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
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/bio.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/page-flags.h>
#include <linux/sched/mm.h>
#include <linux/spinlock.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
#include <linux/fsverity.h>
#include "extent_io.h"
#include "extent-io-tree.h"
#include "extent_map.h"
#include "ctree.h"
#include "btrfs_inode.h"
#include "bio.h"
#include "locking.h"
#include "backref.h"
#include "disk-io.h"
#include "subpage.h"
#include "zoned.h"
#include "block-group.h"
#include "compression.h"
#include "fs.h"
#include "accessors.h"
#include "file-item.h"
#include "file.h"
#include "dev-replace.h"
#include "super.h"
#include "transaction.h"
static struct kmem_cache *extent_buffer_cache;
#ifdef CONFIG_BTRFS_DEBUG
static inline void btrfs_leak_debug_add_eb(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
unsigned long flags;
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
list_add(&eb->leak_list, &fs_info->allocated_ebs);
spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
}
static inline void btrfs_leak_debug_del_eb(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
unsigned long flags;
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
list_del(&eb->leak_list);
spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
}
void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info)
{
struct extent_buffer *eb;
unsigned long flags;
/*
* If we didn't get into open_ctree our allocated_ebs will not be
* initialized, so just skip this.
*/
if (!fs_info->allocated_ebs.next)
return;
WARN_ON(!list_empty(&fs_info->allocated_ebs));
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
while (!list_empty(&fs_info->allocated_ebs)) {
eb = list_first_entry(&fs_info->allocated_ebs,
struct extent_buffer, leak_list);
pr_err(
"BTRFS: buffer leak start %llu len %u refs %d bflags %lu owner %llu\n",
eb->start, eb->len, atomic_read(&eb->refs), eb->bflags,
btrfs_header_owner(eb));
list_del(&eb->leak_list);
WARN_ON_ONCE(1);
kmem_cache_free(extent_buffer_cache, eb);
}
spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
}
#else
#define btrfs_leak_debug_add_eb(eb) do {} while (0)
#define btrfs_leak_debug_del_eb(eb) do {} while (0)
#endif
/*
* Structure to record info about the bio being assembled, and other info like
* how many bytes are there before stripe/ordered extent boundary.
*/
struct btrfs_bio_ctrl {
struct btrfs_bio *bbio;
enum btrfs_compression_type compress_type;
u32 len_to_oe_boundary;
blk_opf_t opf;
btrfs_bio_end_io_t end_io_func;
struct writeback_control *wbc;
/*
* The sectors of the page which are going to be submitted by
* extent_writepage_io().
* This is to avoid touching ranges covered by compression/inline.
*/
unsigned long submit_bitmap;
};
static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
{
struct btrfs_bio *bbio = bio_ctrl->bbio;
if (!bbio)
return;
/* Caller should ensure the bio has at least some range added */
ASSERT(bbio->bio.bi_iter.bi_size);
if (btrfs_op(&bbio->bio) == BTRFS_MAP_READ &&
bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
btrfs_submit_compressed_read(bbio);
else
btrfs_submit_bbio(bbio, 0);
/* The bbio is owned by the end_io handler now */
bio_ctrl->bbio = NULL;
}
/*
* Submit or fail the current bio in the bio_ctrl structure.
*/
static void submit_write_bio(struct btrfs_bio_ctrl *bio_ctrl, int ret)
{
struct btrfs_bio *bbio = bio_ctrl->bbio;
if (!bbio)
return;
if (ret) {
ASSERT(ret < 0);
btrfs_bio_end_io(bbio, errno_to_blk_status(ret));
/* The bio is owned by the end_io handler now */
bio_ctrl->bbio = NULL;
} else {
submit_one_bio(bio_ctrl);
}
}
int __init extent_buffer_init_cachep(void)
{
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
sizeof(struct extent_buffer), 0, 0,
NULL);
if (!extent_buffer_cache)
return -ENOMEM;
return 0;
}
void __cold extent_buffer_free_cachep(void)
{
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
kmem_cache_destroy(extent_buffer_cache);
}
static void process_one_folio(struct btrfs_fs_info *fs_info,
struct folio *folio, const struct folio *locked_folio,
unsigned long page_ops, u64 start, u64 end)
{
u32 len;
ASSERT(end + 1 - start != 0 && end + 1 - start < U32_MAX);
len = end + 1 - start;
if (page_ops & PAGE_SET_ORDERED)
btrfs_folio_clamp_set_ordered(fs_info, folio, start, len);
if (page_ops & PAGE_START_WRITEBACK) {
btrfs_folio_clamp_clear_dirty(fs_info, folio, start, len);
btrfs_folio_clamp_set_writeback(fs_info, folio, start, len);
}
if (page_ops & PAGE_END_WRITEBACK)
btrfs_folio_clamp_clear_writeback(fs_info, folio, start, len);
if (folio != locked_folio && (page_ops & PAGE_UNLOCK))
btrfs_folio_end_writer_lock(fs_info, folio, start, len);
}
static void __process_folios_contig(struct address_space *mapping,
const struct folio *locked_folio, u64 start,
u64 end, unsigned long page_ops)
{
struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host);
pgoff_t start_index = start >> PAGE_SHIFT;
pgoff_t end_index = end >> PAGE_SHIFT;
pgoff_t index = start_index;
struct folio_batch fbatch;
int i;
folio_batch_init(&fbatch);
while (index <= end_index) {
int found_folios;
found_folios = filemap_get_folios_contig(mapping, &index,
end_index, &fbatch);
for (i = 0; i < found_folios; i++) {
struct folio *folio = fbatch.folios[i];
process_one_folio(fs_info, folio, locked_folio,
page_ops, start, end);
}
folio_batch_release(&fbatch);
cond_resched();
}
}
static noinline void __unlock_for_delalloc(const struct inode *inode,
const struct folio *locked_folio,
u64 start, u64 end)
{
unsigned long index = start >> PAGE_SHIFT;
unsigned long end_index = end >> PAGE_SHIFT;
ASSERT(locked_folio);
if (index == locked_folio->index && end_index == index)
return;
__process_folios_contig(inode->i_mapping, locked_folio, start, end,
PAGE_UNLOCK);
}
static noinline int lock_delalloc_folios(struct inode *inode,
const struct folio *locked_folio,
u64 start, u64 end)
{
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
struct address_space *mapping = inode->i_mapping;
pgoff_t start_index = start >> PAGE_SHIFT;
pgoff_t end_index = end >> PAGE_SHIFT;
pgoff_t index = start_index;
u64 processed_end = start;
struct folio_batch fbatch;
if (index == locked_folio->index && index == end_index)
return 0;
folio_batch_init(&fbatch);
while (index <= end_index) {
unsigned int found_folios, i;
found_folios = filemap_get_folios_contig(mapping, &index,
end_index, &fbatch);
if (found_folios == 0)
goto out;
for (i = 0; i < found_folios; i++) {
struct folio *folio = fbatch.folios[i];
u32 len = end + 1 - start;
if (folio == locked_folio)
continue;
if (btrfs_folio_start_writer_lock(fs_info, folio, start,
len))
goto out;
if (!folio_test_dirty(folio) || folio->mapping != mapping) {
btrfs_folio_end_writer_lock(fs_info, folio, start,
len);
goto out;
}
processed_end = folio_pos(folio) + folio_size(folio) - 1;
}
folio_batch_release(&fbatch);
cond_resched();
}
return 0;
out:
folio_batch_release(&fbatch);
if (processed_end > start)
__unlock_for_delalloc(inode, locked_folio, start,
processed_end);
return -EAGAIN;
}
/*
* Find and lock a contiguous range of bytes in the file marked as delalloc, no
* more than @max_bytes.
*
* @start: The original start bytenr to search.
* Will store the extent range start bytenr.
* @end: The original end bytenr of the search range
* Will store the extent range end bytenr.
*
* Return true if we find a delalloc range which starts inside the original
* range, and @start/@end will store the delalloc range start/end.
*
* Return false if we can't find any delalloc range which starts inside the
* original range, and @start/@end will be the non-delalloc range start/end.
*/
EXPORT_FOR_TESTS
noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
struct folio *locked_folio,
u64 *start, u64 *end)
{
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
const u64 orig_start = *start;
const u64 orig_end = *end;
/* The sanity tests may not set a valid fs_info. */
u64 max_bytes = fs_info ? fs_info->max_extent_size : BTRFS_MAX_EXTENT_SIZE;
u64 delalloc_start;
u64 delalloc_end;
bool found;
struct extent_state *cached_state = NULL;
int ret;
int loops = 0;
/* Caller should pass a valid @end to indicate the search range end */
ASSERT(orig_end > orig_start);
/* The range should at least cover part of the folio */
ASSERT(!(orig_start >= folio_pos(locked_folio) + folio_size(locked_folio) ||
orig_end <= folio_pos(locked_folio)));
again:
/* step one, find a bunch of delalloc bytes starting at start */
delalloc_start = *start;
delalloc_end = 0;
found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
max_bytes, &cached_state);
if (!found || delalloc_end <= *start || delalloc_start > orig_end) {
*start = delalloc_start;
/* @delalloc_end can be -1, never go beyond @orig_end */
*end = min(delalloc_end, orig_end);
free_extent_state(cached_state);
return false;
}
/*
* start comes from the offset of locked_folio. We have to lock
* folios in order, so we can't process delalloc bytes before
* locked_folio
*/
if (delalloc_start < *start)
delalloc_start = *start;
/*
* make sure to limit the number of folios we try to lock down
*/
if (delalloc_end + 1 - delalloc_start > max_bytes)
delalloc_end = delalloc_start + max_bytes - 1;
/* step two, lock all the folioss after the folios that has start */
ret = lock_delalloc_folios(inode, locked_folio, delalloc_start,
delalloc_end);
ASSERT(!ret || ret == -EAGAIN);
if (ret == -EAGAIN) {
/* some of the folios are gone, lets avoid looping by
* shortening the size of the delalloc range we're searching
*/
free_extent_state(cached_state);
cached_state = NULL;
if (!loops) {
max_bytes = PAGE_SIZE;
loops = 1;
goto again;
} else {
found = false;
goto out_failed;
}
}
/* step three, lock the state bits for the whole range */
lock_extent(tree, delalloc_start, delalloc_end, &cached_state);
/* then test to make sure it is all still delalloc */
ret = test_range_bit(tree, delalloc_start, delalloc_end,
EXTENT_DELALLOC, cached_state);
unlock_extent(tree, delalloc_start, delalloc_end, &cached_state);
if (!ret) {
__unlock_for_delalloc(inode, locked_folio, delalloc_start,
delalloc_end);
cond_resched();
goto again;
}
*start = delalloc_start;
*end = delalloc_end;
out_failed:
return found;
}
void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
const struct folio *locked_folio,
struct extent_state **cached,
u32 clear_bits, unsigned long page_ops)
{
clear_extent_bit(&inode->io_tree, start, end, clear_bits, cached);
__process_folios_contig(inode->vfs_inode.i_mapping, locked_folio, start,
end, page_ops);
}
static bool btrfs_verify_folio(struct folio *folio, u64 start, u32 len)
{
struct btrfs_fs_info *fs_info = folio_to_fs_info(folio);
if (!fsverity_active(folio->mapping->host) ||
btrfs_folio_test_uptodate(fs_info, folio, start, len) ||
start >= i_size_read(folio->mapping->host))
return true;
return fsverity_verify_folio(folio);
}
static void end_folio_read(struct folio *folio, bool uptodate, u64 start, u32 len)
{
struct btrfs_fs_info *fs_info = folio_to_fs_info(folio);
ASSERT(folio_pos(folio) <= start &&
start + len <= folio_pos(folio) + PAGE_SIZE);
if (uptodate && btrfs_verify_folio(folio, start, len))
btrfs_folio_set_uptodate(fs_info, folio, start, len);
else
btrfs_folio_clear_uptodate(fs_info, folio, start, len);
if (!btrfs_is_subpage(fs_info, folio->mapping))
folio_unlock(folio);
else
btrfs_subpage_end_reader(fs_info, folio, start, len);
}
/*
* After a write IO is done, we need to:
*
* - clear the uptodate bits on error
* - clear the writeback bits in the extent tree for the range
* - filio_end_writeback() if there is no more pending io for the folio
*
* Scheduling is not allowed, so the extent state tree is expected
* to have one and only one object corresponding to this IO.
*/
static void end_bbio_data_write(struct btrfs_bio *bbio)
{
struct btrfs_fs_info *fs_info = bbio->fs_info;
struct bio *bio = &bbio->bio;
int error = blk_status_to_errno(bio->bi_status);
struct folio_iter fi;
const u32 sectorsize = fs_info->sectorsize;
ASSERT(!bio_flagged(bio, BIO_CLONED));
bio_for_each_folio_all(fi, bio) {
struct folio *folio = fi.folio;
u64 start = folio_pos(folio) + fi.offset;
u32 len = fi.length;
/* Only order 0 (single page) folios are allowed for data. */
ASSERT(folio_order(folio) == 0);
/* Our read/write should always be sector aligned. */
if (!IS_ALIGNED(fi.offset, sectorsize))
btrfs_err(fs_info,
"partial page write in btrfs with offset %zu and length %zu",
fi.offset, fi.length);
else if (!IS_ALIGNED(fi.length, sectorsize))
btrfs_info(fs_info,
"incomplete page write with offset %zu and length %zu",
fi.offset, fi.length);
btrfs_finish_ordered_extent(bbio->ordered, folio, start, len,
!error);
if (error)
mapping_set_error(folio->mapping, error);
btrfs_folio_clear_writeback(fs_info, folio, start, len);
}
bio_put(bio);
}
static void begin_folio_read(struct btrfs_fs_info *fs_info, struct folio *folio)
{
ASSERT(folio_test_locked(folio));
if (!btrfs_is_subpage(fs_info, folio->mapping))
return;
ASSERT(folio_test_private(folio));
btrfs_subpage_start_reader(fs_info, folio, folio_pos(folio), PAGE_SIZE);
}
/*
* After a data read IO is done, we need to:
*
* - clear the uptodate bits on error
* - set the uptodate bits if things worked
* - set the folio up to date if all extents in the tree are uptodate
* - clear the lock bit in the extent tree
* - unlock the folio if there are no other extents locked for it
*
* Scheduling is not allowed, so the extent state tree is expected
* to have one and only one object corresponding to this IO.
*/
static void end_bbio_data_read(struct btrfs_bio *bbio)
{
struct btrfs_fs_info *fs_info = bbio->fs_info;
struct bio *bio = &bbio->bio;
struct folio_iter fi;
const u32 sectorsize = fs_info->sectorsize;
ASSERT(!bio_flagged(bio, BIO_CLONED));
bio_for_each_folio_all(fi, &bbio->bio) {
bool uptodate = !bio->bi_status;
struct folio *folio = fi.folio;
struct inode *inode = folio->mapping->host;
u64 start;
u64 end;
u32 len;
/* For now only order 0 folios are supported for data. */
ASSERT(folio_order(folio) == 0);
btrfs_debug(fs_info,
"%s: bi_sector=%llu, err=%d, mirror=%u",
__func__, bio->bi_iter.bi_sector, bio->bi_status,
bbio->mirror_num);
/*
* We always issue full-sector reads, but if some block in a
* folio fails to read, blk_update_request() will advance
* bv_offset and adjust bv_len to compensate. Print a warning
* for unaligned offsets, and an error if they don't add up to
* a full sector.
*/
if (!IS_ALIGNED(fi.offset, sectorsize))
btrfs_err(fs_info,
"partial page read in btrfs with offset %zu and length %zu",
fi.offset, fi.length);
else if (!IS_ALIGNED(fi.offset + fi.length, sectorsize))
btrfs_info(fs_info,
"incomplete page read with offset %zu and length %zu",
fi.offset, fi.length);
start = folio_pos(folio) + fi.offset;
end = start + fi.length - 1;
len = fi.length;
if (likely(uptodate)) {
loff_t i_size = i_size_read(inode);
pgoff_t end_index = i_size >> folio_shift(folio);
/*
* Zero out the remaining part if this range straddles
* i_size.
*
* Here we should only zero the range inside the folio,
* not touch anything else.
*
* NOTE: i_size is exclusive while end is inclusive.
*/
if (folio_index(folio) == end_index && i_size <= end) {
u32 zero_start = max(offset_in_folio(folio, i_size),
offset_in_folio(folio, start));
u32 zero_len = offset_in_folio(folio, end) + 1 -
zero_start;
folio_zero_range(folio, zero_start, zero_len);
}
}
/* Update page status and unlock. */
end_folio_read(folio, uptodate, start, len);
}
bio_put(bio);
}
/*
* Populate every free slot in a provided array with folios using GFP_NOFS.
*
* @nr_folios: number of folios to allocate
* @folio_array: the array to fill with folios; any existing non-NULL entries in
* the array will be skipped
*
* Return: 0 if all folios were able to be allocated;
* -ENOMEM otherwise, the partially allocated folios would be freed and
* the array slots zeroed
*/
int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array)
{
for (int i = 0; i < nr_folios; i++) {
if (folio_array[i])
continue;
folio_array[i] = folio_alloc(GFP_NOFS, 0);
if (!folio_array[i])
goto error;
}
return 0;
error:
for (int i = 0; i < nr_folios; i++) {
if (folio_array[i])
folio_put(folio_array[i]);
}
return -ENOMEM;
}
/*
* Populate every free slot in a provided array with pages, using GFP_NOFS.
*
* @nr_pages: number of pages to allocate
* @page_array: the array to fill with pages; any existing non-null entries in
* the array will be skipped
* @nofail: whether using __GFP_NOFAIL flag
*
* Return: 0 if all pages were able to be allocated;
* -ENOMEM otherwise, the partially allocated pages would be freed and
* the array slots zeroed
*/
int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
bool nofail)
{
const gfp_t gfp = nofail ? (GFP_NOFS | __GFP_NOFAIL) : GFP_NOFS;
unsigned int allocated;
for (allocated = 0; allocated < nr_pages;) {
unsigned int last = allocated;
allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array);
if (unlikely(allocated == last)) {
/* No progress, fail and do cleanup. */
for (int i = 0; i < allocated; i++) {
__free_page(page_array[i]);
page_array[i] = NULL;
}
return -ENOMEM;
}
}
return 0;
}
/*
* Populate needed folios for the extent buffer.
*
* For now, the folios populated are always in order 0 (aka, single page).
*/
static int alloc_eb_folio_array(struct extent_buffer *eb, bool nofail)
{
struct page *page_array[INLINE_EXTENT_BUFFER_PAGES] = { 0 };
int num_pages = num_extent_pages(eb);
int ret;
ret = btrfs_alloc_page_array(num_pages, page_array, nofail);
if (ret < 0)
return ret;
for (int i = 0; i < num_pages; i++)
eb->folios[i] = page_folio(page_array[i]);
eb->folio_size = PAGE_SIZE;
eb->folio_shift = PAGE_SHIFT;
return 0;
}
static bool btrfs_bio_is_contig(struct btrfs_bio_ctrl *bio_ctrl,
struct folio *folio, u64 disk_bytenr,
unsigned int pg_offset)
{
struct bio *bio = &bio_ctrl->bbio->bio;
struct bio_vec *bvec = bio_last_bvec_all(bio);
const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
struct folio *bv_folio = page_folio(bvec->bv_page);
if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) {
/*
* For compression, all IO should have its logical bytenr set
* to the starting bytenr of the compressed extent.
*/
return bio->bi_iter.bi_sector == sector;
}
/*
* The contig check requires the following conditions to be met:
*
* 1) The folios are belonging to the same inode
* This is implied by the call chain.
*
* 2) The range has adjacent logical bytenr
*
* 3) The range has adjacent file offset
* This is required for the usage of btrfs_bio->file_offset.
*/
return bio_end_sector(bio) == sector &&
folio_pos(bv_folio) + bvec->bv_offset + bvec->bv_len ==
folio_pos(folio) + pg_offset;
}
static void alloc_new_bio(struct btrfs_inode *inode,
struct btrfs_bio_ctrl *bio_ctrl,
u64 disk_bytenr, u64 file_offset)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct btrfs_bio *bbio;
bbio = btrfs_bio_alloc(BIO_MAX_VECS, bio_ctrl->opf, fs_info,
bio_ctrl->end_io_func, NULL);
bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
bbio->inode = inode;
bbio->file_offset = file_offset;
bio_ctrl->bbio = bbio;
bio_ctrl->len_to_oe_boundary = U32_MAX;
/* Limit data write bios to the ordered boundary. */
if (bio_ctrl->wbc) {
struct btrfs_ordered_extent *ordered;
ordered = btrfs_lookup_ordered_extent(inode, file_offset);
if (ordered) {
bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX,
ordered->file_offset +
ordered->disk_num_bytes - file_offset);
bbio->ordered = ordered;
}
/*
* Pick the last added device to support cgroup writeback. For
* multi-device file systems this means blk-cgroup policies have
* to always be set on the last added/replaced device.
* This is a bit odd but has been like that for a long time.
*/
bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev);
wbc_init_bio(bio_ctrl->wbc, &bbio->bio);
}
}
/*
* @disk_bytenr: logical bytenr where the write will be
* @page: page to add to the bio
* @size: portion of page that we want to write to
* @pg_offset: offset of the new bio or to check whether we are adding
* a contiguous page to the previous one
*
* The will either add the page into the existing @bio_ctrl->bbio, or allocate a
* new one in @bio_ctrl->bbio.
* The mirror number for this IO should already be initizlied in
* @bio_ctrl->mirror_num.
*/
static void submit_extent_folio(struct btrfs_bio_ctrl *bio_ctrl,
u64 disk_bytenr, struct folio *folio,
size_t size, unsigned long pg_offset)
{
struct btrfs_inode *inode = folio_to_inode(folio);
ASSERT(pg_offset + size <= PAGE_SIZE);
ASSERT(bio_ctrl->end_io_func);
if (bio_ctrl->bbio &&
!btrfs_bio_is_contig(bio_ctrl, folio, disk_bytenr, pg_offset))
submit_one_bio(bio_ctrl);
do {
u32 len = size;
/* Allocate new bio if needed */
if (!bio_ctrl->bbio) {
alloc_new_bio(inode, bio_ctrl, disk_bytenr,
folio_pos(folio) + pg_offset);
}
/* Cap to the current ordered extent boundary if there is one. */
if (len > bio_ctrl->len_to_oe_boundary) {
ASSERT(bio_ctrl->compress_type == BTRFS_COMPRESS_NONE);
ASSERT(is_data_inode(inode));
len = bio_ctrl->len_to_oe_boundary;
}
if (!bio_add_folio(&bio_ctrl->bbio->bio, folio, len, pg_offset)) {
/* bio full: move on to a new one */
submit_one_bio(bio_ctrl);
continue;
}
if (bio_ctrl->wbc)
wbc_account_cgroup_owner(bio_ctrl->wbc, &folio->page,
len);
size -= len;
pg_offset += len;
disk_bytenr += len;
/*
* len_to_oe_boundary defaults to U32_MAX, which isn't folio or
* sector aligned. alloc_new_bio() then sets it to the end of
* our ordered extent for writes into zoned devices.
*
* When len_to_oe_boundary is tracking an ordered extent, we
* trust the ordered extent code to align things properly, and
* the check above to cap our write to the ordered extent
* boundary is correct.
*
* When len_to_oe_boundary is U32_MAX, the cap above would
* result in a 4095 byte IO for the last folio right before
* we hit the bio limit of UINT_MAX. bio_add_folio() has all
* the checks required to make sure we don't overflow the bio,
* and we should just ignore len_to_oe_boundary completely
* unless we're using it to track an ordered extent.
*
* It's pretty hard to make a bio sized U32_MAX, but it can
* happen when the page cache is able to feed us contiguous
* folios for large extents.
*/
if (bio_ctrl->len_to_oe_boundary != U32_MAX)
bio_ctrl->len_to_oe_boundary -= len;
/* Ordered extent boundary: move on to a new bio. */
if (bio_ctrl->len_to_oe_boundary == 0)
submit_one_bio(bio_ctrl);
} while (size);
}
static int attach_extent_buffer_folio(struct extent_buffer *eb,
struct folio *folio,
struct btrfs_subpage *prealloc)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
int ret = 0;
/*
* If the page is mapped to btree inode, we should hold the private
* lock to prevent race.
* For cloned or dummy extent buffers, their pages are not mapped and
* will not race with any other ebs.
*/
if (folio->mapping)
lockdep_assert_held(&folio->mapping->i_private_lock);
if (fs_info->nodesize >= PAGE_SIZE) {
if (!folio_test_private(folio))
folio_attach_private(folio, eb);
else
WARN_ON(folio_get_private(folio) != eb);
return 0;
}
/* Already mapped, just free prealloc */
if (folio_test_private(folio)) {
btrfs_free_subpage(prealloc);
return 0;
}
if (prealloc)
/* Has preallocated memory for subpage */
folio_attach_private(folio, prealloc);
else
/* Do new allocation to attach subpage */
ret = btrfs_attach_subpage(fs_info, folio, BTRFS_SUBPAGE_METADATA);
return ret;
}
int set_page_extent_mapped(struct page *page)
{
return set_folio_extent_mapped(page_folio(page));
}
int set_folio_extent_mapped(struct folio *folio)
{
struct btrfs_fs_info *fs_info;
ASSERT(folio->mapping);
if (folio_test_private(folio))
return 0;
fs_info = folio_to_fs_info(folio);
if (btrfs_is_subpage(fs_info, folio->mapping))
return btrfs_attach_subpage(fs_info, folio, BTRFS_SUBPAGE_DATA);
folio_attach_private(folio, (void *)EXTENT_FOLIO_PRIVATE);
return 0;
}
void clear_folio_extent_mapped(struct folio *folio)
{
struct btrfs_fs_info *fs_info;
ASSERT(folio->mapping);
if (!folio_test_private(folio))
return;
fs_info = folio_to_fs_info(folio);
if (btrfs_is_subpage(fs_info, folio->mapping))
return btrfs_detach_subpage(fs_info, folio);
folio_detach_private(folio);
}
static struct extent_map *__get_extent_map(struct inode *inode,
struct folio *folio, u64 start,
u64 len, struct extent_map **em_cached)
{
struct extent_map *em;
struct extent_state *cached_state = NULL;
ASSERT(em_cached);
if (*em_cached) {
em = *em_cached;
if (extent_map_in_tree(em) && start >= em->start &&
start < extent_map_end(em)) {
refcount_inc(&em->refs);
return em;
}
free_extent_map(em);
*em_cached = NULL;
}
btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), start, start + len - 1, &cached_state);
em = btrfs_get_extent(BTRFS_I(inode), folio, start, len);
if (!IS_ERR(em)) {
BUG_ON(*em_cached);
refcount_inc(&em->refs);
*em_cached = em;
}
unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len - 1, &cached_state);
return em;
}
/*
* basic readpage implementation. Locked extent state structs are inserted
* into the tree that are removed when the IO is done (by the end_io
* handlers)
* XXX JDM: This needs looking at to ensure proper page locking
* return 0 on success, otherwise return error
*/
static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start)
{
struct inode *inode = folio->mapping->host;
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
u64 start = folio_pos(folio);
const u64 end = start + PAGE_SIZE - 1;
u64 cur = start;
u64 extent_offset;
u64 last_byte = i_size_read(inode);
u64 block_start;
struct extent_map *em;
int ret = 0;
size_t pg_offset = 0;
size_t iosize;
size_t blocksize = fs_info->sectorsize;
ret = set_folio_extent_mapped(folio);
if (ret < 0) {
folio_unlock(folio);
return ret;
}
if (folio->index == last_byte >> folio_shift(folio)) {
size_t zero_offset = offset_in_folio(folio, last_byte);
if (zero_offset) {
iosize = folio_size(folio) - zero_offset;
folio_zero_range(folio, zero_offset, iosize);
}
}
bio_ctrl->end_io_func = end_bbio_data_read;
begin_folio_read(fs_info, folio);
while (cur <= end) {
enum btrfs_compression_type compress_type = BTRFS_COMPRESS_NONE;
bool force_bio_submit = false;
u64 disk_bytenr;
ASSERT(IS_ALIGNED(cur, fs_info->sectorsize));
if (cur >= last_byte) {
iosize = folio_size(folio) - pg_offset;
folio_zero_range(folio, pg_offset, iosize);
end_folio_read(folio, true, cur, iosize);
break;
}
em = __get_extent_map(inode, folio, cur, end - cur + 1,
em_cached);
if (IS_ERR(em)) {
end_folio_read(folio, false, cur, end + 1 - cur);
return PTR_ERR(em);
}
extent_offset = cur - em->start;
BUG_ON(extent_map_end(em) <= cur);
BUG_ON(end < cur);
compress_type = extent_map_compression(em);
iosize = min(extent_map_end(em) - cur, end - cur + 1);
iosize = ALIGN(iosize, blocksize);
if (compress_type != BTRFS_COMPRESS_NONE)
disk_bytenr = em->disk_bytenr;
else
disk_bytenr = extent_map_block_start(em) + extent_offset;
block_start = extent_map_block_start(em);
if (em->flags & EXTENT_FLAG_PREALLOC)
block_start = EXTENT_MAP_HOLE;
/*
* If we have a file range that points to a compressed extent
* and it's followed by a consecutive file range that points
* to the same compressed extent (possibly with a different
* offset and/or length, so it either points to the whole extent
* or only part of it), we must make sure we do not submit a
* single bio to populate the folios for the 2 ranges because
* this makes the compressed extent read zero out the folios
* belonging to the 2nd range. Imagine the following scenario:
*
* File layout
* [0 - 8K] [8K - 24K]
* | |
* | |
* points to extent X, points to extent X,
* offset 4K, length of 8K offset 0, length 16K
*
* [extent X, compressed length = 4K uncompressed length = 16K]
*
* If the bio to read the compressed extent covers both ranges,
* it will decompress extent X into the folios belonging to the
* first range and then it will stop, zeroing out the remaining
* folios that belong to the other range that points to extent X.
