summaryrefslogtreecommitdiffstats
path: root/mm/memory-failure.c
blob: 9349948f1abfd120977706bbda23456999f057bc (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2008, 2009 Intel Corporation
 * Authors: Andi Kleen, Fengguang Wu
 *
 * High level machine check handler. Handles pages reported by the
 * hardware as being corrupted usually due to a multi-bit ECC memory or cache
 * failure.
 *
 * In addition there is a "soft offline" entry point that allows stop using
 * not-yet-corrupted-by-suspicious pages without killing anything.
 *
 * Handles page cache pages in various states.	The tricky part
 * here is that we can access any page asynchronously in respect to
 * other VM users, because memory failures could happen anytime and
 * anywhere. This could violate some of their assumptions. This is why
 * this code has to be extremely careful. Generally it tries to use
 * normal locking rules, as in get the standard locks, even if that means
 * the error handling takes potentially a long time.
 *
 * It can be very tempting to add handling for obscure cases here.
 * In general any code for handling new cases should only be added iff:
 * - You know how to test it.
 * - You have a test that can be added to mce-test
 *   https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/
 * - The case actually shows up as a frequent (top 10) page state in
 *   tools/mm/page-types when running a real workload.
 *
 * There are several operations here with exponential complexity because
 * of unsuitable VM data structures. For example the operation to map back
 * from RMAP chains to processes has to walk the complete process list and
 * has non linear complexity with the number. But since memory corruptions
 * are rare we hope to get away with this. This avoids impacting the core
 * VM.
 */

#define pr_fmt(fmt) "Memory failure: " fmt

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/dax.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/backing-dev.h>
#include <linux/migrate.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
#include <linux/memremap.h>
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include <linux/pagewalk.h>
#include <linux/shmem_fs.h>
#include <linux/sysctl.h>
#include "swap.h"
#include "internal.h"
#include "ras/ras_event.h"

static int sysctl_memory_failure_early_kill __read_mostly;

static int sysctl_memory_failure_recovery __read_mostly = 1;

atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);

static bool hw_memory_failure __read_mostly = false;

static DEFINE_MUTEX(mf_mutex);

void num_poisoned_pages_inc(unsigned long pfn)
{
	atomic_long_inc(&num_poisoned_pages);
	memblk_nr_poison_inc(pfn);
}

void num_poisoned_pages_sub(unsigned long pfn, long i)
{
	atomic_long_sub(i, &num_poisoned_pages);
	if (pfn != -1UL)
		memblk_nr_poison_sub(pfn, i);
}

/**
 * MF_ATTR_RO - Create sysfs entry for each memory failure statistics.
 * @_name: name of the file in the per NUMA sysfs directory.
 */
#define MF_ATTR_RO(_name)					\
static ssize_t _name##_show(struct device *dev,			\
			    struct device_attribute *attr,	\
			    char *buf)				\
{								\
	struct memory_failure_stats *mf_stats =			\
		&NODE_DATA(dev->id)->mf_stats;			\
	return sprintf(buf, "%lu\n", mf_stats->_name);		\
}								\
static DEVICE_ATTR_RO(_name)

MF_ATTR_RO(total);
MF_ATTR_RO(ignored);
MF_ATTR_RO(failed);
MF_ATTR_RO(delayed);
MF_ATTR_RO(recovered);

static struct attribute *memory_failure_attr[] = {
	&dev_attr_total.attr,
	&dev_attr_ignored.attr,
	&dev_attr_failed.attr,
	&dev_attr_delayed.attr,
	&dev_attr_recovered.attr,
	NULL,
};

const struct attribute_group memory_failure_attr_group = {
	.name = "memory_failure",
	.attrs = memory_failure_attr,
};

static struct ctl_table memory_failure_table[] = {
	{
		.procname	= "memory_failure_early_kill",
		.data		= &sysctl_memory_failure_early_kill,
		.maxlen		= sizeof(sysctl_memory_failure_early_kill),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
	{
		.procname	= "memory_failure_recovery",
		.data		= &sysctl_memory_failure_recovery,
		.maxlen		= sizeof(sysctl_memory_failure_recovery),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
	{ }
};

/*
 * Return values:
 *   1:   the page is dissolved (if needed) and taken off from buddy,
 *   0:   the page is dissolved (if needed) and not taken off from buddy,
 *   < 0: failed to dissolve.
 */
static int __page_handle_poison(struct page *page)
{
	int ret;

	zone_pcp_disable(page_zone(page));
	ret = dissolve_free_huge_page(page);
	if (!ret)
		ret = take_page_off_buddy(page);
	zone_pcp_enable(page_zone(page));

	return ret;
}

static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
{
	if (hugepage_or_freepage) {
		/*
		 * Doing this check for free pages is also fine since dissolve_free_huge_page
		 * returns 0 for non-hugetlb pages as well.
		 */
		if (__page_handle_poison(page) <= 0)
			/*
			 * We could fail to take off the target page from buddy
			 * for example due to racy page allocation, but that's
			 * acceptable because soft-offlined page is not broken
			 * and if someone really want to use it, they should
			 * take it.
			 */
			return false;
	}

	SetPageHWPoison(page);
	if (release)
		put_page(page);
	page_ref_inc(page);
	num_poisoned_pages_inc(page_to_pfn(page));

	return true;
}

#if IS_ENABLED(CONFIG_HWPOISON_INJECT)

u32 hwpoison_filter_enable = 0;
u32 hwpoison_filter_dev_major = ~0U;
u32 hwpoison_filter_dev_minor = ~0U;
u64 hwpoison_filter_flags_mask;
u64 hwpoison_filter_flags_value;
EXPORT_SYMBOL_GPL(hwpoison_filter_enable);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_major);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);

static int hwpoison_filter_dev(struct page *p)
{
	struct address_space *mapping;
	dev_t dev;

	if (hwpoison_filter_dev_major == ~0U &&
	    hwpoison_filter_dev_minor == ~0U)
		return 0;

	mapping = page_mapping(p);
	if (mapping == NULL || mapping->host == NULL)
		return -EINVAL;

	dev = mapping->host->i_sb->s_dev;
	if (hwpoison_filter_dev_major != ~0U &&
	    hwpoison_filter_dev_major != MAJOR(dev))
		return -EINVAL;
	if (hwpoison_filter_dev_minor != ~0U &&
	    hwpoison_filter_dev_minor != MINOR(dev))
		return -EINVAL;

	return 0;
}

static int hwpoison_filter_flags(struct page *p)
{
	if (!hwpoison_filter_flags_mask)
		return 0;

	if ((stable_page_flags(p) & hwpoison_filter_flags_mask) ==
				    hwpoison_filter_flags_value)
		return 0;
	else
		return -EINVAL;
}

/*
 * This allows stress tests to limit test scope to a collection of tasks
 * by putting them under some memcg. This prevents killing unrelated/important
 * processes such as /sbin/init. Note that the target task may share clean
 * pages with init (eg. libc text), which is harmless. If the target task
 * share _dirty_ pages with another task B, the test scheme must make sure B
 * is also included in the memcg. At last, due to race conditions this filter
 * can only guarantee that the page either belongs to the memcg tasks, or is
 * a freed page.
 */
#ifdef CONFIG_MEMCG
u64 hwpoison_filter_memcg;
EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p)
{
	if (!hwpoison_filter_memcg)
		return 0;

	if (page_cgroup_ino(p) != hwpoison_filter_memcg)
		return -EINVAL;

	return 0;
}
#else
static int hwpoison_filter_task(struct page *p) { return 0; }
#endif

int hwpoison_filter(struct page *p)
{
	if (!hwpoison_filter_enable)
		return 0;

	if (hwpoison_filter_dev(p))
		return -EINVAL;

	if (hwpoison_filter_flags(p))
		return -EINVAL;

	if (hwpoison_filter_task(p))
		return -EINVAL;

	return 0;
}
#else
int hwpoison_filter(struct page *p)
{
	return 0;
}
#endif

EXPORT_SYMBOL_GPL(hwpoison_filter);

/*
 * Kill all processes that have a poisoned page mapped and then isolate
 * the page.
 *
 * General strategy:
 * Find all processes having the page mapped and kill them.
 * But we keep a page reference around so that the page is not
 * actually freed yet.
 * Then stash the page away
 *
 * There's no convenient way to get back to mapped processes
 * from the VMAs. So do a brute-force search over all
 * running processes.
 *
 * Remember that machine checks are not common (or rather
 * if they are common you have other problems), so this shouldn't
 * be a performance issue.
 *
 * Also there are some races possible while we get from the
 * error detection to actually handle it.
 */

struct to_kill {
	struct list_head nd;
	struct task_struct *tsk;
	unsigned long addr;
	short size_shift;
};

/*
 * Send all the processes who have the page mapped a signal.
 * ``action optional'' if they are not immediately affected by the error
 * ``action required'' if error happened in current execution context
 */
static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
{
	struct task_struct *t = tk->tsk;
	short addr_lsb = tk->size_shift;
	int ret = 0;

	pr_err("%#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
			pfn, t->comm, t->pid);

	if ((flags & MF_ACTION_REQUIRED) && (t == current))
		ret = force_sig_mceerr(BUS_MCEERR_AR,
				 (void __user *)tk->addr, addr_lsb);
	else
		/*
		 * Signal other processes sharing the page if they have
		 * PF_MCE_EARLY set.
		 * Don't use force here, it's convenient if the signal
		 * can be temporarily blocked.
		 * This could cause a loop when the user sets SIGBUS
		 * to SIG_IGN, but hopefully no one will do that?
		 */
		ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr,
				      addr_lsb, t);
	if (ret < 0)
		pr_info("Error sending signal to %s:%d: %d\n",
			t->comm, t->pid, ret);
	return ret;
}

/*
 * Unknown page type encountered. Try to check whether it can turn PageLRU by
 * lru_add_drain_all.
 */
void shake_page(struct page *p)
{
	if (PageHuge(p))
		return;
	/*
	 * TODO: Could shrink slab caches here if a lightweight range-based
	 * shrinker will be available.
	 */
	if (PageSlab(p))
		return;

	lru_add_drain_all();
}
EXPORT_SYMBOL_GPL(shake_page);

static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
		unsigned long address)
{
	unsigned long ret = 0;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	pte_t ptent;

