1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
|
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/inode.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 64-bit file support on 64-bit platforms by Jakub Jelinek
* (jj@sunsite.ms.mff.cuni.cz)
*
* Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
*/
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/iomap.h>
#include <linux/iversion.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"
#include <trace/events/ext4.h>
static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__u16 dummy_csum = 0;
int offset = offsetof(struct ext4_inode, i_checksum_lo);
unsigned int csum_size = sizeof(dummy_csum);
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
offset += csum_size;
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_GOOD_OLD_INODE_SIZE - offset);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
offset = offsetof(struct ext4_inode, i_checksum_hi);
csum = ext4_chksum(sbi, csum, (__u8 *)raw +
EXT4_GOOD_OLD_INODE_SIZE,
offset - EXT4_GOOD_OLD_INODE_SIZE);
if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
csum_size);
offset += csum_size;
}
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_INODE_SIZE(inode->i_sb) - offset);
}
return csum;
}
static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
__u32 provided, calculated;
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
!ext4_has_metadata_csum(inode->i_sb))
return 1;
provided = le16_to_cpu(raw->i_checksum_lo);
calculated = ext4_inode_csum(inode, raw, ei);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16;
else
calculated &= 0xFFFF;
return provided == calculated;
}
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
__u32 csum;
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
!ext4_has_metadata_csum(inode->i_sb))
return;
csum = ext4_inode_csum(inode, raw, ei);
raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
raw->i_checksum_hi = cpu_to_le16(csum >> 16);
}
static inline int ext4_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
{
trace_ext4_begin_ordered_truncate(inode, new_size);
/*
* If jinode is zero, then we never opened the file for
* writing, so there's no need to call
* jbd2_journal_begin_ordered_truncate() since there's no
* outstanding writes we need to flush.
*/
if (!EXT4_I(inode)->jinode)
return 0;
return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode,
new_size);
}
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents);
/*
* Test whether an inode is a fast symlink.
* A fast symlink has its symlink data stored in ext4_inode_info->i_data.
*/
int ext4_inode_is_fast_symlink(struct inode *inode)
{
if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
if (ext4_has_inline_data(inode))
return 0;
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
return S_ISLNK(inode->i_mode) && inode->i_size &&
(inode->i_size < EXT4_N_BLOCKS * 4);
}
/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
/*
* Credits for final inode cleanup and freeing:
* sb + inode (ext4_orphan_del()), block bitmap, group descriptor
* (xattr block freeing), bitmap, group descriptor (inode freeing)
*/
int extra_credits = 6;
struct ext4_xattr_inode_array *ea_inode_array = NULL;
bool freeze_protected = false;
trace_ext4_evict_inode(inode);
if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
ext4_evict_ea_inode(inode);
if (inode->i_nlink) {
truncate_inode_pages_final(&inode->i_data);
goto no_delete;
}
if (is_bad_inode(inode))
goto no_delete;
dquot_initialize(inode);
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages_final(&inode->i_data);
/*
* For inodes with journalled data, transaction commit could have
* dirtied the inode. And for inodes with dioread_nolock, unwritten
* extents converting worker could merge extents and also have dirtied
* the inode. Flush worker is ignoring it because of I_FREEING flag but
* we still need to remove the inode from the writeback lists.
*/
if (!list_empty_careful(&inode->i_io_list))
inode_io_list_del(inode);
/*
* Protect us against freezing - iput() caller didn't have to have any
* protection against it. When we are in a running transaction though,
* we are already protected against freezing and we cannot grab further
* protection due to lock ordering constraints.
*/
if (!ext4_journal_current_handle()) {
sb_start_intwrite(inode->i_sb);
freeze_protected = true;
}
if (!IS_NOQUOTA(inode))
extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
/*
* Block bitmap, group descriptor, and inode are accounted in both
* ext4_blocks_for_truncate() and extra_credits. So subtract 3.
*/
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
ext4_blocks_for_truncate(inode) + extra_credits - 3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext4_orphan_del(NULL, inode);
if (freeze_protected)
sb_end_intwrite(inode->i_sb);
goto no_delete;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
/*
* Set inode->i_size to 0 before calling ext4_truncate(). We need
* special handling of symlinks here because i_size is used to
* determine whether ext4_inode_info->i_data contains symlink data or
* block mappings. Setting i_size to 0 will remove its fast symlink
* status. Erase i_data so that it becomes a valid empty block map.
*/
if (ext4_inode_is_fast_symlink(inode))
memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data));
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_warning(inode->i_sb,
"couldn't mark inode dirty (err %d)", err);
goto stop_handle;
}
if (inode->i_blocks) {
err = ext4_truncate(inode);
if (err) {
ext4_error_err(inode->i_sb, -err,
"couldn't truncate inode %lu (err %d)",
inode->i_ino, err);
goto stop_handle;
}
}
/* Remove xattr references. */
err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array,
extra_credits);
if (err) {
ext4_warning(inode->i_sb, "xattr delete (err %d)", err);
stop_handle:
ext4_journal_stop(handle);
ext4_orphan_del(NULL, inode);
if (freeze_protected)
sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
goto no_delete;
}
/*
* Kill off the orphan record which ext4_truncate created.
* AKPM: I think this can be inside the above `if'.
* Note that ext4_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - this is because we don't
* know if ext4_truncate() actually created an orphan record.
* (Well, we could do this if we need to, but heck - it works)
*/
ext4_orphan_del(handle, inode);
EXT4_I(inode)->i_dtime = (__u32)ktime_get_real_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext4_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
if (freeze_protected)
sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
return;
no_delete:
/*
* Check out some where else accidentally dirty the evicting inode,
* which may probably cause inode use-after-free issues later.
*/
WARN_ON_ONCE(!list_empty_careful(&inode->i_io_list));
if (!list_empty(&EXT4_I(inode)->i_fc_list))
ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode)
{
return &EXT4_I(inode)->i_reserved_quota;
}
#endif
/*
* Called with i_data_sem down, which is important since we can call
* ext4_discard_preallocations() from here.
*/
void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_warning(inode->i_sb, "%s: ino %lu, used %d "
"with only %d reserved data blocks",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
WARN_ON(1);
used = ei->i_reserved_data_blocks;
}
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);
spin_unlock(&ei->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
if (quota_claim)
dquot_claim_block(inode, EXT4_C2B(sbi, used));
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
* If we have done all the pending block allocations and if
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
if ((ei->i_reserved_data_blocks == 0) &&
!inode_is_open_for_write(inode))
ext4_discard_preallocations(inode, 0);
}
static int __check_block_validity(struct inode *inode, const char *func,
unsigned int line,
struct ext4_map_blocks *map)
{
if (ext4_has_feature_journal(inode->i_sb) &&
(inode->i_ino ==
le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
return 0;
if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
"lblock %lu mapped to illegal pblock %llu "
"(length %d)", (unsigned long) map->m_lblk,
map->m_pblk, map->m_len);
return -EFSCORRUPTED;
}
return 0;
}
int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
ext4_lblk_t len)
{
int ret;
if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
return fscrypt_zeroout_range(inode, lblk, pblk, len);
ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
if (ret > 0)
ret = 0;
return ret;
}
#define check_block_validity(inode, map) \
__check_block_validity((inode), __func__, __LINE__, (map))
#ifdef ES_AGGRESSIVE_TEST
static void ext4_map_blocks_es_recheck(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *es_map,
struct ext4_map_blocks *map,
int flags)
{
int retval;
map->m_flags = 0;
/*
* There is a race window that the result is not the same.
* e.g. xfstests #223 when dioread_nolock enables. The reason
* is that we lookup a block mapping in extent status tree with
* out taking i_data_sem. So at the time the unwritten extent
* could be converted.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
/*
* We don't check m_len because extent will be collpased in status
* tree. So the m_len might not equal.
*/
if (es_map->m_lblk != map->m_lblk ||
es_map->m_flags != map->m_flags ||
es_map->m_pblk != map->m_pblk) {
printk("ES cache assertion failed for inode: %lu "
"es_cached ex [%d/%d/%llu/%x] != "
"found ex [%d/%d/%llu/%x] retval %d flags %x\n",
inode->i_ino, es_map->m_lblk, es_map->m_len,
es_map->m_pblk, es_map->m_flags, map->m_lblk,
map->m_len, map->m_pblk, map->m_flags,
retval, flags);
}
}
#endif /* ES_AGGRESSIVE_TEST */
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
* Otherwise it takes the write lock of the i_data_sem and allocate blocks
* and store the allocated blocks in the result buffer head and mark it
* mapped.
*
* If file type is extents based, it will call ext4_ext_map_blocks(),
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocated. if
* create==0 and the blocks are pre-allocated and unwritten, the resulting @map
* is marked as unwritten. If the create == 1, it will mark @map as mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
* that case, @map is returned as unmapped but we still do fill map->m_len to
* indicate the length of a hole starting at map->m_lblk.
*
* It returns the error in case of allocation failure.
*/
int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct extent_status es;
int retval;
int ret = 0;
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
memcpy(&orig_map, map, sizeof(*map));
#endif
map->m_flags = 0;
ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n",
flags, map->m_len, (unsigned long) map->m_lblk);
/*
* ext4_map_blocks returns an int, and m_len is an unsigned int
*/
if (unlikely(map->m_len > INT_MAX))
map->m_len = INT_MAX;
/* We can handle the block number less than EXT_MAX_BLOCKS */
if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
return -EFSCORRUPTED;
/* Lookup extent status tree firstly */
if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
map->m_pblk = ext4_es_pblock(&es) +
map->m_lblk - es.es_lblk;
map->m_flags |= ext4_es_is_written(&es) ?
EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
map->m_pblk = 0;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
retval = 0;
} else {
BUG();
}
if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT)
return retval;
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(handle, inode, map,
&orig_map, flags);
#endif
goto found;
}
/*
* In the query cache no-wait mode, nothing we can do more if we
* cannot find extent in the cache.
*/
if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT)
return 0;
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
if (retval > 0) {
unsigned int status;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
!(status & EXTENT_STATUS_WRITTEN) &&
ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk,
map->m_len, map->m_pblk, status);
if (ret < 0)
retval = ret;
}
up_read((&EXT4_I(inode)->i_data_sem));
found:
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
/* If it is only a block(s) look up */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
return retval;
/*
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
* ext4_ext_get_block() returns the create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
/*
* If we need to convert extent to unwritten
* we continue and do the actual work in
* ext4_ext_map_blocks()
*/
if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
return retval;
/*
* Here we clear m_flags because after allocating an new extent,
* it will be set again.
*/
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
* New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_block()
* with create == 1 flag.
*/
down_write(&EXT4_I(inode)->i_data_sem);
/*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags);
if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
/*
* We allocated new blocks which will result in
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
/*
* Update reserved blocks/metadata blocks after successful
* block allocation which had been deferred till now. We don't
* support fallocate for non extent files. So we can update
* reserve space here.
*/
if ((retval > 0) &&
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
if (retval > 0) {
unsigned int status;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
/*
* We have to zeroout blocks before inserting them into extent
* status tree. Otherwise someone could look them up there and
* use them before they are really zeroed. We also have to
* unmap metadata before zeroing as otherwise writeback can
* overwrite zeros with stale data from block device.
*/
if (flags & EXT4_GET_BLOCKS_ZERO &&
map->m_flags & EXT4_MAP_MAPPED &&
map->m_flags & EXT4_MAP_NEW) {
ret = ext4_issue_zeroout(inode, map->m_lblk,
map->m_pblk, map->m_len);
if (ret) {
retval = ret;
goto out_sem;
}
}
/*
* If the extent has been zeroed out, we don't need to update
* extent status tree.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
if (ext4_es_is_written(&es))
goto out_sem;
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
!(status & EXTENT_STATUS_WRITTEN) &&
ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status);
if (ret < 0) {
retval = ret;
goto out_sem;
}
}
out_sem:
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
/*
* Inodes with freshly allocated blocks where contents will be
* visible after transaction commit must be on transaction's
* ordered data list.
*/
if (map->m_flags & EXT4_MAP_NEW &&
!(map->m_flags & EXT4_MAP_UNWRITTEN) &&
!(flags & EXT4_GET_BLOCKS_ZERO) &&
!ext4_is_quota_file(inode) &&
ext4_should_order_data(inode)) {
loff_t start_byte =
(loff_t)map->m_lblk << inode->i_blkbits;
loff_t length = (loff_t)map->m_len << inode->i_blkbits;
if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
ret = ext4_jbd2_inode_add_wait(handle, inode,
start_byte, length);
else
ret = ext4_jbd2_inode_add_write(handle, inode,
start_byte, length);
if (ret)
return ret;
}
}
if (retval > 0 && (map->m_flags & EXT4_MAP_UNWRITTEN ||
map->m_flags & EXT4_MAP_MAPPED))
ext4_fc_track_range(handle, inode, map->m_lblk,
map->m_lblk + map->m_len - 1);
if (retval < 0)
ext_debug(inode, "failed with err %d\n", retval);
return retval;
}
/*
* Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
* we have to be careful as someone else may be manipulating b_state as well.
*/
static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
{
unsigned long old_state;
unsigned long new_state;
flags &= EXT4_MAP_FLAGS;
/* Dummy buffer_head? Set non-atomically. */
if (!bh->b_page) {
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
return;
}
/*
* Someone else may be modifying b_state. Be careful! This is ugly but
* once we get rid of using bh as a container for mapping information
* to pass to / from get_block functions, this can go away.
*/
old_state = READ_ONCE(bh->b_state);
do {
new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
} while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state)));
}
static int _ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int flags)
{
struct ext4_map_blocks map;
int ret = 0;
if (ext4_has_inline_data(inode))
return -ERANGE;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map,
flags);
if (ret > 0) {
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
} else if (ret == 0) {
/* hole case, need to fill in bh->b_size */
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
}
return ret;
}
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
return _ext4_get_block(inode, iblock, bh,
create ? EXT4_GET_BLOCKS_CREATE : 0);
}
/*
* Get block function used when preparing for buffered write if we require
* creating an unwritten extent if blocks haven't been allocated. The extent
* will be converted to written after the IO is complete.
*/
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
inode->i_ino, create);
return _ext4_get_block(inode, iblock, bh_result,
EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT);
}
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int map_flags)
{
struct ext4_map_blocks map;
struct buffer_head *bh;
int create = map_flags & EXT4_GET_BLOCKS_CREATE;
bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT;
int err;
ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
|| handle != NULL || create == 0);
ASSERT(create == 0 || !nowait);
map.m_lblk = block;
map.m_len = 1;
err = ext4_map_blocks(handle, inode, &map, map_flags);
if (err == 0)
return create ? ERR_PTR(-ENOSPC) : NULL;
if (err < 0)
return ERR_PTR(err);
if (nowait)
return sb_find_get_block(inode->i_sb, map.m_pblk);
bh = sb_getblk(inode->i_sb, map.m_pblk);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
ASSERT(create != 0);
ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
|| (handle != NULL));
/*
* Now that we do not always journal data, we should
* keep in mind whether this should always journal the
* new buffer as metadata. For now, regular file
* writes use ext4_get_block instead, so it's not a
* problem.
*/
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
err = ext4_journal_get_create_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
if (unlikely(err)) {
unlock_buffer(bh);
goto errout;
}
if (!buffer_uptodate(bh)) {
memset(bh->b_data, 0, inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (unlikely(err))
goto errout;
} else
BUFFER_TRACE(bh, "not a new buffer");
return bh;
errout:
brelse(bh);
return ERR_PTR(err);
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int map_flags)
{
struct buffer_head *bh;
int ret;
bh = ext4_getblk(handle, inode, block, map_flags);
if (IS_ERR(bh))
return bh;
if (!bh || ext4_buffer_uptodate(bh))
return bh;
ret = ext4_read_bh_lock(bh, REQ_META | REQ_PRIO, true);
if (ret) {
put_bh(bh);
return ERR_PTR(ret);
}
return bh;
}
/* Read a contiguous batch of blocks. */
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
bool wait, struct buffer_head **bhs)
{
int i, err;
for (i = 0; i < bh_count; i++) {
bhs[i] = ext4_getblk(NULL, inode, block + i, 0 /* map_flags */);
if (IS_ERR(bhs[i])) {
err = PTR_ERR(bhs[i]);
bh_count = i;
goto out_brelse;
}
}
for (i = 0; i < bh_count; i++)
/* Note that NULL bhs[i] is valid because of holes. */
if (bhs[i] && !ext4_buffer_uptodate(bhs[i]))
ext4_read_bh_lock(bhs[i], REQ_META | REQ_PRIO, false);
if (!wait)
return 0;
for (i = 0; i < bh_count; i++)
if (bhs[i])
wait_on_buffer(bhs[i]);
for (i = 0; i < bh_count; i++) {
if (bhs[i] && !buffer_uptodate(bhs[i])) {
err = -EIO;
goto out_brelse;
}
}
return 0;
out_brelse:
for (i = 0; i < bh_count; i++) {
brelse(bhs[i]);
bhs[i] = NULL;
}
return err;
}
int ext4_walk_page_buffers(handle_t *handle, struct inode *inode,
struct buffer_head *head,
unsigned from,
unsigned to,
int *partial,
int (*fn)(handle_t *handle, struct inode *inode,
struct buffer_head *bh))
{
struct buffer_head *bh;
unsigned block_start, block_end;
unsigned blocksize = head->b_size;
int err, ret = 0;
struct buffer_head *next;
for (bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
block_start = block_end, bh = next) {
next = bh->b_this_page;
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (partial && !buffer_uptodate(bh))
*partial = 1;
continue;
}
err = (*fn)(handle, inode, bh);
if (!ret)
ret = err;
}
return ret;
}
/*
* Helper for handling dirtying of journalled data. We also mark the folio as
* dirty so that writeback code knows about this page (and inode) contains
* dirty data. ext4_writepages() then commits appropriate transaction to
* make data stable.
