleared = pmd_clear_huge(pmd);
		if (cleared || pmd_bad(*pmd))
			*mask |= PGTBL_PMD_MODIFIED;

		if (cleared)
			continue;
		if (pmd_none_or_clear_bad(pmd))
			continue;
		vunmap_pte_range(pmd, addr, next, mask);

		cond_resched();
	} while (pmd++, addr = next, addr != end);
}

static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;
	int cleared;

	pud = pud_offset(p4d, addr);
	do {
		next = pud_addr_end(addr, end);

		cleared = pud_clear_huge(pud);
		if (cleared || pud_bad(*pud))
			*mask |= PGTBL_PUD_MODIFIED;

		if (cleared)
			continue;
		if (pud_none_or_clear_bad(pud))
			continue;
		vunmap_pmd_range(pud, addr, next, mask);
	} while (pud++, addr = next, addr != end);
}

static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;
	int cleared;

	p4d = p4d_offset(pgd, addr);
	do {
		next = p4d_addr_end(addr, end);

		cleared = p4d_clear_huge(p4d);
		if (cleared || p4d_bad(*p4d))
			*mask |= PGTBL_P4D_MODIFIED;

		if (cleared)
			continue;
		if (p4d_none_or_clear_bad(p4d))
			continue;
		vunmap_pud_range(p4d, addr, next, mask);
	} while (p4d++, addr = next, addr != end);
}

/*
 * vunmap_range_noflush is similar to vunmap_range, but does not
 * flush caches or TLBs.
 *
 * The caller is responsible for calling flush_cache_vmap() before calling
 * this function, and flush_tlb_kernel_range after it has returned
 * successfully (and before the addresses are expected to cause a page fault
 * or be re-mapped for something else, if TLB flushes are being delayed or
 * coalesced).
 *
 * This is an internal function only. Do not use outside mm/.
 */
void vunmap_range_noflush(unsigned long start, unsigned long end)
{
	unsigned long next;
	pgd_t *pgd;
	unsigned long addr = start;
	pgtbl_mod_mask mask = 0;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_bad(*pgd))
			mask |= PGTBL_PGD_MODIFIED;
		if (pgd_none_or_clear_bad(pgd))
			continue;
		vunmap_p4d_range(pgd, addr, next, &mask);
	} while (pgd++, addr = next, addr != end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);
}

/**
 * vunmap_range - unmap kernel virtual addresses
 * @addr: start of the VM area to unmap
 * @end: end of the VM area to unmap (non-inclusive)
 *
 * Clears any present PTEs in the virtual address range, flushes TLBs and
 * caches. Any subsequent access to the address before it has been re-mapped
 * is a kernel bug.
 */
void vunmap_range(unsigned long addr, unsigned long end)
{
	flush_cache_vunmap(addr, end);
	vunmap_range_noflush(addr, end);
	flush_tlb_kernel_range(addr, end);
}

static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	pte_t *pte;

	/*
	 * nr is a running index into the array which helps higher level
	 * callers keep track of where we're up to.
	 */

	pte = pte_alloc_kernel_track(pmd, addr, mask);
	if (!pte)
		return -ENOMEM;
	do {
		struct page *page = pages[*nr];

		if (WARN_ON(!pte_none(*pte)))
			return -EBUSY;
		if (WARN_ON(!page))
			return -ENOMEM;
		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
		(*nr)++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	*mask |= PGTBL_PTE_MODIFIED;
	return 0;
}

static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
	if (!p4d)
		return -ENOMEM;
	do {
		next = p4d_addr_end(addr, end);
		if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask))
			return -ENOMEM;
	} while (p4d++, addr = next, addr != end);
	return 0;
}

static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages)
{
	unsigned long start = addr;
	pgd_t *pgd;
	unsigned long next;
	int err = 0;
	int nr = 0;
	pgtbl_mod_mask mask = 0;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_bad(*pgd))
			mask |= PGTBL_PGD_MODIFIED;
		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
		if (err)
			return err;
	} while (pgd++, addr = next, addr != end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);

	return 0;
}

/*
 * vmap_pages_range_noflush is similar to vmap_pages_range, but does not
 * flush caches.
 *
 * The caller is responsible for calling flush_cache_vmap() after this
 * function returns successfully and before the addresses are accessed.
 *
 * This is an internal function only. Do not use outside mm/.
 */
int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages, unsigned int page_shift)
{
	unsigned int i, nr = (end - addr) >> PAGE_SHIFT;

	WARN_ON(page_shift < PAGE_SHIFT);

	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
			page_shift == PAGE_SHIFT)
		return vmap_small_pages_range_noflush(addr, end, prot, pages);

	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
		int err;

		err = vmap_range_noflush(addr, addr + (1UL << page_shift),
					__pa(page_address(pages[i])), prot,
					page_shift);
		if (err)
			return err;

		addr += 1UL << page_shift;
	}

	return 0;
}

/**
 * vmap_pages_range - map pages to a kernel virtual address
 * @addr: start of the VM area to map
 * @end: end of the VM area to map (non-inclusive)
 * @prot: page protection flags to use
 * @pages: pages to map (always PAGE_SIZE pages)
 * @page_shift: maximum shift that the pages may be mapped with, @pages must
 * be aligned and contiguous up to at least this shift.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
static int vmap_pages_range(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages, unsigned int page_shift)
{
	int err;

	err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
	flush_cache_vmap(addr, end);
	return err;
}

int is_vmalloc_or_module_addr(const void *x)
{
	/*
	 * ARM, x86-64 and sparc64 put modules in a special place,
	 * and fall back on vmalloc() if that fails. Others
	 * just put it in the vmalloc space.
	 */
#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
	unsigned long addr = (unsigned long)x;
	if (addr >= MODULES_VADDR && addr < MODULES_END)
		return 1;
#endif
	return is_vmalloc_addr(x);
}

/*
 * Walk a vmap address to the struct page it maps. Huge vmap mappings will
 * return the tail page that corresponds to the base page address, which
 * matches small vmap mappings.
 */
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
	unsigned long addr = (unsigned long) vmalloc_addr;
	struct page *page = NULL;
	pgd_t *pgd = pgd_offset_k(addr);
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;

	/*
	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
	 * architectures that do not vmalloc module space
	 */
	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));

	if (pgd_none(*pgd))
		return NULL;
	if (WARN_ON_ONCE(pgd_leaf(*pgd)))
		return NULL; /* XXX: no allowance for huge pgd */
	if (WARN_ON_ONCE(pgd_bad(*pgd)))
		return NULL;

	p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d))
		return NULL;
	if (p4d_leaf(*p4d))
		return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
	if (WARN_ON_ONCE(p4d_bad(*p4d)))
		return NULL;

	pud = pud_offset(p4d, addr);
	if (pud_none(*pud))
		return NULL;
	if (pud_leaf(*pud))
		return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
	if (WARN_ON_ONCE(pud_bad(*pud)))
		return NULL;

	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return NULL;
	if (pmd_leaf(*pmd))
		return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	if (WARN_ON_ONCE(pmd_bad(*pmd)))
		return NULL;

	ptep = pte_offset_map(pmd, addr);
	pte = *ptep;
	if (pte_present(pte))
		page = pte_page(pte);
	pte_unmap(ptep);

	return page;
}
EXPORT_SYMBOL(vmalloc_to_page);

/*
 * Map a vmalloc()-space virtual address to the physical page frame number.
 */
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
{
	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);


/*** Global kva allocator ***/

#define DEBUG_AUGMENT_PROPAGATE_CHECK 0
#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0


static DEFINE_SPINLOCK(vmap_area_lock);
static DEFINE_SPINLOCK(free_vmap_area_lock);
/* Export for kexec only */
LIST_HEAD(vmap_area_list);
static struct rb_root vmap_area_root = RB_ROOT;
static bool vmap_initialized __read_mostly;

static struct rb_root purge_vmap_area_root = RB_ROOT;
static LIST_HEAD(purge_vmap_area_list);
static DEFINE_SPINLOCK(purge_vmap_area_lock);

/*
 * This kmem_cache is used for vmap_area objects. Instead of
 * allocating from slab we reuse an object from this cache to
 * make things faster. Especially in "no edge" splitting of
 * free block.
 */
static struct kmem_cache *vmap_area_cachep;

/*
 * This linked list is used in pair with free_vmap_area_root.
 * It gives O(1) access to prev/next to perform fast coalescing.
 */
static LIST_HEAD(free_vmap_area_list);

/*
 * This augment red-black tree represents the free vmap space.
 * All vmap_area objects in this tree are sorted by va->va_start
 * address. It is used for allocation and merging when a vmap
 * object is released.
 *
 * Each vmap_area node contains a maximum available free block
 * of its sub-tree, right or left. Therefore it is possible to
 * find a lowest match of free area.
 */
static struct rb_root free_vmap_area_root = RB_ROOT;

/*
 * Preload a CPU with one object for "no edge" split case. The
 * aim is to get rid of allocations from the atomic context, thus
 * to use more permissive allocation masks.
 */
static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);

static __always_inline unsigned long
va_size(struct vmap_area *va)
{
	return (va->va_end - va->va_start);
}

static __always_inline unsigned long
get_subtree_max_size(struct rb_node *node)
{
	struct vmap_area *va;

	va = rb_entry_safe(node, struct vmap_area, rb_node);
	return va ? va->subtree_max_size : 0;
}

/*
 * Gets called when remove the node and rotate.
 */
static __always_inline unsigned long
compute_subtree_max_size(struct vmap_area *va)
{
	return max3(va_size(va),
		get_subtree_max_size(va->rb_node.rb_left),
		get_subtree_max_size(va->rb_node.rb_right));
}

RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb,
	struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size)

static void purge_vmap_area_lazy(void);
static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
static unsigned long lazy_max_pages(void);

static atomic_long_t nr_vmalloc_pages;

unsigned long vmalloc_nr_pages(void)
{
	return atomic_long_read(&nr_vmalloc_pages);
}

static struct vmap_area *__find_vmap_area(unsigned long addr)
{
	struct rb_node *n = vmap_area_root.rb_node;

	while (n) {
		struct vmap_area *va;

		va = rb_entry(n, struct vmap_area, rb_node);
		if (addr < va->va_start)
			n = n->rb_left;
		else if (addr >= va->va_end)
			n = n->rb_right;
		else
			return va;
	}

	return NULL;
}

/*
 * This function returns back addresses of parent node
 * and its left or right link for further processing.
 *
 * Otherwise NULL is returned. In that case all further
 * steps regarding inserting of conflicting overlap range
 * have to be declined and actually considered as a bug.
 */
static __always_inline struct rb_node **
find_va_links(struct vmap_area *va,
	struct rb_root *root, struct rb_node *from,
	struct rb_node **parent)
{
	struct vmap_area *tmp_va;
	struct rb_node **link;

	if (root) {
		link = &root->rb_node;
		if (unlikely(!*link)) {
			*parent = NULL;
			return link;
		}
	} else {
		link = &from;
	}

	/*
	 * Go to the bottom of the tree. When we hit the last point
	 * we end up with parent rb_node and correct direction, i name
	 * it link, where the new va->rb_node will be attached to.
	 */
	do {
		tmp_va = rb_entry(*link, struct vmap_area, rb_node);

		/*
		 * During the traversal we also do some sanity check.
		 * Trigger the BUG() if there are sides(left/right)
		 * or full overlaps.
		 */
		if (va->va_start < tmp_va->va_end &&
				va->va_end <= tmp_va->va_start)
			link = &(*link)->rb_left;
		else if (va->va_end > tmp_va->va_start &&
				va->va_start >= tmp_va->va_end)
			link = &(*link)->rb_right;
		else {
			WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n",
				va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end);

			return NULL;
		}
	} while (*link);

	*parent = &tmp_va->rb_node;
	return link;
}

static __always_inline struct list_head *
get_va_next_sibling(struct rb_node *parent, struct rb_node **link)
{
	struct list_head *list;

	if (unlikely(!parent))
		/*
		 * The red-black tree where we try to find VA neighbors
		 * before merging or inserting is empty, i.e. it means
		 * there is no free vmap space. Normally it does not
		 * happen but we handle this case anyway.
		 */
		return NULL;

	list = &rb_entry(parent, struct vmap_area, rb_node)->list;
	return (&parent->rb_right == link ? list->next : list);
}

static __always_inline void
link_va(struct vmap_area *va, struct rb_root *root,
	struct rb_node *parent, struct rb_node **link, struct list_head *head)
{
	/*
	 * VA is still not in the list, but we can
	 * identify its future previous list_head node.
	 */
	if (likely(parent)) {
		head = &rb_entry(parent, struct vmap_area, rb_node)->list;
		if (&parent->rb_right != link)
			head = head->prev;
	}

	/* Insert to the rb-tree */
	rb_link_node(&va->rb_node, parent, link);
	if (root == &free_vmap_area_root) {
		/*
		 * Some explanation here. Just perform simple insertion
		 * to the tree. We do not set va->subtree_max_size to
		 * its current size before calling rb_insert_augmented().
		 * It is because of we populate the tree from the bottom
		 * to parent levels when the node _is_ in the tree.
		 *
		 * Therefore we set subtree_max_size to zero after insertion,
		 * to let __augment_tree_propagate_from() puts everything to
		 * the correct order later on.
		 */
		rb_insert_augmented(&va->rb_node,
			root, &free_vmap_area_rb_augment_cb);
		va->subtree_max_size = 0;
	} else {
		rb_insert_color(&va->rb_node, root);
	}

	/* Address-sort this list */
	list_add(&va->list, head);
}

static __always_inline void
unlink_va(struct vmap_area *va, struct rb_root *root)
{
	if (WARN_ON(RB_EMPTY_NODE(&va->rb_node)))
		return;

	if (root == &free_vmap_area_root)
		rb_erase_augmented(&va->rb_node,
			root, &free_vmap_area_rb_augment_cb);
	else
		rb_erase(&va->rb_node, root);

	list_del(&va->list);
	RB_CLEAR_NODE(&va->rb_node);
}

#if DEBUG_AUGMENT_PROPAGATE_CHECK
static void
augment_tree_propagate_check(void)
{
	struct vmap_area *va;
	unsigned long computed_size;

	list_for_each_entry(va, &free_vmap_area_list, list) {
		computed_size = compute_subtree_max_size(va);
		if (computed_size != va->subtree_max_size)
			pr_emerg("tree is corrupted: %lu, %lu\n",
				va_size(va), va->subtree_max_size);
	}
}
#endif

/*
 * This function populates subtree_max_size from bottom to upper
 * levels starting from VA point. The propagation must be done
 * when VA size is modified by changing its va_start/va_end. Or
 * in case of newly inserting of VA to the tree.
 *
 * It means that __augment_tree_propagate_from() must be called:
 * - After VA has been inserted to the tree(free path);
 * - After VA has been shrunk(allocation path);
 * - After VA has been increased(merging path).
 *
 * Please note that, it does not mean that upper parent nodes
 * and their subtree_max_size are recalculated all the time up
 * to the root node.
 *
 *       4--8
 *        /\
 *       /  \
 *      /    \
 *    2--2  8--8
 *
 * For example if we modify the node 4, shrinking it to 2, then
 * no any modification is required. If we shrink the node 2 to 1
 * its subtree_max_size is updated only, and set to 1. If we shrink
 * the node 8 to 6, then its subtree_max_size is set to 6 and parent
 * node becomes 4--6.
 */
static __always_inline void
augment_tree_propagate_from(struct vmap_area *va)
{
	/*
	 * Populate the tree from bottom towards the root until
	 * the calculated maximum available size of checked node
	 * is equal to its current one.
	 */
	free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL);

#if DEBUG_AUGMENT_PROPAGATE_CHECK
	augment_tree_propagate_check();
#endif
}

static void
insert_vmap_area(struct vmap_area *va,
	struct rb_root *root, struct list_head *head)
{
	struct rb_node **link;
	struct rb_node *parent;

	link = find_va_links(va, root, NULL, &parent);
	if (link)
		link_va(va, root, parent, link, head);
}

static void
insert_vmap_area_augment(struct vmap_area *va,
	struct rb_node *from, struct rb_root *root,
	struct list_head *head)
{
	struct rb_node **link;
	struct rb_node *parent;

	if (from)
		link = find_va_links(va, NULL, from, &parent);
	else
		link = find_va_links(va, root, NULL, &parent);

	if (link) {
		link_va(va, root, parent, link, head);
		augment_tree_propagate_from(va);
	}
}

/*
 * Merge de-allocated chunk of VA memory with previous
 * and next free blocks. If coalesce is not done a new
 * free area is inserted. If VA has been merged, it is
 * freed.
 *
 * Please note, it can return NULL in case of overlap
 * ranges, followed by WARN() report. Despite it is a
 * buggy behaviour, a system can be alive and keep
 * ongoing.
 */
static __always_inline struct vmap_area *
merge_or_add_vmap_area(struct vmap_area *va,
	struct rb_root *root, struct list_head *head)
{
	struct vmap_area *sibling;
	struct list_head *next;
	struct rb_node **link;
	struct rb_node *parent;
	bool merged = false;

	/*
	 * Find a place in the tree where VA potentially will be
	 * inserted, unless it is merged with its sibling/siblings.
	 */
	link = find_va_links(va, root, NULL, &parent);
	if (!link)
		return NULL;

	/*
	 * Get next node of VA to check if merging can be done.
	 */
	next = get_va_next_sibling(parent, link);
	if (unlikely(next == NULL))
		goto insert;

	/*
	 * start            end
	 * |                |
	 * |<------VA------>|<-----Next----->|
	 *                  |                |
	 *                  start            end
	 */
	if (next != head) {
		sibling = list_entry(next, struct vmap_area, list);
		if (sibling->va_start == va->va_end) {
			sibling->va_start = va->va_start;

			/* Free vmap_area object. */
			kmem_cache_free(vmap_area_cachep, va);

			/* Point to the new merged area. */
			va = sibling;
			merged = true;
		}
	}

	/*
	 * start            end
	 * |                |
	 * |<-----Prev----->|<------VA------>|
	 *                  |                |
	 *                  start            end
	 */
	if (next->prev != head) {
		sibling = list_entry(next->prev, struct vmap_area, list);
		if (sibling->va_end == va->va_start) {
			/*
			 * If both neighbors are coalesced, it is important
			 * to unlink the "next" node first, followed by merging
			 * with "previous" one. Otherwise the tree might not be
			 * fully populated if a sibling's augmented value is
			 * "normalized" because of rotation operations.
			 */
			if (merged)
				unlink_va(va, root);

			sibling->va_end = va->va_end;

			/* Free vmap_area object. */
			kmem_cache_free(vmap_area_cachep, va);

			/* Point to the new merged area. */
			va = sibling;
			merged = true;
		}
	}

insert:
	if (!merged)
		link_va(va, root, parent, link, head);

	return va;
}

static __always_inline struct vmap_area *
merge_or_add_vmap_area_augment(struct vmap_area *va,
	struct rb_root *root, struct list_head *head)
{
	va = merge_or_add_vmap_area(va, root, head);
	if (va)
		augment_tree_propagate_from(va);

	return va;
}

static __always_inline bool
is_within_this_va(struct vmap_area *va, unsigned long size,
	unsigned long align, unsigned long vstart)
{
	unsigned long nva_start_addr;

	if (va->va_start > vstart)
		nva_start_addr = ALIGN(va->va_start, align);
	else
		nva_start_addr = ALIGN(vstart, align);

	/* Can be overflowed due to big size or alignment. */
	if (nva_start_addr + size < nva_start_addr ||
			nva_start_addr < vstart)
		return false;

	return (nva_start_addr + size <= va->va_end);
}

/*
 * Find the first free block(lowest start address) in the tree,
 * that will accomplish the request corresponding to passing
 * parameters.
 */
static __always_inline struct vmap_area *
find_vmap_lowest_match(unsigned long size,
	unsigned long align, unsigned long vstart)
{
	struct vmap_area *va;
	struct rb_node *node;
	unsigned long length;

	/* Start from the root. */
	node = free_vmap_area_root.rb_node;

	/* Adjust the search size for alignment overhead. */
	length = size + align - 1;

	while (node) {
		va = rb_entry(node, struct vmap_area, rb_node);

		if (get_subtree_max_size(node->rb_left) >= length &&
				vstart < va->va_start) {
			node = node->rb_left;
		} else {
			if (is_within_this_va(va, size, align, vstart))
				return va;

			/*
			 * Does not make sense to go deeper towards the right
			 * sub-tree if it does not have a free block that is
			 * equal or bigger to the requested search length.
			 */
			if (get_subtree_max_size(node->rb_right) >= length) {
				node = node->rb_right;
				continue;
			}

			/*
			 * OK. We roll back and find the first right sub-tree,
			 * that will satisfy the search criteria. It can happen
			 * only once due to "vstart" restriction.
			 */
			while ((node = rb_parent(node))) {
				va = rb_entry(node, struct vmap_area, rb_node);
				if (is_within_this_va(va, size, align, vstart))
					return va;

				if (get_subtree_max_size(node->rb_right) >= length &&
						vstart <= va->va_start) {
					node = node->rb_right;
					break;
				}
			}
		}
	}

	return NULL;
}

#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
#include <linux/random.h>

static struct vmap_area *
find_vmap_lowest_linear_match(unsigned long size,
	unsigned long align, unsigned long vstart)
{
	struct vmap_area *va;

	list_for_each_entry(va, &free_vmap_area_list, list) {
		if (!is_within_this_va(va, size, align, vstart))
			continue;

		return va;
	}

	return NULL;
}

static void
find_vmap_lowest_match_check(unsigned long size)
{
	struct vmap_area *va_1, *va_2;
	unsigned long vstart;
	unsigned int rnd;

	get_random_bytes(&rnd, sizeof(rnd));
	vstart = VMALLOC_START + rnd;

	va_1 = find_vmap_lowest_match(size, 1, vstart);
	va_2 = find_vmap_lowest_linear_match(size, 1, vstart);

	if (va_1 != va_2)
		pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n",
			va_1, va_2, vstart);
}
#endif

enum fit_type {
	NOTHING_FIT = 0,
	FL_FIT_TYPE = 1,	/* full fit */
	LE_FIT_TYPE = 2,	/* left edge fit */
	RE_FIT_TYPE = 3,	/* right edge fit */
	NE_FIT_TYPE = 4		/* no edge fit */
};

static __always_inline enum fit_type
classify_va_fit_type(struct vmap_area *va,
	unsigned long nva_start_addr, unsigned long size)
{
	enum fit_type type;

	/* Check if it is within VA. */
	if (nva_start_addr < va->va_start ||
			nva_start_addr + size > va->va_end)
		return NOTHING_FIT;

