reflink.c 23.1 KB
Newer Older
1
2
// SPDX-License-Identifier: GPL-2.0

3
#include <linux/blkdev.h>
4
#include <linux/iversion.h>
5
#include "compression.h"
6
#include "ctree.h"
7
#include "delalloc-space.h"
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
#include "reflink.h"
#include "transaction.h"

#define BTRFS_MAX_DEDUPE_LEN	SZ_16M

static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
				     struct inode *inode,
				     u64 endoff,
				     const u64 destoff,
				     const u64 olen,
				     int no_time_update)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int ret;

	inode_inc_iversion(inode);
	if (!no_time_update)
		inode->i_mtime = inode->i_ctime = current_time(inode);
	/*
	 * We round up to the block size at eof when determining which
	 * extents to clone above, but shouldn't round up the file size.
	 */
	if (endoff > destoff + olen)
		endoff = destoff + olen;
	if (endoff > inode->i_size) {
		i_size_write(inode, endoff);
		btrfs_inode_safe_disk_i_size_write(inode, 0);
	}

	ret = btrfs_update_inode(trans, root, inode);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		btrfs_end_transaction(trans);
		goto out;
	}
	ret = btrfs_end_transaction(trans);
out:
	return ret;
}

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
static int copy_inline_to_page(struct inode *inode,
			       const u64 file_offset,
			       char *inline_data,
			       const u64 size,
			       const u64 datal,
			       const u8 comp_type)
{
	const u64 block_size = btrfs_inode_sectorsize(inode);
	const u64 range_end = file_offset + block_size - 1;
	const size_t inline_size = size - btrfs_file_extent_calc_inline_size(0);
	char *data_start = inline_data + btrfs_file_extent_calc_inline_size(0);
	struct extent_changeset *data_reserved = NULL;
	struct page *page = NULL;
	int ret;

	ASSERT(IS_ALIGNED(file_offset, block_size));

	/*
	 * We have flushed and locked the ranges of the source and destination
	 * inodes, we also have locked the inodes, so we are safe to do a
	 * reservation here. Also we must not do the reservation while holding
	 * a transaction open, otherwise we would deadlock.
	 */
	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, file_offset,
					   block_size);
	if (ret)
		goto out;

	page = find_or_create_page(inode->i_mapping, file_offset >> PAGE_SHIFT,
				   btrfs_alloc_write_mask(inode->i_mapping));
	if (!page) {
		ret = -ENOMEM;
		goto out_unlock;
	}

	set_page_extent_mapped(page);
	clear_extent_bit(&BTRFS_I(inode)->io_tree, file_offset, range_end,
			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
			 0, 0, NULL);
	ret = btrfs_set_extent_delalloc(inode, file_offset, range_end, 0, NULL);
	if (ret)
		goto out_unlock;

	if (comp_type == BTRFS_COMPRESS_NONE) {
		char *map;

		map = kmap(page);
		memcpy(map, data_start, datal);
		flush_dcache_page(page);
		kunmap(page);
	} else {
		ret = btrfs_decompress(comp_type, data_start, page, 0,
				       inline_size, datal);
		if (ret)
			goto out_unlock;
		flush_dcache_page(page);
	}

	/*
	 * If our inline data is smaller then the block/page size, then the
	 * remaining of the block/page is equivalent to zeroes. We had something
	 * like the following done:
	 *
	 * $ xfs_io -f -c "pwrite -S 0xab 0 500" file
	 * $ sync  # (or fsync)
	 * $ xfs_io -c "falloc 0 4K" file
	 * $ xfs_io -c "pwrite -S 0xcd 4K 4K"
	 *
	 * So what's in the range [500, 4095] corresponds to zeroes.
	 */
	if (datal < block_size) {
		char *map;

		map = kmap(page);
		memset(map + datal, 0, block_size - datal);
		flush_dcache_page(page);
		kunmap(page);
	}

	SetPageUptodate(page);
	ClearPageChecked(page);
	set_page_dirty(page);
out_unlock:
	if (page) {
		unlock_page(page);
		put_page(page);
	}
	if (ret)
		btrfs_delalloc_release_space(inode, data_reserved, file_offset,
					     block_size, true);
	btrfs_delalloc_release_extents(BTRFS_I(inode), block_size);
out:
	extent_changeset_free(data_reserved);

	return ret;
}

145
/*
146
147
148
 * Deal with cloning of inline extents. We try to copy the inline extent from
 * the source inode to destination inode when possible. When not possible we
 * copy the inline extent's data into the respective page of the inode.
149
150
151
152
153
154
155
 */
static int clone_copy_inline_extent(struct inode *dst,
				    struct btrfs_path *path,
				    struct btrfs_key *new_key,
				    const u64 drop_start,
				    const u64 datal,
				    const u64 size,
156
157
158
				    const u8 comp_type,
				    char *inline_data,
				    struct btrfs_trans_handle **trans_out)
159
160
161
162
163
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dst->i_sb);
	struct btrfs_root *root = BTRFS_I(dst)->root;
	const u64 aligned_end = ALIGN(new_key->offset + datal,
				      fs_info->sectorsize);
164
	struct btrfs_trans_handle *trans = NULL;
165
166
167
	int ret;
	struct btrfs_key key;

168
169
170
171
172
	if (new_key->offset > 0) {
		ret = copy_inline_to_page(dst, new_key->offset, inline_data,
					  size, datal, comp_type);
		goto out;
	}
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190

	key.objectid = btrfs_ino(BTRFS_I(dst));
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = 0;
	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0) {
		return ret;
	} else if (ret > 0) {
		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				return ret;
			else if (ret > 0)
				goto copy_inline_extent;
		}
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid == btrfs_ino(BTRFS_I(dst)) &&
		    key.type == BTRFS_EXTENT_DATA_KEY) {
191
192
193
194
			/*
			 * There's an implicit hole at file offset 0, copy the
			 * inline extent's data to the page.
			 */
195
			ASSERT(key.offset > 0);
196
197
198
199
			ret = copy_inline_to_page(dst, new_key->offset,
						  inline_data, size, datal,
						  comp_type);
			goto out;
200
201
202
203
204
205
206
		}
	} else if (i_size_read(dst) <= datal) {
		struct btrfs_file_extent_item *ei;

		ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
				    struct btrfs_file_extent_item);
		/*
207
208
209
		 * If it's an inline extent replace it with the source inline
		 * extent, otherwise copy the source inline extent data into
		 * the respective page at the destination inode.
210
211
212
213
214
		 */
		if (btrfs_file_extent_type(path->nodes[0], ei) ==
		    BTRFS_FILE_EXTENT_INLINE)
			goto copy_inline_extent;

215
216
217
		ret = copy_inline_to_page(dst, new_key->offset, inline_data,
					  size, datal, comp_type);
		goto out;
218
219
220
	}

copy_inline_extent:
221
	ret = 0;
222
223
224
225
226
227
	/*
	 * We have no extent items, or we have an extent at offset 0 which may
	 * or may not be inlined. All these cases are dealt the same way.
	 */
	if (i_size_read(dst) > datal) {
		/*
228
229
230
231
		 * At the destination offset 0 we have either a hole, a regular
		 * extent or an inline extent larger then the one we want to
		 * clone. Deal with all these cases by copying the inline extent
		 * data into the respective page at the destination inode.
232
		 */
233
234
235
		ret = copy_inline_to_page(dst, new_key->offset, inline_data,
					   size, datal, comp_type);
		goto out;
236
237
238
	}

	btrfs_release_path(path);
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
	/*
	 * If we end up here it means were copy the inline extent into a leaf
	 * of the destination inode. We know we will drop or adjust at most one
	 * extent item in the destination root.
	 *
	 * 1 unit - adjusting old extent (we may have to split it)
	 * 1 unit - add new extent
	 * 1 unit - inode update
	 */
	trans = btrfs_start_transaction(root, 3);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		trans = NULL;
		goto out;
	}
254
255
	ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1);
	if (ret)
256
		goto out;
257
258
	ret = btrfs_insert_empty_item(trans, root, path, new_key, size);
	if (ret)
259
		goto out;
260
261
262
263
264
265
266

	write_extent_buffer(path->nodes[0], inline_data,
			    btrfs_item_ptr_offset(path->nodes[0],
						  path->slots[0]),
			    size);
	inode_add_bytes(dst, datal);
	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags);
267
	ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end);
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
out:
	if (!ret && !trans) {
		/*
		 * No transaction here means we copied the inline extent into a
		 * page of the destination inode.
		 *
		 * 1 unit to update inode item
		 */
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			trans = NULL;
		}
	}
	if (ret && trans) {
		btrfs_abort_transaction(trans, ret);
		btrfs_end_transaction(trans);
	}
	if (!ret)
		*trans_out = trans;
288

289
	return ret;
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
}

/**
 * btrfs_clone() - clone a range from inode file to another
 *
 * @src: Inode to clone from
 * @inode: Inode to clone to
 * @off: Offset within source to start clone from
 * @olen: Original length, passed by user, of range to clone
 * @olen_aligned: Block-aligned value of olen
 * @destoff: Offset within @inode to start clone
 * @no_time_update: Whether to update mtime/ctime on the target inode
 */
static int btrfs_clone(struct inode *src, struct inode *inode,
		       const u64 off, const u64 olen, const u64 olen_aligned,
		       const u64 destoff, int no_time_update)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_path *path = NULL;
	struct extent_buffer *leaf;
	struct btrfs_trans_handle *trans;
	char *buf = NULL;
	struct btrfs_key key;
	u32 nritems;
	int slot;
	int ret;
	const u64 len = olen_aligned;
	u64 last_dest_end = destoff;

	ret = -ENOMEM;
	buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
	if (!buf)
		return ret;

	path = btrfs_alloc_path();
	if (!path) {
		kvfree(buf);
		return ret;
	}

	path->reada = READA_FORWARD;
	/* Clone data */
	key.objectid = btrfs_ino(BTRFS_I(src));
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = off;

	while (1) {
		u64 next_key_min_offset = key.offset + 1;
		struct btrfs_file_extent_item *extent;
		int type;
		u32 size;
		struct btrfs_key new_key;
		u64 disko = 0, diskl = 0;
		u64 datao = 0, datal = 0;
344
		u8 comp;
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
		u64 drop_start;

		/* Note the key will change type as we walk through the tree */
		path->leave_spinning = 1;
		ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path,
				0, 0);
		if (ret < 0)
			goto out;
		/*
		 * First search, if no extent item that starts at offset off was
		 * found but the previous item is an extent item, it's possible
		 * it might overlap our target range, therefore process it.
		 */
		if (key.offset == off && ret > 0 && path->slots[0] > 0) {
			btrfs_item_key_to_cpu(path->nodes[0], &key,
					      path->slots[0] - 1);
			if (key.type == BTRFS_EXTENT_DATA_KEY)
				path->slots[0]--;
		}

		nritems = btrfs_header_nritems(path->nodes[0]);
process_slot:
		if (path->slots[0] >= nritems) {
			ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
			if (ret < 0)
				goto out;
			if (ret > 0)
				break;
			nritems = btrfs_header_nritems(path->nodes[0]);
		}
		leaf = path->nodes[0];
		slot = path->slots[0];

		btrfs_item_key_to_cpu(leaf, &key, slot);
		if (key.type > BTRFS_EXTENT_DATA_KEY ||
		    key.objectid != btrfs_ino(BTRFS_I(src)))
			break;

		ASSERT(key.type == BTRFS_EXTENT_DATA_KEY);

		extent = btrfs_item_ptr(leaf, slot,
					struct btrfs_file_extent_item);
387
		comp = btrfs_file_extent_compression(leaf, extent);
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
		type = btrfs_file_extent_type(leaf, extent);
		if (type == BTRFS_FILE_EXTENT_REG ||
		    type == BTRFS_FILE_EXTENT_PREALLOC) {
			disko = btrfs_file_extent_disk_bytenr(leaf, extent);
			diskl = btrfs_file_extent_disk_num_bytes(leaf, extent);
			datao = btrfs_file_extent_offset(leaf, extent);
			datal = btrfs_file_extent_num_bytes(leaf, extent);
		} else if (type == BTRFS_FILE_EXTENT_INLINE) {
			/* Take upper bound, may be compressed */
			datal = btrfs_file_extent_ram_bytes(leaf, extent);
		}