	VM_BUG_ON_VMA(address == -EFAULT, vma);
	pgd = pgd_offset(vma->vm_mm, address);
	if (!pgd_present(*pgd))
		return 0;
	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		return 0;
	pud = pud_offset(p4d, address);
	if (!pud_present(*pud))
		return 0;
	if (pud_devmap(*pud))
		return PUD_SHIFT;
	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd))
		return 0;
	if (pmd_devmap(*pmd))
		return PMD_SHIFT;
	pte = pte_offset_map(pmd, address);
	if (!pte)
		return 0;
	ptent = ptep_get(pte);
	if (pte_present(ptent) && pte_devmap(ptent))
		ret = PAGE_SHIFT;
	pte_unmap(pte);
	return ret;
}

/*
 * Failure handling: if we can't find or can't kill a process there's
 * not much we can do.	We just print a message and ignore otherwise.
 */

#define FSDAX_INVALID_PGOFF ULONG_MAX

/*
 * Schedule a process for later kill.
 * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
 *
 * Note: @fsdax_pgoff is used only when @p is a fsdax page and a
 * filesystem with a memory failure handler has claimed the
 * memory_failure event. In all other cases, page->index and
 * page->mapping are sufficient for mapping the page back to its
 * corresponding user virtual address.
 */
static void __add_to_kill(struct task_struct *tsk, struct page *p,
			  struct vm_area_struct *vma, struct list_head *to_kill,
			  unsigned long ksm_addr, pgoff_t fsdax_pgoff)
{
	struct to_kill *tk;

	tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
	if (!tk) {
		pr_err("Out of memory while machine check handling\n");
		return;
	}

	tk->addr = ksm_addr ? ksm_addr : page_address_in_vma(p, vma);
	if (is_zone_device_page(p)) {
		if (fsdax_pgoff != FSDAX_INVALID_PGOFF)
			tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma);
		tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr);
	} else
		tk->size_shift = page_shift(compound_head(p));

	/*
	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
	 * so "tk->size_shift == 0" effectively checks no mapping on
	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
	 * to a process' address space, it's possible not all N VMAs
	 * contain mappings for the page, but at least one VMA does.
	 * Only deliver SIGBUS with payload derived from the VMA that
	 * has a mapping for the page.
	 */
	if (tk->addr == -EFAULT) {
		pr_info("Unable to find user space address %lx in %s\n",
			page_to_pfn(p), tsk->comm);
	} else if (tk->size_shift == 0) {
		kfree(tk);
		return;
	}

	get_task_struct(tsk);
	tk->tsk = tsk;
	list_add_tail(&tk->nd, to_kill);
}

static void add_to_kill_anon_file(struct task_struct *tsk, struct page *p,
				  struct vm_area_struct *vma,
				  struct list_head *to_kill)
{
	__add_to_kill(tsk, p, vma, to_kill, 0, FSDAX_INVALID_PGOFF);
}

#ifdef CONFIG_KSM
static bool task_in_to_kill_list(struct list_head *to_kill,
				 struct task_struct *tsk)
{
	struct to_kill *tk, *next;

	list_for_each_entry_safe(tk, next, to_kill, nd) {
		if (tk->tsk == tsk)
			return true;
	}

	return false;
}
void add_to_kill_ksm(struct task_struct *tsk, struct page *p,
		     struct vm_area_struct *vma, struct list_head *to_kill,
		     unsigned long ksm_addr)
{
	if (!task_in_to_kill_list(to_kill, tsk))
		__add_to_kill(tsk, p, vma, to_kill, ksm_addr, FSDAX_INVALID_PGOFF);
}
#endif
/*
 * Kill the processes that have been collected earlier.
 *
 * Only do anything when FORCEKILL is set, otherwise just free the
 * list (this is used for clean pages which do not need killing)
 * Also when FAIL is set do a force kill because something went
 * wrong earlier.
 */
static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
		unsigned long pfn, int flags)
{
	struct to_kill *tk, *next;

	list_for_each_entry_safe(tk, next, to_kill, nd) {
		if (forcekill) {
			/*
			 * In case something went wrong with munmapping
			 * make sure the process doesn't catch the
			 * signal and then access the memory. Just kill it.
			 */
			if (fail || tk->addr == -EFAULT) {
				pr_err("%#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
				       pfn, tk->tsk->comm, tk->tsk->pid);
				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
						 tk->tsk, PIDTYPE_PID);
			}

			/*
			 * In theory the process could have mapped
			 * something else on the address in-between. We could
			 * check for that, but we need to tell the
			 * process anyways.
			 */
			else if (kill_proc(tk, pfn, flags) < 0)
				pr_err("%#lx: Cannot send advisory machine check signal to %s:%d\n",
				       pfn, tk->tsk->comm, tk->tsk->pid);
		}
		list_del(&tk->nd);
		put_task_struct(tk->tsk);
		kfree(tk);
	}
}

/*
 * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
 * on behalf of the thread group. Return task_struct of the (first found)
 * dedicated thread if found, and return NULL otherwise.
 *
 * We already hold rcu lock in the caller, so we don't have to call
 * rcu_read_lock/unlock() in this function.
 */
static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
{
	struct task_struct *t;

	for_each_thread(tsk, t) {
		if (t->flags & PF_MCE_PROCESS) {
			if (t->flags & PF_MCE_EARLY)
				return t;
		} else {
			if (sysctl_memory_failure_early_kill)
				return t;
		}
	}
	return NULL;
}

/*
 * Determine whether a given process is "early kill" process which expects
 * to be signaled when some page under the process is hwpoisoned.
 * Return task_struct of the dedicated thread (main thread unless explicitly
 * specified) if the process is "early kill" and otherwise returns NULL.
 *
 * Note that the above is true for Action Optional case. For Action Required
 * case, it's only meaningful to the current thread which need to be signaled
 * with SIGBUS, this error is Action Optional for other non current
 * processes sharing the same error page,if the process is "early kill", the
 * task_struct of the dedicated thread will also be returned.
 */
struct task_struct *task_early_kill(struct task_struct *tsk, int force_early)
{
	if (!tsk->mm)
		return NULL;
	/*
	 * Comparing ->mm here because current task might represent
	 * a subthread, while tsk always points to the main thread.
	 */
	if (force_early && tsk->mm == current->mm)
		return current;

	return find_early_kill_thread(tsk);
}

/*
 * Collect processes when the error hit an anonymous page.
 */
static void collect_procs_anon(struct folio *folio, struct page *page,
		struct list_head *to_kill, int force_early)
{
	struct vm_area_struct *vma;
	struct task_struct *tsk;
	struct anon_vma *av;
	pgoff_t pgoff;

	av = folio_lock_anon_vma_read(folio, NULL);
	if (av == NULL)	/* Not actually mapped anymore */
		return;

	pgoff = page_to_pgoff(page);
	rcu_read_lock();
	for_each_process(tsk) {
		struct anon_vma_chain *vmac;
		struct task_struct *t = task_early_kill(tsk, force_early);

		if (!t)
			continue;
		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
					       pgoff, pgoff) {
			vma = vmac->vma;
			if (vma->vm_mm != t->mm)
				continue;
			if (!page_mapped_in_vma(page, vma))
				continue;
			add_to_kill_anon_file(t, page, vma, to_kill);
		}
	}
	rcu_read_unlock();
	anon_vma_unlock_read(av);
}

/*
 * Collect processes when the error hit a file mapped page.
 */
static void collect_procs_file(struct folio *folio, struct page *page,
		struct list_head *to_kill, int force_early)
{
	struct vm_area_struct *vma;
	struct task_struct *tsk;
	struct address_space *mapping = folio->mapping;
	pgoff_t pgoff;

	i_mmap_lock_read(mapping);
	rcu_read_lock();
	pgoff = page_to_pgoff(page);
	for_each_process(tsk) {
		struct task_struct *t = task_early_kill(tsk, force_early);

		if (!t)
			continue;
		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
				      pgoff) {
			/*
			 * Send early kill signal to tasks where a vma covers
			 * the page but the corrupted page is not necessarily
			 * mapped in its pte.
			 * Assume applications who requested early kill want
			 * to be informed of all such data corruptions.
			 */
			if (vma->vm_mm == t->mm)
				add_to_kill_anon_file(t, page, vma, to_kill);
		}
	}
	rcu_read_unlock();
	i_mmap_unlock_read(mapping);
}

#ifdef CONFIG_FS_DAX
static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p,
			      struct vm_area_struct *vma,
			      struct list_head *to_kill, pgoff_t pgoff)
{
	__add_to_kill(tsk, p, vma, to_kill, 0, pgoff);
}

/*
 * Collect processes when the error hit a fsdax page.
 */
static void collect_procs_fsdax(struct page *page,
		struct address_space *mapping, pgoff_t pgoff,
		struct list_head *to_kill, bool pre_remove)
{
	struct vm_area_struct *vma;
	struct task_struct *tsk;

	i_mmap_lock_read(mapping);
	rcu_read_lock();
	for_each_process(tsk) {
		struct task_struct *t = tsk;

		/*
		 * Search for all tasks while MF_MEM_PRE_REMOVE is set, because
		 * the current may not be the one accessing the fsdax page.
		 * Otherwise, search for the current task.
		 */
		if (!pre_remove)
			t = task_early_kill(tsk, true);
		if (!t)
			continue;
		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
			if (vma->vm_mm == t->mm)
				add_to_kill_fsdax(t, page, vma, to_kill, pgoff);
		}
	}
	rcu_read_unlock();
	i_mmap_unlock_read(mapping);
}
#endif /* CONFIG_FS_DAX */

/*
 * Collect the processes who have the corrupted page mapped to kill.
 */
static void collect_procs(struct folio *folio, struct page *page,
		struct list_head *tokill, int force_early)
{
	if (!folio->mapping)
		return;
	if (unlikely(PageKsm(page)))
		collect_procs_ksm(page, tokill, force_early);
	else if (PageAnon(page))
		collect_procs_anon(folio, page, tokill, force_early);
	else
		collect_procs_file(folio, page, tokill, force_early);
}

struct hwpoison_walk {
	struct to_kill tk;
	unsigned long pfn;
	int flags;
};

static void set_to_kill(struct to_kill *tk, unsigned long addr, short shift)
{
	tk->addr = addr;
	tk->size_shift = shift;
}

static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift,
				unsigned long poisoned_pfn, struct to_kill *tk)
{
	unsigned long pfn = 0;

	if (pte_present(pte)) {
		pfn = pte_pfn(pte);
	} else {
		swp_entry_t swp = pte_to_swp_entry(pte);

		if (is_hwpoison_entry(swp))
			pfn = swp_offset_pfn(swp);
	}

	if (!pfn || pfn != poisoned_pfn)
		return 0;

	set_to_kill(tk, addr, shift);
	return 1;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr,
				      struct hwpoison_walk *hwp)
{
	pmd_t pmd = *pmdp;
	unsigned long pfn;
	unsigned long hwpoison_vaddr;

	if (!pmd_present(pmd))
		return 0;
	pfn = pmd_pfn(pmd);
	if (pfn <= hwp->pfn && hwp->pfn < pfn + HPAGE_PMD_NR) {
		hwpoison_vaddr = addr + ((hwp->pfn - pfn) << PAGE_SHIFT);
		set_to_kill(&hwp->tk, hwpoison_vaddr, PAGE_SHIFT);
		return 1;
	}
	return 0;
}
#else
static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr,
				      struct hwpoison_walk *hwp)
{
	return 0;
}
#endif

static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
			      unsigned long end, struct mm_walk *walk)
{
	struct hwpoison_walk *hwp = walk->private;
	int ret = 0;
	pte_t *ptep, *mapped_pte;
	spinlock_t *ptl;

	ptl = pmd_trans_huge_lock(pmdp, walk->vma);
	if (ptl) {
		ret = check_hwpoisoned_pmd_entry(pmdp, addr, hwp);
		spin_unlock(ptl);
		goto out;
	}

	mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp,
						addr, &ptl);
	if (!ptep)
		goto out;

	for (; addr != end; ptep++, addr += PAGE_SIZE) {
		ret = check_hwpoisoned_entry(ptep_get(ptep), addr, PAGE_SHIFT,
					     hwp->pfn, &hwp->tk);
		if (ret == 1)
			break;
	}
	pte_unmap_unlock(mapped_pte, ptl);
out:
	cond_resched();
	return ret;
}

#ifdef CONFIG_HUGETLB_PAGE
static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
			    unsigned long addr, unsigned long end,
			    struct mm_walk *walk)
{
	struct hwpoison_walk *hwp = walk->private;
	pte_t pte = huge_ptep_get(ptep);
	struct hstate *h = hstate_vma(walk->vma);

	return check_hwpoisoned_entry(pte, addr, huge_page_shift(h),
				      hwp->pfn, &hwp->tk);
}
#else
#define hwpoison_hugetlb_range	NULL
#endif

static const struct mm_walk_ops hwpoison_walk_ops = {
	.pmd_entry = hwpoison_pte_range,
	.hugetlb_entry = hwpoison_hugetlb_range,
	.walk_lock = PGWALK_RDLOCK,
};

/*
 * Sends SIGBUS to the current process with error info.
 *
 * This function is intended to handle "Action Required" MCEs on already
 * hardware poisoned pages. They could happen, for example, when
 * memory_failure() failed to unmap the error page at the first call, or
 * when multiple local machine checks happened on different CPUs.
 *
 * MCE handler currently has no easy access to the error virtual address,
 * so this function walks page table to find it. The returned virtual address
 * is proper in most cases, but it could be wrong when the application
 * process has multiple entries mapping the error page.
 */
static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
				  int flags)
{
	int ret;
	struct hwpoison_walk priv = {
		.pfn = pfn,
	};
	priv.tk.tsk = p;

	if (!p->mm)
		return -EFAULT;

	mmap_read_lock(p->mm);
	ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwpoison_walk_ops,
			      (void *)&priv);
	if (ret == 1 && priv.tk.addr)
		kill_proc(&priv.tk, pfn, flags);
	else
		ret = 0;
	mmap_read_unlock(p->mm);
	return ret > 0 ? -EHWPOISON : -EFAULT;
}

static const char *action_name[] = {
	[MF_IGNORED] = "Ignored",
	[MF_FAILED] = "Failed",
	[MF_DELAYED] = "Delayed",
	[MF_RECOVERED] = "Recovered",
};

static const char * const action_page_types[] = {
	[MF_MSG_KERNEL]			= "reserved kernel page",
	[MF_MSG_KERNEL_HIGH_ORDER]	= "high-order kernel page",
	[MF_MSG_SLAB]			= "kernel slab page",
	[MF_MSG_DIFFERENT_COMPOUND]	= "different compound page after locking",
	[MF_MSG_HUGE]			= "huge page",
	[MF_MSG_FREE_HUGE]		= "free huge page",
	[MF_MSG_UNMAP_FAILED]		= "unmapping failed page",
	[MF_MSG_DIRTY_SWAPCACHE]	= "dirty swapcache page",
	[MF_MSG_CLEAN_SWAPCACHE]	= "clean swapcache page",
	[MF_MSG_DIRTY_MLOCKED_LRU]	= "dirty mlocked LRU page",
	[MF_MSG_CLEAN_MLOCKED_LRU]	= "clean mlocked LRU page",
	[MF_MSG_DIRTY_UNEVICTABLE_LRU]	= "dirty unevictable LRU page",
	[MF_MSG_CLEAN_UNEVICTABLE_LRU]	= "clean unevictable LRU page",
	[MF_MSG_DIRTY_LRU]		= "dirty LRU page",
	[MF_MSG_CLEAN_LRU]		= "clean LRU page",
	[MF_MSG_TRUNCATED_LRU]		= "already truncated LRU page",
	[MF_MSG_BUDDY]			= "free buddy page",
	[MF_MSG_DAX]			= "dax page",
	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
	[MF_MSG_UNKNOWN]		= "unknown page",
};

/*
 * XXX: It is possible that a page is isolated from LRU cache,
 * and then kept in swap cache or failed to remove from page cache.
 * The page count will stop it from being freed by unpoison.
 * Stress tests should be aware of this memory leak problem.
 */
static int delete_from_lru_cache(struct folio *folio)
{
	if (folio_isolate_lru(folio)) {
		/*
		 * Clear sensible page flags, so that the buddy system won't
		 * complain when the folio is unpoison-and-freed.
		 */
		folio_clear_active(folio);
		folio_clear_unevictable(folio);

		/*
		 * Poisoned page might never drop its ref count to 0 so we have
		 * to uncharge it manually from its memcg.
		 */
		mem_cgroup_uncharge(folio);

		/*
		 * drop the refcount elevated by folio_isolate_lru()
		 */
		folio_put(folio);
		return 0;
	}
	return -EIO;
}

static int truncate_error_folio(struct folio *folio, unsigned long pfn,
				struct address_space *mapping)
{
	int ret = MF_FAILED;

	if (mapping->a_ops->error_remove_folio) {
		int err = mapping->a_ops->error_remove_folio(mapping, folio);

		if (err != 0)
			pr_info("%#lx: Failed to punch page: %d\n", pfn, err);
		else if (!filemap_release_folio(folio, GFP_NOIO))
			pr_info("%#lx: failed to release buffers\n", pfn);
		else
			ret = MF_RECOVERED;
	} else {
		/*
		 * If the file system doesn't support it just invalidate
		 * This fails on dirty or anything with private pages
		 */
		if (mapping_evict_folio(mapping, folio))
			ret = MF_RECOVERED;
		else
			pr_info("%#lx: Failed to invalidate\n",	pfn);
	}

	return ret;
}

struct page_state {
	unsigned long mask;
	unsigned long res;
	enum mf_action_page_type type;

	/* Callback ->action() has to unlock the relevant page inside it. */
	int (*action)(struct page_state *ps, struct page *p);
};

/*
 * Return true if page is still referenced by others, otherwise return
 * false.
 *
 * The extra_pins is true when one extra refcount is expected.
 */
static bool has_extra_refcount(struct page_state *ps, struct page *p,
			       bool extra_pins)
{
	int count = page_count(p) - 1;

	if (extra_pins)
		count -= folio_nr_pages(page_folio(p));

	if (count > 0) {
		pr_err("%#lx: %s still referenced by %d users\n",
		       page_to_pfn(p), action_page_types[ps->type], count);
		return true;
	}

	return false;
}

/*
 * Error hit kernel page.
 * Do nothing, try to be lucky and not touch this instead. For a few cases we
 * could be more sophisticated.
 */
static int me_kernel(struct page_state *ps, struct page *p)
{
	unlock_page(p);
	return MF_IGNORED;
}

/*
 * Page in unknown state. Do nothing.
 */
static int me_unknown(struct page_state *ps, struct page *p)
{
	pr_err("%#lx: Unknown page state\n", page_to_pfn(p));
	unlock_page(p);
	return MF_FAILED;
}

/*
 * Clean (or cleaned) page cache page.
 */
static int me_pagecache_clean(struct page_state *ps, struct page *p)
{
	struct folio *folio = page_folio(p);
	int ret;
	struct address_space *mapping;
	bool extra_pins;

	delete_from_lru_cache(folio);

	/*
	 * For anonymous folios the only reference left
	 * should be the one m_f() holds.
	 */
	if (folio_test_anon(folio)) {
		ret = MF_RECOVERED;
		goto out;
	}

	/*
	 * Now truncate the page in the page cache. This is really
	 * more like a "temporary hole punch"
	 * Don't do this for block devices when someone else
	 * has a reference, because it could be file system metadata
	 * and that's not safe to truncate.
	 */
	mapping = folio_mapping(folio);
	if (!mapping) {
		/* Folio has been torn down in the meantime */
		ret = MF_FAILED;
		goto out;
	}

	/*
	 * The shmem page is kept in page cache instead of truncating
	 * so is expected to have an extra refcount after error-handling.
	 */
	extra_pins = shmem_mapping(mapping);

