[PATCH 0/4] Zoned device cleanups

[PATCH 0/4] Zoned device cleanups

[cem]

From: Carlos Maiolino <cem@kernel.org>

These patches initially were part from an attempt to implement atomic
writes for zoned devices.

Due to unforeseen circumstances, we can't implement it, at least for now
without restructuring a big part of the code.

Christoph though suggested those cleanups were good enough to be sent
even without proceeding with the implementation.

Carlos Maiolino (4):
  xfs: factor out isize updates from xfs_dio_write_end_io
  xfs: move zoned dio ioend to its own function
  xfs: factor out xfs_zone_inc_written
  xfs: opencode xfs_zone_record_blocks

 fs/xfs/xfs_file.c       | 94 +++++++++++++++++++++++++++++------------
 fs/xfs/xfs_zone_alloc.c | 32 ++++++--------
 2 files changed, 81 insertions(+), 45 deletions(-)

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
-- 
2.53.0

[PATCH 1/4] xfs: factor out isize updates from xfs_dio_write_end_io

[cem]

From: Carlos Maiolino <cem@kernel.org>

This is the only code needed for zoned inodes, so factor it out so
we can move zoned inodes ioend to its own callback.

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_file.c | 59 +++++++++++++++++++++++++++++------------------
 1 file changed, 36 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 6246f34df9fd..45ecd743fa32 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -560,6 +560,41 @@ xfs_zoned_write_space_reserve(
 			flags, ac);
 }
 
+/*
+ * We need to lock the test/set EOF update as we can be racing with
+ * other IO completions here to update the EOF. Failing to serialise
+ * here can result in EOF moving backwards and Bad Things Happen when
+ * that occurs.
+ *
+ * As IO completion only ever extends EOF, we can do an unlocked check
+ * here to avoid taking the spinlock. If we land within the current EOF,
+ * then we do not need to do an extending update at all, and we don't
+ * need to take the lock to check this. If we race with an update moving
+ * EOF, then we'll either still be beyond EOF and need to take the lock,
+ * or we'll be within EOF and we don't need to take it at all.
+ */
+static int
+xfs_dio_endio_set_isize(
+	struct inode		*inode,
+	loff_t			offset,
+	ssize_t			size)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	if (offset + size <= i_size_read(inode))
+		return 0;
+
+	spin_lock(&ip->i_flags_lock);
+	if (offset + size > i_size_read(inode)) {
+		i_size_write(inode, offset + size);
+		spin_unlock(&ip->i_flags_lock);
+	} else {
+		spin_unlock(&ip->i_flags_lock);
+	}
+
+	return xfs_setfilesize(ip, offset, size);
+}
+
 static int
 xfs_dio_write_end_io(
 	struct kiocb		*iocb,
@@ -623,30 +658,8 @@ xfs_dio_write_end_io(
 	 * with the on-disk inode size being outside the in-core inode size. We
 	 * have no other method of updating EOF for AIO, so always do it here
 	 * if necessary.
-	 *
-	 * We need to lock the test/set EOF update as we can be racing with
-	 * other IO completions here to update the EOF. Failing to serialise
-	 * here can result in EOF moving backwards and Bad Things Happen when
-	 * that occurs.
-	 *
-	 * As IO completion only ever extends EOF, we can do an unlocked check
-	 * here to avoid taking the spinlock. If we land within the current EOF,
-	 * then we do not need to do an extending update at all, and we don't
-	 * need to take the lock to check this. If we race with an update moving
-	 * EOF, then we'll either still be beyond EOF and need to take the lock,
-	 * or we'll be within EOF and we don't need to take it at all.
 	 */
-	if (offset + size <= i_size_read(inode))
-		goto out;
-
-	spin_lock(&ip->i_flags_lock);
-	if (offset + size > i_size_read(inode)) {
-		i_size_write(inode, offset + size);
-		spin_unlock(&ip->i_flags_lock);
-		error = xfs_setfilesize(ip, offset, size);
-	} else {
-		spin_unlock(&ip->i_flags_lock);
-	}
+	error = xfs_dio_endio_set_isize(inode, offset, size);
 
 out:
 	memalloc_nofs_restore(nofs_flag);
-- 
2.53.0

[PATCH 2/4] xfs: move zoned dio ioend to its own function

[cem]

From: Carlos Maiolino <cem@kernel.org>

All zoned dio needs during endio is set the file size, so move it
out of the generic function.