		/*
		 * The first search might have left us at an extent item that
		 * ends before our target range's start, can happen if we have
		 * holes and NO_HOLES feature enabled.
		 */
		if (key.offset + datal <= off) {
			path->slots[0]++;
			goto process_slot;
		} else if (key.offset >= off + len) {
			break;
		}
		next_key_min_offset = key.offset + datal;
		size = btrfs_item_size_nr(leaf, slot);
		read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot),
				   size);

		btrfs_release_path(path);
		path->leave_spinning = 0;

		memcpy(&new_key, &key, sizeof(new_key));
		new_key.objectid = btrfs_ino(BTRFS_I(inode));
		if (off <= key.offset)
			new_key.offset = key.offset + destoff - off;
		else
			new_key.offset = destoff;

		/*
		 * Deal with a hole that doesn't have an extent item that
		 * represents it (NO_HOLES feature enabled).
		 * This hole is either in the middle of the cloning range or at
		 * the beginning (fully overlaps it or partially overlaps it).
		 */
		if (new_key.offset != last_dest_end)
			drop_start = last_dest_end;
		else
			drop_start = new_key.offset;

		if (type == BTRFS_FILE_EXTENT_REG ||
		    type == BTRFS_FILE_EXTENT_PREALLOC) {
			struct btrfs_clone_extent_info clone_info;

			/*
			 *    a  | --- range to clone ---|  b
			 * | ------------- extent ------------- |
			 */

			/* Subtract range b */
			if (key.offset + datal > off + len)
				datal = off + len - key.offset;

			/* Subtract range a */
			if (off > key.offset) {
				datao += off - key.offset;
				datal -= off - key.offset;
			}

			clone_info.disk_offset = disko;
			clone_info.disk_len = diskl;
			clone_info.data_offset = datao;
			clone_info.data_len = datal;
			clone_info.file_offset = new_key.offset;
			clone_info.extent_buf = buf;
			clone_info.item_size = size;
			ret = btrfs_punch_hole_range(inode, path, drop_start,
					new_key.offset + datal - 1, &clone_info,
					&trans);
			if (ret)
				goto out;
		} else if (type == BTRFS_FILE_EXTENT_INLINE) {
469
470
471
472
473
474
475
476
477
478
479
480
			/*
			 * Inline extents always have to start at file offset 0
			 * and can never be bigger then the sector size. We can
			 * never clone only parts of an inline extent, since all
			 * reflink operations must start at a sector size aligned
			 * offset, and the length must be aligned too or end at
			 * the i_size (which implies the whole inlined data).
			 */
			ASSERT(key.offset == 0);
			ASSERT(datal <= fs_info->sectorsize);
			if (key.offset != 0 || datal > fs_info->sectorsize)
				return -EUCLEAN;
481

482
483
484
485
			ret = clone_copy_inline_extent(inode, path, &new_key,
						       drop_start, datal, size,
						       comp, buf, &trans);
			if (ret)
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
				goto out;
		}

		btrfs_release_path(path);

		last_dest_end = ALIGN(new_key.offset + datal,
				      fs_info->sectorsize);
		ret = clone_finish_inode_update(trans, inode, last_dest_end,
						destoff, olen, no_time_update);
		if (ret)
			goto out;
		if (new_key.offset + datal >= destoff + len)
			break;

		btrfs_release_path(path);
		key.offset = next_key_min_offset;

		if (fatal_signal_pending(current)) {
			ret = -EINTR;
			goto out;
		}
	}
	ret = 0;

	if (last_dest_end < destoff + len) {
		/*
		 * We have an implicit hole that fully or partially overlaps our
		 * cloning range at its end. This means that we either have the
		 * NO_HOLES feature enabled or the implicit hole happened due to
		 * mixing buffered and direct IO writes against this file.
		 */
		btrfs_release_path(path);
		path->leave_spinning = 0;

		ret = btrfs_punch_hole_range(inode, path, last_dest_end,
				destoff + len - 1, NULL, &trans);
		if (ret)
			goto out;

		ret = clone_finish_inode_update(trans, inode, destoff + len,
						destoff, olen, no_time_update);
	}

out:
	btrfs_free_path(path);
	kvfree(buf);
	return ret;
}

static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
				       struct inode *inode2, u64 loff2, u64 len)
{
	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}

static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
				     struct inode *inode2, u64 loff2, u64 len)
{
	if (inode1 < inode2) {
		swap(inode1, inode2);
		swap(loff1, loff2);
	} else if (inode1 == inode2 && loff2 < loff1) {
		swap(loff1, loff2);
	}
	lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
	lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}

static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
				   struct inode *dst, u64 dst_loff)
{
	const u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
	int ret;

