Re: [f2fs-dev] [PATCH 04/14] f2fs: support atomic file large folios buffered write

[Chao Yu via Linux-f2fs-devel <linux-f2fs-devel@lists.sourceforge.net>]

On 8/26/26 16:26, Nanzhe Zhao wrote:
> ioctl can convert an inode with large folio support into an atomic
> file. Support large folio buffered writes for atomic files as well.
> 
> Add a large folio atomic write_begin helper that reserves COW mappings
> for the write range. For partial head and tail subpages, read the
> existing data from either the COW inode or the original inode before
> marking the subpage uptodate.
> 
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
> ---
>  fs/f2fs/data.c | 123 ++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 121 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 7ce96ae02cfc..dff802725544 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -4211,6 +4211,117 @@ static int prepare_large_folio_write_begin(struct inode *inode,
>  	return 0;
>  }
>  
> +static int prepare_large_folio_atomic_write_begin(struct inode *inode,
> +		struct address_space *mapping, struct folio *folio, loff_t pos,
> +		unsigned int len)
> +{
> +	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> +	struct inode *cow_inode = F2FS_I(inode)->cow_inode;
> +	size_t ori_off = offset_in_folio(folio, pos);
> +	size_t need_off = ori_off;
> +	pgoff_t index;
> +	int err = 0;
> +	unsigned int orig_order;
> +	bool need_balance = false;
> +
> +	len = min_t(unsigned int, len, folio_size(folio) - ori_off);
> +
> +	f2fs_ffs_find_or_alloc(folio);
> +
> +	/* Inline data must have been converted before reaching here. */
> +	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
> +
> +	/* Reserve COW blocks for all covered 4K subpages first. */
> +	pgoff_t start_index = folio->index + (ori_off >> PAGE_SHIFT);
> +	pgoff_t end_index = folio->index +
> +		((ori_off + len - 1) >> PAGE_SHIFT);
> +
> +	for (index = start_index; index <= end_index; index++) {
> +		block_t cow_blkaddr = NULL_ADDR;
> +		bool node_changed = false;
> +		int ret;
> +
> +		ret = __find_data_block(cow_inode, index, &cow_blkaddr);
> +		if (ret)
> +			return ret;
> +		if (cow_blkaddr != NULL_ADDR)
> +			continue;
> +
> +		ret = __reserve_data_block(cow_inode, index, &cow_blkaddr,
> +					   &node_changed);
> +		if (ret)
> +			return ret;
> +
> +		inc_atomic_write_cnt(inode);

In order to not miss any logic in prepare_atomic_write_begin(), can you reuse
prepare_atomic_write_begin() as much as possible? needs to change parameters
a bit there.

	for (...) {
		err = prepare_atomic_write_begin(sbi, inode, index, pos, len, ...);
		...
	}

> +		need_balance |= node_changed;
> +	}
> +
> +	if (need_balance && !IS_NOQUOTA(inode) &&
> +				       has_not_enough_free_secs(sbi, 0, 0)) {
> +		orig_order = folio_order(folio);
> +		folio_unlock(folio);
> +		f2fs_balance_fs(sbi, true);
> +		folio_lock(folio);
> +		if (unlikely(folio->mapping != mapping ||
> +			     folio_order(folio) != orig_order))
> +			return -EAGAIN;
> +	}
> +
> +	if (folio_test_uptodate(folio) || len == folio_size(folio))
> +		return 0;
> +
> +	/* Then read partial 4K subpages. */
> +	while (find_next_valid_block(folio, ori_off, &need_off, len)) {

Can we record first and last blkaddr in first loop of
prepare_large_folio_atomic_write_begin(), and then we can avoid lot of complexity
below to find target blkaddr?

We really don't want to miss any corner case of atomic write + large folio, please
consider that.

Thanks,

> +		size_t off;
> +		block_t cow_blkaddr = NULL_ADDR;
> +		block_t ori_blkaddr = NULL_ADDR;
> +		struct inode *read_inode = NULL;
> +		block_t read_blkaddr = NULL_ADDR;
> +
> +		index = folio->index + (need_off >> PAGE_SHIFT);
> +		off = offset_in_folio(folio, index << PAGE_SHIFT);
> +
> +		err = __find_data_block(cow_inode, index, &cow_blkaddr);
> +		if (err)
> +			return err;
> +
> +		if (__is_valid_data_blkaddr(cow_blkaddr)) {
> +			if (!f2fs_is_valid_blkaddr(sbi, cow_blkaddr,
> +						  DATA_GENERIC_ENHANCE_READ))
> +				return -EFSCORRUPTED;
> +			read_inode = cow_inode;
> +			read_blkaddr = cow_blkaddr;
> +		} else if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE)) {
> +			folio_zero_segment(folio, off, off + PAGE_SIZE);
> +			f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE);
> +			continue;
> +		} else {
> +			err = __find_data_block(inode, index, &ori_blkaddr);
> +			if (err)
> +				return err;
> +
> +			if (!__is_valid_data_blkaddr(ori_blkaddr)) {
> +				folio_zero_segment(folio, off, off + PAGE_SIZE);
> +				f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE);
> +				continue;
> +			}
> +
> +			if (!f2fs_is_valid_blkaddr(sbi, ori_blkaddr,
> +						  DATA_GENERIC_ENHANCE_READ))
> +				return -EFSCORRUPTED;
> +			read_inode = inode;
> +			read_blkaddr = ori_blkaddr;
> +		}
> +
> +		err = f2fs_submit_page_read_sync(read_inode, folio,
> +						 index, read_blkaddr);
> +		if (err)
> +			return err;
> +	}
> +
> +	return 0;
> +}
> +
>  static int f2fs_write_begin(const struct kiocb *iocb,
>  			    struct address_space *mapping,
>  			    loff_t pos, unsigned len, struct folio **foliop,
> @@ -4282,7 +4393,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  
>  	*foliop = folio;
>  
> -	if (f2fs_is_atomic_file(inode))
> +	if (f2fs_is_atomic_file(inode) && !folio_test_large(folio))
>  		err = prepare_atomic_write_begin(sbi, folio, pos, len,
>  					&blkaddr, &need_balance);
>  	else if (!folio_test_large(folio))
> @@ -4307,10 +4418,18 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  	f2fs_folio_wait_writeback(folio, DATA, false, true);
>  
>  	if (folio_test_large(folio)) {
> -		err = prepare_large_folio_write_begin(inode,
> +		if (f2fs_is_atomic_file(inode))
> +			err = prepare_large_folio_atomic_write_begin(inode,
> +					mapping, folio, pos, len);
> +		else
> +			err = prepare_large_folio_write_begin(inode,
>  					folio, pos, len);
>  		if (!err)
>  			return 0;
> +		if (err == -EAGAIN) {
> +			f2fs_folio_put(folio, true);
> +			goto repeat;
> +		}
>  		goto put_folio;
>  	}
>  



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel