1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
|
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/smp_lock.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/bit_spinlock.h>
#include <linux/version.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "ioctl.h"
#include "print-tree.h"
#include "volumes.h"
#include "ordered-data.h"
#include "xattr.h"
#include "compat.h"
#include "tree-log.h"
#include "ref-cache.h"
#include "compression.h"
struct btrfs_iget_args {
u64 ino;
struct btrfs_root *root;
};
static struct inode_operations btrfs_dir_inode_operations;
static struct inode_operations btrfs_symlink_inode_operations;
static struct inode_operations btrfs_dir_ro_inode_operations;
static struct inode_operations btrfs_special_inode_operations;
static struct inode_operations btrfs_file_inode_operations;
static struct address_space_operations btrfs_aops;
static struct address_space_operations btrfs_symlink_aops;
static struct file_operations btrfs_dir_file_operations;
static struct extent_io_ops btrfs_extent_io_ops;
static struct kmem_cache *btrfs_inode_cachep;
struct kmem_cache *btrfs_trans_handle_cachep;
struct kmem_cache *btrfs_transaction_cachep;
struct kmem_cache *btrfs_bit_radix_cachep;
struct kmem_cache *btrfs_path_cachep;
#define S_SHIFT 12
static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = BTRFS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = BTRFS_FT_DIR,
[S_IFCHR >> S_SHIFT] = BTRFS_FT_CHRDEV,
[S_IFBLK >> S_SHIFT] = BTRFS_FT_BLKDEV,
[S_IFIFO >> S_SHIFT] = BTRFS_FT_FIFO,
[S_IFSOCK >> S_SHIFT] = BTRFS_FT_SOCK,
[S_IFLNK >> S_SHIFT] = BTRFS_FT_SYMLINK,
};
static void btrfs_truncate(struct inode *inode);
static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end);
/*
* a very lame attempt at stopping writes when the FS is 85% full. There
* are countless ways this is incorrect, but it is better than nothing.
*/
int btrfs_check_free_space(struct btrfs_root *root, u64 num_required,
int for_del)
{
u64 total;
u64 used;
u64 thresh;
unsigned long flags;
int ret = 0;
spin_lock_irqsave(&root->fs_info->delalloc_lock, flags);
total = btrfs_super_total_bytes(&root->fs_info->super_copy);
used = btrfs_super_bytes_used(&root->fs_info->super_copy);
if (for_del)
thresh = total * 90;
else
thresh = total * 85;
do_div(thresh, 100);
if (used + root->fs_info->delalloc_bytes + num_required > thresh)
ret = -ENOSPC;
spin_unlock_irqrestore(&root->fs_info->delalloc_lock, flags);
return ret;
}
/*
* this does all the hard work for inserting an inline extent into
* the btree. The caller should have done a btrfs_drop_extents so that
* no overlapping inline items exist in the btree
*/
static int noinline insert_inline_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
u64 start, size_t size, size_t compressed_size,
struct page **compressed_pages)
{
struct btrfs_key key;
struct btrfs_path *path;
struct extent_buffer *leaf;
struct page *page = NULL;
char *kaddr;
unsigned long ptr;
struct btrfs_file_extent_item *ei;
int err = 0;
int ret;
size_t cur_size = size;
size_t datasize;
unsigned long offset;
int use_compress = 0;
if (compressed_size && compressed_pages) {
use_compress = 1;
cur_size = compressed_size;
}
path = btrfs_alloc_path(); if (!path)
return -ENOMEM;
btrfs_set_trans_block_group(trans, inode);
key.objectid = inode->i_ino;
key.offset = start;
btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
inode_add_bytes(inode, size);
datasize = btrfs_file_extent_calc_inline_size(cur_size);
inode_add_bytes(inode, size);
ret = btrfs_insert_empty_item(trans, root, path, &key,
datasize);
BUG_ON(ret);
if (ret) {
err = ret;
printk("got bad ret %d\n", ret);
goto fail;
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
btrfs_set_file_extent_generation(leaf, ei, trans->transid);
btrfs_set_file_extent_type(leaf, ei, BTRFS_FILE_EXTENT_INLINE);
btrfs_set_file_extent_encryption(leaf, ei, 0);
btrfs_set_file_extent_other_encoding(leaf, ei, 0);
btrfs_set_file_extent_ram_bytes(leaf, ei, size);
ptr = btrfs_file_extent_inline_start(ei);
if (use_compress) {
struct page *cpage;
int i = 0;
while(compressed_size > 0) {
cpage = compressed_pages[i];
cur_size = min(compressed_size,
PAGE_CACHE_SIZE);
kaddr = kmap(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
kunmap(cpage);
i++;
ptr += cur_size;
compressed_size -= cur_size;
}
btrfs_set_file_extent_compression(leaf, ei,
BTRFS_COMPRESS_ZLIB);
} else {
page = find_get_page(inode->i_mapping,
start >> PAGE_CACHE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
kaddr = kmap_atomic(page, KM_USER0);
offset = start & (PAGE_CACHE_SIZE - 1);
write_extent_buffer(leaf, kaddr + offset, ptr, size);
kunmap_atomic(kaddr, KM_USER0);
page_cache_release(page);
}
btrfs_mark_buffer_dirty(leaf);
btrfs_free_path(path);
BTRFS_I(inode)->disk_i_size = inode->i_size;
btrfs_update_inode(trans, root, inode);
return 0;
fail:
btrfs_free_path(path);
return err;
}
/*
* conditionally insert an inline extent into the file. This
* does the checks required to make sure the data is small enough
* to fit as an inline extent.
*/
static int cow_file_range_inline(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode, u64 start, u64 end,
size_t compressed_size,
struct page **compressed_pages)
{
u64 isize = i_size_read(inode);
u64 actual_end = min(end + 1, isize);
u64 inline_len = actual_end - start;
u64 aligned_end = (end + root->sectorsize - 1) &
~((u64)root->sectorsize - 1);
u64 hint_byte;
u64 data_len = inline_len;
int ret;
if (compressed_size)
data_len = compressed_size;
if (start > 0 ||
data_len >= BTRFS_MAX_INLINE_DATA_SIZE(root) ||
(!compressed_size &&
(actual_end & (root->sectorsize - 1)) == 0) ||
end + 1 < isize ||
data_len > root->fs_info->max_inline) {
return 1;
}
mutex_lock(&BTRFS_I(inode)->extent_mutex);
ret = btrfs_drop_extents(trans, root, inode, start,
aligned_end, aligned_end, &hint_byte);
BUG_ON(ret);
if (isize > actual_end)
inline_len = min_t(u64, isize, actual_end);
ret = insert_inline_extent(trans, root, inode, start,
inline_len, compressed_size,
compressed_pages);
BUG_ON(ret);
btrfs_drop_extent_cache(inode, start, aligned_end, 0);
mutex_unlock(&BTRFS_I(inode)->extent_mutex);
return 0;
}
/*
* when extent_io.c finds a delayed allocation range in the file,
* the call backs end up in this code. The basic idea is to
* allocate extents on disk for the range, and create ordered data structs
* in ram to track those extents.
*
* locked_page is the page that writepage had locked already. We use
* it to make sure we don't do extra locks or unlocks.
*
* *page_started is set to one if we unlock locked_page and do everything
* required to start IO on it. It may be clean and already done with
* IO when we return.
*/
static int cow_file_range(struct inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
u64 alloc_hint = 0;
u64 num_bytes;
unsigned long ram_size;
u64 orig_start;
u64 disk_num_bytes;
u64 cur_alloc_size;
u64 blocksize = root->sectorsize;
u64 actual_end;
struct btrfs_key ins;
struct extent_map *em;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
int ret = 0;
struct page **pages = NULL;
unsigned long nr_pages;
unsigned long nr_pages_ret = 0;
unsigned long total_compressed = 0;
unsigned long total_in = 0;
unsigned long max_compressed = 128 * 1024;
unsigned long max_uncompressed = 256 * 1024;
int i;
int will_compress;
trans = btrfs_join_transaction(root, 1);
BUG_ON(!trans);
btrfs_set_trans_block_group(trans, inode);
orig_start = start;
/*
* compression made this loop a bit ugly, but the basic idea is to
* compress some pages but keep the total size of the compressed
* extent relatively small. If compression is off, this goto target
* is never used.
*/
again:
will_compress = 0;
nr_pages = (end >> PAGE_CACHE_SHIFT) - (start >> PAGE_CACHE_SHIFT) + 1;
nr_pages = min(nr_pages, (128 * 1024UL) / PAGE_CACHE_SIZE);
actual_end = min_t(u64, i_size_read(inode), end + 1);
total_compressed = actual_end - start;
/* we want to make sure that amount of ram required to uncompress
* an extent is reasonable, so we limit the total size in ram
* of a compressed extent to 256k
*/
total_compressed = min(total_compressed, max_uncompressed);
num_bytes = (end - start + blocksize) & ~(blocksize - 1);
num_bytes = max(blocksize, num_bytes);
disk_num_bytes = num_bytes;
total_in = 0;
ret = 0;
/* we do compression for mount -o compress and when the
* inode has not been flagged as nocompress
*/
if (!btrfs_test_flag(inode, NOCOMPRESS) &&
btrfs_test_opt(root, COMPRESS)) {
WARN_ON(pages);
pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
/* we want to make sure the amount of IO required to satisfy
* a random read is reasonably small, so we limit the size
* of a compressed extent to 128k
*/
ret = btrfs_zlib_compress_pages(inode->i_mapping, start,
total_compressed, pages,
nr_pages, &nr_pages_ret,
&total_in,
&total_compressed,
max_compressed);
if (!ret) {
unsigned long offset = total_compressed &
(PAGE_CACHE_SIZE - 1);
struct page *page = pages[nr_pages_ret - 1];
char *kaddr;
/* zero the tail end of the last page, we might be
* sending it down to disk
*/
if (offset) {
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr + offset, 0,
PAGE_CACHE_SIZE - offset);
kunmap_atomic(kaddr, KM_USER0);
}
will_compress = 1;
}
}
if (start == 0) {
/* lets try to make an inline extent */
if (ret || total_in < (end - start + 1)) {
/* we didn't compress the entire range, try
* to make an uncompressed inline extent. This
* is almost sure to fail, but maybe inline sizes
* will get bigger later
*/
ret = cow_file_range_inline(trans, root, inode,
start, end, 0, NULL);
} else {
ret = cow_file_range_inline(trans, root, inode,
start, end,
total_compressed, pages);
}
if (ret == 0) {
extent_clear_unlock_delalloc(inode,
&BTRFS_I(inode)->io_tree,
start, end, NULL,
1, 1, 1);
*page_started = 1;
ret = 0;
goto free_pages_out;
}
}
if (will_compress) {
/*
* we aren't doing an inline extent round the compressed size
* up to a block size boundary so the allocator does sane
* things
*/
total_compressed = (total_compressed + blocksize - 1) &
~(blocksize - 1);
/*
* one last check to make sure the compression is really a
* win, compare the page count read with the blocks on disk
*/
total_in = (total_in + PAGE_CACHE_SIZE - 1) &
~(PAGE_CACHE_SIZE - 1);
if (total_compressed >= total_in) {
will_compress = 0;
} else {
disk_num_bytes = total_compressed;
num_bytes = total_in;
}
}
if (!will_compress && pages) {
/*
* the compression code ran but failed to make things smaller,
* free any pages it allocated and our page pointer array
*/
for (i = 0; i < nr_pages_ret; i++) {
page_cache_release(pages[i]);
}
kfree(pages);
pages = NULL;
total_compressed = 0;
nr_pages_ret = 0;
/* flag the file so we don't compress in the future */
btrfs_set_flag(inode, NOCOMPRESS);
}
BUG_ON(disk_num_bytes >
btrfs_super_total_bytes(&root->fs_info->super_copy));
mutex_lock(&BTRFS_I(inode)->extent_mutex);
btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
mutex_unlock(&BTRFS_I(inode)->extent_mutex);
while(disk_num_bytes > 0) {
unsigned long min_bytes;
/*
* the max size of a compressed extent is pretty small,
* make the code a little less complex by forcing
* the allocator to find a whole compressed extent at once
*/
if (will_compress)
min_bytes = disk_num_bytes;
else
min_bytes = root->sectorsize;
cur_alloc_size = min(disk_num_bytes, root->fs_info->max_extent);
ret = btrfs_reserve_extent(trans, root, cur_alloc_size,
min_bytes, 0, alloc_hint,
(u64)-1, &ins, 1);
if (ret) {
WARN_ON(1);
goto free_pages_out_fail;
}
em = alloc_extent_map(GFP_NOFS);
em->start = start;
if (will_compress) {
ram_size = num_bytes;
em->len = num_bytes;
} else {
/* ramsize == disk size */
ram_size = ins.offset;
em->len = ins.offset;
}
em->block_start = ins.objectid;
em->block_len = ins.offset;
em->bdev = root->fs_info->fs_devices->latest_bdev;
mutex_lock(&BTRFS_I(inode)->extent_mutex);
set_bit(EXTENT_FLAG_PINNED, &em->flags);
if (will_compress)
set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
while(1) {
spin_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em);
spin_unlock(&em_tree->lock);
if (ret != -EEXIST) {
free_extent_map(em);
break;
}
btrfs_drop_extent_cache(inode, start,
start + ram_size - 1, 0);
}
mutex_unlock(&BTRFS_I(inode)->extent_mutex);
cur_alloc_size = ins.offset;
ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
ram_size, cur_alloc_size, 0,
will_compress);
BUG_ON(ret);
if (disk_num_bytes < cur_alloc_size) {
printk("num_bytes %Lu cur_alloc %Lu\n", disk_num_bytes,
cur_alloc_size);
break;
}
if (will_compress) {
/*
* we're doing compression, we and we need to
* submit the compressed extents down to the device.
