summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_defer.c
blob: 7079f534c7352518d3edd84a0daf32da2206eb87 (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
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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2016 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_trace.h"

/*
 * Deferred Operations in XFS
 *
 * Due to the way locking rules work in XFS, certain transactions (block
 * mapping and unmapping, typically) have permanent reservations so that
 * we can roll the transaction to adhere to AG locking order rules and
 * to unlock buffers between metadata updates.  Prior to rmap/reflink,
 * the mapping code had a mechanism to perform these deferrals for
 * extents that were going to be freed; this code makes that facility
 * more generic.
 *
 * When adding the reverse mapping and reflink features, it became
 * necessary to perform complex remapping multi-transactions to comply
 * with AG locking order rules, and to be able to spread a single
 * refcount update operation (an operation on an n-block extent can
 * update as many as n records!) among multiple transactions.  XFS can
 * roll a transaction to facilitate this, but using this facility
 * requires us to log "intent" items in case log recovery needs to
 * redo the operation, and to log "done" items to indicate that redo
 * is not necessary.
 *
 * Deferred work is tracked in xfs_defer_pending items.  Each pending
 * item tracks one type of deferred work.  Incoming work items (which
 * have not yet had an intent logged) are attached to a pending item
 * on the dop_intake list, where they wait for the caller to finish
 * the deferred operations.
 *
 * Finishing a set of deferred operations is an involved process.  To
 * start, we define "rolling a deferred-op transaction" as follows:
 *
 * > For each xfs_defer_pending item on the dop_intake list,
 *   - Sort the work items in AG order.  XFS locking
 *     order rules require us to lock buffers in AG order.
 *   - Create a log intent item for that type.
 *   - Attach it to the pending item.
 *   - Move the pending item from the dop_intake list to the
 *     dop_pending list.
 * > Roll the transaction.
 *
 * NOTE: To avoid exceeding the transaction reservation, we limit the
 * number of items that we attach to a given xfs_defer_pending.
 *
 * The actual finishing process looks like this:
 *
 * > For each xfs_defer_pending in the dop_pending list,
 *   - Roll the deferred-op transaction as above.
 *   - Create a log done item for that type, and attach it to the
 *     log intent item.
 *   - For each work item attached to the log intent item,
 *     * Perform the described action.
 *     * Attach the work item to the log done item.
 *     * If the result of doing the work was -EAGAIN, ->finish work
 *       wants a new transaction.  See the "Requesting a Fresh
 *       Transaction while Finishing Deferred Work" section below for
 *       details.
 *
 * The key here is that we must log an intent item for all pending
 * work items every time we roll the transaction, and that we must log
 * a done item as soon as the work is completed.  With this mechanism
 * we can perform complex remapping operations, chaining intent items
 * as needed.
 *
 * Requesting a Fresh Transaction while Finishing Deferred Work
 *
 * If ->finish_item decides that it needs a fresh transaction to
 * finish the work, it must ask its caller (xfs_defer_finish) for a
 * continuation.  The most likely cause of this circumstance are the
 * refcount adjust functions deciding that they've logged enough items
 * to be at risk of exceeding the transaction reservation.
 *
 * To get a fresh transaction, we want to log the existing log done
 * item to prevent the log intent item from replaying, immediately log
 * a new log intent item with the unfinished work items, roll the
 * transaction, and re-call ->finish_item wherever it left off.  The
 * log done item and the new log intent item must be in the same
 * transaction or atomicity cannot be guaranteed; defer_finish ensures
 * that this happens.
 *
 * This requires some coordination between ->finish_item and
 * defer_finish.  Upon deciding to request a new transaction,
 * ->finish_item should update the current work item to reflect the
 * unfinished work.  Next, it should reset the log done item's list
 * count to the number of items finished, and return -EAGAIN.
 * defer_finish sees the -EAGAIN, logs the new log intent item
 * with the remaining work items, and leaves the xfs_defer_pending
 * item at the head of the dop_work queue.  Then it rolls the
 * transaction and picks up processing where it left off.  It is
 * required that ->finish_item must be careful to leave enough
 * transaction reservation to fit the new log intent item.
 *
 * This is an example of remapping the extent (E, E+B) into file X at
 * offset A and dealing with the extent (C, C+B) already being mapped
 * there:
 * +-------------------------------------------------+
 * | Unmap file X startblock C offset A length B     | t0
 * | Intent to reduce refcount for extent (C, B)     |
 * | Intent to remove rmap (X, C, A, B)              |
 * | Intent to free extent (D, 1) (bmbt block)       |
 * | Intent to map (X, A, B) at startblock E         |
 * +-------------------------------------------------+
 * | Map file X startblock E offset A length B       | t1
 * | Done mapping (X, E, A, B)                       |
 * | Intent to increase refcount for extent (E, B)   |
 * | Intent to add rmap (X, E, A, B)                 |
 * +-------------------------------------------------+
 * | Reduce refcount for extent (C, B)               | t2
 * | Done reducing refcount for extent (C, 9)        |
 * | Intent to reduce refcount for extent (C+9, B-9) |
 * | (ran out of space after 9 refcount updates)     |
 * +-------------------------------------------------+
 * | Reduce refcount for extent (C+9, B+9)           | t3
 * | Done reducing refcount for extent (C+9, B-9)    |
 * | Increase refcount for extent (E, B)             |
 * | Done increasing refcount for extent (E, B)      |
 * | Intent to free extent (C, B)                    |
 * | Intent to free extent (F, 1) (refcountbt block) |
 * | Intent to remove rmap (F, 1, REFC)              |
 * +-------------------------------------------------+
 * | Remove rmap (X, C, A, B)                        | t4
 * | Done removing rmap (X, C, A, B)                 |
 * | Add rmap (X, E, A, B)                           |
 * | Done adding rmap (X, E, A, B)                   |
 * | Remove rmap (F, 1, REFC)                        |
 * | Done removing rmap (F, 1, REFC)                 |
 * +-------------------------------------------------+
 * | Free extent (C, B)                              | t5
 * | Done freeing extent (C, B)                      |
 * | Free extent (D, 1)                              |
 * | Done freeing extent (D, 1)                      |
 * | Free extent (F, 1)                              |
 * | Done freeing extent (F, 1)                      |
 * +-------------------------------------------------+
 *
 * If we should crash before t2 commits, log recovery replays
 * the following intent items:
 *
 * - Intent to reduce refcount for extent (C, B)
 * - Intent to remove rmap (X, C, A, B)
 * - Intent to free extent (D, 1) (bmbt block)
 * - Intent to increase refcount for extent (E, B)
 * - Intent to add rmap (X, E, A, B)
 *
 * In the process of recovering, it should also generate and take care
 * of these intent items:
 *
 * - Intent to free extent (C, B)
 * - Intent to free extent (F, 1) (refcountbt block)
 * - Intent to remove rmap (F, 1, REFC)
 *
 * Note that the continuation requested between t2 and t3 is likely to
 * reoccur.
 */

