summaryrefslogtreecommitdiff
path: root/fs/buffer.c
blob: 1fc9a50def0b51ccc916d55003ebb02d2df567c1 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/fs/buffer.c
 *
 *  Copyright (C) 1991, 1992, 2002  Linus Torvalds
 */

/*
 * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95
 *
 * Removed a lot of unnecessary code and simplified things now that
 * the buffer cache isn't our primary cache - Andrew Tridgell 12/96
 *
 * Speed up hash, lru, and free list operations.  Use gfp() for allocating
 * hash table, use SLAB cache for buffer heads. SMP threading.  -DaveM
 *
 * Added 32k buffer block sizes - these are required older ARM systems. - RMK
 *
 * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de>
 */

#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/hash.h>
#include <linux/suspend.h>
#include <linux/buffer_head.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/bio.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
#include <linux/pagevec.h>
#include <linux/sched/mm.h>
#include <trace/events/block.h>
#include <linux/fscrypt.h>
#include <linux/fsverity.h>
#include <linux/sched/isolation.h>

#include "internal.h"

static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
			  enum rw_hint hint, struct writeback_control *wbc);

#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)

inline void touch_buffer(struct buffer_head *bh)
{
	trace_block_touch_buffer(bh);
	folio_mark_accessed(bh->b_folio);
}
EXPORT_SYMBOL(touch_buffer);

void __lock_buffer(struct buffer_head *bh)
{
	wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);

void unlock_buffer(struct buffer_head *bh)
{
	clear_bit_unlock(BH_Lock, &bh->b_state);
	smp_mb__after_atomic();
	wake_up_bit(&bh->b_state, BH_Lock);
}
EXPORT_SYMBOL(unlock_buffer);

/*
 * Returns if the folio has dirty or writeback buffers. If all the buffers
 * are unlocked and clean then the folio_test_dirty information is stale. If
 * any of the buffers are locked, it is assumed they are locked for IO.
 */
void buffer_check_dirty_writeback(struct folio *folio,
				     bool *dirty, bool *writeback)
{
	struct buffer_head *head, *bh;
	*dirty = false;
	*writeback = false;

	BUG_ON(!folio_test_locked(folio));

	head = folio_buffers(folio);
	if (!head)
		return;

	if (folio_test_writeback(folio))
		*writeback = true;

	bh = head;
	do {
		if (buffer_locked(bh))
			*writeback = true;

		if (buffer_dirty(bh))
			*dirty = true;

		bh = bh->b_this_page;
	} while (bh != head);
}

/*
 * Block until a buffer comes unlocked.  This doesn't stop it
 * from becoming locked again - you have to lock it yourself
 * if you want to preserve its state.
 */
void __wait_on_buffer(struct buffer_head * bh)
{
	wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__wait_on_buffer);

static void buffer_io_error(struct buffer_head *bh, char *msg)
{
	if (!test_bit(BH_Quiet, &bh->b_state))
		printk_ratelimited(KERN_ERR
			"Buffer I/O error on dev %pg, logical block %llu%s\n",
			bh->b_bdev, (unsigned long long)bh->b_blocknr, msg);
}

/*
 * End-of-IO handler helper function which does not touch the bh after
 * unlocking it.
 * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but
 * a race there is benign: unlock_buffer() only use the bh's address for
 * hashing after unlocking the buffer, so it doesn't actually touch the bh
 * itself.
 */
static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
{
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		/* This happens, due to failed read-ahead attempts. */
		clear_buffer_uptodate(bh);
	}
	unlock_buffer(bh);
}

/*
 * Default synchronous end-of-IO handler..  Just mark it up-to-date and
 * unlock the buffer.
 */
void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
{
	__end_buffer_read_notouch(bh, uptodate);
	put_bh(bh);
}
EXPORT_SYMBOL(end_buffer_read_sync);

void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		buffer_io_error(bh, ", lost sync page write");
		mark_buffer_write_io_error(bh);
		clear_buffer_uptodate(bh);
	}
	unlock_buffer(bh);
	put_bh(bh);
}
EXPORT_SYMBOL(end_buffer_write_sync);

/*
 * Various filesystems appear to want __find_get_block to be non-blocking.
 * But it's the page lock which protects the buffers.  To get around this,
 * we get exclusion from try_to_free_buffers with the blockdev mapping's
 * i_private_lock.
 *
 * Hack idea: for the blockdev mapping, i_private_lock contention
 * may be quite high.  This code could TryLock the page, and if that
 * succeeds, there is no need to take i_private_lock.
 */
static struct buffer_head *
__find_get_block_slow(struct block_device *bdev, sector_t block)
{
	struct address_space *bd_mapping = bdev->bd_mapping;
	const int blkbits = bd_mapping->host->i_blkbits;
	struct buffer_head *ret = NULL;
	pgoff_t index;
	struct buffer_head *bh;
	struct buffer_head *head;
	struct folio *folio;
	int all_mapped = 1;
	static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);

	index = ((loff_t)block << blkbits) / PAGE_SIZE;
	folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0);
	if (IS_ERR(folio))
		goto out;

	spin_lock(&bd_mapping->i_private_lock);
	head = folio_buffers(folio);
	if (!head)
		goto out_unlock;
	bh = head;
	do {
		if (!buffer_mapped(bh))
			all_mapped = 0;
		else if (bh->b_blocknr == block) {
			ret = bh;
			get_bh(bh);
			goto out_unlock;
		}
		bh = bh->b_this_page;
	} while (bh != head);

	/* we might be here because some of the buffers on this page are
	 * not mapped.  This is due to various races between
	 * file io on the block device and getblk.  It gets dealt with
	 * elsewhere, don't buffer_error if we had some unmapped buffers
	 */
	ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE);
	if (all_mapped && __ratelimit(&last_warned)) {
		printk("__find_get_block_slow() failed. block=%llu, "
		       "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, "
		       "device %pg blocksize: %d\n",
		       (unsigned long long)block,
		       (unsigned long long)bh->b_blocknr,
		       bh->b_state, bh->b_size, bdev,
		       1 << blkbits);
	}
out_unlock:
	spin_unlock(&bd_mapping->i_private_lock);
	folio_put(folio);
out:
	return ret;
}

static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
{
	unsigned long flags;
	struct buffer_head *first;
	struct buffer_head *tmp;
	struct folio *folio;
	int folio_uptodate = 1;

	BUG_ON(!buffer_async_read(bh));

	folio = bh->b_folio;
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		clear_buffer_uptodate(bh);
		buffer_io_error(bh, ", async page read");
	}

	/*
	 * Be _very_ careful from here on. Bad things can happen if
	 * two buffer heads end IO at almost the same time and both
	 * decide that the page is now completely done.
	 */
	first = folio_buffers(folio);
	spin_lock_irqsave(&first->b_uptodate_lock, flags);
	clear_buffer_async_read(bh);
	unlock_buffer(bh);
	tmp = bh;
	do {
		if (!buffer_uptodate(tmp))
			folio_uptodate = 0;
		if (buffer_async_read(tmp)) {
			BUG_ON(!buffer_locked(tmp));
			goto still_busy;
		}
		tmp = tmp->b_this_page;
	} while (tmp != bh);
	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);

	folio_end_read(folio, folio_uptodate);
	return;

still_busy:
	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
	return;
}

struct postprocess_bh_ctx {
	struct work_struct work;
	struct buffer_head *bh;
};

static void verify_bh(struct work_struct *work)
{
	struct postprocess_bh_ctx *ctx =
		container_of(work, struct postprocess_bh_ctx, work);
	struct buffer_head *bh = ctx->bh;
	bool valid;

	valid = fsverity_verify_blocks(bh->b_folio, bh->b_size, bh_offset(bh));
	end_buffer_async_read(bh, valid);
	kfree(ctx);
}

static bool need_fsverity(struct buffer_head *bh)
{
	struct folio *folio = bh->b_folio;
	struct inode *inode = folio->mapping->host;

	return fsverity_active(inode) &&
		/* needed by ext4 */
		folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}

static void decrypt_bh(struct work_struct *work)
{
	struct postprocess_bh_ctx *ctx =
		container_of(work, struct postprocess_bh_ctx, work);
	struct buffer_head *bh = ctx->bh;
	int err;

	err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size,
					       bh_offset(bh));
	if (err == 0 && need_fsverity(bh)) {
		/*
		 * We use different work queues for decryption and for verity
		 * because verity may require reading metadata pages that need
		 * decryption, and we shouldn't recurse to the same workqueue.
		 */
		INIT_WORK(&ctx->work, verify_bh);
		fsverity_enqueue_verify_work(&ctx->work);
		return;
	}
	end_buffer_async_read(bh, err == 0);
	kfree(ctx);
}

/*
 * I/O completion handler for block_read_full_folio() - pages
 * which come unlocked at the end of I/O.
 */
static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
{
	struct inode *inode = bh->b_folio->mapping->host;
	bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode);
	bool verify = need_fsverity(bh);

	/* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */
	if (uptodate && (decrypt || verify)) {
		struct postprocess_bh_ctx *ctx =
			kmalloc(sizeof(*ctx), GFP_ATOMIC);

		if (ctx) {
			ctx->bh = bh;
			if (decrypt) {
				INIT_WORK(&ctx->work, decrypt_bh);
				fscrypt_enqueue_decrypt_work(&ctx->work);
			} else {
				INIT_WORK(&ctx->work, verify_bh);
				fsverity_enqueue_verify_work(&ctx->work);
			}
			return;
		}
		uptodate = 0;
	}
	end_buffer_async_read(bh, uptodate);
}

/*
 * Completion handler for block_write_full_folio() - folios which are unlocked
 * during I/O, and which have the writeback flag cleared upon I/O completion.
 */
static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
	unsigned long flags;
	struct buffer_head *first;
	struct buffer_head *tmp;
	struct folio *folio;

	BUG_ON(!buffer_async_write(bh));

	folio = bh->b_folio;
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		buffer_io_error(bh, ", lost async page write");
		mark_buffer_write_io_error(bh);
		clear_buffer_uptodate(bh);
	}

	first = folio_buffers(folio);
	spin_lock_irqsave(&first->b_uptodate_lock, flags);

	clear_buffer_async_write(bh);
	unlock_buffer(bh);
	tmp = bh->b_this_page;
	while (tmp != bh) {
		if (buffer_async_write(tmp)) {
			BUG_ON(!buffer_locked(tmp));
			goto still_busy;
		}
		tmp = tmp->b_this_page;
	}
	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
	folio_end_writeback(folio);
	return;

still_busy:
	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
	return;
}

/*
 * If a page's buffers are under async readin (end_buffer_async_read
 * completion) then there is a possibility that another thread of
 * control could lock one of the buffers after it has completed
 * but while some of the other buffers have not completed.  This
 * locked buffer would confuse end_buffer_async_read() into not unlocking
 * the page.  So the absence of BH_Async_Read tells end_buffer_async_read()
 * that this buffer is not under async I/O.
 *
 * The page comes unlocked when it has no locked buffer_async buffers
 * left.
 *
 * PageLocked prevents anyone starting new async I/O reads any of
 * the buffers.
 *
 * PageWriteback is used to prevent simultaneous writeout of the same
 * page.
 *
 * PageLocked prevents anyone from starting writeback of a page which is
 * under read I/O (PageWriteback is only ever set against a locked page).
 */
static void mark_buffer_async_read(struct buffer_head *bh)
{
	bh->b_end_io = end_buffer_async_read_io;
	set_buffer_async_read(bh);
}

static void mark_buffer_async_write_endio(struct buffer_head *bh,
					  bh_end_io_t *handler)
{
	bh->b_end_io = handler;
	set_buffer_async_write(bh);
}

void mark_buffer_async_write(struct buffer_head *bh)
{
	mark_buffer_async_write_endio(bh, end_buffer_async_write);
}
EXPORT_SYMBOL(mark_buffer_async_write);


/*
 * fs/buffer.c contains helper functions for buffer-backed address space's
 * fsync functions.  A common requirement for buffer-based filesystems is
 * that certain data from the backing blockdev needs to be written out for
 * a successful fsync().  For example, ext2 indirect blocks need to be
 * written back and waited upon before fsync() returns.
 *
 * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(),
 * inode_has_buffers() and invalidate_inode_buffers() are provided for the
 * management of a list of dependent buffers at ->i_mapping->i_private_list.
 *
 * Locking is a little subtle: try_to_free_buffers() will remove buffers
 * from their controlling inode's queue when they are being freed.  But
 * try_to_free_buffers() will be operating against the *blockdev* mapping
 * at the time, not against the S_ISREG file which depends on those buffers.
 * So the locking for i_private_list is via the i_private_lock in the address_space
 * which backs the buffers.  Which is different from the address_space 
 * against which the buffers are listed.  So for a particular address_space,
 * mapping->i_private_lock does *not* protect mapping->i_private_list!  In fact,
 * mapping->i_private_list will always be protected by the backing blockdev's
 * ->i_private_lock.
 *
 * Which introduces a requirement: all buffers on an address_space's
 * ->i_private_list must be from the same address_space: the blockdev's.
 *
 * address_spaces which do not place buffers at ->i_private_list via these
 * utility functions are free to use i_private_lock and i_private_list for
 * whatever they want.  The only requirement is that list_empty(i_private_list)
 * be true at clear_inode() time.
 *
 * FIXME: clear_inode should not call invalidate_inode_buffers().  The
 * filesystems should do that.  invalidate_inode_buffers() should just go
 * BUG_ON(!list_empty).
 *
 * FIXME: mark_buffer_dirty_inode() is a data-plane operation.  It should
 * take an address_space, not an inode.  And it should be called
 * mark_buffer_dirty_fsync() to clearly define why those buffers are being
 * queued up.
 *
 * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the
 * list if it is already on a list.  Because if the buffer is on a list,
 * it *must* already be on the right one.  If not, the filesystem is being
 * silly.  This will save a ton of locking.  But first we have to ensure
 * that buffers are taken *off* the old inode's list when they are freed
 * (presumably in truncate).  That requires careful auditing of all
 * filesystems (do it inside bforget()).  It could also be done by bringing
 * b_inode back.
 */

/*
 * The buffer's backing address_space's i_private_lock must be held
 */
static void __remove_assoc_queue(struct buffer_head *bh)
{
	list_del_init(&bh->b_assoc_buffers);
	WARN_ON(!bh->b_assoc_map);
	bh->b_assoc_map = NULL;
}

int inode_has_buffers(struct inode *inode)
{
	return !list_empty(&inode->i_data.i_private_list);
}

/*
 * osync is designed to support O_SYNC io.  It waits synchronously for
 * all already-submitted IO to complete, but does not queue any new
 * writes to the disk.
 *
 * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer
 * as you dirty the buffers, and then use osync_inode_buffers to wait for
 * completion.  Any other dirty buffers which are not yet queued for
 * write will not be flushed to disk by the osync.
 */
static int osync_buffers_list(spinlock_t *lock, struct list_head *list)
{
	struct buffer_head *bh;
	struct list_head *p;
	int err = 0;

	spin_lock(lock);
repeat:
	list_for_each_prev(p, list) {
		bh = BH_ENTRY(p);
		if (buffer_locked(bh)) {
			get_bh(bh);
			spin_unlock(lock);
			wait_on_buffer(bh);
			if (!buffer_uptodate(bh))
				err = -EIO;
			brelse(bh);
			spin_lock(lock);
			goto repeat;
		}
	}
	spin_unlock(lock);
	return err;
}

/**
 * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
 * @mapping: the mapping which wants those buffers written
 *
 * Starts I/O against the buffers at mapping->i_private_list, and waits upon
 * that I/O.
 *
 * Basically, this is a convenience function for fsync().
 * @mapping is a file or directory which needs those buffers to be written for
 * a successful fsync().
 */
int sync_mapping_buffers(struct address_space *mapping)
{
	struct address_space *buffer_mapping = mapping->i_private_data;

	if (buffer_mapping == NULL || list_empty(&mapping->i_private_list))
		return 0;

	return fsync_buffers_list(&buffer_mapping->i_private_lock,
					&mapping->i_private_list);
}
EXPORT_SYMBOL(sync_mapping_buffers);

/**
 * generic_buffers_fsync_noflush - generic buffer fsync implementation
 * for simple filesystems with no inode lock
 *
 * @file:	file to synchronize
 * @start:	start offset in bytes
 * @end:	end offset in bytes (inclusive)
 * @datasync:	only synchronize essential metadata if true
 *
 * This is a generic implementation of the fsync method for simple
 * filesystems which track all non-inode metadata in the buffers list
 * hanging off the address_space structure.
 */
int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
				  bool datasync)
{
	struct inode *inode = file->f_mapping->host;
	int err;
	int ret;

	err = file_write_and_wait_range(file, start, end);
	if (err)
		return err;

	ret = sync_mapping_buffers(inode->i_mapping);
	if (!(inode->i_state & I_DIRTY_ALL))
		goto out;
	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
		goto out;

	err = sync_inode_metadata(inode, 1);
	if (ret == 0)
		ret = err;

out:
	/* check and advance again to catch errors after syncing out buffers */
	err = file_check_and_advance_wb_err(file);
	if (ret == 0)
		ret = err;
	return ret;
}
EXPORT_SYMBOL(generic_buffers_fsync_noflush);

/**
 * generic_buffers_fsync - generic buffer fsync implementation
 * for simple filesystems with no inode lock
 *
 * @file:	file to synchronize
 * @start:	start offset in bytes
 * @end:	end offset in bytes (inclusive)
 * @datasync:	only synchronize essential metadata if true
 *
 * This is a generic implementation of the fsync method for simple
 * filesystems which track all non-inode metadata in the buffers list
 * hanging off the address_space structure. This also makes sure that
 * a device cache flush operation is called at the end.
 */
int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
			  bool datasync)
{
	struct inode *inode = file->f_mapping->host;
	int ret;

	ret = generic_buffers_fsync_noflush(file, start, end, datasync);
	if (!ret)
		ret = blkdev_issue_flush(inode->i_sb->s_bdev);
	return ret;
}
EXPORT_SYMBOL(generic_buffers_fsync);

/*
 * Called when we've recently written block `bblock', and it is known that
 * `bblock' was for a buffer_boundary() buffer.  This means that the block at
 * `bblock + 1' is probably a dirty indirect block.  Hunt it down and, if it's
 * dirty, schedule it for IO.  So that indirects merge nicely with their data.
 */
void write_boundary_block(struct block_device *bdev,
			sector_t bblock, unsigned blocksize)
{
	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
	if (bh) {
		if (buffer_dirty(bh))
			write_dirty_buffer(bh, 0);
		put_bh(bh);
	}
}

void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
{
	struct address_space *mapping = inode->i_mapping;
	struct address_space *buffer_mapping = bh->b_folio->mapping;

	mark_buffer_dirty(bh);
	if (!mapping->i_private_data) {
		mapping->i_private_data = buffer_mapping;
	} else {
		BUG_ON(mapping->i_private_data != buffer_mapping);
	}
	if (!bh->b_assoc_map) {
		spin_lock(&buffer_mapping->i_private_lock);
		list_move_tail(&bh->b_assoc_buffers,
				&mapping->i_private_list);
		bh->b_assoc_map = mapping;
		spin_unlock(&buffer_mapping->i_private_lock);
	}
}
EXPORT_SYMBOL(mark_buffer_dirty_inode);

/**
 * block_dirty_folio - Mark a folio as dirty.
 * @mapping: The address space containing this folio.
 * @folio: The folio to mark dirty.
 *
 * Filesystems which use buffer_heads can use this function as their
 * ->dirty_folio implementation.  Some filesystems need to do a little
 * work before calling this function.  Filesystems which do not use
 * buffer_heads should call filemap_dirty_folio() instead.
 *
 * If the folio has buffers, the uptodate buffers are set dirty, to
 * preserve dirty-state coherency between the folio and the buffers.
 * Buffers added to a dirty folio are created dirty.
 *
 * The buffers are dirtied before the folio is dirtied.  There's a small
 * race window in which writeback may see the folio cleanness but not the
 * buffer dirtiness.  That's fine.  If this code were to set the folio
 * dirty before the buffers, writeback could clear the folio dirty flag,
 * see a bunch of clean buffers and we'd end up with dirty buffers/clean
 * folio on the dirty folio list.
 *
 * We use i_private_lock to lock against try_to_free_buffers() while
 * using the folio's buffer list.  This also prevents clean buffers
 * being added to the folio after it was set dirty.
 *
 * Context: May only be called from process context.  Does not sleep.
 * Caller must ensure that @folio cannot be truncated during this call,
 * typically by holding the folio lock or having a page in the folio
 * mapped and holding the page table lock.
 *
 * Return: True if the folio was dirtied; false if it was already dirtied.
 */
bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
{
	struct buffer_head *head;
	bool newly_dirty;

	spin_lock(&mapping->i_private_lock);
	head = folio_buffers(folio);
	if (head) {
		struct buffer_head *bh = head;

		do {
			set_buffer_dirty(bh);
			bh = bh->b_this_page;
		} while (bh != head);
	}
	/*
	 * Lock out page's memcg migration to keep PageDirty
	 * synchronized with per-memcg dirty page counters.
	 */
	folio_memcg_lock(folio);
	newly_dirty = !folio_test_set_dirty(folio);
	spin_unlock(&mapping->i_private_lock);

	if (newly_dirty)
		__folio_mark_dirty(folio, mapping, 1);

	folio_memcg_unlock(folio);

	if (newly_dirty)
		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	return newly_dirty;
}
EXPORT_SYMBOL(block_dirty_folio);

/*
 * Write out and wait upon a list of buffers.
 *
 * We have conflicting pressures: we want to make sure that all
 * initially dirty buffers get waited on, but that any subsequently
 * dirtied buffers don't.  After all, we don't want fsync to last
 * forever if somebody is actively writing to the file.
 *
 * Do this in two main stages: first we copy dirty buffers to a
 * temporary inode list, queueing the writes as we go.  Then we clean
 * up, waiting for those writes to complete.
 * 
 * During this second stage, any subsequent updates to the file may end
 * up refiling the buffer on the original inode's dirty list again, so
 * there is a chance we will end up with a buffer queued for write but
 * not yet completed on that list.  So, as a final cleanup we go through
 * the osync code to catch these locked, dirty buffers without requeuing
 * any newly dirty buffers for write.
 */
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
{
	struct buffer_head *bh;
	struct address_space *mapping;
	int err = 0, err2;
	struct blk_plug plug;
	LIST_HEAD(tmp);

	blk_start_plug(&plug);

	spin_lock(lock);
	while (!list_empty(list)) {
		bh = BH_ENTRY(list->next);
		mapping = bh->b_assoc_map;
		__remove_assoc_queue(bh);
		/* Avoid race with mark_buffer_dirty_inode() which does
		 * a lockless check and we rely on seeing the dirty bit */
		smp_mb();
		if (buffer_dirty(bh) || buffer_locked(bh)) {
			list_add(&bh->b_assoc_buffers, &tmp);
			bh->b_assoc_map = mapping;
			if (buffer_dirty(bh)) {
				get_bh(bh);
				spin_unlock(lock);
				/*
				 * Ensure any pending I/O completes so that
				 * write_dirty_buffer() actually writes the
				 * current contents - it is a noop if I/O is
				 * still in flight on potentially older
				 * contents.
				 */
				write_dirty_buffer(bh, REQ_SYNC);

				/*
				 * Kick off IO for the previous mapping. Note
				 * that we will not run the very last mapping,
				 * wait_on_buffer() will do that for us
				 * through sync_buffer().
				 */
				brelse(bh);
				spin_lock(lock);
			}
		}
	}

	spin_unlock(lock);
	blk_finish_plug(&plug);
	spin_lock(lock);

	while (!list_empty(&tmp)) {
		bh = BH_ENTRY(tmp.prev);
		get_bh(bh);
		mapping = bh->b_assoc_map;
		__remove_assoc_queue(bh);
		/* Avoid race with mark_buffer_dirty_inode() which does
		 * a lockless check and we rely on seeing the dirty bit */
		smp_mb();
		if (buffer_dirty(bh)) {
			list_add(&bh->b_assoc_buffers,
				 &mapping->i_private_list);
			bh->b_assoc_map = mapping;
		}
		spin_unlock(lock);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh))
			err = -EIO;
		brelse(bh);
		spin_lock(lock);
	}
	
	spin_unlock(lock);
	err2 = osync_buffers_list(lock, list);
	if (err)
		return err;
	else
		return err2;
}

/*
 * Invalidate any and all dirty buffers on a given inode.  We are
 * probably unmounting the fs, but that doesn't mean we have already
 * done a sync().  Just drop the buffers from the inode list.
 *
 * NOTE: we take the inode's blockdev's mapping's i_private_lock.  Which
 * assumes that all the buffers are against the blockdev.  Not true
 * for reiserfs.
 */
void invalidate_inode_buffers(struct inode *inode)
{
	if (inode_has_buffers(inode)) {
		struct address_space *mapping = &inode->i_data;
		struct list_head *list = &mapping->i_private_list;
		struct address_space *buffer_mapping = mapping->i_private_data;

		spin_lock(&buffer_mapping->i_private_lock);
		while (!list_empty(list))
			__remove_assoc_queue(BH_ENTRY(list->next));
		spin_unlock(&buffer_mapping->i_private_lock);
	}
}
EXPORT_SYMBOL(invalidate_inode_buffers);

/*
 * Remove any clean buffers from the inode's buffer list.  This is called
 * when we're trying to free the inode itself.  Those buffers can pin it.
 *
 * Returns true if all buffers were removed.
 */
int remove_inode_buffers(struct inode *inode)
{
	int ret = 1;

	if (inode_has_buffers(inode)) {
		struct address_space *mapping = &inode->i_data;
		struct list_head *list = &mapping->i_private_list;
		struct address_space *buffer_mapping = mapping->i_private_data;

		spin_lock(&buffer_mapping->i_private_lock);
		while (!list_empty(list)) {
			struct buffer_head *bh = BH_ENTRY(list->next);
			if (buffer_dirty(bh)) {
				ret = 0;
				break;
			}
			__remove_assoc_queue(bh);
		}
		spin_unlock(&buffer_mapping->i_private_lock);
	}
	return ret;
}

/*
 * Create the appropriate buffers when given a folio for data area and
 * the size of each buffer.. Use the bh->b_this_page linked list to
 * follow the buffers created.  Return NULL if unable to create more
 * buffers.
 *
 * The retry flag is used to differentiate async IO (paging, swapping)
 * which may not fail from ordinary buffer allocations.
 */
struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size,
					gfp_t gfp)
{
	struct buffer_head *bh, *head;
	long offset;
	struct mem_cgroup *memcg, *old_memcg;

	/* The folio lock pins the memcg */
	memcg = folio_memcg(folio);
	old_memcg = set_active_memcg(memcg);

	head = NULL;
	offset = folio_size(folio);
	while ((offset -= size) >= 0) {
		bh = alloc_buffer_head(gfp);
		if (!bh)
			goto no_grow;

		bh->b_this_page = head;
		bh->b_blocknr = -1;
		head = bh;

		bh->b_size = size;

		/* Link the buffer to its folio */
		folio_set_bh(bh, folio, offset);
	}
out:
	set_active_memcg(old_memcg);
	return head;
/*
 * In case anything failed, we just free everything we got.
 */
no_grow:
	if (head) {
		do {
			bh = head;
			head = head->b_this_page;
			free_buffer_head(bh);
		} while (head);
	}

	goto out;
}
EXPORT_SYMBOL_GPL(folio_alloc_buffers);

struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size)
{
	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;

	return folio_alloc_buffers(page_folio(page), size, gfp);
}
EXPORT_SYMBOL_GPL(alloc_page_buffers);

static inline void link_dev_buffers(struct folio *folio,
		struct buffer_head *head)
{
	struct buffer_head *bh, *tail;

	bh = head;
	do {
		tail = bh;
		bh = bh->b_this_page;
	} while (bh);
	tail->b_this_page = head;
	folio_attach_private(folio, head);
}

static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
{
	sector_t retval = ~((sector_t)0);
	loff_t sz = bdev_nr_bytes(bdev);

	if (sz) {
		unsigned int sizebits = blksize_bits(size);
		retval = (sz >> sizebits);
	}
	return retval;
}

/*
 * Initialise the state of a blockdev folio's buffers.
 */ 
static sector_t folio_init_buffers(struct folio *folio,
		struct block_device *bdev, unsigned size)
{
	struct buffer_head *head = folio_buffers(folio);
	struct buffer_head *bh = head;
	bool uptodate = folio_test_uptodate(folio);
	sector_t block = div_u64(folio_pos(folio), size);
	sector_t end_block = blkdev_max_block(bdev, size);

	do {
		if (!buffer_mapped(bh)) {
			bh->b_end_io = NULL;
			bh->b_private = NULL;
			bh->b_bdev = bdev;
			bh->b_blocknr = block;
			if (uptodate)
				set_buffer_uptodate(bh);
			if (block < end_block)
				set_buffer_mapped(bh);
		}
		block++;
		bh = bh->b_this_page;
	} while (bh != head);

	/*
	 * Caller needs to validate requested block against end of device.
	 */
	return end_block;
}

/*
 * Create the page-cache folio that contains the requested block.
 *
 * This is used purely for blockdev mappings.
 *
 * Returns false if we have a failure which cannot be cured by retrying
 * without sleeping.  Returns true if we succeeded, or the caller should retry.
 */
static bool grow_dev_folio(struct block_device *bdev, sector_t block,
		pgoff_t index, unsigned size, gfp_t gfp)
{
	struct address_space *mapping = bdev->bd_mapping;
	struct folio *folio;
	struct buffer_head *bh;
	sector_t end_block = 0;

	folio = __filemap_get_folio(mapping, index,
			FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
	if (IS_ERR(folio))
		return false;

	bh = folio_buffers(folio);
	if (bh) {
		if (bh->b_size == size) {
			end_block = folio_init_buffers(folio, bdev, size);
			goto unlock;
		}

		/*
		 * Retrying may succeed; for example the folio may finish
		 * writeback, or buffers may be cleaned.  This should not
		 * happen very often; maybe we have old buffers attached to
		 * this blockdev's page cache and we're trying to change
		 * the block size?
		 */
		if (!try_to_free_buffers(folio)) {
			end_block = ~0ULL;
			goto unlock;
		}
	}

	bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT);
	if (!bh)
		goto unlock;

	/*
	 * Link the folio to the buffers and initialise them.  Take the
	 * lock to be atomic wrt __find_get_block(), which does not
	 * run under the folio lock.
	 */
	spin_lock(&mapping->i_private_lock);
	link_dev_buffers(folio, bh);
	end_block = folio_init_buffers(folio, bdev, size);
	spin_unlock(&mapping->i_private_lock);
unlock:
	folio_unlock(folio);
	folio_put(folio);
	return block < end_block;
}

/*
 * Create buffers for the specified block device block's folio.  If
 * that folio was dirty, the buffers are set dirty also.  Returns false
 * if we've hit a permanent error.
 */
static bool grow_buffers(struct block_device *bdev, sector_t block,
		unsigned size, gfp_t gfp)
{
	loff_t pos;

	/*
	 * Check for a block which lies outside our maximum possible
	 * pagecache index.
	 */
	if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) {
		printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n",
			__func__, (unsigned long long)block,
			bdev);
		return false;
	}

	/* Create a folio with the proper size buffers */
	return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp);
}

static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block,
	     unsigned size, gfp_t gfp)
{
	/* Size must be multiple of hard sectorsize */
	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
			(size < 512 || size > PAGE_SIZE))) {
		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
					size);
		printk(KERN_ERR "logical block size: %d\n",
					bdev_logical_block_size(bdev));

		dump_stack();
		return NULL;
	}

	for (;;) {
		struct buffer_head *bh;

		bh = __find_get_block(bdev, block, size);
		if (bh)
			return bh;

		if (!grow_buffers(bdev, block, size, gfp))
			return NULL;
	}
}

/*
 * The relationship between dirty buffers and dirty pages:
 *
 * Whenever a page has any dirty buffers, the page's dirty bit is set, and
 * the page is tagged dirty in the page cache.
 *
 * At all times, the dirtiness of the buffers represents the dirtiness of
 * subsections of the page.  If the page has buffers, the page dirty bit is
 * merely a hint about the true dirty state.
 *
 * When a page is set dirty in its entirety, all its buffers are marked dirty
 * (if the page has buffers).
 *
 * When a buffer is marked dirty, its page is dirtied, but the page's other
 * buffers are not.
 *
 * Also.  When blockdev buffers are explicitly read with bread(), they
 * individually become uptodate.  But their backing page remains not
 * uptodate - even if all of its buffers are uptodate.  A subsequent
 * block_read_full_folio() against that folio will discover all the uptodate
 * buffers, will set the folio uptodate and will perform no I/O.
 */

