aboutsummaryrefslogblamecommitdiffstats
path: root/fs/namei.c
blob: 1d93cb4f7c5fdef37ff0ce60daeb6edbad8d12aa (plain) (tree)
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
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
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



























































































































































































































































































































                                                                                
                                  

















































































































































































                                                                                                      




                              
                                                                           

                  
                                             
 
                                       
                              
 

                                  







                                                                    

                          










                                                                
                                                                         







                                                    
                                                           




                                    
                                         

                              

                   
                           

                                  
                         

























                                                             
















                                                                               
                                                                       
 



                                                                     
                              

                               
                                                  
         




                                                             
                                                              




                                            
                              

                               





                                                  
                                                      


                                        
                                                

                                              

                                                      




                                                        

                                                                





                                                  

                                             



                                                    
                                                           

                                            

                                 
         
                                            

 

















                                                                           
                             





















                                                   

                                                                      
  

                                                                    



























































                                                                               
                                                  


















                                                                          









                                               
                                                        










                                                    

                                                




















                                                                 
                                                  












                                                                          


                                                                          
                                                        




                                                    

                                                






































                                                                            
                                        
                                         











































                                                                   



                                                                      






























































                                                                                         
                                                                         

                                                                                    
                       











                                                                          
                                                                










                                                       
    




















































































































































































































































































































































































                                                                                                   
                         










































                                                                                   
                                                               
                           

        

                                     




                                                   
                                    

                                                    
                                                                        

                                         
                                         
















                                                                      
                                    
                               

                                       

                        
                                  
                               
                                                                                  


                             
                                 


                                
                        
                                                                          







                                             
                          
                                
                                 


















                                                                              
                                                            

                               
                                            


                                    
                                       
                        













                                          
                                                               
                           










                                                                   

                                                  


                                                              
                                                 

                                          



                                                            


                                       



                               


                                                    






                                                                        








                                                                       
                                 










































































































































































































































































































































































































































































































                                                                                         

                                                                           










































                                                                                        

                                                                             

















































































































































































































































































































































                                                                                          
/*
 *  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/quotaops.h>
#include <linux/pagemap.h>
#include <linux/dnotify.h>
#include <linux/smp_lock.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <asm/namei.h>
#include <asm/uaccess.h>

#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])

/* [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-existant 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_sem 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 inline 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;
}

char * getname(const char __user * filename)
{
	char *tmp, *result;

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

		result = tmp;
		if (retval < 0) {
			__putname(tmp);
			result = ERR_PTR(retval);
		}
	}
	audit_getname(result);
	return result;
}

#ifdef CONFIG_AUDITSYSCALL
void putname(const char *name)
{
	if (unlikely(current->audit_context))
		audit_putname(name);
	else
		__putname(name);
}
EXPORT_SYMBOL(putname);
#endif


/**
 * 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)
 * @check_acl:	optional callback to check for Posix ACLs
 *
 * 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..
 */
int generic_permission(struct inode *inode, int mask,
		int (*check_acl)(struct inode *inode, int mask))
{
	umode_t			mode = inode->i_mode;

	if (current->fsuid == inode->i_uid)
		mode >>= 6;
	else {
		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
			int error = check_acl(inode, mask);
			if (error == -EACCES)
				goto check_capabilities;
			else if (error != -EAGAIN)
				return error;
		}

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

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

 check_capabilities:
	/*
	 * Read/write DACs are always overridable.
	 * Executable DACs are overridable if at least one exec bit is set.
	 */
	if (!(mask & MAY_EXEC) ||
	    (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
		if (capable(CAP_DAC_OVERRIDE))
			return 0;

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

	return -EACCES;
}

int permission(struct inode *inode, int mask, struct nameidata *nd)
{
	int retval, submask;

	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;
	}


	/* Ordinary permission routines do not understand MAY_APPEND. */
	submask = mask & ~MAY_APPEND;
	if (inode->i_op && inode->i_op->permission)
		retval = inode->i_op->permission(inode, submask, nd);
	else
		retval = generic_permission(inode, submask, NULL);
	if (retval)
		return retval;

	return security_inode_permission(inode, mask, nd);
}

/*
 * get_write_access() gets write permission for a file.
 * put_write_access() releases this write permission.
 * This is used for regular files.
 * We cannot support write (and maybe mmap read-write shared) accesses and
 * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
 * can have the following values:
 * 0: no writers, no VM_DENYWRITE mappings
 * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
 * > 0: (i_writecount) users are writing to the file.
 *
 * Normally we operate on that counter with atomic_{inc,dec} and it's safe
 * except for the cases where we don't hold i_writecount yet. Then we need to
 * use {get,deny}_write_access() - these functions check the sign and refuse
 * to do the change if sign is wrong. Exclusion between them is provided by
 * the inode->i_lock spinlock.
 */

int get_write_access(struct inode * inode)
{
	spin_lock(&inode->i_lock);
	if (atomic_read(&inode->i_writecount) < 0) {
		spin_unlock(&inode->i_lock);
		return -ETXTBSY;
	}
	atomic_inc(&inode->i_writecount);
	spin_unlock(&inode->i_lock);

	return 0;
}

int deny_write_access(struct file * file)
{
	struct inode *inode = file->f_dentry->d_inode;

	spin_lock(&inode->i_lock);
	if (atomic_read(&inode->i_writecount) > 0) {
		spin_unlock(&inode->i_lock);
		return -ETXTBSY;
	}
	atomic_dec(&inode->i_writecount);
	spin_unlock(&inode->i_lock);

	return 0;
}

void path_release(struct nameidata *nd)
{
	dput(nd->dentry);
	mntput(nd->mnt);
}

/*
 * umount() mustn't call path_release()/mntput() as that would clear
 * mnt_expiry_mark
 */
void path_release_on_umount(struct nameidata *nd)
{
	dput(nd->dentry);
	mntput_no_expire(nd->mnt);
}

/*
 * Internal lookup() using the new generic dcache.
 * SMP-safe
 */
static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
{
	struct dentry * dentry = __d_lookup(parent, name);

	/* lockess __d_lookup may fail due to concurrent d_move() 
	 * in some unrelated directory, so try with d_lookup
	 */
	if (!dentry)
		dentry = d_lookup(parent, name);

	if (dentry && dentry->d_op && dentry->d_op->d_revalidate) {
		if (!dentry->d_op->d_revalidate(dentry, nd) && !d_invalidate(dentry)) {
			dput(dentry);
			dentry = NULL;
		}
	}
	return dentry;
}

