1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
|
/*
* Copyright (c) 2000-2005 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_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_inode.h"
#include "xfs_dinode.h"
#include "xfs_error.h"
#include "xfs_mru_cache.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_utils.h"
#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_rw.h"
#include <linux/kthread.h>
#include <linux/freezer.h>
/*
* Sync all the inodes in the given AG according to the
* direction given by the flags.
*/
STATIC int
xfs_sync_inodes_ag(
xfs_mount_t *mp,
int ag,
int flags)
{
xfs_perag_t *pag = &mp->m_perag[ag];
int nr_found;
int first_index = 0;
int error = 0;
int last_error = 0;
int fflag = XFS_B_ASYNC;
int lock_flags = XFS_ILOCK_SHARED;
if (flags & SYNC_DELWRI)
fflag = XFS_B_DELWRI;
if (flags & SYNC_WAIT)
fflag = 0; /* synchronous overrides all */
if (flags & SYNC_DELWRI) {
/*
* We need the I/O lock if we're going to call any of
* the flush/inval routines.
*/
lock_flags |= XFS_IOLOCK_SHARED;
}
do {
struct inode *inode;
boolean_t inode_refed;
xfs_inode_t *ip = NULL;
/*
* use a gang lookup to find the next inode in the tree
* as the tree is sparse and a gang lookup walks to find
* the number of objects requested.
*/
read_lock(&pag->pag_ici_lock);
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void**)&ip, first_index, 1);
if (!nr_found) {
read_unlock(&pag->pag_ici_lock);
break;
}
/* update the index for the next lookup */
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
/*
* skip inodes in reclaim. Let xfs_syncsub do that for
* us so we don't need to worry.
*/
if (xfs_iflags_test(ip, (XFS_IRECLAIM|XFS_IRECLAIMABLE))) {
read_unlock(&pag->pag_ici_lock);
continue;
}
/* bad inodes are dealt with elsewhere */
inode = VFS_I(ip);
if (is_bad_inode(inode)) {
read_unlock(&pag->pag_ici_lock);
continue;
}
/* nothing to sync during shutdown */
if (XFS_FORCED_SHUTDOWN(mp)) {
read_unlock(&pag->pag_ici_lock);
return 0;
}
/*
* If we can't get a reference on the VFS_I, the inode must be
* in reclaim. If we can get the inode lock without blocking,
* it is safe to flush the inode because we hold the tree lock
* and xfs_iextract will block right now. Hence if we lock the
* inode while holding the tree lock, xfs_ireclaim() is
* guaranteed to block on the inode lock we now hold and hence
* it is safe to reference the inode until we drop the inode
* locks completely.
*/
inode_refed = B_FALSE;
if (igrab(inode)) {
read_unlock(&pag->pag_ici_lock);
xfs_ilock(ip, lock_flags);
inode_refed = B_TRUE;
} else {
if (!xfs_ilock_nowait(ip, lock_flags)) {
/* leave it to reclaim */
read_unlock(&pag->pag_ici_lock);
continue;
}
read_unlock(&pag->pag_ici_lock);
}
/*
* If we have to flush data or wait for I/O completion
* we need to drop the ilock that we currently hold.
* If we need to drop the lock, insert a marker if we
* have not already done so.
*/
if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
if (flags & SYNC_IOWAIT)
vn_iowait(ip);
xfs_ilock(ip, XFS_ILOCK_SHARED);
}
if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
if (flags & SYNC_WAIT) {
xfs_iflock(ip);
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
else
xfs_ifunlock(ip);
} else if (xfs_iflock_nowait(ip)) {
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
else
xfs_ifunlock(ip);
}
}
if (lock_flags)
xfs_iunlock(ip, lock_flags);
if (inode_refed) {
IRELE(ip);
}
if (error)
last_error = error;
/*
* bail out if the filesystem is corrupted.