static const struct xfs_defer_op_type *defer_op_types[XFS_DEFER_OPS_TYPE_MAX];

/*
 * For each pending item in the intake list, log its intent item and the
 * associated extents, then add the entire intake list to the end of
 * the pending list.
 */
STATIC void
xfs_defer_intake_work(
	struct xfs_trans		*tp)
{
	struct xfs_defer_ops		*dop = tp->t_dfops;
	struct list_head		*li;
	struct xfs_defer_pending	*dfp;

	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
				dfp->dfp_count);
		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
		list_sort(tp->t_mountp, &dfp->dfp_work,
				dfp->dfp_type->diff_items);
		list_for_each(li, &dfp->dfp_work)
			dfp->dfp_type->log_item(tp, dfp->dfp_intent, li);
	}

	list_splice_tail_init(&dop->dop_intake, &dop->dop_pending);
}

/* Abort all the intents that were committed. */
STATIC void
xfs_defer_trans_abort(
	struct xfs_trans		*tp,
	int				error)
{
	struct xfs_defer_ops		*dop = tp->t_dfops;
	struct xfs_defer_pending	*dfp;

	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);

	/* Abort intent items that don't have a done item. */
	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
		if (dfp->dfp_intent && !dfp->dfp_done) {
			dfp->dfp_type->abort_intent(dfp->dfp_intent);
			dfp->dfp_intent = NULL;
		}
	}

	/* Shut down FS. */
	xfs_force_shutdown(tp->t_mountp, (error == -EFSCORRUPTED) ?
			SHUTDOWN_CORRUPT_INCORE : SHUTDOWN_META_IO_ERROR);
}

/* Roll a transaction so we can do some deferred op processing. */
STATIC int
xfs_defer_trans_roll(
	struct xfs_trans		**tp)
{
	struct xfs_buf_log_item		*bli;
	struct xfs_inode_log_item	*ili;
	struct xfs_log_item		*lip;
	struct xfs_buf			*bplist[XFS_DEFER_OPS_NR_BUFS];
	struct xfs_inode		*iplist[XFS_DEFER_OPS_NR_INODES];
	int				bpcount = 0, ipcount = 0;
	int				i;
	int				error;

	list_for_each_entry(lip, &(*tp)->t_items, li_trans) {
		switch (lip->li_type) {
		case XFS_LI_BUF:
			bli = container_of(lip, struct xfs_buf_log_item,
					   bli_item);
			if (bli->bli_flags & XFS_BLI_HOLD) {
				if (bpcount >= XFS_DEFER_OPS_NR_BUFS) {
					ASSERT(0);
					return -EFSCORRUPTED;
				}
				xfs_trans_dirty_buf(*tp, bli->bli_buf);
				bplist[bpcount++] = bli->bli_buf;
			}
			break;
		case XFS_LI_INODE:
			ili = container_of(lip, struct xfs_inode_log_item,
					   ili_item);
			if (ili->ili_lock_flags == 0) {
				if (ipcount >= XFS_DEFER_OPS_NR_INODES) {
					ASSERT(0);
					return -EFSCORRUPTED;
				}
				xfs_trans_log_inode(*tp, ili->ili_inode,
						    XFS_ILOG_CORE);
				iplist[ipcount++] = ili->ili_inode;
			}
			break;
		default:
			break;
		}
	}

	trace_xfs_defer_trans_roll((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);

	/* Roll the transaction. */
	error = xfs_trans_roll(tp);
	if (error) {
		trace_xfs_defer_trans_roll_error((*tp)->t_mountp,
						 (*tp)->t_dfops, error);
		xfs_defer_trans_abort(*tp,  error);
		return error;
	}

	/* Rejoin the joined inodes. */
	for (i = 0; i < ipcount; i++)
		xfs_trans_ijoin(*tp, iplist[i], 0);

	/* Rejoin the buffers and dirty them so the log moves forward. */
	for (i = 0; i < bpcount; i++) {
		xfs_trans_bjoin(*tp, bplist[i]);
		xfs_trans_bhold(*tp, bplist[i]);
	}

	return error;
}

/* Do we have any work items to finish? */
bool
xfs_defer_has_unfinished_work(
	struct xfs_trans		*tp)
{
	return !list_empty(&tp->t_dfops->dop_pending) ||
		!list_empty(&tp->t_dfops->dop_intake);
}

/*
 * Reset an already used dfops after finish.
 */
static void
xfs_defer_reset(
	struct xfs_trans	*tp)
{
	ASSERT(!xfs_defer_has_unfinished_work(tp));

	/*
	 * Low mode state transfers across transaction rolls to mirror dfops
	 * lifetime. Clear it now that dfops is reset.
	 */
	tp->t_flags &= ~XFS_TRANS_LOWMODE;
}