*/
static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh)
{
folio_mark_dirty(bh->b_folio);
return ext4_handle_dirty_metadata(handle, NULL, bh);
}
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int dirty = buffer_dirty(bh);
int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
/*
* __block_write_begin() could have dirtied some buffers. Clean
* the dirty bit as jbd2_journal_get_write_access() could complain
* otherwise about fs integrity issues. Setting of the dirty bit
* by __block_write_begin() isn't a real problem here as we clear
* the bit before releasing a page lock and thus writeback cannot
* ever write the buffer.
*/
if (dirty)
clear_buffer_dirty(bh);
BUFFER_TRACE(bh, "get write access");
ret = ext4_journal_get_write_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
if (!ret && dirty)
ret = ext4_dirty_journalled_data(handle, bh);
return ret;
}
#ifdef CONFIG_FS_ENCRYPTION
static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
get_block_t *get_block)
{
unsigned from = pos & (PAGE_SIZE - 1);
unsigned to = from + len;
struct inode *inode = folio->mapping->host;
unsigned block_start, block_end;
sector_t block;
int err = 0;
unsigned blocksize = inode->i_sb->s_blocksize;
unsigned bbits;
struct buffer_head *bh, *head, *wait[2];
int nr_wait = 0;
int i;
BUG_ON(!folio_test_locked(folio));
BUG_ON(from > PAGE_SIZE);
BUG_ON(to > PAGE_SIZE);
BUG_ON(from > to);
head = folio_buffers(folio);
if (!head) {
create_empty_buffers(&folio->page, blocksize, 0);
head = folio_buffers(folio);
}
bbits = ilog2(blocksize);
block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
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)) {
set_buffer_uptodate(bh);
}
continue;
}
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
break;
if (buffer_new(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)) {
set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
ext4_read_bh_lock(bh, 0, false);
wait[nr_wait++] = bh;
}
}
/*
* If we issued read requests, let them complete.
*/
for (i = 0; i < nr_wait; i++) {
wait_on_buffer(wait[i]);
if (!buffer_uptodate(wait[i]))
err = -EIO;
}
if (unlikely(err)) {
page_zero_new_buffers(&folio->page, from, to);
} else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
for (i = 0; i < nr_wait; i++) {
int err2;
err2 = fscrypt_decrypt_pagecache_blocks(folio,
blocksize, bh_offset(wait[i]));
if (err2) {
clear_buffer_uptodate(wait[i]);
err = err2;
}
}
}
return err;
}
#endif
/*
* To preserve ordering, it is essential that the hole instantiation and
* the data write be encapsulated in a single transaction. We cannot
* close off a transaction and start a new one between the ext4_get_block()
* and the ext4_write_end(). So doing the jbd2_journal_start at the start of
* ext4_write_begin() is the right place.
*/
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
int ret, needed_blocks;
handle_t *handle;
int retries = 0;
struct folio *folio;
pgoff_t index;
unsigned from, to;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
trace_ext4_write_begin(inode, pos, len);
/*
* Reserve one block more for addition to orphan list in case
* we allocate blocks but write fails for some reason
*/
needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_SHIFT;
from = pos & (PAGE_SIZE - 1);
to = from + len;
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
pagep);
if (ret < 0)
return ret;
if (ret == 1)
return 0;
}
/*
* __filemap_get_folio() can take a long time if the
* system is thrashing due to memory pressure, or if the folio
* is being written back. So grab it first before we start
* the transaction handle. This also allows us to allocate
* the folio (if needed) without using GFP_NOFS.
*/
retry_grab:
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (!folio)
return -ENOMEM;
/*
* The same as page allocation, we prealloc buffer heads before
* starting the handle.
*/
if (!folio_buffers(folio))
create_empty_buffers(&folio->page, inode->i_sb->s_blocksize, 0);
folio_unlock(folio);
retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
folio_put(folio);
return PTR_ERR(handle);
}
folio_lock(folio);
if (folio->mapping != mapping) {
/* The folio got truncated from under us */
folio_unlock(folio);
folio_put(folio);
ext4_journal_stop(handle);
goto retry_grab;
}
/* In case writeback began while the folio was unlocked */
folio_wait_stable(folio);
#ifdef CONFIG_FS_ENCRYPTION
if (ext4_should_dioread_nolock(inode))
ret = ext4_block_write_begin(folio, pos, len,
ext4_get_block_unwritten);
else
ret = ext4_block_write_begin(folio, pos, len, ext4_get_block);
#else
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(&folio->page, pos, len,
ext4_get_block_unwritten);
else
ret = __block_write_begin(&folio->page, pos, len, ext4_get_block);
#endif
if (!ret && ext4_should_journal_data(inode)) {
ret = ext4_walk_page_buffers(handle, inode,
folio_buffers(folio), from, to,
NULL, do_journal_get_write_access);
}
if (ret) {
bool extended = (pos + len > inode->i_size) &&
!ext4_verity_in_progress(inode);
folio_unlock(folio);
/*
* __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold i_rwsem.
*
* Add inode to orphan list in case we crash before
* truncate finishes
*/
if (extended && ext4_can_truncate(inode))
ext4_orphan_add(handle, inode);
ext4_journal_stop(handle);
if (extended) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
* make sure the inode is removed from the
* orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_journal;
folio_put(folio);
return ret;
}
*pagep = &folio->page;
return ret;
}
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
ret = ext4_dirty_journalled_data(handle, bh);
clear_buffer_meta(bh);
clear_buffer_prio(bh);
return ret;
}
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
* ext4 never places buffers on inode->i_mapping->private_list. metadata
* buffers are managed internally.
*/
static int ext4_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct folio *folio = page_folio(page);
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int i_size_changed = 0;
bool verity = ext4_verity_in_progress(inode);
trace_ext4_write_end(inode, pos, len, copied);
if (ext4_has_inline_data(inode) &&
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
return ext4_write_inline_data_end(inode, pos, len, copied, page);
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
/*
* it's important to update i_size while still holding folio lock:
* page writeout could otherwise come in and zero beyond i_size.
*
* If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree
* blocks are being written past EOF, so skip the i_size update.
*/
if (!verity)
i_size_changed = ext4_update_inode_size(inode, pos + copied);
folio_unlock(folio);
folio_put(folio);
if (old_size < pos && !verity)
pagecache_isize_extended(inode, old_size, pos);
/*
* Don't mark the inode dirty under folio lock. First, it unnecessarily
* makes the holding time of folio lock longer. Second, it forces lock
* ordering of folio lock and transaction start for journaling
* filesystems.
*/
if (i_size_changed)
ret = ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size && !verity) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* This is a private version of page_zero_new_buffers() which doesn't
* set the buffer to be dirty, since in data=journalled mode we need
* to call ext4_dirty_journalled_data() instead.
*/
static void ext4_journalled_zero_new_buffers(handle_t *handle,
struct inode *inode,
struct folio *folio,
unsigned from, unsigned to)
{
unsigned int block_start = 0, block_end;
struct buffer_head *head, *bh;
bh = head = folio_buffers(folio);
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
if (!folio_test_uptodate(folio)) {
unsigned start, size;
start = max(from, block_start);
size = min(to, block_end) - start;
folio_zero_range(folio, start, size);
write_end_fn(handle, inode, bh);
}
clear_buffer_new(bh);
}
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
}
static int ext4_journalled_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct folio *folio = page_folio(page);
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
int size_changed = 0;
bool verity = ext4_verity_in_progress(inode);
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_SIZE - 1);
to = from + len;
BUG_ON(!ext4_handle_valid(handle));
if (ext4_has_inline_data(inode))
return ext4_write_inline_data_end(inode, pos, len, copied, page);
if (unlikely(copied < len) && !folio_test_uptodate(folio)) {
copied = 0;
ext4_journalled_zero_new_buffers(handle, inode, folio,
from, to);
} else {
if (unlikely(copied < len))
ext4_journalled_zero_new_buffers(handle, inode, folio,
from + copied, to);
ret = ext4_walk_page_buffers(handle, inode,
folio_buffers(folio),
from, from + copied, &partial,
write_end_fn);
if (!partial)
folio_mark_uptodate(folio);
}
if (!verity)
size_changed = ext4_update_inode_size(inode, pos + copied);
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
folio_unlock(folio);
folio_put(folio);
if (old_size < pos && !verity)
pagecache_isize_extended(inode, old_size, pos);
if (size_changed) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size && !verity) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* Reserve space for a single cluster
*/
static int ext4_da_reserve_space(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
int ret;
/*
* We will charge metadata quota at writeout time; this saves
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
if (ret)
return ret;
spin_lock(&ei->i_block_reservation_lock);
if (ext4_claim_free_clusters(sbi, 1, 0)) {
spin_unlock(&ei->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
return -ENOSPC;
}
ei->i_reserved_data_blocks++;
trace_ext4_da_reserve_space(inode);
spin_unlock(&ei->i_block_reservation_lock);
return 0; /* success */
}
void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
if (!to_free)
return; /* Nothing to release, exit */
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
trace_ext4_da_release_space(inode, to_free);
if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
* if there aren't enough reserved blocks, then the
* counter is messed up somewhere. Since this
* function is called from invalidate page, it's
* harmless to return without any action.
*/
ext4_warning(inode->i_sb, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
WARN_ON(1);
to_free = ei->i_reserved_data_blocks;
}
ei->i_reserved_data_blocks -= to_free;
/* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
/*
* Delayed allocation stuff
*/
struct mpage_da_data {
/* These are input fields for ext4_do_writepages() */
struct inode *inode;
struct writeback_control *wbc;
unsigned int can_map:1; /* Can writepages call map blocks? */
/* These are internal state of ext4_do_writepages() */
pgoff_t first_page; /* The first page to write */
pgoff_t next_page; /* Current page to examine */
pgoff_t last_page; /* Last page to examine */
/*
* Extent to map - this can be after first_page because that can be
* fully mapped. We somewhat abuse m_flags to store whether the extent
* is delalloc or unwritten.
*/
struct ext4_map_blocks map;
struct ext4_io_submit io_submit; /* IO submission data */
unsigned int do_map:1;
unsigned int scanned_until_end:1;
unsigned int journalled_more_data:1;
};
static void mpage_release_unused_pages(struct mpage_da_data *mpd,
bool invalidate)
{
unsigned nr, i;
pgoff_t index, end;
struct folio_batch fbatch;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
/* This is necessary when next_page == 0. */
if (mpd->first_page >= mpd->next_page)
return;
mpd->scanned_until_end = 0;
index = mpd->first_page;
end = mpd->next_page - 1;
if (invalidate) {
ext4_lblk_t start, last;
start = index << (PAGE_SHIFT - inode->i_blkbits);
last = end << (PAGE_SHIFT - inode->i_blkbits);
/*
* avoid racing with extent status tree scans made by
* ext4_insert_delayed_block()
*/
down_write(&EXT4_I(inode)->i_data_sem);
ext4_es_remove_extent(inode, start, last - start + 1);
up_write(&EXT4_I(inode)->i_data_sem);
}
folio_batch_init(&fbatch);
while (index <= end) {
nr = filemap_get_folios(mapping, &index, end, &fbatch);
if (nr == 0)
break;
for (i = 0; i < nr; i++) {
struct folio *folio = fbatch.folios[i];
if (folio->index < mpd->first_page)
continue;
if (folio->index + folio_nr_pages(folio) - 1 > end)
continue;
BUG_ON(!folio_test_locked(folio));
BUG_ON(folio_test_writeback(folio));
if (invalidate) {
if (folio_mapped(folio))
folio_clear_dirty_for_io(folio);
block_invalidate_folio(folio, 0,
folio_size(folio));
folio_clear_uptodate(folio);
}
folio_unlock(folio);
}
folio_batch_release(&fbatch);
}
}
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
EXT4_C2B(EXT4_SB(inode->i_sb),
ext4_count_free_clusters(sb)));
ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_freeclusters_counter)));
ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
ext4_msg(sb, KERN_CRIT, "Block reservation details");
ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
ei->i_reserved_data_blocks);
return;
}
/*
* ext4_insert_delayed_block - adds a delayed block to the extents status
* tree, incrementing the reserved cluster/block
* count or making a pending reservation
* where needed
*
* @inode - file containing the newly added block
* @lblk - logical block to be added
*
* Returns 0 on success, negative error code on failure.
*/
static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
bool allocated = false;
bool reserved = false;
/*
* If the cluster containing lblk is shared with a delayed,
* written, or unwritten extent in a bigalloc file system, it's
* already been accounted for and does not need to be reserved.
* A pending reservation must be made for the cluster if it's
* shared with a written or unwritten extent and doesn't already
* have one. Written and unwritten extents can be purged from the
* extents status tree if the system is under memory pressure, so
* it's necessary to examine the extent tree if a search of the
* extents status tree doesn't get a match.
*/
if (sbi->s_cluster_ratio == 1) {
ret = ext4_da_reserve_space(inode);
if (ret != 0) /* ENOSPC */
goto errout;
reserved = true;
} else { /* bigalloc */
if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
if (!ext4_es_scan_clu(inode,
&ext4_es_is_mapped, lblk)) {
ret = ext4_clu_mapped(inode,
EXT4_B2C(sbi, lblk));
if (ret < 0)
goto errout;
if (ret == 0) {
ret = ext4_da_reserve_space(inode);
if (ret != 0) /* ENOSPC */
goto errout;
reserved = true;
} else {
allocated = true;
}
} else {
allocated = true;
}
}
}
ret = ext4_es_insert_delayed_block(inode, lblk, allocated);
if (ret && reserved)
ext4_da_release_space(inode, 1);
errout:
return ret;
}
/*
* This function is grabs code from the very beginning of
* ext4_map_blocks, but assumes that the caller is from delayed write
* time. This function looks up the requested blocks and sets the
* buffer delay bit under the protection of i_data_sem.
*/
static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
struct ext4_map_blocks *map,
struct buffer_head *bh)
{
struct extent_status es;
int retval;
sector_t invalid_block = ~((sector_t) 0xffff);
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
memcpy(&orig_map, map, sizeof(*map));
#endif
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~0;
map->m_flags = 0;
ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
(unsigned long) map->m_lblk);
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
if (ext4_es_is_hole(&es)) {
retval = 0;
down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed;
}
/*
* Delayed extent could be allocated by fallocate.
* So we need to check it.
*/
if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
return 0;
}
map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
retval = es.es_len - (iblock - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
if (ext4_es_is_written(&es))
map->m_flags |= EXT4_MAP_MAPPED;
else if (ext4_es_is_unwritten(&es))
map->m_flags |= EXT4_MAP_UNWRITTEN;
else
BUG();
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
#endif
return retval;
}
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode))
retval = 0;
else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
retval = ext4_ext_map_blocks(NULL, inode, map, 0);
else
retval = ext4_ind_map_blocks(NULL, inode, map, 0);
add_delayed:
if (retval == 0) {
int ret;
/*
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
ret = ext4_insert_delayed_block(inode, map->m_lblk);
if (ret != 0) {
retval = ret;
goto out_unlock;
}
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
} else if (retval > 0) {
int ret;
unsigned int status;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status);
if (ret != 0)
retval = ret;
}
out_unlock:
up_read((&EXT4_I(inode)->i_data_sem));
return retval;
}
/*
* This is a special get_block_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
*
* For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
* We also have b_blocknr = -1 and b_bdev initialized properly
*
* For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
* We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
* initialized properly.
*/
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
struct ext4_map_blocks map;
int ret = 0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
map.m_lblk = iblock;
map.m_len = 1;
/*
* first, we need to know whether the block is allocated already
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
ret = ext4_da_map_blocks(inode, iblock, &map, bh);
if (ret <= 0)
return ret;
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
if (buffer_unwritten(bh)) {
/* A delayed write to unwritten bh should be marked
* new and mapped. Mapped ensures that we don't do
* get_block multiple times when we write to the same
* offset and new ensures that we do proper zero out
* for partial write.
*/
set_buffer_new(bh);
set_buffer_mapped(bh);
}
return 0;
}
static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio)
{
mpd->first_page += folio_nr_pages(folio);
folio_unlock(folio);
}
static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio)
{
size_t len;
loff_t size;
int err;
BUG_ON(folio->index != mpd->first_page);
folio_clear_dirty_for_io(folio);
/*
* We have to be very careful here! Nothing protects writeback path
* against i_size changes and the page can be writeably mapped into
* page tables. So an application can be growing i_size and writing
* data through mmap while writeback runs. folio_clear_dirty_for_io()
* write-protects our page in page tables and the page cannot get
* written to again until we release folio lock. So only after
* folio_clear_dirty_for_io() we are safe to sample i_size for
* ext4_bio_write_folio() to zero-out tail of the written page. We rely
* on the barrier provided by folio_test_clear_dirty() in
* folio_clear_dirty_for_io() to make sure i_size is really sampled only
* after page tables are updated.
*/
size = i_size_read(mpd->inode);
len = folio_size(folio);
if (folio_pos(folio) + len > size &&
!ext4_verity_in_progress(mpd->inode))
len = size & ~PAGE_MASK;
err = ext4_bio_write_folio(&mpd->io_submit, folio, len);
if (!err)
mpd->wbc->nr_to_write--;
return err;
}
#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay))
/*
* mballoc gives us at most this number of blocks...
* XXX: That seems to be only a limitation of ext4_mb_normalize_request().
* The rest of mballoc seems to handle chunks up to full group size.
*/
#define MAX_WRITEPAGES_EXTENT_LEN 2048
/*
* mpage_add_bh_to_extent - try to add bh to extent of blocks to map
*
* @mpd - extent of blocks
* @lblk - logical number of the block in the file
* @bh - buffer head we want to add to the extent
*
* The function is used to collect contig. blocks in the same state. If the
* buffer doesn't require mapping for writeback and we haven't started the
* extent of buffers to map yet, the function returns 'true' immediately - the
* caller can write the buffer right away. Otherwise the function returns true
* if the block has been added to the extent, false if the block couldn't be
* added.
*/
static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
struct buffer_head *bh)
{
struct ext4_map_blocks *map = &mpd->map;
/* Buffer that doesn't need mapping for writeback? */
if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
(!buffer_delay(bh) && !buffer_unwritten(bh))) {
/* So far no extent to map => we write the buffer right away */
if (map->m_len == 0)
return true;
return false;
}
/* First block in the extent? */
if (map->m_len == 0) {
/* We cannot map unless handle is started... */
if (!mpd->do_map)
return false;
map->m_lblk = lblk;
map->m_len = 1;
map->m_flags = bh->b_state & BH_FLAGS;
return true;
}
/* Don't go larger than mballoc is willing to allocate */
if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
return false;
/* Can we merge the block to our big extent? */
if (lblk == map->m_lblk + map->m_len &&
(bh->b_state & BH_FLAGS) == map->m_flags) {
map->m_len++;
return true;
}
return false;
}
/*
* mpage_process_page_bufs - submit page buffers for IO or add them to extent
*
* @mpd - extent of blocks for mapping
* @head - the first buffer in the page
* @bh - buffer we should start processing from
* @lblk - logical number of the block in the file corresponding to @bh
*
* Walk through page buffers from @bh upto @head (exclusive) and either submit
* the page for IO if all buffers in this page were mapped and there's no
* accumulated extent of buffers to map or add buffers in the page to the
* extent of buffers to map. The function returns 1 if the caller can continue
* by processing the next page, 0 if it should stop adding buffers to the
* extent to map because we cannot extend it anymore. It can also return value
* < 0 in case of error during IO submission.
*/
static int mpage_process_page_bufs(struct mpage_da_data *mpd,
struct buffer_head *head,
struct buffer_head *bh,
ext4_lblk_t lblk)
{
struct inode *inode = mpd->inode;
int err;
ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
>> inode->i_blkbits;
if (ext4_verity_in_progress(inode))
blocks = EXT_MAX_BLOCKS;
do {
BUG_ON(buffer_locked(bh));
if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) {
/* Found extent to map? */
if (mpd->map.m_len)
return 0;
/* Buffer needs mapping and handle is not started? */
if (!mpd->do_map)
return 0;
/* Everything mapped so far and we hit EOF */
break;
}
} while (lblk++, (bh = bh->b_this_page) != head);
/* So far everything mapped? Submit the page for IO. */
if (mpd->map.m_len == 0) {
err = mpage_submit_folio(mpd, head->b_folio);
if (err < 0)
return err;
mpage_folio_done(mpd, head->b_folio);
}
if (lblk >= blocks) {
mpd->scanned_until_end = 1;
return 0;
}
return 1;
}
/*
* mpage_process_folio - update folio buffers corresponding to changed extent
* and may submit fully mapped page for IO
* @mpd: description of extent to map, on return next extent to map
* @folio: Contains these buffers.
* @m_lblk: logical block mapping.
* @m_pblk: corresponding physical mapping.
* @map_bh: determines on return whether this page requires any further
* mapping or not.
*
* Scan given folio buffers corresponding to changed extent and update buffer
* state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits.
* If the given folio is not fully mapped, we update @mpd to the next extent in
* the given folio that needs mapping & return @map_bh as true.
*/
static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio,
ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
bool *map_bh)
{
struct buffer_head *head, *bh;
ext4_io_end_t *io_end = mpd->io_submit.io_end;
ext4_lblk_t lblk = *m_lblk;
ext4_fsblk_t pblock = *m_pblk;
int err = 0;
int blkbits = mpd->inode->i_blkbits;
ssize_t io_end_size = 0;
struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
bh = head = folio_buffers(folio);
do {
if (lblk < mpd->map.m_lblk)
continue;
if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
/*
* Buffer after end of mapped extent.
* Find next buffer in the folio to map.
*/
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
io_end_vec->size += io_end_size;
err = mpage_process_page_bufs(mpd, head, bh, lblk);
if (err > 0)
err = 0;
if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) {
io_end_vec = ext4_alloc_io_end_vec(io_end);
if (IS_ERR(io_end_vec)) {
err = PTR_ERR(io_end_vec);
goto out;
}
io_end_vec->offset = (loff_t)mpd->map.m_lblk << blkbits;
}
*map_bh = true;
goto out;
}
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock++;
}
clear_buffer_unwritten(bh);
io_end_size += (1 << blkbits);
} while (lblk++, (bh = bh->b_this_page) != head);
io_end_vec->size += io_end_size;
*map_bh = false;
out:
*m_lblk = lblk;
*m_pblk = pblock;
return err;
}
/*
* mpage_map_buffers - update buffers corresponding to changed extent and
* submit fully mapped pages for IO
*
* @mpd - description of extent to map, on return next extent to map
*
* Scan buffers corresponding to changed extent (we expect corresponding pages
* to be already locked) and update buffer state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits,
* and mark buffers as uninit when we perform writes to unwritten extents
* and do extent conversion after IO is finished. If the last page is not fully
* mapped, we update @map to the next extent in the last page that needs
* mapping. Otherwise we submit the page for IO.
*/
static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
{
struct folio_batch fbatch;
unsigned nr, i;
struct inode *inode = mpd->inode;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
ext4_fsblk_t pblock;
int err;
bool map_bh = false;
start = mpd->map.m_lblk >> bpp_bits;
end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
lblk = start << bpp_bits;
pblock = mpd->map.m_pblk;
folio_batch_init(&fbatch);
while (start <= end) {
nr = filemap_get_folios(inode->i_mapping, &start, end, &fbatch);
if (nr == 0)
break;
for (i = 0; i < nr; i++) {
struct folio *folio = fbatch.folios[i];
err = mpage_process_folio(mpd, folio, &lblk, &pblock,
&map_bh);
/*
* If map_bh is true, means page may require further bh
* mapping, or maybe the page was submitted for IO.
* So we return to call further extent mapping.
*/
if (err < 0 || map_bh)
goto out;
/* Page fully mapped - let IO run! */
err = mpage_submit_folio(mpd, folio);
if (err < 0)
goto out;
mpage_folio_done(mpd, folio);
}
folio_batch_release(&fbatch);
}
/* Extent fully mapped and matches with page boundary. We are done. */
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
out:
folio_batch_release(&fbatch);
return err;
}
static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
{
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int get_blocks_flags;
int err, dioread_nolock;
trace_ext4_da_write_pages_extent(inode, map);
/*
* Call ext4_map_blocks() to allocate any delayed allocation blocks, or
* to convert an unwritten extent to be initialized (in the case
* where we have written into one or more preallocated blocks). It is
* possible that we're going to need more metadata blocks than
* previously reserved. However we must not fail because we're in
* writeback and there is nothing we can do about it so it might result
* in data loss. So use reserved blocks to allocate metadata if
* possible.
*
* We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if
* the blocks in question are delalloc blocks. This indicates
* that the blocks and quotas has already been checked when
* the data was copied into the page cache.
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL |
EXT4_GET_BLOCKS_IO_SUBMIT;
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (map->m_flags & BIT(BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
if (err < 0)
return err;
if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
if (!mpd->io_submit.io_end->handle &&
ext4_handle_valid(handle)) {
mpd->io_submit.io_end->handle = handle->h_rsv_handle;
handle->h_rsv_handle = NULL;
}
ext4_set_io_unwritten_flag(inode, mpd->io_submit.io_end);
}
BUG_ON(map->m_len == 0);
return 0;
}
/*
* mpage_map_and_submit_extent - map extent starting at mpd->lblk of length
* mpd->len and submit pages underlying it for IO
*
* @handle - handle for journal operations
* @mpd - extent to map
* @give_up_on_write - we set this to true iff there is a fatal error and there
* is no hope of writing the data. The caller should discard
* dirty pages to avoid infinite loops.
*
* The function maps extent starting at mpd->lblk of length mpd->len. If it is
* delayed, blocks are allocated, if it is unwritten, we may need to convert
* them to initialized or split the described range from larger unwritten
* extent. Note that we need not map all the described range since allocation
* can return less blocks or the range is covered by more unwritten extents. We
* cannot map more because we are limited by reserved transaction credits. On
* the other hand we always make sure that the last touched page is fully
* mapped so that it can be written out (and thus forward progress is
* guaranteed). After mapping we submit all mapped pages for IO.
*/
static int mpage_map_and_submit_extent(handle_t *handle,
struct mpage_da_data *mpd,
bool *give_up_on_write)
{
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int err;
loff_t disksize;
int progress = 0;
ext4_io_end_t *io_end = mpd->io_submit.io_end;
struct ext4_io_end_vec *io_end_vec;
io_end_vec = ext4_alloc_io_end_vec(io_end);
if (IS_ERR(io_end_vec))
return PTR_ERR(io_end_vec);
io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
struct super_block *sb = inode->i_sb;
if (ext4_forced_shutdown(EXT4_SB(sb)) ||
ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
* In the case of ENOSPC, if ext4_count_free_blocks()
* is non-zero, a commit should free up blocks.
*/
if ((err == -ENOMEM) ||
(err == -ENOSPC && ext4_count_free_clusters(sb))) {
if (progress)
goto update_disksize;
return err;
}
ext4_msg(sb, KERN_CRIT,
"Delayed block allocation failed for "
"inode %lu at logical offset %llu with"
" max blocks %u with error %d",
inode->i_ino,
(unsigned long long)map->m_lblk,
(unsigned)map->m_len, -err);
ext4_msg(sb, KERN_CRIT,
"This should not happen!! Data will "
"be lost\n");
if (err == -ENOSPC)
ext4_print_free_blocks(inode);
invalidate_dirty_pages:
*give_up_on_write = true;
return err;
}
progress = 1;
/*
* Update buffer state, submit mapped pages, and get us new
* extent to map
*/
err = mpage_map_and_submit_buffers(mpd);
if (err < 0)
goto update_disksize;
} while (map->m_len);
update_disksize:
/*
* Update on-disk size after IO is submitted. Races with
* truncate are avoided by checking i_size under i_data_sem.
*/
disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
int err2;
loff_t i_size;
down_write(&EXT4_I(inode)->i_data_sem);
i_size = i_size_read(inode);
if (disksize > i_size)
disksize = i_size;
if (disksize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = disksize;
up_write(&EXT4_I(inode)->i_data_sem);
err2 = ext4_mark_inode_dirty(handle, inode);
if (err2) {
ext4_error_err(inode->i_sb, -err2,
"Failed to mark inode %lu dirty",
inode->i_ino);
}
if (!err)
err = err2;
}
return err;
}
/*
* Calculate the total number of credits to reserve for one writepages
* iteration. This is called from ext4_writepages(). We map an extent of
* up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
* the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
* bpp - 1 blocks in bpp different extents.
*/
static int ext4_da_writepages_trans_blocks(struct inode *inode)
{
int bpp = ext4_journal_blocks_per_page(inode);
return ext4_meta_trans_blocks(inode,
MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
}
static int ext4_journal_page_buffers(handle_t *handle, struct page *page,
int len)
{
struct buffer_head *page_bufs = page_buffers(page);
struct inode *inode = page->mapping->host;
int ret, err;
ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
NULL, do_journal_get_write_access);
err = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
NULL, write_end_fn);
if (ret == 0)
ret = err;
err = ext4_jbd2_inode_add_write(handle, inode, page_offset(page), len);
if (ret == 0)
ret = err;
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
return ret;
}
static int mpage_journal_page_buffers(handle_t *handle,
struct mpage_da_data *mpd,
struct page *page)
{
struct inode *inode = mpd->inode;
loff_t size = i_size_read(inode);
int len;
ClearPageChecked(page);
mpd->wbc->nr_to_write--;
if (page->index == size >> PAGE_SHIFT &&
!ext4_verity_in_progress(inode))
len = size & ~PAGE_MASK;
else
len = PAGE_SIZE;
return ext4_journal_page_buffers(handle, page, len);
}
/*
* mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages
* needing mapping, submit mapped pages
*
* @mpd - where to look for pages
*
* Walk dirty pages in the mapping. If they are fully mapped, submit them for
* IO immediately. If we cannot map blocks, we submit just already mapped
* buffers in the page for IO and keep page dirty. When we can map blocks and
* we find a page which isn't mapped we start accumulating extent of buffers
* underlying these pages that needs mapping (formed by either delayed or
* unwritten buffers). We also lock the pages containing these buffers. The
* extent found is returned in @mpd structure (starting at mpd->lblk with
* length mpd->len blocks).
*
* Note that this function can attach bios to one io_end structure which are
* neither logically nor physically contiguous. Although it may seem as an
* unnecessary complication, it is actually inevitable in blocksize < pagesize
* case as we need to track IO to all buffers underlying a page in one io_end.
*/
static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
{
struct address_space *mapping = mpd->inode->i_mapping;
struct super_block *sb = mpd->inode->i_sb;
struct folio_batch fbatch;
unsigned int nr_folios;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
xa_mark_t tag;
int i, err = 0;
int blkbits = mpd->inode->i_blkbits;
ext4_lblk_t lblk;
struct buffer_head *head;
handle_t *handle = NULL;
int bpp = ext4_journal_blocks_per_page(mpd->inode);
if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
mpd->map.m_len = 0;
mpd->next_page = index;
/*
* Start a transaction for writeback of journalled data. We don't start
* the transaction if the filesystem is frozen. In that case we
* should not have any dirty data to write anymore but possibly there
* are stray page dirty bits left by the checkpointing code so this
* loop clears them.
*/
if (ext4_should_journal_data(mpd->inode) &&
sb->s_writers.frozen < SB_FREEZE_FS) {
handle = ext4_journal_start(mpd->inode, EXT4_HT_WRITE_PAGE,
bpp);
if (IS_ERR(handle))
return PTR_ERR(handle);
}
folio_batch_init(&fbatch);
while (index <= end) {
nr_folios = filemap_get_folios_tag(mapping, &index, end,
tag, &fbatch);
if (nr_folios == 0)
break;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
/*
* Accumulated enough dirty pages? This doesn't apply
* to WB_SYNC_ALL mode. For integrity sync we have to
* keep going because someone may be concurrently
* dirtying pages, and we might have synced a lot of
* newly appeared dirty pages, but have not synced all
* of the old dirty pages.
*/
if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
mpd->wbc->nr_to_write <=
mpd->map.m_len >> (PAGE_SHIFT - blkbits))
goto out;
/* If we can't merge this page, we are done. */
if (mpd->map.m_len > 0 && mpd->next_page != folio->index)
goto out;
if (handle) {
err = ext4_journal_ensure_credits(handle, bpp,
0);
if (err < 0)
goto out;
}
folio_lock(folio);
/*
* If the page is no longer dirty, or its mapping no
* longer corresponds to inode we are writing (which
* means it has been truncated or invalidated), or the
* page is already under writeback and we are not doing
* a data integrity writeback, skip the page
*/
if (!folio_test_dirty(folio) ||
(folio_test_writeback(folio) &&
(mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
continue;
}
folio_wait_writeback(folio);
BUG_ON(folio_test_writeback(folio));
/*
* Should never happen but for buggy code in
* other subsystems that call
* set_page_dirty() without properly warning
* the file system first. See [1] for more
* information.
*
* [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz
*/
if (!folio_buffers(folio)) {
ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", folio->index);
folio_clear_dirty(folio);
folio_unlock(folio);
continue;
}
if (mpd->map.m_len == 0)
mpd->first_page = folio->index;
mpd->next_page = folio->index + folio_nr_pages(folio);
/*
* Writeout when we cannot modify metadata is simple.
* Just submit the page. For data=journal mode we
* first handle writeout of the page for checkpoint and
* only after that handle delayed page dirtying. This
* makes sure current data is checkpointed to the final
* location before possibly journalling it again which
* is desirable when the page is frequently dirtied
* through a pin.
*/
if (!mpd->can_map) {
WARN_ON_ONCE(sb->s_writers.frozen ==
SB_FREEZE_COMPLETE);
err = mpage_submit_folio(mpd, folio);
if (err < 0)
goto out;
/* Pending dirtying of journalled data? */
if (folio_test_checked(folio)) {
WARN_ON_ONCE(sb->s_writers.frozen >=
SB_FREEZE_FS);
err = mpage_journal_page_buffers(handle,
mpd, &folio->page);
if (err < 0)
goto out;
mpd->journalled_more_data = 1;
}
mpage_folio_done(mpd, folio);
} else {
/* Add all dirty buffers to mpd */
lblk = ((ext4_lblk_t)folio->index) <<
(PAGE_SHIFT - blkbits);
head = folio_buffers(folio);
err = mpage_process_page_bufs(mpd, head, head,
lblk);
if (err <= 0)
goto out;
err = 0;
}
}
folio_batch_release(&fbatch);
cond_resched();
}
mpd->scanned_until_end = 1;
if (handle)
ext4_journal_stop(handle);
return 0;
out:
folio_batch_release(&fbatch);
if (handle)
ext4_journal_stop(handle);
return err;
}
static int ext4_do_writepages(struct mpage_da_data *mpd)
{
struct writeback_control *wbc = mpd->wbc;
pgoff_t writeback_index = 0;
long nr_to_write = wbc->nr_to_write;
int range_whole = 0;
int cycled = 1;
handle_t *handle = NULL;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
struct blk_plug plug;
bool give_up_on_write = false;
trace_ext4_writepages(inode, wbc);
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
* because that could violate lock ordering on umount
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
goto out_writepages;
/*
* If the filesystem has aborted, it is read-only, so return
* right away instead of dumping stack traces later on that
* will obscure the real source of the problem. We test
* EXT4_MF_FS_ABORTED instead of sb->s_flag's SB_RDONLY because
* the latter could be true if the filesystem is mounted
* read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
ret = -EROFS;
goto out_writepages;
}
/*
* If we have inline data and arrive here, it means that
* we will soon create the block for the 1st page, so
* we'd better clear the inline data here.
*/
if (ext4_has_inline_data(inode)) {
/* Just inode will be modified... */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out_writepages;
}
BUG_ON(ext4_test_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA));
ext4_destroy_inline_data(handle, inode);
ext4_journal_stop(handle);
}
/*
* data=journal mode does not do delalloc so we just need to writeout /
* journal already mapped buffers. On the other hand we need to commit
* transaction to make data stable. We expect all the data to be
* already in the journal (the only exception are DMA pinned pages
* dirtied behind our back) so we commit transaction here and run the
* writeback loop to checkpoint them. The checkpointing is not actually
* necessary to make data persistent *but* quite a few places (extent
* shifting operations, fsverity, ...) depend on being able to drop
* pagecache pages after calling filemap_write_and_wait() and for that
* checkpointing needs to happen.
*/
if (ext4_should_journal_data(inode)) {
mpd->can_map = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
ext4_fc_commit(sbi->s_journal,
EXT4_I(inode)->i_datasync_tid);
}
mpd->journalled_more_data = 0;
if (ext4_should_dioread_nolock(inode)) {
/*
* We may need to convert up to one extent per block in
* the page and we may dirty the inode.
*/
rsv_blocks = 1 + ext4_chunk_trans_blocks(inode,
PAGE_SIZE >> inode->i_blkbits);
}
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index;
if (writeback_index)
cycled = 0;
mpd->first_page = writeback_index;
mpd->last_page = -1;
} else {
mpd->first_page = wbc->range_start >> PAGE_SHIFT;
mpd->last_page = wbc->range_end >> PAGE_SHIFT;
}
ext4_io_submit_init(&mpd->io_submit, wbc);
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, mpd->first_page,
mpd->last_page);
blk_start_plug(&plug);
/*
* First writeback pages that don't need mapping - we can avoid
* starting a transaction unnecessarily and also avoid being blocked
* in the block layer on device congestion while having transaction
* started.
*/
mpd->do_map = 0;
mpd->scanned_until_end = 0;
mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd->io_submit.io_end) {
ret = -ENOMEM;
goto unplug;
}
ret = mpage_prepare_extent_to_map(mpd);
/* Unlock pages we didn't use */
mpage_release_unused_pages(mpd, false);
/* Submit prepared bio */
ext4_io_submit(&mpd->io_submit);
ext4_put_io_end_defer(mpd->io_submit.io_end);
mpd->io_submit.io_end = NULL;
if (ret < 0)
goto unplug;
while (!mpd->scanned_until_end && wbc->nr_to_write > 0) {
/* For each extent of pages we use new io_end */
mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd->io_submit.io_end) {
ret = -ENOMEM;
break;
}
WARN_ON_ONCE(!mpd->can_map);
/*
* We have two constraints: We find one extent to map and we
* must always write out whole page (makes a difference when
* blocksize < pagesize) so that we don't block on IO when we
* try to write out the rest of the page. Journalled mode is
* not supported by delalloc.
*/
BUG_ON(ext4_should_journal_data(inode));
needed_blocks = ext4_da_writepages_trans_blocks(inode);
/* start a new transaction */
handle = ext4_journal_start_with_reserve(inode,
EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
/* Release allocated io_end */
ext4_put_io_end(mpd->io_submit.io_end);
mpd->io_submit.io_end = NULL;
break;
}
mpd->do_map = 1;
trace_ext4_da_write_pages(inode, mpd->first_page, wbc);
ret = mpage_prepare_extent_to_map(mpd);
if (!ret && mpd->map.m_len)
ret = mpage_map_and_submit_extent(handle, mpd,
&give_up_on_write);
/*
* Caution: If the handle is synchronous,
* ext4_journal_stop() can wait for transaction commit
* to finish which may depend on writeback of pages to
* complete or on page lock to be released. In that
* case, we have to wait until after we have
* submitted all the IO, released page locks we hold,
* and dropped io_end reference (for extent conversion
* to be able to complete) before stopping the handle.
*/
if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
ext4_journal_stop(handle);
handle = NULL;
mpd->do_map = 0;
}
/* Unlock pages we didn't use */
mpage_release_unused_pages(mpd, give_up_on_write);
/* Submit prepared bio */
ext4_io_submit(&mpd->io_submit);
/*
* Drop our io_end reference we got from init. We have
* to be careful and use deferred io_end finishing if
* we are still holding the transaction as we can
* release the last reference to io_end which may end
* up doing unwritten extent conversion.
*/
if (handle) {
ext4_put_io_end_defer(mpd->io_submit.io_end);
ext4_journal_stop(handle);
} else
ext4_put_io_end(mpd->io_submit.io_end);
mpd->io_submit.io_end = NULL;
if (ret == -ENOSPC && sbi->s_journal) {
/*
* Commit the transaction which would
* free blocks released in the transaction
* and try again
*/
jbd2_journal_force_commit_nested(sbi->s_journal);
ret = 0;
continue;
}
/* Fatal error - ENOMEM, EIO... */
if (ret)
break;
}
unplug:
blk_finish_plug(&plug);
if (!ret && !cycled && wbc->nr_to_write > 0) {
cycled = 1;
mpd->last_page = writeback_index - 1;
mpd->first_page = 0;
goto retry;
}
/* Update index */
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
* Set the writeback_index so that range_cyclic
* mode will write it back later
*/
mapping->writeback_index = mpd->first_page;
out_writepages:
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
return ret;
}
static int ext4_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct super_block *sb = mapping->host->i_sb;
struct mpage_da_data mpd = {
.inode = mapping->host,
.wbc = wbc,
.can_map = 1,
};
int ret;
if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
return -EIO;
percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
ret = ext4_do_writepages(&mpd);
/*
* For data=journal writeback we could have come across pages marked
* for delayed dirtying (PageChecked) which were just added to the
* running transaction. Try once more to get them to stable storage.
*/
if (!ret && mpd.journalled_more_data)
ret = ext4_do_writepages(&mpd);
percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
return ret;
}
int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = jinode->i_dirty_start,
.range_end = jinode->i_dirty_end,
};
struct mpage_da_data mpd = {
.inode = jinode->i_vfs_inode,
.wbc = &wbc,
.can_map = 0,
};
return ext4_do_writepages(&mpd);
}
static int ext4_dax_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret;
long nr_to_write = wbc->nr_to_write;
struct inode *inode = mapping->host;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
percpu_down_read(&sbi->s_writepages_rwsem);
trace_ext4_writepages(inode, wbc);
ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
percpu_up_read(&sbi->s_writepages_rwsem);
return ret;
}
static int ext4_nonda_switch(struct super_block *sb)
{
s64 free_clusters, dirty_clusters;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/*
* switch to non delalloc mode if we are running low
* on free block. The free block accounting via percpu
* counters can get slightly wrong with percpu_counter_batch getting
* accumulated on each CPU without updating global counters
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
free_clusters =
percpu_counter_read_positive(&sbi->s_freeclusters_counter);
dirty_clusters =
percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
/*
* Start pushing delalloc when 1/2 of free blocks are dirty.
*/
if (dirty_clusters && (free_clusters < 2 * dirty_clusters))
try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
if (2 * free_clusters < 3 * dirty_clusters ||
free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
*/
return 1;
}
return 0;
}
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct page **pagep, void **fsdata)
{
int ret, retries = 0;
struct folio *folio;
pgoff_t index;
struct inode *inode = mapping->host;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
index = pos >> PAGE_SHIFT;
if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
return ext4_write_begin(file, mapping, pos,
len, pagep, fsdata);
}
*fsdata = (void *)0;
trace_ext4_da_write_begin(inode, pos, len);
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len,
pagep, fsdata);
if (ret < 0)
return ret;
if (ret == 1)
return 0;
}
retry:
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (!folio)
return -ENOMEM;
/* In case writeback began while the folio was unlocked */
folio_wait_stable(folio);
#ifdef CONFIG_FS_ENCRYPTION
ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
#else
ret = __block_write_begin(&folio->page, pos, len, ext4_da_get_block_prep);
#endif
if (ret < 0) {
folio_unlock(folio);
folio_put(folio);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold inode lock.
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
return ret;
}
*pagep = &folio->page;
return ret;
}
/*
* Check if we should update i_disksize
* when write to the end of file but not require block allocation
*/
static int ext4_da_should_update_i_disksize(struct page *page,
unsigned long offset)
{
struct buffer_head *bh;
struct inode *inode = page->mapping->host;
unsigned int idx;
int i;
bh = page_buffers(page);
idx = offset >> inode->i_blkbits;
for (i = 0; i < idx; i++)
bh = bh->b_this_page;
if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
return 0;
return 1;
}
static int ext4_da_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
if (write_mode == FALL_BACK_TO_NONDELALLOC)
return ext4_write_end(file, mapping, pos,
len, copied, page, fsdata);
trace_ext4_da_write_end(inode, pos, len, copied);
if (write_mode != CONVERT_INLINE_DATA &&
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
ext4_has_inline_data(inode))
return ext4_write_inline_data_end(inode, pos, len, copied, page);
start = pos & (PAGE_SIZE - 1);
end = start + copied - 1;
/*
* Since we are holding inode lock, we are sure i_disksize <=
* i_size. We also know that if i_disksize < i_size, there are
* delalloc writes pending in the range upto i_size. If the end of
* the current write is <= i_size, there's no need to touch
* i_disksize since writeback will push i_disksize upto i_size
* eventually. If the end of the current write is > i_size and
* inside an allocated block (ext4_da_should_update_i_disksize()
* check), we need to update i_disksize here as certain
* ext4_writepages() paths not allocating blocks update i_disksize.
*
* Note that we defer inode dirtying to generic_write_end() /
* ext4_da_write_inline_data_end().
*/
new_i_size = pos + copied;
if (copied && new_i_size > inode->i_size &&
ext4_da_should_update_i_disksize(page, end))
ext4_update_i_disksize(inode, new_i_size);
return generic_write_end(file, mapping, pos, len, copied, page, fsdata);
}
/*
* Force all delayed allocation blocks to be allocated for a given inode.
*/
int ext4_alloc_da_blocks(struct inode *inode)
{
trace_ext4_alloc_da_blocks(inode);
if (!EXT4_I(inode)->i_reserved_data_blocks)
return 0;
/*
* We do something simple for now. The filemap_flush() will
* also start triggering a write of the data blocks, which is
* not strictly speaking necessary (and for users of
* laptop_mode, not even desirable). However, to do otherwise
* would require replicating code paths in:
*
* ext4_writepages() ->
* write_cache_pages() ---> (via passed in callback function)
* __mpage_da_writepage() -->
* mpage_add_bh_to_extent()
* mpage_da_map_blocks()
*
* The problem is that write_cache_pages(), located in
* mm/page-writeback.c, marks pages clean in preparation for
* doing I/O, which is not desirable if we're not planning on
* doing I/O at all.
*
* We could call write_cache_pages(), and then redirty all of
* the pages by calling redirty_page_for_writepage() but that
* would be ugly in the extreme. So instead we would need to
* replicate parts of the code in the above functions,
* simplifying them because we wouldn't actually intend to
* write out the pages, but rather only collect contiguous
* logical block extents, call the multi-block allocator, and
* then update the buffer heads with the block allocations.
*
* For now, though, we'll cheat by calling filemap_flush(),
* which will map the blocks, and start the I/O, but not
* actually wait for the I/O to complete.
*/
return filemap_flush(inode->i_mapping);
}
/*
* bmap() is special. It gets used by applications such as lilo and by
* the swapper to find the on-disk block of a specific piece of data.
*
* Naturally, this is dangerous if the block concerned is still in the
* journal. If somebody makes a swapfile on an ext4 data-journaling
* filesystem and enables swap, then they may get a nasty shock when the
* data getting swapped to that swapfile suddenly gets overwritten by
* the original zero's written out previously to the journal and
* awaiting writeback in the kernel's buffer cache.
*
* So, if we see any bmap calls here on a modified, data-journaled file,
* take extra steps to flush any blocks which might be in the cache.
*/
static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
sector_t ret = 0;
inode_lock_shared(inode);
/*
* We can get here for an inline file via the FIBMAP ioctl
*/
if (ext4_has_inline_data(inode))
goto out;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
(test_opt(inode->i_sb, DELALLOC) ||
ext4_should_journal_data(inode))) {
/*
* With delalloc or journalled data we want to sync the file so
* that we can make sure we allocate blocks for file and data
* is in place for the user to see it
*/
filemap_write_and_wait(mapping);
}
ret = iomap_bmap(mapping, block, &ext4_iomap_ops);
out:
inode_unlock_shared(inode);
return ret;
}
static int ext4_read_folio(struct file *file, struct folio *folio)
{
int ret = -EAGAIN;
struct inode *inode = folio->mapping->host;
trace_ext4_readpage(&folio->page);
if (ext4_has_inline_data(inode))
ret = ext4_readpage_inline(inode, folio);
if (ret == -EAGAIN)
return ext4_mpage_readpages(inode, NULL, folio);
return ret;
}
static void ext4_readahead(struct readahead_control *rac)
{
struct inode *inode = rac->mapping->host;
/* If the file has inline data, no need to do readahead. */
if (ext4_has_inline_data(inode))
return;
ext4_mpage_readpages(inode, rac, NULL);
}
static void ext4_invalidate_folio(struct folio *folio, size_t offset,
size_t length)
{
trace_ext4_invalidate_folio(folio, offset, length);
/* No journalling happens on data buffers when this function is used */
WARN_ON(folio_buffers(folio) && buffer_jbd(folio_buffers(folio)));
block_invalidate_folio(folio, offset, length);
}
static int __ext4_journalled_invalidate_folio(struct folio *folio,
size_t offset, size_t length)
{
journal_t *journal = EXT4_JOURNAL(folio->mapping->host);
trace_ext4_journalled_invalidate_folio(folio, offset, length);
/*
* If it's a full truncate we just forget about the pending dirtying
*/
if (offset == 0 && length == folio_size(folio))
folio_clear_checked(folio);
return jbd2_journal_invalidate_folio(journal, folio, offset, length);
}
/* Wrapper for aops... */
static void ext4_journalled_invalidate_folio(struct folio *folio,
size_t offset,
size_t length)
{
WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0);
}
static bool ext4_release_folio(struct folio *folio, gfp_t wait)
{
journal_t *journal = EXT4_JOURNAL(folio->mapping->host);
trace_ext4_releasepage(&folio->page);
/* Page has dirty journalled data -> cannot release */
if (folio_test_checked(folio))
return false;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, folio);
else
return try_to_free_buffers(folio);
}
static bool ext4_inode_datasync_dirty(struct inode *inode)
{
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
if (journal) {
if (jbd2_transaction_committed(journal,
EXT4_I(inode)->i_datasync_tid))
return false;
if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
return !list_empty(&EXT4_I(inode)->i_fc_list);
return true;
}
/* Any metadata buffers to write? */
if (!list_empty(&inode->i_mapping->private_list))
return true;
return inode->i_state & I_DIRTY_DATASYNC;
}
static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
struct ext4_map_blocks *map, loff_t offset,
loff_t length, unsigned int flags)
{
u8 blkbits = inode->i_blkbits;
/*
* Writes that span EOF might trigger an I/O size update on completion,
* so consider them to be dirty for the purpose of O_DSYNC, even if
* there is no other metadata changes being made or are pending.
