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
|
/*
* (C) 2001 Clemson University and The University of Chicago
*
* See COPYING in top-level directory.
*/
/*
* Linux VFS namei operations.
*/
#include "protocol.h"
#include "orangefs-kernel.h"
/*
* Get a newly allocated inode to go with a negative dentry.
*/
static int orangefs_create(struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool exclusive)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
int ret;
gossip_debug(GOSSIP_NAME_DEBUG, "%s: %s\n",
__func__,
dentry->d_name.name);
new_op = op_alloc(ORANGEFS_VFS_OP_CREATE);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.create.parent_refn = parent->refn;
fill_default_sys_attrs(new_op->upcall.req.create.attributes,
ORANGEFS_TYPE_METAFILE, mode);
strncpy(new_op->upcall.req.create.d_name,
dentry->d_name.name, ORANGEFS_NAME_MAX);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: %s: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
__func__,
dentry->d_name.name,
&new_op->downcall.resp.create.refn.khandle,
new_op->downcall.resp.create.refn.fs_id,
new_op,
ret);
if (ret < 0)
goto out;
inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0,
&new_op->downcall.resp.create.refn);
if (IS_ERR(inode)) {
gossip_err("%s: Failed to allocate inode for file :%s:\n",
__func__,
dentry->d_name.name);
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: Assigned inode :%pU: for file :%s:\n",
__func__,
get_khandle_from_ino(inode),
dentry->d_name.name);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: dentry instantiated for %s\n",
__func__,
dentry->d_name.name);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_time(dir);
mark_inode_dirty_sync(dir);
ret = 0;
out:
op_release(new_op);
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: %s: returning %d\n",
__func__,
dentry->d_name.name,
ret);
return ret;
}
/*
* Attempt to resolve an object name (dentry->d_name), parent handle, and
* fsid into a handle for the object.
*/
static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
struct dentry *res;
int ret = -EINVAL;
/*
* in theory we could skip a lookup here (if the intent is to
* create) in order to avoid a potentially failed lookup, but
* leaving it in can skip a valid lookup and try to create a file
* that already exists (e.g. the vfs already handles checking for
* -EEXIST on O_EXCL opens, which is broken if we skip this lookup
* in the create path)
*/
gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %s\n",
__func__, dentry->d_name.name);
if (dentry->d_name.len > (ORANGEFS_NAME_MAX - 1))
return ERR_PTR(-ENAMETOOLONG);
new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
if (!new_op)
return ERR_PTR(-ENOMEM);
new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
gossip_debug(GOSSIP_NAME_DEBUG, "%s:%s:%d using parent %pU\n",
__FILE__,
__func__,
__LINE__,
&parent->refn.khandle);
new_op->upcall.req.lookup.parent_refn = parent->refn;
strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name,
ORANGEFS_NAME_MAX);
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: doing lookup on %s under %pU,%d\n",
__func__,
new_op->upcall.req.lookup.d_name,
&new_op->upcall.req.lookup.parent_refn.khandle,
new_op->upcall.req.lookup.parent_refn.fs_id);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"Lookup Got %pU, fsid %d (ret=%d)\n",
&new_op->downcall.resp.lookup.refn.khandle,
new_op->downcall.resp.lookup.refn.fs_id,
ret);
if (ret < 0) {
if (ret == -ENOENT) {
/*
* if no inode was found, add a negative dentry to
* dcache anyway; if we don't, we don't hold expected
* lookup semantics and we most noticeably break
* during directory renames.
*
* however, if the operation failed or exited, do not
* add the dentry (e.g. in the case that a touch is
* issued on a file that already exists that was
* interrupted during this lookup -- no need to add
* another negative dentry for an existing file)
*/
gossip_debug(GOSSIP_NAME_DEBUG,
"orangefs_lookup: Adding *negative* dentry "
"%p for %s\n",
dentry,
dentry->d_name.name);
d_add(dentry, NULL);
res = NULL;
goto out;
}
/* must be a non-recoverable error */
res = ERR_PTR(ret);
goto out;
}
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
if (IS_ERR(inode)) {
gossip_debug(GOSSIP_NAME_DEBUG,
"error %ld from iget\n", PTR_ERR(inode));
res = ERR_CAST(inode);
goto out;
}
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"%s:%s:%d "
"Found good inode [%lu] with count [%d]\n",
__FILE__,
__func__,
__LINE__,
inode->i_ino,
(int)atomic_read(&inode->i_count));
/* update dentry/inode pair into dcache */
res = d_splice_alias(inode, dentry);
gossip_debug(GOSSIP_NAME_DEBUG,
"Lookup success (inode ct = %d)\n",
(int)atomic_read(&inode->i_count));
out:
op_release(new_op);
return res;
}
/* return 0 on success; non-zero otherwise */
static int orangefs_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
int ret;
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: called on %s\n"
" (inode %pU): Parent is %pU | fs_id %d\n",
__func__,
dentry->d_name.name,
get_khandle_from_ino(inode),
&parent->refn.khandle,
parent->refn.fs_id);
new_op = op_alloc(ORANGEFS_VFS_OP_REMOVE);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.remove.parent_refn = parent->refn;
strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name,
ORANGEFS_NAME_MAX);
ret = service_operation(new_op, "orangefs_unlink",
get_interruptible_flag(inode));
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: service_operation returned:%d:\n",
__func__,
ret);
op_release(new_op);
if (!ret) {
drop_nlink(inode);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_time(dir);
mark_inode_dirty_sync(dir);
}
return ret;
}
static int orangefs_symlink(struct inode *dir,
struct dentry *dentry,
const char *symname)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
int mode = 755;
int ret;
gossip_debug(GOSSIP_NAME_DEBUG, "%s: called\n", __func__);
if (!symname)
return -EINVAL;
if (strlen(symname)+1 > ORANGEFS_NAME_MAX)
return -ENAMETOOLONG;
new_op = op_alloc(ORANGEFS_VFS_OP_SYMLINK);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.sym.parent_refn = parent->refn;
fill_default_sys_attrs(new_op->upcall.req.sym.attributes,
ORANGEFS_TYPE_SYMLINK,
mode);
strncpy(new_op->upcall.req.sym.entry_name,
dentry->d_name.name,
ORANGEFS_NAME_MAX);
strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"Symlink Got ORANGEFS handle %pU on fsid %d (ret=%d)\n",
&new_op->downcall.resp.sym.refn.khandle,
new_op->downcall.resp.sym.refn.fs_id, ret);
if (ret < 0) {
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: failed with error code %d\n",
__func__, ret);
goto out;
}
inode = orangefs_new_inode(dir->i_sb, dir, S_IFLNK | mode, 0,
&new_op->downcall.resp.sym.refn);
if (IS_ERR(inode)) {
gossip_err
("*** Failed to allocate orangefs symlink inode\n");
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
"Assigned symlink inode new number of %pU\n",
get_khandle_from_ino(inode));
d_instantiate(dentry, inode);
unlock_new_inode(inode);
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"Inode (Symlink) %pU -> %s\n",
get_khandle_from_ino(inode),
dentry->d_name.name);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_time(dir);
mark_inode_dirty_sync(dir);
ret = 0;
out:
op_release(new_op);
return ret;
}
static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
int ret;
new_op = op_alloc(ORANGEFS_VFS_OP_MKDIR);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.mkdir.parent_refn = parent->refn;
fill_default_sys_attrs(new_op->upcall.req.mkdir.attributes,
ORANGEFS_TYPE_DIRECTORY, mode);
strncpy(new_op->upcall.req.mkdir.d_name,
dentry->d_name.name, ORANGEFS_NAME_MAX);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"Mkdir Got ORANGEFS handle %pU on fsid %d\n",
&new_op->downcall.resp.mkdir.refn.khandle,
new_op->downcall.resp.mkdir.refn.fs_id);
if (ret < 0) {
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: failed with error code %d\n",
__func__, ret);
goto out;
}
inode = orangefs_new_inode(dir->i_sb, dir, S_IFDIR | mode, 0,
&new_op->downcall.resp.mkdir.refn);
if (IS_ERR(inode)) {
gossip_err("*** Failed to allocate orangefs dir inode\n");
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
"Assigned dir inode new number of %pU\n",
get_khandle_from_ino(inode));
d_instantiate(dentry, inode);
unlock_new_inode(inode);
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"Inode (Directory) %pU -> %s\n",
get_khandle_from_ino(inode),
dentry->d_name.name);
/*
* NOTE: we have no good way to keep nlink consistent for directories
* across clients; keep constant at 1.
*/
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_time(dir);
mark_inode_dirty_sync(dir);
out:
op_release(new_op);
return ret;
}
static int orangefs_rename(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry,
unsigned int flags)
{
struct orangefs_kernel_op_s *new_op;
int ret;
if (flags)
return -EINVAL;
gossip_debug(GOSSIP_NAME_DEBUG,
"orangefs_rename: called (%pd2 => %pd2) ct=%d\n",
old_dentry, new_dentry, d_count(new_dentry));
ORANGEFS_I(new_dentry->d_parent->d_inode)->getattr_time = jiffies - 1;
new_op = op_alloc(ORANGEFS_VFS_OP_RENAME);
if (!new_op)
return -EINVAL;
new_op->upcall.req.rename.old_parent_refn = ORANGEFS_I(old_dir)->refn;
new_op->upcall.req.rename.new_parent_refn = ORANGEFS_I(new_dir)->refn;
strncpy(new_op->upcall.req.rename.d_old_name,
old_dentry->d_name.name,
ORANGEFS_NAME_MAX);
strncpy(new_op->upcall.req.rename.d_new_name,
new_dentry->d_name.name,
ORANGEFS_NAME_MAX);
ret = service_operation(new_op,
"orangefs_rename",
get_interruptible_flag(old_dentry->d_inode));
gossip_debug(GOSSIP_NAME_DEBUG,
"orangefs_rename: got downcall status %d\n",
ret);
if (new_dentry->d_inode)
new_dentry->d_inode->i_ctime = current_time(new_dentry->d_inode);
op_release(new_op);
return ret;
}
/* ORANGEFS implementation of VFS inode operations for directories */
const struct inode_operations orangefs_dir_inode_operations = {
.lookup = orangefs_lookup,
.get_acl = orangefs_get_acl,
.set_acl = orangefs_set_acl,
.create = orangefs_create,
.unlink = orangefs_unlink,
.symlink = orangefs_symlink,
.mkdir = orangefs_mkdir,
.rmdir = orangefs_unlink,
.rename = orangefs_rename,
.setattr = orangefs_setattr,
.getattr = orangefs_getattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = orangefs_listxattr,
.permission = orangefs_permission,
};
|