*/
if (error == EFSCORRUPTED)
return XFS_ERROR(error);
} while (nr_found);
return last_error;
}
int
xfs_sync_inodes(
xfs_mount_t *mp,
int flags)
{
int error;
int last_error;
int i;
int lflags = XFS_LOG_FORCE;
if (mp->m_flags & XFS_MOUNT_RDONLY)
return 0;
error = 0;
last_error = 0;
if (flags & SYNC_WAIT)
lflags |= XFS_LOG_SYNC;
for (i = 0; i < mp->m_sb.sb_agcount; i++) {
if (!mp->m_perag[i].pag_ici_init)
continue;
error = xfs_sync_inodes_ag(mp, i, flags);
if (error)
last_error = error;
if (error == EFSCORRUPTED)
break;
}
if (flags & SYNC_DELWRI)
xfs_log_force(mp, 0, lflags);
return XFS_ERROR(last_error);
}
STATIC int
xfs_commit_dummy_trans(
struct xfs_mount *mp,
uint log_flags)
{
struct xfs_inode *ip = mp->m_rootip;
struct xfs_trans *tp;
int error;
/*
* Put a dummy transaction in the log to tell recovery
* that all others are OK.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/* XXX(hch): ignoring the error here.. */
error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_log_force(mp, 0, log_flags);
return 0;
}
int
xfs_sync_fsdata(
struct xfs_mount *mp,
int flags)
{
struct xfs_buf *bp;
struct xfs_buf_log_item *bip;
int error = 0;
/*
* If this is xfssyncd() then only sync the superblock if we can
* lock it without sleeping and it is not pinned.
*/
if (flags & SYNC_BDFLUSH) {
ASSERT(!(flags & SYNC_WAIT));
bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
if (!bp)
goto out;
bip = XFS_BUF_FSPRIVATE(bp, struct xfs_buf_log_item *);
if (!bip || !xfs_buf_item_dirty(bip) || XFS_BUF_ISPINNED(bp))
goto out_brelse;
} else {
bp = xfs_getsb(mp, 0);
/*
* If the buffer is pinned then push on the log so we won't
* get stuck waiting in the write for someone, maybe
* ourselves, to flush the log.
*
* Even though we just pushed the log above, we did not have
* the superblock buffer locked at that point so it can
* become pinned in between there and here.
*/
if (XFS_BUF_ISPINNED(bp))
xfs_log_force(mp, 0, XFS_LOG_FORCE);
}
if (flags & SYNC_WAIT)
XFS_BUF_UNASYNC(bp);
else
XFS_BUF_ASYNC(bp);
return xfs_bwrite(mp, bp);
out_brelse:
xfs_buf_relse(bp);
out:
return error;
}
/*
* First stage of freeze - no more writers will make progress now we are here,
* so we flush delwri and delalloc buffers here, then wait for all I/O to
* complete. Data is frozen at that point. Metadata is not frozen,
* transactions can still occur here so don't bother flushing the buftarg (i.e
* SYNC_QUIESCE) because it'll just get dirty again.
*/
int
xfs_quiesce_data(
struct xfs_mount *mp)
{
int error;
/* push non-blocking */
xfs_sync_inodes(mp, SYNC_DELWRI|SYNC_BDFLUSH);
XFS_QM_DQSYNC(mp, SYNC_BDFLUSH);
xfs_filestream_flush(mp);
/* push and block */
xfs_sync_inodes(mp, SYNC_DELWRI|SYNC_WAIT|SYNC_IOWAIT);
XFS_QM_DQSYNC(mp, SYNC_WAIT);
/* write superblock and hoover shutdown errors */
error = xfs_sync_fsdata(mp, 0);
/* flush devices */
XFS_bflush(mp->m_ddev_targp);
if (mp->m_rtdev_targp)
XFS_bflush(mp->m_rtdev_targp);
return error;
}
/*
* xfs_sync flushes any pending I/O to file system vfsp.
*
* This routine is called by vfs_sync() to make sure that things make it
* out to disk eventually, on sync() system calls to flush out everything,
* and when the file system is unmounted. For the vfs_sync() case, all
* we really need to do is sync out the log to make all of our meta-data
* updates permanent (except for timestamps). For calls from pflushd(),
* dirty pages are kept moving by calling pdflush() on the inodes
* containing them. We also flush the inodes that we can lock without
* sleeping and the superblock if we can lock it without sleeping from
* vfs_sync() so that items at the tail of the log are always moving out.
*
* Flags:
* SYNC_BDFLUSH - We're being called from vfs_sync() so we don't want
* to sleep if we can help it. All we really need
* to do is ensure that the log is synced at least
* periodically. We also push the inodes and
* superblock if we can lock them without sleeping
* and they are not pinned.
* SYNC_ATTR - We need to flush the inodes. Now handled by direct calls
* to xfs_sync_inodes().
* SYNC_WAIT - All the flushes that take place in this call should
* be synchronous.
* SYNC_DELWRI - This tells us to push dirty pages associated with
* inodes. SYNC_WAIT and SYNC_BDFLUSH are used to
* determine if they should be flushed sync, async, or
* delwri.
* SYNC_FSDATA - This indicates that the caller would like to make
* sure the superblock is safe on disk. We can ensure
* this by simply making sure the log gets flushed
* if SYNC_BDFLUSH is set, and by actually writing it
* out otherwise.
* SYNC_IOWAIT - The caller wants us to wait for all data I/O to complete
* before we return (including direct I/O). Forms the drain
* side of the write barrier needed to safely quiesce the
* filesystem.
*
*/
int
xfs_sync(
xfs_mount_t *mp,
int flags)
{
int error;
int last_error = 0;
uint log_flags = XFS_LOG_FORCE;
ASSERT(!(flags & SYNC_ATTR));
/*
* Get the Quota Manager to flush the dquots.
*
* If XFS quota support is not enabled or this filesystem
* instance does not use quotas XFS_QM_DQSYNC will always
* return zero.
*/
error = XFS_QM_DQSYNC(mp, flags);
if (error) {
/*
* If we got an IO error, we will be shutting down.
* So, there's nothing more for us to do here.
*/
ASSERT(error != EIO || XFS_FORCED_SHUTDOWN(mp));
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(error);
}
if (flags & SYNC_IOWAIT)
xfs_filestream_flush(mp);
/*
* Sync out the log. This ensures that the log is periodically
* flushed even if there is not enough activity to fill it up.
*/
if (flags & SYNC_WAIT)
log_flags |= XFS_LOG_SYNC;
xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
if (flags & SYNC_DELWRI) {
if (flags & SYNC_BDFLUSH)
xfs_finish_reclaim_all(mp, 1, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
else
error = xfs_sync_inodes(mp, flags);
/*
* Flushing out dirty data above probably generated more
* log activity, so if this isn't vfs_sync() then flush
* the log again.
*/
xfs_log_force(mp, 0, log_flags);
}
if (flags & SYNC_FSDATA) {
error = xfs_sync_fsdata(mp, flags);
if (error)
last_error = error;
}
/*
* Now check to see if the log needs a "dummy" transaction.
*/
if (!(flags & SYNC_REMOUNT) && xfs_log_need_covered(mp)) {
error = xfs_commit_dummy_trans(mp, log_flags);
if (error)
return error;
}
return XFS_ERROR(last_error);
}
/*
* Enqueue a work item to be picked up by the vfs xfssyncd thread.
* Doing this has two advantages:
* - It saves on stack space, which is tight in certain situations
* - It can be used (with care) as a mechanism to avoid deadlocks.
* Flushing while allocating in a full filesystem requires both.
