initial_commit

46 files changed, 25721 insertions, 0 deletions

diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
new file mode 100644
index 00000000..c465ae06
--- /dev/null
+++ b/fs/gfs2/Kconfig
@@ -0,0 +1,38 @@
+config GFS2_FS
+	tristate "GFS2 file system support"
+	depends on (64BIT || LBDAF)
+	select DLM if GFS2_FS_LOCKING_DLM
+	select CONFIGFS_FS if GFS2_FS_LOCKING_DLM
+	select SYSFS if GFS2_FS_LOCKING_DLM
+	select IP_SCTP if DLM_SCTP
+	select FS_POSIX_ACL
+	select CRC32
+	select QUOTACTL
+	help
+	  A cluster filesystem.
+
+	  Allows a cluster of computers to simultaneously use a block device
+	  that is shared between them (with FC, iSCSI, NBD, etc...).  GFS reads
+	  and writes to the block device like a local filesystem, but also uses
+	  a lock module to allow the computers coordinate their I/O so
+	  filesystem consistency is maintained.  One of the nifty features of
+	  GFS is perfect consistency -- changes made to the filesystem on one
+	  machine show up immediately on all other machines in the cluster.
+
+	  To use the GFS2 filesystem in a cluster, you will need to enable
+	  the locking module below. Documentation and utilities for GFS2 can
+	  be found here: http://sources.redhat.com/cluster
+
+	  The "nolock" lock module is now built in to GFS2 by default. If
+	  you want to use the DLM, be sure to enable HOTPLUG and IPv4/6
+	  networking.
+
+config GFS2_FS_LOCKING_DLM
+	bool "GFS2 DLM locking"
+	depends on (GFS2_FS!=n) && NET && INET && (IPV6 || IPV6=n) && HOTPLUG
+	help
+	  Multiple node locking module for GFS2
+
+	  Most users of GFS2 will require this. It provides the locking
+	  interface between GFS2 and the DLM, which is required to use GFS2
+	  in a cluster environment.
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
new file mode 100644
index 00000000..86128202
--- /dev/null
+++ b/fs/gfs2/Makefile
@@ -0,0 +1,10 @@
+ccflags-y := -I$(src)
+obj-$(CONFIG_GFS2_FS) += gfs2.o
+gfs2-y := acl.o bmap.o dir.o xattr.o glock.o \
+	glops.o log.o lops.o main.o meta_io.o \
+	aops.o dentry.o export.o file.o \
+	ops_fstype.o inode.o quota.o \
+	recovery.o rgrp.o super.o sys.o trans.o util.o
+
+gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
+
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
new file mode 100644
index 00000000..cbc07155
--- /dev/null
+++ b/fs/gfs2/acl.c
@@ -0,0 +1,354 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "xattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+
+static const char *gfs2_acl_name(int type)
+{
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		return GFS2_POSIX_ACL_ACCESS;
+	case ACL_TYPE_DEFAULT:
+		return GFS2_POSIX_ACL_DEFAULT;
+	}
+	return NULL;
+}
+
+static struct posix_acl *gfs2_acl_get(struct gfs2_inode *ip, int type)
+{
+	struct posix_acl *acl;
+	const char *name;
+	char *data;
+	int len;
+
+	if (!ip->i_eattr)
+		return NULL;
+
+	acl = get_cached_acl(&ip->i_inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+
+	name = gfs2_acl_name(type);
+	if (name == NULL)
+		return ERR_PTR(-EINVAL);
+
+	len = gfs2_xattr_acl_get(ip, name, &data);
+	if (len < 0)
+		return ERR_PTR(len);
+	if (len == 0)
+		return NULL;
+
+	acl = posix_acl_from_xattr(data, len);
+	kfree(data);
+	return acl;
+}
+
+/**
+ * gfs2_check_acl - Check an ACL to see if we're allowed to do something
+ * @inode: the file we want to do something to
+ * @mask: what we want to do
+ *
+ * Returns: errno
+ */
+
+int gfs2_check_acl(struct inode *inode, int mask, unsigned int flags)
+{
+	struct posix_acl *acl;
+	int error;
+
+	if (flags & IPERM_FLAG_RCU) {
+		if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+			return -ECHILD;
+		return -EAGAIN;
+	}
+
+	acl = gfs2_acl_get(GFS2_I(inode), ACL_TYPE_ACCESS);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+
+	if (acl) {
+		error = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return error;
+	}
+
+	return -EAGAIN;
+}
+
+static int gfs2_set_mode(struct inode *inode, mode_t mode)
+{
+	int error = 0;
+
+	if (mode != inode->i_mode) {
+		struct iattr iattr;
+
+		iattr.ia_valid = ATTR_MODE;
+		iattr.ia_mode = mode;
+
+		error = gfs2_setattr_simple(GFS2_I(inode), &iattr);
+	}
+
+	return error;
+}
+
+static int gfs2_acl_set(struct inode *inode, int type, struct posix_acl *acl)
+{
+	int error;
+	int len;
+	char *data;
+	const char *name = gfs2_acl_name(type);
+
+	BUG_ON(name == NULL);
+	len = posix_acl_to_xattr(acl, NULL, 0);
+	if (len == 0)
+		return 0;
+	data = kmalloc(len, GFP_NOFS);
+	if (data == NULL)
+		return -ENOMEM;
+	error = posix_acl_to_xattr(acl, data, len);
+	if (error < 0)
+		goto out;
+	error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+out:
+	kfree(data);
+	return error;
+}
+
+int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct posix_acl *acl, *clone;
+	mode_t mode = inode->i_mode;
+	int error = 0;
+
+	if (!sdp->sd_args.ar_posix_acl)
+		return 0;
+	if (S_ISLNK(inode->i_mode))
+		return 0;
+
+	acl = gfs2_acl_get(dip, ACL_TYPE_DEFAULT);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (!acl) {
+		mode &= ~current_umask();
+		if (mode != inode->i_mode)
+			error = gfs2_set_mode(inode, mode);
+		return error;
+	}
+
+	if (S_ISDIR(inode->i_mode)) {
+		error = gfs2_acl_set(inode, ACL_TYPE_DEFAULT, acl);
+		if (error)
+			goto out;
+	}
+
+	clone = posix_acl_clone(acl, GFP_NOFS);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	error = posix_acl_create_masq(acl, &mode);
+	if (error < 0)
+		goto out;
+	if (error == 0)
+		goto munge;
+
+	error = gfs2_acl_set(inode, ACL_TYPE_ACCESS, acl);
+	if (error)
+		goto out;
+munge:
+	error = gfs2_set_mode(inode, mode);
+out:
+	posix_acl_release(acl);
+	return error;
+}
+
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
+{
+	struct posix_acl *acl, *clone;
+	char *data;
+	unsigned int len;
+	int error;
+
+	acl = gfs2_acl_get(ip, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (!acl)
+		return gfs2_setattr_simple(ip, attr);
+
+	clone = posix_acl_clone(acl, GFP_NOFS);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	error = posix_acl_chmod_masq(acl, attr->ia_mode);
+	if (!error) {
+		len = posix_acl_to_xattr(acl, NULL, 0);
+		data = kmalloc(len, GFP_NOFS);
+		error = -ENOMEM;
+		if (data == NULL)
+			goto out;
+		posix_acl_to_xattr(acl, data, len);
+		error = gfs2_xattr_acl_chmod(ip, attr, data);
+		kfree(data);
+		set_cached_acl(&ip->i_inode, ACL_TYPE_ACCESS, acl);
+	}
+
+out:
+	posix_acl_release(acl);
+	return error;
+}
+
+static int gfs2_acl_type(const char *name)
+{
+	if (strcmp(name, GFS2_POSIX_ACL_ACCESS) == 0)
+		return ACL_TYPE_ACCESS;
+	if (strcmp(name, GFS2_POSIX_ACL_DEFAULT) == 0)
+		return ACL_TYPE_DEFAULT;
+	return -EINVAL;
+}
+
+static int gfs2_xattr_system_get(struct dentry *dentry, const char *name,
+				 void *buffer, size_t size, int xtype)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct posix_acl *acl;
+	int type;
+	int error;
+
+	if (!sdp->sd_args.ar_posix_acl)
+		return -EOPNOTSUPP;
+
+	type = gfs2_acl_type(name);
+	if (type < 0)
+		return type;
+
+	acl = gfs2_acl_get(GFS2_I(inode), type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+
+	error = posix_acl_to_xattr(acl, buffer, size);
+	posix_acl_release(acl);
+
+	return error;
+}
+
+static int gfs2_xattr_system_set(struct dentry *dentry, const char *name,
+				 const void *value, size_t size, int flags,
+				 int xtype)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct posix_acl *acl = NULL;
+	int error = 0, type;
+
+	if (!sdp->sd_args.ar_posix_acl)
+		return -EOPNOTSUPP;
+
+	type = gfs2_acl_type(name);
+	if (type < 0)
+		return type;
+	if (flags & XATTR_CREATE)
+		return -EINVAL;
+	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+		return value ? -EACCES : 0;
+	if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
+		return -EPERM;
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (!value)
+		goto set_acl;
+
+	acl = posix_acl_from_xattr(value, size);
+	if (!acl) {
+		/*
+		 * acl_set_file(3) may request that we set default ACLs with
+		 * zero length -- defend (gracefully) against that here.
+		 */
+		goto out;
+	}
+	if (IS_ERR(acl)) {
+		error = PTR_ERR(acl);
+		goto out;
+	}
+
+	error = posix_acl_valid(acl);
+	if (error)
+		goto out_release;
+
+	error = -EINVAL;
+	if (acl->a_count > GFS2_ACL_MAX_ENTRIES)
+		goto out_release;
+
+	if (type == ACL_TYPE_ACCESS) {
+		mode_t mode = inode->i_mode;
+		error = posix_acl_equiv_mode(acl, &mode);
+
+		if (error <= 0) {
+			posix_acl_release(acl);
+			acl = NULL;
+
+			if (error < 0)
+				return error;
+		}
+
+		error = gfs2_set_mode(inode, mode);
+		if (error)
+			goto out_release;
+	}
+
+set_acl:
+	error = __gfs2_xattr_set(inode, name, value, size, 0, GFS2_EATYPE_SYS);
+	if (!error) {
+		if (acl)
+			set_cached_acl(inode, type, acl);
+		else
+			forget_cached_acl(inode, type);
+	}
+out_release:
+	posix_acl_release(acl);
+out:
+	return error;
+}
+
+const struct xattr_handler gfs2_xattr_system_handler = {
+	.prefix = XATTR_SYSTEM_PREFIX,
+	.flags  = GFS2_EATYPE_SYS,
+	.get    = gfs2_xattr_system_get,
+	.set    = gfs2_xattr_system_set,
+};
+
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
new file mode 100644
index 00000000..a93907c8
--- /dev/null
+++ b/fs/gfs2/acl.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __ACL_DOT_H__
+#define __ACL_DOT_H__
+
+#include "incore.h"
+
+#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
+#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
+#define GFS2_ACL_MAX_ENTRIES		25
+
+extern int gfs2_check_acl(struct inode *inode, int mask, unsigned int);
+extern int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode);
+extern int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
+extern const struct xattr_handler gfs2_xattr_system_handler;
+
+#endif /* __ACL_DOT_H__ */
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
new file mode 100644
index 00000000..f9fbbe96
--- /dev/null
+++ b/fs/gfs2/aops.c
@@ -0,0 +1,1182 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/fs.h>
+#include <linux/writeback.h>
+#include <linux/swap.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/backing-dev.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "trans.h"
+#include "rgrp.h"
+#include "super.h"
+#include "util.h"
+#include "glops.h"
+
+
+void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+			    unsigned int from, unsigned int to)
+{
+	struct buffer_head *head = page_buffers(page);
+	unsigned int bsize = head->b_size;
+	struct buffer_head *bh;
+	unsigned int start, end;
+
+	for (bh = head, start = 0; bh != head || !start;
+	     bh = bh->b_this_page, start = end) {
+		end = start + bsize;
+		if (end <= from || start >= to)
+			continue;
+		if (gfs2_is_jdata(ip))
+			set_buffer_uptodate(bh);
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+	}
+}
+
+/**
+ * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
+ * @inode: The inode
+ * @lblock: The block number to look up
+ * @bh_result: The buffer head to return the result in
+ * @create: Non-zero if we may add block to the file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
+				  struct buffer_head *bh_result, int create)
+{
+	int error;
+
+	error = gfs2_block_map(inode, lblock, bh_result, 0);
+	if (error)
+		return error;
+	if (!buffer_mapped(bh_result))
+		return -EIO;
+	return 0;
+}
+
+static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
+				 struct buffer_head *bh_result, int create)
+{
+	return gfs2_block_map(inode, lblock, bh_result, 0);
+}
+
+/**
+ * gfs2_writepage_common - Common bits of writepage
+ * @page: The page to be written
+ * @wbc: The writeback control
+ *
+ * Returns: 1 if writepage is ok, otherwise an error code or zero if no error.
+ */
+
+static int gfs2_writepage_common(struct page *page,
+				 struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset;
+
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
+		goto out;
+	if (current->journal_info)
+		goto redirty;
+	/* Is the page fully outside i_size? (truncate in progress) */
+	offset = i_size & (PAGE_CACHE_SIZE-1);
+	if (page->index > end_index || (page->index == end_index && !offset)) {
+		page->mapping->a_ops->invalidatepage(page, 0);
+		goto out;
+	}
+	return 1;
+redirty:
+	redirty_page_for_writepage(wbc, page);
+out:
+	unlock_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_writeback_writepage - Write page for writeback mappings
+ * @page: The page
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_writeback_writepage(struct page *page,
+				    struct writeback_control *wbc)
+{
+	int ret;
+
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret <= 0)
+		return ret;
+
+	return nobh_writepage(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * gfs2_ordered_writepage - Write page for ordered data files
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_ordered_writepage(struct page *page,
+				  struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int ret;
+
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret <= 0)
+		return ret;
+
+	if (!page_has_buffers(page)) {
+		create_empty_buffers(page, inode->i_sb->s_blocksize,
+				     (1 << BH_Dirty)|(1 << BH_Uptodate));
+	}
+	gfs2_page_add_databufs(ip, page, 0, inode->i_sb->s_blocksize-1);
+	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * __gfs2_jdata_writepage - The core of jdata writepage
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ * This is shared between writepage and writepages and implements the
+ * core of the writepage operation. If a transaction is required then
+ * PageChecked will have been set and the transaction will have
+ * already been started before this is called.
+ */
+
+static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	if (PageChecked(page)) {
+		ClearPageChecked(page);
+		if (!page_has_buffers(page)) {
+			create_empty_buffers(page, inode->i_sb->s_blocksize,
+					     (1 << BH_Dirty)|(1 << BH_Uptodate));
+		}
+		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
+	}
+	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * gfs2_jdata_writepage - Write complete page
+ * @page: Page to write
+ *
+ * Returns: errno
+ *
+ */
+
+static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	int ret;
+	int done_trans = 0;
+
+	if (PageChecked(page)) {
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			goto out_ignore;
+		ret = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
+		if (ret)
+			goto out_ignore;
+		done_trans = 1;
+	}
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret > 0)
+		ret = __gfs2_jdata_writepage(page, wbc);
+	if (done_trans)
+		gfs2_trans_end(sdp);
+	return ret;
+
+out_ignore:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: Write-back control
+ *
+ * For the data=writeback case we can already ignore buffer heads
+ * and write whole extents at once. This is a big reduction in the
+ * number of I/O requests we send and the bmap calls we make in this case.
+ */
+static int gfs2_writeback_writepages(struct address_space *mapping,
+				     struct writeback_control *wbc)
+{
+	return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+}
+
+/**
+ * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages
+ * @mapping: The mapping
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call for each page
+ * @pvec: The vector of pages
+ * @nr_pages: The number of pages to write
+ *
+ * Returns: non-zero if loop should terminate, zero otherwise
+ */
+
+static int gfs2_write_jdata_pagevec(struct address_space *mapping,
+				    struct writeback_control *wbc,
+				    struct pagevec *pvec,
+				    int nr_pages, pgoff_t end)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
+	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
+	int i;
+	int ret;
+
+	ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
+	if (ret < 0)
+		return ret;
+
+	for(i = 0; i < nr_pages; i++) {
+		struct page *page = pvec->pages[i];
+
+		lock_page(page);
+
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			continue;
+		}
+
+		if (!wbc->range_cyclic && page->index > end) {
+			ret = 1;
+			unlock_page(page);
+			continue;
+		}
+
+		if (wbc->sync_mode != WB_SYNC_NONE)
+			wait_on_page_writeback(page);
+
+		if (PageWriteback(page) ||
+		    !clear_page_dirty_for_io(page)) {
+			unlock_page(page);
+			continue;
+		}
+
+		/* Is the page fully outside i_size? (truncate in progress) */
+		if (page->index > end_index || (page->index == end_index && !offset)) {
+			page->mapping->a_ops->invalidatepage(page, 0);
+			unlock_page(page);
+			continue;
+		}
+
+		ret = __gfs2_jdata_writepage(page, wbc);
+
+		if (ret || (--(wbc->nr_to_write) <= 0))
+			ret = 1;
+	}
+	gfs2_trans_end(sdp);
+	return ret;
+}
+
+/**
+ * gfs2_write_cache_jdata - Like write_cache_pages but different
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call
+ * @data: The data to pass to writepage
+ *
+ * The reason that we use our own function here is that we need to
+ * start transactions before we grab page locks. This allows us
+ * to get the ordering right.
+ */
+
+static int gfs2_write_cache_jdata(struct address_space *mapping,
+				  struct writeback_control *wbc)
+{
+	int ret = 0;
+	int done = 0;
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;
+	int scanned = 0;
+	int range_whole = 0;
+
+	pagevec_init(&pvec, 0);
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index; /* Start from prev offset */
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
+		scanned = 1;
+	}
+
+retry:
+	 while (!done && (index <= end) &&
+		(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					       PAGECACHE_TAG_DIRTY,
+					       min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+		scanned = 1;
+		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
+		if (ret)
+			done = 1;
+		if (ret > 0)
+			ret = 0;
+
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+
+	if (!scanned && !done) {
+		/*
+		 * We hit the last page and there is more work to be done: wrap
+		 * back to the start of the file
+		 */
+		scanned = 1;
+		index = 0;
+		goto retry;
+	}
+
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		mapping->writeback_index = index;
+	return ret;
+}
+
+
+/**
+ * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * 
+ */
+
+static int gfs2_jdata_writepages(struct address_space *mapping,
+				 struct writeback_control *wbc)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	int ret;
+
+	ret = gfs2_write_cache_jdata(mapping, wbc);
+	if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
+		gfs2_log_flush(sdp, ip->i_gl);
+		ret = gfs2_write_cache_jdata(mapping, wbc);
+	}
+	return ret;
+}
+
+/**
+ * stuffed_readpage - Fill in a Linux page with stuffed file data
+ * @ip: the inode
+ * @page: the page
+ *
+ * Returns: errno
+ */
+
+static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
+{
+	struct buffer_head *dibh;
+	u64 dsize = i_size_read(&ip->i_inode);
+	void *kaddr;
+	int error;
+
+	/*
+	 * Due to the order of unstuffing files and ->fault(), we can be
+	 * asked for a zero page in the case of a stuffed file being extended,
+	 * so we need to supply one here. It doesn't happen often.
+	 */
+	if (unlikely(page->index)) {
+		zero_user(page, 0, PAGE_CACHE_SIZE);
+		SetPageUptodate(page);
+		return 0;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
+		dsize = (dibh->b_size - sizeof(struct gfs2_dinode));
+	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
+	memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
+	kunmap_atomic(kaddr, KM_USER0);
+	flush_dcache_page(page);
+	brelse(dibh);
+	SetPageUptodate(page);
+
+	return 0;
+}
+
+
+/**
+ * __gfs2_readpage - readpage
+ * @file: The file to read a page for
+ * @page: The page to read
+ *
+ * This is the core of gfs2's readpage. Its used by the internal file
+ * reading code as in that case we already hold the glock. Also its
+ * called by gfs2_readpage() once the required lock has been granted.
+ *
+ */
+
+static int __gfs2_readpage(void *file, struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	int error;
+
+	if (gfs2_is_stuffed(ip)) {
+		error = stuffed_readpage(ip, page);
+		unlock_page(page);
+	} else {
+		error = mpage_readpage(page, gfs2_block_map);
+	}
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	return error;
+}
+
+/**
+ * gfs2_readpage - read a page of a file
+ * @file: The file to read
+ * @page: The page of the file
+ *
+ * This deals with the locking required. We have to unlock and
+ * relock the page in order to get the locking in the right
+ * order.
+ */
+
+static int gfs2_readpage(struct file *file, struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_holder gh;
+	int error;
+
+	unlock_page(page);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
+	if (unlikely(error))
+		goto out;
+	error = AOP_TRUNCATED_PAGE;
+	lock_page(page);
+	if (page->mapping == mapping && !PageUptodate(page))
+		error = __gfs2_readpage(file, page);
+	else
+		unlock_page(page);
+	gfs2_glock_dq(&gh);
+out:
+	gfs2_holder_uninit(&gh);
+	if (error && error != AOP_TRUNCATED_PAGE)
+		lock_page(page);
+	return error;
+}
+
+/**
+ * gfs2_internal_read - read an internal file
+ * @ip: The gfs2 inode
+ * @ra_state: The readahead state (or NULL for no readahead)
+ * @buf: The buffer to fill
+ * @pos: The file position
+ * @size: The amount to read
+ *
+ */
+
+int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
+                       char *buf, loff_t *pos, unsigned size)
+{
+	struct address_space *mapping = ip->i_inode.i_mapping;
+	unsigned long index = *pos / PAGE_CACHE_SIZE;
+	unsigned offset = *pos & (PAGE_CACHE_SIZE - 1);
+	unsigned copied = 0;
+	unsigned amt;
+	struct page *page;
+	void *p;
+
+	do {
+		amt = size - copied;
+		if (offset + size > PAGE_CACHE_SIZE)
+			amt = PAGE_CACHE_SIZE - offset;
+		page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+		p = kmap_atomic(page, KM_USER0);
+		memcpy(buf + copied, p + offset, amt);
+		kunmap_atomic(p, KM_USER0);
+		mark_page_accessed(page);
+		page_cache_release(page);
+		copied += amt;
+		index++;
+		offset = 0;
+	} while(copied < size);
+	(*pos) += size;
+	return size;
+}
+
+/**
+ * gfs2_readpages - Read a bunch of pages at once
+ *
+ * Some notes:
+ * 1. This is only for readahead, so we can simply ignore any things
+ *    which are slightly inconvenient (such as locking conflicts between
+ *    the page lock and the glock) and return having done no I/O. Its
+ *    obviously not something we'd want to do on too regular a basis.
+ *    Any I/O we ignore at this time will be done via readpage later.
+ * 2. We don't handle stuffed files here we let readpage do the honours.
+ * 3. mpage_readpages() does most of the heavy lifting in the common case.
+ * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
+ */
+
+static int gfs2_readpages(struct file *file, struct address_space *mapping,
+			  struct list_head *pages, unsigned nr_pages)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (unlikely(ret))
+		goto out_uninit;
+	if (!gfs2_is_stuffed(ip))
+		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret = -EIO;
+	return ret;
+}
+
+/**
+ * gfs2_write_begin - Begin to write to a file
+ * @file: The file to write to
+ * @mapping: The mapping in which to write
+ * @pos: The file offset at which to start writing
+ * @len: Length of the write
+ * @flags: Various flags
+ * @pagep: Pointer to return the page
+ * @fsdata: Pointer to return fs data (unused by GFS2)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_begin(struct file *file, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+	int alloc_required;
+	int error = 0;
+	struct gfs2_alloc *al = NULL;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	struct page *page;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
+	if (unlikely(error))
+		goto out_uninit;
+	if (&ip->i_inode == sdp->sd_rindex) {
+		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
+					   GL_NOCACHE, &m_ip->i_gh);
+		if (unlikely(error)) {
+			gfs2_glock_dq(&ip->i_gh);
+			goto out_uninit;
+		}
+	}
+
+	alloc_required = gfs2_write_alloc_required(ip, pos, len);
+
+	if (alloc_required || gfs2_is_jdata(ip))
+		gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
+
+	if (alloc_required) {
+		al = gfs2_alloc_get(ip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_unlock;
+		}
+
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto out_alloc_put;
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto out_qunlock;
+	}
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+	if (&ip->i_inode == sdp->sd_rindex)
+		rblocks += 2 * RES_STATFS;
+	if (alloc_required)
+		rblocks += gfs2_rg_blocks(al);
+
+	error = gfs2_trans_begin(sdp, rblocks,
+				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+	if (error)
+		goto out_trans_fail;
+
+	error = -ENOMEM;
+	flags |= AOP_FLAG_NOFS;
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	*pagep = page;
+	if (unlikely(!page))
+		goto out_endtrans;
+
+	if (gfs2_is_stuffed(ip)) {
+		error = 0;
+		if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
+			error = gfs2_unstuff_dinode(ip, page);
+			if (error == 0)
+				goto prepare_write;
+		} else if (!PageUptodate(page)) {
+			error = stuffed_readpage(ip, page);
+		}
+		goto out;
+	}
+
+prepare_write:
+	error = __block_write_begin(page, from, len, gfs2_block_map);
+out:
+	if (error == 0)
+		return 0;
+
+	unlock_page(page);
+	page_cache_release(page);
+
+	gfs2_trans_end(sdp);
+	if (pos + len > ip->i_inode.i_size)
+		gfs2_trim_blocks(&ip->i_inode);
+	goto out_trans_fail;
+
+out_endtrans:
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	if (alloc_required) {
+		gfs2_inplace_release(ip);
+out_qunlock:
+		gfs2_quota_unlock(ip);
+out_alloc_put:
+		gfs2_alloc_put(ip);
+	}
+out_unlock:
+	if (&ip->i_inode == sdp->sd_rindex) {
+		gfs2_glock_dq(&m_ip->i_gh);
+		gfs2_holder_uninit(&m_ip->i_gh);
+	}
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
+	return error;
+}
+
+/**
+ * adjust_fs_space - Adjusts the free space available due to gfs2_grow
+ * @inode: the rindex inode
+ */
+static void adjust_fs_space(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct buffer_head *m_bh, *l_bh;
+	u64 fs_total, new_free;
+
+	/* Total up the file system space, according to the latest rindex. */
+	fs_total = gfs2_ri_total(sdp);
+	if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0)
+		return;
+
+	spin_lock(&sdp->sd_statfs_spin);
+	gfs2_statfs_change_in(m_sc, m_bh->b_data +
+			      sizeof(struct gfs2_dinode));
+	if (fs_total > (m_sc->sc_total + l_sc->sc_total))
+		new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
+	else
+		new_free = 0;
+	spin_unlock(&sdp->sd_statfs_spin);
+	fs_warn(sdp, "File system extended by %llu blocks.\n",
+		(unsigned long long)new_free);
+	gfs2_statfs_change(sdp, new_free, new_free, 0);
+
+	if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0)
+		goto out;
+	update_statfs(sdp, m_bh, l_bh);
+	brelse(l_bh);
+out:
+	brelse(m_bh);
+}
+
+/**
+ * gfs2_stuffed_write_end - Write end for stuffed files
+ * @inode: The inode
+ * @dibh: The buffer_head containing the on-disk inode
+ * @pos: The file position
+ * @len: The length of the write
+ * @copied: How much was actually copied by the VFS
+ * @page: The page
+ *
+ * This copies the data from the page into the inode block after
+ * the inode data structure itself.
