summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_aops.c
blob: 813f85156b0c3b9ed97a5d5740db2d20e3810e59 (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
585
586
587
588
589
590
591
592
593
594
595
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * Copyright (c) 2016-2018 Christoph Hellwig.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_reflink.h"
#include "xfs_errortag.h"
#include "xfs_error.h"

struct xfs_writepage_ctx {
	struct iomap_writepage_ctx ctx;
	unsigned int		data_seq;
	unsigned int		cow_seq;
};

static inline struct xfs_writepage_ctx *
XFS_WPC(struct iomap_writepage_ctx *ctx)
{
	return container_of(ctx, struct xfs_writepage_ctx, ctx);
}

/*
 * Fast and loose check if this write could update the on-disk inode size.
 */
static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend)
{
	return ioend->io_offset + ioend->io_size >
		XFS_I(ioend->io_inode)->i_disk_size;
}

/*
 * Update on-disk file size now that data has been written to disk.
 */
int
xfs_setfilesize(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	size_t			size)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	xfs_fsize_t		isize;
	int			error;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
	if (error)
		return error;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	isize = xfs_new_eof(ip, offset + size);
	if (!isize) {
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		xfs_trans_cancel(tp);
		return 0;
	}

	trace_xfs_setfilesize(ip, offset, size);

	ip->i_disk_size = isize;
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	return xfs_trans_commit(tp);
}

/*
 * IO write completion.
 */
STATIC void
xfs_end_ioend(
	struct iomap_ioend	*ioend)
{
	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
	struct xfs_mount	*mp = ip->i_mount;
	xfs_off_t		offset = ioend->io_offset;
	size_t			size = ioend->io_size;
	unsigned int		nofs_flag;
	int			error;

	/*
	 * We can allocate memory here while doing writeback on behalf of
	 * memory reclaim.  To avoid memory allocation deadlocks set the
	 * task-wide nofs context for the following operations.
	 */
	nofs_flag = memalloc_nofs_save();

	/*
	 * Just clean up the in-memory structures if the fs has been shut down.
	 */
	if (xfs_is_shutdown(mp)) {
		error = -EIO;
		goto done;
	}

	/*
	 * Clean up all COW blocks and underlying data fork delalloc blocks on
	 * I/O error. The delalloc punch is required because this ioend was
	 * mapped to blocks in the COW fork and the associated pages are no
	 * longer dirty. If we don't remove delalloc blocks here, they become
	 * stale and can corrupt free space accounting on unmount.
	 */
	error = blk_status_to_errno(ioend->io_bio->bi_status);
	if (unlikely(error)) {
		if (ioend->io_flags & IOMAP_F_SHARED) {
			xfs_reflink_cancel_cow_range(ip, offset, size, true);
			xfs_bmap_punch_delalloc_range(ip, offset,
					offset + size);
		}
		goto done;
	}

	/*
	 * Success: commit the COW or unwritten blocks if needed.
	 */
	if (ioend->io_flags & IOMAP_F_SHARED)
		error = xfs_reflink_end_cow(ip, offset, size);
	else if (ioend->io_type == IOMAP_UNWRITTEN)
		error = xfs_iomap_write_unwritten(ip, offset, size, false);

	if (!error && xfs_ioend_is_append(ioend))
		error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
done:
	iomap_finish_ioends(ioend, error);
	memalloc_nofs_restore(nofs_flag);
}

/*
 * Finish all pending IO completions that require transactional modifications.
 *
 * We try to merge physical and logically contiguous ioends before completion to
 * minimise the number of transactions we need to perform during IO completion.
 * Both unwritten extent conversion and COW remapping need to iterate and modify
 * one physical extent at a time, so we gain nothing by merging physically
 * discontiguous extents here.
 *
 * The ioend chain length that we can be processing here is largely unbound in
 * length and we may have to perform significant amounts of work on each ioend
 * to complete it. Hence we have to be careful about holding the CPU for too
 * long in this loop.
 */
void
xfs_end_io(
	struct work_struct	*work)
{
	struct xfs_inode	*ip =
		container_of(work, struct xfs_inode, i_ioend_work);
	struct iomap_ioend	*ioend;
	struct list_head	tmp;
	unsigned long		flags;

	spin_lock_irqsave(&ip->i_ioend_lock, flags);
	list_replace_init(&ip->i_ioend_list, &tmp);
	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);

	iomap_sort_ioends(&tmp);
	while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
			io_list))) {
		list_del_init(&ioend->io_list);
		iomap_ioend_try_merge(ioend, &tmp);
		xfs_end_ioend(ioend);
		cond_resched();
	}
}

STATIC void
xfs_end_bio(
	struct bio		*bio)
{
	struct iomap_ioend	*ioend = bio->bi_private;
	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
	unsigned long		flags;

	spin_lock_irqsave(&ip->i_ioend_lock, flags);
	if (list_empty(&ip->i_ioend_list))
		WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue,
					 &ip->i_ioend_work));
	list_add_tail(&ioend->io_list, &ip->i_ioend_list);
	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
}

/*
 * Fast revalidation of the cached writeback mapping. Return true if the current
 * mapping is valid, false otherwise.
 */
static bool
xfs_imap_valid(
	struct iomap_writepage_ctx	*wpc,
	struct xfs_inode		*ip,
	loff_t				offset)
{
	if (offset < wpc->iomap.offset ||
	    offset >= wpc->iomap.offset + wpc->iomap.length)
		return false;
	/*
	 * If this is a COW mapping, it is sufficient to check that the mapping
	 * covers the offset. Be careful to check this first because the caller
	 * can revalidate a COW mapping without updating the data seqno.
	 */
	if (wpc->iomap.flags & IOMAP_F_SHARED)
		return true;

	/*
	 * This is not a COW mapping. Check the sequence number of the data fork
	 * because concurrent changes could have invalidated the extent. Check
	 * the COW fork because concurrent changes since the last time we
	 * checked (and found nothing at this offset) could have added
	 * overlapping blocks.
	 */
	if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq)) {
		trace_xfs_wb_data_iomap_invalid(ip, &wpc->iomap,
				XFS_WPC(wpc)->data_seq, XFS_DATA_FORK);
		return false;
	}
	if (xfs_inode_has_cow_data(ip) &&
	    XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) {
		trace_xfs_wb_cow_iomap_invalid(ip, &wpc->iomap,
				XFS_WPC(wpc)->cow_seq, XFS_COW_FORK);
		return false;
	}
	return true;
}

/*
 * Pass in a dellalloc extent and convert it to real extents, return the real
 * extent that maps offset_fsb in wpc->iomap.
 *
 * The current page is held locked so nothing could have removed the block
 * backing offset_fsb, although it could have moved from the COW to the data
 * fork by another thread.
 */
static int
xfs_convert_blocks(
	struct iomap_writepage_ctx *wpc,
	struct xfs_inode	*ip,
	int			whichfork,
	loff_t			offset)
{
	int			error;
	unsigned		*seq;

	if (whichfork == XFS_COW_FORK)
		seq = &XFS_WPC(wpc)->cow_seq;
	else
		seq = &XFS_WPC(wpc)->data_seq;

	/*
	 * Attempt to allocate whatever delalloc extent currently backs offset
	 * and put the result into wpc->iomap.  Allocate in a loop because it
	 * may take several attempts to allocate real blocks for a contiguous
	 * delalloc extent if free space is sufficiently fragmented.
	 */
	do {
		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
				&wpc->iomap, seq);
		if (error)
			return error;
	} while (wpc->iomap.offset + wpc->iomap.length <= offset);

	return 0;
}

static int
xfs_map_blocks(
	struct iomap_writepage_ctx *wpc,
	struct inode		*inode,
	loff_t			offset)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	ssize_t			count = i_blocksize(inode);
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
	xfs_fileoff_t		cow_fsb;
	int			whichfork;
	struct xfs_bmbt_irec	imap;
	struct xfs_iext_cursor	icur;
	int			retries = 0;
	int			error = 0;

	if (xfs_is_shutdown(mp))
		return -EIO;

	XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS);

	/*
	 * COW fork blocks can overlap data fork blocks even if the blocks
	 * aren't shared.  COW I/O always takes precedent, so we must always
	 * check for overlap on reflink inodes unless the mapping is already a
	 * COW one, or the COW fork hasn't changed from the last time we looked
	 * at it.
	 *
	 * It's safe to check the COW fork if_seq here without the ILOCK because
	 * we've indirectly protected against concurrent updates: writeback has
	 * the page locked, which prevents concurrent invalidations by reflink
	 * and directio and prevents concurrent buffered writes to the same
	 * page.  Changes to if_seq always happen under i_lock, which protects
	 * against concurrent updates and provides a memory barrier on the way
	 * out that ensures that we always see the current value.
	 */
	if (xfs_imap_valid(wpc, ip, offset))
		return 0;

