Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: (64 commits)
  ocfs2/net: Add debug interface to o2net
  ocfs2: Only build ocfs2/dlm with the o2cb stack module
  ocfs2/cluster: Get rid of arguments to the timeout routines
  ocfs2: Put tree in MAINTAINERS
  ocfs2: Use BUG_ON
  ocfs2: Convert ocfs2 over to unlocked_ioctl
  ocfs2: Improve rename locking
  fs/ocfs2/aops.c: test for IS_ERR rather than 0
  ocfs2: Add inode stealing for ocfs2_reserve_new_inode
  ocfs2: Add ac_alloc_slot in ocfs2_alloc_context
  ocfs2: Add a new parameter for ocfs2_reserve_suballoc_bits
  ocfs2: Enable cross extent block merge.
  ocfs2: Add support for cross extent block
  ocfs2: Move /sys/o2cb to /sys/fs/o2cb
  sysfs: Allow removal of symlinks in the sysfs root
  ocfs2:  Reconnect after idle time out.
  ocfs2/dlm: Cleanup lockres print
  ocfs2/dlm: Fix lockname in lockres print function
  ocfs2/dlm: Move dlm_print_one_mle() from dlmmaster.c to dlmdebug.c
  ocfs2/dlm: Dumps the purgelist into a debugfs file
  ...