	/* Now classify. */
	if (va->va_start == nva_start_addr) {
		if (va->va_end == nva_start_addr + size)
			type = FL_FIT_TYPE;
		else
			type = LE_FIT_TYPE;
	} else if (va->va_end == nva_start_addr + size) {
		type = RE_FIT_TYPE;
	} else {
		type = NE_FIT_TYPE;
	}

	return type;
}

static __always_inline int
adjust_va_to_fit_type(struct vmap_area *va,
	unsigned long nva_start_addr, unsigned long size,
	enum fit_type type)
{
	struct vmap_area *lva = NULL;

	if (type == FL_FIT_TYPE) {
		/*
		 * No need to split VA, it fully fits.
		 *
		 * |               |
		 * V      NVA      V
		 * |---------------|
		 */
		unlink_va(va, &free_vmap_area_root);
		kmem_cache_free(vmap_area_cachep, va);
	} else if (type == LE_FIT_TYPE) {
		/*
		 * Split left edge of fit VA.
		 *
		 * |       |
		 * V  NVA  V   R
		 * |-------|-------|
		 */
		va->va_start += size;
	} else if (type == RE_FIT_TYPE) {
		/*
		 * Split right edge of fit VA.
		 *
		 *         |       |
		 *     L   V  NVA  V
		 * |-------|-------|
		 */
		va->va_end = nva_start_addr;
	} else if (type == NE_FIT_TYPE) {
		/*
		 * Split no edge of fit VA.
		 *
		 *     |       |
		 *   L V  NVA  V R
		 * |---|-------|---|
		 */
		lva = __this_cpu_xchg(ne_fit_preload_node, NULL);
		if (unlikely(!lva)) {
			/*
			 * For percpu allocator we do not do any pre-allocation
			 * and leave it as it is. The reason is it most likely
			 * never ends up with NE_FIT_TYPE splitting. In case of
			 * percpu allocations offsets and sizes are aligned to
			 * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE
			 * are its main fitting cases.
			 *
			 * There are a few exceptions though, as an example it is
			 * a first allocation (early boot up) when we have "one"
			 * big free space that has to be split.
			 *
			 * Also we can hit this path in case of regular "vmap"
			 * allocations, if "this" current CPU was not preloaded.
			 * See the comment in alloc_vmap_area() why. If so, then
			 * GFP_NOWAIT is used instead to get an extra object for
			 * split purpose. That is rare and most time does not
			 * occur.
			 *
			 * What happens if an allocation gets failed. Basically,
			 * an "overflow" path is triggered to purge lazily freed
			 * areas to free some memory, then, the "retry" path is
			 * triggered to repeat one more time. See more details
			 * in alloc_vmap_area() function.
			 */
			lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
			if (!lva)
				return -1;
		}

		/*
		 * Build the remainder.
		 */
		lva->va_start = va->va_start;
		lva->va_end = nva_start_addr;

		/*
		 * Shrink this VA to remaining size.
		 */
		va->va_start = nva_start_addr + size;
	} else {
		return -1;
	}

	if (type != FL_FIT_TYPE) {
		augment_tree_propagate_from(va);

		if (lva)	/* type == NE_FIT_TYPE */
			insert_vmap_area_augment(lva, &va->rb_node,
				&free_vmap_area_root, &free_vmap_area_list);
	}

	return 0;
}

/*
 * Returns a start address of the newly allocated area, if success.
 * Otherwise a vend is returned that indicates failure.
 */
static __always_inline unsigned long
__alloc_vmap_area(unsigned long size, unsigned long align,
	unsigned long vstart, unsigned long vend)
{
	unsigned long nva_start_addr;
	struct vmap_area *va;
	enum fit_type type;
	int ret;

	va = find_vmap_lowest_match(size, align, vstart);
	if (unlikely(!va))
		return vend;

	if (va->va_start > vstart)
		nva_start_addr = ALIGN(va->va_start, align);
	else
		nva_start_addr = ALIGN(vstart, align);

	/* Check the "vend" restriction. */
	if (nva_start_addr + size > vend)
		return vend;

	/* Classify what we have found. */
	type = classify_va_fit_type(va, nva_start_addr, size);
	if (WARN_ON_ONCE(type == NOTHING_FIT))
		return vend;

	/* Update the free vmap_area. */
	ret = adjust_va_to_fit_type(va, nva_start_addr, size, type);
	if (ret)
		return vend;

#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
	find_vmap_lowest_match_check(size);
#endif

	return nva_start_addr;
}

/*
 * Free a region of KVA allocated by alloc_vmap_area
 */
static void free_vmap_area(struct vmap_area *va)
{
	/*
	 * Remove from the busy tree/list.
	 */
	spin_lock(&vmap_area_lock);
	unlink_va(va, &vmap_area_root);
	spin_unlock(&vmap_area_lock);

	/*
	 * Insert/Merge it back to the free tree/list.
	 */
	spin_lock(&free_vmap_area_lock);
	merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list);
	spin_unlock(&free_vmap_area_lock);
}

static inline void
preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node)
{
	struct vmap_area *va = NULL;

	/*
	 * Preload this CPU with one extra vmap_area object. It is used
	 * when fit type of free area is NE_FIT_TYPE. It guarantees that
	 * a CPU that does an allocation is preloaded.
	 *
	 * We do it in non-atomic context, thus it allows us to use more
	 * permissive allocation masks to be more stable under low memory
	 * condition and high memory pressure.
	 */
	if (!this_cpu_read(ne_fit_preload_node))
		va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);

	spin_lock(lock);

	if (va && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, va))
		kmem_cache_free(vmap_area_cachep, va);
}

/*
 * Allocate a region of KVA of the specified size and alignment, within the
 * vstart and vend.
 */
static struct vmap_area *alloc_vmap_area(unsigned long size,
				unsigned long align,
				unsigned long vstart, unsigned long vend,
				int node, gfp_t gfp_mask)
{
	struct vmap_area *va;
	unsigned long addr;
	int purged = 0;
	int ret;

	BUG_ON(!size);
	BUG_ON(offset_in_page(size));
	BUG_ON(!is_power_of_2(align));

	if (unlikely(!vmap_initialized))
		return ERR_PTR(-EBUSY);

	might_sleep();
	gfp_mask = gfp_mask & GFP_RECLAIM_MASK;

	va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
	if (unlikely(!va))
		return ERR_PTR(-ENOMEM);

	/*
	 * Only scan the relevant parts containing pointers to other objects
	 * to avoid false negatives.
	 */
	kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask);

retry:
	preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node);
	addr = __alloc_vmap_area(size, align, vstart, vend);
	spin_unlock(&free_vmap_area_lock);

	/*
	 * If an allocation fails, the "vend" address is
	 * returned. Therefore trigger the overflow path.
	 */
	if (unlikely(addr == vend))
		goto overflow;

	va->va_start = addr;
	va->va_end = addr + size;
	va->vm = NULL;

	spin_lock(&vmap_area_lock);
	insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
	spin_unlock(&vmap_area_lock);

	BUG_ON(!IS_ALIGNED(va->va_start, align));
	BUG_ON(va->va_start < vstart);
	BUG_ON(va->va_end > vend);

	ret = kasan_populate_vmalloc(addr, size);
	if (ret) {
		free_vmap_area(va);
		return ERR_PTR(ret);
	}

	return va;

overflow:
	if (!purged) {
		purge_vmap_area_lazy();
		purged = 1;
		goto retry;
	}

	if (gfpflags_allow_blocking(gfp_mask)) {
		unsigned long freed = 0;
		blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
		if (freed > 0) {
			purged = 0;
			goto retry;
		}
	}

	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
		pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
			size);

	kmem_cache_free(vmap_area_cachep, va);
	return ERR_PTR(-EBUSY);
}

int register_vmap_purge_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_vmap_purge_notifier);

int unregister_vmap_purge_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);

/*
 * lazy_max_pages is the maximum amount of virtual address space we gather up
 * before attempting to purge with a TLB flush.
 *
 * There is a tradeoff here: a larger number will cover more kernel page tables
 * and take slightly longer to purge, but it will linearly reduce the number of
 * global TLB flushes that must be performed. It would seem natural to scale
 * this number up linearly with the number of CPUs (because vmapping activity
 * could also scale linearly with the number of CPUs), however it is likely
 * that in practice, workloads might be constrained in other ways that mean
 * vmap activity will not scale linearly with CPUs. Also, I want to be
 * conservative and not introduce a big latency on huge systems, so go with
 * a less aggressive log scale. It will still be an improvement over the old
 * code, and it will be simple to change the scale factor if we find that it
 * becomes a problem on bigger systems.
 */
static unsigned long lazy_max_pages(void)
{
	unsigned int log;

	log = fls(num_online_cpus());

	return log * (32UL * 1024 * 1024 / PAGE_SIZE);
}

static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0);

/*
 * Serialize vmap purging.  There is no actual criticial section protected
 * by this look, but we want to avoid concurrent calls for performance
 * reasons and to make the pcpu_get_vm_areas more deterministic.
 */
static DEFINE_MUTEX(vmap_purge_lock);

/* for per-CPU blocks */
static void purge_fragmented_blocks_allcpus(void);

/*
 * called before a call to iounmap() if the caller wants vm_area_struct's
 * immediately freed.
 */
void set_iounmap_nonlazy(void)
{
	atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1);
}

/*
 * Purges all lazily-freed vmap areas.
 */
static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
{
	unsigned long resched_threshold;
	struct list_head local_pure_list;
	struct vmap_area *va, *n_va;

	lockdep_assert_held(&vmap_purge_lock);

	spin_lock(&purge_vmap_area_lock);
	purge_vmap_area_root = RB_ROOT;
	list_replace_init(&purge_vmap_area_list, &local_pure_list);
	spin_unlock(&purge_vmap_area_lock);

	if (unlikely(list_empty(&local_pure_list)))
		return false;

	start = min(start,
		list_first_entry(&local_pure_list,
			struct vmap_area, list)->va_start);

	end = max(end,
		list_last_entry(&local_pure_list,
			struct vmap_area, list)->va_end);

	flush_tlb_kernel_range(start, end);
	resched_threshold = lazy_max_pages() << 1;

	spin_lock(&free_vmap_area_lock);
	list_for_each_entry_safe(va, n_va, &local_pure_list, list) {
		unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
		unsigned long orig_start = va->va_start;
		unsigned long orig_end = va->va_end;

		/*
		 * Finally insert or merge lazily-freed area. It is
		 * detached and there is no need to "unlink" it from
		 * anything.
		 */
		va = merge_or_add_vmap_area_augment(va, &free_vmap_area_root,
				&free_vmap_area_list);

		if (!va)
			continue;

		if (is_vmalloc_or_module_addr((void *)orig_start))
			kasan_release_vmalloc(orig_start, orig_end,
					      va->va_start, va->va_end);

		atomic_long_sub(nr, &vmap_lazy_nr);

		if (atomic_long_read(&vmap_lazy_nr) < resched_threshold)
			cond_resched_lock(&free_vmap_area_lock);
	}
	spin_unlock(&free_vmap_area_lock);
	return true;
}

/*
 * Kick off a purge of the outstanding lazy areas. Don't bother if somebody
 * is already purging.
 */
static void try_purge_vmap_area_lazy(void)
{
	if (mutex_trylock(&vmap_purge_lock)) {
		__purge_vmap_area_lazy(ULONG_MAX, 0);
		mutex_unlock(&vmap_purge_lock);
	}
}

/*
 * Kick off a purge of the outstanding lazy areas.
 */
static void purge_vmap_area_lazy(void)
{
	mutex_lock(&vmap_purge_lock);
	purge_fragmented_blocks_allcpus();
	__purge_vmap_area_lazy(ULONG_MAX, 0);
	mutex_unlock(&vmap_purge_lock);
}

/*
 * Free a vmap area, caller ensuring that the area has been unmapped
 * and flush_cache_vunmap had been called for the correct range
 * previously.
 */
static void free_vmap_area_noflush(struct vmap_area *va)
{
	unsigned long nr_lazy;

	spin_lock(&vmap_area_lock);
	unlink_va(va, &vmap_area_root);
	spin_unlock(&vmap_area_lock);

	nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
				PAGE_SHIFT, &vmap_lazy_nr);

	/*
	 * Merge or place it to the purge tree/list.
	 */
	spin_lock(&purge_vmap_area_lock);
	merge_or_add_vmap_area(va,
		&purge_vmap_area_root, &purge_vmap_area_list);
	spin_unlock(&purge_vmap_area_lock);

	/* After this point, we may free va at any time */
	if (unlikely(nr_lazy > lazy_max_pages()))
		try_purge_vmap_area_lazy();
}

