summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_refcount_item.c
blob: e5866b714d5f3803587dbf0aab317b2804b7257b (plain)
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
/*
 * Copyright (C) 2016 Oracle.  All Rights Reserved.
 *
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 *
 * 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; either version 2
 * of the License, or (at your option) any later version.
 *
 * 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_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_shared.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_buf_item.h"
#include "xfs_refcount_item.h"
#include "xfs_log.h"
#include "xfs_refcount.h"


kmem_zone_t	*xfs_cui_zone;
kmem_zone_t	*xfs_cud_zone;

static inline struct xfs_cui_log_item *CUI_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_cui_log_item, cui_item);
}

void
xfs_cui_item_free(
	struct xfs_cui_log_item	*cuip)
{
	if (cuip->cui_format.cui_nextents > XFS_CUI_MAX_FAST_EXTENTS)
		kmem_free(cuip);
	else
		kmem_zone_free(xfs_cui_zone, cuip);
}

/*
 * Freeing the CUI requires that we remove it from the AIL if it has already
 * been placed there. However, the CUI may not yet have been placed in the AIL
 * when called by xfs_cui_release() from CUD processing due to the ordering of
 * committed vs unpin operations in bulk insert operations. Hence the reference
 * count to ensure only the last caller frees the CUI.
 */
void
xfs_cui_release(
	struct xfs_cui_log_item	*cuip)
{
	ASSERT(atomic_read(&cuip->cui_refcount) > 0);
	if (atomic_dec_and_test(&cuip->cui_refcount)) {
		xfs_trans_ail_remove(&cuip->cui_item, SHUTDOWN_LOG_IO_ERROR);
		xfs_cui_item_free(cuip);
	}
}


STATIC void
xfs_cui_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_cui_log_item	*cuip = CUI_ITEM(lip);

	*nvecs += 1;
	*nbytes += xfs_cui_log_format_sizeof(cuip->cui_format.cui_nextents);
}

/*
 * This is called to fill in the vector of log iovecs for the
 * given cui log item. We use only 1 iovec, and we point that
 * at the cui_log_format structure embedded in the cui item.
 * It is at this point that we assert that all of the extent
 * slots in the cui item have been filled.
 */
STATIC void
xfs_cui_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_vec	*lv)
{
	struct xfs_cui_log_item	*cuip = CUI_ITEM(lip);
	struct xfs_log_iovec	*vecp = NULL;

	ASSERT(atomic_read(&cuip->cui_next_extent) ==
			cuip->cui_format.cui_nextents);

	cuip->cui_format.cui_type = XFS_LI_CUI;
	cuip->cui_format.cui_size = 1;

	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUI_FORMAT, &cuip->cui_format,
			xfs_cui_log_format_sizeof(cuip->cui_format.cui_nextents));
}

/*
 * Pinning has no meaning for an cui item, so just return.
 */
STATIC void
xfs_cui_item_pin(
	struct xfs_log_item	*lip)
{
}

/*
 * The unpin operation is the last place an CUI is manipulated in the log. It is
 * either inserted in the AIL or aborted in the event of a log I/O error. In
 * either case, the CUI transaction has been successfully committed to make it
 * this far. Therefore, we expect whoever committed the CUI to either construct
 * and commit the CUD or drop the CUD's reference in the event of error. Simply
 * drop the log's CUI reference now that the log is done with it.
 */
STATIC void
xfs_cui_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{
	struct xfs_cui_log_item	*cuip = CUI_ITEM(lip);

	xfs_cui_release(cuip);
}

/*
 * CUI items have no locking or pushing.  However, since CUIs are pulled from
 * the AIL when their corresponding CUDs are committed to disk, their situation
 * is very similar to being pinned.  Return XFS_ITEM_PINNED so that the caller
 * will eventually flush the log.  This should help in getting the CUI out of
 * the AIL.
 */
STATIC uint
xfs_cui_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
{
	return XFS_ITEM_PINNED;
}

/*
 * The CUI has been either committed or aborted if the transaction has been
 * cancelled. If the transaction was cancelled, an CUD isn't going to be
 * constructed and thus we free the CUI here directly.
 */
STATIC void
xfs_cui_item_unlock(
	struct xfs_log_item	*lip)
{
	if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
		xfs_cui_release(CUI_ITEM(lip));
}

/*
 * The CUI is logged only once and cannot be moved in the log, so simply return
 * the lsn at which it's been logged.
 */
STATIC xfs_lsn_t
xfs_cui_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	return lsn;
}

/*
 * The CUI dependency tracking op doesn't do squat.  It can't because
 * it doesn't know where the free extent is coming from.  The dependency
 * tracking has to be handled by the "enclosing" metadata object.  For
 * example, for inodes, the inode is locked throughout the extent freeing
 * so the dependency should be recorded there.
 */
STATIC void
xfs_cui_item_committing(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
}