/**
 * mark_buffer_dirty - mark a buffer_head as needing writeout
 * @bh: the buffer_head to mark dirty
 *
 * mark_buffer_dirty() will set the dirty bit against the buffer, then set
 * its backing page dirty, then tag the page as dirty in the page cache
 * and then attach the address_space's inode to its superblock's dirty
 * inode list.
 *
 * mark_buffer_dirty() is atomic.  It takes bh->b_folio->mapping->i_private_lock,
 * i_pages lock and mapping->host->i_lock.
 */
void mark_buffer_dirty(struct buffer_head *bh)
{
	WARN_ON_ONCE(!buffer_uptodate(bh));

	trace_block_dirty_buffer(bh);

	/*
	 * Very *carefully* optimize the it-is-already-dirty case.
	 *
	 * Don't let the final "is it dirty" escape to before we
	 * perhaps modified the buffer.
	 */
	if (buffer_dirty(bh)) {
		smp_mb();
		if (buffer_dirty(bh))
			return;
	}

	if (!test_set_buffer_dirty(bh)) {
		struct folio *folio = bh->b_folio;
		struct address_space *mapping = NULL;

		folio_memcg_lock(folio);
		if (!folio_test_set_dirty(folio)) {
			mapping = folio->mapping;
			if (mapping)
				__folio_mark_dirty(folio, mapping, 0);
		}
		folio_memcg_unlock(folio);
		if (mapping)
			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
	}
}
EXPORT_SYMBOL(mark_buffer_dirty);

void mark_buffer_write_io_error(struct buffer_head *bh)
{
	set_buffer_write_io_error(bh);
	/* FIXME: do we need to set this in both places? */
	if (bh->b_folio && bh->b_folio->mapping)
		mapping_set_error(bh->b_folio->mapping, -EIO);
	if (bh->b_assoc_map) {
		mapping_set_error(bh->b_assoc_map, -EIO);
		errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
	}
}
EXPORT_SYMBOL(mark_buffer_write_io_error);

/**
 * __brelse - Release a buffer.
 * @bh: The buffer to release.
 *
 * This variant of brelse() can be called if @bh is guaranteed to not be NULL.
 */
void __brelse(struct buffer_head *bh)
{
	if (atomic_read(&bh->b_count)) {
		put_bh(bh);
		return;
	}
	WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}
EXPORT_SYMBOL(__brelse);

/**
 * __bforget - Discard any dirty data in a buffer.
 * @bh: The buffer to forget.
 *
 * This variant of bforget() can be called if @bh is guaranteed to not
 * be NULL.
 */
void __bforget(struct buffer_head *bh)
{
	clear_buffer_dirty(bh);
	if (bh->b_assoc_map) {
		struct address_space *buffer_mapping = bh->b_folio->mapping;

		spin_lock(&buffer_mapping->i_private_lock);
		list_del_init(&bh->b_assoc_buffers);
		bh->b_assoc_map = NULL;
		spin_unlock(&buffer_mapping->i_private_lock);
	}
	__brelse(bh);
}
EXPORT_SYMBOL(__bforget);

static struct buffer_head *__bread_slow(struct buffer_head *bh)
{
	lock_buffer(bh);
	if (buffer_uptodate(bh)) {
		unlock_buffer(bh);
		return bh;
	} else {
		get_bh(bh);
		bh->b_end_io = end_buffer_read_sync;
		submit_bh(REQ_OP_READ, bh);
		wait_on_buffer(bh);
		if (buffer_uptodate(bh))
			return bh;
	}
	brelse(bh);
	return NULL;
}

/*
 * Per-cpu buffer LRU implementation.  To reduce the cost of __find_get_block().
 * The bhs[] array is sorted - newest buffer is at bhs[0].  Buffers have their
 * refcount elevated by one when they're in an LRU.  A buffer can only appear
 * once in a particular CPU's LRU.  A single buffer can be present in multiple
 * CPU's LRUs at the same time.
 *
 * This is a transparent caching front-end to sb_bread(), sb_getblk() and
 * sb_find_get_block().
 *
 * The LRUs themselves only need locking against invalidate_bh_lrus.  We use
 * a local interrupt disable for that.
 */

#define BH_LRU_SIZE	16

struct bh_lru {
	struct buffer_head *bhs[BH_LRU_SIZE];
};

static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};

#ifdef CONFIG_SMP
#define bh_lru_lock()	local_irq_disable()
#define bh_lru_unlock()	local_irq_enable()
#else
#define bh_lru_lock()	preempt_disable()
#define bh_lru_unlock()	preempt_enable()
#endif

static inline void check_irqs_on(void)
{
#ifdef irqs_disabled
	BUG_ON(irqs_disabled());
#endif
}

/*
 * Install a buffer_head into this cpu's LRU.  If not already in the LRU, it is
 * inserted at the front, and the buffer_head at the back if any is evicted.
 * Or, if already in the LRU it is moved to the front.
 */
static void bh_lru_install(struct buffer_head *bh)
{
	struct buffer_head *evictee = bh;
	struct bh_lru *b;
	int i;

	check_irqs_on();
	bh_lru_lock();

	/*
	 * the refcount of buffer_head in bh_lru prevents dropping the
	 * attached page(i.e., try_to_free_buffers) so it could cause
	 * failing page migration.
	 * Skip putting upcoming bh into bh_lru until migration is done.
	 */
	if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) {
		bh_lru_unlock();
		return;
	}

	b = this_cpu_ptr(&bh_lrus);
	for (i = 0; i < BH_LRU_SIZE; i++) {
		swap(evictee, b->bhs[i]);
		if (evictee == bh) {
			bh_lru_unlock();
			return;
		}
	}

	get_bh(bh);
	bh_lru_unlock();
	brelse(evictee);
}

/*
 * Look up the bh in this cpu's LRU.  If it's there, move it to the head.
 */
static struct buffer_head *
lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *ret = NULL;
	unsigned int i;

	check_irqs_on();
	bh_lru_lock();
	if (cpu_is_isolated(smp_processor_id())) {
		bh_lru_unlock();
		return NULL;
	}
	for (i = 0; i < BH_LRU_SIZE; i++) {
		struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);

		if (bh && bh->b_blocknr == block && bh->b_bdev == bdev &&
		    bh->b_size == size) {
			if (i) {
				while (i) {
					__this_cpu_write(bh_lrus.bhs[i],
						__this_cpu_read(bh_lrus.bhs[i - 1]));
					i--;
				}
				__this_cpu_write(bh_lrus.bhs[0], bh);
			}
			get_bh(bh);
			ret = bh;
			break;
		}
	}
	bh_lru_unlock();
	return ret;
}

/*
 * Perform a pagecache lookup for the matching buffer.  If it's there, refresh
 * it in the LRU and mark it as accessed.  If it is not present then return
 * NULL
 */
struct buffer_head *
__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);

	if (bh == NULL) {
		/* __find_get_block_slow will mark the page accessed */
		bh = __find_get_block_slow(bdev, block);
		if (bh)
			bh_lru_install(bh);
	} else
		touch_buffer(bh);

	return bh;
}
EXPORT_SYMBOL(__find_get_block);

/**
 * bdev_getblk - Get a buffer_head in a block device's buffer cache.
 * @bdev: The block device.
 * @block: The block number.
 * @size: The size of buffer_heads for this @bdev.
 * @gfp: The memory allocation flags to use.
 *
 * The returned buffer head has its reference count incremented, but is
 * not locked.  The caller should call brelse() when it has finished
 * with the buffer.  The buffer may not be uptodate.  If needed, the
 * caller can bring it uptodate either by reading it or overwriting it.
 *
 * Return: The buffer head, or NULL if memory could not be allocated.
 */
struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
		unsigned size, gfp_t gfp)
{
	struct buffer_head *bh = __find_get_block(bdev, block, size);

	might_alloc(gfp);
	if (bh)
		return bh;

	return __getblk_slow(bdev, block, size, gfp);
}
EXPORT_SYMBOL(bdev_getblk);

/*
 * Do async read-ahead on a buffer..
 */
void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *bh = bdev_getblk(bdev, block, size,
			GFP_NOWAIT | __GFP_MOVABLE);

	if (likely(bh)) {
		bh_readahead(bh, REQ_RAHEAD);
		brelse(bh);
	}
}
EXPORT_SYMBOL(__breadahead);

/**
 * __bread_gfp() - Read a block.
 * @bdev: The block device to read from.
 * @block: Block number in units of block size.
 * @size: The block size of this device in bytes.
 * @gfp: Not page allocation flags; see below.
 *
 * You are not expected to call this function.  You should use one of
 * sb_bread(), sb_bread_unmovable() or __bread().
 *
 * Read a specified block, and return the buffer head that refers to it.
 * If @gfp is 0, the memory will be allocated using the block device's
 * default GFP flags.  If @gfp is __GFP_MOVABLE, the memory may be
 * allocated from a movable area.  Do not pass in a complete set of
 * GFP flags.
 *
 * The returned buffer head has its refcount increased.  The caller should
 * call brelse() when it has finished with the buffer.
 *
 * Context: May sleep waiting for I/O.
 * Return: NULL if the block was unreadable.
 */
struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block,
		unsigned size, gfp_t gfp)
{
	struct buffer_head *bh;

	gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);

	/*
	 * Prefer looping in the allocator rather than here, at least that
	 * code knows what it's doing.
	 */
	gfp |= __GFP_NOFAIL;

	bh = bdev_getblk(bdev, block, size, gfp);

	if (likely(bh) && !buffer_uptodate(bh))
		bh = __bread_slow(bh);
	return bh;
}
EXPORT_SYMBOL(__bread_gfp);

static void __invalidate_bh_lrus(struct bh_lru *b)
{
	int i;

	for (i = 0; i < BH_LRU_SIZE; i++) {
		brelse(b->bhs[i]);
		b->bhs[i] = NULL;
	}
}
/*
 * invalidate_bh_lrus() is called rarely - but not only at unmount.
 * This doesn't race because it runs in each cpu either in irq
 * or with preempt disabled.
 */
static void invalidate_bh_lru(void *arg)
{
	struct bh_lru *b = &get_cpu_var(bh_lrus);

	__invalidate_bh_lrus(b);
	put_cpu_var(bh_lrus);
}

bool has_bh_in_lru(int cpu, void *dummy)
{
	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
	int i;
	
	for (i = 0; i < BH_LRU_SIZE; i++) {
		if (b->bhs[i])
			return true;
	}

	return false;
}

void invalidate_bh_lrus(void)
{
	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1);
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);