/*
 * Short-cut version of permission(), for calling by
 * path_walk(), when dcache lock is held.  Combines parts
 * of 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_lite(struct inode *inode,
				       struct nameidata *nd)
{
	umode_t	mode = inode->i_mode;

	if (inode->i_op && inode->i_op->permission)
		return -EAGAIN;

	if (current->fsuid == inode->i_uid)
		mode >>= 6;
	else if (in_group_p(inode->i_gid))
		mode >>= 3;

	if (mode & MAY_EXEC)
		goto ok;

	if ((inode->i_mode & S_IXUGO) && capable(CAP_DAC_OVERRIDE))
		goto ok;

	if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_OVERRIDE))
		goto ok;

	if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_READ_SEARCH))
		goto ok;

	return -EACCES;
ok:
	return security_inode_permission(inode, MAY_EXEC, nd);
}

/*
 * This is called when everything else fails, and we actually have
 * to go to the low-level filesystem to find out what we should do..
 *
 * We get the directory semaphore, and after getting that we also
 * make sure that nobody added the entry to the dcache in the meantime..
 * SMP-safe
 */
static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
{
	struct dentry * result;
	struct inode *dir = parent->d_inode;

	down(&dir->i_sem);
	/*
	 * First re-do the cached lookup just in case it was created
	 * while we waited for the directory semaphore..
	 *
	 * FIXME! This could use version numbering or similar to
	 * avoid unnecessary cache lookups.
	 *
	 * The "dcache_lock" is purely to protect the RCU list walker
	 * from concurrent renames at this point (we mustn't get false
	 * negatives from the RCU list walk here, unlike the optimistic
	 * fast walk).
	 *
	 * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
	 */
	result = d_lookup(parent, name);
	if (!result) {
		struct dentry * dentry = d_alloc(parent, name);
		result = ERR_PTR(-ENOMEM);
		if (dentry) {
			result = dir->i_op->lookup(dir, dentry, nd);
			if (result)
				dput(dentry);
			else
				result = dentry;
		}
		up(&dir->i_sem);
		return result;
	}

	/*
	 * Uhhuh! Nasty case: the cache was re-populated while
	 * we waited on the semaphore. Need to revalidate.
	 */
	up(&dir->i_sem);
	if (result->d_op && result->d_op->d_revalidate) {
		if (!result->d_op->d_revalidate(result, nd) && !d_invalidate(result)) {
			dput(result);
			result = ERR_PTR(-ENOENT);
		}
	}
	return result;
}

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

/* SMP-safe */
static inline int
walk_init_root(const char *name, struct nameidata *nd)
{
	read_lock(&current->fs->lock);
	if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
		nd->mnt = mntget(current->fs->altrootmnt);
		nd->dentry = dget(current->fs->altroot);
		read_unlock(&current->fs->lock);
		if (__emul_lookup_dentry(name,nd))
			return 0;
		read_lock(&current->fs->lock);
	}
	nd->mnt = mntget(current->fs->rootmnt);
	nd->dentry = dget(current->fs->root);
	read_unlock(&current->fs->lock);
	return 1;
}

static inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
	int res = 0;
	char *name;
	if (IS_ERR(link))
		goto fail;

	if (*link == '/') {
		path_release(nd);
		if (!walk_init_root(link, nd))
			/* weird __emul_prefix() stuff did it */
			goto out;
	}
	res = link_path_walk(link, nd);
out:
	if (nd->depth || res || nd->last_type!=LAST_NORM)
		return res;
	/*
	 * If it is an iterative symlinks resolution in open_namei() we
	 * have to copy the last component. And all that crap because of
	 * bloody create() on broken symlinks. Furrfu...
	 */
	name = __getname();
	if (unlikely(!name)) {
		path_release(nd);
		return -ENOMEM;
	}
	strcpy(name, nd->last.name);
	nd->last.name = name;
	return 0;
fail:
	path_release(nd);
	return PTR_ERR(link);
}

struct path {
	struct vfsmount *mnt;
	struct dentry *dentry;
};

static inline int __do_follow_link(struct path *path, struct nameidata *nd)
{
	int error;
	struct dentry *dentry = path->dentry;

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

	if (path->mnt == nd->mnt)
		mntget(path->mnt);
	error = dentry->d_inode->i_op->follow_link(dentry, nd);
	if (!error) {
		char *s = nd_get_link(nd);
		if (s)
			error = __vfs_follow_link(nd, s);
		if (dentry->d_inode->i_op->put_link)
			dentry->d_inode->i_op->put_link(dentry, nd);
	}
	dput(dentry);
	mntput(path->mnt);

	return error;
}

/*
 * 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 do_follow_link(struct path *path, struct nameidata *nd)
{
	int err = -ELOOP;
	if (current->link_count >= MAX_NESTED_LINKS)
		goto loop;
	if (current->total_link_count >= 40)
		goto loop;
	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
	cond_resched();
	err = security_inode_follow_link(path->dentry, nd);
	if (err)
		goto loop;
	current->link_count++;
	current->total_link_count++;
	nd->depth++;
	err = __do_follow_link(path, nd);
	current->link_count--;
	nd->depth--;
	return err;
loop:
	dput(path->dentry);
	if (path->mnt != nd->mnt)
		mntput(path->mnt);
	path_release(nd);
	return err;
}

int follow_up(struct vfsmount **mnt, struct dentry **dentry)
{
	struct vfsmount *parent;
	struct dentry *mountpoint;
	spin_lock(&vfsmount_lock);
	parent=(*mnt)->mnt_parent;
	if (parent == *mnt) {
		spin_unlock(&vfsmount_lock);
		return 0;
	}
	mntget(parent);
	mountpoint=dget((*mnt)->mnt_mountpoint);
	spin_unlock(&vfsmount_lock);
	dput(*dentry);
	*dentry = mountpoint;
	mntput(*mnt);
	*mnt = parent;
	return 1;
}