*
* We lock down all the file pages, clearing their
* dirty bits and setting them writeback. Everyone
* that wants to modify the page will wait on the
* ordered extent above.
*
* The writeback bits on the file pages are
* cleared when the compressed pages are on disk
*/
btrfs_end_transaction(trans, root);
if (start <= page_offset(locked_page) &&
page_offset(locked_page) < start + ram_size) {
*page_started = 1;
}
extent_clear_unlock_delalloc(inode,
&BTRFS_I(inode)->io_tree,
start,
start + ram_size - 1,
NULL, 1, 1, 0);
ret = btrfs_submit_compressed_write(inode, start,
ram_size, ins.objectid,
cur_alloc_size, pages,
nr_pages_ret);
BUG_ON(ret);
trans = btrfs_join_transaction(root, 1);
if (start + ram_size < end) {
start += ram_size;
alloc_hint = ins.objectid + ins.offset;
/* pages will be freed at end_bio time */
pages = NULL;
goto again;
} else {
/* we've written everything, time to go */
break;
}
}
/* we're not doing compressed IO, don't unlock the first
* page (which the caller expects to stay locked), don't
* clear any dirty bits and don't set any writeback bits
*/
extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
start, start + ram_size - 1,
locked_page, 0, 0, 0);
disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
start += cur_alloc_size;
}
ret = 0;
out:
btrfs_end_transaction(trans, root);
return ret;
free_pages_out_fail:
extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
start, end, locked_page, 0, 0, 0);
free_pages_out:
for (i = 0; i < nr_pages_ret; i++)
page_cache_release(pages[i]);
if (pages)
kfree(pages);
goto out;
}
/*
* when nowcow writeback call back. This checks for snapshots or COW copies
* of the extents that exist in the file, and COWs the file as required.
*
* If no cow copies or snapshots exist, we write directly to the existing
* blocks on disk
*/
static int run_delalloc_nocow(struct inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started)
{
u64 extent_start;
u64 extent_end;
u64 bytenr;
u64 loops = 0;
u64 total_fs_bytes;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_group_cache *block_group;
struct btrfs_trans_handle *trans;
struct extent_buffer *leaf;
int found_type;
struct btrfs_path *path;
struct btrfs_file_extent_item *item;
int ret;
int err = 0;
struct btrfs_key found_key;
total_fs_bytes = btrfs_super_total_bytes(&root->fs_info->super_copy);
path = btrfs_alloc_path();
BUG_ON(!path);
trans = btrfs_join_transaction(root, 1);
BUG_ON(!trans);
again:
ret = btrfs_lookup_file_extent(NULL, root, path,
inode->i_ino, start, 0);
if (ret < 0) {
err = ret;
goto out;
}
if (ret != 0) {
if (path->slots[0] == 0)
goto not_found;
path->slots[0]--;
}
leaf = path->nodes[0];
item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
/* are we inside the extent that was found? */
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
if (found_key.objectid != inode->i_ino ||
found_type != BTRFS_EXTENT_DATA_KEY)
goto not_found;
found_type = btrfs_file_extent_type(leaf, item);
extent_start = found_key.offset;
if (found_type == BTRFS_FILE_EXTENT_REG) {
u64 extent_num_bytes;
extent_num_bytes = btrfs_file_extent_num_bytes(leaf, item);
extent_end = extent_start + extent_num_bytes;
err = 0;
if (btrfs_file_extent_compression(leaf, item) ||
btrfs_file_extent_encryption(leaf,item) ||
btrfs_file_extent_other_encoding(leaf, item))
goto not_found;
if (loops && start != extent_start)
goto not_found;
if (start < extent_start || start >= extent_end)
goto not_found;
bytenr = btrfs_file_extent_disk_bytenr(leaf, item);
if (bytenr == 0)
goto not_found;
if (btrfs_cross_ref_exists(trans, root, &found_key, bytenr))
goto not_found;
/*
* we may be called by the resizer, make sure we're inside
* the limits of the FS
*/
block_group = btrfs_lookup_block_group(root->fs_info,
bytenr);
if (!block_group || block_group->ro)
goto not_found;
bytenr += btrfs_file_extent_offset(leaf, item);
extent_num_bytes = min(end + 1, extent_end) - start;
ret = btrfs_add_ordered_extent(inode, start, bytenr,
extent_num_bytes,
extent_num_bytes, 1, 0);
if (ret) {
err = ret;
goto out;
}
btrfs_release_path(root, path);
start = extent_end;
if (start <= end) {
loops++;
goto again;
}
} else {
not_found:
btrfs_end_transaction(trans, root);
btrfs_free_path(path);
return cow_file_range(inode, locked_page, start, end,
page_started);
}
out:
WARN_ON(err);
btrfs_end_transaction(trans, root);
btrfs_free_path(path);
return err;
}
/*
* extent_io.c call back to do delayed allocation processing
*/
static int run_delalloc_range(struct inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
if (btrfs_test_opt(root, NODATACOW) ||
btrfs_test_flag(inode, NODATACOW))
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started);
else
ret = cow_file_range(inode, locked_page, start, end,
page_started);
return ret;
}
/*
* extent_io.c set_bit_hook, used to track delayed allocation
* bytes in this file, and to maintain the list of inodes that
* have pending delalloc work to be done.
*/
int btrfs_set_bit_hook(struct inode *inode, u64 start, u64 end,
unsigned long old, unsigned long bits)
{
unsigned long flags;
if (!(old & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
struct btrfs_root *root = BTRFS_I(inode)->root;
spin_lock_irqsave(&root->fs_info->delalloc_lock, flags);
BTRFS_I(inode)->delalloc_bytes += end - start + 1;
root->fs_info->delalloc_bytes += end - start + 1;
if (list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
list_add_tail(&BTRFS_I(inode)->delalloc_inodes,
&root->fs_info->delalloc_inodes);
}
spin_unlock_irqrestore(&root->fs_info->delalloc_lock, flags);
}
return 0;
}
/*
* extent_io.c clear_bit_hook, see set_bit_hook for why
*/
int btrfs_clear_bit_hook(struct inode *inode, u64 start, u64 end,
unsigned long old, unsigned long bits)
{
if ((old & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
struct btrfs_root *root = BTRFS_I(inode)->root;
unsigned long flags;
spin_lock_irqsave(&root->fs_info->delalloc_lock, flags);
if (end - start + 1 > root->fs_info->delalloc_bytes) {
printk("warning: delalloc account %Lu %Lu\n",
end - start + 1, root->fs_info->delalloc_bytes);
root->fs_info->delalloc_bytes = 0;
BTRFS_I(inode)->delalloc_bytes = 0;
} else {
root->fs_info->delalloc_bytes -= end - start + 1;
BTRFS_I(inode)->delalloc_bytes -= end - start + 1;
}
if (BTRFS_I(inode)->delalloc_bytes == 0 &&
!list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
list_del_init(&BTRFS_I(inode)->delalloc_inodes);
}
spin_unlock_irqrestore(&root->fs_info->delalloc_lock, flags);
}
return 0;
}
/*
* extent_io.c merge_bio_hook, this must check the chunk tree to make sure
* we don't create bios that span stripes or chunks
*/
int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags)
{
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
struct btrfs_mapping_tree *map_tree;
u64 logical = (u64)bio->bi_sector << 9;
u64 length = 0;
u64 map_length;
int ret;
length = bio->bi_size;
map_tree = &root->fs_info->mapping_tree;
map_length = length;
ret = btrfs_map_block(map_tree, READ, logical,
&map_length, NULL, 0);
if (map_length < length + size) {
return 1;
}
return 0;
}
/*
* in order to insert checksums into the metadata in large chunks,
* we wait until bio submission time. All the pages in the bio are
* checksummed and sums are attached onto the ordered extent record.
*
* At IO completion time the cums attached on the ordered extent record
* are inserted into the btree
*/
int __btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
int mirror_num, unsigned long bio_flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
ret = btrfs_csum_one_bio(root, inode, bio);
BUG_ON(ret);
return btrfs_map_bio(root, rw, bio, mirror_num, 1);
}
/*
* extent_io.c submission hook. This does the right thing for csum calculation on write,
* or reading the csums from the tree before a read
*/
int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
int mirror_num, unsigned long bio_flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
BUG_ON(ret);
if (btrfs_test_opt(root, NODATASUM) ||
btrfs_test_flag(inode, NODATASUM)) {
goto mapit;
}
if (!(rw & (1 << BIO_RW))) {
btrfs_lookup_bio_sums(root, inode, bio);
if (bio_flags & EXTENT_BIO_COMPRESSED) {
return btrfs_submit_compressed_read(inode, bio,
mirror_num, bio_flags);
}
goto mapit;
}
return btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
inode, rw, bio, mirror_num,
bio_flags, __btrfs_submit_bio_hook);
mapit:
return btrfs_map_bio(root, rw, bio, mirror_num, 0);
}
/*
* given a list of ordered sums record them in the inode. This happens
* at IO completion time based on sums calculated at bio submission time.
*/
static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
struct inode *inode, u64 file_offset,
struct list_head *list)
{
struct list_head *cur;
struct btrfs_ordered_sum *sum;
btrfs_set_trans_block_group(trans, inode);
list_for_each(cur, list) {
sum = list_entry(cur, struct btrfs_ordered_sum, list);
btrfs_csum_file_blocks(trans, BTRFS_I(inode)->root,
inode, sum);
}
return 0;
}
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end)
{
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
GFP_NOFS);
}
/* see btrfs_writepage_start_hook for details on why this is required */
struct btrfs_writepage_fixup {
struct page *page;
struct btrfs_work work;
};
void btrfs_writepage_fixup_worker(struct btrfs_work *work)
{
struct btrfs_writepage_fixup *fixup;
struct btrfs_ordered_extent *ordered;
struct page *page;
struct inode *inode;
u64 page_start;
u64 page_end;
fixup = container_of(work, struct btrfs_writepage_fixup, work);
page = fixup->page;
again:
lock_page(page);
if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
ClearPageChecked(page);
goto out_page;
}
inode = page->mapping->host;
page_start = page_offset(page);
page_end = page_offset(page) + PAGE_CACHE_SIZE - 1;
lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end, GFP_NOFS);
/* already ordered? We're done */
if (test_range_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
EXTENT_ORDERED, 0)) {
goto out;
}
ordered = btrfs_lookup_ordered_extent(inode, page_start);
if (ordered) {
unlock_extent(&BTRFS_I(inode)->io_tree, page_start,
page_end, GFP_NOFS);
unlock_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
goto again;
}
btrfs_set_extent_delalloc(inode, page_start, page_end);
ClearPageChecked(page);
out:
unlock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end, GFP_NOFS);
out_page:
unlock_page(page);
page_cache_release(page);
}
/*
* There are a few paths in the higher layers of the kernel that directly
* set the page dirty bit without asking the filesystem if it is a
* good idea. This causes problems because we want to make sure COW
* properly happens and the data=ordered rules are followed.
*
* In our case any range that doesn't have the ORDERED bit set
* hasn't been properly setup for IO. We kick off an async process
* to fix it up. The async helper will wait for ordered extents, set
* the delalloc bit and make it safe to write the page.
*/
int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
{
struct inode *inode = page->mapping->host;
struct btrfs_writepage_fixup *fixup;
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
ret = test_range_bit(&BTRFS_I(inode)->io_tree, start, end,
EXTENT_ORDERED, 0);
if (ret)
return 0;
if (PageChecked(page))
return -EAGAIN;
fixup = kzalloc(sizeof(*fixup), GFP_NOFS);
if (!fixup)
return -EAGAIN;
SetPageChecked(page);
page_cache_get(page);
fixup->work.func = btrfs_writepage_fixup_worker;
fixup->page = page;
btrfs_queue_worker(&root->fs_info->fixup_workers, &fixup->work);
return -EAGAIN;
}
/* as ordered data IO finishes, this gets called so we can finish
* an ordered extent if the range of bytes in the file it covers are
* fully written.
