summaryrefslogtreecommitdiffstats
path: root/fs/ceph/caps.c
blob: de17bb232ff8d30906c53f34248ce99ea566562a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
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
#include <linux/ceph/ceph_debug.h>

#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/wait.h>
#include <linux/writeback.h>

#include "super.h"
#include "mds_client.h"
#include "cache.h"
#include <linux/ceph/decode.h>
#include <linux/ceph/messenger.h>

/*
 * Capability management
 *
 * The Ceph metadata servers control client access to inode metadata
 * and file data by issuing capabilities, granting clients permission
 * to read and/or write both inode field and file data to OSDs
 * (storage nodes).  Each capability consists of a set of bits
 * indicating which operations are allowed.
 *
 * If the client holds a *_SHARED cap, the client has a coherent value
 * that can be safely read from the cached inode.
 *
 * In the case of a *_EXCL (exclusive) or FILE_WR capabilities, the
 * client is allowed to change inode attributes (e.g., file size,
 * mtime), note its dirty state in the ceph_cap, and asynchronously
 * flush that metadata change to the MDS.
 *
 * In the event of a conflicting operation (perhaps by another
 * client), the MDS will revoke the conflicting client capabilities.
 *
 * In order for a client to cache an inode, it must hold a capability
 * with at least one MDS server.  When inodes are released, release
 * notifications are batched and periodically sent en masse to the MDS
 * cluster to release server state.
 */


/*
 * Generate readable cap strings for debugging output.
 */
#define MAX_CAP_STR 20
static char cap_str[MAX_CAP_STR][40];
static DEFINE_SPINLOCK(cap_str_lock);
static int last_cap_str;

static char *gcap_string(char *s, int c)
{
	if (c & CEPH_CAP_GSHARED)
		*s++ = 's';
	if (c & CEPH_CAP_GEXCL)
		*s++ = 'x';
	if (c & CEPH_CAP_GCACHE)
		*s++ = 'c';
	if (c & CEPH_CAP_GRD)
		*s++ = 'r';
	if (c & CEPH_CAP_GWR)
		*s++ = 'w';
	if (c & CEPH_CAP_GBUFFER)
		*s++ = 'b';
	if (c & CEPH_CAP_GLAZYIO)
		*s++ = 'l';
	return s;
}

const char *ceph_cap_string(int caps)
{
	int i;
	char *s;
	int c;

	spin_lock(&cap_str_lock);
	i = last_cap_str++;
	if (last_cap_str == MAX_CAP_STR)
		last_cap_str = 0;
	spin_unlock(&cap_str_lock);

	s = cap_str[i];

	if (caps & CEPH_CAP_PIN)
		*s++ = 'p';

	c = (caps >> CEPH_CAP_SAUTH) & 3;
	if (c) {
		*s++ = 'A';
		s = gcap_string(s, c);
	}

	c = (caps >> CEPH_CAP_SLINK) & 3;
	if (c) {
		*s++ = 'L';
		s = gcap_string(s, c);
	}

	c = (caps >> CEPH_CAP_SXATTR) & 3;
	if (c) {
		*s++ = 'X';
		s = gcap_string(s, c);
	}

	c = caps >> CEPH_CAP_SFILE;
	if (c) {
		*s++ = 'F';
		s = gcap_string(s, c);
	}

	if (s == cap_str[i])
		*s++ = '-';
	*s = 0;
	return cap_str[i];
}

void ceph_caps_init(struct ceph_mds_client *mdsc)
{
	INIT_LIST_HEAD(&mdsc->caps_list);
	spin_lock_init(&mdsc->caps_list_lock);
}

void ceph_caps_finalize(struct ceph_mds_client *mdsc)
{
	struct ceph_cap *cap;

	spin_lock(&mdsc->caps_list_lock);
	while (!list_empty(&mdsc->caps_list)) {
		cap = list_first_entry(&mdsc->caps_list,
				       struct ceph_cap, caps_item);
		list_del(&cap->caps_item);
		kmem_cache_free(ceph_cap_cachep, cap);
	}
	mdsc->caps_total_count = 0;
	mdsc->caps_avail_count = 0;
	mdsc->caps_use_count = 0;
	mdsc->caps_reserve_count = 0;
	mdsc->caps_min_count = 0;
	spin_unlock(&mdsc->caps_list_lock);
}

void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta)
{
	spin_lock(&mdsc->caps_list_lock);
	mdsc->caps_min_count += delta;
	BUG_ON(mdsc->caps_min_count < 0);
	spin_unlock(&mdsc->caps_list_lock);
}

void ceph_reserve_caps(struct ceph_mds_client *mdsc,
		      struct ceph_cap_reservation *ctx, int need)
{
	int i;
	struct ceph_cap *cap;
	int have;
	int alloc = 0;
	LIST_HEAD(newcaps);

	dout("reserve caps ctx=%p need=%d\n", ctx, need);

	/* first reserve any caps that are already allocated */
	spin_lock(&mdsc->caps_list_lock);
	if (mdsc->caps_avail_count >= need)
		have = need;
	else
		have = mdsc->caps_avail_count;
	mdsc->caps_avail_count -= have;
	mdsc->caps_reserve_count += have;
	BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
					 mdsc->caps_reserve_count +
					 mdsc->caps_avail_count);
	spin_unlock(&mdsc->caps_list_lock);

	for (i = have; i < need; i++) {
		cap = kmem_cache_alloc(ceph_cap_cachep, GFP_NOFS);
		if (!cap)
			break;
		list_add(&cap->caps_item, &newcaps);
		alloc++;
	}
	/* we didn't manage to reserve as much as we needed */
	if (have + alloc != need)
		pr_warn("reserve caps ctx=%p ENOMEM need=%d got=%d\n",
			ctx, need, have + alloc);

	spin_lock(&mdsc->caps_list_lock);
	mdsc->caps_total_count += alloc;
	mdsc->caps_reserve_count += alloc;
	list_splice(&newcaps, &mdsc->caps_list);

	BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
					 mdsc->caps_reserve_count +
					 mdsc->caps_avail_count);
	spin_unlock(&mdsc->caps_list_lock);

	ctx->count = need;
	dout("reserve caps ctx=%p %d = %d used + %d resv + %d avail\n",
	     ctx, mdsc->caps_total_count, mdsc->caps_use_count,
	     mdsc->caps_reserve_count, mdsc->caps_avail_count);
}

int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
			struct ceph_cap_reservation *ctx)
{
	dout("unreserve caps ctx=%p count=%d\n", ctx, ctx->count);
	if (ctx->count) {
		spin_lock(&mdsc->caps_list_lock);
		BUG_ON(mdsc->caps_reserve_count < ctx->count);
		mdsc->caps_reserve_count -= ctx->count;
		mdsc->caps_avail_count += ctx->count;
		ctx->count = 0;
		dout("unreserve caps %d = %d used + %d resv + %d avail\n",
		     mdsc->caps_total_count, mdsc->caps_use_count,
		     mdsc->caps_reserve_count, mdsc->caps_avail_count);
		BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
						 mdsc->caps_reserve_count +
						 mdsc->caps_avail_count);
		spin_unlock(&mdsc->caps_list_lock);
	}
	return 0;
}

struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
			      struct ceph_cap_reservation *ctx)
{
	struct ceph_cap *cap = NULL;

	/* temporary, until we do something about cap import/export */
	if (!ctx) {
		cap = kmem_cache_alloc(ceph_cap_cachep, GFP_NOFS);
		if (cap) {
			spin_lock(&mdsc->caps_list_lock);
			mdsc->caps_use_count++;
			mdsc->caps_total_count++;
			spin_unlock(&mdsc->caps_list_lock);
		}
		return cap;
	}

	spin_lock(&mdsc->caps_list_lock);
	dout("get_cap ctx=%p (%d) %d = %d used + %d resv + %d avail\n",
	     ctx, ctx->count, mdsc->caps_total_count, mdsc->caps_use_count,
	     mdsc->caps_reserve_count, mdsc->caps_avail_count);
	BUG_ON(!ctx->count);
	BUG_ON(ctx->count > mdsc->caps_reserve_count);
	BUG_ON(list_empty(&mdsc->caps_list));

	ctx->count--;
	mdsc->caps_reserve_count--;
	mdsc->caps_use_count++;

	cap = list_first_entry(&mdsc->caps_list, struct ceph_cap, caps_item);
	list_del(&cap->caps_item);

	BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
	       mdsc->caps_reserve_count + mdsc->caps_avail_count);
	spin_unlock(&mdsc->caps_list_lock);
	return cap;
}

void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap)
{
	spin_lock(&mdsc->caps_list_lock);
	dout("put_cap %p %d = %d used + %d resv + %d avail\n",
	     cap, mdsc->caps_total_count, mdsc->caps_use_count,
	     mdsc->caps_reserve_count, mdsc->caps_avail_count);
	mdsc->caps_use_count--;
	/*
	 * Keep some preallocated caps around (ceph_min_count), to
	 * avoid lots of free/alloc churn.
	 */
	if (mdsc->caps_avail_count >= mdsc->caps_reserve_count +
				      mdsc->caps_min_count) {
		mdsc->caps_total_count--;
		kmem_cache_free(ceph_cap_cachep, cap);
	} else {
		mdsc->caps_avail_count++;
		list_add(&cap->caps_item, &mdsc->caps_list);
	}

	BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
	       mdsc->caps_reserve_count + mdsc->caps_avail_count);
	spin_unlock(&mdsc->caps_list_lock);
}

void ceph_reservation_status(struct ceph_fs_client *fsc,
			     int *total, int *avail, int *used, int *reserved,
			     int *min)
{
	struct ceph_mds_client *mdsc = fsc->mdsc;

	if (total)
		*total = mdsc->caps_total_count;
	if (avail)
		*avail = mdsc->caps_avail_count;
	if (used)
		*used = mdsc->caps_use_count;
	if (reserved)
		*reserved = mdsc->caps_reserve_count;
	if (min)
		*min = mdsc->caps_min_count;
}

/*
 * Find ceph_cap for given mds, if any.
 *
 * Called with i_ceph_lock held.
 */
static struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds)
{
	struct ceph_cap *cap;
	struct rb_node *n = ci->i_caps.rb_node;

	while (n) {
		cap = rb_entry(n, struct ceph_cap, ci_node);
		if (mds < cap->mds)
			n = n->rb_left;
		else if (mds > cap->mds)
			n = n->rb_right;
		else
			return cap;
	}
	return NULL;
}

struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci, int mds)
{
	struct ceph_cap *cap;

	spin_lock(&ci->i_ceph_lock);
	cap = __get_cap_for_mds(ci, mds);
	spin_unlock(&ci->i_ceph_lock);
	return cap;
}

/*
 * Return id of any MDS with a cap, preferably FILE_WR|BUFFER|EXCL, else -1.
 */
static int __ceph_get_cap_mds(struct ceph_inode_info *ci)
{
	struct ceph_cap *cap;
	int mds = -1;
	struct rb_node *p;

	/* prefer mds with WR|BUFFER|EXCL caps */
	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		mds = cap->mds;
		if (cap->issued & (CEPH_CAP_FILE_WR |
				   CEPH_CAP_FILE_BUFFER |
				   CEPH_CAP_FILE_EXCL))
			break;
	}
	return mds;
}

int ceph_get_cap_mds(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int mds;
	spin_lock(&ci->i_ceph_lock);
	mds = __ceph_get_cap_mds(ceph_inode(inode));
	spin_unlock(&ci->i_ceph_lock);
	return mds;
}

/*
 * Called under i_ceph_lock.
 */
static void __insert_cap_node(struct ceph_inode_info *ci,
			      struct ceph_cap *new)
{
	struct rb_node **p = &ci->i_caps.rb_node;
	struct rb_node *parent = NULL;
	struct ceph_cap *cap = NULL;

	while (*p) {
		parent = *p;
		cap = rb_entry(parent, struct ceph_cap, ci_node);
		if (new->mds < cap->mds)
			p = &(*p)->rb_left;
		else if (new->mds > cap->mds)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&new->ci_node, parent, p);
	rb_insert_color(&new->ci_node, &ci->i_caps);
}

/*
 * (re)set cap hold timeouts, which control the delayed release
 * of unused caps back to the MDS.  Should be called on cap use.
 */
static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
			       struct ceph_inode_info *ci)
{
	struct ceph_mount_options *ma = mdsc->fsc->mount_options;

	ci->i_hold_caps_min = round_jiffies(jiffies +
					    ma->caps_wanted_delay_min * HZ);
	ci->i_hold_caps_max = round_jiffies(jiffies +
					    ma->caps_wanted_delay_max * HZ);
	dout("__cap_set_timeouts %p min %lu max %lu\n", &ci->vfs_inode,
	     ci->i_hold_caps_min - jiffies, ci->i_hold_caps_max - jiffies);
}

/*
 * (Re)queue cap at the end of the delayed cap release list.
 *
 * If I_FLUSH is set, leave the inode at the front of the list.
 *
 * Caller holds i_ceph_lock
 *    -> we take mdsc->cap_delay_lock
 */
static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
				struct ceph_inode_info *ci)
{
	__cap_set_timeouts(mdsc, ci);
	dout("__cap_delay_requeue %p flags %d at %lu\n", &ci->vfs_inode,
	     ci->i_ceph_flags, ci->i_hold_caps_max);
	if (!mdsc->stopping) {
		spin_lock(&mdsc->cap_delay_lock);
		if (!list_empty(&ci->i_cap_delay_list)) {
			if (ci->i_ceph_flags & CEPH_I_FLUSH)
				goto no_change;
			list_del_init(&ci->i_cap_delay_list);
		}
		list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_delay_list);
no_change:
		spin_unlock(&mdsc->cap_delay_lock);
	}
}

/*
 * Queue an inode for immediate writeback.  Mark inode with I_FLUSH,
 * indicating we should send a cap message to flush dirty metadata
 * asap, and move to the front of the delayed cap list.
 */
static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
				      struct ceph_inode_info *ci)
{
	dout("__cap_delay_requeue_front %p\n", &ci->vfs_inode);
	spin_lock(&mdsc->cap_delay_lock);
	ci->i_ceph_flags |= CEPH_I_FLUSH;
	if (!list_empty(&ci->i_cap_delay_list))
		list_del_init(&ci->i_cap_delay_list);
	list_add(&ci->i_cap_delay_list, &mdsc->cap_delay_list);
	spin_unlock(&mdsc->cap_delay_lock);
}

/*
 * Cancel delayed work on cap.
 *
 * Caller must hold i_ceph_lock.
 */
static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
			       struct ceph_inode_info *ci)
{
	dout("__cap_delay_cancel %p\n", &ci->vfs_inode);
	if (list_empty(&ci->i_cap_delay_list))
		return;
	spin_lock(&mdsc->cap_delay_lock);
	list_del_init(&ci->i_cap_delay_list);
	spin_unlock(&mdsc->cap_delay_lock);
}

/*
 * Common issue checks for add_cap, handle_cap_grant.
 */
static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
			      unsigned issued)
{
	unsigned had = __ceph_caps_issued(ci, NULL);

	/*
	 * Each time we receive FILE_CACHE anew, we increment
	 * i_rdcache_gen.
	 */
	if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
	    (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
		ci->i_rdcache_gen++;
	}