/* no need for dcache_lock, as serialization is taken care in
 * namespace.c
 */
static int __follow_mount(struct path *path)
{
	int res = 0;
	while (d_mountpoint(path->dentry)) {
		struct vfsmount *mounted = lookup_mnt(path->mnt, path->dentry);
		if (!mounted)
			break;
		dput(path->dentry);
		if (res)
			mntput(path->mnt);
		path->mnt = mounted;
		path->dentry = dget(mounted->mnt_root);
		res = 1;
	}
	return res;
}

static void follow_mount(struct vfsmount **mnt, struct dentry **dentry)
{
	while (d_mountpoint(*dentry)) {
		struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
		if (!mounted)
			break;
		dput(*dentry);
		mntput(*mnt);
		*mnt = mounted;
		*dentry = dget(mounted->mnt_root);
	}
}

/* no need for dcache_lock, as serialization is taken care in
 * namespace.c
 */
int follow_down(struct vfsmount **mnt, struct dentry **dentry)
{
	struct vfsmount *mounted;

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

static inline void follow_dotdot(struct nameidata *nd)
{
	while(1) {
		struct vfsmount *parent;
		struct dentry *old = nd->dentry;

                read_lock(&current->fs->lock);
		if (nd->dentry == current->fs->root &&
		    nd->mnt == current->fs->rootmnt) {
                        read_unlock(&current->fs->lock);
			break;
		}
                read_unlock(&current->fs->lock);
		spin_lock(&dcache_lock);
		if (nd->dentry != nd->mnt->mnt_root) {
			nd->dentry = dget(nd->dentry->d_parent);
			spin_unlock(&dcache_lock);
			dput(old);
			break;
		}
		spin_unlock(&dcache_lock);
		spin_lock(&vfsmount_lock);
		parent = nd->mnt->mnt_parent;
		if (parent == nd->mnt) {
			spin_unlock(&vfsmount_lock);
			break;
		}
		mntget(parent);
		nd->dentry = dget(nd->mnt->mnt_mountpoint);
		spin_unlock(&vfsmount_lock);
		dput(old);
		mntput(nd->mnt);
		nd->mnt = parent;
	}
	follow_mount(&nd->mnt, &nd->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 vfsmount *mnt = nd->mnt;
	struct dentry *dentry = __d_lookup(nd->dentry, name);

	if (!dentry)
		goto need_lookup;
	if (dentry->d_op && dentry->d_op->d_revalidate)
		goto need_revalidate;
done:
	path->mnt = mnt;
	path->dentry = dentry;
	__follow_mount(path);
	return 0;

need_lookup:
	dentry = real_lookup(nd->dentry, name, nd);
	if (IS_ERR(dentry))
		goto fail;
	goto done;

need_revalidate:
	if (dentry->d_op->d_revalidate(dentry, nd))
		goto done;
	if (d_invalidate(dentry))
		goto done;
	dput(dentry);
	goto need_lookup;

fail:
	return PTR_ERR(dentry);
}

/*
 * 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 fastcall int __link_path_walk(const char * name, struct nameidata *nd)
{
	struct path next;
	struct inode *inode;
	int err;
	unsigned int lookup_flags = nd->flags;
	
	while (*name=='/')
		name++;
	if (!*name)
		goto return_reval;

	inode = nd->dentry->d_inode;
	if (nd->depth)
		lookup_flags = LOOKUP_FOLLOW;

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

		err = exec_permission_lite(inode, nd);
		if (err == -EAGAIN) { 
			err = permission(inode, MAY_EXEC, 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);

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

		/*
		 * "." and ".." are special - ".." especially so because it has
		 * to be able to know about the current root directory and
		 * parent relationships.
		 */
		if (this.name[0] == '.') switch (this.len) {
			default:
				break;
			case 2:	
				if (this.name[1] != '.')
					break;
				follow_dotdot(nd);
				inode = nd->dentry->d_inode;
				/* fallthrough */
			case 1:
				continue;
		}
		/*
		 * See if the low-level filesystem might want
		 * to use its own hash..
		 */
		if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
			err = nd->dentry->d_op->d_hash(nd->dentry, &this);
			if (err < 0)
				break;
		}
		nd->flags |= LOOKUP_CONTINUE;
		/* This does the actual lookups.. */
		err = do_lookup(nd, &this, &next);
		if (err)
			break;

		err = -ENOENT;
		inode = next.dentry->d_inode;
		if (!inode)
			goto out_dput;
		err = -ENOTDIR; 
		if (!inode->i_op)
			goto out_dput;

		if (inode->i_op->follow_link) {
			err = do_follow_link(&next, nd);
			if (err)
				goto return_err;
			err = -ENOENT;
			inode = nd->dentry->d_inode;
			if (!inode)
				break;
			err = -ENOTDIR; 
			if (!inode->i_op)
				break;
		} else {
			dput(nd->dentry);
			if (nd->mnt != next.mnt)
				mntput(nd->mnt);
			nd->mnt = next.mnt;
			nd->dentry = next.dentry;
		}
		err = -ENOTDIR; 
		if (!inode->i_op->lookup)
			break;
		continue;
		/* here ends the main loop */

last_with_slashes:
		lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
last_component:
		nd->flags &= ~LOOKUP_CONTINUE;
		if (lookup_flags & LOOKUP_PARENT)
			goto lookup_parent;
		if (this.name[0] == '.') switch (this.len) {
			default:
				break;
			case 2:	
				if (this.name[1] != '.')
					break;
				follow_dotdot(nd);
				inode = nd->dentry->d_inode;
				/* fallthrough */
			case 1:
				goto return_reval;
		}
		if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
			err = nd->dentry->d_op->d_hash(nd->dentry, &this);
			if (err < 0)
				break;
		}
		err = do_lookup(nd, &this, &next);
		if (err)
			break;
		inode = next.dentry->d_inode;
		if ((lookup_flags & LOOKUP_FOLLOW)
		    && inode && inode->i_op && inode->i_op->follow_link) {
			err = do_follow_link(&next, nd);
			if (err)
				goto return_err;
			inode = nd->dentry->d_inode;
		} else {
			dput(nd->dentry);
			if (nd->mnt != next.mnt)
				mntput(nd->mnt);
			nd->mnt = next.mnt;
			nd->dentry = next.dentry;
		}
		err = -ENOENT;
		if (!inode)
			break;
		if (lookup_flags & LOOKUP_DIRECTORY) {
			err = -ENOTDIR; 
			if (!inode->i_op || !inode->i_op->lookup)
				break;
		}
		goto return_base;
lookup_parent:
		nd->last = this;
		nd->last_type = LAST_NORM;
		if (this.name[0] != '.')
			goto return_base;
		if (this.len == 1)
			nd->last_type = LAST_DOT;
		else if (this.len == 2 && this.name[1] == '.')
			nd->last_type = LAST_DOTDOT;
		else
			goto return_base;
return_reval:
		/*
		 * We bypassed the ordinary revalidation routines.
		 * We may need to check the cached dentry for staleness.
		 */
		if (nd->dentry && nd->dentry->d_sb &&
		    (nd->dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) {
			err = -ESTALE;
			/* Note: we do not d_invalidate() */
			if (!nd->dentry->d_op->d_revalidate(nd->dentry, nd))
				break;
		}
return_base:
		return 0;
out_dput:
		dput(next.dentry);
		if (nd->mnt != next.mnt)
			mntput(next.mnt);
		break;
	}
	path_release(nd);
return_err:
	return err;
}