	/*
	 * Lock destination range to serialize with concurrent readpages() and
	 * source range to serialize with relocation.
	 */
	btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
	ret = btrfs_clone(src, dst, loff, len, ALIGN(len, bs), dst_loff, 1);
	btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);

	return ret;
}

static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
			     struct inode *dst, u64 dst_loff)
{
	int ret;
	u64 i, tail_len, chunk_count;
	struct btrfs_root *root_dst = BTRFS_I(dst)->root;

	spin_lock(&root_dst->root_item_lock);
	if (root_dst->send_in_progress) {
		btrfs_warn_rl(root_dst->fs_info,
"cannot deduplicate to root %llu while send operations are using it (%d in progress)",
			      root_dst->root_key.objectid,
			      root_dst->send_in_progress);
		spin_unlock(&root_dst->root_item_lock);
		return -EAGAIN;
	}
	root_dst->dedupe_in_progress++;
	spin_unlock(&root_dst->root_item_lock);

	tail_len = olen % BTRFS_MAX_DEDUPE_LEN;
	chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN);

	for (i = 0; i < chunk_count; i++) {
		ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
					      dst, dst_loff);
		if (ret)
			goto out;

		loff += BTRFS_MAX_DEDUPE_LEN;
		dst_loff += BTRFS_MAX_DEDUPE_LEN;
	}

	if (tail_len > 0)
		ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff);
out:
	spin_lock(&root_dst->root_item_lock);
	root_dst->dedupe_in_progress--;
	spin_unlock(&root_dst->root_item_lock);

	return ret;
}

static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
					u64 off, u64 olen, u64 destoff)
{
	struct inode *inode = file_inode(file);
	struct inode *src = file_inode(file_src);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	int ret;
621
	int wb_ret;
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
	u64 len = olen;
	u64 bs = fs_info->sb->s_blocksize;

	/*
	 * VFS's generic_remap_file_range_prep() protects us from cloning the
	 * eof block into the middle of a file, which would result in corruption
	 * if the file size is not blocksize aligned. So we don't need to check
	 * for that case here.
	 */
	if (off + len == src->i_size)
		len = ALIGN(src->i_size, bs) - off;

	if (destoff > inode->i_size) {
		const u64 wb_start = ALIGN_DOWN(inode->i_size, bs);

		ret = btrfs_cont_expand(inode, inode->i_size, destoff);
		if (ret)
			return ret;
		/*
		 * We may have truncated the last block if the inode's size is
		 * not sector size aligned, so we need to wait for writeback to
		 * complete before proceeding further, otherwise we can race
		 * with cloning and attempt to increment a reference to an
		 * extent that no longer exists (writeback completed right after
		 * we found the previous extent covering eof and before we
		 * attempted to increment its reference count).
		 */
		ret = btrfs_wait_ordered_range(inode, wb_start,
					       destoff - wb_start);
		if (ret)
			return ret;
	}

	/*
	 * Lock destination range to serialize with concurrent readpages() and
	 * source range to serialize with relocation.
	 */
	btrfs_double_extent_lock(src, off, inode, destoff, len);
	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
	btrfs_double_extent_unlock(src, off, inode, destoff, len);
662
663
664
665
666
667
668
669

	/*
	 * We may have copied an inline extent into a page of the destination
	 * range, so wait for writeback to complete before truncating pages
	 * from the page cache. This is a rare case.
	 */
	wb_ret = btrfs_wait_ordered_range(inode, destoff, len);
	ret = ret ? ret : wb_ret;
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
	/*
	 * Truncate page cache pages so that future reads will see the cloned
	 * data immediately and not the previous data.
	 */
	truncate_inode_pages_range(&inode->i_data,
				round_down(destoff, PAGE_SIZE),
				round_up(destoff + len, PAGE_SIZE) - 1);

	return ret;
}

static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
				       struct file *file_out, loff_t pos_out,
				       loff_t *len, unsigned int remap_flags)
{
	struct inode *inode_in = file_inode(file_in);
	struct inode *inode_out = file_inode(file_out);
	u64 bs = BTRFS_I(inode_out)->root->fs_info->sb->s_blocksize;
	bool same_inode = inode_out == inode_in;
	u64 wb_len;
	int ret;

	if (!(remap_flags & REMAP_FILE_DEDUP)) {
		struct btrfs_root *root_out = BTRFS_I(inode_out)->root;

		if (btrfs_root_readonly(root_out))
			return -EROFS;

		if (file_in->f_path.mnt != file_out->f_path.mnt ||
		    inode_in->i_sb != inode_out->i_sb)
			return -EXDEV;
	}