+ *
+ * Returns: errno
+ */
+static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+				  loff_t pos, unsigned len, unsigned copied,
+				  struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	u64 to = pos + copied;
+	void *kaddr;
+	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
+	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+
+	BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(buf + pos, kaddr + pos, copied);
+	memset(kaddr + pos + copied, 0, len - copied);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr, KM_USER0);
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+	unlock_page(page);
+	page_cache_release(page);
+
+	if (copied) {
+		if (inode->i_size < to)
+			i_size_write(inode, to);
+		gfs2_dinode_out(ip, di);
+		mark_inode_dirty(inode);
+	}
+
+	if (inode == sdp->sd_rindex) {
+		adjust_fs_space(inode);
+		ip->i_gh.gh_flags |= GL_NOCACHE;
+	}
+
+	brelse(dibh);
+	gfs2_trans_end(sdp);
+	if (inode == sdp->sd_rindex) {
+		gfs2_glock_dq(&m_ip->i_gh);
+		gfs2_holder_uninit(&m_ip->i_gh);
+	}
+	gfs2_glock_dq(&ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+	return copied;
+}
+
+/**
+ * gfs2_write_end
+ * @file: The file to write to
+ * @mapping: The address space to write to
+ * @pos: The file position
+ * @len: The length of the data
+ * @copied:
+ * @page: The page that has been written
+ * @fsdata: The fsdata (unused in GFS2)
+ *
+ * The main write_end function for GFS2. We have a separate one for
+ * stuffed files as they are slightly different, otherwise we just
+ * put our locking around the VFS provided functions.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_end(struct file *file, struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct page *page, void *fsdata)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct buffer_head *dibh;
+	struct gfs2_alloc *al = ip->i_alloc;
+	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned int to = from + len;
+	int ret;
+
+	BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
+
+	ret = gfs2_meta_inode_buffer(ip, &dibh);
+	if (unlikely(ret)) {
+		unlock_page(page);
+		page_cache_release(page);
+		goto failed;
+	}
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (gfs2_is_stuffed(ip))
+		return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
+
+	if (!gfs2_is_writeback(ip))
+		gfs2_page_add_databufs(ip, page, from, to);
+
+	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	if (ret > 0) {
+		gfs2_dinode_out(ip, dibh->b_data);
+		mark_inode_dirty(inode);
+	}
+
+	if (inode == sdp->sd_rindex) {
+		adjust_fs_space(inode);
+		ip->i_gh.gh_flags |= GL_NOCACHE;
+	}
+
+	brelse(dibh);
+failed:
+	gfs2_trans_end(sdp);
+	if (al) {
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	if (inode == sdp->sd_rindex) {
+		gfs2_glock_dq(&m_ip->i_gh);
+		gfs2_holder_uninit(&m_ip->i_gh);
+	}
+	gfs2_glock_dq(&ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+	return ret;
+}
+
+/**
+ * gfs2_set_page_dirty - Page dirtying function
+ * @page: The page to dirty
+ *
+ * Returns: 1 if it dirtyed the page, or 0 otherwise
+ */
+ 
+static int gfs2_set_page_dirty(struct page *page)
+{
+	SetPageChecked(page);
+	return __set_page_dirty_buffers(page);
+}
+
+/**
+ * gfs2_bmap - Block map function
+ * @mapping: Address space info
+ * @lblock: The block to map
+ *
+ * Returns: The disk address for the block or 0 on hole or error
+ */
+
+static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_holder i_gh;
+	sector_t dblock = 0;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return 0;
+
+	if (!gfs2_is_stuffed(ip))
+		dblock = generic_block_bmap(mapping, lblock, gfs2_block_map);
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return dblock;
+}
+
+static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	lock_buffer(bh);
+	gfs2_log_lock(sdp);
+	clear_buffer_dirty(bh);
+	bd = bh->b_private;
+	if (bd) {
+		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
+			list_del_init(&bd->bd_le.le_list);
+		else
+			gfs2_remove_from_journal(bh, current->journal_info, 0);
+	}
+	bh->b_bdev = NULL;
+	clear_buffer_mapped(bh);
+	clear_buffer_req(bh);
+	clear_buffer_new(bh);
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bh);
+}
+
+static void gfs2_invalidatepage(struct page *page, unsigned long offset)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	struct buffer_head *bh, *head;
+	unsigned long pos = 0;
+
+	BUG_ON(!PageLocked(page));
+	if (offset == 0)
+		ClearPageChecked(page);
+	if (!page_has_buffers(page))
+		goto out;
+
+	bh = head = page_buffers(page);
+	do {
+		if (offset <= pos)
+			gfs2_discard(sdp, bh);
+		pos += bh->b_size;
+		bh = bh->b_this_page;
+	} while (bh != head);
+out:
+	if (offset == 0)
+		try_to_release_page(page, 0);
+}
+
+/**
+ * gfs2_ok_for_dio - check that dio is valid on this file
+ * @ip: The inode
+ * @rw: READ or WRITE
+ * @offset: The offset at which we are reading or writing
+ *
+ * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
+ *          1 (to accept the i/o request)
+ */
+static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
+{
+	/*
+	 * Should we return an error here? I can't see that O_DIRECT for
+	 * a stuffed file makes any sense. For now we'll silently fall
+	 * back to buffered I/O
+	 */
+	if (gfs2_is_stuffed(ip))
+		return 0;
+
+	if (offset >= i_size_read(&ip->i_inode))
+		return 0;
+	return 1;
+}
+
+
+
+static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int rv;
+
+	/*
+	 * Deferred lock, even if its a write, since we do no allocation
+	 * on this path. All we need change is atime, and this lock mode
+	 * ensures that other nodes have flushed their buffered read caches
+	 * (i.e. their page cache entries for this inode). We do not,
+	 * unfortunately have the option of only flushing a range like
+	 * the VFS does.
+	 */
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	rv = gfs2_glock_nq(&gh);
+	if (rv)
+		return rv;
+	rv = gfs2_ok_for_dio(ip, rw, offset);
+	if (rv != 1)
+		goto out; /* dio not valid, fall back to buffered i/o */
+
+	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+				  offset, nr_segs, gfs2_get_block_direct,
+				  NULL, NULL, 0);
+out:
+	gfs2_glock_dq_m(1, &gh);
+	gfs2_holder_uninit(&gh);
+	return rv;
+}
+
+/**
+ * gfs2_releasepage - free the metadata associated with a page
+ * @page: the page that's being released
+ * @gfp_mask: passed from Linux VFS, ignored by us
+ *
+ * Call try_to_free_buffers() if the buffers in this page can be
+ * released.
+ *
+ * Returns: 0
+ */
+
+int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	struct address_space *mapping = page->mapping;
+	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
+	struct buffer_head *bh, *head;
+	struct gfs2_bufdata *bd;
+
+	if (!page_has_buffers(page))
+		return 0;
+
+	gfs2_log_lock(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	head = bh = page_buffers(page);
+	do {
+		if (atomic_read(&bh->b_count))
+			goto cannot_release;
+		bd = bh->b_private;
+		if (bd && bd->bd_ail)
+			goto cannot_release;
+		if (buffer_pinned(bh) || buffer_dirty(bh))
+			goto not_possible;
+		bh = bh->b_this_page;
+	} while(bh != head);
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+
+	head = bh = page_buffers(page);
+	do {
+		gfs2_log_lock(sdp);
+		bd = bh->b_private;
+		if (bd) {
+			gfs2_assert_warn(sdp, bd->bd_bh == bh);
+			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
+			if (!list_empty(&bd->bd_le.le_list)) {
+				if (!buffer_pinned(bh))
+					list_del_init(&bd->bd_le.le_list);
+				else
+					bd = NULL;
+			}
+			if (bd)
+				bd->bd_bh = NULL;
+			bh->b_private = NULL;
+		}
+		gfs2_log_unlock(sdp);
+		if (bd)
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	return try_to_free_buffers(page);
+
+not_possible: /* Should never happen */
+	WARN_ON(buffer_dirty(bh));
+	WARN_ON(buffer_pinned(bh));
+cannot_release:
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+	return 0;
+}
+
+static const struct address_space_operations gfs2_writeback_aops = {
+	.writepage = gfs2_writeback_writepage,
+	.writepages = gfs2_writeback_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+	.migratepage = buffer_migrate_page,
+	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
+};
+
+static const struct address_space_operations gfs2_ordered_aops = {
+	.writepage = gfs2_ordered_writepage,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.set_page_dirty = gfs2_set_page_dirty,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+	.migratepage = buffer_migrate_page,
+	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
+};
+
+static const struct address_space_operations gfs2_jdata_aops = {
+	.writepage = gfs2_jdata_writepage,
+	.writepages = gfs2_jdata_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.set_page_dirty = gfs2_set_page_dirty,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
+};
+
+void gfs2_set_aops(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (gfs2_is_writeback(ip))
+		inode->i_mapping->a_ops = &gfs2_writeback_aops;
+	else if (gfs2_is_ordered(ip))
+		inode->i_mapping->a_ops = &gfs2_ordered_aops;
+	else if (gfs2_is_jdata(ip))
+		inode->i_mapping->a_ops = &gfs2_jdata_aops;
+	else
+		BUG();
+}
+
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
new file mode 100644
index 00000000..e65493a8
--- /dev/null
+++ b/fs/gfs2/bmap.c
@@ -0,0 +1,1297 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "super.h"
+#include "trans.h"
+#include "dir.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+/* This doesn't need to be that large as max 64 bit pointers in a 4k
+ * block is 512, so __u16 is fine for that. It saves stack space to
+ * keep it small.
+ */
+struct metapath {
+	struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT];
+	__u16 mp_list[GFS2_MAX_META_HEIGHT];
+};
+
+typedef int (*block_call_t) (struct gfs2_inode *ip, struct buffer_head *dibh,
+			     struct buffer_head *bh, __be64 *top,
+			     __be64 *bottom, unsigned int height,
+			     void *data);
+
+struct strip_mine {
+	int sm_first;
+	unsigned int sm_height;
+};
+
+/**
+ * gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
+ * @ip: the inode
+ * @dibh: the dinode buffer
+ * @block: the block number that was allocated
+ * @page: The (optional) page. This is looked up if @page is NULL
+ *
+ * Returns: errno
+ */
+
+static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
+			       u64 block, struct page *page)
+{
+	struct inode *inode = &ip->i_inode;
+	struct buffer_head *bh;
+	int release = 0;
+
+	if (!page || page->index) {
+		page = grab_cache_page(inode->i_mapping, 0);
+		if (!page)
+			return -ENOMEM;
+		release = 1;
+	}
+
+	if (!PageUptodate(page)) {
+		void *kaddr = kmap(page);
+		u64 dsize = i_size_read(inode);
+ 
+		if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
+			dsize = dibh->b_size - sizeof(struct gfs2_dinode);
+
+		memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
+		memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
+		kunmap(page);
+
+		SetPageUptodate(page);
+	}
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, 1 << inode->i_blkbits,
+				     (1 << BH_Uptodate));
+
+	bh = page_buffers(page);
+
+	if (!buffer_mapped(bh))
+		map_bh(bh, inode->i_sb, block);
+
+	set_buffer_uptodate(bh);
+	if (!gfs2_is_jdata(ip))
+		mark_buffer_dirty(bh);
+	if (!gfs2_is_writeback(ip))
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+
+	if (release) {
+		unlock_page(page);
+		page_cache_release(page);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
+ * @ip: The GFS2 inode to unstuff
+ * @page: The (optional) page. This is looked up if the @page is NULL
+ *
+ * This routine unstuffs a dinode and returns it to a "normal" state such
+ * that the height can be grown in the traditional way.
+ *
+ * Returns: errno
+ */
+
+int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
+{
+	struct buffer_head *bh, *dibh;
+	struct gfs2_dinode *di;
+	u64 block = 0;
+	int isdir = gfs2_is_dir(ip);
+	int error;
+
+	down_write(&ip->i_rw_mutex);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out;
+
+	if (i_size_read(&ip->i_inode)) {
+		/* Get a free block, fill it with the stuffed data,
+		   and write it out to disk */
+
+		unsigned int n = 1;
+		error = gfs2_alloc_block(ip, &block, &n);
+		if (error)
+			goto out_brelse;
+		if (isdir) {
+			gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
+			error = gfs2_dir_get_new_buffer(ip, block, &bh);
+			if (error)
+				goto out_brelse;
+			gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header),
+					      dibh, sizeof(struct gfs2_dinode));
+			brelse(bh);
+		} else {
+			error = gfs2_unstuffer_page(ip, dibh, block, page);
+			if (error)
+				goto out_brelse;
+		}
+	}
+
+	/*  Set up the pointer to the new block  */
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	di = (struct gfs2_dinode *)dibh->b_data;
+	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
+
+	if (i_size_read(&ip->i_inode)) {
+		*(__be64 *)(di + 1) = cpu_to_be64(block);
+		gfs2_add_inode_blocks(&ip->i_inode, 1);
+		di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
+	}
+
+	ip->i_height = 1;
+	di->di_height = cpu_to_be16(1);
+
+out_brelse:
+	brelse(dibh);
+out:
+	up_write(&ip->i_rw_mutex);
+	return error;
+}
+
+
+/**
+ * find_metapath - Find path through the metadata tree
+ * @sdp: The superblock
+ * @mp: The metapath to return the result in
+ * @block: The disk block to look up
+ * @height: The pre-calculated height of the metadata tree
+ *
+ *   This routine returns a struct metapath structure that defines a path
+ *   through the metadata of inode "ip" to get to block "block".
+ *
+ *   Example:
+ *   Given:  "ip" is a height 3 file, "offset" is 101342453, and this is a
+ *   filesystem with a blocksize of 4096.
+ *
+ *   find_metapath() would return a struct metapath structure set to:
+ *   mp_offset = 101342453, mp_height = 3, mp_list[0] = 0, mp_list[1] = 48,
+ *   and mp_list[2] = 165.
+ *
+ *   That means that in order to get to the block containing the byte at
+ *   offset 101342453, we would load the indirect block pointed to by pointer
+ *   0 in the dinode.  We would then load the indirect block pointed to by
+ *   pointer 48 in that indirect block.  We would then load the data block
+ *   pointed to by pointer 165 in that indirect block.
+ *
+ *             ----------------------------------------
+ *             | Dinode |                             |
+ *             |        |                            4|
+ *             |        |0 1 2 3 4 5                 9|
+ *             |        |                            6|
+ *             ----------------------------------------
+ *                       |
+ *                       |
+ *                       V
+ *             ----------------------------------------
+ *             | Indirect Block                       |
+ *             |                                     5|
+ *             |            4 4 4 4 4 5 5            1|
+ *             |0           5 6 7 8 9 0 1            2|
+ *             ----------------------------------------
+ *                                |
+ *                                |
+ *                                V
+ *             ----------------------------------------
+ *             | Indirect Block                       |
+ *             |                         1 1 1 1 1   5|
+ *             |                         6 6 6 6 6   1|
+ *             |0                        3 4 5 6 7   2|
+ *             ----------------------------------------
+ *                                           |
+ *                                           |
+ *                                           V
+ *             ----------------------------------------
+ *             | Data block containing offset         |
+ *             |            101342453                 |
+ *             |                                      |
+ *             |                                      |
+ *             ----------------------------------------
+ *
+ */
+
+static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
+			  struct metapath *mp, unsigned int height)
+{
+	unsigned int i;
+
+	for (i = height; i--;)
+		mp->mp_list[i] = do_div(block, sdp->sd_inptrs);
+
+}
+
+static inline unsigned int metapath_branch_start(const struct metapath *mp)
+{
+	if (mp->mp_list[0] == 0)
+		return 2;
+	return 1;
+}
+
+/**
+ * metapointer - Return pointer to start of metadata in a buffer
+ * @height: The metadata height (0 = dinode)
+ * @mp: The metapath
+ *
+ * Return a pointer to the block number of the next height of the metadata
+ * tree given a buffer containing the pointer to the current height of the
+ * metadata tree.
+ */
+
+static inline __be64 *metapointer(unsigned int height, const struct metapath *mp)
+{
+	struct buffer_head *bh = mp->mp_bh[height];
+	unsigned int head_size = (height > 0) ?
+		sizeof(struct gfs2_meta_header) : sizeof(struct gfs2_dinode);
+	return ((__be64 *)(bh->b_data + head_size)) + mp->mp_list[height];
+}
+
+/**
+ * lookup_metapath - Walk the metadata tree to a specific point
+ * @ip: The inode
+ * @mp: The metapath
+ *
+ * Assumes that the inode's buffer has already been looked up and
+ * hooked onto mp->mp_bh[0] and that the metapath has been initialised
+ * by find_metapath().
+ *
+ * If this function encounters part of the tree which has not been
+ * allocated, it returns the current height of the tree at the point
+ * at which it found the unallocated block. Blocks which are found are
+ * added to the mp->mp_bh[] list.
+ *
+ * Returns: error or height of metadata tree
+ */
+
+static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
+{
+	unsigned int end_of_metadata = ip->i_height - 1;
+	unsigned int x;
+	__be64 *ptr;
+	u64 dblock;
+	int ret;
+
+	for (x = 0; x < end_of_metadata; x++) {
+		ptr = metapointer(x, mp);
+		dblock = be64_to_cpu(*ptr);
+		if (!dblock)
+			return x + 1;
+
+		ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, 0, &mp->mp_bh[x+1]);
+		if (ret)
+			return ret;
+	}
+
+	return ip->i_height;
+}
+
+static inline void release_metapath(struct metapath *mp)
+{
+	int i;
+
+	for (i = 0; i < GFS2_MAX_META_HEIGHT; i++) {
+		if (mp->mp_bh[i] == NULL)
+			break;
+		brelse(mp->mp_bh[i]);
+	}
+}
+
+/**
+ * gfs2_extent_length - Returns length of an extent of blocks
+ * @start: Start of the buffer
+ * @len: Length of the buffer in bytes
+ * @ptr: Current position in the buffer
+ * @limit: Max extent length to return (0 = unlimited)
+ * @eob: Set to 1 if we hit "end of block"
+ *
+ * If the first block is zero (unallocated) it will return the number of
+ * unallocated blocks in the extent, otherwise it will return the number
+ * of contiguous blocks in the extent.
+ *
+ * Returns: The length of the extent (minimum of one block)
+ */
+
+static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __be64 *ptr, unsigned limit, int *eob)
+{
+	const __be64 *end = (start + len);
+	const __be64 *first = ptr;
+	u64 d = be64_to_cpu(*ptr);
+
+	*eob = 0;
+	do {
+		ptr++;
+		if (ptr >= end)
+			break;
+		if (limit && --limit == 0)
+			break;
+		if (d)
+			d++;
+	} while(be64_to_cpu(*ptr) == d);
+	if (ptr >= end)
+		*eob = 1;
+	return (ptr - first);
+}
+
+static inline void bmap_lock(struct gfs2_inode *ip, int create)
+{
+	if (create)
+		down_write(&ip->i_rw_mutex);
+	else
+		down_read(&ip->i_rw_mutex);
+}
+
+static inline void bmap_unlock(struct gfs2_inode *ip, int create)
+{
+	if (create)
+		up_write(&ip->i_rw_mutex);
+	else
+		up_read(&ip->i_rw_mutex);
+}
+
+static inline __be64 *gfs2_indirect_init(struct metapath *mp,
+					 struct gfs2_glock *gl, unsigned int i,
+					 unsigned offset, u64 bn)
+{
+	__be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data +
+		       ((i > 1) ? sizeof(struct gfs2_meta_header) :
+				 sizeof(struct gfs2_dinode)));
+	BUG_ON(i < 1);
+	BUG_ON(mp->mp_bh[i] != NULL);
+	mp->mp_bh[i] = gfs2_meta_new(gl, bn);
+	gfs2_trans_add_bh(gl, mp->mp_bh[i], 1);
+	gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
+	gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
+	ptr += offset;
+	*ptr = cpu_to_be64(bn);
+	return ptr;
+}
+
+enum alloc_state {
+	ALLOC_DATA = 0,
+	ALLOC_GROW_DEPTH = 1,
+	ALLOC_GROW_HEIGHT = 2,
+	/* ALLOC_UNSTUFF = 3,   TBD and rather complicated */
+};
+
+/**
+ * gfs2_bmap_alloc - Build a metadata tree of the requested height
+ * @inode: The GFS2 inode
+ * @lblock: The logical starting block of the extent
+ * @bh_map: This is used to return the mapping details
+ * @mp: The metapath
+ * @sheight: The starting height (i.e. whats already mapped)
+ * @height: The height to build to
+ * @maxlen: The max number of data blocks to alloc
+ *
+ * In this routine we may have to alloc:
+ *   i) Indirect blocks to grow the metadata tree height
+ *  ii) Indirect blocks to fill in lower part of the metadata tree
+ * iii) Data blocks
+ *
+ * The function is in two parts. The first part works out the total
+ * number of blocks which we need. The second part does the actual
+ * allocation asking for an extent at a time (if enough contiguous free
+ * blocks are available, there will only be one request per bmap call)
+ * and uses the state machine to initialise the blocks in order.
+ *
+ * Returns: errno on error
+ */
+
+static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
+			   struct buffer_head *bh_map, struct metapath *mp,
+			   const unsigned int sheight,
+			   const unsigned int height,
+			   const unsigned int maxlen)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *dibh = mp->mp_bh[0];
+	u64 bn, dblock = 0;
+	unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
+	unsigned dblks = 0;
+	unsigned ptrs_per_blk;
+	const unsigned end_of_metadata = height - 1;
+	int eob = 0;
+	enum alloc_state state;
+	__be64 *ptr;
+	__be64 zero_bn = 0;
+
+	BUG_ON(sheight < 1);
+	BUG_ON(dibh == NULL);
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (height == sheight) {
+		struct buffer_head *bh;
+		/* Bottom indirect block exists, find unalloced extent size */
+		ptr = metapointer(end_of_metadata, mp);
+		bh = mp->mp_bh[end_of_metadata];
+		dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen,
+					   &eob);
+		BUG_ON(dblks < 1);
+		state = ALLOC_DATA;
+	} else {
+		/* Need to allocate indirect blocks */
+		ptrs_per_blk = height > 1 ? sdp->sd_inptrs : sdp->sd_diptrs;
+		dblks = min(maxlen, ptrs_per_blk - mp->mp_list[end_of_metadata]);
+		if (height == ip->i_height) {
+			/* Writing into existing tree, extend tree down */
+			iblks = height - sheight;
+			state = ALLOC_GROW_DEPTH;
+		} else {
+			/* Building up tree height */
+			state = ALLOC_GROW_HEIGHT;
+			iblks = height - ip->i_height;
+			branch_start = metapath_branch_start(mp);
+			iblks += (height - branch_start);
+		}
+	}
+
+	/* start of the second part of the function (state machine) */
+
+	blks = dblks + iblks;
+	i = sheight;
+	do {
+		int error;
+		n = blks - alloced;
+		error = gfs2_alloc_block(ip, &bn, &n);
+		if (error)
+			return error;
+		alloced += n;
+		if (state != ALLOC_DATA || gfs2_is_jdata(ip))
+			gfs2_trans_add_unrevoke(sdp, bn, n);
+		switch (state) {
+		/* Growing height of tree */
+		case ALLOC_GROW_HEIGHT:
+			if (i == 1) {
+				ptr = (__be64 *)(dibh->b_data +
+						 sizeof(struct gfs2_dinode));
+				zero_bn = *ptr;
+			}
+			for (; i - 1 < height - ip->i_height && n > 0; i++, n--)
+				gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++);
+			if (i - 1 == height - ip->i_height) {
+				i--;
+				gfs2_buffer_copy_tail(mp->mp_bh[i],
+						sizeof(struct gfs2_meta_header),
+						dibh, sizeof(struct gfs2_dinode));
+				gfs2_buffer_clear_tail(dibh,
+						sizeof(struct gfs2_dinode) +
+						sizeof(__be64));
+				ptr = (__be64 *)(mp->mp_bh[i]->b_data +
+					sizeof(struct gfs2_meta_header));
+				*ptr = zero_bn;
+				state = ALLOC_GROW_DEPTH;
+				for(i = branch_start; i < height; i++) {
+					if (mp->mp_bh[i] == NULL)
+						break;
+					brelse(mp->mp_bh[i]);
+					mp->mp_bh[i] = NULL;
+				}
+				i = branch_start;
+			}
+			if (n == 0)
+				break;
+		/* Branching from existing tree */
+		case ALLOC_GROW_DEPTH:
+			if (i > 1 && i < height)
+				gfs2_trans_add_bh(ip->i_gl, mp->mp_bh[i-1], 1);
+			for (; i < height && n > 0; i++, n--)
+				gfs2_indirect_init(mp, ip->i_gl, i,
+						   mp->mp_list[i-1], bn++);
+			if (i == height)
+				state = ALLOC_DATA;
+			if (n == 0)
+				break;
+		/* Tree complete, adding data blocks */
+		case ALLOC_DATA:
+			BUG_ON(n > dblks);
+			BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
+			gfs2_trans_add_bh(ip->i_gl, mp->mp_bh[end_of_metadata], 1);
+			dblks = n;
+			ptr = metapointer(end_of_metadata, mp);
+			dblock = bn;
+			while (n-- > 0)
+				*ptr++ = cpu_to_be64(bn++);
+			break;
+		}
+	} while ((state != ALLOC_DATA) || !dblock);
+
+	ip->i_height = height;
+	gfs2_add_inode_blocks(&ip->i_inode, alloced);
+	gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
+	map_bh(bh_map, inode->i_sb, dblock);
+	bh_map->b_size = dblks << inode->i_blkbits;
+	set_buffer_new(bh_map);
+	return 0;
+}
+
+/**
+ * gfs2_block_map - Map a block from an inode to a disk block
+ * @inode: The inode
+ * @lblock: The logical block number
+ * @bh_map: The bh to be mapped
+ * @create: True if its ok to alloc blocks to satify the request
+ *
+ * Sets buffer_mapped() if successful, sets buffer_boundary() if a
+ * read of metadata will be required before the next block can be
+ * mapped. Sets buffer_new() if new blocks were allocated.
+ *
+ * Returns: errno
+ */
+
+int gfs2_block_map(struct inode *inode, sector_t lblock,
+		   struct buffer_head *bh_map, int create)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	unsigned int bsize = sdp->sd_sb.sb_bsize;
+	const unsigned int maxlen = bh_map->b_size >> inode->i_blkbits;
+	const u64 *arr = sdp->sd_heightsize;
+	__be64 *ptr;
+	u64 size;
+	struct metapath mp;
+	int ret;
+	int eob;
+	unsigned int len;
+	struct buffer_head *bh;
+	u8 height;
+
+	BUG_ON(maxlen == 0);
+
+	memset(mp.mp_bh, 0, sizeof(mp.mp_bh));
+	bmap_lock(ip, create);
+	clear_buffer_mapped(bh_map);
+	clear_buffer_new(bh_map);
+	clear_buffer_boundary(bh_map);
+	trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
+	if (gfs2_is_dir(ip)) {
+		bsize = sdp->sd_jbsize;
+		arr = sdp->sd_jheightsize;
+	}
+
+	ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
+	if (ret)
+		goto out;
+
+	height = ip->i_height;
+	size = (lblock + 1) * bsize;
+	while (size > arr[height])
+		height++;
+	find_metapath(sdp, lblock, &mp, height);
+	ret = 1;
+	if (height > ip->i_height || gfs2_is_stuffed(ip))
+		goto do_alloc;
+	ret = lookup_metapath(ip, &mp);
+	if (ret < 0)
+		goto out;
+	if (ret != ip->i_height)
+		goto do_alloc;
+	ptr = metapointer(ip->i_height - 1, &mp);
+	if (*ptr == 0)
+		goto do_alloc;
+	map_bh(bh_map, inode->i_sb, be64_to_cpu(*ptr));
+	bh = mp.mp_bh[ip->i_height - 1];
+	len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen, &eob);
+	bh_map->b_size = (len << inode->i_blkbits);
+	if (eob)
+		set_buffer_boundary(bh_map);
+	ret = 0;
+out:
+	release_metapath(&mp);
+	trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
+	bmap_unlock(ip, create);
+	return ret;
+
+do_alloc:
+	/* All allocations are done here, firstly check create flag */
+	if (!create) {
+		BUG_ON(gfs2_is_stuffed(ip));
+		ret = 0;
+		goto out;
+	}
+
+	/* At this point ret is the tree depth of already allocated blocks */
+	ret = gfs2_bmap_alloc(inode, lblock, bh_map, &mp, ret, height, maxlen);
+	goto out;
+}
+
+/*
+ * Deprecated: do not use in new code
+ */
+int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen)
+{
+	struct buffer_head bh = { .b_state = 0, .b_blocknr = 0 };
+	int ret;
+	int create = *new;
+
+	BUG_ON(!extlen);
+	BUG_ON(!dblock);
+	BUG_ON(!new);
+
+	bh.b_size = 1 << (inode->i_blkbits + (create ? 0 : 5));
+	ret = gfs2_block_map(inode, lblock, &bh, create);
+	*extlen = bh.b_size >> inode->i_blkbits;
+	*dblock = bh.b_blocknr;
+	if (buffer_new(&bh))
+		*new = 1;
+	else
+		*new = 0;
+	return ret;
+}
+
+/**
+ * recursive_scan - recursively scan through the end of a file
+ * @ip: the inode
+ * @dibh: the dinode buffer
+ * @mp: the path through the metadata to the point to start
+ * @height: the height the recursion is at
+ * @block: the indirect block to look at
+ * @first: 1 if this is the first block
+ * @bc: the call to make for each piece of metadata
+ * @data: data opaque to this function to pass to @bc
+ *
+ * When this is first called @height and @block should be zero and
+ * @first should be 1.
+ *
+ * Returns: errno
+ */
+
+static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
+			  struct metapath *mp, unsigned int height,
+			  u64 block, int first, block_call_t bc,
+			  void *data)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh = NULL;
+	__be64 *top, *bottom;
+	u64 bn;
+	int error;
+	int mh_size = sizeof(struct gfs2_meta_header);
+
+	if (!height) {
+		error = gfs2_meta_inode_buffer(ip, &bh);
+		if (error)
+			return error;
+		dibh = bh;
+
+		top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0];
+		bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs;
+	} else {
+		error = gfs2_meta_indirect_buffer(ip, height, block, 0, &bh);
+		if (error)
+			return error;
+
+		top = (__be64 *)(bh->b_data + mh_size) +
+				  (first ? mp->mp_list[height] : 0);
+
+		bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs;
+	}
+
+	error = bc(ip, dibh, bh, top, bottom, height, data);
+	if (error)
+		goto out;
+
+	if (height < ip->i_height - 1)
+		for (; top < bottom; top++, first = 0) {
+			if (!*top)
+				continue;
+
+			bn = be64_to_cpu(*top);
+
+			error = recursive_scan(ip, dibh, mp, height + 1, bn,
+					       first, bc, data);
+			if (error)
+				break;
+		}
+
+out:
+	brelse(bh);
+	return error;
+}
+
+/**
+ * do_strip - Look for a layer a particular layer of the file and strip it off
+ * @ip: the inode
+ * @dibh: the dinode buffer
+ * @bh: A buffer of pointers
+ * @top: The first pointer in the buffer
+ * @bottom: One more than the last pointer
+ * @height: the height this buffer is at
+ * @data: a pointer to a struct strip_mine
+ *
+ * Returns: errno
+ */
+
+static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
+		    struct buffer_head *bh, __be64 *top, __be64 *bottom,
+		    unsigned int height, void *data)
+{
+	struct strip_mine *sm = data;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrp_list rlist;
+	u64 bn, bstart;
+	u32 blen, btotal;
+	__be64 *p;
+	unsigned int rg_blocks = 0;
+	int metadata;
+	unsigned int revokes = 0;
+	int x;
+	int error = 0;
+
+	if (!*top)
+		sm->sm_first = 0;
+
+	if (height != sm->sm_height)
+		return 0;
+
+	if (sm->sm_first) {
+		top++;
+		sm->sm_first = 0;
+	}
+
+	metadata = (height != ip->i_height - 1);
+	if (metadata)
+		revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs;
+	else if (ip->i_depth)
+		revokes = sdp->sd_inptrs;
+
+	if (ip != GFS2_I(sdp->sd_rindex))
+		error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
+	else if (!sdp->sd_rgrps)
+		error = gfs2_ri_update(ip);
+
+	if (error)
+		return error;
+
+	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
+	bstart = 0;
+	blen = 0;
+
+	for (p = top; p < bottom; p++) {
+		if (!*p)
+			continue;
+
+		bn = be64_to_cpu(*p);
+
+		if (bstart + blen == bn)
+			blen++;
+		else {
+			if (bstart)
+				gfs2_rlist_add(sdp, &rlist, bstart);
+
+			bstart = bn;
+			blen = 1;
+		}
+	}
+
+	if (bstart)
+		gfs2_rlist_add(sdp, &rlist, bstart);
+	else
+		goto out; /* Nothing to do */
+
+	gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE);
+
+	for (x = 0; x < rlist.rl_rgrps; x++) {
+		struct gfs2_rgrpd *rgd;
+		rgd = rlist.rl_ghs[x].gh_gl->gl_object;
+		rg_blocks += rgd->rd_length;
+	}
+
+	error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs);
+	if (error)
+		goto out_rlist;
+
+	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
+				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
+				 revokes);
+	if (error)
+		goto out_rg_gunlock;
+
+	down_write(&ip->i_rw_mutex);
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+
+	bstart = 0;
+	blen = 0;
+	btotal = 0;
+
+	for (p = top; p < bottom; p++) {
+		if (!*p)
+			continue;
+
+		bn = be64_to_cpu(*p);
+
+		if (bstart + blen == bn)
+			blen++;
+		else {
+			if (bstart) {
+				if (metadata)
+					__gfs2_free_meta(ip, bstart, blen);
+				else
+					__gfs2_free_data(ip, bstart, blen);
+
+				btotal += blen;
+			}
+
+			bstart = bn;
+			blen = 1;
+		}
+
+		*p = 0;
+		gfs2_add_inode_blocks(&ip->i_inode, -1);
+	}
+	if (bstart) {
+		if (metadata)
+			__gfs2_free_meta(ip, bstart, blen);
+		else
+			__gfs2_free_data(ip, bstart, blen);
+
+		btotal += blen;
+	}
+
+	gfs2_statfs_change(sdp, 0, +btotal, 0);
+	gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid,
+			  ip->i_inode.i_gid);
+
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+
+	gfs2_dinode_out(ip, dibh->b_data);
+
+	up_write(&ip->i_rw_mutex);
+
+	gfs2_trans_end(sdp);
+
+out_rg_gunlock:
+	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
+out_rlist:
+	gfs2_rlist_free(&rlist);
+out:
+	if (ip != GFS2_I(sdp->sd_rindex))
+		gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
+	return error;
+}
+
+/**
+ * gfs2_block_truncate_page - Deal with zeroing out data for truncate
+ *
+ * This is partly borrowed from ext3.