/*
 * Free and unmap a vmap area
 */
static void free_unmap_vmap_area(struct vmap_area *va)
{
	flush_cache_vunmap(va->va_start, va->va_end);
	vunmap_range_noflush(va->va_start, va->va_end);
	if (debug_pagealloc_enabled_static())
		flush_tlb_kernel_range(va->va_start, va->va_end);

	free_vmap_area_noflush(va);
}

static struct vmap_area *find_vmap_area(unsigned long addr)
{
	struct vmap_area *va;

	spin_lock(&vmap_area_lock);
	va = __find_vmap_area(addr);
	spin_unlock(&vmap_area_lock);

	return va;
}

/*** Per cpu kva allocator ***/

/*
 * vmap space is limited especially on 32 bit architectures. Ensure there is
 * room for at least 16 percpu vmap blocks per CPU.
 */
/*
 * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
 * to #define VMALLOC_SPACE		(VMALLOC_END-VMALLOC_START). Guess
 * instead (we just need a rough idea)
 */
#if BITS_PER_LONG == 32
#define VMALLOC_SPACE		(128UL*1024*1024)
#else
#define VMALLOC_SPACE		(128UL*1024*1024*1024)
#endif

#define VMALLOC_PAGES		(VMALLOC_SPACE / PAGE_SIZE)
#define VMAP_MAX_ALLOC		BITS_PER_LONG	/* 256K with 4K pages */
#define VMAP_BBMAP_BITS_MAX	1024	/* 4MB with 4K pages */
#define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
#define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
#define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
#define VMAP_BBMAP_BITS		\
		VMAP_MIN(VMAP_BBMAP_BITS_MAX,	\
		VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
			VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))

#define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)

struct vmap_block_queue {
	spinlock_t lock;
	struct list_head free;
};

struct vmap_block {
	spinlock_t lock;
	struct vmap_area *va;
	unsigned long free, dirty;
	unsigned long dirty_min, dirty_max; /*< dirty range */
	struct list_head free_list;
	struct rcu_head rcu_head;
	struct list_head purge;
};

/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);

/*
 * XArray of vmap blocks, indexed by address, to quickly find a vmap block
 * in the free path. Could get rid of this if we change the API to return a
 * "cookie" from alloc, to be passed to free. But no big deal yet.
 */
static DEFINE_XARRAY(vmap_blocks);

/*
 * We should probably have a fallback mechanism to allocate virtual memory
 * out of partially filled vmap blocks. However vmap block sizing should be
 * fairly reasonable according to the vmalloc size, so it shouldn't be a
 * big problem.
 */

static unsigned long addr_to_vb_idx(unsigned long addr)
{
	addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
	addr /= VMAP_BLOCK_SIZE;
	return addr;
}

static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off)
{
	unsigned long addr;

	addr = va_start + (pages_off << PAGE_SHIFT);
	BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start));
	return (void *)addr;
}

/**
 * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this
 *                  block. Of course pages number can't exceed VMAP_BBMAP_BITS
 * @order:    how many 2^order pages should be occupied in newly allocated block
 * @gfp_mask: flags for the page level allocator
 *
 * Return: virtual address in a newly allocated block or ERR_PTR(-errno)
 */
static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
{
	struct vmap_block_queue *vbq;
	struct vmap_block *vb;
	struct vmap_area *va;
	unsigned long vb_idx;
	int node, err;
	void *vaddr;

	node = numa_node_id();

	vb = kmalloc_node(sizeof(struct vmap_block),
			gfp_mask & GFP_RECLAIM_MASK, node);
	if (unlikely(!vb))
		return ERR_PTR(-ENOMEM);

	va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
					VMALLOC_START, VMALLOC_END,
					node, gfp_mask);
	if (IS_ERR(va)) {
		kfree(vb);
		return ERR_CAST(va);
	}

	vaddr = vmap_block_vaddr(va->va_start, 0);
	spin_lock_init(&vb->lock);
	vb->va = va;
	/* At least something should be left free */
	BUG_ON(VMAP_BBMAP_BITS <= (1UL << order));
	vb->free = VMAP_BBMAP_BITS - (1UL << order);
	vb->dirty = 0;
	vb->dirty_min = VMAP_BBMAP_BITS;
	vb->dirty_max = 0;
	INIT_LIST_HEAD(&vb->free_list);

	vb_idx = addr_to_vb_idx(va->va_start);
	err = xa_insert(&vmap_blocks, vb_idx, vb, gfp_mask);
	if (err) {
		kfree(vb);
		free_vmap_area(va);
		return ERR_PTR(err);
	}

	vbq = &get_cpu_var(vmap_block_queue);
	spin_lock(&vbq->lock);
	list_add_tail_rcu(&vb->free_list, &vbq->free);
	spin_unlock(&vbq->lock);
	put_cpu_var(vmap_block_queue);

	return vaddr;
}

static void free_vmap_block(struct vmap_block *vb)
{
	struct vmap_block *tmp;

	tmp = xa_erase(&vmap_blocks, addr_to_vb_idx(vb->va->va_start));
	BUG_ON(tmp != vb);

	free_vmap_area_noflush(vb->va);
	kfree_rcu(vb, rcu_head);
}

static void purge_fragmented_blocks(int cpu)
{
	LIST_HEAD(purge);
	struct vmap_block *vb;
	struct vmap_block *n_vb;
	struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);

	rcu_read_lock();
	list_for_each_entry_rcu(vb, &vbq->free, free_list) {

		if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS))
			continue;

		spin_lock(&vb->lock);
		if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) {
			vb->free = 0; /* prevent further allocs after releasing lock */
			vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */
			vb->dirty_min = 0;
			vb->dirty_max = VMAP_BBMAP_BITS;
			spin_lock(&vbq->lock);
			list_del_rcu(&vb->free_list);
			spin_unlock(&vbq->lock);
			spin_unlock(&vb->lock);
			list_add_tail(&vb->purge, &purge);
		} else
			spin_unlock(&vb->lock);
	}
	rcu_read_unlock();

	list_for_each_entry_safe(vb, n_vb, &purge, purge) {
		list_del(&vb->purge);
		free_vmap_block(vb);
	}
}

static void purge_fragmented_blocks_allcpus(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		purge_fragmented_blocks(cpu);
}

static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
{
	struct vmap_block_queue *vbq;
	struct vmap_block *vb;
	void *vaddr = NULL;
	unsigned int order;

	BUG_ON(offset_in_page(size));
	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
	if (WARN_ON(size == 0)) {
		/*
		 * Allocating 0 bytes isn't what caller wants since
		 * get_order(0) returns funny result. Just warn and terminate
		 * early.
		 */
		return NULL;
	}
	order = get_order(size);

	rcu_read_lock();
	vbq = &get_cpu_var(vmap_block_queue);
	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
		unsigned long pages_off;

		spin_lock(&vb->lock);
		if (vb->free < (1UL << order)) {
			spin_unlock(&vb->lock);
			continue;
		}

		pages_off = VMAP_BBMAP_BITS - vb->free;
		vaddr = vmap_block_vaddr(vb->va->va_start, pages_off);
		vb->free -= 1UL << order;
		if (vb->free == 0) {
			spin_lock(&vbq->lock);
			list_del_rcu(&vb->free_list);
			spin_unlock(&vbq->lock);
		}

		spin_unlock(&vb->lock);
		break;
	}

	put_cpu_var(vmap_block_queue);
	rcu_read_unlock();

	/* Allocate new block if nothing was found */
	if (!vaddr)
		vaddr = new_vmap_block(order, gfp_mask);

	return vaddr;
}

static void vb_free(unsigned long addr, unsigned long size)
{
	unsigned long offset;
	unsigned int order;
	struct vmap_block *vb;

	BUG_ON(offset_in_page(size));
	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);

	flush_cache_vunmap(addr, addr + size);

	order = get_order(size);
	offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT;
	vb = xa_load(&vmap_blocks, addr_to_vb_idx(addr));

	vunmap_range_noflush(addr, addr + size);

	if (debug_pagealloc_enabled_static())
		flush_tlb_kernel_range(addr, addr + size);

	spin_lock(&vb->lock);

	/* Expand dirty range */
	vb->dirty_min = min(vb->dirty_min, offset);
	vb->dirty_max = max(vb->dirty_max, offset + (1UL << order));

	vb->dirty += 1UL << order;
	if (vb->dirty == VMAP_BBMAP_BITS) {
		BUG_ON(vb->free);
		spin_unlock(&vb->lock);
		free_vmap_block(vb);
	} else
		spin_unlock(&vb->lock);
}

static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
{
	int cpu;

	if (unlikely(!vmap_initialized))
		return;

	might_sleep();

	for_each_possible_cpu(cpu) {
		struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
		struct vmap_block *vb;

		rcu_read_lock();
		list_for_each_entry_rcu(vb, &vbq->free, free_list) {
			spin_lock(&vb->lock);
			if (vb->dirty && vb->dirty != VMAP_BBMAP_BITS) {
				unsigned long va_start = vb->va->va_start;
				unsigned long s, e;

				s = va_start + (vb->dirty_min << PAGE_SHIFT);
				e = va_start + (vb->dirty_max << PAGE_SHIFT);

				start = min(s, start);
				end   = max(e, end);

				flush = 1;
			}
			spin_unlock(&vb->lock);
		}
		rcu_read_unlock();
	}

	mutex_lock(&vmap_purge_lock);
	purge_fragmented_blocks_allcpus();
	if (!__purge_vmap_area_lazy(start, end) && flush)
		flush_tlb_kernel_range(start, end);
	mutex_unlock(&vmap_purge_lock);
}

/**
 * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
 *
 * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
 * to amortize TLB flushing overheads. What this means is that any page you
 * have now, may, in a former life, have been mapped into kernel virtual
 * address by the vmap layer and so there might be some CPUs with TLB entries
 * still referencing that page (additional to the regular 1:1 kernel mapping).
 *
 * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
 * be sure that none of the pages we have control over will have any aliases
 * from the vmap layer.
 */
void vm_unmap_aliases(void)
{
	unsigned long start = ULONG_MAX, end = 0;
	int flush = 0;

	_vm_unmap_aliases(start, end, flush);
}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);

/**
 * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
 * @mem: the pointer returned by vm_map_ram
 * @count: the count passed to that vm_map_ram call (cannot unmap partial)
 */
void vm_unmap_ram(const void *mem, unsigned int count)
{
	unsigned long size = (unsigned long)count << PAGE_SHIFT;
	unsigned long addr = (unsigned long)mem;
	struct vmap_area *va;

	might_sleep();
	BUG_ON(!addr);
	BUG_ON(addr < VMALLOC_START);
	BUG_ON(addr > VMALLOC_END);
	BUG_ON(!PAGE_ALIGNED(addr));

	kasan_poison_vmalloc(mem, size);

	if (likely(count <= VMAP_MAX_ALLOC)) {
		debug_check_no_locks_freed(mem, size);
		vb_free(addr, size);
		return;
	}

	va = find_vmap_area(addr);
	BUG_ON(!va);
	debug_check_no_locks_freed((void *)va->va_start,
				    (va->va_end - va->va_start));
	free_unmap_vmap_area(va);
}
EXPORT_SYMBOL(vm_unmap_ram);

