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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2008 Red Hat. All rights reserved.
*/
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/math64.h>
#include <linux/ratelimit.h>
#include <linux/error-injection.h>
#include <linux/sched/mm.h>
#include "misc.h"
#include "ctree.h"
#include "free-space-cache.h"
#include "transaction.h"
#include "disk-io.h"
#include "extent_io.h"
#include "volumes.h"
#include "space-info.h"
#include "delalloc-space.h"
#include "block-group.h"
#include "discard.h"
#include "subpage.h"
#include "inode-item.h"
#define BITS_PER_BITMAP (PAGE_SIZE * 8UL)
#define MAX_CACHE_BYTES_PER_GIG SZ_64K
#define FORCE_EXTENT_THRESHOLD SZ_1M
struct btrfs_trim_range {
u64 start;
u64 bytes;
struct list_head list;
};
static int link_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info);
static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, bool update_stat);
static int search_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *bitmap_info, u64 *offset,
u64 *bytes, bool for_alloc);
static void free_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *bitmap_info);
static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, u64 offset,
u64 bytes, bool update_stats);
static void __btrfs_remove_free_space_cache_locked(
struct btrfs_free_space_ctl *ctl)
{
struct btrfs_free_space *info;
struct rb_node *node;
while ((node = rb_last(&ctl->free_space_offset)) != NULL) {
info = rb_entry(node, struct btrfs_free_space, offset_index);
if (!info->bitmap) {
unlink_free_space(ctl, info, true);
kmem_cache_free(btrfs_free_space_cachep, info);
} else {
free_bitmap(ctl, info);
}
cond_resched_lock(&ctl->tree_lock);
}
}
static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
struct btrfs_path *path,
u64 offset)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key key;
struct btrfs_key location;
struct btrfs_disk_key disk_key;
struct btrfs_free_space_header *header;
struct extent_buffer *leaf;
struct inode *inode = NULL;
unsigned nofs_flag;
int ret;
key.objectid = BTRFS_FREE_SPACE_OBJECTID;
key.offset = offset;
key.type = 0;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
return ERR_PTR(ret);
if (ret > 0) {
btrfs_release_path(path);
return ERR_PTR(-ENOENT);
}
leaf = path->nodes[0];
header = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_free_space_header);
btrfs_free_space_key(leaf, header, &disk_key);
btrfs_disk_key_to_cpu(&location, &disk_key);
btrfs_release_path(path);
/*
* We are often under a trans handle at this point, so we need to make
* sure NOFS is set to keep us from deadlocking.
*/
nofs_flag = memalloc_nofs_save();
inode = btrfs_iget_path(fs_info->sb, location.objectid, root, path);
btrfs_release_path(path);
memalloc_nofs_restore(nofs_flag);
if (IS_ERR(inode))
return inode;
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_constraint(inode->i_mapping,
~(__GFP_FS | __GFP_HIGHMEM)));
return inode;
}
struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct inode *inode = NULL;
u32 flags = BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW;
spin_lock(&block_group->lock);
if (block_group->inode)
inode = igrab(block_group->inode);
spin_unlock(&block_group->lock);
if (inode)
return inode;
inode = __lookup_free_space_inode(fs_info->tree_root, path,
block_group->start);
if (IS_ERR(inode))
return inode;
spin_lock(&block_group->lock);
if (!((BTRFS_I(inode)->flags & flags) == flags)) {
btrfs_info(fs_info, "Old style space inode found, converting.");
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM |
BTRFS_INODE_NODATACOW;
block_group->disk_cache_state = BTRFS_DC_CLEAR;
}
if (!test_and_set_bit(BLOCK_GROUP_FLAG_IREF, &block_group->runtime_flags))
block_group->inode = igrab(inode);
spin_unlock(&block_group->lock);
return inode;
}
static int __create_free_space_inode(struct btrfs_root *root,
struct btrfs_trans_handle *trans,
struct btrfs_path *path,
u64 ino, u64 offset)
{
struct btrfs_key key;
struct btrfs_disk_key disk_key;
struct btrfs_free_space_header *header;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
/* We inline CRCs for the free disk space cache */
const u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC |
BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW;
int ret;
ret = btrfs_insert_empty_inode(trans, root, path, ino);
if (ret)
return ret;
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
btrfs_item_key(leaf, &disk_key, path->slots[0]);
memzero_extent_buffer(leaf, (unsigned long)inode_item,
sizeof(*inode_item));
btrfs_set_inode_generation(leaf, inode_item, trans->transid);
btrfs_set_inode_size(leaf, inode_item, 0);
btrfs_set_inode_nbytes(leaf, inode_item, 0);
btrfs_set_inode_uid(leaf, inode_item, 0);
btrfs_set_inode_gid(leaf, inode_item, 0);
btrfs_set_inode_mode(leaf, inode_item, S_IFREG | 0600);
btrfs_set_inode_flags(leaf, inode_item, flags);
btrfs_set_inode_nlink(leaf, inode_item, 1);
btrfs_set_inode_transid(leaf, inode_item, trans->transid);
btrfs_set_inode_block_group(leaf, inode_item, offset);
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
key.objectid = BTRFS_FREE_SPACE_OBJECTID;
key.offset = offset;
key.type = 0;
ret = btrfs_insert_empty_item(trans, root, path, &key,
sizeof(struct btrfs_free_space_header));
if (ret < 0) {
btrfs_release_path(path);
return ret;
}
leaf = path->nodes[0];
header = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_free_space_header);
memzero_extent_buffer(leaf, (unsigned long)header, sizeof(*header));
btrfs_set_free_space_key(leaf, header, &disk_key);
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
return 0;
}
int create_free_space_inode(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
int ret;
u64 ino;
ret = btrfs_get_free_objectid(trans->fs_info->tree_root, &ino);
if (ret < 0)
return ret;
return __create_free_space_inode(trans->fs_info->tree_root, trans, path,
ino, block_group->start);
}
/*
* inode is an optional sink: if it is NULL, btrfs_remove_free_space_inode
* handles lookup, otherwise it takes ownership and iputs the inode.
* Don't reuse an inode pointer after passing it into this function.
*/
int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
struct inode *inode,
struct btrfs_block_group *block_group)
{
struct btrfs_path *path;
struct btrfs_key key;
int ret = 0;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
if (!inode)
inode = lookup_free_space_inode(block_group, path);
if (IS_ERR(inode)) {
if (PTR_ERR(inode) != -ENOENT)
ret = PTR_ERR(inode);
goto out;
}
ret = btrfs_orphan_add(trans, BTRFS_I(inode));
if (ret) {
btrfs_add_delayed_iput(inode);
goto out;
}
clear_nlink(inode);
/* One for the block groups ref */
spin_lock(&block_group->lock);
if (test_and_clear_bit(BLOCK_GROUP_FLAG_IREF, &block_group->runtime_flags)) {
block_group->inode = NULL;
spin_unlock(&block_group->lock);
iput(inode);
} else {
spin_unlock(&block_group->lock);
}
/* One for the lookup ref */
btrfs_add_delayed_iput(inode);
key.objectid = BTRFS_FREE_SPACE_OBJECTID;
key.type = 0;
key.offset = block_group->start;
ret = btrfs_search_slot(trans, trans->fs_info->tree_root, &key, path,
-1, 1);
if (ret) {
if (ret > 0)
ret = 0;
goto out;
}
ret = btrfs_del_item(trans, trans->fs_info->tree_root, path);
out:
btrfs_free_path(path);
return ret;
}
int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv)
{
u64 needed_bytes;
int ret;
/* 1 for slack space, 1 for updating the inode */
needed_bytes = btrfs_calc_insert_metadata_size(fs_info, 1) +
btrfs_calc_metadata_size(fs_info, 1);
spin_lock(&rsv->lock);
if (rsv->reserved < needed_bytes)
ret = -ENOSPC;
else
ret = 0;
spin_unlock(&rsv->lock);
return ret;
}
int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct inode *vfs_inode)
{
struct btrfs_truncate_control control = {
.inode = BTRFS_I(vfs_inode),
.new_size = 0,
.ino = btrfs_ino(BTRFS_I(vfs_inode)),
.min_type = BTRFS_EXTENT_DATA_KEY,
.clear_extent_range = true,
};
struct btrfs_inode *inode = BTRFS_I(vfs_inode);
struct btrfs_root *root = inode->root;
struct extent_state *cached_state = NULL;
int ret = 0;
bool locked = false;
if (block_group) {
struct btrfs_path *path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto fail;
}
locked = true;
mutex_lock(&trans->transaction->cache_write_mutex);
if (!list_empty(&block_group->io_list)) {
list_del_init(&block_group->io_list);
btrfs_wait_cache_io(trans, block_group, path);
btrfs_put_block_group(block_group);
}
/*
* now that we've truncated the cache away, its no longer
* setup or written
*/
spin_lock(&block_group->lock);
block_group->disk_cache_state = BTRFS_DC_CLEAR;
spin_unlock(&block_group->lock);
btrfs_free_path(path);
}
btrfs_i_size_write(inode, 0);
truncate_pagecache(vfs_inode, 0);
lock_extent_bits(&inode->io_tree, 0, (u64)-1, &cached_state);
btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
/*
* We skip the throttling logic for free space cache inodes, so we don't
* need to check for -EAGAIN.
*/
ret = btrfs_truncate_inode_items(trans, root, &control);
inode_sub_bytes(&inode->vfs_inode, control.sub_bytes);
btrfs_inode_safe_disk_i_size_write(inode, control.last_size);
unlock_extent_cached(&inode->io_tree, 0, (u64)-1, &cached_state);
if (ret)
goto fail;
ret = btrfs_update_inode(trans, root, inode);
fail:
if (locked)
mutex_unlock(&trans->transaction->cache_write_mutex);
if (ret)
btrfs_abort_transaction(trans, ret);
return ret;
}
static void readahead_cache(struct inode *inode)
{
struct file_ra_state ra;
unsigned long last_index;
file_ra_state_init(&ra, inode->i_mapping);
last_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
page_cache_sync_readahead(inode->i_mapping, &ra, NULL, 0, last_index);
}
static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
int write)
{
int num_pages;
num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
/* Make sure we can fit our crcs and generation into the first page */
if (write && (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE)
return -ENOSPC;
memset(io_ctl, 0, sizeof(struct btrfs_io_ctl));
io_ctl->pages = kcalloc(num_pages, sizeof(struct page *), GFP_NOFS);
if (!io_ctl->pages)
return -ENOMEM;
io_ctl->num_pages = num_pages;
io_ctl->fs_info = btrfs_sb(inode->i_sb);
io_ctl->inode = inode;
return 0;
}
ALLOW_ERROR_INJECTION(io_ctl_init, ERRNO);
static void io_ctl_free(struct btrfs_io_ctl *io_ctl)
{
kfree(io_ctl->pages);
io_ctl->pages = NULL;
}
static void io_ctl_unmap_page(struct btrfs_io_ctl *io_ctl)
{
if (io_ctl->cur) {
io_ctl->cur = NULL;
io_ctl->orig = NULL;
}
}
static void io_ctl_map_page(struct btrfs_io_ctl *io_ctl, int clear)
{
ASSERT(io_ctl->index < io_ctl->num_pages);
io_ctl->page = io_ctl->pages[io_ctl->index++];
io_ctl->cur = page_address(io_ctl->page);
io_ctl->orig = io_ctl->cur;
io_ctl->size = PAGE_SIZE;
if (clear)
clear_page(io_ctl->cur);
}
static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl)
{
int i;
io_ctl_unmap_page(io_ctl);
for (i = 0; i < io_ctl->num_pages; i++) {
if (io_ctl->pages[i]) {
btrfs_page_clear_checked(io_ctl->fs_info,
io_ctl->pages[i],
page_offset(io_ctl->pages[i]),
PAGE_SIZE);
unlock_page(io_ctl->pages[i]);
put_page(io_ctl->pages[i]);
}
}
}
static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate)
{
struct page *page;
struct inode *inode = io_ctl->inode;
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
int i;
for (i = 0; i < io_ctl->num_pages; i++) {
int ret;
page = find_or_create_page(inode->i_mapping, i, mask);
if (!page) {
io_ctl_drop_pages(io_ctl);
return -ENOMEM;
}
ret = set_page_extent_mapped(page);
if (ret < 0) {
unlock_page(page);
put_page(page);
io_ctl_drop_pages(io_ctl);
return ret;
}
io_ctl->pages[i] = page;
if (uptodate && !PageUptodate(page)) {
btrfs_read_folio(NULL, page_folio(page));
lock_page(page);
if (page->mapping != inode->i_mapping) {
btrfs_err(BTRFS_I(inode)->root->fs_info,
"free space cache page truncated");
io_ctl_drop_pages(io_ctl);
return -EIO;
}
if (!PageUptodate(page)) {
btrfs_err(BTRFS_I(inode)->root->fs_info,
"error reading free space cache");
io_ctl_drop_pages(io_ctl);
return -EIO;
}
}
}
for (i = 0; i < io_ctl->num_pages; i++)
clear_page_dirty_for_io(io_ctl->pages[i]);
return 0;
}
static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
{
io_ctl_map_page(io_ctl, 1);
/*
* Skip the csum areas. If we don't check crcs then we just have a
* 64bit chunk at the front of the first page.
*/
io_ctl->cur += (sizeof(u32) * io_ctl->num_pages);
io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages);
put_unaligned_le64(generation, io_ctl->cur);
io_ctl->cur += sizeof(u64);
}
static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
{
u64 cache_gen;
/*
* Skip the crc area. If we don't check crcs then we just have a 64bit
* chunk at the front of the first page.