	/*
	 * if we are newly issued FILE_SHARED, mark dir not complete; we
	 * don't know what happened to this directory while we didn't
	 * have the cap.
	 */
	if ((issued & CEPH_CAP_FILE_SHARED) &&
	    (had & CEPH_CAP_FILE_SHARED) == 0) {
		ci->i_shared_gen++;
		if (S_ISDIR(ci->vfs_inode.i_mode)) {
			dout(" marking %p NOT complete\n", &ci->vfs_inode);
			__ceph_dir_clear_complete(ci);
		}
	}
}

/*
 * Add a capability under the given MDS session.
 *
 * Caller should hold session snap_rwsem (read) and s_mutex.
 *
 * @fmode is the open file mode, if we are opening a file, otherwise
 * it is < 0.  (This is so we can atomically add the cap and add an
 * open file reference to it.)
 */
void ceph_add_cap(struct inode *inode,
		  struct ceph_mds_session *session, u64 cap_id,
		  int fmode, unsigned issued, unsigned wanted,
		  unsigned seq, unsigned mseq, u64 realmino, int flags,
		  struct ceph_cap **new_cap)
{
	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap *cap;
	int mds = session->s_mds;
	int actual_wanted;

	dout("add_cap %p mds%d cap %llx %s seq %d\n", inode,
	     session->s_mds, cap_id, ceph_cap_string(issued), seq);

	/*
	 * If we are opening the file, include file mode wanted bits
	 * in wanted.
	 */
	if (fmode >= 0)
		wanted |= ceph_caps_for_mode(fmode);

	cap = __get_cap_for_mds(ci, mds);
	if (!cap) {
		cap = *new_cap;
		*new_cap = NULL;

		cap->issued = 0;
		cap->implemented = 0;
		cap->mds = mds;
		cap->mds_wanted = 0;
		cap->mseq = 0;

		cap->ci = ci;
		__insert_cap_node(ci, cap);

		/* add to session cap list */
		cap->session = session;
		spin_lock(&session->s_cap_lock);
		list_add_tail(&cap->session_caps, &session->s_caps);
		session->s_nr_caps++;
		spin_unlock(&session->s_cap_lock);
	} else {
		/*
		 * auth mds of the inode changed. we received the cap export
		 * message, but still haven't received the cap import message.
		 * handle_cap_export() updated the new auth MDS' cap.
		 *
		 * "ceph_seq_cmp(seq, cap->seq) <= 0" means we are processing
		 * a message that was send before the cap import message. So
		 * don't remove caps.
		 */
		if (ceph_seq_cmp(seq, cap->seq) <= 0) {
			WARN_ON(cap != ci->i_auth_cap);
			WARN_ON(cap->cap_id != cap_id);
			seq = cap->seq;
			mseq = cap->mseq;
			issued |= cap->issued;
			flags |= CEPH_CAP_FLAG_AUTH;
		}
	}

	if (!ci->i_snap_realm) {
		/*
		 * add this inode to the appropriate snap realm
		 */
		struct ceph_snap_realm *realm = ceph_lookup_snap_realm(mdsc,
							       realmino);
		if (realm) {
			spin_lock(&realm->inodes_with_caps_lock);
			ci->i_snap_realm = realm;
			list_add(&ci->i_snap_realm_item,
				 &realm->inodes_with_caps);
			spin_unlock(&realm->inodes_with_caps_lock);
		} else {
			pr_err("ceph_add_cap: couldn't find snap realm %llx\n",
			       realmino);
			WARN_ON(!realm);
		}
	}

	__check_cap_issue(ci, cap, issued);

	/*
	 * If we are issued caps we don't want, or the mds' wanted
	 * value appears to be off, queue a check so we'll release
	 * later and/or update the mds wanted value.
	 */
	actual_wanted = __ceph_caps_wanted(ci);
	if ((wanted & ~actual_wanted) ||
	    (issued & ~actual_wanted & CEPH_CAP_ANY_WR)) {
		dout(" issued %s, mds wanted %s, actual %s, queueing\n",
		     ceph_cap_string(issued), ceph_cap_string(wanted),
		     ceph_cap_string(actual_wanted));
		__cap_delay_requeue(mdsc, ci);
	}

	if (flags & CEPH_CAP_FLAG_AUTH) {
		if (ci->i_auth_cap == NULL ||
		    ceph_seq_cmp(ci->i_auth_cap->mseq, mseq) < 0) {
			ci->i_auth_cap = cap;
			cap->mds_wanted = wanted;
		}
	} else {
		WARN_ON(ci->i_auth_cap == cap);
	}

	dout("add_cap inode %p (%llx.%llx) cap %p %s now %s seq %d mds%d\n",
	     inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
	     ceph_cap_string(issued|cap->issued), seq, mds);
	cap->cap_id = cap_id;
	cap->issued = issued;
	cap->implemented |= issued;
	if (ceph_seq_cmp(mseq, cap->mseq) > 0)
		cap->mds_wanted = wanted;
	else
		cap->mds_wanted |= wanted;
	cap->seq = seq;
	cap->issue_seq = seq;
	cap->mseq = mseq;
	cap->cap_gen = session->s_cap_gen;

	if (fmode >= 0)
		__ceph_get_fmode(ci, fmode);
}

/*
 * Return true if cap has not timed out and belongs to the current
 * generation of the MDS session (i.e. has not gone 'stale' due to
 * us losing touch with the mds).
 */
static int __cap_is_valid(struct ceph_cap *cap)
{
	unsigned long ttl;
	u32 gen;

	spin_lock(&cap->session->s_gen_ttl_lock);
	gen = cap->session->s_cap_gen;
	ttl = cap->session->s_cap_ttl;
	spin_unlock(&cap->session->s_gen_ttl_lock);

	if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
		dout("__cap_is_valid %p cap %p issued %s "
		     "but STALE (gen %u vs %u)\n", &cap->ci->vfs_inode,
		     cap, ceph_cap_string(cap->issued), cap->cap_gen, gen);
		return 0;
	}

	return 1;
}

/*
 * Return set of valid cap bits issued to us.  Note that caps time
 * out, and may be invalidated in bulk if the client session times out
 * and session->s_cap_gen is bumped.
 */
int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
{
	int have = ci->i_snap_caps;
	struct ceph_cap *cap;
	struct rb_node *p;

	if (implemented)
		*implemented = 0;
	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		if (!__cap_is_valid(cap))
			continue;
		dout("__ceph_caps_issued %p cap %p issued %s\n",
		     &ci->vfs_inode, cap, ceph_cap_string(cap->issued));
		have |= cap->issued;
		if (implemented)
			*implemented |= cap->implemented;
	}
	/*
	 * exclude caps issued by non-auth MDS, but are been revoking
	 * by the auth MDS. The non-auth MDS should be revoking/exporting
	 * these caps, but the message is delayed.
	 */
	if (ci->i_auth_cap) {
		cap = ci->i_auth_cap;
		have &= ~cap->implemented | cap->issued;
	}
	return have;
}

/*
 * Get cap bits issued by caps other than @ocap
 */
int __ceph_caps_issued_other(struct ceph_inode_info *ci, struct ceph_cap *ocap)
{
	int have = ci->i_snap_caps;
	struct ceph_cap *cap;
	struct rb_node *p;

	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		if (cap == ocap)
			continue;
		if (!__cap_is_valid(cap))
			continue;
		have |= cap->issued;
	}
	return have;
}

/*
 * Move a cap to the end of the LRU (oldest caps at list head, newest
 * at list tail).
 */
static void __touch_cap(struct ceph_cap *cap)
{
	struct ceph_mds_session *s = cap->session;

	spin_lock(&s->s_cap_lock);
	if (s->s_cap_iterator == NULL) {
		dout("__touch_cap %p cap %p mds%d\n", &cap->ci->vfs_inode, cap,
		     s->s_mds);
		list_move_tail(&cap->session_caps, &s->s_caps);
	} else {
		dout("__touch_cap %p cap %p mds%d NOP, iterating over caps\n",
		     &cap->ci->vfs_inode, cap, s->s_mds);
	}
	spin_unlock(&s->s_cap_lock);
}

/*
 * Check if we hold the given mask.  If so, move the cap(s) to the
 * front of their respective LRUs.  (This is the preferred way for
 * callers to check for caps they want.)
 */
int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
{
	struct ceph_cap *cap;
	struct rb_node *p;
	int have = ci->i_snap_caps;

	if ((have & mask) == mask) {
		dout("__ceph_caps_issued_mask %p snap issued %s"
		     " (mask %s)\n", &ci->vfs_inode,
		     ceph_cap_string(have),
		     ceph_cap_string(mask));
		return 1;
	}

	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		if (!__cap_is_valid(cap))
			continue;
		if ((cap->issued & mask) == mask) {
			dout("__ceph_caps_issued_mask %p cap %p issued %s"
			     " (mask %s)\n", &ci->vfs_inode, cap,
			     ceph_cap_string(cap->issued),
			     ceph_cap_string(mask));
			if (touch)
				__touch_cap(cap);
			return 1;
		}

		/* does a combination of caps satisfy mask? */
		have |= cap->issued;
		if ((have & mask) == mask) {
			dout("__ceph_caps_issued_mask %p combo issued %s"
			     " (mask %s)\n", &ci->vfs_inode,
			     ceph_cap_string(cap->issued),
			     ceph_cap_string(mask));
			if (touch) {
				struct rb_node *q;

				/* touch this + preceding caps */
				__touch_cap(cap);
				for (q = rb_first(&ci->i_caps); q != p;
				     q = rb_next(q)) {
					cap = rb_entry(q, struct ceph_cap,
						       ci_node);
					if (!__cap_is_valid(cap))
						continue;
					__touch_cap(cap);
				}
			}
			return 1;
		}
	}

	return 0;
}

/*
 * Return true if mask caps are currently being revoked by an MDS.
 */
int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
			       struct ceph_cap *ocap, int mask)
{
	struct ceph_cap *cap;
	struct rb_node *p;

	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		if (cap != ocap &&
		    (cap->implemented & ~cap->issued & mask))
			return 1;
	}
	return 0;
}

int ceph_caps_revoking(struct ceph_inode_info *ci, int mask)
{
	struct inode *inode = &ci->vfs_inode;
	int ret;

	spin_lock(&ci->i_ceph_lock);
	ret = __ceph_caps_revoking_other(ci, NULL, mask);
	spin_unlock(&ci->i_ceph_lock);
	dout("ceph_caps_revoking %p %s = %d\n", inode,
	     ceph_cap_string(mask), ret);
	return ret;
}

int __ceph_caps_used(struct ceph_inode_info *ci)
{
	int used = 0;
	if (ci->i_pin_ref)
		used |= CEPH_CAP_PIN;
	if (ci->i_rd_ref)
		used |= CEPH_CAP_FILE_RD;
	if (ci->i_rdcache_ref ||
	    (!S_ISDIR(ci->vfs_inode.i_mode) && /* ignore readdir cache */
	     ci->vfs_inode.i_data.nrpages))
		used |= CEPH_CAP_FILE_CACHE;
	if (ci->i_wr_ref)
		used |= CEPH_CAP_FILE_WR;
	if (ci->i_wb_ref || ci->i_wrbuffer_ref)
		used |= CEPH_CAP_FILE_BUFFER;
	return used;
}

/*
 * wanted, by virtue of open file modes
 */
int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
{
	int want = 0;
	int mode;
	for (mode = 0; mode < CEPH_FILE_MODE_NUM; mode++)
		if (ci->i_nr_by_mode[mode])
			want |= ceph_caps_for_mode(mode);
	return want;
}

/*
 * Return caps we have registered with the MDS(s) as 'wanted'.
 */
int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
{
	struct ceph_cap *cap;
	struct rb_node *p;
	int mds_wanted = 0;

	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		if (!__cap_is_valid(cap))
			continue;
		if (cap == ci->i_auth_cap)
			mds_wanted |= cap->mds_wanted;
		else
			mds_wanted |= (cap->mds_wanted & ~CEPH_CAP_ANY_FILE_WR);
	}
	return mds_wanted;
}

/*
 * called under i_ceph_lock
 */
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
	return !RB_EMPTY_ROOT(&ci->i_caps);
}

int ceph_is_any_caps(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int ret;

	spin_lock(&ci->i_ceph_lock);
	ret = __ceph_is_any_caps(ci);
	spin_unlock(&ci->i_ceph_lock);

	return ret;
}

static void drop_inode_snap_realm(struct ceph_inode_info *ci)
{
	struct ceph_snap_realm *realm = ci->i_snap_realm;
	spin_lock(&realm->inodes_with_caps_lock);
	list_del_init(&ci->i_snap_realm_item);
	ci->i_snap_realm_counter++;
	ci->i_snap_realm = NULL;
	spin_unlock(&realm->inodes_with_caps_lock);
	ceph_put_snap_realm(ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc,
			    realm);
}

/*
 * Remove a cap.  Take steps to deal with a racing iterate_session_caps.
 *
 * caller should hold i_ceph_lock.
 * caller will not hold session s_mutex if called from destroy_inode.
 */
void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
{
	struct ceph_mds_session *session = cap->session;
	struct ceph_inode_info *ci = cap->ci;
	struct ceph_mds_client *mdsc =
		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
	int removed = 0;

	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);

	/* remove from session list */
	spin_lock(&session->s_cap_lock);
	if (session->s_cap_iterator == cap) {
		/* not yet, we are iterating over this very cap */
		dout("__ceph_remove_cap  delaying %p removal from session %p\n",
		     cap, cap->session);
	} else {
		list_del_init(&cap->session_caps);
		session->s_nr_caps--;
		cap->session = NULL;
		removed = 1;
	}
	/* protect backpointer with s_cap_lock: see iterate_session_caps */
	cap->ci = NULL;

	/*
	 * s_cap_reconnect is protected by s_cap_lock. no one changes
	 * s_cap_gen while session is in the reconnect state.
	 */
	if (queue_release &&
	    (!session->s_cap_reconnect || cap->cap_gen == session->s_cap_gen)) {
		cap->queue_release = 1;
		if (removed) {
			list_add_tail(&cap->session_caps,
				      &session->s_cap_releases);
			session->s_num_cap_releases++;
			removed = 0;
		}
	} else {
		cap->queue_release = 0;
	}
	cap->cap_ino = ci->i_vino.ino;

	spin_unlock(&session->s_cap_lock);

	/* remove from inode list */
	rb_erase(&cap->ci_node, &ci->i_caps);
	if (ci->i_auth_cap == cap)
		ci->i_auth_cap = NULL;

	if (removed)
		ceph_put_cap(mdsc, cap);

	/* when reconnect denied, we remove session caps forcibly,
	 * i_wr_ref can be non-zero. If there are ongoing write,
	 * keep i_snap_realm.
	 */
	if (!__ceph_is_any_caps(ci) && ci->i_wr_ref == 0 && ci->i_snap_realm)
		drop_inode_snap_realm(ci);

	if (!__ceph_is_any_real_caps(ci))
		__cap_delay_cancel(mdsc, ci);
}

/*
 * Build and send a cap message to the given MDS.
 *
 * Caller should be holding s_mutex.
 */
static int send_cap_msg(struct ceph_mds_session *session,
			u64 ino, u64 cid, int op,
			int caps, int wanted, int dirty,
			u32 seq, u64 flush_tid, u64 oldest_flush_tid,
			u32 issue_seq, u32 mseq, u64 size, u64 max_size,
			struct timespec *mtime, struct timespec *atime,
			struct timespec *ctime, u64 time_warp_seq,
			kuid_t uid, kgid_t gid, umode_t mode,
			u64 xattr_version,
			struct ceph_buffer *xattrs_buf,
			u64 follows, bool inline_data)
{
	struct ceph_mds_caps *fc;
	struct ceph_msg *msg;
	void *p;
	size_t extra_len;

	dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
	     " seq %u/%u tid %llu/%llu mseq %u follows %lld size %llu/%llu"
	     " xattr_ver %llu xattr_len %d\n", ceph_cap_op_name(op),
	     cid, ino, ceph_cap_string(caps), ceph_cap_string(wanted),
	     ceph_cap_string(dirty),
	     seq, issue_seq, flush_tid, oldest_flush_tid,
	     mseq, follows, size, max_size,
	     xattr_version, xattrs_buf ? (int)xattrs_buf->vec.iov_len : 0);

	/* flock buffer size + inline version + inline data size +
	 * osd_epoch_barrier + oldest_flush_tid */
	extra_len = 4 + 8 + 4 + 4 + 8;
	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc) + extra_len,
			   GFP_NOFS, false);
	if (!msg)
		return -ENOMEM;

	msg->hdr.version = cpu_to_le16(6);
	msg->hdr.tid = cpu_to_le64(flush_tid);

	fc = msg->front.iov_base;
	memset(fc, 0, sizeof(*fc));

	fc->cap_id = cpu_to_le64(cid);
	fc->op = cpu_to_le32(op);
	fc->seq = cpu_to_le32(seq);
	fc->issue_seq = cpu_to_le32(issue_seq);
	fc->migrate_seq = cpu_to_le32(mseq);
	fc->caps = cpu_to_le32(caps);
	fc->wanted = cpu_to_le32(wanted);
	fc->dirty = cpu_to_le32(dirty);
	fc->ino = cpu_to_le64(ino);
	fc->snap_follows = cpu_to_le64(follows);

	fc->size = cpu_to_le64(size);
	fc->max_size = cpu_to_le64(max_size);
	if (mtime)
		ceph_encode_timespec(&fc->mtime, mtime);
	if (atime)
		ceph_encode_timespec(&fc->atime, atime);
	if (ctime)
		ceph_encode_timespec(&fc->ctime, ctime);
	fc->time_warp_seq = cpu_to_le32(time_warp_seq);

	fc->uid = cpu_to_le32(from_kuid(&init_user_ns, uid));
	fc->gid = cpu_to_le32(from_kgid(&init_user_ns, gid));
	fc->mode = cpu_to_le32(mode);

	p = fc + 1;
	/* flock buffer size */
	ceph_encode_32(&p, 0);
	/* inline version */
	ceph_encode_64(&p, inline_data ? 0 : CEPH_INLINE_NONE);
	/* inline data size */
	ceph_encode_32(&p, 0);
	/* osd_epoch_barrier */
	ceph_encode_32(&p, 0);
	/* oldest_flush_tid */
	ceph_encode_64(&p, oldest_flush_tid);

	fc->xattr_version = cpu_to_le64(xattr_version);
	if (xattrs_buf) {
		msg->middle = ceph_buffer_get(xattrs_buf);
		fc->xattr_len = cpu_to_le32(xattrs_buf->vec.iov_len);
		msg->hdr.middle_len = cpu_to_le32(xattrs_buf->vec.iov_len);
	}

	ceph_con_send(&session->s_con, msg);
	return 0;
}

/*
 * Queue cap releases when an inode is dropped from our cache.  Since
 * inode is about to be destroyed, there is no need for i_ceph_lock.
 */
void ceph_queue_caps_release(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct rb_node *p;

	p = rb_first(&ci->i_caps);
	while (p) {
		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
		p = rb_next(p);
		__ceph_remove_cap(cap, true);
	}
}

/*
 * Send a cap msg on the given inode.  Update our caps state, then
 * drop i_ceph_lock and send the message.
 *
 * Make note of max_size reported/requested from mds, revoked caps
 * that have now been implemented.
 *
 * Make half-hearted attempt ot to invalidate page cache if we are
 * dropping RDCACHE.  Note that this will leave behind locked pages
 * that we'll then need to deal with elsewhere.
 *
 * Return non-zero if delayed release, or we experienced an error
 * such that the caller should requeue + retry later.
 *
 * called with i_ceph_lock, then drops it.
 * caller should hold snap_rwsem (read), s_mutex.
 */
static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
		      int op, int used, int want, int retain, int flushing,
		      u64 flush_tid, u64 oldest_flush_tid)
	__releases(cap->ci->i_ceph_lock)
{
	struct ceph_inode_info *ci = cap->ci;
	struct inode *inode = &ci->vfs_inode;
	u64 cap_id = cap->cap_id;
	int held, revoking, dropping, keep;
	u64 seq, issue_seq, mseq, time_warp_seq, follows;
	u64 size, max_size;
	struct timespec mtime, atime, ctime;
	int wake = 0;
	umode_t mode;
	kuid_t uid;
	kgid_t gid;
	struct ceph_mds_session *session;
	u64 xattr_version = 0;
	struct ceph_buffer *xattr_blob = NULL;
	int delayed = 0;
	int ret;
	bool inline_data;

	held = cap->issued | cap->implemented;
	revoking = cap->implemented & ~cap->issued;
	retain &= ~revoking;
	dropping = cap->issued & ~retain;

	dout("__send_cap %p cap %p session %p %s -> %s (revoking %s)\n",
	     inode, cap, cap->session,
	     ceph_cap_string(held), ceph_cap_string(held & retain),
	     ceph_cap_string(revoking));
	BUG_ON((retain & CEPH_CAP_PIN) == 0);

	session = cap->session;

	/* don't release wanted unless we've waited a bit. */
	if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 &&
	    time_before(jiffies, ci->i_hold_caps_min)) {
		dout(" delaying issued %s -> %s, wanted %s -> %s on send\n",
		     ceph_cap_string(cap->issued),
		     ceph_cap_string(cap->issued & retain),
		     ceph_cap_string(cap->mds_wanted),
		     ceph_cap_string(want));
		want |= cap->mds_wanted;
		retain |= cap->issued;
		delayed = 1;
	}
	ci->i_ceph_flags &= ~(CEPH_I_NODELAY | CEPH_I_FLUSH);

	cap->issued &= retain;  /* drop bits we don't want */
	if (cap->implemented & ~cap->issued) {
		/*
		 * Wake up any waiters on wanted -> needed transition.
		 * This is due to the weird transition from buffered
		 * to sync IO... we need to flush dirty pages _before_
		 * allowing sync writes to avoid reordering.
		 */
		wake = 1;
	}
	cap->implemented &= cap->issued | used;
	cap->mds_wanted = want;

	follows = flushing ? ci->i_head_snapc->seq : 0;

	keep = cap->implemented;
	seq = cap->seq;
	issue_seq = cap->issue_seq;
	mseq = cap->mseq;
	size = inode->i_size;
	ci->i_reported_size = size;
	max_size = ci->i_wanted_max_size;
	ci->i_requested_max_size = max_size;
	mtime = inode->i_mtime;
	atime = inode->i_atime;
	ctime = inode->i_ctime;
	time_warp_seq = ci->i_time_warp_seq;
	uid = inode->i_uid;
	gid = inode->i_gid;
	mode = inode->i_mode;

	if (flushing & CEPH_CAP_XATTR_EXCL) {
		__ceph_build_xattrs_blob(ci);
		xattr_blob = ci->i_xattrs.blob;
		xattr_version = ci->i_xattrs.version;
	}

	inline_data = ci->i_inline_version != CEPH_INLINE_NONE;

	spin_unlock(&ci->i_ceph_lock);

	ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
		op, keep, want, flushing, seq,
		flush_tid, oldest_flush_tid, issue_seq, mseq,
		size, max_size, &mtime, &atime, &ctime, time_warp_seq,
		uid, gid, mode, xattr_version, xattr_blob,
		follows, inline_data);
	if (ret < 0) {
		dout("error sending cap msg, must requeue %p\n", inode);
		delayed = 1;
	}

	if (wake)
		wake_up_all(&ci->i_cap_wq);

	return delayed;
}

/*
 * When a snapshot is taken, clients accumulate dirty metadata on
 * inodes with capabilities in ceph_cap_snaps to describe the file
 * state at the time the snapshot was taken.  This must be flushed
 * asynchronously back to the MDS once sync writes complete and dirty
 * data is written out.
 *
 * Unless @kick is true, skip cap_snaps that were already sent to
 * the MDS (i.e., during this session).
 *
 * Called under i_ceph_lock.  Takes s_mutex as needed.
 */
void __ceph_flush_snaps(struct ceph_inode_info *ci,
			struct ceph_mds_session **psession,
			int kick)
		__releases(ci->i_ceph_lock)
		__acquires(ci->i_ceph_lock)
{
	struct inode *inode = &ci->vfs_inode;
	int mds;
	struct ceph_cap_snap *capsnap;
	u32 mseq;
	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
	struct ceph_mds_session *session = NULL; /* if session != NULL, we hold
						    session->s_mutex */
	u64 next_follows = 0;  /* keep track of how far we've gotten through the
			     i_cap_snaps list, and skip these entries next time
			     around to avoid an infinite loop */

	if (psession)
		session = *psession;

	dout("__flush_snaps %p\n", inode);
retry:
	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
		/* avoid an infiniute loop after retry */
		if (capsnap->follows < next_follows)
			continue;
		/*
		 * we need to wait for sync writes to complete and for dirty
		 * pages to be written out.
		 */
		if (capsnap->dirty_pages || capsnap->writing)
			break;

		/* should be removed by ceph_try_drop_cap_snap() */
		BUG_ON(!capsnap->need_flush);

		/* pick mds, take s_mutex */
		if (ci->i_auth_cap == NULL) {
			dout("no auth cap (migrating?), doing nothing\n");
			goto out;
		}

		/* only flush each capsnap once */
		if (!kick && !list_empty(&capsnap->flushing_item)) {
			dout("already flushed %p, skipping\n", capsnap);
			continue;
		}

		mds = ci->i_auth_cap->session->s_mds;
		mseq = ci->i_auth_cap->mseq;

		if (session && session->s_mds != mds) {
			dout("oops, wrong session %p mutex\n", session);
			if (kick)
				goto out;

			mutex_unlock(&session->s_mutex);
			ceph_put_mds_session(session);
			session = NULL;
		}
		if (!session) {
			spin_unlock(&ci->i_ceph_lock);
			mutex_lock(&mdsc->mutex);
			session = __ceph_lookup_mds_session(mdsc, mds);
			mutex_unlock(&mdsc->mutex);
			if (session) {
				dout("inverting session/ino locks on %p\n",
				     session);
				mutex_lock(&session->s_mutex);
			}
			/*
			 * if session == NULL, we raced against a cap
			 * deletion or migration.  retry, and we'll
			 * get a better @mds value next time.
			 */
			spin_lock(&ci->i_ceph_lock);
			goto retry;
		}

		spin_lock(&mdsc->cap_dirty_lock);
		capsnap->flush_tid = ++mdsc->last_cap_flush_tid;
		spin_unlock(&mdsc->cap_dirty_lock);

		atomic_inc(&capsnap->nref);
		if (list_empty(&capsnap->flushing_item))
			list_add_tail(&capsnap->flushing_item,
				      &session->s_cap_snaps_flushing);
		spin_unlock(&ci->i_ceph_lock);

		dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
		     inode, capsnap, capsnap->follows, capsnap->flush_tid);
		send_cap_msg(session, ceph_vino(inode).ino, 0,
			     CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0,
			     capsnap->dirty, 0, capsnap->flush_tid, 0,
			     0, mseq, capsnap->size, 0,
			     &capsnap->mtime, &capsnap->atime,
			     &capsnap->ctime, capsnap->time_warp_seq,
			     capsnap->uid, capsnap->gid, capsnap->mode,
			     capsnap->xattr_version, capsnap->xattr_blob,
			     capsnap->follows, capsnap->inline_data);

		next_follows = capsnap->follows + 1;
		ceph_put_cap_snap(capsnap);

		spin_lock(&ci->i_ceph_lock);
		goto retry;
	}

	/* we flushed them all; remove this inode from the queue */
	spin_lock(&mdsc->snap_flush_lock);
	list_del_init(&ci->i_snap_flush_item);
	spin_unlock(&mdsc->snap_flush_lock);

out:
	if (psession)
		*psession = session;
	else if (session) {
		mutex_unlock(&session->s_mutex);
		ceph_put_mds_session(session);
	}
}

static void ceph_flush_snaps(struct ceph_inode_info *ci)
{
	spin_lock(&ci->i_ceph_lock);
	__ceph_flush_snaps(ci, NULL, 0);
	spin_unlock(&ci->i_ceph_lock);
}

/*
 * Mark caps dirty.  If inode is newly dirty, return the dirty flags.
 * Caller is then responsible for calling __mark_inode_dirty with the
 * returned flags value.
 */
int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
			   struct ceph_cap_flush **pcf)
{
	struct ceph_mds_client *mdsc =
		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
	struct inode *inode = &ci->vfs_inode;
	int was = ci->i_dirty_caps;
	int dirty = 0;

	if (!ci->i_auth_cap) {
		pr_warn("__mark_dirty_caps %p %llx mask %s, "
			"but no auth cap (session was closed?)\n",
			inode, ceph_ino(inode), ceph_cap_string(mask));
		return 0;
	}

	dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->vfs_inode,
	     ceph_cap_string(mask), ceph_cap_string(was),
	     ceph_cap_string(was | mask));
	ci->i_dirty_caps |= mask;
	if (was == 0) {
		WARN_ON_ONCE(ci->i_prealloc_cap_flush);
		swap(ci->i_prealloc_cap_flush, *pcf);

		if (!ci->i_head_snapc) {
			WARN_ON_ONCE(!rwsem_is_locked(&mdsc->snap_rwsem));
			ci->i_head_snapc = ceph_get_snap_context(
				ci->i_snap_realm->cached_context);
		}
		dout(" inode %p now dirty snapc %p auth cap %p\n",
		     &ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap);
		BUG_ON(!list_empty(&ci->i_dirty_item));
		spin_lock(&mdsc->cap_dirty_lock);
		list_add(&ci->i_dirty_item, &mdsc->cap_dirty);
		spin_unlock(&mdsc->cap_dirty_lock);
		if (ci->i_flushing_caps == 0) {
			ihold(inode);
			dirty |= I_DIRTY_SYNC;
		}
	} else {
		WARN_ON_ONCE(!ci->i_prealloc_cap_flush);
	}
	BUG_ON(list_empty(&ci->i_dirty_item));
	if (((was | ci->i_flushing_caps) & CEPH_CAP_FILE_BUFFER) &&
	    (mask & CEPH_CAP_FILE_BUFFER))
		dirty |= I_DIRTY_DATASYNC;
	__cap_delay_requeue(mdsc, ci);
	return dirty;
}

static void __add_cap_flushing_to_inode(struct ceph_inode_info *ci,
					struct ceph_cap_flush *cf)
{
	struct rb_node **p = &ci->i_cap_flush_tree.rb_node;
	struct rb_node *parent = NULL;
	struct ceph_cap_flush *other = NULL;

	while (*p) {
		parent = *p;
		other = rb_entry(parent, struct ceph_cap_flush, i_node);

		if (cf->tid < other->tid)
			p = &(*p)->rb_left;
		else if (cf->tid > other->tid)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&cf->i_node, parent, p);
	rb_insert_color(&cf->i_node, &ci->i_cap_flush_tree);
}

static void __add_cap_flushing_to_mdsc(struct ceph_mds_client *mdsc,
				       struct ceph_cap_flush *cf)
{
	struct rb_node **p = &mdsc->cap_flush_tree.rb_node;
	struct rb_node *parent = NULL;
	struct ceph_cap_flush *other = NULL;

	while (*p) {
		parent = *p;
		other = rb_entry(parent, struct ceph_cap_flush, g_node);

		if (cf->tid < other->tid)
			p = &(*p)->rb_left;
		else if (cf->tid > other->tid)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&cf->g_node, parent, p);
	rb_insert_color(&cf->g_node, &mdsc->cap_flush_tree);
}

struct ceph_cap_flush *ceph_alloc_cap_flush(void)
{
	return kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
}

void ceph_free_cap_flush(struct ceph_cap_flush *cf)
{
	if (cf)
		kmem_cache_free(ceph_cap_flush_cachep, cf);
}

static u64 __get_oldest_flush_tid(struct ceph_mds_client *mdsc)
{
	struct rb_node *n = rb_first(&mdsc->cap_flush_tree);
	if (n) {
		struct ceph_cap_flush *cf =
			rb_entry(n, struct ceph_cap_flush, g_node);
		return cf->tid;
	}
	return 0;
}

/*
 * Add dirty inode to the flushing list.  Assigned a seq number so we
 * can wait for caps to flush without starving.
 *
 * Called under i_ceph_lock.
 */
static int __mark_caps_flushing(struct inode *inode,
				struct ceph_mds_session *session,
				u64 *flush_tid, u64 *oldest_flush_tid)
{
	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap_flush *cf = NULL;
	int flushing;

	BUG_ON(ci->i_dirty_caps == 0);
	BUG_ON(list_empty(&ci->i_dirty_item));
	BUG_ON(!ci->i_prealloc_cap_flush);

	flushing = ci->i_dirty_caps;
	dout("__mark_caps_flushing flushing %s, flushing_caps %s -> %s\n",
	     ceph_cap_string(flushing),
	     ceph_cap_string(ci->i_flushing_caps),
	     ceph_cap_string(ci->i_flushing_caps | flushing));
	ci->i_flushing_caps |= flushing;
	ci->i_dirty_caps = 0;
	dout(" inode %p now !dirty\n", inode);

	swap(cf, ci->i_prealloc_cap_flush);
	cf->caps = flushing;

	spin_lock(&mdsc->cap_dirty_lock);
	list_del_init(&ci->i_dirty_item);

	cf->tid = ++mdsc->last_cap_flush_tid;
	__add_cap_flushing_to_mdsc(mdsc, cf);
	*oldest_flush_tid = __get_oldest_flush_tid(mdsc);

	if (list_empty(&ci->i_flushing_item)) {
		list_add_tail(&ci->i_flushing_item, &session->s_cap_flushing);
		mdsc->num_cap_flushing++;
		dout(" inode %p now flushing tid %llu\n", inode, cf->tid);
	} else {
		list_move_tail(&ci->i_flushing_item, &session->s_cap_flushing);
		dout(" inode %p now flushing (more) tid %llu\n",
		     inode, cf->tid);
	}
	spin_unlock(&mdsc->cap_dirty_lock);

	__add_cap_flushing_to_inode(ci, cf);

	*flush_tid = cf->tid;
	return flushing;
}

/*
 * try to invalidate mapping pages without blocking.
 */
static int try_nonblocking_invalidate(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	u32 invalidating_gen = ci->i_rdcache_gen;

	spin_unlock(&ci->i_ceph_lock);
	invalidate_mapping_pages(&inode->i_data, 0, -1);
	spin_lock(&ci->i_ceph_lock);

	if (inode->i_data.nrpages == 0 &&
	    invalidating_gen == ci->i_rdcache_gen) {
		/* success. */
		dout("try_nonblocking_invalidate %p success\n", inode);
		/* save any racing async invalidate some trouble */
		ci->i_rdcache_revoking = ci->i_rdcache_gen - 1;
		return 0;
	}
	dout("try_nonblocking_invalidate %p failed\n", inode);
	return -1;
}

/*
 * Swiss army knife function to examine currently used and wanted
 * versus held caps.  Release, flush, ack revoked caps to mds as
 * appropriate.
 *
 *  CHECK_CAPS_NODELAY - caller is delayed work and we should not delay
 *    cap release further.
 *  CHECK_CAPS_AUTHONLY - we should only check the auth cap
 *  CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without
 *    further delay.
 */
void ceph_check_caps(struct ceph_inode_info *ci, int flags,
		     struct ceph_mds_session *session)
{
	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct inode *inode = &ci->vfs_inode;
	struct ceph_cap *cap;
	u64 flush_tid, oldest_flush_tid;
	int file_wanted, used, cap_used;
	int took_snap_rwsem = 0;             /* true if mdsc->snap_rwsem held */
	int issued, implemented, want, retain, revoking, flushing = 0;
	int mds = -1;   /* keep track of how far we've gone through i_caps list
			   to avoid an infinite loop on retry */
	struct rb_node *p;
	int tried_invalidate = 0;
	int delayed = 0, sent = 0, force_requeue = 0, num;
	int queue_invalidate = 0;
	int is_delayed = flags & CHECK_CAPS_NODELAY;

	/* if we are unmounting, flush any unused caps immediately. */
	if (mdsc->stopping)
		is_delayed = 1;

	spin_lock(&ci->i_ceph_lock);

	if (ci->i_ceph_flags & CEPH_I_FLUSH)
		flags |= CHECK_CAPS_FLUSH;

	/* flush snaps first time around only */
	if (!list_empty(&ci->i_cap_snaps))
		__ceph_flush_snaps(ci, &session, 0);
	goto retry_locked;
retry:
	spin_lock(&ci->i_ceph_lock);
retry_locked:
	file_wanted = __ceph_caps_file_wanted(ci);
	used = __ceph_caps_used(ci);
	issued = __ceph_caps_issued(ci, &implemented);
	revoking = implemented & ~issued;

	want = file_wanted;
	retain = file_wanted | used | CEPH_CAP_PIN;
	if (!mdsc->stopping && inode->i_nlink > 0) {
		if (file_wanted) {
			retain |= CEPH_CAP_ANY;       /* be greedy */
		} else if (S_ISDIR(inode->i_mode) &&
			   (issued & CEPH_CAP_FILE_SHARED) &&
			    __ceph_dir_is_complete(ci)) {
			/*
			 * If a directory is complete, we want to keep
			 * the exclusive cap. So that MDS does not end up
			 * revoking the shared cap on every create/unlink
			 * operation.
			 */
			want = CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL;
			retain |= want;
		} else {

			retain |= CEPH_CAP_ANY_SHARED;
			/*
			 * keep RD only if we didn't have the file open RW,
			 * because then the mds would revoke it anyway to
			 * journal max_size=0.
			 */
			if (ci->i_max_size == 0)
				retain |= CEPH_CAP_ANY_RD;
		}
	}

	dout("check_caps %p file_want %s used %s dirty %s flushing %s"
	     " issued %s revoking %s retain %s %s%s%s\n", inode,
	     ceph_cap_string(file_wanted),
	     ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
	     ceph_cap_string(ci->i_flushing_caps),
	     ceph_cap_string(issued), ceph_cap_string(revoking),
	     ceph_cap_string(retain),
	     (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
	     (flags & CHECK_CAPS_NODELAY) ? " NODELAY" : "",
	     (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "");

	/*
	 * If we no longer need to hold onto old our caps, and we may
	 * have cached pages, but don't want them, then try to invalidate.
	 * If we fail, it's because pages are locked.... try again later.
	 */
	if ((!is_delayed || mdsc->stopping) &&
	    !S_ISDIR(inode->i_mode) &&		/* ignore readdir cache */
	    ci->i_wrbuffer_ref == 0 &&		/* no dirty pages... */
	    inode->i_data.nrpages &&		/* have cached pages */
	    (revoking & (CEPH_CAP_FILE_CACHE|
			 CEPH_CAP_FILE_LAZYIO)) && /*  or revoking cache */
	    !tried_invalidate) {
		dout("check_caps trying to invalidate on %p\n", inode);
		if (try_nonblocking_invalidate(inode) < 0) {
			if (revoking & (CEPH_CAP_FILE_CACHE|
					CEPH_CAP_FILE_LAZYIO)) {
				dout("check_caps queuing invalidate\n");
				queue_invalidate = 1;
				ci->i_rdcache_revoking = ci->i_rdcache_gen;
			} else {
				dout("check_caps failed to invalidate pages\n");
				/* we failed to invalidate pages.  check these
				   caps again later. */
				force_requeue = 1;
				__cap_set_timeouts(mdsc, ci);
			}
		}
		tried_invalidate = 1;
		goto retry_locked;
	}

	num = 0;
	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
		cap = rb_entry(p, struct ceph_cap, ci_node);
		num++;

		/* avoid looping forever */
		if (mds >= cap->mds ||
		    ((flags & CHECK_CAPS_AUTHONLY) && cap != ci->i_auth_cap))
			continue;

		/* NOTE: no side-effects allowed, until we take s_mutex */

		cap_used = used;
		if (ci->i_auth_cap && cap != ci->i_auth_cap)
			cap_used &= ~ci->i_auth_cap->issued;

		revoking = cap->implemented & ~cap->issued;
		dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
		     cap->mds, cap, ceph_cap_string(cap->issued),
		     ceph_cap_string(cap_used),
		     ceph_cap_string(cap->implemented),
		     ceph_cap_string(revoking));

		if (cap == ci->i_auth_cap &&
		    (cap->issued & CEPH_CAP_FILE_WR)) {
			/* request larger max_size from MDS? */
			if (ci->i_wanted_max_size > ci->i_max_size &&
			    ci->i_wanted_max_size > ci->i_requested_max_size) {
				dout("requesting new max_size\n");
				goto ack;
			}

			/* approaching file_max? */
			if ((inode->i_size << 1) >= ci->i_max_size &&
			    (ci->i_reported_size << 1) < ci->i_max_size) {
				dout("i_size approaching max_size\n");
				goto ack;
			}
		}
		/* flush anything dirty? */
		if (cap == ci->i_auth_cap && (flags & CHECK_CAPS_FLUSH) &&
		    ci->i_dirty_caps) {
			dout("flushing dirty caps\n");
			goto ack;
		}

		/* completed revocation? going down and there are no caps? */
		if (revoking && (revoking & cap_used) == 0) {
			dout("completed revocation of %s\n",
			     ceph_cap_string(cap->implemented & ~cap->issued));
			goto ack;
		}

		/* want more caps from mds? */
		if (want & ~(cap->mds_wanted | cap->issued))
			goto ack;

		/* things we might delay */
		if ((cap->issued & ~retain) == 0 &&
		    cap->mds_wanted == want)
			continue;     /* nope, all good */

		if (is_delayed)
			goto ack;

		/* delay? */
		if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 &&
		    time_before(jiffies, ci->i_hold_caps_max)) {
			dout(" delaying issued %s -> %s, wanted %s -> %s\n",
			     ceph_cap_string(cap->issued),
			     ceph_cap_string(cap->issued & retain),
			     ceph_cap_string(cap->mds_wanted),
			     ceph_cap_string(want));
			delayed++;
			continue;
		}

ack:
		if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
			dout(" skipping %p I_NOFLUSH set\n", inode);
			continue;
		}

		if (session && session != cap->session) {
			dout("oops, wrong session %p mutex\n", session);
			mutex_unlock(&session->s_mutex);
			session = NULL;
		}
		if (!session) {
			session = cap->session;
			if (mutex_trylock(&session->s_mutex) == 0) {
				dout("inverting session/ino locks on %p\n",
				     session);
				spin_unlock(&ci->i_ceph_lock);
				if (took_snap_rwsem) {
					up_read(&mdsc->snap_rwsem);
					took_snap_rwsem = 0;
				}
				mutex_lock(&session->s_mutex);
				goto retry;
			}
		}
		/* take snap_rwsem after session mutex */
		if (!took_snap_rwsem) {
			if (down_read_trylock(&mdsc->snap_rwsem) == 0) {
				dout("inverting snap/in locks on %p\n",
				     inode);
				spin_unlock(&ci->i_ceph_lock);
				down_read(&mdsc->snap_rwsem);
				took_snap_rwsem = 1;
				goto retry;
			}
			took_snap_rwsem = 1;
		}

		if (cap == ci->i_auth_cap && ci->i_dirty_caps) {
			flushing = __mark_caps_flushing(inode, session,
							&flush_tid,
							&oldest_flush_tid);
		} else {
			flushing = 0;
			flush_tid = 0;
			spin_lock(&mdsc->cap_dirty_lock);
			oldest_flush_tid = __get_oldest_flush_tid(mdsc);
			spin_unlock(&mdsc->cap_dirty_lock);
		}

		mds = cap->mds;  /* remember mds, so we don't repeat */
		sent++;

		/* __send_cap drops i_ceph_lock */
		delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, cap_used,
				      want, retain, flushing,
				      flush_tid, oldest_flush_tid);
		goto retry; /* retake i_ceph_lock and restart our cap scan. */
	}

	/*
	 * Reschedule delayed caps release if we delayed anything,
	 * otherwise cancel.
	 */
	if (delayed && is_delayed)
		force_requeue = 1;   /* __send_cap delayed release; requeue */
	if (!delayed && !is_delayed)
		__cap_delay_cancel(mdsc, ci);
	else if (!is_delayed || force_requeue)
		__cap_delay_requeue(mdsc, ci);

	spin_unlock(&ci->i_ceph_lock);

	if (queue_invalidate)
		ceph_queue_invalidate(inode);

	if (session)
		mutex_unlock(&session->s_mutex);
	if (took_snap_rwsem)
		up_read(&mdsc->snap_rwsem);
}

/*
 * Try to flush dirty caps back to the auth mds.
 */
static int try_flush_caps(struct inode *inode, u64 *ptid)
{
	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_mds_session *session = NULL;
	int flushing = 0;
	u64 flush_tid = 0, oldest_flush_tid = 0;

retry:
	spin_lock(&ci->i_ceph_lock);
	if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
		dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
		goto out;
	}
	if (ci->i_dirty_caps && ci->i_auth_cap) {
		struct ceph_cap *cap = ci->i_auth_cap;
		int used = __ceph_caps_used(ci);
		int want = __ceph_caps_wanted(ci);
		int delayed;

		if (!session || session != cap->session) {
			spin_unlock(&ci->i_ceph_lock);
			if (session)
				mutex_unlock(&session->s_mutex);
			session = cap->session;
			mutex_lock(&session->s_mutex);
			goto retry;
		}
		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN)
			goto out;

		flushing = __mark_caps_flushing(inode, session, &flush_tid,
						&oldest_flush_tid);

		/* __send_cap drops i_ceph_lock */
		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, used, want,
				     (cap->issued | cap->implemented),
				     flushing, flush_tid, oldest_flush_tid);

		if (delayed) {
			spin_lock(&ci->i_ceph_lock);
			__cap_delay_requeue(mdsc, ci);
			spin_unlock(&ci->i_ceph_lock);
		}
	} else {
		struct rb_node *n = rb_last(&ci->i_cap_flush_tree);
		if (n) {
			struct ceph_cap_flush *cf =
				rb_entry(n, struct ceph_cap_flush, i_node);
			flush_tid = cf->tid;
		}
		flushing = ci->i_flushing_caps;
		spin_unlock(&ci->i_ceph_lock);
	}
out:
	if (session)
		mutex_unlock(&session->s_mutex);