/**
 * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
 * @pages: an array of pointers to the pages to be mapped
 * @count: number of pages
 * @node: prefer to allocate data structures on this node
 *
 * If you use this function for less than VMAP_MAX_ALLOC pages, it could be
 * faster than vmap so it's good.  But if you mix long-life and short-life
 * objects with vm_map_ram(), it could consume lots of address space through
 * fragmentation (especially on a 32bit machine).  You could see failures in
 * the end.  Please use this function for short-lived objects.
 *
 * Returns: a pointer to the address that has been mapped, or %NULL on failure
 */
void *vm_map_ram(struct page **pages, unsigned int count, int node)
{
	unsigned long size = (unsigned long)count << PAGE_SHIFT;
	unsigned long addr;
	void *mem;

	if (likely(count <= VMAP_MAX_ALLOC)) {
		mem = vb_alloc(size, GFP_KERNEL);
		if (IS_ERR(mem))
			return NULL;
		addr = (unsigned long)mem;
	} else {
		struct vmap_area *va;
		va = alloc_vmap_area(size, PAGE_SIZE,
				VMALLOC_START, VMALLOC_END, node, GFP_KERNEL);
		if (IS_ERR(va))
			return NULL;

		addr = va->va_start;
		mem = (void *)addr;
	}

	kasan_unpoison_vmalloc(mem, size);

	if (vmap_pages_range(addr, addr + size, PAGE_KERNEL,
				pages, PAGE_SHIFT) < 0) {
		vm_unmap_ram(mem, count);
		return NULL;
	}

	return mem;
}
EXPORT_SYMBOL(vm_map_ram);

static struct vm_struct *vmlist __initdata;

static inline unsigned int vm_area_page_order(struct vm_struct *vm)
{
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
	return vm->page_order;
#else
	return 0;
#endif
}

static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order)
{
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
	vm->page_order = order;
#else
	BUG_ON(order != 0);
#endif
}

/**
 * vm_area_add_early - add vmap area early during boot
 * @vm: vm_struct to add
 *
 * This function is used to add fixed kernel vm area to vmlist before
 * vmalloc_init() is called.  @vm->addr, @vm->size, and @vm->flags
 * should contain proper values and the other fields should be zero.
 *
 * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
 */
void __init vm_area_add_early(struct vm_struct *vm)
{
	struct vm_struct *tmp, **p;

	BUG_ON(vmap_initialized);
	for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
		if (tmp->addr >= vm->addr) {
			BUG_ON(tmp->addr < vm->addr + vm->size);
			break;
		} else
			BUG_ON(tmp->addr + tmp->size > vm->addr);
	}
	vm->next = *p;
	*p = vm;
}

/**
 * vm_area_register_early - register vmap area early during boot
 * @vm: vm_struct to register
 * @align: requested alignment
 *
 * This function is used to register kernel vm area before
 * vmalloc_init() is called.  @vm->size and @vm->flags should contain
 * proper values on entry and other fields should be zero.  On return,
 * vm->addr contains the allocated address.
 *
 * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
 */
void __init vm_area_register_early(struct vm_struct *vm, size_t align)
{
	static size_t vm_init_off __initdata;
	unsigned long addr;

	addr = ALIGN(VMALLOC_START + vm_init_off, align);
	vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;

	vm->addr = (void *)addr;

	vm_area_add_early(vm);
}

static void vmap_init_free_space(void)
{
	unsigned long vmap_start = 1;
	const unsigned long vmap_end = ULONG_MAX;
	struct vmap_area *busy, *free;

	/*
	 *     B     F     B     B     B     F
	 * -|-----|.....|-----|-----|-----|.....|-
	 *  |           The KVA space           |
	 *  |<--------------------------------->|
	 */
	list_for_each_entry(busy, &vmap_area_list, list) {
		if (busy->va_start - vmap_start > 0) {
			free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
			if (!WARN_ON_ONCE(!free)) {
				free->va_start = vmap_start;
				free->va_end = busy->va_start;

				insert_vmap_area_augment(free, NULL,
					&free_vmap_area_root,
						&free_vmap_area_list);
			}
		}

		vmap_start = busy->va_end;
	}

	if (vmap_end - vmap_start > 0) {
		free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
		if (!WARN_ON_ONCE(!free)) {
			free->va_start = vmap_start;
			free->va_end = vmap_end;

			insert_vmap_area_augment(free, NULL,
				&free_vmap_area_root,
					&free_vmap_area_list);
		}
	}
}

void __init vmalloc_init(void)
{
	struct vmap_area *va;
	struct vm_struct *tmp;
	int i;

	/*
	 * Create the cache for vmap_area objects.
	 */
	vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC);

	for_each_possible_cpu(i) {
		struct vmap_block_queue *vbq;
		struct vfree_deferred *p;

		vbq = &per_cpu(vmap_block_queue, i);
		spin_lock_init(&vbq->lock);
		INIT_LIST_HEAD(&vbq->free);
		p = &per_cpu(vfree_deferred, i);
		init_llist_head(&p->list);
		INIT_WORK(&p->wq, free_work);
	}

	/* Import existing vmlist entries. */
	for (tmp = vmlist; tmp; tmp = tmp->next) {
		va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
		if (WARN_ON_ONCE(!va))
			continue;

		va->va_start = (unsigned long)tmp->addr;
		va->va_end = va->va_start + tmp->size;
		va->vm = tmp;
		insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
	}

	/*
	 * Now we can initialize a free vmap space.
	 */
	vmap_init_free_space();
	vmap_initialized = true;
}

static inline void setup_vmalloc_vm_locked(struct vm_struct *vm,
	struct vmap_area *va, unsigned long flags, const void *caller)
{
	vm->flags = flags;
	vm->addr = (void *)va->va_start;
	vm->size = va->va_end - va->va_start;
	vm->caller = caller;
	va->vm = vm;
}

static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
			      unsigned long flags, const void *caller)
{
	spin_lock(&vmap_area_lock);
	setup_vmalloc_vm_locked(vm, va, flags, caller);
	spin_unlock(&vmap_area_lock);
}

static void clear_vm_uninitialized_flag(struct vm_struct *vm)
{
	/*
	 * Before removing VM_UNINITIALIZED,
	 * we should make sure that vm has proper values.
	 * Pair with smp_rmb() in show_numa_info().
	 */
	smp_wmb();
	vm->flags &= ~VM_UNINITIALIZED;
}

static struct vm_struct *__get_vm_area_node(unsigned long size,
		unsigned long align, unsigned long flags, unsigned long start,
		unsigned long end, int node, gfp_t gfp_mask, const void *caller)
{
	struct vmap_area *va;
	struct vm_struct *area;
	unsigned long requested_size = size;

	BUG_ON(in_interrupt());
	size = PAGE_ALIGN(size);
	if (unlikely(!size))
		return NULL;

	if (flags & VM_IOREMAP)
		align = 1ul << clamp_t(int, get_count_order_long(size),
				       PAGE_SHIFT, IOREMAP_MAX_ORDER);

	area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
	if (unlikely(!area))
		return NULL;

	if (!(flags & VM_NO_GUARD))
		size += PAGE_SIZE;

	va = alloc_vmap_area(size, align, start, end, node, gfp_mask);
	if (IS_ERR(va)) {
		kfree(area);
		return NULL;
	}

	kasan_unpoison_vmalloc((void *)va->va_start, requested_size);

	setup_vmalloc_vm(area, va, flags, caller);

	return area;
}

struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
				       unsigned long start, unsigned long end,
				       const void *caller)
{
	return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
				  GFP_KERNEL, caller);
}

/**
 * get_vm_area - reserve a contiguous kernel virtual area
 * @size:	 size of the area
 * @flags:	 %VM_IOREMAP for I/O mappings or VM_ALLOC
 *
 * Search an area of @size in the kernel virtual mapping area,
 * and reserved it for out purposes.  Returns the area descriptor
 * on success or %NULL on failure.
 *
 * Return: the area descriptor on success or %NULL on failure.
 */
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
{
	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
				  NUMA_NO_NODE, GFP_KERNEL,
				  __builtin_return_address(0));
}

struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
				const void *caller)
{
	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
				  NUMA_NO_NODE, GFP_KERNEL, caller);
}

/**
 * find_vm_area - find a continuous kernel virtual area
 * @addr:	  base address
 *
 * Search for the kernel VM area starting at @addr, and return it.
 * It is up to the caller to do all required locking to keep the returned
 * pointer valid.
 *
 * Return: the area descriptor on success or %NULL on failure.
 */
struct vm_struct *find_vm_area(const void *addr)
{
	struct vmap_area *va;

	va = find_vmap_area((unsigned long)addr);
	if (!va)
		return NULL;

	return va->vm;
}

/**
 * remove_vm_area - find and remove a continuous kernel virtual area
 * @addr:	    base address
 *
 * Search for the kernel VM area starting at @addr, and remove it.
 * This function returns the found VM area, but using it is NOT safe
 * on SMP machines, except for its size or flags.
 *
 * Return: the area descriptor on success or %NULL on failure.
 */
struct vm_struct *remove_vm_area(const void *addr)
{
	struct vmap_area *va;

	might_sleep();

	spin_lock(&vmap_area_lock);
	va = __find_vmap_area((unsigned long)addr);
	if (va && va->vm) {
		struct vm_struct *vm = va->vm;

		va->vm = NULL;
		spin_unlock(&vmap_area_lock);

		kasan_free_shadow(vm);
		free_unmap_vmap_area(va);

		return vm;
	}

	spin_unlock(&vmap_area_lock);
	return NULL;
}

static inline void set_area_direct_map(const struct vm_struct *area,
				       int (*set_direct_map)(struct page *page))
{
	int i;

	/* HUGE_VMALLOC passes small pages to set_direct_map */
	for (i = 0; i < area->nr_pages; i++)
		if (page_address(area->pages[i]))
			set_direct_map(area->pages[i]);
}

/* Handle removing and resetting vm mappings related to the vm_struct. */
static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
{
	unsigned long start = ULONG_MAX, end = 0;
	unsigned int page_order = vm_area_page_order(area);
	int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
	int flush_dmap = 0;
	int i;

	remove_vm_area(area->addr);

	/* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
	if (!flush_reset)
		return;

	/*
	 * If not deallocating pages, just do the flush of the VM area and
	 * return.
	 */
	if (!deallocate_pages) {
		vm_unmap_aliases();
		return;
	}

	/*
	 * If execution gets here, flush the vm mapping and reset the direct
	 * map. Find the start and end range of the direct mappings to make sure
	 * the vm_unmap_aliases() flush includes the direct map.
	 */
	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
		unsigned long addr = (unsigned long)page_address(area->pages[i]);
		if (addr) {
			unsigned long page_size;

			page_size = PAGE_SIZE << page_order;
			start = min(addr, start);
			end = max(addr + page_size, end);
			flush_dmap = 1;
		}
	}

	/*
	 * Set direct map to something invalid so that it won't be cached if
	 * there are any accesses after the TLB flush, then flush the TLB and
	 * reset the direct map permissions to the default.
	 */
	set_area_direct_map(area, set_direct_map_invalid_noflush);
	_vm_unmap_aliases(start, end, flush_dmap);
	set_area_direct_map(area, set_direct_map_default_noflush);
}

static void __vunmap(const void *addr, int deallocate_pages)
{
	struct vm_struct *area;

	if (!addr)
		return;

	if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
			addr))
		return;

	area = find_vm_area(addr);
	if (unlikely(!area)) {
		WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
				addr);
		return;
	}

	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));

	kasan_poison_vmalloc(area->addr, get_vm_area_size(area));

	vm_remove_mappings(area, deallocate_pages);

	if (deallocate_pages) {
		unsigned int page_order = vm_area_page_order(area);
		int i;

		for (i = 0; i < area->nr_pages; i += 1U << page_order) {
			struct page *page = area->pages[i];

			BUG_ON(!page);
			__free_pages(page, page_order);
		}
		atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);

		kvfree(area->pages);
	}

	kfree(area);
}

static inline void __vfree_deferred(const void *addr)
{
	/*
	 * Use raw_cpu_ptr() because this can be called from preemptible
	 * context. Preemption is absolutely fine here, because the llist_add()
	 * implementation is lockless, so it works even if we are adding to
	 * another cpu's list. schedule_work() should be fine with this too.
	 */
	struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred);

	if (llist_add((struct llist_node *)addr, &p->list))
		schedule_work(&p->wq);
}

/**
 * vfree_atomic - release memory allocated by vmalloc()
 * @addr:	  memory base address
 *
 * This one is just like vfree() but can be called in any atomic context
 * except NMIs.
 */
void vfree_atomic(const void *addr)
{
	BUG_ON(in_nmi());

	kmemleak_free(addr);

	if (!addr)
		return;
	__vfree_deferred(addr);
}

static void __vfree(const void *addr)
{
	if (unlikely(in_interrupt()))
		__vfree_deferred(addr);
	else
		__vunmap(addr, 1);
}

/**
 * vfree - Release memory allocated by vmalloc()
 * @addr:  Memory base address
 *
 * Free the virtually continuous memory area starting at @addr, as obtained
 * from one of the vmalloc() family of APIs.  This will usually also free the
 * physical memory underlying the virtual allocation, but that memory is
 * reference counted, so it will not be freed until the last user goes away.
 *
 * If @addr is NULL, no operation is performed.
 *
 * Context:
 * May sleep if called *not* from interrupt context.
 * Must not be called in NMI context (strictly speaking, it could be
 * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
 * conventions for vfree() arch-depenedent would be a really bad idea).
 */
void vfree(const void *addr)
{
	BUG_ON(in_nmi());

	kmemleak_free(addr);

	might_sleep_if(!in_interrupt());

	if (!addr)
		return;

	__vfree(addr);
}
EXPORT_SYMBOL(vfree);

/**
 * vunmap - release virtual mapping obtained by vmap()
 * @addr:   memory base address
 *
 * Free the virtually contiguous memory area starting at @addr,
 * which was created from the page array passed to vmap().
 *
 * Must not be called in interrupt context.
 */
void vunmap(const void *addr)
{
	BUG_ON(in_interrupt());
	might_sleep();
	if (addr)
		__vunmap(addr, 0);
}
EXPORT_SYMBOL(vunmap);

/**
 * vmap - map an array of pages into virtually contiguous space
 * @pages: array of page pointers
 * @count: number of pages to map
 * @flags: vm_area->flags
 * @prot: page protection for the mapping
 *
 * Maps @count pages from @pages into contiguous kernel virtual space.
 * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself
 * (which must be kmalloc or vmalloc memory) and one reference per pages in it
 * are transferred from the caller to vmap(), and will be freed / dropped when
 * vfree() is called on the return value.
 *
 * Return: the address of the area or %NULL on failure
 */
void *vmap(struct page **pages, unsigned int count,
	   unsigned long flags, pgprot_t prot)
{
	struct vm_struct *area;
	unsigned long addr;
	unsigned long size;		/* In bytes */

	might_sleep();

	if (count > totalram_pages())
		return NULL;

	size = (unsigned long)count << PAGE_SHIFT;
	area = get_vm_area_caller(size, flags, __builtin_return_address(0));
	if (!area)
		return NULL;

	addr = (unsigned long)area->addr;
	if (vmap_pages_range(addr, addr + size, pgprot_nx(prot),
				pages, PAGE_SHIFT) < 0) {
		vunmap(area->addr);
		return NULL;
	}

	if (flags & VM_MAP_PUT_PAGES) {
		area->pages = pages;
		area->nr_pages = count;
	}
	return area->addr;
}
EXPORT_SYMBOL(vmap);

#ifdef CONFIG_VMAP_PFN
struct vmap_pfn_data {
	unsigned long	*pfns;
	pgprot_t	prot;
	unsigned int	idx;
};

static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private)
{
	struct vmap_pfn_data *data = private;

	if (WARN_ON_ONCE(pfn_valid(data->pfns[data->idx])))
		return -EINVAL;
	*pte = pte_mkspecial(pfn_pte(data->pfns[data->idx++], data->prot));
	return 0;
}

/**
 * vmap_pfn - map an array of PFNs into virtually contiguous space
 * @pfns: array of PFNs
 * @count: number of pages to map
 * @prot: page protection for the mapping
 *
 * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns
 * the start address of the mapping.
 */
void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
{
	struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) };
	struct vm_struct *area;

	area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP,
			__builtin_return_address(0));
	if (!area)
		return NULL;
	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
			count * PAGE_SIZE, vmap_pfn_apply, &data)) {
		free_vm_area(area);
		return NULL;
	}
	return area->addr;
}
EXPORT_SYMBOL_GPL(vmap_pfn);
#endif /* CONFIG_VMAP_PFN */

static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
				 pgprot_t prot, unsigned int page_shift,
				 int node)
{
	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
	unsigned long addr = (unsigned long)area->addr;
	unsigned long size = get_vm_area_size(area);
	unsigned long array_size;
	unsigned int nr_small_pages = size >> PAGE_SHIFT;
	unsigned int page_order;
	struct page **pages;
	unsigned int i;

	array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
	gfp_mask |= __GFP_NOWARN;
	if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
		gfp_mask |= __GFP_HIGHMEM;

	/* Please note that the recursion is strictly bounded. */
	if (array_size > PAGE_SIZE) {
		pages = __vmalloc_node(array_size, 1, nested_gfp, node,
					area->caller);
	} else {
		pages = kmalloc_node(array_size, nested_gfp, node);
	}

	if (!pages) {
		free_vm_area(area);
		warn_alloc(gfp_mask, NULL,
			   "vmalloc size %lu allocation failure: "
			   "page array size %lu allocation failed",
			   nr_small_pages * PAGE_SIZE, array_size);
		return NULL;
	}

	area->pages = pages;
	area->nr_pages = nr_small_pages;
	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);

	page_order = vm_area_page_order(area);

	/*
	 * Careful, we allocate and map page_order pages, but tracking is done
	 * per PAGE_SIZE page so as to keep the vm_struct APIs independent of
	 * the physical/mapped size.
	 */
	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
		struct page *page;
		int p;

		/* Compound pages required for remap_vmalloc_page */
		page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order);
		if (unlikely(!page)) {
			/* Successfully allocated i pages, free them in __vfree() */
			area->nr_pages = i;
			atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
			warn_alloc(gfp_mask, NULL,
				   "vmalloc size %lu allocation failure: "
				   "page order %u allocation failed",
				   area->nr_pages * PAGE_SIZE, page_order);
			goto fail;
		}

		for (p = 0; p < (1U << page_order); p++)
			area->pages[i + p] = page + p;

		if (gfpflags_allow_blocking(gfp_mask))
			cond_resched();
	}
	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);

	if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0) {
		warn_alloc(gfp_mask, NULL,
			   "vmalloc size %lu allocation failure: "
			   "failed to map pages",
			   area->nr_pages * PAGE_SIZE);
		goto fail;
	}

	return area->addr;

fail:
	__vfree(area->addr);
	return NULL;
}

/**
 * __vmalloc_node_range - allocate virtually contiguous memory
 * @size:		  allocation size
 * @align:		  desired alignment
 * @start:		  vm area range start
 * @end:		  vm area range end
 * @gfp_mask:		  flags for the page level allocator
 * @prot:		  protection mask for the allocated pages
 * @vm_flags:		  additional vm area flags (e.g. %VM_NO_GUARD)
 * @node:		  node to use for allocation or NUMA_NO_NODE
 * @caller:		  caller's return address
 *
 * Allocate enough pages to cover @size from the page level
 * allocator with @gfp_mask flags.  Map them into contiguous
 * kernel virtual space, using a pagetable protection of @prot.
 *
 * Return: the address of the area or %NULL on failure
 */
void *__vmalloc_node_range(unsigned long size, unsigned long align,
			unsigned long start, unsigned long end, gfp_t gfp_mask,
			pgprot_t prot, unsigned long vm_flags, int node,
			const void *caller)
{
	struct vm_struct *area;
	void *addr;
	unsigned long real_size = size;
	unsigned long real_align = align;
	unsigned int shift = PAGE_SHIFT;

	if (WARN_ON_ONCE(!size))
		return NULL;

	if ((size >> PAGE_SHIFT) > totalram_pages()) {
		warn_alloc(gfp_mask, NULL,
			   "vmalloc size %lu allocation failure: "
			   "exceeds total pages", real_size);
		return NULL;
	}

	if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) &&
			arch_vmap_pmd_supported(prot)) {
		unsigned long size_per_node;

		/*
		 * Try huge pages. Only try for PAGE_KERNEL allocations,
		 * others like modules don't yet expect huge pages in
		 * their allocations due to apply_to_page_range not
		 * supporting them.
		 */

		size_per_node = size;
		if (node == NUMA_NO_NODE)
			size_per_node /= num_online_nodes();
		if (size_per_node >= PMD_SIZE) {
			shift = PMD_SHIFT;
			align = max(real_align, 1UL << shift);
			size = ALIGN(real_size, 1UL << shift);
		}
	}

again:
	size = PAGE_ALIGN(size);
	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
				vm_flags, start, end, node, gfp_mask, caller);
	if (!area) {
		warn_alloc(gfp_mask, NULL,
			   "vmalloc size %lu allocation failure: "
			   "vm_struct allocation failed", real_size);
		goto fail;
	}

	addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
	if (!addr)
		goto fail;

	/*
	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
	 * flag. It means that vm_struct is not fully initialized.
	 * Now, it is fully initialized, so remove this flag here.
	 */
	clear_vm_uninitialized_flag(area);

	kmemleak_vmalloc(area, size, gfp_mask);

	return addr;

fail:
	if (shift > PAGE_SHIFT) {
		shift = PAGE_SHIFT;
		align = real_align;
		size = real_size;
		goto again;
	}

	return NULL;
}

/**
 * __vmalloc_node - allocate virtually contiguous memory
 * @size:	    allocation size
 * @align:	    desired alignment
 * @gfp_mask:	    flags for the page level allocator
 * @node:	    node to use for allocation or NUMA_NO_NODE
 * @caller:	    caller's return address
 *
 * Allocate enough pages to cover @size from the page level allocator with
 * @gfp_mask flags.  Map them into contiguous kernel virtual space.
 *
 * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
 * and __GFP_NOFAIL are not supported
 *
 * Any use of gfp flags outside of GFP_KERNEL should be consulted
 * with mm people.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *__vmalloc_node(unsigned long size, unsigned long align,
			    gfp_t gfp_mask, int node, const void *caller)
{
	return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
				gfp_mask, PAGE_KERNEL, 0, node, caller);
}
/*
 * This is only for performance analysis of vmalloc and stress purpose.
 * It is required by vmalloc test module, therefore do not use it other
 * than that.
 */
#ifdef CONFIG_TEST_VMALLOC_MODULE
EXPORT_SYMBOL_GPL(__vmalloc_node);
#endif

void *__vmalloc(unsigned long size, gfp_t gfp_mask)
{
	return __vmalloc_node(size, 1, gfp_mask, NUMA_NO_NODE,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(__vmalloc);

/**
 * vmalloc - allocate virtually contiguous memory
 * @size:    allocation size
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 *
 * For tight control over page level allocator and protection flags
 * use __vmalloc() instead.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc(unsigned long size)
{
	return __vmalloc_node(size, 1, GFP_KERNEL, NUMA_NO_NODE,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc);

/**
 * vzalloc - allocate virtually contiguous memory with zero fill
 * @size:    allocation size
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 * The memory allocated is set to zero.
 *
 * For tight control over page level allocator and protection flags
 * use __vmalloc() instead.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vzalloc(unsigned long size)
{
	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc);

/**
 * vmalloc_user - allocate zeroed virtually contiguous memory for userspace
 * @size: allocation size
 *
 * The resulting memory area is zeroed so it can be mapped to userspace
 * without leaking data.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_user(unsigned long size)
{
	return __vmalloc_node_range(size, SHMLBA,  VMALLOC_START, VMALLOC_END,
				    GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL,
				    VM_USERMAP, NUMA_NO_NODE,
				    __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_user);

/**
 * vmalloc_node - allocate memory on a specific node
 * @size:	  allocation size
 * @node:	  numa node
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 *
 * For tight control over page level allocator and protection flags
 * use __vmalloc() instead.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_node(unsigned long size, int node)
{
	return __vmalloc_node(size, 1, GFP_KERNEL, node,
			__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node);

