[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241022111059.2566137-25-yi.zhang@huaweicloud.com>
Date: Tue, 22 Oct 2024 19:10:55 +0800
From: Zhang Yi <yi.zhang@...weicloud.com>
To: linux-ext4@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org,
linux-kernel@...r.kernel.org,
tytso@....edu,
adilger.kernel@...ger.ca,
jack@...e.cz,
ritesh.list@...il.com,
hch@...radead.org,
djwong@...nel.org,
david@...morbit.com,
zokeefe@...gle.com,
yi.zhang@...wei.com,
yi.zhang@...weicloud.com,
chengzhihao1@...wei.com,
yukuai3@...wei.com,
yangerkun@...wei.com
Subject: [PATCH 24/27] ext4: partially enable iomap for the buffered I/O path of regular files
From: Zhang Yi <yi.zhang@...wei.com>
Partially enable iomap for the buffered I/O path of regular files with
the default mount option. This supports default filesystem features and
the bigalloc feature. However, it does not yet support inline data,
fs_verity, fs_crypt, online defrag and data=journal mode. Some of these
features should be supported gradually in the future. The filesystem
will fallback to the buffered_head path automatically if these mount
options or features are enabled.
Signed-off-by: Zhang Yi <yi.zhang@...wei.com>
---
fs/ext4/ext4.h | 1 +
fs/ext4/ialloc.c | 3 +++
fs/ext4/inode.c | 32 ++++++++++++++++++++++++++++++++
3 files changed, 36 insertions(+)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e1b7f7024f07..0096191b454c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2987,6 +2987,7 @@ 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 7f1a5f90dbbd..2e3e257b9808 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1333,6 +1333,9 @@ 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);
+
ext4_update_inode_fsync_trans(handle, inode, 1);
err = ext4_mark_inode_dirty(handle, inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 50e4afd17e93..512094dc4117 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -776,6 +776,8 @@ 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;
@@ -2572,6 +2574,9 @@ 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()
@@ -5144,6 +5149,30 @@ 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 (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)
@@ -5408,6 +5437,9 @@ 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;
--
2.46.1
Powered by blists - more mailing lists