/*
 * Wrapper to retry pathname resolution whenever the underlying
 * file system returns an ESTALE.
 *
 * Retry the whole path once, forcing real lookup requests
 * instead of relying on the dcache.
 */
int fastcall link_path_walk(const char *name, struct nameidata *nd)
{
	struct nameidata save = *nd;
	int result;

	/* make sure the stuff we saved doesn't go away */
	dget(save.dentry);
	mntget(save.mnt);

	result = __link_path_walk(name, nd);
	if (result == -ESTALE) {
		*nd = save;
		dget(nd->dentry);
		mntget(nd->mnt);
		nd->flags |= LOOKUP_REVAL;
		result = __link_path_walk(name, nd);
	}

	dput(save.dentry);
	mntput(save.mnt);

	return result;
}

int fastcall path_walk(const char * name, struct nameidata *nd)
{
	current->total_link_count = 0;
	return link_path_walk(name, nd);
}

/* 
 * SMP-safe: Returns 1 and nd will have valid dentry and mnt, if
 * everything is done. Returns 0 and drops input nd, if lookup failed;
 */
static int __emul_lookup_dentry(const char *name, struct nameidata *nd)
{
	if (path_walk(name, nd))
		return 0;		/* something went wrong... */

	if (!nd->dentry->d_inode || S_ISDIR(nd->dentry->d_inode->i_mode)) {
		struct dentry *old_dentry = nd->dentry;
		struct vfsmount *old_mnt = nd->mnt;
		struct qstr last = nd->last;
		int last_type = nd->last_type;
		/*
		 * NAME was not found in alternate root or it's a directory.  Try to find
		 * it in the normal root:
		 */
		nd->last_type = LAST_ROOT;
		read_lock(&current->fs->lock);
		nd->mnt = mntget(current->fs->rootmnt);
		nd->dentry = dget(current->fs->root);
		read_unlock(&current->fs->lock);
		if (path_walk(name, nd) == 0) {
			if (nd->dentry->d_inode) {
				dput(old_dentry);
				mntput(old_mnt);
				return 1;
			}
			path_release(nd);
		}
		nd->dentry = old_dentry;
		nd->mnt = old_mnt;
		nd->last = last;
		nd->last_type = last_type;
	}
	return 1;
}

void set_fs_altroot(void)
{
	char *emul = __emul_prefix();
	struct nameidata nd;
	struct vfsmount *mnt = NULL, *oldmnt;
	struct dentry *dentry = NULL, *olddentry;
	int err;

	if (!emul)
		goto set_it;
	err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd);
	if (!err) {
		mnt = nd.mnt;
		dentry = nd.dentry;
	}
set_it:
	write_lock(&current->fs->lock);
	oldmnt = current->fs->altrootmnt;
	olddentry = current->fs->altroot;
	current->fs->altrootmnt = mnt;
	current->fs->altroot = dentry;
	write_unlock(&current->fs->lock);
	if (olddentry) {
		dput(olddentry);
		mntput(oldmnt);
	}
}

/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata *nd)
{
	int retval = 0;

	nd->last_type = LAST_ROOT; /* if there are only slashes... */
	nd->flags = flags;
	nd->depth = 0;

	read_lock(&current->fs->lock);
	if (*name=='/') {
		if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
			nd->mnt = mntget(current->fs->altrootmnt);
			nd->dentry = dget(current->fs->altroot);
			read_unlock(&current->fs->lock);
			if (__emul_lookup_dentry(name,nd))
				goto out; /* found in altroot */
			read_lock(&current->fs->lock);
		}
		nd->mnt = mntget(current->fs->rootmnt);
		nd->dentry = dget(current->fs->root);
	} else {
		nd->mnt = mntget(current->fs->pwdmnt);
		nd->dentry = dget(current->fs->pwd);
	}
	read_unlock(&current->fs->lock);
	current->total_link_count = 0;
	retval = link_path_walk(name, nd);
out:
	if (unlikely(current->audit_context
		     && nd && nd->dentry && nd->dentry->d_inode))
		audit_inode(name, nd->dentry->d_inode);
	return retval;
}

/*
 * 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 qstr *name, struct dentry * base, struct nameidata *nd)
{
	struct dentry * dentry;
	struct inode *inode;
	int err;

	inode = base->d_inode;
	err = permission(inode, MAY_EXEC, nd);
	dentry = ERR_PTR(err);
	if (err)
		goto out;

	/*
	 * See if the low-level filesystem might want
	 * to use its own hash..
	 */
	if (base->d_op && base->d_op->d_hash) {
		err = base->d_op->d_hash(base, name);
		dentry = ERR_PTR(err);
		if (err < 0)
			goto out;
	}

	dentry = cached_lookup(base, name, nd);
	if (!dentry) {
		struct dentry *new = d_alloc(base, name);
		dentry = ERR_PTR(-ENOMEM);
		if (!new)
			goto out;
		dentry = inode->i_op->lookup(inode, new, nd);
		if (!dentry)
			dentry = new;
		else
			dput(new);
	}
out:
	return dentry;
}

struct dentry * lookup_hash(struct qstr *name, struct dentry * base)
{
	return __lookup_hash(name, base, NULL);
}