*/
io_ctl->cur += sizeof(u32) * io_ctl->num_pages;
io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages);
cache_gen = get_unaligned_le64(io_ctl->cur);
if (cache_gen != generation) {
btrfs_err_rl(io_ctl->fs_info,
"space cache generation (%llu) does not match inode (%llu)",
cache_gen, generation);
io_ctl_unmap_page(io_ctl);
return -EIO;
}
io_ctl->cur += sizeof(u64);
return 0;
}
static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index)
{
u32 *tmp;
u32 crc = ~(u32)0;
unsigned offset = 0;
if (index == 0)
offset = sizeof(u32) * io_ctl->num_pages;
crc = btrfs_crc32c(crc, io_ctl->orig + offset, PAGE_SIZE - offset);
btrfs_crc32c_final(crc, (u8 *)&crc);
io_ctl_unmap_page(io_ctl);
tmp = page_address(io_ctl->pages[0]);
tmp += index;
*tmp = crc;
}
static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index)
{
u32 *tmp, val;
u32 crc = ~(u32)0;
unsigned offset = 0;
if (index == 0)
offset = sizeof(u32) * io_ctl->num_pages;
tmp = page_address(io_ctl->pages[0]);
tmp += index;
val = *tmp;
io_ctl_map_page(io_ctl, 0);
crc = btrfs_crc32c(crc, io_ctl->orig + offset, PAGE_SIZE - offset);
btrfs_crc32c_final(crc, (u8 *)&crc);
if (val != crc) {
btrfs_err_rl(io_ctl->fs_info,
"csum mismatch on free space cache");
io_ctl_unmap_page(io_ctl);
return -EIO;
}
return 0;
}
static int io_ctl_add_entry(struct btrfs_io_ctl *io_ctl, u64 offset, u64 bytes,
void *bitmap)
{
struct btrfs_free_space_entry *entry;
if (!io_ctl->cur)
return -ENOSPC;
entry = io_ctl->cur;
put_unaligned_le64(offset, &entry->offset);
put_unaligned_le64(bytes, &entry->bytes);
entry->type = (bitmap) ? BTRFS_FREE_SPACE_BITMAP :
BTRFS_FREE_SPACE_EXTENT;
io_ctl->cur += sizeof(struct btrfs_free_space_entry);
io_ctl->size -= sizeof(struct btrfs_free_space_entry);
if (io_ctl->size >= sizeof(struct btrfs_free_space_entry))
return 0;
io_ctl_set_crc(io_ctl, io_ctl->index - 1);
/* No more pages to map */
if (io_ctl->index >= io_ctl->num_pages)
return 0;
/* map the next page */
io_ctl_map_page(io_ctl, 1);
return 0;
}
static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap)
{
if (!io_ctl->cur)
return -ENOSPC;
/*
* If we aren't at the start of the current page, unmap this one and
* map the next one if there is any left.
*/
if (io_ctl->cur != io_ctl->orig) {
io_ctl_set_crc(io_ctl, io_ctl->index - 1);
if (io_ctl->index >= io_ctl->num_pages)
return -ENOSPC;
io_ctl_map_page(io_ctl, 0);
}
copy_page(io_ctl->cur, bitmap);
io_ctl_set_crc(io_ctl, io_ctl->index - 1);
if (io_ctl->index < io_ctl->num_pages)
io_ctl_map_page(io_ctl, 0);
return 0;
}
static void io_ctl_zero_remaining_pages(struct btrfs_io_ctl *io_ctl)
{
/*
* If we're not on the boundary we know we've modified the page and we
* need to crc the page.
*/
if (io_ctl->cur != io_ctl->orig)
io_ctl_set_crc(io_ctl, io_ctl->index - 1);
else
io_ctl_unmap_page(io_ctl);
while (io_ctl->index < io_ctl->num_pages) {
io_ctl_map_page(io_ctl, 1);
io_ctl_set_crc(io_ctl, io_ctl->index - 1);
}
}
static int io_ctl_read_entry(struct btrfs_io_ctl *io_ctl,
struct btrfs_free_space *entry, u8 *type)
{
struct btrfs_free_space_entry *e;
int ret;
if (!io_ctl->cur) {
ret = io_ctl_check_crc(io_ctl, io_ctl->index);
if (ret)
return ret;
}
e = io_ctl->cur;
entry->offset = get_unaligned_le64(&e->offset);
entry->bytes = get_unaligned_le64(&e->bytes);
*type = e->type;
io_ctl->cur += sizeof(struct btrfs_free_space_entry);
io_ctl->size -= sizeof(struct btrfs_free_space_entry);
if (io_ctl->size >= sizeof(struct btrfs_free_space_entry))
return 0;
io_ctl_unmap_page(io_ctl);
return 0;
}
static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl,
struct btrfs_free_space *entry)
{
int ret;
ret = io_ctl_check_crc(io_ctl, io_ctl->index);
if (ret)
return ret;
copy_page(entry->bitmap, io_ctl->cur);
io_ctl_unmap_page(io_ctl);
return 0;
}
static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
{
struct btrfs_block_group *block_group = ctl->block_group;
u64 max_bytes;
u64 bitmap_bytes;
u64 extent_bytes;
u64 size = block_group->length;
u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
max_bitmaps = max_t(u64, max_bitmaps, 1);
if (ctl->total_bitmaps > max_bitmaps)
btrfs_err(block_group->fs_info,
"invalid free space control: bg start=%llu len=%llu total_bitmaps=%u unit=%u max_bitmaps=%llu bytes_per_bg=%llu",
block_group->start, block_group->length,
ctl->total_bitmaps, ctl->unit, max_bitmaps,
bytes_per_bg);
ASSERT(ctl->total_bitmaps <= max_bitmaps);
/*
* We are trying to keep the total amount of memory used per 1GiB of
* space to be MAX_CACHE_BYTES_PER_GIG. However, with a reclamation
* mechanism of pulling extents >= FORCE_EXTENT_THRESHOLD out of
* bitmaps, we may end up using more memory than this.
*/
if (size < SZ_1G)
max_bytes = MAX_CACHE_BYTES_PER_GIG;
else
max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G);
bitmap_bytes = ctl->total_bitmaps * ctl->unit;
/*
* we want the extent entry threshold to always be at most 1/2 the max
* bytes we can have, or whatever is less than that.
*/
extent_bytes = max_bytes - bitmap_bytes;
extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1);
ctl->extents_thresh =
div_u64(extent_bytes, sizeof(struct btrfs_free_space));
}
static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
struct btrfs_free_space_ctl *ctl,
struct btrfs_path *path, u64 offset)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_free_space_header *header;
struct extent_buffer *leaf;
struct btrfs_io_ctl io_ctl;
struct btrfs_key key;
struct btrfs_free_space *e, *n;
LIST_HEAD(bitmaps);
u64 num_entries;
u64 num_bitmaps;
u64 generation;
u8 type;
int ret = 0;
/* Nothing in the space cache, goodbye */
if (!i_size_read(inode))
return 0;
key.objectid = BTRFS_FREE_SPACE_OBJECTID;
key.offset = offset;
key.type = 0;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
return 0;
else if (ret > 0) {
btrfs_release_path(path);
return 0;
}
ret = -1;
leaf = path->nodes[0];
header = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_free_space_header);
num_entries = btrfs_free_space_entries(leaf, header);
num_bitmaps = btrfs_free_space_bitmaps(leaf, header);
generation = btrfs_free_space_generation(leaf, header);
btrfs_release_path(path);
if (!BTRFS_I(inode)->generation) {
btrfs_info(fs_info,
"the free space cache file (%llu) is invalid, skip it",
offset);
return 0;
}
if (BTRFS_I(inode)->generation != generation) {
btrfs_err(fs_info,
"free space inode generation (%llu) did not match free space cache generation (%llu)",
BTRFS_I(inode)->generation, generation);
return 0;
}
if (!num_entries)
return 0;
ret = io_ctl_init(&io_ctl, inode, 0);
if (ret)
return ret;
readahead_cache(inode);
ret = io_ctl_prepare_pages(&io_ctl, true);
if (ret)
goto out;
ret = io_ctl_check_crc(&io_ctl, 0);
if (ret)
goto free_cache;
ret = io_ctl_check_generation(&io_ctl, generation);
if (ret)
goto free_cache;
while (num_entries) {
e = kmem_cache_zalloc(btrfs_free_space_cachep,
GFP_NOFS);
if (!e) {
ret = -ENOMEM;
goto free_cache;
}
ret = io_ctl_read_entry(&io_ctl, e, &type);
if (ret) {
kmem_cache_free(btrfs_free_space_cachep, e);
goto free_cache;
}
if (!e->bytes) {
ret = -1;
kmem_cache_free(btrfs_free_space_cachep, e);
goto free_cache;
}
if (type == BTRFS_FREE_SPACE_EXTENT) {
spin_lock(&ctl->tree_lock);
ret = link_free_space(ctl, e);
spin_unlock(&ctl->tree_lock);
if (ret) {
btrfs_err(fs_info,
"Duplicate entries in free space cache, dumping");
kmem_cache_free(btrfs_free_space_cachep, e);
goto free_cache;
}
} else {
ASSERT(num_bitmaps);
num_bitmaps--;
e->bitmap = kmem_cache_zalloc(
btrfs_free_space_bitmap_cachep, GFP_NOFS);
if (!e->bitmap) {
ret = -ENOMEM;
kmem_cache_free(
btrfs_free_space_cachep, e);
goto free_cache;
}
spin_lock(&ctl->tree_lock);
ret = link_free_space(ctl, e);
ctl->total_bitmaps++;
recalculate_thresholds(ctl);
spin_unlock(&ctl->tree_lock);
if (ret) {
btrfs_err(fs_info,
"Duplicate entries in free space cache, dumping");
kmem_cache_free(btrfs_free_space_cachep, e);
goto free_cache;
}
list_add_tail(&e->list, &bitmaps);
}
num_entries--;
}
io_ctl_unmap_page(&io_ctl);
/*
* We add the bitmaps at the end of the entries in order that
* the bitmap entries are added to the cache.
*/
list_for_each_entry_safe(e, n, &bitmaps, list) {
list_del_init(&e->list);
ret = io_ctl_read_bitmap(&io_ctl, e);
if (ret)
goto free_cache;
}
io_ctl_drop_pages(&io_ctl);
ret = 1;
out:
io_ctl_free(&io_ctl);
return ret;
free_cache:
io_ctl_drop_pages(&io_ctl);
/*
* We need to call the _locked variant so we don't try to update the
* discard counters.
*/
spin_lock(&ctl->tree_lock);
__btrfs_remove_free_space_cache_locked(ctl);
spin_unlock(&ctl->tree_lock);
goto out;
}
static int copy_free_space_cache(struct btrfs_block_group *block_group,
struct btrfs_free_space_ctl *ctl)
{
struct btrfs_free_space *info;
struct rb_node *n;
int ret = 0;
while (!ret && (n = rb_first(&ctl->free_space_offset)) != NULL) {
info = rb_entry(n, struct btrfs_free_space, offset_index);
if (!info->bitmap) {
unlink_free_space(ctl, info, true);
ret = btrfs_add_free_space(block_group, info->offset,
info->bytes);
kmem_cache_free(btrfs_free_space_cachep, info);
} else {
u64 offset = info->offset;
u64 bytes = ctl->unit;
while (search_bitmap(ctl, info, &offset, &bytes,
false) == 0) {
ret = btrfs_add_free_space(block_group, offset,
bytes);
if (ret)
break;
bitmap_clear_bits(ctl, info, offset, bytes, true);
offset = info->offset;
bytes = ctl->unit;
}
free_bitmap(ctl, info);
}
cond_resched();
}
return ret;
}
static struct lock_class_key btrfs_free_space_inode_key;
int load_free_space_cache(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space_ctl tmp_ctl = {};
struct inode *inode;
struct btrfs_path *path;
int ret = 0;
bool matched;
u64 used = block_group->used;
/*
* Because we could potentially discard our loaded free space, we want
* to load everything into a temporary structure first, and then if it's
* valid copy it all into the actual free space ctl.
*/
btrfs_init_free_space_ctl(block_group, &tmp_ctl);
/*
* If this block group has been marked to be cleared for one reason or
* another then we can't trust the on disk cache, so just return.
*/
spin_lock(&block_group->lock);
if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) {
spin_unlock(&block_group->lock);
return 0;
}
spin_unlock(&block_group->lock);
path = btrfs_alloc_path();
if (!path)
return 0;
path->search_commit_root = 1;
path->skip_locking = 1;
/*
* We must pass a path with search_commit_root set to btrfs_iget in
* order to avoid a deadlock when allocating extents for the tree root.
*
* When we are COWing an extent buffer from the tree root, when looking
* for a free extent, at extent-tree.c:find_free_extent(), we can find
* block group without its free space cache loaded. When we find one
* we must load its space cache which requires reading its free space
* cache's inode item from the root tree. If this inode item is located
* in the same leaf that we started COWing before, then we end up in
* deadlock on the extent buffer (trying to read lock it when we
* previously write locked it).
*
* It's safe to read the inode item using the commit root because
* block groups, once loaded, stay in memory forever (until they are
* removed) as well as their space caches once loaded. New block groups
* once created get their ->cached field set to BTRFS_CACHE_FINISHED so
* we will never try to read their inode item while the fs is mounted.
*/
inode = lookup_free_space_inode(block_group, path);
if (IS_ERR(inode)) {
btrfs_free_path(path);
return 0;
}
/* We may have converted the inode and made the cache invalid. */
spin_lock(&block_group->lock);
if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) {
spin_unlock(&block_group->lock);
btrfs_free_path(path);
goto out;
}
spin_unlock(&block_group->lock);
/*
* Reinitialize the class of struct inode's mapping->invalidate_lock for
* free space inodes to prevent false positives related to locks for normal
* inodes.
*/
lockdep_set_class(&(&inode->i_data)->invalidate_lock,
&btrfs_free_space_inode_key);
ret = __load_free_space_cache(fs_info->tree_root, inode, &tmp_ctl,
path, block_group->start);
btrfs_free_path(path);
if (ret <= 0)
goto out;
matched = (tmp_ctl.free_space == (block_group->length - used -
block_group->bytes_super));
if (matched) {
ret = copy_free_space_cache(block_group, &tmp_ctl);
/*
* ret == 1 means we successfully loaded the free space cache,
* so we need to re-set it here.
*/
if (ret == 0)
ret = 1;
} else {
/*
* We need to call the _locked variant so we don't try to update
* the discard counters.
*/
spin_lock(&tmp_ctl.tree_lock);
__btrfs_remove_free_space_cache(&tmp_ctl);
spin_unlock(&tmp_ctl.tree_lock);
btrfs_warn(fs_info,
"block group %llu has wrong amount of free space",
block_group->start);
ret = -1;
}
out:
if (ret < 0) {
/* This cache is bogus, make sure it gets cleared */
spin_lock(&block_group->lock);
block_group->disk_cache_state = BTRFS_DC_CLEAR;
spin_unlock(&block_group->lock);
ret = 0;
btrfs_warn(fs_info,
"failed to load free space cache for block group %llu, rebuilding it now",
block_group->start);
}
spin_lock(&ctl->tree_lock);
btrfs_discard_update_discardable(block_group);
spin_unlock(&ctl->tree_lock);
iput(inode);
return ret;
}
static noinline_for_stack
int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl,
struct btrfs_free_space_ctl *ctl,
struct btrfs_block_group *block_group,
int *entries, int *bitmaps,
struct list_head *bitmap_list)
{
int ret;
struct btrfs_free_cluster *cluster = NULL;
struct btrfs_free_cluster *cluster_locked = NULL;
struct rb_node *node = rb_first(&ctl->free_space_offset);
struct btrfs_trim_range *trim_entry;
/* Get the cluster for this block_group if it exists */
if (block_group && !list_empty(&block_group->cluster_list)) {
cluster = list_entry(block_group->cluster_list.next,
struct btrfs_free_cluster,
block_group_list);
}
if (!node && cluster) {
cluster_locked = cluster;
spin_lock(&cluster_locked->lock);
node = rb_first(&cluster->root);
cluster = NULL;
}
/* Write out the extent entries */
while (node) {
struct btrfs_free_space *e;
e = rb_entry(node, struct btrfs_free_space, offset_index);
*entries += 1;
ret = io_ctl_add_entry(io_ctl, e->offset, e->bytes,
e->bitmap);
if (ret)
goto fail;
if (e->bitmap) {
list_add_tail(&e->list, bitmap_list);
*bitmaps += 1;
}
node = rb_next(node);
if (!node && cluster) {
node = rb_first(&cluster->root);
cluster_locked = cluster;
spin_lock(&cluster_locked->lock);
cluster = NULL;
}
}
if (cluster_locked) {
spin_unlock(&cluster_locked->lock);
cluster_locked = NULL;
}
/*
* Make sure we don't miss any range that was removed from our rbtree
* because trimming is running. Otherwise after a umount+mount (or crash
* after committing the transaction) we would leak free space and get
* an inconsistent free space cache report from fsck.
*/
list_for_each_entry(trim_entry, &ctl->trimming_ranges, list) {
ret = io_ctl_add_entry(io_ctl, trim_entry->start,
trim_entry->bytes, NULL);
if (ret)
goto fail;
*entries += 1;
}
return 0;
fail:
if (cluster_locked)
spin_unlock(&cluster_locked->lock);
return -ENOSPC;
}
static noinline_for_stack int
update_cache_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode,
struct btrfs_path *path, u64 offset,
int entries, int bitmaps)
{
struct btrfs_key key;
struct btrfs_free_space_header *header;
struct extent_buffer *leaf;
int ret;
key.objectid = BTRFS_FREE_SPACE_OBJECTID;
key.offset = offset;
key.type = 0;
ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret < 0) {
clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
EXTENT_DELALLOC, 0, 0, NULL);
goto fail;
}
leaf = path->nodes[0];
if (ret > 0) {
struct btrfs_key found_key;
ASSERT(path->slots[0]);
path->slots[0]--;
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID ||
found_key.offset != offset) {
clear_extent_bit(&BTRFS_I(inode)->io_tree, 0,
inode->i_size - 1, EXTENT_DELALLOC, 0,
0, NULL);
btrfs_release_path(path);
goto fail;
}
}
BTRFS_I(inode)->generation = trans->transid;
header = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_free_space_header);
btrfs_set_free_space_entries(leaf, header, entries);
btrfs_set_free_space_bitmaps(leaf, header, bitmaps);
btrfs_set_free_space_generation(leaf, header, trans->transid);
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
return 0;
fail:
return -1;
}
static noinline_for_stack int write_pinned_extent_entries(
struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_io_ctl *io_ctl,
int *entries)
{
u64 start, extent_start, extent_end, len;
struct extent_io_tree *unpin = NULL;
int ret;
if (!block_group)
return 0;
/*
* We want to add any pinned extents to our free space cache
* so we don't leak the space
*
* We shouldn't have switched the pinned extents yet so this is the
* right one
*/
unpin = &trans->transaction->pinned_extents;
start = block_group->start;
while (start < block_group->start + block_group->length) {
ret = find_first_extent_bit(unpin, start,
&extent_start, &extent_end,
EXTENT_DIRTY, NULL);
if (ret)
return 0;
/* This pinned extent is out of our range */
if (extent_start >= block_group->start + block_group->length)
return 0;
extent_start = max(extent_start, start);
extent_end = min(block_group->start + block_group->length,
extent_end + 1);
len = extent_end - extent_start;
*entries += 1;
ret = io_ctl_add_entry(io_ctl, extent_start, len, NULL);
if (ret)
return -ENOSPC;
start = extent_end;
}
return 0;
}
static noinline_for_stack int
write_bitmap_entries(struct btrfs_io_ctl *io_ctl, struct list_head *bitmap_list)
{
struct btrfs_free_space *entry, *next;
int ret;
/* Write out the bitmaps */
list_for_each_entry_safe(entry, next, bitmap_list, list) {
ret = io_ctl_add_bitmap(io_ctl, entry->bitmap);
if (ret)
return -ENOSPC;
list_del_init(&entry->list);
}
return 0;
}
static int flush_dirty_cache(struct inode *inode)
{
int ret;
ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
if (ret)
clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
EXTENT_DELALLOC, 0, 0, NULL);
return ret;
}
static void noinline_for_stack
cleanup_bitmap_list(struct list_head *bitmap_list)
{
struct btrfs_free_space *entry, *next;
list_for_each_entry_safe(entry, next, bitmap_list, list)
list_del_init(&entry->list);
}
static void noinline_for_stack
cleanup_write_cache_enospc(struct inode *inode,
struct btrfs_io_ctl *io_ctl,
struct extent_state **cached_state)
{
io_ctl_drop_pages(io_ctl);
unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
i_size_read(inode) - 1, cached_state);
}
static int __btrfs_wait_cache_io(struct btrfs_root *root,
struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_io_ctl *io_ctl,
struct btrfs_path *path, u64 offset)
{
int ret;
struct inode *inode = io_ctl->inode;
if (!inode)
return 0;
/* Flush the dirty pages in the cache file. */
ret = flush_dirty_cache(inode);
if (ret)
goto out;
/* Update the cache item to tell everyone this cache file is valid. */
ret = update_cache_item(trans, root, inode, path, offset,
io_ctl->entries, io_ctl->bitmaps);
out:
if (ret) {
invalidate_inode_pages2(inode->i_mapping);
BTRFS_I(inode)->generation = 0;
if (block_group)
btrfs_debug(root->fs_info,
"failed to write free space cache for block group %llu error %d",
block_group->start, ret);
}
btrfs_update_inode(trans, root, BTRFS_I(inode));
if (block_group) {
/* the dirty list is protected by the dirty_bgs_lock */
spin_lock(&trans->transaction->dirty_bgs_lock);
/* the disk_cache_state is protected by the block group lock */
spin_lock(&block_group->lock);
/*
* only mark this as written if we didn't get put back on
* the dirty list while waiting for IO. Otherwise our
* cache state won't be right, and we won't get written again
*/
if (!ret && list_empty(&block_group->dirty_list))
block_group->disk_cache_state = BTRFS_DC_WRITTEN;
else if (ret)
block_group->disk_cache_state = BTRFS_DC_ERROR;
spin_unlock(&block_group->lock);
spin_unlock(&trans->transaction->dirty_bgs_lock);
io_ctl->inode = NULL;
iput(inode);
}
return ret;
}
int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
return __btrfs_wait_cache_io(block_group->fs_info->tree_root, trans,
block_group, &block_group->io_ctl,
path, block_group->start);
}
/**
* Write out cached info to an inode
*
* @root: root the inode belongs to
* @inode: freespace inode we are writing out
* @ctl: free space cache we are going to write out
* @block_group: block_group for this cache if it belongs to a block_group
* @io_ctl: holds context for the io
* @trans: the trans handle
*
* This function writes out a free space cache struct to disk for quick recovery
* on mount. This will return 0 if it was successful in writing the cache out,
* or an errno if it was not.
*/
static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
struct btrfs_free_space_ctl *ctl,
struct btrfs_block_group *block_group,
struct btrfs_io_ctl *io_ctl,
struct btrfs_trans_handle *trans)
{
struct extent_state *cached_state = NULL;
LIST_HEAD(bitmap_list);
int entries = 0;
int bitmaps = 0;
int ret;
int must_iput = 0;
if (!i_size_read(inode))
return -EIO;
WARN_ON(io_ctl->pages);
ret = io_ctl_init(io_ctl, inode, 1);
if (ret)
return ret;
if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) {
down_write(&block_group->data_rwsem);
spin_lock(&block_group->lock);
if (block_group->delalloc_bytes) {
block_group->disk_cache_state = BTRFS_DC_WRITTEN;
spin_unlock(&block_group->lock);
up_write(&block_group->data_rwsem);
BTRFS_I(inode)->generation = 0;
ret = 0;
must_iput = 1;
goto out;
}
spin_unlock(&block_group->lock);
}
/* Lock all pages first so we can lock the extent safely. */
ret = io_ctl_prepare_pages(io_ctl, false);
if (ret)
goto out_unlock;
lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
&cached_state);
io_ctl_set_generation(io_ctl, trans->transid);
mutex_lock(&ctl->cache_writeout_mutex);
/* Write out the extent entries in the free space cache */
spin_lock(&ctl->tree_lock);
ret = write_cache_extent_entries(io_ctl, ctl,
block_group, &entries, &bitmaps,
&bitmap_list);
if (ret)
goto out_nospc_locked;
/*
* Some spaces that are freed in the current transaction are pinned,
* they will be added into free space cache after the transaction is
* committed, we shouldn't lose them.
*
* If this changes while we are working we'll get added back to
* the dirty list and redo it. No locking needed
*/
ret = write_pinned_extent_entries(trans, block_group, io_ctl, &entries);
if (ret)
goto out_nospc_locked;
/*
* At last, we write out all the bitmaps and keep cache_writeout_mutex
* locked while doing it because a concurrent trim can be manipulating
* or freeing the bitmap.
*/
ret = write_bitmap_entries(io_ctl, &bitmap_list);
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
if (ret)
goto out_nospc;
/* Zero out the rest of the pages just to make sure */
io_ctl_zero_remaining_pages(io_ctl);
/* Everything is written out, now we dirty the pages in the file. */
ret = btrfs_dirty_pages(BTRFS_I(inode), io_ctl->pages,
io_ctl->num_pages, 0, i_size_read(inode),
&cached_state, false);
if (ret)
goto out_nospc;
if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
up_write(&block_group->data_rwsem);
/*
* Release the pages and unlock the extent, we will flush
* them out later
*/
io_ctl_drop_pages(io_ctl);
io_ctl_free(io_ctl);
unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
i_size_read(inode) - 1, &cached_state);
/*
* at this point the pages are under IO and we're happy,
* The caller is responsible for waiting on them and updating
* the cache and the inode
*/
io_ctl->entries = entries;
io_ctl->bitmaps = bitmaps;
ret = btrfs_fdatawrite_range(inode, 0, (u64)-1);
if (ret)
goto out;
return 0;
out_nospc_locked:
cleanup_bitmap_list(&bitmap_list);
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
out_nospc:
cleanup_write_cache_enospc(inode, io_ctl, &cached_state);
out_unlock:
if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
up_write(&block_group->data_rwsem);
out:
io_ctl->inode = NULL;
io_ctl_free(io_ctl);
if (ret) {
invalidate_inode_pages2(inode->i_mapping);
BTRFS_I(inode)->generation = 0;
}
btrfs_update_inode(trans, root, BTRFS_I(inode));
if (must_iput)
iput(inode);
return ret;
}
int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct inode *inode;
int ret = 0;
spin_lock(&block_group->lock);
if (block_group->disk_cache_state < BTRFS_DC_SETUP) {
spin_unlock(&block_group->lock);
return 0;
}
spin_unlock(&block_group->lock);
inode = lookup_free_space_inode(block_group, path);
if (IS_ERR(inode))
return 0;
ret = __btrfs_write_out_cache(fs_info->tree_root, inode, ctl,
block_group, &block_group->io_ctl, trans);
if (ret) {
btrfs_debug(fs_info,
"failed to write free space cache for block group %llu error %d",
block_group->start, ret);
spin_lock(&block_group->lock);
block_group->disk_cache_state = BTRFS_DC_ERROR;
spin_unlock(&block_group->lock);
block_group->io_ctl.inode = NULL;
iput(inode);
}
/*
* if ret == 0 the caller is expected to call btrfs_wait_cache_io
* to wait for IO and put the inode
*/
return ret;
}
static inline unsigned long offset_to_bit(u64 bitmap_start, u32 unit,
u64 offset)
{
ASSERT(offset >= bitmap_start);
offset -= bitmap_start;
return (unsigned long)(div_u64(offset, unit));
}
static inline unsigned long bytes_to_bits(u64 bytes, u32 unit)
{
return (unsigned long)(div_u64(bytes, unit));
}
static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl,
u64 offset)
{
u64 bitmap_start;
u64 bytes_per_bitmap;
bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit;
bitmap_start = offset - ctl->start;
bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap);
bitmap_start *= bytes_per_bitmap;
bitmap_start += ctl->start;
return bitmap_start;
}
static int tree_insert_offset(struct rb_root *root, u64 offset,
struct rb_node *node, int bitmap)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct btrfs_free_space *info;
while (*p) {
parent = *p;
info = rb_entry(parent, struct btrfs_free_space, offset_index);
if (offset < info->offset) {
p = &(*p)->rb_left;
} else if (offset > info->offset) {
p = &(*p)->rb_right;
} else {
/*
* we could have a bitmap entry and an extent entry
* share the same offset. If this is the case, we want
* the extent entry to always be found first if we do a
* linear search through the tree, since we want to have
* the quickest allocation time, and allocating from an
* extent is faster than allocating from a bitmap. So
* if we're inserting a bitmap and we find an entry at
* this offset, we want to go right, or after this entry
* logically. If we are inserting an extent and we've
* found a bitmap, we want to go left, or before
* logically.
*/
if (bitmap) {
if (info->bitmap) {
WARN_ON_ONCE(1);
return -EEXIST;
}
p = &(*p)->rb_right;
} else {
if (!info->bitmap) {
WARN_ON_ONCE(1);
return -EEXIST;
}
p = &(*p)->rb_left;
}
}
}
rb_link_node(node, parent, p);
rb_insert_color(node, root);
return 0;
}
/*
* This is a little subtle. We *only* have ->max_extent_size set if we actually
* searched through the bitmap and figured out the largest ->max_extent_size,
* otherwise it's 0. In the case that it's 0 we don't want to tell the
* allocator the wrong thing, we want to use the actual real max_extent_size
* we've found already if it's larger, or we want to use ->bytes.
*
* This matters because find_free_space() will skip entries who's ->bytes is
* less than the required bytes. So if we didn't search down this bitmap, we
* may pick some previous entry that has a smaller ->max_extent_size than we
* have. For example, assume we have two entries, one that has
* ->max_extent_size set to 4K and ->bytes set to 1M. A second entry hasn't set
* ->max_extent_size yet, has ->bytes set to 8K and it's contiguous. We will
* call into find_free_space(), and return with max_extent_size == 4K, because
* that first bitmap entry had ->max_extent_size set, but the second one did
* not. If instead we returned 8K we'd come in searching for 8K, and find the
* 8K contiguous range.
*
* Consider the other case, we have 2 8K chunks in that second entry and still
* don't have ->max_extent_size set. We'll return 16K, and the next time the
* allocator comes in it'll fully search our second bitmap, and this time it'll
* get an uptodate value of 8K as the maximum chunk size. Then we'll get the
* right allocation the next loop through.
*/
static inline u64 get_max_extent_size(const struct btrfs_free_space *entry)
{
if (entry->bitmap && entry->max_extent_size)
return entry->max_extent_size;
return entry->bytes;
}
/*
* We want the largest entry to be leftmost, so this is inverted from what you'd
* normally expect.
*/
static bool entry_less(struct rb_node *node, const struct rb_node *parent)
{
const struct btrfs_free_space *entry, *exist;
entry = rb_entry(node, struct btrfs_free_space, bytes_index);
exist = rb_entry(parent, struct btrfs_free_space, bytes_index);
return get_max_extent_size(exist) < get_max_extent_size(entry);
}
/*
* searches the tree for the given offset.
*
* fuzzy - If this is set, then we are trying to make an allocation, and we just
* want a section that has at least bytes size and comes at or after the given
* offset.
*/
static struct btrfs_free_space *
tree_search_offset(struct btrfs_free_space_ctl *ctl,
u64 offset, int bitmap_only, int fuzzy)
{
struct rb_node *n = ctl->free_space_offset.rb_node;
struct btrfs_free_space *entry = NULL, *prev = NULL;
/* find entry that is closest to the 'offset' */
while (n) {
entry = rb_entry(n, struct btrfs_free_space, offset_index);
prev = entry;
if (offset < entry->offset)
n = n->rb_left;
else if (offset > entry->offset)
n = n->rb_right;
else
break;
entry = NULL;
}
if (bitmap_only) {
if (!entry)
return NULL;
if (entry->bitmap)
return entry;
/*
* bitmap entry and extent entry may share same offset,
* in that case, bitmap entry comes after extent entry.
*/
n = rb_next(n);
if (!n)
return NULL;
entry = rb_entry(n, struct btrfs_free_space, offset_index);
if (entry->offset != offset)
return NULL;
WARN_ON(!entry->bitmap);
return entry;
} else if (entry) {
if (entry->bitmap) {
/*
* if previous extent entry covers the offset,
* we should return it instead of the bitmap entry
*/
n = rb_prev(&entry->offset_index);
if (n) {
prev = rb_entry(n, struct btrfs_free_space,
offset_index);
if (!prev->bitmap &&
prev->offset + prev->bytes > offset)
entry = prev;
}
}
return entry;
}
if (!prev)
return NULL;
/* find last entry before the 'offset' */
entry = prev;
if (entry->offset > offset) {
n = rb_prev(&entry->offset_index);
if (n) {
entry = rb_entry(n, struct btrfs_free_space,
offset_index);
ASSERT(entry->offset <= offset);
} else {
if (fuzzy)
return entry;
else
return NULL;
}
}
if (entry->bitmap) {
n = rb_prev(&entry->offset_index);
if (n) {
prev = rb_entry(n, struct btrfs_free_space,
offset_index);
if (!prev->bitmap &&
prev->offset + prev->bytes > offset)
return prev;
}
if (entry->offset + BITS_PER_BITMAP * ctl->unit > offset)
return entry;
} else if (entry->offset + entry->bytes > offset)
return entry;
if (!fuzzy)
return NULL;
while (1) {
n = rb_next(&entry->offset_index);
if (!n)
return NULL;
entry = rb_entry(n, struct btrfs_free_space, offset_index);
if (entry->bitmap) {
if (entry->offset + BITS_PER_BITMAP *
ctl->unit > offset)
break;
} else {
if (entry->offset + entry->bytes > offset)
break;
}
}
return entry;
}
static inline void unlink_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info,
bool update_stat)
{
rb_erase(&info->offset_index, &ctl->free_space_offset);
rb_erase_cached(&info->bytes_index, &ctl->free_space_bytes);
ctl->free_extents--;
if (!info->bitmap && !btrfs_free_space_trimmed(info)) {
ctl->discardable_extents[BTRFS_STAT_CURR]--;
ctl->discardable_bytes[BTRFS_STAT_CURR] -= info->bytes;
}
if (update_stat)
ctl->free_space -= info->bytes;
}
static int link_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info)
{
int ret = 0;
ASSERT(info->bytes || info->bitmap);
ret = tree_insert_offset(&ctl->free_space_offset, info->offset,
&info->offset_index, (info->bitmap != NULL));
if (ret)
return ret;
rb_add_cached(&info->bytes_index, &ctl->free_space_bytes, entry_less);
if (!info->bitmap && !btrfs_free_space_trimmed(info)) {
ctl->discardable_extents[BTRFS_STAT_CURR]++;
ctl->discardable_bytes[BTRFS_STAT_CURR] += info->bytes;
}
ctl->free_space += info->bytes;
ctl->free_extents++;
return ret;
}
static void relink_bitmap_entry(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info)
{
ASSERT(info->bitmap);
/*
* If our entry is empty it's because we're on a cluster and we don't
* want to re-link it into our ctl bytes index.
*/
if (RB_EMPTY_NODE(&info->bytes_index))
return;
rb_erase_cached(&info->bytes_index, &ctl->free_space_bytes);
rb_add_cached(&info->bytes_index, &ctl->free_space_bytes, entry_less);
}
static inline void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info,
u64 offset, u64 bytes, bool update_stat)
{
unsigned long start, count, end;
int extent_delta = -1;
start = offset_to_bit(info->offset, ctl->unit, offset);
count = bytes_to_bits(bytes, ctl->unit);
end = start + count;
ASSERT(end <= BITS_PER_BITMAP);
bitmap_clear(info->bitmap, start, count);
info->bytes -= bytes;
if (info->max_extent_size > ctl->unit)
info->max_extent_size = 0;
relink_bitmap_entry(ctl, info);
if (start && test_bit(start - 1, info->bitmap))
extent_delta++;
if (end < BITS_PER_BITMAP && test_bit(end, info->bitmap))
extent_delta++;
info->bitmap_extents += extent_delta;
if (!btrfs_free_space_trimmed(info)) {
ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta;
ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes;
}
if (update_stat)
ctl->free_space -= bytes;
}
static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, u64 offset,
u64 bytes)
{
unsigned long start, count, end;
int extent_delta = 1;
start = offset_to_bit(info->offset, ctl->unit, offset);
count = bytes_to_bits(bytes, ctl->unit);
end = start + count;
ASSERT(end <= BITS_PER_BITMAP);
bitmap_set(info->bitmap, start, count);
/*
* We set some bytes, we have no idea what the max extent size is
* anymore.
*/
info->max_extent_size = 0;
info->bytes += bytes;
ctl->free_space += bytes;
relink_bitmap_entry(ctl, info);
if (start && test_bit(start - 1, info->bitmap))
extent_delta--;
if (end < BITS_PER_BITMAP && test_bit(end, info->bitmap))
extent_delta--;
info->bitmap_extents += extent_delta;
if (!btrfs_free_space_trimmed(info)) {
ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta;
ctl->discardable_bytes[BTRFS_STAT_CURR] += bytes;
}
}
/*
* If we can not find suitable extent, we will use bytes to record
* the size of the max extent.
*/
static int search_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *bitmap_info, u64 *offset,
u64 *bytes, bool for_alloc)
{
unsigned long found_bits = 0;
unsigned long max_bits = 0;
unsigned long bits, i;
unsigned long next_zero;
unsigned long extent_bits;
/*
* Skip searching the bitmap if we don't have a contiguous section that
* is large enough for this allocation.
*/
if (for_alloc &&
bitmap_info->max_extent_size &&
bitmap_info->max_extent_size < *bytes) {
*bytes = bitmap_info->max_extent_size;
return -1;
}
i = offset_to_bit(bitmap_info->offset, ctl->unit,
max_t(u64, *offset, bitmap_info->offset));
bits = bytes_to_bits(*bytes, ctl->unit);
for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) {
if (for_alloc && bits == 1) {
found_bits = 1;
break;
}
next_zero = find_next_zero_bit(bitmap_info->bitmap,
BITS_PER_BITMAP, i);
extent_bits = next_zero - i;
if (extent_bits >= bits) {
found_bits = extent_bits;
break;
} else if (extent_bits > max_bits) {
max_bits = extent_bits;
}
i = next_zero;
}
if (found_bits) {
*offset = (u64)(i * ctl->unit) + bitmap_info->offset;
*bytes = (u64)(found_bits) * ctl->unit;
return 0;
}
*bytes = (u64)(max_bits) * ctl->unit;
bitmap_info->max_extent_size = *bytes;
relink_bitmap_entry(ctl, bitmap_info);
return -1;
}
/* Cache the size of the max extent in bytes */
static struct btrfs_free_space *
find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
unsigned long align, u64 *max_extent_size, bool use_bytes_index)
{
struct btrfs_free_space *entry;
struct rb_node *node;
u64 tmp;
u64 align_off;
int ret;
if (!ctl->free_space_offset.rb_node)
goto out;
again:
if (use_bytes_index) {
node = rb_first_cached(&ctl->free_space_bytes);
} else {
entry = tree_search_offset(ctl, offset_to_bitmap(ctl, *offset),
0, 1);
if (!entry)
goto out;
node = &entry->offset_index;
}
for (; node; node = rb_next(node)) {
if (use_bytes_index)
entry = rb_entry(node, struct btrfs_free_space,
bytes_index);
else
entry = rb_entry(node, struct btrfs_free_space,
offset_index);
/*
* If we are using the bytes index then all subsequent entries
* in this tree are going to be < bytes, so simply set the max
* extent size and exit the loop.
*
* If we're using the offset index then we need to keep going
* through the rest of the tree.
*/
if (entry->bytes < *bytes) {
*max_extent_size = max(get_max_extent_size(entry),
*max_extent_size);
if (use_bytes_index)
break;
continue;
}
/* make sure the space returned is big enough
* to match our requested alignment
*/
if (*bytes >= align) {
tmp = entry->offset - ctl->start + align - 1;
tmp = div64_u64(tmp, align);
tmp = tmp * align + ctl->start;
align_off = tmp - entry->offset;
} else {
align_off = 0;
tmp = entry->offset;
}
/*
* We don't break here if we're using the bytes index because we
* may have another entry that has the correct alignment that is
* the right size, so we don't want to miss that possibility.
* At worst this adds another loop through the logic, but if we
* broke here we could prematurely ENOSPC.
*/
if (entry->bytes < *bytes + align_off) {
*max_extent_size = max(get_max_extent_size(entry),
*max_extent_size);
continue;
}
if (entry->bitmap) {
struct rb_node *old_next = rb_next(node);
u64 size = *bytes;
ret = search_bitmap(ctl, entry, &tmp, &size, true);
if (!ret) {
*offset = tmp;
*bytes = size;
return entry;
} else {
*max_extent_size =
max(get_max_extent_size(entry),
*max_extent_size);
}
/*
* The bitmap may have gotten re-arranged in the space
* index here because the max_extent_size may have been
* updated. Start from the beginning again if this
* happened.
*/
if (use_bytes_index && old_next != rb_next(node))
goto again;
continue;
}
*offset = tmp;
*bytes = entry->bytes - align_off;
return entry;
}
out:
return NULL;
}
static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, u64 offset)
{
info->offset = offset_to_bitmap(ctl, offset);
info->bytes = 0;
info->bitmap_extents = 0;
INIT_LIST_HEAD(&info->list);
link_free_space(ctl, info);
ctl->total_bitmaps++;
recalculate_thresholds(ctl);
}
static void free_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *bitmap_info)
{
/*
* Normally when this is called, the bitmap is completely empty. However,
* if we are blowing up the free space cache for one reason or another
* via __btrfs_remove_free_space_cache(), then it may not be freed and
* we may leave stats on the table.
