[PATCH] ext3: fix data=journal mode

ext3's fully data-journalled mode has been broken for a year.  This patch
fixes it up.

The prepare_write/commit_write/writepage implementations have been split up.
Instead of having each function handle all three journalling mode we now have
three separate sets of address_space_operations.

The problematic part of data=journal is MAP_SHARED writepage traffic: pages
which don't have buffers.  In 2.4 these were cheatingly treated as
data-ordered buffers and that caused several nasty problems.

Here we do it properly: writepage traffic is fully journalled.  This means
that the various workarounds for the 2.4 scheme can be removed, when I
remember where they all are.

The PG_checked flag has been borrowed: it it set in the atomic set_page_dirty
a_op to tell the subsequent writepage() that this page needs to have buffers
attached, dirtied and journalled.

This rather defines PG_checked as "fs-private info in page->flags" and it
should be renamed sometime.

fs/ext3/namei.c

@@ -1644,10 +1644,7 @@ static int ext3_create (struct inode * dir, struct dentry * dentry, int mode)
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext3_file_inode_operations;
 		inode->i_fop = &ext3_file_operations;
-		if (ext3_should_writeback_data(inode))
-			inode->i_mapping->a_ops = &ext3_writeback_aops;
-		else
-			inode->i_mapping->a_ops = &ext3_aops;
+		ext3_set_aops(inode);
 		err = ext3_add_nondir(handle, dentry, inode);
 	}
 	ext3_journal_stop(handle);
@@ -2100,10 +2097,7 @@ static int ext3_symlink (struct inode * dir,
 
 	if (l > sizeof (EXT3_I(inode)->i_data)) {
 		inode->i_op = &ext3_symlink_inode_operations;
-		if (ext3_should_writeback_data(inode))
-			inode->i_mapping->a_ops = &ext3_writeback_aops;
-		else
-			inode->i_mapping->a_ops = &ext3_aops;
+		ext3_set_aops(inode);
 		/*
 		 * page_symlink() calls into ext3_prepare/commit_write.
 		 * We have a transaction open.  All is sweetness.  It also sets

fs/jbd/transaction.c

@@ -1120,7 +1120,6 @@ int journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		/* And this case is illegal: we can't reuse another
 		 * transaction's data buffer, ever. */
 		/* FIXME: writepage() should be journalled */
-		J_ASSERT_JH(jh, jh->b_jlist != BJ_SyncData);
 		goto done_locked;
 	}
 

include/linux/ext3_fs.h

@@ -735,6 +735,7 @@ extern void ext3_dirty_inode(struct inode *);
 extern int ext3_change_inode_journal_flag(struct inode *, int);
 extern void ext3_truncate (struct inode *);
 extern void ext3_set_inode_flags(struct inode *);
+extern void ext3_set_aops(struct inode *inode);
 
 /* ioctl.c */
 extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
@@ -783,10 +784,6 @@ extern struct file_operations ext3_dir_operations;
 extern struct inode_operations ext3_file_inode_operations;
 extern struct file_operations ext3_file_operations;
 
-/* inode.c */
-extern struct address_space_operations ext3_aops;
-extern struct address_space_operations ext3_writeback_aops;
-
 /* namei.c */
 extern struct inode_operations ext3_dir_inode_operations;
 extern struct inode_operations ext3_special_inode_operations;

include/linux/page-flags.h

@@ -200,6 +200,7 @@ extern void get_full_page_state(struct page_state *ret);
 
 #define PageChecked(page)	test_bit(PG_checked, &(page)->flags)
 #define SetPageChecked(page)	set_bit(PG_checked, &(page)->flags)
+#define ClearPageChecked(page)	clear_bit(PG_checked, &(page)->flags)
 
 #define PageReserved(page)	test_bit(PG_reserved, &(page)->flags)
 #define SetPageReserved(page)	set_bit(PG_reserved, &(page)->flags)