path: root/fs/btrfs/free-space-tree.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2015 Facebook.  All rights reserved.
 */

#include <linux/kernel.h>
#include <linux/sched/mm.h>
#include "ctree.h"
#include "disk-io.h"
#include "locking.h"
#include "free-space-tree.h"
#include "transaction.h"
#include "block-group.h"

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

void set_free_space_tree_thresholds(struct btrfs_block_group *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.
	 */
	bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
	num_bitmaps = div_u64(cache->length + 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 *block_group,
				   struct btrfs_path *path)
{
	struct btrfs_root *root = trans->fs_info->free_space_root;
	struct btrfs_free_space_info *info;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	int ret;

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

	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;
}

EXPORT_FOR_TESTS
struct btrfs_free_space_info *search_free_space_info(
		struct btrfs_trans_handle *trans,
		struct btrfs_block_group *block_group,
		struct btrfs_path *path, int cow)
{
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	struct btrfs_root *root = fs_info->free_space_root;
	struct btrfs_key key;
	int ret;

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

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

static unsigned long *alloc_bitmap(u32 bitmap_size)
{
	unsigned long *ret;
	unsigned int nofs_flag;
	u32 bitmap_rounded_size = round_up(bitmap_size, sizeof(unsigned long));

	/*
	 * 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.
	 */
	nofs_flag = memalloc_nofs_save();
	ret = kvzalloc(bitmap_rounded_size, GFP_KERNEL);
	memalloc_nofs_restore(nofs_flag);
	return ret;
}

static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
{
	u8 *p = ((u8 *)map) + BIT_BYTE(start);
	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;
	}
}

EXPORT_FOR_TESTS
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
				  struct btrfs_block_group *block_group,
				  struct btrfs_path *path)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	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;
	unsigned long *bitmap;
	char *bitmap_cursor;
	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->length,
					     fs_info->sectorsize);
	bitmap = alloc_bitmap(bitmap_size);
	if (!bitmap) {
		ret = -ENOMEM;
		goto out;
	}

	start = block_group->start;
	end = block_group->start + block_group->length;

	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->start);
				ASSERT(found_key.offset == block_group->length);
				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(