47 files changed, 5800 insertions, 1042 deletions

diff --git a/Documentation/ABI/obsolete/o2cb b/Documentation/ABI/obsolete/o2cb
new file mode 100644
index 00000000000..9c49d8e6c0c
--- /dev/null
+++ b/Documentation/ABI/obsolete/o2cb
@@ -0,0 +1,11 @@
+What:		/sys/o2cb symlink
+Date:		Dec 2005
+KernelVersion:	2.6.16
+Contact:	ocfs2-devel@oss.oracle.com
+Description:	This is a symlink: /sys/o2cb to /sys/fs/o2cb. The symlink will
+		be removed when new versions of ocfs2-tools which know to look
+		in /sys/fs/o2cb are sufficiently prevalent. Don't code new
+		software to look here, it should try /sys/fs/o2cb instead.
+		See Documentation/ABI/stable/o2cb for more information on usage.
+Users:		ocfs2-tools. It's sufficient to mail proposed changes to
+		ocfs2-devel@oss.oracle.com.
diff --git a/Documentation/ABI/stable/o2cb b/Documentation/ABI/stable/o2cb
new file mode 100644
index 00000000000..5eb1545e0b8
--- /dev/null
+++ b/Documentation/ABI/stable/o2cb
@@ -0,0 +1,10 @@
+What:		/sys/fs/o2cb/ (was /sys/o2cb)
+Date:		Dec 2005
+KernelVersion:	2.6.16
+Contact:	ocfs2-devel@oss.oracle.com
+Description:	Ocfs2-tools looks at 'interface-revision' for versioning
+		information. Each logmask/ file controls a set of debug prints
+		and can be written into with the strings "allow", "deny", or
+		"off". Reading the file returns the current state.
+Users:		ocfs2-tools. It's sufficient to mail proposed changes to
+		ocfs2-devel@oss.oracle.com.
diff --git a/Documentation/ABI/testing/sysfs-ocfs2 b/Documentation/ABI/testing/sysfs-ocfs2
new file mode 100644
index 00000000000..b7cc516a8a8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-ocfs2
@@ -0,0 +1,89 @@
+What:		/sys/fs/ocfs2/
+Date:		April 2008
+Contact:	ocfs2-devel@oss.oracle.com
+Description:
+		The /sys/fs/ocfs2 directory contains knobs used by the
+		ocfs2-tools to interact with the filesystem.
+
+What:		/sys/fs/ocfs2/max_locking_protocol
+Date:		April 2008
+Contact:	ocfs2-devel@oss.oracle.com
+Description:
+		The /sys/fs/ocfs2/max_locking_protocol file displays version
+		of ocfs2 locking supported by the filesystem.  This version
+		covers how ocfs2 uses distributed locking between cluster
+		nodes.
+
+		The protocol version has a major and minor number.  Two
+		cluster nodes can interoperate if they have an identical
+		major number and an overlapping minor number - thus,
+		a node with version 1.10 can interoperate with a node
+		sporting version 1.8, as long as both use the 1.8 protocol.
+
+		Reading from this file returns a single line, the major
+		number and minor number joined by a period, eg "1.10".
+
+		This file is read-only.  The value is compiled into the
+		driver.
+
+What:		/sys/fs/ocfs2/loaded_cluster_plugins
+Date:		April 2008
+Contact:	ocfs2-devel@oss.oracle.com
+Description:
+		The /sys/fs/ocfs2/loaded_cluster_plugins file describes
+		the available plugins to support ocfs2 cluster operation.
+		A cluster plugin is required to use ocfs2 in a cluster.
+		There are currently two available plugins:
+
+		* 'o2cb' - The classic o2cb cluster stack that ocfs2 has
+			used since its inception.
+		* 'user' - A plugin supporting userspace cluster software
+			in conjunction with fs/dlm.
+
+		Reading from this file returns the names of all loaded
+		plugins, one per line.
+
+		This file is read-only.  Its contents may change as
+		plugins are loaded or removed.
+
+What:		/sys/fs/ocfs2/active_cluster_plugin
+Date:		April 2008
+Contact:	ocfs2-devel@oss.oracle.com
+Description:
+		The /sys/fs/ocfs2/active_cluster_plugin displays which
+		cluster plugin is currently in use by the filesystem.
+		The active plugin will appear in the loaded_cluster_plugins
+		file as well.  Only one plugin can be used at a time.
+
+		Reading from this file returns the name of the active plugin
+		on a single line.
+
+		This file is read-only.  Which plugin is active depends on
+		the cluster stack in use.  The contents may change
+		when all filesystems are unmounted and the cluster stack
+		is changed.
+
+What:		/sys/fs/ocfs2/cluster_stack
+Date:		April 2008
+Contact:	ocfs2-devel@oss.oracle.com
+Description:
+		The /sys/fs/ocfs2/cluster_stack file contains the name
+		of current ocfs2 cluster stack.  This value is set by
+		userspace tools when bringing the cluster stack online.
+
+		Cluster stack names are 4 characters in length.
+
+		When the 'o2cb' cluster stack is used, the 'o2cb' cluster
+		plugin is active.  All other cluster stacks use the 'user'
+		cluster plugin.
+
+		Reading from this file returns the name of the current
+		cluster stack on a single line.
+
+		Writing a new stack name to this file changes the current
+		cluster stack unless there are mounted ocfs2 filesystems.
+		If there are mounted filesystems, attempts to change the
+		stack return an error.
+
+Users:
+	ocfs2-tools <ocfs2-tools-devel@oss.oracle.com>
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 164c89394cf..4b70622a8a9 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -318,3 +318,13 @@ Why:	Not used in-tree. The current out-of-tree users used it to
 	code / infrastructure should be in the kernel and not in some
 	out-of-tree driver.
 Who:	Thomas Gleixner <tglx@linutronix.de>
+
+---------------------------
+
+What:	/sys/o2cb symlink
+When:	January 2010
+Why:	/sys/fs/o2cb is the proper location for this information - /sys/o2cb
+	exists as a symlink for backwards compatibility for old versions of
+	ocfs2-tools. 2 years should be sufficient time to phase in new versions
+	which know to look in /sys/fs/o2cb.
+Who:	ocfs2-devel@oss.oracle.com
diff --git a/MAINTAINERS b/MAINTAINERS
index 3eceebb48c9..974ee8ddb12 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2952,6 +2952,7 @@ P:	Joel Becker
 M:	joel.becker@oracle.com
 L:	ocfs2-devel@oss.oracle.com
 W:	http://oss.oracle.com/projects/ocfs2/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2.git
 S:	Supported
 
 OMNIKEY CARDMAN 4000 DRIVER
diff --git a/fs/Kconfig b/fs/Kconfig
index c509123bea4..028ae38ecc5 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -444,6 +444,32 @@ config OCFS2_FS
 	  For more information on OCFS2, see the file
 	  <file:Documentation/filesystems/ocfs2.txt>.
 
