path: root/fs/btrfs/reflink.c

// SPDX-License-Identifier: GPL-2.0

#include <linux/blkdev.h>
#include <linux/fscrypt.h>
#include <linux/iversion.h>
#include "ctree.h"
#include "fs.h"
#include "messages.h"
#include "compression.h"
#include "delalloc-space.h"
#include "disk-io.h"
#include "reflink.h"
#include "transaction.h"
#include "subpage.h"
#include "accessors.h"
#include "file-item.h"
#include "file.h"
#include "super.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,
				     bool no_time_update)
{
	int ret;

	inode_inc_iversion(inode);
	if (!no_time_update) {
		inode_set_mtime_to_ts(inode, inode_set_ctime_current(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(BTRFS_I(inode), 0);
	}

	ret = btrfs_update_inode(trans, BTRFS_I(inode));
	if (unlikely(ret)) {
		btrfs_abort_transaction(trans, ret);
		btrfs_end_transaction(trans);
		return ret;
	}
	return btrfs_end_transaction(trans);
}

static int copy_inline_to_page(struct btrfs_inode *inode,
			       const u64 file_offset,
			       char *inline_data,
			       const u64 size,
			       const u64 datal,
			       const u8 comp_type)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	const u32 block_size = fs_info->sectorsize;
	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 folio *folio = NULL;
	struct address_space *mapping = inode->vfs_inode.i_mapping;
	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;

	folio = __filemap_get_folio(mapping, file_offset >> PAGE_SHIFT,
					FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
					btrfs_alloc_write_mask(mapping));
	if (IS_ERR(folio)) {
		ret = PTR_ERR(folio);
		goto out_unlock;
	}

	ret = set_folio_extent_mapped(folio);
	if (ret < 0)
		goto out_unlock;

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

	/*
	 * After dirtying the page our caller will need to start a transaction,
	 * and if we are low on metadata free space, that can cause flushing of
	 * delalloc for all inodes in order to get metadata space released.
	 * However we are holding the range locked for the whole duration of
	 * the clone/dedupe operation, so we may deadlock if that happens and no
	 * other task releases enough space. So mark this inode as not being
	 * possible to flush to avoid such deadlock. We will clear that flag
	 * when we finish cloning all extents, since a transaction is started
	 * after finding each extent to clone.
	 */
	set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags);

	if (comp_type == BTRFS_COMPRESS_NONE) {
		memcpy_to_folio(folio, offset_in_folio(folio, file_offset), data_start,
					datal);
	} else {
		ret = btrfs_decompress(comp_type, data_start, folio,
				       offset_in_folio(folio, file_offset),
				       inline_size, datal);
		if (ret)
			goto out_unlock;
		flush_dcache_folio(folio);
	}

	/*
	 * 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)
		folio_zero_range(folio, datal, block_size - datal);

	btrfs_folio_set_uptodate(fs_info, folio, file_offset, block_size);
	btrfs_folio_clear_checked(fs_info, folio, file_offset, block_size);
	btrfs_folio_set_dirty(fs_info, folio, file_offset, block_size);
out_unlock:
	if (!IS_ERR(folio)) </