/*
 * Finish all the pending work.  This involves logging intent items for
 * any work items that wandered in since the last transaction roll (if
 * one has even happened), rolling the transaction, and finishing the
 * work items in the first item on the logged-and-pending list.
 *
 * If an inode is provided, relog it to the new transaction.
 */
int
xfs_defer_finish_noroll(
	struct xfs_trans		**tp)
{
	struct xfs_defer_pending	*dfp;
	struct list_head		*li;
	struct list_head		*n;
	void				*state;
	int				error = 0;
	void				(*cleanup_fn)(struct xfs_trans *, void *, int);

	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);

	trace_xfs_defer_finish((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);

	/* Until we run out of pending work to finish... */
	while (xfs_defer_has_unfinished_work(*tp)) {
		/* Log intents for work items sitting in the intake. */
		xfs_defer_intake_work(*tp);

		/*
		 * Roll the transaction.
		 */
		error = xfs_defer_trans_roll(tp);
		if (error)
			goto out;

		/* Log an intent-done item for the first pending item. */
		dfp = list_first_entry(&(*tp)->t_dfops->dop_pending,
				struct xfs_defer_pending, dfp_list);
		trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp);
		dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
				dfp->dfp_count);
		cleanup_fn = dfp->dfp_type->finish_cleanup;

		/* Finish the work items. */
		state = NULL;
		list_for_each_safe(li, n, &dfp->dfp_work) {
			list_del(li);
			dfp->dfp_count--;
			error = dfp->dfp_type->finish_item(*tp, li,
					dfp->dfp_done, &state);
			if (error == -EAGAIN) {
				/*
				 * Caller wants a fresh transaction;
				 * put the work item back on the list
				 * and jump out.
				 */
				list_add(li, &dfp->dfp_work);
				dfp->dfp_count++;
				break;
			} else if (error) {
				/*
				 * Clean up after ourselves and jump out.
				 * xfs_defer_cancel will take care of freeing
				 * all these lists and stuff.
				 */
				if (cleanup_fn)
					cleanup_fn(*tp, state, error);
				xfs_defer_trans_abort(*tp, error);
				goto out;
			}
		}
		if (error == -EAGAIN) {
			/*
			 * Caller wants a fresh transaction, so log a
			 * new log intent item to replace the old one
			 * and roll the transaction.  See "Requesting
			 * a Fresh Transaction while Finishing
			 * Deferred Work" above.
			 */
			dfp->dfp_intent = dfp->dfp_type->create_intent(*tp,
					dfp->dfp_count);
			dfp->dfp_done = NULL;
			list_for_each(li, &dfp->dfp_work)
				dfp->dfp_type->log_item(*tp, dfp->dfp_intent,
						li);
		} else {
			/* Done with the dfp, free it. */
			list_del(&dfp->dfp_list);
			kmem_free(dfp);
		}

		if (cleanup_fn)
			cleanup_fn(*tp, state, error);
	}

out:
	if (error)
		trace_xfs_defer_finish_error((*tp)->t_mountp, (*tp)->t_dfops,
					     error);
	 else
		trace_xfs_defer_finish_done((*tp)->t_mountp, (*tp)->t_dfops,
					    _RET_IP_);

	return error;
}

int
xfs_defer_finish(
	struct xfs_trans	**tp)
{
	int			error;

	/*
	 * Finish and roll the transaction once more to avoid returning to the
	 * caller with a dirty transaction.
	 */
	error = xfs_defer_finish_noroll(tp);
	if (error)
		return error;
	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
		error = xfs_defer_trans_roll(tp);
		if (error)
			return error;
	}
	xfs_defer_reset(*tp);
	return 0;
}

/*
 * Free up any items left in the list.
 */
void
xfs_defer_cancel(
	struct xfs_trans		*tp)
{
	struct xfs_defer_ops		*dop = tp->t_dfops;
	struct xfs_defer_pending	*dfp;
	struct xfs_defer_pending	*pli;
	struct list_head		*pwi;
	struct list_head		*n;

	trace_xfs_defer_cancel(NULL, dop, _RET_IP_);