/*
 * It's called from workqueue context so we need a bh_lru_lock to close
 * the race with preemption/irq.
 */
void invalidate_bh_lrus_cpu(void)
{
	struct bh_lru *b;

	bh_lru_lock();
	b = this_cpu_ptr(&bh_lrus);
	__invalidate_bh_lrus(b);
	bh_lru_unlock();
}

void folio_set_bh(struct buffer_head *bh, struct folio *folio,
		  unsigned long offset)
{
	bh->b_folio = folio;
	BUG_ON(offset >= folio_size(folio));
	if (folio_test_highmem(folio))
		/*
		 * This catches illegal uses and preserves the offset:
		 */
		bh->b_data = (char *)(0 + offset);
	else
		bh->b_data = folio_address(folio) + offset;
}
EXPORT_SYMBOL(folio_set_bh);

/*
 * Called when truncating a buffer on a page completely.
 */

/* Bits that are cleared during an invalidate */
#define BUFFER_FLAGS_DISCARD \
	(1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
	 1 << BH_Delay | 1 << BH_Unwritten)

static void discard_buffer(struct buffer_head * bh)
{
	unsigned long b_state;

	lock_buffer(bh);
	clear_buffer_dirty(bh);
	bh->b_bdev = NULL;
	b_state = READ_ONCE(bh->b_state);
	do {
	} while (!try_cmpxchg(&bh->b_state, &b_state,
			      b_state & ~BUFFER_FLAGS_DISCARD));
	unlock_buffer(bh);
}

/**
 * block_invalidate_folio - Invalidate part or all of a buffer-backed folio.
 * @folio: The folio which is affected.
 * @offset: start of the range to invalidate
 * @length: length of the range to invalidate
 *
 * block_invalidate_folio() is called when all or part of the folio has been
 * invalidated by a truncate operation.
 *
 * block_invalidate_folio() does not have to release all buffers, but it must
 * ensure that no dirty buffer is left outside @offset and that no I/O
 * is underway against any of the blocks which are outside the truncation
 * point.  Because the caller is about to free (and possibly reuse) those
 * blocks on-disk.
 */
void block_invalidate_folio(struct folio *folio, size_t offset, size_t length)
{
	struct buffer_head *head, *bh, *next;
	size_t curr_off = 0;
	size_t stop = length + offset;

	BUG_ON(!folio_test_locked(folio));

	/*
	 * Check for overflow
	 */
	BUG_ON(stop > folio_size(folio) || stop < length);

	head = folio_buffers(folio);
	if (!head)
		return;

	bh = head;
	do {
		size_t next_off = curr_off + bh->b_size;
		next = bh->b_this_page;

		/*
		 * Are we still fully in range ?
		 */
		if (next_off > stop)
			goto out;

		/*
		 * is this block fully invalidated?
		 */
		if (offset <= curr_off)
			discard_buffer(bh);
		curr_off = next_off;
		bh = next;
	} while (bh != head);

	/*
	 * We release buffers only if the entire folio is being invalidated.
	 * The get_block cached value has been unconditionally invalidated,
	 * so real IO is not possible anymore.
	 */
	if (length == folio_size(folio))
		filemap_release_folio(folio, 0);
out:
	return;
}
EXPORT_SYMBOL(block_invalidate_folio);

/*
 * We attach and possibly dirty the buffers atomically wrt
 * block_dirty_folio() via i_private_lock.  try_to_free_buffers
 * is already excluded via the folio lock.
 */
struct buffer_head *create_empty_buffers(struct folio *folio,
		unsigned long blocksize, unsigned long b_state)
{
	struct buffer_head *bh, *head, *tail;
	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL;

	head = folio_alloc_buffers(folio, blocksize, gfp);
	bh = head;
	do {
		bh->b_state |= b_state;
		tail = bh;
		bh = bh->b_this_page;
	} while (bh);
	tail->b_this_page = head;

	spin_lock(&folio->mapping->i_private_lock);
	if (folio_test_uptodate(folio) || folio_test_dirty(folio)) {
		bh = head;
		do {
			if (folio_test_dirty(folio))
				set_buffer_dirty(bh);
			if (folio_test_uptodate(folio))
				set_buffer_uptodate(bh);
			bh = bh->b_this_page;
		} while (bh != head);
	}
	folio_attach_private(folio, head);
	spin_unlock(&folio->mapping->i_private_lock);

	return head;
}
EXPORT_SYMBOL(create_empty_buffers);

/**
 * clean_bdev_aliases: clean a range of buffers in block device
 * @bdev: Block device to clean buffers in
 * @block: Start of a range of blocks to clean
 * @len: Number of blocks to clean
 *
 * We are taking a range of blocks for data and we don't want writeback of any
 * buffer-cache aliases starting from return from this function and until the
 * moment when something will explicitly mark the buffer dirty (hopefully that
 * will not happen until we will free that block ;-) We don't even need to mark
 * it not-uptodate - nobody can expect anything from a newly allocated buffer
 * anyway. We used to use unmap_buffer() for such invalidation, but that was
 * wrong. We definitely don't want to mark the alias unmapped, for example - it
 * would confuse anyone who might pick it with bread() afterwards...
 *
 * Also..  Note that bforget() doesn't lock the buffer.  So there can be
 * writeout I/O going on against recently-freed buffers.  We don't wait on that
 * I/O in bforget() - it's more efficient to wait on the I/O only if we really
 * need to.  That happens here.
 */
void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
{
	struct address_space *bd_mapping = bdev->bd_mapping;
	const int blkbits = bd_mapping->host->i_blkbits;
	struct folio_batch fbatch;
	pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE;
	pgoff_t end;
	int i, count;
	struct buffer_head *bh;
	struct buffer_head *head;

	end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE;
	folio_batch_init(&fbatch);
	while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) {
		count = folio_batch_count(&fbatch);
		for (i = 0; i < count; i++) {
			struct folio *folio = fbatch.folios[i];

			if (!folio_buffers(folio))
				continue;
			/*
			 * We use folio lock instead of bd_mapping->i_private_lock
			 * to pin buffers here since we can afford to sleep and
			 * it scales better than a global spinlock lock.
			 */
			folio_lock(folio);
			/* Recheck when the folio is locked which pins bhs */
			head = folio_buffers(folio);
			if (!head)
				goto unlock_page;
			bh = head;
			do {
				if (!buffer_mapped(bh) || (bh->b_blocknr < block))
					goto next;
				if (bh->b_blocknr >= block + len)
					break;
				clear_buffer_dirty(bh);
				wait_on_buffer(bh);
				clear_buffer_req(bh);
next:
				bh = bh->b_this_page;
			} while (bh != head);
unlock_page:
			folio_unlock(folio);
		}
		folio_batch_release(&fbatch);
		cond_resched();
		/* End of range already reached? */
		if (index > end || !index)
			break;
	}
}
EXPORT_SYMBOL(clean_bdev_aliases);

static struct buffer_head *folio_create_buffers(struct folio *folio,
						struct inode *inode,
						unsigned int b_state)
{
	struct buffer_head *bh;

	BUG_ON(!folio_test_locked(folio));

	bh = folio_buffers(folio);
	if (!bh)
		bh = create_empty_buffers(folio,
				1 << READ_ONCE(inode->i_blkbits), b_state);
	return bh;
}

/*
 * NOTE! All mapped/uptodate combinations are valid:
 *
 *	Mapped	Uptodate	Meaning
 *
 *	No	No		"unknown" - must do get_block()
 *	No	Yes		"hole" - zero-filled
 *	Yes	No		"allocated" - allocated on disk, not read in
 *	Yes	Yes		"valid" - allocated and up-to-date in memory.
 *
 * "Dirty" is valid only with the last case (mapped+uptodate).
 */

/*
 * While block_write_full_folio is writing back the dirty buffers under
 * the page lock, whoever dirtied the buffers may decide to clean them
 * again at any time.  We handle that by only looking at the buffer
 * state inside lock_buffer().
 *
 * If block_write_full_folio() is called for regular writeback
 * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
 * locked buffer.   This only can happen if someone has written the buffer
 * directly, with submit_bh().  At the address_space level PageWriteback
 * prevents this contention from occurring.
 *
 * If block_write_full_folio() is called with wbc->sync_mode ==
 * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this
 * causes the writes to be flagged as synchronous writes.
 */
int __block_write_full_folio(struct inode *inode, struct folio *folio,
			get_block_t *get_block, struct writeback_control *wbc)
{
	int err;
	sector_t block;
	sector_t last_block;
	struct buffer_head *bh, *head;
	size_t blocksize;
	int nr_underway = 0;
	blk_opf_t write_flags = wbc_to_write_flags(wbc);

	head = folio_create_buffers(folio, inode,
				    (1 << BH_Dirty) | (1 << BH_Uptodate));

	/*
	 * Be very careful.  We have no exclusion from block_dirty_folio
	 * here, and the (potentially unmapped) buffers may become dirty at
	 * any time.  If a buffer becomes dirty here after we've inspected it
	 * then we just miss that fact, and the folio stays dirty.
	 *
	 * Buffers outside i_size may be dirtied by block_dirty_folio;
	 * handle that here by just cleaning them.
	 */

	bh = head;
	blocksize = bh->b_size;

	block = div_u64(folio_pos(folio), blocksize);
	last_block = div_u64(i_size_read(inode) - 1, blocksize);

	/*
	 * Get all the dirty buffers mapped to disk addresses and
	 * handle any aliases from the underlying blockdev's mapping.
	 */
	do {
		if (block > last_block) {
			/*
			 * mapped buffers outside i_size will occur, because
			 * this folio can be outside i_size when there is a
			 * truncate in progress.
			 */
			/*
			 * The buffer was zeroed by block_write_full_folio()
			 */
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
		} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
			   buffer_dirty(bh)) {
			WARN_ON(bh->b_size != blocksize);
			err = get_block(inode, block, bh, 1);
			if (err)
				goto recover;
			clear_buffer_delay(bh);
			if (buffer_new(bh)) {
				/* blockdev mappings never come here */
				clear_buffer_new(bh);
				clean_bdev_bh_alias(bh);
			}
		}
		bh = bh->b_this_page;
		block++;
	} while (bh != head);

	do {
		if (!buffer_mapped(bh))
			continue;
		/*
		 * If it's a fully non-blocking write attempt and we cannot
		 * lock the buffer then redirty the folio.  Note that this can
		 * potentially cause a busy-wait loop from writeback threads
		 * and kswapd activity, but those code paths have their own
		 * higher-level throttling.
		 */
		if (wbc->sync_mode != WB_SYNC_NONE) {
			lock_buffer(bh);
		} else if (!trylock_buffer(bh)) {
			folio_redirty_for_writepage(wbc, folio);
			continue;
		}
		if (test_clear_buffer_dirty(bh)) {
			mark_buffer_async_write_endio(bh,
				end_buffer_async_write);
		} else {
			unlock_buffer(bh);
		}
	} while ((bh = bh->b_this_page) != head);

	/*
	 * The folio and its buffers are protected by the writeback flag,
	 * so we can drop the bh refcounts early.
	 */
	BUG_ON(folio_test_writeback(folio));
	folio_start_writeback(folio);

	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
				      inode->i_write_hint, wbc);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	folio_unlock(folio);

	err = 0;
done:
	if (nr_underway == 0) {
		/*
		 * The folio was marked dirty, but the buffers were
		 * clean.  Someone wrote them back by hand with
		 * write_dirty_buffer/submit_bh.  A rare case.
		 */
		folio_end_writeback(folio);

		/*
		 * The folio and buffer_heads can be released at any time from
		 * here on.
		 */
	}
	return err;

recover:
	/*
	 * ENOSPC, or some other error.  We may already have added some
	 * blocks to the file, so we need to write these out to avoid
	 * exposing stale data.
	 * The folio is currently locked and not marked for writeback
	 */
	bh = head;
	/* Recovery: lock and submit the mapped buffers */
	do {
		if (buffer_mapped(bh) && buffer_dirty(bh) &&
		    !buffer_delay(bh)) {
			lock_buffer(bh);
			mark_buffer_async_write_endio(bh,
				end_buffer_async_write);
		} else {
			/*
			 * The buffer may have been set dirty during
			 * attachment to a dirty folio.
			 */
			clear_buffer_dirty(bh);
		}
	} while ((bh = bh->b_this_page) != head);
	BUG_ON(folio_test_writeback(folio));
	mapping_set_error(folio->mapping, err);
	folio_start_writeback(folio);
	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			clear_buffer_dirty(bh);
			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
				      inode->i_write_hint, wbc);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	folio_unlock(folio);
	goto done;
}
EXPORT_SYMBOL(__block_write_full_folio);

/*
 * If a folio has any new buffers, zero them out here, and mark them uptodate
 * and dirty so they'll be written out (in order to prevent uninitialised
 * block data from leaking). And clear the new bit.
 */
void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to)
{
	size_t block_start, block_end;
	struct buffer_head *head, *bh;

	BUG_ON(!folio_test_locked(folio));
	head = folio_buffers(folio);
	if (!head)
		return;

	bh = head;
	block_start = 0;
	do {
		block_end = block_start + bh->b_size;

		if (buffer_new(bh)) {
			if (block_end > from && block_start < to) {
				if (!folio_test_uptodate(folio)) {
					size_t start, xend;

					start = max(from, block_start);
					xend = min(to, block_end);

					folio_zero_segment(folio, start, xend);
					set_buffer_uptodate(bh);
				}

				clear_buffer_new(bh);
				mark_buffer_dirty(bh);
			}
		}

		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);
}
EXPORT_SYMBOL(folio_zero_new_buffers);

static int
iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
		const struct iomap *iomap)
{
	loff_t offset = (loff_t)block << inode->i_blkbits;

	bh->b_bdev = iomap->bdev;

	/*
	 * Block points to offset in file we need to map, iomap contains
	 * the offset at which the map starts. If the map ends before the
	 * current block, then do not map the buffer and let the caller
	 * handle it.
	 */
	if (offset >= iomap->offset + iomap->length)
		return -EIO;

	switch (iomap->type) {
	case IOMAP_HOLE:
		/*
		 * If the buffer is not up to date or beyond the current EOF,
		 * we need to mark it as new to ensure sub-block zeroing is
		 * executed if necessary.
		 */
		if (!buffer_uptodate(bh) ||
		    (offset >= i_size_read(inode)))
			set_buffer_new(bh);
		return 0;
	case IOMAP_DELALLOC:
		if (!buffer_uptodate(bh) ||
		    (offset >= i_size_read(inode)))
			set_buffer_new(bh);
		set_buffer_uptodate(bh);
		set_buffer_mapped(bh);
		set_buffer_delay(bh);
		return 0;
	case IOMAP_UNWRITTEN:
		/*
		 * For unwritten regions, we always need to ensure that regions
		 * in the block we are not writing to are zeroed. Mark the
		 * buffer as new to ensure this.
		 */
		set_buffer_new(bh);
		set_buffer_unwritten(bh);
		fallthrough;
	case IOMAP_MAPPED:
		if ((iomap->flags & IOMAP_F_NEW) ||
		    offset >= i_size_read(inode)) {
			/*
			 * This can happen if truncating the block device races
			 * with the check in the caller as i_size updates on
			 * block devices aren't synchronized by i_rwsem for
			 * block devices.
			 */
			if (S_ISBLK(inode->i_mode))
				return -EIO;
			set_buffer_new(bh);
		}
		bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
				inode->i_blkbits;
		set_buffer_mapped(bh);
		return 0;
	default:
		WARN_ON_ONCE(1);
		return -EIO;
	}
}

int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
		get_block_t *get_block, const struct iomap *iomap)
{
	size_t from = offset_in_folio(folio, pos);
	size_t to = from + len;
	struct inode *inode = folio->mapping->host;
	size_t block_start, block_end;
	sector_t block;
	int err = 0;
	size_t blocksize;
	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;

	BUG_ON(!folio_test_locked(folio));
	BUG_ON(to > folio_size(folio));
	BUG_ON(from > to);

	head = folio_create_buffers(folio, inode, 0);
	blocksize = head->b_size;
	block = div_u64(folio_pos(folio), blocksize);

	for (bh = head, block_start = 0; bh != head || !block_start;
	    block++, block_start=block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (folio_test_uptodate(folio)) {
				if (!buffer_uptodate(bh))
					set_buffer_uptodate(bh);
			}
			continue;
		}
		if (buffer_new(bh))
			clear_buffer_new(bh);
		if (!buffer_mapped(bh)) {
			WARN_ON(bh->b_size != blocksize);
			if (get_block)
				err = get_block(inode, block, bh, 1);
			else
				err = iomap_to_bh(inode, block, bh, iomap);
			if (err)
				break;

			if (buffer_new(bh)) {
				clean_bdev_bh_alias(bh);
				if (folio_test_uptodate(folio)) {
					clear_buffer_new(bh);
					set_buffer_uptodate(bh);
					mark_buffer_dirty(bh);
					continue;
				}
				if (block_end > to || block_start < from)
					folio_zero_segments(folio,
						to, block_end,
						block_start, from);
				continue;
			}
		}
		if (folio_test_uptodate(folio)) {
			if (!buffer_uptodate(bh))
				set_buffer_uptodate(bh);
			continue; 
		}
		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
		    !buffer_unwritten(bh) &&
		     (block_start < from || block_end > to)) {
			bh_read_nowait(bh, 0);
			*wait_bh++=bh;
		}
	}
	/*
	 * If we issued read requests - let them complete.
	 */
	while(wait_bh > wait) {
		wait_on_buffer(*--wait_bh);
		if (!buffer_uptodate(*wait_bh))
			err = -EIO;
	}
	if (unlikely(err))
		folio_zero_new_buffers(folio, from, to);
	return err;
}

int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
		get_block_t *get_block)
{
	return __block_write_begin_int(folio, pos, len, get_block, NULL);
}
EXPORT_SYMBOL(__block_write_begin);

static void __block_commit_write(struct folio *folio, size_t from, size_t to)
{
	size_t block_start, block_end;
	bool partial = false;
	unsigned blocksize;
	struct buffer_head *bh, *head;

	bh = head = folio_buffers(folio);
	if (!bh)
		return;
	blocksize = bh->b_size;

	block_start = 0;
	do {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (!buffer_uptodate(bh))
				partial = true;
		} else {
			set_buffer_uptodate(bh);
			mark_buffer_dirty(bh);
		}
		if (buffer_new(bh))
			clear_buffer_new(bh);

		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);

	/*
	 * If this is a partial write which happened to make all buffers
	 * uptodate then we can optimize away a bogus read_folio() for
	 * the next read(). Here we 'discover' whether the folio went
	 * uptodate as a result of this (potentially partial) write.
	 */
	if (!partial)
		folio_mark_uptodate(folio);
}

/*
 * block_write_begin takes care of the basic task of block allocation and
 * bringing partial write blocks uptodate first.
 *
 * The filesystem needs to handle block truncation upon failure.
 */
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
		struct folio **foliop, get_block_t *get_block)
{
	pgoff_t index = pos >> PAGE_SHIFT;
	struct folio *folio;
	int status;

	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
			mapping_gfp_mask(mapping));
	if (IS_ERR(folio))
		return PTR_ERR(folio);

	status = __block_write_begin_int(folio, pos, len, get_block, NULL);
	if (unlikely(status)) {
		folio_unlock(folio);
		folio_put(folio);
		folio = NULL;
	}

	*foliop = folio;
	return status;
}
EXPORT_SYMBOL(block_write_begin);

int block_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct folio *folio, void *fsdata)
{
	size_t start = pos - folio_pos(folio);

	if (unlikely(copied < len)) {
		/*
		 * The buffers that were written will now be uptodate, so
		 * we don't have to worry about a read_folio reading them
		 * and overwriting a partial write. However if we have
		 * encountered a short write and only partially written
		 * into a buffer, it will not be marked uptodate, so a
		 * read_folio might come in and destroy our partial write.
		 *
		 * Do the simplest thing, and just treat any short write to a
		 * non uptodate folio as a zero-length write, and force the
		 * caller to redo the whole thing.
		 */
		if (!folio_test_uptodate(folio))
			copied = 0;

		folio_zero_new_buffers(folio, start+copied, start+len);
	}
	flush_dcache_folio(folio);

	/* This could be a short (even 0-length) commit */
	__block_commit_write(folio, start, start + copied);

	return copied;
}
EXPORT_SYMBOL(block_write_end);

int generic_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct folio *folio, void *fsdata)
{
	struct inode *inode = mapping->host;
	loff_t old_size = inode->i_size;
	bool i_size_changed = false;

	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);

	/*
	 * No need to use i_size_read() here, the i_size cannot change under us
	 * because we hold i_rwsem.
	 *
	 * But it's important to update i_size while still holding folio lock:
	 * page writeout could otherwise come in and zero beyond i_size.
	 */
	if (pos + copied > inode->i_size) {
		i_size_write(inode, pos + copied);
		i_size_changed = true;
	}

	folio_unlock(folio);
	folio_put(folio);

	if (old_size < pos)
		pagecache_isize_extended(inode, old_size, pos);
	/*
	 * Don't mark the inode dirty under page lock. First, it unnecessarily
	 * makes the holding time of page lock longer. Second, it forces lock
	 * ordering of page lock and transaction start for journaling
	 * filesystems.
	 */
	if (i_size_changed)
		mark_inode_dirty(inode);
	return copied;
}
EXPORT_SYMBOL(generic_write_end);

/*
 * block_is_partially_uptodate checks whether buffers within a folio are
 * uptodate or not.
 *
 * Returns true if all buffers which correspond to the specified part
 * of the folio are uptodate.
 */
bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
{
	unsigned block_start, block_end, blocksize;
	unsigned to;
	struct buffer_head *bh, *head;
	bool ret = true;

	head = folio_buffers(folio);
	if (!head)
		return false;
	blocksize = head->b_size;
	to = min_t(unsigned, folio_size(folio) - from, count);
	to = from + to;
	if (from < blocksize && to > folio_size(folio) - blocksize)
		return false;

	bh = head;
	block_start = 0;
	do {
		block_end = block_start + blocksize;
		if (block_end > from && block_start < to) {
			if (!buffer_uptodate(bh)) {
				ret = false;
				break;
			}
			if (block_end >= to)
				break;
		}
		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);

	return ret;
}
EXPORT_SYMBOL(block_is_partially_uptodate);

