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: (31 commits)
  ocfs2: clean up bh null checks
  ocfs2: document access rules for blocked_lock_list
  configfs: file.c fix possible recursive locking
  configfs: dir.c fix possible recursive locking
  configfs: Remove EXPERIMENTAL
  ocfs2: bump version number
  ocfs2/dlm: Clear joining_node on hearbeat node down
  ocfs2: convert byte order of constant instead of variable
  ocfs2: Update default cluster timeouts
  ocfs2: printf fixes
  ocfs2: Use generic_file_llseek
  ocfs2: Safer read_inline_data()
  ocfs2: Silence false lockdep warnings
  [PATCH 2/2] ocfs2: cluster aware flock()
  [PATCH 1/2] ocfs2: add flock lock type
  ocfs2: Local alloc window size changeable via mount option
  ocfs2: Support commit= mount option
  ocfs2: Add missing permission checks
  [PATCH 2/2] ocfs2: Implement group add for online resize
  [PATCH 1/2] ocfs2: Add group extend for online resize
  ...

48 files changed, 1827 insertions, 1453 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index b4799efaf9e8..b6df18f1f677 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -440,14 +440,8 @@ config OCFS2_FS
 	  Tools web page:      http://oss.oracle.com/projects/ocfs2-tools
 	  OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/
 
-	  Note: Features which OCFS2 does not support yet:
-	          - extended attributes
-	          - quotas
-	          - cluster aware flock
-	          - Directory change notification (F_NOTIFY)
-	          - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
-	          - POSIX ACLs
-	          - readpages / writepages (not user visible)
+	  For more information on OCFS2, see the file
+	  <file:Documentation/filesystems/ocfs2.txt>.
 
 config OCFS2_DEBUG_MASKLOG
 	bool "OCFS2 logging support"
@@ -1028,8 +1022,8 @@ config HUGETLB_PAGE
 	def_bool HUGETLBFS
 
 config CONFIGFS_FS
-	tristate "Userspace-driven configuration filesystem (EXPERIMENTAL)"
-	depends on SYSFS && EXPERIMENTAL
+	tristate "Userspace-driven configuration filesystem"
+	depends on SYSFS
 	help
 	  configfs is a ram-based filesystem that provides the converse
 	  of sysfs's functionality. Where sysfs is a filesystem-based
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 50ed691098bc..a48dc7dd8765 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -546,7 +546,7 @@ static int populate_groups(struct config_group *group)
 		 * That said, taking our i_mutex is closer to mkdir
 		 * emulation, and shouldn't hurt.
 		 */
-		mutex_lock(&dentry->d_inode->i_mutex);
+		mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
 
 		for (i = 0; group->default_groups[i]; i++) {
 			new_group = group->default_groups[i];
@@ -1405,7 +1405,8 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
 	sd = configfs_sb->s_root->d_fsdata;
 	link_group(to_config_group(sd->s_element), group);
 
-	mutex_lock(&configfs_sb->s_root->d_inode->i_mutex);
+	mutex_lock_nested(&configfs_sb->s_root->d_inode->i_mutex,
+			I_MUTEX_PARENT);
 
 	name.name = group->cg_item.ci_name;
 	name.len = strlen(name.name);
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index a3658f9a082c..397cb503a180 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -320,7 +320,7 @@ int configfs_add_file(struct dentry * dir, const struct configfs_attribute * att
 	umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
 	int error = 0;
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL);
 	error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode, type);
 	mutex_unlock(&dir->d_inode->i_mutex);
 
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index 9fb8132f19b0..4d4ce48bb42c 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -19,16 +19,17 @@ ocfs2-objs := \
 	ioctl.o 		\
 	journal.o 		\
 	localalloc.o 		\
+	locks.o			\
 	mmap.o 			\
 	namei.o 		\
+	resize.o		\
 	slot_map.o 		\
 	suballoc.o 		\
 	super.o 		\
 	symlink.o 		\
 	sysfile.o 		\
 	uptodate.o		\
-	ver.o 			\
-	vote.o
+	ver.o
 
 obj-$(CONFIG_OCFS2_FS) += cluster/
 obj-$(CONFIG_OCFS2_FS) += dlm/
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 23c8cda43f19..e6df06ac6405 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -4731,7 +4731,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 
 	mutex_lock(&data_alloc_inode->i_mutex);
 