/**
 * vzalloc_node - allocate memory on a specific node with zero fill
 * @size:	allocation size
 * @node:	numa node
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 * The memory allocated is set to zero.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vzalloc_node(unsigned long size, int node)
{
	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, node,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_node);

#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL)
#else
/*
 * 64b systems should always have either DMA or DMA32 zones. For others
 * GFP_DMA32 should do the right thing and use the normal zone.
 */
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
#endif

/**
 * vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
 * @size:	allocation size
 *
 * Allocate enough 32bit PA addressable pages to cover @size from the
 * page level allocator and map them into contiguous kernel virtual space.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_32(unsigned long size)
{
	return __vmalloc_node(size, 1, GFP_VMALLOC32, NUMA_NO_NODE,
			__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32);

/**
 * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
 * @size:	     allocation size
 *
 * The resulting memory area is 32bit addressable and zeroed so it can be
 * mapped to userspace without leaking data.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_32_user(unsigned long size)
{
	return __vmalloc_node_range(size, SHMLBA,  VMALLOC_START, VMALLOC_END,
				    GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
				    VM_USERMAP, NUMA_NO_NODE,
				    __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_user);

/*
 * small helper routine , copy contents to buf from addr.
 * If the page is not present, fill zero.
 */

static int aligned_vread(char *buf, char *addr, unsigned long count)
{
	struct page *p;
	int copied = 0;

	while (count) {
		unsigned long offset, length;

		offset = offset_in_page(addr);
		length = PAGE_SIZE - offset;
		if (length > count)
			length = count;
		p = vmalloc_to_page(addr);
		/*
		 * To do safe access to this _mapped_ area, we need
		 * lock. But adding lock here means that we need to add
		 * overhead of vmalloc()/vfree() calles for this _debug_
		 * interface, rarely used. Instead of that, we'll use
		 * kmap() and get small overhead in this access function.
		 */
		if (p) {
			/*
			 * we can expect USER0 is not used (see vread/vwrite's
			 * function description)
			 */
			void *map = kmap_atomic(p);
			memcpy(buf, map + offset, length);
			kunmap_atomic(map);
		} else
			memset(buf, 0, length);

		addr += length;
		buf += length;
		copied += length;
		count -= length;
	}
	return copied;
}

static int aligned_vwrite(char *buf, char *addr, unsigned long count)
{
	struct page *p;
	int copied = 0;

	while (count) {
		unsigned long offset, length;

		offset = offset_in_page(addr);
		length = PAGE_SIZE - offset;
		if (length > count)
			length = count;
		p = vmalloc_to_page(addr);
		/*
		 * To do safe access to this _mapped_ area, we need
		 * lock. But adding lock here means that we need to add
		 * overhead of vmalloc()/vfree() calles for this _debug_
		 * interface, rarely used. Instead of that, we'll use
		 * kmap() and get small overhead in this access function.
		 */
		if (p) {
			/*
			 * we can expect USER0 is not used (see vread/vwrite's
			 * function description)
			 */
			void *map = kmap_atomic(p);
			memcpy(map + offset, buf, length);
			kunmap_atomic(map);
		}
		addr += length;
		buf += length;
		copied += length;
		count -= length;
	}
	return copied;
}

/**
 * vread() - read vmalloc area in a safe way.
 * @buf:     buffer for reading data
 * @addr:    vm address.
 * @count:   number of bytes to be read.
 *
 * This function checks that addr is a valid vmalloc'ed area, and
 * copy data from that area to a given buffer. If the given memory range
 * of [addr...addr+count) includes some valid address, data is copied to
 * proper area of @buf. If there are memory holes, they'll be zero-filled.
 * IOREMAP area is treated as memory hole and no copy is done.
 *
 * If [addr...addr+count) doesn't includes any intersects with alive
 * vm_struct area, returns 0. @buf should be kernel's buffer.
 *
 * Note: In usual ops, vread() is never necessary because the caller
 * should know vmalloc() area is valid and can use memcpy().
 * This is for routines which have to access vmalloc area without
 * any information, as /dev/kmem.
 *
 * Return: number of bytes for which addr and buf should be increased
 * (same number as @count) or %0 if [addr...addr+count) doesn't
 * include any intersection with valid vmalloc area
 */
long vread(char *buf, char *addr, unsigned long count)
{
	struct vmap_area *va;
	struct vm_struct *vm;
	char *vaddr, *buf_start = buf;
	unsigned long buflen = count;
	unsigned long n;

	/* Don't allow overflow */
	if ((unsigned long) addr + count < count)
		count = -(unsigned long) addr;

	spin_lock(&vmap_area_lock);
	va = __find_vmap_area((unsigned long)addr);
	if (!va)
		goto finished;
	list_for_each_entry_from(va, &vmap_area_list, list) {
		if (!count)
			break;

		if (!va->vm)
			continue;

		vm = va->vm;
		vaddr = (char *) vm->addr;
		if (addr >= vaddr + get_vm_area_size(vm))
			continue;
		while (addr < vaddr) {
			if (count == 0)
				goto finished;
			*buf = '\0';
			buf++;
			addr++;
			count--;
		}
		n = vaddr + get_vm_area_size(vm) - addr;
		if (n > count)
			n = count;
		if (!(vm->flags & VM_IOREMAP))
			aligned_vread(buf, addr, n);
		else /* IOREMAP area is treated as memory hole */
			memset(buf, 0, n);
		buf += n;
		addr += n;
		count -= n;
	}
finished:
	spin_unlock(&vmap_area_lock);

	if (buf == buf_start)
		return 0;
	/* zero-fill memory holes */
	if (buf != buf_start + buflen)
		memset(buf, 0, buflen - (buf - buf_start));

	return buflen;
}

/**
 * vwrite() - write vmalloc area in a safe way.
 * @buf:      buffer for source data
 * @addr:     vm address.
 * @count:    number of bytes to be read.
 *
 * This function checks that addr is a valid vmalloc'ed area, and
 * copy data from a buffer to the given addr. If specified range of
 * [addr...addr+count) includes some valid address, data is copied from
 * proper area of @buf. If there are memory holes, no copy to hole.
 * IOREMAP area is treated as memory hole and no copy is done.
 *
 * If [addr...addr+count) doesn't includes any intersects with alive
 * vm_struct area, returns 0. @buf should be kernel's buffer.
 *
 * Note: In usual ops, vwrite() is never necessary because the caller
 * should know vmalloc() area is valid and can use memcpy().
 * This is for routines which have to access vmalloc area without
 * any information, as /dev/kmem.
 *
 * Return: number of bytes for which addr and buf should be
 * increased (same number as @count) or %0 if [addr...addr+count)
 * doesn't include any intersection with valid vmalloc area
 */
long vwrite(char *buf, char *addr, unsigned long count)
{
	struct vmap_area *va;
	struct vm_struct *vm;
	char *vaddr;
	unsigned long n, buflen;
	int copied = 0;

	/* Don't allow overflow */
	if ((unsigned long) addr + count < count)
		count = -(unsigned long) addr;
	buflen = count;

	spin_lock(&vmap_area_lock);
	list_for_each_entry(va, &vmap_area_list, list) {
		if (!count)
			break;

		if (!va->vm)
			continue;

		vm = va->vm;
		vaddr = (char *) vm->addr;
		if (addr >= vaddr + get_vm_area_size(vm))
			continue;
		while (addr < vaddr) {
			if (count == 0)
				goto finished;
			buf++;
			addr++;
			count--;
		}
		n = vaddr + get_vm_area_size(vm) - addr;
		if (n > count)
			n = count;
		if (!(vm->flags & VM_IOREMAP)) {
			aligned_vwrite(buf, addr, n);
			copied++;
		}
		buf += n;
		addr += n;
		count -= n;
	}
finished:
	spin_unlock(&vmap_area_lock);
	if (!copied)
		return 0;
	return buflen;
}

/**
 * remap_vmalloc_range_partial - map vmalloc pages to userspace
 * @vma:		vma to cover
 * @uaddr:		target user address to start at
 * @kaddr:		virtual address of vmalloc kernel memory
 * @pgoff:		offset from @kaddr to start at
 * @size:		size of map area
 *
 * Returns:	0 for success, -Exxx on failure
 *
 * This function checks that @kaddr is a valid vmalloc'ed area,
 * and that it is big enough to cover the range starting at
 * @uaddr in @vma. Will return failure if that criteria isn't
 * met.
 *
 * Similar to remap_pfn_range() (see mm/memory.c)
 */
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
				void *kaddr, unsigned long pgoff,
				unsigned long size)
{
	struct vm_struct *area;
	unsigned long off;
	unsigned long end_index;

	if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
		return -EINVAL;

	size = PAGE_ALIGN(size);

	if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr))
		return -EINVAL;

	area = find_vm_area(kaddr);
	if (!area)
		return -EINVAL;

	if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
		return -EINVAL;

	if (check_add_overflow(size, off, &end_index) ||
	    end_index > get_vm_area_size(area))
		return -EINVAL;
	kaddr += off;

	do {
		struct page *page = vmalloc_to_page(kaddr);
		int ret;

		ret = vm_insert_page(vma, uaddr, page);
		if (ret)
			return ret;

		uaddr += PAGE_SIZE;
		kaddr += PAGE_SIZE;
		size -= PAGE_SIZE;
	} while (size > 0);

	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;

	return 0;
}

/**
 * remap_vmalloc_range - map vmalloc pages to userspace
 * @vma:		vma to cover (map full range of vma)
 * @addr:		vmalloc memory
 * @pgoff:		number of pages into addr before first page to map
 *
 * Returns:	0 for success, -Exxx on failure
 *
 * This function checks that addr is a valid vmalloc'ed area, and
 * that it is big enough to cover the vma. Will return failure if
 * that criteria isn't met.
 *
 * Similar to remap_pfn_range() (see mm/memory.c)
 */
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
						unsigned long pgoff)
{
	return remap_vmalloc_range_partial(vma, vma->vm_start,
					   addr, pgoff,
					   vma->vm_end - vma->vm_start);
}
EXPORT_SYMBOL(remap_vmalloc_range);

void free_vm_area(struct vm_struct *area)
{
	struct vm_struct *ret;
	ret = remove_vm_area(area->addr);
	BUG_ON(ret != area);
	kfree(area);
}
EXPORT_SYMBOL_GPL(free_vm_area);

#ifdef CONFIG_SMP
static struct vmap_area *node_to_va(struct rb_node *n)
{
	return rb_entry_safe(n, struct vmap_area, rb_node);
}

/**
 * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to
 * @addr: target address
 *
 * Returns: vmap_area if it is found. If there is no such area
 *   the first highest(reverse order) vmap_area is returned
 *   i.e. va->va_start < addr && va->va_end < addr or NULL
 *   if there are no any areas before @addr.
 */
static struct vmap_area *
pvm_find_va_enclose_addr(unsigned long addr)
{
	struct vmap_area *va, *tmp;
	struct rb_node *n;

	n = free_vmap_area_root.rb_node;
	va = NULL;

	while (n) {
		tmp = rb_entry(n, struct vmap_area, rb_node);
		if (tmp->va_start <= addr) {
			va = tmp;
			if (tmp->va_end >= addr)
				break;

			n = n->rb_right;
		} else {
			n = n->rb_left;
		}
	}

	return va;
}

/**
 * pvm_determine_end_from_reverse - find the highest aligned address
 * of free block below VMALLOC_END
 * @va:
 *   in - the VA we start the search(reverse order);
 *   out - the VA with the highest aligned end address.
 * @align: alignment for required highest address
 *
 * Returns: determined end address within vmap_area
 */
static unsigned long
pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align)
{
	unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
	unsigned long addr;

	if (likely(*va)) {
		list_for_each_entry_from_reverse((*va),
				&free_vmap_area_list, list) {
			addr = min((*va)->va_end & ~(align - 1), vmalloc_end);
			if ((*va)->va_start < addr)
				return addr;
		}
	}

	return 0;
}

/**
 * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator
 * @offsets: array containing offset of each area
 * @sizes: array containing size of each area
 * @nr_vms: the number of areas to allocate
 * @align: alignment, all entries in @offsets and @sizes must be aligned to this
 *
 * Returns: kmalloc'd vm_struct pointer array pointing to allocated
 *	    vm_structs on success, %NULL on failure
 *
 * Percpu allocator wants to use congruent vm areas so that it can
 * maintain the offsets among percpu areas.  This function allocates
 * congruent vmalloc areas for it with GFP_KERNEL.  These areas tend to
 * be scattered pretty far, distance between two areas easily going up
 * to gigabytes.  To avoid interacting with regular vmallocs, these
 * areas are allocated from top.
 *
 * Despite its complicated look, this allocator is rather simple. It
 * does everything top-down and scans free blocks from the end looking
 * for matching base. While scanning, if any of the areas do not fit the
 * base address is pulled down to fit the area. Scanning is repeated till
 * all the areas fit and then all necessary data structures are inserted
 * and the result is returned.
 */
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
				     const size_t *sizes, int nr_vms,
				     size_t align)
{
	const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
	const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
	struct vmap_area **vas, *va;
	struct vm_struct **vms;
	int area, area2, last_area, term_area;
	unsigned long base, start, size, end, last_end, orig_start, orig_end;
	bool purged = false;
	enum fit_type type;