	*ptid = flush_tid;
	return flushing;
}

/*
 * Return true if we've flushed caps through the given flush_tid.
 */
static int caps_are_flushed(struct inode *inode, u64 flush_tid)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap_flush *cf;
	struct rb_node *n;
	int ret = 1;

	spin_lock(&ci->i_ceph_lock);
	n = rb_first(&ci->i_cap_flush_tree);
	if (n) {
		cf = rb_entry(n, struct ceph_cap_flush, i_node);
		if (cf->tid <= flush_tid)
			ret = 0;
	}
	spin_unlock(&ci->i_ceph_lock);
	return ret;
}

/*
 * Wait on any unsafe replies for the given inode.  First wait on the
 * newest request, and make that the upper bound.  Then, if there are
 * more requests, keep waiting on the oldest as long as it is still older
 * than the original request.
 */
static void sync_write_wait(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct list_head *head = &ci->i_unsafe_writes;
	struct ceph_osd_request *req;
	u64 last_tid;

	if (!S_ISREG(inode->i_mode))
		return;

	spin_lock(&ci->i_unsafe_lock);
	if (list_empty(head))
		goto out;

	/* set upper bound as _last_ entry in chain */
	req = list_last_entry(head, struct ceph_osd_request,
			      r_unsafe_item);
	last_tid = req->r_tid;

	do {
		ceph_osdc_get_request(req);
		spin_unlock(&ci->i_unsafe_lock);
		dout("sync_write_wait on tid %llu (until %llu)\n",
		     req->r_tid, last_tid);
		wait_for_completion(&req->r_safe_completion);
		spin_lock(&ci->i_unsafe_lock);
		ceph_osdc_put_request(req);

		/*
		 * from here on look at first entry in chain, since we
		 * only want to wait for anything older than last_tid
		 */
		if (list_empty(head))
			break;
		req = list_first_entry(head, struct ceph_osd_request,
				       r_unsafe_item);
	} while (req->r_tid < last_tid);
out:
	spin_unlock(&ci->i_unsafe_lock);
}

/*
 * wait for any unsafe requests to complete.
 */
static int unsafe_request_wait(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_mds_request *req1 = NULL, *req2 = NULL;
	int ret, err = 0;

	spin_lock(&ci->i_unsafe_lock);
	if (S_ISDIR(inode->i_mode) && !list_empty(&ci->i_unsafe_dirops)) {
		req1 = list_last_entry(&ci->i_unsafe_dirops,
					struct ceph_mds_request,
					r_unsafe_dir_item);
		ceph_mdsc_get_request(req1);
	}
	if (!list_empty(&ci->i_unsafe_iops)) {
		req2 = list_last_entry(&ci->i_unsafe_iops,
					struct ceph_mds_request,
					r_unsafe_target_item);
		ceph_mdsc_get_request(req2);
	}
	spin_unlock(&ci->i_unsafe_lock);

	dout("unsafe_requeset_wait %p wait on tid %llu %llu\n",
	     inode, req1 ? req1->r_tid : 0ULL, req2 ? req2->r_tid : 0ULL);
	if (req1) {
		ret = !wait_for_completion_timeout(&req1->r_safe_completion,
					ceph_timeout_jiffies(req1->r_timeout));
		if (ret)
			err = -EIO;
		ceph_mdsc_put_request(req1);
	}
	if (req2) {
		ret = !wait_for_completion_timeout(&req2->r_safe_completion,
					ceph_timeout_jiffies(req2->r_timeout));
		if (ret)
			err = -EIO;
		ceph_mdsc_put_request(req2);
	}
	return err;
}

int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct inode *inode = file->f_mapping->host;
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 flush_tid;
	int ret;
	int dirty;

	dout("fsync %p%s\n", inode, datasync ? " datasync" : "");
	sync_write_wait(inode);

	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (ret < 0)
		goto out;

	if (datasync)
		goto out;

	inode_lock(inode);

	dirty = try_flush_caps(inode, &flush_tid);
	dout("fsync dirty caps are %s\n", ceph_cap_string(dirty));

	ret = unsafe_request_wait(inode);

	/*
	 * only wait on non-file metadata writeback (the mds
	 * can recover size and mtime, so we don't need to
	 * wait for that)
	 */
	if (!ret && (dirty & ~CEPH_CAP_ANY_FILE_WR)) {
		ret = wait_event_interruptible(ci->i_cap_wq,
					caps_are_flushed(inode, flush_tid));
	}
	inode_unlock(inode);
out:
	dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret);
	return ret;
}

/*
 * Flush any dirty caps back to the mds.  If we aren't asked to wait,
 * queue inode for flush but don't do so immediately, because we can
 * get by with fewer MDS messages if we wait for data writeback to
 * complete first.
 */
int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 flush_tid;
	int err = 0;
	int dirty;
	int wait = wbc->sync_mode == WB_SYNC_ALL;

	dout("write_inode %p wait=%d\n", inode, wait);
	if (wait) {
		dirty = try_flush_caps(inode, &flush_tid);
		if (dirty)
			err = wait_event_interruptible(ci->i_cap_wq,
				       caps_are_flushed(inode, flush_tid));
	} else {
		struct ceph_mds_client *mdsc =
			ceph_sb_to_client(inode->i_sb)->mdsc;

		spin_lock(&ci->i_ceph_lock);
		if (__ceph_caps_dirty(ci))
			__cap_delay_requeue_front(mdsc, ci);
		spin_unlock(&ci->i_ceph_lock);
	}
	return err;
}

/*
 * After a recovering MDS goes active, we need to resend any caps
 * we were flushing.
 *
 * Caller holds session->s_mutex.
 */
static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc,
				   struct ceph_mds_session *session)
{
	struct ceph_cap_snap *capsnap;

	dout("kick_flushing_capsnaps mds%d\n", session->s_mds);
	list_for_each_entry(capsnap, &session->s_cap_snaps_flushing,
			    flushing_item) {
		struct ceph_inode_info *ci = capsnap->ci;
		struct inode *inode = &ci->vfs_inode;
		struct ceph_cap *cap;

		spin_lock(&ci->i_ceph_lock);
		cap = ci->i_auth_cap;
		if (cap && cap->session == session) {
			dout("kick_flushing_caps %p cap %p capsnap %p\n", inode,
			     cap, capsnap);
			__ceph_flush_snaps(ci, &session, 1);
		} else {
			pr_err("%p auth cap %p not mds%d ???\n", inode,
			       cap, session->s_mds);
		}
		spin_unlock(&ci->i_ceph_lock);
	}
}

static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
				struct ceph_mds_session *session,
				struct ceph_inode_info *ci)
{
	struct inode *inode = &ci->vfs_inode;
	struct ceph_cap *cap;
	struct ceph_cap_flush *cf;
	struct rb_node *n;
	int delayed = 0;
	u64 first_tid = 0;
	u64 oldest_flush_tid;

	spin_lock(&mdsc->cap_dirty_lock);
	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
	spin_unlock(&mdsc->cap_dirty_lock);

	while (true) {
		spin_lock(&ci->i_ceph_lock);
		cap = ci->i_auth_cap;
		if (!(cap && cap->session == session)) {
			pr_err("%p auth cap %p not mds%d ???\n", inode,
					cap, session->s_mds);
			spin_unlock(&ci->i_ceph_lock);
			break;
		}

		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
			cf = rb_entry(n, struct ceph_cap_flush, i_node);
			if (cf->tid >= first_tid)
				break;
		}
		if (!n) {
			spin_unlock(&ci->i_ceph_lock);
			break;
		}

		cf = rb_entry(n, struct ceph_cap_flush, i_node);

		first_tid = cf->tid + 1;

		dout("kick_flushing_caps %p cap %p tid %llu %s\n", inode,
		     cap, cf->tid, ceph_cap_string(cf->caps));
		delayed |= __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
				      __ceph_caps_used(ci),
				      __ceph_caps_wanted(ci),
				      cap->issued | cap->implemented,
				      cf->caps, cf->tid, oldest_flush_tid);
	}
	return delayed;
}

void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
				   struct ceph_mds_session *session)
{
	struct ceph_inode_info *ci;
	struct ceph_cap *cap;

	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
		spin_lock(&ci->i_ceph_lock);
		cap = ci->i_auth_cap;
		if (!(cap && cap->session == session)) {
			pr_err("%p auth cap %p not mds%d ???\n",
				&ci->vfs_inode, cap, session->s_mds);
			spin_unlock(&ci->i_ceph_lock);
			continue;
		}


		/*
		 * if flushing caps were revoked, we re-send the cap flush
		 * in client reconnect stage. This guarantees MDS * processes
		 * the cap flush message before issuing the flushing caps to
		 * other client.
		 */
		if ((cap->issued & ci->i_flushing_caps) !=
		    ci->i_flushing_caps) {
			spin_unlock(&ci->i_ceph_lock);
			if (!__kick_flushing_caps(mdsc, session, ci))
				continue;
			spin_lock(&ci->i_ceph_lock);
		}

		spin_unlock(&ci->i_ceph_lock);
	}
}

void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
			     struct ceph_mds_session *session)
{
	struct ceph_inode_info *ci;

	kick_flushing_capsnaps(mdsc, session);

	dout("kick_flushing_caps mds%d\n", session->s_mds);
	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
		int delayed = __kick_flushing_caps(mdsc, session, ci);
		if (delayed) {
			spin_lock(&ci->i_ceph_lock);
			__cap_delay_requeue(mdsc, ci);
			spin_unlock(&ci->i_ceph_lock);
		}
	}
}

static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
				     struct ceph_mds_session *session,
				     struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap *cap;

	spin_lock(&ci->i_ceph_lock);
	cap = ci->i_auth_cap;
	dout("kick_flushing_inode_caps %p flushing %s\n", inode,
	     ceph_cap_string(ci->i_flushing_caps));

	__ceph_flush_snaps(ci, &session, 1);

	if (ci->i_flushing_caps) {
		int delayed;

		spin_lock(&mdsc->cap_dirty_lock);
		list_move_tail(&ci->i_flushing_item,
			       &cap->session->s_cap_flushing);
		spin_unlock(&mdsc->cap_dirty_lock);

		spin_unlock(&ci->i_ceph_lock);

		delayed = __kick_flushing_caps(mdsc, session, ci);
		if (delayed) {
			spin_lock(&ci->i_ceph_lock);
			__cap_delay_requeue(mdsc, ci);
			spin_unlock(&ci->i_ceph_lock);
		}
	} else {
		spin_unlock(&ci->i_ceph_lock);
	}
}


/*
 * Take references to capabilities we hold, so that we don't release
 * them to the MDS prematurely.
 *
 * Protected by i_ceph_lock.
 */
static void __take_cap_refs(struct ceph_inode_info *ci, int got,
			    bool snap_rwsem_locked)
{
	if (got & CEPH_CAP_PIN)
		ci->i_pin_ref++;
	if (got & CEPH_CAP_FILE_RD)
		ci->i_rd_ref++;
	if (got & CEPH_CAP_FILE_CACHE)
		ci->i_rdcache_ref++;
	if (got & CEPH_CAP_FILE_WR) {
		if (ci->i_wr_ref == 0 && !ci->i_head_snapc) {
			BUG_ON(!snap_rwsem_locked);
			ci->i_head_snapc = ceph_get_snap_context(
					ci->i_snap_realm->cached_context);
		}
		ci->i_wr_ref++;
	}
	if (got & CEPH_CAP_FILE_BUFFER) {
		if (ci->i_wb_ref == 0)
			ihold(&ci->vfs_inode);
		ci->i_wb_ref++;
		dout("__take_cap_refs %p wb %d -> %d (?)\n",
		     &ci->vfs_inode, ci->i_wb_ref-1, ci->i_wb_ref);
	}
}

/*
 * Try to grab cap references.  Specify those refs we @want, and the
 * minimal set we @need.  Also include the larger offset we are writing
 * to (when applicable), and check against max_size here as well.
 * Note that caller is responsible for ensuring max_size increases are
 * requested from the MDS.
 */
static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
			    loff_t endoff, bool nonblock, int *got, int *err)
{
	struct inode *inode = &ci->vfs_inode;
	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
	int ret = 0;
	int have, implemented;
	int file_wanted;
	bool snap_rwsem_locked = false;

	dout("get_cap_refs %p need %s want %s\n", inode,
	     ceph_cap_string(need), ceph_cap_string(want));

again:
	spin_lock(&ci->i_ceph_lock);

	/* make sure file is actually open */
	file_wanted = __ceph_caps_file_wanted(ci);
	if ((file_wanted & need) == 0) {
		dout("try_get_cap_refs need %s file_wanted %s, EBADF\n",
		     ceph_cap_string(need), ceph_cap_string(file_wanted));
		*err = -EBADF;
		ret = 1;
		goto out_unlock;
	}

	/* finish pending truncate */
	while (ci->i_truncate_pending) {
		spin_unlock(&ci->i_ceph_lock);
		if (snap_rwsem_locked) {
			up_read(&mdsc->snap_rwsem);
			snap_rwsem_locked = false;
		}
		__ceph_do_pending_vmtruncate(inode);
		spin_lock(&ci->i_ceph_lock);
	}

	have = __ceph_caps_issued(ci, &implemented);

	if (have & need & CEPH_CAP_FILE_WR) {
		if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) {
			dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
			     inode, endoff, ci->i_max_size);
			if (endoff > ci->i_requested_max_size) {
				*err = -EAGAIN;
				ret = 1;
			}
			goto out_unlock;
		}
		/*
		 * If a sync write is in progress, we must wait, so that we
		 * can get a final snapshot value for size+mtime.
		 */
		if (__ceph_have_pending_cap_snap(ci)) {
			dout("get_cap_refs %p cap_snap_pending\n", inode);
			goto out_unlock;
		}
	}

	if ((have & need) == need) {
		/*
		 * Look at (implemented & ~have & not) so that we keep waiting
		 * on transition from wanted -> needed caps.  This is needed
		 * for WRBUFFER|WR -> WR to avoid a new WR sync write from
		 * going before a prior buffered writeback happens.
		 */
		int not = want & ~(have & need);
		int revoking = implemented & ~have;
		dout("get_cap_refs %p have %s but not %s (revoking %s)\n",
		     inode, ceph_cap_string(have), ceph_cap_string(not),
		     ceph_cap_string(revoking));
		if ((revoking & not) == 0) {
			if (!snap_rwsem_locked &&
			    !ci->i_head_snapc &&
			    (need & CEPH_CAP_FILE_WR)) {
				if (!down_read_trylock(&mdsc->snap_rwsem)) {
					/*
					 * we can not call down_read() when
					 * task isn't in TASK_RUNNING state
					 */
					if (nonblock) {
						*err = -EAGAIN;
						ret = 1;
						goto out_unlock;
					}

					spin_unlock(&ci->i_ceph_lock);
					down_read(&mdsc->snap_rwsem);
					snap_rwsem_locked = true;
					goto again;
				}
				snap_rwsem_locked = true;
			}
			*got = need | (have & want);
			__take_cap_refs(ci, *got, true);
			ret = 1;
		}
	} else {
		int session_readonly = false;
		if ((need & CEPH_CAP_FILE_WR) && ci->i_auth_cap) {
			struct ceph_mds_session *s = ci->i_auth_cap->session;
			spin_lock(&s->s_cap_lock);
			session_readonly = s->s_readonly;
			spin_unlock(&s->s_cap_lock);
		}
		if (session_readonly) {
			dout("get_cap_refs %p needed %s but mds%d readonly\n",
			     inode, ceph_cap_string(need), ci->i_auth_cap->mds);
			*err = -EROFS;
			ret = 1;
			goto out_unlock;
		}

		if (!__ceph_is_any_caps(ci) &&
		    ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
			dout("get_cap_refs %p forced umount\n", inode);
			*err = -EIO;
			ret = 1;
			goto out_unlock;
		}

		dout("get_cap_refs %p have %s needed %s\n", inode,
		     ceph_cap_string(have), ceph_cap_string(need));
	}
out_unlock:
	spin_unlock(&ci->i_ceph_lock);
	if (snap_rwsem_locked)
		up_read(&mdsc->snap_rwsem);

	dout("get_cap_refs %p ret %d got %s\n", inode,
	     ret, ceph_cap_string(*got));
	return ret;
}

/*
 * Check the offset we are writing up to against our current
 * max_size.  If necessary, tell the MDS we want to write to
 * a larger offset.
 */
static void check_max_size(struct inode *inode, loff_t endoff)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int check = 0;

	/* do we need to explicitly request a larger max_size? */
	spin_lock(&ci->i_ceph_lock);
	if (endoff >= ci->i_max_size && endoff > ci->i_wanted_max_size) {
		dout("write %p at large endoff %llu, req max_size\n",
		     inode, endoff);
		ci->i_wanted_max_size = endoff;
	}
	/* duplicate ceph_check_caps()'s logic */
	if (ci->i_auth_cap &&
	    (ci->i_auth_cap->issued & CEPH_CAP_FILE_WR) &&
	    ci->i_wanted_max_size > ci->i_max_size &&
	    ci->i_wanted_max_size > ci->i_requested_max_size)
		check = 1;
	spin_unlock(&ci->i_ceph_lock);
	if (check)
		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}

/*
 * Wait for caps, and take cap references.  If we can't get a WR cap
 * due to a small max_size, make sure we check_max_size (and possibly
 * ask the mds) so we don't get hung up indefinitely.
 */
int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
		  loff_t endoff, int *got, struct page **pinned_page)
{
	int _got, ret, err = 0;

	ret = ceph_pool_perm_check(ci, need);
	if (ret < 0)
		return ret;

	while (true) {
		if (endoff > 0)
			check_max_size(&ci->vfs_inode, endoff);

		err = 0;
		_got = 0;
		ret = try_get_cap_refs(ci, need, want, endoff,
				       false, &_got, &err);
		if (ret) {
			if (err == -EAGAIN)
				continue;
			if (err < 0)
				return err;
		} else {
			ret = wait_event_interruptible(ci->i_cap_wq,
					try_get_cap_refs(ci, need, want, endoff,
							 true, &_got, &err));
			if (err == -EAGAIN)
				continue;
			if (err < 0)
				ret = err;
			if (ret < 0)
				return ret;
		}

		if (ci->i_inline_version != CEPH_INLINE_NONE &&
		    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
		    i_size_read(&ci->vfs_inode) > 0) {
			struct page *page =
				find_get_page(ci->vfs_inode.i_mapping, 0);
			if (page) {
				if (PageUptodate(page)) {
					*pinned_page = page;
					break;
				}
				page_cache_release(page);
			}
			/*
			 * drop cap refs first because getattr while
			 * holding * caps refs can cause deadlock.
			 */
			ceph_put_cap_refs(ci, _got);
			_got = 0;

			/*
			 * getattr request will bring inline data into
			 * page cache
			 */
			ret = __ceph_do_getattr(&ci->vfs_inode, NULL,
						CEPH_STAT_CAP_INLINE_DATA,
						true);
			if (ret < 0)
				return ret;
			continue;
		}
		break;
	}

	*got = _got;
	return 0;
}

/*
 * Take cap refs.  Caller must already know we hold at least one ref
 * on the caps in question or we don't know this is safe.
 */
void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps)
{
	spin_lock(&ci->i_ceph_lock);
	__take_cap_refs(ci, caps, false);
	spin_unlock(&ci->i_ceph_lock);
}


/*
 * drop cap_snap that is not associated with any snapshot.
 * we don't need to send FLUSHSNAP message for it.
 */
static int ceph_try_drop_cap_snap(struct ceph_cap_snap *capsnap)
{
	if (!capsnap->need_flush &&
	    !capsnap->writing && !capsnap->dirty_pages) {

		dout("dropping cap_snap %p follows %llu\n",
		     capsnap, capsnap->follows);
		ceph_put_snap_context(capsnap->context);
		list_del(&capsnap->ci_item);
		list_del(&capsnap->flushing_item);
		ceph_put_cap_snap(capsnap);
		return 1;
	}
	return 0;
}

/*
 * Release cap refs.
 *
 * If we released the last ref on any given cap, call ceph_check_caps
 * to release (or schedule a release).
 *
 * If we are releasing a WR cap (from a sync write), finalize any affected
 * cap_snap, and wake up any waiters.
 */
void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
{
	struct inode *inode = &ci->vfs_inode;
	int last = 0, put = 0, flushsnaps = 0, wake = 0;

	spin_lock(&ci->i_ceph_lock);
	if (had & CEPH_CAP_PIN)
		--ci->i_pin_ref;
	if (had & CEPH_CAP_FILE_RD)
		if (--ci->i_rd_ref == 0)
			last++;
	if (had & CEPH_CAP_FILE_CACHE)
		if (--ci->i_rdcache_ref == 0)
			last++;
	if (had & CEPH_CAP_FILE_BUFFER) {
		if (--ci->i_wb_ref == 0) {
			last++;
			put++;
		}
		dout("put_cap_refs %p wb %d -> %d (?)\n",
		     inode, ci->i_wb_ref+1, ci->i_wb_ref);
	}
	if (had & CEPH_CAP_FILE_WR)
		if (--ci->i_wr_ref == 0) {
			last++;
			if (__ceph_have_pending_cap_snap(ci)) {
				struct ceph_cap_snap *capsnap =
					list_last_entry(&ci->i_cap_snaps,
							struct ceph_cap_snap,
							ci_item);
				capsnap->writing = 0;
				if (ceph_try_drop_cap_snap(capsnap))
					put++;
				else if (__ceph_finish_cap_snap(ci, capsnap))
					flushsnaps = 1;
				wake = 1;
			}
			if (ci->i_wrbuffer_ref_head == 0 &&
			    ci->i_dirty_caps == 0 &&
			    ci->i_flushing_caps == 0) {
				BUG_ON(!ci->i_head_snapc);
				ceph_put_snap_context(ci->i_head_snapc);
				ci->i_head_snapc = NULL;
			}
			/* see comment in __ceph_remove_cap() */
			if (!__ceph_is_any_caps(ci) && ci->i_snap_realm)
				drop_inode_snap_realm(ci);
		}
	spin_unlock(&ci->i_ceph_lock);

	dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
	     last ? " last" : "", put ? " put" : "");

	if (last && !flushsnaps)
		ceph_check_caps(ci, 0, NULL);
	else if (flushsnaps)
		ceph_flush_snaps(ci);
	if (wake)
		wake_up_all(&ci->i_cap_wq);
	while (put-- > 0)
		iput(inode);
}

/*
 * Release @nr WRBUFFER refs on dirty pages for the given @snapc snap
 * context.  Adjust per-snap dirty page accounting as appropriate.
 * Once all dirty data for a cap_snap is flushed, flush snapped file
 * metadata back to the MDS.  If we dropped the last ref, call
 * ceph_check_caps.
 */
void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
				struct ceph_snap_context *snapc)
{
	struct inode *inode = &ci->vfs_inode;
	int last = 0;
	int complete_capsnap = 0;
	int drop_capsnap = 0;
	int found = 0;
	struct ceph_cap_snap *capsnap = NULL;

	spin_lock(&ci->i_ceph_lock);
	ci->i_wrbuffer_ref -= nr;
	last = !ci->i_wrbuffer_ref;

	if (ci->i_head_snapc == snapc) {
		ci->i_wrbuffer_ref_head -= nr;
		if (ci->i_wrbuffer_ref_head == 0 &&
		    ci->i_wr_ref == 0 &&
		    ci->i_dirty_caps == 0 &&
		    ci->i_flushing_caps == 0) {
			BUG_ON(!ci->i_head_snapc);
			ceph_put_snap_context(ci->i_head_snapc);
			ci->i_head_snapc = NULL;
		}
		dout("put_wrbuffer_cap_refs on %p head %d/%d -> %d/%d %s\n",
		     inode,
		     ci->i_wrbuffer_ref+nr, ci->i_wrbuffer_ref_head+nr,
		     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
		     last ? " LAST" : "");
	} else {
		list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
			if (capsnap->context == snapc) {
				found = 1;
				break;
			}
		}
		BUG_ON(!found);
		capsnap->dirty_pages -= nr;
		if (capsnap->dirty_pages == 0) {
			complete_capsnap = 1;
			drop_capsnap = ceph_try_drop_cap_snap(capsnap);
		}
		dout("put_wrbuffer_cap_refs on %p cap_snap %p "
		     " snap %lld %d/%d -> %d/%d %s%s\n",
		     inode, capsnap, capsnap->context->seq,
		     ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
		     ci->i_wrbuffer_ref, capsnap->dirty_pages,
		     last ? " (wrbuffer last)" : "",
		     complete_capsnap ? " (complete capsnap)" : "");
	}

	spin_unlock(&ci->i_ceph_lock);

	if (last) {
		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
		iput(inode);
	} else if (complete_capsnap) {
		ceph_flush_snaps(ci);
		wake_up_all(&ci->i_cap_wq);
	}
	if (drop_capsnap)
		iput(inode);
}

/*
 * Invalidate unlinked inode's aliases, so we can drop the inode ASAP.
 */
static void invalidate_aliases(struct inode *inode)
{
	struct dentry *dn, *prev = NULL;

	dout("invalidate_aliases inode %p\n", inode);
	d_prune_aliases(inode);
	/*
	 * For non-directory inode, d_find_alias() only returns
	 * hashed dentry. After calling d_invalidate(), the
	 * dentry becomes unhashed.
	 *
	 * For directory inode, d_find_alias() can return
	 * unhashed dentry. But directory inode should have
	 * one alias at most.
	 */
	while ((dn = d_find_alias(inode))) {
		if (dn == prev) {
			dput(dn);
			break;
		}
		d_invalidate(dn);
		if (prev)
			dput(prev);
		prev = dn;
	}
	if (prev)
		dput(prev);
}

/*
 * Handle a cap GRANT message from the MDS.  (Note that a GRANT may
 * actually be a revocation if it specifies a smaller cap set.)
 *
 * caller holds s_mutex and i_ceph_lock, we drop both.
 */
static void handle_cap_grant(struct ceph_mds_client *mdsc,
			     struct inode *inode, struct ceph_mds_caps *grant,
			     u64 inline_version,
			     void *inline_data, int inline_len,
			     struct ceph_buffer *xattr_buf,
			     struct ceph_mds_session *session,
			     struct ceph_cap *cap, int issued,
			     u32 pool_ns_len)
	__releases(ci->i_ceph_lock)
	__releases(mdsc->snap_rwsem)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int mds = session->s_mds;
	int seq = le32_to_cpu(grant->seq);
	int newcaps = le32_to_cpu(grant->caps);
	int used, wanted, dirty;
	u64 size = le64_to_cpu(grant->size);
	u64 max_size = le64_to_cpu(grant->max_size);
	struct timespec mtime, atime, ctime;
	int check_caps = 0;
	bool wake = false;
	bool writeback = false;
	bool queue_trunc = false;
	bool queue_invalidate = false;
	bool queue_revalidate = false;
	bool deleted_inode = false;
	bool fill_inline = false;

	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
	     inode, cap, mds, seq, ceph_cap_string(newcaps));
	dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
		inode->i_size);


	/*
	 * auth mds of the inode changed. we received the cap export message,
	 * but still haven't received the cap import message. handle_cap_export
	 * updated the new auth MDS' cap.
	 *
	 * "ceph_seq_cmp(seq, cap->seq) <= 0" means we are processing a message
	 * that was sent before the cap import message. So don't remove caps.
	 */
	if (ceph_seq_cmp(seq, cap->seq) <= 0) {
		WARN_ON(cap != ci->i_auth_cap);
		WARN_ON(cap->cap_id != le64_to_cpu(grant->cap_id));
		seq = cap->seq;
		newcaps |= cap->issued;
	}

	/*
	 * If CACHE is being revoked, and we have no dirty buffers,
	 * try to invalidate (once).  (If there are dirty buffers, we
	 * will invalidate _after_ writeback.)
	 */
	if (!S_ISDIR(inode->i_mode) && /* don't invalidate readdir cache */
	    ((cap->issued & ~newcaps) & CEPH_CAP_FILE_CACHE) &&
	    (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 &&
	    !ci->i_wrbuffer_ref) {
		if (try_nonblocking_invalidate(inode)) {
			/* there were locked pages.. invalidate later
			   in a separate thread. */
			if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
				queue_invalidate = true;
				ci->i_rdcache_revoking = ci->i_rdcache_gen;
			}
		}

		ceph_fscache_invalidate(inode);
	}

	/* side effects now are allowed */
	cap->cap_gen = session->s_cap_gen;
	cap->seq = seq;

	__check_cap_issue(ci, cap, newcaps);

	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
		inode->i_mode = le32_to_cpu(grant->mode);
		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
		     from_kuid(&init_user_ns, inode->i_uid),
		     from_kgid(&init_user_ns, inode->i_gid));
	}

	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
	    (issued & CEPH_CAP_LINK_EXCL) == 0) {
		set_nlink(inode, le32_to_cpu(grant->nlink));
		if (inode->i_nlink == 0 &&
		    (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
			deleted_inode = true;
	}

	if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) {
		int len = le32_to_cpu(grant->xattr_len);
		u64 version = le64_to_cpu(grant->xattr_version);

		if (version > ci->i_xattrs.version) {
			dout(" got new xattrs v%llu on %p len %d\n",
			     version, inode, len);
			if (ci->i_xattrs.blob)
				ceph_buffer_put(ci->i_xattrs.blob);
			ci->i_xattrs.blob = ceph_buffer_get(xattr_buf);
			ci->i_xattrs.version = version;
			ceph_forget_all_cached_acls(inode);
		}
	}

	/* Do we need to revalidate our fscache cookie. Don't bother on the
	 * first cache cap as we already validate at cookie creation time. */
	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
		queue_revalidate = true;

	if (newcaps & CEPH_CAP_ANY_RD) {
		/* ctime/mtime/atime? */
		ceph_decode_timespec(&mtime, &grant->mtime);
		ceph_decode_timespec(&atime, &grant->atime);
		ceph_decode_timespec(&ctime, &grant->ctime);
		ceph_fill_file_time(inode, issued,
				    le32_to_cpu(grant->time_warp_seq),
				    &ctime, &mtime, &atime);
	}

	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
		/* file layout may have changed */
		ci->i_layout = grant->layout;
		ci->i_pool_ns_len = pool_ns_len;

		/* size/truncate_seq? */
		queue_trunc = ceph_fill_file_size(inode, issued,
					le32_to_cpu(grant->truncate_seq),
					le64_to_cpu(grant->truncate_size),
					size);
		/* max size increase? */
		if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
			dout("max_size %lld -> %llu\n",
			     ci->i_max_size, max_size);
			ci->i_max_size = max_size;
			if (max_size >= ci->i_wanted_max_size) {
				ci->i_wanted_max_size = 0;  /* reset */
				ci->i_requested_max_size = 0;
			}
			wake = true;
		}
	}

	/* check cap bits */
	wanted = __ceph_caps_wanted(ci);
	used = __ceph_caps_used(ci);
	dirty = __ceph_caps_dirty(ci);
	dout(" my wanted = %s, used = %s, dirty %s\n",
	     ceph_cap_string(wanted),
	     ceph_cap_string(used),
	     ceph_cap_string(dirty));
	if (wanted != le32_to_cpu(grant->wanted)) {
		dout("mds wanted %s -> %s\n",
		     ceph_cap_string(le32_to_cpu(grant->wanted)),
		     ceph_cap_string(wanted));
		/* imported cap may not have correct mds_wanted */
		if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT)
			check_caps = 1;
	}

	/* revocation, grant, or no-op? */
	if (cap->issued & ~newcaps) {
		int revoking = cap->issued & ~newcaps;

		dout("revocation: %s -> %s (revoking %s)\n",
		     ceph_cap_string(cap->issued),
		     ceph_cap_string(newcaps),
		     ceph_cap_string(revoking));
		if (revoking & used & CEPH_CAP_FILE_BUFFER)
			writeback = true;  /* initiate writeback; will delay ack */
		else if (revoking == CEPH_CAP_FILE_CACHE &&
			 (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 &&
			 queue_invalidate)
			; /* do nothing yet, invalidation will be queued */
		else if (cap == ci->i_auth_cap)
			check_caps = 1; /* check auth cap only */
		else
			check_caps = 2; /* check all caps */
		cap->issued = newcaps;
		cap->implemented |= newcaps;
	} else if (cap->issued == newcaps) {
		dout("caps unchanged: %s -> %s\n",
		     ceph_cap_string(cap->issued), ceph_cap_string(newcaps));
	} else {
		dout("grant: %s -> %s\n", ceph_cap_string(cap->issued),
		     ceph_cap_string(newcaps));
		/* non-auth MDS is revoking the newly grant caps ? */
		if (cap == ci->i_auth_cap &&
		    __ceph_caps_revoking_other(ci, cap, newcaps))
		    check_caps = 2;

		cap->issued = newcaps;
		cap->implemented |= newcaps; /* add bits only, to
					      * avoid stepping on a
					      * pending revocation */
		wake = true;
	}
	BUG_ON(cap->issued & ~cap->implemented);

	if (inline_version > 0 && inline_version >= ci->i_inline_version) {
		ci->i_inline_version = inline_version;
		if (ci->i_inline_version != CEPH_INLINE_NONE &&
		    (newcaps & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)))
			fill_inline = true;
	}

	spin_unlock(&ci->i_ceph_lock);

	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
		kick_flushing_inode_caps(mdsc, session, inode);
		up_read(&mdsc->snap_rwsem);
		if (newcaps & ~issued)
			wake = true;
	}

	if (fill_inline)
		ceph_fill_inline_data(inode, NULL, inline_data, inline_len);

	if (queue_trunc) {
		ceph_queue_vmtruncate(inode);
		ceph_queue_revalidate(inode);
	} else if (queue_revalidate)
		ceph_queue_revalidate(inode);

	if (writeback)
		/*
		 * queue inode for writeback: we can't actually call
		 * filemap_write_and_wait, etc. from message handler
		 * context.
		 */
		ceph_queue_writeback(inode);
	if (queue_invalidate)
		ceph_queue_invalidate(inode);
	if (deleted_inode)
		invalidate_aliases(inode);
	if (wake)
		wake_up_all(&ci->i_cap_wq);

	if (check_caps == 1)
		ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_AUTHONLY,
				session);
	else if (check_caps == 2)
		ceph_check_caps(ci, CHECK_CAPS_NODELAY, session);
	else
		mutex_unlock(&session->s_mutex);
}

/*
 * Handle FLUSH_ACK from MDS, indicating that metadata we sent to the
 * MDS has been safely committed.
 */
static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
				 struct ceph_mds_caps *m,
				 struct ceph_mds_session *session,
				 struct ceph_cap *cap)
	__releases(ci->i_ceph_lock)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
	struct ceph_cap_flush *cf;
	struct rb_node *n;
	LIST_HEAD(to_remove);
	unsigned seq = le32_to_cpu(m->seq);
	int dirty = le32_to_cpu(m->dirty);
	int cleaned = 0;
	int drop = 0;

	n = rb_first(&ci->i_cap_flush_tree);
	while (n) {
		cf = rb_entry(n, struct ceph_cap_flush, i_node);
		n = rb_next(&cf->i_node);
		if (cf->tid == flush_tid)
			cleaned = cf->caps;
		if (cf->tid <= flush_tid) {
			rb_erase(&cf->i_node, &ci->i_cap_flush_tree);
			list_add_tail(&cf->list, &to_remove);
		} else {
			cleaned &= ~cf->caps;
			if (!cleaned)
				break;
		}
	}

	dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s,"
	     " flushing %s -> %s\n",
	     inode, session->s_mds, seq, ceph_cap_string(dirty),
	     ceph_cap_string(cleaned), ceph_cap_string(ci->i_flushing_caps),
	     ceph_cap_string(ci->i_flushing_caps & ~cleaned));

	if (list_empty(&to_remove) && !cleaned)
		goto out;

	ci->i_flushing_caps &= ~cleaned;

	spin_lock(&mdsc->cap_dirty_lock);

	if (!list_empty(&to_remove)) {
		list_for_each_entry(cf, &to_remove, list)
			rb_erase(&cf->g_node, &mdsc->cap_flush_tree);

		n = rb_first(&mdsc->cap_flush_tree);
		cf = n ? rb_entry(n, struct ceph_cap_flush, g_node) : NULL;
		if (!cf || cf->tid > flush_tid)
			wake_up_all(&mdsc->cap_flushing_wq);
	}

	if (ci->i_flushing_caps == 0) {
		list_del_init(&ci->i_flushing_item);
		if (!list_empty(&session->s_cap_flushing))
			dout(" mds%d still flushing cap on %p\n",
			     session->s_mds,
			     &list_entry(session->s_cap_flushing.next,
					 struct ceph_inode_info,
					 i_flushing_item)->vfs_inode);
		mdsc->num_cap_flushing--;
		dout(" inode %p now !flushing\n", inode);

		if (ci->i_dirty_caps == 0) {
			dout(" inode %p now clean\n", inode);
			BUG_ON(!list_empty(&ci->i_dirty_item));
			drop = 1;
			if (ci->i_wr_ref == 0 &&
			    ci->i_wrbuffer_ref_head == 0) {
				BUG_ON(!ci->i_head_snapc);
				ceph_put_snap_context(ci->i_head_snapc);
				ci->i_head_snapc = NULL;
			}
		} else {
			BUG_ON(list_empty(&ci->i_dirty_item));
		}
	}
	spin_unlock(&mdsc->cap_dirty_lock);
	wake_up_all(&ci->i_cap_wq);

out:
	spin_unlock(&ci->i_ceph_lock);

	while (!list_empty(&to_remove)) {
		cf = list_first_entry(&to_remove,
				      struct ceph_cap_flush, list);
		list_del(&cf->list);
		ceph_free_cap_flush(cf);
	}
	if (drop)
		iput(inode);
}

/*
 * Handle FLUSHSNAP_ACK.  MDS has flushed snap data to disk and we can
 * throw away our cap_snap.
 *
 * Caller hold s_mutex.
 */
static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
				     struct ceph_mds_caps *m,
				     struct ceph_mds_session *session)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
	u64 follows = le64_to_cpu(m->snap_follows);
	struct ceph_cap_snap *capsnap;
	int drop = 0;

	dout("handle_cap_flushsnap_ack inode %p ci %p mds%d follows %lld\n",
	     inode, ci, session->s_mds, follows);

	spin_lock(&ci->i_ceph_lock);
	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
		if (capsnap->follows == follows) {
			if (capsnap->flush_tid != flush_tid) {
				dout(" cap_snap %p follows %lld tid %lld !="
				     " %lld\n", capsnap, follows,
				     flush_tid, capsnap->flush_tid);
				break;
			}
			WARN_ON(capsnap->dirty_pages || capsnap->writing);
			dout(" removing %p cap_snap %p follows %lld\n",
			     inode, capsnap, follows);
			ceph_put_snap_context(capsnap->context);
			list_del(&capsnap->ci_item);
			list_del(&capsnap->flushing_item);
			ceph_put_cap_snap(capsnap);
			wake_up_all(&mdsc->cap_flushing_wq);
			drop = 1;
			break;
		} else {
			dout(" skipping cap_snap %p follows %lld\n",
			     capsnap, capsnap->follows);
		}
	}
	spin_unlock(&ci->i_ceph_lock);
	if (drop)
		iput(inode);
}

/*
 * Handle TRUNC from MDS, indicating file truncation.
 *
 * caller hold s_mutex.
 */
static void handle_cap_trunc(struct inode *inode,
			     struct ceph_mds_caps *trunc,
			     struct ceph_mds_session *session)
	__releases(ci->i_ceph_lock)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int mds = session->s_mds;
	int seq = le32_to_cpu(trunc->seq);
	u32 truncate_seq = le32_to_cpu(trunc->truncate_seq);
	u64 truncate_size = le64_to_cpu(trunc->truncate_size);
	u64 size = le64_to_cpu(trunc->size);
	int implemented = 0;
	int dirty = __ceph_caps_dirty(ci);
	int issued = __ceph_caps_issued(ceph_inode(inode), &implemented);
	int queue_trunc = 0;

	issued |= implemented | dirty;

	dout("handle_cap_trunc inode %p mds%d seq %d to %lld seq %d\n",
	     inode, mds, seq, truncate_size, truncate_seq);
	queue_trunc = ceph_fill_file_size(inode, issued,
					  truncate_seq, truncate_size, size);
	spin_unlock(&ci->i_ceph_lock);

	if (queue_trunc) {
		ceph_queue_vmtruncate(inode);
		ceph_fscache_invalidate(inode);
	}
}

/*
 * Handle EXPORT from MDS.  Cap is being migrated _from_ this mds to a
 * different one.  If we are the most recent migration we've seen (as
 * indicated by mseq), make note of the migrating cap bits for the
 * duration (until we see the corresponding IMPORT).
 *
 * caller holds s_mutex
 */
static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
			      struct ceph_mds_cap_peer *ph,
			      struct ceph_mds_session *session)
{
	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
	struct ceph_mds_session *tsession = NULL;
	struct ceph_cap *cap, *tcap, *new_cap = NULL;
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 t_cap_id;
	unsigned mseq = le32_to_cpu(ex->migrate_seq);
	unsigned t_seq, t_mseq;
	int target, issued;
	int mds = session->s_mds;

	if (ph) {
		t_cap_id = le64_to_cpu(ph->cap_id);
		t_seq = le32_to_cpu(ph->seq);
		t_mseq = le32_to_cpu(ph->mseq);
		target = le32_to_cpu(ph->mds);
	} else {
		t_cap_id = t_seq = t_mseq = 0;
		target = -1;
	}

	dout("handle_cap_export inode %p ci %p mds%d mseq %d target %d\n",
	     inode, ci, mds, mseq, target);
retry:
	spin_lock(&ci->i_ceph_lock);
	cap = __get_cap_for_mds(ci, mds);
	if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
		goto out_unlock;

	if (target < 0) {
		__ceph_remove_cap(cap, false);
		goto out_unlock;
	}

	/*
	 * now we know we haven't received the cap import message yet
	 * because the exported cap still exist.
	 */

	issued = cap->issued;
	WARN_ON(issued != cap->implemented);

	tcap = __get_cap_for_mds(ci, target);
	if (tcap) {
		/* already have caps from the target */
		if (tcap->cap_id != t_cap_id ||
		    ceph_seq_cmp(tcap->seq, t_seq) < 0) {
			dout(" updating import cap %p mds%d\n", tcap, target);
			tcap->cap_id = t_cap_id;
			tcap->seq = t_seq - 1;
			tcap->issue_seq = t_seq - 1;
			tcap->mseq = t_mseq;
			tcap->issued |= issued;
			tcap->implemented |= issued;
			if (cap == ci->i_auth_cap)
				ci->i_auth_cap = tcap;
			if (ci->i_flushing_caps && ci->i_auth_cap == tcap) {
				spin_lock(&mdsc->cap_dirty_lock);
				list_move_tail(&ci->i_flushing_item,
					       &tcap->session->s_cap_flushing);
				spin_unlock(&mdsc->cap_dirty_lock);
			}
		}
		__ceph_remove_cap(cap, false);
		goto out_unlock;
	} else if (tsession) {
		/* add placeholder for the export tagert */
		int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
		ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
			     t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);

		__ceph_remove_cap(cap, false);
		goto out_unlock;
	}

	spin_unlock(&ci->i_ceph_lock);
	mutex_unlock(&session->s_mutex);

	/* open target session */
	tsession = ceph_mdsc_open_export_target_session(mdsc, target);
	if (!IS_ERR(tsession)) {
		if (mds > target) {
			mutex_lock(&session->s_mutex);
			mutex_lock_nested(&tsession->s_mutex,
					  SINGLE_DEPTH_NESTING);
		} else {
			mutex_lock(&tsession->s_mutex);
			mutex_lock_nested(&session->s_mutex,
					  SINGLE_DEPTH_NESTING);
		}
		new_cap = ceph_get_cap(mdsc, NULL);
	} else {
		WARN_ON(1);
		tsession = NULL;
		target = -1;
	}
	goto retry;

out_unlock:
	spin_unlock(&ci->i_ceph_lock);
	mutex_unlock(&session->s_mutex);
	if (tsession) {
		mutex_unlock(&tsession->s_mutex);
		ceph_put_mds_session(tsession);
	}
	if (new_cap)
		ceph_put_cap(mdsc, new_cap);
}

/*
 * Handle cap IMPORT.
 *
 * caller holds s_mutex. acquires i_ceph_lock
 */
static void handle_cap_import(struct ceph_mds_client *mdsc,
			      struct inode *inode, struct ceph_mds_caps *im,
			      struct ceph_mds_cap_peer *ph,
			      struct ceph_mds_session *session,
			      struct ceph_cap **target_cap, int *old_issued)
	__acquires(ci->i_ceph_lock)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap *cap, *ocap, *new_cap = NULL;
	int mds = session->s_mds;
	int issued;
	unsigned caps = le32_to_cpu(im->caps);
	unsigned wanted = le32_to_cpu(im->wanted);
	unsigned seq = le32_to_cpu(im->seq);
	unsigned mseq = le32_to_cpu(im->migrate_seq);
	u64 realmino = le64_to_cpu(im->realm);
	u64 cap_id = le64_to_cpu(im->cap_id);
	u64 p_cap_id;
	int peer;

	if (ph) {
		p_cap_id = le64_to_cpu(ph->cap_id);
		peer = le32_to_cpu(ph->mds);
	} else {
		p_cap_id = 0;
		peer = -1;
	}

	dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
	     inode, ci, mds, mseq, peer);

retry:
	spin_lock(&ci->i_ceph_lock);
	cap = __get_cap_for_mds(ci, mds);
	if (!cap) {
		if (!new_cap) {
			spin_unlock(&ci->i_ceph_lock);
			new_cap = ceph_get_cap(mdsc, NULL);
			goto retry;
		}
		cap = new_cap;
	} else {
		if (new_cap) {
			ceph_put_cap(mdsc, new_cap);
			new_cap = NULL;
		}
	}