* So here we make sure we submit 2 bios, one for the first
* range and another one for the third range. Both will target
* the same physical extent from disk, but we can't currently
* make the compressed bio endio callback populate the folios
* for both ranges because each compressed bio is tightly
* coupled with a single extent map, and each range can have
* an extent map with a different offset value relative to the
* uncompressed data of our extent and different lengths. This
* is a corner case so we prioritize correctness over
* non-optimal behavior (submitting 2 bios for the same extent).
*/
if (compress_type != BTRFS_COMPRESS_NONE &&
prev_em_start && *prev_em_start != (u64)-1 &&
*prev_em_start != em->start)
force_bio_submit = true;
if (prev_em_start)
*prev_em_start = em->start;
free_extent_map(em);
em = NULL;
/* we've found a hole, just zero and go on */
if (block_start == EXTENT_MAP_HOLE) {
folio_zero_range(folio, pg_offset, iosize);
end_folio_read(folio, true, cur, iosize);
cur = cur + iosize;
pg_offset += iosize;
continue;
}
/* the get_extent function already copied into the folio */
if (block_start == EXTENT_MAP_INLINE) {
end_folio_read(folio, true, cur, iosize);
cur = cur + iosize;
pg_offset += iosize;
continue;
}
if (bio_ctrl->compress_type != compress_type) {
submit_one_bio(bio_ctrl);
bio_ctrl->compress_type = compress_type;
}
if (force_bio_submit)
submit_one_bio(bio_ctrl);
submit_extent_folio(bio_ctrl, disk_bytenr, folio, iosize,
pg_offset);
cur = cur + iosize;
pg_offset += iosize;
}
return 0;
}
int btrfs_read_folio(struct file *file, struct folio *folio)
{
struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
struct extent_map *em_cached = NULL;
int ret;
ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
free_extent_map(em_cached);
/*
* If btrfs_do_readpage() failed we will want to submit the assembled
* bio to do the cleanup.
*/
submit_one_bio(&bio_ctrl);
return ret;
}
/*
* helper for extent_writepage(), doing all of the delayed allocation setup.
*
* This returns 1 if btrfs_run_delalloc_range function did all the work required
* to write the page (copy into inline extent). In this case the IO has
* been started and the page is already unlocked.
*
* This returns 0 if all went well (page still locked)
* This returns < 0 if there were errors (page still locked)
*/
static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
struct folio *folio,
struct btrfs_bio_ctrl *bio_ctrl)
{
struct btrfs_fs_info *fs_info = inode_to_fs_info(&inode->vfs_inode);
struct writeback_control *wbc = bio_ctrl->wbc;
const bool is_subpage = btrfs_is_subpage(fs_info, folio->mapping);
const u64 page_start = folio_pos(folio);
const u64 page_end = page_start + folio_size(folio) - 1;
/*
* Save the last found delalloc end. As the delalloc end can go beyond
* page boundary, thus we cannot rely on subpage bitmap to locate the
* last delalloc end.
*/
u64 last_delalloc_end = 0;
u64 delalloc_start = page_start;
u64 delalloc_end = page_end;
u64 delalloc_to_write = 0;
int ret = 0;
/* Save the dirty bitmap as our submission bitmap will be a subset of it. */
if (btrfs_is_subpage(fs_info, inode->vfs_inode.i_mapping)) {
ASSERT(fs_info->sectors_per_page > 1);
btrfs_get_subpage_dirty_bitmap(fs_info, folio, &bio_ctrl->submit_bitmap);
} else {
bio_ctrl->submit_bitmap = 1;
}
/* Lock all (subpage) delalloc ranges inside the folio first. */
while (delalloc_start < page_end) {
delalloc_end = page_end;
if (!find_lock_delalloc_range(&inode->vfs_inode, folio,
&delalloc_start, &delalloc_end)) {
delalloc_start = delalloc_end + 1;
continue;
}
btrfs_folio_set_writer_lock(fs_info, folio, delalloc_start,
min(delalloc_end, page_end) + 1 -
delalloc_start);
last_delalloc_end = delalloc_end;
delalloc_start = delalloc_end + 1;
}
delalloc_start = page_start;
if (!last_delalloc_end)
goto out;
/* Run the delalloc ranges for the above locked ranges. */
while (delalloc_start < page_end) {
u64 found_start;
u32 found_len;
bool found;
if (!is_subpage) {
/*
* For non-subpage case, the found delalloc range must
* cover this folio and there must be only one locked
* delalloc range.
*/
found_start = page_start;
found_len = last_delalloc_end + 1 - found_start;
found = true;
} else {
found = btrfs_subpage_find_writer_locked(fs_info, folio,
delalloc_start, &found_start, &found_len);
}
if (!found)
break;
/*
* The subpage range covers the last sector, the delalloc range may
* end beyond the folio boundary, use the saved delalloc_end
* instead.
*/
if (found_start + found_len >= page_end)
found_len = last_delalloc_end + 1 - found_start;
if (ret >= 0) {
/* No errors hit so far, run the current delalloc range. */
ret = btrfs_run_delalloc_range(inode, folio,
found_start,
found_start + found_len - 1,
wbc);
} else {
/*
* We've hit an error during previous delalloc range,
* have to cleanup the remaining locked ranges.
*/
unlock_extent(&inode->io_tree, found_start,
found_start + found_len - 1, NULL);
__unlock_for_delalloc(&inode->vfs_inode, folio,
found_start,
found_start + found_len - 1);
}
/*
* We have some ranges that's going to be submitted asynchronously
* (compression or inline). These range have their own control
* on when to unlock the pages. We should not touch them
* anymore, so clear the range from the submission bitmap.
*/
if (ret > 0) {
unsigned int start_bit = (found_start - page_start) >>
fs_info->sectorsize_bits;
unsigned int end_bit = (min(page_end + 1, found_start + found_len) -
page_start) >> fs_info->sectorsize_bits;
bitmap_clear(&bio_ctrl->submit_bitmap, start_bit, end_bit - start_bit);
}
/*
* Above btrfs_run_delalloc_range() may have unlocked the folio,
* thus for the last range, we cannot touch the folio anymore.
*/
if (found_start + found_len >= last_delalloc_end + 1)
break;
delalloc_start = found_start + found_len;
}
if (ret < 0)
return ret;
out:
if (last_delalloc_end)
delalloc_end = last_delalloc_end;
else
delalloc_end = page_end;
/*
* delalloc_end is already one less than the total length, so
* we don't subtract one from PAGE_SIZE
*/
delalloc_to_write +=
DIV_ROUND_UP(delalloc_end + 1 - page_start, PAGE_SIZE);
/*
* If all ranges are submitted asynchronously, we just need to account
* for them here.
*/
if (bitmap_empty(&bio_ctrl->submit_bitmap, fs_info->sectors_per_page)) {
wbc->nr_to_write -= delalloc_to_write;
return 1;
}
if (wbc->nr_to_write < delalloc_to_write) {
int thresh = 8192;
if (delalloc_to_write < thresh * 2)
thresh = delalloc_to_write;
wbc->nr_to_write = min_t(u64, delalloc_to_write,
thresh);
}
return 0;
}
/*
* Return 0 if we have submitted or queued the sector for submission.
* Return <0 for critical errors.
*
* Caller should make sure filepos < i_size and handle filepos >= i_size case.
*/
static int submit_one_sector(struct btrfs_inode *inode,
struct folio *folio,
u64 filepos, struct btrfs_bio_ctrl *bio_ctrl,
loff_t i_size)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct extent_map *em;
u64 block_start;
u64 disk_bytenr;
u64 extent_offset;
u64 em_end;
const u32 sectorsize = fs_info->sectorsize;
ASSERT(IS_ALIGNED(filepos, sectorsize));
/* @filepos >= i_size case should be handled by the caller. */
ASSERT(filepos < i_size);
em = btrfs_get_extent(inode, NULL, filepos, sectorsize);
if (IS_ERR(em))
return PTR_ERR_OR_ZERO(em);
extent_offset = filepos - em->start;
em_end = extent_map_end(em);
ASSERT(filepos <= em_end);
ASSERT(IS_ALIGNED(em->start, sectorsize));
ASSERT(IS_ALIGNED(em->len, sectorsize));
block_start = extent_map_block_start(em);
disk_bytenr = extent_map_block_start(em) + extent_offset;
ASSERT(!extent_map_is_compressed(em));
ASSERT(block_start != EXTENT_MAP_HOLE);
ASSERT(block_start != EXTENT_MAP_INLINE);
free_extent_map(em);
em = NULL;
/*
* Although the PageDirty bit is cleared before entering this
* function, subpage dirty bit is not cleared.
* So clear subpage dirty bit here so next time we won't submit
* a folio for a range already written to disk.
*/
btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize);
btrfs_set_range_writeback(inode, filepos, filepos + sectorsize - 1);
/*
* Above call should set the whole folio with writeback flag, even
* just for a single subpage sector.
* As long as the folio is properly locked and the range is correct,
* we should always get the folio with writeback flag.
*/
ASSERT(folio_test_writeback(folio));
submit_extent_folio(bio_ctrl, disk_bytenr, folio,
sectorsize, filepos - folio_pos(folio));
return 0;
}
/*
* Helper for extent_writepage(). This calls the writepage start hooks,
* and does the loop to map the page into extents and bios.
*
* We return 1 if the IO is started and the page is unlocked,
* 0 if all went well (page still locked)
* < 0 if there were errors (page still locked)
*/
static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
struct folio *folio,
u64 start, u32 len,
struct btrfs_bio_ctrl *bio_ctrl,
loff_t i_size)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
unsigned long range_bitmap = 0;
bool submitted_io = false;
const u64 folio_start = folio_pos(folio);
u64 cur;
int bit;
int ret = 0;
ASSERT(start >= folio_start &&
start + len <= folio_start + folio_size(folio));
ret = btrfs_writepage_cow_fixup(folio);
if (ret) {
/* Fixup worker will requeue */
folio_redirty_for_writepage(bio_ctrl->wbc, folio);
folio_unlock(folio);
return 1;
}
for (cur = start; cur < start + len; cur += fs_info->sectorsize)
set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap);
bitmap_and(&bio_ctrl->submit_bitmap, &bio_ctrl->submit_bitmap, &range_bitmap,
fs_info->sectors_per_page);
bio_ctrl->end_io_func = end_bbio_data_write;
for_each_set_bit(bit, &bio_ctrl->submit_bitmap, fs_info->sectors_per_page) {
cur = folio_pos(folio) + (bit << fs_info->sectorsize_bits);
if (cur >= i_size) {
btrfs_mark_ordered_io_finished(inode, folio, cur,
start + len - cur, true);
/*
* This range is beyond i_size, thus we don't need to
* bother writing back.
* But we still need to clear the dirty subpage bit, or
* the next time the folio gets dirtied, we will try to
* writeback the sectors with subpage dirty bits,
* causing writeback without ordered extent.
*/
btrfs_folio_clear_dirty(fs_info, folio, cur,
start + len - cur);
break;
}
ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size);
if (ret < 0)
goto out;
submitted_io = true;
}
btrfs_folio_assert_not_dirty(fs_info, folio, start, len);
out:
/*
* If we didn't submitted any sector (>= i_size), folio dirty get
* cleared but PAGECACHE_TAG_DIRTY is not cleared (only cleared
* by folio_start_writeback() if the folio is not dirty).
*
* Here we set writeback and clear for the range. If the full folio
* is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag.
*/
if (!submitted_io) {
btrfs_folio_set_writeback(fs_info, folio, start, len);
btrfs_folio_clear_writeback(fs_info, folio, start, len);
}
return ret;
}
/*
* the writepage semantics are similar to regular writepage. extent
* records are inserted to lock ranges in the tree, and as dirty areas
* are found, they are marked writeback. Then the lock bits are removed
* and the end_io handler clears the writeback ranges
*
* Return 0 if everything goes well.
* Return <0 for error.
*/
static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl)
{
struct inode *inode = folio->mapping->host;
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
const u64 page_start = folio_pos(folio);
int ret;
size_t pg_offset;
loff_t i_size = i_size_read(inode);
unsigned long end_index = i_size >> PAGE_SHIFT;
trace_extent_writepage(folio, inode, bio_ctrl->wbc);
WARN_ON(!folio_test_locked(folio));
pg_offset = offset_in_folio(folio, i_size);
if (folio->index > end_index ||
(folio->index == end_index && !pg_offset)) {
folio_invalidate(folio, 0, folio_size(folio));
folio_unlock(folio);
return 0;
}
if (folio->index == end_index)
folio_zero_range(folio, pg_offset, folio_size(folio) - pg_offset);
/*
* Default to unlock the whole folio.
* The proper bitmap can only be initialized until writepage_delalloc().
*/
bio_ctrl->submit_bitmap = (unsigned long)-1;
ret = set_folio_extent_mapped(folio);
if (ret < 0)
goto done;
ret = writepage_delalloc(BTRFS_I(inode), folio, bio_ctrl);
if (ret == 1)
return 0;
if (ret)
goto done;
ret = extent_writepage_io(BTRFS_I(inode), folio, folio_pos(folio),
PAGE_SIZE, bio_ctrl, i_size);
if (ret == 1)
return 0;
bio_ctrl->wbc->nr_to_write--;
done:
if (ret) {
btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio,
page_start, PAGE_SIZE, !ret);
mapping_set_error(folio->mapping, ret);
}
/*
* Only unlock ranges that are submitted. As there can be some async
* submitted ranges inside the folio.
*/
btrfs_folio_end_writer_lock_bitmap(fs_info, folio, bio_ctrl->submit_bitmap);
ASSERT(ret <= 0);
return ret;
}
void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
{
wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
TASK_UNINTERRUPTIBLE);
}
/*
* Lock extent buffer status and pages for writeback.
*
* Return %false if the extent buffer doesn't need to be submitted (e.g. the
* extent buffer is not dirty)
* Return %true is the extent buffer is submitted to bio.
*/
static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *eb,
struct writeback_control *wbc)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
bool ret = false;
btrfs_tree_lock(eb);
while (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
btrfs_tree_unlock(eb);
if (wbc->sync_mode != WB_SYNC_ALL)
return false;
wait_on_extent_buffer_writeback(eb);
btrfs_tree_lock(eb);
}
/*
* We need to do this to prevent races in people who check if the eb is
* under IO since we can end up having no IO bits set for a short period
* of time.
*/
spin_lock(&eb->refs_lock);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
spin_unlock(&eb->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
-eb->len,
fs_info->dirty_metadata_batch);
ret = true;
} else {
spin_unlock(&eb->refs_lock);
}
btrfs_tree_unlock(eb);
return ret;
}
static void set_btree_ioerr(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
/*
* A read may stumble upon this buffer later, make sure that it gets an
* error and knows there was an error.
*/
clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
/*
* We need to set the mapping with the io error as well because a write
* error will flip the file system readonly, and then syncfs() will
* return a 0 because we are readonly if we don't modify the err seq for
* the superblock.
*/
mapping_set_error(eb->fs_info->btree_inode->i_mapping, -EIO);
/*
* If writeback for a btree extent that doesn't belong to a log tree
* failed, increment the counter transaction->eb_write_errors.
* We do this because while the transaction is running and before it's
* committing (when we call filemap_fdata[write|wait]_range against
* the btree inode), we might have
* btree_inode->i_mapping->a_ops->writepages() called by the VM - if it
* returns an error or an error happens during writeback, when we're
* committing the transaction we wouldn't know about it, since the pages
* can be no longer dirty nor marked anymore for writeback (if a
* subsequent modification to the extent buffer didn't happen before the
* transaction commit), which makes filemap_fdata[write|wait]_range not
* able to find the pages which contain errors at transaction
* commit time. So if this happens we must abort the transaction,
* otherwise we commit a super block with btree roots that point to
* btree nodes/leafs whose content on disk is invalid - either garbage
* or the content of some node/leaf from a past generation that got
* cowed or deleted and is no longer valid.
*
* Note: setting AS_EIO/AS_ENOSPC in the btree inode's i_mapping would
* not be enough - we need to distinguish between log tree extents vs
* non-log tree extents, and the next filemap_fdatawait_range() call
* will catch and clear such errors in the mapping - and that call might
* be from a log sync and not from a transaction commit. Also, checking
* for the eb flag EXTENT_BUFFER_WRITE_ERR at transaction commit time is
* not done and would not be reliable - the eb might have been released
* from memory and reading it back again means that flag would not be
* set (since it's a runtime flag, not persisted on disk).
*
* Using the flags below in the btree inode also makes us achieve the
* goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
* writeback for all dirty pages and before filemap_fdatawait_range()
* is called, the writeback for all dirty pages had already finished
* with errors - because we were not using AS_EIO/AS_ENOSPC,
* filemap_fdatawait_range() would return success, as it could not know
* that writeback errors happened (the pages were no longer tagged for
* writeback).
*/
switch (eb->log_index) {
case -1:
set_bit(BTRFS_FS_BTREE_ERR, &fs_info->flags);
break;
case 0:
set_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags);
break;
case 1:
set_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags);
break;
default:
BUG(); /* unexpected, logic error */
}
}
/*
* The endio specific version which won't touch any unsafe spinlock in endio
* context.
*/
static struct extent_buffer *find_extent_buffer_nolock(
const struct btrfs_fs_info *fs_info, u64 start)
{
struct extent_buffer *eb;
rcu_read_lock();
eb = radix_tree_lookup(&fs_info->buffer_radix,
start >> fs_info->sectorsize_bits);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
return eb;
}
rcu_read_unlock();
return NULL;
}
static void end_bbio_meta_write(struct btrfs_bio *bbio)
{
struct extent_buffer *eb = bbio->private;
struct btrfs_fs_info *fs_info = eb->fs_info;
bool uptodate = !bbio->bio.bi_status;
struct folio_iter fi;
u32 bio_offset = 0;
if (!uptodate)
set_btree_ioerr(eb);
bio_for_each_folio_all(fi, &bbio->bio) {
u64 start = eb->start + bio_offset;
struct folio *folio = fi.folio;
u32 len = fi.length;
btrfs_folio_clear_writeback(fs_info, folio, start, len);
bio_offset += len;
}
clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
smp_mb__after_atomic();
wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
bio_put(&bbio->bio);
}
static void prepare_eb_write(struct extent_buffer *eb)
{
u32 nritems;
unsigned long start;
unsigned long end;
clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
/* Set btree blocks beyond nritems with 0 to avoid stale content */
nritems = btrfs_header_nritems(eb);
if (btrfs_header_level(eb) > 0) {
end = btrfs_node_key_ptr_offset(eb, nritems);
memzero_extent_buffer(eb, end, eb->len - end);
} else {
/*
* Leaf:
* header 0 1 2 .. N ... data_N .. data_2 data_1 data_0
*/
start = btrfs_item_nr_offset(eb, nritems);
end = btrfs_item_nr_offset(eb, 0);
if (nritems == 0)
end += BTRFS_LEAF_DATA_SIZE(eb->fs_info);
else
end += btrfs_item_offset(eb, nritems - 1);
memzero_extent_buffer(eb, start, end - start);
}
}
static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
struct writeback_control *wbc)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_bio *bbio;
prepare_eb_write(eb);
bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES,
REQ_OP_WRITE | REQ_META | wbc_to_write_flags(wbc),
eb->fs_info, end_bbio_meta_write, eb);
bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT;
bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev);
wbc_init_bio(wbc, &bbio->bio);
bbio->inode = BTRFS_I(eb->fs_info->btree_inode);
bbio->file_offset = eb->start;
if (fs_info->nodesize < PAGE_SIZE) {
struct folio *folio = eb->folios[0];
bool ret;
folio_lock(folio);
btrfs_subpage_set_writeback(fs_info, folio, eb->start, eb->len);
if (btrfs_subpage_clear_and_test_dirty(fs_info, folio, eb->start,
eb->len)) {
folio_clear_dirty_for_io(folio);
wbc->nr_to_write--;
}
ret = bio_add_folio(&bbio->bio, folio, eb->len,
eb->start - folio_pos(folio));
ASSERT(ret);
wbc_account_cgroup_owner(wbc, folio_page(folio, 0), eb->len);
folio_unlock(folio);
} else {
int num_folios = num_extent_folios(eb);
for (int i = 0; i < num_folios; i++) {
struct folio *folio = eb->folios[i];
bool ret;
folio_lock(folio);
folio_clear_dirty_for_io(folio);
folio_start_writeback(folio);
ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
ASSERT(ret);
wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
eb->folio_size);
wbc->nr_to_write -= folio_nr_pages(folio);
folio_unlock(folio);
}
}
btrfs_submit_bbio(bbio, 0);
}
/*
* Submit one subpage btree page.
*
* The main difference to submit_eb_page() is:
* - Page locking
* For subpage, we don't rely on page locking at all.
*
* - Flush write bio
* We only flush bio if we may be unable to fit current extent buffers into
* current bio.
*
* Return >=0 for the number of submitted extent buffers.
* Return <0 for fatal error.
*/
static int submit_eb_subpage(struct folio *folio, struct writeback_control *wbc)
{
struct btrfs_fs_info *fs_info = folio_to_fs_info(folio);
int submitted = 0;
u64 folio_start = folio_pos(folio);
int bit_start = 0;
int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits;
/* Lock and write each dirty extent buffers in the range */
while (bit_start < fs_info->sectors_per_page) {
struct btrfs_subpage *subpage = folio_get_private(folio);
struct extent_buffer *eb;
unsigned long flags;
u64 start;
/*
* Take private lock to ensure the subpage won't be detached
* in the meantime.
*/
spin_lock(&folio->mapping->i_private_lock);
if (!folio_test_private(folio)) {
spin_unlock(&folio->mapping->i_private_lock);
break;
}
spin_lock_irqsave(&subpage->lock, flags);
if (!test_bit(bit_start + btrfs_bitmap_nr_dirty * fs_info->sectors_per_page,
subpage->bitmaps)) {
spin_unlock_irqrestore(&subpage->lock, flags);
spin_unlock(&folio->mapping->i_private_lock);
bit_start++;
continue;
}
start = folio_start + bit_start * fs_info->sectorsize;
bit_start += sectors_per_node;
/*
* Here we just want to grab the eb without touching extra
* spin locks, so call find_extent_buffer_nolock().
*/
eb = find_extent_buffer_nolock(fs_info, start);
spin_unlock_irqrestore(&subpage->lock, flags);
spin_unlock(&folio->mapping->i_private_lock);
/*
* The eb has already reached 0 refs thus find_extent_buffer()
* doesn't return it. We don't need to write back such eb
* anyway.
*/
if (!eb)
continue;
if (lock_extent_buffer_for_io(eb, wbc)) {
write_one_eb(eb, wbc);
submitted++;
}
free_extent_buffer(eb);
}
return submitted;
}
/*
* Submit all page(s) of one extent buffer.
*
* @page: the page of one extent buffer
* @eb_context: to determine if we need to submit this page, if current page
* belongs to this eb, we don't need to submit
*
* The caller should pass each page in their bytenr order, and here we use
* @eb_context to determine if we have submitted pages of one extent buffer.
*
* If we have, we just skip until we hit a new page that doesn't belong to
* current @eb_context.
*
* If not, we submit all the page(s) of the extent buffer.
*
* Return >0 if we have submitted the extent buffer successfully.
* Return 0 if we don't need to submit the page, as it's already submitted by
* previous call.
* Return <0 for fatal error.
*/
static int submit_eb_page(struct folio *folio, struct btrfs_eb_write_context *ctx)
{
struct writeback_control *wbc = ctx->wbc;
struct address_space *mapping = folio->mapping;
struct extent_buffer *eb;
int ret;
if (!folio_test_private(folio))
return 0;
if (folio_to_fs_info(folio)->nodesize < PAGE_SIZE)
return submit_eb_subpage(folio, wbc);
spin_lock(&mapping->i_private_lock);
if (!folio_test_private(folio)) {
spin_unlock(&mapping->i_private_lock);
return 0;
}
eb = folio_get_private(folio);
/*
* Shouldn't happen and normally this would be a BUG_ON but no point
* crashing the machine for something we can survive anyway.
*/
if (WARN_ON(!eb)) {
spin_unlock(&mapping->i_private_lock);
return 0;
}
if (eb == ctx->eb) {
spin_unlock(&mapping->i_private_lock);
return 0;
}
ret = atomic_inc_not_zero(&eb->refs);
spin_unlock(&mapping->i_private_lock);
if (!ret)
return 0;
ctx->eb = eb;
ret = btrfs_check_meta_write_pointer(eb->fs_info, ctx);
if (ret) {
if (ret == -EBUSY)
ret = 0;
free_extent_buffer(eb);
return ret;
}
if (!lock_extent_buffer_for_io(eb, wbc)) {
free_extent_buffer(eb);
return 0;
}
/* Implies write in zoned mode. */
if (ctx->zoned_bg) {
/* Mark the last eb in the block group. */
btrfs_schedule_zone_finish_bg(ctx->zoned_bg, eb);
ctx->zoned_bg->meta_write_pointer += eb->len;
}
write_one_eb(eb, wbc);
free_extent_buffer(eb);
return 1;
}
int btree_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct btrfs_eb_write_context ctx = { .wbc = wbc };
struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host);
int ret = 0;
int done = 0;
int nr_to_write_done = 0;
struct folio_batch fbatch;
unsigned int nr_folios;
pgoff_t index;
pgoff_t end; /* Inclusive */
int scanned = 0;
xa_mark_t tag;
folio_batch_init(&fbatch);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
/*
* Start from the beginning does not need to cycle over the
* range, mark it as scanned.
*/
scanned = (index == 0);
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
scanned = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
btrfs_zoned_meta_io_lock(fs_info);
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
while (!done && !nr_to_write_done && (index <= end) &&
(nr_folios = filemap_get_folios_tag(mapping, &index, end,
tag, &fbatch))) {
unsigned i;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
ret = submit_eb_page(folio, &ctx);
if (ret == 0)
continue;
if (ret < 0) {
done = 1;
break;
}
/*
* the filesystem may choose to bump up nr_to_write.
* We have to make sure to honor the new nr_to_write
* at any time
*/
nr_to_write_done = wbc->nr_to_write <= 0;
}
folio_batch_release(&fbatch);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
goto retry;
}
/*
* If something went wrong, don't allow any metadata write bio to be
* submitted.
*
* This would prevent use-after-free if we had dirty pages not
* cleaned up, which can still happen by fuzzed images.
*
* - Bad extent tree
* Allowing existing tree block to be allocated for other trees.
*
* - Log tree operations
* Exiting tree blocks get allocated to log tree, bumps its
* generation, then get cleaned in tree re-balance.
* Such tree block will not be written back, since it's clean,
* thus no WRITTEN flag set.
* And after log writes back, this tree block is not traced by
* any dirty extent_io_tree.
*
* - Offending tree block gets re-dirtied from its original owner
* Since it has bumped generation, no WRITTEN flag, it can be
* reused without COWing. This tree block will not be traced
* by btrfs_transaction::dirty_pages.
*
* Now such dirty tree block will not be cleaned by any dirty
* extent io tree. Thus we don't want to submit such wild eb
* if the fs already has error.
*
* We can get ret > 0 from submit_extent_folio() indicating how many ebs
* were submitted. Reset it to 0 to avoid false alerts for the caller.
*/
if (ret > 0)
ret = 0;
if (!ret && BTRFS_FS_ERROR(fs_info))
ret = -EROFS;
if (ctx.zoned_bg)
btrfs_put_block_group(ctx.zoned_bg);
btrfs_zoned_meta_io_unlock(fs_info);
return ret;
}
/*
* Walk the list of dirty pages of the given address space and write all of them.
*
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @bio_ctrl: holds context for the write, namely the bio
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
static int extent_write_cache_pages(struct address_space *mapping,
struct btrfs_bio_ctrl *bio_ctrl)
{
struct writeback_control *wbc = bio_ctrl->wbc;
struct inode *inode = mapping->host;
int ret = 0;
int done = 0;
int nr_to_write_done = 0;
struct folio_batch fbatch;
unsigned int nr_folios;
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int range_whole = 0;
int scanned = 0;
xa_mark_t tag;
/*
* We have to hold onto the inode so that ordered extents can do their
* work when the IO finishes. The alternative to this is failing to add
* an ordered extent if the igrab() fails there and that is a huge pain
* to deal with, so instead just hold onto the inode throughout the
* writepages operation. If it fails here we are freeing up the inode
* anyway and we'd rather not waste our time writing out stuff that is
* going to be truncated anyway.
*/
if (!igrab(inode))
return 0;
folio_batch_init(&fbatch);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
/*
* Start from the beginning does not need to cycle over the
* range, mark it as scanned.
*/
scanned = (index == 0);
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
scanned = 1;
}
/*
* We do the tagged writepage as long as the snapshot flush bit is set
* and we are the first one who do the filemap_flush() on this inode.
*
* The nr_to_write == LONG_MAX is needed to make sure other flushers do
* not race in and drop the bit.
*/
if (range_whole && wbc->nr_to_write == LONG_MAX &&
test_and_clear_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
&BTRFS_I(inode)->runtime_flags))
wbc->tagged_writepages = 1;
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && !nr_to_write_done && (index <= end) &&
(nr_folios = filemap_get_folios_tag(mapping, &index,
end, tag, &fbatch))) {
unsigned i;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
done_index = folio_next_index(folio);
/*
* At this point we hold neither the i_pages lock nor
* the page lock: the page may be truncated or
* invalidated (changing page->mapping to NULL),
* or even swizzled back from swapper_space to
* tmpfs file mapping
*/
if (!folio_trylock(folio)) {
submit_write_bio(bio_ctrl, 0);
folio_lock(folio);
}
if (unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
continue;
}
if (!folio_test_dirty(folio)) {
/* Someone wrote it for us. */
folio_unlock(folio);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
folio_wait_writeback(folio);
}
if (folio_test_writeback(folio) ||
!folio_clear_dirty_for_io(folio)) {
folio_unlock(folio);
continue;
}
ret = extent_writepage(folio, bio_ctrl);
if (ret < 0) {
done = 1;
break;
}
/*
* The filesystem may choose to bump up nr_to_write.
* We have to make sure to honor the new nr_to_write
* at any time.
*/
nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE &&
wbc->nr_to_write <= 0);
}
folio_batch_release(&fbatch);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
/*
* If we're looping we could run into a page that is locked by a
* writer and that writer could be waiting on writeback for a
* page in our current bio, and thus deadlock, so flush the
* write bio here.
*/
submit_write_bio(bio_ctrl, 0);
goto retry;
}
if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
mapping->writeback_index = done_index;
btrfs_add_delayed_iput(BTRFS_I(inode));
return ret;
}
/*
* Submit the pages in the range to bio for call sites which delalloc range has
* already been ran (aka, ordered extent inserted) and all pages are still
* locked.
*/
void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio,
u64 start, u64 end, struct writeback_control *wbc,
bool pages_dirty)
{
bool found_error = false;
int ret = 0;
struct address_space *mapping = inode->i_mapping;
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
const u32 sectorsize = fs_info->sectorsize;
loff_t i_size = i_size_read(inode);
u64 cur = start;
struct btrfs_bio_ctrl bio_ctrl = {
.wbc = wbc,
.opf = REQ_OP_WRITE | wbc_to_write_flags(wbc),
};
if (wbc->no_cgroup_owner)
bio_ctrl.opf |= REQ_BTRFS_CGROUP_PUNT;
ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(end + 1, sectorsize));
while (cur <= end) {
u64 cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1, end);
u32 cur_len = cur_end + 1 - cur;
struct folio *folio;
folio = __filemap_get_folio(mapping, cur >> PAGE_SHIFT, 0, 0);
/*
* This shouldn't happen, the pages are pinned and locked, this
* code is just in case, but shouldn't actually be run.
*/
if (IS_ERR(folio)) {
btrfs_mark_ordered_io_finished(BTRFS_I(inode), NULL,
cur, cur_len, false);
mapping_set_error(mapping, PTR_ERR(folio));
cur = cur_end + 1;
continue;
}
ASSERT(folio_test_locked(folio));
if (pages_dirty && folio != locked_folio)
ASSERT(folio_test_dirty(folio));
/*
* Set the submission bitmap to submit all sectors.
* extent_writepage_io() will do the truncation correctly.
*/
bio_ctrl.submit_bitmap = (unsigned long)-1;
ret = extent_writepage_io(BTRFS_I(inode), folio, cur, cur_len,
&bio_ctrl, i_size);
if (ret == 1)
goto next_page;
if (ret) {
btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio,
cur, cur_len, !ret);
mapping_set_error(mapping, ret);
}
btrfs_folio_end_writer_lock(fs_info, folio, cur, cur_len);
if (ret < 0)
found_error = true;
next_page:
folio_put(folio);
cur = cur_end + 1;
}
submit_write_bio(&bio_ctrl, found_error ? ret : 0);
}
int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
int ret = 0;
struct btrfs_bio_ctrl bio_ctrl = {
.wbc = wbc,
.opf = REQ_OP_WRITE | wbc_to_write_flags(wbc),
};
/*
* Allow only a single thread to do the reloc work in zoned mode to
* protect the write pointer updates.
*/
btrfs_zoned_data_reloc_lock(BTRFS_I(inode));
ret = extent_write_cache_pages(mapping, &bio_ctrl);
submit_write_bio(&bio_ctrl, ret);
btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
return ret;
}
void btrfs_readahead(struct readahead_control *rac)
{
struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD };
struct folio *folio;
struct extent_map *em_cached = NULL;
u64 prev_em_start = (u64)-1;
while ((folio = readahead_folio(rac)) != NULL)
btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);
if (em_cached)
free_extent_map(em_cached);
submit_one_bio(&bio_ctrl);
}
/*
* basic invalidate_folio code, this waits on any locked or writeback
* ranges corresponding to the folio, and then deletes any extent state
* records from the tree
*/
int extent_invalidate_folio(struct extent_io_tree *tree,
struct folio *folio, size_t offset)
{
struct extent_state *cached_state = NULL;
u64 start = folio_pos(folio);
u64 end = start + folio_size(folio) - 1;
size_t blocksize = folio_to_fs_info(folio)->sectorsize;
/* This function is only called for the btree inode */
ASSERT(tree->owner == IO_TREE_BTREE_INODE_IO);
start += ALIGN(offset, blocksize);
if (start > end)
return 0;
lock_extent(tree, start, end, &cached_state);
folio_wait_writeback(folio);
/*
* Currently for btree io tree, only EXTENT_LOCKED is utilized,
* so here we only need to unlock the extent range to free any
* existing extent state.
*/
unlock_extent(tree, start, end, &cached_state);
return 0;
}
/*
* a helper for release_folio, this tests for areas of the page that
* are locked or under IO and drops the related state bits if it is safe
* to drop the page.
*/
static bool try_release_extent_state(struct extent_io_tree *tree,
struct folio *folio, gfp_t mask)
{
u64 start = folio_pos(folio);
u64 end = start + PAGE_SIZE - 1;
bool ret;
if (test_range_bit_exists(tree, start, end, EXTENT_LOCKED)) {
ret = false;
} else {
u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
EXTENT_QGROUP_RESERVED);
int ret2;
/*
* At this point we can safely clear everything except the
* locked bit, the nodatasum bit and the delalloc new bit.
* The delalloc new bit will be cleared by ordered extent
* completion.
*/
ret2 = __clear_extent_bit(tree, start, end, clear_bits, NULL, NULL);
/* if clear_extent_bit failed for enomem reasons,
* we can't allow the release to continue.
*/
if (ret2 < 0)
ret = false;
else
ret = true;
}
return ret;
}
/*
* a helper for release_folio. As long as there are no locked extents
* in the range corresponding to the page, both state records and extent
* map records are removed
*/
bool try_release_extent_mapping(struct folio *folio, gfp_t mask)
{
u64 start = folio_pos(folio);
u64 end = start + PAGE_SIZE - 1;
struct btrfs_inode *inode = folio_to_inode(folio);
struct extent_io_tree *io_tree = &inode->io_tree;
while (start <= end) {
const u64 cur_gen = btrfs_get_fs_generation(inode->root->fs_info);
const u64 len = end - start + 1;
struct extent_map_tree *extent_tree = &inode->extent_tree;
struct extent_map *em;
write_lock(&extent_tree->lock);
em = lookup_extent_mapping(extent_tree, start, len);
if (!em) {
write_unlock(&extent_tree->lock);
break;
}
if ((em->flags & EXTENT_FLAG_PINNED) || em->start != start) {
write_unlock(&extent_tree->lock);
free_extent_map(em);
break;
}
if (test_range_bit_exists(io_tree, em->start,
extent_map_end(em) - 1, EXTENT_LOCKED))
goto next;
/*
* If it's not in the list of modified extents, used by a fast
* fsync, we can remove it. If it's being logged we can safely
* remove it since fsync took an extra reference on the em.
*/
if (list_empty(&em->list) || (em->flags & EXTENT_FLAG_LOGGING))
goto remove_em;
/*
* If it's in the list of modified extents, remove it only if
* its generation is older then the current one, in which case
* we don't need it for a fast fsync. Otherwise don't remove it,
* we could be racing with an ongoing fast fsync that could miss
* the new extent.
*/
if (em->generation >= cur_gen)
goto next;
remove_em:
/*
* We only remove extent maps that are not in the list of
* modified extents or that are in the list but with a
* generation lower then the current generation, so there is no
* need to set the full fsync flag on the inode (it hurts the
* fsync performance for workloads with a data size that exceeds
* or is close to the system's memory).
*/
remove_extent_mapping(inode, em);
/* Once for the inode's extent map tree. */
free_extent_map(em);
next:
start = extent_map_end(em);
write_unlock(&extent_tree->lock);
/* Once for us, for the lookup_extent_mapping() reference. */
free_extent_map(em);
if (need_resched()) {
/*
* If we need to resched but we can't block just exit
* and leave any remaining extent maps.
*/
if (!gfpflags_allow_blocking(mask))
break;
cond_resched();
}
}
return try_release_extent_state(io_tree, folio, mask);
}
static void __free_extent_buffer(struct extent_buffer *eb)
{
kmem_cache_free(extent_buffer_cache, eb);
}
static int extent_buffer_under_io(const struct extent_buffer *eb)
{
return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
}
static bool folio_range_has_eb(struct btrfs_fs_info *fs_info, struct folio *folio)
{
struct btrfs_subpage *subpage;
lockdep_assert_held(&folio->mapping->i_private_lock);
if (folio_test_private(folio)) {
subpage = folio_get_private(folio);
if (atomic_read(&subpage->eb_refs))
return true;
/*
* Even there is no eb refs here, we may still have
* end_folio_read() call relying on page::private.
*/
if (atomic_read(&subpage->readers))
return true;
}
return false;
}
static void detach_extent_buffer_folio(const struct extent_buffer *eb, struct folio *folio)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
/*
* For mapped eb, we're going to change the folio private, which should
* be done under the i_private_lock.
*/
if (mapped)
spin_lock(&folio->mapping->i_private_lock);
if (!folio_test_private(folio)) {
if (mapped)
spin_unlock(&folio->mapping->i_private_lock);
return;
}
if (fs_info->nodesize >= PAGE_SIZE) {
/*
* We do this since we'll remove the pages after we've
* removed the eb from the radix tree, so we could race
* and have this page now attached to the new eb. So
* only clear folio if it's still connected to
* this eb.
*/
if (folio_test_private(folio) && folio_get_private(folio) == eb) {
BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
BUG_ON(folio_test_dirty(folio));
BUG_ON(folio_test_writeback(folio));
/* We need to make sure we haven't be attached to a new eb. */
folio_detach_private(folio);
}
if (mapped)
spin_unlock(&folio->mapping->i_private_lock);
return;
}
/*
* For subpage, we can have dummy eb with folio private attached. In
* this case, we can directly detach the private as such folio is only
* attached to one dummy eb, no sharing.
*/
if (!mapped) {
btrfs_detach_subpage(fs_info, folio);
return;
}
btrfs_folio_dec_eb_refs(fs_info, folio);
/*
* We can only detach the folio private if there are no other ebs in the
* page range and no unfinished IO.
*/
if (!folio_range_has_eb(fs_info, folio))
btrfs_detach_subpage(fs_info, folio);
spin_unlock(&folio->mapping->i_private_lock);
}
/* Release all pages attached to the extent buffer */
static void btrfs_release_extent_buffer_pages(const struct extent_buffer *eb)
{
ASSERT(!extent_buffer_under_io(eb));
for (int i = 0; i < INLINE_EXTENT_BUFFER_PAGES; i++) {
struct folio *folio = eb->folios[i];
if (!folio)
continue;
detach_extent_buffer_folio(eb, folio);
/* One for when we allocated the folio. */
folio_put(folio);
}
}
/*
* Helper for releasing the extent buffer.
*/
static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
{
btrfs_release_extent_buffer_pages(eb);
btrfs_leak_debug_del_eb(eb);
__free_extent_buffer(eb);
}
static struct extent_buffer *
__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
unsigned long len)
{
struct extent_buffer *eb = NULL;
eb = kmem_cache_zalloc(extent_buffer_cache, GFP_NOFS|__GFP_NOFAIL);
eb->start = start;
eb->len = len;
eb->fs_info = fs_info;
init_rwsem(&eb->lock);
btrfs_leak_debug_add_eb(eb);
spin_lock_init(&eb->refs_lock);
atomic_set(&eb->refs, 1);
ASSERT(len <= BTRFS_MAX_METADATA_BLOCKSIZE);
return eb;
}
struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
{
struct extent_buffer *new;
int num_folios = num_extent_folios(src);
int ret;
new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
if (new == NULL)
return NULL;
/*
* Set UNMAPPED before calling btrfs_release_extent_buffer(), as
* btrfs_release_extent_buffer() have different behavior for
* UNMAPPED subpage extent buffer.