*/
if (bitmap_info->bytes && !btrfs_free_space_trimmed(bitmap_info)) {
ctl->discardable_extents[BTRFS_STAT_CURR] -=
bitmap_info->bitmap_extents;
ctl->discardable_bytes[BTRFS_STAT_CURR] -= bitmap_info->bytes;
}
unlink_free_space(ctl, bitmap_info, true);
kmem_cache_free(btrfs_free_space_bitmap_cachep, bitmap_info->bitmap);
kmem_cache_free(btrfs_free_space_cachep, bitmap_info);
ctl->total_bitmaps--;
recalculate_thresholds(ctl);
}
static noinline int remove_from_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *bitmap_info,
u64 *offset, u64 *bytes)
{
u64 end;
u64 search_start, search_bytes;
int ret;
again:
end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1;
/*
* We need to search for bits in this bitmap. We could only cover some
* of the extent in this bitmap thanks to how we add space, so we need
* to search for as much as it as we can and clear that amount, and then
* go searching for the next bit.
*/
search_start = *offset;
search_bytes = ctl->unit;
search_bytes = min(search_bytes, end - search_start + 1);
ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes,
false);
if (ret < 0 || search_start != *offset)
return -EINVAL;
/* We may have found more bits than what we need */
search_bytes = min(search_bytes, *bytes);
/* Cannot clear past the end of the bitmap */
search_bytes = min(search_bytes, end - search_start + 1);
bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes, true);
*offset += search_bytes;
*bytes -= search_bytes;
if (*bytes) {
struct rb_node *next = rb_next(&bitmap_info->offset_index);
if (!bitmap_info->bytes)
free_bitmap(ctl, bitmap_info);
/*
* no entry after this bitmap, but we still have bytes to
* remove, so something has gone wrong.
*/
if (!next)
return -EINVAL;
bitmap_info = rb_entry(next, struct btrfs_free_space,
offset_index);
/*
* if the next entry isn't a bitmap we need to return to let the
* extent stuff do its work.
*/
if (!bitmap_info->bitmap)
return -EAGAIN;
/*
* Ok the next item is a bitmap, but it may not actually hold
* the information for the rest of this free space stuff, so
* look for it, and if we don't find it return so we can try
* everything over again.
*/
search_start = *offset;
search_bytes = ctl->unit;
ret = search_bitmap(ctl, bitmap_info, &search_start,
&search_bytes, false);
if (ret < 0 || search_start != *offset)
return -EAGAIN;
goto again;
} else if (!bitmap_info->bytes)
free_bitmap(ctl, bitmap_info);
return 0;
}
static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, u64 offset,
u64 bytes, enum btrfs_trim_state trim_state)
{
u64 bytes_to_set = 0;
u64 end;
/*
* This is a tradeoff to make bitmap trim state minimal. We mark the
* whole bitmap untrimmed if at any point we add untrimmed regions.
*/
if (trim_state == BTRFS_TRIM_STATE_UNTRIMMED) {
if (btrfs_free_space_trimmed(info)) {
ctl->discardable_extents[BTRFS_STAT_CURR] +=
info->bitmap_extents;
ctl->discardable_bytes[BTRFS_STAT_CURR] += info->bytes;
}
info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
}
end = info->offset + (u64)(BITS_PER_BITMAP * ctl->unit);
bytes_to_set = min(end - offset, bytes);
bitmap_set_bits(ctl, info, offset, bytes_to_set);
return bytes_to_set;
}
static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info)
{
struct btrfs_block_group *block_group = ctl->block_group;
struct btrfs_fs_info *fs_info = block_group->fs_info;
bool forced = false;
#ifdef CONFIG_BTRFS_DEBUG
if (btrfs_should_fragment_free_space(block_group))
forced = true;
#endif
/* This is a way to reclaim large regions from the bitmaps. */
if (!forced && info->bytes >= FORCE_EXTENT_THRESHOLD)
return false;
/*
* If we are below the extents threshold then we can add this as an
* extent, and don't have to deal with the bitmap
*/
if (!forced && ctl->free_extents < ctl->extents_thresh) {
/*
* If this block group has some small extents we don't want to
* use up all of our free slots in the cache with them, we want
* to reserve them to larger extents, however if we have plenty
* of cache left then go ahead an dadd them, no sense in adding
* the overhead of a bitmap if we don't have to.
*/
if (info->bytes <= fs_info->sectorsize * 8) {
if (ctl->free_extents * 3 <= ctl->extents_thresh)
return false;
} else {
return false;
}
}
/*
* The original block groups from mkfs can be really small, like 8
* megabytes, so don't bother with a bitmap for those entries. However
* some block groups can be smaller than what a bitmap would cover but
* are still large enough that they could overflow the 32k memory limit,
* so allow those block groups to still be allowed to have a bitmap
* entry.
*/
if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->length)
return false;
return true;
}
static const struct btrfs_free_space_op free_space_op = {
.use_bitmap = use_bitmap,
};
static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info)
{
struct btrfs_free_space *bitmap_info;
struct btrfs_block_group *block_group = NULL;
int added = 0;
u64 bytes, offset, bytes_added;
enum btrfs_trim_state trim_state;
int ret;
bytes = info->bytes;
offset = info->offset;
trim_state = info->trim_state;
if (!ctl->op->use_bitmap(ctl, info))
return 0;
if (ctl->op == &free_space_op)
block_group = ctl->block_group;
again:
/*
* Since we link bitmaps right into the cluster we need to see if we
* have a cluster here, and if so and it has our bitmap we need to add
* the free space to that bitmap.
*/
if (block_group && !list_empty(&block_group->cluster_list)) {
struct btrfs_free_cluster *cluster;
struct rb_node *node;
struct btrfs_free_space *entry;
cluster = list_entry(block_group->cluster_list.next,
struct btrfs_free_cluster,
block_group_list);
spin_lock(&cluster->lock);
node = rb_first(&cluster->root);
if (!node) {
spin_unlock(&cluster->lock);
goto no_cluster_bitmap;
}
entry = rb_entry(node, struct btrfs_free_space, offset_index);
if (!entry->bitmap) {
spin_unlock(&cluster->lock);
goto no_cluster_bitmap;
}
if (entry->offset == offset_to_bitmap(ctl, offset)) {
bytes_added = add_bytes_to_bitmap(ctl, entry, offset,
bytes, trim_state);
bytes -= bytes_added;
offset += bytes_added;
}
spin_unlock(&cluster->lock);
if (!bytes) {
ret = 1;
goto out;
}
}
no_cluster_bitmap:
bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!bitmap_info) {
ASSERT(added == 0);
goto new_bitmap;
}
bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes,
trim_state);
bytes -= bytes_added;
offset += bytes_added;
added = 0;
if (!bytes) {
ret = 1;
goto out;
} else
goto again;
new_bitmap:
if (info && info->bitmap) {
add_new_bitmap(ctl, info, offset);
added = 1;
info = NULL;
goto again;
} else {
spin_unlock(&ctl->tree_lock);
/* no pre-allocated info, allocate a new one */
if (!info) {
info = kmem_cache_zalloc(btrfs_free_space_cachep,
GFP_NOFS);
if (!info) {
spin_lock(&ctl->tree_lock);
ret = -ENOMEM;
goto out;
}
}
/* allocate the bitmap */
info->bitmap = kmem_cache_zalloc(btrfs_free_space_bitmap_cachep,
GFP_NOFS);
info->trim_state = BTRFS_TRIM_STATE_TRIMMED;
spin_lock(&ctl->tree_lock);
if (!info->bitmap) {
ret = -ENOMEM;
goto out;
}
goto again;
}
out:
if (info) {
if (info->bitmap)
kmem_cache_free(btrfs_free_space_bitmap_cachep,
info->bitmap);
kmem_cache_free(btrfs_free_space_cachep, info);
}
return ret;
}
/*
* Free space merging rules:
* 1) Merge trimmed areas together
* 2) Let untrimmed areas coalesce with trimmed areas
* 3) Always pull neighboring regions from bitmaps
*
* The above rules are for when we merge free space based on btrfs_trim_state.
* Rules 2 and 3 are subtle because they are suboptimal, but are done for the
* same reason: to promote larger extent regions which makes life easier for
* find_free_extent(). Rule 2 enables coalescing based on the common path
* being returning free space from btrfs_finish_extent_commit(). So when free
* space is trimmed, it will prevent aggregating trimmed new region and
* untrimmed regions in the rb_tree. Rule 3 is purely to obtain larger extents
* and provide find_free_extent() with the largest extents possible hoping for
* the reuse path.
*/
static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, bool update_stat)
{
struct btrfs_free_space *left_info = NULL;
struct btrfs_free_space *right_info;
bool merged = false;
u64 offset = info->offset;
u64 bytes = info->bytes;
const bool is_trimmed = btrfs_free_space_trimmed(info);
/*
* first we want to see if there is free space adjacent to the range we
* are adding, if there is remove that struct and add a new one to
* cover the entire range
*/
right_info = tree_search_offset(ctl, offset + bytes, 0, 0);
if (right_info && rb_prev(&right_info->offset_index))
left_info = rb_entry(rb_prev(&right_info->offset_index),
struct btrfs_free_space, offset_index);
else if (!right_info)
left_info = tree_search_offset(ctl, offset - 1, 0, 0);
/* See try_merge_free_space() comment. */
if (right_info && !right_info->bitmap &&
(!is_trimmed || btrfs_free_space_trimmed(right_info))) {
unlink_free_space(ctl, right_info, update_stat);
info->bytes += right_info->bytes;
kmem_cache_free(btrfs_free_space_cachep, right_info);
merged = true;
}
/* See try_merge_free_space() comment. */
if (left_info && !left_info->bitmap &&
left_info->offset + left_info->bytes == offset &&
(!is_trimmed || btrfs_free_space_trimmed(left_info))) {
unlink_free_space(ctl, left_info, update_stat);
info->offset = left_info->offset;
info->bytes += left_info->bytes;
kmem_cache_free(btrfs_free_space_cachep, left_info);
merged = true;
}
return merged;
}
static bool steal_from_bitmap_to_end(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info,
bool update_stat)
{
struct btrfs_free_space *bitmap;
unsigned long i;
unsigned long j;
const u64 end = info->offset + info->bytes;
const u64 bitmap_offset = offset_to_bitmap(ctl, end);
u64 bytes;
bitmap = tree_search_offset(ctl, bitmap_offset, 1, 0);
if (!bitmap)
return false;
i = offset_to_bit(bitmap->offset, ctl->unit, end);
j = find_next_zero_bit(bitmap->bitmap, BITS_PER_BITMAP, i);
if (j == i)
return false;
bytes = (j - i) * ctl->unit;
info->bytes += bytes;
/* See try_merge_free_space() comment. */
if (!btrfs_free_space_trimmed(bitmap))
info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
bitmap_clear_bits(ctl, bitmap, end, bytes, update_stat);
if (!bitmap->bytes)
free_bitmap(ctl, bitmap);
return true;
}
static bool steal_from_bitmap_to_front(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info,
bool update_stat)
{
struct btrfs_free_space *bitmap;
u64 bitmap_offset;
unsigned long i;
unsigned long j;
unsigned long prev_j;
u64 bytes;
bitmap_offset = offset_to_bitmap(ctl, info->offset);
/* If we're on a boundary, try the previous logical bitmap. */
if (bitmap_offset == info->offset) {
if (info->offset == 0)
return false;
bitmap_offset = offset_to_bitmap(ctl, info->offset - 1);
}
bitmap = tree_search_offset(ctl, bitmap_offset, 1, 0);
if (!bitmap)
return false;
i = offset_to_bit(bitmap->offset, ctl->unit, info->offset) - 1;
j = 0;
prev_j = (unsigned long)-1;
for_each_clear_bit_from(j, bitmap->bitmap, BITS_PER_BITMAP) {
if (j > i)
break;
prev_j = j;
}
if (prev_j == i)
return false;
if (prev_j == (unsigned long)-1)
bytes = (i + 1) * ctl->unit;
else
bytes = (i - prev_j) * ctl->unit;
info->offset -= bytes;
info->bytes += bytes;
/* See try_merge_free_space() comment. */
if (!btrfs_free_space_trimmed(bitmap))
info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
bitmap_clear_bits(ctl, bitmap, info->offset, bytes, update_stat);
if (!bitmap->bytes)
free_bitmap(ctl, bitmap);
return true;
}
/*
* We prefer always to allocate from extent entries, both for clustered and
* non-clustered allocation requests. So when attempting to add a new extent
* entry, try to see if there's adjacent free space in bitmap entries, and if
* there is, migrate that space from the bitmaps to the extent.
* Like this we get better chances of satisfying space allocation requests
* because we attempt to satisfy them based on a single cache entry, and never
* on 2 or more entries - even if the entries represent a contiguous free space
* region (e.g. 1 extent entry + 1 bitmap entry starting where the extent entry
* ends).
*/
static void steal_from_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info,
bool update_stat)
{
/*
* Only work with disconnected entries, as we can change their offset,
* and must be extent entries.
*/
ASSERT(!info->bitmap);
ASSERT(RB_EMPTY_NODE(&info->offset_index));
if (ctl->total_bitmaps > 0) {
bool stole_end;
bool stole_front = false;
stole_end = steal_from_bitmap_to_end(ctl, info, update_stat);
if (ctl->total_bitmaps > 0)
stole_front = steal_from_bitmap_to_front(ctl, info,
update_stat);
if (stole_end || stole_front)
try_merge_free_space(ctl, info, update_stat);
}
}
int __btrfs_add_free_space(struct btrfs_block_group *block_group,
u64 offset, u64 bytes,
enum btrfs_trim_state trim_state)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *info;
int ret = 0;
u64 filter_bytes = bytes;
ASSERT(!btrfs_is_zoned(fs_info));
info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
if (!info)
return -ENOMEM;
info->offset = offset;
info->bytes = bytes;
info->trim_state = trim_state;
RB_CLEAR_NODE(&info->offset_index);
RB_CLEAR_NODE(&info->bytes_index);
spin_lock(&ctl->tree_lock);
if (try_merge_free_space(ctl, info, true))
goto link;
/*
* There was no extent directly to the left or right of this new
* extent then we know we're going to have to allocate a new extent, so
* before we do that see if we need to drop this into a bitmap
*/
ret = insert_into_bitmap(ctl, info);
if (ret < 0) {
goto out;
} else if (ret) {
ret = 0;
goto out;
}
link:
/*
* Only steal free space from adjacent bitmaps if we're sure we're not
* going to add the new free space to existing bitmap entries - because
* that would mean unnecessary work that would be reverted. Therefore
* attempt to steal space from bitmaps if we're adding an extent entry.