/* SMP-safe */
struct dentry * lookup_one_len(const char * name, struct dentry * base, int len)
{
	unsigned long hash;
	struct qstr this;
	unsigned int c;

	this.name = name;
	this.len = len;
	if (!len)
		goto access;

	hash = init_name_hash();
	while (len--) {
		c = *(const unsigned char *)name++;
		if (c == '/' || c == '\0')
			goto access;
		hash = partial_name_hash(c, hash);
	}
	this.hash = end_name_hash(hash);

	return lookup_hash(&this, base);
access:
	return ERR_PTR(-EACCES);
}

/*
 *	namei()
 *
 * is used by most simple commands to get the inode of a specified name.
 * Open, link etc use their own routines, but this is enough for things
 * like 'chmod' etc.
 *
 * namei exists in two versions: namei/lnamei. The only difference is
 * that namei follows links, while lnamei does not.
 * SMP-safe
 */
int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
{
	char *tmp = getname(name);
	int err = PTR_ERR(tmp);

	if (!IS_ERR(tmp)) {
		err = path_lookup(tmp, flags, nd);
		putname(tmp);
	}
	return err;
}

/*
 * 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)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;
	if (inode->i_uid == current->fsuid)
		return 0;
	if (dir->i_uid == current->fsuid)
		return 0;
	return !capable(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 inline 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);

	error = permission(dir,MAY_WRITE | MAY_EXEC, NULL);
	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))
		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,
			     struct nameidata *nd)
{
	if (child->d_inode)
		return -EEXIST;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	return permission(dir,MAY_WRITE | MAY_EXEC, nd);
}

/* 
 * Special case: O_CREAT|O_EXCL implies O_NOFOLLOW for security
 * reasons.
 *
 * O_DIRECTORY translates into forcing a directory lookup.
 */
static inline int lookup_flags(unsigned int f)
{
	unsigned long retval = LOOKUP_FOLLOW;

	if (f & O_NOFOLLOW)
		retval &= ~LOOKUP_FOLLOW;
	
	if ((f & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
		retval &= ~LOOKUP_FOLLOW;
	
	if (f & O_DIRECTORY)
		retval |= LOOKUP_DIRECTORY;

	return retval;
}

/*
 * 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) {
		down(&p1->d_inode->i_sem);
		return NULL;
	}

	down(&p1->d_inode->i_sb->s_vfs_rename_sem);

	for (p = p1; p->d_parent != p; p = p->d_parent) {
		if (p->d_parent == p2) {
			down(&p2->d_inode->i_sem);
			down(&p1->d_inode->i_sem);
			return p;
		}
	}

	for (p = p2; p->d_parent != p; p = p->d_parent) {
		if (p->d_parent == p1) {
			down(&p1->d_inode->i_sem);
			down(&p2->d_inode->i_sem);
			return p;
		}
	}

	down(&p1->d_inode->i_sem);
	down(&p2->d_inode->i_sem);
	return NULL;
}

void unlock_rename(struct dentry *p1, struct dentry *p2)
{
	up(&p1->d_inode->i_sem);
	if (p1 != p2) {
		up(&p2->d_inode->i_sem);
		up(&p1->d_inode->i_sb->s_vfs_rename_sem);
	}
}

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

	if (error)
		return error;

	if (!dir->i_op || !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;
	DQUOT_INIT(dir);
	error = dir->i_op->create(dir, dentry, mode, nd);
	if (!error) {
		inode_dir_notify(dir, DN_CREATE);
		security_inode_post_create(dir, dentry, mode);
	}
	return error;
}

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

	if (!inode)
		return -ENOENT;

	if (S_ISLNK(inode->i_mode))
		return -ELOOP;
	
	if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE))
		return -EISDIR;

	error = permission(inode, acc_mode, nd);
	if (error)
		return error;

	/*
	 * FIFO's, sockets and device files are special: they don't
	 * actually live on the filesystem itself, and as such you
	 * can write to them even if the filesystem is read-only.
	 */
	if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
	    	flag &= ~O_TRUNC;
	} else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) {
		if (nd->mnt->mnt_flags & MNT_NODEV)
			return -EACCES;

		flag &= ~O_TRUNC;
	} else if (IS_RDONLY(inode) && (flag & FMODE_WRITE))
		return -EROFS;
	/*
	 * An append-only file must be opened in append mode for writing.
	 */
	if (IS_APPEND(inode)) {
		if  ((flag & FMODE_WRITE) && !(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)
		if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
			return -EPERM;

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

	if (flag & O_TRUNC) {
		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) {
			DQUOT_INIT(inode);
			
			error = do_truncate(dentry, 0);
		}
		put_write_access(inode);
		if (error)
			return error;
	} else
		if (flag & FMODE_WRITE)
			DQUOT_INIT(inode);

	return 0;
}

/*
 *	open_namei()
 *
 * namei for open - this is in fact almost the whole open-routine.
 *
 * Note that the low bits of "flag" aren't the same as in the open
 * system call - they are 00 - no permissions needed
 *			  01 - read permission needed
 *			  10 - write permission needed
 *			  11 - read/write permissions needed
 * which is a lot more logical, and also allows the "no perm" needed
 * for symlinks (where the permissions are checked later).
 * SMP-safe
 */
int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd)
{
	int acc_mode, error = 0;
	struct path path;
	struct dentry *dir;
	int count = 0;

	acc_mode = ACC_MODE(flag);

	/* Allow the LSM permission hook to distinguish append 
	   access from general write access. */
	if (flag & O_APPEND)
		acc_mode |= MAY_APPEND;

	/* Fill in the open() intent data */
	nd->intent.open.flags = flag;
	nd->intent.open.create_mode = mode;

	/*
	 * The simplest case - just a plain lookup.
	 */
	if (!(flag & O_CREAT)) {
		error = path_lookup(pathname, lookup_flags(flag)|LOOKUP_OPEN, nd);
		if (error)
			return error;
		goto ok;
	}

	/*
	 * Create - we need to know the parent.
	 */
	error = path_lookup(pathname, LOOKUP_PARENT|LOOKUP_OPEN|LOOKUP_CREATE, nd);
	if (error)
		return error;