*/
set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
ret = alloc_eb_folio_array(new, false);
if (ret) {
btrfs_release_extent_buffer(new);
return NULL;
}
for (int i = 0; i < num_folios; i++) {
struct folio *folio = new->folios[i];
ret = attach_extent_buffer_folio(new, folio, NULL);
if (ret < 0) {
btrfs_release_extent_buffer(new);
return NULL;
}
WARN_ON(folio_test_dirty(folio));
}
copy_extent_buffer_full(new, src);
set_extent_buffer_uptodate(new);
return new;
}
struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len)
{
struct extent_buffer *eb;
int num_folios = 0;
int ret;
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
return NULL;
ret = alloc_eb_folio_array(eb, false);
if (ret)
goto err;
num_folios = num_extent_folios(eb);
for (int i = 0; i < num_folios; i++) {
ret = attach_extent_buffer_folio(eb, eb->folios[i], NULL);
if (ret < 0)
goto err;
}
set_extent_buffer_uptodate(eb);
btrfs_set_header_nritems(eb, 0);
set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
return eb;
err:
for (int i = 0; i < num_folios; i++) {
if (eb->folios[i]) {
detach_extent_buffer_folio(eb, eb->folios[i]);
folio_put(eb->folios[i]);
}
}
__free_extent_buffer(eb);
return NULL;
}
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
{
return __alloc_dummy_extent_buffer(fs_info, start, fs_info->nodesize);
}
static void check_buffer_tree_ref(struct extent_buffer *eb)
{
int refs;
/*
* The TREE_REF bit is first set when the extent_buffer is added
* to the radix tree. It is also reset, if unset, when a new reference
* is created by find_extent_buffer.
*
* It is only cleared in two cases: freeing the last non-tree
* reference to the extent_buffer when its STALE bit is set or
* calling release_folio when the tree reference is the only reference.
*
* In both cases, care is taken to ensure that the extent_buffer's
* pages are not under io. However, release_folio can be concurrently
* called with creating new references, which is prone to race
* conditions between the calls to check_buffer_tree_ref in those
* codepaths and clearing TREE_REF in try_release_extent_buffer.
*
* The actual lifetime of the extent_buffer in the radix tree is
* adequately protected by the refcount, but the TREE_REF bit and
* its corresponding reference are not. To protect against this
* class of races, we call check_buffer_tree_ref from the codepaths
* which trigger io. Note that once io is initiated, TREE_REF can no
* longer be cleared, so that is the moment at which any such race is
* best fixed.
*/
refs = atomic_read(&eb->refs);
if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
return;
spin_lock(&eb->refs_lock);
if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
atomic_inc(&eb->refs);
spin_unlock(&eb->refs_lock);
}
static void mark_extent_buffer_accessed(struct extent_buffer *eb)
{
int num_folios= num_extent_folios(eb);
check_buffer_tree_ref(eb);
for (int i = 0; i < num_folios; i++)
folio_mark_accessed(eb->folios[i]);
}
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
{
struct extent_buffer *eb;
eb = find_extent_buffer_nolock(fs_info, start);
if (!eb)
return NULL;
/*
* Lock our eb's refs_lock to avoid races with free_extent_buffer().
* When we get our eb it might be flagged with EXTENT_BUFFER_STALE and
* another task running free_extent_buffer() might have seen that flag
* set, eb->refs == 2, that the buffer isn't under IO (dirty and
* writeback flags not set) and it's still in the tree (flag
* EXTENT_BUFFER_TREE_REF set), therefore being in the process of
* decrementing the extent buffer's reference count twice. So here we
* could race and increment the eb's reference count, clear its stale
* flag, mark it as dirty and drop our reference before the other task
* finishes executing free_extent_buffer, which would later result in
* an attempt to free an extent buffer that is dirty.
*/
if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
spin_lock(&eb->refs_lock);
spin_unlock(&eb->refs_lock);
}
mark_extent_buffer_accessed(eb);
return eb;
}
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
{
struct extent_buffer *eb, *exists = NULL;
int ret;
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
eb = alloc_dummy_extent_buffer(fs_info, start);
if (!eb)
return ERR_PTR(-ENOMEM);
eb->fs_info = fs_info;
again:
ret = radix_tree_preload(GFP_NOFS);
if (ret) {
exists = ERR_PTR(ret);
goto free_eb;
}
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
start >> fs_info->sectorsize_bits, eb);
spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
exists = find_extent_buffer(fs_info, start);
if (exists)
goto free_eb;
else
goto again;
}
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
return eb;
free_eb:
btrfs_release_extent_buffer(eb);
return exists;
}
#endif
static struct extent_buffer *grab_extent_buffer(
struct btrfs_fs_info *fs_info, struct page *page)
{
struct folio *folio = page_folio(page);
struct extent_buffer *exists;
lockdep_assert_held(&page->mapping->i_private_lock);
/*
* For subpage case, we completely rely on radix tree to ensure we
* don't try to insert two ebs for the same bytenr. So here we always
* return NULL and just continue.
*/
if (fs_info->nodesize < PAGE_SIZE)
return NULL;
/* Page not yet attached to an extent buffer */
if (!folio_test_private(folio))
return NULL;
/*
* We could have already allocated an eb for this page and attached one
* so lets see if we can get a ref on the existing eb, and if we can we
* know it's good and we can just return that one, else we know we can
* just overwrite folio private.
*/
exists = folio_get_private(folio);
if (atomic_inc_not_zero(&exists->refs))
return exists;
WARN_ON(PageDirty(page));
folio_detach_private(folio);
return NULL;
}
static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
{
if (!IS_ALIGNED(start, fs_info->sectorsize)) {
btrfs_err(fs_info, "bad tree block start %llu", start);
return -EINVAL;
}
if (fs_info->nodesize < PAGE_SIZE &&
offset_in_page(start) + fs_info->nodesize > PAGE_SIZE) {
btrfs_err(fs_info,
"tree block crosses page boundary, start %llu nodesize %u",
start, fs_info->nodesize);
return -EINVAL;
}
if (fs_info->nodesize >= PAGE_SIZE &&
!PAGE_ALIGNED(start)) {
btrfs_err(fs_info,
"tree block is not page aligned, start %llu nodesize %u",
start, fs_info->nodesize);
return -EINVAL;
}
if (!IS_ALIGNED(start, fs_info->nodesize) &&
!test_and_set_bit(BTRFS_FS_UNALIGNED_TREE_BLOCK, &fs_info->flags)) {
btrfs_warn(fs_info,
"tree block not nodesize aligned, start %llu nodesize %u, can be resolved by a full metadata balance",
start, fs_info->nodesize);
}
return 0;
}
/*
* Return 0 if eb->folios[i] is attached to btree inode successfully.
* Return >0 if there is already another extent buffer for the range,
* and @found_eb_ret would be updated.
* Return -EAGAIN if the filemap has an existing folio but with different size
* than @eb.
* The caller needs to free the existing folios and retry using the same order.
*/
static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i,
struct btrfs_subpage *prealloc,
struct extent_buffer **found_eb_ret)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct address_space *mapping = fs_info->btree_inode->i_mapping;
const unsigned long index = eb->start >> PAGE_SHIFT;
struct folio *existing_folio = NULL;
int ret;
ASSERT(found_eb_ret);
/* Caller should ensure the folio exists. */
ASSERT(eb->folios[i]);
retry:
ret = filemap_add_folio(mapping, eb->folios[i], index + i,
GFP_NOFS | __GFP_NOFAIL);
if (!ret)
goto finish;
existing_folio = filemap_lock_folio(mapping, index + i);
/* The page cache only exists for a very short time, just retry. */
if (IS_ERR(existing_folio)) {
existing_folio = NULL;
goto retry;
}
/* For now, we should only have single-page folios for btree inode. */
ASSERT(folio_nr_pages(existing_folio) == 1);
if (folio_size(existing_folio) != eb->folio_size) {
folio_unlock(existing_folio);
folio_put(existing_folio);
return -EAGAIN;
}
finish:
spin_lock(&mapping->i_private_lock);
if (existing_folio && fs_info->nodesize < PAGE_SIZE) {
/* We're going to reuse the existing page, can drop our folio now. */
__free_page(folio_page(eb->folios[i], 0));
eb->folios[i] = existing_folio;
} else if (existing_folio) {
struct extent_buffer *existing_eb;
existing_eb = grab_extent_buffer(fs_info,
folio_page(existing_folio, 0));
if (existing_eb) {
/* The extent buffer still exists, we can use it directly. */
*found_eb_ret = existing_eb;
spin_unlock(&mapping->i_private_lock);
folio_unlock(existing_folio);
folio_put(existing_folio);
return 1;
}
/* The extent buffer no longer exists, we can reuse the folio. */
__free_page(folio_page(eb->folios[i], 0));
eb->folios[i] = existing_folio;
}
eb->folio_size = folio_size(eb->folios[i]);
eb->folio_shift = folio_shift(eb->folios[i]);
/* Should not fail, as we have preallocated the memory. */
ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc);
ASSERT(!ret);
/*
* To inform we have an extra eb under allocation, so that
* detach_extent_buffer_page() won't release the folio private when the
* eb hasn't been inserted into radix tree yet.
*
* The ref will be decreased when the eb releases the page, in
* detach_extent_buffer_page(). Thus needs no special handling in the
* error path.
*/
btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]);
spin_unlock(&mapping->i_private_lock);
return 0;
}
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, u64 owner_root, int level)
{
unsigned long len = fs_info->nodesize;
int num_folios;
int attached = 0;
struct extent_buffer *eb;
struct extent_buffer *existing_eb = NULL;
struct btrfs_subpage *prealloc = NULL;
u64 lockdep_owner = owner_root;
bool page_contig = true;
int uptodate = 1;
int ret;
if (check_eb_alignment(fs_info, start))
return ERR_PTR(-EINVAL);
#if BITS_PER_LONG == 32
if (start >= MAX_LFS_FILESIZE) {
btrfs_err_rl(fs_info,
"extent buffer %llu is beyond 32bit page cache limit", start);
btrfs_err_32bit_limit(fs_info);
return ERR_PTR(-EOVERFLOW);
}
if (start >= BTRFS_32BIT_EARLY_WARN_THRESHOLD)
btrfs_warn_32bit_limit(fs_info);
#endif
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
return ERR_PTR(-ENOMEM);
/*
* The reloc trees are just snapshots, so we need them to appear to be
* just like any other fs tree WRT lockdep.
*/
if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID)
lockdep_owner = BTRFS_FS_TREE_OBJECTID;
btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
/*
* Preallocate folio private for subpage case, so that we won't
* allocate memory with i_private_lock nor page lock hold.
*
* The memory will be freed by attach_extent_buffer_page() or freed
* manually if we exit earlier.
*/
if (fs_info->nodesize < PAGE_SIZE) {
prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA);
if (IS_ERR(prealloc)) {
ret = PTR_ERR(prealloc);
goto out;
}
}
reallocate:
/* Allocate all pages first. */
ret = alloc_eb_folio_array(eb, true);
if (ret < 0) {
btrfs_free_subpage(prealloc);
goto out;
}
num_folios = num_extent_folios(eb);
/* Attach all pages to the filemap. */
for (int i = 0; i < num_folios; i++) {
struct folio *folio;
ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb);
if (ret > 0) {
ASSERT(existing_eb);
goto out;
}
/*
* TODO: Special handling for a corner case where the order of
* folios mismatch between the new eb and filemap.
*
* This happens when:
*
* - the new eb is using higher order folio
*
* - the filemap is still using 0-order folios for the range
* This can happen at the previous eb allocation, and we don't
* have higher order folio for the call.
*
* - the existing eb has already been freed
*
* In this case, we have to free the existing folios first, and
* re-allocate using the same order.
* Thankfully this is not going to happen yet, as we're still
* using 0-order folios.
*/
if (unlikely(ret == -EAGAIN)) {
ASSERT(0);
goto reallocate;
}
attached++;
/*
* Only after attach_eb_folio_to_filemap(), eb->folios[] is
* reliable, as we may choose to reuse the existing page cache
* and free the allocated page.
*/
folio = eb->folios[i];
WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len));
/*
* Check if the current page is physically contiguous with previous eb
* page.
* At this stage, either we allocated a large folio, thus @i
* would only be 0, or we fall back to per-page allocation.
*/
if (i && folio_page(eb->folios[i - 1], 0) + 1 != folio_page(folio, 0))
page_contig = false;
if (!btrfs_folio_test_uptodate(fs_info, folio, eb->start, eb->len))
uptodate = 0;
/*
* We can't unlock the pages just yet since the extent buffer
* hasn't been properly inserted in the radix tree, this
* opens a race with btree_release_folio which can free a page
* while we are still filling in all pages for the buffer and
* we could crash.
*/
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
/* All pages are physically contiguous, can skip cross page handling. */
if (page_contig)
eb->addr = folio_address(eb->folios[0]) + offset_in_page(eb->start);
again:
ret = radix_tree_preload(GFP_NOFS);
if (ret)
goto out;
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
start >> fs_info->sectorsize_bits, eb);
spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
ret = 0;
existing_eb = find_extent_buffer(fs_info, start);
if (existing_eb)
goto out;
else
goto again;
}
/* add one reference for the tree */
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
/*
* Now it's safe to unlock the pages because any calls to
* btree_release_folio will correctly detect that a page belongs to a
* live buffer and won't free them prematurely.
*/
for (int i = 0; i < num_folios; i++)
unlock_page(folio_page(eb->folios[i], 0));
return eb;
out:
WARN_ON(!atomic_dec_and_test(&eb->refs));
/*
* Any attached folios need to be detached before we unlock them. This
* is because when we're inserting our new folios into the mapping, and
* then attaching our eb to that folio. If we fail to insert our folio
* we'll lookup the folio for that index, and grab that EB. We do not
* want that to grab this eb, as we're getting ready to free it. So we
* have to detach it first and then unlock it.
*
* We have to drop our reference and NULL it out here because in the
* subpage case detaching does a btrfs_folio_dec_eb_refs() for our eb.
* Below when we call btrfs_release_extent_buffer() we will call
* detach_extent_buffer_folio() on our remaining pages in the !subpage
* case. If we left eb->folios[i] populated in the subpage case we'd
* double put our reference and be super sad.
*/
for (int i = 0; i < attached; i++) {
ASSERT(eb->folios[i]);
detach_extent_buffer_folio(eb, eb->folios[i]);
unlock_page(folio_page(eb->folios[i], 0));
folio_put(eb->folios[i]);
eb->folios[i] = NULL;
}
/*
* Now all pages of that extent buffer is unmapped, set UNMAPPED flag,
* so it can be cleaned up without utlizing page->mapping.
*/
set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
btrfs_release_extent_buffer(eb);
if (ret < 0)
return ERR_PTR(ret);
ASSERT(existing_eb);
return existing_eb;
}
static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
{
struct extent_buffer *eb =
container_of(head, struct extent_buffer, rcu_head);
__free_extent_buffer(eb);
}
static int release_extent_buffer(struct extent_buffer *eb)
__releases(&eb->refs_lock)
{
lockdep_assert_held(&eb->refs_lock);
WARN_ON(atomic_read(&eb->refs) == 0);
if (atomic_dec_and_test(&eb->refs)) {
if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
struct btrfs_fs_info *fs_info = eb->fs_info;
spin_unlock(&eb->refs_lock);
spin_lock(&fs_info->buffer_lock);
radix_tree_delete(&fs_info->buffer_radix,
eb->start >> fs_info->sectorsize_bits);
spin_unlock(&fs_info->buffer_lock);
} else {
spin_unlock(&eb->refs_lock);
}
btrfs_leak_debug_del_eb(eb);
/* Should be safe to release our pages at this point */
btrfs_release_extent_buffer_pages(eb);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) {
__free_extent_buffer(eb);
return 1;
}
#endif
call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
return 1;
}
spin_unlock(&eb->refs_lock);
return 0;
}
void free_extent_buffer(struct extent_buffer *eb)
{
int refs;
if (!eb)
return;
refs = atomic_read(&eb->refs);
while (1) {
if ((!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags) && refs <= 3)
|| (test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags) &&
refs == 1))
break;
if (atomic_try_cmpxchg(&eb->refs, &refs, refs - 1))
return;
}
spin_lock(&eb->refs_lock);
if (atomic_read(&eb->refs) == 2 &&
test_bit(EXTENT_BUFFER_STALE, &eb->bflags) &&
!extent_buffer_under_io(eb) &&
test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
atomic_dec(&eb->refs);
/*
* I know this is terrible, but it's temporary until we stop tracking
* the uptodate bits and such for the extent buffers.
*/
release_extent_buffer(eb);
}
void free_extent_buffer_stale(struct extent_buffer *eb)
{
if (!eb)
return;
spin_lock(&eb->refs_lock);
set_bit(EXTENT_BUFFER_STALE, &eb->bflags);
if (atomic_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) &&
test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
atomic_dec(&eb->refs);
release_extent_buffer(eb);
}
static void btree_clear_folio_dirty(struct folio *folio)
{
ASSERT(folio_test_dirty(folio));
ASSERT(folio_test_locked(folio));
folio_clear_dirty_for_io(folio);
xa_lock_irq(&folio->mapping->i_pages);
if (!folio_test_dirty(folio))
__xa_clear_mark(&folio->mapping->i_pages,
folio_index(folio), PAGECACHE_TAG_DIRTY);
xa_unlock_irq(&folio->mapping->i_pages);
}
static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct folio *folio = eb->folios[0];
bool last;
/* btree_clear_folio_dirty() needs page locked. */
folio_lock(folio);
last = btrfs_subpage_clear_and_test_dirty(fs_info, folio, eb->start, eb->len);
if (last)
btree_clear_folio_dirty(folio);
folio_unlock(folio);
WARN_ON(atomic_read(&eb->refs) == 0);
}
void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
int num_folios;
btrfs_assert_tree_write_locked(eb);
if (trans && btrfs_header_generation(eb) != trans->transid)
return;
/*
* Instead of clearing the dirty flag off of the buffer, mark it as
* EXTENT_BUFFER_ZONED_ZEROOUT. This allows us to preserve
* write-ordering in zoned mode, without the need to later re-dirty
* the extent_buffer.
*
* The actual zeroout of the buffer will happen later in
* btree_csum_one_bio.
*/
if (btrfs_is_zoned(fs_info) && test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags);
return;
}
if (!test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags))
return;
percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len,
fs_info->dirty_metadata_batch);
if (eb->fs_info->nodesize < PAGE_SIZE)
return clear_subpage_extent_buffer_dirty(eb);
num_folios = num_extent_folios(eb);
for (int i = 0; i < num_folios; i++) {
struct folio *folio = eb->folios[i];
if (!folio_test_dirty(folio))
continue;
folio_lock(folio);
btree_clear_folio_dirty(folio);
folio_unlock(folio);
}
WARN_ON(atomic_read(&eb->refs) == 0);
}
void set_extent_buffer_dirty(struct extent_buffer *eb)
{
int num_folios;
bool was_dirty;
check_buffer_tree_ref(eb);
was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
num_folios = num_extent_folios(eb);
WARN_ON(atomic_read(&eb->refs) == 0);
WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
WARN_ON(test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags));
if (!was_dirty) {
bool subpage = eb->fs_info->nodesize < PAGE_SIZE;
/*
* For subpage case, we can have other extent buffers in the
* same page, and in clear_subpage_extent_buffer_dirty() we
* have to clear page dirty without subpage lock held.
* This can cause race where our page gets dirty cleared after
* we just set it.
*
* Thankfully, clear_subpage_extent_buffer_dirty() has locked
* its page for other reasons, we can use page lock to prevent
* the above race.
*/
if (subpage)
lock_page(folio_page(eb->folios[0], 0));
for (int i = 0; i < num_folios; i++)
btrfs_folio_set_dirty(eb->fs_info, eb->folios[i],
eb->start, eb->len);
if (subpage)
unlock_page(folio_page(eb->folios[0], 0));
percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes,
eb->len,
eb->fs_info->dirty_metadata_batch);
}
#ifdef CONFIG_BTRFS_DEBUG
for (int i = 0; i < num_folios; i++)
ASSERT(folio_test_dirty(eb->folios[i]));
#endif
}
void clear_extent_buffer_uptodate(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
int num_folios = num_extent_folios(eb);
clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
for (int i = 0; i < num_folios; i++) {
struct folio *folio = eb->folios[i];
if (!folio)
continue;
/*
* This is special handling for metadata subpage, as regular
* btrfs_is_subpage() can not handle cloned/dummy metadata.
*/
if (fs_info->nodesize >= PAGE_SIZE)
folio_clear_uptodate(folio);
else
btrfs_subpage_clear_uptodate(fs_info, folio,
eb->start, eb->len);
}
}
void set_extent_buffer_uptodate(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
int num_folios = num_extent_folios(eb);
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
for (int i = 0; i < num_folios; i++) {
struct folio *folio = eb->folios[i];
/*
* This is special handling for metadata subpage, as regular
* btrfs_is_subpage() can not handle cloned/dummy metadata.
*/
if (fs_info->nodesize >= PAGE_SIZE)
folio_mark_uptodate(folio);
else
btrfs_subpage_set_uptodate(fs_info, folio,
eb->start, eb->len);
}
}
static void clear_extent_buffer_reading(struct extent_buffer *eb)
{
clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
smp_mb__after_atomic();
wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
}
static void end_bbio_meta_read(struct btrfs_bio *bbio)
{
struct extent_buffer *eb = bbio->private;
struct btrfs_fs_info *fs_info = eb->fs_info;
bool uptodate = !bbio->bio.bi_status;
struct folio_iter fi;
u32 bio_offset = 0;
/*
* If the extent buffer is marked UPTODATE before the read operation
* completes, other calls to read_extent_buffer_pages() will return
* early without waiting for the read to finish, causing data races.
*/
WARN_ON(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags));
eb->read_mirror = bbio->mirror_num;
if (uptodate &&
btrfs_validate_extent_buffer(eb, &bbio->parent_check) < 0)
uptodate = false;
if (uptodate) {
set_extent_buffer_uptodate(eb);
} else {
clear_extent_buffer_uptodate(eb);
set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
}
bio_for_each_folio_all(fi, &bbio->bio) {
struct folio *folio = fi.folio;
u64 start = eb->start + bio_offset;
u32 len = fi.length;
if (uptodate)
btrfs_folio_set_uptodate(fs_info, folio, start, len);
else
btrfs_folio_clear_uptodate(fs_info, folio, start, len);
bio_offset += len;
}
clear_extent_buffer_reading(eb);
free_extent_buffer(eb);
bio_put(&bbio->bio);
}
int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
const struct btrfs_tree_parent_check *check)
{
struct btrfs_bio *bbio;
bool ret;
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
return 0;
/*
* We could have had EXTENT_BUFFER_UPTODATE cleared by the write
* operation, which could potentially still be in flight. In this case
* we simply want to return an error.
*/
if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)))
return -EIO;
/* Someone else is already reading the buffer, just wait for it. */
if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags))
goto done;
/*
* Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above
* test_and_set_bit(EXTENT_BUFFER_READING), someone else could have
* started and finished reading the same eb. In this case, UPTODATE
* will now be set, and we shouldn't read it in again.
*/
if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) {
clear_extent_buffer_reading(eb);
return 0;
}
clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = 0;
check_buffer_tree_ref(eb);
atomic_inc(&eb->refs);
bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES,
REQ_OP_READ | REQ_META, eb->fs_info,
end_bbio_meta_read, eb);
bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT;
bbio->inode = BTRFS_I(eb->fs_info->btree_inode);
bbio->file_offset = eb->start;
memcpy(&bbio->parent_check, check, sizeof(*check));
if (eb->fs_info->nodesize < PAGE_SIZE) {
ret = bio_add_folio(&bbio->bio, eb->folios[0], eb->len,
eb->start - folio_pos(eb->folios[0]));
ASSERT(ret);
} else {
int num_folios = num_extent_folios(eb);
for (int i = 0; i < num_folios; i++) {
struct folio *folio = eb->folios[i];
ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
ASSERT(ret);
}
}
btrfs_submit_bbio(bbio, mirror_num);
done:
if (wait == WAIT_COMPLETE) {
wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE);
if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
return -EIO;
}
return 0;
}
static bool report_eb_range(const struct extent_buffer *eb, unsigned long start,
unsigned long len)
{
btrfs_warn(eb->fs_info,
"access to eb bytenr %llu len %u out of range start %lu len %lu",
eb->start, eb->len, start, len);
WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
return true;
}
/*
* Check if the [start, start + len) range is valid before reading/writing
* the eb.
* NOTE: @start and @len are offset inside the eb, not logical address.
*
* Caller should not touch the dst/src memory if this function returns error.
*/
static inline int check_eb_range(const struct extent_buffer *eb,
unsigned long start, unsigned long len)
{
unsigned long offset;
/* start, start + len should not go beyond eb->len nor overflow */
if (unlikely(check_add_overflow(start, len, &offset) || offset > eb->len))
return report_eb_range(eb, start, len);
return false;
}
void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
unsigned long start, unsigned long len)
{
const int unit_size = eb->folio_size;
size_t cur;
size_t offset;
char *dst = (char *)dstv;
unsigned long i = get_eb_folio_index(eb, start);
if (check_eb_range(eb, start, len)) {
/*
* Invalid range hit, reset the memory, so callers won't get
* some random garbage for their uninitialized memory.
*/
memset(dstv, 0, len);
return;
}
if (eb->addr) {
memcpy(dstv, eb->addr + start, len);
return;
}
offset = get_eb_offset_in_folio(eb, start);
while (len > 0) {
char *kaddr;
cur = min(len, unit_size - offset);
kaddr = folio_address(eb->folios[i]);
memcpy(dst, kaddr + offset, cur);
dst += cur;
len -= cur;
offset = 0;
i++;
}
}
int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
void __user *dstv,
unsigned long start, unsigned long len)
{
const int unit_size = eb->folio_size;
size_t cur;
size_t offset;
char __user *dst = (char __user *)dstv;
unsigned long i = get_eb_folio_index(eb, start);
int ret = 0;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
if (eb->addr) {
if (copy_to_user_nofault(dstv, eb->addr + start, len))
ret = -EFAULT;
return ret;
}
offset = get_eb_offset_in_folio(eb, start);
while (len > 0) {
char *kaddr;
cur = min(len, unit_size - offset);
kaddr = folio_address(eb->folios[i]);
if (copy_to_user_nofault(dst, kaddr + offset, cur)) {
ret = -EFAULT;
break;
}
dst += cur;
len -= cur;
offset = 0;
i++;
}
return ret;
}
int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
unsigned long start, unsigned long len)
{
const int unit_size = eb->folio_size;
size_t cur;
size_t offset;
char *kaddr;
char *ptr = (char *)ptrv;
unsigned long i = get_eb_folio_index(eb, start);
int ret = 0;
if (check_eb_range(eb, start, len))
return -EINVAL;
if (eb->addr)
return memcmp(ptrv, eb->addr + start, len);
offset = get_eb_offset_in_folio(eb, start);
while (len > 0) {
cur = min(len, unit_size - offset);
kaddr = folio_address(eb->folios[i]);
ret = memcmp(ptr, kaddr + offset, cur);
if (ret)
break;
ptr += cur;
len -= cur;
offset = 0;
i++;
}
return ret;
}
/*
* Check that the extent buffer is uptodate.
*
* For regular sector size == PAGE_SIZE case, check if @page is uptodate.
* For subpage case, check if the range covered by the eb has EXTENT_UPTODATE.
*/
static void assert_eb_folio_uptodate(const struct extent_buffer *eb, int i)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct folio *folio = eb->folios[i];
ASSERT(folio);
/*
* If we are using the commit root we could potentially clear a page
* Uptodate while we're using the extent buffer that we've previously
* looked up. We don't want to complain in this case, as the page was
* valid before, we just didn't write it out. Instead we want to catch
* the case where we didn't actually read the block properly, which
* would have !PageUptodate and !EXTENT_BUFFER_WRITE_ERR.