+config OCFS2_FS_O2CB
+	tristate "O2CB Kernelspace Clustering"
+	depends on OCFS2_FS
+	default y
+	help
+	  OCFS2 includes a simple kernelspace clustering package, the OCFS2
+	  Cluster Base.  It only requires a very small userspace component
+	  to configure it. This comes with the standard ocfs2-tools package.
+	  O2CB is limited to maintaining a cluster for OCFS2 file systems.
+	  It cannot manage any other cluster applications.
+
+	  It is always safe to say Y here, as the clustering method is
+	  run-time selectable.
+
+config OCFS2_FS_USERSPACE_CLUSTER
+	tristate "OCFS2 Userspace Clustering"
+	depends on OCFS2_FS && DLM
+	default y
+	help
+	  This option will allow OCFS2 to use userspace clustering services
+	  in conjunction with the DLM in fs/dlm.  If you are using a
+	  userspace cluster manager, say Y here.
+
+	  It is safe to say Y, as the clustering method is run-time
+	  selectable.
+
 config OCFS2_DEBUG_MASKLOG
 	bool "OCFS2 logging support"
 	depends on OCFS2_FS
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index 4d4ce48bb42..f6956de56fd 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -2,7 +2,12 @@ EXTRA_CFLAGS += -Ifs/ocfs2
 
 EXTRA_CFLAGS += -DCATCH_BH_JBD_RACES
 
-obj-$(CONFIG_OCFS2_FS) += ocfs2.o
+obj-$(CONFIG_OCFS2_FS) += 	\
+	ocfs2.o			\
+	ocfs2_stackglue.o
+
+obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_stack_o2cb.o
+obj-$(CONFIG_OCFS2_FS_USERSPACE_CLUSTER) += ocfs2_stack_user.o
 
 ocfs2-objs := \
 	alloc.o 		\
@@ -31,5 +36,10 @@ ocfs2-objs := \
 	uptodate.o		\
 	ver.o
 
+ocfs2_stackglue-objs := stackglue.o
+ocfs2_stack_o2cb-objs := stack_o2cb.o
+ocfs2_stack_user-objs := stack_user.o
+
+# cluster/ is always needed when OCFS2_FS for masklog support
 obj-$(CONFIG_OCFS2_FS) += cluster/
-obj-$(CONFIG_OCFS2_FS) += dlm/
+obj-$(CONFIG_OCFS2_FS_O2CB) += dlm/
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 447206eb5c2..41f84c92094 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -1029,8 +1029,7 @@ static void ocfs2_rotate_leaf(struct ocfs2_extent_list *el,
 	BUG_ON(!next_free);
 
 	/* The tree code before us didn't allow enough room in the leaf. */
-	if (el->l_next_free_rec == el->l_count && !has_empty)
-		BUG();
+	BUG_ON(el->l_next_free_rec == el->l_count && !has_empty);
 
 	/*
 	 * The easiest way to approach this is to just remove the
@@ -1450,6 +1449,8 @@ static void ocfs2_adjust_root_records(struct ocfs2_extent_list *root_el,
  *   - When our insert into the right path leaf is at the leftmost edge
  *     and requires an update of the path immediately to it's left. This
  *     can occur at the end of some types of rotation and appending inserts.
+ *   - When we've adjusted the last extent record in the left path leaf and the
+ *     1st extent record in the right path leaf during cross extent block merge.
  */
 static void ocfs2_complete_edge_insert(struct inode *inode, handle_t *handle,
 				       struct ocfs2_path *left_path,
@@ -2712,24 +2713,147 @@ static void ocfs2_cleanup_merge(struct ocfs2_extent_list *el,
 	}
 }
 