	/* Don't make the dst file partly checksummed */
	if ((BTRFS_I(inode_in)->flags & BTRFS_INODE_NODATASUM) !=
	    (BTRFS_I(inode_out)->flags & BTRFS_INODE_NODATASUM)) {
		return -EINVAL;
	}

	/*
	 * Now that the inodes are locked, we need to start writeback ourselves
	 * and can not rely on the writeback from the VFS's generic helper
	 * generic_remap_file_range_prep() because:
	 *
	 * 1) For compression we must call filemap_fdatawrite_range() range
	 *    twice (btrfs_fdatawrite_range() does it for us), and the generic
	 *    helper only calls it once;
	 *
	 * 2) filemap_fdatawrite_range(), called by the generic helper only
	 *    waits for the writeback to complete, i.e. for IO to be done, and
	 *    not for the ordered extents to complete. We need to wait for them
	 *    to complete so that new file extent items are in the fs tree.
	 */
	if (*len == 0 && !(remap_flags & REMAP_FILE_DEDUP))
		wb_len = ALIGN(inode_in->i_size, bs) - ALIGN_DOWN(pos_in, bs);
	else
		wb_len = ALIGN(*len, bs);

	/*
	 * Since we don't lock ranges, wait for ongoing lockless dio writes (as
	 * any in progress could create its ordered extents after we wait for
	 * existing ordered extents below).
	 */
	inode_dio_wait(inode_in);
	if (!same_inode)
		inode_dio_wait(inode_out);

	/*
	 * Workaround to make sure NOCOW buffered write reach disk as NOCOW.
	 *
	 * Btrfs' back references do not have a block level granularity, they
	 * work at the whole extent level.
	 * NOCOW buffered write without data space reserved may not be able
	 * to fall back to CoW due to lack of data space, thus could cause
	 * data loss.
	 *
	 * Here we take a shortcut by flushing the whole inode, so that all
	 * nocow write should reach disk as nocow before we increase the
	 * reference of the extent. We could do better by only flushing NOCOW
	 * data, but that needs extra accounting.
	 *
	 * Also we don't need to check ASYNC_EXTENT, as async extent will be
	 * CoWed anyway, not affecting nocow part.
	 */
	ret = filemap_flush(inode_in->i_mapping);
	if (ret < 0)
		return ret;

	ret = btrfs_wait_ordered_range(inode_in, ALIGN_DOWN(pos_in, bs),
				       wb_len);
	if (ret < 0)
		return ret;
	ret = btrfs_wait_ordered_range(inode_out, ALIGN_DOWN(pos_out, bs),
				       wb_len);
	if (ret < 0)
		return ret;

	return generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
					    len, remap_flags);
}

loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
		struct file *dst_file, loff_t destoff, loff_t len,
		unsigned int remap_flags)
{
	struct inode *src_inode = file_inode(src_file);
	struct inode *dst_inode = file_inode(dst_file);
	bool same_inode = dst_inode == src_inode;
	int ret;

	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
		return -EINVAL;

	if (same_inode)
		inode_lock(src_inode);
	else
		lock_two_nondirectories(src_inode, dst_inode);

	ret = btrfs_remap_file_range_prep(src_file, off, dst_file, destoff,
					  &len, remap_flags);
	if (ret < 0 || len == 0)
		goto out_unlock;

	if (remap_flags & REMAP_FILE_DEDUP)
		ret = btrfs_extent_same(src_inode, off, len, dst_inode, destoff);
	else
		ret = btrfs_clone_files(dst_file, src_file, off, len, destoff);

out_unlock:
	if (same_inode)
		inode_unlock(src_inode);
	else
		unlock_two_nondirectories(src_inode, dst_inode);

	return ret < 0 ? ret : len;
}