/*
 * This is the ops vector shared by all cui log items.
 */
static const struct xfs_item_ops xfs_cui_item_ops = {
	.iop_size	= xfs_cui_item_size,
	.iop_format	= xfs_cui_item_format,
	.iop_pin	= xfs_cui_item_pin,
	.iop_unpin	= xfs_cui_item_unpin,
	.iop_unlock	= xfs_cui_item_unlock,
	.iop_committed	= xfs_cui_item_committed,
	.iop_push	= xfs_cui_item_push,
	.iop_committing = xfs_cui_item_committing,
};

/*
 * Allocate and initialize an cui item with the given number of extents.
 */
struct xfs_cui_log_item *
xfs_cui_init(
	struct xfs_mount		*mp,
	uint				nextents)

{
	struct xfs_cui_log_item		*cuip;

	ASSERT(nextents > 0);
	if (nextents > XFS_CUI_MAX_FAST_EXTENTS)
		cuip = kmem_zalloc(xfs_cui_log_item_sizeof(nextents),
				KM_SLEEP);
	else
		cuip = kmem_zone_zalloc(xfs_cui_zone, KM_SLEEP);

	xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops);
	cuip->cui_format.cui_nextents = nextents;
	cuip->cui_format.cui_id = (uintptr_t)(void *)cuip;
	atomic_set(&cuip->cui_next_extent, 0);
	atomic_set(&cuip->cui_refcount, 2);

	return cuip;
}

static inline struct xfs_cud_log_item *CUD_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_cud_log_item, cud_item);
}

STATIC void
xfs_cud_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	*nvecs += 1;
	*nbytes += sizeof(struct xfs_cud_log_format);
}

/*
 * This is called to fill in the vector of log iovecs for the
 * given cud log item. We use only 1 iovec, and we point that
 * at the cud_log_format structure embedded in the cud item.
 * It is at this point that we assert that all of the extent
 * slots in the cud item have been filled.
 */
STATIC void
xfs_cud_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_vec	*lv)
{
	struct xfs_cud_log_item	*cudp = CUD_ITEM(lip);
	struct xfs_log_iovec	*vecp = NULL;

	cudp->cud_format.cud_type = XFS_LI_CUD;
	cudp->cud_format.cud_size = 1;

	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUD_FORMAT, &cudp->cud_format,
			sizeof(struct xfs_cud_log_format));
}

/*
 * Pinning has no meaning for an cud item, so just return.
 */
STATIC void
xfs_cud_item_pin(
	struct xfs_log_item	*lip)
{
}

/*
 * Since pinning has no meaning for an cud item, unpinning does
 * not either.
 */
STATIC void
xfs_cud_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{
}

/*
 * There isn't much you can do to push on an cud item.  It is simply stuck
 * waiting for the log to be flushed to disk.
 */
STATIC uint
xfs_cud_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
{
	return XFS_ITEM_PINNED;
}

/*
 * The CUD is either committed or aborted if the transaction is cancelled. If
 * the transaction is cancelled, drop our reference to the CUI and free the
 * CUD.
 */
STATIC void
xfs_cud_item_unlock(
	struct xfs_log_item	*lip)
{
	struct xfs_cud_log_item	*cudp = CUD_ITEM(lip);

	if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
		xfs_cui_release(cudp->cud_cuip);
		kmem_zone_free(xfs_cud_zone, cudp);
	}
}

/*
 * When the cud item is committed to disk, all we need to do is delete our
 * reference to our partner cui item and then free ourselves. Since we're
 * freeing ourselves we must return -1 to keep the transaction code from
 * further referencing this item.
 */
STATIC xfs_lsn_t
xfs_cud_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	struct xfs_cud_log_item	*cudp = CUD_ITEM(lip);

	/*
	 * Drop the CUI reference regardless of whether the CUD has been
	 * aborted. Once the CUD transaction is constructed, it is the sole
	 * responsibility of the CUD to release the CUI (even if the CUI is
	 * aborted due to log I/O error).
	 */
	xfs_cui_release(cudp->cud_cuip);
	kmem_zone_free(xfs_cud_zone, cudp);

	return (xfs_lsn_t)-1;
}

/*
 * The CUD dependency tracking op doesn't do squat.  It can't because
 * it doesn't know where the free extent is coming from.  The dependency
 * tracking has to be handled by the "enclosing" metadata object.  For
 * example, for inodes, the inode is locked throughout the extent freeing
 * so the dependency should be recorded there.
 */
STATIC void
xfs_cud_item_committing(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
}

/*
 * This is the ops vector shared by all cud log items.
 */
static const struct xfs_item_ops xfs_cud_item_ops = {
	.iop_size	= xfs_cud_item_size,
	.iop_format	= xfs_cud_item_format,
	.iop_pin	= xfs_cud_item_pin,
	.iop_unpin	= xfs_cud_item_unpin,
	.iop_unlock	= xfs_cud_item_unlock,
	.iop_committed	= xfs_cud_item_committed,
	.iop_push	= xfs_cud_item_push,
	.iop_committing = xfs_cud_item_committing,
};

/*
 * Allocate and initialize an cud item with the given number of extents.
 */
struct xfs_cud_log_item *
xfs_cud_init(
	struct xfs_mount		*mp,
	struct xfs_cui_log_item		*cuip)

{
	struct xfs_cud_log_item	*cudp;

	cudp = kmem_zone_zalloc(xfs_cud_zone, KM_SLEEP);
	xfs_log_item_init(mp, &cudp->cud_item, XFS_LI_CUD, &xfs_cud_item_ops);
	cudp->cud_cuip = cuip;
	cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id;

	return cudp;
}

/*
 * Process a refcount update intent item that was recovered from the log.
 * We need to update the refcountbt.
 */
int
xfs_cui_recover(
	struct xfs_mount		*mp,
	struct xfs_cui_log_item		*cuip,
	struct xfs_defer_ops		*dfops)
{
	int				i;
	int				error = 0;
	unsigned int			refc_type;
	struct xfs_phys_extent		*refc;
	xfs_fsblock_t			startblock_fsb;
	bool				op_ok;
	struct xfs_cud_log_item		*cudp;
	struct xfs_trans		*tp;
	struct xfs_btree_cur		*rcur = NULL;
	enum xfs_refcount_intent_type	type;
	xfs_fsblock_t			new_fsb;
	xfs_extlen_t			new_len;
	struct xfs_bmbt_irec		irec;
	bool				requeue_only = false;

	ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags));

	/*
	 * First check the validity of the extents described by the
	 * CUI.  If any are bad, then assume that all are bad and
	 * just toss the CUI.
	 */
	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
		refc = &cuip->cui_format.cui_extents[i];
		startblock_fsb = XFS_BB_TO_FSB(mp,
				   XFS_FSB_TO_DADDR(mp, refc->pe_startblock));
		switch (refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK) {
		case XFS_REFCOUNT_INCREASE:
		case XFS_REFCOUNT_DECREASE:
		case XFS_REFCOUNT_ALLOC_COW:
		case XFS_REFCOUNT_FREE_COW:
			op_ok = true;
			break;
		default:
			op_ok = false;
			break;
		}
		if (!op_ok || startblock_fsb == 0 ||
		    refc->pe_len == 0 ||
		    startblock_fsb >= mp->m_sb.sb_dblocks ||
		    refc->pe_len >= mp->m_sb.sb_agblocks ||
		    (refc->pe_flags & ~XFS_REFCOUNT_EXTENT_FLAGS)) {
			/*
			 * This will pull the CUI from the AIL and
			 * free the memory associated with it.
			 */
			set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
			xfs_cui_release(cuip);
			return -EIO;
		}
	}

	/*
	 * Under normal operation, refcount updates are deferred, so we
	 * wouldn't be adding them directly to a transaction.  All
	 * refcount updates manage reservation usage internally and
	 * dynamically by deferring work that won't fit in the
	 * transaction.  Normally, any work that needs to be deferred
	 * gets attached to the same defer_ops that scheduled the
	 * refcount update.  However, we're in log recovery here, so we
	 * we use the passed in defer_ops and to finish up any work that
	 * doesn't fit.  We need to reserve enough blocks to handle a
	 * full btree split on either end of the refcount range.
	 */
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
			mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
	if (error)
		return error;
	cudp = xfs_trans_get_cud(tp, cuip);

	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
		refc = &cuip->cui_format.cui_extents[i];
		refc_type = refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
		switch (refc_type) {
		case XFS_REFCOUNT_INCREASE:
		case XFS_REFCOUNT_DECREASE:
		case XFS_REFCOUNT_ALLOC_COW:
		case XFS_REFCOUNT_FREE_COW:
			type = refc_type;
			break;
		default:
			error = -EFSCORRUPTED;
			goto abort_error;
		}
		if (requeue_only) {
			new_fsb = refc->pe_startblock;
			new_len = refc->pe_len;
		} else
			error = xfs_trans_log_finish_refcount_update(tp, cudp,
				dfops, type, refc->pe_startblock, refc->pe_len,
				&new_fsb, &new_len, &rcur);
		if (error)
			goto abort_error;

		/* Requeue what we didn't finish. */
		if (new_len > 0) {
			irec.br_startblock = new_fsb;
			irec.br_blockcount = new_len;
			switch (type) {
			case XFS_REFCOUNT_INCREASE:
				error = xfs_refcount_increase_extent(
						tp->t_mountp, dfops, &irec);
				break;
			case XFS_REFCOUNT_DECREASE:
				error = xfs_refcount_decrease_extent(
						tp->t_mountp, dfops, &irec);
				break;
			case XFS_REFCOUNT_ALLOC_COW:
				error = xfs_refcount_alloc_cow_extent(
						tp->t_mountp, dfops,
						irec.br_startblock,
						irec.br_blockcount);
				break;
			case XFS_REFCOUNT_FREE_COW:
				error = xfs_refcount_free_cow_extent(
						tp->t_mountp, dfops,
						irec.br_startblock,
						irec.br_blockcount);
				break;
			default:
				ASSERT(0);
			}
			if (error)
				goto abort_error;
			requeue_only = true;
		}
	}

	xfs_refcount_finish_one_cleanup(tp, rcur, error);
	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
	error = xfs_trans_commit(tp);
	return error;

abort_error:
	xfs_refcount_finish_one_cleanup(tp, rcur, error);
	xfs_trans_cancel(tp);
	return error;
}