On Fri 30-08-24 13:37:38, zhangshida wrote:
> From: Shida Zhang <zhangshida@xxxxxxxxxx>
>
> On an old kernel version(4.19, ext3, data=journal, pagesize=64k),
> an assertion failure will occasionally be triggered by the line below:
> -----------
> jbd2_journal_commit_transaction
> {
> ...
> J_ASSERT_BH(bh, !buffer_dirty(bh));
> /*
> * The buffer on BJ_Forget list and not jbddirty means
> ...
> }
> -----------
>
> The same condition may also be applied to the lattest kernel version.
>
> When blocksize < pagesize and we truncate a file, there can be buffers in
> the mapping tail page beyond i_size. These buffers will be filed to
> transaction's BJ_Forget list by ext4_journalled_invalidatepage() during
> truncation. When the transaction doing truncate starts committing, we can
> grow the file again. This calls __block_write_begin() which allocates new
> blocks under these buffers in the tail page we go through the branch:
>
> if (buffer_new(bh)) {
> clean_bdev_bh_alias(bh);
> if (folio_test_uptodate(folio)) {
> clear_buffer_new(bh);
> set_buffer_uptodate(bh);
> mark_buffer_dirty(bh);
> continue;
> }
> ...
> }
>
> Hence buffers on BJ_Forget list of the committing transaction get marked
> dirty and this triggers the jbd2 assertion.
>
> Teach ext4_block_write_begin() to properly handle files with data
> journalling by avoiding dirtying them directly. Instead of
> folio_zero_new_buffers() we use ext4_journalled_zero_new_buffers() which
> takes care of handling journalling. We also don't need to mark new uptodate
> buffers as dirty in ext4_block_write_begin(). That will be either done
> either by block_commit_write() in case of success or by
> folio_zero_new_buffers() in case of failure.
>
> Reported-by: Baolin Liu <liubaolin@xxxxxxxxxx>
> Suggested-by: Jan Kara <jack@xxxxxxx>
> Signed-off-by: Shida Zhang <zhangshida@xxxxxxxxxx>
Looks good to me. Feel free to add:
Reviewed-by: Jan Kara <jack@xxxxxxx>
Honza
> ---
> fs/ext4/ext4.h | 3 ++-
> fs/ext4/inline.c | 7 ++++---
> fs/ext4/inode.c | 42 ++++++++++++++++++++++++++++++++++--------
> 3 files changed, 40 insertions(+), 12 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index 5f8257b68190..b653bd423b11 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -3851,7 +3851,8 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh)
> return buffer_uptodate(bh);
> }
>
> -extern int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
> +extern int ext4_block_write_begin(handle_t *handle, struct folio *folio,
> + loff_t pos, unsigned len,
> get_block_t *get_block);
> #endif /* __KERNEL__ */
>
> diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
> index 0a1a8431e281..8d5599d5af27 100644
> --- a/fs/ext4/inline.c
> +++ b/fs/ext4/inline.c
> @@ -601,10 +601,11 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
> goto out;
>
> if (ext4_should_dioread_nolock(inode)) {
> - ret = ext4_block_write_begin(folio, from, to,
> + ret = ext4_block_write_begin(handle, folio, from, to,
> ext4_get_block_unwritten);
> } else
> - ret = ext4_block_write_begin(folio, from, to, ext4_get_block);
> + ret = ext4_block_write_begin(handle, folio, from, to,
> + ext4_get_block);
>
> if (!ret && ext4_should_journal_data(inode)) {
> ret = ext4_walk_page_buffers(handle, inode,
> @@ -856,7 +857,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
> goto out;
> }
>
> - ret = ext4_block_write_begin(folio, 0, inline_size,
> + ret = ext4_block_write_begin(NULL, folio, 0, inline_size,
> ext4_da_get_block_prep);
> if (ret) {
> up_read(&EXT4_I(inode)->xattr_sem);
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 4964c67e029e..a28f279fd02f 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -49,6 +49,11 @@
>
> #include <trace/events/ext4.h>
>
> +static void ext4_journalled_zero_new_buffers(handle_t *handle,
> + struct inode *inode,
> + struct folio *folio,
> + unsigned from, unsigned to);
> +
> static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
> struct ext4_inode_info *ei)
> {
> @@ -1041,7 +1046,8 @@ int do_journal_get_write_access(handle_t *handle, struct inode *inode,
> return ret;
> }
>
> -int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
> +int ext4_block_write_begin(handle_t *handle, struct folio *folio,
> + loff_t pos, unsigned len,
> get_block_t *get_block)
> {
> unsigned from = pos & (PAGE_SIZE - 1);
> @@ -1055,6 +1061,7 @@ int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
> struct buffer_head *bh, *head, *wait[2];
> int nr_wait = 0;
> int i;
> + bool should_journal_data = ext4_should_journal_data(inode);
>
> BUG_ON(!folio_test_locked(folio));
> BUG_ON(from > PAGE_SIZE);
> @@ -1084,10 +1091,22 @@ int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
> if (err)
> break;
> if (buffer_new(bh)) {
> + /*
> + * We may be zeroing partial buffers or all new
> + * buffers in case of failure. Prepare JBD2 for
> + * that.
> + */
> + if (should_journal_data)
> + do_journal_get_write_access(handle,
> + inode, bh);
> if (folio_test_uptodate(folio)) {
> - clear_buffer_new(bh);
> + /*
> + * Unlike __block_write_begin() we leave
> + * dirtying of new uptodate buffers to
> + * ->write_end() time or
> + * folio_zero_new_buffers().
> + */
> set_buffer_uptodate(bh);
> - mark_buffer_dirty(bh);
> continue;
> }
> if (block_end > to || block_start < from)
> @@ -1117,7 +1136,11 @@ int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
> err = -EIO;
> }
> if (unlikely(err)) {
> - folio_zero_new_buffers(folio, from, to);
> + if (should_journal_data)
> + ext4_journalled_zero_new_buffers(handle, inode, folio,
> + from, to);
> + else
> + folio_zero_new_buffers(folio, from, to);
> } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
> for (i = 0; i < nr_wait; i++) {
> int err2;
> @@ -1215,10 +1238,11 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
> folio_wait_stable(folio);
>
> if (ext4_should_dioread_nolock(inode))
> - ret = ext4_block_write_begin(folio, pos, len,
> + ret = ext4_block_write_begin(handle, folio, pos, len,
> ext4_get_block_unwritten);
> else
> - ret = ext4_block_write_begin(folio, pos, len, ext4_get_block);
> + ret = ext4_block_write_begin(handle, folio, pos, len,
> + ext4_get_block);
> if (!ret && ext4_should_journal_data(inode)) {
> ret = ext4_walk_page_buffers(handle, inode,
> folio_buffers(folio), from, to,
> @@ -2951,7 +2975,8 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
> if (IS_ERR(folio))
> return PTR_ERR(folio);
>
> - ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
> + ret = ext4_block_write_begin(NULL, folio, pos, len,
> + ext4_da_get_block_prep);
> if (ret < 0) {
> folio_unlock(folio);
> folio_put(folio);
> @@ -6205,7 +6230,8 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
> if (folio_pos(folio) + len > size)
> len = size - folio_pos(folio);
>
> - err = __block_write_begin(&folio->page, 0, len, ext4_get_block);
> + err = ext4_block_write_begin(handle, folio, 0, len,
> + ext4_get_block);
> if (!err) {
> ret = VM_FAULT_SIGBUS;
> if (ext4_journal_folio_buffers(handle, folio, len))
> --
> 2.33.0
>
--
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR
