Ext4:  inverse locking ordering of page_lock and transaction start in delalloc

From: Mingming Cao <cmm@us.ibm.com>

Inverse locking ordering of page_lock and transaction start in delalloc

Signed-off-by: Mingming Cao <cmm@us.ibm.com>

---
 fs/ext4/inode.c     |   95 ++++++++++++++++++++++++++++++++++++----------------
 mm/page-writeback.c |    2 -
 2 files changed, 68 insertions(+), 29 deletions(-)

Index: linux-2.6.26-rc1/fs/ext4/inode.c
===================================================================
--- linux-2.6.26-rc1.orig/fs/ext4/inode.c	2008-05-05 17:10:23.000000000 -0700
+++ linux-2.6.26-rc1/fs/ext4/inode.c	2008-05-05 17:10:23.000000000 -0700
@@ -1412,18 +1412,14 @@ static int ext4_da_get_block_prep(struct
 static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
 {
-	int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
+	int ret;
 	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
 	loff_t disksize = EXT4_I(inode)->i_disksize;
 	handle_t *handle = NULL;
 
-	if (create) {
-		handle = ext4_journal_start(inode, needed_blocks);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			goto out;
-		}
-	}
+	handle = ext4_journal_current_handle();
+	BUG_ON(handle == 0);
+	BUG_ON(create == 0);
 
 	ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
 				   bh_result, create, 0);
@@ -1458,29 +1454,17 @@ static int ext4_da_get_block_write(struc
 		ret = 0;
 	}
 
-out:
-	if (handle && !IS_ERR(handle))
-		ext4_journal_stop(handle);
-
 	return ret;
 }
 /* FIXME!! only support data=writeback mode */
-static int ext4_da_writepage(struct page *page,
+static int __ext4_da_writepage(struct page *page,
 				struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	handle_t *handle = NULL;
 	int ret = 0;
-	int err;
-
-	if (ext4_journal_current_handle())
-		goto out_fail;
 
-	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		goto out_fail;
-	}
+	handle = ext4_journal_current_handle();
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
 		ret = nobh_writepage(page, ext4_get_block, wbc);
@@ -1492,21 +1476,76 @@ static int ext4_da_writepage(struct page
 		ext4_mark_inode_dirty(handle, inode);
 	}
 
-	err = ext4_journal_stop(handle);
-	if (!ret)
-		ret = err;
 	return ret;
+}
+static int ext4_da_writepage(struct page *page,
+				struct writeback_control *wbc)
+{
+	if (!ext4_journal_current_handle())
+		return __ext4_da_writepage(page, wbc);
 
-out_fail:
 	redirty_page_for_writepage(wbc, page);
 	unlock_page(page);
-	return ret;
+	return 0;
 }
 
+/*
+ * For now just follow the DIO way to estimate the max credits
+ * needed to write out EXT4_MAX_WRITEBACK_PAGES.
+ * todo: need to calculate the max credits need for
+ * extent based files, currently the DIO credits is based on
+ * indirect-blocks mapping way.
+ *
+ * Probably should have a generic way to calculate credits
+ * for DIO, writepages, and truncate
+ */
+#define EXT4_MAX_WRITEBACK_PAGES      DIO_MAX_BLOCKS
+#define EXT4_MAX_WRITEBACK_CREDITS    DIO_CREDITS
+
 static int ext4_da_writepages(struct address_space *mapping,
 				struct writeback_control *wbc)
 {
-	return mpage_da_writepages(mapping, wbc, ext4_da_get_block_write);
+	struct inode *inode = mapping->host;
+	handle_t *handle = NULL;
+	int needed_blocks;
+	int ret = 0;
+	unsigned range_cyclic;
+	long to_write;
+
+	/*
+	 *  Estimate the worse case needed credits to write out
+	 * EXT4_MAX_BUF_BLOCKS pages
+	 */
+	needed_blocks = EXT4_MAX_WRITEBACK_CREDITS;
+
+	to_write = wbc->nr_to_write;
+	range_cyclic = wbc->range_cyclic;
+	wbc->range_cyclic = 1;
+
+	while (!ret && to_write) {
+		/* start a new transaction*/
+		handle = ext4_journal_start(inode, needed_blocks);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto out_writepages;
+		}
+		/*
+		 * set the max dirty pages could be write at a time
+		 * to fit into the reserved transaction credits
+		 */
+		if (wbc->nr_to_write > EXT4_MAX_WRITEBACK_PAGES)
+			wbc->nr_to_write = EXT4_MAX_WRITEBACK_PAGES;
+		to_write -= wbc->nr_to_write;
+
+		ret = mpage_da_writepages(mapping, wbc, ext4_da_get_block_write);
+		ext4_journal_stop(handle);
+		to_write +=wbc->nr_to_write;
+	}
+
+out_writepages:
+	wbc->nr_to_write = to_write;
+	wbc->range_cyclic = range_cyclic;
+	return ret;
 }
 
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
Index: linux-2.6.26-rc1/mm/page-writeback.c
===================================================================
--- linux-2.6.26-rc1.orig/mm/page-writeback.c	2008-05-05 17:10:07.000000000 -0700
+++ linux-2.6.26-rc1/mm/page-writeback.c	2008-05-05 17:10:23.000000000 -0700
@@ -881,7 +881,7 @@ int write_cache_pages(struct address_spa
 	pagevec_init(&pvec, 0);
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
-		end = -1;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
 	} else {
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 		end = wbc->range_end >> PAGE_CACHE_SHIFT;