summaryrefslogtreecommitdiffstats
path: root/kernel/fs/xfs/xfs_extfree_item.c
blob: cb7fe64cdbfa0d2cb41c4389ab1b03005c0bbe36 (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
/*
 * Copyright (c) 2000-2001,2005 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_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_buf_item.h"
#include "xfs_extfree_item.h"
#include "xfs_log.h"


kmem_zone_t	*xfs_efi_zone;
kmem_zone_t	*xfs_efd_zone;

static inline struct xfs_efi_log_item *EFI_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_efi_log_item, efi_item);
}

void
xfs_efi_item_free(
	struct xfs_efi_log_item	*efip)
{
	if (efip->efi_format.efi_nextents > XFS_EFI_MAX_FAST_EXTENTS)
		kmem_free(efip);
	else
		kmem_zone_free(xfs_efi_zone, efip);
}

/*
 * Freeing the efi requires that we remove it from the AIL if it has already
 * been placed there. However, the EFI may not yet have been placed in the AIL
 * when called by xfs_efi_release() from EFD 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 EFI.
 */
STATIC void
__xfs_efi_release(
	struct xfs_efi_log_item	*efip)
{
	struct xfs_ail		*ailp = efip->efi_item.li_ailp;

	if (atomic_dec_and_test(&efip->efi_refcount)) {
		spin_lock(&ailp->xa_lock);
		/* xfs_trans_ail_delete() drops the AIL lock. */
		xfs_trans_ail_delete(ailp, &efip->efi_item,
				     SHUTDOWN_LOG_IO_ERROR);
		xfs_efi_item_free(efip);
	}
}

/*
 * This returns the number of iovecs needed to log the given efi item.
 * We only need 1 iovec for an efi item.  It just logs the efi_log_format
 * structure.
 */
static inline int
xfs_efi_item_sizeof(
	struct xfs_efi_log_item *efip)
{
	return sizeof(struct xfs_efi_log_format) +
	       (efip->efi_format.efi_nextents - 1) * sizeof(xfs_extent_t);
}

STATIC void
xfs_efi_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	*nvecs += 1;
	*nbytes += xfs_efi_item_sizeof(EFI_ITEM(lip));
}

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

	ASSERT(atomic_read(&efip->efi_next_extent) ==
				efip->efi_format.efi_nextents);

	efip->efi_format.efi_type = XFS_LI_EFI;
	efip->efi_format.efi_size = 1;

	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT,
			&efip->efi_format,
			xfs_efi_item_sizeof(efip));
}


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

/*
 * While EFIs cannot really be pinned, the unpin operation is the last place at
 * which the EFI is manipulated during a transaction.  If we are being asked to
 * remove the EFI it's because the transaction has been cancelled and by
 * definition that means the EFI cannot be in the AIL so remove it from the
 * transaction and free it.  Otherwise coordinate with xfs_efi_release()
 * to determine who gets to free the EFI.
 */
STATIC void
xfs_efi_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{
	struct xfs_efi_log_item	*efip = EFI_ITEM(lip);

	if (remove) {
		ASSERT(!(lip->li_flags & XFS_LI_IN_AIL));
		if (lip->li_desc)
			xfs_trans_del_item(lip);
		xfs_efi_item_free(efip);
		return;
	}
	__xfs_efi_release(efip);
}

/*
 * Efi items have no locking or pushing.  However, since EFIs are pulled from
 * the AIL when their corresponding EFDs 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 EFI out of
 * the AIL.
 */
STATIC uint
xfs_efi_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
{
	return XFS_ITEM_PINNED;
}

STATIC void
xfs_efi_item_unlock(
	struct xfs_log_item	*lip)
{
	if (lip->li_flags & XFS_LI_ABORTED)
		xfs_efi_item_free(EFI_ITEM(lip));
}

/*
 * The EFI 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_efi_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	return lsn;
}

/*
 * The EFI 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_efi_item_committing(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
}