*/
if (test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
return;
if (fs_info->nodesize < PAGE_SIZE) {
folio = eb->folios[0];
ASSERT(i == 0);
if (WARN_ON(!btrfs_subpage_test_uptodate(fs_info, folio,
eb->start, eb->len)))
btrfs_subpage_dump_bitmap(fs_info, folio, eb->start, eb->len);
} else {
WARN_ON(!folio_test_uptodate(folio));
}
}
static void __write_extent_buffer(const struct extent_buffer *eb,
const void *srcv, unsigned long start,
unsigned long len, bool use_memmove)
{
const int unit_size = eb->folio_size;
size_t cur;
size_t offset;
char *kaddr;
const char *src = (const char *)srcv;
unsigned long i = get_eb_folio_index(eb, start);
/* For unmapped (dummy) ebs, no need to check their uptodate status. */
const bool check_uptodate = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
if (check_eb_range(eb, start, len))
return;
if (eb->addr) {
if (use_memmove)
memmove(eb->addr + start, srcv, len);
else
memcpy(eb->addr + start, srcv, len);
return;
}
offset = get_eb_offset_in_folio(eb, start);
while (len > 0) {
if (check_uptodate)
assert_eb_folio_uptodate(eb, i);
cur = min(len, unit_size - offset);
kaddr = folio_address(eb->folios[i]);
if (use_memmove)
memmove(kaddr + offset, src, cur);
else
memcpy(kaddr + offset, src, cur);
src += cur;
len -= cur;
offset = 0;
i++;
}
}
void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
unsigned long start, unsigned long len)
{
return __write_extent_buffer(eb, srcv, start, len, false);
}
static void memset_extent_buffer(const struct extent_buffer *eb, int c,
unsigned long start, unsigned long len)
{
const int unit_size = eb->folio_size;
unsigned long cur = start;
if (eb->addr) {
memset(eb->addr + start, c, len);
return;
}
while (cur < start + len) {
unsigned long index = get_eb_folio_index(eb, cur);
unsigned int offset = get_eb_offset_in_folio(eb, cur);
unsigned int cur_len = min(start + len - cur, unit_size - offset);
assert_eb_folio_uptodate(eb, index);
memset(folio_address(eb->folios[index]) + offset, c, cur_len);
cur += cur_len;
}
}
void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
unsigned long len)
{
if (check_eb_range(eb, start, len))
return;
return memset_extent_buffer(eb, 0, start, len);
}
void copy_extent_buffer_full(const struct extent_buffer *dst,
const struct extent_buffer *src)
{
const int unit_size = src->folio_size;
unsigned long cur = 0;
ASSERT(dst->len == src->len);
while (cur < src->len) {
unsigned long index = get_eb_folio_index(src, cur);
unsigned long offset = get_eb_offset_in_folio(src, cur);
unsigned long cur_len = min(src->len, unit_size - offset);
void *addr = folio_address(src->folios[index]) + offset;
write_extent_buffer(dst, addr, cur, cur_len);
cur += cur_len;
}
}
void copy_extent_buffer(const struct extent_buffer *dst,
const struct extent_buffer *src,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len)
{
const int unit_size = dst->folio_size;
u64 dst_len = dst->len;
size_t cur;
size_t offset;
char *kaddr;
unsigned long i = get_eb_folio_index(dst, dst_offset);
if (check_eb_range(dst, dst_offset, len) ||
check_eb_range(src, src_offset, len))
return;
WARN_ON(src->len != dst_len);
offset = get_eb_offset_in_folio(dst, dst_offset);
while (len > 0) {
assert_eb_folio_uptodate(dst, i);
cur = min(len, (unsigned long)(unit_size - offset));
kaddr = folio_address(dst->folios[i]);
read_extent_buffer(src, kaddr + offset, src_offset, cur);
src_offset += cur;
len -= cur;
offset = 0;
i++;
}
}
/*
* Calculate the folio and offset of the byte containing the given bit number.
*
* @eb: the extent buffer
* @start: offset of the bitmap item in the extent buffer
* @nr: bit number
* @folio_index: return index of the folio in the extent buffer that contains
* the given bit number
* @folio_offset: return offset into the folio given by folio_index
*
* This helper hides the ugliness of finding the byte in an extent buffer which
* contains a given bit.
*/
static inline void eb_bitmap_offset(const struct extent_buffer *eb,
unsigned long start, unsigned long nr,
unsigned long *folio_index,
size_t *folio_offset)
{
size_t byte_offset = BIT_BYTE(nr);
size_t offset;
/*
* The byte we want is the offset of the extent buffer + the offset of
* the bitmap item in the extent buffer + the offset of the byte in the
* bitmap item.
*/
offset = start + offset_in_eb_folio(eb, eb->start) + byte_offset;
*folio_index = offset >> eb->folio_shift;
*folio_offset = offset_in_eb_folio(eb, offset);
}
/*
* Determine whether a bit in a bitmap item is set.
*
* @eb: the extent buffer
* @start: offset of the bitmap item in the extent buffer
* @nr: bit number to test
*/
int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
unsigned long nr)
{
unsigned long i;
size_t offset;
u8 *kaddr;
eb_bitmap_offset(eb, start, nr, &i, &offset);
assert_eb_folio_uptodate(eb, i);
kaddr = folio_address(eb->folios[i]);
return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
}
static u8 *extent_buffer_get_byte(const struct extent_buffer *eb, unsigned long bytenr)
{
unsigned long index = get_eb_folio_index(eb, bytenr);
if (check_eb_range(eb, bytenr, 1))
return NULL;
return folio_address(eb->folios[index]) + get_eb_offset_in_folio(eb, bytenr);
}
/*
* Set an area of a bitmap to 1.
*
* @eb: the extent buffer
* @start: offset of the bitmap item in the extent buffer
* @pos: bit number of the first bit
* @len: number of bits to set
*/
void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start,
unsigned long pos, unsigned long len)
{
unsigned int first_byte = start + BIT_BYTE(pos);
unsigned int last_byte = start + BIT_BYTE(pos + len - 1);
const bool same_byte = (first_byte == last_byte);
u8 mask = BITMAP_FIRST_BYTE_MASK(pos);
u8 *kaddr;
if (same_byte)
mask &= BITMAP_LAST_BYTE_MASK(pos + len);
/* Handle the first byte. */
kaddr = extent_buffer_get_byte(eb, first_byte);
*kaddr |= mask;
if (same_byte)
return;
/* Handle the byte aligned part. */
ASSERT(first_byte + 1 <= last_byte);
memset_extent_buffer(eb, 0xff, first_byte + 1, last_byte - first_byte - 1);
/* Handle the last byte. */
kaddr = extent_buffer_get_byte(eb, last_byte);
*kaddr |= BITMAP_LAST_BYTE_MASK(pos + len);
}
/*
* Clear an area of a bitmap.
*
* @eb: the extent buffer
* @start: offset of the bitmap item in the extent buffer
* @pos: bit number of the first bit
* @len: number of bits to clear
*/
void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
unsigned long start, unsigned long pos,
unsigned long len)
{
unsigned int first_byte = start + BIT_BYTE(pos);
unsigned int last_byte = start + BIT_BYTE(pos + len - 1);
const bool same_byte = (first_byte == last_byte);
u8 mask = BITMAP_FIRST_BYTE_MASK(pos);
u8 *kaddr;
if (same_byte)
mask &= BITMAP_LAST_BYTE_MASK(pos + len);
/* Handle the first byte. */
kaddr = extent_buffer_get_byte(eb, first_byte);
*kaddr &= ~mask;
if (same_byte)
return;
/* Handle the byte aligned part. */
ASSERT(first_byte + 1 <= last_byte);
memset_extent_buffer(eb, 0, first_byte + 1, last_byte - first_byte - 1);
/* Handle the last byte. */
kaddr = extent_buffer_get_byte(eb, last_byte);
*kaddr &= ~BITMAP_LAST_BYTE_MASK(pos + len);
}
static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
{
unsigned long distance = (src > dst) ? src - dst : dst - src;
return distance < len;
}
void memcpy_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len)
{
const int unit_size = dst->folio_size;
unsigned long cur_off = 0;
if (check_eb_range(dst, dst_offset, len) ||
check_eb_range(dst, src_offset, len))
return;
if (dst->addr) {
const bool use_memmove = areas_overlap(src_offset, dst_offset, len);
if (use_memmove)
memmove(dst->addr + dst_offset, dst->addr + src_offset, len);
else
memcpy(dst->addr + dst_offset, dst->addr + src_offset, len);
return;
}
while (cur_off < len) {
unsigned long cur_src = cur_off + src_offset;
unsigned long folio_index = get_eb_folio_index(dst, cur_src);
unsigned long folio_off = get_eb_offset_in_folio(dst, cur_src);
unsigned long cur_len = min(src_offset + len - cur_src,
unit_size - folio_off);
void *src_addr = folio_address(dst->folios[folio_index]) + folio_off;
const bool use_memmove = areas_overlap(src_offset + cur_off,
dst_offset + cur_off, cur_len);
__write_extent_buffer(dst, src_addr, dst_offset + cur_off, cur_len,
use_memmove);
cur_off += cur_len;
}
}
void memmove_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len)
{
unsigned long dst_end = dst_offset + len - 1;
unsigned long src_end = src_offset + len - 1;
if (check_eb_range(dst, dst_offset, len) ||
check_eb_range(dst, src_offset, len))
return;
if (dst_offset < src_offset) {
memcpy_extent_buffer(dst, dst_offset, src_offset, len);
return;
}
if (dst->addr) {
memmove(dst->addr + dst_offset, dst->addr + src_offset, len);
return;
}
while (len > 0) {
unsigned long src_i;
size_t cur;
size_t dst_off_in_folio;
size_t src_off_in_folio;
void *src_addr;
bool use_memmove;
src_i = get_eb_folio_index(dst, src_end);
dst_off_in_folio = get_eb_offset_in_folio(dst, dst_end);
src_off_in_folio = get_eb_offset_in_folio(dst, src_end);
cur = min_t(unsigned long, len, src_off_in_folio + 1);
cur = min(cur, dst_off_in_folio + 1);
src_addr = folio_address(dst->folios[src_i]) + src_off_in_folio -
cur + 1;
use_memmove = areas_overlap(src_end - cur + 1, dst_end - cur + 1,
cur);
__write_extent_buffer(dst, src_addr, dst_end - cur + 1, cur,
use_memmove);
dst_end -= cur;
src_end -= cur;
len -= cur;
}
}
#define GANG_LOOKUP_SIZE 16
static struct extent_buffer *get_next_extent_buffer(
const struct btrfs_fs_info *fs_info, struct folio *folio, u64 bytenr)
{
struct extent_buffer *gang[GANG_LOOKUP_SIZE];
struct extent_buffer *found = NULL;
u64 folio_start = folio_pos(folio);
u64 cur = folio_start;
ASSERT(in_range(bytenr, folio_start, PAGE_SIZE));
lockdep_assert_held(&fs_info->buffer_lock);
while (cur < folio_start + PAGE_SIZE) {
int ret;
int i;
ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
(void **)gang, cur >> fs_info->sectorsize_bits,
min_t(unsigned int, GANG_LOOKUP_SIZE,
PAGE_SIZE / fs_info->nodesize));
if (ret == 0)
goto out;
for (i = 0; i < ret; i++) {
/* Already beyond page end */
if (gang[i]->start >= folio_start + PAGE_SIZE)
goto out;
/* Found one */
if (gang[i]->start >= bytenr) {
found = gang[i];
goto out;
}
}
cur = gang[ret - 1]->start + gang[ret - 1]->len;
}
out:
return found;
}
static int try_release_subpage_extent_buffer(struct folio *folio)
{
struct btrfs_fs_info *fs_info = folio_to_fs_info(folio);
u64 cur = folio_pos(folio);
const u64 end = cur + PAGE_SIZE;
int ret;
while (cur < end) {
struct extent_buffer *eb = NULL;
/*
* Unlike try_release_extent_buffer() which uses folio private
* to grab buffer, for subpage case we rely on radix tree, thus
* we need to ensure radix tree consistency.
*
* We also want an atomic snapshot of the radix tree, thus go
* with spinlock rather than RCU.
*/
spin_lock(&fs_info->buffer_lock);
eb = get_next_extent_buffer(fs_info, folio, cur);
if (!eb) {
/* No more eb in the page range after or at cur */
spin_unlock(&fs_info->buffer_lock);
break;
}
cur = eb->start + eb->len;
/*
* The same as try_release_extent_buffer(), to ensure the eb
* won't disappear out from under us.
*/
spin_lock(&eb->refs_lock);
if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
spin_unlock(&eb->refs_lock);
spin_unlock(&fs_info->buffer_lock);
break;
}
spin_unlock(&fs_info->buffer_lock);
/*
* If tree ref isn't set then we know the ref on this eb is a
* real ref, so just return, this eb will likely be freed soon
* anyway.
*/
if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
spin_unlock(&eb->refs_lock);
break;
}
/*
* Here we don't care about the return value, we will always
* check the folio private at the end. And
* release_extent_buffer() will release the refs_lock.
*/
release_extent_buffer(eb);
}
/*
* Finally to check if we have cleared folio private, as if we have
* released all ebs in the page, the folio private should be cleared now.
*/
spin_lock(&folio->mapping->i_private_lock);
if (!folio_test_private(folio))
ret = 1;
else
ret = 0;
spin_unlock(&folio->mapping->i_private_lock);
return ret;
}
int try_release_extent_buffer(struct folio *folio)
{
struct extent_buffer *eb;
if (folio_to_fs_info(folio)->nodesize < PAGE_SIZE)
return try_release_subpage_extent_buffer(folio);
/*
* We need to make sure nobody is changing folio private, as we rely on
* folio private as the pointer to extent buffer.
*/
spin_lock(&folio->mapping->i_private_lock);
if (!folio_test_private(folio)) {
spin_unlock(&folio->mapping->i_private_lock);
return 1;
}
eb = folio_get_private(folio);
BUG_ON(!eb);
/*
* This is a little awful but should be ok, we need to make sure that
* the eb doesn't disappear out from under us while we're looking at
* this page.
*/
spin_lock(&eb->refs_lock);
if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
spin_unlock(&eb->refs_lock);
spin_unlock(&folio->mapping->i_private_lock);
return 0;
}
spin_unlock(&folio->mapping->i_private_lock);
/*
* If tree ref isn't set then we know the ref on this eb is a real ref,
* so just return, this page will likely be freed soon anyway.
*/
if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
spin_unlock(&eb->refs_lock);
return 0;
}
return release_extent_buffer(eb);
}
/*
* Attempt to readahead a child block.
*
* @fs_info: the fs_info
* @bytenr: bytenr to read
* @owner_root: objectid of the root that owns this eb
* @gen: generation for the uptodate check, can be 0
* @level: level for the eb
*
* Attempt to readahead a tree block at @bytenr. If @gen is 0 then we do a
* normal uptodate check of the eb, without checking the generation. If we have
* to read the block we will not block on anything.
*/
void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 owner_root, u64 gen, int level)
{
struct btrfs_tree_parent_check check = {
.has_first_key = 0,
.level = level,
.transid = gen
};
struct extent_buffer *eb;
int ret;
eb = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level);
if (IS_ERR(eb))
return;
if (btrfs_buffer_uptodate(eb, gen, 1)) {
free_extent_buffer(eb);
return;
}
ret = read_extent_buffer_pages(eb, WAIT_NONE, 0, &check);
if (ret < 0)
free_extent_buffer_stale(eb);
else
free_extent_buffer(eb);
}
/*
* Readahead a node's child block.
*
* @node: parent node we're reading from
* @slot: slot in the parent node for the child we want to read
*
* A helper for btrfs_readahead_tree_block, we simply read the bytenr pointed at
* the slot in the node provided.
*/
void btrfs_readahead_node_child(struct extent_buffer *node, int slot)
{
btrfs_readahead_tree_block(node->fs_info,
btrfs_node_blockptr(node, slot),
btrfs_header_owner(node),
btrfs_node_ptr_generation(node, slot),
btrfs_header_level(node) - 1);
}
|