On Mon, Jul 28, 2025 at 10:30:05PM +0200, Andrey Albershteyn wrote:
> From: Andrey Albershteyn <aalbersh@xxxxxxxxxx>
>
> Add iomap_writepages_unbound() without limit in form of EOF. XFS
> will use this to write metadata (fs-verity Merkle tree) in range far
> beyond EOF.
...and I guess some day fscrypt might use it to encrypt merkle trees
too?
> Signed-off-by: Andrey Albershteyn <aalbersh@xxxxxxxxxx>
> ---
> fs/iomap/buffered-io.c | 51 +++++++++++++++++++++++++++++++++++++++-----------
> include/linux/iomap.h | 3 +++
> 2 files changed, 43 insertions(+), 11 deletions(-)
>
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 3729391a18f3..7bef232254a3 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -1881,18 +1881,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
> int error = 0;
> u32 rlen;
>
> - WARN_ON_ONCE(!folio_test_locked(folio));
> - WARN_ON_ONCE(folio_test_dirty(folio));
> - WARN_ON_ONCE(folio_test_writeback(folio));
> -
> - trace_iomap_writepage(inode, pos, folio_size(folio));
> -
> - if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) {
> - folio_unlock(folio);
> - return 0;
> - }
> WARN_ON_ONCE(end_pos <= pos);
>
> + trace_iomap_writepage(inode, pos, folio_size(folio));
> +
> if (i_blocks_per_folio(inode, folio) > 1) {
> if (!ifs) {
> ifs = ifs_alloc(inode, folio, 0);
> @@ -1956,6 +1948,23 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
> return error;
> }
>
> +/* Map pages bound by EOF */
> +static int iomap_writepage_map_eof(struct iomap_writepage_ctx *wpc,
iomap_writepage_map_within_eof ?
> + struct writeback_control *wbc, struct folio *folio)
> +{
> + int error;
> + struct inode *inode = folio->mapping->host;
> + u64 end_pos = folio_pos(folio) + folio_size(folio);
> +
> + if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) {
> + folio_unlock(folio);
> + return 0;
> + }
> +
> + error = iomap_writepage_map(wpc, wbc, folio);
> + return error;
> +}
> +
> int
> iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
> struct iomap_writepage_ctx *wpc,
> @@ -1972,9 +1981,29 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
> PF_MEMALLOC))
> return -EIO;
>
> + wpc->ops = ops;
> + while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
> + WARN_ON_ONCE(!folio_test_locked(folio));
> + WARN_ON_ONCE(folio_test_dirty(folio));
> + WARN_ON_ONCE(folio_test_writeback(folio));
> +
> + error = iomap_writepage_map_eof(wpc, wbc, folio);
> + }
> + return iomap_submit_ioend(wpc, error);
> +}
> +EXPORT_SYMBOL_GPL(iomap_writepages);
> +
> +int
> +iomap_writepages_unbound(struct address_space *mapping, struct writeback_control *wbc,
Might want to leave a comment here explaining what's the difference
between the two iomap_writepages exports:
/*
* Write dirty pages, including any beyond EOF. This is solely for use
* by files that allow post-EOF pagecache, which means fsverity.
*/
> + struct iomap_writepage_ctx *wpc,
> + const struct iomap_writeback_ops *ops)
> +{
> + struct folio *folio = NULL;
> + int error;
> +
...and you might want a:
WARN_ON(!IS_VERITY(wpc->inode));
to keep it that way.
--D
> wpc->ops = ops;
> while ((folio = writeback_iter(mapping, wbc, folio, &error)))
> error = iomap_writepage_map(wpc, wbc, folio);
> return iomap_submit_ioend(wpc, error);
> }
> -EXPORT_SYMBOL_GPL(iomap_writepages);
> +EXPORT_SYMBOL_GPL(iomap_writepages_unbound);
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 522644d62f30..4a0b5ebb79e9 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -464,6 +464,9 @@ void iomap_sort_ioends(struct list_head *ioend_list);
> int iomap_writepages(struct address_space *mapping,
> struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
> const struct iomap_writeback_ops *ops);
> +int iomap_writepages_unbound(struct address_space *mapping,
> + struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
> + const struct iomap_writeback_ops *ops);
>
> /*
> * Flags for direct I/O ->end_io:
>
> --
> 2.50.0
>
>