/*
 * This is the ops vector shared by all efi log items.
 */
static const struct xfs_item_ops xfs_efi_item_ops = {
	.iop_size	= xfs_efi_item_size,
	.iop_format	= xfs_efi_item_format,
	.iop_pin	= xfs_efi_item_pin,
	.iop_unpin	= xfs_efi_item_unpin,
	.iop_unlock	= xfs_efi_item_unlock,
	.iop_committed	= xfs_efi_item_committed,
	.iop_push	= xfs_efi_item_push,
	.iop_committing = xfs_efi_item_committing
};


/*
 * Allocate and initialize an efi item with the given number of extents.
 */
struct xfs_efi_log_item *
xfs_efi_init(
	struct xfs_mount	*mp,
	uint			nextents)

{
	struct xfs_efi_log_item	*efip;
	uint			size;

	ASSERT(nextents > 0);
	if (nextents > XFS_EFI_MAX_FAST_EXTENTS) {
		size = (uint)(sizeof(xfs_efi_log_item_t) +
			((nextents - 1) * sizeof(xfs_extent_t)));
		efip = kmem_zalloc(size, KM_SLEEP);
	} else {
		efip = kmem_zone_zalloc(xfs_efi_zone, KM_SLEEP);
	}

	xfs_log_item_init(mp, &efip->efi_item, XFS_LI_EFI, &xfs_efi_item_ops);
	efip->efi_format.efi_nextents = nextents;
	efip->efi_format.efi_id = (__psint_t)(void*)efip;
	atomic_set(&efip->efi_next_extent, 0);
	atomic_set(&efip->efi_refcount, 2);

	return efip;
}

/*
 * Copy an EFI format buffer from the given buf, and into the destination
 * EFI format structure.
 * The given buffer can be in 32 bit or 64 bit form (which has different padding),
 * one of which will be the native format for this kernel.
 * It will handle the conversion of formats if necessary.
 */
int
xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
{
	xfs_efi_log_format_t *src_efi_fmt = buf->i_addr;
	uint i;
	uint len = sizeof(xfs_efi_log_format_t) + 
		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t);  
	uint len32 = sizeof(xfs_efi_log_format_32_t) + 
		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t);  
	uint len64 = sizeof(xfs_efi_log_format_64_t) + 
		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t);  

	if (buf->i_len == len) {
		memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len);
		return 0;
	} else if (buf->i_len == len32) {
		xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr;

		dst_efi_fmt->efi_type     = src_efi_fmt_32->efi_type;
		dst_efi_fmt->efi_size     = src_efi_fmt_32->efi_size;
		dst_efi_fmt->efi_nextents = src_efi_fmt_32->efi_nextents;
		dst_efi_fmt->efi_id       = src_efi_fmt_32->efi_id;
		for (i = 0; i < dst_efi_fmt->efi_nextents; i++) {
			dst_efi_fmt->efi_extents[i].ext_start =
				src_efi_fmt_32->efi_extents[i].ext_start;
			dst_efi_fmt->efi_extents[i].ext_len =
				src_efi_fmt_32->efi_extents[i].ext_len;
		}
		return 0;
	} else if (buf->i_len == len64) {
		xfs_efi_log_format_64_t *src_efi_fmt_64 = buf->i_addr;

		dst_efi_fmt->efi_type     = src_efi_fmt_64->efi_type;
		dst_efi_fmt->efi_size     = src_efi_fmt_64->efi_size;
		dst_efi_fmt->efi_nextents = src_efi_fmt_64->efi_nextents;
		dst_efi_fmt->efi_id       = src_efi_fmt_64->efi_id;
		for (i = 0; i < dst_efi_fmt->efi_nextents; i++) {
			dst_efi_fmt->efi_extents[i].ext_start =
				src_efi_fmt_64->efi_extents[i].ext_start;
			dst_efi_fmt->efi_extents[i].ext_len =
				src_efi_fmt_64->efi_extents[i].ext_len;
		}
		return 0;
	}
	return -EFSCORRUPTED;
}

/*
 * This is called by the efd item code below to release references to the given
 * efi item.  Each efd calls this with the number of extents that it has
 * logged, and when the sum of these reaches the total number of extents logged
 * by this efi item we can free the efi item.
 */
void
xfs_efi_release(xfs_efi_log_item_t	*efip,
		uint			nextents)
{
	ASSERT(atomic_read(&efip->efi_next_extent) >= nextents);
	if (atomic_sub_and_test(nextents, &efip->efi_next_extent)) {
		/* recovery needs us to drop the EFI reference, too */
		if (test_bit(XFS_EFI_RECOVERED, &efip->efi_flags))
			__xfs_efi_release(efip);

		__xfs_efi_release(efip);
		/* efip may now have been freed, do not reference it again. */
	}
}

static inline struct xfs_efd_log_item *EFD_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_efd_log_item, efd_item);
}

STATIC void
xfs_efd_item_free(struct xfs_efd_log_item *efdp)
{
	if (efdp->efd_format.efd_nextents > XFS_EFD_MAX_FAST_EXTENTS)
		kmem_free(efdp);
	else
		kmem_zone_free(xfs_efd_zone, efdp);
}

/*
 * This returns the number of iovecs needed to log the given efd item.
 * We only need 1 iovec for an efd item.  It just logs the efd_log_format
 * structure.
 */
static inline int
xfs_efd_item_sizeof(
	struct xfs_efd_log_item *efdp)
{
	return sizeof(xfs_efd_log_format_t) +
	       (efdp->efd_format.efd_nextents - 1) * sizeof(xfs_extent_t);
}

STATIC void
xfs_efd_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	*nvecs += 1;
	*nbytes += xfs_efd_item_sizeof(EFD_ITEM(lip));
}

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

	ASSERT(efdp->efd_next_extent == efdp->efd_format.efd_nextents);

	efdp->efd_format.efd_type = XFS_LI_EFD;
	efdp->efd_format.efd_size = 1;

	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT,
			&efdp->efd_format,
			xfs_efd_item_sizeof(efdp));
}

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

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

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

STATIC void
xfs_efd_item_unlock(
	struct xfs_log_item	*lip)
{
	if (lip->li_flags & XFS_LI_ABORTED)
		xfs_efd_item_free(EFD_ITEM(lip));
}

/*
 * When the efd item is committed to disk, all we need to do
 * is delete our reference to our partner efi 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_efd_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	struct xfs_efd_log_item	*efdp = EFD_ITEM(lip);

	/*
	 * If we got a log I/O error, it's always the case that the LR with the
	 * EFI got unpinned and freed before the EFD got aborted.
	 */
	if (!(lip->li_flags & XFS_LI_ABORTED))
		xfs_efi_release(efdp->efd_efip, efdp->efd_format.efd_nextents);

	xfs_efd_item_free(efdp);
	return (xfs_lsn_t)-1;
}

/*
 * The EFD 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_efd_item_committing(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
}

/*
 * This is the ops vector shared by all efd log items.
 */
static const struct xfs_item_ops xfs_efd_item_ops = {
	.iop_size	= xfs_efd_item_size,
	.iop_format	= xfs_efd_item_format,
	.iop_pin	= xfs_efd_item_pin,
	.iop_unpin	= xfs_efd_item_unpin,
	.iop_unlock	= xfs_efd_item_unlock,
	.iop_committed	= xfs_efd_item_committed,
	.iop_push	= xfs_efd_item_push,
	.iop_committing = xfs_efd_item_committing
};

/*
 * Allocate and initialize an efd item with the given number of extents.
 */
struct xfs_efd_log_item *
xfs_efd_init(
	struct xfs_mount	*mp,
	struct xfs_efi_log_item	*efip,
	uint			nextents)

{
	struct xfs_efd_log_item	*efdp;
	uint			size;

	ASSERT(nextents > 0);
	if (nextents > XFS_EFD_MAX_FAST_EXTENTS) {
		size = (uint)(sizeof(xfs_efd_log_item_t) +
			((nextents - 1) * sizeof(xfs_extent_t)));
		efdp = kmem_zalloc(size, KM_SLEEP);
	} else {
		efdp = kmem_zone_zalloc(xfs_efd_zone, KM_SLEEP);
	}

	xfs_log_item_init(mp, &efdp->efd_item, XFS_LI_EFD, &xfs_efd_item_ops);
	efdp->efd_efip = efip;
	efdp->efd_format.efd_nextents = nextents;
	efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;

	return efdp;
}