/*
 * Generic "read_folio" function for block devices that have the normal
 * get_block functionality. This is most of the block device filesystems.
 * Reads the folio asynchronously --- the unlock_buffer() and
 * set/clear_buffer_uptodate() functions propagate buffer state into the
 * folio once IO has completed.
 */
int block_read_full_folio(struct folio *folio, get_block_t *get_block)
{
	struct inode *inode = folio->mapping->host;
	sector_t iblock, lblock;
	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
	size_t blocksize;
	int nr, i;
	int fully_mapped = 1;
	bool page_error = false;
	loff_t limit = i_size_read(inode);

	/* This is needed for ext4. */
	if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
		limit = inode->i_sb->s_maxbytes;

	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);

	head = folio_create_buffers(folio, inode, 0);
	blocksize = head->b_size;

	iblock = div_u64(folio_pos(folio), blocksize);
	lblock = div_u64(limit + blocksize - 1, blocksize);
	bh = head;
	nr = 0;
	i = 0;

	do {
		if (buffer_uptodate(bh))
			continue;

		if (!buffer_mapped(bh)) {
			int err = 0;

			fully_mapped = 0;
			if (iblock < lblock) {
				WARN_ON(bh->b_size != blocksize);
				err = get_block(inode, iblock, bh, 0);
				if (err)
					page_error = true;
			}
			if (!buffer_mapped(bh)) {
				folio_zero_range(folio, i * blocksize,
						blocksize);
				if (!err)
					set_buffer_uptodate(bh);
				continue;
			}
			/*
			 * get_block() might have updated the buffer
			 * synchronously
			 */
			if (buffer_uptodate(bh))
				continue;
		}
		arr[nr++] = bh;
	} while (i++, iblock++, (bh = bh->b_this_page) != head);

	if (fully_mapped)
		folio_set_mappedtodisk(folio);

	if (!nr) {
		/*
		 * All buffers are uptodate or get_block() returned an
		 * error when trying to map them - we can finish the read.
		 */
		folio_end_read(folio, !page_error);
		return 0;
	}

	/* Stage two: lock the buffers */
	for (i = 0; i < nr; i++) {
		bh = arr[i];
		lock_buffer(bh);
		mark_buffer_async_read(bh);
	}

	/*
	 * Stage 3: start the IO.  Check for uptodateness
	 * inside the buffer lock in case another process reading
	 * the underlying blockdev brought it uptodate (the sct fix).
	 */
	for (i = 0; i < nr; i++) {
		bh = arr[i];
		if (buffer_uptodate(bh))
			end_buffer_async_read(bh, 1);
		else
			submit_bh(REQ_OP_READ, bh);
	}
	return 0;
}
EXPORT_SYMBOL(block_read_full_folio);

/* utility function for filesystems that need to do work on expanding
 * truncates.  Uses filesystem pagecache writes to allow the filesystem to
 * deal with the hole.  
 */
int generic_cont_expand_simple(struct inode *inode, loff_t size)
{
	struct address_space *mapping = inode->i_mapping;
	const struct address_space_operations *aops = mapping->a_ops;
	struct folio *folio;
	void *fsdata = NULL;
	int err;

	err = inode_newsize_ok(inode, size);
	if (err)
		goto out;

	err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata);
	if (err)
		goto out;

	err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata);
	BUG_ON(err > 0);

out:
	return err;
}
EXPORT_SYMBOL(generic_cont_expand_simple);

static int cont_expand_zero(struct file *file, struct address_space *mapping,
			    loff_t pos, loff_t *bytes)
{
	struct inode *inode = mapping->host;
	const struct address_space_operations *aops = mapping->a_ops;
	unsigned int blocksize = i_blocksize(inode);
	struct folio *folio;
	void *fsdata = NULL;
	pgoff_t index, curidx;
	loff_t curpos;
	unsigned zerofrom, offset, len;
	int err = 0;

	index = pos >> PAGE_SHIFT;
	offset = pos & ~PAGE_MASK;

	while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) {
		zerofrom = curpos & ~PAGE_MASK;
		if (zerofrom & (blocksize-1)) {
			*bytes |= (blocksize-1);
			(*bytes)++;
		}
		len = PAGE_SIZE - zerofrom;

		err = aops->write_begin(file, mapping, curpos, len,
					    &folio, &fsdata);
		if (err)
			goto out;
		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
		err = aops->write_end(file, mapping, curpos, len, len,
						folio, fsdata);
		if (err < 0)
			goto out;
		BUG_ON(err != len);
		err = 0;

		balance_dirty_pages_ratelimited(mapping);

		if (fatal_signal_pending(current)) {
			err = -EINTR;
			goto out;
		}
	}

	/* page covers the boundary, find the boundary offset */
	if (index == curidx) {
		zerofrom = curpos & ~PAGE_MASK;
		/* if we will expand the thing last block will be filled */
		if (offset <= zerofrom) {
			goto out;
		}
		if (zerofrom & (blocksize-1)) {
			*bytes |= (blocksize-1);
			(*bytes)++;
		}
		len = offset - zerofrom;

		err = aops->write_begin(file, mapping, curpos, len,
					    &folio, &fsdata);
		if (err)
			goto out;
		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
		err = aops->write_end(file, mapping, curpos, len, len,
						folio, fsdata);
		if (err < 0)
			goto out;
		BUG_ON(err != len);
		err = 0;
	}
out:
	return err;
}

/*
 * For moronic filesystems that do not allow holes in file.
 * We may have to extend the file.
 */
int cont_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len,
			struct folio **foliop, void **fsdata,
			get_block_t *get_block, loff_t *bytes)
{
	struct inode *inode = mapping->host;
	unsigned int blocksize = i_blocksize(inode);
	unsigned int zerofrom;
	int err;

	err = cont_expand_zero(file, mapping, pos, bytes);
	if (err)
		return err;

	zerofrom = *bytes & ~PAGE_MASK;
	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
		*bytes |= (blocksize-1);
		(*bytes)++;
	}

	return block_write_begin(mapping, pos, len, foliop, get_block);
}
EXPORT_SYMBOL(cont_write_begin);

void block_commit_write(struct page *page, unsigned from, unsigned to)
{
	struct folio *folio = page_folio(page);
	__block_commit_write(folio, from, to);
}
EXPORT_SYMBOL(block_commit_write);

/*
 * block_page_mkwrite() is not allowed to change the file size as it gets
 * called from a page fault handler when a page is first dirtied. Hence we must
 * be careful to check for EOF conditions here. We set the page up correctly
 * for a written page which means we get ENOSPC checking when writing into
 * holes and correct delalloc and unwritten extent mapping on filesystems that
 * support these features.
 *
 * We are not allowed to take the i_mutex here so we have to play games to
 * protect against truncate races as the page could now be beyond EOF.  Because
 * truncate writes the inode size before removing pages, once we have the
 * page lock we can determine safely if the page is beyond EOF. If it is not
 * beyond EOF, then the page is guaranteed safe against truncation until we
 * unlock the page.
 *
 * Direct callers of this function should protect against filesystem freezing
 * using sb_start_pagefault() - sb_end_pagefault() functions.
 */
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
			 get_block_t get_block)
{
	struct folio *folio = page_folio(vmf->page);
	struct inode *inode = file_inode(vma->vm_file);
	unsigned long end;
	loff_t size;
	int ret;

	folio_lock(folio);
	size = i_size_read(inode);
	if ((folio->mapping != inode->i_mapping) ||
	    (folio_pos(folio) >= size)) {
		/* We overload EFAULT to mean page got truncated */
		ret = -EFAULT;
		goto out_unlock;
	}

	end = folio_size(folio);
	/* folio is wholly or partially inside EOF */
	if (folio_pos(folio) + end > size)
		end = size - folio_pos(folio);

	ret = __block_write_begin_int(folio, 0, end, get_block, NULL);
	if (unlikely(ret))
		goto out_unlock;

	__block_commit_write(folio, 0, end);

	folio_mark_dirty(folio);
	folio_wait_stable(folio);
	return 0;
out_unlock:
	folio_unlock(folio);
	return ret;
}
EXPORT_SYMBOL(block_page_mkwrite);

int block_truncate_page(struct address_space *mapping,
			loff_t from, get_block_t *get_block)
{
	pgoff_t index = from >> PAGE_SHIFT;
	unsigned blocksize;
	sector_t iblock;
	size_t offset, length, pos;
	struct inode *inode = mapping->host;
	struct folio *folio;
	struct buffer_head *bh;
	int err = 0;

	blocksize = i_blocksize(inode);
	length = from & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!length)
		return 0;

	length = blocksize - length;
	iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits;

	folio = filemap_grab_folio(mapping, index);
	if (IS_ERR(folio))
		return PTR_ERR(folio);

	bh = folio_buffers(folio);
	if (!bh)
		bh = create_empty_buffers(folio, blocksize, 0);

	/* Find the buffer that contains "offset" */
	offset = offset_in_folio(folio, from);
	pos = blocksize;
	while (offset >= pos) {
		bh = bh->b_this_page;
		iblock++;
		pos += blocksize;
	}

	if (!buffer_mapped(bh)) {
		WARN_ON(bh->b_size != blocksize);
		err = get_block(inode, iblock, bh, 0);
		if (err)
			goto unlock;
		/* unmapped? It's a hole - nothing to do */
		if (!buffer_mapped(bh))
			goto unlock;
	}

	/* Ok, it's mapped. Make sure it's up-to-date */
	if (folio_test_uptodate(folio))
		set_buffer_uptodate(bh);

	if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
		err = bh_read(bh, 0);
		/* Uhhuh. Read error. Complain and punt. */
		if (err < 0)
			goto unlock;
	}

	folio_zero_range(folio, offset, length);
	mark_buffer_dirty(bh);

unlock:
	folio_unlock(folio);
	folio_put(folio);

	return err;
}
EXPORT_SYMBOL(block_truncate_page);

/*
 * The generic ->writepage function for buffer-backed address_spaces
 */
int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
		void *get_block)
{
	struct inode * const inode = folio->mapping->host;
	loff_t i_size = i_size_read(inode);

	/* Is the folio fully inside i_size? */
	if (folio_pos(folio) + folio_size(folio) <= i_size)
		return __block_write_full_folio(inode, folio, get_block, wbc);

	/* Is the folio fully outside i_size? (truncate in progress) */
	if (folio_pos(folio) >= i_size) {
		folio_unlock(folio);
		return 0; /* don't care */
	}