	/*
	 * We have the parent and last component. First of all, check
	 * that we are not asked to creat(2) an obvious directory - that
	 * will not do.
	 */
	error = -EISDIR;
	if (nd->last_type != LAST_NORM || nd->last.name[nd->last.len])
		goto exit;

	dir = nd->dentry;
	nd->flags &= ~LOOKUP_PARENT;
	down(&dir->d_inode->i_sem);
	path.dentry = __lookup_hash(&nd->last, nd->dentry, nd);
	path.mnt = nd->mnt;

do_last:
	error = PTR_ERR(path.dentry);
	if (IS_ERR(path.dentry)) {
		up(&dir->d_inode->i_sem);
		goto exit;
	}

	/* Negative dentry, just create the file */
	if (!path.dentry->d_inode) {
		if (!IS_POSIXACL(dir->d_inode))
			mode &= ~current->fs->umask;
		error = vfs_create(dir->d_inode, path.dentry, mode, nd);
		up(&dir->d_inode->i_sem);
		dput(nd->dentry);
		nd->dentry = path.dentry;
		if (error)
			goto exit;
		/* Don't check for write permission, don't truncate */
		acc_mode = 0;
		flag &= ~O_TRUNC;
		goto ok;
	}

	/*
	 * It already exists.
	 */
	up(&dir->d_inode->i_sem);

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

	if (__follow_mount(&path)) {
		error = -ELOOP;
		if (flag & O_NOFOLLOW)
			goto exit_dput;
	}
	error = -ENOENT;
	if (!path.dentry->d_inode)
		goto exit_dput;
	if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link)
		goto do_link;

	dput(nd->dentry);
	nd->dentry = path.dentry;
	if (nd->mnt != path.mnt)
		mntput(nd->mnt);
	nd->mnt = path.mnt;
	error = -EISDIR;
	if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode))
		goto exit;
ok:
	error = may_open(nd, acc_mode, flag);
	if (error)
		goto exit;
	return 0;

exit_dput:
	dput(path.dentry);
	if (nd->mnt != path.mnt)
		mntput(path.mnt);
exit:
	path_release(nd);
	return error;

do_link:
	error = -ELOOP;
	if (flag & O_NOFOLLOW)
		goto exit_dput;
	/*
	 * This is subtle. Instead of calling do_follow_link() we do the
	 * thing by hands. The reason is that this way we have zero link_count
	 * and path_walk() (called from ->follow_link) honoring LOOKUP_PARENT.
	 * After that we have the parent and last component, i.e.
	 * we are in the same situation as after the first path_walk().
	 * Well, almost - if the last component is normal we get its copy
	 * stored in nd->last.name and we will have to putname() it when we
	 * are done. Procfs-like symlinks just set LAST_BIND.
	 */
	nd->flags |= LOOKUP_PARENT;
	error = security_inode_follow_link(path.dentry, nd);
	if (error)
		goto exit_dput;
	error = __do_follow_link(&path, nd);
	if (error)
		return error;
	nd->flags &= ~LOOKUP_PARENT;
	if (nd->last_type == LAST_BIND)
		goto ok;
	error = -EISDIR;
	if (nd->last_type != LAST_NORM)
		goto exit;
	if (nd->last.name[nd->last.len]) {
		putname(nd->last.name);
		goto exit;
	}
	error = -ELOOP;
	if (count++==32) {
		putname(nd->last.name);
		goto exit;
	}
	dir = nd->dentry;
	down(&dir->d_inode->i_sem);
	path.dentry = __lookup_hash(&nd->last, nd->dentry, nd);
	path.mnt = nd->mnt;
	putname(nd->last.name);
	goto do_last;
}

/**
 * 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->dentry->d_inode->i_sem locked.
 */
struct dentry *lookup_create(struct nameidata *nd, int is_dir)
{
	struct dentry *dentry = ERR_PTR(-EEXIST);

	down(&nd->dentry->d_inode->i_sem);
	/*
	 * Yucky last component or no last component at all?
	 * (foo/., foo/.., /////)
	 */
	if (nd->last_type != LAST_NORM)
		goto fail;
	nd->flags &= ~LOOKUP_PARENT;

	/*
	 * Do the final lookup.
	 */
	dentry = lookup_hash(&nd->last, nd->dentry);
	if (IS_ERR(dentry))
		goto fail;

	/*
	 * 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 (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode)
		goto enoent;
	return dentry;
enoent:
	dput(dentry);
	dentry = ERR_PTR(-ENOENT);
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, NULL);

	if (error)
		return error;

	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
		return -EPERM;

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

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

	DQUOT_INIT(dir);
	error = dir->i_op->mknod(dir, dentry, mode, dev);
	if (!error) {
		inode_dir_notify(dir, DN_CREATE);
		security_inode_post_mknod(dir, dentry, mode, dev);
	}
	return error;
}

asmlinkage long sys_mknod(const char __user * filename, int mode, unsigned dev)
{
	int error = 0;
	char * tmp;
	struct dentry * dentry;
	struct nameidata nd;

	if (S_ISDIR(mode))
		return -EPERM;
	tmp = getname(filename);
	if (IS_ERR(tmp))
		return PTR_ERR(tmp);

	error = path_lookup(tmp, LOOKUP_PARENT, &nd);
	if (error)
		goto out;
	dentry = lookup_create(&nd, 0);
	error = PTR_ERR(dentry);

	if (!IS_POSIXACL(nd.dentry->d_inode))
		mode &= ~current->fs->umask;
	if (!IS_ERR(dentry)) {
		switch (mode & S_IFMT) {
		case 0: case S_IFREG:
			error = vfs_create(nd.dentry->d_inode,dentry,mode,&nd);
			break;
		case S_IFCHR: case S_IFBLK:
			error = vfs_mknod(nd.dentry->d_inode,dentry,mode,
					new_decode_dev(dev));
			break;
		case S_IFIFO: case S_IFSOCK:
			error = vfs_mknod(nd.dentry->d_inode,dentry,mode,0);
			break;
		case S_IFDIR:
			error = -EPERM;
			break;
		default:
			error = -EINVAL;
		}
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
	path_release(&nd);
out:
	putname(tmp);

	return error;
}

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

	if (error)
		return error;

