[PATCH v9 20/21] erofs: implement fscache-based data readahead

[Gao Xiang]

On Fri, Apr 15, 2022 at 08:36:13PM +0800, Jeffle Xu wrote:
> Implement fscache-based data readahead. Also registers an individual
> bdi for each erofs instance to enable readahead.
> 
> Signed-off-by: Jeffle Xu <jefflexu at linux.alibaba.com>
> ---
>  fs/erofs/fscache.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++
>  fs/erofs/super.c   |  4 +++
>  2 files changed, 90 insertions(+)
> 
> diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
> index 08849c15500f..eaa50692ddba 100644
> --- a/fs/erofs/fscache.c
> +++ b/fs/erofs/fscache.c
> @@ -163,12 +163,98 @@ static int erofs_fscache_readpage(struct file *file, struct page *page)
>  	return ret;
>  }
>  
> +static void erofs_fscache_unlock_folios(struct readahead_control *rac,
> +					size_t len)
> +{
> +	while (len) {
> +		struct folio *folio = readahead_folio(rac);
> +
> +		len -= folio_size(folio);
> +		folio_mark_uptodate(folio);
> +		folio_unlock(folio);
> +	}
> +}
> +
> +static void erofs_fscache_readahead(struct readahead_control *rac)
> +{
> +	struct inode *inode = rac->mapping->host;
> +	struct super_block *sb = inode->i_sb;
> +	size_t len, count, done = 0;
> +	erofs_off_t pos;
> +	loff_t start, offset;
> +	int ret;
> +
> +	if (!readahead_count(rac))
> +		return;
> +
> +	start = readahead_pos(rac);
> +	len = readahead_length(rac);
> +
> +	do {
> +		struct erofs_map_blocks map;
> +		struct erofs_map_dev mdev;
> +
> +		pos = start + done;
> +		map.m_la = pos;
> +
> +		ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
> +		if (ret)
> +			return;
> +
> +		offset = start + done;
> +		count = min_t(size_t, map.m_llen - (pos - map.m_la),
> +			      len - done);
> +
> +		if (!(map.m_flags & EROFS_MAP_MAPPED)) {
> +			struct iov_iter iter;
> +
> +			iov_iter_xarray(&iter, READ, &rac->mapping->i_pages,
> +					offset, count);
> +			iov_iter_zero(count, &iter);
> +
> +			erofs_fscache_unlock_folios(rac, count);
> +			ret = count;
> +			continue;
> +		}
> +
> +		if (map.m_flags & EROFS_MAP_META) {
> +			struct folio *folio = readahead_folio(rac);
> +
> +			ret = erofs_fscache_readpage_inline(folio, &map);
> +			if (!ret) {
> +				folio_mark_uptodate(folio);
> +				ret = folio_size(folio);
> +			}
> +
> +			folio_unlock(folio);
> +			continue;
> +		}
> +
> +		mdev = (struct erofs_map_dev) {
> +			.m_deviceid = map.m_deviceid,
> +			.m_pa = map.m_pa,
> +		};
> +		ret = erofs_map_dev(sb, &mdev);
> +		if (ret)
> +			return;
> +
> +		ret = erofs_fscache_read_folios(mdev.m_fscache->cookie,
> +				rac->mapping, offset, count,
> +				mdev.m_pa + (pos - map.m_la));
> +		if (!ret) {
> +			erofs_fscache_unlock_folios(rac, count);
> +			ret = count;
> +		}

I think this really needs a comment why we don't need to unlock folios
for the error cases.

Thanks,
Gao Xiang

> +	} while (ret > 0 && ((done += ret) < len));
> +}
> +