	/*
	 * Truncation is a bit tricky. Enable it per file system for now.
	 *
	 * Open: to take i_rwsem or not for this? Right now we don't.
	 */
	ret = truncate_error_folio(folio, page_to_pfn(p), mapping);
	if (has_extra_refcount(ps, p, extra_pins))
		ret = MF_FAILED;

out:
	folio_unlock(folio);

	return ret;
}

/*
 * Dirty pagecache page
 * Issues: when the error hit a hole page the error is not properly
 * propagated.
 */
static int me_pagecache_dirty(struct page_state *ps, struct page *p)
{
	struct address_space *mapping = page_mapping(p);

	SetPageError(p);
	/* TBD: print more information about the file. */
	if (mapping) {
		/*
		 * IO error will be reported by write(), fsync(), etc.
		 * who check the mapping.
		 * This way the application knows that something went
		 * wrong with its dirty file data.
		 *
		 * There's one open issue:
		 *
		 * The EIO will be only reported on the next IO
		 * operation and then cleared through the IO map.
		 * Normally Linux has two mechanisms to pass IO error
		 * first through the AS_EIO flag in the address space
		 * and then through the PageError flag in the page.
		 * Since we drop pages on memory failure handling the
		 * only mechanism open to use is through AS_AIO.
		 *
		 * This has the disadvantage that it gets cleared on
		 * the first operation that returns an error, while
		 * the PageError bit is more sticky and only cleared
		 * when the page is reread or dropped.  If an
		 * application assumes it will always get error on
		 * fsync, but does other operations on the fd before
		 * and the page is dropped between then the error
		 * will not be properly reported.
		 *
		 * This can already happen even without hwpoisoned
		 * pages: first on metadata IO errors (which only
		 * report through AS_EIO) or when the page is dropped
		 * at the wrong time.
		 *
		 * So right now we assume that the application DTRT on
		 * the first EIO, but we're not worse than other parts
		 * of the kernel.
		 */
		mapping_set_error(mapping, -EIO);
	}

	return me_pagecache_clean(ps, p);
}

/*
 * Clean and dirty swap cache.
 *
 * Dirty swap cache page is tricky to handle. The page could live both in page
 * cache and swap cache(ie. page is freshly swapped in). So it could be
 * referenced concurrently by 2 types of PTEs:
 * normal PTEs and swap PTEs. We try to handle them consistently by calling
 * try_to_unmap(!TTU_HWPOISON) to convert the normal PTEs to swap PTEs,
 * and then
 *      - clear dirty bit to prevent IO
 *      - remove from LRU
 *      - but keep in the swap cache, so that when we return to it on
 *        a later page fault, we know the application is accessing
 *        corrupted data and shall be killed (we installed simple
 *        interception code in do_swap_page to catch it).
 *
 * Clean swap cache pages can be directly isolated. A later page fault will
 * bring in the known good data from disk.
 */
static int me_swapcache_dirty(struct page_state *ps, struct page *p)
{
	struct folio *folio = page_folio(p);
	int ret;
	bool extra_pins = false;

	folio_clear_dirty(folio);
	/* Trigger EIO in shmem: */
	folio_clear_uptodate(folio);

	ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_DELAYED;
	folio_unlock(folio);

	if (ret == MF_DELAYED)
		extra_pins = true;

	if (has_extra_refcount(ps, p, extra_pins))
		ret = MF_FAILED;

	return ret;
}

static int me_swapcache_clean(struct page_state *ps, struct page *p)
{
	struct folio *folio = page_folio(p);
	int ret;

	delete_from_swap_cache(folio);

	ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_RECOVERED;
	folio_unlock(folio);

	if (has_extra_refcount(ps, p, false))
		ret = MF_FAILED;

	return ret;
}

/*
 * Huge pages. Needs work.
 * Issues:
 * - Error on hugepage is contained in hugepage unit (not in raw page unit.)
 *   To narrow down kill region to one page, we need to break up pmd.
 */
static int me_huge_page(struct page_state *ps, struct page *p)
{
	struct folio *folio = page_folio(p);
	int res;
	struct address_space *mapping;
	bool extra_pins = false;

	mapping = folio_mapping(folio);
	if (mapping) {
		res = truncate_error_folio(folio, page_to_pfn(p), mapping);
		/* The page is kept in page cache. */
		extra_pins = true;
		folio_unlock(folio);
	} else {
		folio_unlock(folio);
		/*
		 * migration entry prevents later access on error hugepage,
		 * so we can free and dissolve it into buddy to save healthy
		 * subpages.
		 */
		folio_put(folio);
		if (__page_handle_poison(p) >= 0) {
			page_ref_inc(p);
			res = MF_RECOVERED;
		} else {
			res = MF_FAILED;
		}
	}

	if (has_extra_refcount(ps, p, extra_pins))
		res = MF_FAILED;

	return res;
}

/*
 * Various page states we can handle.
 *
 * A page state is defined by its current page->flags bits.
 * The table matches them in order and calls the right handler.
 *
 * This is quite tricky because we can access page at any time
 * in its live cycle, so all accesses have to be extremely careful.
 *
 * This is not complete. More states could be added.
 * For any missing state don't attempt recovery.
 */

#define dirty		(1UL << PG_dirty)
#define sc		((1UL << PG_swapcache) | (1UL << PG_swapbacked))
#define unevict		(1UL << PG_unevictable)
#define mlock		(1UL << PG_mlocked)
#define lru		(1UL << PG_lru)
#define head		(1UL << PG_head)
#define slab		(1UL << PG_slab)
#define reserved	(1UL << PG_reserved)

static struct page_state error_states[] = {
	{ reserved,	reserved,	MF_MSG_KERNEL,	me_kernel },
	/*
	 * free pages are specially detected outside this table:
	 * PG_buddy pages only make a small fraction of all free pages.
	 */

	/*
	 * Could in theory check if slab page is free or if we can drop
	 * currently unused objects without touching them. But just
	 * treat it as standard kernel for now.
	 */
	{ slab,		slab,		MF_MSG_SLAB,	me_kernel },

	{ head,		head,		MF_MSG_HUGE,		me_huge_page },

	{ sc|dirty,	sc|dirty,	MF_MSG_DIRTY_SWAPCACHE,	me_swapcache_dirty },
	{ sc|dirty,	sc,		MF_MSG_CLEAN_SWAPCACHE,	me_swapcache_clean },

	{ mlock|dirty,	mlock|dirty,	MF_MSG_DIRTY_MLOCKED_LRU,	me_pagecache_dirty },
	{ mlock|dirty,	mlock,		MF_MSG_CLEAN_MLOCKED_LRU,	me_pagecache_clean },

	{ unevict|dirty, unevict|dirty,	MF_MSG_DIRTY_UNEVICTABLE_LRU,	me_pagecache_dirty },
	{ unevict|dirty, unevict,	MF_MSG_CLEAN_UNEVICTABLE_LRU,	me_pagecache_clean },

	{ lru|dirty,	lru|dirty,	MF_MSG_DIRTY_LRU,	me_pagecache_dirty },
	{ lru|dirty,	lru,		MF_MSG_CLEAN_LRU,	me_pagecache_clean },

	/*
	 * Catchall entry: must be at end.
	 */
	{ 0,		0,		MF_MSG_UNKNOWN,	me_unknown },
};

#undef dirty
#undef sc
#undef unevict
#undef mlock
#undef lru
#undef head
#undef slab
#undef reserved

static void update_per_node_mf_stats(unsigned long pfn,
				     enum mf_result result)
{
	int nid = MAX_NUMNODES;
	struct memory_failure_stats *mf_stats = NULL;

	nid = pfn_to_nid(pfn);
	if (unlikely(nid < 0 || nid >= MAX_NUMNODES)) {
		WARN_ONCE(1, "Memory failure: pfn=%#lx, invalid nid=%d", pfn, nid);
		return;
	}

	mf_stats = &NODE_DATA(nid)->mf_stats;
	switch (result) {
	case MF_IGNORED:
		++mf_stats->ignored;
		break;
	case MF_FAILED:
		++mf_stats->failed;
		break;
	case MF_DELAYED:
		++mf_stats->delayed;
		break;
	case MF_RECOVERED:
		++mf_stats->recovered;
		break;
	default:
		WARN_ONCE(1, "Memory failure: mf_result=%d is not properly handled", result);
		break;
	}
	++mf_stats->total;
}

/*
 * "Dirty/Clean" indication is not 100% accurate due to the possibility of
 * setting PG_dirty outside page lock. See also comment above set_page_dirty().
 */
static int action_result(unsigned long pfn, enum mf_action_page_type type,
			 enum mf_result result)
{
	trace_memory_failure_event(pfn, type, result);

	num_poisoned_pages_inc(pfn);

	update_per_node_mf_stats(pfn, result);

	pr_err("%#lx: recovery action for %s: %s\n",
		pfn, action_page_types[type], action_name[result]);

	return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
}

static int page_action(struct page_state *ps, struct page *p,
			unsigned long pfn)
{
	int result;

	/* page p should be unlocked after returning from ps->action().  */
	result = ps->action(ps, p);

	/* Could do more checks here if page looks ok */
	/*
	 * Could adjust zone counters here to correct for the missing page.
	 */

	return action_result(pfn, ps->type, result);
}

static inline bool PageHWPoisonTakenOff(struct page *page)
{
	return PageHWPoison(page) && page_private(page) == MAGIC_HWPOISON;
}

void SetPageHWPoisonTakenOff(struct page *page)
{
	set_page_private(page, MAGIC_HWPOISON);
}

void ClearPageHWPoisonTakenOff(struct page *page)
{
	if (PageHWPoison(page))
		set_page_private(page, 0);
}

/*
 * Return true if a page type of a given page is supported by hwpoison
 * mechanism (while handling could fail), otherwise false.  This function
 * does not return true for hugetlb or device memory pages, so it's assumed
 * to be called only in the context where we never have such pages.
 */
static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
{
	if (PageSlab(page))
		return false;

	/* Soft offline could migrate non-LRU movable pages */
	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
		return true;

	return PageLRU(page) || is_free_buddy_page(page);
}

static int __get_hwpoison_page(struct page *page, unsigned long flags)
{
	struct folio *folio = page_folio(page);
	int ret = 0;
	bool hugetlb = false;

	ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, false);
	if (hugetlb) {
		/* Make sure hugetlb demotion did not happen from under us. */
		if (folio == page_folio(page))
			return ret;
		if (ret > 0) {
			folio_put(folio);
			folio = page_folio(page);
		}
	}

	/*
	 * This check prevents from calling folio_try_get() for any
	 * unsupported type of folio in order to reduce the risk of unexpected
	 * races caused by taking a folio refcount.
	 */
	if (!HWPoisonHandlable(&folio->page, flags))
		return -EBUSY;

	if (folio_try_get(folio)) {
		if (folio == page_folio(page))
			return 1;

		pr_info("%#lx cannot catch tail\n", page_to_pfn(page));
		folio_put(folio);
	}

	return 0;
}

static int get_any_page(struct page *p, unsigned long flags)
{
	int ret = 0, pass = 0;
	bool count_increased = false;

	if (flags & MF_COUNT_INCREASED)
		count_increased = true;

try_again:
	if (!count_increased) {
		ret = __get_hwpoison_page(p, flags);
		if (!ret) {
			if (page_count(p)) {
				/* We raced with an allocation, retry. */
				if (pass++ < 3)
					goto try_again;
				ret = -EBUSY;
			} else if (!PageHuge(p) && !is_free_buddy_page(p)) {
				/* We raced with put_page, retry. */
				if (pass++ < 3)
					goto try_again;
				ret = -EIO;
			}
			goto out;
		} else if (ret == -EBUSY) {
			/*
			 * We raced with (possibly temporary) unhandlable
			 * page, retry.
			 */
			if (pass++ < 3) {
				shake_page(p);
				goto try_again;
			}
			ret = -EIO;
			goto out;
		}
	}

	if (PageHuge(p) || HWPoisonHandlable(p, flags)) {
		ret = 1;
	} else {
		/*
		 * A page we cannot handle. Check whether we can turn
		 * it into something we can handle.
		 */
		if (pass++ < 3) {
			put_page(p);
			shake_page(p);
			count_increased = false;
			goto try_again;
		}
		put_page(p);
		ret = -EIO;
	}
out:
	if (ret == -EIO)
		pr_err("%#lx: unhandlable page.\n", page_to_pfn(p));

	return ret;
}

static int __get_unpoison_page(struct page *page)
{
	struct folio *folio = page_folio(page);
	int ret = 0;
	bool hugetlb = false;

	ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, true);
	if (hugetlb) {
		/* Make sure hugetlb demotion did not happen from under us. */
		if (folio == page_folio(page))
			return ret;
		if (ret > 0)
			folio_put(folio);
	}

	/*
	 * PageHWPoisonTakenOff pages are not only marked as PG_hwpoison,
	 * but also isolated from buddy freelist, so need to identify the
	 * state and have to cancel both operations to unpoison.
	 */
	if (PageHWPoisonTakenOff(page))
		return -EHWPOISON;

	return get_page_unless_zero(page) ? 1 : 0;
}

/**
 * get_hwpoison_page() - Get refcount for memory error handling
 * @p:		Raw error page (hit by memory error)
 * @flags:	Flags controlling behavior of error handling
 *
 * get_hwpoison_page() takes a page refcount of an error page to handle memory
 * error on it, after checking that the error page is in a well-defined state
 * (defined as a page-type we can successfully handle the memory error on it,
 * such as LRU page and hugetlb page).
 *
 * Memory error handling could be triggered at any time on any type of page,
 * so it's prone to race with typical memory management lifecycle (like
 * allocation and free).  So to avoid such races, get_hwpoison_page() takes
 * extra care for the error page's state (as done in __get_hwpoison_page()),
 * and has some retry logic in get_any_page().
 *
 * When called from unpoison_memory(), the caller should already ensure that
 * the given page has PG_hwpoison. So it's never reused for other page
 * allocations, and __get_unpoison_page() never races with them.
 *
 * Return: 0 on failure,
 *         1 on success for in-use pages in a well-defined state,
 *         -EIO for pages on which we can not handle memory errors,
 *         -EBUSY when get_hwpoison_page() has raced with page lifecycle
 *         operations like allocation and free,
 *         -EHWPOISON when the page is hwpoisoned and taken off from buddy.
 */
static int get_hwpoison_page(struct page *p, unsigned long flags)
{
	int ret;

	zone_pcp_disable(page_zone(p));
	if (flags & MF_UNPOISON)
		ret = __get_unpoison_page(p);
	else
		ret = get_any_page(p, flags);
	zone_pcp_enable(page_zone(p));

	return ret;
}

/*
 * Do all that is necessary to remove user space mappings. Unmap
 * the pages and send SIGBUS to the processes if the data was dirty.
 */
static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
				  int flags, struct page *hpage)
{
	struct folio *folio = page_folio(hpage);
	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
	struct address_space *mapping;
	LIST_HEAD(tokill);
	bool unmap_success;
	int forcekill;
	bool mlocked = PageMlocked(hpage);

	/*
	 * Here we are interested only in user-mapped pages, so skip any
	 * other types of pages.
	 */
	if (PageReserved(p) || PageSlab(p) || PageTable(p) || PageOffline(p))
		return true;
	if (!(PageLRU(hpage) || PageHuge(p)))
		return true;

	/*
	 * This check implies we don't kill processes if their pages
	 * are in the swap cache early. Those are always late kills.
	 */
	if (!page_mapped(p))
		return true;

	if (PageSwapCache(p)) {
		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
		ttu &= ~TTU_HWPOISON;
	}

	/*
	 * Propagate the dirty bit from PTEs to struct page first, because we
	 * need this to decide if we should kill or just drop the page.
	 * XXX: the dirty test could be racy: set_page_dirty() may not always
	 * be called inside page lock (it's recommended but not enforced).
	 */
	mapping = page_mapping(hpage);
	if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
	    mapping_can_writeback(mapping)) {
		if (page_mkclean(hpage)) {
			SetPageDirty(hpage);
		} else {
			ttu &= ~TTU_HWPOISON;
			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
				pfn);
		}
	}

	/*
	 * First collect all the processes that have the page
	 * mapped in dirty form.  This has to be done before try_to_unmap,
	 * because ttu takes the rmap data structures down.
	 */
	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);

	if (PageHuge(hpage) && !PageAnon(hpage)) {
		/*
		 * For hugetlb pages in shared mappings, try_to_unmap
		 * could potentially call huge_pmd_unshare.  Because of
		 * this, take semaphore in write mode here and set
		 * TTU_RMAP_LOCKED to indicate we have taken the lock
		 * at this higher level.
		 */
		mapping = hugetlb_page_mapping_lock_write(hpage);
		if (mapping) {
			try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
			i_mmap_unlock_write(mapping);
		} else
			pr_info("%#lx: could not lock mapping for mapped huge page\n", pfn);
	} else {
		try_to_unmap(folio, ttu);
	}

	unmap_success = !page_mapped(p);
	if (!unmap_success)
		pr_err("%#lx: failed to unmap page (mapcount=%d)\n",
		       pfn, page_mapcount(p));

	/*
	 * try_to_unmap() might put mlocked page in lru cache, so call
	 * shake_page() again to ensure that it's flushed.
	 */
	if (mlocked)
		shake_page(hpage);

	/*
	 * Now that the dirty bit has been propagated to the
	 * struct page and all unmaps done we can decide if
	 * killing is needed or not.  Only kill when the page
	 * was dirty or the process is not restartable,
	 * otherwise the tokill list is merely
	 * freed.  When there was a problem unmapping earlier
	 * use a more force-full uncatchable kill to prevent
	 * any accesses to the poisoned memory.
	 */
	forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL) ||
		    !unmap_success;
	kill_procs(&tokill, forcekill, !unmap_success, pfn, flags);

	return unmap_success;
}

static int identify_page_state(unsigned long pfn, struct page *p,
				unsigned long page_flags)
{
	struct page_state *ps;

	/*
	 * The first check uses the current page flags which may not have any
	 * relevant information. The second check with the saved page flags is
	 * carried out only if the first check can't determine the page status.
	 */
	for (ps = error_states;; ps++)
		if ((p->flags & ps->mask) == ps->res)
			break;

	page_flags |= (p->flags & (1UL << PG_dirty));

	if (!ps->mask)
		for (ps = error_states;; ps++)
			if ((page_flags & ps->mask) == ps->res)
				break;
	return page_action(ps, p, pfn);
}

static int try_to_split_thp_page(struct page *page)
{
	int ret;

	lock_page(page);
	ret = split_huge_page(page);
	unlock_page(page);

	if (unlikely(ret))
		put_page(page);

	return ret;
}

static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn,
		struct address_space *mapping, pgoff_t index, int flags)
{
	struct to_kill *tk;
	unsigned long size = 0;

	list_for_each_entry(tk, to_kill, nd)
		if (tk->size_shift)
			size = max(size, 1UL << tk->size_shift);

	if (size) {
		/*
		 * Unmap the largest mapping to avoid breaking up device-dax
		 * mappings which are constant size. The actual size of the
		 * mapping being torn down is communicated in siginfo, see
		 * kill_proc()
		 */
		loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1);

		unmap_mapping_range(mapping, start, size, 0);
	}

	kill_procs(to_kill, flags & MF_MUST_KILL, false, pfn, flags);
}

/*
 * Only dev_pagemap pages get here, such as fsdax when the filesystem
 * either do not claim or fails to claim a hwpoison event, or devdax.
 * The fsdax pages are initialized per base page, and the devdax pages
 * could be initialized either as base pages, or as compound pages with
 * vmemmap optimization enabled. Devdax is simplistic in its dealing with
 * hwpoison, such that, if a subpage of a compound page is poisoned,
 * simply mark the compound head page is by far sufficient.
 */
static int mf_generic_kill_procs(unsigned long long pfn, int flags,
		struct dev_pagemap *pgmap)
{
	struct folio *folio = pfn_folio(pfn);
	LIST_HEAD(to_kill);
	dax_entry_t cookie;
	int rc = 0;