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

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

	DQUOT_INIT(dir);
	error = dir->i_op->mkdir(dir, dentry, mode);
	if (!error) {
		inode_dir_notify(dir, DN_CREATE);
		security_inode_post_mkdir(dir,dentry, mode);
	}
	return error;
}

asmlinkage long sys_mkdir(const char __user * pathname, int mode)
{
	int error = 0;
	char * tmp;

	tmp = getname(pathname);
	error = PTR_ERR(tmp);
	if (!IS_ERR(tmp)) {
		struct dentry *dentry;
		struct nameidata nd;

		error = path_lookup(tmp, LOOKUP_PARENT, &nd);
		if (error)
			goto out;
		dentry = lookup_create(&nd, 1);
		error = PTR_ERR(dentry);
		if (!IS_ERR(dentry)) {
			if (!IS_POSIXACL(nd.dentry->d_inode))
				mode &= ~current->fs->umask;
			error = vfs_mkdir(nd.dentry->d_inode, dentry, mode);
			dput(dentry);
		}
		up(&nd.dentry->d_inode->i_sem);
		path_release(&nd);
out:
		putname(tmp);
	}

	return error;
}

/*
 * We 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)
{
	dget(dentry);
	if (atomic_read(&dentry->d_count))
		shrink_dcache_parent(dentry);
	spin_lock(&dcache_lock);
	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count) == 2)
		__d_drop(dentry);
	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_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 || !dir->i_op->rmdir)
		return -EPERM;

	DQUOT_INIT(dir);

	down(&dentry->d_inode->i_sem);
	dentry_unhash(dentry);
	if (d_mountpoint(dentry))
		error = -EBUSY;
	else {
		error = security_inode_rmdir(dir, dentry);
		if (!error) {
			error = dir->i_op->rmdir(dir, dentry);
			if (!error)
				dentry->d_inode->i_flags |= S_DEAD;
		}
	}
	up(&dentry->d_inode->i_sem);
	if (!error) {
		inode_dir_notify(dir, DN_DELETE);
		d_delete(dentry);
	}
	dput(dentry);

	return error;
}

asmlinkage long sys_rmdir(const char __user * pathname)
{
	int error = 0;
	char * name;
	struct dentry *dentry;
	struct nameidata nd;

	name = getname(pathname);
	if(IS_ERR(name))
		return PTR_ERR(name);

	error = path_lookup(name, LOOKUP_PARENT, &nd);
	if (error)
		goto exit;

	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;
	}
	down(&nd.dentry->d_inode->i_sem);
	dentry = lookup_hash(&nd.last, nd.dentry);
	error = PTR_ERR(dentry);
	if (!IS_ERR(dentry)) {
		error = vfs_rmdir(nd.dentry->d_inode, dentry);
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
exit1:
	path_release(&nd);
exit:
	putname(name);
	return error;
}

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

	if (error)
		return error;

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

	DQUOT_INIT(dir);

	down(&dentry->d_inode->i_sem);
	if (d_mountpoint(dentry))
		error = -EBUSY;
	else {
		error = security_inode_unlink(dir, dentry);
		if (!error)
			error = dir->i_op->unlink(dir, dentry);
	}
	up(&dentry->d_inode->i_sem);

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

/*
 * Make sure that the actual truncation of the file will occur outside its
 * directory's i_sem.  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.
 */
asmlinkage long sys_unlink(const char __user * pathname)
{
	int error = 0;
	char * name;
	struct dentry *dentry;
	struct nameidata nd;
	struct inode *inode = NULL;

	name = getname(pathname);
	if(IS_ERR(name))
		return PTR_ERR(name);

	error = path_lookup(name, LOOKUP_PARENT, &nd);
	if (error)
		goto exit;
	error = -EISDIR;
	if (nd.last_type != LAST_NORM)
		goto exit1;
	down(&nd.dentry->d_inode->i_sem);
	dentry = lookup_hash(&nd.last, nd.dentry);
	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)
			atomic_inc(&inode->i_count);
		error = vfs_unlink(nd.dentry->d_inode, dentry);
	exit2:
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
	if (inode)
		iput(inode);	/* truncate the inode here */
exit1:
	path_release(&nd);
exit:
	putname(name);
	return error;

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

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

	if (error)
		return error;

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

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

	DQUOT_INIT(dir);
	error = dir->i_op->symlink(dir, dentry, oldname);
	if (!error) {
		inode_dir_notify(dir, DN_CREATE);
		security_inode_post_symlink(dir, dentry, oldname);
	}
	return error;
}

asmlinkage long sys_symlink(const char __user * oldname, const char __user * newname)
{
	int error = 0;
	char * from;
	char * to;

	from = getname(oldname);
	if(IS_ERR(from))
		return PTR_ERR(from);
	to = getname(newname);
	error = PTR_ERR(to);
	if (!IS_ERR(to)) {
		struct dentry *dentry;
		struct nameidata nd;

		error = path_lookup(to, LOOKUP_PARENT, &nd);
		if (error)
			goto out;
		dentry = lookup_create(&nd, 0);
		error = PTR_ERR(dentry);
		if (!IS_ERR(dentry)) {
			error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO);
			dput(dentry);
		}
		up(&nd.dentry->d_inode->i_sem);
		path_release(&nd);
out:
		putname(to);
	}
	putname(from);
	return error;
}

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, NULL);
	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 || !dir->i_op->link)
		return -EPERM;
	if (S_ISDIR(old_dentry->d_inode->i_mode))
		return -EPERM;

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

	down(&old_dentry->d_inode->i_sem);
	DQUOT_INIT(dir);
	error = dir->i_op->link(old_dentry, dir, new_dentry);
	up(&old_dentry->d_inode->i_sem);
	if (!error) {
		inode_dir_notify(dir, DN_CREATE);
		security_inode_post_link(old_dentry, dir, 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
 */
asmlinkage long sys_link(const char __user * oldname, const char __user * newname)
{
	struct dentry *new_dentry;
	struct nameidata nd, old_nd;
	int error;
	char * to;

	to = getname(newname);
	if (IS_ERR(to))
		return PTR_ERR(to);

	error = __user_walk(oldname, 0, &old_nd);
	if (error)
		goto exit;
	error = path_lookup(to, LOOKUP_PARENT, &nd);
	if (error)
		goto out;
	error = -EXDEV;
	if (old_nd.mnt != nd.mnt)
		goto out_release;
	new_dentry = lookup_create(&nd, 0);
	error = PTR_ERR(new_dentry);
	if (!IS_ERR(new_dentry)) {
		error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry);
		dput(new_dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
out_release:
	path_release(&nd);
out:
	path_release(&old_nd);
exit:
	putname(to);

	return error;
}

/*
 * 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_sem. 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_sem 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_sem _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_sem.
 *	   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) some filesystems don't support opened-but-unlinked directories,
 *	   either because of layout or because they are not ready to deal with
 *	   all cases correctly. The latter will be fixed (taking this sort of
 *	   stuff into VFS), but the former is not going away. Solution: the same
 *	   trick as in rmdir().
 *	e) conversion from fhandle to dentry may come in the wrong moment - when
 *	   we are removing the target. Solution: we will have to grab ->i_sem
 *	   in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
 *	   ->i_sem on parents, which works but leads to some truely 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;

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

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

	target = new_dentry->d_inode;
	if (target) {
		down(&target->i_sem);
		dentry_unhash(new_dentry);
	}
	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
		error = -EBUSY;
	else 
		error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
	if (target) {
		if (!error)
			target->i_flags |= S_DEAD;
		up(&target->i_sem);
		if (d_unhashed(new_dentry))
			d_rehash(new_dentry);
		dput(new_dentry);
	}
	if (!error) {
		d_move(old_dentry,new_dentry);
		security_inode_post_rename(old_dir, old_dentry,
					   new_dir, 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;
	int error;

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

	dget(new_dentry);
	target = new_dentry->d_inode;
	if (target)
		down(&target->i_sem);
	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
		error = -EBUSY;
	else
		error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
	if (!error) {
		/* The following d_move() should become unconditional */
		if (!(old_dir->i_sb->s_type->fs_flags & FS_ODD_RENAME))
			d_move(old_dentry, new_dentry);
		security_inode_post_rename(old_dir, old_dentry, new_dir, new_dentry);
	}
	if (target)
		up(&target->i_sem);
	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);

	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, NULL);
	else
		error = may_delete(new_dir, new_dentry, is_dir);
	if (error)
		return error;

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

	DQUOT_INIT(old_dir);
	DQUOT_INIT(new_dir);

	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) {
		if (old_dir == new_dir)
			inode_dir_notify(old_dir, DN_RENAME);
		else {
			inode_dir_notify(old_dir, DN_DELETE);
			inode_dir_notify(new_dir, DN_CREATE);
		}
	}
	return error;
}

static inline int do_rename(const char * oldname, const char * newname)
{
	int error = 0;
	struct dentry * old_dir, * new_dir;
	struct dentry * old_dentry, *new_dentry;
	struct dentry * trap;
	struct nameidata oldnd, newnd;

	error = path_lookup(oldname, LOOKUP_PARENT, &oldnd);
	if (error)
		goto exit;

	error = path_lookup(newname, LOOKUP_PARENT, &newnd);
	if (error)
		goto exit1;

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

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

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

	trap = lock_rename(new_dir, old_dir);

	old_dentry = lookup_hash(&oldnd.last, old_dir);
	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.last, new_dir);
	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 = vfs_rename(old_dir->d_inode, old_dentry,
				   new_dir->d_inode, new_dentry);
exit5:
	dput(new_dentry);
exit4:
	dput(old_dentry);
exit3:
	unlock_rename(new_dir, old_dir);
exit2:
	path_release(&newnd);
exit1:
	path_release(&oldnd);
exit:
	return error;
}

asmlinkage long sys_rename(const char __user * oldname, const char __user * newname)
{
	int error;
	char * from;
	char * to;

	from = getname(oldname);
	if(IS_ERR(from))
		return PTR_ERR(from);
	to = getname(newname);
	error = PTR_ERR(to);
	if (!IS_ERR(to)) {
		error = do_rename(from,to);
		putname(to);
	}
	putname(from);
	return error;
}

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;
	int res;
	nd.depth = 0;
	res = dentry->d_inode->i_op->follow_link(dentry, &nd);
	if (!res) {
		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);
	}
	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)
{
	struct page * page;
	struct address_space *mapping = dentry->d_inode->i_mapping;
	page = read_cache_page(mapping, 0, (filler_t *)mapping->a_ops->readpage,
				NULL);
	if (IS_ERR(page))
		goto sync_fail;
	wait_on_page_locked(page);
	if (!PageUptodate(page))
		goto async_fail;
	*ppage = page;
	return kmap(page);

async_fail:
	page_cache_release(page);
	return ERR_PTR(-EIO);

sync_fail:
	return (char*)page;
}

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;
}

int page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
{
	struct page *page;
	nd_set_link(nd, page_getlink(dentry, &page));
	return 0;
}

void page_put_link(struct dentry *dentry, struct nameidata *nd)
{
	if (!IS_ERR(nd_get_link(nd))) {
		struct page *page;
		page = find_get_page(dentry->d_inode->i_mapping, 0);
		if (!page)
			BUG();
		kunmap(page);
		page_cache_release(page);
		page_cache_release(page);
	}
}

int page_symlink(struct inode *inode, const char *symname, int len)
{
	struct address_space *mapping = inode->i_mapping;
	struct page *page = grab_cache_page(mapping, 0);
	int err = -ENOMEM;
	char *kaddr;

	if (!page)
		goto fail;
	err = mapping->a_ops->prepare_write(NULL, page, 0, len-1);
	if (err)
		goto fail_map;
	kaddr = kmap_atomic(page, KM_USER0);
	memcpy(kaddr, symname, len-1);
	kunmap_atomic(kaddr, KM_USER0);
	mapping->a_ops->commit_write(NULL, page, 0, len-1);
	/*
	 * Notice that we are _not_ going to block here - end of page is
	 * unmapped, so this will only try to map the rest of page, see
	 * that it is unmapped (typically even will not look into inode -
	 * ->i_size will be enough for everything) and zero it out.
	 * OTOH it's obviously correct and should make the page up-to-date.
	 */
	if (!PageUptodate(page)) {
		err = mapping->a_ops->readpage(NULL, page);
		wait_on_page_locked(page);
	} else {
		unlock_page(page);
	}
	page_cache_release(page);
	if (err < 0)
		goto fail;
	mark_inode_dirty(inode);
	return 0;
fail_map:
	unlock_page(page);
	page_cache_release(page);
fail:
	return err;
}

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

EXPORT_SYMBOL(__user_walk);
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_hash);
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_inode_operations);
EXPORT_SYMBOL(path_lookup);
EXPORT_SYMBOL(path_release);
EXPORT_SYMBOL(path_walk);
EXPORT_SYMBOL(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);