Re: [PATCH v2 3/22] iomap: introduce IOMAP_F_BEYOND_EOF

["Darrick J. Wong" <djwong@kernel.org>]

On Mon, Jan 12, 2026 at 03:50:05PM +0100, Andrey Albershteyn wrote:
> Flag to indicate to iomap that read/write is happening beyond EOF and no
> isize checks/update is needed.
> 
> Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
> ---
>  fs/iomap/buffered-io.c | 13 ++++++++-----
>  fs/iomap/trace.h       |  3 ++-
>  include/linux/iomap.h  |  5 +++++
>  3 files changed, 15 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index e5c1ca440d..cc1cbf2a4c 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -533,7 +533,8 @@

(Does your diff program not set --show-c-function?  That makes reviewing
harder because I have to search on the comment text to figure out which
function this is)

>  			return 0;
>  
>  		/* zero post-eof blocks as the page may be mapped */
> -		if (iomap_block_needs_zeroing(iter, pos)) {
> +		if (iomap_block_needs_zeroing(iter, pos) &&
> +		    !(iomap->flags & IOMAP_F_BEYOND_EOF)) {

Hrm.  The last test in iomap_block_needs_zeroing is if pos is at or
beyond EOF, and iomap_adjust_read_range takes great pains to reduce plen
so that poff/plen never cross EOF.  I think the intent of that code is
to ensure that we always zero the post-EOF part of a folio when reading
it in from disk.

For verity I can see why you don't want to zero the merkle tree blocks
beyond EOF, but I think this code can expose unwritten junk in the
post-EOF part of the EOF block on disk.

Would it be more correct to do:

static inline bool
iomap_block_needs_zeroing(
	const struct iomap_iter *iter,
	struct folio *folio,
	loff_t pos)
{
	const struct iomap *srcmap = iomap_iter_srcmap(iter);

	if (srcmap->type != IOMAP_MAPPED)
		return true;
	if (srcmap->flags & IOMAP_F_NEW);
		return true;

	/*
	 * Merkle tree exists in a separate folio beyond EOF, so
	 * only zero if this is the EOF folio.
	 */
	if (iomap->flags & IOMAP_F_BEYOND_EOF)
		return folio_pos(folio) == i_size_read(iter->inode);

	return pos >= i_size_read(iter->inode);
}

>  			folio_zero_range(folio, poff, plen);
>  			iomap_set_range_uptodate(folio, poff, plen);
>  		} else {
> @@ -1130,13 +1131,14 @@
>  		 * unlock and release the folio.
>  		 */
>  		old_size = iter->inode->i_size;
> -		if (pos + written > old_size) {
> +		if (pos + written > old_size &&
> +		    !(iter->flags & IOMAP_F_BEYOND_EOF)) {
>  			i_size_write(iter->inode, pos + written);
>  			iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
>  		}
>  		__iomap_put_folio(iter, write_ops, written, folio);
>  
> -		if (old_size < pos)
> +		if (old_size < pos && !(iter->flags & IOMAP_F_BEYOND_EOF))
>  			pagecache_isize_extended(iter->inode, old_size, pos);
>  
>  		cond_resched();
> @@ -1815,8 +1817,9 @@
>  
>  	trace_iomap_writeback_folio(inode, pos, folio_size(folio));
>  
> -	if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
> -		return 0;
> +	if (!(wpc->iomap.flags & IOMAP_F_BEYOND_EOF) &&
> +	    !iomap_writeback_handle_eof(folio, inode, &end_pos))

Hrm.  I /think/ this might break post-eof zeroing on writeback if
BEYOND_EOF is set.  For verity this isn't a problem because there's no
writeback, but it's a bit of a logic bomb if someone ever tries to set
BEYOND_EOF on a non-verity file.

--D

> + 		return 0;
>  	WARN_ON_ONCE(end_pos <= pos);
>  
>  	if (i_blocks_per_folio(inode, folio) > 1) {
> diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
> index 532787277b..f1895f7ae5 100644
> --- a/fs/iomap/trace.h
> +++ b/fs/iomap/trace.h
> @@ -118,7 +118,8 @@
>  	{ IOMAP_F_ATOMIC_BIO,	"ATOMIC_BIO" }, \
>  	{ IOMAP_F_PRIVATE,	"PRIVATE" }, \
>  	{ IOMAP_F_SIZE_CHANGED,	"SIZE_CHANGED" }, \
> -	{ IOMAP_F_STALE,	"STALE" }
> +	{ IOMAP_F_STALE,	"STALE" }, \
> +	{ IOMAP_F_BEYOND_EOF,	"BEYOND_EOF" }
>  
>  
>  #define IOMAP_DIO_STRINGS \
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 520e967cb5..7a7e31c499 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -86,6 +86,11 @@
>  #define IOMAP_F_PRIVATE		(1U << 12)
>  
>  /*
> + * IO happens beyound inode EOF

s/beyound/beyond/

> + */
> +#define IOMAP_F_BEYOND_EOF	(1U << 13)
> +
> +/*
>   * Flags set by the core iomap code during operations:
>   *
>   * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size
> 
> -- 
> - Andrey
> 
>