	/*
	 * Prevent the inode from being freed while we are interrogating
	 * the address_space, typically this would be handled by
	 * lock_page(), but dax pages do not use the page lock. This
	 * also prevents changes to the mapping of this pfn until
	 * poison signaling is complete.
	 */
	cookie = dax_lock_folio(folio);
	if (!cookie)
		return -EBUSY;

	if (hwpoison_filter(&folio->page)) {
		rc = -EOPNOTSUPP;
		goto unlock;
	}

	switch (pgmap->type) {
	case MEMORY_DEVICE_PRIVATE:
	case MEMORY_DEVICE_COHERENT:
		/*
		 * TODO: Handle device pages which may need coordination
		 * with device-side memory.
		 */
		rc = -ENXIO;
		goto unlock;
	default:
		break;
	}

	/*
	 * Use this flag as an indication that the dax page has been
	 * remapped UC to prevent speculative consumption of poison.
	 */
	SetPageHWPoison(&folio->page);

	/*
	 * Unlike System-RAM there is no possibility to swap in a
	 * different physical page at a given virtual address, so all
	 * userspace consumption of ZONE_DEVICE memory necessitates
	 * SIGBUS (i.e. MF_MUST_KILL)
	 */
	flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
	collect_procs(folio, &folio->page, &to_kill, true);

	unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags);
unlock:
	dax_unlock_folio(folio, cookie);
	return rc;
}

#ifdef CONFIG_FS_DAX
/**
 * mf_dax_kill_procs - Collect and kill processes who are using this file range
 * @mapping:	address_space of the file in use
 * @index:	start pgoff of the range within the file
 * @count:	length of the range, in unit of PAGE_SIZE
 * @mf_flags:	memory failure flags
 */
int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
		unsigned long count, int mf_flags)
{
	LIST_HEAD(to_kill);
	dax_entry_t cookie;
	struct page *page;
	size_t end = index + count;
	bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE;

	mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;

	for (; index < end; index++) {
		page = NULL;
		cookie = dax_lock_mapping_entry(mapping, index, &page);
		if (!cookie)
			return -EBUSY;
		if (!page)
			goto unlock;

		if (!pre_remove)
			SetPageHWPoison(page);

		/*
		 * The pre_remove case is revoking access, the memory is still
		 * good and could theoretically be put back into service.
		 */
		collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove);
		unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
				index, mf_flags);
unlock:
		dax_unlock_mapping_entry(mapping, index, cookie);
	}
	return 0;
}
EXPORT_SYMBOL_GPL(mf_dax_kill_procs);
#endif /* CONFIG_FS_DAX */

#ifdef CONFIG_HUGETLB_PAGE

/*
 * Struct raw_hwp_page represents information about "raw error page",
 * constructing singly linked list from ->_hugetlb_hwpoison field of folio.
 */
struct raw_hwp_page {
	struct llist_node node;
	struct page *page;
};

static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
{
	return (struct llist_head *)&folio->_hugetlb_hwpoison;
}

bool is_raw_hwpoison_page_in_hugepage(struct page *page)
{
	struct llist_head *raw_hwp_head;
	struct raw_hwp_page *p;
	struct folio *folio = page_folio(page);
	bool ret = false;

	if (!folio_test_hwpoison(folio))
		return false;

	if (!folio_test_hugetlb(folio))
		return PageHWPoison(page);

	/*
	 * When RawHwpUnreliable is set, kernel lost track of which subpages
	 * are HWPOISON. So return as if ALL subpages are HWPOISONed.
	 */
	if (folio_test_hugetlb_raw_hwp_unreliable(folio))
		return true;

	mutex_lock(&mf_mutex);

	raw_hwp_head = raw_hwp_list_head(folio);
	llist_for_each_entry(p, raw_hwp_head->first, node) {
		if (page == p->page) {
			ret = true;
			break;
		}
	}

	mutex_unlock(&mf_mutex);

	return ret;
}

static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
{
	struct llist_node *head;
	struct raw_hwp_page *p, *next;
	unsigned long count = 0;

	head = llist_del_all(raw_hwp_list_head(folio));
	llist_for_each_entry_safe(p, next, head, node) {
		if (move_flag)
			SetPageHWPoison(p->page);
		else
			num_poisoned_pages_sub(page_to_pfn(p->page), 1);
		kfree(p);
		count++;
	}
	return count;
}

static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page)
{
	struct llist_head *head;
	struct raw_hwp_page *raw_hwp;
	struct raw_hwp_page *p, *next;
	int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0;

	/*
	 * Once the hwpoison hugepage has lost reliable raw error info,
	 * there is little meaning to keep additional error info precisely,
	 * so skip to add additional raw error info.
	 */
	if (folio_test_hugetlb_raw_hwp_unreliable(folio))
		return -EHWPOISON;
	head = raw_hwp_list_head(folio);
	llist_for_each_entry_safe(p, next, head->first, node) {
		if (p->page == page)
			return -EHWPOISON;
	}

	raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC);
	if (raw_hwp) {
		raw_hwp->page = page;
		llist_add(&raw_hwp->node, head);
		/* the first error event will be counted in action_result(). */
		if (ret)
			num_poisoned_pages_inc(page_to_pfn(page));
	} else {
		/*
		 * Failed to save raw error info.  We no longer trace all
		 * hwpoisoned subpages, and we need refuse to free/dissolve
		 * this hwpoisoned hugepage.
		 */
		folio_set_hugetlb_raw_hwp_unreliable(folio);
		/*
		 * Once hugetlb_raw_hwp_unreliable is set, raw_hwp_page is not
		 * used any more, so free it.
		 */
		__folio_free_raw_hwp(folio, false);
	}
	return ret;
}

static unsigned long folio_free_raw_hwp(struct folio *folio, bool move_flag)
{
	/*
	 * hugetlb_vmemmap_optimized hugepages can't be freed because struct
	 * pages for tail pages are required but they don't exist.
	 */
	if (move_flag && folio_test_hugetlb_vmemmap_optimized(folio))
		return 0;

	/*
	 * hugetlb_raw_hwp_unreliable hugepages shouldn't be unpoisoned by
	 * definition.
	 */
	if (folio_test_hugetlb_raw_hwp_unreliable(folio))
		return 0;

	return __folio_free_raw_hwp(folio, move_flag);
}

void folio_clear_hugetlb_hwpoison(struct folio *folio)
{
	if (folio_test_hugetlb_raw_hwp_unreliable(folio))
		return;
	if (folio_test_hugetlb_vmemmap_optimized(folio))
		return;
	folio_clear_hwpoison(folio);
	folio_free_raw_hwp(folio, true);
}

/*
 * Called from hugetlb code with hugetlb_lock held.
 *
 * Return values:
 *   0             - free hugepage
 *   1             - in-use hugepage
 *   2             - not a hugepage
 *   -EBUSY        - the hugepage is busy (try to retry)
 *   -EHWPOISON    - the hugepage is already hwpoisoned
 */
int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
				 bool *migratable_cleared)
{
	struct page *page = pfn_to_page(pfn);
	struct folio *folio = page_folio(page);
	int ret = 2;	/* fallback to normal page handling */
	bool count_increased = false;

	if (!folio_test_hugetlb(folio))
		goto out;

	if (flags & MF_COUNT_INCREASED) {
		ret = 1;
		count_increased = true;
	} else if (folio_test_hugetlb_freed(folio)) {
		ret = 0;
	} else if (folio_test_hugetlb_migratable(folio)) {
		ret = folio_try_get(folio);
		if (ret)
			count_increased = true;
	} else {
		ret = -EBUSY;
		if (!(flags & MF_NO_RETRY))
			goto out;
	}

	if (folio_set_hugetlb_hwpoison(folio, page)) {
		ret = -EHWPOISON;
		goto out;
	}

	/*
	 * Clearing hugetlb_migratable for hwpoisoned hugepages to prevent them
	 * from being migrated by memory hotremove.
	 */
	if (count_increased && folio_test_hugetlb_migratable(folio)) {
		folio_clear_hugetlb_migratable(folio);
		*migratable_cleared = true;
	}

	return ret;
out:
	if (count_increased)
		folio_put(folio);
	return ret;
}

/*
 * Taking refcount of hugetlb pages needs extra care about race conditions
 * with basic operations like hugepage allocation/free/demotion.
 * So some of prechecks for hwpoison (pinning, and testing/setting
 * PageHWPoison) should be done in single hugetlb_lock range.
 */
static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
{
	int res;
	struct page *p = pfn_to_page(pfn);
	struct folio *folio;
	unsigned long page_flags;
	bool migratable_cleared = false;

	*hugetlb = 1;
retry:
	res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared);
	if (res == 2) { /* fallback to normal page handling */
		*hugetlb = 0;
		return 0;
	} else if (res == -EHWPOISON) {
		pr_err("%#lx: already hardware poisoned\n", pfn);
		if (flags & MF_ACTION_REQUIRED) {
			folio = page_folio(p);
			res = kill_accessing_process(current, folio_pfn(folio), flags);
		}
		return res;
	} else if (res == -EBUSY) {
		if (!(flags & MF_NO_RETRY)) {
			flags |= MF_NO_RETRY;
			goto retry;
		}
		return action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
	}

	folio = page_folio(p);
	folio_lock(folio);

	if (hwpoison_filter(p)) {
		folio_clear_hugetlb_hwpoison(folio);
		if (migratable_cleared)
			folio_set_hugetlb_migratable(folio);
		folio_unlock(folio);
		if (res == 1)
			folio_put(folio);
		return -EOPNOTSUPP;
	}

	/*
	 * Handling free hugepage.  The possible race with hugepage allocation
	 * or demotion can be prevented by PageHWPoison flag.
	 */
	if (res == 0) {
		folio_unlock(folio);
		if (__page_handle_poison(p) >= 0) {
			page_ref_inc(p);
			res = MF_RECOVERED;
		} else {
			res = MF_FAILED;
		}
		return action_result(pfn, MF_MSG_FREE_HUGE, res);
	}

	page_flags = folio->flags;

	if (!hwpoison_user_mappings(p, pfn, flags, &folio->page)) {
		folio_unlock(folio);
		return action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
	}

	return identify_page_state(pfn, p, page_flags);
}

#else
static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
{
	return 0;
}

static inline unsigned long folio_free_raw_hwp(struct folio *folio, bool flag)
{
	return 0;
}
#endif	/* CONFIG_HUGETLB_PAGE */

