summaryrefslogtreecommitdiffstats
path: root/fs/namei.c
blob: e0624e2f0bba6f9efe150c43776b636519d845f9 (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
/*
 *  linux/fs/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * Some corrections by tytso.
 */

/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
 * lookup logic.
 */
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/ima.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
#include <linux/device_cgroup.h>
#include <linux/fs_struct.h>
#include <asm/uaccess.h>

#include "internal.h"

/* [Feb-1997 T. Schoebel-Theuer]
 * Fundamental changes in the pathname lookup mechanisms (namei)
 * were necessary because of omirr.  The reason is that omirr needs
 * to know the _real_ pathname, not the user-supplied one, in case
 * of symlinks (and also when transname replacements occur).
 *
 * The new code replaces the old recursive symlink resolution with
 * an iterative one (in case of non-nested symlink chains).  It does
 * this with calls to <fs>_follow_link().
 * As a side effect, dir_namei(), _namei() and follow_link() are now 
 * replaced with a single function lookup_dentry() that can handle all 
 * the special cases of the former code.
 *
 * With the new dcache, the pathname is stored at each inode, at least as
 * long as the refcount of the inode is positive.  As a side effect, the
 * size of the dcache depends on the inode cache and thus is dynamic.
 *
 * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
 * resolution to correspond with current state of the code.
 *
 * Note that the symlink resolution is not *completely* iterative.
 * There is still a significant amount of tail- and mid- recursion in
 * the algorithm.  Also, note that <fs>_readlink() is not used in
 * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
 * may return different results than <fs>_follow_link().  Many virtual
 * filesystems (including /proc) exhibit this behavior.
 */

/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
 * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
 * and the name already exists in form of a symlink, try to create the new
 * name indicated by the symlink. The old code always complained that the
 * name already exists, due to not following the symlink even if its target
 * is nonexistent.  The new semantics affects also mknod() and link() when
 * the name is a symlink pointing to a non-existent name.
 *
 * I don't know which semantics is the right one, since I have no access
 * to standards. But I found by trial that HP-UX 9.0 has the full "new"
 * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
 * "old" one. Personally, I think the new semantics is much more logical.
 * Note that "ln old new" where "new" is a symlink pointing to a non-existing
 * file does succeed in both HP-UX and SunOs, but not in Solaris
 * and in the old Linux semantics.
 */

/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
 * semantics.  See the comments in "open_namei" and "do_link" below.
 *
 * [10-Sep-98 Alan Modra] Another symlink change.
 */

/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
 *	inside the path - always follow.
 *	in the last component in creation/removal/renaming - never follow.
 *	if LOOKUP_FOLLOW passed - follow.
 *	if the pathname has trailing slashes - follow.
 *	otherwise - don't follow.
 * (applied in that order).
 *
 * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
 * restored for 2.4. This is the last surviving part of old 4.2BSD bug.
 * During the 2.4 we need to fix the userland stuff depending on it -
 * hopefully we will be able to get rid of that wart in 2.5. So far only
 * XEmacs seems to be relying on it...
 */
/*
 * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
 * implemented.  Let's see if raised priority of ->s_vfs_rename_mutex gives
 * any extra contention...
 */

/* In order to reduce some races, while at the same time doing additional
 * checking and hopefully speeding things up, we copy filenames to the
 * kernel data space before using them..
 *
 * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
 * PATH_MAX includes the nul terminator --RR.
 */
static int do_getname(const char __user *filename, char *page)
{
	int retval;
	unsigned long len = PATH_MAX;

	if (!segment_eq(get_fs(), KERNEL_DS)) {
		if ((unsigned long) filename >= TASK_SIZE)
			return -EFAULT;
		if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
			len = TASK_SIZE - (unsigned long) filename;
	}

	retval = strncpy_from_user(page, filename, len);
	if (retval > 0) {
		if (retval < len)
			return 0;
		return -ENAMETOOLONG;
	} else if (!retval)
		retval = -ENOENT;
	return retval;
}

static char *getname_flags(const char __user * filename, int flags)
{
	char *tmp, *result;

	result = ERR_PTR(-ENOMEM);
	tmp = __getname();
	if (tmp)  {
		int retval = do_getname(filename, tmp);

		result = tmp;
		if (retval < 0) {
			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
				__putname(tmp);
				result = ERR_PTR(retval);
			}
		}
	}
	audit_getname(result);
	return result;
}

char *getname(const char __user * filename)
{
	return getname_flags(filename, 0);
}

#ifdef CONFIG_AUDITSYSCALL
void putname(const char *name)
{
	if (unlikely(!audit_dummy_context()))
		audit_putname(name);
	else
		__putname(name);
}
EXPORT_SYMBOL(putname);
#endif

/*
 * This does basic POSIX ACL permission checking
 */
static int acl_permission_check(struct inode *inode, int mask, unsigned int flags)
{
	int (*check_acl)(struct inode *inode, int mask, unsigned int flags);
	unsigned int mode = inode->i_mode;

	mask &= MAY_READ | MAY_WRITE | MAY_EXEC | MAY_NOT_BLOCK;

	if (current_user_ns() != inode_userns(inode))
		goto other_perms;

	if (current_fsuid() == inode->i_uid)
		mode >>= 6;
	else {
		check_acl = inode->i_op->check_acl;
		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
			int error = check_acl(inode, mask, flags);
			if (error != -EAGAIN)
				return error;
		}

		if (in_group_p(inode->i_gid))
			mode >>= 3;
	}

other_perms:
	/*
	 * If the DACs are ok we don't need any capability check.
	 */
	if ((mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
		return 0;
	return -EACCES;
}

/**
 * generic_permission -  check for access rights on a Posix-like filesystem
 * @inode:	inode to check access rights for
 * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 * @flags:	IPERM_FLAG_ flags.
 *
 * Used to check for read/write/execute permissions on a file.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things.
 *
 * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
 * request cannot be satisfied (eg. requires blocking or too much complexity).
 * It would then be called again in ref-walk mode.
 */
int generic_permission(struct inode *inode, int mask, unsigned int flags)
{
	int ret;

	/*
	 * Do the basic POSIX ACL permission checks.
	 */
	ret = acl_permission_check(inode, mask, flags);
	if (ret != -EACCES)
		return ret;

	/*
	 * Read/write DACs are always overridable.
	 * Executable DACs are overridable for all directories and
	 * for non-directories that have least one exec bit set.
	 */
	if (!(mask & MAY_EXEC) || execute_ok(inode))
		if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
			return 0;

	/*
	 * Searching includes executable on directories, else just read.
	 */
	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
	if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
		if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
			return 0;

	return -EACCES;
}

/**
 * inode_permission  -  check for access rights to a given inode
 * @inode:	inode to check permission on
 * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Used to check for read/write/execute permissions on an inode.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things.
 */
int inode_permission(struct inode *inode, int mask)
{
	int retval;

	if (mask & MAY_WRITE) {
		umode_t mode = inode->i_mode;

		/*
		 * Nobody gets write access to a read-only fs.
		 */
		if (IS_RDONLY(inode) &&
		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
			return -EROFS;

		/*
		 * Nobody gets write access to an immutable file.
		 */
		if (IS_IMMUTABLE(inode))
			return -EACCES;
	}

	if (inode->i_op->permission)
		retval = inode->i_op->permission(inode, mask, 0);
	else
		retval = generic_permission(inode, mask, 0);

	if (retval)
		return retval;

	retval = devcgroup_inode_permission(inode, mask);
	if (retval)
		return retval;

	return security_inode_permission(inode, mask);
}

/**
 * exec_permission  -  check for right to do lookups in a given directory
 * @inode:	inode to check permission on
 * @flags:	IPERM_FLAG_ flags.
 *
 * Short-cut version of inode_permission(), for calling on directories
 * during pathname resolution.  Combines parts of inode_permission()
 * and generic_permission(), and tests ONLY for MAY_EXEC permission.
 *
 * If appropriate, check DAC only.  If not appropriate, or
 * short-cut DAC fails, then call ->permission() to do more
 * complete permission check.
 */
static inline int exec_permission(struct inode *inode, unsigned int flags)
{
	int ret;
	struct user_namespace *ns = inode_userns(inode);
	int mask = MAY_EXEC;
	if (flags & IPERM_FLAG_RCU)
		mask |= MAY_NOT_BLOCK;

	if (inode->i_op->permission) {
		ret = inode->i_op->permission(inode, mask, flags);
		if (likely(!ret))
			goto ok;
	} else {
		ret = acl_permission_check(inode, mask, flags);
		if (likely(!ret))
			goto ok;
		if (ret != -EACCES)
			return ret;
		if (ns_capable(ns, CAP_DAC_OVERRIDE) ||
				ns_capable(ns, CAP_DAC_READ_SEARCH))
			goto ok;
	}
	return ret;
ok:
	return security_inode_exec_permission(inode, flags);
}

/**
 * path_get - get a reference to a path
 * @path: path to get the reference to
 *
 * Given a path increment the reference count to the dentry and the vfsmount.
 */
void path_get(struct path *path)
{
	mntget(path->mnt);
	dget(path->dentry);
}
EXPORT_SYMBOL(path_get);

/**
 * path_put - put a reference to a path
 * @path: path to put the reference to
 *
 * Given a path decrement the reference count to the dentry and the vfsmount.
 */
void path_put(struct path *path)
{
	dput(path->dentry);
	mntput(path->mnt);
}
EXPORT_SYMBOL(path_put);

/*
 * Path walking has 2 modes, rcu-walk and ref-walk (see
 * Documentation/filesystems/path-lookup.txt).  In situations when we can't
 * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
 * normal reference counts on dentries and vfsmounts to transition to rcu-walk
 * mode.  Refcounts are grabbed at the last known good point before rcu-walk
 * got stuck, so ref-walk may continue from there. If this is not successful
 * (eg. a seqcount has changed), then failure is returned and it's up to caller
 * to restart the path walk from the beginning in ref-walk mode.
 */

/**
 * unlazy_walk - try to switch to ref-walk mode.
 * @nd: nameidata pathwalk data
 * @dentry: child of nd->path.dentry or NULL
 * Returns: 0 on success, -ECHILD on failure
 *
 * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
 * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
 * @nd or NULL.  Must be called from rcu-walk context.
 */
static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
{
	struct fs_struct *fs = current->fs;
	struct dentry *parent = nd->path.dentry;
	int want_root = 0;

	BUG_ON(!(nd->flags & LOOKUP_RCU));
	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
		want_root = 1;
		spin_lock(&fs->lock);
		if (nd->root.mnt != fs->root.mnt ||
				nd->root.dentry != fs->root.dentry)
			goto err_root;
	}
	spin_lock(&parent->d_lock);
	if (!dentry) {
		if (!__d_rcu_to_refcount(parent, nd->seq))
			goto err_parent;
		BUG_ON(nd->inode != parent->d_inode);
	} else {
		if (dentry->d_parent != parent)
			goto err_parent;
		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
		if (!__d_rcu_to_refcount(dentry, nd->seq))
			goto err_child;
		/*
		 * If the sequence check on the child dentry passed, then
		 * the child has not been removed from its parent. This
		 * means the parent dentry must be valid and able to take
		 * a reference at this point.
		 */
		BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
		BUG_ON(!parent->d_count);
		parent->d_count++;
		spin_unlock(&dentry->d_lock);
	}
	spin_unlock(&parent->d_lock);
	if (want_root) {
		path_get(&nd->root);
		spin_unlock(&fs->lock);
	}
	mntget(nd->path.mnt);

	rcu_read_unlock();
	br_read_unlock(vfsmount_lock);
	nd->flags &= ~LOOKUP_RCU;
	return 0;

err_child:
	spin_unlock(&dentry->d_lock);
err_parent:
	spin_unlock(&parent->d_lock);
err_root:
	if (want_root)
		spin_unlock(&fs->lock);
	return -ECHILD;
}

/**
 * release_open_intent - free up open intent resources
 * @nd: pointer to nameidata
 */
void release_open_intent(struct nameidata *nd)
{
	struct file *file = nd->intent.open.file;

	if (file && !IS_ERR(file)) {
		if (file->f_path.dentry == NULL)
			put_filp(file);
		else
			fput(file);
	}
}

static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	return dentry->d_op->d_revalidate(dentry, nd);
}

static struct dentry *
do_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	int status = d_revalidate(dentry, nd);
	if (unlikely(status <= 0)) {
		/*
		 * The dentry failed validation.
		 * If d_revalidate returned 0 attempt to invalidate
		 * the dentry otherwise d_revalidate is asking us
		 * to return a fail status.
		 */
		if (status < 0) {
			dput(dentry);
			dentry = ERR_PTR(status);
		} else if (!d_invalidate(dentry)) {
			dput(dentry);
			dentry = NULL;
		}
	}
	return dentry;
}

/**
 * complete_walk - successful completion of path walk
 * @nd:  pointer nameidata
 *
 * If we had been in RCU mode, drop out of it and legitimize nd->path.
 * Revalidate the final result, unless we'd already done that during
 * the path walk or the filesystem doesn't ask for it.  Return 0 on
 * success, -error on failure.  In case of failure caller does not
 * need to drop nd->path.
 */
static int complete_walk(struct nameidata *nd)
{
	struct dentry *dentry = nd->path.dentry;
	int status;

	if (nd->flags & LOOKUP_RCU) {
		nd->flags &= ~LOOKUP_RCU;
		if (!(nd->flags & LOOKUP_ROOT))
			nd->root.mnt = NULL;
		spin_lock(&dentry->d_lock);
		if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
			spin_unlock(&dentry->d_lock);
			rcu_read_unlock();
			br_read_unlock(vfsmount_lock);
			return -ECHILD;
		}
		BUG_ON(nd->inode != dentry->d_inode);
		spin_unlock(&dentry->d_lock);
		mntget(nd->path.mnt);
		rcu_read_unlock();
		br_read_unlock(vfsmount_lock);
	}

	if (likely(!(nd->flags & LOOKUP_JUMPED)))
		return 0;

	if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
		return 0;

	if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
		return 0;

	/* Note: we do not d_invalidate() */
	status = d_revalidate(dentry, nd);
	if (status > 0)
		return 0;

	if (!status)
		status = -ESTALE;

	path_put(&nd->path);
	return status;
}

static __always_inline void set_root(struct nameidata *nd)
{
	if (!nd->root.mnt)
		get_fs_root(current->fs, &nd->root);
}

static int link_path_walk(const char *, struct nameidata *);

static __always_inline void set_root_rcu(struct nameidata *nd)
{
	if (!nd->root.mnt) {
		struct fs_struct *fs = current->fs;
		unsigned seq;

		do {
			seq = read_seqcount_begin(&fs->seq);
			nd->root = fs->root;
			nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
		} while (read_seqcount_retry(&fs->seq, seq));
	}
}

static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
	int ret;

	if (IS_ERR(link))
		goto fail;

	if (*link == '/') {
		set_root(nd);
		path_put(&nd->path);
		nd->path = nd->root;
		path_get(&nd->root);
		nd->flags |= LOOKUP_JUMPED;
	}
	nd->inode = nd->path.dentry->d_inode;

	ret = link_path_walk(link, nd);
	return ret;
fail:
	path_put(&nd->path);
	return PTR_ERR(link);
}

static void path_put_conditional(struct path *path, struct nameidata *nd)
{
	dput(path->dentry);
	if (path->mnt != nd->path.mnt)
		mntput(path->mnt);
}

static inline void path_to_nameidata(const struct path *path,
					struct nameidata *nd)
{
	if (!(nd->flags & LOOKUP_RCU)) {
		dput(nd->path.dentry);
		if (nd->path.mnt != path->mnt)
			mntput(nd->path.mnt);
	}
	nd->path.mnt = path->mnt;
	nd->path.dentry = path->dentry;
}

static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
{
	struct inode *inode = link->dentry->d_inode;
	if (!IS_ERR(cookie) && inode->i_op->put_link)
		inode->i_op->put_link(link->dentry, nd, cookie);
	path_put(link);
}

static __always_inline int
follow_link(struct path *link, struct nameidata *nd, void **p)
{
	int error;
	struct dentry *dentry = link->dentry;

	BUG_ON(nd->flags & LOOKUP_RCU);

	if (link->mnt == nd->path.mnt)
		mntget(link->mnt);

	if (unlikely(current->total_link_count >= 40)) {
		*p = ERR_PTR(-ELOOP); /* no ->put_link(), please */
		path_put(&nd->path);
		return -ELOOP;
	}
	cond_resched();
	current->total_link_count++;

	touch_atime(link->mnt, dentry);
	nd_set_link(nd, NULL);

	error = security_inode_follow_link(link->dentry, nd);
	if (error) {
		*p = ERR_PTR(error); /* no ->put_link(), please */
		path_put(&nd->path);
		return error;
	}

	nd->last_type = LAST_BIND;
	*p = dentry->d_inode->i_op->follow_link(dentry, nd);
	error = PTR_ERR(*p);
	if (!IS_ERR(*p)) {
		char *s = nd_get_link(nd);
		error = 0;
		if (s)
			error = __vfs_follow_link(nd, s);
		else if (nd->last_type == LAST_BIND) {
			nd->flags |= LOOKUP_JUMPED;
			nd->inode = nd->path.dentry->d_inode;
			if (nd->inode->i_op->follow_link) {
				/* stepped on a _really_ weird one */
				path_put(&nd->path);
				error = -ELOOP;
			}
		}
	}
	return error;
}

static int follow_up_rcu(struct path *path)
{
	struct vfsmount *parent;
	struct dentry *mountpoint;

	parent = path->mnt->mnt_parent;
	if (parent == path->mnt)
		return 0;
	mountpoint = path->mnt->mnt_mountpoint;
	path->dentry = mountpoint;
	path->mnt = parent;
	return 1;
}

int follow_up(struct path *path)
{
	struct vfsmount *parent;
	struct dentry *mountpoint;

	br_read_lock(vfsmount_lock);
	parent = path->mnt->mnt_parent;
	if (parent == path->mnt) {
		br_read_unlock(vfsmount_lock);
		return 0;
	}
	mntget(parent);
	mountpoint = dget(path->mnt->mnt_mountpoint);
	br_read_unlock(vfsmount_lock);
	dput(path->dentry);
	path->dentry = mountpoint;
	mntput(path->mnt);
	path->mnt = parent;
	return 1;
}

/*
 * Perform an automount
 * - return -EISDIR to tell follow_managed() to stop and return the path we
 *   were called with.
 */
static int follow_automount(struct path *path, unsigned flags,
			    bool *need_mntput)
{
	struct vfsmount *mnt;
	int err;

	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
		return -EREMOTE;

	/* We don't want to mount if someone supplied AT_NO_AUTOMOUNT
	 * and this is the terminal part of the path.
	 */
	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_CONTINUE))
		return -EISDIR; /* we actually want to stop here */

	/* We want to mount if someone is trying to open/create a file of any
	 * type under the mountpoint, wants to traverse through the mountpoint
	 * or wants to open the mounted directory.
	 *
	 * We don't want to mount if someone's just doing a stat and they've
	 * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
	 * appended a '/' to the name.
	 */
	if (!(flags & LOOKUP_FOLLOW) &&
	    !(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
		       LOOKUP_OPEN | LOOKUP_CREATE)))
		return -EISDIR;

	current->total_link_count++;
	if (current->total_link_count >= 40)
		return -ELOOP;

	mnt = path->dentry->d_op->d_automount(path);
	if (IS_ERR(mnt)) {
		/*
		 * The filesystem is allowed to return -EISDIR here to indicate
		 * it doesn't want to automount.  For instance, autofs would do
		 * this so that its userspace daemon can mount on this dentry.
		 *
		 * However, we can only permit this if it's a terminal point in
		 * the path being looked up; if it wasn't then the remainder of
		 * the path is inaccessible and we should say so.
		 */
		if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_CONTINUE))
			return -EREMOTE;
		return PTR_ERR(mnt);
	}

	if (!mnt) /* mount collision */
		return 0;

	if (!*need_mntput) {
		/* lock_mount() may release path->mnt on error */
		mntget(path->mnt);
		*need_mntput = true;
	}
	err = finish_automount(mnt, path);

	switch (err) {
	case -EBUSY:
		/* Someone else made a mount here whilst we were busy */
		return 0;
	case 0:
		path_put(path);
		path->mnt = mnt;
		path->dentry = dget(mnt->mnt_root);
		return 0;
	default:
		return err;
	}

}

/*
 * Handle a dentry that is managed in some way.
 * - Flagged for transit management (autofs)
 * - Flagged as mountpoint
 * - Flagged as automount point
 *
 * This may only be called in refwalk mode.
 *
 * Serialization is taken care of in namespace.c
 */
static int follow_managed(struct path *path, unsigned flags)
{
	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
	unsigned managed;
	bool need_mntput = false;
	int ret = 0;

	/* Given that we're not holding a lock here, we retain the value in a
	 * local variable for each dentry as we look at it so that we don't see
	 * the components of that value change under us */
	while (managed = ACCESS_ONCE(path->dentry->d_flags),
	       managed &= DCACHE_MANAGED_DENTRY,
	       unlikely(managed != 0)) {
		/* Allow the filesystem to manage the transit without i_mutex
		 * being held. */
		if (managed & DCACHE_MANAGE_TRANSIT) {
			BUG_ON(!path->dentry->d_op);
			BUG_ON(!path->dentry->d_op->d_manage);
			ret = path->dentry->d_op->d_manage(path->dentry, false);
			if (ret < 0)
				break;
		}