*/
STATIC void
xfs_syncd_queue_work(
struct xfs_mount *mp,
void *data,
void (*syncer)(struct xfs_mount *, void *))
{
struct bhv_vfs_sync_work *work;
work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
INIT_LIST_HEAD(&work->w_list);
work->w_syncer = syncer;
work->w_data = data;
work->w_mount = mp;
spin_lock(&mp->m_sync_lock);
list_add_tail(&work->w_list, &mp->m_sync_list);
spin_unlock(&mp->m_sync_lock);
wake_up_process(mp->m_sync_task);
}
/*
* Flush delayed allocate data, attempting to free up reserved space
* from existing allocations. At this point a new allocation attempt
* has failed with ENOSPC and we are in the process of scratching our
* heads, looking about for more room...
*/
STATIC void
xfs_flush_inode_work(
struct xfs_mount *mp,
void *arg)
{
struct inode *inode = arg;
filemap_flush(inode->i_mapping);
iput(inode);
}
void
xfs_flush_inode(
xfs_inode_t *ip)
{
struct inode *inode = VFS_I(ip);
igrab(inode);
xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
delay(msecs_to_jiffies(500));
}
/*
* This is the "bigger hammer" version of xfs_flush_inode_work...
* (IOW, "If at first you don't succeed, use a Bigger Hammer").
*/
STATIC void
xfs_flush_device_work(
struct xfs_mount *mp,
void *arg)
{
struct inode *inode = arg;
sync_blockdev(mp->m_super->s_bdev);
iput(inode);
}
void
xfs_flush_device(
xfs_inode_t *ip)
{
struct inode *inode = VFS_I(ip);
igrab(inode);
xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
delay(msecs_to_jiffies(500));
xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
}
/*
* Every sync period we need to unpin all items, reclaim inodes, sync
* quota and write out the superblock. We might need to cover the log
* to indicate it is idle.
*/
STATIC void
xfs_sync_worker(
struct xfs_mount *mp,
void *unused)
{
int error;
if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
xfs_finish_reclaim_all(mp, 1, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
/* dgc: errors ignored here */
error = XFS_QM_DQSYNC(mp, SYNC_BDFLUSH);
error = xfs_sync_fsdata(mp, SYNC_BDFLUSH);
if (xfs_log_need_covered(mp))
error = xfs_commit_dummy_trans(mp, XFS_LOG_FORCE);
}
mp->m_sync_seq++;
wake_up(&mp->m_wait_single_sync_task);
}
STATIC int
xfssyncd(
void *arg)
{
struct xfs_mount *mp = arg;
long timeleft;
bhv_vfs_sync_work_t *work, *n;
LIST_HEAD (tmp);
set_freezable();
timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
for (;;) {
timeleft = schedule_timeout_interruptible(timeleft);
/* swsusp */
try_to_freeze();
if (kthread_should_stop() && list_empty(&mp->m_sync_list))
break;
spin_lock(&mp->m_sync_lock);
/*
* We can get woken by laptop mode, to do a sync -
* that's the (only!) case where the list would be
* empty with time remaining.
*/
if (!timeleft || list_empty(&mp->m_sync_list)) {
if (!timeleft)
timeleft = xfs_syncd_centisecs *
msecs_to_jiffies(10);
INIT_LIST_HEAD(&mp->m_sync_work.w_list);
list_add_tail(&mp->m_sync_work.w_list,
&mp->m_sync_list);
}
list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
list_move(&work->w_list, &tmp);
spin_unlock(&mp->m_sync_lock);
list_for_each_entry_safe(work, n, &tmp, w_list) {
(*work->w_syncer)(mp, work->w_data);
list_del(&work->w_list);
if (work == &mp->m_sync_work)
continue;
kmem_free(work);
}
}
return 0;
}
int
xfs_syncd_init(
struct xfs_mount *mp)
{
mp->m_sync_work.w_syncer = xfs_sync_worker;
mp->m_sync_work.w_mount = mp;
mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
if (IS_ERR(mp->m_sync_task))
return -PTR_ERR(mp->m_sync_task);
return 0;
}
void
xfs_syncd_stop(
struct xfs_mount *mp)
{
kthread_stop(mp->m_sync_task);
}
|