	__ceph_caps_issued(ci, &issued);
	issued |= __ceph_caps_dirty(ci);

	ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
		     realmino, CEPH_CAP_FLAG_AUTH, &new_cap);

	ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
	if (ocap && ocap->cap_id == p_cap_id) {
		dout(" remove export cap %p mds%d flags %d\n",
		     ocap, peer, ph->flags);
		if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
		    (ocap->seq != le32_to_cpu(ph->seq) ||
		     ocap->mseq != le32_to_cpu(ph->mseq))) {
			pr_err("handle_cap_import: mismatched seq/mseq: "
			       "ino (%llx.%llx) mds%d seq %d mseq %d "
			       "importer mds%d has peer seq %d mseq %d\n",
			       ceph_vinop(inode), peer, ocap->seq,
			       ocap->mseq, mds, le32_to_cpu(ph->seq),
			       le32_to_cpu(ph->mseq));
		}
		__ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
	}

	/* make sure we re-request max_size, if necessary */
	ci->i_wanted_max_size = 0;
	ci->i_requested_max_size = 0;

	*old_issued = issued;
	*target_cap = cap;
}

/*
 * Handle a caps message from the MDS.
 *
 * Identify the appropriate session, inode, and call the right handler
 * based on the cap op.
 */
void ceph_handle_caps(struct ceph_mds_session *session,
		      struct ceph_msg *msg)
{
	struct ceph_mds_client *mdsc = session->s_mdsc;
	struct super_block *sb = mdsc->fsc->sb;
	struct inode *inode;
	struct ceph_inode_info *ci;
	struct ceph_cap *cap;
	struct ceph_mds_caps *h;
	struct ceph_mds_cap_peer *peer = NULL;
	struct ceph_snap_realm *realm;
	int mds = session->s_mds;
	int op, issued;
	u32 seq, mseq;
	struct ceph_vino vino;
	u64 cap_id;
	u64 size, max_size;
	u64 tid;
	u64 inline_version = 0;
	void *inline_data = NULL;
	u32  inline_len = 0;
	void *snaptrace;
	size_t snaptrace_len;
	u32 pool_ns_len = 0;
	void *p, *end;

	dout("handle_caps from mds%d\n", mds);

	/* decode */
	end = msg->front.iov_base + msg->front.iov_len;
	tid = le64_to_cpu(msg->hdr.tid);
	if (msg->front.iov_len < sizeof(*h))
		goto bad;
	h = msg->front.iov_base;
	op = le32_to_cpu(h->op);
	vino.ino = le64_to_cpu(h->ino);
	vino.snap = CEPH_NOSNAP;
	cap_id = le64_to_cpu(h->cap_id);
	seq = le32_to_cpu(h->seq);
	mseq = le32_to_cpu(h->migrate_seq);
	size = le64_to_cpu(h->size);
	max_size = le64_to_cpu(h->max_size);

	snaptrace = h + 1;
	snaptrace_len = le32_to_cpu(h->snap_trace_len);
	p = snaptrace + snaptrace_len;

	if (le16_to_cpu(msg->hdr.version) >= 2) {
		u32 flock_len;
		ceph_decode_32_safe(&p, end, flock_len, bad);
		if (p + flock_len > end)
			goto bad;
		p += flock_len;
	}

	if (le16_to_cpu(msg->hdr.version) >= 3) {
		if (op == CEPH_CAP_OP_IMPORT) {
			if (p + sizeof(*peer) > end)
				goto bad;
			peer = p;
			p += sizeof(*peer);
		} else if (op == CEPH_CAP_OP_EXPORT) {
			/* recorded in unused fields */
			peer = (void *)&h->size;
		}
	}

	if (le16_to_cpu(msg->hdr.version) >= 4) {
		ceph_decode_64_safe(&p, end, inline_version, bad);
		ceph_decode_32_safe(&p, end, inline_len, bad);
		if (p + inline_len > end)
			goto bad;
		inline_data = p;
		p += inline_len;
	}

	if (le16_to_cpu(msg->hdr.version) >= 8) {
		u64 flush_tid;
		u32 caller_uid, caller_gid;
		u32 osd_epoch_barrier;
		/* version >= 5 */
		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
		/* version >= 6 */
		ceph_decode_64_safe(&p, end, flush_tid, bad);
		/* version >= 7 */
		ceph_decode_32_safe(&p, end, caller_uid, bad);
		ceph_decode_32_safe(&p, end, caller_gid, bad);
		/* version >= 8 */
		ceph_decode_32_safe(&p, end, pool_ns_len, bad);
	}

	/* lookup ino */
	inode = ceph_find_inode(sb, vino);
	ci = ceph_inode(inode);
	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
	     vino.snap, inode);

	mutex_lock(&session->s_mutex);
	session->s_seq++;
	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
	     (unsigned)seq);

	if (!inode) {
		dout(" i don't have ino %llx\n", vino.ino);

		if (op == CEPH_CAP_OP_IMPORT) {
			cap = ceph_get_cap(mdsc, NULL);
			cap->cap_ino = vino.ino;
			cap->queue_release = 1;
			cap->cap_id = cap_id;
			cap->mseq = mseq;
			cap->seq = seq;
			spin_lock(&session->s_cap_lock);
			list_add_tail(&cap->session_caps,
					&session->s_cap_releases);
			session->s_num_cap_releases++;
			spin_unlock(&session->s_cap_lock);
		}
		goto flush_cap_releases;
	}

	/* these will work even if we don't have a cap yet */
	switch (op) {
	case CEPH_CAP_OP_FLUSHSNAP_ACK:
		handle_cap_flushsnap_ack(inode, tid, h, session);
		goto done;

	case CEPH_CAP_OP_EXPORT:
		handle_cap_export(inode, h, peer, session);
		goto done_unlocked;

	case CEPH_CAP_OP_IMPORT:
		realm = NULL;
		if (snaptrace_len) {
			down_write(&mdsc->snap_rwsem);
			ceph_update_snap_trace(mdsc, snaptrace,
					       snaptrace + snaptrace_len,
					       false, &realm);
			downgrade_write(&mdsc->snap_rwsem);
		} else {
			down_read(&mdsc->snap_rwsem);
		}
		handle_cap_import(mdsc, inode, h, peer, session,
				  &cap, &issued);
		handle_cap_grant(mdsc, inode, h,
				 inline_version, inline_data, inline_len,
				 msg->middle, session, cap, issued,
				 pool_ns_len);
		if (realm)
			ceph_put_snap_realm(mdsc, realm);
		goto done_unlocked;
	}

	/* the rest require a cap */
	spin_lock(&ci->i_ceph_lock);
	cap = __get_cap_for_mds(ceph_inode(inode), mds);
	if (!cap) {
		dout(" no cap on %p ino %llx.%llx from mds%d\n",
		     inode, ceph_ino(inode), ceph_snap(inode), mds);
		spin_unlock(&ci->i_ceph_lock);
		goto flush_cap_releases;
	}

	/* note that each of these drops i_ceph_lock for us */
	switch (op) {
	case CEPH_CAP_OP_REVOKE:
	case CEPH_CAP_OP_GRANT:
		__ceph_caps_issued(ci, &issued);
		issued |= __ceph_caps_dirty(ci);
		handle_cap_grant(mdsc, inode, h,
				 inline_version, inline_data, inline_len,
				 msg->middle, session, cap, issued,
				 pool_ns_len);
		goto done_unlocked;

	case CEPH_CAP_OP_FLUSH_ACK:
		handle_cap_flush_ack(inode, tid, h, session, cap);
		break;

	case CEPH_CAP_OP_TRUNC:
		handle_cap_trunc(inode, h, session);
		break;

	default:
		spin_unlock(&ci->i_ceph_lock);
		pr_err("ceph_handle_caps: unknown cap op %d %s\n", op,
		       ceph_cap_op_name(op));
	}

	goto done;

flush_cap_releases:
	/*
	 * send any cap release message to try to move things
	 * along for the mds (who clearly thinks we still have this
	 * cap).
	 */
	ceph_send_cap_releases(mdsc, session);

done:
	mutex_unlock(&session->s_mutex);
done_unlocked:
	iput(inode);
	return;

bad:
	pr_err("ceph_handle_caps: corrupt message\n");
	ceph_msg_dump(msg);
	return;
}

/*
 * Delayed work handler to process end of delayed cap release LRU list.
 */
void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
{
	struct ceph_inode_info *ci;
	int flags = CHECK_CAPS_NODELAY;

	dout("check_delayed_caps\n");
	while (1) {
		spin_lock(&mdsc->cap_delay_lock);
		if (list_empty(&mdsc->cap_delay_list))
			break;
		ci = list_first_entry(&mdsc->cap_delay_list,
				      struct ceph_inode_info,
				      i_cap_delay_list);
		if ((ci->i_ceph_flags & CEPH_I_FLUSH) == 0 &&
		    time_before(jiffies, ci->i_hold_caps_max))
			break;
		list_del_init(&ci->i_cap_delay_list);
		spin_unlock(&mdsc->cap_delay_lock);
		dout("check_delayed_caps on %p\n", &ci->vfs_inode);
		ceph_check_caps(ci, flags, NULL);
	}
	spin_unlock(&mdsc->cap_delay_lock);
}

/*
 * Flush all dirty caps to the mds
 */
void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
{
	struct ceph_inode_info *ci;
	struct inode *inode;

	dout("flush_dirty_caps\n");
	spin_lock(&mdsc->cap_dirty_lock);
	while (!list_empty(&mdsc->cap_dirty)) {
		ci = list_first_entry(&mdsc->cap_dirty, struct ceph_inode_info,
				      i_dirty_item);
		inode = &ci->vfs_inode;
		ihold(inode);
		dout("flush_dirty_caps %p\n", inode);
		spin_unlock(&mdsc->cap_dirty_lock);
		ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH, NULL);
		iput(inode);
		spin_lock(&mdsc->cap_dirty_lock);
	}
	spin_unlock(&mdsc->cap_dirty_lock);
	dout("flush_dirty_caps done\n");
}

/*
 * Drop open file reference.  If we were the last open file,
 * we may need to release capabilities to the MDS (or schedule
 * their delayed release).
 */
void ceph_put_fmode(struct ceph_inode_info *ci, int fmode)
{
	struct inode *inode = &ci->vfs_inode;
	int last = 0;

	spin_lock(&ci->i_ceph_lock);
	dout("put_fmode %p fmode %d %d -> %d\n", inode, fmode,
	     ci->i_nr_by_mode[fmode], ci->i_nr_by_mode[fmode]-1);
	BUG_ON(ci->i_nr_by_mode[fmode] == 0);
	if (--ci->i_nr_by_mode[fmode] == 0)
		last++;
	spin_unlock(&ci->i_ceph_lock);

	if (last && ci->i_vino.snap == CEPH_NOSNAP)
		ceph_check_caps(ci, 0, NULL);
}

/*
 * Helpers for embedding cap and dentry lease releases into mds
 * requests.
 *
 * @force is used by dentry_release (below) to force inclusion of a
 * record for the directory inode, even when there aren't any caps to
 * drop.
 */
int ceph_encode_inode_release(void **p, struct inode *inode,
			      int mds, int drop, int unless, int force)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap *cap;
	struct ceph_mds_request_release *rel = *p;
	int used, dirty;
	int ret = 0;

	spin_lock(&ci->i_ceph_lock);
	used = __ceph_caps_used(ci);
	dirty = __ceph_caps_dirty(ci);

	dout("encode_inode_release %p mds%d used|dirty %s drop %s unless %s\n",
	     inode, mds, ceph_cap_string(used|dirty), ceph_cap_string(drop),
	     ceph_cap_string(unless));

	/* only drop unused, clean caps */
	drop &= ~(used | dirty);

	cap = __get_cap_for_mds(ci, mds);
	if (cap && __cap_is_valid(cap)) {
		if (force ||
		    ((cap->issued & drop) &&
		     (cap->issued & unless) == 0)) {
			if ((cap->issued & drop) &&
			    (cap->issued & unless) == 0) {
				int wanted = __ceph_caps_wanted(ci);
				if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0)
					wanted |= cap->mds_wanted;
				dout("encode_inode_release %p cap %p "
				     "%s -> %s, wanted %s -> %s\n", inode, cap,
				     ceph_cap_string(cap->issued),
				     ceph_cap_string(cap->issued & ~drop),
				     ceph_cap_string(cap->mds_wanted),
				     ceph_cap_string(wanted));

				cap->issued &= ~drop;
				cap->implemented &= ~drop;
				cap->mds_wanted = wanted;
			} else {
				dout("encode_inode_release %p cap %p %s"
				     " (force)\n", inode, cap,
				     ceph_cap_string(cap->issued));
			}

			rel->ino = cpu_to_le64(ceph_ino(inode));
			rel->cap_id = cpu_to_le64(cap->cap_id);
			rel->seq = cpu_to_le32(cap->seq);
			rel->issue_seq = cpu_to_le32(cap->issue_seq);
			rel->mseq = cpu_to_le32(cap->mseq);
			rel->caps = cpu_to_le32(cap->implemented);
			rel->wanted = cpu_to_le32(cap->mds_wanted);
			rel->dname_len = 0;
			rel->dname_seq = 0;
			*p += sizeof(*rel);
			ret = 1;
		} else {
			dout("encode_inode_release %p cap %p %s\n",
			     inode, cap, ceph_cap_string(cap->issued));
		}
	}
	spin_unlock(&ci->i_ceph_lock);
	return ret;
}

int ceph_encode_dentry_release(void **p, struct dentry *dentry,
			       int mds, int drop, int unless)
{
	struct inode *dir = d_inode(dentry->d_parent);
	struct ceph_mds_request_release *rel = *p;
	struct ceph_dentry_info *di = ceph_dentry(dentry);
	int force = 0;
	int ret;

	/*
	 * force an record for the directory caps if we have a dentry lease.
	 * this is racy (can't take i_ceph_lock and d_lock together), but it
	 * doesn't have to be perfect; the mds will revoke anything we don't
	 * release.
	 */
	spin_lock(&dentry->d_lock);
	if (di->lease_session && di->lease_session->s_mds == mds)
		force = 1;
	spin_unlock(&dentry->d_lock);

	ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force);

	spin_lock(&dentry->d_lock);
	if (ret && di->lease_session && di->lease_session->s_mds == mds) {
		dout("encode_dentry_release %p mds%d seq %d\n",
		     dentry, mds, (int)di->lease_seq);
		rel->dname_len = cpu_to_le32(dentry->d_name.len);
		memcpy(*p, dentry->d_name.name, dentry->d_name.len);
		*p += dentry->d_name.len;
		rel->dname_seq = cpu_to_le32(di->lease_seq);
		__ceph_mdsc_drop_dentry_lease(dentry);
	}
	spin_unlock(&dentry->d_lock);
	return ret;
}