Received-SPF: pass (google.com: domain of linux-ext4+bounces-973-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Zhang Yi <yi.zhang@huaweicloud.com>
To: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	tytso@mit.edu,
	adilger.kernel@dilger.ca,
	jack@suse.cz,
	ritesh.list@gmail.com,
	hch@infradead.org,
	djwong@kernel.org,
	willy@infradead.org,
	zokeefe@google.com,
	yi.zhang@huawei.com,
	yi.zhang@huaweicloud.com,
	chengzhihao1@huawei.com,
	yukuai3@huawei.com,
	wangkefeng.wang@huawei.com
Subject: [RFC PATCH v3 24/26] ext4: partially enable iomap for regular file's buffered IO path
Date: Sat, 27 Jan 2024 09:58:23 +0800
Message-Id: <20240127015825.1608160-25-yi.zhang@huaweicloud.com>
In-Reply-To: <20240127015825.1608160-1-yi.zhang@huaweicloud.com>
References: <20240127015825.1608160-1-yi.zhang@huaweicloud.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Zhang Yi <yi.zhang@huawei.com>

Partially enable iomap for regular file's buffered IO path on default
mount option and default filesystem features. Set inode state flag
EXT4_STATE_BUFFERED_IOMAP when creating one inode to indicate that this
inode choice the iomap path.

Now it still have many limitations, it doesn't support inline data,
fs_verity, fs_crypt, defrag, bigalloc, dax and data=journal mode yet, so
we have to fallback to buffered_head path if these options/features were
enabled. I hope these would be supported gradually in the future.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/ext4/ext4.h   |  1 +
 fs/ext4/ialloc.c |  3 +++
 fs/ext4/inode.c  | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index eaf29bade606..16dce8701c5e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2972,6 +2972,7 @@ int ext4_walk_page_buffers(handle_t *handle,
 				     struct buffer_head *bh));
 int do_journal_get_write_access(handle_t *handle, struct inode *inode,
 				struct buffer_head *bh);
+bool ext4_should_use_buffered_iomap(struct inode *inode);
 int ext4_nonda_switch(struct super_block *sb);
 #define FALL_BACK_TO_NONDELALLOC 1
 #define CONVERT_INLINE_DATA	 2
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index e9bbb1da2d0a..956b9d69c559 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1336,6 +1336,9 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 		}
 	}
 
+	if (ext4_should_use_buffered_iomap(inode))
+		ext4_set_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+
 	if (ext4_handle_valid(handle)) {
 		ei->i_sync_tid = handle->h_transaction->t_tid;
 		ei->i_datasync_tid = handle->h_transaction->t_tid;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f8e9f566ef6a..30067775e828 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -774,6 +774,8 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 	if (ext4_has_inline_data(inode))
 		return -ERANGE;
+	if (WARN_ON(ext4_test_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP)))
+		return -EINVAL;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
@@ -2552,6 +2554,9 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (WARN_ON(ext4_test_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP)))
+		return -EINVAL;
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -5089,6 +5094,32 @@ static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags)
 	return NULL;
 }
 
+bool ext4_should_use_buffered_iomap(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (ext4_has_feature_inline_data(sb))
+		return false;
+	if (ext4_has_feature_verity(sb))
+		return false;
+	if (ext4_has_feature_bigalloc(sb))
+		return false;
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return false;
+	if (!S_ISREG(inode->i_mode))
+		return false;
+	if (IS_DAX(inode))
+		return false;
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return false;
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
+		return false;
+	if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT))
+		return false;
+
+	return true;
+}
+
 struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 			  ext4_iget_flags flags, const char *function,
 			  unsigned int line)
@@ -5353,6 +5384,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	if (ret)
 		goto bad_inode;
 
+	if (ext4_should_use_buffered_iomap(inode))
+		ext4_set_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
-- 
2.39.2