+ */
+static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned long index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize, iblock, length, pos;
+	struct buffer_head *bh;
+	struct page *page;
+	int err;
+
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return 0;
+
+	blocksize = inode->i_sb->s_blocksize;
+	length = blocksize - (offset & (blocksize - 1));
+	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
+
+	/* Find the buffer that contains "offset" */
+	bh = page_buffers(page);
+	pos = blocksize;
+	while (offset >= pos) {
+		bh = bh->b_this_page;
+		iblock++;
+		pos += blocksize;
+	}
+
+	err = 0;
+
+	if (!buffer_mapped(bh)) {
+		gfs2_block_map(inode, iblock, bh, 0);
+		/* unmapped? It's a hole - nothing to do */
+		if (!buffer_mapped(bh))
+			goto unlock;
+	}
+
+	/* Ok, it's mapped. Make sure it's up-to-date */
+	if (PageUptodate(page))
+		set_buffer_uptodate(bh);
+
+	if (!buffer_uptodate(bh)) {
+		err = -EIO;
+		ll_rw_block(READ, 1, &bh);
+		wait_on_buffer(bh);
+		/* Uhhuh. Read error. Complain and punt. */
+		if (!buffer_uptodate(bh))
+			goto unlock;
+		err = 0;
+	}
+
+	if (!gfs2_is_writeback(ip))
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+
+	zero_user(page, offset, length);
+	mark_buffer_dirty(bh);
+unlock:
+	unlock_page(page);
+	page_cache_release(page);
+	return err;
+}
+
+static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct address_space *mapping = inode->i_mapping;
+	struct buffer_head *dibh;
+	int journaled = gfs2_is_jdata(ip);
+	int error;
+
+	error = gfs2_trans_begin(sdp,
+				 RES_DINODE + (journaled ? RES_JDATA : 0), 0);
+	if (error)
+		return error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (gfs2_is_stuffed(ip)) {
+		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
+	} else {
+		if (newsize & (u64)(sdp->sd_sb.sb_bsize - 1)) {
+			error = gfs2_block_truncate_page(mapping, newsize);
+			if (error)
+				goto out_brelse;
+		}
+		ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;
+	}
+
+	i_size_write(inode, newsize);
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_dinode_out(ip, dibh->b_data);
+
+	truncate_pagecache(inode, oldsize, newsize);
+out_brelse:
+	brelse(dibh);
+out:
+	gfs2_trans_end(sdp);
+	return error;
+}
+
+static int trunc_dealloc(struct gfs2_inode *ip, u64 size)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int height = ip->i_height;
+	u64 lblock;
+	struct metapath mp;
+	int error;
+
+	if (!size)
+		lblock = 0;
+	else
+		lblock = (size - 1) >> sdp->sd_sb.sb_bsize_shift;
+
+	find_metapath(sdp, lblock, &mp, ip->i_height);
+	if (!gfs2_alloc_get(ip))
+		return -ENOMEM;
+
+	error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto out;
+
+	while (height--) {
+		struct strip_mine sm;
+		sm.sm_first = !!size;
+		sm.sm_height = height;
+
+		error = recursive_scan(ip, NULL, &mp, 0, 0, 1, do_strip, &sm);
+		if (error)
+			break;
+	}
+
+	gfs2_quota_unhold(ip);
+
+out:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+static int trunc_end(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		return error;
+
+	down_write(&ip->i_rw_mutex);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out;
+
+	if (!i_size_read(&ip->i_inode)) {
+		ip->i_height = 0;
+		ip->i_goal = ip->i_no_addr;
+		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
+	}
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+
+out:
+	up_write(&ip->i_rw_mutex);
+	gfs2_trans_end(sdp);
+	return error;
+}
+
+/**
+ * do_shrink - make a file smaller
+ * @inode: the inode
+ * @oldsize: the current inode size
+ * @newsize: the size to make the file
+ *
+ * Called with an exclusive lock on @inode. The @size must
+ * be equal to or smaller than the current inode size.
+ *
+ * Returns: errno
+ */
+
+static int do_shrink(struct inode *inode, u64 oldsize, u64 newsize)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int error;
+
+	error = trunc_start(inode, oldsize, newsize);
+	if (error < 0)
+		return error;
+	if (gfs2_is_stuffed(ip))
+		return 0;
+
+	error = trunc_dealloc(ip, newsize);
+	if (error == 0)
+		error = trunc_end(ip);
+
+	return error;
+}
+
+void gfs2_trim_blocks(struct inode *inode)
+{
+	u64 size = inode->i_size;
+	int ret;
+
+	ret = do_shrink(inode, size, size);
+	WARN_ON(ret != 0);
+}
+
+/**
+ * do_grow - Touch and update inode size
+ * @inode: The inode
+ * @size: The new size
+ *
+ * This function updates the timestamps on the inode and
+ * may also increase the size of the inode. This function
+ * must not be called with @size any smaller than the current
+ * inode size.
+ *
+ * Although it is not strictly required to unstuff files here,
+ * earlier versions of GFS2 have a bug in the stuffed file reading
+ * code which will result in a buffer overrun if the size is larger
+ * than the max stuffed file size. In order to prevent this from
+ * occurring, such files are unstuffed, but in other cases we can
+ * just update the inode size directly.
+ *
+ * Returns: 0 on success, or -ve on error
+ */
+
+static int do_grow(struct inode *inode, u64 size)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *dibh;
+	struct gfs2_alloc *al = NULL;
+	int error;
+
+	if (gfs2_is_stuffed(ip) &&
+	    (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) {
+		al = gfs2_alloc_get(ip);
+		if (al == NULL)
+			return -ENOMEM;
+
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto do_grow_alloc_put;
+
+		al->al_requested = 1;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto do_grow_qunlock;
+	}
+
+	error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT, 0);
+	if (error)
+		goto do_grow_release;
+
+	if (al) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (error)
+			goto do_end_trans;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto do_end_trans;
+
+	i_size_write(inode, size);
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+
+do_end_trans:
+	gfs2_trans_end(sdp);
+do_grow_release:
+	if (al) {
+		gfs2_inplace_release(ip);
+do_grow_qunlock:
+		gfs2_quota_unlock(ip);
+do_grow_alloc_put:
+		gfs2_alloc_put(ip);
+	}
+	return error;
+}
+
+/**
+ * gfs2_setattr_size - make a file a given size
+ * @inode: the inode
+ * @newsize: the size to make the file
+ *
+ * The file size can grow, shrink, or stay the same size. This
+ * is called holding i_mutex and an exclusive glock on the inode
+ * in question.
+ *
+ * Returns: errno
+ */
+
+int gfs2_setattr_size(struct inode *inode, u64 newsize)
+{
+	int ret;
+	u64 oldsize;
+
+	BUG_ON(!S_ISREG(inode->i_mode));
+
+	ret = inode_newsize_ok(inode, newsize);
+	if (ret)
+		return ret;
+
+	oldsize = inode->i_size;
+	if (newsize >= oldsize)
+		return do_grow(inode, newsize);
+
+	return do_shrink(inode, oldsize, newsize);
+}
+
+int gfs2_truncatei_resume(struct gfs2_inode *ip)
+{
+	int error;
+	error = trunc_dealloc(ip, i_size_read(&ip->i_inode));
+	if (!error)
+		error = trunc_end(ip);
+	return error;
+}
+
+int gfs2_file_dealloc(struct gfs2_inode *ip)
+{
+	return trunc_dealloc(ip, 0);
+}
+
+/**
+ * gfs2_write_alloc_required - figure out if a write will require an allocation
+ * @ip: the file being written to
+ * @offset: the offset to write to
+ * @len: the number of bytes being written
+ *
+ * Returns: 1 if an alloc is required, 0 otherwise
+ */
+
+int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+			      unsigned int len)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head bh;
+	unsigned int shift;
+	u64 lblock, lblock_stop, size;
+	u64 end_of_file;
+
+	if (!len)
+		return 0;
+
+	if (gfs2_is_stuffed(ip)) {
+		if (offset + len >
+		    sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode))
+			return 1;
+		return 0;
+	}
+
+	shift = sdp->sd_sb.sb_bsize_shift;
+	BUG_ON(gfs2_is_dir(ip));
+	end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift;
+	lblock = offset >> shift;
+	lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
+	if (lblock_stop > end_of_file)
+		return 1;
+
+	size = (lblock_stop - lblock) << shift;
+	do {
+		bh.b_state = 0;
+		bh.b_size = size;
+		gfs2_block_map(&ip->i_inode, lblock, &bh, 0);
+		if (!buffer_mapped(&bh))
+			return 1;
+		size -= bh.b_size;
+		lblock += (bh.b_size >> ip->i_inode.i_blkbits);
+	} while(size > 0);
+
+	return 0;
+}
+
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
new file mode 100644
index 00000000..42fea03e
--- /dev/null
+++ b/fs/gfs2/bmap.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __BMAP_DOT_H__
+#define __BMAP_DOT_H__
+
+#include "inode.h"
+
+struct inode;
+struct gfs2_inode;
+struct page;
+
+
+/**
+ * gfs2_write_calc_reserv - calculate number of blocks needed to write to a file
+ * @ip: the file
+ * @len: the number of bytes to be written to the file
+ * @data_blocks: returns the number of data blocks required
+ * @ind_blocks: returns the number of indirect blocks required
+ *
+ */
+
+static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
+					  unsigned int len,
+					  unsigned int *data_blocks,
+					  unsigned int *ind_blocks)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int tmp;
+
+	BUG_ON(gfs2_is_dir(ip));
+	*data_blocks = (len >> sdp->sd_sb.sb_bsize_shift) + 3;
+	*ind_blocks = 3 * (sdp->sd_max_height - 1);
+
+	for (tmp = *data_blocks; tmp > sdp->sd_diptrs;) {
+		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+		*ind_blocks += tmp;
+	}
+}
+
+extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_block_map(struct inode *inode, sector_t lblock,
+			  struct buffer_head *bh, int create);
+extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
+			   u64 *dblock, unsigned *extlen);
+extern int gfs2_setattr_size(struct inode *inode, u64 size);
+extern void gfs2_trim_blocks(struct inode *inode);
+extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
+extern int gfs2_file_dealloc(struct gfs2_inode *ip);
+extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+				     unsigned int len);
+
+#endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
new file mode 100644
index 00000000..0da8da2c
--- /dev/null
+++ b/fs/gfs2/dentry.c
@@ -0,0 +1,141 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/namei.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "super.h"
+#include "util.h"
+#include "inode.h"
+
+/**
+ * gfs2_drevalidate - Check directory lookup consistency
+ * @dentry: the mapping to check
+ * @nd:
+ *
+ * Check to make sure the lookup necessary to arrive at this inode from its
+ * parent is still good.
+ *
+ * Returns: 1 if the dentry is ok, 0 if it isn't
+ */
+
+static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *parent;
+	struct gfs2_sbd *sdp;
+	struct gfs2_inode *dip;
+	struct inode *inode;
+	struct gfs2_holder d_gh;
+	struct gfs2_inode *ip = NULL;
+	int error;
+	int had_lock = 0;
+
+	if (nd && nd->flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	parent = dget_parent(dentry);
+	sdp = GFS2_SB(parent->d_inode);
+	dip = GFS2_I(parent->d_inode);
+	inode = dentry->d_inode;
+
+	if (inode) {
+		if (is_bad_inode(inode))
+			goto invalid;
+		ip = GFS2_I(inode);
+	}
+
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		goto valid;
+
+	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
+	if (!had_lock) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+		if (error)
+			goto fail;
+	} 
+
+	error = gfs2_dir_check(parent->d_inode, &dentry->d_name, ip);
+	switch (error) {
+	case 0:
+		if (!inode)
+			goto invalid_gunlock;
+		break;
+	case -ENOENT:
+		if (!inode)
+			goto valid_gunlock;
+		goto invalid_gunlock;
+	default:
+		goto fail_gunlock;
+	}
+
+valid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+valid:
+	dput(parent);
+	return 1;
+
+invalid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+invalid:
+	if (inode && S_ISDIR(inode->i_mode)) {
+		if (have_submounts(dentry))
+			goto valid;
+		shrink_dcache_parent(dentry);
+	}
+	d_drop(dentry);
+	dput(parent);
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+fail:
+	dput(parent);
+	return 0;
+}
+
+static int gfs2_dhash(const struct dentry *dentry, const struct inode *inode,
+		struct qstr *str)
+{
+	str->hash = gfs2_disk_hash(str->name, str->len);
+	return 0;
+}
+
+static int gfs2_dentry_delete(const struct dentry *dentry)
+{
+	struct gfs2_inode *ginode;
+
+	if (!dentry->d_inode)
+		return 0;
+
+	ginode = GFS2_I(dentry->d_inode);
+	if (!ginode->i_iopen_gh.gh_gl)
+		return 0;
+
+	if (test_bit(GLF_DEMOTE, &ginode->i_iopen_gh.gh_gl->gl_flags))
+		return 1;
+
+	return 0;
+}
+
+const struct dentry_operations gfs2_dops = {
+	.d_revalidate = gfs2_drevalidate,
+	.d_hash = gfs2_dhash,
+	.d_delete = gfs2_dentry_delete,
+};
+
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
new file mode 100644
index 00000000..091ee477
--- /dev/null
+++ b/fs/gfs2/dir.c
@@ -0,0 +1,2006 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+/*
+ * Implements Extendible Hashing as described in:
+ *   "Extendible Hashing" by Fagin, et al in
+ *     __ACM Trans. on Database Systems__, Sept 1979.