*/
steal_from_bitmap(ctl, info, true);
filter_bytes = max(filter_bytes, info->bytes);
ret = link_free_space(ctl, info);
if (ret)
kmem_cache_free(btrfs_free_space_cachep, info);
out:
btrfs_discard_update_discardable(block_group);
spin_unlock(&ctl->tree_lock);
if (ret) {
btrfs_crit(fs_info, "unable to add free space :%d", ret);
ASSERT(ret != -EEXIST);
}
if (trim_state != BTRFS_TRIM_STATE_TRIMMED) {
btrfs_discard_check_filter(block_group, filter_bytes);
btrfs_discard_queue_work(&fs_info->discard_ctl, block_group);
}
return ret;
}
static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
u64 bytenr, u64 size, bool used)
{
struct btrfs_space_info *sinfo = block_group->space_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
u64 offset = bytenr - block_group->start;
u64 to_free, to_unusable;
int bg_reclaim_threshold = 0;
bool initial = (size == block_group->length);
u64 reclaimable_unusable;
WARN_ON(!initial && offset + size > block_group->zone_capacity);
if (!initial)
bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);
spin_lock(&ctl->tree_lock);
if (!used)
to_free = size;
else if (initial)
to_free = block_group->zone_capacity;
else if (offset >= block_group->alloc_offset)
to_free = size;
else if (offset + size <= block_group->alloc_offset)
to_free = 0;
else
to_free = offset + size - block_group->alloc_offset;
to_unusable = size - to_free;
ctl->free_space += to_free;
/*
* If the block group is read-only, we should account freed space into
* bytes_readonly.
*/
if (!block_group->ro)
block_group->zone_unusable += to_unusable;
spin_unlock(&ctl->tree_lock);
if (!used) {
spin_lock(&block_group->lock);
block_group->alloc_offset -= size;
spin_unlock(&block_group->lock);
}
reclaimable_unusable = block_group->zone_unusable -
(block_group->length - block_group->zone_capacity);
/* All the region is now unusable. Mark it as unused and reclaim */
if (block_group->zone_unusable == block_group->length) {
btrfs_mark_bg_unused(block_group);
} else if (bg_reclaim_threshold &&
reclaimable_unusable >=
div_factor_fine(block_group->zone_capacity,
bg_reclaim_threshold)) {
btrfs_mark_bg_to_reclaim(block_group);
}
return 0;
}
int btrfs_add_free_space(struct btrfs_block_group *block_group,
u64 bytenr, u64 size)
{
enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
if (btrfs_is_zoned(block_group->fs_info))
return __btrfs_add_free_space_zoned(block_group, bytenr, size,
true);
if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC))
trim_state = BTRFS_TRIM_STATE_TRIMMED;
return __btrfs_add_free_space(block_group, bytenr, size, trim_state);
}
int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
u64 bytenr, u64 size)
{
if (btrfs_is_zoned(block_group->fs_info))
return __btrfs_add_free_space_zoned(block_group, bytenr, size,
false);
return btrfs_add_free_space(block_group, bytenr, size);
}
/*
* This is a subtle distinction because when adding free space back in general,
* we want it to be added as untrimmed for async. But in the case where we add
* it on loading of a block group, we want to consider it trimmed.
*/
int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
u64 bytenr, u64 size)
{
enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
if (btrfs_is_zoned(block_group->fs_info))
return __btrfs_add_free_space_zoned(block_group, bytenr, size,
true);
if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) ||
btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC))
trim_state = BTRFS_TRIM_STATE_TRIMMED;
return __btrfs_add_free_space(block_group, bytenr, size, trim_state);
}
int btrfs_remove_free_space(struct btrfs_block_group *block_group,
u64 offset, u64 bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *info;
int ret;
bool re_search = false;
if (btrfs_is_zoned(block_group->fs_info)) {
/*
* This can happen with conventional zones when replaying log.
* Since the allocation info of tree-log nodes are not recorded
* to the extent-tree, calculate_alloc_pointer() failed to
* advance the allocation pointer after last allocated tree log
* node blocks.
*
* This function is called from
* btrfs_pin_extent_for_log_replay() when replaying the log.
* Advance the pointer not to overwrite the tree-log nodes.
*/
if (block_group->start + block_group->alloc_offset <
offset + bytes) {
block_group->alloc_offset =
offset + bytes - block_group->start;
}
return 0;
}
spin_lock(&ctl->tree_lock);
again:
ret = 0;
if (!bytes)
goto out_lock;
info = tree_search_offset(ctl, offset, 0, 0);
if (!info) {
/*
* oops didn't find an extent that matched the space we wanted
* to remove, look for a bitmap instead
*/
info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!info) {
/*
* If we found a partial bit of our free space in a
* bitmap but then couldn't find the other part this may
* be a problem, so WARN about it.
*/
WARN_ON(re_search);
goto out_lock;
}
}
re_search = false;
if (!info->bitmap) {
unlink_free_space(ctl, info, true);
if (offset == info->offset) {
u64 to_free = min(bytes, info->bytes);
info->bytes -= to_free;
info->offset += to_free;
if (info->bytes) {
ret = link_free_space(ctl, info);
WARN_ON(ret);
} else {
kmem_cache_free(btrfs_free_space_cachep, info);
}
offset += to_free;
bytes -= to_free;
goto again;
} else {
u64 old_end = info->bytes + info->offset;
info->bytes = offset - info->offset;
ret = link_free_space(ctl, info);
WARN_ON(ret);
if (ret)
goto out_lock;
/* Not enough bytes in this entry to satisfy us */
if (old_end < offset + bytes) {
bytes -= old_end - offset;
offset = old_end;
goto again;
} else if (old_end == offset + bytes) {
/* all done */
goto out_lock;
}
spin_unlock(&ctl->tree_lock);
ret = __btrfs_add_free_space(block_group,
offset + bytes,
old_end - (offset + bytes),
info->trim_state);
WARN_ON(ret);
goto out;
}
}
ret = remove_from_bitmap(ctl, info, &offset, &bytes);
if (ret == -EAGAIN) {
re_search = true;
goto again;
}
out_lock:
btrfs_discard_update_discardable(block_group);
spin_unlock(&ctl->tree_lock);
out:
return ret;
}
void btrfs_dump_free_space(struct btrfs_block_group *block_group,
u64 bytes)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *info;
struct rb_node *n;
int count = 0;
/*
* Zoned btrfs does not use free space tree and cluster. Just print
* out the free space after the allocation offset.
*/
if (btrfs_is_zoned(fs_info)) {
btrfs_info(fs_info, "free space %llu active %d",
block_group->zone_capacity - block_group->alloc_offset,
test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
&block_group->runtime_flags));
return;
}
spin_lock(&ctl->tree_lock);
for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
info = rb_entry(n, struct btrfs_free_space, offset_index);
if (info->bytes >= bytes && !block_group->ro)
count++;
btrfs_crit(fs_info, "entry offset %llu, bytes %llu, bitmap %s",
info->offset, info->bytes,
(info->bitmap) ? "yes" : "no");
}
spin_unlock(&ctl->tree_lock);
btrfs_info(fs_info, "block group has cluster?: %s",
list_empty(&block_group->cluster_list) ? "no" : "yes");
btrfs_info(fs_info,
"%d blocks of free space at or bigger than bytes is", count);
}
void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
struct btrfs_free_space_ctl *ctl)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
spin_lock_init(&ctl->tree_lock);
ctl->unit = fs_info->sectorsize;
ctl->start = block_group->start;
ctl->block_group = block_group;
ctl->op = &free_space_op;
ctl->free_space_bytes = RB_ROOT_CACHED;
INIT_LIST_HEAD(&ctl->trimming_ranges);
mutex_init(&ctl->cache_writeout_mutex);
/*
* we only want to have 32k of ram per block group for keeping
* track of free space, and if we pass 1/2 of that we want to
* start converting things over to using bitmaps
*/
ctl->extents_thresh = (SZ_32K / 2) / sizeof(struct btrfs_free_space);
}
/*
* for a given cluster, put all of its extents back into the free
* space cache. If the block group passed doesn't match the block group
* pointed to by the cluster, someone else raced in and freed the
* cluster already. In that case, we just return without changing anything
*/
static void __btrfs_return_cluster_to_free_space(
struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
struct rb_node *node;
spin_lock(&cluster->lock);
if (cluster->block_group != block_group) {
spin_unlock(&cluster->lock);
return;
}
cluster->block_group = NULL;
cluster->window_start = 0;
list_del_init(&cluster->block_group_list);
node = rb_first(&cluster->root);
while (node) {
bool bitmap;
entry = rb_entry(node, struct btrfs_free_space, offset_index);
node = rb_next(&entry->offset_index);
rb_erase(&entry->offset_index, &cluster->root);
RB_CLEAR_NODE(&entry->offset_index);
bitmap = (entry->bitmap != NULL);
if (!bitmap) {
/* Merging treats extents as if they were new */
if (!btrfs_free_space_trimmed(entry)) {
ctl->discardable_extents[BTRFS_STAT_CURR]--;
ctl->discardable_bytes[BTRFS_STAT_CURR] -=
entry->bytes;
}
try_merge_free_space(ctl, entry, false);
steal_from_bitmap(ctl, entry, false);
/* As we insert directly, update these statistics */
if (!btrfs_free_space_trimmed(entry)) {
ctl->discardable_extents[BTRFS_STAT_CURR]++;
ctl->discardable_bytes[BTRFS_STAT_CURR] +=
entry->bytes;
}
}
tree_insert_offset(&ctl->free_space_offset,
entry->offset, &entry->offset_index, bitmap);
rb_add_cached(&entry->bytes_index, &ctl->free_space_bytes,
entry_less);
}
cluster->root = RB_ROOT;
spin_unlock(&cluster->lock);
btrfs_put_block_group(block_group);
}
void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
{
spin_lock(&ctl->tree_lock);
__btrfs_remove_free_space_cache_locked(ctl);
if (ctl->block_group)
btrfs_discard_update_discardable(ctl->block_group);
spin_unlock(&ctl->tree_lock);
}
void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_cluster *cluster;
struct list_head *head;
spin_lock(&ctl->tree_lock);
while ((head = block_group->cluster_list.next) !=
&block_group->cluster_list) {
cluster = list_entry(head, struct btrfs_free_cluster,
block_group_list);
WARN_ON(cluster->block_group != block_group);
__btrfs_return_cluster_to_free_space(block_group, cluster);
cond_resched_lock(&ctl->tree_lock);
}
__btrfs_remove_free_space_cache_locked(ctl);
btrfs_discard_update_discardable(block_group);
spin_unlock(&ctl->tree_lock);
}
/**
* btrfs_is_free_space_trimmed - see if everything is trimmed
* @block_group: block_group of interest
*
* Walk @block_group's free space rb_tree to determine if everything is trimmed.
*/
bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *info;
struct rb_node *node;
bool ret = true;
spin_lock(&ctl->tree_lock);
node = rb_first(&ctl->free_space_offset);
while (node) {
info = rb_entry(node, struct btrfs_free_space, offset_index);
if (!btrfs_free_space_trimmed(info)) {
ret = false;
break;
}
node = rb_next(node);
}
spin_unlock(&ctl->tree_lock);
return ret;
}
u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
u64 offset, u64 bytes, u64 empty_size,
u64 *max_extent_size)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_discard_ctl *discard_ctl =
&block_group->fs_info->discard_ctl;
struct btrfs_free_space *entry = NULL;
u64 bytes_search = bytes + empty_size;
u64 ret = 0;
u64 align_gap = 0;
u64 align_gap_len = 0;
enum btrfs_trim_state align_gap_trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
bool use_bytes_index = (offset == block_group->start);
ASSERT(!btrfs_is_zoned(block_group->fs_info));
spin_lock(&ctl->tree_lock);
entry = find_free_space(ctl, &offset, &bytes_search,
block_group->full_stripe_len, max_extent_size,
use_bytes_index);
if (!entry)
goto out;
ret = offset;
if (entry->bitmap) {
bitmap_clear_bits(ctl, entry, offset, bytes, true);
if (!btrfs_free_space_trimmed(entry))
atomic64_add(bytes, &discard_ctl->discard_bytes_saved);
if (!entry->bytes)
free_bitmap(ctl, entry);
} else {
unlink_free_space(ctl, entry, true);
align_gap_len = offset - entry->offset;
align_gap = entry->offset;
align_gap_trim_state = entry->trim_state;
if (!btrfs_free_space_trimmed(entry))
atomic64_add(bytes, &discard_ctl->discard_bytes_saved);
entry->offset = offset + bytes;
WARN_ON(entry->bytes < bytes + align_gap_len);
entry->bytes -= bytes + align_gap_len;
if (!entry->bytes)
kmem_cache_free(btrfs_free_space_cachep, entry);
else
link_free_space(ctl, entry);
}
out:
btrfs_discard_update_discardable(block_group);
spin_unlock(&ctl->tree_lock);
if (align_gap_len)
__btrfs_add_free_space(block_group, align_gap, align_gap_len,
align_gap_trim_state);
return ret;
}
/*
* given a cluster, put all of its extents back into the free space
* cache. If a block group is passed, this function will only free
* a cluster that belongs to the passed block group.
*
* Otherwise, it'll get a reference on the block group pointed to by the
* cluster and remove the cluster from it.