	/* verify parameters and allocate data structures */
	BUG_ON(offset_in_page(align) || !is_power_of_2(align));
	for (last_area = 0, area = 0; area < nr_vms; area++) {
		start = offsets[area];
		end = start + sizes[area];

		/* is everything aligned properly? */
		BUG_ON(!IS_ALIGNED(offsets[area], align));
		BUG_ON(!IS_ALIGNED(sizes[area], align));

		/* detect the area with the highest address */
		if (start > offsets[last_area])
			last_area = area;

		for (area2 = area + 1; area2 < nr_vms; area2++) {
			unsigned long start2 = offsets[area2];
			unsigned long end2 = start2 + sizes[area2];

			BUG_ON(start2 < end && start < end2);
		}
	}
	last_end = offsets[last_area] + sizes[last_area];

	if (vmalloc_end - vmalloc_start < last_end) {
		WARN_ON(true);
		return NULL;
	}

	vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL);
	vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL);
	if (!vas || !vms)
		goto err_free2;

	for (area = 0; area < nr_vms; area++) {
		vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL);
		vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL);
		if (!vas[area] || !vms[area])
			goto err_free;
	}
retry:
	spin_lock(&free_vmap_area_lock);

	/* start scanning - we scan from the top, begin with the last area */
	area = term_area = last_area;
	start = offsets[area];
	end = start + sizes[area];

	va = pvm_find_va_enclose_addr(vmalloc_end);
	base = pvm_determine_end_from_reverse(&va, align) - end;

	while (true) {
		/*
		 * base might have underflowed, add last_end before
		 * comparing.
		 */
		if (base + last_end < vmalloc_start + last_end)
			goto overflow;

		/*
		 * Fitting base has not been found.
		 */
		if (va == NULL)
			goto overflow;

		/*
		 * If required width exceeds current VA block, move
		 * base downwards and then recheck.
		 */
		if (base + end > va->va_end) {
			base = pvm_determine_end_from_reverse(&va, align) - end;
			term_area = area;
			continue;
		}

		/*
		 * If this VA does not fit, move base downwards and recheck.
		 */
		if (base + start < va->va_start) {
			va = node_to_va(rb_prev(&va->rb_node));
			base = pvm_determine_end_from_reverse(&va, align) - end;
			term_area = area;
			continue;
		}

		/*
		 * This area fits, move on to the previous one.  If
		 * the previous one is the terminal one, we're done.
		 */
		area = (area + nr_vms - 1) % nr_vms;
		if (area == term_area)
			break;

		start = offsets[area];
		end = start + sizes[area];
		va = pvm_find_va_enclose_addr(base + end);
	}

	/* we've found a fitting base, insert all va's */
	for (area = 0; area < nr_vms; area++) {
		int ret;

		start = base + offsets[area];
		size = sizes[area];

		va = pvm_find_va_enclose_addr(start);
		if (WARN_ON_ONCE(va == NULL))
			/* It is a BUG(), but trigger recovery instead. */
			goto recovery;

		type = classify_va_fit_type(va, start, size);
		if (WARN_ON_ONCE(type == NOTHING_FIT))
			/* It is a BUG(), but trigger recovery instead. */
			goto recovery;

		ret = adjust_va_to_fit_type(va, start, size, type);
		if (unlikely(ret))
			goto recovery;

		/* Allocated area. */
		va = vas[area];
		va->va_start = start;
		va->va_end = start + size;
	}

	spin_unlock(&free_vmap_area_lock);

	/* populate the kasan shadow space */
	for (area = 0; area < nr_vms; area++) {
		if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
			goto err_free_shadow;

		kasan_unpoison_vmalloc((void *)vas[area]->va_start,
				       sizes[area]);
	}

	/* insert all vm's */
	spin_lock(&vmap_area_lock);
	for (area = 0; area < nr_vms; area++) {
		insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list);

		setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC,
				 pcpu_get_vm_areas);
	}
	spin_unlock(&vmap_area_lock);

	kfree(vas);
	return vms;

recovery:
	/*
	 * Remove previously allocated areas. There is no
	 * need in removing these areas from the busy tree,
	 * because they are inserted only on the final step
	 * and when pcpu_get_vm_areas() is success.
	 */
	while (area--) {
		orig_start = vas[area]->va_start;
		orig_end = vas[area]->va_end;
		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
				&free_vmap_area_list);
		if (va)
			kasan_release_vmalloc(orig_start, orig_end,
				va->va_start, va->va_end);
		vas[area] = NULL;
	}

overflow:
	spin_unlock(&free_vmap_area_lock);
	if (!purged) {
		purge_vmap_area_lazy();
		purged = true;

		/* Before "retry", check if we recover. */
		for (area = 0; area < nr_vms; area++) {
			if (vas[area])
				continue;

			vas[area] = kmem_cache_zalloc(
				vmap_area_cachep, GFP_KERNEL);
			if (!vas[area])
				goto err_free;
		}

		goto retry;
	}

err_free:
	for (area = 0; area < nr_vms; area++) {
		if (vas[area])
			kmem_cache_free(vmap_area_cachep, vas[area]);

		kfree(vms[area]);
	}
err_free2:
	kfree(vas);
	kfree(vms);
	return NULL;

err_free_shadow:
	spin_lock(&free_vmap_area_lock);
	/*
	 * We release all the vmalloc shadows, even the ones for regions that
	 * hadn't been successfully added. This relies on kasan_release_vmalloc
	 * being able to tolerate this case.
	 */
	for (area = 0; area < nr_vms; area++) {
		orig_start = vas[area]->va_start;
		orig_end = vas[area]->va_end;
		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
				&free_vmap_area_list);
		if (va)
			kasan_release_vmalloc(orig_start, orig_end,
				va->va_start, va->va_end);
		vas[area] = NULL;
		kfree(vms[area]);
	}
	spin_unlock(&free_vmap_area_lock);
	kfree(vas);
	kfree(vms);
	return NULL;
}

/**
 * pcpu_free_vm_areas - free vmalloc areas for percpu allocator
 * @vms: vm_struct pointer array returned by pcpu_get_vm_areas()
 * @nr_vms: the number of allocated areas
 *
 * Free vm_structs and the array allocated by pcpu_get_vm_areas().
 */
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
	int i;

	for (i = 0; i < nr_vms; i++)
		free_vm_area(vms[i]);
	kfree(vms);
}
#endif	/* CONFIG_SMP */

#ifdef CONFIG_PRINTK
bool vmalloc_dump_obj(void *object)
{
	struct vm_struct *vm;
	void *objp = (void *)PAGE_ALIGN((unsigned long)object);

	vm = find_vm_area(objp);
	if (!vm)
		return false;
	pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n",
		vm->nr_pages, (unsigned long)vm->addr, vm->caller);
	return true;
}
#endif

#ifdef CONFIG_PROC_FS
static void *s_start(struct seq_file *m, loff_t *pos)
	__acquires(&vmap_purge_lock)
	__acquires(&vmap_area_lock)
{
	mutex_lock(&vmap_purge_lock);
	spin_lock(&vmap_area_lock);

	return seq_list_start(&vmap_area_list, *pos);
}

static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
	return seq_list_next(p, &vmap_area_list, pos);
}

static void s_stop(struct seq_file *m, void *p)
	__releases(&vmap_area_lock)
	__releases(&vmap_purge_lock)
{
	spin_unlock(&vmap_area_lock);
	mutex_unlock(&vmap_purge_lock);
}

static void show_numa_info(struct seq_file *m, struct vm_struct *v)
{
	if (IS_ENABLED(CONFIG_NUMA)) {
		unsigned int nr, *counters = m->private;

		if (!counters)
			return;

		if (v->flags & VM_UNINITIALIZED)
			return;
		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
		smp_rmb();

		memset(counters, 0, nr_node_ids * sizeof(unsigned int));

		for (nr = 0; nr < v->nr_pages; nr++)
			counters[page_to_nid(v->pages[nr])]++;

		for_each_node_state(nr, N_HIGH_MEMORY)
			if (counters[nr])
				seq_printf(m, " N%u=%u", nr, counters[nr]);
	}
}

static void show_purge_info(struct seq_file *m)
{
	struct vmap_area *va;

	spin_lock(&purge_vmap_area_lock);
	list_for_each_entry(va, &purge_vmap_area_list, list) {
		seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
			(void *)va->va_start, (void *)va->va_end,
			va->va_end - va->va_start);
	}
	spin_unlock(&purge_vmap_area_lock);
}

static int s_show(struct seq_file *m, void *p)
{
	struct vmap_area *va;
	struct vm_struct *v;

	va = list_entry(p, struct vmap_area, list);

	/*
	 * s_show can encounter race with remove_vm_area, !vm on behalf
	 * of vmap area is being tear down or vm_map_ram allocation.
	 */
	if (!va->vm) {
		seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
			(void *)va->va_start, (void *)va->va_end,
			va->va_end - va->va_start);

		return 0;
	}

	v = va->vm;

	seq_printf(m, "0x%pK-0x%pK %7ld",
		v->addr, v->addr + v->size, v->size);

	if (v->caller)
		seq_printf(m, " %pS", v->caller);

	if (v->nr_pages)
		seq_printf(m, " pages=%d", v->nr_pages);

	if (v->phys_addr)
		seq_printf(m, " phys=%pa", &v->phys_addr);

	if (v->flags & VM_IOREMAP)
		seq_puts(m, " ioremap");

	if (v->flags & VM_ALLOC)
		seq_puts(m, " vmalloc");

	if (v->flags & VM_MAP)
		seq_puts(m, " vmap");

	if (v->flags & VM_USERMAP)
		seq_puts(m, " user");

	if (v->flags & VM_DMA_COHERENT)
		seq_puts(m, " dma-coherent");

	if (is_vmalloc_addr(v->pages))
		seq_puts(m, " vpages");

	show_numa_info(m, v);
	seq_putc(m, '\n');

	/*
	 * As a final step, dump "unpurged" areas.
	 */
	if (list_is_last(&va->list, &vmap_area_list))
		show_purge_info(m);

	return 0;
}

static const struct seq_operations vmalloc_op = {
	.start = s_start,
	.next = s_next,
	.stop = s_stop,
	.show = s_show,
};

static int __init proc_vmalloc_init(void)
{
	if (IS_ENABLED(CONFIG_NUMA))
		proc_create_seq_private("vmallocinfo", 0400, NULL,
				&vmalloc_op,
				nr_node_ids * sizeof(unsigned int), NULL);
	else
		proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op);
	return 0;
}
module_init(proc_vmalloc_init);

#endif