		/* Transit to a mounted filesystem. */
		if (managed & DCACHE_MOUNTED) {
			struct vfsmount *mounted = lookup_mnt(path);
			if (mounted) {
				dput(path->dentry);
				if (need_mntput)
					mntput(path->mnt);
				path->mnt = mounted;
				path->dentry = dget(mounted->mnt_root);
				need_mntput = true;
				continue;
			}

			/* Something is mounted on this dentry in another
			 * namespace and/or whatever was mounted there in this
			 * namespace got unmounted before we managed to get the
			 * vfsmount_lock */
		}

		/* Handle an automount point */
		if (managed & DCACHE_NEED_AUTOMOUNT) {
			ret = follow_automount(path, flags, &need_mntput);
			if (ret < 0)
				break;
			continue;
		}

		/* We didn't change the current path point */
		break;
	}

	if (need_mntput && path->mnt == mnt)
		mntput(path->mnt);
	if (ret == -EISDIR)
		ret = 0;
	return ret;
}

int follow_down_one(struct path *path)
{
	struct vfsmount *mounted;

	mounted = lookup_mnt(path);
	if (mounted) {
		dput(path->dentry);
		mntput(path->mnt);
		path->mnt = mounted;
		path->dentry = dget(mounted->mnt_root);
		return 1;
	}
	return 0;
}

static inline bool managed_dentry_might_block(struct dentry *dentry)
{
	return (dentry->d_flags & DCACHE_MANAGE_TRANSIT &&
		dentry->d_op->d_manage(dentry, true) < 0);
}

/*
 * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
 * we meet a managed dentry that would need blocking.
 */
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
			       struct inode **inode)
{
	for (;;) {
		struct vfsmount *mounted;
		/*
		 * Don't forget we might have a non-mountpoint managed dentry
		 * that wants to block transit.
		 */
		if (unlikely(managed_dentry_might_block(path->dentry)))
			return false;

		if (!d_mountpoint(path->dentry))
			break;

		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
		if (!mounted)
			break;
		path->mnt = mounted;
		path->dentry = mounted->mnt_root;
		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
		/*
		 * Update the inode too. We don't need to re-check the
		 * dentry sequence number here after this d_inode read,
		 * because a mount-point is always pinned.
		 */
		*inode = path->dentry->d_inode;
	}
	return true;
}

static void follow_mount_rcu(struct nameidata *nd)
{
	while (d_mountpoint(nd->path.dentry)) {
		struct vfsmount *mounted;
		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry, 1);
		if (!mounted)
			break;
		nd->path.mnt = mounted;
		nd->path.dentry = mounted->mnt_root;
		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
	}
}

static int follow_dotdot_rcu(struct nameidata *nd)
{
	set_root_rcu(nd);

	while (1) {
		if (nd->path.dentry == nd->root.dentry &&
		    nd->path.mnt == nd->root.mnt) {
			break;
		}
		if (nd->path.dentry != nd->path.mnt->mnt_root) {
			struct dentry *old = nd->path.dentry;
			struct dentry *parent = old->d_parent;
			unsigned seq;

			seq = read_seqcount_begin(&parent->d_seq);
			if (read_seqcount_retry(&old->d_seq, nd->seq))
				goto failed;
			nd->path.dentry = parent;
			nd->seq = seq;
			break;
		}
		if (!follow_up_rcu(&nd->path))
			break;
		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
	}
	follow_mount_rcu(nd);
	nd->inode = nd->path.dentry->d_inode;
	return 0;

failed:
	nd->flags &= ~LOOKUP_RCU;
	if (!(nd->flags & LOOKUP_ROOT))
		nd->root.mnt = NULL;
	rcu_read_unlock();
	br_read_unlock(vfsmount_lock);
	return -ECHILD;
}

/*
 * Follow down to the covering mount currently visible to userspace.  At each
 * point, the filesystem owning that dentry may be queried as to whether the
 * caller is permitted to proceed or not.
 */
int follow_down(struct path *path)
{
	unsigned managed;
	int ret;

	while (managed = ACCESS_ONCE(path->dentry->d_flags),
	       unlikely(managed & DCACHE_MANAGED_DENTRY)) {
		/* Allow the filesystem to manage the transit without i_mutex
		 * being held.
		 *
		 * We indicate to the filesystem if someone is trying to mount
		 * something here.  This gives autofs the chance to deny anyone
		 * other than its daemon the right to mount on its
		 * superstructure.
		 *
		 * The filesystem may sleep at this point.
		 */
		if (managed & DCACHE_MANAGE_TRANSIT) {
			BUG_ON(!path->dentry->d_op);
			BUG_ON(!path->dentry->d_op->d_manage);
			ret = path->dentry->d_op->d_manage(
				path->dentry, false);
			if (ret < 0)
				return ret == -EISDIR ? 0 : ret;
		}

		/* Transit to a mounted filesystem. */
		if (managed & DCACHE_MOUNTED) {
			struct vfsmount *mounted = lookup_mnt(path);
			if (!mounted)
				break;
			dput(path->dentry);
			mntput(path->mnt);
			path->mnt = mounted;
			path->dentry = dget(mounted->mnt_root);
			continue;
		}

		/* Don't handle automount points here */
		break;
	}
	return 0;
}

/*
 * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
 */
static void follow_mount(struct path *path)
{
	while (d_mountpoint(path->dentry)) {
		struct vfsmount *mounted = lookup_mnt(path);
		if (!mounted)
			break;
		dput(path->dentry);
		mntput(path->mnt);
		path->mnt = mounted;
		path->dentry = dget(mounted->mnt_root);
	}
}

static void follow_dotdot(struct nameidata *nd)
{
	set_root(nd);

	while(1) {
		struct dentry *old = nd->path.dentry;

		if (nd->path.dentry == nd->root.dentry &&
		    nd->path.mnt == nd->root.mnt) {
			break;
		}
		if (nd->path.dentry != nd->path.mnt->mnt_root) {
			/* rare case of legitimate dget_parent()... */
			nd->path.dentry = dget_parent(nd->path.dentry);
			dput(old);
			break;
		}
		if (!follow_up(&nd->path))
			break;
	}
	follow_mount(&nd->path);
	nd->inode = nd->path.dentry->d_inode;
}

/*
 * Allocate a dentry with name and parent, and perform a parent
 * directory ->lookup on it. Returns the new dentry, or ERR_PTR
 * on error. parent->d_inode->i_mutex must be held. d_lookup must
 * have verified that no child exists while under i_mutex.
 */
static struct dentry *d_alloc_and_lookup(struct dentry *parent,
				struct qstr *name, struct nameidata *nd)
{
	struct inode *inode = parent->d_inode;
	struct dentry *dentry;
	struct dentry *old;

	/* Don't create child dentry for a dead directory. */
	if (unlikely(IS_DEADDIR(inode)))
		return ERR_PTR(-ENOENT);

	dentry = d_alloc(parent, name);
	if (unlikely(!dentry))
		return ERR_PTR(-ENOMEM);

	old = inode->i_op->lookup(inode, dentry, nd);
	if (unlikely(old)) {
		dput(dentry);
		dentry = old;
	}
	return dentry;
}

/*
 * We already have a dentry, but require a lookup to be performed on the parent
 * directory to fill in d_inode. Returns the new dentry, or ERR_PTR on error.
 * parent->d_inode->i_mutex must be held. d_lookup must have verified that no
 * child exists while under i_mutex.
 */
static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentry,
				     struct nameidata *nd)
{
	struct inode *inode = parent->d_inode;
	struct dentry *old;

	/* Don't create child dentry for a dead directory. */
	if (unlikely(IS_DEADDIR(inode)))
		return ERR_PTR(-ENOENT);

	old = inode->i_op->lookup(inode, dentry, nd);
	if (unlikely(old)) {
		dput(dentry);
		dentry = old;
	}
	return dentry;
}

/*
 *  It's more convoluted than I'd like it to be, but... it's still fairly
 *  small and for now I'd prefer to have fast path as straight as possible.
 *  It _is_ time-critical.
 */
static int do_lookup(struct nameidata *nd, struct qstr *name,
			struct path *path, struct inode **inode)
{
	struct vfsmount *mnt = nd->path.mnt;
	struct dentry *dentry, *parent = nd->path.dentry;
	int need_reval = 1;
	int status = 1;
	int err;

	/*
	 * Rename seqlock is not required here because in the off chance
	 * of a false negative due to a concurrent rename, we're going to
	 * do the non-racy lookup, below.
	 */
	if (nd->flags & LOOKUP_RCU) {
		unsigned seq;
		*inode = nd->inode;
		dentry = __d_lookup_rcu(parent, name, &seq, inode);
		if (!dentry)
			goto unlazy;

		/* Memory barrier in read_seqcount_begin of child is enough */
		if (__read_seqcount_retry(&parent->d_seq, nd->seq))
			return -ECHILD;
		nd->seq = seq;

		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
			status = d_revalidate(dentry, nd);
			if (unlikely(status <= 0)) {
				if (status != -ECHILD)
					need_reval = 0;
				goto unlazy;
			}
		}
		if (unlikely(d_need_lookup(dentry)))
			goto unlazy;
		path->mnt = mnt;
		path->dentry = dentry;
		if (unlikely(!__follow_mount_rcu(nd, path, inode)))
			goto unlazy;
		if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
			goto unlazy;
		return 0;
unlazy:
		if (unlazy_walk(nd, dentry))
			return -ECHILD;
	} else {
		dentry = __d_lookup(parent, name);
	}

	if (dentry && unlikely(d_need_lookup(dentry))) {
		dput(dentry);
		dentry = NULL;
	}
retry:
	if (unlikely(!dentry)) {
		struct inode *dir = parent->d_inode;
		BUG_ON(nd->inode != dir);

		mutex_lock(&dir->i_mutex);
		dentry = d_lookup(parent, name);
		if (likely(!dentry)) {
			dentry = d_alloc_and_lookup(parent, name, nd);
			if (IS_ERR(dentry)) {
				mutex_unlock(&dir->i_mutex);
				return PTR_ERR(dentry);
			}
			/* known good */
			need_reval = 0;
			status = 1;
		} else if (unlikely(d_need_lookup(dentry))) {
			dentry = d_inode_lookup(parent, dentry, nd);
			if (IS_ERR(dentry)) {
				mutex_unlock(&dir->i_mutex);
				return PTR_ERR(dentry);
			}
			/* known good */
			need_reval = 0;
			status = 1;
		}
		mutex_unlock(&dir->i_mutex);
	}
	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
		status = d_revalidate(dentry, nd);
	if (unlikely(status <= 0)) {
		if (status < 0) {
			dput(dentry);
			return status;
		}
		if (!d_invalidate(dentry)) {
			dput(dentry);
			dentry = NULL;
			need_reval = 1;
			goto retry;
		}
	}

	path->mnt = mnt;
	path->dentry = dentry;
	err = follow_managed(path, nd->flags);
	if (unlikely(err < 0)) {
		path_put_conditional(path, nd);
		return err;
	}
	*inode = path->dentry->d_inode;
	return 0;
}

static inline int may_lookup(struct nameidata *nd)
{
	if (nd->flags & LOOKUP_RCU) {
		int err = exec_permission(nd->inode, IPERM_FLAG_RCU);
		if (err != -ECHILD)
			return err;
		if (unlazy_walk(nd, NULL))
			return -ECHILD;
	}
	return exec_permission(nd->inode, 0);
}

static inline int handle_dots(struct nameidata *nd, int type)
{
	if (type == LAST_DOTDOT) {
		if (nd->flags & LOOKUP_RCU) {
			if (follow_dotdot_rcu(nd))
				return -ECHILD;
		} else
			follow_dotdot(nd);
	}
	return 0;
}

static void terminate_walk(struct nameidata *nd)
{
	if (!(nd->flags & LOOKUP_RCU)) {
		path_put(&nd->path);
	} else {
		nd->flags &= ~LOOKUP_RCU;
		if (!(nd->flags & LOOKUP_ROOT))
			nd->root.mnt = NULL;
		rcu_read_unlock();
		br_read_unlock(vfsmount_lock);
	}
}

static inline int walk_component(struct nameidata *nd, struct path *path,
		struct qstr *name, int type, int follow)
{
	struct inode *inode;
	int err;
	/*
	 * "." and ".." are special - ".." especially so because it has
	 * to be able to know about the current root directory and
	 * parent relationships.
	 */
	if (unlikely(type != LAST_NORM))
		return handle_dots(nd, type);
	err = do_lookup(nd, name, path, &inode);
	if (unlikely(err)) {
		terminate_walk(nd);
		return err;
	}
	if (!inode) {
		path_to_nameidata(path, nd);
		terminate_walk(nd);
		return -ENOENT;
	}
	if (unlikely(inode->i_op->follow_link) && follow) {
		if (nd->flags & LOOKUP_RCU) {
			if (unlikely(unlazy_walk(nd, path->dentry))) {
				terminate_walk(nd);
				return -ECHILD;
			}
		}
		BUG_ON(inode != path->dentry->d_inode);
		return 1;
	}
	path_to_nameidata(path, nd);
	nd->inode = inode;
	return 0;
}

/*
 * This limits recursive symlink follows to 8, while
 * limiting consecutive symlinks to 40.
 *
 * Without that kind of total limit, nasty chains of consecutive
 * symlinks can cause almost arbitrarily long lookups.
 */
static inline int nested_symlink(struct path *path, struct nameidata *nd)
{
	int res;

	if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
		path_put_conditional(path, nd);
		path_put(&nd->path);
		return -ELOOP;
	}
	BUG_ON(nd->depth >= MAX_NESTED_LINKS);

	nd->depth++;
	current->link_count++;

	do {
		struct path link = *path;
		void *cookie;

		res = follow_link(&link, nd, &cookie);
		if (!res)
			res = walk_component(nd, path, &nd->last,
					     nd->last_type, LOOKUP_FOLLOW);
		put_link(nd, &link, cookie);
	} while (res > 0);

	current->link_count--;
	nd->depth--;
	return res;
}

/*
 * Name resolution.
 * This is the basic name resolution function, turning a pathname into
 * the final dentry. We expect 'base' to be positive and a directory.
 *
 * Returns 0 and nd will have valid dentry and mnt on success.
 * Returns error and drops reference to input namei data on failure.
 */
static int link_path_walk(const char *name, struct nameidata *nd)
{
	struct path next;
	int err;
	unsigned int lookup_flags = nd->flags;
	
	while (*name=='/')
		name++;
	if (!*name)
		return 0;

	/* At this point we know we have a real path component. */
	for(;;) {
		unsigned long hash;
		struct qstr this;
		unsigned int c;
		int type;

		nd->flags |= LOOKUP_CONTINUE;

		err = may_lookup(nd);
 		if (err)
			break;

		this.name = name;
		c = *(const unsigned char *)name;

		hash = init_name_hash();
		do {
			name++;
			hash = partial_name_hash(c, hash);
			c = *(const unsigned char *)name;
		} while (c && (c != '/'));
		this.len = name - (const char *) this.name;
		this.hash = end_name_hash(hash);

		type = LAST_NORM;
		if (this.name[0] == '.') switch (this.len) {
			case 2:
				if (this.name[1] == '.') {
					type = LAST_DOTDOT;
					nd->flags |= LOOKUP_JUMPED;
				}
				break;
			case 1:
				type = LAST_DOT;
		}
		if (likely(type == LAST_NORM)) {
			struct dentry *parent = nd->path.dentry;
			nd->flags &= ~LOOKUP_JUMPED;
			if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
				err = parent->d_op->d_hash(parent, nd->inode,
							   &this);
				if (err < 0)
					break;
			}
		}

		/* remove trailing slashes? */
		if (!c)
			goto last_component;
		while (*++name == '/');
		if (!*name)
			goto last_component;

		err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
		if (err < 0)
			return err;

		if (err) {
			err = nested_symlink(&next, nd);
			if (err)
				return err;
		}
		err = -ENOTDIR; 
		if (!nd->inode->i_op->lookup)
			break;
		continue;
		/* here ends the main loop */

last_component:
		/* Clear LOOKUP_CONTINUE iff it was previously unset */
		nd->flags &= lookup_flags | ~LOOKUP_CONTINUE;
		nd->last = this;
		nd->last_type = type;
		return 0;
	}
	terminate_walk(nd);
	return err;
}

static int path_init(int dfd, const char *name, unsigned int flags,
		     struct nameidata *nd, struct file **fp)
{
	int retval = 0;
	int fput_needed;
	struct file *file;

	nd->last_type = LAST_ROOT; /* if there are only slashes... */
	nd->flags = flags | LOOKUP_JUMPED;
	nd->depth = 0;
	if (flags & LOOKUP_ROOT) {
		struct inode *inode = nd->root.dentry->d_inode;
		if (*name) {
			if (!inode->i_op->lookup)
				return -ENOTDIR;
			retval = inode_permission(inode, MAY_EXEC);
			if (retval)
				return retval;
		}
		nd->path = nd->root;
		nd->inode = inode;
		if (flags & LOOKUP_RCU) {
			br_read_lock(vfsmount_lock);
			rcu_read_lock();
			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
		} else {
			path_get(&nd->path);
		}
		return 0;
	}

	nd->root.mnt = NULL;

	if (*name=='/') {
		if (flags & LOOKUP_RCU) {
			br_read_lock(vfsmount_lock);
			rcu_read_lock();
			set_root_rcu(nd);
		} else {
			set_root(nd);
			path_get(&nd->root);
		}
		nd->path = nd->root;
	} else if (dfd == AT_FDCWD) {
		if (flags & LOOKUP_RCU) {
			struct fs_struct *fs = current->fs;
			unsigned seq;

			br_read_lock(vfsmount_lock);
			rcu_read_lock();

			do {
				seq = read_seqcount_begin(&fs->seq);
				nd->path = fs->pwd;
				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
			} while (read_seqcount_retry(&fs->seq, seq));
		} else {
			get_fs_pwd(current->fs, &nd->path);
		}
	} else {
		struct dentry *dentry;

		file = fget_raw_light(dfd, &fput_needed);
		retval = -EBADF;
		if (!file)
			goto out_fail;

		dentry = file->f_path.dentry;

		if (*name) {
			retval = -ENOTDIR;
			if (!S_ISDIR(dentry->d_inode->i_mode))
				goto fput_fail;

			retval = exec_permission(dentry->d_inode, 0);
			if (retval)
				goto fput_fail;
		}

		nd->path = file->f_path;
		if (flags & LOOKUP_RCU) {
			if (fput_needed)
				*fp = file;
			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
			br_read_lock(vfsmount_lock);
			rcu_read_lock();
		} else {
			path_get(&file->f_path);
			fput_light(file, fput_needed);
		}
	}

	nd->inode = nd->path.dentry->d_inode;
	return 0;

fput_fail:
	fput_light(file, fput_needed);
out_fail:
	return retval;
}

static inline int lookup_last(struct nameidata *nd, struct path *path)
{
	if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;

	nd->flags &= ~LOOKUP_PARENT;
	return walk_component(nd, path, &nd->last, nd->last_type,
					nd->flags & LOOKUP_FOLLOW);
}

/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(int dfd, const char *name,
				unsigned int flags, struct nameidata *nd)
{
	struct file *base = NULL;
	struct path path;
	int err;

	/*
	 * Path walking is largely split up into 2 different synchronisation
	 * schemes, rcu-walk and ref-walk (explained in
	 * Documentation/filesystems/path-lookup.txt). These share much of the
	 * path walk code, but some things particularly setup, cleanup, and
	 * following mounts are sufficiently divergent that functions are
	 * duplicated. Typically there is a function foo(), and its RCU
	 * analogue, foo_rcu().
	 *
	 * -ECHILD is the error number of choice (just to avoid clashes) that
	 * is returned if some aspect of an rcu-walk fails. Such an error must
	 * be handled by restarting a traditional ref-walk (which will always
	 * be able to complete).
	 */
	err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base);

	if (unlikely(err))
		return err;

	current->total_link_count = 0;
	err = link_path_walk(name, nd);

	if (!err && !(flags & LOOKUP_PARENT)) {
		err = lookup_last(nd, &path);
		while (err > 0) {
			void *cookie;
			struct path link = path;
			nd->flags |= LOOKUP_PARENT;
			err = follow_link(&link, nd, &cookie);
			if (!err)
				err = lookup_last(nd, &path);
			put_link(nd, &link, cookie);
		}
	}

	if (!err)
		err = complete_walk(nd);

	if (!err && nd->flags & LOOKUP_DIRECTORY) {
		if (!nd->inode->i_op->lookup) {
			path_put(&nd->path);
			err = -ENOTDIR;
		}
	}

	if (base)
		fput(base);

	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
		path_put(&nd->root);
		nd->root.mnt = NULL;
	}
	return err;
}

static int do_path_lookup(int dfd, const char *name,
				unsigned int flags, struct nameidata *nd)
{
	int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
	if (unlikely(retval == -ECHILD))
		retval = path_lookupat(dfd, name, flags, nd);
	if (unlikely(retval == -ESTALE))
		retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);

	if (likely(!retval)) {
		if (unlikely(!audit_dummy_context())) {
			if (nd->path.dentry && nd->inode)
				audit_inode(name, nd->path.dentry);
		}
	}
	return retval;
}

int kern_path_parent(const char *name, struct nameidata *nd)
{
	return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd);
}

int kern_path(const char *name, unsigned int flags, struct path *path)
{
	struct nameidata nd;
	int res = do_path_lookup(AT_FDCWD, name, flags, &nd);
	if (!res)
		*path = nd.path;
	return res;
}

