From: yangerkun yangerkun@huawei.com
mainline inclusion from mainline-v6.12-rc1 commit 59efe53e380ee305ec11378233adb6aaebe1856c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAU1DM
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
Any extending write for ext4 requires the inode to be placed on the orphan list before the actual write. In addition, the inode can be actually removed from the orphan list only after all writes are completed. Otherwise we'd leave allocated blocks beyond i_disksize if we could not copy all the data into allocated block and e2fsck would complain.
Currently, direct IO and buffered IO comply with this logic(buffered IO will truncate all overflow allocated blocks that has not been written successfully, and direct IO will truncate all allocated blocks when error occurs). However, dax write break this since dax write will remove the inode from the orphan list by calling ext4_handle_inode_extension unconditionally during extending write.
We add a argument to help determine does we do a fully write, and for the case not fully write, we leave the inode on the orphan list, and the latter ext4_inode_extension_cleanup will help us truncate the overflow allocated blocks, and then remove the inode from the orphan list.
Signed-off-by: yangerkun yangerkun@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://patch.msgid.link/20240829110222.126685-1-yangerkun@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Zhihao Cheng chengzhihao1@huawei.com --- fs/ext4/file.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ffa6bb50d23e..90c8f5d675a5 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -283,7 +283,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, }
static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, - ssize_t count) + ssize_t written, ssize_t count) { handle_t *handle;
@@ -292,7 +292,7 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, if (IS_ERR(handle)) return PTR_ERR(handle);
- if (ext4_update_inode_size(inode, offset + count)) { + if (ext4_update_inode_size(inode, offset + written)) { int ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) { ext4_journal_stop(handle); @@ -300,11 +300,11 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, } }
- if (inode->i_nlink) + if ((written == count) && inode->i_nlink) ext4_orphan_del(handle, inode); ext4_journal_stop(handle);
- return count; + return written; }
/* @@ -370,7 +370,7 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) && pos + size <= i_size_read(inode)) return size; - return ext4_handle_inode_extension(inode, pos, size); + return ext4_handle_inode_extension(inode, pos, size, size); }
static const struct iomap_dio_ops ext4_dio_write_ops = { @@ -642,7 +642,7 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
if (extend) { - ret = ext4_handle_inode_extension(inode, offset, ret); + ret = ext4_handle_inode_extension(inode, offset, ret, count); ext4_inode_extension_cleanup(inode, ret < (ssize_t)count); } out: