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
|
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (C) 2011 Lawrence Livermore National Security, LLC.
*/
#ifndef _ZFS_VFS_H
#define _ZFS_VFS_H
#include <sys/taskq.h>
/*
* 2.6.28 API change,
* Added insert_inode_locked() helper function, prior to this most callers
* used insert_inode_hash(). The older method doesn't check for collisions
* in the inode_hashtable but it still acceptible for use.
*/
#ifndef HAVE_INSERT_INODE_LOCKED
static inline int
insert_inode_locked(struct inode *ip)
{
insert_inode_hash(ip);
return (0);
}
#endif /* HAVE_INSERT_INODE_LOCKED */
/*
* 2.6.35 API change,
* Add truncate_setsize() if it is not exported by the Linux kernel.
*
* Truncate the inode and pages associated with the inode. The pages are
* unmapped and removed from cache.
*/
#ifndef HAVE_TRUNCATE_SETSIZE
static inline void
truncate_setsize(struct inode *ip, loff_t new)
{
struct address_space *mapping = ip->i_mapping;
i_size_write(ip, new);
unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(mapping, new);
unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
}
#endif /* HAVE_TRUNCATE_SETSIZE */
#if defined(HAVE_BDI) && !defined(HAVE_BDI_SETUP_AND_REGISTER)
/*
* 2.6.34 API change,
* Add bdi_setup_and_register() function if not yet provided by kernel.
* It is used to quickly initialize and register a BDI for the filesystem.
*/
extern atomic_long_t zfs_bdi_seq;
static inline int
bdi_setup_and_register(
struct backing_dev_info *bdi,
char *name,
unsigned int cap)
{
char tmp[32];
int error;
bdi->name = name;
bdi->capabilities = cap;
error = bdi_init(bdi);
if (error)
return (error);
sprintf(tmp, "%.28s%s", name, "-%d");
error = bdi_register(bdi, NULL, tmp,
atomic_long_inc_return(&zfs_bdi_seq));
if (error) {
bdi_destroy(bdi);
return (error);
}
return (error);
}
#endif /* HAVE_BDI && !HAVE_BDI_SETUP_AND_REGISTER */
/*
* 2.6.38 API change,
* LOOKUP_RCU flag introduced to distinguish rcu-walk from ref-walk cases.
*/
#ifndef LOOKUP_RCU
#define LOOKUP_RCU 0x0
#endif /* LOOKUP_RCU */
/*
* 3.2-rc1 API change,
* Add set_nlink() if it is not exported by the Linux kernel.
*
* i_nlink is read-only in Linux 3.2, but it can be set directly in
* earlier kernels.
*/
#ifndef HAVE_SET_NLINK
static inline void
set_nlink(struct inode *inode, unsigned int nlink)
{
inode->i_nlink = nlink;
}
#endif /* HAVE_SET_NLINK */
/*
* 3.3 API change,
* The VFS .create, .mkdir and .mknod callbacks were updated to take a
* umode_t type rather than an int. To cleanly handle both definitions
* the zpl_umode_t type is introduced and set accordingly.
*/
#ifdef HAVE_MKDIR_UMODE_T
typedef umode_t zpl_umode_t;
#else
typedef int zpl_umode_t;
#endif
/*
* 3.5 API change,
* The clear_inode() function replaces end_writeback() and introduces an
* ordering change regarding when the inode_sync_wait() occurs. See the
* configure check in config/kernel-clear-inode.m4 for full details.
*/
#if defined(HAVE_EVICT_INODE) && !defined(HAVE_CLEAR_INODE)
#define clear_inode(ip) end_writeback(ip)
#endif /* HAVE_EVICT_INODE && !HAVE_CLEAR_INODE */
/*
* 3.6 API change,
* The sget() helper function now takes the mount flags as an argument.
*/
#ifdef HAVE_5ARG_SGET
#define zpl_sget(type, cmp, set, fl, mtd) sget(type, cmp, set, fl, mtd)
#else
#define zpl_sget(type, cmp, set, fl, mtd) sget(type, cmp, set, mtd)
#endif /* HAVE_5ARG_SGET */
#if defined(SEEK_HOLE) && defined(SEEK_DATA) && !defined(HAVE_LSEEK_EXECUTE)
static inline loff_t
lseek_execute(
struct file *filp,
struct inode *inode,
loff_t offset,
loff_t maxsize)
{
if (offset < 0 && !(filp->f_mode & FMODE_UNSIGNED_OFFSET))
return (-EINVAL);
if (offset > maxsize)
return (-EINVAL);
if (offset != filp->f_pos) {
spin_lock(&filp->f_lock);
filp->f_pos = offset;
filp->f_version = 0;
spin_unlock(&filp->f_lock);
}
return (offset);
}
#endif /* SEEK_HOLE && SEEK_DATA && !HAVE_LSEEK_EXECUTE */
#if defined(CONFIG_FS_POSIX_ACL)
/*
* These functions safely approximates the behavior of posix_acl_release()
* which cannot be used because it calls the GPL-only symbol kfree_rcu().