/**
 * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
 * @dentry:  pointer to dentry of the base directory
 * @mnt: pointer to vfs mount of the base directory
 * @name: pointer to file name
 * @flags: lookup flags
 * @nd: pointer to nameidata
 */
int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
		    const char *name, unsigned int flags,
		    struct nameidata *nd)
{
	nd->root.dentry = dentry;
	nd->root.mnt = mnt;
	/* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */
	return do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, nd);
}

static struct dentry *__lookup_hash(struct qstr *name,
		struct dentry *base, struct nameidata *nd)
{
	struct inode *inode = base->d_inode;
	struct dentry *dentry;
	int err;

	err = exec_permission(inode, 0);
	if (err)
		return ERR_PTR(err);

	/*
	 * Don't bother with __d_lookup: callers are for creat as
	 * well as unlink, so a lot of the time it would cost
	 * a double lookup.
	 */
	dentry = d_lookup(base, name);

	if (dentry && d_need_lookup(dentry)) {
		/*
		 * __lookup_hash is called with the parent dir's i_mutex already
		 * held, so we are good to go here.
		 */
		dentry = d_inode_lookup(base, dentry, nd);
		if (IS_ERR(dentry))
			return dentry;
	}

	if (dentry && (dentry->d_flags & DCACHE_OP_REVALIDATE))
		dentry = do_revalidate(dentry, nd);

	if (!dentry)
		dentry = d_alloc_and_lookup(base, name, nd);

	return dentry;
}

/*
 * Restricted form of lookup. Doesn't follow links, single-component only,
 * needs parent already locked. Doesn't follow mounts.
 * SMP-safe.
 */
static struct dentry *lookup_hash(struct nameidata *nd)
{
	return __lookup_hash(&nd->last, nd->path.dentry, nd);
}

/**
 * lookup_one_len - filesystem helper to lookup single pathname component
 * @name:	pathname component to lookup
 * @base:	base directory to lookup from
 * @len:	maximum length @len should be interpreted to
 *
 * Note that this routine is purely a helper for filesystem usage and should
 * not be called by generic code.  Also note that by using this function the
 * nameidata argument is passed to the filesystem methods and a filesystem
 * using this helper needs to be prepared for that.
 */
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
	struct qstr this;
	unsigned long hash;
	unsigned int c;

	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));

	this.name = name;
	this.len = len;
	if (!len)
		return ERR_PTR(-EACCES);

	hash = init_name_hash();
	while (len--) {
		c = *(const unsigned char *)name++;
		if (c == '/' || c == '\0')
			return ERR_PTR(-EACCES);
		hash = partial_name_hash(c, hash);
	}
	this.hash = end_name_hash(hash);
	/*
	 * See if the low-level filesystem might want
	 * to use its own hash..
	 */
	if (base->d_flags & DCACHE_OP_HASH) {
		int err = base->d_op->d_hash(base, base->d_inode, &this);
		if (err < 0)
			return ERR_PTR(err);
	}

	return __lookup_hash(&this, base, NULL);
}

int user_path_at(int dfd, const char __user *name, unsigned flags,
		 struct path *path)
{
	struct nameidata nd;
	char *tmp = getname_flags(name, flags);
	int err = PTR_ERR(tmp);
	if (!IS_ERR(tmp)) {

		BUG_ON(flags & LOOKUP_PARENT);

		err = do_path_lookup(dfd, tmp, flags, &nd);
		putname(tmp);
		if (!err)
			*path = nd.path;
	}
	return err;
}

static int user_path_parent(int dfd, const char __user *path,
			struct nameidata *nd, char **name)
{
	char *s = getname(path);
	int error;

	if (IS_ERR(s))
		return PTR_ERR(s);

	error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd);
	if (error)
		putname(s);
	else
		*name = s;

	return error;
}

/*
 * It's inline, so penalty for filesystems that don't use sticky bit is
 * minimal.
 */
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
	uid_t fsuid = current_fsuid();

	if (!(dir->i_mode & S_ISVTX))
		return 0;
	if (current_user_ns() != inode_userns(inode))
		goto other_userns;
	if (inode->i_uid == fsuid)
		return 0;
	if (dir->i_uid == fsuid)
		return 0;

other_userns:
	return !ns_capable(inode_userns(inode), CAP_FOWNER);
}

/*
 *	Check whether we can remove a link victim from directory dir, check
 *  whether the type of victim is right.
 *  1. We can't do it if dir is read-only (done in permission())
 *  2. We should have write and exec permissions on dir
 *  3. We can't remove anything from append-only dir
 *  4. We can't do anything with immutable dir (done in permission())
 *  5. If the sticky bit on dir is set we should either
 *	a. be owner of dir, or
 *	b. be owner of victim, or
 *	c. have CAP_FOWNER capability
 *  6. If the victim is append-only or immutable we can't do antyhing with
 *     links pointing to it.
 *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
 *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
 *  9. We can't remove a root or mountpoint.
 * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
 *     nfs_async_unlink().
 */
static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
{
	int error;

	if (!victim->d_inode)
		return -ENOENT;

	BUG_ON(victim->d_parent->d_inode != dir);
	audit_inode_child(victim, dir);

	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		return error;
	if (IS_APPEND(dir))
		return -EPERM;
	if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
		return -EPERM;
	if (isdir) {
		if (!S_ISDIR(victim->d_inode->i_mode))
			return -ENOTDIR;
		if (IS_ROOT(victim))
			return -EBUSY;
	} else if (S_ISDIR(victim->d_inode->i_mode))
		return -EISDIR;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	if (victim->d_flags & DCACHE_NFSFS_RENAMED)
		return -EBUSY;
	return 0;
}

/*	Check whether we can create an object with dentry child in directory
 *  dir.
 *  1. We can't do it if child already exists (open has special treatment for
 *     this case, but since we are inlined it's OK)
 *  2. We can't do it if dir is read-only (done in permission())
 *  3. We should have write and exec permissions on dir
 *  4. We can't do it if dir is immutable (done in permission())
 */
static inline int may_create(struct inode *dir, struct dentry *child)
{
	if (child->d_inode)
		return -EEXIST;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	return inode_permission(dir, MAY_WRITE | MAY_EXEC);
}

/*
 * p1 and p2 should be directories on the same fs.
 */
struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
{
	struct dentry *p;

	if (p1 == p2) {
		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
		return NULL;
	}

	mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);

	p = d_ancestor(p2, p1);
	if (p) {
		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
		return p;
	}

	p = d_ancestor(p1, p2);
	if (p) {
		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
		return p;
	}

	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
	return NULL;
}

void unlock_rename(struct dentry *p1, struct dentry *p2)
{
	mutex_unlock(&p1->d_inode->i_mutex);
	if (p1 != p2) {
		mutex_unlock(&p2->d_inode->i_mutex);
		mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
	}
}

int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
		struct nameidata *nd)
{
	int error = may_create(dir, dentry);

	if (error)
		return error;

	if (!dir->i_op->create)
		return -EACCES;	/* shouldn't it be ENOSYS? */
	mode &= S_IALLUGO;
	mode |= S_IFREG;
	error = security_inode_create(dir, dentry, mode);
	if (error)
		return error;
	error = dir->i_op->create(dir, dentry, mode, nd);
	if (!error)
		fsnotify_create(dir, dentry);
	return error;
}

static int may_open(struct path *path, int acc_mode, int flag)
{
	struct dentry *dentry = path->dentry;
	struct inode *inode = dentry->d_inode;
	int error;

	/* O_PATH? */
	if (!acc_mode)
		return 0;

	if (!inode)
		return -ENOENT;

	switch (inode->i_mode & S_IFMT) {
	case S_IFLNK:
		return -ELOOP;
	case S_IFDIR:
		if (acc_mode & MAY_WRITE)
			return -EISDIR;
		break;
	case S_IFBLK:
	case S_IFCHR:
		if (path->mnt->mnt_flags & MNT_NODEV)
			return -EACCES;
		/*FALLTHRU*/
	case S_IFIFO:
	case S_IFSOCK:
		flag &= ~O_TRUNC;
		break;
	}

	error = inode_permission(inode, acc_mode);
	if (error)
		return error;

	/*
	 * An append-only file must be opened in append mode for writing.
	 */
	if (IS_APPEND(inode)) {
		if  ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
			return -EPERM;
		if (flag & O_TRUNC)
			return -EPERM;
	}

	/* O_NOATIME can only be set by the owner or superuser */
	if (flag & O_NOATIME && !inode_owner_or_capable(inode))
		return -EPERM;

	/*
	 * Ensure there are no outstanding leases on the file.
	 */
	return break_lease(inode, flag);
}

static int handle_truncate(struct file *filp)
{
	struct path *path = &filp->f_path;
	struct inode *inode = path->dentry->d_inode;
	int error = get_write_access(inode);
	if (error)
		return error;
	/*
	 * Refuse to truncate files with mandatory locks held on them.
	 */
	error = locks_verify_locked(inode);
	if (!error)
		error = security_path_truncate(path);
	if (!error) {
		error = do_truncate(path->dentry, 0,
				    ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
				    filp);
	}
	put_write_access(inode);
	return error;
}

/*
 * Note that while the flag value (low two bits) for sys_open means:
 *	00 - read-only
 *	01 - write-only
 *	10 - read-write
 *	11 - special
 * it is changed into
 *	00 - no permissions needed
 *	01 - read-permission
 *	10 - write-permission
 *	11 - read-write
 * for the internal routines (ie open_namei()/follow_link() etc)
 * This is more logical, and also allows the 00 "no perm needed"
 * to be used for symlinks (where the permissions are checked
 * later).
 *
*/
static inline int open_to_namei_flags(int flag)
{
	if ((flag+1) & O_ACCMODE)
		flag++;
	return flag;
}

/*
 * Handle the last step of open()
 */
static struct file *do_last(struct nameidata *nd, struct path *path,
			    const struct open_flags *op, const char *pathname)
{
	struct dentry *dir = nd->path.dentry;
	struct dentry *dentry;
	int open_flag = op->open_flag;
	int will_truncate = open_flag & O_TRUNC;
	int want_write = 0;
	int acc_mode = op->acc_mode;
	struct file *filp;
	int error;

	nd->flags &= ~LOOKUP_PARENT;
	nd->flags |= op->intent;

	switch (nd->last_type) {
	case LAST_DOTDOT:
	case LAST_DOT:
		error = handle_dots(nd, nd->last_type);
		if (error)
			return ERR_PTR(error);
		/* fallthrough */
	case LAST_ROOT:
		error = complete_walk(nd);
		if (error)
			return ERR_PTR(error);
		audit_inode(pathname, nd->path.dentry);
		if (open_flag & O_CREAT) {
			error = -EISDIR;
			goto exit;
		}
		goto ok;
	case LAST_BIND:
		error = complete_walk(nd);
		if (error)
			return ERR_PTR(error);
		audit_inode(pathname, dir);
		goto ok;
	}

	if (!(open_flag & O_CREAT)) {
		int symlink_ok = 0;
		if (nd->last.name[nd->last.len])
			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
		if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
			symlink_ok = 1;
		/* we _can_ be in RCU mode here */
		error = walk_component(nd, path, &nd->last, LAST_NORM,
					!symlink_ok);
		if (error < 0)
			return ERR_PTR(error);
		if (error) /* symlink */
			return NULL;
		/* sayonara */
		error = complete_walk(nd);
		if (error)
			return ERR_PTR(-ECHILD);

		error = -ENOTDIR;
		if (nd->flags & LOOKUP_DIRECTORY) {
			if (!nd->inode->i_op->lookup)
				goto exit;
		}
		audit_inode(pathname, nd->path.dentry);
		goto ok;
	}

	/* create side of things */
	error = complete_walk(nd);
	if (error)
		return ERR_PTR(error);

	audit_inode(pathname, dir);
	error = -EISDIR;
	/* trailing slashes? */
	if (nd->last.name[nd->last.len])
		goto exit;

	mutex_lock(&dir->d_inode->i_mutex);

	dentry = lookup_hash(nd);
	error = PTR_ERR(dentry);
	if (IS_ERR(dentry)) {
		mutex_unlock(&dir->d_inode->i_mutex);
		goto exit;
	}

	path->dentry = dentry;
	path->mnt = nd->path.mnt;

	/* Negative dentry, just create the file */
	if (!dentry->d_inode) {
		int mode = op->mode;
		if (!IS_POSIXACL(dir->d_inode))
			mode &= ~current_umask();
		/*
		 * This write is needed to ensure that a
		 * rw->ro transition does not occur between
		 * the time when the file is created and when
		 * a permanent write count is taken through
		 * the 'struct file' in nameidata_to_filp().
		 */
		error = mnt_want_write(nd->path.mnt);
		if (error)
			goto exit_mutex_unlock;
		want_write = 1;
		/* Don't check for write permission, don't truncate */
		open_flag &= ~O_TRUNC;
		will_truncate = 0;
		acc_mode = MAY_OPEN;
		error = security_path_mknod(&nd->path, dentry, mode, 0);
		if (error)
			goto exit_mutex_unlock;
		error = vfs_create(dir->d_inode, dentry, mode, nd);
		if (error)
			goto exit_mutex_unlock;
		mutex_unlock(&dir->d_inode->i_mutex);
		dput(nd->path.dentry);
		nd->path.dentry = dentry;
		goto common;
	}

	/*
	 * It already exists.
	 */
	mutex_unlock(&dir->d_inode->i_mutex);
	audit_inode(pathname, path->dentry);

	error = -EEXIST;
	if (open_flag & O_EXCL)
		goto exit_dput;

	error = follow_managed(path, nd->flags);
	if (error < 0)
		goto exit_dput;

	error = -ENOENT;
	if (!path->dentry->d_inode)
		goto exit_dput;

	if (path->dentry->d_inode->i_op->follow_link)
		return NULL;

	path_to_nameidata(path, nd);
	nd->inode = path->dentry->d_inode;
	error = -EISDIR;
	if (S_ISDIR(nd->inode->i_mode))
		goto exit;
ok:
	if (!S_ISREG(nd->inode->i_mode))
		will_truncate = 0;

	if (will_truncate) {
		error = mnt_want_write(nd->path.mnt);
		if (error)
			goto exit;
		want_write = 1;
	}
common:
	error = may_open(&nd->path, acc_mode, open_flag);
	if (error)
		goto exit;
	filp = nameidata_to_filp(nd);
	if (!IS_ERR(filp)) {
		error = ima_file_check(filp, op->acc_mode);
		if (error) {
			fput(filp);
			filp = ERR_PTR(error);
		}
	}
	if (!IS_ERR(filp)) {
		if (will_truncate) {
			error = handle_truncate(filp);
			if (error) {
				fput(filp);
				filp = ERR_PTR(error);
			}
		}
	}
out:
	if (want_write)
		mnt_drop_write(nd->path.mnt);
	path_put(&nd->path);
	return filp;

exit_mutex_unlock:
	mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
	path_put_conditional(path, nd);
exit:
	filp = ERR_PTR(error);
	goto out;
}

static struct file *path_openat(int dfd, const char *pathname,
		struct nameidata *nd, const struct open_flags *op, int flags)
{
	struct file *base = NULL;
	struct file *filp;
	struct path path;
	int error;

	filp = get_empty_filp();
	if (!filp)
		return ERR_PTR(-ENFILE);

	filp->f_flags = op->open_flag;
	nd->intent.open.file = filp;
	nd->intent.open.flags = open_to_namei_flags(op->open_flag);
	nd->intent.open.create_mode = op->mode;

	error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
	if (unlikely(error))
		goto out_filp;

	current->total_link_count = 0;
	error = link_path_walk(pathname, nd);
	if (unlikely(error))
		goto out_filp;

	filp = do_last(nd, &path, op, pathname);
	while (unlikely(!filp)) { /* trailing symlink */
		struct path link = path;
		void *cookie;
		if (!(nd->flags & LOOKUP_FOLLOW)) {
			path_put_conditional(&path, nd);
			path_put(&nd->path);
			filp = ERR_PTR(-ELOOP);
			break;
		}
		nd->flags |= LOOKUP_PARENT;
		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
		error = follow_link(&link, nd, &cookie);
		if (unlikely(error))
			filp = ERR_PTR(error);
		else
			filp = do_last(nd, &path, op, pathname);
		put_link(nd, &link, cookie);
	}
out:
	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT))
		path_put(&nd->root);
	if (base)
		fput(base);
	release_open_intent(nd);
	return filp;

out_filp:
	filp = ERR_PTR(error);
	goto out;
}

struct file *do_filp_open(int dfd, const char *pathname,
		const struct open_flags *op, int flags)
{
	struct nameidata nd;
	struct file *filp;

	filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
	if (unlikely(filp == ERR_PTR(-ECHILD)))
		filp = path_openat(dfd, pathname, &nd, op, flags);
	if (unlikely(filp == ERR_PTR(-ESTALE)))
		filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
	return filp;
}

struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
		const char *name, const struct open_flags *op, int flags)
{
	struct nameidata nd;
	struct file *file;

	nd.root.mnt = mnt;
	nd.root.dentry = dentry;

	flags |= LOOKUP_ROOT;

	if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
		return ERR_PTR(-ELOOP);

	file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU);
	if (unlikely(file == ERR_PTR(-ECHILD)))
		file = path_openat(-1, name, &nd, op, flags);
	if (unlikely(file == ERR_PTR(-ESTALE)))
		file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL);
	return file;
}

/**
 * lookup_create - lookup a dentry, creating it if it doesn't exist
 * @nd: nameidata info
 * @is_dir: directory flag
 *
 * Simple function to lookup and return a dentry and create it
 * if it doesn't exist.  Is SMP-safe.
 *
 * Returns with nd->path.dentry->d_inode->i_mutex locked.
 */
struct dentry *lookup_create(struct nameidata *nd, int is_dir)
{
	struct dentry *dentry = ERR_PTR(-EEXIST);

	mutex_lock_nested(&nd->path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
	/*
	 * Yucky last component or no last component at all?
	 * (foo/., foo/.., /////)
	 */
	if (nd->last_type != LAST_NORM)
		goto fail;
	nd->flags &= ~LOOKUP_PARENT;
	nd->flags |= LOOKUP_CREATE | LOOKUP_EXCL;
	nd->intent.open.flags = O_EXCL;

	/*
	 * Do the final lookup.
	 */
	dentry = lookup_hash(nd);
	if (IS_ERR(dentry))
		goto fail;

	if (dentry->d_inode)
		goto eexist;
	/*
	 * Special case - lookup gave negative, but... we had foo/bar/
	 * From the vfs_mknod() POV we just have a negative dentry -
	 * all is fine. Let's be bastards - you had / on the end, you've
	 * been asking for (non-existent) directory. -ENOENT for you.
	 */
	if (unlikely(!is_dir && nd->last.name[nd->last.len])) {
		dput(dentry);
		dentry = ERR_PTR(-ENOENT);
	}
	return dentry;
eexist:
	dput(dentry);
	dentry = ERR_PTR(-EEXIST);
fail:
	return dentry;
}
EXPORT_SYMBOL_GPL(lookup_create);

int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
	int error = may_create(dir, dentry);

	if (error)
		return error;

	if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
	    !ns_capable(inode_userns(dir), CAP_MKNOD))
		return -EPERM;

	if (!dir->i_op->mknod)
		return -EPERM;

	error = devcgroup_inode_mknod(mode, dev);
	if (error)
		return error;

	error = security_inode_mknod(dir, dentry, mode, dev);
	if (error)
		return error;

	error = dir->i_op->mknod(dir, dentry, mode, dev);
	if (!error)
		fsnotify_create(dir, dentry);
	return error;
}

static int may_mknod(mode_t mode)
{
	switch (mode & S_IFMT) {
	case S_IFREG:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFIFO:
	case S_IFSOCK:
	case 0: /* zero mode translates to S_IFREG */
		return 0;
	case S_IFDIR:
		return -EPERM;
	default:
		return -EINVAL;
	}
}

SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, int, mode,
		unsigned, dev)
{
	int error;
	char *tmp;
	struct dentry *dentry;
	struct nameidata nd;

	if (S_ISDIR(mode))
		return -EPERM;

	error = user_path_parent(dfd, filename, &nd, &tmp);
	if (error)
		return error;

	dentry = lookup_create(&nd, 0);
	if (IS_ERR(dentry)) {
		error = PTR_ERR(dentry);
		goto out_unlock;
	}
	if (!IS_POSIXACL(nd.path.dentry->d_inode))
		mode &= ~current_umask();
	error = may_mknod(mode);
	if (error)
		goto out_dput;
	error = mnt_want_write(nd.path.mnt);
	if (error)
		goto out_dput;
	error = security_path_mknod(&nd.path, dentry, mode, dev);
	if (error)
		goto out_drop_write;
	switch (mode & S_IFMT) {
		case 0: case S_IFREG:
			error = vfs_create(nd.path.dentry->d_inode,dentry,mode,&nd);
			break;
		case S_IFCHR: case S_IFBLK:
			error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,
					new_decode_dev(dev));
			break;
		case S_IFIFO: case S_IFSOCK:
			error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,0);
			break;
	}
out_drop_write:
	mnt_drop_write(nd.path.mnt);
out_dput:
	dput(dentry);
out_unlock:
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
	path_put(&nd.path);
	putname(tmp);

	return error;
}

SYSCALL_DEFINE3(mknod, const char __user *, filename, int, mode, unsigned, dev)
{
	return sys_mknodat(AT_FDCWD, filename, mode, dev);
}

int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	int error = may_create(dir, dentry);

	if (error)
		return error;

	if (!dir->i_op->mkdir)
		return -EPERM;

	mode &= (S_IRWXUGO|S_ISVTX);
	error = security_inode_mkdir(dir, dentry, mode);
	if (error)
		return error;

	error = dir->i_op->mkdir(dir, dentry, mode);
	if (!error)
		fsnotify_mkdir(dir, dentry);
	return error;
}

SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, int, mode)
{
	int error = 0;
	char * tmp;
	struct dentry *dentry;
	struct nameidata nd;

	error = user_path_parent(dfd, pathname, &nd, &tmp);
	if (error)
		goto out_err;

	dentry = lookup_create(&nd, 1);
	error = PTR_ERR(dentry);
	if (IS_ERR(dentry))
		goto out_unlock;

	if (!IS_POSIXACL(nd.path.dentry->d_inode))
		mode &= ~current_umask();
	error = mnt_want_write(nd.path.mnt);
	if (error)
		goto out_dput;
	error = security_path_mkdir(&nd.path, dentry, mode);
	if (error)
		goto out_drop_write;
	error = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
out_drop_write:
	mnt_drop_write(nd.path.mnt);
out_dput:
	dput(dentry);
out_unlock:
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
	path_put(&nd.path);
	putname(tmp);
out_err:
	return error;
}

SYSCALL_DEFINE2(mkdir, const char __user *, pathname, int, mode)
{
	return sys_mkdirat(AT_FDCWD, pathname, mode);
}

/*
 * The dentry_unhash() helper will try to drop the dentry early: we
 * should have a usage count of 2 if we're the only user of this
 * dentry, and if that is true (possibly after pruning the dcache),
 * then we drop the dentry now.
 *
 * A low-level filesystem can, if it choses, legally
 * do a
 *
 *	if (!d_unhashed(dentry))
 *		return -EBUSY;
 *
 * if it cannot handle the case of removing a directory
 * that is still in use by something else..
 */
void dentry_unhash(struct dentry *dentry)
{
	shrink_dcache_parent(dentry);
	spin_lock(&dentry->d_lock);
	if (dentry->d_count == 1)
		__d_drop(dentry);
	spin_unlock(&dentry->d_lock);
}

int vfs_rmdir(struct inode *dir, struct dentry *dentry)
{
	int error = may_delete(dir, dentry, 1);

	if (error)
		return error;

	if (!dir->i_op->rmdir)
		return -EPERM;

	mutex_lock(&dentry->d_inode->i_mutex);

	error = -EBUSY;
	if (d_mountpoint(dentry))
		goto out;

	error = security_inode_rmdir(dir, dentry);
	if (error)
		goto out;

	shrink_dcache_parent(dentry);
	error = dir->i_op->rmdir(dir, dentry);
	if (error)
		goto out;

	dentry->d_inode->i_flags |= S_DEAD;
	dont_mount(dentry);

out:
	mutex_unlock(&dentry->d_inode->i_mutex);
	if (!error)
		d_delete(dentry);
	return error;
}

static long do_rmdir(int dfd, const char __user *pathname)
{
	int error = 0;
	char * name;
	struct dentry *dentry;
	struct nameidata nd;

	error = user_path_parent(dfd, pathname, &nd, &name);
	if (error)
		return error;

	switch(nd.last_type) {
	case LAST_DOTDOT:
		error = -ENOTEMPTY;
		goto exit1;
	case LAST_DOT:
		error = -EINVAL;
		goto exit1;
	case LAST_ROOT:
		error = -EBUSY;
		goto exit1;
	}

	nd.flags &= ~LOOKUP_PARENT;

	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
	dentry = lookup_hash(&nd);
	error = PTR_ERR(dentry);
	if (IS_ERR(dentry))
		goto exit2;
	if (!dentry->d_inode) {
		error = -ENOENT;
		goto exit3;
	}
	error = mnt_want_write(nd.path.mnt);
	if (error)
		goto exit3;
	error = security_path_rmdir(&nd.path, dentry);
	if (error)
		goto exit4;
	error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
exit4:
	mnt_drop_write(nd.path.mnt);
exit3:
	dput(dentry);
exit2:
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
exit1:
	path_put(&nd.path);
	putname(name);
	return error;
}

SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
{
	return do_rmdir(AT_FDCWD, pathname);
}

int vfs_unlink(struct inode *dir, struct dentry *dentry)
{
	int error = may_delete(dir, dentry, 0);

	if (error)
		return error;

	if (!dir->i_op->unlink)
		return -EPERM;

	mutex_lock(&dentry->d_inode->i_mutex);
	if (d_mountpoint(dentry))
		error = -EBUSY;
	else {
		error = security_inode_unlink(dir, dentry);
		if (!error) {
			error = dir->i_op->unlink(dir, dentry);
			if (!error)
				dont_mount(dentry);
		}
	}
	mutex_unlock(&dentry->d_inode->i_mutex);

	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
		fsnotify_link_count(dentry->d_inode);
		d_delete(dentry);
	}

	return error;
}

/*
 * Make sure that the actual truncation of the file will occur outside its
 * directory's i_mutex.  Truncate can take a long time if there is a lot of
 * writeout happening, and we don't want to prevent access to the directory
 * while waiting on the I/O.
 */
static long do_unlinkat(int dfd, const char __user *pathname)
{
	int error;
	char *name;
	struct dentry *dentry;
	struct nameidata nd;
	struct inode *inode = NULL;

	error = user_path_parent(dfd, pathname, &nd, &name);
	if (error)
		return error;

	error = -EISDIR;
	if (nd.last_type != LAST_NORM)
		goto exit1;

	nd.flags &= ~LOOKUP_PARENT;

	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
	dentry = lookup_hash(&nd);
	error = PTR_ERR(dentry);
	if (!IS_ERR(dentry)) {
		/* Why not before? Because we want correct error value */
		if (nd.last.name[nd.last.len])
			goto slashes;
		inode = dentry->d_inode;
		if (!inode)
			goto slashes;
		ihold(inode);
		error = mnt_want_write(nd.path.mnt);
		if (error)
			goto exit2;
		error = security_path_unlink(&nd.path, dentry);
		if (error)
			goto exit3;
		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
exit3:
		mnt_drop_write(nd.path.mnt);
	exit2:
		dput(dentry);
	}
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
	if (inode)
		iput(inode);	/* truncate the inode here */
exit1:
	path_put(&nd.path);
	putname(name);
	return error;

slashes:
	error = !dentry->d_inode ? -ENOENT :
		S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
	goto exit2;
}

SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
{
	if ((flag & ~AT_REMOVEDIR) != 0)
		return -EINVAL;

	if (flag & AT_REMOVEDIR)
		return do_rmdir(dfd, pathname);

	return do_unlinkat(dfd, pathname);
}

SYSCALL_DEFINE1(unlink, const char __user *, pathname)
{
	return do_unlinkat(AT_FDCWD, pathname);
}

int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
{
	int error = may_create(dir, dentry);

	if (error)
		return error;

	if (!dir->i_op->symlink)
		return -EPERM;

	error = security_inode_symlink(dir, dentry, oldname);
	if (error)
		return error;

	error = dir->i_op->symlink(dir, dentry, oldname);
	if (!error)
		fsnotify_create(dir, dentry);
	return error;
}

SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
		int, newdfd, const char __user *, newname)
{
	int error;
	char *from;
	char *to;
	struct dentry *dentry;
	struct nameidata nd;

	from = getname(oldname);
	if (IS_ERR(from))
		return PTR_ERR(from);

	error = user_path_parent(newdfd, newname, &nd, &to);
	if (error)
		goto out_putname;

	dentry = lookup_create(&nd, 0);
	error = PTR_ERR(dentry);
	if (IS_ERR(dentry))
		goto out_unlock;

	error = mnt_want_write(nd.path.mnt);
	if (error)
		goto out_dput;
	error = security_path_symlink(&nd.path, dentry, from);
	if (error)
		goto out_drop_write;
	error = vfs_symlink(nd.path.dentry->d_inode, dentry, from);
out_drop_write:
	mnt_drop_write(nd.path.mnt);
out_dput:
	dput(dentry);
out_unlock:
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
	path_put(&nd.path);
	putname(to);
out_putname:
	putname(from);
	return error;
}

SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
{
	return sys_symlinkat(oldname, AT_FDCWD, newname);
}

int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
{
	struct inode *inode = old_dentry->d_inode;
	int error;

	if (!inode)
		return -ENOENT;

	error = may_create(dir, new_dentry);
	if (error)
		return error;

	if (dir->i_sb != inode->i_sb)
		return -EXDEV;

	/*
	 * A link to an append-only or immutable file cannot be created.
	 */
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return -EPERM;
	if (!dir->i_op->link)
		return -EPERM;
	if (S_ISDIR(inode->i_mode))
		return -EPERM;

	error = security_inode_link(old_dentry, dir, new_dentry);
	if (error)
		return error;

	mutex_lock(&inode->i_mutex);
	/* Make sure we don't allow creating hardlink to an unlinked file */
	if (inode->i_nlink == 0)
		error =  -ENOENT;
	else
		error = dir->i_op->link(old_dentry, dir, new_dentry);
	mutex_unlock(&inode->i_mutex);
	if (!error)
		fsnotify_link(dir, inode, new_dentry);
	return error;
}

/*
 * Hardlinks are often used in delicate situations.  We avoid
 * security-related surprises by not following symlinks on the
 * newname.  --KAB
 *
 * We don't follow them on the oldname either to be compatible
 * with linux 2.0, and to avoid hard-linking to directories
 * and other special files.  --ADM
 */
SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
		int, newdfd, const char __user *, newname, int, flags)
{
	struct dentry *new_dentry;
	struct nameidata nd;
	struct path old_path;
	int how = 0;
	int error;
	char *to;

	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;
	/*
	 * To use null names we require CAP_DAC_READ_SEARCH
	 * This ensures that not everyone will be able to create
	 * handlink using the passed filedescriptor.
	 */
	if (flags & AT_EMPTY_PATH) {
		if (!capable(CAP_DAC_READ_SEARCH))
			return -ENOENT;
		how = LOOKUP_EMPTY;
	}

	if (flags & AT_SYMLINK_FOLLOW)
		how |= LOOKUP_FOLLOW;

	error = user_path_at(olddfd, oldname, how, &old_path);
	if (error)
		return error;

	error = user_path_parent(newdfd, newname, &nd, &to);
	if (error)
		goto out;
	error = -EXDEV;
	if (old_path.mnt != nd.path.mnt)
		goto out_release;
	new_dentry = lookup_create(&nd, 0);
	error = PTR_ERR(new_dentry);
	if (IS_ERR(new_dentry))
		goto out_unlock;
	error = mnt_want_write(nd.path.mnt);
	if (error)
		goto out_dput;
	error = security_path_link(old_path.dentry, &nd.path, new_dentry);
	if (error)
		goto out_drop_write;
	error = vfs_link(old_path.dentry, nd.path.dentry->d_inode, new_dentry);
out_drop_write:
	mnt_drop_write(nd.path.mnt);
out_dput:
	dput(new_dentry);
out_unlock:
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
out_release:
	path_put(&nd.path);
	putname(to);
out:
	path_put(&old_path);

	return error;
}

SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
{
	return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
}