	/*
	 * Free the pending items.  Caller should already have arranged
	 * for the intent items to be released.
	 */
	list_for_each_entry_safe(dfp, pli, &dop->dop_intake, dfp_list) {
		trace_xfs_defer_intake_cancel(NULL, dfp);
		list_del(&dfp->dfp_list);
		list_for_each_safe(pwi, n, &dfp->dfp_work) {
			list_del(pwi);
			dfp->dfp_count--;
			dfp->dfp_type->cancel_item(pwi);
		}
		ASSERT(dfp->dfp_count == 0);
		kmem_free(dfp);
	}
	list_for_each_entry_safe(dfp, pli, &dop->dop_pending, dfp_list) {
		trace_xfs_defer_pending_cancel(NULL, dfp);
		list_del(&dfp->dfp_list);
		list_for_each_safe(pwi, n, &dfp->dfp_work) {
			list_del(pwi);
			dfp->dfp_count--;
			dfp->dfp_type->cancel_item(pwi);
		}
		ASSERT(dfp->dfp_count == 0);
		kmem_free(dfp);
	}
}

/* Add an item for later deferred processing. */
void
xfs_defer_add(
	struct xfs_defer_ops		*dop,
	enum xfs_defer_ops_type		type,
	struct list_head		*li)
{
	struct xfs_defer_pending	*dfp = NULL;

	/*
	 * Add the item to a pending item at the end of the intake list.
	 * If the last pending item has the same type, reuse it.  Else,
	 * create a new pending item at the end of the intake list.
	 */
	if (!list_empty(&dop->dop_intake)) {
		dfp = list_last_entry(&dop->dop_intake,
				struct xfs_defer_pending, dfp_list);
		if (dfp->dfp_type->type != type ||
		    (dfp->dfp_type->max_items &&
		     dfp->dfp_count >= dfp->dfp_type->max_items))
			dfp = NULL;
	}
	if (!dfp) {
		dfp = kmem_alloc(sizeof(struct xfs_defer_pending),
				KM_SLEEP | KM_NOFS);
		dfp->dfp_type = defer_op_types[type];
		dfp->dfp_intent = NULL;
		dfp->dfp_done = NULL;
		dfp->dfp_count = 0;
		INIT_LIST_HEAD(&dfp->dfp_work);
		list_add_tail(&dfp->dfp_list, &dop->dop_intake);
	}

	list_add_tail(li, &dfp->dfp_work);
	dfp->dfp_count++;
}

/* Initialize a deferred operation list. */
void
xfs_defer_init_op_type(
	const struct xfs_defer_op_type	*type)
{
	defer_op_types[type->type] = type;
}

/* Initialize a deferred operation. */
void
xfs_defer_init(
	struct xfs_trans		*tp,
	struct xfs_defer_ops		*dop)
{
	struct xfs_mount		*mp = NULL;

	memset(dop, 0, sizeof(struct xfs_defer_ops));
	INIT_LIST_HEAD(&dop->dop_intake);
	INIT_LIST_HEAD(&dop->dop_pending);
	if (tp) {
		ASSERT(tp->t_firstblock == NULLFSBLOCK);
		tp->t_dfops = dop;
		mp = tp->t_mountp;
	}
	trace_xfs_defer_init(mp, dop, _RET_IP_);
}

/*
 * Move state from one xfs_defer_ops to another and reset the source to initial
 * state. This is primarily used to carry state forward across transaction rolls
 * with internal dfops.
 */
void
xfs_defer_move(
	struct xfs_trans	*dtp,
	struct xfs_trans	*stp)
{
	struct xfs_defer_ops	*dst = dtp->t_dfops;
	struct xfs_defer_ops	*src = stp->t_dfops;
	ASSERT(dst != src);

	list_splice_init(&src->dop_intake, &dst->dop_intake);
	list_splice_init(&src->dop_pending, &dst->dop_pending);

	/*
	 * Low free space mode was historically controlled by a dfops field.
	 * This meant that low mode state potentially carried across multiple
	 * transaction rolls. Transfer low mode on a dfops move to preserve
	 * that behavior.
	 */
	dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);

	xfs_defer_reset(stp);
}