/* Drop the extra refcount in case we come from madvise() */
static void put_ref_page(unsigned long pfn, int flags)
{
	struct page *page;

	if (!(flags & MF_COUNT_INCREASED))
		return;

	page = pfn_to_page(pfn);
	if (page)
		put_page(page);
}

static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
		struct dev_pagemap *pgmap)
{
	int rc = -ENXIO;

	/* device metadata space is not recoverable */
	if (!pgmap_pfn_valid(pgmap, pfn))
		goto out;

	/*
	 * Call driver's implementation to handle the memory failure, otherwise
	 * fall back to generic handler.
	 */
	if (pgmap_has_memory_failure(pgmap)) {
		rc = pgmap->ops->memory_failure(pgmap, pfn, 1, flags);
		/*
		 * Fall back to generic handler too if operation is not
		 * supported inside the driver/device/filesystem.
		 */
		if (rc != -EOPNOTSUPP)
			goto out;
	}

	rc = mf_generic_kill_procs(pfn, flags, pgmap);
out:
	/* drop pgmap ref acquired in caller */
	put_dev_pagemap(pgmap);
	if (rc != -EOPNOTSUPP)
		action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED);
	return rc;
}

/**
 * memory_failure - Handle memory failure of a page.
 * @pfn: Page Number of the corrupted page
 * @flags: fine tune action taken
 *
 * This function is called by the low level machine check code
 * of an architecture when it detects hardware memory corruption
 * of a page. It tries its best to recover, which includes
 * dropping pages, killing processes etc.
 *
 * The function is primarily of use for corruptions that
 * happen outside the current execution context (e.g. when
 * detected by a background scrubber)
 *
 * Must run in process context (e.g. a work queue) with interrupts
 * enabled and no spinlocks held.
 *
 * Return: 0 for successfully handled the memory error,
 *         -EOPNOTSUPP for hwpoison_filter() filtered the error event,
 *         < 0(except -EOPNOTSUPP) on failure.
 */
int memory_failure(unsigned long pfn, int flags)
{
	struct page *p;
	struct page *hpage;
	struct dev_pagemap *pgmap;
	int res = 0;
	unsigned long page_flags;
	bool retry = true;
	int hugetlb = 0;

	if (!sysctl_memory_failure_recovery)
		panic("Memory failure on page %lx", pfn);

	mutex_lock(&mf_mutex);

	if (!(flags & MF_SW_SIMULATED))
		hw_memory_failure = true;

	p = pfn_to_online_page(pfn);
	if (!p) {
		res = arch_memory_failure(pfn, flags);
		if (res == 0)
			goto unlock_mutex;

		if (pfn_valid(pfn)) {
			pgmap = get_dev_pagemap(pfn, NULL);
			put_ref_page(pfn, flags);
			if (pgmap) {
				res = memory_failure_dev_pagemap(pfn, flags,
								 pgmap);
				goto unlock_mutex;
			}
		}
		pr_err("%#lx: memory outside kernel control\n", pfn);
		res = -ENXIO;
		goto unlock_mutex;
	}

try_again:
	res = try_memory_failure_hugetlb(pfn, flags, &hugetlb);
	if (hugetlb)
		goto unlock_mutex;

	if (TestSetPageHWPoison(p)) {
		pr_err("%#lx: already hardware poisoned\n", pfn);
		res = -EHWPOISON;
		if (flags & MF_ACTION_REQUIRED)
			res = kill_accessing_process(current, pfn, flags);
		if (flags & MF_COUNT_INCREASED)
			put_page(p);
		goto unlock_mutex;
	}

	/*
	 * We need/can do nothing about count=0 pages.
	 * 1) it's a free page, and therefore in safe hand:
	 *    check_new_page() will be the gate keeper.
	 * 2) it's part of a non-compound high order page.
	 *    Implies some kernel user: cannot stop them from
	 *    R/W the page; let's pray that the page has been
	 *    used and will be freed some time later.
	 * In fact it's dangerous to directly bump up page count from 0,
	 * that may make page_ref_freeze()/page_ref_unfreeze() mismatch.
	 */
	if (!(flags & MF_COUNT_INCREASED)) {
		res = get_hwpoison_page(p, flags);
		if (!res) {
			if (is_free_buddy_page(p)) {
				if (take_page_off_buddy(p)) {
					page_ref_inc(p);
					res = MF_RECOVERED;
				} else {
					/* We lost the race, try again */
					if (retry) {
						ClearPageHWPoison(p);
						retry = false;
						goto try_again;
					}
					res = MF_FAILED;
				}
				res = action_result(pfn, MF_MSG_BUDDY, res);
			} else {
				res = action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
			}
			goto unlock_mutex;
		} else if (res < 0) {
			res = action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
			goto unlock_mutex;
		}
	}

	hpage = compound_head(p);
	if (PageTransHuge(hpage)) {
		/*
		 * The flag must be set after the refcount is bumped
		 * otherwise it may race with THP split.
		 * And the flag can't be set in get_hwpoison_page() since
		 * it is called by soft offline too and it is just called
		 * for !MF_COUNT_INCREASED.  So here seems to be the best
		 * place.
		 *
		 * Don't need care about the above error handling paths for
		 * get_hwpoison_page() since they handle either free page
		 * or unhandlable page.  The refcount is bumped iff the
		 * page is a valid handlable page.
		 */
		SetPageHasHWPoisoned(hpage);
		if (try_to_split_thp_page(p) < 0) {
			res = action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
			goto unlock_mutex;
		}
		VM_BUG_ON_PAGE(!page_count(p), p);
	}

	/*
	 * We ignore non-LRU pages for good reasons.
	 * - PG_locked is only well defined for LRU pages and a few others
	 * - to avoid races with __SetPageLocked()
	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
	 * The check (unnecessarily) ignores LRU pages being isolated and
	 * walked by the page reclaim code, however that's not a big loss.
	 */
	shake_page(p);

	lock_page(p);

	/*
	 * We're only intended to deal with the non-Compound page here.
	 * However, the page could have changed compound pages due to
	 * race window. If this happens, we could try again to hopefully
	 * handle the page next round.
	 */
	if (PageCompound(p)) {
		if (retry) {
			ClearPageHWPoison(p);
			unlock_page(p);
			put_page(p);
			flags &= ~MF_COUNT_INCREASED;
			retry = false;
			goto try_again;
		}
		res = action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED);
		goto unlock_page;
	}

	/*
	 * We use page flags to determine what action should be taken, but
	 * the flags can be modified by the error containment action.  One
	 * example is an mlocked page, where PG_mlocked is cleared by
	 * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page
	 * status correctly, we save a copy of the page flags at this time.
	 */
	page_flags = p->flags;

	if (hwpoison_filter(p)) {
		ClearPageHWPoison(p);
		unlock_page(p);
		put_page(p);
		res = -EOPNOTSUPP;
		goto unlock_mutex;
	}

	/*
	 * __munlock_folio() may clear a writeback page's LRU flag without
	 * page_lock. We need wait writeback completion for this page or it
	 * may trigger vfs BUG while evict inode.
	 */
	if (!PageLRU(p) && !PageWriteback(p))
		goto identify_page_state;

	/*
	 * It's very difficult to mess with pages currently under IO
	 * and in many cases impossible, so we just avoid it here.
	 */
	wait_on_page_writeback(p);

	/*
	 * Now take care of user space mappings.
	 * Abort on fail: __filemap_remove_folio() assumes unmapped page.
	 */
	if (!hwpoison_user_mappings(p, pfn, flags, p)) {
		res = action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
		goto unlock_page;
	}

	/*
	 * Torn down by someone else?
	 */
	if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
		res = action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED);
		goto unlock_page;
	}

identify_page_state:
	res = identify_page_state(pfn, p, page_flags);
	mutex_unlock(&mf_mutex);
	return res;
unlock_page:
	unlock_page(p);
unlock_mutex:
	mutex_unlock(&mf_mutex);
	return res;
}
EXPORT_SYMBOL_GPL(memory_failure);

#define MEMORY_FAILURE_FIFO_ORDER	4
#define MEMORY_FAILURE_FIFO_SIZE	(1 << MEMORY_FAILURE_FIFO_ORDER)

struct memory_failure_entry {
	unsigned long pfn;
	int flags;
};

struct memory_failure_cpu {
	DECLARE_KFIFO(fifo, struct memory_failure_entry,
		      MEMORY_FAILURE_FIFO_SIZE);
	spinlock_t lock;
	struct work_struct work;
};

static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);

/**
 * memory_failure_queue - Schedule handling memory failure of a page.
 * @pfn: Page Number of the corrupted page
 * @flags: Flags for memory failure handling
 *
 * This function is called by the low level hardware error handler
 * when it detects hardware memory corruption of a page. It schedules
 * the recovering of error page, including dropping pages, killing
 * processes etc.
 *
 * The function is primarily of use for corruptions that
 * happen outside the current execution context (e.g. when
 * detected by a background scrubber)
 *
 * Can run in IRQ context.
 */
void memory_failure_queue(unsigned long pfn, int flags)
{
	struct memory_failure_cpu *mf_cpu;
	unsigned long proc_flags;
	struct memory_failure_entry entry = {
		.pfn =		pfn,
		.flags =	flags,
	};

	mf_cpu = &get_cpu_var(memory_failure_cpu);
	spin_lock_irqsave(&mf_cpu->lock, proc_flags);
	if (kfifo_put(&mf_cpu->fifo, entry))
		schedule_work_on(smp_processor_id(), &mf_cpu->work);
	else
		pr_err("buffer overflow when queuing memory failure at %#lx\n",
		       pfn);
	spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
	put_cpu_var(memory_failure_cpu);
}
EXPORT_SYMBOL_GPL(memory_failure_queue);

static void memory_failure_work_func(struct work_struct *work)
{
	struct memory_failure_cpu *mf_cpu;
	struct memory_failure_entry entry = { 0, };
	unsigned long proc_flags;
	int gotten;

	mf_cpu = container_of(work, struct memory_failure_cpu, work);
	for (;;) {
		spin_lock_irqsave(&mf_cpu->lock, proc_flags);
		gotten = kfifo_get(&mf_cpu->fifo, &entry);
		spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
		if (!gotten)
			break;
		if (entry.flags & MF_SOFT_OFFLINE)
			soft_offline_page(entry.pfn, entry.flags);
		else
			memory_failure(entry.pfn, entry.flags);
	}
}