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_file.c | 35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 45ecd743fa32..29b02673111b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -595,6 +595,36 @@ xfs_dio_endio_set_isize(
 	return xfs_setfilesize(ip, offset, size);
 }
 
+static int
+xfs_zoned_dio_write_end_io(
+	struct kiocb		*iocb,
+	ssize_t			size,
+	int			error,
+	unsigned		flags)
+{
+	struct inode		*inode = file_inode(iocb->ki_filp);
+	struct xfs_inode	*ip = XFS_I(inode);
+	unsigned int		nofs_flag;
+
+	ASSERT(!(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
+
+	trace_xfs_end_io_direct_write(ip, iocb->ki_pos, size);
+
+	if (xfs_is_shutdown(ip->i_mount))
+		return -EIO;
+
+	if (error || !size)
+		return error;
+
+	XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size);
+
+	nofs_flag = memalloc_nofs_save();
+	error = xfs_dio_endio_set_isize(inode, iocb->ki_pos, size);
+	memalloc_nofs_restore(nofs_flag);
+
+	return error;
+}
+
 static int
 xfs_dio_write_end_io(
 	struct kiocb		*iocb,
@@ -607,8 +637,7 @@ xfs_dio_write_end_io(
 	loff_t			offset = iocb->ki_pos;
 	unsigned int		nofs_flag;
 
-	ASSERT(!xfs_is_zoned_inode(ip) ||
-	       !(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
+	ASSERT(!xfs_is_zoned_inode(ip));
 
 	trace_xfs_end_io_direct_write(ip, offset, size);
 
@@ -701,7 +730,7 @@ xfs_dio_zoned_submit_io(
 static const struct iomap_dio_ops xfs_dio_zoned_write_ops = {
 	.bio_set	= &iomap_ioend_bioset,
 	.submit_io	= xfs_dio_zoned_submit_io,
-	.end_io		= xfs_dio_write_end_io,
+	.end_io		= xfs_zoned_dio_write_end_io,
 };
 
 /*
-- 
2.53.0

[PATCH 3/4] xfs: factor out xfs_zone_inc_written

[cem]

From: Carlos Maiolino <cem@kernel.org>

Move the written blocks increment and full zone check into a new helper.
Also add an assert to ensure rmap lock is held here.

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_zone_alloc.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index e3d19b6dc64a..97149bfc2512 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -189,6 +189,18 @@ xfs_open_zone_mark_full(
 		xfs_zone_account_reclaimable(rtg, rtg_blocks(rtg) - used);
 }
 
+static inline void
+xfs_zone_inc_written(
+	struct xfs_open_zone	*oz,
+	xfs_filblks_t		len)
+{
+	xfs_assert_ilocked(rtg_rmap(oz->oz_rtg), XFS_ILOCK_EXCL);
+
+	oz->oz_written += len;
+	if (oz->oz_written == rtg_blocks(oz->oz_rtg))
+		xfs_open_zone_mark_full(oz);
+}
+
 static void
 xfs_zone_record_blocks(
 	struct xfs_trans	*tp,
@@ -206,9 +218,7 @@ xfs_zone_record_blocks(
 	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
 	rmapip->i_used_blocks += len;
 	ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg));
-	oz->oz_written += len;
-	if (oz->oz_written == rtg_blocks(rtg))
-		xfs_open_zone_mark_full(oz);
+	xfs_zone_inc_written(oz, len);
 	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
 }
 