*/
static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
struct btrfs_ordered_extent *ordered_extent;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_file_extent_item *extent_item;
struct btrfs_path *path = NULL;
struct extent_buffer *leaf;
u64 alloc_hint = 0;
struct list_head list;
struct btrfs_key ins;
int ret;
ret = btrfs_dec_test_ordered_pending(inode, start, end - start + 1);
if (!ret)
return 0;
trans = btrfs_join_transaction(root, 1);
ordered_extent = btrfs_lookup_ordered_extent(inode, start);
BUG_ON(!ordered_extent);
if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags))
goto nocow;
path = btrfs_alloc_path();
BUG_ON(!path);
lock_extent(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset + ordered_extent->len - 1,
GFP_NOFS);
INIT_LIST_HEAD(&list);
mutex_lock(&BTRFS_I(inode)->extent_mutex);
ret = btrfs_drop_extents(trans, root, inode,
ordered_extent->file_offset,
ordered_extent->file_offset +
ordered_extent->len,
ordered_extent->file_offset, &alloc_hint);
BUG_ON(ret);
ins.objectid = inode->i_ino;
ins.offset = ordered_extent->file_offset;
ins.type = BTRFS_EXTENT_DATA_KEY;
ret = btrfs_insert_empty_item(trans, root, path, &ins,
sizeof(*extent_item));
BUG_ON(ret);
leaf = path->nodes[0];
extent_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
btrfs_set_file_extent_generation(leaf, extent_item, trans->transid);
btrfs_set_file_extent_type(leaf, extent_item, BTRFS_FILE_EXTENT_REG);
btrfs_set_file_extent_disk_bytenr(leaf, extent_item,
ordered_extent->start);
btrfs_set_file_extent_disk_num_bytes(leaf, extent_item,
ordered_extent->disk_len);
btrfs_set_file_extent_offset(leaf, extent_item, 0);
if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
btrfs_set_file_extent_compression(leaf, extent_item, 1);
else
btrfs_set_file_extent_compression(leaf, extent_item, 0);
btrfs_set_file_extent_encryption(leaf, extent_item, 0);
btrfs_set_file_extent_other_encoding(leaf, extent_item, 0);
/* ram bytes = extent_num_bytes for now */
btrfs_set_file_extent_num_bytes(leaf, extent_item,
ordered_extent->len);
btrfs_set_file_extent_ram_bytes(leaf, extent_item,
ordered_extent->len);
btrfs_mark_buffer_dirty(leaf);
btrfs_drop_extent_cache(inode, ordered_extent->file_offset,
ordered_extent->file_offset +
ordered_extent->len - 1, 0);
mutex_unlock(&BTRFS_I(inode)->extent_mutex);
ins.objectid = ordered_extent->start;
ins.offset = ordered_extent->disk_len;
ins.type = BTRFS_EXTENT_ITEM_KEY;
ret = btrfs_alloc_reserved_extent(trans, root, leaf->start,
root->root_key.objectid,
trans->transid, inode->i_ino, &ins);
BUG_ON(ret);
btrfs_release_path(root, path);
inode_add_bytes(inode, ordered_extent->len);
unlock_extent(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset + ordered_extent->len - 1,
GFP_NOFS);
nocow:
add_pending_csums(trans, inode, ordered_extent->file_offset,
&ordered_extent->list);
mutex_lock(&BTRFS_I(inode)->extent_mutex);
btrfs_ordered_update_i_size(inode, ordered_extent);
btrfs_update_inode(trans, root, inode);
btrfs_remove_ordered_extent(inode, ordered_extent);
mutex_unlock(&BTRFS_I(inode)->extent_mutex);
/* once for us */
btrfs_put_ordered_extent(ordered_extent);
/* once for the tree */
btrfs_put_ordered_extent(ordered_extent);
btrfs_end_transaction(trans, root);
if (path)
btrfs_free_path(path);
return 0;
}
int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
struct extent_state *state, int uptodate)
{
return btrfs_finish_ordered_io(page->mapping->host, start, end);
}
/*
* When IO fails, either with EIO or csum verification fails, we
* try other mirrors that might have a good copy of the data. This
* io_failure_record is used to record state as we go through all the
* mirrors. If another mirror has good data, the page is set up to date
* and things continue. If a good mirror can't be found, the original
* bio end_io callback is called to indicate things have failed.
*/
struct io_failure_record {
struct page *page;
u64 start;
u64 len;
u64 logical;
int last_mirror;
};
int btrfs_io_failed_hook(struct bio *failed_bio,
struct page *page, u64 start, u64 end,
struct extent_state *state)
{
struct io_failure_record *failrec = NULL;
u64 private;
struct extent_map *em;
struct inode *inode = page->mapping->host;
struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct bio *bio;
int num_copies;
int ret;
int rw;
u64 logical;
unsigned long bio_flags = 0;
ret = get_state_private(failure_tree, start, &private);
if (ret) {
failrec = kmalloc(sizeof(*failrec), GFP_NOFS);
if (!failrec)
return -ENOMEM;
failrec->start = start;
failrec->len = end - start + 1;
failrec->last_mirror = 0;
spin_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, failrec->len);
if (em->start > start || em->start + em->len < start) {
free_extent_map(em);
em = NULL;
}
spin_unlock(&em_tree->lock);
if (!em || IS_ERR(em)) {
kfree(failrec);
return -EIO;
}
logical = start - em->start;
logical = em->block_start + logical;
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
bio_flags = EXTENT_BIO_COMPRESSED;
failrec->logical = logical;
free_extent_map(em);
set_extent_bits(failure_tree, start, end, EXTENT_LOCKED |
EXTENT_DIRTY, GFP_NOFS);
set_state_private(failure_tree, start,
(u64)(unsigned long)failrec);
} else {
failrec = (struct io_failure_record *)(unsigned long)private;
}
num_copies = btrfs_num_copies(
&BTRFS_I(inode)->root->fs_info->mapping_tree,
failrec->logical, failrec->len);
failrec->last_mirror++;
if (!state) {
spin_lock_irq(&BTRFS_I(inode)->io_tree.lock);
state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree,
failrec->start,
EXTENT_LOCKED);
if (state && state->start != failrec->start)
state = NULL;
spin_unlock_irq(&BTRFS_I(inode)->io_tree.lock);
}
if (!state || failrec->last_mirror > num_copies) {
set_state_private(failure_tree, failrec->start, 0);
clear_extent_bits(failure_tree, failrec->start,
failrec->start + failrec->len - 1,
EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
kfree(failrec);
return -EIO;
}
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_private = state;
bio->bi_end_io = failed_bio->bi_end_io;
bio->bi_sector = failrec->logical >> 9;
bio->bi_bdev = failed_bio->bi_bdev;
bio->bi_size = 0;
bio_add_page(bio, page, failrec->len, start - page_offset(page));
if (failed_bio->bi_rw & (1 << BIO_RW))
rw = WRITE;
else
rw = READ;
BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
failrec->last_mirror,
bio_flags);
return 0;
}
/*
* each time an IO finishes, we do a fast check in the IO failure tree
* to see if we need to process or clean up an io_failure_record
*/
int btrfs_clean_io_failures(struct inode *inode, u64 start)
{
u64 private;
u64 private_failure;
struct io_failure_record *failure;
int ret;
private = 0;
if (count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
(u64)-1, 1, EXTENT_DIRTY)) {
ret = get_state_private(&BTRFS_I(inode)->io_failure_tree,
start, &private_failure);
if (ret == 0) {
failure = (struct io_failure_record *)(unsigned long)
private_failure;
set_state_private(&BTRFS_I(inode)->io_failure_tree,
failure->start, 0);
clear_extent_bits(&BTRFS_I(inode)->io_failure_tree,
failure->start,
failure->start + failure->len - 1,
EXTENT_DIRTY | EXTENT_LOCKED,
GFP_NOFS);
kfree(failure);
}
}
return 0;
}
/*
* when reads are done, we need to check csums to verify the data is correct
* if there's a match, we allow the bio to finish. If not, we go through
* the io_failure_record routines to find good copies
*/
int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
struct extent_state *state)
{
size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT);
struct inode *inode = page->mapping->host;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
char *kaddr;
u64 private = ~(u32)0;
int ret;
struct btrfs_root *root = BTRFS_I(inode)->root;
u32 csum = ~(u32)0;
unsigned long flags;
if (btrfs_test_opt(root, NODATASUM) ||
btrfs_test_flag(inode, NODATASUM))
return 0;
if (state && state->start == start) {
private = state->private;
ret = 0;
} else {
ret = get_state_private(io_tree, start, &private);
}
local_irq_save(flags);
kaddr = kmap_atomic(page, KM_IRQ0);
if (ret) {
goto zeroit;
}
csum = btrfs_csum_data(root, kaddr + offset, csum, end - start + 1);
btrfs_csum_final(csum, (char *)&csum);
if (csum != private) {
goto zeroit;
}
kunmap_atomic(kaddr, KM_IRQ0);
local_irq_restore(flags);
/* if the io failure tree for this inode is non-empty,
* check to see if we've recovered from a failed IO
*/
btrfs_clean_io_failures(inode, start);
return 0;
zeroit:
printk("btrfs csum failed ino %lu off %llu csum %u private %Lu\n",
page->mapping->host->i_ino, (unsigned long long)start, csum,
private);
memset(kaddr + offset, 1, end - start + 1);
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_IRQ0);
local_irq_restore(flags);
if (private == 0)
return 0;
return -EIO;
}
/*
* This creates an orphan entry for the given inode in case something goes
* wrong in the middle of an unlink/truncate.
*/
int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
spin_lock(&root->list_lock);
/* already on the orphan list, we're good */
if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
spin_unlock(&root->list_lock);
return 0;
}
list_add(&BTRFS_I(inode)->i_orphan, &root->orphan_list);
spin_unlock(&root->list_lock);
/*
* insert an orphan item to track this unlinked/truncated file
*/
ret = btrfs_insert_orphan_item(trans, root, inode->i_ino);
return ret;
}
/*
* We have done the truncate/delete so we can go ahead and remove the orphan
* item for this particular inode.
*/
int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
spin_lock(&root->list_lock);
if (list_empty(&BTRFS_I(inode)->i_orphan)) {
spin_unlock(&root->list_lock);
return 0;
}
list_del_init(&BTRFS_I(inode)->i_orphan);
if (!trans) {
spin_unlock(&root->list_lock);
return 0;
}
spin_unlock(&root->list_lock);
ret = btrfs_del_orphan_item(trans, root, inode->i_ino);
return ret;
}
/*
* this cleans up any orphans that may be left on the list from the last use
* of this root.
*/
void btrfs_orphan_cleanup(struct btrfs_root *root)
{
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_item *item;
struct btrfs_key key, found_key;
struct btrfs_trans_handle *trans;
struct inode *inode;
int ret = 0, nr_unlink = 0, nr_truncate = 0;
/* don't do orphan cleanup if the fs is readonly. */
if (root->fs_info->sb->s_flags & MS_RDONLY)
return;
path = btrfs_alloc_path();
if (!path)
return;
path->reada = -1;
key.objectid = BTRFS_ORPHAN_OBJECTID;
btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
key.offset = (u64)-1;
while (1) {
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0) {
printk(KERN_ERR "Error searching slot for orphan: %d"
"\n", ret);
break;
}
/*
* if ret == 0 means we found what we were searching for, which
* is weird, but possible, so only screw with path if we didnt
* find the key and see if we have stuff that matches
*/
if (ret > 0) {
if (path->slots[0] == 0)
break;
path->slots[0]--;
}
/* pull out the item */
leaf = path->nodes[0];
item = btrfs_item_nr(leaf, path->slots[0]);
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
/* make sure the item matches what we want */
if (found_key.objectid != BTRFS_ORPHAN_OBJECTID)
break;
if (btrfs_key_type(&found_key) != BTRFS_ORPHAN_ITEM_KEY)
break;
/* release the path since we're done with it */
btrfs_release_path(root, path);
/*
* this is where we are basically btrfs_lookup, without the
* crossing root thing. we store the inode number in the
* offset of the orphan item.
*/
inode = btrfs_iget_locked(root->fs_info->sb,
found_key.offset, root);
if (!inode)
break;
if (inode->i_state & I_NEW) {
BTRFS_I(inode)->root = root;
/* have to set the location manually */
BTRFS_I(inode)->location.objectid = inode->i_ino;
BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
BTRFS_I(inode)->location.offset = 0;
btrfs_read_locked_inode(inode);
unlock_new_inode(inode);
}
/*
* add this inode to the orphan list so btrfs_orphan_del does
* the proper thing when we hit it
*/
spin_lock(&root->list_lock);
list_add(&BTRFS_I(inode)->i_orphan, &root->orphan_list);
spin_unlock(&root->list_lock);
/*
* if this is a bad inode, means we actually succeeded in
* removing the inode, but not the orphan record, which means
* we need to manually delete the orphan since iput will just
* do a destroy_inode
*/
if (is_bad_inode(inode)) {
trans = btrfs_start_transaction(root, 1);
btrfs_orphan_del(trans, inode);
btrfs_end_transaction(trans, root);
iput(inode);
continue;
}
/* if we have links, this was a truncate, lets do that */
if (inode->i_nlink) {
nr_truncate++;
btrfs_truncate(inode);
} else {
nr_unlink++;
}
/* this will do delete_inode and everything for us */
iput(inode);
}
if (nr_unlink)
printk(KERN_INFO "btrfs: unlinked %d orphans\n", nr_unlink);
if (nr_truncate)
printk(KERN_INFO "btrfs: truncated %d orphans\n", nr_truncate);
btrfs_free_path(path);
}
/*
* read an inode from the btree into the in-memory inode
*/
void btrfs_read_locked_inode(struct inode *inode)
{
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_inode_item *inode_item;
struct btrfs_timespec *tspec;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_key location;
u64 alloc_group_block;
u32 rdev;
int ret;
path = btrfs_alloc_path();
BUG_ON(!path);
memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
if (ret)
goto make_bad;
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
inode->i_mode = btrfs_inode_mode(leaf, inode_item);
inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
inode->i_uid = btrfs_inode_uid(leaf, inode_item);
inode->i_gid = btrfs_inode_gid(leaf, inode_item);
btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
tspec = btrfs_inode_atime(inode_item);
inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, tspec);
inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
tspec = btrfs_inode_mtime(inode_item);
inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, tspec);
inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
tspec = btrfs_inode_ctime(inode_item);
inode->i_ctime.tv_sec = btrfs_timespec_sec(leaf, tspec);
inode->i_ctime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item));
BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
inode->i_generation = BTRFS_I(inode)->generation;
inode->i_rdev = 0;
rdev = btrfs_inode_rdev(leaf, inode_item);
BTRFS_I(inode)->index_cnt = (u64)-1;
alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
BTRFS_I(inode)->block_group = btrfs_lookup_block_group(root->fs_info,
alloc_group_block);
BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
if (!BTRFS_I(inode)->block_group) {
BTRFS_I(inode)->block_group = btrfs_find_block_group(root,
NULL, 0,
BTRFS_BLOCK_GROUP_METADATA, 0);
}
btrfs_free_path(path);
inode_item = NULL;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
break;
case S_IFDIR:
inode->i_fop = &btrfs_dir_file_operations;
if (root == root->fs_info->tree_root)
inode->i_op = &btrfs_dir_ro_inode_operations;
else
inode->i_op = &btrfs_dir_inode_operations;
break;
case S_IFLNK:
inode->i_op = &btrfs_symlink_inode_operations;
inode->i_mapping->a_ops = &btrfs_symlink_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
break;
default:
init_special_inode(inode, inode->i_mode, rdev);
break;
}
return;
make_bad:
btrfs_free_path(path);
make_bad_inode(inode);
}
/*
* given a leaf and an inode, copy the inode fields into the leaf
*/
static void fill_inode_item(struct btrfs_trans_handle *trans,
struct extent_buffer *leaf,
struct btrfs_inode_item *item,
struct inode *inode)
{
btrfs_set_inode_uid(leaf, item, inode->i_uid);
btrfs_set_inode_gid(leaf, item, inode->i_gid);
btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size);
btrfs_set_inode_mode(leaf, item, inode->i_mode);
btrfs_set_inode_nlink(leaf, item, inode->i_nlink);
btrfs_set_timespec_sec(leaf, btrfs_inode_atime(item),
inode->i_atime.tv_sec);
btrfs_set_timespec_nsec(leaf, btrfs_inode_atime(item),
inode->i_atime.tv_nsec);
btrfs_set_timespec_sec(leaf, btrfs_inode_mtime(item),
inode->i_mtime.tv_sec);
btrfs_set_timespec_nsec(leaf, btrfs_inode_mtime(item),
inode->i_mtime.tv_nsec);
btrfs_set_timespec_sec(leaf, btrfs_inode_ctime(item),
inode->i_ctime.tv_sec);
btrfs_set_timespec_nsec(leaf, btrfs_inode_ctime(item),
inode->i_ctime.tv_nsec);
btrfs_set_inode_nbytes(leaf, item, inode_get_bytes(inode));
btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation);
btrfs_set_inode_transid(leaf, item, trans->transid);
btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
btrfs_set_inode_block_group(leaf, item,
BTRFS_I(inode)->block_group->key.objectid);
}
/*
* copy everything in the in-memory inode into the btree.
*/
int noinline btrfs_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode)
{
struct btrfs_inode_item *inode_item;
struct btrfs_path *path;
struct extent_buffer *leaf;
int ret;
path = btrfs_alloc_path();
BUG_ON(!path);
ret = btrfs_lookup_inode(trans, root, path,
&BTRFS_I(inode)->location, 1);
if (ret) {
if (ret > 0)
ret = -ENOENT;
goto failed;
}
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
fill_inode_item(trans, leaf, inode_item, inode);
btrfs_mark_buffer_dirty(leaf);
btrfs_set_inode_last_trans(trans, inode);
ret = 0;
failed:
btrfs_free_path(path);
return ret;
}
/*
* unlink helper that gets used here in inode.c and in the tree logging
* recovery code. It remove a link in a directory with a given name, and
* also drops the back refs in the inode to the directory
*/
int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir, struct inode *inode,
const char *name, int name_len)
{
struct btrfs_path *path;
int ret = 0;
struct extent_buffer *leaf;
struct btrfs_dir_item *di;
struct btrfs_key key;
u64 index;
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto err;
}
di = btrfs_lookup_dir_item(trans, root, path, dir->i_ino,
name, name_len, -1);
if (IS_ERR(di)) {
ret = PTR_ERR(di);
goto err;
}
if (!di) {
ret = -ENOENT;
goto err;
}
leaf = path->nodes[0];
btrfs_dir_item_key_to_cpu(leaf, di, &key);
ret = btrfs_delete_one_dir_name(trans, root, path, di);
if (ret)
goto err;
btrfs_release_path(root, path);
ret = btrfs_del_inode_ref(trans, root, name, name_len,
inode->i_ino,
dir->i_ino, &index);
if (ret) {
printk("failed to delete reference to %.*s, "
"inode %lu parent %lu\n", name_len, name,
inode->i_ino, dir->i_ino);
goto err;
}
di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
index, name, name_len, -1);
if (IS_ERR(di)) {
ret = PTR_ERR(di);
goto err;
}
if (!di) {
ret = -ENOENT;
goto err;
}
ret = btrfs_delete_one_dir_name(trans, root, path, di);
btrfs_release_path(root, path);
ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len,
inode, dir->i_ino);
BUG_ON(ret != 0 && ret != -ENOENT);
if (ret != -ENOENT)
BTRFS_I(dir)->log_dirty_trans = trans->transid;
ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len,
dir, index);
BUG_ON(ret);
err:
btrfs_free_path(path);
if (ret)
goto out;
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
btrfs_update_inode(trans, root, dir);
btrfs_drop_nlink(inode);
ret = btrfs_update_inode(trans, root, inode);
dir->i_sb->s_dirt = 1;
out:
return ret;
}
static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
{
struct btrfs_root *root;
struct btrfs_trans_handle *trans;
struct inode *inode = dentry->d_inode;
int ret;
unsigned long nr = 0;
root = BTRFS_I(dir)->root;
ret = btrfs_check_free_space(root, 1, 1);
if (ret)
goto fail;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
dentry->d_name.name, dentry->d_name.len);
if (inode->i_nlink == 0)
ret = btrfs_orphan_add(trans, inode);
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
fail:
btrfs_btree_balance_dirty(root, nr);
return ret;
}
static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
int err = 0;
int ret;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_trans_handle *trans;
unsigned long nr = 0;
if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) {
return -ENOTEMPTY;
}
ret = btrfs_check_free_space(root, 1, 1);
if (ret)
goto fail;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
err = btrfs_orphan_add(trans, inode);
if (err)
goto fail_trans;
/* now the directory is empty */
err = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
dentry->d_name.name, dentry->d_name.len);
if (!err) {
btrfs_i_size_write(inode, 0);
}
fail_trans:
nr = trans->blocks_used;
ret = btrfs_end_transaction_throttle(trans, root);
fail:
btrfs_btree_balance_dirty(root, nr);
if (ret && !err)
err = ret;
return err;
}
/*
* when truncating bytes in a file, it is possible to avoid reading
* the leaves that contain only checksum items. This can be the
* majority of the IO required to delete a large file, but it must
* be done carefully.
*
* The keys in the level just above the leaves are checked to make sure
* the lowest key in a given leaf is a csum key, and starts at an offset
* after the new size.
*
* Then the key for the next leaf is checked to make sure it also has
* a checksum item for the same file. If it does, we know our target leaf
* contains only checksum items, and it can be safely freed without reading
* it.
*
* This is just an optimization targeted at large files. It may do
* nothing. It will return 0 unless things went badly.
*/
static noinline int drop_csum_leaves(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
struct inode *inode, u64 new_size)
{
struct btrfs_key key;
int ret;
int nritems;
struct btrfs_key found_key;
struct btrfs_key other_key;
struct btrfs_leaf_ref *ref;
u64 leaf_gen;
u64 leaf_start;
path->lowest_level = 1;
key.objectid = inode->i_ino;
key.type = BTRFS_CSUM_ITEM_KEY;
key.offset = new_size;
again:
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret < 0)
goto out;
if (path->nodes[1] == NULL) {
ret = 0;
goto out;
}
ret = 0;
btrfs_node_key_to_cpu(path->nodes[1], &found_key, path->slots[1]);
nritems = btrfs_header_nritems(path->nodes[1]);
if (!nritems)
goto out;
if (path->slots[1] >= nritems)
goto next_node;
/* did we find a key greater than anything we want to delete? */
if (found_key.objectid > inode->i_ino ||
(found_key.objectid == inode->i_ino && found_key.type > key.type))
goto out;
/* we check the next key in the node to make sure the leave contains
* only checksum items. This comparison doesn't work if our
* leaf is the last one in the node
*/
if (path->slots[1] + 1 >= nritems) {
next_node:
/* search forward from the last key in the node, this
* will bring us into the next node in the tree
*/
btrfs_node_key_to_cpu(path->nodes[1], &found_key, nritems - 1);
/* unlikely, but we inc below, so check to be safe */
if (found_key.offset == (u64)-1)
goto out;
/* search_forward needs a path with locks held, do the
* search again for the original key. It is possible
* this will race with a balance and return a path that
* we could modify, but this drop is just an optimization
* and is allowed to miss some leaves.
*/
btrfs_release_path(root, path);
found_key.offset++;
/* setup a max key for search_forward */
other_key.offset = (u64)-1;
other_key.type = key.type;
other_key.objectid = key.objectid;
path->keep_locks = 1;
ret = btrfs_search_forward(root, &found_key, &other_key,
path, 0, 0);
path->keep_locks = 0;
if (ret || found_key.objectid != key.objectid ||
found_key.type != key.type) {
ret = 0;
goto out;
}
key.offset = found_key.offset;
btrfs_release_path(root, path);
cond_resched();
goto again;
}
/* we know there's one more slot after us in the tree,
* read that key so we can verify it is also a checksum item
*/
btrfs_node_key_to_cpu(path->nodes[1], &other_key, path->slots[1] + 1);
if (found_key.objectid < inode->i_ino)
goto next_key;
if (found_key.type != key.type || found_key.offset < new_size)
goto next_key;
/*
* if the key for the next leaf isn't a csum key from this objectid,
* we can't be sure there aren't good items inside this leaf.
* Bail out
*/
if (other_key.objectid != inode->i_ino || other_key.type != key.type)
goto out;
leaf_start = btrfs_node_blockptr(path->nodes[1], path->slots[1]);
leaf_gen = btrfs_node_ptr_generation(path->nodes[1], path->slots[1]);
/*
* it is safe to delete this leaf, it contains only
* csum items from this inode at an offset >= new_size
*/
ret = btrfs_del_leaf(trans, root, path, leaf_start);
BUG_ON(ret);
if (root->ref_cows && leaf_gen < trans->transid) {
ref = btrfs_alloc_leaf_ref(root, 0);
if (ref) {
ref->root_gen = root->root_key.offset;
ref->bytenr = leaf_start;
ref->owner = 0;
ref->generation = leaf_gen;
ref->nritems = 0;
ret = btrfs_add_leaf_ref(root, ref, 0);
WARN_ON(ret);
btrfs_free_leaf_ref(root, ref);
} else {
WARN_ON(1);
}
}
next_key:
btrfs_release_path(root, path);
if (other_key.objectid == inode->i_ino &&
other_key.type == key.type && other_key.offset > key.offset) {
key.offset = other_key.offset;
cond_resched();
goto again;
}
ret = 0;
out:
/* fixup any changes we've made to the path */
path->lowest_level = 0;
path->keep_locks = 0;
btrfs_release_path(root, path);
return ret;
}
/*
* this can truncate away extent items, csum items and directory items.
* It starts at a high offset and removes keys until it can't find
* any higher than new_size
*
* csum items that cross the new i_size are truncated to the new size
* as well.
*
* min_type is the minimum key type to truncate down to. If set to 0, this
* will kill all the items on this inode, including the INODE_ITEM_KEY.
*/
noinline int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode,
u64 new_size, u32 min_type)
{
int ret;
struct btrfs_path *path;
struct btrfs_key key;
struct btrfs_key found_key;
u32 found_type;
struct extent_buffer *leaf;
struct btrfs_file_extent_item *fi;
u64 extent_start = 0;
u64 extent_num_bytes = 0;
u64 item_end = 0;
u64 root_gen = 0;
u64 root_owner = 0;
int found_extent;
int del_item;
int pending_del_nr = 0;
int pending_del_slot = 0;
int extent_type = -1;
u64 mask = root->sectorsize - 1;
if (root->ref_cows)
btrfs_drop_extent_cache(inode, new_size & (~mask), (u64)-1, 0);
path = btrfs_alloc_path();
path->reada = -1;
BUG_ON(!path);
/* FIXME, add redo link to tree so we don't leak on crash */
key.objectid = inode->i_ino;
key.offset = (u64)-1;
key.type = (u8)-1;
btrfs_init_path(path);
ret = drop_csum_leaves(trans, root, path, inode, new_size);
BUG_ON(ret);
search_again:
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret < 0) {
goto error;
}
if (ret > 0) {
/* there are no items in the tree for us to truncate, we're
* done
*/
if (path->slots[0] == 0) {
ret = 0;
goto error;
}
path->slots[0]--;
}
while(1) {
fi = NULL;
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
if (found_key.objectid != inode->i_ino)
break;
if (found_type < min_type)
break;
item_end = found_key.offset;
if (found_type == BTRFS_EXTENT_DATA_KEY) {
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
extent_type = btrfs_file_extent_type(leaf, fi);
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
item_end +=
btrfs_file_extent_num_bytes(leaf, fi);
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
item_end += btrfs_file_extent_inline_len(leaf,
fi);
}
item_end--;
}
if (found_type == BTRFS_CSUM_ITEM_KEY) {
ret = btrfs_csum_truncate(trans, root, path,
new_size);
BUG_ON(ret);
}
if (item_end < new_size) {
if (found_type == BTRFS_DIR_ITEM_KEY) {
found_type = BTRFS_INODE_ITEM_KEY;
} else if (found_type == BTRFS_EXTENT_ITEM_KEY) {
found_type = BTRFS_CSUM_ITEM_KEY;
} else if (found_type == BTRFS_EXTENT_DATA_KEY) {
found_type = BTRFS_XATTR_ITEM_KEY;
} else if (found_type == BTRFS_XATTR_ITEM_KEY) {
found_type = BTRFS_INODE_REF_KEY;
} else if (found_type) {
found_type--;
} else {
break;
}
btrfs_set_key_type(&key, found_type);
goto next;
}
if (found_key.offset >= new_size)
del_item = 1;
else
del_item = 0;
found_extent = 0;
/* FIXME, shrink the extent if the ref count is only 1 */
if (found_type != BTRFS_EXTENT_DATA_KEY)
goto delete;
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
u64 num_dec;
extent_start = btrfs_file_extent_disk_bytenr(leaf, fi);
if (!del_item) {
u64 orig_num_bytes =
btrfs_file_extent_num_bytes(leaf, fi);
extent_num_bytes = new_size -
found_key.offset + root->sectorsize - 1;
extent_num_bytes = extent_num_bytes &
~((u64)root->sectorsize - 1);
btrfs_set_file_extent_num_bytes(leaf, fi,
extent_num_bytes);
num_dec = (orig_num_bytes -
extent_num_bytes);
if (root->ref_cows && extent_start != 0)
inode_sub_bytes(inode, num_dec);
btrfs_mark_buffer_dirty(leaf);
} else {
extent_num_bytes =
btrfs_file_extent_disk_num_bytes(leaf,
fi);
/* FIXME blocksize != 4096 */
num_dec = btrfs_file_extent_num_bytes(leaf, fi);
if (extent_start != 0) {
found_extent = 1;
if (root->ref_cows)
inode_sub_bytes(inode, num_dec);
}
root_gen = btrfs_header_generation(leaf);
root_owner = btrfs_header_owner(leaf);
}
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
/*
* we can't truncate inline items that have had
* special encodings
*/
if (!del_item &&
btrfs_file_extent_compression(leaf, fi) == 0 &&
btrfs_file_extent_encryption(leaf, fi) == 0 &&
btrfs_file_extent_other_encoding(leaf, fi) == 0) {
u32 size = new_size - found_key.offset;
if (root->ref_cows) {
inode_sub_bytes(inode, item_end + 1 -
new_size);
}
size =
btrfs_file_extent_calc_inline_size(size);
ret = btrfs_truncate_item(trans, root, path,
size, 1);
BUG_ON(ret);
} else if (root->ref_cows) {
inode_sub_bytes(inode, item_end + 1 -
found_key.offset);
}
}
delete:
if (del_item) {
if (!pending_del_nr) {
/* no pending yet, add ourselves */
pending_del_slot = path->slots[0];
pending_del_nr = 1;
} else if (pending_del_nr &&
path->slots[0] + 1 == pending_del_slot) {
/* hop on the pending chunk */
pending_del_nr++;
pending_del_slot = path->slots[0];
} else {
printk("bad pending slot %d pending_del_nr %d pending_del_slot %d\n", path->slots[0], pending_del_nr, pending_del_slot);
}
} else {
break;
}
if (found_extent) {
ret = btrfs_free_extent(trans, root, extent_start,
extent_num_bytes,
leaf->start, root_owner,
root_gen, inode->i_ino, 0);
BUG_ON(ret);
}
next:
if (path->slots[0] == 0) {
if (pending_del_nr)
goto del_pending;
btrfs_release_path(root, path);
goto search_again;
}
path->slots[0]--;
if (pending_del_nr &&
path->slots[0] + 1 != pending_del_slot) {
struct btrfs_key debug;
del_pending:
btrfs_item_key_to_cpu(path->nodes[0], &debug,
pending_del_slot);
ret = btrfs_del_items(trans, root, path,
pending_del_slot,
pending_del_nr);
BUG_ON(ret);
pending_del_nr = 0;
btrfs_release_path(root, path);
goto search_again;
}
}
ret = 0;
error:
if (pending_del_nr) {
ret = btrfs_del_items(trans, root, path, pending_del_slot,
pending_del_nr);
}
btrfs_free_path(path);
inode->i_sb->s_dirt = 1;
return ret;
}
/*
* taken from block_truncate_page, but does cow as it zeros out
* any bytes left in the last page in the file.
