free-space-tree.c 39.8 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2 3 4 5 6
/*
 * Copyright (C) 2015 Facebook.  All rights reserved.
 */

#include <linux/kernel.h>
7
#include <linux/sched/mm.h>
8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27
#include "ctree.h"
#include "disk-io.h"
#include "locking.h"
#include "free-space-tree.h"
#include "transaction.h"

static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
					struct btrfs_block_group_cache *block_group,
					struct btrfs_path *path);

void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
{
	u32 bitmap_range;
	size_t bitmap_size;
	u64 num_bitmaps, total_bitmap_size;

	/*
	 * We convert to bitmaps when the disk space required for using extents
	 * exceeds that required for using bitmaps.
	 */
28
	bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
	num_bitmaps = div_u64(cache->key.offset + bitmap_range - 1,
			      bitmap_range);
	bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE;
	total_bitmap_size = num_bitmaps * bitmap_size;
	cache->bitmap_high_thresh = div_u64(total_bitmap_size,
					    sizeof(struct btrfs_item));

	/*
	 * We allow for a small buffer between the high threshold and low
	 * threshold to avoid thrashing back and forth between the two formats.
	 */
	if (cache->bitmap_high_thresh > 100)
		cache->bitmap_low_thresh = cache->bitmap_high_thresh - 100;
	else
		cache->bitmap_low_thresh = 0;
}

static int add_new_free_space_info(struct btrfs_trans_handle *trans,
				   struct btrfs_block_group_cache *block_group,
				   struct btrfs_path *path)
{
50
	struct btrfs_root *root = trans->fs_info->free_space_root;
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
	struct btrfs_free_space_info *info;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	int ret;

	key.objectid = block_group->key.objectid;
	key.type = BTRFS_FREE_SPACE_INFO_KEY;
	key.offset = block_group->key.offset;

	ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info));
	if (ret)
		goto out;

	leaf = path->nodes[0];
	info = btrfs_item_ptr(leaf, path->slots[0],
			      struct btrfs_free_space_info);
	btrfs_set_free_space_extent_count(leaf, info, 0);
	btrfs_set_free_space_flags(leaf, info, 0);
	btrfs_mark_buffer_dirty(leaf);

	ret = 0;
out:
	btrfs_release_path(path);
	return ret;
}

77 78 79 80 81
EXPORT_FOR_TESTS
struct btrfs_free_space_info *search_free_space_info(
		struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info,
		struct btrfs_block_group_cache *block_group,
		struct btrfs_path *path, int cow)
82 83 84 85 86 87 88 89 90 91 92 93 94
{
	struct btrfs_root *root = fs_info->free_space_root;
	struct btrfs_key key;
	int ret;

	key.objectid = block_group->key.objectid;
	key.type = BTRFS_FREE_SPACE_INFO_KEY;
	key.offset = block_group->key.offset;

	ret = btrfs_search_slot(trans, root, &key, path, 0, cow);
	if (ret < 0)
		return ERR_PTR(ret);
	if (ret != 0) {
95
		btrfs_warn(fs_info, "missing free space info for %llu",
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
			   block_group->key.objectid);
		ASSERT(0);
		return ERR_PTR(-ENOENT);
	}

	return btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_free_space_info);
}

/*
 * btrfs_search_slot() but we're looking for the greatest key less than the
 * passed key.
 */
static int btrfs_search_prev_slot(struct btrfs_trans_handle *trans,
				  struct btrfs_root *root,
				  struct btrfs_key *key, struct btrfs_path *p,
				  int ins_len, int cow)
{
	int ret;

	ret = btrfs_search_slot(trans, root, key, p, ins_len, cow);
	if (ret < 0)
		return ret;

	if (ret == 0) {
		ASSERT(0);
		return -EIO;
	}

	if (p->slots[0] == 0) {
		ASSERT(0);
		return -EIO;
	}
	p->slots[0]--;

	return 0;
}

static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
{
	return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE);
}

139
static unsigned long *alloc_bitmap(u32 bitmap_size)
140
{
141
	unsigned long *ret;
142
	unsigned int nofs_flag;
143
	u32 bitmap_rounded_size = round_up(bitmap_size, sizeof(unsigned long));
144 145

	/*
146 147 148 149 150 151
	 * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse
	 * into the filesystem as the free space bitmap can be modified in the
	 * critical section of a transaction commit.
	 *
	 * TODO: push the memalloc_nofs_{save,restore}() to the caller where we
	 * know that recursion is unsafe.
152
	 */
153
	nofs_flag = memalloc_nofs_save();
154
	ret = kvzalloc(bitmap_rounded_size, GFP_KERNEL);
155 156
	memalloc_nofs_restore(nofs_flag);
	return ret;
157 158
}

159
static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
160
{
161
	u8 *p = ((u8 *)map) + BIT_BYTE(start);
162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
	const unsigned int size = start + len;
	int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
	u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);

	while (len - bits_to_set >= 0) {
		*p |= mask_to_set;
		len -= bits_to_set;
		bits_to_set = BITS_PER_BYTE;
		mask_to_set = ~0;
		p++;
	}
	if (len) {
		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
		*p |= mask_to_set;
	}
}