*/
void btrfs_return_cluster_to_free_space(
struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster)
{
struct btrfs_free_space_ctl *ctl;
/* first, get a safe pointer to the block group */
spin_lock(&cluster->lock);
if (!block_group) {
block_group = cluster->block_group;
if (!block_group) {
spin_unlock(&cluster->lock);
return;
}
} else if (cluster->block_group != block_group) {
/* someone else has already freed it don't redo their work */
spin_unlock(&cluster->lock);
return;
}
btrfs_get_block_group(block_group);
spin_unlock(&cluster->lock);
ctl = block_group->free_space_ctl;
/* now return any extents the cluster had on it */
spin_lock(&ctl->tree_lock);
__btrfs_return_cluster_to_free_space(block_group, cluster);
spin_unlock(&ctl->tree_lock);
btrfs_discard_queue_work(&block_group->fs_info->discard_ctl, block_group);
/* finally drop our ref */
btrfs_put_block_group(block_group);
}
static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
struct btrfs_free_space *entry,
u64 bytes, u64 min_start,
u64 *max_extent_size)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
int err;
u64 search_start = cluster->window_start;
u64 search_bytes = bytes;
u64 ret = 0;
search_start = min_start;
search_bytes = bytes;
err = search_bitmap(ctl, entry, &search_start, &search_bytes, true);
if (err) {
*max_extent_size = max(get_max_extent_size(entry),
*max_extent_size);
return 0;
}
ret = search_start;
bitmap_clear_bits(ctl, entry, ret, bytes, false);
return ret;
}
/*
* given a cluster, try to allocate 'bytes' from it, returns 0
* if it couldn't find anything suitably large, or a logical disk offset
* if things worked out
*/
u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster, u64 bytes,
u64 min_start, u64 *max_extent_size)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_discard_ctl *discard_ctl =
&block_group->fs_info->discard_ctl;
struct btrfs_free_space *entry = NULL;
struct rb_node *node;
u64 ret = 0;
ASSERT(!btrfs_is_zoned(block_group->fs_info));
spin_lock(&cluster->lock);
if (bytes > cluster->max_size)
goto out;
if (cluster->block_group != block_group)
goto out;
node = rb_first(&cluster->root);
if (!node)
goto out;
entry = rb_entry(node, struct btrfs_free_space, offset_index);
while (1) {
if (entry->bytes < bytes)
*max_extent_size = max(get_max_extent_size(entry),
*max_extent_size);
if (entry->bytes < bytes ||
(!entry->bitmap && entry->offset < min_start)) {
node = rb_next(&entry->offset_index);
if (!node)
break;
entry = rb_entry(node, struct btrfs_free_space,
offset_index);
continue;
}
if (entry->bitmap) {
ret = btrfs_alloc_from_bitmap(block_group,
cluster, entry, bytes,
cluster->window_start,
max_extent_size);
if (ret == 0) {
node = rb_next(&entry->offset_index);
if (!node)
break;
entry = rb_entry(node, struct btrfs_free_space,
offset_index);
continue;
}
cluster->window_start += bytes;
} else {
ret = entry->offset;
entry->offset += bytes;
entry->bytes -= bytes;
}
break;
}
out:
spin_unlock(&cluster->lock);
if (!ret)
return 0;
spin_lock(&ctl->tree_lock);
if (!btrfs_free_space_trimmed(entry))
atomic64_add(bytes, &discard_ctl->discard_bytes_saved);
ctl->free_space -= bytes;
if (!entry->bitmap && !btrfs_free_space_trimmed(entry))
ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes;
spin_lock(&cluster->lock);
if (entry->bytes == 0) {
rb_erase(&entry->offset_index, &cluster->root);
ctl->free_extents--;
if (entry->bitmap) {
kmem_cache_free(btrfs_free_space_bitmap_cachep,
entry->bitmap);
ctl->total_bitmaps--;
recalculate_thresholds(ctl);
} else if (!btrfs_free_space_trimmed(entry)) {
ctl->discardable_extents[BTRFS_STAT_CURR]--;
}
kmem_cache_free(btrfs_free_space_cachep, entry);
}
spin_unlock(&cluster->lock);
spin_unlock(&ctl->tree_lock);
return ret;
}
static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_space *entry,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes,
u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
unsigned long next_zero;
unsigned long i;
unsigned long want_bits;
unsigned long min_bits;
unsigned long found_bits;
unsigned long max_bits = 0;
unsigned long start = 0;
unsigned long total_found = 0;
int ret;
i = offset_to_bit(entry->offset, ctl->unit,
max_t(u64, offset, entry->offset));
want_bits = bytes_to_bits(bytes, ctl->unit);
min_bits = bytes_to_bits(min_bytes, ctl->unit);
/*
* Don't bother looking for a cluster in this bitmap if it's heavily
* fragmented.
*/
if (entry->max_extent_size &&
entry->max_extent_size < cont1_bytes)
return -ENOSPC;
again:
found_bits = 0;
for_each_set_bit_from(i, entry->bitmap, BITS_PER_BITMAP) {
next_zero = find_next_zero_bit(entry->bitmap,
BITS_PER_BITMAP, i);
if (next_zero - i >= min_bits) {
found_bits = next_zero - i;
if (found_bits > max_bits)
max_bits = found_bits;
break;
}
if (next_zero - i > max_bits)
max_bits = next_zero - i;
i = next_zero;
}
if (!found_bits) {
entry->max_extent_size = (u64)max_bits * ctl->unit;
return -ENOSPC;
}
if (!total_found) {
start = i;
cluster->max_size = 0;
}
total_found += found_bits;
if (cluster->max_size < found_bits * ctl->unit)
cluster->max_size = found_bits * ctl->unit;
if (total_found < want_bits || cluster->max_size < cont1_bytes) {
i = next_zero + 1;
goto again;
}
cluster->window_start = start * ctl->unit + entry->offset;
rb_erase(&entry->offset_index, &ctl->free_space_offset);
rb_erase_cached(&entry->bytes_index, &ctl->free_space_bytes);
/*
* We need to know if we're currently on the normal space index when we
* manipulate the bitmap so that we know we need to remove and re-insert
* it into the space_index tree. Clear the bytes_index node here so the
* bitmap manipulation helpers know not to mess with the space_index
* until this bitmap entry is added back into the normal cache.
*/
RB_CLEAR_NODE(&entry->bytes_index);
ret = tree_insert_offset(&cluster->root, entry->offset,
&entry->offset_index, 1);
ASSERT(!ret); /* -EEXIST; Logic error */
trace_btrfs_setup_cluster(block_group, cluster,
total_found * ctl->unit, 1);
return 0;
}
/*
* This searches the block group for just extents to fill the cluster with.
* Try to find a cluster with at least bytes total bytes, at least one
* extent of cont1_bytes, and other clusters of at least min_bytes.
*/
static noinline int
setup_cluster_no_bitmap(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *first = NULL;
struct btrfs_free_space *entry = NULL;
struct btrfs_free_space *last;
struct rb_node *node;
u64 window_free;
u64 max_extent;
u64 total_size = 0;
entry = tree_search_offset(ctl, offset, 0, 1);
if (!entry)
return -ENOSPC;
/*
* We don't want bitmaps, so just move along until we find a normal
* extent entry.
*/
while (entry->bitmap || entry->bytes < min_bytes) {
if (entry->bitmap && list_empty(&entry->list))
list_add_tail(&entry->list, bitmaps);
node = rb_next(&entry->offset_index);
if (!node)
return -ENOSPC;
entry = rb_entry(node, struct btrfs_free_space, offset_index);
}
window_free = entry->bytes;
max_extent = entry->bytes;
first = entry;
last = entry;
for (node = rb_next(&entry->offset_index); node;
node = rb_next(&entry->offset_index)) {
entry = rb_entry(node, struct btrfs_free_space, offset_index);
if (entry->bitmap) {
if (list_empty(&entry->list))
list_add_tail(&entry->list, bitmaps);
continue;
}
if (entry->bytes < min_bytes)
continue;
last = entry;
window_free += entry->bytes;
if (entry->bytes > max_extent)
max_extent = entry->bytes;
}
if (window_free < bytes || max_extent < cont1_bytes)
return -ENOSPC;
cluster->window_start = first->offset;
node = &first->offset_index;
/*
* now we've found our entries, pull them out of the free space
* cache and put them into the cluster rbtree
*/
do {
int ret;
entry = rb_entry(node, struct btrfs_free_space, offset_index);
node = rb_next(&entry->offset_index);
if (entry->bitmap || entry->bytes < min_bytes)
continue;
rb_erase(&entry->offset_index, &ctl->free_space_offset);
rb_erase_cached(&entry->bytes_index, &ctl->free_space_bytes);
ret = tree_insert_offset(&cluster->root, entry->offset,
&entry->offset_index, 0);
total_size += entry->bytes;
ASSERT(!ret); /* -EEXIST; Logic error */
} while (node && entry != last);
cluster->max_size = max_extent;
trace_btrfs_setup_cluster(block_group, cluster, total_size, 0);
return 0;
}
/*
* This specifically looks for bitmaps that may work in the cluster, we assume
* that we have already failed to find extents that will work.
*/
static noinline int
setup_cluster_bitmap(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry = NULL;
int ret = -ENOSPC;
u64 bitmap_offset = offset_to_bitmap(ctl, offset);
if (ctl->total_bitmaps == 0)
return -ENOSPC;
/*
* The bitmap that covers offset won't be in the list unless offset
* is just its start offset.
*/
if (!list_empty(bitmaps))
entry = list_first_entry(bitmaps, struct btrfs_free_space, list);
if (!entry || entry->offset != bitmap_offset) {
entry = tree_search_offset(ctl, bitmap_offset, 1, 0);
if (entry && list_empty(&entry->list))
list_add(&entry->list, bitmaps);
}
list_for_each_entry(entry, bitmaps, list) {
if (entry->bytes < bytes)
continue;
ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
bytes, cont1_bytes, min_bytes);
if (!ret)
return 0;
}
/*
* The bitmaps list has all the bitmaps that record free space
* starting after offset, so no more search is required.
*/
return -ENOSPC;
}
/*
* here we try to find a cluster of blocks in a block group. The goal
* is to find at least bytes+empty_size.
* We might not find them all in one contiguous area.
*
* returns zero and sets up cluster if things worked out, otherwise
* it returns -enospc
*/
int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes, u64 empty_size)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry, *tmp;
LIST_HEAD(bitmaps);
u64 min_bytes;
u64 cont1_bytes;
int ret;
/*
* Choose the minimum extent size we'll require for this
* cluster. For SSD_SPREAD, don't allow any fragmentation.
* For metadata, allow allocates with smaller extents. For
* data, keep it dense.
*/
if (btrfs_test_opt(fs_info, SSD_SPREAD)) {
cont1_bytes = bytes + empty_size;
min_bytes = cont1_bytes;
} else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
cont1_bytes = bytes;
min_bytes = fs_info->sectorsize;
} else {
cont1_bytes = max(bytes, (bytes + empty_size) >> 2);
min_bytes = fs_info->sectorsize;
}
spin_lock(&ctl->tree_lock);
/*
* If we know we don't have enough space to make a cluster don't even
* bother doing all the work to try and find one.
*/
if (ctl->free_space < bytes) {
spin_unlock(&ctl->tree_lock);
return -ENOSPC;
}
spin_lock(&cluster->lock);
/* someone already found a cluster, hooray */
if (cluster->block_group) {
ret = 0;
goto out;
}
trace_btrfs_find_cluster(block_group, offset, bytes, empty_size,
min_bytes);
ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
bytes + empty_size,
cont1_bytes, min_bytes);
if (ret)
ret = setup_cluster_bitmap(block_group, cluster, &bitmaps,
offset, bytes + empty_size,
cont1_bytes, min_bytes);
/* Clear our temporary list */
list_for_each_entry_safe(entry, tmp, &bitmaps, list)
list_del_init(&entry->list);
if (!ret) {
btrfs_get_block_group(block_group);
list_add_tail(&cluster->block_group_list,
&block_group->cluster_list);
cluster->block_group = block_group;
} else {
trace_btrfs_failed_cluster_setup(block_group);
}
out:
spin_unlock(&cluster->lock);
spin_unlock(&ctl->tree_lock);
return ret;
}
/*
* simple code to zero out a cluster
*/
void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
{
spin_lock_init(&cluster->lock);
spin_lock_init(&cluster->refill_lock);
cluster->root = RB_ROOT;
cluster->max_size = 0;
cluster->fragmented = false;
INIT_LIST_HEAD(&cluster->block_group_list);
cluster->block_group = NULL;
}
static int do_trimming(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 bytes,
u64 reserved_start, u64 reserved_bytes,
enum btrfs_trim_state reserved_trim_state,
struct btrfs_trim_range *trim_entry)
{
struct btrfs_space_info *space_info = block_group->space_info;
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
int ret;
int update = 0;
const u64 end = start + bytes;
const u64 reserved_end = reserved_start + reserved_bytes;
enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
u64 trimmed = 0;
spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
if (!block_group->ro) {
block_group->reserved += reserved_bytes;
space_info->bytes_reserved += reserved_bytes;
update = 1;
}
spin_unlock(&block_group->lock);
spin_unlock(&space_info->lock);
ret = btrfs_discard_extent(fs_info, start, bytes, &trimmed);
if (!ret) {
*total_trimmed += trimmed;
trim_state = BTRFS_TRIM_STATE_TRIMMED;
}
mutex_lock(&ctl->cache_writeout_mutex);
if (reserved_start < start)
__btrfs_add_free_space(block_group, reserved_start,
start - reserved_start,
reserved_trim_state);
if (start + bytes < reserved_start + reserved_bytes)
__btrfs_add_free_space(block_group, end, reserved_end - end,
reserved_trim_state);
__btrfs_add_free_space(block_group, start, bytes, trim_state);
list_del(&trim_entry->list);
mutex_unlock(&ctl->cache_writeout_mutex);
if (update) {
spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
if (block_group->ro)
space_info->bytes_readonly += reserved_bytes;
block_group->reserved -= reserved_bytes;
space_info->bytes_reserved -= reserved_bytes;
spin_unlock(&block_group->lock);
spin_unlock(&space_info->lock);
}
return ret;
}
/*
* If @async is set, then we will trim 1 region and return.