*/
iomap->flags = 0;
if (ext4_inode_datasync_dirty(inode) ||
offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
if (map->m_flags & EXT4_MAP_NEW)
iomap->flags |= IOMAP_F_NEW;
if (flags & IOMAP_DAX)
iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
else
iomap->bdev = inode->i_sb->s_bdev;
iomap->offset = (u64) map->m_lblk << blkbits;
iomap->length = (u64) map->m_len << blkbits;
if ((map->m_flags & EXT4_MAP_MAPPED) &&
!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
iomap->flags |= IOMAP_F_MERGED;
/*
* Flags passed to ext4_map_blocks() for direct I/O writes can result
* in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits
* set. In order for any allocated unwritten extents to be converted
* into written extents correctly within the ->end_io() handler, we
* need to ensure that the iomap->type is set appropriately. Hence, the
* reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has
* been set first.
*/
if (map->m_flags & EXT4_MAP_UNWRITTEN) {
iomap->type = IOMAP_UNWRITTEN;
iomap->addr = (u64) map->m_pblk << blkbits;
if (flags & IOMAP_DAX)
iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
} else if (map->m_flags & EXT4_MAP_MAPPED) {
iomap->type = IOMAP_MAPPED;
iomap->addr = (u64) map->m_pblk << blkbits;
if (flags & IOMAP_DAX)
iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
} else {
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
}
}
static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
unsigned int flags)
{
handle_t *handle;
u8 blkbits = inode->i_blkbits;
int ret, dio_credits, m_flags = 0, retries = 0;
/*
* Trim the mapping request to the maximum value that we can map at
* once for direct I/O.
*/
if (map->m_len > DIO_MAX_BLOCKS)
map->m_len = DIO_MAX_BLOCKS;
dio_credits = ext4_chunk_trans_blocks(inode, map->m_len);
retry:
/*
* Either we allocate blocks and then don't get an unwritten extent, so
* in that case we have reserved enough credits. Or, the blocks are
* already allocated and unwritten. In that case, the extent conversion
* fits into the credits as well.
*/
handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
if (IS_ERR(handle))
return PTR_ERR(handle);
/*
* DAX and direct I/O are the only two operations that are currently
* supported with IOMAP_WRITE.
*/
WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
if (flags & IOMAP_DAX)
m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
/*
* We use i_size instead of i_disksize here because delalloc writeback
* can complete at any point during the I/O and subsequently push the
* i_disksize out to i_size. This could be beyond where direct I/O is
* happening and thus expose allocated blocks to direct I/O reads.
*/
else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode))
m_flags = EXT4_GET_BLOCKS_CREATE;
else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
ret = ext4_map_blocks(handle, inode, map, m_flags);
/*
* We cannot fill holes in indirect tree based inodes as that could
* expose stale data in the case of a crash. Use the magic error code
* to fallback to buffered I/O.
*/
if (!m_flags && !ret)
ret = -ENOTBLK;
ext4_journal_stop(handle);
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
return ret;
}
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
int ret;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
return -ERANGE;
/*
* Calculate the first and last logical blocks respectively.
*/
map.m_lblk = offset >> blkbits;
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
if (flags & IOMAP_WRITE) {
/*
* We check here if the blocks are already allocated, then we
* don't need to start a journal txn and we can directly return
* the mapping information. This could boost performance
* especially in multi-threaded overwrite requests.
*/
if (offset + length <= i_size_read(inode)) {
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret > 0 && (map.m_flags & EXT4_MAP_MAPPED))
goto out;
}
ret = ext4_iomap_alloc(inode, &map, flags);
} else {
ret = ext4_map_blocks(NULL, inode, &map, 0);
}
if (ret < 0)
return ret;
out:
/*
* When inline encryption is enabled, sometimes I/O to an encrypted file
* has to be broken up to guarantee DUN contiguity. Handle this by
* limiting the length of the mapping returned.
*/
map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
ext4_set_iomap(inode, iomap, &map, offset, length, flags);
return 0;
}
static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
loff_t length, unsigned flags, struct iomap *iomap,
struct iomap *srcmap)
{
int ret;
/*
* Even for writes we don't need to allocate blocks, so just pretend
* we are reading to save overhead of starting a transaction.
*/
flags &= ~IOMAP_WRITE;
ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
WARN_ON_ONCE(iomap->type != IOMAP_MAPPED);
return ret;
}
static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
/*
* Check to see whether an error occurred while writing out the data to
* the allocated blocks. If so, return the magic error code so that we
* fallback to buffered I/O and attempt to complete the remainder of
* the I/O. Any blocks that may have been allocated in preparation for
* the direct I/O will be reused during buffered I/O.
*/
if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0)
return -ENOTBLK;
return 0;
}
const struct iomap_ops ext4_iomap_ops = {
.iomap_begin = ext4_iomap_begin,
.iomap_end = ext4_iomap_end,
};
const struct iomap_ops ext4_iomap_overwrite_ops = {
.iomap_begin = ext4_iomap_overwrite_begin,
.iomap_end = ext4_iomap_end,
};
static bool ext4_iomap_is_delalloc(struct inode *inode,
struct ext4_map_blocks *map)
{
struct extent_status es;
ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
map->m_lblk, end, &es);
if (!es.es_len || es.es_lblk > end)
return false;
if (es.es_lblk > map->m_lblk) {
map->m_len = es.es_lblk - map->m_lblk;
return false;
}
offset = map->m_lblk - es.es_lblk;
map->m_len = es.es_len - offset;
return true;
}
static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
loff_t length, unsigned int flags,
struct iomap *iomap, struct iomap *srcmap)
{
int ret;
bool delalloc = false;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
if (ext4_has_inline_data(inode)) {
ret = ext4_inline_data_iomap(inode, iomap);
if (ret != -EAGAIN) {
if (ret == 0 && offset >= iomap->length)
ret = -ENOENT;
return ret;
}
}
/*
* Calculate the first and last logical block respectively.
*/
map.m_lblk = offset >> blkbits;
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
/*
* Fiemap callers may call for offset beyond s_bitmap_maxbytes.
* So handle it here itself instead of querying ext4_map_blocks().
* Since ext4_map_blocks() will warn about it and will return
* -EIO error.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (offset >= sbi->s_bitmap_maxbytes) {
map.m_flags = 0;
goto set_iomap;
}
}
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret < 0)
return ret;
if (ret == 0)
delalloc = ext4_iomap_is_delalloc(inode, &map);
set_iomap:
ext4_set_iomap(inode, iomap, &map, offset, length, flags);
if (delalloc && iomap->type == IOMAP_HOLE)
iomap->type = IOMAP_DELALLOC;
return 0;
}
const struct iomap_ops ext4_iomap_report_ops = {
.iomap_begin = ext4_iomap_begin_report,
};
/*
* For data=journal mode, folio should be marked dirty only when it was
* writeably mapped. When that happens, it was already attached to the
* transaction and marked as jbddirty (we take care of this in
* ext4_page_mkwrite()). On transaction commit, we writeprotect page mappings
* so we should have nothing to do here, except for the case when someone
* had the page pinned and dirtied the page through this pin (e.g. by doing
* direct IO to it). In that case we'd need to attach buffers here to the
* transaction but we cannot due to lock ordering. We cannot just dirty the
* folio and leave attached buffers clean, because the buffers' dirty state is
* "definitive". We cannot just set the buffers dirty or jbddirty because all
* the journalling code will explode. So what we do is to mark the folio
* "pending dirty" and next time ext4_writepages() is called, attach buffers
* to the transaction appropriately.
*/
static bool ext4_journalled_dirty_folio(struct address_space *mapping,
struct folio *folio)
{
WARN_ON_ONCE(!folio_buffers(folio));
if (folio_maybe_dma_pinned(folio))
folio_set_checked(folio);
return filemap_dirty_folio(mapping, folio);
}
static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio)
{
WARN_ON_ONCE(!folio_test_locked(folio) && !folio_test_dirty(folio));
WARN_ON_ONCE(!folio_buffers(folio));
return block_dirty_folio(mapping, folio);
}
static int ext4_iomap_swap_activate(struct swap_info_struct *sis,
struct file *file, sector_t *span)
{
return iomap_swapfile_activate(sis, file, span,
&ext4_iomap_report_ops);
}
static const struct address_space_operations ext4_aops = {
.read_folio = ext4_read_folio,
.readahead = ext4_readahead,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_write_end,
.dirty_folio = ext4_dirty_folio,
.bmap = ext4_bmap,
.invalidate_folio = ext4_invalidate_folio,
.release_folio = ext4_release_folio,
.direct_IO = noop_direct_IO,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_journalled_aops = {
.read_folio = ext4_read_folio,
.readahead = ext4_readahead,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.dirty_folio = ext4_journalled_dirty_folio,
.bmap = ext4_bmap,
.invalidate_folio = ext4_journalled_invalidate_folio,
.release_folio = ext4_release_folio,
.direct_IO = noop_direct_IO,
.migrate_folio = buffer_migrate_folio_norefs,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_da_aops = {
.read_folio = ext4_read_folio,
.readahead = ext4_readahead,
.writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.dirty_folio = ext4_dirty_folio,
.bmap = ext4_bmap,
.invalidate_folio = ext4_invalidate_folio,
.release_folio = ext4_release_folio,
.direct_IO = noop_direct_IO,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_dax_aops = {
.writepages = ext4_dax_writepages,
.direct_IO = noop_direct_IO,
.dirty_folio = noop_dirty_folio,
.bmap = ext4_bmap,
.swap_activate = ext4_iomap_swap_activate,
};
void ext4_set_aops(struct inode *inode)
{
switch (ext4_inode_journal_mode(inode)) {
case EXT4_INODE_ORDERED_DATA_MODE:
case EXT4_INODE_WRITEBACK_DATA_MODE:
break;
case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
return;
default:
BUG();
}
if (IS_DAX(inode))
inode->i_mapping->a_ops = &ext4_dax_aops;
else if (test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else
inode->i_mapping->a_ops = &ext4_aops;
}
static int __ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
ext4_fsblk_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize, pos;
ext4_lblk_t iblock;
struct inode *inode = mapping->host;
struct buffer_head *bh;
struct folio *folio;
int err = 0;
folio = __filemap_get_folio(mapping, from >> PAGE_SHIFT,
FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
mapping_gfp_constraint(mapping, ~__GFP_FS));
if (!folio)
return -ENOMEM;
blocksize = inode->i_sb->s_blocksize;
iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
bh = folio_buffers(folio);
if (!bh) {
create_empty_buffers(&folio->page, blocksize, 0);
bh = folio_buffers(folio);
}
/* Find the buffer that contains "offset" */
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
if (buffer_freed(bh)) {
BUFFER_TRACE(bh, "freed: skip");
goto unlock;
}
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "unmapped");
ext4_get_block(inode, iblock, bh, 0);
/* unmapped? It's a hole - nothing to do */
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "still unmapped");
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)) {
err = ext4_read_bh_lock(bh, 0, true);
if (err)
goto unlock;
if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
err = fscrypt_decrypt_pagecache_blocks(folio,
blocksize,
bh_offset(bh));
if (err) {
clear_buffer_uptodate(bh);
goto unlock;
}
}
}
if (ext4_should_journal_data(inode)) {
BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
if (err)
goto unlock;
}
folio_zero_range(folio, offset, length);
BUFFER_TRACE(bh, "zeroed end of block");
if (ext4_should_journal_data(inode)) {
err = ext4_dirty_journalled_data(handle, bh);
} else {
err = 0;
mark_buffer_dirty(bh);
if (ext4_should_order_data(inode))
err = ext4_jbd2_inode_add_write(handle, inode, from,
length);
}
unlock:
folio_unlock(folio);
folio_put(folio);
return err;
}
/*
* ext4_block_zero_page_range() zeros out a mapping of length 'length'
* starting from file offset 'from'. The range to be zero'd must
* be contained with in one block. If the specified range exceeds
* the end of the block it will be shortened to end of the block
* that corresponds to 'from'
*/
static int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
struct inode *inode = mapping->host;
unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize = inode->i_sb->s_blocksize;
unsigned max = blocksize - (offset & (blocksize - 1));
/*
* correct length if it does not fall between
* 'from' and the end of the block
*/
if (length > max || length < 0)
length = max;
if (IS_DAX(inode)) {
return dax_zero_range(inode, from, length, NULL,
&ext4_iomap_ops);
}
return __ext4_block_zero_page_range(handle, mapping, from, length);
}
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
* This required during truncate. We need to physically zero the tail end
* of that block so it doesn't yield old data if the file is later grown.
*/
static int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from)
{
unsigned offset = from & (PAGE_SIZE-1);
unsigned length;
unsigned blocksize;
struct inode *inode = mapping->host;
/* If we are processing an encrypted inode during orphan list handling */
if (IS_ENCRYPTED(inode) && !fscrypt_has_encryption_key(inode))
return 0;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
return ext4_block_zero_page_range(handle, mapping, from, length);
}
int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t length)
{
struct super_block *sb = inode->i_sb;
struct address_space *mapping = inode->i_mapping;
unsigned partial_start, partial_end;
ext4_fsblk_t start, end;
loff_t byte_end = (lstart + length - 1);
int err = 0;
partial_start = lstart & (sb->s_blocksize - 1);
partial_end = byte_end & (sb->s_blocksize - 1);
start = lstart >> sb->s_blocksize_bits;
end = byte_end >> sb->s_blocksize_bits;
/* Handle partial zero within the single block */
if (start == end &&
(partial_start || (partial_end != sb->s_blocksize - 1))) {
err = ext4_block_zero_page_range(handle, mapping,
lstart, length);
return err;
}
/* Handle partial zero out on the start of the range */
if (partial_start) {
err = ext4_block_zero_page_range(handle, mapping,
lstart, sb->s_blocksize);
if (err)
return err;
}
/* Handle partial zero out on the end of the range */
if (partial_end != sb->s_blocksize - 1)
err = ext4_block_zero_page_range(handle, mapping,
byte_end - partial_end,
partial_end + 1);
return err;
}
int ext4_can_truncate(struct inode *inode)
{
if (S_ISREG(inode->i_mode))
return 1;
if (S_ISDIR(inode->i_mode))
return 1;
if (S_ISLNK(inode->i_mode))
return !ext4_inode_is_fast_symlink(inode);
return 0;
}
/*
* We have to make sure i_disksize gets properly updated before we truncate
* page cache due to hole punching or zero range. Otherwise i_disksize update
* can get lost as it may have been postponed to submission of writeback but
* that will never happen after we truncate page cache.
*/
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
loff_t len)
{
handle_t *handle;
int ret;
loff_t size = i_size_read(inode);
WARN_ON(!inode_is_locked(inode));
if (offset > size || offset + len < size)
return 0;
if (EXT4_I(inode)->i_disksize >= size)
return 0;
handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_update_i_disksize(inode, size);
ret = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
return ret;
}
static void ext4_wait_dax_page(struct inode *inode)
{
filemap_invalidate_unlock(inode->i_mapping);
schedule();
filemap_invalidate_lock(inode->i_mapping);
}
int ext4_break_layouts(struct inode *inode)
{
struct page *page;
int error;
if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
return -EINVAL;
do {
page = dax_layout_busy_page(inode->i_mapping);
if (!page)
return 0;
error = ___wait_var_event(&page->_refcount,
atomic_read(&page->_refcount) == 1,
TASK_INTERRUPTIBLE, 0, 0,
ext4_wait_dax_page(inode));
} while (error == 0);
return error;
}
/*
* ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
*
* @inode: File inode
* @offset: The offset where the hole will begin
* @len: The length of the hole
*
* Returns: 0 on success or negative on failure
*/
int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
ext4_lblk_t first_block, stop_block;
struct address_space *mapping = inode->i_mapping;
loff_t first_block_offset, last_block_offset, max_length;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
handle_t *handle;
unsigned int credits;
int ret = 0, ret2 = 0;
trace_ext4_punch_hole(inode, offset, length, 0);
/*
* Write out all dirty pages to avoid race conditions
* Then release them.