179
EXPORT_FOR_TESTS
180 181 182 183
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
				  struct btrfs_block_group_cache *block_group,
				  struct btrfs_path *path)
{
184
	struct btrfs_fs_info *fs_info = trans->fs_info;
185 186 187 188
	struct btrfs_root *root = fs_info->free_space_root;
	struct btrfs_free_space_info *info;
	struct btrfs_key key, found_key;
	struct extent_buffer *leaf;
189 190
	unsigned long *bitmap;
	char *bitmap_cursor;
191 192 193 194 195 196 197 198
	u64 start, end;
	u64 bitmap_range, i;
	u32 bitmap_size, flags, expected_extent_count;
	u32 extent_count = 0;
	int done = 0, nr;
	int ret;

	bitmap_size = free_space_bitmap_size(block_group->key.offset,
199
					     fs_info->sectorsize);
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
	bitmap = alloc_bitmap(bitmap_size);
	if (!bitmap) {
		ret = -ENOMEM;
		goto out;
	}

	start = block_group->key.objectid;
	end = block_group->key.objectid + block_group->key.offset;

	key.objectid = end - 1;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	while (!done) {
		ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
		if (ret)
			goto out;

		leaf = path->nodes[0];
		nr = 0;
		path->slots[0]++;
		while (path->slots[0] > 0) {
			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);

			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
				ASSERT(found_key.objectid == block_group->key.objectid);
				ASSERT(found_key.offset == block_group->key.offset);
				done = 1;
				break;
			} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) {
				u64 first, last;

				ASSERT(found_key.objectid >= start);
				ASSERT(found_key.objectid < end);
				ASSERT(found_key.objectid + found_key.offset <= end);

				first = div_u64(found_key.objectid - start,
237
						fs_info->sectorsize);
238
				last = div_u64(found_key.objectid + found_key.offset - start,
239
					       fs_info->sectorsize);
240
				le_bitmap_set(bitmap, first, last - first);
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

				extent_count++;
				nr++;
				path->slots[0]--;
			} else {
				ASSERT(0);
			}
		}

		ret = btrfs_del_items(trans, root, path, path->slots[0], nr);
		if (ret)
			goto out;
		btrfs_release_path(path);
	}

	info = search_free_space_info(trans, fs_info, block_group, path, 1);
	if (IS_ERR(info)) {
		ret = PTR_ERR(info);
		goto out;
	}
	leaf = path->nodes[0];
	flags = btrfs_free_space_flags(leaf, info);
	flags |= BTRFS_FREE_SPACE_USING_BITMAPS;
	btrfs_set_free_space_flags(leaf, info, flags);
	expected_extent_count = btrfs_free_space_extent_count(leaf, info);
	btrfs_mark_buffer_dirty(leaf);
	btrfs_release_path(path);

	if (extent_count != expected_extent_count) {
270 271
		btrfs_err(fs_info,
			  "incorrect extent count for %llu; counted %u, expected %u",
272 273 274 275 276 277 278
			  block_group->key.objectid, extent_count,
			  expected_extent_count);
		ASSERT(0);
		ret = -EIO;
		goto out;
	}

279
	bitmap_cursor = (char *)bitmap;
280
	bitmap_range = fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
281 282 283 284 285 286 287 288
	i = start;
	while (i < end) {
		unsigned long ptr;
		u64 extent_size;
		u32 data_size;

		extent_size = min(end - i, bitmap_range);
		data_size = free_space_bitmap_size(extent_size,
289
						   fs_info->sectorsize);
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312

		key.objectid = i;
		key.type = BTRFS_FREE_SPACE_BITMAP_KEY;
		key.offset = extent_size;

		ret = btrfs_insert_empty_item(trans, root, path, &key,
					      data_size);
		if (ret)
			goto out;

		leaf = path->nodes[0];
		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
		write_extent_buffer(leaf, bitmap_cursor, ptr,
				    data_size);
		btrfs_mark_buffer_dirty(leaf);
		btrfs_release_path(path);

		i += extent_size;
		bitmap_cursor += data_size;
	}

	ret = 0;
out:
313
	kvfree(bitmap);
314
	if (ret)
315
		btrfs_abort_transaction(trans, ret);
316 317 318
	return ret;
}

319
EXPORT_FOR_TESTS
320 321 322 323
int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
				  struct btrfs_block_group_cache *block_group,
				  struct btrfs_path *path)
{
324
	struct btrfs_fs_info *fs_info = trans->fs_info;
325 326 327 328
	struct btrfs_root *root = fs_info->free_space_root;
	struct btrfs_free_space_info *info;
	struct btrfs_key key, found_key;
	struct extent_buffer *leaf;
329
	unsigned long *bitmap;
330 331
	u64 start, end;
	u32 bitmap_size, flags, expected_extent_count;
332
	unsigned long nrbits, start_bit, end_bit;
333 334 335 336 337
	u32 extent_count = 0;
	int done = 0, nr;
	int ret;

	bitmap_size = free_space_bitmap_size(block_group->key.offset,
338
					     fs_info->sectorsize);
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
	bitmap = alloc_bitmap(bitmap_size);
	if (!bitmap) {
		ret = -ENOMEM;
		goto out;
	}

	start = block_group->key.objectid;
	end = block_group->key.objectid + block_group->key.offset;

	key.objectid = end - 1;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	while (!done) {
		ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
		if (ret)
			goto out;

		leaf = path->nodes[0];
		nr = 0;
		path->slots[0]++;
		while (path->slots[0] > 0) {
			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);

			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
				ASSERT(found_key.objectid == block_group->key.objectid);
				ASSERT(found_key.offset == block_group->key.offset);
				done = 1;
				break;
			} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
				unsigned long ptr;
370
				char *bitmap_cursor;
371 372 373 374 375 376 377
				u32 bitmap_pos, data_size;

