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;
From:   Jeffle Xu <jefflexu@linux.alibaba.com>
To:     dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org,
        chao@kernel.org, linux-erofs@lists.ozlabs.org
Cc:     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
Subject: [PATCH v7 18/19] erofs: implement fscache-based data readahead
Date:   Thu, 31 Mar 2022 19:57:52 +0800
Message-Id: <20220331115753.89431-19-jefflexu@linux.alibaba.com>
In-Reply-To: <20220331115753.89431-1-jefflexu@linux.alibaba.com>
References: <20220331115753.89431-1-jefflexu@linux.alibaba.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Implement fscache-based data readahead. Also registers an individual
bdi for each erofs instance to enable readahead.

Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
---
 fs/erofs/fscache.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/erofs/super.c   |  4 ++
 2 files changed, 98 insertions(+)

diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index d32cb5840c6d..620d44210809 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -148,12 +148,106 @@ static int erofs_fscache_readpage(struct file *file, struct page *page)
 	return ret;
 }
 
+static inline 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;
+
+		/*
+		 * 1) For CHUNK_BASED layout, the output m_la is rounded down to
+		 * the nearest chunk boundary, and the output m_llen actually
+		 * starts from the start of the containing chunk.
+		 * 2) For other cases, the output m_la is equal to o_la.
+		 */
+		offset = start + done;
+		count = min_t(size_t, map.m_llen - (pos - map.m_la), len - done);
+
+		/* Read-ahead Hole */
+		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;
+		}
+
+		/* Read-ahead Inline */
+		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;
+		}
+
+		/* Read-ahead No-inline */
+		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;
+		}
+	} 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,
 };
 
 /*
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 8c7181cd37e6..a5e4de60a0d8 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -621,6 +621,10 @@ 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;
 	}
 
 	err = erofs_read_superblock(sb);
-- 
2.27.0