* The in-kernel version, which can access the RCU, frees the ACLs after
* the grace period expires. Because we're unsure how long that grace
* period may be this implementation conservatively delays for 60 seconds.
* This is several orders of magnitude larger than expected grace period.
* At 60 seconds the kernel will also begin issuing RCU stall warnings.
*/
#include <linux/posix_acl.h>
#ifndef HAVE_POSIX_ACL_CACHING
#define ACL_NOT_CACHED ((void *)(-1))
#endif /* HAVE_POSIX_ACL_CACHING */
#if defined(HAVE_POSIX_ACL_RELEASE) && !defined(HAVE_POSIX_ACL_RELEASE_GPL_ONLY)
#define zpl_posix_acl_release(arg) posix_acl_release(arg)
#define zpl_set_cached_acl(ip, ty, n) set_cached_acl(ip, ty, n)
#define zpl_forget_cached_acl(ip, ty) forget_cached_acl(ip, ty)
#else
static inline void
zpl_posix_acl_free(void *arg) {
kfree(arg);
}
static inline void
zpl_posix_acl_release(struct posix_acl *acl)
{
if ((acl == NULL) || (acl == ACL_NOT_CACHED))
return;
if (atomic_dec_and_test(&acl->a_refcount)) {
taskq_dispatch_delay(system_taskq, zpl_posix_acl_free, acl,
TQ_SLEEP, ddi_get_lbolt() + 60*HZ);
}
}
static inline void
zpl_set_cached_acl(struct inode *ip, int type, struct posix_acl *newer) {
#ifdef HAVE_POSIX_ACL_CACHING
struct posix_acl *older = NULL;
spin_lock(&ip->i_lock);
if ((newer != ACL_NOT_CACHED) && (newer != NULL))
posix_acl_dup(newer);
switch (type) {
case ACL_TYPE_ACCESS:
older = ip->i_acl;
rcu_assign_pointer(ip->i_acl, newer);
break;
case ACL_TYPE_DEFAULT:
older = ip->i_default_acl;
rcu_assign_pointer(ip->i_default_acl, newer);
break;
}
spin_unlock(&ip->i_lock);
zpl_posix_acl_release(older);
#endif /* HAVE_POSIX_ACL_CACHING */
}
static inline void
zpl_forget_cached_acl(struct inode *ip, int type) {
zpl_set_cached_acl(ip, type, (struct posix_acl *)ACL_NOT_CACHED);
}
#endif /* HAVE_POSIX_ACL_RELEASE */
#ifndef HAVE___POSIX_ACL_CHMOD
#ifdef HAVE_POSIX_ACL_CHMOD
#define __posix_acl_chmod(acl, gfp, mode) posix_acl_chmod(acl, gfp, mode)
#define __posix_acl_create(acl, gfp, mode) posix_acl_create(acl, gfp, mode)
#else
static inline int
__posix_acl_chmod(struct posix_acl **acl, int flags, umode_t umode) {
struct posix_acl *oldacl = *acl;
mode_t mode = umode;
int error;
*acl = posix_acl_clone(*acl, flags);
zpl_posix_acl_release(oldacl);
if (!(*acl))
return (-ENOMEM);
error = posix_acl_chmod_masq(*acl, mode);
if (error) {
zpl_posix_acl_release(*acl);
*acl = NULL;
}
return (error);
}
static inline int
__posix_acl_create(struct posix_acl **acl, int flags, umode_t *umodep) {
struct posix_acl *oldacl = *acl;
mode_t mode = *umodep;
int error;
*acl = posix_acl_clone(*acl, flags);
zpl_posix_acl_release(oldacl);
if (!(*acl))
return (-ENOMEM);
error = posix_acl_create_masq(*acl, &mode);
*umodep = mode;
if (error < 0) {
zpl_posix_acl_release(*acl);
*acl = NULL;
}
return (error);
}
#endif /* HAVE_POSIX_ACL_CHMOD */
#endif /* HAVE___POSIX_ACL_CHMOD */
#ifdef HAVE_POSIX_ACL_EQUIV_MODE_UMODE_T
typedef umode_t zpl_equivmode_t;
#else
typedef mode_t zpl_equivmode_t;
#endif /* HAVE_POSIX_ACL_EQUIV_MODE_UMODE_T */
#endif /* CONFIG_FS_POSIX_ACL */
#ifndef HAVE_CURRENT_UMASK
static inline int
current_umask(void)
{
return (current->fs->umask);
}
#endif /* HAVE_CURRENT_UMASK */
/*
* 2.6.38 API change,
* The is_owner_or_cap() function was renamed to inode_owner_or_capable().
*/
#ifdef HAVE_INODE_OWNER_OR_CAPABLE
#define zpl_inode_owner_or_capable(ip) inode_owner_or_capable(ip)
#else
#define zpl_inode_owner_or_capable(ip) is_owner_or_cap(ip)
#endif /* HAVE_INODE_OWNER_OR_CAPABLE */
#endif /* _ZFS_VFS_H */
|