*/
static int btrfs_truncate_page(struct address_space *mapping, loff_t from)
{
struct inode *inode = mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
char *kaddr;
u32 blocksize = root->sectorsize;
pgoff_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
struct page *page;
int ret = 0;
u64 page_start;
u64 page_end;
if ((offset & (blocksize - 1)) == 0)
goto out;
ret = -ENOMEM;
again:
page = grab_cache_page(mapping, index);
if (!page)
goto out;
page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
if (!PageUptodate(page)) {
ret = btrfs_readpage(NULL, page);
lock_page(page);
if (page->mapping != mapping) {
unlock_page(page);
page_cache_release(page);
goto again;
}
if (!PageUptodate(page)) {
ret = -EIO;
goto out_unlock;
}
}
wait_on_page_writeback(page);
lock_extent(io_tree, page_start, page_end, GFP_NOFS);
set_page_extent_mapped(page);
ordered = btrfs_lookup_ordered_extent(inode, page_start);
if (ordered) {
unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
unlock_page(page);
page_cache_release(page);
btrfs_start_ordered_extent(inode, ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
}
btrfs_set_extent_delalloc(inode, page_start, page_end);
ret = 0;
if (offset != PAGE_CACHE_SIZE) {
kaddr = kmap(page);
memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
flush_dcache_page(page);
kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
out_unlock:
unlock_page(page);
page_cache_release(page);
out:
return ret;
}
static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
int err;
err = inode_change_ok(inode, attr);
if (err)
return err;
if (S_ISREG(inode->i_mode) &&
attr->ia_valid & ATTR_SIZE && attr->ia_size > inode->i_size) {
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
u64 mask = root->sectorsize - 1;
u64 hole_start = (inode->i_size + mask) & ~mask;
u64 block_end = (attr->ia_size + mask) & ~mask;
u64 hole_size;
u64 alloc_hint = 0;
if (attr->ia_size <= hole_start)
goto out;
err = btrfs_check_free_space(root, 1, 0);
if (err)
goto fail;
btrfs_truncate_page(inode->i_mapping, inode->i_size);
hole_size = block_end - hole_start;
while(1) {
struct btrfs_ordered_extent *ordered;
btrfs_wait_ordered_range(inode, hole_start, hole_size);
lock_extent(io_tree, hole_start, block_end - 1, GFP_NOFS);
ordered = btrfs_lookup_ordered_extent(inode, hole_start);
if (ordered) {
unlock_extent(io_tree, hole_start,
block_end - 1, GFP_NOFS);
btrfs_put_ordered_extent(ordered);
} else {
break;
}
}
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
mutex_lock(&BTRFS_I(inode)->extent_mutex);
err = btrfs_drop_extents(trans, root, inode,
hole_start, block_end, hole_start,
&alloc_hint);
if (alloc_hint != EXTENT_MAP_INLINE) {
err = btrfs_insert_file_extent(trans, root,
inode->i_ino,
hole_start, 0, 0,
hole_size, 0, hole_size,
0, 0, 0);
btrfs_drop_extent_cache(inode, hole_start,
(u64)-1, 0);
btrfs_check_file(root, inode);
}
mutex_unlock(&BTRFS_I(inode)->extent_mutex);
btrfs_end_transaction(trans, root);
unlock_extent(io_tree, hole_start, block_end - 1, GFP_NOFS);
if (err)
return err;
}
out:
err = inode_setattr(inode, attr);
if (!err && ((attr->ia_valid & ATTR_MODE)))
err = btrfs_acl_chmod(inode);
fail:
return err;
}
void btrfs_delete_inode(struct inode *inode)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
unsigned long nr;
int ret;
truncate_inode_pages(&inode->i_data, 0);
if (is_bad_inode(inode)) {
btrfs_orphan_del(NULL, inode);
goto no_delete;
}
btrfs_wait_ordered_range(inode, 0, (u64)-1);
btrfs_i_size_write(inode, 0);
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
ret = btrfs_truncate_inode_items(trans, root, inode, inode->i_size, 0);
if (ret) {
btrfs_orphan_del(NULL, inode);
goto no_delete_lock;
}
btrfs_orphan_del(trans, inode);
nr = trans->blocks_used;
clear_inode(inode);
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root, nr);
return;
no_delete_lock:
nr = trans->blocks_used;
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root, nr);
no_delete:
clear_inode(inode);
}
/*
* this returns the key found in the dir entry in the location pointer.
* If no dir entries were found, location->objectid is 0.
*/
static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
struct btrfs_key *location)
{
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
struct btrfs_dir_item *di;
struct btrfs_path *path;
struct btrfs_root *root = BTRFS_I(dir)->root;
int ret = 0;
path = btrfs_alloc_path();
BUG_ON(!path);
di = btrfs_lookup_dir_item(NULL, root, path, dir->i_ino, name,
namelen, 0);
if (IS_ERR(di))
ret = PTR_ERR(di);
if (!di || IS_ERR(di)) {
goto out_err;
}
btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
out:
btrfs_free_path(path);
return ret;
out_err:
location->objectid = 0;
goto out;
}
/*
* when we hit a tree root in a directory, the btrfs part of the inode
* needs to be changed to reflect the root directory of the tree root. This
* is kind of like crossing a mount point.
*/
static int fixup_tree_root_location(struct btrfs_root *root,
struct btrfs_key *location,
struct btrfs_root **sub_root,
struct dentry *dentry)
{
struct btrfs_root_item *ri;
if (btrfs_key_type(location) != BTRFS_ROOT_ITEM_KEY)
return 0;
if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
return 0;
*sub_root = btrfs_read_fs_root(root->fs_info, location,
dentry->d_name.name,
dentry->d_name.len);
if (IS_ERR(*sub_root))
return PTR_ERR(*sub_root);
ri = &(*sub_root)->root_item;
location->objectid = btrfs_root_dirid(ri);
btrfs_set_key_type(location, BTRFS_INODE_ITEM_KEY);
location->offset = 0;
return 0;
}
static noinline void init_btrfs_i(struct inode *inode)
{
struct btrfs_inode *bi = BTRFS_I(inode);
bi->i_acl = NULL;
bi->i_default_acl = NULL;
bi->generation = 0;
bi->last_trans = 0;
bi->logged_trans = 0;
bi->delalloc_bytes = 0;
bi->disk_i_size = 0;
bi->flags = 0;
bi->index_cnt = (u64)-1;
bi->log_dirty_trans = 0;
extent_map_tree_init(&BTRFS_I(inode)->extent_tree, GFP_NOFS);
extent_io_tree_init(&BTRFS_I(inode)->io_tree,
inode->i_mapping, GFP_NOFS);
extent_io_tree_init(&BTRFS_I(inode)->io_failure_tree,
inode->i_mapping, GFP_NOFS);
INIT_LIST_HEAD(&BTRFS_I(inode)->delalloc_inodes);
btrfs_ordered_inode_tree_init(&BTRFS_I(inode)->ordered_tree);
mutex_init(&BTRFS_I(inode)->csum_mutex);
mutex_init(&BTRFS_I(inode)->extent_mutex);
mutex_init(&BTRFS_I(inode)->log_mutex);
}
static int btrfs_init_locked_inode(struct inode *inode, void *p)
{
struct btrfs_iget_args *args = p;
inode->i_ino = args->ino;
init_btrfs_i(inode);
BTRFS_I(inode)->root = args->root;
return 0;
}
static int btrfs_find_actor(struct inode *inode, void *opaque)
{
struct btrfs_iget_args *args = opaque;
return (args->ino == inode->i_ino &&
args->root == BTRFS_I(inode)->root);
}
struct inode *btrfs_ilookup(struct super_block *s, u64 objectid,
struct btrfs_root *root, int wait)
{
struct inode *inode;
struct btrfs_iget_args args;
args.ino = objectid;
args.root = root;
if (wait) {
inode = ilookup5(s, objectid, btrfs_find_actor,
(void *)&args);
} else {
inode = ilookup5_nowait(s, objectid, btrfs_find_actor,
(void *)&args);
}
return inode;
}
struct inode *btrfs_iget_locked(struct super_block *s, u64 objectid,
struct btrfs_root *root)
{
struct inode *inode;
struct btrfs_iget_args args;
args.ino = objectid;
args.root = root;
inode = iget5_locked(s, objectid, btrfs_find_actor,
btrfs_init_locked_inode,
(void *)&args);
return inode;
}
/* Get an inode object given its location and corresponding root.
