ocfs2: Switch over to JBD2.

ocfs2 wants JBD2 for many reasons, not the least of which is that JBD is
limiting our maximum filesystem size.

It's a pretty trivial change.  Most functions are just renamed.  The
only functional change is moving to Jan's inode-based ordered data mode.
It's better, too.

Because JBD2 reads and writes JBD journals, this is compatible with any
existing filesystem.  It can even interact with JBD-based ocfs2 as long
as the journal is formated for JBD.

We provide a compatibility option so that paranoid people can still use
JBD for the time being.  This will go away shortly.

[ Moved call of ocfs2_begin_ordered_truncate() from ocfs2_delete_inode() to
  ocfs2_truncate_for_delete(). --Mark ]

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

fs/Kconfig

@@ -220,17 +220,16 @@ config JBD
 	tristate
 	help
 	  This is a generic journalling layer for block devices.  It is
-	  currently used by the ext3 and OCFS2 file systems, but it could
-	  also be used to add journal support to other file systems or block
+	  currently used by the ext3 file system, but it could also be
+	  used to add journal support to other file systems or block
 	  devices such as RAID or LVM.
 
-	  If you are using the ext3 or OCFS2 file systems, you need to
-	  say Y here. If you are not using ext3 OCFS2 then you will probably
-	  want to say N.
+	  If you are using the ext3 file system, you need to say Y here.
+	  If you are not using ext3 then you will probably want to say N.
 
 	  To compile this device as a module, choose M here: the module will be
-	  called jbd.  If you are compiling ext3 or OCFS2 into the kernel,
-	  you cannot compile this code as a module.
+	  called jbd.  If you are compiling ext3 into the kernel, you
+	  cannot compile this code as a module.
 
 config JBD_DEBUG
 	bool "JBD (ext3) debugging support"
@@ -254,15 +253,16 @@ config JBD2
 	help
 	  This is a generic journaling layer for block devices that support
 	  both 32-bit and 64-bit block numbers.  It is currently used by
-	  the ext4 filesystem, but it could also be used to add
+	  the ext4 and OCFS2 filesystems, but it could also be used to add
 	  journal support to other file systems or block devices such
 	  as RAID or LVM.
 
-	  If you are using ext4, you need to say Y here. If you are not
-	  using ext4 then you will probably want to say N.
+	  If you are using ext4 or OCFS2, you need to say Y here.
+	  If you are not using ext4 or OCFS2 then you will
+	  probably want to say N.
 
 	  To compile this device as a module, choose M here. The module will be
-	  called jbd2.  If you are compiling ext4 into the kernel,
+	  called jbd2.  If you are compiling ext4 or OCFS2 into the kernel,
 	  you cannot compile this code as a module.
 
 config JBD2_DEBUG
@@ -440,7 +440,7 @@ config OCFS2_FS
 	tristate "OCFS2 file system support"
 	depends on NET && SYSFS
 	select CONFIGFS_FS
-	select JBD
+	select JBD2
 	select CRC32
 	help
 	  OCFS2 is a general purpose extent based shared disk cluster file
@@ -511,6 +511,16 @@ config OCFS2_DEBUG_FS
 	  this option for debugging only as it is likely to decrease
 	  performance of the filesystem.
 
+config OCFS2_COMPAT_JBD
+	bool "Use JBD for compatibility"
+	depends on OCFS2_FS
+	default n
+	select JBD
+	help
+	  The ocfs2 filesystem now uses JBD2 for its journalling.  JBD2
+	  is backwards compatible with JBD.  It is safe to say N here.
+	  However, if you really want to use the original JBD, say Y here.
+
 endif # BLOCK
 
 config DNOTIFY

fs/ocfs2/alloc.c

@@ -6421,20 +6421,13 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb,
 	return status;
 }
 
-static int ocfs2_writeback_zero_func(handle_t *handle, struct buffer_head *bh)
+static int ocfs2_zero_func(handle_t *handle, struct buffer_head *bh)
 {
 	set_buffer_uptodate(bh);
 	mark_buffer_dirty(bh);
 	return 0;
 }
 
-static int ocfs2_ordered_zero_func(handle_t *handle, struct buffer_head *bh)
-{
-	set_buffer_uptodate(bh);
-	mark_buffer_dirty(bh);
-	return ocfs2_journal_dirty_data(handle, bh);
-}
-
 static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
 				     unsigned int from, unsigned int to,
 				     struct page *page, int zero, u64 *phys)
@@ -6453,17 +6446,18 @@ static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
 	 * here if they aren't - ocfs2_map_page_blocks()
 	 * might've skipped some
 	 */
-	if (ocfs2_should_order_data(inode)) {
-		ret = walk_page_buffers(handle,
-					page_buffers(page),
-					from, to, &partial,
-					ocfs2_ordered_zero_func);
-		if (ret < 0)
-			mlog_errno(ret);
-	} else {
+	ret = walk_page_buffers(handle, page_buffers(page),
+				from, to, &partial,
+				ocfs2_zero_func);
+	if (ret < 0)
+		mlog_errno(ret);
+	else if (ocfs2_should_order_data(inode)) {
+		ret = ocfs2_jbd2_file_inode(handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
 		ret = walk_page_buffers(handle, page_buffers(page),
 					from, to, &partial,
-					ocfs2_writeback_zero_func);
+					ocfs2_journal_dirty_data);
+#endif
 		if (ret < 0)
 			mlog_errno(ret);
 	}

