Re: [PATCH] erofs: support direct IO for uncompressed file

[Gao Xiang <hsiangkao@redhat.com>]

Hi Jianan,

On Mon, Dec 14, 2020 at 10:04:27PM +0800, Huang Jianan wrote:
> direct IO is useful in certain scenarios for uncompressed files.
> For example, it can avoid double pagecache when use the uncompressed
> file to mount upper layer filesystem.
> 
> In addition, another patch adds direct IO test for the stress tool
> which was mentioned here:
> https://lore.kernel.org/linux-erofs/20200206135631.1491-1-hsiangkao@aol.com/
> 
> Signed-off-by: Huang Jianan <huangjianan@oppo.com>
> Signed-off-by: Guo Weichao <guoweichao@oppo.com>
> ---
>  fs/erofs/data.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 57 insertions(+)
> 
> diff --git a/fs/erofs/data.c b/fs/erofs/data.c
> index ea4f693bee22..3067aa3defff 100644
> --- a/fs/erofs/data.c
> +++ b/fs/erofs/data.c
> @@ -6,6 +6,8 @@
>   */
>  #include "internal.h"
>  #include <linux/prefetch.h>
> +#include <linux/uio.h>
> +#include <linux/blkdev.h>
>  
>  #include <trace/events/erofs.h>
>  
> @@ -312,6 +314,60 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
>  		submit_bio(bio);
>  }
>  
> +static int erofs_get_block(struct inode *inode, sector_t iblock,
> +			   struct buffer_head *bh, int create)
> +{
> +	struct erofs_map_blocks map = {
> +		.m_la = blknr_to_addr(iblock),
> +	};
> +	int err;
> +
> +	err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
> +	if (err)
> +		return err;
> +
> +	if (map.m_flags & EROFS_MAP_MAPPED)
> +		map_bh(bh, inode->i_sb, erofs_blknr(map.m_pa));
> +
> +	return err;
> +}
> +
> +static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
> +			   loff_t offset)
> +{
> +	unsigned i_blkbits = READ_ONCE(inode->i_blkbits);

It would be better to fold in check_direct_IO, also the READ_ONCE above
is somewhat weird...

No rush here, since 5.11-rc1 haven't be out yet, we have >= 2 months to
work it out.

Thanks,
Gao Xiang

> +	unsigned blkbits = i_blkbits;
> +	unsigned blocksize_mask = (1 << blkbits) - 1;
> +	unsigned long align = offset | iov_iter_alignment(iter);
> +	struct block_device *bdev = inode->i_sb->s_bdev;
> +
> +	if (align & blocksize_mask) {
> +		if (bdev)
> +			blkbits = blksize_bits(bdev_logical_block_size(bdev));
> +		blocksize_mask = (1 << blkbits) - 1;
> +		if (align & blocksize_mask)
> +			return -EINVAL;
> +		return 1;
> +	}
> +	return 0;
> +}
> +
> +static ssize_t erofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
> +{
> +	struct address_space *mapping = iocb->ki_filp->f_mapping;
> +	struct inode *inode = mapping->host;
> +	loff_t offset = iocb->ki_pos;
> +	int err;
> +
> +	err = check_direct_IO(inode, iter, offset);
> +	if (err)
> +		return err < 0 ? err : 0;
> +
> +	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
> +				    erofs_get_block, NULL, NULL,
> +				    DIO_LOCKING | DIO_SKIP_HOLES);
> +}
> +
>  static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
>  {
>  	struct inode *inode = mapping->host;
> @@ -336,6 +392,7 @@ static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
>  const struct address_space_operations erofs_raw_access_aops = {
>  	.readpage = erofs_raw_access_readpage,
>  	.readahead = erofs_raw_access_readahead,
> +	.direct_IO = erofs_direct_IO,
>  	.bmap = erofs_bmap,
>  };
>  
> -- 
> 2.25.1
>