* Returns in *is_new if the inode was read from disk
*/
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *is_new)
{
struct inode *inode;
inode = btrfs_iget_locked(s, location->objectid, root);
if (!inode)
return ERR_PTR(-EACCES);
if (inode->i_state & I_NEW) {
BTRFS_I(inode)->root = root;
memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
btrfs_read_locked_inode(inode);
unlock_new_inode(inode);
if (is_new)
*is_new = 1;
} else {
if (is_new)
*is_new = 0;
}
return inode;
}
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct inode * inode;
struct btrfs_inode *bi = BTRFS_I(dir);
struct btrfs_root *root = bi->root;
struct btrfs_root *sub_root = root;
struct btrfs_key location;
int ret, new, do_orphan = 0;
if (dentry->d_name.len > BTRFS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
ret = btrfs_inode_by_name(dir, dentry, &location);
if (ret < 0)
return ERR_PTR(ret);
inode = NULL;
if (location.objectid) {
ret = fixup_tree_root_location(root, &location, &sub_root,
dentry);
if (ret < 0)
return ERR_PTR(ret);
if (ret > 0)
return ERR_PTR(-ENOENT);
inode = btrfs_iget(dir->i_sb, &location, sub_root, &new);
if (IS_ERR(inode))
return ERR_CAST(inode);
/* the inode and parent dir are two different roots */
if (new && root != sub_root) {
igrab(inode);
sub_root->inode = inode;
do_orphan = 1;
}
}
if (unlikely(do_orphan))
btrfs_orphan_cleanup(sub_root);
return d_splice_alias(inode, dentry);
}
static unsigned char btrfs_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
static int btrfs_real_readdir(struct file *filp, void *dirent,
filldir_t filldir)
{
struct inode *inode = filp->f_dentry->d_inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_item *item;
struct btrfs_dir_item *di;
struct btrfs_key key;
struct btrfs_key found_key;
struct btrfs_path *path;
int ret;
u32 nritems;
struct extent_buffer *leaf;
int slot;
int advance;
unsigned char d_type;
int over = 0;
u32 di_cur;
u32 di_total;
u32 di_len;
int key_type = BTRFS_DIR_INDEX_KEY;
char tmp_name[32];
char *name_ptr;
int name_len;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
key_type = BTRFS_DIR_ITEM_KEY;
/* special case for "." */
if (filp->f_pos == 0) {
over = filldir(dirent, ".", 1,
1, inode->i_ino,
DT_DIR);
if (over)
return 0;
filp->f_pos = 1;
}
/* special case for .., just use the back ref */
if (filp->f_pos == 1) {
u64 pino = parent_ino(filp->f_path.dentry);
over = filldir(dirent, "..", 2,
2, pino, DT_DIR);
if (over)
return 0;
filp->f_pos = 2;
}
path = btrfs_alloc_path();
path->reada = 2;
btrfs_set_key_type(&key, key_type);
key.offset = filp->f_pos;
key.objectid = inode->i_ino;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto err;
advance = 0;
while (1) {
leaf = path->nodes[0];
nritems = btrfs_header_nritems(leaf);
slot = path->slots[0];
if (advance || slot >= nritems) {
if (slot >= nritems - 1) {
ret = btrfs_next_leaf(root, path);
if (ret)
break;
leaf = path->nodes[0];
nritems = btrfs_header_nritems(leaf);
slot = path->slots[0];
} else {
slot++;
path->slots[0]++;
}
}
advance = 1;
item = btrfs_item_nr(leaf, slot);
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.objectid != key.objectid)
break;
if (btrfs_key_type(&found_key) != key_type)
break;
if (found_key.offset < filp->f_pos)
continue;
filp->f_pos = found_key.offset;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
di_cur = 0;
di_total = btrfs_item_size(leaf, item);
while (di_cur < di_total) {
struct btrfs_key location;
name_len = btrfs_dir_name_len(leaf, di);
if (name_len <= sizeof(tmp_name)) {
name_ptr = tmp_name;
} else {
name_ptr = kmalloc(name_len, GFP_NOFS);
if (!name_ptr) {
ret = -ENOMEM;
goto err;
}
}
read_extent_buffer(leaf, name_ptr,
(unsigned long)(di + 1), name_len);
d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
btrfs_dir_item_key_to_cpu(leaf, di, &location);
over = filldir(dirent, name_ptr, name_len,
found_key.offset, location.objectid,
d_type);
if (name_ptr != tmp_name)
kfree(name_ptr);
if (over)
goto nopos;
di_len = btrfs_dir_name_len(leaf, di) +
btrfs_dir_data_len(leaf, di) + sizeof(*di);
di_cur += di_len;
di = (struct btrfs_dir_item *)((char *)di + di_len);
}
}
/* Reached end of directory/root. Bump pos past the last item. */
if (key_type == BTRFS_DIR_INDEX_KEY)
filp->f_pos = INT_LIMIT(typeof(filp->f_pos));
else
filp->f_pos++;
nopos:
ret = 0;
err:
btrfs_free_path(path);
return ret;
}
int btrfs_write_inode(struct inode *inode, int wait)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret = 0;
if (root->fs_info->closing > 1)
return 0;
if (wait) {
trans = btrfs_join_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
ret = btrfs_commit_transaction(trans, root);
}
return ret;
}
/*
* This is somewhat expensive, updating the tree every time the
* inode changes. But, it is most likely to find the inode in cache.
* FIXME, needs more benchmarking...there are no reasons other than performance
* to keep or drop this code.
*/
void btrfs_dirty_inode(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
trans = btrfs_join_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
}
/*
* find the highest existing sequence number in a directory
* and then set the in-memory index_cnt variable to reflect
* free sequence numbers
*/
static int btrfs_set_inode_index_count(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_key key, found_key;
struct btrfs_path *path;
struct extent_buffer *leaf;
int ret;
key.objectid = inode->i_ino;
btrfs_set_key_type(&key, BTRFS_DIR_INDEX_KEY);
key.offset = (u64)-1;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
/* FIXME: we should be able to handle this */
if (ret == 0)
goto out;
ret = 0;
/*
* MAGIC NUMBER EXPLANATION:
* since we search a directory based on f_pos we have to start at 2
* since '.' and '..' have f_pos of 0 and 1 respectively, so everybody
* else has to start at 2
*/
if (path->slots[0] == 0) {
BTRFS_I(inode)->index_cnt = 2;
goto out;
}
path->slots[0]--;
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
if (found_key.objectid != inode->i_ino ||
btrfs_key_type(&found_key) != BTRFS_DIR_INDEX_KEY) {
BTRFS_I(inode)->index_cnt = 2;
goto out;
}
BTRFS_I(inode)->index_cnt = found_key.offset + 1;
out:
btrfs_free_path(path);
return ret;
}
/*
* helper to find a free sequence number in a given directory. This current
* code is very simple, later versions will do smarter things in the btree
*/
static int btrfs_set_inode_index(struct inode *dir, struct inode *inode,
u64 *index)
{
int ret = 0;
if (BTRFS_I(dir)->index_cnt == (u64)-1) {
ret = btrfs_set_inode_index_count(dir);
if (ret) {
return ret;
}
}
*index = BTRFS_I(dir)->index_cnt;
BTRFS_I(dir)->index_cnt++;
return ret;
}
static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir,
const char *name, int name_len,
u64 ref_objectid,
u64 objectid,
struct btrfs_block_group_cache *group,
int mode, u64 *index)
{
struct inode *inode;
struct btrfs_inode_item *inode_item;
struct btrfs_block_group_cache *new_inode_group;
struct btrfs_key *location;
struct btrfs_path *path;
struct btrfs_inode_ref *ref;
struct btrfs_key key[2];
u32 sizes[2];
unsigned long ptr;
int ret;
int owner;
path = btrfs_alloc_path();
BUG_ON(!path);
inode = new_inode(root->fs_info->sb);
if (!inode)
return ERR_PTR(-ENOMEM);
if (dir) {
ret = btrfs_set_inode_index(dir, inode, index);
if (ret)
return ERR_PTR(ret);
}
/*
* index_cnt is ignored for everything but a dir,
* btrfs_get_inode_index_count has an explanation for the magic
* number
*/
init_btrfs_i(inode);
BTRFS_I(inode)->index_cnt = 2;
BTRFS_I(inode)->root = root;
BTRFS_I(inode)->generation = trans->transid;
if (mode & S_IFDIR)
owner = 0;
else
owner = 1;
new_inode_group = btrfs_find_block_group(root, group, 0,
BTRFS_BLOCK_GROUP_METADATA, owner);
if (!new_inode_group) {
printk("find_block group failed\n");
new_inode_group = group;
}
BTRFS_I(inode)->block_group = new_inode_group;
key[0].objectid = objectid;
btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
key[0].offset = 0;
key[1].objectid = objectid;
btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
key[1].offset = ref_objectid;
sizes[0] = sizeof(struct btrfs_inode_item);
sizes[1] = name_len + sizeof(*ref);
ret = btrfs_insert_empty_items(trans, root, path, key, sizes, 2);
if (ret != 0)
goto fail;
if (objectid > root->highest_inode)
root->highest_inode = objectid;
inode->i_uid = current->fsuid;
inode->i_gid = current->fsgid;
inode->i_mode = mode;
inode->i_ino = objectid;
inode_set_bytes(inode, 0);
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_inode_item);
fill_inode_item(trans, path->nodes[0], inode_item, inode);
ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
struct btrfs_inode_ref);
btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
ptr = (unsigned long)(ref + 1);
write_extent_buffer(path->nodes[0], name, ptr, name_len);
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_free_path(path);
location = &BTRFS_I(inode)->location;
location->objectid = objectid;
location->offset = 0;
btrfs_set_key_type(location, BTRFS_INODE_ITEM_KEY);
insert_inode_hash(inode);
return inode;
fail:
if (dir)
BTRFS_I(dir)->index_cnt--;
btrfs_free_path(path);
return ERR_PTR(ret);
}
static inline u8 btrfs_inode_type(struct inode *inode)
{
return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT];
}
/*
* utility function to add 'inode' into 'parent_inode' with
* a give name and a given sequence number.
* if 'add_backref' is true, also insert a backref from the
* inode to the parent directory.
*/
int btrfs_add_link(struct btrfs_trans_handle *trans,
struct inode *parent_inode, struct inode *inode,
const char *name, int name_len, int add_backref, u64 index)
{
int ret;
struct btrfs_key key;
struct btrfs_root *root = BTRFS_I(parent_inode)->root;
key.objectid = inode->i_ino;
btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
key.offset = 0;
ret = btrfs_insert_dir_item(trans, root, name, name_len,
parent_inode->i_ino,
&key, btrfs_inode_type(inode),
index);
if (ret == 0) {
if (add_backref) {
ret = btrfs_insert_inode_ref(trans, root,
name, name_len,
inode->i_ino,
parent_inode->i_ino,
index);
}
btrfs_i_size_write(parent_inode, parent_inode->i_size +
name_len * 2);
parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, parent_inode);
}
return ret;
}
static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
struct dentry *dentry, struct inode *inode,
int backref, u64 index)
{
int err = btrfs_add_link(trans, dentry->d_parent->d_inode,
inode, dentry->d_name.name,
dentry->d_name.len, backref, index);
if (!err) {
d_instantiate(dentry, inode);
return 0;
}
if (err > 0)
err = -EEXIST;
return err;
}
static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
int mode, dev_t rdev)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct inode *inode = NULL;
int err;
int drop_inode = 0;
u64 objectid;
unsigned long nr = 0;
u64 index = 0;
if (!new_valid_dev(rdev))
return -EINVAL;
err = btrfs_check_free_space(root, 1, 0);
if (err)
goto fail;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
err = btrfs_find_free_objectid(trans, root, dir->i_ino, &objectid);
if (err) {
err = -ENOSPC;
goto out_unlock;
}
inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
dentry->d_name.len,
dentry->d_parent->d_inode->i_ino, objectid,
BTRFS_I(dir)->block_group, mode, &index);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_unlock;
err = btrfs_init_acl(inode, dir);
if (err) {
drop_inode = 1;
goto out_unlock;
}
btrfs_set_trans_block_group(trans, inode);
err = btrfs_add_nondir(trans, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_op = &btrfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
btrfs_update_inode(trans, root, inode);
}
dir->i_sb->s_dirt = 1;
btrfs_update_inode_block_group(trans, inode);
btrfs_update_inode_block_group(trans, dir);
out_unlock:
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
fail:
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
}
btrfs_btree_balance_dirty(root, nr);
return err;
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
int mode, struct nameidata *nd)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct inode *inode = NULL;
int err;
int drop_inode = 0;
unsigned long nr = 0;
u64 objectid;
u64 index = 0;
err = btrfs_check_free_space(root, 1, 0);
if (err)
goto fail;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
err = btrfs_find_free_objectid(trans, root, dir->i_ino, &objectid);
if (err) {
err = -ENOSPC;
goto out_unlock;
}
inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
dentry->d_name.len,
dentry->d_parent->d_inode->i_ino,
objectid, BTRFS_I(dir)->block_group, mode,
&index);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_unlock;
err = btrfs_init_acl(inode, dir);
if (err) {
drop_inode = 1;
goto out_unlock;
}
btrfs_set_trans_block_group(trans, inode);
err = btrfs_add_nondir(trans, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
dir->i_sb->s_dirt = 1;
btrfs_update_inode_block_group(trans, inode);
btrfs_update_inode_block_group(trans, dir);
out_unlock:
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
fail:
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
}
btrfs_btree_balance_dirty(root, nr);
return err;
}
static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct inode *inode = old_dentry->d_inode;
u64 index;
unsigned long nr = 0;
int err;
int drop_inode = 0;
if (inode->i_nlink == 0)
return -ENOENT;
btrfs_inc_nlink(inode);
err = btrfs_check_free_space(root, 1, 0);
if (err)
goto fail;
err = btrfs_set_inode_index(dir, inode, &index);
if (err)
goto fail;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
atomic_inc(&inode->i_count);
err = btrfs_add_nondir(trans, dentry, inode, 1, index);
if (err)
drop_inode = 1;
dir->i_sb->s_dirt = 1;
btrfs_update_inode_block_group(trans, dir);
err = btrfs_update_inode(trans, root, inode);
if (err)
drop_inode = 1;
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
fail:
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
}
btrfs_btree_balance_dirty(root, nr);
return err;
}
static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
struct inode *inode = NULL;
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
int err = 0;
int drop_on_err = 0;
u64 objectid = 0;
u64 index = 0;
unsigned long nr = 1;
err = btrfs_check_free_space(root, 1, 0);
if (err)
goto out_unlock;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_unlock;
}
err = btrfs_find_free_objectid(trans, root, dir->i_ino, &objectid);
if (err) {
err = -ENOSPC;
goto out_unlock;
}
inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
dentry->d_name.len,
dentry->d_parent->d_inode->i_ino, objectid,
BTRFS_I(dir)->block_group, S_IFDIR | mode,
&index);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto out_fail;
}
drop_on_err = 1;
err = btrfs_init_acl(inode, dir);
if (err)
goto out_fail;
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
btrfs_set_trans_block_group(trans, inode);
btrfs_i_size_write(inode, 0);
err = btrfs_update_inode(trans, root, inode);
if (err)
goto out_fail;
err = btrfs_add_link(trans, dentry->d_parent->d_inode,
inode, dentry->d_name.name,
dentry->d_name.len, 0, index);
if (err)
goto out_fail;
d_instantiate(dentry, inode);
drop_on_err = 0;
dir->i_sb->s_dirt = 1;
btrfs_update_inode_block_group(trans, inode);
btrfs_update_inode_block_group(trans, dir);
out_fail:
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
out_unlock:
if (drop_on_err)
iput(inode);
btrfs_btree_balance_dirty(root, nr);
return err;
}
/* helper for btfs_get_extent. Given an existing extent in the tree,
* and an extent that you want to insert, deal with overlap and insert
* the new extent into the tree.