fs/ocfs2/aops.c

@@ -485,11 +485,14 @@ handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 	}
 
 	if (ocfs2_should_order_data(inode)) {
+		ret = ocfs2_jbd2_file_inode(handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
 		ret = walk_page_buffers(handle,
 					page_buffers(page),
 					from, to, NULL,
 					ocfs2_journal_dirty_data);
-		if (ret < 0) 
+#endif
+		if (ret < 0)
 			mlog_errno(ret);
 	}
 out:
@@ -669,7 +672,7 @@ static void ocfs2_invalidatepage(struct page *page, unsigned long offset)
 {
 	journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
 
-	journal_invalidatepage(journal, page, offset);
+	jbd2_journal_invalidatepage(journal, page, offset);
 }
 
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
@@ -678,7 +681,7 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 
 	if (!page_has_buffers(page))
 		return 0;
-	return journal_try_to_free_buffers(journal, page, wait);
+	return jbd2_journal_try_to_free_buffers(journal, page, wait);
 }
 
 static ssize_t ocfs2_direct_IO(int rw,
@@ -1074,11 +1077,15 @@ static void ocfs2_write_failure(struct inode *inode,
 		tmppage = wc->w_pages[i];
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode))
+			if (ocfs2_should_order_data(inode)) {
+				ocfs2_jbd2_file_inode(wc->w_handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
 				walk_page_buffers(wc->w_handle,
 						  page_buffers(tmppage),
 						  from, to, NULL,
 						  ocfs2_journal_dirty_data);
+#endif
+			}
 
 			block_commit_write(tmppage, from, to);
 		}
@@ -1917,11 +1924,15 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode))
+			if (ocfs2_should_order_data(inode)) {
+				ocfs2_jbd2_file_inode(wc->w_handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
 				walk_page_buffers(wc->w_handle,
 						  page_buffers(tmppage),
 						  from, to, NULL,
 						  ocfs2_journal_dirty_data);
+#endif
+			}
 			block_commit_write(tmppage, from, to);
 		}
 	}

fs/ocfs2/file.c

@@ -185,7 +185,7 @@ static int ocfs2_sync_file(struct file *file,
 		goto bail;
 
 	journal = osb->journal->j_journal;
-	err = journal_force_commit(journal);
+	err = jbd2_journal_force_commit(journal);
 
 bail:
 	mlog_exit(err);
@@ -941,9 +941,15 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 			goto bail_unlock;
 		}
 
-		if (i_size_read(inode) > attr->ia_size)
+		if (i_size_read(inode) > attr->ia_size) {
+			if (ocfs2_should_order_data(inode)) {
+				status = ocfs2_begin_ordered_truncate(inode,
+								      attr->ia_size);
+				if (status)
+					goto bail_unlock;
+			}
 			status = ocfs2_truncate_file(inode, bh, attr->ia_size);
-		else
+		} else
 			status = ocfs2_extend_file(inode, bh, attr->ia_size);
 		if (status < 0) {
 			if (status != -ENOSPC)
@@ -1888,7 +1894,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		 */
 		if (old_size != i_size_read(inode) ||
 		    old_clusters != OCFS2_I(inode)->ip_clusters) {
-			ret = journal_force_commit(osb->journal->j_journal);
+			ret = jbd2_journal_force_commit(osb->journal->j_journal);
 			if (ret < 0)
 				written = ret;
 		}

fs/ocfs2/inode.c

@@ -534,6 +534,9 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 	 * data and fast symlinks.
 	 */
 	if (fe->i_clusters) {
+		if (ocfs2_should_order_data(inode))
+			ocfs2_begin_ordered_truncate(inode, 0);
+
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
@@ -1100,6 +1103,8 @@ void ocfs2_clear_inode(struct inode *inode)
 	oi->ip_last_trans = 0;
 	oi->ip_dir_start_lookup = 0;
 	oi->ip_blkno = 0ULL;
+	jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
+				       &oi->ip_jinode);
 
 bail:
 	mlog_exit_void();

fs/ocfs2/inode.h

@@ -71,6 +71,7 @@ struct ocfs2_inode_info
 	struct ocfs2_extent_map		ip_extent_map;
 
 	struct inode			vfs_inode;
+	struct jbd2_inode		ip_jinode;
 };
 
 /*