Re: [PATCH v16 12/21] xfs: use read ioend for fsverity data verification

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

On Fri, Sep 18, 2026 at 01:15:24PM +0200, Andrey Albershteyn wrote:
> Use read ioends for fsverity verification. Do not issue fsverity
> metadata I/O through the same workqueue due to risk of a deadlock by a
> filled workqueue.
> 
> Pass fsverity_info from iomap context down to the ioend as hashtable
> lookups are expensive.
> 
> Add a simple helper to check that this is not fsverity metadata but file
> data that needs verification.
> 
> Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>

Seems fine to me, though I would like to see hch's blessing on this
since he's written more of the read ioend workqueue completion code.

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

--D

> ---
>  fs/xfs/xfs_aops.c     | 13 +++++----
>  fs/xfs/xfs_file.c     |  3 +-
>  fs/xfs/xfs_fsverity.c | 11 ++++++++
>  fs/xfs/xfs_fsverity.h | 14 ++++++++++
>  fs/xfs/xfs_ioend.c    | 65 +++++++++++++++++++++++++++++++++++++++----
>  fs/xfs/xfs_ioend.h    |  4 ++-
>  fs/xfs/xfs_super.c    | 15 ++++++++++
>  7 files changed, 112 insertions(+), 13 deletions(-)
> 
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 19640e4e3ed1..a36f840884b4 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -24,6 +24,7 @@
>  #include "xfs_zone_alloc.h"
>  #include "xfs_rtgroup.h"
>  #include "xfs_fsverity.h"
> +#include <linux/fsverity.h>
>  
>  struct xfs_writepage_ctx {
>  	struct iomap_writepage_ctx ctx;
> @@ -611,7 +612,7 @@ xfs_bio_submit_read(
>  {
>  	xfs_ioend_submit_read(iter->inode, ctx->read_ctx,
>  			ctx->read_ctx_file_offset,
> -			iomap_ioend_flags(&iter->iomap));
> +			iomap_ioend_flags(&iter->iomap), ctx->vi);
>  	ctx->read_ctx = NULL;
>  }
>  
> @@ -623,11 +624,13 @@ static const struct iomap_read_ops xfs_iomap_read_ops = {
>  
>  static inline const struct iomap_read_ops *
>  xfs_get_iomap_read_ops(
> -	const struct address_space	*mapping)
> +	const struct address_space	*mapping,
> +	loff_t				pos)
>  {
>  	struct xfs_inode		*ip = XFS_I(mapping->host);
>  
> -	if (bdev_has_integrity_csum(xfs_inode_buftarg(ip)->bt_bdev))
> +	if (bdev_has_integrity_csum(xfs_inode_buftarg(ip)->bt_bdev) ||
> +	    xfs_fsverity_is_file_data(ip, pos))
>  		return &xfs_iomap_read_ops;
>  	return &iomap_bio_read_ops;
>  }
> @@ -639,7 +642,7 @@ xfs_vm_read_folio(
>  {
>  	struct iomap_read_folio_ctx	ctx = { .cur_folio = folio };
>  
> -	ctx.ops = xfs_get_iomap_read_ops(folio->mapping);
> +	ctx.ops = xfs_get_iomap_read_ops(folio->mapping, folio_pos(folio));
>  	iomap_read_folio(&xfs_read_iomap_ops, &ctx, NULL);
>  	return 0;
>  }
> @@ -650,7 +653,7 @@ xfs_vm_readahead(
>  {
>  	struct iomap_read_folio_ctx	ctx = { .rac = rac };
>  
> -	ctx.ops = xfs_get_iomap_read_ops(rac->mapping),
> +	ctx.ops = xfs_get_iomap_read_ops(rac->mapping, readahead_pos(rac));
>  	iomap_readahead(&xfs_read_iomap_ops, &ctx, NULL);
>  }
>  
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 07abf6e8783f..578ca6fb8292 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -225,7 +225,8 @@ xfs_dio_read_bounce_submit_io(
>  	loff_t			file_offset)
>  {
>  	xfs_ioend_submit_read(iter->inode, bio, file_offset,
> -			iomap_ioend_flags(&iter->iomap) | IOMAP_IOEND_DIRECT);
> +			iomap_ioend_flags(&iter->iomap) | IOMAP_IOEND_DIRECT,
> +			NULL);
>  }
>  
>  static const struct iomap_dio_ops xfs_dio_read_bounce_ops = {