	/*
	 * If we don't have a valid map, now it's time to get a new one for this
	 * offset.  This will convert delayed allocations (including COW ones)
	 * into real extents.  If we return without a valid map, it means we
	 * landed in a hole and we skip the block.
	 */
retry:
	cow_fsb = NULLFILEOFF;
	whichfork = XFS_DATA_FORK;
	xfs_ilock(ip, XFS_ILOCK_SHARED);
	ASSERT(!xfs_need_iread_extents(&ip->i_df));

	/*
	 * Check if this is offset is covered by a COW extents, and if yes use
	 * it directly instead of looking up anything in the data fork.
	 */
	if (xfs_inode_has_cow_data(ip) &&
	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
		cow_fsb = imap.br_startoff;
	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
		XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
		xfs_iunlock(ip, XFS_ILOCK_SHARED);

		whichfork = XFS_COW_FORK;
		goto allocate_blocks;
	}

	/*
	 * No COW extent overlap. Revalidate now that we may have updated
	 * ->cow_seq. If the data mapping is still valid, we're done.
	 */
	if (xfs_imap_valid(wpc, ip, offset)) {
		xfs_iunlock(ip, XFS_ILOCK_SHARED);
		return 0;
	}

	/*
	 * If we don't have a valid map, now it's time to get a new one for this
	 * offset.  This will convert delayed allocations (including COW ones)
	 * into real extents.
	 */
	if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
	XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq);
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	/* landed in a hole or beyond EOF? */
	if (imap.br_startoff > offset_fsb) {
		imap.br_blockcount = imap.br_startoff - offset_fsb;
		imap.br_startoff = offset_fsb;
		imap.br_startblock = HOLESTARTBLOCK;
		imap.br_state = XFS_EXT_NORM;
	}

	/*
	 * Truncate to the next COW extent if there is one.  This is the only
	 * opportunity to do this because we can skip COW fork lookups for the
	 * subsequent blocks in the mapping; however, the requirement to treat
	 * the COW range separately remains.
	 */
	if (cow_fsb != NULLFILEOFF &&
	    cow_fsb < imap.br_startoff + imap.br_blockcount)
		imap.br_blockcount = cow_fsb - imap.br_startoff;

	/* got a delalloc extent? */
	if (imap.br_startblock != HOLESTARTBLOCK &&
	    isnullstartblock(imap.br_startblock))
		goto allocate_blocks;

	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq);
	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
	return 0;
allocate_blocks:
	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
	if (error) {
		/*
		 * If we failed to find the extent in the COW fork we might have
		 * raced with a COW to data fork conversion or truncate.
		 * Restart the lookup to catch the extent in the data fork for
		 * the former case, but prevent additional retries to avoid
		 * looping forever for the latter case.
		 */
		if (error == -EAGAIN && whichfork == XFS_COW_FORK && !retries++)
			goto retry;
		ASSERT(error != -EAGAIN);
		return error;
	}

	/*
	 * Due to merging the return real extent might be larger than the
	 * original delalloc one.  Trim the return extent to the next COW
	 * boundary again to force a re-lookup.
	 */
	if (whichfork != XFS_COW_FORK && cow_fsb != NULLFILEOFF) {
		loff_t		cow_offset = XFS_FSB_TO_B(mp, cow_fsb);

		if (cow_offset < wpc->iomap.offset + wpc->iomap.length)
			wpc->iomap.length = cow_offset - wpc->iomap.offset;
	}

	ASSERT(wpc->iomap.offset <= offset);
	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
	trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap);
	return 0;
}

static int
xfs_prepare_ioend(
	struct iomap_ioend	*ioend,
	int			status)
{
	unsigned int		nofs_flag;

	/*
	 * We can allocate memory here while doing writeback on behalf of
	 * memory reclaim.  To avoid memory allocation deadlocks set the
	 * task-wide nofs context for the following operations.
	 */
	nofs_flag = memalloc_nofs_save();

	/* Convert CoW extents to regular */
	if (!status && (ioend->io_flags & IOMAP_F_SHARED)) {
		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
				ioend->io_offset, ioend->io_size);
	}

	memalloc_nofs_restore(nofs_flag);

	/* send ioends that might require a transaction to the completion wq */
	if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN ||
	    (ioend->io_flags & IOMAP_F_SHARED))
		ioend->io_bio->bi_end_io = xfs_end_bio;
	return status;
}

