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
|
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_itable.h"
#include "xfs_dfrag.h"
#include "xfs_error.h"
#include "xfs_vnodeops.h"
#include "xfs_trace.h"
static int xfs_swap_extents(
xfs_inode_t *ip, /* target inode */
xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp);
/*
* ioctl interface for swapext
*/
int
xfs_swapext(
xfs_swapext_t *sxp)
{
xfs_inode_t *ip, *tip;
struct file *file, *tmp_file;
int error = 0;
/* Pull information for the target fd */
file = fget((int)sxp->sx_fdtarget);
if (!file) {
error = XFS_ERROR(EINVAL);
goto out;
}
if (!(file->f_mode & FMODE_WRITE) ||
!(file->f_mode & FMODE_READ) ||
(file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
goto out_put_file;
}
tmp_file = fget((int)sxp->sx_fdtmp);
if (!tmp_file) {
error = XFS_ERROR(EINVAL);
goto out_put_file;
}
if (!(tmp_file->f_mode & FMODE_WRITE) ||
!(tmp_file->f_mode & FMODE_READ) ||
(tmp_file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
goto out_put_tmp_file;
}
if (IS_SWAPFILE(file->f_path.dentry->d_inode) ||
IS_SWAPFILE(tmp_file->f_path.dentry->d_inode)) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
ip = XFS_I(file->f_path.dentry->d_inode);
tip = XFS_I(tmp_file->f_path.dentry->d_inode);
if (ip->i_mount != tip->i_mount) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
if (ip->i_ino == tip->i_ino) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
error = XFS_ERROR(EIO);
goto out_put_tmp_file;
}
error = xfs_swap_extents(ip, tip, sxp);
out_put_tmp_file:
fput(tmp_file);
out_put_file:
fput(file);
out:
return error;
}
/*
* We need to check that the format of the data fork in the temporary inode is
* valid for the target inode before doing the swap. This is not a problem with
* attr1 because of the fixed fork offset, but attr2 has a dynamically sized
* data fork depending on the space the attribute fork is taking so we can get
* invalid formats on the target inode.
*
* E.g. target has space for 7 extents in extent format, temp inode only has
* space for 6. If we defragment down to 7 extents, then the tmp format is a
* btree, but when swapped it needs to be in extent format. Hence we can't just
* blindly swap data forks on attr2 filesystems.
*
* Note that we check the swap in both directions so that we don't end up with
* a corrupt temporary inode, either.
*
* Note that fixing the way xfs_fsr sets up the attribute fork in the source
* inode will prevent this situation from occurring, so all we do here is
* reject and log the attempt. basically we are putting the responsibility on
* userspace to get this right.
*/
static int
xfs_swap_extents_check_format(
xfs_inode_t *ip, /* target inode */
xfs_inode_t *tip) /* tmp inode */
{
/* Should never get a local format */
if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
return EINVAL;
/*
* if the target inode has less extents that then temporary inode then
* why did userspace call us?
*/
if (ip->i_d.di_nextents < tip->i_d.di_nextents)
return EINVAL;
/*
* if the target inode is in extent form and the temp inode is in btree
* form then we will end up with the target inode in the wrong format
* as we already know there are less extents in the temp inode.
*/
if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
return EINVAL;
/* Check temp in extent form to max in target */
if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
return EINVAL;
/* Check target in extent form to max in temp */
if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
return EINVAL;
/*
* If we are in a btree format, check that the temp root block will fit
* in the target and that it has enough extents to be in btree format
* in the target.
*
* Note that we have to be careful to allow btree->extent conversions
* (a common defrag case) which will occur when the temp inode is in
* extent format...
*/
if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
if (XFS_IFORK_BOFF(ip) &&
tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip))
return EINVAL;
if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
return EINVAL;
}
/* Reciprocal target->temp btree format checks */
if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
if (XFS_IFORK_BOFF(tip) &&
ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip))
return EINVAL;
if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
return EINVAL;
}
return 0;
}
static int
xfs_swap_extents(
xfs_inode_t *ip, /* target inode */
xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp = ip->i_mount;
xfs_trans_t *tp;
xfs_bstat_t *sbp = &sxp->sx_stat;
xfs_ifork_t *tempifp, *ifp, *tifp;
int ilf_fields, tilf_fields;
int error = 0;
int aforkblks = 0;
int taforkblks = 0;
__uint64_t tmp;
tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
if (!tempifp) {
error = XFS_ERROR(ENOMEM);
goto out;
}
/*
* we have to do two separate lock calls here to keep lockdep
* happy. If we try to get all the locks in one call, lock will
* report false positives when we drop the ILOCK and regain them
* below.
*/
xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/* Verify that both files have the same format */
if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify both files are either real-time or non-realtime */
if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
if (VN_CACHED(VFS_I(tip)) != 0) {
error = xfs_flushinval_pages(tip, 0, -1,
FI_REMAPF_LOCKED);
if (error)
goto out_unlock;
}
/* Verify O_DIRECT for ftmp */
if (VN_CACHED(VFS_I(tip)) != 0) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify all data are being swapped */
if (sxp->sx_offset != 0 ||
sxp->sx_length != ip->i_d.di_size ||
sxp->sx_length != tip->i_d.di_size) {
error = XFS_ERROR(EFAULT);
goto out_unlock;
}
trace_xfs_swap_extent_before(ip, 0);
trace_xfs_swap_extent_before(tip, 1);
/* check inode formats now that data is flushed */
error = xfs_swap_extents_check_format(ip, tip);
if (error) {
xfs_notice(mp,
"%s: inode 0x%llx format is incompatible for exchanging.",
__func__, ip->i_ino);
goto out_unlock;
}
/*
* Compare the current change & modify times with that
* passed in. If they differ, we abort this swap.
* This is the mechanism used to ensure the calling
* process that the file was not changed out from
* under it.
*/
if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
(
|