*/
static int merge_extent_mapping(struct extent_map_tree *em_tree,
struct extent_map *existing,
struct extent_map *em,
u64 map_start, u64 map_len)
{
u64 start_diff;
BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
start_diff = map_start - em->start;
em->start = map_start;
em->len = map_len;
if (em->block_start < EXTENT_MAP_LAST_BYTE &&
!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
em->block_start += start_diff;
em->block_len -= start_diff;
}
return add_extent_mapping(em_tree, em);
}
static noinline int uncompress_inline(struct btrfs_path *path,
struct inode *inode, struct page *page,
size_t pg_offset, u64 extent_offset,
struct btrfs_file_extent_item *item)
{
int ret;
struct extent_buffer *leaf = path->nodes[0];
char *tmp;
size_t max_size;
unsigned long inline_size;
unsigned long ptr;
WARN_ON(pg_offset != 0);
max_size = btrfs_file_extent_ram_bytes(leaf, item);
inline_size = btrfs_file_extent_inline_item_len(leaf,
btrfs_item_nr(leaf, path->slots[0]));
tmp = kmalloc(inline_size, GFP_NOFS);
ptr = btrfs_file_extent_inline_start(item);
read_extent_buffer(leaf, tmp, ptr, inline_size);
max_size = min(PAGE_CACHE_SIZE, max_size);
ret = btrfs_zlib_decompress(tmp, page, extent_offset,
inline_size, max_size);
if (ret) {
char *kaddr = kmap_atomic(page, KM_USER0);
unsigned long copy_size = min_t(u64,
PAGE_CACHE_SIZE - pg_offset,
max_size - extent_offset);
memset(kaddr + pg_offset, 0, copy_size);
kunmap_atomic(kaddr, KM_USER0);
}
kfree(tmp);
return 0;
}
/*
* a bit scary, this does extent mapping from logical file offset to the disk.
* the ugly parts come from merging extents from the disk with the
* in-ram representation. This gets more complex because of the data=ordered code,
* where the in-ram extents might be locked pending data=ordered completion.
*
* This also copies inline extents directly into the page.
*/
struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
size_t pg_offset, u64 start, u64 len,
int create)
{
int ret;
int err = 0;
u64 bytenr;
u64 extent_start = 0;
u64 extent_end = 0;
u64 objectid = inode->i_ino;
u32 found_type;
struct btrfs_path *path = NULL;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_file_extent_item *item;
struct extent_buffer *leaf;
struct btrfs_key found_key;
struct extent_map *em = NULL;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_trans_handle *trans = NULL;
int compressed;
again:
spin_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
if (em)
em->bdev = root->fs_info->fs_devices->latest_bdev;
spin_unlock(&em_tree->lock);
if (em) {
if (em->start > start || em->start + em->len <= start)
free_extent_map(em);
else if (em->block_start == EXTENT_MAP_INLINE && page)
free_extent_map(em);
else
goto out;
}
em = alloc_extent_map(GFP_NOFS);
if (!em) {
err = -ENOMEM;
goto out;
}
em->bdev = root->fs_info->fs_devices->latest_bdev;
em->start = EXTENT_MAP_HOLE;
em->len = (u64)-1;
em->block_len = (u64)-1;
if (!path) {
path = btrfs_alloc_path();
BUG_ON(!path);
}
ret = btrfs_lookup_file_extent(trans, root, path,
objectid, start, trans != NULL);
if (ret < 0) {
err = ret;
goto out;
}
if (ret != 0) {
if (path->slots[0] == 0)
goto not_found;
path->slots[0]--;
}
leaf = path->nodes[0];
item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
/* are we inside the extent that was found? */
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
if (found_key.objectid != objectid ||
found_type != BTRFS_EXTENT_DATA_KEY) {
goto not_found;
}
found_type = btrfs_file_extent_type(leaf, item);
extent_start = found_key.offset;
compressed = btrfs_file_extent_compression(leaf, item);
if (found_type == BTRFS_FILE_EXTENT_REG) {
extent_end = extent_start +
btrfs_file_extent_num_bytes(leaf, item);
err = 0;
if (start < extent_start || start >= extent_end) {
em->start = start;
if (start < extent_start) {
if (start + len <= extent_start)
goto not_found;
em->len = extent_end - extent_start;
} else {
em->len = len;
}
goto not_found_em;
}
bytenr = btrfs_file_extent_disk_bytenr(leaf, item);
if (bytenr == 0) {
em->start = extent_start;
em->len = extent_end - extent_start;
em->block_start = EXTENT_MAP_HOLE;
goto insert;
}
em->start = extent_start;
em->len = extent_end - extent_start;
if (compressed) {
set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
em->block_start = bytenr;
em->block_len = btrfs_file_extent_disk_num_bytes(leaf,
item);
} else {
bytenr += btrfs_file_extent_offset(leaf, item);
em->block_start = bytenr;
em->block_len = em->len;
}
goto insert;
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
u64 page_start;
unsigned long ptr;
char *map;
size_t size;
size_t extent_offset;
size_t copy_size;
size = btrfs_file_extent_inline_len(leaf, item);
extent_end = (extent_start + size + root->sectorsize - 1) &
~((u64)root->sectorsize - 1);
if (start < extent_start || start >= extent_end) {
em->start = start;
if (start < extent_start) {
if (start + len <= extent_start)
goto not_found;
em->len = extent_end - extent_start;
} else {
em->len = len;
}
goto not_found_em;
}
em->block_start = EXTENT_MAP_INLINE;
if (!page || create) {
em->start = extent_start;
em->len = (size + root->sectorsize - 1) &
~((u64)root->sectorsize - 1);
goto out;
}
page_start = page_offset(page) + pg_offset;
extent_offset = page_start - extent_start;
copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
size - extent_offset);
em->start = extent_start + extent_offset;
em->len = (copy_size + root->sectorsize - 1) &
~((u64)root->sectorsize - 1);
if (compressed)
set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
ptr = btrfs_file_extent_inline_start(item) + extent_offset;
if (create == 0 && !PageUptodate(page)) {
if (btrfs_file_extent_compression(leaf, item) ==
BTRFS_COMPRESS_ZLIB) {
ret = uncompress_inline(path, inode, page,
pg_offset,
extent_offset, item);
BUG_ON(ret);
} else {
map = kmap(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
copy_size);
kunmap(page);
}
flush_dcache_page(page);
} else if (create && PageUptodate(page)) {
if (!trans) {
kunmap(page);
free_extent_map(em);
em = NULL;
btrfs_release_path(root, path);
trans = btrfs_join_transaction(root, 1);
goto again;
}
map = kmap(page);
write_extent_buffer(leaf, map + pg_offset, ptr,
copy_size);
kunmap(page);
btrfs_mark_buffer_dirty(leaf);
}
set_extent_uptodate(io_tree, em->start,
extent_map_end(em) - 1, GFP_NOFS);
goto insert;
} else {
printk("unkknown found_type %d\n", found_type);
WARN_ON(1);
}
not_found:
em->start = start;
em->len = len;
not_found_em:
em->block_start = EXTENT_MAP_HOLE;
insert:
btrfs_release_path(root, path);
if (em->start > start || extent_map_end(em) <= start) {
printk("bad extent! em: [%Lu %Lu] passed [%Lu %Lu]\n", em->start, em->len, start, len);
err = -EIO;
goto out;
}
err = 0;
spin_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em);
/* it is possible that someone inserted the extent into the tree
* while we had the lock dropped. It is also possible that
* an overlapping map exists in the tree
*/
if (ret == -EEXIST) {
struct extent_map *existing;
ret = 0;
existing = lookup_extent_mapping(em_tree, start, len);
if (existing && (existing->start > start ||
existing->start + existing->len <= start)) {
free_extent_map(existing);
existing = NULL;
}
if (!existing) {
existing = lookup_extent_mapping(em_tree, em->start,
em->len);
if (existing) {
err = merge_extent_mapping(em_tree, existing,
em, start,
root->sectorsize);
free_extent_map(existing);
if (err) {
free_extent_map(em);
em = NULL;
}
} else {
err = -EIO;
printk("failing to insert %Lu %Lu\n",
start, len);
free_extent_map(em);
em = NULL;
}
} else {
free_extent_map(em);
em = existing;
err = 0;
}
}
spin_unlock(&em_tree->lock);
out:
if (path)
btrfs_free_path(path);
if (trans) {
ret = btrfs_end_transaction(trans, root);
if (!err) {
err = ret;
}
}
if (err) {
free_extent_map(em);
WARN_ON(1);
return ERR_PTR(err);
}
return em;
}
static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
return -EINVAL;
}
static sector_t btrfs_bmap(struct address_space *mapping, sector_t iblock)
{
return extent_bmap(mapping, iblock, btrfs_get_extent);
}
int btrfs_readpage(struct file *file, struct page *page)
{
struct extent_io_tree *tree;
tree = &BTRFS_I(page->mapping->host)->io_tree;
return extent_read_full_page(tree, page, btrfs_get_extent);
}
static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
{
struct extent_io_tree *tree;
if (current->flags & PF_MEMALLOC) {
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
tree = &BTRFS_I(page->mapping->host)->io_tree;
return extent_write_full_page(tree, page, btrfs_get_extent, wbc);
}
int btrfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct extent_io_tree *tree;
tree = &BTRFS_I(mapping->host)->io_tree;
return extent_writepages(tree, mapping, btrfs_get_extent, wbc);
}
static int
btrfs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct extent_io_tree *tree;
tree = &BTRFS_I(mapping->host)->io_tree;
return extent_readpages(tree, mapping, pages, nr_pages,
btrfs_get_extent);
}
static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
struct extent_io_tree *tree;
struct extent_map_tree *map;
int ret;
tree = &BTRFS_I(page->mapping->host)->io_tree;
map = &BTRFS_I(page->mapping->host)->extent_tree;
ret = try_release_extent_mapping(map, tree, page, gfp_flags);
if (ret == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
}
return ret;
}
static int btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
if (PageWriteback(page) || PageDirty(page))
return 0;
return __btrfs_releasepage(page, gfp_flags);
}
static void btrfs_invalidatepage(struct page *page, unsigned long offset)
{
struct extent_io_tree *tree;
struct btrfs_ordered_extent *ordered;
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
wait_on_page_writeback(page);
tree = &BTRFS_I(page->mapping->host)->io_tree;
if (offset) {
btrfs_releasepage(page, GFP_NOFS);
return;
}
lock_extent(tree, page_start, page_end, GFP_NOFS);
ordered = btrfs_lookup_ordered_extent(page->mapping->host,
page_offset(page));
if (ordered) {
/*
* IO on this page will never be started, so we need
* to account for any ordered extents now
*/
clear_extent_bit(tree, page_start, page_end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_LOCKED, 1, 0, GFP_NOFS);
btrfs_finish_ordered_io(page->mapping->host,
page_start, page_end);
btrfs_put_ordered_extent(ordered);
lock_extent(tree, page_start, page_end, GFP_NOFS);
}
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_ORDERED,
1, 1, GFP_NOFS);
__btrfs_releasepage(page, GFP_NOFS);
ClearPageChecked(page);
if (PagePrivate(page)) {
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
}
}
/*
* btrfs_page_mkwrite() is not allowed to change the file size as it gets
* called from a page fault handler when a page is first dirtied. Hence we must
* be careful to check for EOF conditions here. We set the page up correctly
* for a written page which means we get ENOSPC checking when writing into
* holes and correct delalloc and unwritten extent mapping on filesystems that
* support these features.
*
* We are not allowed to take the i_mutex here so we have to play games to
* protect against truncate races as the page could now be beyond EOF. Because
* vmtruncate() writes the inode size before removing pages, once we have the
* page lock we can determine safely if the page is beyond EOF. If it is not
* beyond EOF, then the page is guaranteed safe against truncation until we
* unlock the page.
*/
int btrfs_page_mkwrite(struct vm_area_struct *vma, struct page *page)
{
struct inode *inode = fdentry(vma->vm_file)->d_inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
char *kaddr;
unsigned long zero_start;
loff_t size;
int ret;
u64 page_start;
u64 page_end;
ret = btrfs_check_free_space(root, PAGE_CACHE_SIZE, 0);
if (ret)
goto out;
ret = -EINVAL;
again:
lock_page(page);
size = i_size_read(inode);
page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
if ((page->mapping != inode->i_mapping) ||
(page_start >= size)) {
/* page got truncated out from underneath us */
goto out_unlock;
}
wait_on_page_writeback(page);
lock_extent(io_tree, page_start, page_end, GFP_NOFS);
set_page_extent_mapped(page);
/*
* we can't set the delalloc bits if there are pending ordered
* extents. Drop our locks and wait for them to finish
*/
ordered = btrfs_lookup_ordered_extent(inode, page_start);
if (ordered) {
unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
unlock_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
}
btrfs_set_extent_delalloc(inode, page_start, page_end);
ret = 0;
/* page is wholly or partially inside EOF */
if (page_start + PAGE_CACHE_SIZE > size)
zero_start = size & ~PAGE_CACHE_MASK;
else
zero_start = PAGE_CACHE_SIZE;
if (zero_start != PAGE_CACHE_SIZE) {
kaddr = kmap(page);
memset(kaddr + zero_start, 0, PAGE_CACHE_SIZE - zero_start);
flush_dcache_page(page);
kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
out_unlock:
unlock_page(page);
out:
return ret;
}
static void btrfs_truncate(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
struct btrfs_trans_handle *trans;
unsigned long nr;
u64 mask = root->sectorsize - 1;
if (!S_ISREG(inode->i_mode))
return;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return;
btrfs_truncate_page(inode->i_mapping, inode->i_size);
btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
btrfs_i_size_write(inode, inode->i_size);
ret = btrfs_orphan_add(trans, inode);
if (ret)
goto out;
/* FIXME, add redo link to tree so we don't leak on crash */
ret = btrfs_truncate_inode_items(trans, root, inode, inode->i_size,
BTRFS_EXTENT_DATA_KEY);
btrfs_update_inode(trans, root, inode);
ret = btrfs_orphan_del(trans, inode);
BUG_ON(ret);
out:
nr = trans->blocks_used;
ret = btrfs_end_transaction_throttle(trans, root);
BUG_ON(ret);
btrfs_btree_balance_dirty(root, nr);
}
/*
* Invalidate a single dcache entry at the root of the filesystem.