*/
static int trim_no_bitmap(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 end, u64 minlen,
bool async)
{
struct btrfs_discard_ctl *discard_ctl =
&block_group->fs_info->discard_ctl;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
struct rb_node *node;
int ret = 0;
u64 extent_start;
u64 extent_bytes;
enum btrfs_trim_state extent_trim_state;
u64 bytes;
const u64 max_discard_size = READ_ONCE(discard_ctl->max_discard_size);
while (start < end) {
struct btrfs_trim_range trim_entry;
mutex_lock(&ctl->cache_writeout_mutex);
spin_lock(&ctl->tree_lock);
if (ctl->free_space < minlen)
goto out_unlock;
entry = tree_search_offset(ctl, start, 0, 1);
if (!entry)
goto out_unlock;
/* Skip bitmaps and if async, already trimmed entries */
while (entry->bitmap ||
(async && btrfs_free_space_trimmed(entry))) {
node = rb_next(&entry->offset_index);
if (!node)
goto out_unlock;
entry = rb_entry(node, struct btrfs_free_space,
offset_index);
}
if (entry->offset >= end)
goto out_unlock;
extent_start = entry->offset;
extent_bytes = entry->bytes;
extent_trim_state = entry->trim_state;
if (async) {
start = entry->offset;
bytes = entry->bytes;
if (bytes < minlen) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
goto next;
}
unlink_free_space(ctl, entry, true);
/*
* Let bytes = BTRFS_MAX_DISCARD_SIZE + X.
* If X < BTRFS_ASYNC_DISCARD_MIN_FILTER, we won't trim
* X when we come back around. So trim it now.
*/
if (max_discard_size &&
bytes >= (max_discard_size +
BTRFS_ASYNC_DISCARD_MIN_FILTER)) {
bytes = max_discard_size;
extent_bytes = max_discard_size;
entry->offset += max_discard_size;
entry->bytes -= max_discard_size;
link_free_space(ctl, entry);
} else {
kmem_cache_free(btrfs_free_space_cachep, entry);
}
} else {
start = max(start, extent_start);
bytes = min(extent_start + extent_bytes, end) - start;
if (bytes < minlen) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
goto next;
}
unlink_free_space(ctl, entry, true);
kmem_cache_free(btrfs_free_space_cachep, entry);
}
spin_unlock(&ctl->tree_lock);
trim_entry.start = extent_start;
trim_entry.bytes = extent_bytes;
list_add_tail(&trim_entry.list, &ctl->trimming_ranges);
mutex_unlock(&ctl->cache_writeout_mutex);
ret = do_trimming(block_group, total_trimmed, start, bytes,
extent_start, extent_bytes, extent_trim_state,
&trim_entry);
if (ret) {
block_group->discard_cursor = start + bytes;
break;
}
next:
start += bytes;
block_group->discard_cursor = start;
if (async && *total_trimmed)
break;
if (fatal_signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
cond_resched();
}
return ret;
out_unlock:
block_group->discard_cursor = btrfs_block_group_end(block_group);
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
return ret;
}
/*
* If we break out of trimming a bitmap prematurely, we should reset the
* trimming bit. In a rather contrieved case, it's possible to race here so
* reset the state to BTRFS_TRIM_STATE_UNTRIMMED.
*
* start = start of bitmap
* end = near end of bitmap
*
* Thread 1: Thread 2:
* trim_bitmaps(start)
* trim_bitmaps(end)
* end_trimming_bitmap()
* reset_trimming_bitmap()
*/
static void reset_trimming_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset)
{
struct btrfs_free_space *entry;
spin_lock(&ctl->tree_lock);
entry = tree_search_offset(ctl, offset, 1, 0);
if (entry) {
if (btrfs_free_space_trimmed(entry)) {
ctl->discardable_extents[BTRFS_STAT_CURR] +=
entry->bitmap_extents;
ctl->discardable_bytes[BTRFS_STAT_CURR] += entry->bytes;
}
entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
}
spin_unlock(&ctl->tree_lock);
}
static void end_trimming_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *entry)
{
if (btrfs_free_space_trimming_bitmap(entry)) {
entry->trim_state = BTRFS_TRIM_STATE_TRIMMED;
ctl->discardable_extents[BTRFS_STAT_CURR] -=
entry->bitmap_extents;
ctl->discardable_bytes[BTRFS_STAT_CURR] -= entry->bytes;
}
}
/*
* If @async is set, then we will trim 1 region and return.
*/
static int trim_bitmaps(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 end, u64 minlen,
u64 maxlen, bool async)
{
struct btrfs_discard_ctl *discard_ctl =
&block_group->fs_info->discard_ctl;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
int ret = 0;
int ret2;
u64 bytes;
u64 offset = offset_to_bitmap(ctl, start);
const u64 max_discard_size = READ_ONCE(discard_ctl->max_discard_size);
while (offset < end) {
bool next_bitmap = false;
struct btrfs_trim_range trim_entry;
mutex_lock(&ctl->cache_writeout_mutex);
spin_lock(&ctl->tree_lock);
if (ctl->free_space < minlen) {
block_group->discard_cursor =
btrfs_block_group_end(block_group);
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
break;
}
entry = tree_search_offset(ctl, offset, 1, 0);
/*
* Bitmaps are marked trimmed lossily now to prevent constant
* discarding of the same bitmap (the reason why we are bound
* by the filters). So, retrim the block group bitmaps when we
* are preparing to punt to the unused_bgs list. This uses
* @minlen to determine if we are in BTRFS_DISCARD_INDEX_UNUSED
* which is the only discard index which sets minlen to 0.
*/
if (!entry || (async && minlen && start == offset &&
btrfs_free_space_trimmed(entry))) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
next_bitmap = true;
goto next;
}
/*
* Async discard bitmap trimming begins at by setting the start
* to be key.objectid and the offset_to_bitmap() aligns to the
* start of the bitmap. This lets us know we are fully
* scanning the bitmap rather than only some portion of it.
*/
if (start == offset)
entry->trim_state = BTRFS_TRIM_STATE_TRIMMING;
bytes = minlen;
ret2 = search_bitmap(ctl, entry, &start, &bytes, false);
if (ret2 || start >= end) {
/*
* We lossily consider a bitmap trimmed if we only skip
* over regions <= BTRFS_ASYNC_DISCARD_MIN_FILTER.
*/
if (ret2 && minlen <= BTRFS_ASYNC_DISCARD_MIN_FILTER)
end_trimming_bitmap(ctl, entry);
else
entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
next_bitmap = true;
goto next;
}
/*
* We already trimmed a region, but are using the locking above
* to reset the trim_state.
*/
if (async && *total_trimmed) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
goto out;
}
bytes = min(bytes, end - start);
if (bytes < minlen || (async && maxlen && bytes > maxlen)) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
goto next;
}
/*
* Let bytes = BTRFS_MAX_DISCARD_SIZE + X.
* If X < @minlen, we won't trim X when we come back around.
* So trim it now. We differ here from trimming extents as we
* don't keep individual state per bit.
*/
if (async &&
max_discard_size &&
bytes > (max_discard_size + minlen))
bytes = max_discard_size;
bitmap_clear_bits(ctl, entry, start, bytes, true);
if (entry->bytes == 0)
free_bitmap(ctl, entry);
spin_unlock(&ctl->tree_lock);
trim_entry.start = start;
trim_entry.bytes = bytes;
list_add_tail(&trim_entry.list, &ctl->trimming_ranges);
mutex_unlock(&ctl->cache_writeout_mutex);
ret = do_trimming(block_group, total_trimmed, start, bytes,
start, bytes, 0, &trim_entry);
if (ret) {
reset_trimming_bitmap(ctl, offset);
block_group->discard_cursor =
btrfs_block_group_end(block_group);
break;
}
next:
if (next_bitmap) {
offset += BITS_PER_BITMAP * ctl->unit;
start = offset;
} else {
start += bytes;
}
block_group->discard_cursor = start;
if (fatal_signal_pending(current)) {
if (start != offset)
reset_trimming_bitmap(ctl, offset);
ret = -ERESTARTSYS;
break;
}
cond_resched();
}
if (offset >= end)
block_group->discard_cursor = end;
out:
return ret;
}
int btrfs_trim_block_group(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
int ret;
u64 rem = 0;
ASSERT(!btrfs_is_zoned(block_group->fs_info));
*trimmed = 0;
spin_lock(&block_group->lock);
if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
return 0;
}
btrfs_freeze_block_group(block_group);
spin_unlock(&block_group->lock);
ret = trim_no_bitmap(block_group, trimmed, start, end, minlen, false);
if (ret)
goto out;
ret = trim_bitmaps(block_group, trimmed, start, end, minlen, 0, false);
div64_u64_rem(end, BITS_PER_BITMAP * ctl->unit, &rem);
/* If we ended in the middle of a bitmap, reset the trimming flag */
if (rem)
reset_trimming_bitmap(ctl, offset_to_bitmap(ctl, end));
out:
btrfs_unfreeze_block_group(block_group);
return ret;
}
int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen,
bool async)
{
int ret;
*trimmed = 0;
spin_lock(&block_group->lock);
if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
return 0;
}
btrfs_freeze_block_group(block_group);
spin_unlock(&block_group->lock);
ret = trim_no_bitmap(block_group, trimmed, start, end, minlen, async);
btrfs_unfreeze_block_group(block_group);
return ret;
}
int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen,
u64 maxlen, bool async)
{
int ret;
*trimmed = 0;
spin_lock(&block_group->lock);
if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
return 0;
}
btrfs_freeze_block_group(block_group);
spin_unlock(&block_group->lock);
ret = trim_bitmaps(block_group, trimmed, start, end, minlen, maxlen,
async);
btrfs_unfreeze_block_group(block_group);
return ret;
}
bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info)
{
return btrfs_super_cache_generation(fs_info->super_copy);
}
static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans)
{
struct btrfs_block_group *block_group;
struct rb_node *node;
int ret = 0;
btrfs_info(fs_info, "cleaning free space cache v1");
node = rb_first_cached(&fs_info->block_group_cache_tree);
while (node) {
block_group = rb_entry(node, struct btrfs_block_group, cache_node);
ret = btrfs_remove_free_space_inode(trans, NULL, block_group);
if (ret)
goto out;
node = rb_next(node);
}
out:
return ret;
}
int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active)
{
struct btrfs_trans_handle *trans;
int ret;
/*
* update_super_roots will appropriately set or unset
* super_copy->cache_generation based on SPACE_CACHE and
* BTRFS_FS_CLEANUP_SPACE_CACHE_V1. For this reason, we need a
* transaction commit whether we are enabling space cache v1 and don't
* have any other work to do, or are disabling it and removing free
* space inodes.
*/
trans = btrfs_start_transaction(fs_info->tree_root, 0);
if (IS_ERR(trans))
return PTR_ERR(trans);
if (!active) {
set_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags);
ret = cleanup_free_space_cache_v1(fs_info, trans);
if (ret) {
btrfs_abort_transaction(trans, ret);
btrfs_end_transaction(trans);
goto out;
}
}
ret = btrfs_commit_transaction(trans);
out:
clear_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags);
return ret;
}
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/*
* Use this if you need to make a bitmap or extent entry specifically, it
* doesn't do any of the merging that add_free_space does, this acts a lot like
* how the free space cache loading stuff works, so you can get really weird
* configurations.
*/
int test_add_free_space_entry(struct btrfs_block_group *cache,
u64 offset, u64 bytes, bool bitmap)
{
struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
struct btrfs_free_space *info = NULL, *bitmap_info;
void *map = NULL;
enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_TRIMMED;
u64 bytes_added;
int ret;
again:
if (!info) {
info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
if (!info)
return -ENOMEM;
}
if (!bitmap) {
spin_lock(&ctl->tree_lock);
info->offset = offset;
info->bytes = bytes;
info->max_extent_size = 0;
ret = link_free_space(ctl, info);
spin_unlock(&ctl->tree_lock);
if (ret)
kmem_cache_free(btrfs_free_space_cachep, info);
return ret;
}
if (!map) {
map = kmem_cache_zalloc(btrfs_free_space_bitmap_cachep, GFP_NOFS);
if (!map) {
kmem_cache_free(btrfs_free_space_cachep, info);
return -ENOMEM;
}
}
spin_lock(&ctl->tree_lock);
bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!bitmap_info) {
info->bitmap = map;
map = NULL;
add_new_bitmap(ctl, info, offset);
bitmap_info = info;
info = NULL;
}
bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes,
trim_state);
bytes -= bytes_added;
offset += bytes_added;
spin_unlock(&ctl->tree_lock);
if (bytes)
goto again;
if (info)
kmem_cache_free(btrfs_free_space_cachep, info);
if (map)
kmem_cache_free(btrfs_free_space_bitmap_cachep, map);
return 0;
}
/*
* Checks to see if the given range is in the free space cache. This is really
* just used to check the absence of space, so if there is free space in the
* range at all we will return 1.
*/
int test_check_exists(struct btrfs_block_group *cache,
u64 offset, u64 bytes)
{
struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
struct btrfs_free_space *info;
int ret = 0;
spin_lock(&ctl->tree_lock);
info = tree_search_offset(ctl, offset, 0, 0);
if (!info) {
info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!info)
goto out;
}
have_info:
if (info->bitmap) {
u64 bit_off, bit_bytes;
struct rb_node *n;
struct btrfs_free_space *tmp;
bit_off = offset;
bit_bytes = ctl->unit;
ret = search_bitmap(ctl, info, &bit_off, &bit_bytes, false);
if (!ret) {
if (bit_off == offset) {
ret = 1;
goto out;
} else if (bit_off > offset &&
offset + bytes > bit_off) {
ret = 1;
goto out;
}
}
n = rb_prev(&info->offset_index);
while (n) {
tmp = rb_entry(n, struct btrfs_free_space,
offset_index);
if (tmp->offset + tmp->bytes < offset)
break;
if (offset + bytes < tmp->offset) {
n = rb_prev(&tmp->offset_index);
continue;
}
info = tmp;
goto have_info;
}
n = rb_next(&info->offset_index);
while (n) {
tmp = rb_entry(n, struct btrfs_free_space,
offset_index);
if (offset + bytes < tmp->offset)
break;
if (tmp->offset + tmp->bytes < offset) {
n = rb_next(&tmp->offset_index);
continue;
}
info = tmp;
goto have_info;
}
ret = 0;
goto out;
}
if (info->offset == offset) {
ret = 1;
goto out;
}
if (offset > info->offset && offset < info->offset + info->bytes)
ret = 1;
out:
spin_unlock(&ctl->tree_lock);
return ret;
}
#endif /* CONFIG_BTRFS_FS_RUN_SANITY_TESTS */
|