/*
 * The worst of all namespace operations - renaming directory. "Perverted"
 * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
 * Problems:
 *	a) we can get into loop creation. Check is done in is_subdir().
 *	b) race potential - two innocent renames can create a loop together.
 *	   That's where 4.4 screws up. Current fix: serialization on
 *	   sb->s_vfs_rename_mutex. We might be more accurate, but that's another
 *	   story.
 *	c) we have to lock _three_ objects - parents and victim (if it exists).
 *	   And that - after we got ->i_mutex on parents (until then we don't know
 *	   whether the target exists).  Solution: try to be smart with locking
 *	   order for inodes.  We rely on the fact that tree topology may change
 *	   only under ->s_vfs_rename_mutex _and_ that parent of the object we
 *	   move will be locked.  Thus we can rank directories by the tree
 *	   (ancestors first) and rank all non-directories after them.
 *	   That works since everybody except rename does "lock parent, lookup,
 *	   lock child" and rename is under ->s_vfs_rename_mutex.
 *	   HOWEVER, it relies on the assumption that any object with ->lookup()
 *	   has no more than 1 dentry.  If "hybrid" objects will ever appear,
 *	   we'd better make sure that there's no link(2) for them.
 *	d) conversion from fhandle to dentry may come in the wrong moment - when
 *	   we are removing the target. Solution: we will have to grab ->i_mutex
 *	   in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
 *	   ->i_mutex on parents, which works but leads to some truly excessive
 *	   locking].
 */
static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
			  struct inode *new_dir, struct dentry *new_dentry)
{
	int error = 0;
	struct inode *target = new_dentry->d_inode;

	/*
	 * If we are going to change the parent - check write permissions,
	 * we'll need to flip '..'.
	 */
	if (new_dir != old_dir) {
		error = inode_permission(old_dentry->d_inode, MAY_WRITE);
		if (error)
			return error;
	}

	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
	if (error)
		return error;

	if (target)
		mutex_lock(&target->i_mutex);

	error = -EBUSY;
	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
		goto out;

	if (target)
		shrink_dcache_parent(new_dentry);
	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
	if (error)
		goto out;

	if (target) {
		target->i_flags |= S_DEAD;
		dont_mount(new_dentry);
	}
out:
	if (target)
		mutex_unlock(&target->i_mutex);
	if (!error)
		if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
			d_move(old_dentry,new_dentry);
	return error;
}

static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
			    struct inode *new_dir, struct dentry *new_dentry)
{
	struct inode *target = new_dentry->d_inode;
	int error;

	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
	if (error)
		return error;

	dget(new_dentry);
	if (target)
		mutex_lock(&target->i_mutex);

	error = -EBUSY;
	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
		goto out;

	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
	if (error)
		goto out;

	if (target)
		dont_mount(new_dentry);
	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
		d_move(old_dentry, new_dentry);
out:
	if (target)
		mutex_unlock(&target->i_mutex);
	dput(new_dentry);
	return error;
}

int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
	       struct inode *new_dir, struct dentry *new_dentry)
{
	int error;
	int is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
	const unsigned char *old_name;

	if (old_dentry->d_inode == new_dentry->d_inode)
 		return 0;
 
	error = may_delete(old_dir, old_dentry, is_dir);
	if (error)
		return error;

	if (!new_dentry->d_inode)
		error = may_create(new_dir, new_dentry);
	else
		error = may_delete(new_dir, new_dentry, is_dir);
	if (error)
		return error;

	if (!old_dir->i_op->rename)
		return -EPERM;

	old_name = fsnotify_oldname_init(old_dentry->d_name.name);

	if (is_dir)
		error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
	else
		error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry);
	if (!error)
		fsnotify_move(old_dir, new_dir, old_name, is_dir,
			      new_dentry->d_inode, old_dentry);
	fsnotify_oldname_free(old_name);

	return error;
}

SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
		int, newdfd, const char __user *, newname)
{
	struct dentry *old_dir, *new_dir;
	struct dentry *old_dentry, *new_dentry;
	struct dentry *trap;
	struct nameidata oldnd, newnd;
	char *from;
	char *to;
	int error;

	error = user_path_parent(olddfd, oldname, &oldnd, &from);
	if (error)
		goto exit;

	error = user_path_parent(newdfd, newname, &newnd, &to);
	if (error)
		goto exit1;

	error = -EXDEV;
	if (oldnd.path.mnt != newnd.path.mnt)
		goto exit2;

	old_dir = oldnd.path.dentry;
	error = -EBUSY;
	if (oldnd.last_type != LAST_NORM)
		goto exit2;

	new_dir = newnd.path.dentry;
	if (newnd.last_type != LAST_NORM)
		goto exit2;

	oldnd.flags &= ~LOOKUP_PARENT;
	newnd.flags &= ~LOOKUP_PARENT;
	newnd.flags |= LOOKUP_RENAME_TARGET;

	trap = lock_rename(new_dir, old_dir);

	old_dentry = lookup_hash(&oldnd);
	error = PTR_ERR(old_dentry);
	if (IS_ERR(old_dentry))
		goto exit3;
	/* source must exist */
	error = -ENOENT;
	if (!old_dentry->d_inode)
		goto exit4;
	/* unless the source is a directory trailing slashes give -ENOTDIR */
	if (!S_ISDIR(old_dentry->d_inode->i_mode)) {
		error = -ENOTDIR;
		if (oldnd.last.name[oldnd.last.len])
			goto exit4;
		if (newnd.last.name[newnd.last.len])
			goto exit4;
	}
	/* source should not be ancestor of target */
	error = -EINVAL;
	if (old_dentry == trap)
		goto exit4;
	new_dentry = lookup_hash(&newnd);
	error = PTR_ERR(new_dentry);
	if (IS_ERR(new_dentry))
		goto exit4;
	/* target should not be an ancestor of source */
	error = -ENOTEMPTY;
	if (new_dentry == trap)
		goto exit5;

	error = mnt_want_write(oldnd.path.mnt);
	if (error)
		goto exit5;
	error = security_path_rename(&oldnd.path, old_dentry,
				     &newnd.path, new_dentry);
	if (error)
		goto exit6;
	error = vfs_rename(old_dir->d_inode, old_dentry,
				   new_dir->d_inode, new_dentry);
exit6:
	mnt_drop_write(oldnd.path.mnt);
exit5:
	dput(new_dentry);
exit4:
	dput(old_dentry);
exit3:
	unlock_rename(new_dir, old_dir);
exit2:
	path_put(&newnd.path);
	putname(to);
exit1:
	path_put(&oldnd.path);
	putname(from);
exit:
	return error;
}

SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
{
	return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
}

int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
{
	int len;

	len = PTR_ERR(link);
	if (IS_ERR(link))
		goto out;

	len = strlen(link);
	if (len > (unsigned) buflen)
		len = buflen;
	if (copy_to_user(buffer, link, len))
		len = -EFAULT;
out:
	return len;
}

/*
 * A helper for ->readlink().  This should be used *ONLY* for symlinks that
 * have ->follow_link() touching nd only in nd_set_link().  Using (or not
 * using) it for any given inode is up to filesystem.
 */
int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
	struct nameidata nd;
	void *cookie;
	int res;

	nd.depth = 0;
	cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
	if (IS_ERR(cookie))
		return PTR_ERR(cookie);

	res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
	if (dentry->d_inode->i_op->put_link)
		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
	return res;
}

int vfs_follow_link(struct nameidata *nd, const char *link)
{
	return __vfs_follow_link(nd, link);
}

/* get the link contents into pagecache */
static char *page_getlink(struct dentry * dentry, struct page **ppage)
{
	char *kaddr;
	struct page *page;
	struct address_space *mapping = dentry->d_inode->i_mapping;
	page = read_mapping_page(mapping, 0, NULL);
	if (IS_ERR(page))
		return (char*)page;
	*ppage = page;
	kaddr = kmap(page);
	nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1);
	return kaddr;
}

int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
	struct page *page = NULL;
	char *s = page_getlink(dentry, &page);
	int res = vfs_readlink(dentry,buffer,buflen,s);
	if (page) {
		kunmap(page);
		page_cache_release(page);
	}
	return res;
}

void *page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
{
	struct page *page = NULL;
	nd_set_link(nd, page_getlink(dentry, &page));
	return page;
}

void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
{
	struct page *page = cookie;

	if (page) {
		kunmap(page);
		page_cache_release(page);
	}
}

/*
 * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
 */
int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
{
	struct address_space *mapping = inode->i_mapping;
	struct page *page;
	void *fsdata;
	int err;
	char *kaddr;
	unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
	if (nofs)
		flags |= AOP_FLAG_NOFS;

retry:
	err = pagecache_write_begin(NULL, mapping, 0, len-1,
				flags, &page, &fsdata);
	if (err)
		goto fail;

	kaddr = kmap_atomic(page, KM_USER0);
	memcpy(kaddr, symname, len-1);
	kunmap_atomic(kaddr, KM_USER0);

	err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
							page, fsdata);
	if (err < 0)
		goto fail;
	if (err < len-1)
		goto retry;

	mark_inode_dirty(inode);
	return 0;
fail:
	return err;
}

int page_symlink(struct inode *inode, const char *symname, int len)
{
	return __page_symlink(inode, symname, len,
			!(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
}

const struct inode_operations page_symlink_inode_operations = {
	.readlink	= generic_readlink,
	.follow_link	= page_follow_link_light,
	.put_link	= page_put_link,
};

EXPORT_SYMBOL(user_path_at);
EXPORT_SYMBOL(follow_down_one);
EXPORT_SYMBOL(follow_down);
EXPORT_SYMBOL(follow_up);
EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
EXPORT_SYMBOL(getname);
EXPORT_SYMBOL(lock_rename);
EXPORT_SYMBOL(lookup_one_len);
EXPORT_SYMBOL(page_follow_link_light);
EXPORT_SYMBOL(page_put_link);
EXPORT_SYMBOL(page_readlink);
EXPORT_SYMBOL(__page_symlink);
EXPORT_SYMBOL(page_symlink);
EXPORT_SYMBOL(page_symlink_inode_operations);
EXPORT_SYMBOL(kern_path_parent);
EXPORT_SYMBOL(kern_path);
EXPORT_SYMBOL(vfs_path_lookup);
EXPORT_SYMBOL(inode_permission);
EXPORT_SYMBOL(unlock_rename);
EXPORT_SYMBOL(vfs_create);
EXPORT_SYMBOL(vfs_follow_link);
EXPORT_SYMBOL(vfs_link);
EXPORT_SYMBOL(vfs_mkdir);
EXPORT_SYMBOL(vfs_mknod);
EXPORT_SYMBOL(generic_permission);
EXPORT_SYMBOL(vfs_readlink);
EXPORT_SYMBOL(vfs_rename);
EXPORT_SYMBOL(vfs_rmdir);
EXPORT_SYMBOL(vfs_symlink);
EXPORT_SYMBOL(vfs_unlink);
EXPORT_SYMBOL(dentry_unhash);
EXPORT_SYMBOL(generic_readlink);
OpenPOWER on IntegriCloud