Re: [PATCH v4 07/25] iomap: introduce IOMAP_F_FSVERITY and teach writeback to handle fsverity

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

On Mon, Mar 09, 2026 at 08:23:22PM +0100, Andrey Albershteyn wrote:
> This flag indicates that I/O is for fsverity metadata.
> 
> In the write path skip i_size check and i_size updates as metadata is
> past EOF. In writeback don't update i_size and continue writeback if
> even folio is beyond EOF. In read path don't zero fsverity folios, again
> they are past EOF.
> 
> The iomap_block_needs_zeroing() is also called from write path. For
> folios of larger order we don't want to zero out pages in the folio as
> these could contain other merkle tree blocks. For fsverity, filesystem
> will request to read PAGE_SIZE memory regions. For data folios, iomap
> will zero the rest of the folio for anything which is beyond EOF. We
> don't want this for fsverity folios.
> 
> Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>

This feels like a reasonable means to implement post-EOF data stashing
for fsverity having gone through many other merkle tree IO path designs
and discarded them all. :/

Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>

Hey, at least some day we might get fscrypt+fsverity on xfs for free.

--D

> ---
>  fs/iomap/buffered-io.c | 34 +++++++++++++++++++++++++---------
>  fs/iomap/trace.h       |  3 ++-
>  include/linux/iomap.h  |  5 +++++
>  3 files changed, 32 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 51a58a0bfe6c..530794dcdd91 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -344,9 +344,16 @@ static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
>  {
>  	const struct iomap *srcmap = iomap_iter_srcmap(iter);
>  
> -	return srcmap->type != IOMAP_MAPPED ||
> -		(srcmap->flags & IOMAP_F_NEW) ||
> -		pos >= i_size_read(iter->inode);
> +	if (srcmap->type != IOMAP_MAPPED)
> +		return true;
> +
> +	if (srcmap->flags & IOMAP_F_NEW)
> +		return true;
> +
> +	if (srcmap->flags & IOMAP_F_FSVERITY)
> +		return false;
> +
> +	return pos >= i_size_read(iter->inode);
>  }
>  
>  /**
> @@ -1152,13 +1159,14 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
>  		 * unlock and release the folio.
>  		 */
>  		old_size = iter->inode->i_size;
> -		if (pos + written > old_size) {
> +		if (pos + written > old_size &&
> +		    !(iter->iomap.flags & IOMAP_F_FSVERITY)) {
>  			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->iomap.flags & IOMAP_F_FSVERITY))
>  			pagecache_isize_extended(iter->inode, old_size, pos);
>  
>  		cond_resched();
> @@ -1786,13 +1794,21 @@ static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
>   * Check interaction of the folio with the file end.
>   *
>   * If the folio is entirely beyond i_size, return false.  If it straddles
> - * i_size, adjust end_pos and zero all data beyond i_size.
> + * i_size, adjust end_pos and zero all data beyond i_size. Don't skip fsverity
> + * folios as those are beyond i_size.
>   */
> -static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
> -		u64 *end_pos)
> +static bool iomap_writeback_handle_eof(struct folio *folio,
> +				       struct iomap_writepage_ctx *wpc,
> +				       u64 *end_pos)
>  {
> +	struct inode *inode = wpc->inode;
>  	u64 isize = i_size_read(inode);
>  
> +	if (wpc->iomap.flags & IOMAP_F_FSVERITY) {
> +		WARN_ON_ONCE(folio_pos(folio) < isize);
> +		return true;
> +	}
> +
>  	if (*end_pos > isize) {
>  		size_t poff = offset_in_folio(folio, isize);
>  		pgoff_t end_index = isize >> PAGE_SHIFT;
> @@ -1858,7 +1874,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
>  
>  	trace_iomap_writeback_folio(inode, pos, folio_size(folio));
>  
> -	if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
> +	if (!iomap_writeback_handle_eof(folio, wpc, &end_pos))
>  		return 0;
>  	WARN_ON_ONCE(end_pos <= pos);
>  
> diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
> index 532787277b16..5252051cc137 100644
> --- a/fs/iomap/trace.h
> +++ b/fs/iomap/trace.h
> @@ -118,7 +118,8 @@ DEFINE_RANGE_EVENT(iomap_zero_iter);
>  	{ 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_FSVERITY,	"FSVERITY" }
>  
>  
>  #define IOMAP_DIO_STRINGS \
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 531f9ebdeeae..dc39837b0d45 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -87,6 +87,11 @@ struct vm_fault;
>  #define IOMAP_F_INTEGRITY	0
>  #endif /* CONFIG_BLK_DEV_INTEGRITY */
>  
> +/*
> + * IO happens beyond inode EOF, fsverity metadata is stored there
> + */
> +#define IOMAP_F_FSVERITY	(1U << 10)
> +
>  /*
>   * Flag reserved for file system specific usage
>   */
> -- 
> 2.51.2
> 
>