				ASSERT(found_key.objectid >= start);
				ASSERT(found_key.objectid < end);
				ASSERT(found_key.objectid + found_key.offset <= end);

				bitmap_pos = div_u64(found_key.objectid - start,
378
						     fs_info->sectorsize *
379
						     BITS_PER_BYTE);
380
				bitmap_cursor = ((char *)bitmap) + bitmap_pos;
381
				data_size = free_space_bitmap_size(found_key.offset,
382
								   fs_info->sectorsize);
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

				ptr = btrfs_item_ptr_offset(leaf, path->slots[0] - 1);
				read_extent_buffer(leaf, bitmap_cursor, ptr,
						   data_size);

				nr++;
				path->slots[0]--;
			} else {
				ASSERT(0);
			}
		}

		ret = btrfs_del_items(trans, root, path, path->slots[0], nr);
		if (ret)
			goto out;
		btrfs_release_path(path);
	}

	info = search_free_space_info(trans, fs_info, block_group, path, 1);
	if (IS_ERR(info)) {
		ret = PTR_ERR(info);
		goto out;
	}
	leaf = path->nodes[0];
	flags = btrfs_free_space_flags(leaf, info);
	flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS;
	btrfs_set_free_space_flags(leaf, info, flags);
	expected_extent_count = btrfs_free_space_extent_count(leaf, info);
	btrfs_mark_buffer_dirty(leaf);
	btrfs_release_path(path);

414 415 416 417 418 419 420 421
	nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize);
	start_bit = find_next_bit_le(bitmap, nrbits, 0);

	while (start_bit < nrbits) {
		end_bit = find_next_zero_bit_le(bitmap, nrbits, start_bit);
		ASSERT(start_bit < end_bit);

		key.objectid = start + start_bit * block_group->fs_info->sectorsize;
422
		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
423
		key.offset = (end_bit - start_bit) * block_group->fs_info->sectorsize;
424 425 426 427 428 429 430

		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
		if (ret)
			goto out;
		btrfs_release_path(path);

		extent_count++;
431 432

		start_bit = find_next_bit_le(bitmap, nrbits, end_bit);
433 434 435
	}

	if (extent_count != expected_extent_count) {
436 437
		btrfs_err(fs_info,
			  "incorrect extent count for %llu; counted %u, expected %u",
438 439 440 441 442 443 444 445 446
			  block_group->key.objectid, extent_count,
			  expected_extent_count);
		ASSERT(0);
		ret = -EIO;
		goto out;
	}

	ret = 0;
out:
447
	kvfree(bitmap);
448
	if (ret)
449
		btrfs_abort_transaction(trans, ret);
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465
	return ret;
}

static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
					  struct btrfs_block_group_cache *block_group,
					  struct btrfs_path *path,
					  int new_extents)
{
	struct btrfs_free_space_info *info;
	u32 flags;
	u32 extent_count;
	int ret = 0;

	if (new_extents == 0)
		return 0;

466 467
	info = search_free_space_info(trans, trans->fs_info, block_group, path,
				      1);
468 469 470 471 472 473 474 475 476 477 478 479 480 481
	if (IS_ERR(info)) {
		ret = PTR_ERR(info);
		goto out;
	}
	flags = btrfs_free_space_flags(path->nodes[0], info);
	extent_count = btrfs_free_space_extent_count(path->nodes[0], info);

	extent_count += new_extents;
	btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count);
	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_release_path(path);

	if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
	    extent_count > block_group->bitmap_high_thresh) {
482
		ret = convert_free_space_to_bitmaps(trans, block_group, path);
483 484
	} else if ((flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
		   extent_count < block_group->bitmap_low_thresh) {
485
		ret = convert_free_space_to_extents(trans, block_group, path);
486 487 488 489 490 491
	}

out:
	return ret;
}

492
EXPORT_FOR_TESTS
493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509
int free_space_test_bit(struct btrfs_block_group_cache *block_group,
			struct btrfs_path *path, u64 offset)
{
	struct extent_buffer *leaf;
	struct btrfs_key key;
	u64 found_start, found_end;
	unsigned long ptr, i;

	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
	ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);

	found_start = key.objectid;
	found_end = key.objectid + key.offset;
	ASSERT(offset >= found_start && offset < found_end);

	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
510 511
	i = div_u64(offset - found_start,
		    block_group->fs_info->sectorsize);
512 513 514 515 516 517 518
	return !!extent_buffer_test_bit(leaf, ptr, i);
}

static void free_space_set_bits(struct btrfs_block_group_cache *block_group,
				struct btrfs_path *path, u64 *start, u64 *size,
				int bit)
{
519
	struct btrfs_fs_info *fs_info = block_group->fs_info;
520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538
	struct extent_buffer *leaf;
	struct btrfs_key key;
	u64 end = *start + *size;
	u64 found_start, found_end;
	unsigned long ptr, first, last;

	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
	ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);

	found_start = key.objectid;
	found_end = key.objectid + key.offset;
	ASSERT(*start >= found_start && *start < found_end);
	ASSERT(end > found_start);

	if (end > found_end)
		end = found_end;

	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
539 540
	first = div_u64(*start - found_start, fs_info->sectorsize);
	last = div_u64(end - found_start, fs_info->sectorsize);
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
	if (bit)
		extent_buffer_bitmap_set(leaf, ptr, first, last - first);
	else
		extent_buffer_bitmap_clear(leaf, ptr, first, last - first);
	btrfs_mark_buffer_dirty(leaf);

	*size -= end - *start;
	*start = end;
}

/*
 * We can't use btrfs_next_item() in modify_free_space_bitmap() because
 * btrfs_next_leaf() doesn't get the path for writing. We can forgo the fancy
 * tree walking in btrfs_next_leaf() anyways because we know exactly what we're
 * looking for.
 */
static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
				  struct btrfs_root *root, struct btrfs_path *p)
{
	struct btrfs_key key;

	if (p->slots[0] + 1 < btrfs_header_nritems(p->nodes[0])) {
		p->slots[0]++;
		return 0;
	}

	btrfs_item_key_to_cpu(p->nodes[0], &key, p->slots[0]);
	btrfs_release_path(p);

	key.objectid += key.offset;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	return btrfs_search_prev_slot(trans, root, &key, p, 0, 1);
}

/*
 * If remove is 1, then we are removing free space, thus clearing bits in the
 * bitmap. If remove is 0, then we are adding free space, thus setting bits in
 * the bitmap.
 */
static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
				    struct btrfs_block_group_cache *block_group,
				    struct btrfs_path *path,
				    u64 start, u64 size, int remove)
{
587
	struct btrfs_root *root = block_group->fs_info->free_space_root;
588 589 590 591 592 593 594 595 596 597 598 599
	struct btrfs_key key;
	u64 end = start + size;
	u64 cur_start, cur_size;
	int prev_bit, next_bit;
	int new_extents;
	int ret;

	/*
	 * Read the bit for the block immediately before the extent of space if
	 * that block is within the block group.
	 */
	if (start > block_group->key.objectid) {
600
		u64 prev_block = start - block_group->fs_info->sectorsize;
601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687

		key.objectid = prev_block;
		key.type = (u8)-1;
		key.offset = (u64)-1;

		ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1);
		if (ret)
			goto out;

		prev_bit = free_space_test_bit(block_group, path, prev_block);

		/* The previous block may have been in the previous bitmap. */
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (start >= key.objectid + key.offset) {
			ret = free_space_next_bitmap(trans, root, path);
			if (ret)
				goto out;
		}
	} else {
		key.objectid = start;
		key.type = (u8)-1;
		key.offset = (u64)-1;

		ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1);
		if (ret)
			goto out;

		prev_bit = -1;
	}

	/*
	 * Iterate over all of the bitmaps overlapped by the extent of space,
	 * clearing/setting bits as required.
	 */
	cur_start = start;
	cur_size = size;
	while (1) {
		free_space_set_bits(block_group, path, &cur_start, &cur_size,
				    !remove);
		if (cur_size == 0)
			break;
		ret = free_space_next_bitmap(trans, root, path);
		if (ret)
			goto out;
	}

	/*
	 * Read the bit for the block immediately after the extent of space if
	 * that block is within the block group.
	 */
	if (end < block_group->key.objectid + block_group->key.offset) {
		/* The next block may be in the next bitmap. */
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (end >= key.objectid + key.offset) {
			ret = free_space_next_bitmap(trans, root, path);
			if (ret)
				goto out;
		}

		next_bit = free_space_test_bit(block_group, path, end);
	} else {
		next_bit = -1;
	}

	if (remove) {
		new_extents = -1;
		if (prev_bit == 1) {
			/* Leftover on the left. */
			new_extents++;
		}
		if (next_bit == 1) {
			/* Leftover on the right. */
			new_extents++;
		}
	} else {
		new_extents = 1;
		if (prev_bit == 1) {
			/* Merging with neighbor on the left. */
			new_extents--;
		}
		if (next_bit == 1) {
			/* Merging with neighbor on the right. */
			new_extents--;
		}
	}

	btrfs_release_path(path);
688
	ret = update_free_space_extent_count(trans, block_group, path,
689 690 691 692 693 694 695 696 697 698 699
					     new_extents);

out:
	return ret;
}

static int remove_free_space_extent(struct btrfs_trans_handle *trans,
				    struct btrfs_block_group_cache *block_group,
				    struct btrfs_path *path,
				    u64 start, u64 size)
{
700
	struct btrfs_root *root = trans->fs_info->free_space_root;
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
	struct btrfs_key key;
	u64 found_start, found_end;
	u64 end = start + size;
	int new_extents = -1;
	int ret;

	key.objectid = start;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
	if (ret)
		goto out;

	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY);

	found_start = key.objectid;
	found_end = key.objectid + key.offset;
	ASSERT(start >= found_start && end <= found_end);

	/*
	 * Okay, now that we've found the free space extent which contains the
	 * free space that we are removing, there are four cases:
	 *
	 * 1. We're using the whole extent: delete the key we found and
	 * decrement the free space extent count.
	 * 2. We are using part of the extent starting at the beginning: delete
	 * the key we found and insert a new key representing the leftover at
	 * the end. There is no net change in the number of extents.
	 * 3. We are using part of the extent ending at the end: delete the key
	 * we found and insert a new key representing the leftover at the
	 * beginning. There is no net change in the number of extents.
	 * 4. We are using part of the extent in the middle: delete the key we
	 * found and insert two new keys representing the leftovers on each
	 * side. Where we used to have one extent, we now have two, so increment
	 * the extent count. We may need to convert the block group to bitmaps
	 * as a result.
	 */