-	status = ocfs2_meta_lock(data_alloc_inode, &data_alloc_bh, 1);
+	status = ocfs2_inode_lock(data_alloc_inode, &data_alloc_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
 		goto out_mutex;
@@ -4753,7 +4753,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 
 out_unlock:
 	brelse(data_alloc_bh);
-	ocfs2_meta_unlock(data_alloc_inode, 1);
+	ocfs2_inode_unlock(data_alloc_inode, 1);
 
 out_mutex:
 	mutex_unlock(&data_alloc_inode->i_mutex);
@@ -5077,7 +5077,7 @@ static int ocfs2_free_cached_items(struct ocfs2_super *osb,
 
 	mutex_lock(&inode->i_mutex);
 
-	ret = ocfs2_meta_lock(inode, &di_bh, 1);
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_mutex;
@@ -5118,7 +5118,7 @@ out_journal:
 	ocfs2_commit_trans(osb, handle);
 
 out_unlock:
-	ocfs2_meta_unlock(inode, 1);
+	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 56f7790cad46..bc7b4cbbe8ec 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -26,6 +26,7 @@
 #include <asm/byteorder.h>
 #include <linux/swap.h>
 #include <linux/pipe_fs_i.h>
+#include <linux/mpage.h>
 
 #define MLOG_MASK_PREFIX ML_FILE_IO
 #include <cluster/masklog.h>
@@ -139,7 +140,8 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 {
 	int err = 0;
 	unsigned int ext_flags;
-	u64 p_blkno, past_eof;
+	u64 max_blocks = bh_result->b_size >> inode->i_blkbits;
+	u64 p_blkno, count, past_eof;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	mlog_entry("(0x%p, %llu, 0x%p, %d)\n", inode,
@@ -155,7 +157,7 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 		goto bail;
 	}
 
-	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, NULL,
+	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
 					  &ext_flags);
 	if (err) {
 		mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
@@ -164,6 +166,9 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 		goto bail;
 	}
 
+	if (max_blocks < count)
+		count = max_blocks;
+
 	/*
 	 * ocfs2 never allocates in this function - the only time we
 	 * need to use BH_New is when we're extending i_size on a file
@@ -178,6 +183,8 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
 		map_bh(bh_result, inode->i_sb, p_blkno);
 
+	bh_result->b_size = count << inode->i_blkbits;
+
 	if (!ocfs2_sparse_alloc(osb)) {
 		if (p_blkno == 0) {
 			err = -EIO;
@@ -210,7 +217,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 			   struct buffer_head *di_bh)
 {
 	void *kaddr;
-	unsigned int size;
+	loff_t size;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
 	if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
@@ -224,8 +231,9 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 	if (size > PAGE_CACHE_SIZE ||
 	    size > ocfs2_max_inline_data(inode->i_sb)) {
 		ocfs2_error(inode->i_sb,
-			    "Inode %llu has with inline data has bad size: %u",
-			    (unsigned long long)OCFS2_I(inode)->ip_blkno, size);
+			    "Inode %llu has with inline data has bad size: %Lu",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
+			    (unsigned long long)size);
 		return -EROFS;
 	}
 
@@ -275,7 +283,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 
 	mlog_entry("(0x%p, %lu)\n", file, (page ? page->index : 0));
 
-	ret = ocfs2_meta_lock_with_page(inode, NULL, 0, page);
+	ret = ocfs2_inode_lock_with_page(inode, NULL, 0, page);
 	if (ret != 0) {
 		if (ret == AOP_TRUNCATED_PAGE)
 			unlock = 0;
@@ -285,7 +293,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 
 	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
 		ret = AOP_TRUNCATED_PAGE;
-		goto out_meta_unlock;
+		goto out_inode_unlock;
 	}
 