@@ -227,9 +237,7 @@ xfs_zone_skip_blocks(
 	trace_xfs_zone_skip_blocks(oz, 0, len);
 
 	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
-	oz->oz_written += len;
-	if (oz->oz_written == rtg_blocks(rtg))
-		xfs_open_zone_mark_full(oz);
+	xfs_zone_inc_written(oz, len);
 	xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 
 	xfs_add_frextents(rtg_mount(rtg), len);
-- 
2.53.0

[PATCH 4/4] xfs: opencode xfs_zone_record_blocks

[cem]

From: Carlos Maiolino <cem@kernel.org>

We only have a single caller, no need to keep it in its own function.

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_zone_alloc.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 97149bfc2512..7d712d5a5ce0 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -201,27 +201,6 @@ xfs_zone_inc_written(
 		xfs_open_zone_mark_full(oz);
 }
 
-static void
-xfs_zone_record_blocks(
-	struct xfs_trans	*tp,
-	struct xfs_open_zone	*oz,
-	xfs_fsblock_t		fsbno,
-	xfs_filblks_t		len)
-{
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_rtgroup	*rtg = oz->oz_rtg;
-	struct xfs_inode	*rmapip = rtg_rmap(rtg);
-
-	trace_xfs_zone_record_blocks(oz, xfs_rtb_to_rgbno(mp, fsbno), len);
-
-	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
-	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
-	rmapip->i_used_blocks += len;
-	ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg));
-	xfs_zone_inc_written(oz, len);
-	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
-}
-
 /*
  * Called for blocks that have been written to disk, but not actually linked to
  * an inode, which can happen when garbage collection races with user data
@@ -252,6 +231,8 @@ xfs_zoned_map_extent(
 	xfs_fsblock_t		old_startblock)
 {
 	struct xfs_bmbt_irec	data;
+	struct xfs_rtgroup	*rtg = oz->oz_rtg;
+	struct xfs_inode	*rmapip = rtg_rmap(rtg);
 	int			nmaps = 1;
 	int			error;
 
@@ -310,7 +291,12 @@ xfs_zoned_map_extent(
 		}
 	}
 
-	xfs_zone_record_blocks(tp, oz, new->br_startblock, new->br_blockcount);
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
+	rmapip->i_used_blocks += new->br_blockcount;
+	ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg));
+	xfs_zone_inc_written(oz, new->br_blockcount);
+	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
 
 	/* Map the new blocks into the data fork. */
 	xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new);
-- 
2.53.0

Re: [PATCH 1/4] xfs: factor out isize updates from xfs_dio_write_end_io

[Damien Le Moal]

On 2026/03/10 12:55, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
> 
> This is the only code needed for zoned inodes, so factor it out so
> we can move zoned inodes ioend to its own callback.
> 
> Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
> ---
>  fs/xfs/xfs_file.c | 59 +++++++++++++++++++++++++++++------------------
>  1 file changed, 36 insertions(+), 23 deletions(-)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 6246f34df9fd..45ecd743fa32 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -560,6 +560,41 @@ xfs_zoned_write_space_reserve(
>  			flags, ac);
>  }
>  
> +/*
> + * We need to lock the test/set EOF update as we can be racing with
> + * other IO completions here to update the EOF. Failing to serialise
> + * here can result in EOF moving backwards and Bad Things Happen when
> + * that occurs.
> + *
> + * As IO completion only ever extends EOF, we can do an unlocked check
> + * here to avoid taking the spinlock. If we land within the current EOF,
> + * then we do not need to do an extending update at all, and we don't
> + * need to take the lock to check this. If we race with an update moving
> + * EOF, then we'll either still be beyond EOF and need to take the lock,
> + * or we'll be within EOF and we don't need to take it at all.
> + */
> +static int
> +xfs_dio_endio_set_isize(
> +	struct inode		*inode,
> +	loff_t			offset,
> +	ssize_t			size)
> +{
> +	struct xfs_inode	*ip = XFS_I(inode);
> +
> +	if (offset + size <= i_size_read(inode))
> +		return 0;
> +
> +	spin_lock(&ip->i_flags_lock);
> +	if (offset + size > i_size_read(inode)) {
> +		i_size_write(inode, offset + size);
> +		spin_unlock(&ip->i_flags_lock);
> +	} else {
> +		spin_unlock(&ip->i_flags_lock);
> +	}

