Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 26 Apr 2022 13:43:01 +0800
From:   Gao Xiang <hsiangkao@linux.alibaba.com>
To:     Jeffle Xu <jefflexu@linux.alibaba.com>
Cc:     dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org,
        chao@kernel.org, linux-erofs@lists.ozlabs.org,
        torvalds@linux-foundation.org, gregkh@linuxfoundation.org,
        willy@infradead.org, linux-fsdevel@vger.kernel.org,
        joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com,
        tao.peng@linux.alibaba.com, gerry@linux.alibaba.com,
        eguan@linux.alibaba.com, linux-kernel@vger.kernel.org,
        luodaowen.backend@bytedance.com, tianzichen@kuaishou.com,
        fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com,
        zhujia.zj@bytedance.com
Subject: Re: [PATCH v10 20/21] erofs: implement fscache-based data readahead
Message-ID: <YmeGZZHnbrQy4pnR@B-P7TQMD6M-0146.local>
Mail-Followup-To: Jeffle Xu <jefflexu@linux.alibaba.com>,
        dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org,
        chao@kernel.org, linux-erofs@lists.ozlabs.org,
        torvalds@linux-foundation.org, gregkh@linuxfoundation.org,
        willy@infradead.org, linux-fsdevel@vger.kernel.org,
        joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com,
        tao.peng@linux.alibaba.com, gerry@linux.alibaba.com,
        eguan@linux.alibaba.com, linux-kernel@vger.kernel.org,
        luodaowen.backend@bytedance.com, tianzichen@kuaishou.com,
        fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com,
        zhujia.zj@bytedance.com
References: <20220425122143.56815-1-jefflexu@linux.alibaba.com>
 <20220425122143.56815-21-jefflexu@linux.alibaba.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20220425122143.56815-21-jefflexu@linux.alibaba.com>
Precedence: bulk

On Mon, Apr 25, 2022 at 08:21:42PM +0800, Jeffle Xu wrote:
> Implement fscache-based data readahead. Also registers an individual
                                               ^ register

> bdi for each erofs instance to enable readahead.
> 
> Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>

Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>

Thanks,
Gao Xiang

> ---
>  fs/erofs/fscache.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++
>  fs/erofs/super.c   |  4 +++
>  2 files changed, 94 insertions(+)
> 
> diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
> index 5b779812a5ee..a402d8f0a063 100644
> --- a/fs/erofs/fscache.c
> +++ b/fs/erofs/fscache.c
> @@ -162,12 +162,102 @@ 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));
> +		/*
> +		 * For the error cases, the folios will be unlocked when
> +		 * .readahead() returns.
> +		 */
> +		if (!ret) {
> +			erofs_fscache_unlock_folios(rac, count);
> +			ret = count;
> +		}
> +	} while (ret > 0 && ((done += ret) < len));
> +}
> +
>  static const struct address_space_operations erofs_fscache_meta_aops = {
>  	.readpage = erofs_fscache_meta_readpage,
>  };
>  
>  const struct address_space_operations erofs_fscache_access_aops = {
>  	.readpage = erofs_fscache_readpage,
> +	.readahead = erofs_fscache_readahead,
>  };
>  
>  int erofs_fscache_register_cookie(struct super_block *sb,
> diff --git a/fs/erofs/super.c b/fs/erofs/super.c
> index c6755bcae4a6..f68ba929100d 100644
> --- a/fs/erofs/super.c
> +++ b/fs/erofs/super.c
> @@ -619,6 +619,10 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
>  						    sbi->opt.fsid, true);
>  		if (err)
>  			return err;
> +
> +		err = super_setup_bdi(sb);
> +		if (err)
> +			return err;
>  	} else {
>  		if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) {
>  			erofs_err(sb, "failed to set erofs blksize");
> -- 
> 2.27.0