 	/*
@@ -305,25 +313,16 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 		goto out_alloc;
 	}
 
-	ret = ocfs2_data_lock_with_page(inode, 0, page);
-	if (ret != 0) {
-		if (ret == AOP_TRUNCATED_PAGE)
-			unlock = 0;
-		mlog_errno(ret);
-		goto out_alloc;
-	}
-
 	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		ret = ocfs2_readpage_inline(inode, page);
 	else
 		ret = block_read_full_page(page, ocfs2_get_block);
 	unlock = 0;
 
-	ocfs2_data_unlock(inode, 0);
 out_alloc:
 	up_read(&OCFS2_I(inode)->ip_alloc_sem);
-out_meta_unlock:
-	ocfs2_meta_unlock(inode, 0);
+out_inode_unlock:
+	ocfs2_inode_unlock(inode, 0);
 out:
 	if (unlock)
 		unlock_page(page);
@@ -331,6 +330,62 @@ out:
 	return ret;
 }
 
+/*
+ * This is used only for read-ahead. Failures or difficult to handle
+ * situations are safe to ignore.
+ *
+ * Right now, we don't bother with BH_Boundary - in-inode extent lists
+ * are quite large (243 extents on 4k blocks), so most inodes don't
+ * grow out to a tree. If need be, detecting boundary extents could
+ * trivially be added in a future version of ocfs2_get_block().
+ */
+static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
+			   struct list_head *pages, unsigned nr_pages)
+{
+	int ret, err = -EIO;
+	struct inode *inode = mapping->host;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	loff_t start;
+	struct page *last;
+
+	/*
+	 * Use the nonblocking flag for the dlm code to avoid page
+	 * lock inversion, but don't bother with retrying.
+	 */
+	ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK);
+	if (ret)
+		return err;
+
+	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
+		ocfs2_inode_unlock(inode, 0);
+		return err;
+	}
+
+	/*
+	 * Don't bother with inline-data. There isn't anything
+	 * to read-ahead in that case anyway...
+	 */
+	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		goto out_unlock;
+
+	/*
+	 * Check whether a remote node truncated this file - we just
+	 * drop out in that case as it's not worth handling here.
+	 */
+	last = list_entry(pages->prev, struct page, lru);
+	start = (loff_t)last->index << PAGE_CACHE_SHIFT;
+	if (start >= i_size_read(inode))
+		goto out_unlock;
+
+	err = mpage_readpages(mapping, pages, nr_pages, ocfs2_get_block);
+
+out_unlock:
+	up_read(&oi->ip_alloc_sem);
+	ocfs2_inode_unlock(inode, 0);
+
+	return err;
+}
+
 /* Note: Because we don't support holes, our allocation has
  * already happened (allocation writes zeros to the file data)
  * so we don't have to worry about ordered writes in
@@ -452,7 +507,7 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 	 * accessed concurrently from multiple nodes.
 	 */
 	if (!INODE_JOURNAL(inode)) {
-		err = ocfs2_meta_lock(inode, NULL, 0);
+		err = ocfs2_inode_lock(inode, NULL, 0);
 		if (err) {
 			if (err != -ENOENT)
 				mlog_errno(err);
@@ -467,7 +522,7 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 
 	if (!INODE_JOURNAL(inode)) {
 		up_read(&OCFS2_I(inode)->ip_alloc_sem);
-		ocfs2_meta_unlock(inode, 0);
+		ocfs2_inode_unlock(inode, 0);
 	}
 