The spinlock unlock does not need to be inside the if and else:

+	spin_lock(&ip->i_flags_lock);
+	if (offset + size > i_size_read(inode))
+		i_size_write(inode, offset + size);
+	spin_unlock(&ip->i_flags_lock);

Other than this, looks OK to me.

> +
> +	return xfs_setfilesize(ip, offset, size);
> +}
> +
>  static int
>  xfs_dio_write_end_io(
>  	struct kiocb		*iocb,
> @@ -623,30 +658,8 @@ xfs_dio_write_end_io(
>  	 * with the on-disk inode size being outside the in-core inode size. We
>  	 * have no other method of updating EOF for AIO, so always do it here
>  	 * if necessary.
> -	 *
> -	 * We need to lock the test/set EOF update as we can be racing with
> -	 * other IO completions here to update the EOF. Failing to serialise
> -	 * here can result in EOF moving backwards and Bad Things Happen when
> -	 * that occurs.
> -	 *
> -	 * As IO completion only ever extends EOF, we can do an unlocked check
> -	 * here to avoid taking the spinlock. If we land within the current EOF,
> -	 * then we do not need to do an extending update at all, and we don't
> -	 * need to take the lock to check this. If we race with an update moving
> -	 * EOF, then we'll either still be beyond EOF and need to take the lock,
> -	 * or we'll be within EOF and we don't need to take it at all.
>  	 */
> -	if (offset + size <= i_size_read(inode))
> -		goto out;
> -
> -	spin_lock(&ip->i_flags_lock);
> -	if (offset + size > i_size_read(inode)) {
> -		i_size_write(inode, offset + size);
> -		spin_unlock(&ip->i_flags_lock);
> -		error = xfs_setfilesize(ip, offset, size);
> -	} else {
> -		spin_unlock(&ip->i_flags_lock);
> -	}
> +	error = xfs_dio_endio_set_isize(inode, offset, size);
>  
>  out:
>  	memalloc_nofs_restore(nofs_flag);


-- 
Damien Le Moal
Western Digital Research

Re: [PATCH 1/4] xfs: factor out isize updates from xfs_dio_write_end_io

[Christoph Hellwig]

On Tue, Mar 10, 2026 at 12:55:04PM +0100, cem@kernel.org wrote:
> +static int
> +xfs_dio_endio_set_isize(
> +	struct inode		*inode,
> +	loff_t			offset,
> +	ssize_t			size)
> +{
> +	struct xfs_inode	*ip = XFS_I(inode);
> +
> +	if (offset + size <= i_size_read(inode))
> +		return 0;
> +
> +	spin_lock(&ip->i_flags_lock);
> +	if (offset + size > i_size_read(inode)) {
> +		i_size_write(inode, offset + size);
> +		spin_unlock(&ip->i_flags_lock);
> +	} else {
> +		spin_unlock(&ip->i_flags_lock);
> +	}
> +
> +	return xfs_setfilesize(ip, offset, size);

This now calls xfs_setfilesize for the case where we don't update
the inode size.  This looks harmless to be, but isn't needed.

This should become something like:

	if (offset + size <= i_size_read(inode)) {
		spin_unlock(&ip->i_flags_lock);
		return 0;
	}
	i_size_write(inode, offset + size);
	spin_unlock(&ip->i_flags_lock);
	return xfs_setfilesize(ip, offset, size);

Re: [PATCH 2/4] xfs: move zoned dio ioend to its own function

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/4] xfs: factor out xfs_zone_inc_written

[Christoph Hellwig]

On Tue, Mar 10, 2026 at 12:55:06PM +0100, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
> 
> Move the written blocks increment and full zone check into a new helper.
> Also add an assert to ensure rmap lock is held here.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/4] xfs: move zoned dio ioend to its own function

[Damien Le Moal]

On 2026/03/10 12:55, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
> 
> All zoned dio needs during endio is set the file size, so move it
> out of the generic function.

"move" is unclear here since this patch is adding code but not deleting
anything. Maye be rephrase this ?

> 
> Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
> ---
>  fs/xfs/xfs_file.c | 35 ++++++++++++++++++++++++++++++++---
>  1 file changed, 32 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 45ecd743fa32..29b02673111b 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -595,6 +595,36 @@ xfs_dio_endio_set_isize(
>  	return xfs_setfilesize(ip, offset, size);
>  }
>  
> +static int
> +xfs_zoned_dio_write_end_io(
> +	struct kiocb		*iocb,
> +	ssize_t			size,
> +	int			error,
> +	unsigned		flags)
> +{
> +	struct inode		*inode = file_inode(iocb->ki_filp);
> +	struct xfs_inode	*ip = XFS_I(inode);
> +	unsigned int		nofs_flag;
> +
> +	ASSERT(!(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
> +
> +	trace_xfs_end_io_direct_write(ip, iocb->ki_pos, size);
> +
> +	if (xfs_is_shutdown(ip->i_mount))
> +		return -EIO;
> +
> +	if (error || !size)
> +		return error;
> +
> +	XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size);
> +
> +	nofs_flag = memalloc_nofs_save();
> +	error = xfs_dio_endio_set_isize(inode, iocb->ki_pos, size);
> +	memalloc_nofs_restore(nofs_flag);
> +
> +	return error;
> +}
> +
>  static int
>  xfs_dio_write_end_io(
>  	struct kiocb		*iocb,
> @@ -607,8 +637,7 @@ xfs_dio_write_end_io(
>  	loff_t			offset = iocb->ki_pos;
>  	unsigned int		nofs_flag;
>  
> -	ASSERT(!xfs_is_zoned_inode(ip) ||
> -	       !(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
> +	ASSERT(!xfs_is_zoned_inode(ip));
>  
>  	trace_xfs_end_io_direct_write(ip, offset, size);
>  
> @@ -701,7 +730,7 @@ xfs_dio_zoned_submit_io(
>  static const struct iomap_dio_ops xfs_dio_zoned_write_ops = {
>  	.bio_set	= &iomap_ioend_bioset,
>  	.submit_io	= xfs_dio_zoned_submit_io,
> -	.end_io		= xfs_dio_write_end_io,
> +	.end_io		= xfs_zoned_dio_write_end_io,
>  };
>  
>  /*


-- 
Damien Le Moal
Western Digital Research

Re: [PATCH 4/4] xfs: opencode xfs_zone_record_blocks

[Christoph Hellwig]

On Tue, Mar 10, 2026 at 12:55:07PM +0100, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
> 
> We only have a single caller, no need to keep it in its own function.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/4] xfs: factor out xfs_zone_inc_written

[Damien Le Moal]

On 2026/03/10 12:55, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
> 
> Move the written blocks increment and full zone check into a new helper.
> Also add an assert to ensure rmap lock is held here.
> 
> Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>


-- 
Damien Le Moal
Western Digital Research

Re: [PATCH 4/4] xfs: opencode xfs_zone_record_blocks

[Damien Le Moal]

On 2026/03/10 12:55, cem@kernel.org wrote:
> From: Carlos Maiolino <cem@kernel.org>
> 
> We only have a single caller, no need to keep it in its own function.
> 
> Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>


-- 
Damien Le Moal
Western Digital Research