/*
 * Process memory_failure work queued on the specified CPU.
 * Used to avoid return-to-userspace racing with the memory_failure workqueue.
 */
void memory_failure_queue_kick(int cpu)
{
	struct memory_failure_cpu *mf_cpu;

	mf_cpu = &per_cpu(memory_failure_cpu, cpu);
	cancel_work_sync(&mf_cpu->work);
	memory_failure_work_func(&mf_cpu->work);
}

static int __init memory_failure_init(void)
{
	struct memory_failure_cpu *mf_cpu;
	int cpu;

	for_each_possible_cpu(cpu) {
		mf_cpu = &per_cpu(memory_failure_cpu, cpu);
		spin_lock_init(&mf_cpu->lock);
		INIT_KFIFO(mf_cpu->fifo);
		INIT_WORK(&mf_cpu->work, memory_failure_work_func);
	}

	register_sysctl_init("vm", memory_failure_table);

	return 0;
}
core_initcall(memory_failure_init);

#undef pr_fmt
#define pr_fmt(fmt)	"" fmt
#define unpoison_pr_info(fmt, pfn, rs)			\
({							\
	if (__ratelimit(rs))				\
		pr_info(fmt, pfn);			\
})

/**
 * unpoison_memory - Unpoison a previously poisoned page
 * @pfn: Page number of the to be unpoisoned page
 *
 * Software-unpoison a page that has been poisoned by
 * memory_failure() earlier.
 *
 * This is only done on the software-level, so it only works
 * for linux injected failures, not real hardware failures
 *
 * Returns 0 for success, otherwise -errno.
 */
int unpoison_memory(unsigned long pfn)
{
	struct folio *folio;
	struct page *p;
	int ret = -EBUSY, ghp;
	unsigned long count = 1;
	bool huge = false;
	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
					DEFAULT_RATELIMIT_BURST);

	if (!pfn_valid(pfn))
		return -ENXIO;

	p = pfn_to_page(pfn);
	folio = page_folio(p);

	mutex_lock(&mf_mutex);

	if (hw_memory_failure) {
		unpoison_pr_info("Unpoison: Disabled after HW memory failure %#lx\n",
				 pfn, &unpoison_rs);
		ret = -EOPNOTSUPP;
		goto unlock_mutex;
	}

	if (!PageHWPoison(p)) {
		unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
				 pfn, &unpoison_rs);
		goto unlock_mutex;
	}

	if (folio_ref_count(folio) > 1) {
		unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n",
				 pfn, &unpoison_rs);
		goto unlock_mutex;
	}

	if (folio_test_slab(folio) || PageTable(&folio->page) ||
	    folio_test_reserved(folio) || PageOffline(&folio->page))
		goto unlock_mutex;

	/*
	 * Note that folio->_mapcount is overloaded in SLAB, so the simple test
	 * in folio_mapped() has to be done after folio_test_slab() is checked.
	 */
	if (folio_mapped(folio)) {
		unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n",
				 pfn, &unpoison_rs);
		goto unlock_mutex;
	}

	if (folio_mapping(folio)) {
		unpoison_pr_info("Unpoison: the hwpoison page has non-NULL mapping %#lx\n",
				 pfn, &unpoison_rs);
		goto unlock_mutex;
	}

	ghp = get_hwpoison_page(p, MF_UNPOISON);
	if (!ghp) {
		if (PageHuge(p)) {
			huge = true;
			count = folio_free_raw_hwp(folio, false);
			if (count == 0)
				goto unlock_mutex;
		}
		ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY;
	} else if (ghp < 0) {
		if (ghp == -EHWPOISON) {
			ret = put_page_back_buddy(p) ? 0 : -EBUSY;
		} else {
			ret = ghp;
			unpoison_pr_info("Unpoison: failed to grab page %#lx\n",
					 pfn, &unpoison_rs);
		}
	} else {
		if (PageHuge(p)) {
			huge = true;
			count = folio_free_raw_hwp(folio, false);
			if (count == 0) {
				folio_put(folio);
				goto unlock_mutex;
			}
		}

		folio_put(folio);
		if (TestClearPageHWPoison(p)) {
			folio_put(folio);
			ret = 0;
		}
	}

unlock_mutex:
	mutex_unlock(&mf_mutex);
	if (!ret) {
		if (!huge)
			num_poisoned_pages_sub(pfn, 1);
		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
				 page_to_pfn(p), &unpoison_rs);
	}
	return ret;
}
EXPORT_SYMBOL(unpoison_memory);

static bool mf_isolate_folio(struct folio *folio, struct list_head *pagelist)
{
	bool isolated = false;

	if (folio_test_hugetlb(folio)) {
		isolated = isolate_hugetlb(folio, pagelist);
	} else {
		bool lru = !__folio_test_movable(folio);

		if (lru)
			isolated = folio_isolate_lru(folio);
		else
			isolated = isolate_movable_page(&folio->page,
							ISOLATE_UNEVICTABLE);

		if (isolated) {
			list_add(&folio->lru, pagelist);
			if (lru)
				node_stat_add_folio(folio, NR_ISOLATED_ANON +
						    folio_is_file_lru(folio));
		}
	}

	/*
	 * If we succeed to isolate the folio, we grabbed another refcount on
	 * the folio, so we can safely drop the one we got from get_any_page().
	 * If we failed to isolate the folio, it means that we cannot go further
	 * and we will return an error, so drop the reference we got from
	 * get_any_page() as well.
	 */
	folio_put(folio);
	return isolated;
}

/*
 * soft_offline_in_use_page handles hugetlb-pages and non-hugetlb pages.
 * If the page is a non-dirty unmapped page-cache page, it simply invalidates.
 * If the page is mapped, it migrates the contents over.
 */
static int soft_offline_in_use_page(struct page *page)
{
	long ret = 0;
	unsigned long pfn = page_to_pfn(page);
	struct folio *folio = page_folio(page);
	char const *msg_page[] = {"page", "hugepage"};
	bool huge = folio_test_hugetlb(folio);
	LIST_HEAD(pagelist);
	struct migration_target_control mtc = {
		.nid = NUMA_NO_NODE,
		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
	};

	if (!huge && folio_test_large(folio)) {
		if (try_to_split_thp_page(page)) {
			pr_info("soft offline: %#lx: thp split failed\n", pfn);
			return -EBUSY;
		}
		folio = page_folio(page);
	}

	folio_lock(folio);
	if (!huge)
		folio_wait_writeback(folio);
	if (PageHWPoison(page)) {
		folio_unlock(folio);
		folio_put(folio);
		pr_info("soft offline: %#lx page already poisoned\n", pfn);
		return 0;
	}

	if (!huge && folio_test_lru(folio) && !folio_test_swapcache(folio))
		/*
		 * Try to invalidate first. This should work for
		 * non dirty unmapped page cache pages.
		 */
		ret = mapping_evict_folio(folio_mapping(folio), folio);
	folio_unlock(folio);

	if (ret) {
		pr_info("soft_offline: %#lx: invalidated\n", pfn);
		page_handle_poison(page, false, true);
		return 0;
	}

	if (mf_isolate_folio(folio, &pagelist)) {
		ret = migrate_pages(&pagelist, alloc_migration_target, NULL,
			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL);
		if (!ret) {
			bool release = !huge;

			if (!page_handle_poison(page, huge, release))
				ret = -EBUSY;
		} else {
			if (!list_empty(&pagelist))
				putback_movable_pages(&pagelist);

			pr_info("soft offline: %#lx: %s migration failed %ld, type %pGp\n",
				pfn, msg_page[huge], ret, &page->flags);
			if (ret > 0)
				ret = -EBUSY;
		}
	} else {
		pr_info("soft offline: %#lx: %s isolation failed, page count %d, type %pGp\n",
			pfn, msg_page[huge], page_count(page), &page->flags);
		ret = -EBUSY;
	}
	return ret;
}

/**
 * soft_offline_page - Soft offline a page.
 * @pfn: pfn to soft-offline
 * @flags: flags. Same as memory_failure().
 *
 * Returns 0 on success
 *         -EOPNOTSUPP for hwpoison_filter() filtered the error event
 *         < 0 otherwise negated errno.
 *
 * Soft offline a page, by migration or invalidation,
 * without killing anything. This is for the case when
 * a page is not corrupted yet (so it's still valid to access),
 * but has had a number of corrected errors and is better taken
 * out.
 *
 * The actual policy on when to do that is maintained by
 * user space.
 *
 * This should never impact any application or cause data loss,
 * however it might take some time.
 *
 * This is not a 100% solution for all memory, but tries to be
 * ``good enough'' for the majority of memory.
 */
int soft_offline_page(unsigned long pfn, int flags)
{
	int ret;
	bool try_again = true;
	struct page *page;

	if (!pfn_valid(pfn)) {
		WARN_ON_ONCE(flags & MF_COUNT_INCREASED);
		return -ENXIO;
	}

	/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
	page = pfn_to_online_page(pfn);
	if (!page) {
		put_ref_page(pfn, flags);
		return -EIO;
	}

	mutex_lock(&mf_mutex);

	if (PageHWPoison(page)) {
		pr_info("%s: %#lx page already poisoned\n", __func__, pfn);
		put_ref_page(pfn, flags);
		mutex_unlock(&mf_mutex);
		return 0;
	}

retry:
	get_online_mems();
	ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE);
	put_online_mems();

	if (hwpoison_filter(page)) {
		if (ret > 0)
			put_page(page);

		mutex_unlock(&mf_mutex);
		return -EOPNOTSUPP;
	}

	if (ret > 0) {
		ret = soft_offline_in_use_page(page);
	} else if (ret == 0) {
		if (!page_handle_poison(page, true, false)) {
			if (try_again) {
				try_again = false;
				flags &= ~MF_COUNT_INCREASED;
				goto retry;
			}
			ret = -EBUSY;
		}
	}

	mutex_unlock(&mf_mutex);

	return ret;
}