 	if (err) {
@@ -638,34 +693,12 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
-		/*
-		 * We get PR data locks even for O_DIRECT.  This
-		 * allows concurrent O_DIRECT I/O but doesn't let
-		 * O_DIRECT with extending and buffered zeroing writes
-		 * race.  If they did race then the buffered zeroing
-		 * could be written back after the O_DIRECT I/O.  It's
-		 * one thing to tell people not to mix buffered and
-		 * O_DIRECT writes, but expecting them to understand
-		 * that file extension is also an implicit buffered
-		 * write is too much.  By getting the PR we force
-		 * writeback of the buffered zeroing before
-		 * proceeding.
-		 */
-		ret = ocfs2_data_lock(inode, 0);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-		ocfs2_data_unlock(inode, 0);
-	}
-
 	ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
 					    inode->i_sb->s_bdev, iov, offset,
 					    nr_segs, 
 					    ocfs2_direct_IO_get_blocks,
 					    ocfs2_dio_end_io);
-out:
+
 	mlog_exit(ret);
 	return ret;
 }
@@ -1754,7 +1787,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	struct buffer_head *di_bh = NULL;
 	struct inode *inode = mapping->host;
 
-	ret = ocfs2_meta_lock(inode, &di_bh, 1);
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret) {
 		mlog_errno(ret);
 		return ret;
@@ -1769,30 +1802,22 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = ocfs2_data_lock(inode, 1);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_fail;
-	}
-
 	ret = ocfs2_write_begin_nolock(mapping, pos, len, flags, pagep,
 				       fsdata, di_bh, NULL);
 	if (ret) {
 		mlog_errno(ret);
-		goto out_fail_data;
+		goto out_fail;
 	}
 
 	brelse(di_bh);
 
 	return 0;
 
-out_fail_data:
-	ocfs2_data_unlock(inode, 1);
 out_fail:
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 
 	brelse(di_bh);
-	ocfs2_meta_unlock(inode, 1);
+	ocfs2_inode_unlock(inode, 1);
 
 	return ret;
 }
@@ -1908,15 +1933,15 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 
 	ret = ocfs2_write_end_nolock(mapping, pos, len, copied, page, fsdata);
 
-	ocfs2_data_unlock(inode, 1);
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
-	ocfs2_meta_unlock(inode, 1);
+	ocfs2_inode_unlock(inode, 1);
 
 	return ret;
 }
 
 const struct address_space_operations ocfs2_aops = {
 	.readpage	= ocfs2_readpage,
+	.readpages	= ocfs2_readpages,
 	.writepage	= ocfs2_writepage,
 	.write_begin	= ocfs2_write_begin,
 	.write_end	= ocfs2_write_end,
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index c9037414f4f6..f136639f5b41 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -79,7 +79,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		 * information for this bh as it's not marked locally
 		 * uptodate. */
 		ret = -EIO;
-		brelse(bh);
+		put_bh(bh);
 	}
 
 	mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
@@ -256,7 +256,7 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
 				 * for this bh as it's not marked locally
 				 * uptodate. */
 				status = -EIO;
-				brelse(bh);
+				put_bh(bh);
 				bhs[i] = NULL;
 				continue;
 			}
@@ -280,3 +280,64 @@ bail:
 	mlog_exit(status);
 	return status;
 }
+
+/* Check whether the blkno is the super block or one of the backups. */
+static void ocfs2_check_super_or_backup(struct super_block *sb,
+					sector_t blkno)
+{
+	int i;
+	u64 backup_blkno;
+
+	if (blkno == OCFS2_SUPER_BLOCK_BLKNO)
+		return;
+
+	for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
+		backup_blkno = ocfs2_backup_super_blkno(sb, i);
+		if (backup_blkno == blkno)
+			return;
+	}
+
+	BUG();
+}
+
+/*
+ * Write super block and backups doesn't need to collaborate with journal,
+ * so we don't need to lock ip_io_mutex and inode doesn't need to bea passed
+ * into this function.
+ */
+int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
+				struct buffer_head *bh)
+{
+	int ret = 0;
+
+	mlog_entry_void();
+
+	BUG_ON(buffer_jbd(bh));
+	ocfs2_check_super_or_backup(osb->sb, bh->b_blocknr);
+
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) {
+		ret = -EROFS;
+		goto out;
+	}
+
+	lock_buffer(bh);
+	set_buffer_uptodate(bh);
+
+	/* remove from dirty list before I/O. */
+	clear_buffer_dirty(bh);
+
+	get_bh(bh); /* for end_buffer_write_sync() */
+	bh->b_end_io = end_buffer_write_sync;
+	submit_bh(WRITE, bh);
+
+	wait_on_buffer(bh);
+
+	if (!buffer_uptodate(bh)) {
+		ret = -EIO;
+		put_bh(bh);
+	}
+
+out:
+	mlog_exit(ret);
+	return ret;
+}
diff --git a/fs/ocfs2/buffer_head_io.h b/fs/ocfs2/buffer_head_io.h
index 6cc20930fac3..c2e78614c3e5 100644
--- a/fs/ocfs2/buffer_head_io.h
+++ b/fs/ocfs2/buffer_head_io.h
@@ -47,6 +47,8 @@ int ocfs2_read_blocks(struct ocfs2_super          *osb,
 		      int                  flags,
 		      struct inode        *inode);
 
+int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
+				struct buffer_head *bh);
 
 #define OCFS2_BH_CACHED            1
 #define OCFS2_BH_READAHEAD         8
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index 35397dd5ecdb..e511339886b3 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -35,7 +35,7 @@
 #define O2HB_LIVE_THRESHOLD	   2
 /* number of equal samples to be seen as dead */
 extern unsigned int o2hb_dead_threshold;
-#define O2HB_DEFAULT_DEAD_THRESHOLD	   7
+#define O2HB_DEFAULT_DEAD_THRESHOLD	   31
 /* Otherwise MAX_WRITE_TIMEOUT will be zero... */
 #define O2HB_MIN_DEAD_THRESHOLD	  2
 #define O2HB_MAX_WRITE_TIMEOUT_MS (O2HB_REGION_TIMEOUT_MS * (o2hb_dead_threshold - 1))
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index da880fc215f0..f36f66aab3dd 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -60,8 +60,8 @@ typedef void (o2net_post_msg_handler_func)(int status, void *data,
 /* same as hb delay, we're waiting for another node to recognize our hb */
 #define O2NET_RECONNECT_DELAY_MS_DEFAULT	2000
 
-#define O2NET_KEEPALIVE_DELAY_MS_DEFAULT	5000
-#define O2NET_IDLE_TIMEOUT_MS_DEFAULT		10000
+#define O2NET_KEEPALIVE_DELAY_MS_DEFAULT	2000
+#define O2NET_IDLE_TIMEOUT_MS_DEFAULT		30000
 
 
 /* TODO: figure this out.... */
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index 9606111fe89d..b2e832aca567 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -38,6 +38,12 @@
  * locking semantics of the file system using the protocol.  It should 
  * be somewhere else, I'm sure, but right now it isn't.
  *
+ * New in version 10:
+ * 	- Meta/data locks combined
+ *
+ * New in version 9:
+ * 	- All votes removed
+ *
  * New in version 8:
  * 	- Replace delete inode votes with a cluster lock
  *
@@ -60,7 +66,7 @@
  * 	- full 64 bit i_size in the metadata lock lvbs
  * 	- introduction of "rw" lock and pushing meta/data locking down
  */
-#define O2NET_PROTOCOL_VERSION 8ULL
+#define O2NET_PROTOCOL_VERSION 10ULL
 struct o2net_handshake {
 	__be64	protocol_version;
 	__be64	connector_id;
diff --git a/fs/ocfs2/cluster/ver.c b/fs/ocfs2/cluster/ver.c
index 7286c48bb30d..a56eee6abad3 100644
--- a/fs/ocfs2/cluster/ver.c
+++ b/fs/ocfs2/cluster/ver.c
@@ -28,7 +28,7 @@
 
 #include "ver.h"
 
-#define CLUSTER_BUILD_VERSION "1.3.3"
+#define CLUSTER_BUILD_VERSION "1.5.0"
 
 #define VERSION_STR "OCFS2 Node Manager " CLUSTER_BUILD_VERSION
 
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 9923278ea6d4..b1cc7c381e88 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -128,9 +128,9 @@ static int ocfs2_match_dentry(struct dentry *dentry,
 /*
  * Walk the inode alias list, and find a dentry which has a given
  * parent. ocfs2_dentry_attach_lock() wants to find _any_ alias as it
- * is looking for a dentry_lock reference. The vote thread is looking
- * to unhash aliases, so we allow it to skip any that already have
- * that property.
+ * is looking for a dentry_lock reference. The downconvert thread is
+ * looking to unhash aliases, so we allow it to skip any that already
+ * have that property.
  */
 struct dentry *ocfs2_find_local_alias(struct inode *inode,
 				      u64 parent_blkno,
@@ -266,7 +266,7 @@ int ocfs2_dentry_attach_lock(struct dentry *dentry,
 	dl->dl_count = 0;
 	/*
 	 * Does this have to happen below, for all attaches, in case
-	 * the struct inode gets blown away by votes?
+	 * the struct inode gets blown away by the downconvert thread?
 	 */
 	dl->dl_inode = igrab(inode);
 	dl->dl_parent_blkno = parent_blkno;
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 63b28fdceb4a..6b0107f21344 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -846,14 +846,14 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	mlog_entry("dirino=%llu\n",
 		   (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
-	error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
+	error = ocfs2_inode_lock_atime(inode, filp->f_vfsmnt, &lock_level);
 	if (lock_level && error >= 0) {
 		/* We release EX lock which used to update atime
 		 * and get PR lock again to reduce contention
 		 * on commonly accessed directories. */
-		ocfs2_meta_unlock(inode, 1);
+		ocfs2_inode_unlock(inode, 1);
 		lock_level = 0;
-		error = ocfs2_meta_lock(inode, NULL, 0);
+		error = ocfs2_inode_lock(inode, NULL, 0);
 	}
 	if (error < 0) {
 		if (error != -ENOENT)
@@ -865,7 +865,7 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	error = ocfs2_dir_foreach_blk(inode, &filp->f_version, &filp->f_pos,
 				      dirent, filldir, NULL);
 
-	ocfs2_meta_unlock(inode, lock_level);
+	ocfs2_inode_unlock(inode, lock_level);
 
 bail_nolock:
 	mlog_exit(error);
diff --git a/fs/ocfs2/dlm/dlmfsver.c b/fs/ocfs2/dlm/dlmfsver.c
index d2be3ad841f9..a733b3321f83 100644
--- a/fs/ocfs2/dlm/dlmfsver.c
+++ b/fs/ocfs2/dlm/dlmfsver.c
@@ -28,7 +28,7 @@
 
 #include "dlmfsver.h"
 
-#define DLM_BUILD_VERSION "1.3.3"
+#define DLM_BUILD_VERSION "1.5.0"
 
 #define VERSION_STR "OCFS2 DLMFS " DLM_BUILD_VERSION
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 2fde7bf91434..91f747b8a538 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2270,6 +2270,12 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 		}
 	}
 
+	/* Clean up join state on node death. */
+	if (dlm->joining_node == idx) {
+		mlog(0, "Clearing join state for node %u\n", idx);
+		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
+	}
+
 	/* check to see if the node is already considered dead */
 	if (!test_bit(idx, dlm->live_nodes_map)) {
 		mlog(0, "for domain %s, node %d is already dead. "
@@ -2288,12 +2294,6 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 
 	clear_bit(idx, dlm->live_nodes_map);
 
-	/* Clean up join state on node death. */
-	if (dlm->joining_node == idx) {
-		mlog(0, "Clearing join state for node %u\n", idx);
-		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
-	}
-
 	/* make sure local cleanup occurs before the heartbeat events */
 	if (!test_bit(idx, dlm->recovery_map))
 		dlm_do_local_recovery_cleanup(dlm, idx);
@@ -2321,6 +2321,13 @@ void dl