*/
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
ret = filemap_write_and_wait_range(mapping, offset,
offset + length - 1);
if (ret)
return ret;
}
inode_lock(inode);
/* No need to punch hole beyond i_size */
if (offset >= inode->i_size)
goto out_mutex;
/*
* If the hole extends beyond i_size, set the hole
* to end after the page that contains i_size
*/
if (offset + length > inode->i_size) {
length = inode->i_size +
PAGE_SIZE - (inode->i_size & (PAGE_SIZE - 1)) -
offset;
}
/*
* For punch hole the length + offset needs to be within one block
* before last range. Adjust the length if it goes beyond that limit.
*/
max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize;
if (offset + length > max_length)
length = max_length - offset;
if (offset & (sb->s_blocksize - 1) ||
(offset + length) & (sb->s_blocksize - 1)) {
/*
* Attach jinode to inode for jbd2 if we do any zeroing of
* partial block
*/
ret = ext4_inode_attach_jinode(inode);
if (ret < 0)
goto out_mutex;
}
/* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
ret = file_modified(file);
if (ret)
goto out_mutex;
/*
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
goto out_dio;
first_block_offset = round_up(offset, sb->s_blocksize);
last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
/* Now release the pages and zero block aligned part of pages*/
if (last_block_offset > first_block_offset) {
ret = ext4_update_disksize_before_punch(inode, offset, length);
if (ret)
goto out_dio;
truncate_pagecache_range(inode, first_block_offset,
last_block_offset);
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
else
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_std_error(sb, ret);
goto out_dio;
}
ret = ext4_zero_partial_blocks(handle, inode, offset,
length);
if (ret)
goto out_stop;
first_block = (offset + sb->s_blocksize - 1) >>
EXT4_BLOCK_SIZE_BITS(sb);
stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
/* If there are blocks to remove, do it */
if (stop_block > first_block) {
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode, 0);
ret = ext4_es_remove_extent(inode, first_block,
stop_block - first_block);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_remove_space(inode, first_block,
stop_block - 1);
else
ret = ext4_ind_remove_space(handle, inode, first_block,
stop_block);
up_write(&EXT4_I(inode)->i_data_sem);
}
ext4_fc_track_range(handle, inode, first_block, stop_block);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = current_time(inode);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret2))
ret = ret2;
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
out_dio:
filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
}
int ext4_inode_attach_jinode(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct jbd2_inode *jinode;
if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal)
return 0;
jinode = jbd2_alloc_inode(GFP_KERNEL);
spin_lock(&inode->i_lock);
if (!ei->jinode) {
if (!jinode) {
spin_unlock(&inode->i_lock);
return -ENOMEM;
}
ei->jinode = jinode;
jbd2_journal_init_jbd_inode(ei->jinode, inode);
jinode = NULL;
}
spin_unlock(&inode->i_lock);
if (unlikely(jinode != NULL))
jbd2_free_inode(jinode);
return 0;
}
/*
* ext4_truncate()
*
* We block out ext4_get_block() block instantiations across the entire
* transaction, and VFS/VM ensures that ext4_truncate() cannot run
* simultaneously on behalf of the same inode.
*
* As we work through the truncate and commit bits of it to the journal there
* is one core, guiding principle: the file's tree must always be consistent on
* disk. We must be able to restart the truncate after a crash.
*
* The file's tree may be transiently inconsistent in memory (although it
* probably isn't), but whenever we close off and commit a journal transaction,
* the contents of (the filesystem + the journal) must be consistent and
* restartable. It's pretty simple, really: bottom up, right to left (although
* left-to-right works OK too).
*
* Note that at recovery time, journal replay occurs *before* the restart of
* truncate against the orphan inode list.
*
* The committed inode has the new, desired i_size (which is the same as
* i_disksize in this case). After a crash, ext4_orphan_cleanup() will see
* that this inode's truncate did not complete and it will again call
* ext4_truncate() to have another go. So there will be instantiated blocks
* to the right of the truncation point in a crashed ext4 filesystem. But
* that's fine - as long as they are linked from the inode, the post-crash
* ext4_truncate() run will find them and release them.
*/
int ext4_truncate(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int credits;
int err = 0, err2;
handle_t *handle;
struct address_space *mapping = inode->i_mapping;
/*
* There is a possibility that we're either freeing the inode
* or it's a completely new inode. In those cases we might not
* have i_rwsem locked because it's not necessary.
*/
if (!(inode->i_state & (I_NEW|I_FREEING)))
WARN_ON(!inode_is_locked(inode));
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
goto out_trace;
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
if (ext4_has_inline_data(inode)) {
int has_inline = 1;
err = ext4_inline_data_truncate(inode, &has_inline);
if (err || has_inline)
goto out_trace;
}
/* If we zero-out tail of the page, we have to create jinode for jbd2 */
if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
err = ext4_inode_attach_jinode(inode);
if (err)
goto out_trace;
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
else
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out_trace;
}
if (inode->i_size & (inode->i_sb->s_blocksize - 1))
ext4_block_truncate_page(handle, mapping, inode->i_size);
/*
* We add the inode to the orphan list, so that if this
* truncate spans multiple transactions, and we crash, we will
* resume the truncate when the filesystem recovers. It also
* marks the inode dirty, to catch the new size.
*
* Implication: the file must always be in a sane, consistent
* truncatable state while each transaction commits.
*/
err = ext4_orphan_add(handle, inode);
if (err)
goto out_stop;
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode, 0);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
err = ext4_ext_truncate(handle, inode);
else
ext4_ind_truncate(handle, inode);
up_write(&ei->i_data_sem);
if (err)
goto out_stop;
if (IS_SYNC(inode))
ext4_handle_sync(handle);
out_stop:
/*
* If this was a simple ftruncate() and the file will remain alive,
* then we need to clear up the orphan record which we created above.
* However, if this was a real unlink then we were called by
* ext4_evict_inode(), and we allow that function to clean up the
* orphan info for us.
*/
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
inode->i_mtime = inode->i_ctime = current_time(inode);
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2 && !err))
err = err2;
ext4_journal_stop(handle);
out_trace:
trace_ext4_truncate_exit(inode);
return err;
}
static inline u64 ext4_inode_peek_iversion(const struct inode *inode)
{
if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
return inode_peek_iversion_raw(inode);
else
return inode_peek_iversion(inode);
}
static int ext4_inode_blocks_set(struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
struct inode *inode = &(ei->vfs_inode);
u64 i_blocks = READ_ONCE(inode->i_blocks);
struct super_block *sb = inode->i_sb;
if (i_blocks <= ~0U) {
/*
* i_blocks can be represented in a 32 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = 0;
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
return 0;
}
/*
* This should never happen since sb->s_maxbytes should not have
* allowed this, sb->s_maxbytes was set according to the huge_file
* feature in ext4_fill_super().
*/
if (!ext4_has_feature_huge_file(sb))
return -EFSCORRUPTED;
if (i_blocks <= 0xffffffffffffULL) {
/*
* i_blocks can be represented in a 48 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
} else {
ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE);
/* i_block is stored in file system block size */
i_blocks = i_blocks >> (inode->i_blkbits - 9);
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
}
return 0;
}
static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
uid_t i_uid;
gid_t i_gid;
projid_t i_projid;
int block;
int err;
err = ext4_inode_blocks_set(raw_inode, ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
i_uid = i_uid_read(inode);
i_gid = i_gid_read(inode);
i_projid = from_kprojid(&init_user_ns, ei->i_projid);
if (!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid));
raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid));
/*
* Fix up interoperability with old kernels. Otherwise,
* old inodes get re-used with the upper 16 bits of the
* uid/gid intact.
*/
if (ei->i_dtime && list_empty(&ei->i_orphan)) {
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
} else {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(i_gid));
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid));
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
ext4_isize_set(raw_inode, ei->i_disksize);
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
raw_inode->i_block[0] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
raw_inode->i_block[1] = 0;
} else {
raw_inode->i_block[0] = 0;
raw_inode->i_block[1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
raw_inode->i_block[2] = 0;
}
} else if (!ext4_has_inline_data(inode)) {
for (block = 0; block < EXT4_N_BLOCKS; block++)
raw_inode->i_block[block] = ei->i_data[block];
}
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
u64 ivers = ext4_inode_peek_iversion(inode);
raw_inode->i_disk_version = cpu_to_le32(ivers);
if (ei->i_extra_isize) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
raw_inode->i_version_hi =
cpu_to_le32(ivers >> 32);
raw_inode->i_extra_isize =
cpu_to_le16(ei->i_extra_isize);
}
}
if (i_projid != EXT4_DEF_PROJID &&
!ext4_has_feature_project(inode->i_sb))
err = err ?: -EFSCORRUPTED;
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
raw_inode->i_projid = cpu_to_le32(i_projid);
ext4_inode_csum_set(inode, raw_inode, ei);
return err;
}
/*
* ext4_get_inode_loc returns with an extra refcount against the inode's
* underlying buffer_head on success. If we pass 'inode' and it does not
* have in-inode xattr, we have all inode data in memory that is needed
* to recreate the on-disk version of this inode.
*/
static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
struct inode *inode, struct ext4_iloc *iloc,
ext4_fsblk_t *ret_block)
{
struct ext4_group_desc *gdp;
struct buffer_head *bh;
ext4_fsblk_t block;
struct blk_plug plug;
int inodes_per_block, inode_offset;
iloc->bh = NULL;
if (ino < EXT4_ROOT_INO ||
ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return -EFSCORRUPTED;
iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
if (!gdp)
return -EIO;
/*
* Figure out the offset within the block group inode table
*/
inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
inode_offset = ((ino - 1) %
EXT4_INODES_PER_GROUP(sb));
iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
block = ext4_inode_table(sb, gdp);
if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) ||
(block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) {
ext4_error(sb, "Invalid inode table block %llu in "
"block_group %u", block, iloc->block_group);
return -EFSCORRUPTED;
}
block += (inode_offset / inodes_per_block);
bh = sb_getblk(sb, block);
if (unlikely(!bh))
return -ENOMEM;
if (ext4_buffer_uptodate(bh))
goto has_buffer;
lock_buffer(bh);
if (ext4_buffer_uptodate(bh)) {
/* Someone brought it uptodate while we waited */
unlock_buffer(bh);
goto has_buffer;
}
/*
* If we have all information of the inode in memory and this
* is the only valid inode in the block, we need not read the
* block.
*/
if (inode && !ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
struct buffer_head *bitmap_bh;
int i, start;
start = inode_offset & ~(inodes_per_block - 1);
/* Is the inode bitmap in cache? */
bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
if (unlikely(!bitmap_bh))
goto make_io;
/*
* If the inode bitmap isn't in cache then the
* optimisation may end up performing two reads instead
* of one, so skip it.
*/
if (!buffer_uptodate(bitmap_bh)) {
brelse(bitmap_bh);
goto make_io;
}
for (i = start; i < start + inodes_per_block; i++) {
if (i == inode_offset)
continue;
if (ext4_test_bit(i, bitmap_bh->b_data))
break;
}
brelse(bitmap_bh);
if (i == start + inodes_per_block) {
struct ext4_inode *raw_inode =
(struct ext4_inode *) (bh->b_data + iloc->offset);
/* all other inodes are free, so skip I/O */
memset(bh->b_data, 0, bh->b_size);
if (!ext4_test_inode_state(inode, EXT4_STATE_NEW))
ext4_fill_raw_inode(inode, raw_inode);
set_buffer_uptodate(bh);
unlock_buffer(bh);
goto has_buffer;
}
}
make_io:
/*
* If we need to do any I/O, try to pre-readahead extra
* blocks from the inode table.
*/
blk_start_plug(&plug);
if (EXT4_SB(sb)->s_inode_readahead_blks) {
ext4_fsblk_t b, end, table;
unsigned num;
__u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks;
table = ext4_inode_table(sb, gdp);
/* s_inode_readahead_blks is always a power of 2 */
b = block & ~((ext4_fsblk_t) ra_blks - 1);
if (table > b)
b = table;
end = b + ra_blks;
num = EXT4_INODES_PER_GROUP(sb);
if (ext4_has_group_desc_csum(sb))
num -= ext4_itable_unused_count(sb, gdp);
table += num / inodes_per_block;
if (end > table)
end = table;
while (b <= end)
ext4_sb_breadahead_unmovable(sb, b++);
}
/*
* There are other valid inodes in the buffer, this inode
* has in-inode xattrs, or we don't have this inode in memory.
* Read the block from disk.
*/
trace_ext4_load_inode(sb, ino);
ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
blk_finish_plug(&plug);
wait_on_buffer(bh);
ext4_simulate_fail_bh(sb, bh, EXT4_SIM_INODE_EIO);
if (!buffer_uptodate(bh)) {
if (ret_block)
*ret_block = block;
brelse(bh);
return -EIO;
}
has_buffer:
iloc->bh = bh;
return 0;
}
static int __ext4_get_inode_loc_noinmem(struct inode *inode,
struct ext4_iloc *iloc)
{
ext4_fsblk_t err_blk = 0;
int ret;
ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, NULL, iloc,
&err_blk);
if (ret == -EIO)
ext4_error_inode_block(inode, err_blk, EIO,
"unable to read itable block");
return ret;
}
int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
{
ext4_fsblk_t err_blk = 0;
int ret;
ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, inode, iloc,
&err_blk);
if (ret == -EIO)
ext4_error_inode_block(inode, err_blk, EIO,
"unable to read itable block");
return ret;
}
int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
struct ext4_iloc *iloc)
{
return __ext4_get_inode_loc(sb, ino, NULL, iloc, NULL);
}
static bool ext4_should_enable_dax(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (test_opt2(inode->i_sb, DAX_NEVER))
return false;
if (!S_ISREG(inode->i_mode))
return false;
if (ext4_should_journal_data(inode))
return false;
if (ext4_has_inline_data(inode))
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT))
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
return false;
if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
return false;
if (test_opt(inode->i_sb, DAX_ALWAYS))
return true;
return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
}
void ext4_set_inode_flags(struct inode *inode, bool init)
{
unsigned int flags = EXT4_I(inode)->i_flags;
unsigned int new_fl = 0;
WARN_ON_ONCE(IS_DAX(inode) && init);
if (flags & EXT4_SYNC_FL)
new_fl |= S_SYNC;
if (flags & EXT4_APPEND_FL)
new_fl |= S_APPEND;
if (flags & EXT4_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & EXT4_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
/* Because of the way inode_set_flags() works we must preserve S_DAX
* here if already set. */
new_fl |= (inode->i_flags & S_DAX);
if (init && ext4_should_enable_dax(inode))
new_fl |= S_DAX;
if (flags & EXT4_ENCRYPT_FL)
new_fl |= S_ENCRYPTED;
if (flags & EXT4_CASEFOLD_FL)
new_fl |= S_CASEFOLD;
if (flags & EXT4_VERITY_FL)
new_fl |= S_VERITY;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX|
S_ENCRYPTED|S_CASEFOLD|S_VERITY);
}
static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
blkcnt_t i_blocks ;
struct inode *inode = &(ei->vfs_inode);
struct super_block *sb = inode->i_sb;
if (ext4_has_feature_huge_file(sb)) {
/* we are using combined 48 bit field */
i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
le32_to_cpu(raw_inode->i_blocks_lo);
if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) {
/* i_blocks represent file system block size */
return i_blocks << (inode->i_blkbits - 9);
} else {
return i_blocks;
}
} else {
return le32_to_cpu(raw_inode->i_blocks_lo);
}
}
static inline int ext4_iget_extra_inode(struct inode *inode,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
if (EXT4_INODE_HAS_XATTR_SPACE(inode) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
int err;
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
err = ext4_find_inline_data_nolock(inode);
if (!err && ext4_has_inline_data(inode))
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
return err;
} else
EXT4_I(inode)->i_inline_off = 0;
return 0;
}
int ext4_get_projid(struct inode *inode, kprojid_t *projid)
{
if (!ext4_has_feature_project(inode->i_sb))
return -EOPNOTSUPP;
*projid = EXT4_I(inode)->i_projid;
return 0;
}
/*
* ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of
* refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag
* set.