+ *
+ *
+ * Here's the layout of dirents which is essentially the same as that of ext2
+ * within a single block. The field de_name_len is the number of bytes
+ * actually required for the name (no null terminator). The field de_rec_len
+ * is the number of bytes allocated to the dirent. The offset of the next
+ * dirent in the block is (dirent + dirent->de_rec_len). When a dirent is
+ * deleted, the preceding dirent inherits its allocated space, ie
+ * prev->de_rec_len += deleted->de_rec_len. Since the next dirent is obtained
+ * by adding de_rec_len to the current dirent, this essentially causes the
+ * deleted dirent to get jumped over when iterating through all the dirents.
+ *
+ * When deleting the first dirent in a block, there is no previous dirent so
+ * the field de_ino is set to zero to designate it as deleted. When allocating
+ * a dirent, gfs2_dirent_alloc iterates through the dirents in a block. If the
+ * first dirent has (de_ino == 0) and de_rec_len is large enough, this first
+ * dirent is allocated. Otherwise it must go through all the 'used' dirents
+ * searching for one in which the amount of total space minus the amount of
+ * used space will provide enough space for the new dirent.
+ *
+ * There are two types of blocks in which dirents reside. In a stuffed dinode,
+ * the dirents begin at offset sizeof(struct gfs2_dinode) from the beginning of
+ * the block.  In leaves, they begin at offset sizeof(struct gfs2_leaf) from the
+ * beginning of the leaf block. The dirents reside in leaves when
+ *
+ * dip->i_diskflags & GFS2_DIF_EXHASH is true
+ *
+ * Otherwise, the dirents are "linear", within a single stuffed dinode block.
+ *
+ * When the dirents are in leaves, the actual contents of the directory file are
+ * used as an array of 64-bit block pointers pointing to the leaf blocks. The
+ * dirents are NOT in the directory file itself. There can be more than one
+ * block pointer in the array that points to the same leaf. In fact, when a
+ * directory is first converted from linear to exhash, all of the pointers
+ * point to the same leaf.
+ *
+ * When a leaf is completely full, the size of the hash table can be
+ * doubled unless it is already at the maximum size which is hard coded into
+ * GFS2_DIR_MAX_DEPTH. After that, leaves are chained together in a linked list,
+ * but never before the maximum hash table size has been reached.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/buffer_head.h>
+#include <linux/sort.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/vmalloc.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "bmap.h"
+#include "util.h"
+
+#define IS_LEAF     1 /* Hashed (leaf) directory */
+#define IS_DINODE   2 /* Linear (stuffed dinode block) directory */
+
+#define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
+#define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1))
+
+struct qstr gfs2_qdot __read_mostly;
+struct qstr gfs2_qdotdot __read_mostly;
+
+typedef int (*gfs2_dscan_t)(const struct gfs2_dirent *dent,
+			    const struct qstr *name, void *opaque);
+
+int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+			    struct buffer_head **bhp)
+{
+	struct buffer_head *bh;
+
+	bh = gfs2_meta_new(ip->i_gl, block);
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_metatype_set(bh, GFS2_METATYPE_JD, GFS2_FORMAT_JD);
+	gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
+	*bhp = bh;
+	return 0;
+}
+
+static int gfs2_dir_get_existing_buffer(struct gfs2_inode *ip, u64 block,
+					struct buffer_head **bhp)
+{
+	struct buffer_head *bh;
+	int error;
+
+	error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, &bh);
+	if (error)
+		return error;
+	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_JD)) {
+		brelse(bh);
+		return -EIO;
+	}
+	*bhp = bh;
+	return 0;
+}
+
+static int gfs2_dir_write_stuffed(struct gfs2_inode *ip, const char *buf,
+				  unsigned int offset, unsigned int size)
+{
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size);
+	if (ip->i_inode.i_size < offset + size)
+		i_size_write(&ip->i_inode, offset + size);
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_dinode_out(ip, dibh->b_data);
+
+	brelse(dibh);
+
+	return size;
+}
+
+
+
+/**
+ * gfs2_dir_write_data - Write directory information to the inode
+ * @ip: The GFS2 inode
+ * @buf: The buffer containing information to be written
+ * @offset: The file offset to start writing at
+ * @size: The amount of data to write
+ *
+ * Returns: The number of bytes correctly written or error code
+ */
+static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf,
+			       u64 offset, unsigned int size)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *dibh;
+	u64 lblock, dblock;
+	u32 extlen = 0;
+	unsigned int o;
+	int copied = 0;
+	int error = 0;
+	int new = 0;
+
+	if (!size)
+		return 0;
+
+	if (gfs2_is_stuffed(ip) &&
+	    offset + size <= sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode))
+		return gfs2_dir_write_stuffed(ip, buf, (unsigned int)offset,
+					      size);
+
+	if (gfs2_assert_warn(sdp, gfs2_is_jdata(ip)))
+		return -EINVAL;
+
+	if (gfs2_is_stuffed(ip)) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (error)
+			return error;
+	}
+
+	lblock = offset;
+	o = do_div(lblock, sdp->sd_jbsize) + sizeof(struct gfs2_meta_header);
+
+	while (copied < size) {
+		unsigned int amount;
+		struct buffer_head *bh;
+
+		amount = size - copied;
+		if (amount > sdp->sd_sb.sb_bsize - o)
+			amount = sdp->sd_sb.sb_bsize - o;
+
+		if (!extlen) {
+			new = 1;
+			error = gfs2_extent_map(&ip->i_inode, lblock, &new,
+						&dblock, &extlen);
+			if (error)
+				goto fail;
+			error = -EIO;
+			if (gfs2_assert_withdraw(sdp, dblock))
+				goto fail;
+		}
+
+		if (amount == sdp->sd_jbsize || new)
+			error = gfs2_dir_get_new_buffer(ip, dblock, &bh);
+		else
+			error = gfs2_dir_get_existing_buffer(ip, dblock, &bh);
+
+		if (error)
+			goto fail;
+
+		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		memcpy(bh->b_data + o, buf, amount);
+		brelse(bh);
+
+		buf += amount;
+		copied += amount;
+		lblock++;
+		dblock++;
+		extlen--;
+
+		o = sizeof(struct gfs2_meta_header);
+	}
+
+out:
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	if (ip->i_inode.i_size < offset + copied)
+		i_size_write(&ip->i_inode, offset + copied);
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+
+	return copied;
+fail:
+	if (copied)
+		goto out;
+	return error;
+}
+
+static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, char *buf,
+				 u64 offset, unsigned int size)
+{
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		offset += sizeof(struct gfs2_dinode);
+		memcpy(buf, dibh->b_data + offset, size);
+		brelse(dibh);
+	}
+
+	return (error) ? error : size;
+}
+
+
+/**
+ * gfs2_dir_read_data - Read a data from a directory inode
+ * @ip: The GFS2 Inode
+ * @buf: The buffer to place result into
+ * @offset: File offset to begin jdata_readng from
+ * @size: Amount of data to transfer
+ *
+ * Returns: The amount of data actually copied or the error
+ */
+static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
+			      unsigned int size, unsigned ra)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	u64 lblock, dblock;
+	u32 extlen = 0;
+	unsigned int o;
+	int copied = 0;
+	int error = 0;
+	u64 disksize = i_size_read(&ip->i_inode);
+
+	if (offset >= disksize)
+		return 0;
+
+	if (offset + size > disksize)
+		size = disksize - offset;
+
+	if (!size)
+		return 0;
+
+	if (gfs2_is_stuffed(ip))
+		return gfs2_dir_read_stuffed(ip, buf, offset, size);
+
+	if (gfs2_assert_warn(sdp, gfs2_is_jdata(ip)))
+		return -EINVAL;
+
+	lblock = offset;
+	o = do_div(lblock, sdp->sd_jbsize) + sizeof(struct gfs2_meta_header);
+
+	while (copied < size) {
+		unsigned int amount;
+		struct buffer_head *bh;
+		int new;
+
+		amount = size - copied;
+		if (amount > sdp->sd_sb.sb_bsize - o)
+			amount = sdp->sd_sb.sb_bsize - o;
+
+		if (!extlen) {
+			new = 0;
+			error = gfs2_extent_map(&ip->i_inode, lblock, &new,
+						&dblock, &extlen);
+			if (error || !dblock)
+				goto fail;
+			BUG_ON(extlen < 1);
+			if (!ra)
+				extlen = 1;
+			bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
+		} else {
+			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh);
+			if (error)
+				goto fail;
+		}
+		error = gfs2_metatype_check(sdp, bh, GFS2_METATYPE_JD);
+		if (error) {
+			brelse(bh);
+			goto fail;
+		}
+		dblock++;
+		extlen--;
+		memcpy(buf, bh->b_data + o, amount);
+		brelse(bh);
+		buf += amount;
+		copied += amount;
+		lblock++;
+		o = sizeof(struct gfs2_meta_header);
+	}
+
+	return copied;
+fail:
+	return (copied) ? copied : error;
+}
+
+static inline int gfs2_dirent_sentinel(const struct gfs2_dirent *dent)
+{
+	return dent->de_inum.no_addr == 0 || dent->de_inum.no_formal_ino == 0;
+}
+
+static inline int __gfs2_dirent_find(const struct gfs2_dirent *dent,
+				     const struct qstr *name, int ret)
+{
+	if (!gfs2_dirent_sentinel(dent) &&
+	    be32_to_cpu(dent->de_hash) == name->hash &&
+	    be16_to_cpu(dent->de_name_len) == name->len &&
+	    memcmp(dent+1, name->name, name->len) == 0)
+		return ret;
+	return 0;
+}
+
+static int gfs2_dirent_find(const struct gfs2_dirent *dent,
+			    const struct qstr *name,
+			    void *opaque)
+{
+	return __gfs2_dirent_find(dent, name, 1);
+}
+
+static int gfs2_dirent_prev(const struct gfs2_dirent *dent,
+			    const struct qstr *name,
+			    void *opaque)
+{
+	return __gfs2_dirent_find(dent, name, 2);
+}
+
+/*
+ * name->name holds ptr to start of block.
+ * name->len holds size of block.
+ */
+static int gfs2_dirent_last(const struct gfs2_dirent *dent,
+			    const struct qstr *name,
+			    void *opaque)
+{
+	const char *start = name->name;
+	const char *end = (const char *)dent + be16_to_cpu(dent->de_rec_len);
+	if (name->len == (end - start))
+		return 1;
+	return 0;
+}
+
+static int gfs2_dirent_find_space(const struct gfs2_dirent *dent,
+				  const struct qstr *name,
+				  void *opaque)
+{
+	unsigned required = GFS2_DIRENT_SIZE(name->len);
+	unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
+	unsigned totlen = be16_to_cpu(dent->de_rec_len);
+
+	if (gfs2_dirent_sentinel(dent))
+		actual = 0;
+	if (totlen - actual >= required)
+		return 1;
+	return 0;
+}
+
+struct dirent_gather {
+	const struct gfs2_dirent **pdent;
+	unsigned offset;
+};
+
+static int gfs2_dirent_gather(const struct gfs2_dirent *dent,
+			      const struct qstr *name,
+			      void *opaque)
+{
+	struct dirent_gather *g = opaque;
+	if (!gfs2_dirent_sentinel(dent)) {
+		g->pdent[g->offset++] = dent;
+	}
+	return 0;
+}
+
+/*
+ * Other possible things to check:
+ * - Inode located within filesystem size (and on valid block)
+ * - Valid directory entry type
+ * Not sure how heavy-weight we want to make this... could also check
+ * hash is correct for example, but that would take a lot of extra time.
+ * For now the most important thing is to check that the various sizes
+ * are correct.
+ */
+static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset,
+			     unsigned int size, unsigned int len, int first)
+{
+	const char *msg = "gfs2_dirent too small";
+	if (unlikely(size < sizeof(struct gfs2_dirent)))
+		goto error;
+	msg = "gfs2_dirent misaligned";
+	if (unlikely(offset & 0x7))
+		goto error;
+	msg = "gfs2_dirent points beyond end of block";
+	if (unlikely(offset + size > len))
+		goto error;
+	msg = "zero inode number";
+	if (unlikely(!first && gfs2_dirent_sentinel(dent)))
+		goto error;
+	msg = "name length is greater than space in dirent";
+	if (!gfs2_dirent_sentinel(dent) &&
+	    unlikely(sizeof(struct gfs2_dirent)+be16_to_cpu(dent->de_name_len) >
+		     size))
+		goto error;
+	return 0;
+error:
+	printk(KERN_WARNING "gfs2_check_dirent: %s (%s)\n", msg,
+	       first ? "first in block" : "not first in block");
+	return -EIO;
+}
+
+static int gfs2_dirent_offset(const void *buf)
+{
+	const struct gfs2_meta_header *h = buf;
+	int offset;
+
+	BUG_ON(buf == NULL);
+
+	switch(be32_to_cpu(h->mh_type)) {
+	case GFS2_METATYPE_LF:
+		offset = sizeof(struct gfs2_leaf);
+		break;
+	case GFS2_METATYPE_DI:
+		offset = sizeof(struct gfs2_dinode);
+		break;
+	default:
+		goto wrong_type;
+	}
+	return offset;
+wrong_type:
+	printk(KERN_WARNING "gfs2_scan_dirent: wrong block type %u\n",
+	       be32_to_cpu(h->mh_type));
+	return -1;
+}
+
+static struct gfs2_dirent *gfs2_dirent_scan(struct inode *inode, void *buf,
+					    unsigned int len, gfs2_dscan_t scan,
+					    const struct qstr *name,
+					    void *opaque)
+{
+	struct gfs2_dirent *dent, *prev;
+	unsigned offset;
+	unsigned size;
+	int ret = 0;
+
+	ret = gfs2_dirent_offset(buf);
+	if (ret < 0)
+		goto consist_inode;
+
+	offset = ret;
+	prev = NULL;
+	dent = buf + offset;
+	size = be16_to_cpu(dent->de_rec_len);
+	if (gfs2_check_dirent(dent, offset, size, len, 1))
+		goto consist_inode;
+	do {
+		ret = scan(dent, name, opaque);
+		if (ret)
+			break;
+		offset += size;
+		if (offset == len)
+			break;
+		prev = dent;
+		dent = buf + offset;
+		size = be16_to_cpu(dent->de_rec_len);
+		if (gfs2_check_dirent(dent, offset, size, len, 0))
+			goto consist_inode;
+	} while(1);
+
+	switch(ret) {
+	case 0:
+		return NULL;
+	case 1:
+		return dent;
+	case 2:
+		return prev ? prev : dent;
+	default:
+		BUG_ON(ret > 0);
+		return ERR_PTR(ret);
+	}
+
+consist_inode:
+	gfs2_consist_inode(GFS2_I(inode));
+	return ERR_PTR(-EIO);
+}
+
+static int dirent_check_reclen(struct gfs2_inode *dip,
+			       const struct gfs2_dirent *d, const void *end_p)
+{
+	const void *ptr = d;
+	u16 rec_len = be16_to_cpu(d->de_rec_len);
+
+	if (unlikely(rec_len < sizeof(struct gfs2_dirent)))
+		goto broken;
+	ptr += rec_len;
+	if (ptr < end_p)
+		return rec_len;
+	if (ptr == end_p)
+		return -ENOENT;
+broken:
+	gfs2_consist_inode(dip);
+	return -EIO;
+}
+
+/**
+ * dirent_next - Next dirent
+ * @dip: the directory
+ * @bh: The buffer
+ * @dent: Pointer to list of dirents
+ *
+ * Returns: 0 on success, error code otherwise
+ */
+
+static int dirent_next(struct gfs2_inode *dip, struct buffer_head *bh,
+		       struct gfs2_dirent **dent)
+{
+	struct gfs2_dirent *cur = *dent, *tmp;
+	char *bh_end = bh->b_data + bh->b_size;
+	int ret;
+
+	ret = dirent_check_reclen(dip, cur, bh_end);
+	if (ret < 0)
+		return ret;
+
+	tmp = (void *)cur + ret;
+	ret = dirent_check_reclen(dip, tmp, bh_end);
+	if (ret == -EIO)
+		return ret;
+
+        /* Only the first dent could ever have de_inum.no_addr == 0 */
+	if (gfs2_dirent_sentinel(tmp)) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+
+	*dent = tmp;
+	return 0;
+}
+
+/**
+ * dirent_del - Delete a dirent
+ * @dip: The GFS2 inode
+ * @bh: The buffer
+ * @prev: The previous dirent
+ * @cur: The current dirent
+ *
+ */
+
+static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh,
+		       struct gfs2_dirent *prev, struct gfs2_dirent *cur)
+{
+	u16 cur_rec_len, prev_rec_len;
+
+	if (gfs2_dirent_sentinel(cur)) {
+		gfs2_consist_inode(dip);
+		return;
+	}
+
+	gfs2_trans_add_bh(dip->i_gl, bh, 1);
+
+	/* If there is no prev entry, this is the first entry in the block.