* Needed after creation of snapshot or subvolume.
*/
void btrfs_invalidate_dcache_root(struct btrfs_root *root, char *name,
int namelen)
{
struct dentry *alias, *entry;
struct qstr qstr;
alias = d_find_alias(root->fs_info->sb->s_root->d_inode);
if (alias) {
qstr.name = name;
qstr.len = namelen;
/* change me if btrfs ever gets a d_hash operation */
qstr.hash = full_name_hash(qstr.name, qstr.len);
entry = d_lookup(alias, &qstr);
dput(alias);
if (entry) {
d_invalidate(entry);
dput(entry);
}
}
}
/*
* create a new subvolume directory/inode (helper for the ioctl).
*/
int btrfs_create_subvol_root(struct btrfs_root *new_root, struct dentry *dentry,
struct btrfs_trans_handle *trans, u64 new_dirid,
struct btrfs_block_group_cache *block_group)
{
struct inode *inode;
int error;
u64 index = 0;
inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, new_dirid,
new_dirid, block_group, S_IFDIR | 0700, &index);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
new_root->inode = inode;
inode->i_nlink = 1;
btrfs_i_size_write(inode, 0);
error = btrfs_update_inode(trans, new_root, inode);
if (error)
return error;
d_instantiate(dentry, inode);
return 0;
}
/* helper function for file defrag and space balancing. This
* forces readahead on a given range of bytes in an inode
*/
unsigned long btrfs_force_ra(struct address_space *mapping,
struct file_ra_state *ra, struct file *file,
pgoff_t offset, pgoff_t last_index)
{
pgoff_t req_size = last_index - offset + 1;
page_cache_sync_readahead(mapping, ra, file, offset, req_size);
return offset + req_size;
}
struct inode *btrfs_alloc_inode(struct super_block *sb)
{
struct btrfs_inode *ei;
ei = kmem_cache_alloc(btrfs_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
ei->last_trans = 0;
ei->logged_trans = 0;
btrfs_ordered_inode_tree_init(&ei->ordered_tree);
ei->i_acl = BTRFS_ACL_NOT_CACHED;
ei->i_default_acl = BTRFS_ACL_NOT_CACHED;
INIT_LIST_HEAD(&ei->i_orphan);
return &ei->vfs_inode;
}
void btrfs_destroy_inode(struct inode *inode)
{
struct btrfs_ordered_extent *ordered;
WARN_ON(!list_empty(&inode->i_dentry));
WARN_ON(inode->i_data.nrpages);
if (BTRFS_I(inode)->i_acl &&
BTRFS_I(inode)->i_acl != BTRFS_ACL_NOT_CACHED)
posix_acl_release(BTRFS_I(inode)->i_acl);
if (BTRFS_I(inode)->i_default_acl &&
BTRFS_I(inode)->i_default_acl != BTRFS_ACL_NOT_CACHED)
posix_acl_release(BTRFS_I(inode)->i_default_acl);
spin_lock(&BTRFS_I(inode)->root->list_lock);
if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
printk(KERN_ERR "BTRFS: inode %lu: inode still on the orphan"
" list\n", inode->i_ino);
dump_stack();
}
spin_unlock(&BTRFS_I(inode)->root->list_lock);
while(1) {
ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
if (!ordered)
break;
else {
printk("found ordered extent %Lu %Lu\n",
ordered->file_offset, ordered->len);
btrfs_remove_ordered_extent(inode, ordered);
btrfs_put_ordered_extent(ordered);
btrfs_put_ordered_extent(ordered);
}
}
btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
}
static void init_once(void *foo)
{
struct btrfs_inode *ei = (struct btrfs_inode *) foo;
inode_init_once(&ei->vfs_inode);
}
void btrfs_destroy_cachep(void)
{
if (btrfs_inode_cachep)
kmem_cache_destroy(btrfs_inode_cachep);
if (btrfs_trans_handle_cachep)
kmem_cache_destroy(btrfs_trans_handle_cachep);
if (btrfs_transaction_cachep)
kmem_cache_destroy(btrfs_transaction_cachep);
if (btrfs_bit_radix_cachep)
kmem_cache_destroy(btrfs_bit_radix_cachep);
if (btrfs_path_cachep)
kmem_cache_destroy(btrfs_path_cachep);
}
struct kmem_cache *btrfs_cache_create(const char *name, size_t size,
unsigned long extra_flags,
void (*ctor)(void *))
{
return kmem_cache_create(name, size, 0, (SLAB_RECLAIM_ACCOUNT |
SLAB_MEM_SPREAD | extra_flags), ctor);
}
int btrfs_init_cachep(void)
{
btrfs_inode_cachep = btrfs_cache_create("btrfs_inode_cache",
sizeof(struct btrfs_inode),
0, init_once);
if (!btrfs_inode_cachep)
goto fail;
btrfs_trans_handle_cachep =
btrfs_cache_create("btrfs_trans_handle_cache",
sizeof(struct btrfs_trans_handle),
0, NULL);
if (!btrfs_trans_handle_cachep)
goto fail;
btrfs_transaction_cachep = btrfs_cache_create("btrfs_transaction_cache",
sizeof(struct btrfs_transaction),
0, NULL);
if (!btrfs_transaction_cachep)
goto fail;
btrfs_path_cachep = btrfs_cache_create("btrfs_path_cache",
sizeof(struct btrfs_path),
0, NULL);
if (!btrfs_path_cachep)
goto fail;
btrfs_bit_radix_cachep = btrfs_cache_create("btrfs_radix", 256,
SLAB_DESTROY_BY_RCU, NULL);
if (!btrfs_bit_radix_cachep)
goto fail;
return 0;
fail:
btrfs_destroy_cachep();
return -ENOMEM;
}
static int btrfs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
generic_fillattr(inode, stat);
stat->blksize = PAGE_CACHE_SIZE;
stat->blocks = (inode_get_bytes(inode) +
BTRFS_I(inode)->delalloc_bytes) >> 9;
return 0;
}
static int btrfs_rename(struct inode * old_dir, struct dentry *old_dentry,
struct inode * new_dir,struct dentry *new_dentry)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(old_dir)->root;
struct inode *new_inode = new_dentry->d_inode;
struct inode *old_inode = old_dentry->d_inode;
struct timespec ctime = CURRENT_TIME;
u64 index = 0;
int ret;
if (S_ISDIR(old_inode->i_mode) && new_inode &&
new_inode->i_size > BTRFS_EMPTY_DIR_SIZE) {
return -ENOTEMPTY;
}
ret = btrfs_check_free_space(root, 1, 0);
if (ret)
goto out_unlock;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, new_dir);
btrfs_inc_nlink(old_dentry->d_inode);
old_dir->i_ctime = old_dir->i_mtime = ctime;
new_dir->i_ctime = new_dir->i_mtime = ctime;
old_inode->i_ctime = ctime;
ret = btrfs_unlink_inode(trans, root, old_dir, old_dentry->d_inode,
old_dentry->d_name.name,
old_dentry->d_name.len);
if (ret)
goto out_fail;
if (new_inode) {
new_inode->i_ctime = CURRENT_TIME;
ret = btrfs_unlink_inode(trans, root, new_dir,
new_dentry->d_inode,
new_dentry->d_name.name,
new_dentry->d_name.len);
if (ret)
goto out_fail;
if (new_inode->i_nlink == 0) {
ret = btrfs_orphan_add(trans, new_dentry->d_inode);
if (ret)
goto out_fail;
}
}
ret = btrfs_set_inode_index(new_dir, old_inode, &index);
if (ret)
goto out_fail;
ret = btrfs_add_link(trans, new_dentry->d_parent->d_inode,
old_inode, new_dentry->d_name.name,
new_dentry->d_name.len, 1, index);
if (ret)
goto out_fail;
out_fail:
btrfs_end_transaction_throttle(trans, root);
out_unlock:
return ret;
}
/*
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
int btrfs_start_delalloc_inodes(struct btrfs_root *root)
{
struct list_head *head = &root->fs_info->delalloc_inodes;
struct btrfs_inode *binode;
struct inode *inode;
unsigned long flags;
spin_lock_irqsave(&root->fs_info->delalloc_lock, flags);
while(!list_empty(head)) {
binode = list_entry(head->next, struct btrfs_inode,
delalloc_inodes);
inode = igrab(&binode->vfs_inode);
if (!inode)
list_del_init(&binode->delalloc_inodes);
spin_unlock_irqrestore(&root->fs_info->delalloc_lock, flags);
if (inode) {
filemap_flush(inode->i_mapping);
iput(inode);
}
cond_resched();
spin_lock_irqsave(&root->fs_info->delalloc_lock, flags);
}
spin_unlock_irqrestore(&root->fs_info->delalloc_lock, flags);
/* the filemap_flush will queue IO into the worker threads, but
* we have to make sure the IO is actually started and that
* ordered extents get created before we return
*/
atomic_inc(&root->fs_info->async_submit_draining);
while(atomic_read(&root->fs_info->nr_async_submits)) {
wait_event(root->fs_info->async_submit_wait,
(atomic_read(&root->fs_info->nr_async_submits) == 0));
}
atomic_dec(&root->fs_info->async_submit_draining);
return 0;
}
static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_path *path;
struct btrfs_key key;
struct inode *inode = NULL;
int err;
int drop_inode = 0;
u64 objectid;
u64 index = 0 ;
int name_len;
int datasize;
unsigned long ptr;
struct btrfs_file_extent_item *ei;
struct extent_buffer *leaf;
unsigned long nr = 0;
name_len = strlen(symname) + 1;
if (name_len > BTRFS_MAX_INLINE_DATA_SIZE(root))
return -ENAMETOOLONG;
err = btrfs_check_free_space(root, 1, 0);
if (err)
goto out_fail;
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, dir);
err = btrfs_find_free_objectid(trans, root, dir->i_ino, &objectid);
if (err) {
err = -ENOSPC;
goto out_unlock;
}
inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
dentry->d_name.len,
dentry->d_parent->d_inode->i_ino, objectid,
BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO,
&index);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_unlock;
err = btrfs_init_acl(inode, dir);
if (err) {
drop_inode = 1;
goto out_unlock;
}
btrfs_set_trans_block_group(trans, inode);
err = btrfs_add_nondir(trans, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
dir->i_sb->s_dirt = 1;
btrfs_update_inode_block_group(trans, inode);
btrfs_update_inode_block_group(trans, dir);
if (drop_inode)
goto out_unlock;
path = btrfs_alloc_path();
BUG_ON(!path);
key.objectid = inode->i_ino;
key.offset = 0;
btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
datasize = btrfs_file_extent_calc_inline_size(name_len);
err = btrfs_insert_empty_item(trans, root, path, &key,
datasize);
if (err) {
drop_inode = 1;
goto out_unlock;
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
btrfs_set_file_extent_generation(leaf, ei, trans->transid);
btrfs_set_file_extent_type(leaf, ei,
BTRFS_FILE_EXTENT_INLINE);
btrfs_set_file_extent_encryption(leaf, ei, 0);
btrfs_set_file_extent_compression(leaf, ei, 0);
btrfs_set_file_extent_other_encoding(leaf, ei, 0);
btrfs_set_file_extent_ram_bytes(leaf, ei, name_len);
ptr = btrfs_file_extent_inline_start(ei);
write_extent_buffer(leaf, symname, ptr, name_len);
btrfs_mark_buffer_dirty(leaf);
btrfs_free_path(path);
inode->i_op = &btrfs_symlink_inode_operations;
inode->i_mapping->a_ops = &btrfs_symlink_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
btrfs_i_size_write(inode, name_len - 1);
err = btrfs_update_inode(trans, root, inode);
if (err)
drop_inode = 1;
out_unlock:
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
out_fail:
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
}
btrfs_btree_balance_dirty(root, nr);
return err;
}
static int btrfs_set_page_dirty(struct page *page)
{
return __set_page_dirty_nobuffers(page);
}
static int btrfs_permission(struct inode *inode, int mask)
{
if (btrfs_test_flag(inode, READONLY) && (mask & MAY_WRITE))
return -EACCES;
return generic_permission(inode, mask, btrfs_check_acl);
}
static struct inode_operations btrfs_dir_inode_operations = {
.lookup = btrfs_lookup,
.create = btrfs_create,
.unlink = btrfs_unlink,
.link = btrfs_link,
.mkdir = btrfs_mkdir,
.rmdir = btrfs_rmdir,
.rename = btrfs_rename,
.symlink = btrfs_symlink,
.setattr = btrfs_setattr,
.mknod = btrfs_mknod,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
};
static struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,
.permission = btrfs_permission,
};
static struct file_operations btrfs_dir_file_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.readdir = btrfs_real_readdir,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_ioctl,
#endif
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
};
static struct extent_io_ops btrfs_extent_io_ops = {
.fill_delalloc = run_delalloc_range,
.submit_bio_hook = btrfs_submit_bio_hook,
.merge_bio_hook = btrfs_merge_bio_hook,
.readpage_end_io_hook = btrfs_readpage_end_io_hook,
.writepage_end_io_hook = btrfs_writepage_end_io_hook,
.writepage_start_hook = btrfs_writepage_start_hook,
.readpage_io_failed_hook = btrfs_io_failed_hook,
.set_bit_hook = btrfs_set_bit_hook,
.clear_bit_hook = btrfs_clear_bit_hook,
};
static struct address_space_operations btrfs_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
.readpages = btrfs_readpages,
.sync_page = block_sync_page,
.bmap = btrfs_bmap,
.direct_IO = btrfs_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
.set_page_dirty = btrfs_set_page_dirty,
};
static struct address_space_operations btrfs_symlink_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
};
static struct inode_operations btrfs_file_inode_operations = {
.truncate = btrfs_truncate,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
};
static struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
};
static struct inode_operations btrfs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.permission = btrfs_permission,
};
|