*/
static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
{
if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
inode_set_iversion_raw(inode, val);
else
inode_set_iversion_queried(inode, val);
}
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ext4_iget_flags flags, const char *function,
unsigned int line)
{
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct inode *inode;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
loff_t size;
int block;
uid_t i_uid;
gid_t i_gid;
projid_t i_projid;
if ((!(flags & EXT4_IGET_SPECIAL) &&
((ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) ||
ino == le32_to_cpu(es->s_usr_quota_inum) ||
ino == le32_to_cpu(es->s_grp_quota_inum) ||
ino == le32_to_cpu(es->s_prj_quota_inum) ||
ino == le32_to_cpu(es->s_orphan_file_inum))) ||
(ino < EXT4_ROOT_INO) ||
(ino > le32_to_cpu(es->s_inodes_count))) {
if (flags & EXT4_IGET_HANDLE)
return ERR_PTR(-ESTALE);
__ext4_error(sb, function, line, false, EFSCORRUPTED, 0,
"inode #%lu: comm %s: iget: illegal inode #",
ino, current->comm);
return ERR_PTR(-EFSCORRUPTED);
}
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
ei = EXT4_I(inode);
iloc.bh = NULL;
ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
if (ret < 0)
goto bad_inode;
raw_inode = ext4_raw_inode(&iloc);
if ((flags & EXT4_IGET_HANDLE) &&
(raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) {
ret = -ESTALE;
goto bad_inode;
}
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb) ||
(ei->i_extra_isize & 3)) {
ext4_error_inode(inode, function, line, 0,
"iget: bad extra_isize %u "
"(inode size %u)",
ei->i_extra_isize,
EXT4_INODE_SIZE(inode->i_sb));
ret = -EFSCORRUPTED;
goto bad_inode;
}
} else
ei->i_extra_isize = 0;
/* Precompute checksum seed for inode metadata */
if (ext4_has_metadata_csum(sb)) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__le32 inum = cpu_to_le32(inode->i_ino);
__le32 gen = raw_inode->i_generation;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum,
sizeof(inum));
ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen,
sizeof(gen));
}
if ((!ext4_inode_csum_verify(inode, raw_inode, ei) ||
ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) &&
(!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
ext4_error_inode_err(inode, function, line, 0,
EFSBADCRC, "iget: checksum invalid");
ret = -EFSBADCRC;
goto bad_inode;
}
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
if (ext4_has_feature_project(sb) &&
EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
else
i_projid = EXT4_DEF_PROJID;
if (!(test_opt(inode->i_sb, NO_UID32))) {
i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
i_uid_write(inode, i_uid);
i_gid_write(inode, i_gid);
ei->i_projid = make_kprojid(&init_user_ns, i_projid);
set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
ei->i_inline_off = 0;
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
* This is needed because nfsd might try to access dead inodes
* the test is that same one that e2fsck uses
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0) {
if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
ino != EXT4_BOOT_LOADER_INO) {
/* this inode is deleted or unallocated */
if (flags & EXT4_IGET_SPECIAL) {
ext4_error_inode(inode, function, line, 0,
"iget: special inode unallocated");
ret = -EFSCORRUPTED;
} else
ret = -ESTALE;
goto bad_inode;
}
/* The only unlinked inodes we let through here have
* valid i_mode and are being read by the orphan
* recovery code: that's fine, we're about to complete
* the process of deleting those.
* OR it is the EXT4_BOOT_LOADER_INO which is
* not initialized on a new filesystem. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
ext4_set_inode_flags(inode, true);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (ext4_has_feature_64bit(sb))
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(sb, raw_inode);
if ((size = i_size_read(inode)) < 0) {
ext4_error_inode(inode, function, line, 0,
"iget: bad i_size value: %lld", size);
ret = -EFSCORRUPTED;
goto bad_inode;
}
/*
* If dir_index is not enabled but there's dir with INDEX flag set,
* we'd normally treat htree data as empty space. But with metadata
* checksumming that corrupts checksums so forbid that.
*/
if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) &&
ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
ext4_error_inode(inode, function, line, 0,
"iget: Dir with htree data on filesystem without dir_index feature.");
ret = -EFSCORRUPTED;
goto bad_inode;
}
ei->i_disksize = inode->i_size;
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
#endif
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
ei->i_last_alloc_group = ~0;
/*
* NOTE! The in-memory inode i_data array is in little-endian order
* even on big-endian machines: we do NOT byteswap the block numbers!
*/
for (block = 0; block < EXT4_N_BLOCKS; block++)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
ext4_fc_init_inode(&ei->vfs_inode);
/*
* Set transaction id's of transactions that have to be committed
* to finish f[data]sync. We set them to currently running transaction
* as we cannot be sure that the inode or some of its metadata isn't
* part of the transaction - the inode could have been reclaimed and
* now it is reread from disk.
*/
if (journal) {
transaction_t *transaction;
tid_t tid;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction)
transaction = journal->j_running_transaction;
else
transaction = journal->j_committing_transaction;
if (transaction)
tid = transaction->t_tid;
else
tid = journal->j_commit_sequence;
read_unlock(&journal->j_state_lock);
ei->i_sync_tid = tid;
ei->i_datasync_tid = tid;
}
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
BUILD_BUG_ON(sizeof(struct ext4_inode) & 3);
ei->i_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
} else {
ret = ext4_iget_extra_inode(inode, raw_inode, ei);
if (ret)
goto bad_inode;
}
}
EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode);
EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
u64 ivers = le32_to_cpu(raw_inode->i_disk_version);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
ivers |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
ext4_inode_set_iversion_queried(inode, ivers);
}
ret = 0;
if (ei->i_file_acl &&
!ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
ext4_error_inode(inode, function, line, 0,
"iget: bad extended attribute block %llu",
ei->i_file_acl);
ret = -EFSCORRUPTED;
goto bad_inode;
} else if (!ext4_has_inline_data(inode)) {
/* validate the block references in the inode */
if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode)))) {
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_check_inode(inode);
else
ret = ext4_ind_check_inode(inode);
}
}
if (ret)
goto bad_inode;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
/* VFS does not allow setting these so must be corruption */
if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
ext4_error_inode(inode, function, line, 0,
"iget: immutable or append flags "
"not allowed on symlinks");
ret = -EFSCORRUPTED;
goto bad_inode;
}
if (IS_ENCRYPTED(inode)) {
inode->i_op = &ext4_encrypted_symlink_inode_operations;
} else if (ext4_inode_is_fast_symlink(inode)) {
inode->i_link = (char *)ei->i_data;
inode->i_op = &ext4_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
} else {
inode->i_op = &ext4_symlink_inode_operations;
}
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &ext4_special_inode_operations;
if (raw_inode->i_block[0])
init_special_inode(inode, inode->i_mode,
old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else if (ino == EXT4_BOOT_LOADER_INO) {
make_bad_inode(inode);
} else {
ret = -EFSCORRUPTED;
ext4_error_inode(inode, function, line, 0,
"iget: bogus i_mode (%o)", inode->i_mode);
goto bad_inode;
}
if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb))
ext4_error_inode(inode, function, line, 0,
"casefold flag without casefold feature");
if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) {
ext4_error_inode(inode, function, line, 0,
"bad inode without EXT4_IGET_BAD flag");
ret = -EUCLEAN;
goto bad_inode;
}
brelse(iloc.bh);
unlock_new_inode(inode);
return inode;
bad_inode:
brelse(iloc.bh);
iget_failed(inode);
return ERR_PTR(ret);
}
static void __ext4_update_other_inode_time(struct super_block *sb,
unsigned long orig_ino,
unsigned long ino,
struct ext4_inode *raw_inode)
{
struct inode *inode;
inode = find_inode_by_ino_rcu(sb, ino);
if (!inode)
return;
if (!inode_is_dirtytime_only(inode))
return;
spin_lock(&inode->i_lock);
if (inode_is_dirtytime_only(inode)) {
struct ext4_inode_info *ei = EXT4_I(inode);
inode->i_state &= ~I_DIRTY_TIME;
spin_unlock(&inode->i_lock);
spin_lock(&ei->i_raw_lock);
EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
ext4_inode_csum_set(inode, raw_inode, ei);
spin_unlock(&ei->i_raw_lock);
trace_ext4_other_inode_update_time(inode, orig_ino);
return;
}
spin_unlock(&inode->i_lock);
}
/*
* Opportunistically update the other time fields for other inodes in
* the same inode table block.
*/
static void ext4_update_other_inodes_time(struct super_block *sb,
unsigned long orig_ino, char *buf)
{
unsigned long ino;
int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
int inode_size = EXT4_INODE_SIZE(sb);
/*
* Calculate the first inode in the inode table block. Inode
* numbers are one-based. That is, the first inode in a block
* (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
*/
ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
rcu_read_lock();
for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
if (ino == orig_ino)
continue;
__ext4_update_other_inode_time(sb, orig_ino, ino,
(struct ext4_inode *)buf);
}
rcu_read_unlock();
}
/*
* Post the struct inode info into an on-disk inode location in the
* buffer-cache. This gobbles the caller's reference to the
* buffer_head in the inode location struct.
*
* The caller must have write access to iloc->bh.
*/
static int ext4_do_update_inode(handle_t *handle,
struct inode *inode,
struct ext4_iloc *iloc)
{
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
struct super_block *sb = inode->i_sb;
int err;
int need_datasync = 0, set_large_file = 0;
spin_lock(&ei->i_raw_lock);
/*
* For fields not tracked in the in-memory inode, initialise them
* to zero for new inodes.
*/
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode))
need_datasync = 1;
if (ei->i_disksize > 0x7fffffffULL) {
if (!ext4_has_feature_large_file(sb) ||
EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV))
set_large_file = 1;
}
err = ext4_fill_raw_inode(inode, raw_inode);
spin_unlock(&ei->i_raw_lock);
if (err) {
EXT4_ERROR_INODE(inode, "corrupted inode contents");
goto out_brelse;
}
if (inode->i_sb->s_flags & SB_LAZYTIME)
ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
bh->b_data);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
goto out_error;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
if (set_large_file) {
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
err = ext4_journal_get_write_access(handle, sb,
EXT4_SB(sb)->s_sbh,
EXT4_JTR_NONE);
if (err)
goto out_error;
lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_large_file(sb);
ext4_superblock_csum_set(sb);
unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_handle_sync(handle);
err = ext4_handle_dirty_metadata(handle, NULL,
EXT4_SB(sb)->s_sbh);
}
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_error:
ext4_std_error(inode->i_sb, err);
out_brelse:
brelse(bh);
return err;
}
/*
* ext4_write_inode()
*
* We are called from a few places:
*
* - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
* transaction to commit.
*
* - Within flush work (sys_sync(), kupdate and such).
* We wait on commit, if told to.
*
* - Within iput_final() -> write_inode_now()
* We wait on commit, if told to.
*
* In all cases it is actually safe for us to return without doing anything,
* because the inode has been copied into a raw inode buffer in
* ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL
* writeback.
*
* Note that we are absolutely dependent upon all inode dirtiers doing the
* right thing: they *must* call mark_inode_dirty() after dirtying info in
* which we are interested.
*
* It would be a bug for them to not do this. The code:
*
* mark_inode_dirty(inode)
* stuff();
* inode->i_size = expr;
*
* is in error because write_inode() could occur while `stuff()' is running,
* and the new i_size will be lost. Plus the inode will no longer be on the
* superblock's dirty inode list.
*/
int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err;
if (WARN_ON_ONCE(current->flags & PF_MEMALLOC) ||
sb_rdonly(inode->i_sb))
return 0;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
if (EXT4_SB(inode->i_sb)->s_journal) {
if (ext4_journal_current_handle()) {
ext4_debug("called recursively, non-PF_MEMALLOC!\n");
dump_stack();
return -EIO;
}
/*
* No need to force transaction in WB_SYNC_NONE mode. Also
* ext4_sync_fs() will force the commit after everything is
* written.
*/
if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
return 0;
err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
EXT4_I(inode)->i_sync_tid);
} else {
struct ext4_iloc iloc;
err = __ext4_get_inode_loc_noinmem(inode, &iloc);
if (err)
return err;
/*
* sync(2) will flush the whole buffer cache. No need to do
* it here separately for each inode.
*/
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
ext4_error_inode_block(inode, iloc.bh->b_blocknr, EIO,
"IO error syncing inode");
err = -EIO;
}
brelse(iloc.bh);
}
return err;
}
/*
* In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate
* buffers that are attached to a folio straddling i_size and are undergoing
* commit. In that case we have to wait for commit to finish and try again.
*/
static void ext4_wait_for_tail_page_commit(struct inode *inode)
{
unsigned offset;
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = 0;
int ret;
offset = inode->i_size & (PAGE_SIZE - 1);
/*
* If the folio is fully truncated, we don't need to wait for any commit
* (and we even should not as __ext4_journalled_invalidate_folio() may
* strip all buffers from the folio but keep the folio dirty which can then
* confuse e.g. concurrent ext4_writepages() seeing dirty folio without
* buffers). Also we don't need to wait for any commit if all buffers in
* the folio remain valid. This is most beneficial for the common case of
* blocksize == PAGESIZE.
*/
if (!offset || offset > (PAGE_SIZE - i_blocksize(inode)))
return;
while (1) {
struct folio *folio = filemap_lock_folio(inode->i_mapping,
inode->i_size >> PAGE_SHIFT);
if (!folio)
return;
ret = __ext4_journalled_invalidate_folio(folio, offset,
folio_size(folio) - offset);
folio_unlock(folio);
folio_put(folio);
if (ret != -EBUSY)
return;
commit_tid = 0;
read_lock(&journal->j_state_lock);
if (journal->j_committing_transaction)
commit_tid = journal->j_committing_transaction->t_tid;
read_unlock(&journal->j_state_lock);
if (commit_tid)
jbd2_log_wait_commit(journal, commit_tid);
}
}
/*
* ext4_setattr()
*
* Called from notify_change.
*
* We want to trap VFS attempts to truncate the file as soon as
* possible. In particular, we want to make sure that when the VFS
* shrinks i_size, we put the inode on the orphan list and modify
* i_disksize immediately, so that during the subsequent flushing of
* dirty pages and freeing of disk blocks, we can guarantee that any
* commit will leave the blocks being flushed in an unused state on
* disk. (On recovery, the inode will get truncated and the blocks will
* be freed, so we have a strong guarantee that no future commit will
* leave these blocks visible to the user.)
*
* Another thing we have to assure is that if we are in ordered mode
* and inode is still attached to the committing transaction, we must
* we start writeout of all the dirty pages which are being truncated.
* This way we are sure that all the data written in the previous
* transaction are already on disk (truncate waits for pages under
* writeback).
*
* Called with inode->i_rwsem down.
*/
int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error, rc = 0;
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
bool inc_ivers = true;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
if (unlikely(IS_IMMUTABLE(inode)))
return -EPERM;
if (unlikely(IS_APPEND(inode) &&
(ia_valid & (ATTR_MODE | ATTR_UID |
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
error = setattr_prepare(idmap, dentry, attr);
if (error)
return error;
error = fscrypt_prepare_setattr(dentry, attr);
if (error)
return error;
error = fsverity_prepare_setattr(dentry, attr);
if (error)
return error;
if (is_quota_modification(idmap, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
if (i_uid_needs_update(idmap, attr, inode) ||
i_gid_needs_update(idmap, attr, inode)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
(EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) +
EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)) + 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
}
/* dquot_transfer() calls back ext4_get_inode_usage() which
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
error = dquot_transfer(idmap, inode, attr);
up_read(&EXT4_I(inode)->xattr_sem);
if (error) {
ext4_journal_stop(handle);
return error;
}
/* Update corresponding info in inode so that everything is in
* one transaction */
i_uid_update(idmap, attr, inode);
i_gid_update(idmap, attr, inode);
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
if (unlikely(error)) {
return error;
}
}
if (attr->ia_valid & ATTR_SIZE) {
handle_t *handle;
loff_t oldsize = inode->i_size;
loff_t old_disksize;
int shrink = (attr->ia_size < inode->i_size);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (attr->ia_size > sbi->s_bitmap_maxbytes) {
return -EFBIG;
}
}
if (!S_ISREG(inode->i_mode)) {
return -EINVAL;
}
if (attr->ia_size == inode->i_size)
inc_ivers = false;
if (shrink) {
if (ext4_should_order_data(inode)) {
error = ext4_begin_ordered_truncate(inode,
attr->ia_size);
if (error)
goto err_out;
}
/*
* Blocks are going to be removed from the inode. Wait
* for dio in flight.
*/
inode_dio_wait(inode);
}
filemap_invalidate_lock(inode->i_mapping);
rc = ext4_break_layouts(inode);
if (rc) {
filemap_invalidate_unlock(inode->i_mapping);
goto err_out;
}
if (attr->ia_size != inode->i_size) {
handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto out_mmap_sem;
}
if (ext4_handle_valid(handle) && shrink) {
error = ext4_orphan_add(handle, inode);
orphan = 1;
}
/*
* Update c/mtime on truncate up, ext4_truncate() will
* update c/mtime in shrink case below
*/
if (!shrink) {
inode->i_mtime = current_time(inode);
inode->i_ctime = inode->i_mtime;
}
if (shrink)
ext4_fc_track_range(handle, inode,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits,
EXT_MAX_BLOCKS - 1);
else
ext4_fc_track_range(
handle, inode,
(oldsize > 0 ? oldsize - 1 : oldsize) >>
inode->i_sb->s_blocksize_bits,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits);
down_write(&EXT4_I(inode)->i_data_sem);
old_disksize = EXT4_I(inode)->i_disksize;
EXT4_I(inode)->i_disksize = attr->ia_size;
rc = ext4_mark_inode_dirty(handle, inode);
if (!error)
error = rc;
/*
* We have to update i_size under i_data_sem together
* with i_disksize to avoid races with writeback code
* running ext4_wb_update_i_disksize().