	/*
	 * The folio straddles i_size.  It must be zeroed out on each and every
	 * writepage invocation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	folio_zero_segment(folio, offset_in_folio(folio, i_size),
			folio_size(folio));
	return __block_write_full_folio(inode, folio, get_block, wbc);
}

sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
			    get_block_t *get_block)
{
	struct inode *inode = mapping->host;
	struct buffer_head tmp = {
		.b_size = i_blocksize(inode),
	};

	get_block(inode, block, &tmp, 0);
	return tmp.b_blocknr;
}
EXPORT_SYMBOL(generic_block_bmap);

static void end_bio_bh_io_sync(struct bio *bio)
{
	struct buffer_head *bh = bio->bi_private;

	if (unlikely(bio_flagged(bio, BIO_QUIET)))
		set_bit(BH_Quiet, &bh->b_state);

	bh->b_end_io(bh, !bio->bi_status);
	bio_put(bio);
}

static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
			  enum rw_hint write_hint,
			  struct writeback_control *wbc)
{
	const enum req_op op = opf & REQ_OP_MASK;
	struct bio *bio;

	BUG_ON(!buffer_locked(bh));
	BUG_ON(!buffer_mapped(bh));
	BUG_ON(!bh->b_end_io);
	BUG_ON(buffer_delay(bh));
	BUG_ON(buffer_unwritten(bh));

	/*
	 * Only clear out a write error when rewriting
	 */
	if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
		clear_buffer_write_io_error(bh);

	if (buffer_meta(bh))
		opf |= REQ_META;
	if (buffer_prio(bh))
		opf |= REQ_PRIO;

	bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO);

	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);

	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
	bio->bi_write_hint = write_hint;

	__bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));

	bio->bi_end_io = end_bio_bh_io_sync;
	bio->bi_private = bh;

	/* Take care of bh's that straddle the end of the device */
	guard_bio_eod(bio);

	if (wbc) {
		wbc_init_bio(wbc, bio);
		wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
	}

	submit_bio(bio);
}

void submit_bh(blk_opf_t opf, struct buffer_head *bh)
{
	submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL);
}
EXPORT_SYMBOL(submit_bh);

void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
	lock_buffer(bh);
	if (!test_clear_buffer_dirty(bh)) {
		unlock_buffer(bh);
		return;
	}
	bh->b_end_io = end_buffer_write_sync;
	get_bh(bh);
	submit_bh(REQ_OP_WRITE | op_flags, bh);
}
EXPORT_SYMBOL(write_dirty_buffer);

/*
 * For a data-integrity writeout, we need to wait upon any in-progress I/O
 * and then start new I/O and then wait upon it.  The caller must have a ref on
 * the buffer_head.
 */
int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
	WARN_ON(atomic_read(&bh->b_count) < 1);
	lock_buffer(bh);
	if (test_clear_buffer_dirty(bh)) {
		/*
		 * The bh should be mapped, but it might not be if the
		 * device was hot-removed. Not much we can do but fail the I/O.
		 */
		if (!buffer_mapped(bh)) {
			unlock_buffer(bh);
			return -EIO;
		}

		get_bh(bh);
		bh->b_end_io = end_buffer_write_sync;
		submit_bh(REQ_OP_WRITE | op_flags, bh);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh))
			return -EIO;
	} else {
		unlock_buffer(bh);
	}
	return 0;
}
EXPORT_SYMBOL(__sync_dirty_buffer);

int sync_dirty_buffer(struct buffer_head *bh)
{
	return __sync_dirty_buffer(bh, REQ_SYNC);
}
EXPORT_SYMBOL(sync_dirty_buffer);

static inline int buffer_busy(struct buffer_head *bh)
{
	return atomic_read(&bh->b_count) |
		(bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock)));
}

static bool
drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free)
{
	struct buffer_head *head = folio_buffers(folio);
	struct buffer_head *bh;

	bh = head;
	do {
		if (buffer_busy(bh))
			goto failed;
		bh = bh->b_this_page;
	} while (bh != head);

	do {
		struct buffer_head *next = bh->b_this_page;

		if (bh->b_assoc_map)
			__remove_assoc_queue(bh);
		bh = next;
	} while (bh != head);
	*buffers_to_free = head;
	folio_detach_private(folio);
	return true;
failed:
	return false;
}

/**
 * try_to_free_buffers - Release buffers attached to this folio.
 * @folio: The folio.
 *
 * If any buffers are in use (dirty, under writeback, elevated refcount),
 * no buffers will be freed.
 *
 * If the folio is dirty but all the buffers are clean then we need to
 * be sure to mark the folio clean as well.  This is because the folio
 * may be against a block device, and a later reattachment of buffers
 * to a dirty folio will set *all* buffers dirty.  Which would corrupt
 * filesystem data on the same device.
 *
 * The same applies to regular filesystem folios: if all the buffers are
 * clean then we set the folio clean and proceed.  To do that, we require
 * total exclusion from block_dirty_folio().  That is obtained with
 * i_private_lock.
 *
 * Exclusion against try_to_free_buffers may be obtained by either
 * locking the folio or by holding its mapping's i_private_lock.
 *
 * Context: Process context.  @folio must be locked.  Will not sleep.
 * Return: true if all buffers attached to this folio were freed.
 */
bool try_to_free_buffers(struct folio *folio)
{
	struct address_space * const mapping = folio->mapping;
	struct buffer_head *buffers_to_free = NULL;
	bool ret = 0;

	BUG_ON(!folio_test_locked(folio));
	if (folio_test_writeback(folio))
		return false;

	if (mapping == NULL) {		/* can this still happen? */
		ret = drop_buffers(folio, &buffers_to_free);
		goto out;
	}

	spin_lock(&mapping->i_private_lock);
	ret = drop_buffers(folio, &buffers_to_free);

	/*
	 * If the filesystem writes its buffers by hand (eg ext3)
	 * then we can have clean buffers against a dirty folio.  We
	 * clean the folio here; otherwise the VM will never notice
	 * that the filesystem did any IO at all.
	 *
	 * Also, during truncate, discard_buffer will have marked all
	 * the folio's buffers clean.  We discover that here and clean
	 * the folio also.
	 *
	 * i_private_lock must be held over this entire operation in order
	 * to synchronise against block_dirty_folio and prevent the
	 * dirty bit from being lost.
	 */
	if (ret)
		folio_cancel_dirty(folio);
	spin_unlock(&mapping->i_private_lock);
out:
	if (buffers_to_free) {
		struct buffer_head *bh = buffers_to_free;

		do {
			struct buffer_head *next = bh->b_this_page;
			free_buffer_head(bh);
			bh = next;
		} while (bh != buffers_to_free);
	}
	return ret;
}
EXPORT_SYMBOL(try_to_free_buffers);

/*
 * Buffer-head allocation
 */
static struct kmem_cache *bh_cachep __ro_after_init;

/*
 * Once the number of bh's in the machine exceeds this level, we start
 * stripping them in writeback.
 */
static unsigned long max_buffer_heads __ro_after_init;

int buffer_heads_over_limit;

struct bh_accounting {
	int nr;			/* Number of live bh's */
	int ratelimit;		/* Limit cacheline bouncing */
};

static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};

static void recalc_bh_state(void)
{
	int i;
	int tot = 0;

	if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096)
		return;
	__this_cpu_write(bh_accounting.ratelimit, 0);
	for_each_online_cpu(i)
		tot += per_cpu(bh_accounting, i).nr;
	buffer_heads_over_limit = (tot > max_buffer_heads);
}

struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
{
	struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
	if (ret) {
		INIT_LIST_HEAD(&ret->b_assoc_buffers);
		spin_lock_init(&ret->b_uptodate_lock);
		preempt_disable();
		__this_cpu_inc(bh_accounting.nr);
		recalc_bh_state();
		preempt_enable();
	}
	return ret;
}
EXPORT_SYMBOL(alloc_buffer_head);

void free_buffer_head(struct buffer_head *bh)
{
	BUG_ON(!list_empty(&bh->b_assoc_buffers));
	kmem_cache_free(bh_cachep, bh);
	preempt_disable();
	__this_cpu_dec(bh_accounting.nr);
	recalc_bh_state();
	preempt_enable();
}
EXPORT_SYMBOL(free_buffer_head);

static int buffer_exit_cpu_dead(unsigned int cpu)
{
	int i;
	struct bh_lru *b = &per_cpu(bh_lrus, cpu);

	for (i = 0; i < BH_LRU_SIZE; i++) {
		brelse(b->bhs[i]);
		b->bhs[i] = NULL;
	}
	this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr);
	per_cpu(bh_accounting, cpu).nr = 0;
	return 0;
}

/**
 * bh_uptodate_or_lock - Test whether the buffer is uptodate
 * @bh: struct buffer_head
 *
 * Return true if the buffer is up-to-date and false,
 * with the buffer locked, if not.
 */
int bh_uptodate_or_lock(struct buffer_head *bh)
{
	if (!buffer_uptodate(bh)) {
		lock_buffer(bh);
		if (!buffer_uptodate(bh))
			return 0;
		unlock_buffer(bh);
	}
	return 1;
}
EXPORT_SYMBOL(bh_uptodate_or_lock);

/**
 * __bh_read - Submit read for a locked buffer
 * @bh: struct buffer_head
 * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ
 * @wait: wait until reading finish
 *
 * Returns zero on success or don't wait, and -EIO on error.
 */
int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
{
	int ret = 0;

	BUG_ON(!buffer_locked(bh));

	get_bh(bh);
	bh->b_end_io = end_buffer_read_sync;
	submit_bh(REQ_OP_READ | op_flags, bh);
	if (wait) {
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh))
			ret = -EIO;
	}
	return ret;
}
EXPORT_SYMBOL(__bh_read);

/**
 * __bh_read_batch - Submit read for a batch of unlocked buffers
 * @nr: entry number of the buffer batch
 * @bhs: a batch of struct buffer_head
 * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ
 * @force_lock: force to get a lock on the buffer if set, otherwise drops any
 *              buffer that cannot lock.
 *
 * Returns zero on success or don't wait, and -EIO on error.
 */
void __bh_read_batch(int nr, struct buffer_head *bhs[],
		     blk_opf_t op_flags, bool force_lock)
{
	int i;

	for (i = 0; i < nr; i++) {
		struct buffer_head *bh = bhs[i];

		if (buffer_uptodate(bh))
			continue;

		if (force_lock)
			lock_buffer(bh);
		else
			if (!trylock_buffer(bh))
				continue;

		if (buffer_uptodate(bh)) {
			unlock_buffer(bh);
			continue;
		}

		bh->b_end_io = end_buffer_read_sync;
		get_bh(bh);
		submit_bh(REQ_OP_READ | op_flags, bh);
	}
}
EXPORT_SYMBOL(__bh_read_batch);

void __init buffer_init(void)
{
	unsigned long nrpages;
	int ret;

	bh_cachep = KMEM_CACHE(buffer_head,
				SLAB_RECLAIM_ACCOUNT|SLAB_PANIC);
	/*
	 * Limit the bh occupancy to 10% of ZONE_NORMAL
	 */
	nrpages = (nr_free_buffer_pages() * 10) / 100;
	max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head));
	ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead",
					NULL, buffer_exit_cpu_dead);
	WARN_ON(ret < 0);
}