/*
 * If the folio has delalloc blocks on it, the caller is asking us to punch them
 * out. If we don't, we can leave a stale delalloc mapping covered by a clean
 * page that needs to be dirtied again before the delalloc mapping can be
 * converted. This stale delalloc mapping can trip up a later direct I/O read
 * operation on the same region.
 *
 * We prevent this by truncating away the delalloc regions on the folio. Because
 * they are delalloc, we can do this without needing a transaction. Indeed - if
 * we get ENOSPC errors, we have to be able to do this truncation without a
 * transaction as there is no space left for block reservation (typically why
 * we see a ENOSPC in writeback).
 */
static void
xfs_discard_folio(
	struct folio		*folio,
	loff_t			pos)
{
	struct xfs_inode	*ip = XFS_I(folio->mapping->host);
	struct xfs_mount	*mp = ip->i_mount;
	int			error;

	if (xfs_is_shutdown(mp))
		return;

	xfs_alert_ratelimited(mp,
		"page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
			folio, ip->i_ino, pos);

	/*
	 * The end of the punch range is always the offset of the first
	 * byte of the next folio. Hence the end offset is only dependent on the
	 * folio itself and not the start offset that is passed in.
	 */
	error = xfs_bmap_punch_delalloc_range(ip, pos,
				folio_pos(folio) + folio_size(folio));

	if (error && !xfs_is_shutdown(mp))
		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
}

static const struct iomap_writeback_ops xfs_writeback_ops = {
	.map_blocks		= xfs_map_blocks,
	.prepare_ioend		= xfs_prepare_ioend,
	.discard_folio		= xfs_discard_folio,
};

STATIC int
xfs_vm_writepages(
	struct address_space	*mapping,
	struct writeback_control *wbc)
{
	struct xfs_writepage_ctx wpc = { };

	/*
	 * Writing back data in a transaction context can result in recursive
	 * transactions. This is bad, so issue a warning and get out of here.
	 */
	if (WARN_ON_ONCE(current->journal_info))
		return 0;

	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
}

STATIC int
xfs_dax_writepages(
	struct address_space	*mapping,
	struct writeback_control *wbc)
{
	struct xfs_inode	*ip = XFS_I(mapping->host);

	xfs_iflags_clear(ip, XFS_ITRUNCATED);
	return dax_writeback_mapping_range(mapping,
			xfs_inode_buftarg(ip)->bt_daxdev, wbc);
}

STATIC sector_t
xfs_vm_bmap(
	struct address_space	*mapping,
	sector_t		block)
{
	struct xfs_inode	*ip = XFS_I(mapping->host);

	trace_xfs_vm_bmap(ip);

	/*
	 * The swap code (ab-)uses ->bmap to get a block mapping and then
	 * bypasses the file system for actual I/O.  We really can't allow
	 * that on reflinks inodes, so we have to skip out here.  And yes,
	 * 0 is the magic code for a bmap error.
	 *
	 * Since we don't pass back blockdev info, we can't return bmap
	 * information for rt files either.
	 */
	if (xfs_is_cow_inode(ip) || XFS_IS_REALTIME_INODE(ip))
		return 0;
	return iomap_bmap(mapping, block, &xfs_read_iomap_ops);
}

STATIC int
xfs_vm_read_folio(
	struct file		*unused,
	struct folio		*folio)
{
	return iomap_read_folio(folio, &xfs_read_iomap_ops);
}

STATIC void
xfs_vm_readahead(
	struct readahead_control	*rac)
{
	iomap_readahead(rac, &xfs_read_iomap_ops);
}

static int
xfs_iomap_swapfile_activate(
	struct swap_info_struct		*sis,
	struct file			*swap_file,
	sector_t			*span)
{
	sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev;
	return iomap_swapfile_activate(sis, swap_file, span,
			&xfs_read_iomap_ops);
}

const struct address_space_operations xfs_address_space_operations = {
	.read_folio		= xfs_vm_read_folio,
	.readahead		= xfs_vm_readahead,
	.writepages		= xfs_vm_writepages,
	.dirty_folio		= iomap_dirty_folio,
	.release_folio		= iomap_release_folio,
	.invalidate_folio	= iomap_invalidate_folio,
	.bmap			= xfs_vm_bmap,
	.migrate_folio		= filemap_migrate_folio,
	.is_partially_uptodate  = iomap_is_partially_uptodate,
	.error_remove_folio	= generic_error_remove_folio,
	.swap_activate		= xfs_iomap_swapfile_activate,
};

const struct address_space_operations xfs_dax_aops = {
	.writepages		= xfs_dax_writepages,
	.dirty_folio		= noop_dirty_folio,
	.swap_activate		= xfs_iomap_swapfile_activate,
};