	/* Delete the existing key (cases 1-4). */
	ret = btrfs_del_item(trans, root, path);
	if (ret)
		goto out;

	/* Add a key for leftovers at the beginning (cases 3 and 4). */
	if (start > found_start) {
		key.objectid = found_start;
		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
		key.offset = start - found_start;

		btrfs_release_path(path);
		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
		if (ret)
			goto out;
		new_extents++;
	}

	/* Add a key for leftovers at the end (cases 2 and 4). */
	if (end < found_end) {
		key.objectid = end;
		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
		key.offset = found_end - end;

		btrfs_release_path(path);
		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
		if (ret)
			goto out;
		new_extents++;
	}

	btrfs_release_path(path);
774
	ret = update_free_space_extent_count(trans, block_group, path,
775 776 777 778 779 780
					     new_extents);

out:
	return ret;
}

781
EXPORT_FOR_TESTS
782 783 784 785 786 787 788 789 790
int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
				  struct btrfs_block_group_cache *block_group,
				  struct btrfs_path *path, u64 start, u64 size)
{
	struct btrfs_free_space_info *info;
	u32 flags;
	int ret;

	if (block_group->needs_free_space) {
791
		ret = __add_block_group_free_space(trans, block_group, path);
792 793 794 795
		if (ret)
			return ret;
	}

796 797
	info = search_free_space_info(NULL, trans->fs_info, block_group, path,
				      0);
798 799 800 801 802 803
	if (IS_ERR(info))
		return PTR_ERR(info);
	flags = btrfs_free_space_flags(path->nodes[0], info);
	btrfs_release_path(path);

	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
804 805
		return modify_free_space_bitmap(trans, block_group, path,
						start, size, 1);
806
	} else {
807 808
		return remove_free_space_extent(trans, block_group, path,
						start, size);
809 810 811 812 813 814 815 816 817 818
	}
}

int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
				u64 start, u64 size)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_path *path;
	int ret;

819
	if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
820 821 822 823 824 825 826 827
		return 0;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

828
	block_group = btrfs_lookup_block_group(trans->fs_info, start);
829 830 831 832 833 834 835
	if (!block_group) {
		ASSERT(0);
		ret = -ENOENT;
		goto out;
	}

	mutex_lock(&block_group->free_space_lock);
836 837
	ret = __remove_from_free_space_tree(trans, block_group, path, start,
					    size);
838 839 840 841 842 843
	mutex_unlock(&block_group->free_space_lock);

	btrfs_put_block_group(block_group);
out:
	btrfs_free_path(path);
	if (ret)
844
		btrfs_abort_transaction(trans, ret);
845 846 847 848 849 850 851 852
	return ret;
}

static int add_free_space_extent(struct btrfs_trans_handle *trans,
				 struct btrfs_block_group_cache *block_group,
				 struct btrfs_path *path,
				 u64 start, u64 size)
{
853
	struct btrfs_root *root = trans->fs_info->free_space_root;
854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967
	struct btrfs_key key, new_key;
	u64 found_start, found_end;
	u64 end = start + size;
	int new_extents = 1;
	int ret;

	/*
	 * We are adding a new extent of free space, but we need to merge
	 * extents. There are four cases here:
	 *
	 * 1. The new extent does not have any immediate neighbors to merge
	 * with: add the new key and increment the free space extent count. We
	 * may need to convert the block group to bitmaps as a result.
	 * 2. The new extent has an immediate neighbor before it: remove the
	 * previous key and insert a new key combining both of them. There is no
	 * net change in the number of extents.
	 * 3. The new extent has an immediate neighbor after it: remove the next
	 * key and insert a new key combining both of them. There is no net
	 * change in the number of extents.
	 * 4. The new extent has immediate neighbors on both sides: remove both
	 * of the keys and insert a new key combining all of them. Where we used
	 * to have two extents, we now have one, so decrement the extent count.
	 */

	new_key.objectid = start;
	new_key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
	new_key.offset = size;

	/* Search for a neighbor on the left. */
	if (start == block_group->key.objectid)
		goto right;
	key.objectid = start - 1;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
	if (ret)
		goto out;

	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) {
		ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY);
		btrfs_release_path(path);
		goto right;
	}

	found_start = key.objectid;
	found_end = key.objectid + key.offset;
	ASSERT(found_start >= block_group->key.objectid &&
	       found_end > block_group->key.objectid);
	ASSERT(found_start < start && found_end <= start);

	/*
	 * Delete the neighbor on the left and absorb it into the new key (cases
	 * 2 and 4).
	 */
	if (found_end == start) {
		ret = btrfs_del_item(trans, root, path);
		if (ret)
			goto out;
		new_key.objectid = found_start;
		new_key.offset += key.offset;
		new_extents--;
	}
	btrfs_release_path(path);

right:
	/* Search for a neighbor on the right. */
	if (end == block_group->key.objectid + block_group->key.offset)
		goto insert;
	key.objectid = end;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
	if (ret)
		goto out;

	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) {
		ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY);
		btrfs_release_path(path);
		goto insert;
	}

	found_start = key.objectid;
	found_end = key.objectid + key.offset;
	ASSERT(found_start >= block_group->key.objectid &&
	       found_end > block_group->key.objectid);
	ASSERT((found_start < start && found_end <= start) ||
	       (found_start >= end && found_end > end));