> diff --git a/fs/xfs/xfs_fsverity.c b/fs/xfs/xfs_fsverity.c
> index e30021c22683..525855fdd30d 100644
> --- a/fs/xfs/xfs_fsverity.c
> +++ b/fs/xfs/xfs_fsverity.c
> @@ -14,9 +14,20 @@
>  #include <linux/fsverity.h>
>  #include <linux/iomap.h>
>  
> +struct kmem_cache *xfs_fsverity_ioend_cache;
> +
>  loff_t
>  xfs_fsverity_metadata_offset(
>  	const struct xfs_inode	*ip)
>  {
>  	return round_up(i_size_read(VFS_IC(ip)), XFS_FSVERITY_START_ALIGN);
>  }
> +
> +bool
> +xfs_fsverity_is_file_data(
> +	const struct xfs_inode	*ip,
> +	loff_t			offset)
> +{
> +	return fsverity_active(VFS_IC(ip)) &&
> +			offset < xfs_fsverity_metadata_offset(ip);
> +}
> diff --git a/fs/xfs/xfs_fsverity.h b/fs/xfs/xfs_fsverity.h
> index c2ab5af89370..836e3a4eb194 100644
> --- a/fs/xfs/xfs_fsverity.h
> +++ b/fs/xfs/xfs_fsverity.h
> @@ -6,15 +6,29 @@
>  #define __XFS_FSVERITY_H__
>  
>  #include "xfs_platform.h"
> +#include <linux/iomap.h>
>  
>  #ifdef CONFIG_FS_VERITY
>  loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip);
> +bool xfs_fsverity_is_file_data(const struct xfs_inode *ip, loff_t offset);
>  #else
>  static inline loff_t xfs_fsverity_metadata_offset(const struct xfs_inode *ip)
>  {
>  	WARN_ON_ONCE(1);
>  	return ULLONG_MAX;
>  }
> +static inline bool xfs_fsverity_is_file_data(const struct xfs_inode *ip,
> +					    loff_t offset)
> +{
> +	return false;
> +}
>  #endif	/* CONFIG_FS_VERITY */
>  
> +struct xfs_fsverity_ioend {
> +	struct iomap_ioend	*ioend;
> +	struct work_struct	work;
> +};
> +
> +extern struct kmem_cache *xfs_fsverity_ioend_cache;
> +
>  #endif	/* __XFS_FSVERITY_H__ */
> diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c
> index e70be5b86f0b..2f46855b052f 100644
> --- a/fs/xfs/xfs_ioend.c
> +++ b/fs/xfs/xfs_ioend.c
> @@ -18,7 +18,26 @@
>  #include "xfs_ioend.h"
>  #include "xfs_error.h"
>  #include "xfs_errortag.h"
> +#include "xfs_fsverity.h"
>  #include <linux/bio-integrity.h>
> +#include <linux/fsverity.h>
> +
> +static void
> +xfs_end_fsverity_io_read(
> +	struct work_struct		*work)
> +{
> +	struct xfs_fsverity_ioend	*fsv_ioend =
> +			container_of(work, struct xfs_fsverity_ioend, work);
> +	struct iomap_ioend		*ioend = fsv_ioend->ioend;
> +	struct bio			*bio = &ioend->io_bio;
> +
> +	kmem_cache_free(xfs_fsverity_ioend_cache, fsv_ioend);
> +
> +	if (!bio->bi_status)
> +		fsverity_verify_bio(ioend->io_vi, bio);
> +
> +	iomap_finish_ioends(ioend, blk_status_to_errno(bio->bi_status));
> +}
>  
>  static void
>  xfs_dio_bounce_end_io(
> @@ -93,12 +112,14 @@ xfs_read_bounce_and_resubmit(
>  
>  static void
>  xfs_end_io_read(
> -	struct bio		*bio)
> +	struct bio			*bio)
>  {
> -	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
> -	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
> -	struct xfs_mount	*mp = ip->i_mount;
> -	int			error = blk_status_to_errno(bio->bi_status);
> +	struct iomap_ioend		*ioend = iomap_ioend_from_bio(bio);
> +	struct xfs_inode		*ip = XFS_I(ioend->io_inode);
> +	struct xfs_mount		*mp = ip->i_mount;
> +	int				error =
> +			blk_status_to_errno(bio->bi_status);
> +	struct xfs_fsverity_ioend	*fsv_ioend;
>  
>  	if (!error && (ioend->io_flags & IOMAP_IOEND_INTEGRITY)) {
>  		error = iomap_ioend_integrity_verify(ioend);
> @@ -117,6 +138,36 @@ xfs_end_io_read(
>  		}
>  	}
>  
> +	/*
> +	 * If we have fsverity and block device integrity attached to this bio,
> +	 * we need to run fsverity verification of data folios from a separate