+	   The de_rec_len is already as big as it needs to be.  Just zero
+	   out the inode number and return.  */
+
+	if (!prev) {
+		cur->de_inum.no_addr = 0;
+		cur->de_inum.no_formal_ino = 0;
+		return;
+	}
+
+	/*  Combine this dentry with the previous one.  */
+
+	prev_rec_len = be16_to_cpu(prev->de_rec_len);
+	cur_rec_len = be16_to_cpu(cur->de_rec_len);
+
+	if ((char *)prev + prev_rec_len != (char *)cur)
+		gfs2_consist_inode(dip);
+	if ((char *)cur + cur_rec_len > bh->b_data + bh->b_size)
+		gfs2_consist_inode(dip);
+
+	prev_rec_len += cur_rec_len;
+	prev->de_rec_len = cpu_to_be16(prev_rec_len);
+}
+
+/*
+ * Takes a dent from which to grab space as an argument. Returns the
+ * newly created dent.
+ */
+static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode,
+					    struct gfs2_dirent *dent,
+					    const struct qstr *name,
+					    struct buffer_head *bh)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_dirent *ndent;
+	unsigned offset = 0, totlen;
+
+	if (!gfs2_dirent_sentinel(dent))
+		offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
+	totlen = be16_to_cpu(dent->de_rec_len);
+	BUG_ON(offset + name->len > totlen);
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	ndent = (struct gfs2_dirent *)((char *)dent + offset);
+	dent->de_rec_len = cpu_to_be16(offset);
+	gfs2_qstr2dirent(name, totlen - offset, ndent);
+	return ndent;
+}
+
+static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode,
+					     struct buffer_head *bh,
+					     const struct qstr *name)
+{
+	struct gfs2_dirent *dent;
+	dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
+				gfs2_dirent_find_space, name, NULL);
+	if (!dent || IS_ERR(dent))
+		return dent;
+	return gfs2_init_dirent(inode, dent, name, bh);
+}
+
+static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
+		    struct buffer_head **bhp)
+{
+	int error;
+
+	error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp);
+	if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) {
+		/* printk(KERN_INFO "block num=%llu\n", leaf_no); */
+		error = -EIO;
+	}
+
+	return error;
+}
+
+/**
+ * get_leaf_nr - Get a leaf number associated with the index
+ * @dip: The GFS2 inode
+ * @index:
+ * @leaf_out:
+ *
+ * Returns: 0 on success, error code otherwise
+ */
+
+static int get_leaf_nr(struct gfs2_inode *dip, u32 index,
+		       u64 *leaf_out)
+{
+	__be64 leaf_no;
+	int error;
+
+	error = gfs2_dir_read_data(dip, (char *)&leaf_no,
+				    index * sizeof(__be64),
+				    sizeof(__be64), 0);
+	if (error != sizeof(u64))
+		return (error < 0) ? error : -EIO;
+
+	*leaf_out = be64_to_cpu(leaf_no);
+
+	return 0;
+}
+
+static int get_first_leaf(struct gfs2_inode *dip, u32 index,
+			  struct buffer_head **bh_out)
+{
+	u64 leaf_no;
+	int error;
+
+	error = get_leaf_nr(dip, index, &leaf_no);
+	if (!error)
+		error = get_leaf(dip, leaf_no, bh_out);
+
+	return error;
+}
+
+static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode,
+					      const struct qstr *name,
+					      gfs2_dscan_t scan,
+					      struct buffer_head **pbh)
+{
+	struct buffer_head *bh;
+	struct gfs2_dirent *dent;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int error;
+
+	if (ip->i_diskflags & GFS2_DIF_EXHASH) {
+		struct gfs2_leaf *leaf;
+		unsigned hsize = 1 << ip->i_depth;
+		unsigned index;
+		u64 ln;
+		if (hsize * sizeof(u64) != i_size_read(inode)) {
+			gfs2_consist_inode(ip);
+			return ERR_PTR(-EIO);
+		}
+
+		index = name->hash >> (32 - ip->i_depth);
+		error = get_first_leaf(ip, index, &bh);
+		if (error)
+			return ERR_PTR(error);
+		do {
+			dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
+						scan, name, NULL);
+			if (dent)
+				goto got_dent;
+			leaf = (struct gfs2_leaf *)bh->b_data;
+			ln = be64_to_cpu(leaf->lf_next);
+			brelse(bh);
+			if (!ln)
+				break;
+
+			error = get_leaf(ip, ln, &bh);
+		} while(!error);
+
+		return error ? ERR_PTR(error) : NULL;
+	}
+
+
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		return ERR_PTR(error);
+	dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, scan, name, NULL);
+got_dent:
+	if (unlikely(dent == NULL || IS_ERR(dent))) {
+		brelse(bh);
+		bh = NULL;
+	}
+	*pbh = bh;
+	return dent;
+}
+
+static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, u16 depth)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned int n = 1;
+	u64 bn;
+	int error;
+	struct buffer_head *bh;
+	struct gfs2_leaf *leaf;
+	struct gfs2_dirent *dent;
+	struct qstr name = { .name = "", .len = 0, .hash = 0 };
+
+	error = gfs2_alloc_block(ip, &bn, &n);
+	if (error)
+		return NULL;
+	bh = gfs2_meta_new(ip->i_gl, bn);
+	if (!bh)
+		return NULL;
+
+	gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1);
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF);
+	leaf = (struct gfs2_leaf *)bh->b_data;
+	leaf->lf_depth = cpu_to_be16(depth);
+	leaf->lf_entries = 0;
+	leaf->lf_dirent_format = cpu_to_be32(GFS2_FORMAT_DE);
+	leaf->lf_next = 0;
+	memset(leaf->lf_reserved, 0, sizeof(leaf->lf_reserved));
+	dent = (struct gfs2_dirent *)(leaf+1);
+	gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent);
+	*pbh = bh;
+	return leaf;
+}
+
+/**
+ * dir_make_exhash - Convert a stuffed directory into an ExHash directory
+ * @dip: The GFS2 inode
+ *
+ * Returns: 0 on success, error code otherwise
+ */
+
+static int dir_make_exhash(struct inode *inode)
+{
+	struct gfs2_inode *dip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_dirent *dent;
+	struct qstr args;
+	struct buffer_head *bh, *dibh;
+	struct gfs2_leaf *leaf;
+	int y;
+	u32 x;
+	__be64 *lp;
+	u64 bn;
+	int error;
+
+	error = gfs2_meta_inode_buffer(dip, &dibh);
+	if (error)
+		return error;
+
+	/*  Turn over a new leaf  */
+
+	leaf = new_leaf(inode, &bh, 0);
+	if (!leaf)
+		return -ENOSPC;
+	bn = bh->b_blocknr;
+
+	gfs2_assert(sdp, dip->i_entries < (1 << 16));
+	leaf->lf_entries = cpu_to_be16(dip->i_entries);
+
+	/*  Copy dirents  */
+
+	gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_leaf), dibh,
+			     sizeof(struct gfs2_dinode));
+
+	/*  Find last entry  */
+
+	x = 0;
+	args.len = bh->b_size - sizeof(struct gfs2_dinode) +
+		   sizeof(struct gfs2_leaf);
+	args.name = bh->b_data;
+	dent = gfs2_dirent_scan(&dip->i_inode, bh->b_data, bh->b_size,
+				gfs2_dirent_last, &args, NULL);
+	if (!dent) {
+		brelse(bh);
+		brelse(dibh);
+		return -EIO;
+	}
+	if (IS_ERR(dent)) {
+		brelse(bh);
+		brelse(dibh);
+		return PTR_ERR(dent);
+	}
+
+	/*  Adjust the last dirent's record length
+	   (Remember that dent still points to the last entry.)  */
+
+	dent->de_rec_len = cpu_to_be16(be16_to_cpu(dent->de_rec_len) +
+		sizeof(struct gfs2_dinode) -
+		sizeof(struct gfs2_leaf));
+
+	brelse(bh);
+
+	/*  We're done with the new leaf block, now setup the new
+	    hash table.  */
+
+	gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
+
+	lp = (__be64 *)(dibh->b_data + sizeof(struct gfs2_dinode));
+
+	for (x = sdp->sd_hash_ptrs; x--; lp++)
+		*lp = cpu_to_be64(bn);
+
+	i_size_write(inode, sdp->sd_sb.sb_bsize / 2);
+	gfs2_add_inode_blocks(&dip->i_inode, 1);
+	dip->i_diskflags |= GFS2_DIF_EXHASH;
+
+	for (x = sdp->sd_hash_ptrs, y = -1; x; x >>= 1, y++) ;
+	dip->i_depth = y;
+
+	gfs2_dinode_out(dip, dibh->b_data);
+
+	brelse(dibh);
+
+	return 0;
+}
+
+/**
+ * dir_split_leaf - Split a leaf block into two
+ * @dip: The GFS2 inode
+ * @index:
+ * @leaf_no:
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int dir_split_leaf(struct inode *inode, const struct qstr *name)
+{
+	struct gfs2_inode *dip = GFS2_I(inode);
+	struct buffer_head *nbh, *obh, *dibh;
+	struct gfs2_leaf *nleaf, *oleaf;
+	struct gfs2_dirent *dent = NULL, *prev = NULL, *next = NULL, *new;
+	u32 start, len, half_len, divider;
+	u64 bn, leaf_no;
+	__be64 *lp;
+	u32 index;
+	int x, moved = 0;
+	int error;
+
+	index = name->hash >> (32 - dip->i_depth);
+	error = get_leaf_nr(dip, index, &leaf_no);
+	if (error)
+		return error;
+
+	/*  Get the old leaf block  */
+	error = get_leaf(dip, leaf_no, &obh);
+	if (error)
+		return error;
+
+	oleaf = (struct gfs2_leaf *)obh->b_data;
+	if (dip->i_depth == be16_to_cpu(oleaf->lf_depth)) {
+		brelse(obh);
+		return 1; /* can't split */
+	}
+
+	gfs2_trans_add_bh(dip->i_gl, obh, 1);
+
+	nleaf = new_leaf(inode, &nbh, be16_to_cpu(oleaf->lf_depth) + 1);
+	if (!nleaf) {
+		brelse(obh);
+		return -ENOSPC;
+	}
+	bn = nbh->b_blocknr;
+
+	/*  Compute the start and len of leaf pointers in the hash table.  */
+	len = 1 << (dip->i_depth - be16_to_cpu(oleaf->lf_depth));
+	half_len = len >> 1;
+	if (!half_len) {
+		printk(KERN_WARNING "i_depth %u lf_depth %u index %u\n", dip->i_depth, be16_to_cpu(oleaf->lf_depth), index);
+		gfs2_consist_inode(dip);
+		error = -EIO;
+		goto fail_brelse;
+	}
+
+	start = (index & ~(len - 1));
+
+	/* Change the pointers.
+	   Don't bother distinguishing stuffed from non-stuffed.