	/*
	 * Delete the neighbor on the right and absorb it into the new key
	 * (cases 3 and 4).
	 */
	if (found_start == end) {
		ret = btrfs_del_item(trans, root, path);
		if (ret)
			goto out;
		new_key.offset += key.offset;
		new_extents--;
	}
	btrfs_release_path(path);

insert:
	/* Insert the new key (cases 1-4). */
	ret = btrfs_insert_empty_item(trans, root, path, &new_key, 0);
	if (ret)
		goto out;

	btrfs_release_path(path);
968
	ret = update_free_space_extent_count(trans, block_group, path,
969 970 971 972 973 974
					     new_extents);

out:
	return ret;
}

975
EXPORT_FOR_TESTS
976 977 978 979
int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
			     struct btrfs_block_group_cache *block_group,
			     struct btrfs_path *path, u64 start, u64 size)
{
980
	struct btrfs_fs_info *fs_info = trans->fs_info;
981 982 983 984 985
	struct btrfs_free_space_info *info;
	u32 flags;
	int ret;

	if (block_group->needs_free_space) {
986
		ret = __add_block_group_free_space(trans, block_group, path);
987 988 989 990 991 992 993 994 995 996 997
		if (ret)
			return ret;
	}

	info = search_free_space_info(NULL, fs_info, block_group, path, 0);
	if (IS_ERR(info))
		return PTR_ERR(info);
	flags = btrfs_free_space_flags(path->nodes[0], info);
	btrfs_release_path(path);

	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
998 999
		return modify_free_space_bitmap(trans, block_group, path,
						start, size, 0);
1000
	} else {
1001 1002
		return add_free_space_extent(trans, block_group, path, start,
					     size);
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
	}
}

int add_to_free_space_tree(struct btrfs_trans_handle *trans,
			   u64 start, u64 size)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_path *path;
	int ret;

1013
	if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
1014 1015 1016 1017 1018 1019 1020 1021
		return 0;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

1022
	block_group = btrfs_lookup_block_group(trans->fs_info, start);
1023 1024 1025 1026 1027 1028 1029
	if (!block_group) {
		ASSERT(0);
		ret = -ENOENT;
		goto out;
	}

	mutex_lock(&block_group->free_space_lock);
1030
	ret = __add_to_free_space_tree(trans, block_group, path, start, size);
1031 1032 1033 1034 1035 1036
	mutex_unlock(&block_group->free_space_lock);

	btrfs_put_block_group(block_group);
out:
	btrfs_free_path(path);
	if (ret)
1037
		btrfs_abort_transaction(trans, ret);
1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048
	return ret;
}

/*
 * Populate the free space tree by walking the extent tree. Operations on the
 * extent tree that happen as a result of writes to the free space tree will go
 * through the normal add/remove hooks.
 */
static int populate_free_space_tree(struct btrfs_trans_handle *trans,
				    struct btrfs_block_group_cache *block_group)
{
1049
	struct btrfs_root *extent_root = trans->fs_info->extent_root;
1050 1051 1052 1053 1054 1055 1056 1057
	struct btrfs_path *path, *path2;
	struct btrfs_key key;
	u64 start, end;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
1058
	path->reada = READA_FORWARD;
1059 1060 1061 1062 1063 1064 1065

	path2 = btrfs_alloc_path();
	if (!path2) {
		btrfs_free_path(path);
		return -ENOMEM;
	}

1066
	ret = add_new_free_space_info(trans, block_group, path2);
1067 1068 1069
	if (ret)
		goto out;

1070 1071
	mutex_lock(&block_group->free_space_lock);

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084
	/*
	 * Iterate through all of the extent and metadata items in this block
	 * group, adding the free space between them and the free space at the
	 * end. Note that EXTENT_ITEM and METADATA_ITEM are less than
	 * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's
	 * contained in.
	 */
	key.objectid = block_group->key.objectid;
	key.type = BTRFS_EXTENT_ITEM_KEY;
	key.offset = 0;

	ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0);
	if (ret < 0)
1085
		goto out_locked;
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098
	ASSERT(ret == 0);

	start = block_group->key.objectid;
	end = block_group->key.objectid + block_group->key.offset;
	while (1) {
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
		    key.type == BTRFS_METADATA_ITEM_KEY) {
			if (key.objectid >= end)
				break;

			if (start < key.objectid) {
1099
				ret = __add_to_free_space_tree(trans,
1100 1101 1102 1103 1104
							       block_group,
							       path2, start,
							       key.objectid -
							       start);
				if (ret)
1105
					goto out_locked;
1106 1107 1108
			}
			start = key.objectid;
			if (key.type == BTRFS_METADATA_ITEM_KEY)
1109
				start += trans->fs_info->nodesize;
1110 1111 1112 1113 1114 1115 1116 1117 1118
			else
				start += key.offset;
		} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
			if (key.objectid != block_group->key.objectid)
				break;
		}

		ret = btrfs_next_item(extent_root, path);
		if (ret < 0)
1119
			goto out_locked;
1120 1121 1122 1123
		if (ret)
			break;
	}
	if (start < end) {
1124 1125
		ret = __add_to_free_space_tree(trans, block_group, path2,
					       start, end - start);
1126
		if (ret)
1127
			goto out_locked;
1128 1129 1130
	}

	ret = 0;
1131 1132
out_locked:
	mutex_unlock(&block_group->free_space_lock);
1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151
out:
	btrfs_free_path(path2);
	btrfs_free_path(path);
	return ret;
}

int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *free_space_root;
	struct btrfs_block_group_cache *block_group;
	struct rb_node *node;
	int ret;

	trans = btrfs_start_transaction(tree_root, 0);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