> +	 * fsverity workqueue. This is necessary to avoid deadlocking due to
> +	 * fsverity issuing more reads of fsverity metadata which would be
> +	 * processed by the same worker in the BIO completion workqueue.
> +	 *
> +	 * Without block device integrity, fsverity metadata IO will not use
> +	 * ioends for completion.
> +	 */
> +	if (IS_ENABLED(CONFIG_FS_VERITY) && !error && ioend->io_vi &&
> +			xfs_fsverity_is_file_data(ip, ioend->io_offset)) {
> +		if (ioend->io_flags & IOMAP_IOEND_INTEGRITY) {
> +			fsv_ioend = kmem_cache_zalloc(xfs_fsverity_ioend_cache,
> +					GFP_KERNEL);
> +			if (!fsv_ioend) {
> +				iomap_finish_ioends(ioend, -ENOMEM);
> +				return;
> +			}
> +			fsv_ioend->ioend = ioend;
> +			INIT_WORK(&fsv_ioend->work, xfs_end_fsverity_io_read);
> +
> +			fsverity_enqueue_verify_work(&fsv_ioend->work);
> +			return;
> +		}
> +
> +		fsverity_verify_bio(ioend->io_vi, &ioend->io_bio);
> +		error = blk_status_to_errno(ioend->io_bio.bi_status);
> +	}
> +
>  	iomap_finish_ioends(ioend, error);
>  }
>  
> @@ -125,13 +176,15 @@ xfs_ioend_submit_read(
>  	struct inode		*inode,
>  	struct bio		*bio,
>  	loff_t			file_offset,
> -	u16			ioend_flags)
> +	u16			ioend_flags,
> +	struct fsverity_info	*vi)
>  {
>  	struct xfs_inode	*ip = XFS_I(inode);
>  	struct xfs_mount	*mp = ip->i_mount;
>  	struct iomap_ioend	*ioend;
>  
>  	ioend = iomap_init_ioend(inode, bio, file_offset, ioend_flags);
> +	ioend->io_vi = vi;
>  	if ((ioend_flags & IOMAP_IOEND_DIRECT) &&
>  	    READ_ONCE(mp->m_read_bounce) == XFS_READ_BOUNCE_ALWAYS) {
>  		iomap_bounce_read(ioend, bdev_logical_block_size(bio->bi_bdev),
> diff --git a/fs/xfs/xfs_ioend.h b/fs/xfs/xfs_ioend.h
> index 7c2a1ea3e6ed..992c248a693a 100644
> --- a/fs/xfs/xfs_ioend.h
> +++ b/fs/xfs/xfs_ioend.h
> @@ -2,6 +2,8 @@
>  #ifndef __XFS_IOEND_H
>  #define __XFS_IOEND_H
>  
> +#include <linux/fsverity.h>
> +
>  /*
>   * Fast and loose check if this write could update the on-disk inode size.
>   */
> @@ -13,6 +15,6 @@ static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend)
>  
>  void xfs_end_bio(struct bio *bio);
>  void xfs_ioend_submit_read(struct inode *inode, struct bio *bio,
> -		loff_t file_offset, u16 ioend_flags);
> +		loff_t file_offset, u16 ioend_flags, struct fsverity_info *vi);
>  
>  #endif /* __XFS_IOEND_H */
> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
> index fce1d2905c94..aca50130625e 100644
> --- a/fs/xfs/xfs_super.c
> +++ b/fs/xfs/xfs_super.c
> @@ -2516,8 +2516,20 @@ xfs_init_caches(void)
>  	if (!xfs_parent_args_cache)
>  		goto out_destroy_xmi_cache;
>  
> +#ifdef CONFIG_FS_VERITY
> +	xfs_fsverity_ioend_cache = kmem_cache_create("xfs_fsverity_ioend",
> +					     sizeof(struct xfs_fsverity_ioend),
> +					     0, 0, NULL);
> +	if (!xfs_fsverity_ioend_cache)
> +		goto out_destroy_fsverity_ioend_cache;
> +#endif
> +
>  	return 0;
>  
> +#ifdef CONFIG_FS_VERITY
> + out_destroy_fsverity_ioend_cache:
> +	kmem_cache_destroy(xfs_fsverity_ioend_cache);
> +#endif
>   out_destroy_xmi_cache:
>  	kmem_cache_destroy(xfs_xmi_cache);
>   out_destroy_xmd_cache:
> @@ -2580,6 +2592,9 @@ xfs_destroy_caches(void)
>  	 * destroy caches.
>  	 */
>  	rcu_barrier();
> +#ifdef CONFIG_FS_VERITY
> +	kmem_cache_destroy(xfs_fsverity_ioend_cache);
> +#endif
>  	kmem_cache_destroy(xfs_parent_args_cache);
>  	kmem_cache_destroy(xfs_xmd_cache);
>  	kmem_cache_destroy(xfs_xmi_cache);
> -- 
> 2.54.0
> 
>