Re: [PATCH 2/5] iomap: use accelerated zeroing on a block device to zero a file range

[riteshh <riteshh@linux.ibm.com>]

On 21/09/17 06:30PM, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
>
> Create a function that ensures that the storage backing part of a file
> contains zeroes and will not trip over old media errors if the contents
> are re-read.
>
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> ---
>  fs/iomap/direct-io.c  |   75 +++++++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/iomap.h |    3 ++
>  2 files changed, 78 insertions(+)
>
>
> diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
> index 4ecd255e0511..48826a49f976 100644
> --- a/fs/iomap/direct-io.c
> +++ b/fs/iomap/direct-io.c
> @@ -652,3 +652,78 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
>  	return iomap_dio_complete(dio);
>  }
>  EXPORT_SYMBOL_GPL(iomap_dio_rw);
> +
> +static loff_t
> +iomap_zeroinit_iter(struct iomap_iter *iter)
> +{
> +	struct iomap *iomap = &iter->iomap;
> +	const struct iomap *srcmap = iomap_iter_srcmap(iter);
> +	const u64 start = iomap->addr + iter->pos - iomap->offset;
> +	const u64 nr_bytes = iomap_length(iter);
> +	sector_t sector = start >> SECTOR_SHIFT;
> +	sector_t nr_sectors = nr_bytes >> SECTOR_SHIFT;
> +	int ret;
> +
> +	if (!iomap->bdev)
> +		return -ECANCELED;
> +
> +	/* The physical extent must be sector-aligned for block layer APIs. */
> +	if ((start | nr_bytes) & (SECTOR_SIZE - 1))
> +		return -EINVAL;
> +
> +	/* Must be able to zero storage directly without fs intervention. */
> +	if (iomap->flags & IOMAP_F_SHARED)
> +		return -ECANCELED;
> +	if (srcmap != iomap)
> +		return -ECANCELED;
> +
> +	switch (iomap->type) {
> +	case IOMAP_MAPPED:
> +		ret = blkdev_issue_zeroout(iomap->bdev, sector, nr_sectors,
> +				GFP_KERNEL, 0);
> +		if (ret)
> +			return ret;
> +		fallthrough;
> +	case IOMAP_UNWRITTEN:
> +		return nr_bytes;
> +	}
> +
> +	/* Reject holes, inline data, or delalloc extents. */
> +	return -ECANCELED;

Same comment here as in patch-1 which implements dax_zeroinit_iter().

-ritesh

> +}
> +
> +/*
> + * Use a storage device's accelerated zero-writing command to ensure the media
> + * are ready to accept read and write commands.  FSDAX is not supported.
> + *
> + * The range arguments must be aligned to sector size.  The file must be backed
> + * by a block device.  The extents returned must not require copy on write (or
> + * any other mapping interventions from the filesystem) and must be contiguous.
> + * @done will be set to true if the reset succeeded.
> + *
> + * Returns 0 if the zero initialization succeeded, -ECANCELED if the storage
> + * mappings do not support zero initialization, -EOPNOTSUPP if the device does
> + * not support it, or the usual negative errno.
> + */
> +int
> +iomap_zeroout_range(struct inode *inode, loff_t pos, u64 len,
> +		   const struct iomap_ops *ops)
> +{
> +	struct iomap_iter iter = {
> +		.inode		= inode,
> +		.pos		= pos,
> +		.len		= len,
> +		.flags		= IOMAP_REPORT,
> +	};
> +	int ret;
> +
> +	if (IS_DAX(inode))
> +		return -EINVAL;
> +	if (pos + len > i_size_read(inode))
> +		return -EINVAL;
> +
> +	while ((ret = iomap_iter(&iter, ops)) > 0)
> +		iter.processed = iomap_zeroinit_iter(&iter);
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(iomap_zeroout_range);
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 24f8489583ca..f4b9c6698388 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -339,6 +339,9 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
>  ssize_t iomap_dio_complete(struct iomap_dio *dio);
>  int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
>
> +int iomap_zeroout_range(struct inode *inode, loff_t pos, u64 len,
> +		const struct iomap_ops *ops);
> +
>  #ifdef CONFIG_SWAP
>  struct file;
>  struct swap_info_struct;
>