1152
	set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
	free_space_root = btrfs_create_tree(trans, fs_info,
					    BTRFS_FREE_SPACE_TREE_OBJECTID);
	if (IS_ERR(free_space_root)) {
		ret = PTR_ERR(free_space_root);
		goto abort;
	}
	fs_info->free_space_root = free_space_root;

	node = rb_first(&fs_info->block_group_cache_tree);
	while (node) {
		block_group = rb_entry(node, struct btrfs_block_group_cache,
				       cache_node);
1165
		ret = populate_free_space_tree(trans, block_group);
1166 1167 1168 1169 1170 1171
		if (ret)
			goto abort;
		node = rb_next(node);
	}

	btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
1172
	btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
1173
	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
1174

1175
	return btrfs_commit_transaction(trans);
1176 1177

abort:
1178
	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
1179
	btrfs_abort_transaction(trans, ret);
1180
	btrfs_end_transaction(trans);
1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
	return ret;
}

static int clear_free_space_tree(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root)
{
	struct btrfs_path *path;
	struct btrfs_key key;
	int nr;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	path->leave_spinning = 1;

	key.objectid = 0;
	key.type = 0;
	key.offset = 0;

	while (1) {
		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
		if (ret < 0)
			goto out;

		nr = btrfs_header_nritems(path->nodes[0]);
		if (!nr)
			break;

		path->slots[0] = 0;
		ret = btrfs_del_items(trans, root, path, 0, nr);
		if (ret)
			goto out;

		btrfs_release_path(path);
	}

	ret = 0;
out:
	btrfs_free_path(path);
	return ret;
}

int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *free_space_root = fs_info->free_space_root;
	int ret;

	trans = btrfs_start_transaction(tree_root, 0);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE);
1237
	btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
1238 1239 1240 1241 1242 1243
	fs_info->free_space_root = NULL;

	ret = clear_free_space_tree(trans, free_space_root);
	if (ret)
		goto abort;

1244
	ret = btrfs_del_root(trans, &free_space_root->root_key);
1245 1246 1247 1248 1249 1250
	if (ret)
		goto abort;

	list_del(&free_space_root->dirty_list);

	btrfs_tree_lock(free_space_root->node);
1251
	btrfs_clean_tree_block(free_space_root->node);
1252 1253 1254 1255 1256 1257 1258 1259
	btrfs_tree_unlock(free_space_root->node);
	btrfs_free_tree_block(trans, free_space_root, free_space_root->node,
			      0, 1);

	free_extent_buffer(free_space_root->node);
	free_extent_buffer(free_space_root->commit_root);
	kfree(free_space_root);

1260
	return btrfs_commit_transaction(trans);
1261 1262

abort:
1263
	btrfs_abort_transaction(trans, ret);
1264
	btrfs_end_transaction(trans);
1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275
	return ret;
}

static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
					struct btrfs_block_group_cache *block_group,
					struct btrfs_path *path)
{
	int ret;

	block_group->needs_free_space = 0;

1276
	ret = add_new_free_space_info(trans, block_group, path);
1277 1278 1279
	if (ret)
		return ret;

1280
	return __add_to_free_space_tree(trans, block_group, path,
1281 1282 1283 1284 1285 1286 1287
					block_group->key.objectid,
					block_group->key.offset);
}

int add_block_group_free_space(struct btrfs_trans_handle *trans,
			       struct btrfs_block_group_cache *block_group)
{
1288
	struct btrfs_fs_info *fs_info = trans->fs_info;
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304
	struct btrfs_path *path = NULL;
	int ret = 0;

	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
		return 0;

	mutex_lock(&block_group->free_space_lock);
	if (!block_group->needs_free_space)
		goto out;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

1305
	ret = __add_block_group_free_space(trans, block_group, path);
1306 1307 1308 1309 1310

out:
	btrfs_free_path(path);
	mutex_unlock(&block_group->free_space_lock);
	if (ret)
1311
		btrfs_abort_transaction(trans, ret);
1312 1313 1314 1315 1316 1317
	return ret;
}

int remove_block_group_free_space(struct btrfs_trans_handle *trans,
				  struct btrfs_block_group_cache *block_group)
{
1318
	struct btrfs_root *root = trans->fs_info->free_space_root;
1319 1320 1321 1322 1323 1324 1325
	struct btrfs_path *path;
	struct btrfs_key key, found_key;
	struct extent_buffer *leaf;
	u64 start, end;
	int done = 0, nr;
	int ret;

1326
	if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386
		return 0;

	if (block_group->needs_free_space) {
		/* We never added this block group to the free space tree. */
		return 0;
	}

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	start = block_group->key.objectid;
	end = block_group->key.objectid + block_group->key.offset;

	key.objectid = end - 1;
	key.type = (u8)-1;
	key.offset = (u64)-1;

	while (!done) {
		ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
		if (ret)
			goto out;

		leaf = path->nodes[0];
		nr = 0;
		path->slots[0]++;
		while (path->slots[0] > 0) {
			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);

			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
				ASSERT(found_key.objectid == block_group->key.objectid);
				ASSERT(found_key.offset == block_group->key.offset);
				done = 1;
				nr++;
				path->slots[0]--;
				break;
			} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY ||
				   found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
				ASSERT(found_key.objectid >= start);
				ASSERT(found_key.objectid < end);
				ASSERT(found_key.objectid + found_key.offset <= end);
				nr++;
				path->slots[0]--;
			} else {
				ASSERT(0);
			}
		}

		ret = btrfs_del_items(trans, root, path, path->slots[0], nr);
		if (ret)
			goto out;
		btrfs_release_path(path);
	}

	ret = 0;
out:
	btrfs_free_path(path);
	if (ret)
1387
		btrfs_abort_transaction(trans, ret);
1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
	return ret;
}

static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
				   struct btrfs_path *path,
				   u32 expected_extent_count)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_fs_info *fs_info;
	struct btrfs_root *root;
	struct btrfs_key key;
	int prev_bit = 0, bit;
	/* Initialize to silence GCC. */
	u64 extent_start = 0;
	u64 end, offset;
	u64 total_found = 0;
	u32 extent_count = 0;
	int ret;

	block_group = caching_ctl->block_group;
	fs_info = block_group->fs_info;
	root = fs_info->free_space_root;

	end = block_group->key.objectid + block_group->key.offset;

	while (1) {
		ret = btrfs_next_item(root, path);
		if (ret < 0)
			goto out;
		if (ret)
			break;

		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

		if (key.type == BTRFS_FREE_SPACE_INFO_KEY)
			break;

		ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);
		ASSERT(key.objectid < end && key.objectid + key.offset <= end);

		caching_ctl->progress = key.objectid;

		offset = key.objectid;
		while (offset < key.objectid + key.offset) {
			bit = free_space_test_bit(block_group, path, offset);
			if (prev_bit == 0 && bit == 1) {
				extent_start = offset;
			} else if (prev_bit == 1 && bit == 0) {
				total_found += add_new_free_space(block_group,
								  extent_start,
								  offset);
				if (total_found > CACHING_CTL_WAKE_UP) {
					total_found = 0;
					wake_up(&caching_ctl->wait);
				}
				extent_count++;
			}
			prev_bit = bit;
1446
			offset += fs_info->sectorsize;
1447 1448 1449
		}
	}
	if (prev_bit == 1) {
1450 1451
		total_found += add_new_free_space(block_group, extent_start,
						  end);
1452 1453 1454 1455
		extent_count++;
	}

	if (extent_count != expected_extent_count) {
1456 1457
		btrfs_err(fs_info,
			  "incorrect extent count for %llu; counted %u, expected %u",
1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507
			  block_group->key.objectid, extent_count,
			  expected_extent_count);
		ASSERT(0);
		ret = -EIO;
		goto out;
	}

	caching_ctl->progress = (u64)-1;

	ret = 0;
out:
	return ret;
}

static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
				   struct btrfs_path *path,
				   u32 expected_extent_count)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_fs_info *fs_info;
	struct btrfs_root *root;
	struct btrfs_key key;
	u64 end;
	u64 total_found = 0;
	u32 extent_count = 0;
	int ret;

	block_group = caching_ctl->block_group;
	fs_info = block_group->fs_info;
	root = fs_info->free_space_root;

	end = block_group->key.objectid + block_group->key.offset;

	while (1) {
		ret = btrfs_next_item(root, path);
		if (ret < 0)
			goto out;
		if (ret)
			break;

		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

		if (key.type == BTRFS_FREE_SPACE_INFO_KEY)
			break;

		ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY);
		ASSERT(key.objectid < end && key.objectid + key.offset <= end);

		caching_ctl->progress = key.objectid;

1508
		total_found += add_new_free_space(block_group, key.objectid,
1509 1510 1511 1512 1513 1514 1515 1516 1517
						  key.objectid + key.offset);
		if (total_found > CACHING_CTL_WAKE_UP) {
			total_found = 0;
			wake_up(&caching_ctl->wait);
		}
		extent_count++;
	}

	if (extent_count != expected_extent_count) {
1518 1519
		btrfs_err(fs_info,
			  "incorrect extent count for %llu; counted %u, expected %u",
1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555
			  block_group->key.objectid, extent_count,
			  expected_extent_count);
		ASSERT(0);
		ret = -EIO;
		goto out;
	}

	caching_ctl->progress = (u64)-1;

	ret = 0;
out:
	return ret;
}

int load_free_space_tree(struct btrfs_caching_control *caching_ctl)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_fs_info *fs_info;
	struct btrfs_free_space_info *info;
	struct btrfs_path *path;
	u32 extent_count, flags;
	int ret;

	block_group = caching_ctl->block_group;
	fs_info = block_group->fs_info;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/*
	 * Just like caching_thread() doesn't want to deadlock on the extent
	 * tree, we don't want to deadlock on the free space tree.
	 */
	path->skip_locking = 1;
	path->search_commit_root = 1;
1556
	path->reada = READA_FORWARD;
1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579

	info = search_free_space_info(NULL, fs_info, block_group, path, 0);
	if (IS_ERR(info)) {
		ret = PTR_ERR(info);
		goto out;
	}
	extent_count = btrfs_free_space_extent_count(path->nodes[0], info);
	flags = btrfs_free_space_flags(path->nodes[0], info);

	/*
	 * We left path pointing to the free space info item, so now
	 * load_free_space_foo can just iterate through the free space tree from
	 * there.
	 */
	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS)
		ret = load_free_space_bitmaps(caching_ctl, path, extent_count);
	else
		ret = load_free_space_extents(caching_ctl, path, extent_count);

out:
	btrfs_free_path(path);
	return ret;
}