From 597599268e3b91cac71faf48743f4783dec682fc Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Sun, 10 Feb 2019 23:26:06 -0500 Subject: jbd2: discard dirty data when forgetting an un-journalled buffer We do not unmap and clear dirty flag when forgetting a buffer without journal or does not belongs to any transaction, so the invalid dirty data may still be written to the disk later. It's fine if the corresponding block is never used before the next mount, and it's also fine that we invoke clean_bdev_aliases() related functions to unmap the block device mapping when re-allocating such freed block as data block. But this logic is somewhat fragile and risky that may lead to data corruption if we forget to clean bdev aliases. So, It's better to discard dirty data during forget time. We have been already handled all the cases of forgetting journalled buffer, this patch deal with the remaining two cases. - buffer is not journalled yet, - buffer is journalled but doesn't belongs to any transaction. We invoke __bforget() instead of __brelese() when forgetting an un-journalled buffer in jbd2_journal_forget(). After this patch we can remove all clean_bdev_aliases() related calls in ext4. Suggested-by: Jan Kara Signed-off-by: zhangyi (F) Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/jbd2/transaction.c | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6f4dff182c91..135f0a10f557 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1597,9 +1597,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) __jbd2_journal_unfile_buffer(jh); if (!buffer_jbd(bh)) { spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); - __bforget(bh); - goto drop; + goto not_jbd; } } spin_unlock(&journal->j_list_lock); @@ -1632,9 +1630,40 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) if (was_modified) drop_reserve = 1; } + } else { + /* + * Finally, if the buffer is not belongs to any + * transaction, we can just drop it now if it has no + * checkpoint. + */ + spin_lock(&journal->j_list_lock); + if (!jh->b_cp_transaction) { + JBUFFER_TRACE(jh, "belongs to none transaction"); + spin_unlock(&journal->j_list_lock); + goto not_jbd; + } + + /* + * Otherwise, if the buffer has been written to disk, + * it is safe to remove the checkpoint and drop it. + */ + if (!buffer_dirty(bh)) { + __jbd2_journal_remove_checkpoint(jh); + spin_unlock(&journal->j_list_lock); + goto not_jbd; + } + + /* + * The buffer is still not written to disk, we should + * attach this buffer to current transaction so that the + * buffer can be checkpointed only after the current + * transaction commits. + */ + clear_buffer_dirty(bh); + __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); + spin_unlock(&journal->j_list_lock); } -not_jbd: jbd_unlock_bh_state(bh); __brelse(bh); drop: @@ -1643,6 +1672,11 @@ drop: handle->h_buffer_credits++; } return err; + +not_jbd: + jbd_unlock_bh_state(bh); + __bforget(bh); + goto drop; } /** -- cgit v1.2.3-58-ga151