+static int ocfs2_get_right_path(struct inode *inode,
+				struct ocfs2_path *left_path,
+				struct ocfs2_path **ret_right_path)
+{
+	int ret;
+	u32 right_cpos;
+	struct ocfs2_path *right_path = NULL;
+	struct ocfs2_extent_list *left_el;
+
+	*ret_right_path = NULL;
+
+	/* This function shouldn't be called for non-trees. */
+	BUG_ON(left_path->p_tree_depth == 0);
+
+	left_el = path_leaf_el(left_path);
+	BUG_ON(left_el->l_next_free_rec != left_el->l_count);
+
+	ret = ocfs2_find_cpos_for_right_leaf(inode->i_sb, left_path,
+					     &right_cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/* This function shouldn't be called for the rightmost leaf. */
+	BUG_ON(right_cpos == 0);
+
+	right_path = ocfs2_new_path(path_root_bh(left_path),
+				    path_root_el(left_path));
+	if (!right_path) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_find_path(inode, right_path, right_cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	*ret_right_path = right_path;
+out:
+	if (ret)
+		ocfs2_free_path(right_path);
+	return ret;
+}
+
 /*
  * Remove split_rec clusters from the record at index and merge them
- * onto the beginning of the record at index + 1.
+ * onto the beginning of the record "next" to it.
+ * For index < l_count - 1, the next means the extent rec at index + 1.
+ * For index == l_count - 1, the "next" means the 1st extent rec of the
+ * next extent block.
  */
-static int ocfs2_merge_rec_right(struct inode *inode, struct buffer_head *bh,
-				handle_t *handle,
-				struct ocfs2_extent_rec *split_rec,
-				struct ocfs2_extent_list *el, int index)
+static int ocfs2_merge_rec_right(struct inode *inode,
+				 struct ocfs2_path *left_path,
+				 handle_t *handle,
+				 struct ocfs2_extent_rec *split_rec,
+				 int index)
 {
-	int ret;
+	int ret, next_free, i;
 	unsigned int split_clusters = le16_to_cpu(split_rec->e_leaf_clusters);
 	struct ocfs2_extent_rec *left_rec;
 	struct ocfs2_extent_rec *right_rec;
+	struct ocfs2_extent_list *right_el;
+	struct ocfs2_path *right_path = NULL;
+	int subtree_index = 0;
+	struct ocfs2_extent_list *el = path_leaf_el(left_path);
+	struct buffer_head *bh = path_leaf_bh(left_path);
+	struct buffer_head *root_bh = NULL;
 
 	BUG_ON(index >= le16_to_cpu(el->l_next_free_rec));
-
 	left_rec = &el->l_recs[index];
-	right_rec = &el->l_recs[index + 1];
+
+	if (index == le16_to_cpu(el->l_next_free_rec - 1) &&
+	    le16_to_cpu(el->l_next_free_rec) == le16_to_cpu(el->l_count)) {
+		/* we meet with a cross extent block merge. */
+		ret = ocfs2_get_right_path(inode, left_path, &right_path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		right_el = path_leaf_el(right_path);
+		next_free = le16_to_cpu(right_el->l_next_free_rec);
+		BUG_ON(next_free <= 0);
+		right_rec = &right_el->l_recs[0];
+		if (ocfs2_is_empty_extent(right_rec)) {
+			BUG_ON(le16_to_cpu(next_free) <= 1);
+			right_rec = &right_el->l_recs[1];
+		}
+
+		BUG_ON(le32_to_cpu(left_rec->e_cpos) +
+		       le16_to_cpu(left_rec->e_leaf_clusters) !=
+		       le32_to_cpu(right_rec->e_cpos));
+
+		subtree_index = ocfs2_find_subtree_root(inode,
+							left_path, right_path);
+
+		ret = ocfs2_extend_rotate_transaction(handle, subtree_index,
+						      handle->h_buffer_credits,
+						      right_path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		root_bh = left_path->p_node[subtree_index].bh;
+		BUG_ON(root_bh != right_path->p_node[subtree_index].bh);
+
+		ret = ocfs2_journal_access(handle, inode, root_bh,
+					   OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		for (i = subtree_index + 1;
+		     i < path_num_items(right_path); i++) {
+			ret = ocfs2_journal_access(handle, inode,
+						   right_path->p_node[i].bh,
+						   OCFS2_JOURNAL_ACCESS_WRITE);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+
+			ret = ocfs2_journal_access(handle, inode,
+						   left_path->p_node[i].bh,
+						   OCFS2_JOURNAL_ACCESS_WRITE);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+		}
+
+	} else {
+		BUG_ON(index == le16_to_cpu(el->l_next_free_rec) - 1);
+		right_rec = &el->l_recs[index + 1];
+	}
 
 	ret = ocfs2_journal_access(handle, inode, bh,
 				   OCFS2_JOURNAL_ACCESS_WRITE);
@@ -2751,30 +2875,156 @@ static int ocfs2_merge_rec_right(struct inode *inode, struct buffer_head *bh,
 	if (ret)
 		mlog_errno(ret);
 