*/
if (!error)
i_size_write(inode, attr->ia_size);
else
EXT4_I(inode)->i_disksize = old_disksize;
up_write(&EXT4_I(inode)->i_data_sem);
ext4_journal_stop(handle);
if (error)
goto out_mmap_sem;
if (!shrink) {
pagecache_isize_extended(inode, oldsize,
inode->i_size);
} else if (ext4_should_journal_data(inode)) {
ext4_wait_for_tail_page_commit(inode);
}
}
/*
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
*/
truncate_pagecache(inode, inode->i_size);
/*
* Call ext4_truncate() even if i_size didn't change to
* truncate possible preallocated blocks.
*/
if (attr->ia_size <= oldsize) {
rc = ext4_truncate(inode);
if (rc)
error = rc;
}
out_mmap_sem:
filemap_invalidate_unlock(inode->i_mapping);
}
if (!error) {
if (inc_ivers)
inode_inc_iversion(inode);
setattr_copy(idmap, inode, attr);
mark_inode_dirty(inode);
}
/*
* If the call to ext4_truncate failed to get a transaction handle at
* all, we need to clean up the in-core orphan list manually.
*/
if (orphan && inode->i_nlink)
ext4_orphan_del(NULL, inode);
if (!error && (ia_valid & ATTR_MODE))
rc = posix_acl_chmod(idmap, dentry, inode->i_mode);
err_out:
if (error)
ext4_std_error(inode->i_sb, error);
if (!error)
error = rc;
return error;
}
u32 ext4_dio_alignment(struct inode *inode)
{
if (fsverity_active(inode))
return 0;
if (ext4_should_journal_data(inode))
return 0;
if (ext4_has_inline_data(inode))
return 0;
if (IS_ENCRYPTED(inode)) {
if (!fscrypt_dio_supported(inode))
return 0;
return i_blocksize(inode);
}
return 1; /* use the iomap defaults */
}
int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
if ((request_mask & STATX_BTIME) &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = ei->i_crtime.tv_sec;
stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
}
/*
* Return the DIO alignment restrictions if requested. We only return
* this information when requested, since on encrypted files it might
* take a fair bit of work to get if the file wasn't opened recently.
*/
if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
u32 dio_align = ext4_dio_alignment(inode);
stat->result_mask |= STATX_DIOALIGN;
if (dio_align == 1) {
struct block_device *bdev = inode->i_sb->s_bdev;
/* iomap defaults */
stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
stat->dio_offset_align = bdev_logical_block_size(bdev);
} else {
stat->dio_mem_align = dio_align;
stat->dio_offset_align = dio_align;
}
}
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
if (flags & EXT4_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (flags & EXT4_COMPR_FL)
stat->attributes |= STATX_ATTR_COMPRESSED;
if (flags & EXT4_ENCRYPT_FL)
stat->attributes |= STATX_ATTR_ENCRYPTED;
if (flags & EXT4_IMMUTABLE_FL)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & EXT4_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
if (flags & EXT4_VERITY_FL)
stat->attributes |= STATX_ATTR_VERITY;
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_COMPRESSED |
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
generic_fillattr(idmap, inode, stat);
return 0;
}
int ext4_file_getattr(struct mnt_idmap *idmap,
const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
u64 delalloc_blocks;
ext4_getattr(idmap, path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
* have data blocks allocated (it may have an external xattr block).
* Report at least one sector for such files, so tools like tar, rsync,
* others don't incorrectly think the file is completely sparse.
*/
if (unlikely(ext4_has_inline_data(inode)))
stat->blocks += (stat->size + 511) >> 9;
/*
* We can't update i_blocks if the block allocation is delayed
* otherwise in the case of system crash before the real block
* allocation is done, we will have i_blocks inconsistent with
* on-disk file blocks.
* We always keep i_blocks updated together with real
* allocation. But to not confuse with user, stat
* will return the blocks that include the delayed allocation
* blocks for this file.
*/
delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
EXT4_I(inode)->i_reserved_data_blocks);
stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9);
return 0;
}
static int ext4_index_trans_blocks(struct inode *inode, int lblocks,
int pextents)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return ext4_ind_trans_blocks(inode, lblocks);
return ext4_ext_index_trans_blocks(inode, pextents);
}
/*
* Account for index blocks, block groups bitmaps and block group
* descriptor blocks if modify datablocks and index blocks
* worse case, the indexs blocks spread over different block groups
*
* If datablocks are discontiguous, they are possible to spread over
* different block groups too. If they are contiguous, with flexbg,
* they could still across block group boundary.
*
* Also account for superblock, inode, quota and xattr blocks
*/
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
int idxblocks;
int ret;
/*
* How many index blocks need to touch to map @lblocks logical blocks
* to @pextents physical extents?
*/
idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents);
ret = idxblocks;
/*
* Now let's see how many group bitmaps and group descriptors need
* to account
*/
groups = idxblocks + pextents;
gdpblocks = groups;
if (groups > ngroups)
groups = ngroups;
if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
/* bitmaps and block group descriptor blocks */
ret += groups + gdpblocks;
/* Blocks for super block, inode, quota and xattr blocks */
ret += EXT4_META_TRANS_BLOCKS(inode->i_sb);
return ret;
}
/*
* Calculate the total number of credits to reserve to fit
* the modification of a single pages into a single transaction,
* which may include multiple chunks of block allocations.
*
* This could be called via ext4_write_begin()
*
* We need to consider the worse case, when
* one new block per extent.
*/
int ext4_writepage_trans_blocks(struct inode *inode)
{
int bpp = ext4_journal_blocks_per_page(inode);
int ret;
ret = ext4_meta_trans_blocks(inode, bpp, bpp);
/* Account for data blocks for journalled mode */
if (ext4_should_journal_data(inode))
ret += bpp;
return ret;
}
/*
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
* ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
*/
int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks)
{
return ext4_meta_trans_blocks(inode, nrblocks, 1);
}
/*
* The caller must have previously called ext4_reserve_inode_write().
* Give this, we know that the caller already has write access to iloc->bh.
*/
int ext4_mark_iloc_dirty(handle_t *handle,
struct inode *inode, struct ext4_iloc *iloc)
{
int err = 0;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
put_bh(iloc->bh);
return -EIO;
}
ext4_fc_track_inode(handle, inode);
/* the do_update_inode consumes one bh->b_count */
get_bh(iloc->bh);
/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
err = ext4_do_update_inode(handle, inode, iloc);
put_bh(iloc->bh);
return err;
}
/*
* On success, We end up with an outstanding reference count against
* iloc->bh. This _must_ be cleaned up later.
*/
int
ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc)
{
int err;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
err = ext4_get_inode_loc(inode, iloc);
if (!err) {
BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, inode->i_sb,
iloc->bh, EXT4_JTR_NONE);
if (err) {
brelse(iloc->bh);
iloc->bh = NULL;
}
}
ext4_std_error(inode->i_sb, err);
return err;
}
static int __ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc *iloc,
handle_t *handle, int *no_expand)
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
int error;
/* this was checked at iget time, but double check for good measure */
if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) ||
(ei->i_extra_isize & 3)) {
EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)",
ei->i_extra_isize,
EXT4_INODE_SIZE(inode->i_sb));
return -EFSCORRUPTED;
}
if ((new_extra_isize < ei->i_extra_isize) ||
(new_extra_isize < 4) ||
(new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE))
return -EINVAL; /* Should never happen */
raw_inode = ext4_raw_inode(iloc);
header = IHDR(inode, raw_inode);
/* No extended attributes present */
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
EXT4_I(inode)->i_extra_isize, 0,
new_extra_isize - EXT4_I(inode)->i_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
return 0;
}
/*
* We may need to allocate external xattr block so we need quotas
* initialized. Here we can be called with various locks held so we
* cannot affort to initialize quotas ourselves. So just bail.
*/
if (dquot_initialize_needed(inode))
return -EAGAIN;
/* try to expand with EAs present */
error = ext4_expand_extra_isize_ea(inode, new_extra_isize,
raw_inode, handle);
if (error) {
/*
* Inode size expansion failed; don't try again
*/
*no_expand = 1;
}
return error;
}
/*
* Expand an inode by new_extra_isize bytes.
* Returns 0 on success or negative error number on failure.
*/
static int ext4_try_to_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc iloc,
handle_t *handle)
{
int no_expand;
int error;
if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND))
return -EOVERFLOW;
/*
* In nojournal mode, we can immediately attempt to expand
* the inode. When journaled, we first need to obtain extra
* buffer credits since we may write into the EA block
* with this same handle. If journal_extend fails, then it will
* only result in a minor loss of functionality for that inode.
* If this is felt to be critical, then e2fsck should be run to
* force a large enough s_min_extra_isize.
*/
if (ext4_journal_extend(handle,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0)
return -ENOSPC;
if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
return -EBUSY;
error = __ext4_expand_extra_isize(inode, new_extra_isize, &iloc,
handle, &no_expand);
ext4_write_unlock_xattr(inode, &no_expand);
return error;
}
int ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc *iloc)
{
handle_t *handle;
int no_expand;
int error, rc;
if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
brelse(iloc->bh);
return -EOVERFLOW;
}
handle = ext4_journal_start(inode, EXT4_HT_INODE,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
brelse(iloc->bh);
return error;
}
ext4_write_lock_xattr(inode, &no_expand);
BUFFER_TRACE(iloc->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, inode->i_sb, iloc->bh,
EXT4_JTR_NONE);
if (error) {
brelse(iloc->bh);
goto out_unlock;
}
error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc,
handle, &no_expand);
rc = ext4_mark_iloc_dirty(handle, inode, iloc);
if (!error)
error = rc;
out_unlock:
ext4_write_unlock_xattr(inode, &no_expand);
ext4_journal_stop(handle);
return error;
}
/*
* What we do here is to mark the in-core inode as clean with respect to inode
* dirtiness (it may still be data-dirty).
* This means that the in-core inode may be reaped by prune_icache
* without having to perform any I/O. This is a very good thing,
* because *any* task may call prune_icache - even ones which
* have a transaction open against a different journal.
*
* Is this cheating? Not really. Sure, we haven't written the
* inode out, but prune_icache isn't a user-visible syncing function.
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
*/
int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
const char *func, unsigned int line)
{
struct ext4_iloc iloc;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err;
might_sleep();
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out;
if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize)
ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize,
iloc, handle);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
out:
if (unlikely(err))
ext4_error_inode_err(inode, func, line, 0, err,
"mark_inode_dirty error");
return err;
}
/*
* ext4_dirty_inode() is called from __mark_inode_dirty()
*
* We're really interested in the case where a file is being extended.
* i_size has been changed by generic_commit_write() and we thus need
* to include the updated inode in the current transaction.
*
* Also, dquot_alloc_block() will always dirty the inode when blocks
* are allocated to the file.
*
* If the inode is marked synchronous, we don't honour that here - doing
* so would cause a commit on atime updates, which we don't bother doing.
* We handle synchronous inodes at the highest possible level.
*/
void ext4_dirty_inode(struct inode *inode, int flags)
{
handle_t *handle;
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle))
return;
ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
}
int ext4_change_inode_journal_flag(struct inode *inode, int val)
{
journal_t *journal;
handle_t *handle;
int err;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
/*
* We have to be very careful here: changing a data block's
* journaling status dynamically is dangerous. If we write a
* data block to the journal, change the status and then delete
* that block, we risk forgetting to revoke the old log record
* from the journal and so a subsequent replay can corrupt data.
* So, first we make sure that the journal is empty and that
* nobody is changing anything.
*/
journal = EXT4_JOURNAL(inode);
if (!journal)
return 0;
if (is_journal_aborted(journal))
return -EROFS;
/* Wait for all existing dio workers */
inode_dio_wait(inode);
/*
* Before flushing the journal and switching inode's aops, we have
* to flush all dirty data the inode has. There can be outstanding
* delayed allocations, there can be unwritten extents created by
* fallocate or buffered writes in dioread_nolock mode covered by
* dirty data which can be converted only after flushing the dirty
* data (and journalled aops don't know how to handle these cases).
*/
if (val) {
filemap_invalidate_lock(inode->i_mapping);
err = filemap_write_and_wait(inode->i_mapping);
if (err < 0) {
filemap_invalidate_unlock(inode->i_mapping);
return err;
}
}
percpu_down_write(&sbi->s_writepages_rwsem);
jbd2_journal_lock_updates(journal);
/*
* OK, there are no updates running now, and all cached data is
* synced to disk. We are now in a completely consistent state
* which doesn't have anything in the journal, and we know that
* no filesystem updates are running, so it is safe to modify
* the inode's in-core data-journaling state flag now.
*/
if (val)
ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else {
err = jbd2_journal_flush(journal, 0);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
percpu_up_write(&sbi->s_writepages_rwsem);
return err;
}
ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
}
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
percpu_up_write(&sbi->s_writepages_rwsem);
if (val)
filemap_invalidate_unlock(inode->i_mapping);
/* Finally we can mark the inode as dirty. */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_fc_mark_ineligible(inode->i_sb,
EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle);
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
ext4_journal_stop(handle);
ext4_std_error(inode->i_sb, err);
return err;
}
static int ext4_bh_unmapped(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
return !buffer_mapped(bh);
}
vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio = page_folio(vmf->page);
loff_t size;
unsigned long len;
int err;
vm_fault_t ret;
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
handle_t *handle;
get_block_t *get_block;
int retries = 0;
if (unlikely(IS_IMMUTABLE(inode)))
return VM_FAULT_SIGBUS;
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
filemap_invalidate_lock_shared(mapping);
err = ext4_convert_inline_data(inode);
if (err)
goto out_ret;
/*
* On data journalling we skip straight to the transaction handle:
* there's no delalloc; page truncated will be checked later; the
* early return w/ all buffers mapped (calculates size/len) can't
* be used; and there's no dioread_nolock, so only ext4_get_block.
*/
if (ext4_should_journal_data(inode))
goto retry_alloc;
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_nonda_switch(inode->i_sb)) {
do {
err = block_page_mkwrite(vma, vmf,
ext4_da_get_block_prep);
} while (err == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries));
goto out_ret;
}
folio_lock(folio);
size = i_size_read(inode);
/* Page got truncated from under us? */
if (folio->mapping != mapping || folio_pos(folio) > size) {
folio_unlock(folio);
ret = VM_FAULT_NOPAGE;
goto out;
}
len = folio_size(folio);
if (folio_pos(folio) + len > size)
len = size - folio_pos(folio);
/*
* Return if we have all the buffers mapped. This avoids the need to do
* journal_start/journal_stop which can block and take a long time
*
* This cannot be done for data journalling, as we have to add the
* inode to the transaction's list to writeprotect pages on commit.
*/
if (folio_buffers(folio)) {
if (!ext4_walk_page_buffers(NULL, inode, folio_buffers(folio),
0, len, NULL,
ext4_bh_unmapped)) {
/* Wait so that we don't change page under IO */
folio_wait_stable(folio);
ret = VM_FAULT_LOCKED;
goto out;
}
}
folio_unlock(folio);
/* OK, we need to fill the hole... */
if (ext4_should_dioread_nolock(inode))
get_block = ext4_get_block_unwritten;
else
get_block = ext4_get_block;
retry_alloc:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = VM_FAULT_SIGBUS;
goto out;
}
/*
* Data journalling can't use block_page_mkwrite() because it
* will set_buffer_dirty() before do_journal_get_write_access()
* thus might hit warning messages for dirty metadata buffers.
*/
if (!ext4_should_journal_data(inode)) {
err = block_page_mkwrite(vma, vmf, get_block);
} else {
folio_lock(folio);
size = i_size_read(inode);
/* Page got truncated from under us? */
if (folio->mapping != mapping || folio_pos(folio) > size) {
ret = VM_FAULT_NOPAGE;
goto out_error;
}
len = folio_size(folio);
if (folio_pos(folio) + len > size)
len = size - folio_pos(folio);
err = __block_write_begin(&folio->page, 0, len, ext4_get_block);
if (!err) {
ret = VM_FAULT_SIGBUS;
if (ext4_journal_page_buffers(handle, &folio->page, len))
goto out_error;
} else {
folio_unlock(folio);
}
}
ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_alloc;
out_ret:
ret = block_page_mkwrite_return(err);
out:
filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(inode->i_sb);
return ret;
out_error:
folio_unlock(folio);
ext4_journal_stop(handle);
goto out;
}
|