+	if (right_path) {
+		ret = ocfs2_journal_dirty(handle, path_leaf_bh(right_path));
+		if (ret)
+			mlog_errno(ret);
+
+		ocfs2_complete_edge_insert(inode, handle, left_path,
+					   right_path, subtree_index);
+	}
+out:
+	if (right_path)
+		ocfs2_free_path(right_path);
+	return ret;
+}
+
+static int ocfs2_get_left_path(struct inode *inode,
+			       struct ocfs2_path *right_path,
+			       struct ocfs2_path **ret_left_path)
+{
+	int ret;
+	u32 left_cpos;
+	struct ocfs2_path *left_path = NULL;
+
+	*ret_left_path = NULL;
+
+	/* This function shouldn't be called for non-trees. */
+	BUG_ON(right_path->p_tree_depth == 0);
+
+	ret = ocfs2_find_cpos_for_left_leaf(inode->i_sb,
+					    right_path, &left_cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/* This function shouldn't be called for the leftmost leaf. */
+	BUG_ON(left_cpos == 0);
+
+	left_path = ocfs2_new_path(path_root_bh(right_path),
+				   path_root_el(right_path));
+	if (!left_path) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_find_path(inode, left_path, left_cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	*ret_left_path = left_path;
 out:
+	if (ret)
+		ocfs2_free_path(left_path);
 	return ret;
 }
 
 /*
  * Remove split_rec clusters from the record at index and merge them
- * onto the tail of the record at index - 1.
+ * onto the tail of the record "before" it.
+ * For index > 0, the "before" means the extent rec at index - 1.
+ *
+ * For index == 0, the "before" means the last record of the previous
+ * extent block. And there is also a situation that we may need to
+ * remove the rightmost leaf extent block in the right_path and change
+ * the right path to indicate the new rightmost path.
  */
-static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh,
+static int ocfs2_merge_rec_left(struct inode *inode,
+				struct ocfs2_path *right_path,
 				handle_t *handle,
 				struct ocfs2_extent_rec *split_rec,
-				struct ocfs2_extent_list *el, int index)
+				struct ocfs2_cached_dealloc_ctxt *dealloc,
+				int index)
 {
-	int ret, has_empty_extent = 0;
+	int ret, i, subtree_index = 0, has_empty_extent = 0;
 	unsigned int split_clusters = le16_to_cpu(split_rec->e_leaf_clusters);
 	struct ocfs2_extent_rec *left_rec;
 	struct ocfs2_extent_rec *right_rec;
+	struct ocfs2_extent_list *el = path_leaf_el(right_path);
+	struct buffer_head *bh = path_leaf_bh(right_path);
+	struct buffer_head *root_bh = NULL;
+	struct ocfs2_path *left_path = NULL;
+	struct ocfs2_extent_list *left_el;
 
-	BUG_ON(index <= 0);
+	BUG_ON(index < 0);
 
-	left_rec = &el->l_recs[index - 1];
 	right_rec = &el->l_recs[index];
-	if (ocfs2_is_empty_extent(&el->l_recs[0]))
-		has_empty_extent = 1;
+	if (index == 0) {
+		/* we meet with a cross extent block merge. */
+		ret = ocfs2_get_left_path(inode, right_path, &left_path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		left_el = path_leaf_el(left_path);
+		BUG_ON(le16_to_cpu(left_el->l_next_free_rec) !=
+		       le16_to_cpu(left_el->l_count));
+
+		left_rec = &left_el->l_recs[
+				le16_to_cpu(left_el->l_next_free_rec) - 1];
+		BUG_ON(le32_to_cpu(left_rec->e_cpos) +
+		       le16_to_cpu(left_rec->e_leaf_clusters) !=
+		       le32_to_cpu(split_rec->e_cpos));
+
+		subtree_index = ocfs2_find_subtree_root(inode,
+							left_path, right_path);
+
+		ret = ocfs2_extend_rotate_transaction(handle, subtree_index,
+						      handle->h_buffer_credits,
+						      left_path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		root_bh = left_path->p_node[subtree_index].bh;
+		BUG_ON(root_bh != right_path->p_node[subtree_index].bh);
+
+		ret = ocfs2_journal_access(handle, inode, root_bh,
+					   OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		for (i = subtree_index + 1;
+		     i < path_num_items(right_path); i++) {
+			ret = ocfs2_journal_access(handle, inode,
+						   right_path->p_node[i].bh,
+						   OCFS2_JOURNAL_ACCESS_WRITE);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+
+			ret = ocfs2_journal_access(handle, inode,
+						   left_path->p_node[i].bh,
+						   OCFS2_JOURNAL_ACCESS_WRITE);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+		}
+	} else {
+		left_rec = &el->l_recs[index - 1];
+		if (ocfs2_is_empty_extent(&el->l_recs[0]))
+			has_empty_extent = 1;
+	}
 
 	ret = ocfs2_journal_access(handle, inode, bh,
 				   OCFS2_JOURNAL_ACCESS_WRITE);
@@ -2790,9 +3040,8 @@ static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh,
 		*left_rec = *split_rec;
 
 		has_empty_extent = 0;
-	} else {
+	} else
 		le16_add_cpu(&left_rec->e_leaf_clusters, split_clusters);
-	}
 
 	le32_add_cpu(&right_rec->e_cpos, split_clusters);
 	le64_add_cpu(&right_rec->e_blkno,
@@ -2805,13 +3054,44 @@ static int ocfs2_merge_rec_left(struct inode *inode, struct buffer_head *bh,
 	if (ret)
 		mlog_errno(ret);
 
+	if (left_path) {
+		ret = ocfs2_journal_dirty(handle, path_leaf_bh(left_path));
+		if (ret)
+			mlog_errno(ret);
+
+		/*
+		 * In the situation that the right_rec is empty and the extent
+		 * block is empty also,  ocfs2_complete_edge_insert can't handle
+		 * it and we need to delete the right extent block.
+		 */
+		if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 &&
+		    le16_to_cpu(el->l_next_free_rec) == 1) {
+
+			ret = ocfs2_remove_rightmost_path(inode, handle,
+							  right_path, dealloc);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+
+			/* Now the rightmost extent block has been deleted.
+			 * So we use the new rightmost path.
+			 */
+			ocfs2_mv_path(right_path, left_path);
+			left_path = NULL;
+		} else
+			ocfs2_complete_edge_insert(inode, handle, left_path,
+						   right_path, subtree_index);
+	}
 out:
+	if (left_path)
+		ocfs2_free_path(left_path);
 	return ret;
 }
 
 static int ocfs2_try_to_merge_extent(struct inode *inode,
 				     handle_t *handle,
-				     struct ocfs2_path *left_path,
+				     struct ocfs2_path *path,
 				     int split_index,
 				     struct ocfs2_extent_rec *split_rec,
 				     struct ocfs2_cached_dealloc_ctxt *dealloc,
@@ -2819,7 +3099,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
 
 {
 	int ret = 0;
-	struct ocfs2_extent_list *el = path_leaf_el(left_path);
+	struct ocfs2_extent_list *el = path_leaf_el(path);
 	struct ocfs2_extent_rec *rec = &el->l_recs[split_index];
 
 	BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
@@ -2832,7 +3112,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
 		 * extents - having more than one in a leaf is
 		 * illegal.
 		 */
-		ret = ocfs2_rotate_tree_left(inode, handle, left_path,
+		ret = ocfs2_rotate_tree_left(inode, handle, path,
 					     dealloc);
 		if (ret) {
 			mlog_errno(ret);
@@ -2847,7 +3127,6 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
 		 * Left-right contig implies this.
 		 */
 		BUG_ON(!ctxt->c_split_covers_rec);
-		BUG_ON(split_index == 0);
 
 		/*
 		 * Since the leftright insert always covers the entire
@@ -2858,9 +3137,14 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
 		 * Since the adding of an empty extent shifts
 		 * everything back to the right, there's no need to
 		 * update split_index here.
+		 *
+		 * When the split_index is zero, we need to merge it to the
+		 * prevoius extent block. It is more efficient and easier
+		 * if we do merge_right first and merge_left later.
 		 */
-		ret = ocfs2_merge_rec_left(inode, path_leaf_bh(left_path),
-					   handle, split_rec, el, split_index);
+		ret = ocfs2_merge_rec_right(inode, path,
+					    handle, split_rec,
+					    split_index);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -2871,32 +3155,30 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
 		 */
 		BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
 
-		/*
-		 * The left merge left us with an empty extent, remove
-		 * it.
-		 */
-		ret = ocfs2_rotate_tree_left(inode, handle, left_path, dealloc);
+		/* The merge left us with an empty extent, remove it. */
+		ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
 		}
-		split_index--;
+
 		rec = &el->l_recs[split_index];
 
 		/*
 		 * Note that we don't pass split_rec here on purpose -
-		 * we've merged it into the left side.
+		 * we've merged it into the rec already.
 		 */
-		ret = ocfs2_merge_rec_right(inode, path_leaf_bh(left_path),
-					    handle, rec, el, split_index);
+		ret = ocfs2_merge_rec_left(inode, path,
+					   handle, rec,
+					   dealloc,
+					   split_index);
+
 		if (ret) {
 			mlog_err