+	   This code is complicated enough already. */
+	lp = kmalloc(half_len * sizeof(__be64), GFP_NOFS);
+	if (!lp) {
+		error = -ENOMEM;
+		goto fail_brelse;
+	}
+
+	/*  Change the pointers  */
+	for (x = 0; x < half_len; x++)
+		lp[x] = cpu_to_be64(bn);
+
+	error = gfs2_dir_write_data(dip, (char *)lp, start * sizeof(u64),
+				    half_len * sizeof(u64));
+	if (error != half_len * sizeof(u64)) {
+		if (error >= 0)
+			error = -EIO;
+		goto fail_lpfree;
+	}
+
+	kfree(lp);
+
+	/*  Compute the divider  */
+	divider = (start + half_len) << (32 - dip->i_depth);
+
+	/*  Copy the entries  */
+	dent = (struct gfs2_dirent *)(obh->b_data + sizeof(struct gfs2_leaf));
+
+	do {
+		next = dent;
+		if (dirent_next(dip, obh, &next))
+			next = NULL;
+
+		if (!gfs2_dirent_sentinel(dent) &&
+		    be32_to_cpu(dent->de_hash) < divider) {
+			struct qstr str;
+			str.name = (char*)(dent+1);
+			str.len = be16_to_cpu(dent->de_name_len);
+			str.hash = be32_to_cpu(dent->de_hash);
+			new = gfs2_dirent_alloc(inode, nbh, &str);
+			if (IS_ERR(new)) {
+				error = PTR_ERR(new);
+				break;
+			}
+
+			new->de_inum = dent->de_inum; /* No endian worries */
+			new->de_type = dent->de_type; /* No endian worries */
+			be16_add_cpu(&nleaf->lf_entries, 1);
+
+			dirent_del(dip, obh, prev, dent);
+
+			if (!oleaf->lf_entries)
+				gfs2_consist_inode(dip);
+			be16_add_cpu(&oleaf->lf_entries, -1);
+
+			if (!prev)
+				prev = dent;
+
+			moved = 1;
+		} else {
+			prev = dent;
+		}
+		dent = next;
+	} while (dent);
+
+	oleaf->lf_depth = nleaf->lf_depth;
+
+	error = gfs2_meta_inode_buffer(dip, &dibh);
+	if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) {
+		gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+		gfs2_add_inode_blocks(&dip->i_inode, 1);
+		gfs2_dinode_out(dip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	brelse(obh);
+	brelse(nbh);
+
+	return error;
+
+fail_lpfree:
+	kfree(lp);
+
+fail_brelse:
+	brelse(obh);
+	brelse(nbh);
+	return error;
+}
+
+/**
+ * dir_double_exhash - Double size of ExHash table
+ * @dip: The GFS2 dinode
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int dir_double_exhash(struct gfs2_inode *dip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct buffer_head *dibh;
+	u32 hsize;
+	u64 *buf;
+	u64 *from, *to;
+	u64 block;
+	u64 disksize = i_size_read(&dip->i_inode);
+	int x;
+	int error = 0;
+
+	hsize = 1 << dip->i_depth;
+	if (hsize * sizeof(u64) != disksize) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+
+	/*  Allocate both the "from" and "to" buffers in one big chunk  */
+
+	buf = kcalloc(3, sdp->sd_hash_bsize, GFP_NOFS);
+	if (!buf)
+		return -ENOMEM;
+
+	for (block = disksize >> sdp->sd_hash_bsize_shift; block--;) {
+		error = gfs2_dir_read_data(dip, (char *)buf,
+					    block * sdp->sd_hash_bsize,
+					    sdp->sd_hash_bsize, 1);
+		if (error != sdp->sd_hash_bsize) {
+			if (error >= 0)
+				error = -EIO;
+			goto fail;
+		}
+
+		from = buf;
+		to = (u64 *)((char *)buf + sdp->sd_hash_bsize);
+
+		for (x = sdp->sd_hash_ptrs; x--; from++) {
+			*to++ = *from;	/*  No endianess worries  */
+			*to++ = *from;
+		}
+
+		error = gfs2_dir_write_data(dip,
+					     (char *)buf + sdp->sd_hash_bsize,
+					     block * sdp->sd_sb.sb_bsize,
+					     sdp->sd_sb.sb_bsize);
+		if (error != sdp->sd_sb.sb_bsize) {
+			if (error >= 0)
+				error = -EIO;
+			goto fail;
+		}
+	}
+
+	kfree(buf);
+
+	error = gfs2_meta_inode_buffer(dip, &dibh);
+	if (!gfs2_assert_withdraw(sdp, !error)) {
+		dip->i_depth++;
+		gfs2_dinode_out(dip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	return error;
+
+fail:
+	kfree(buf);
+	return error;
+}
+
+/**
+ * compare_dents - compare directory entries by hash value
+ * @a: first dent
+ * @b: second dent
+ *
+ * When comparing the hash entries of @a to @b:
+ *   gt: returns 1
+ *   lt: returns -1
+ *   eq: returns 0
+ */
+
+static int compare_dents(const void *a, const void *b)
+{
+	const struct gfs2_dirent *dent_a, *dent_b;
+	u32 hash_a, hash_b;
+	int ret = 0;
+
+	dent_a = *(const struct gfs2_dirent **)a;
+	hash_a = be32_to_cpu(dent_a->de_hash);
+
+	dent_b = *(const struct gfs2_dirent **)b;
+	hash_b = be32_to_cpu(dent_b->de_hash);
+
+	if (hash_a > hash_b)
+		ret = 1;
+	else if (hash_a < hash_b)
+		ret = -1;
+	else {
+		unsigned int len_a = be16_to_cpu(dent_a->de_name_len);
+		unsigned int len_b = be16_to_cpu(dent_b->de_name_len);
+
+		if (len_a > len_b)
+			ret = 1;
+		else if (len_a < len_b)
+			ret = -1;
+		else
+			ret = memcmp(dent_a + 1, dent_b + 1, len_a);
+	}
+
+	return ret;
+}
+
+/**
+ * do_filldir_main - read out directory entries
+ * @dip: The GFS2 inode
+ * @offset: The offset in the file to read from
+ * @opaque: opaque data to pass to filldir
+ * @filldir: The function to pass entries to
+ * @darr: an array of struct gfs2_dirent pointers to read
+ * @entries: the number of entries in darr
+ * @copied: pointer to int that's non-zero if a entry has been copied out
+ *
+ * Jump through some hoops to make sure that if there are hash collsions,
+ * they are read out at the beginning of a buffer.  We want to minimize
+ * the possibility that they will fall into different readdir buffers or
+ * that someone will want to seek to that location.
+ *
+ * Returns: errno, >0 on exception from filldir
+ */
+
+static int do_filldir_main(struct gfs2_inode *dip, u64 *offset,
+			   void *opaque, filldir_t filldir,
+			   const struct gfs2_dirent **darr, u32 entries,
+			   int *copied)
+{
+	const struct gfs2_dirent *dent, *dent_next;
+	u64 off, off_next;
+	unsigned int x, y;
+	int run = 0;
+	int error = 0;
+
+	sort(darr, entries, sizeof(struct gfs2_dirent *), compare_dents, NULL);
+
+	dent_next = darr[0];
+	off_next = be32_to_cpu(dent_next->de_hash);
+	off_next = gfs2_disk_hash2offset(off_next);
+
+	for (x = 0, y = 1; x < entries; x++, y++) {
+		dent = dent_next;
+		off = off_next;
+
+		if (y < entries) {
+			dent_next = darr[y];
+			off_next = be32_to_cpu(dent_next->de_hash);
+			off_next = gfs2_disk_hash2offset(off_next);
+
+			if (off < *offset)
+				continue;
+			*offset = off;
+
+			if (off_next == off) {
+				if (*copied && !run)
+					return 1;
+				run = 1;
+			} else
+				run = 0;
+		} else {
+			if (off < *offset)
+				continue;
+			*offset = off;
+		}
+
+		error = filldir(opaque, (const char *)(dent + 1),
+				be16_to_cpu(dent->de_name_len),
+				off, be64_to_cpu(dent->de_inum.no_addr),
+				be16_to_cpu(dent->de_type));
+		if (error)
+			return 1;
+
+		*copied = 1;
+	}
+
+	/* Increment the *offset by one, so the next time we come into the
+	   do_filldir fxn, we get the next entry instead of the last one in the
+	   current leaf */
+
+	(*offset)++;
+
+	return 0;
+}
+
+static void *gfs2_alloc_sort_buffer(unsigned size)
+{
+	void *ptr = NULL;
+
+	if (size < KMALLOC_MAX_SIZE)
+		ptr = kmalloc(size, GFP_NOFS | __GFP_NOWARN);
+	if (!ptr)
+		ptr = __vmalloc(size, GFP_NOFS, PAGE_KERNEL);
+	return ptr;
+}
+
+static void gfs2_free_sort_buffer(void *ptr)
+{
+	if (is_vmalloc_addr(ptr))
+		vfree(ptr);
+	else
+		kfree(ptr);
+}
+
+static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
+			      filldir_t filldir, int *copied, unsigned *depth,
+			      u64 leaf_no)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *bh;
+	struct gfs2_leaf *lf;
+	unsigned entries = 0, entries2 = 0;
+	unsigned leaves = 0;
+	const struct gfs2_dirent **darr, *dent;
+	struct dirent_gather g;
+	struct buffer_head **larr;
+	int leaf = 0;
+	int error, i;
+	u64 lfn = leaf_no;
+
+	do {
+		error = get_leaf(ip, lfn, &bh);
+		if (error)
+			goto out;
+		lf = (struct gfs2_leaf *)bh->b_data;
+		if (leaves == 0)
+			*depth = be16_to_cpu(lf->lf_depth);
+		entries += be16_to_cpu(lf->lf_entries);
+		leaves++;
+		lfn = be64_to_cpu(lf->lf_next);
+		brelse(bh);
+	} while(lfn);
+
+	if (!entries)
+		return 0;
+
+	error = -ENOMEM;
+	/*
+	 * The extra 99 entries are not normally used, but are a buffer
+	 * zone in case the number of entries in the leaf is corrupt.
+	 * 99 is the maximum number of entries that can fit in a single
+	 * leaf block.
+	 */
+	larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *));
+	if (!larr)
+		goto out;
+	darr = (const struct gfs2_dirent **)(larr + leaves);
+	g.pdent = darr;
+	g.offset = 0;
+	lfn = leaf_no;
+
+	do {
+		error = get_leaf(ip, lfn, &bh);
+		if (error)
+			goto out_free;
+		lf = (struct gfs2_leaf *)bh->b_data;
+		lfn = be64_to_cpu(lf->lf_next);
+		if (lf->lf_entries) {
+			entries2 += be16_to_cpu(lf->lf_entries);
+			dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
+						gfs2_dirent_gather, NULL, &g);
+			error = PTR_ERR(dent);
+			if (IS_ERR(dent))
+				goto out_free;
+			if (entries2 != g.offset) {
+				fs_warn(sdp, "Number of entries corrupt in dir "
+						"leaf %llu, entries2 (%u) != "
+						"g.offset (%u)\n",
+					(unsigned long long)bh->b_blocknr,
+					entries2, g.offset);
+					
+				error = -EIO;
+				goto out_free;
+			}
+			error = 0;
+			larr[leaf++] = bh;
+		} else {
+			brelse(bh);
+		}
+	} while(lfn);
+
+	BUG_ON(entries2 != entries);
+	error = do_filldir_main(ip, offset, opaque, filldir, darr,
+				entries, copied);
+out_free:
+	for(i = 0; i < leaf; i++)
+		brelse(larr[i]);
+	gfs2_free_sort_buffer(larr);
+out:
+	return error;
+}
+
+/**
+ * dir_e_read - Reads the entries from a directory into a filldir buffer
+ * @dip: dinode pointer
+ * @offset: the hash of the last entry read shifted to the right once
+ * @opaque: buffer for the filldir function to fill
+ * @filldir: points to the filldir function to use
+ *
+ * Returns: errno
+ */
+
+static int dir_e_read(struct inode *inode, u64 *offset, void *opaque,
+		      filldir_t filldir)
+{
+	struct gfs2_inode *dip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	u32 hsize, len = 0;
+	u32 ht_offset, lp_offset, ht_offset_cur = -1;
+	u32 hash, index;
+	__be64 *lp;
+	int copied = 0;
+	int error = 0;
+	unsigned depth = 0;
+
+	hsize = 1 << dip->i_depth;
+	if (hsize * sizeof(u64) != i_size_read(inode)) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+
+	hash = gfs2_dir_offset2hash(*offset);
+	index = hash >> (32 - dip->i_depth);
+
+	lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS);
+	if (!lp)
+		return -ENOMEM;
+
+	while (index < hsize) {
+		lp_offset = index & (sdp->sd_hash_ptrs - 1);
+		ht_offset = index - lp_offset;
+
+		if (ht_offset_cur != ht_offset) {
+			error = gfs2_dir_read_data(dip, (char *)lp,
+						ht_offset * sizeof(__be64),
+						sdp->sd_hash_bsize, 1);
+			if (error != sdp->sd_hash_bsize) {
+				if (error >= 0)
+					error = -EIO;
+				goto out;
+			}
+			ht_offset_cur = ht_offset;
+		}
+
+		error = gfs2_dir_read_leaf(inode, offset, opaque, filldir,
+					   &copied, &depth,
+					   be64_to_cpu(lp[lp_offset]));
+		if (error)
+			break;
+
+		len = 1 << (dip->i_depth - depth);
+		index = (index & ~(len - 1)) + len;
+	}
+
+out:
+	kfree(lp);
+	if (error > 0)
+		error = 0;
+	return error;
+}
+
+int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
+		  filldir_t filldir)
+{
+	struct gfs2_inode *dip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct dirent_gather g;
+	const struct gfs2_dirent **darr, *dent;
+	struct buffer_head *dibh;
+	int copied = 0;
+	int error;
+
+	if (!dip->i_entries)
+		return 0;
+
+	if (dip->i_diskflags & GFS2_DIF_EXHASH)
+		return dir_e_read(inode, offset, opaque, filldir);
+
+	if (!gfs2_is_stuffed(dip)) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+
+	error = gfs2_meta_inode_buffer(dip, &dibh);
+	if (error)
+		return error;
+
+	error = -ENOMEM;
+	/* 96 is max number of dirents which can be stuffed into an inode */
+	darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS);
+	if (darr) {
+		g.pdent = darr;
+		g.offset = 0;
+		dent = gfs2_dirent_scan(inode, dibh->b_data, dibh->b_size,
+					gfs2_dirent_gather, NULL, &g);
+		if (IS_ERR(dent)) {
+			error = PTR_ERR(dent);
+			goto out;
+		}
+		if (dip->i_entries != g.offset) {
+			fs_warn(sdp, "Number of entries corrupt in dir %llu, "
+				"ip->i_entries (%u) != g.offset (%u)\n",
+				(unsigned long long)dip->i_no_addr,
+				dip->i_entries,
+				g.offset);
+			error = -EIO;
+			goto out;
+		}
+		error = do_filldir_main(dip, offset, opaque, filldir, darr,
+					dip->i_entries, &copied);
+out:
+		kfree(darr);
+	}
+
+	if (error > 0)
+		error = 0;
+
+	brelse(dibh);
+
+	return error;
+}
+
+/**
+ * gfs2_dir_search - Search a directory
+ * @dip: The GFS2 inode
+ * @filename:
+ * @inode:
+ *
+ * This routine searches a directory for a file or another directory.
+ * Assumes a glock is held on dip.
+ *
+ * Returns: errno
+ */
+
+struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name)
+{
+	struct buffer_head *bh;
+	struct gfs2_dirent *dent;
+	struct inode *inode;
+
+	dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh);
+	if (dent) {
+		if (IS_ERR(dent))
+			return ERR_CAST(dent);
+		inode = gfs2_inode_lookup(dir->i_sb, 
+				be16_to_cpu(dent->de_type),
+				be64_to_cpu(dent->de_inum.no_addr),
+				be64_to_cpu(dent->de_inum.no_formal_ino), 0);
+		brelse(bh);
+		return inode;
+	}
+	return ERR_PTR(-ENOENT);
+}
+
+int gfs2_dir_check(struct inode *dir, const struct qstr *name,
+		   const struct gfs2_inode *ip)
+{
+	struct buffer_head *bh;
+	struct gfs2_dirent *dent;
+	int ret = -ENOENT;
+
+	dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh);
+	if (dent) {
+		if (IS_ERR(dent))
+			return PTR_ERR(dent);
+		if (ip) {
+			if (be64_to_cpu(dent->de_inum.no_addr) != ip->i_no_addr)
+				goto out;
+			if (be64_to_cpu(dent->de_inum.no_formal_ino) !=
+			    ip->i_no_formal_ino)
+				goto out;
+			if (unlikely(IF2DT(ip->i_inode.i_mode) !=
+			    be16_to_cpu(dent->de_type))) {
+				gfs2_consist_inode(GFS2_I(dir));
+				ret = -EIO;
+				goto out;
+			}
+		}
+		ret = 0;
+out:
+		brelse(bh);
+	}
+	return ret;
+}
+
+static int dir_new_leaf(struct inode *inode, const struct qstr *name)
+{
+	struct buffer_head *bh, *obh;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_leaf *leaf, *oleaf;
+	int error;
+	u32 index;
+	u64 bn;
+
+	index = name->hash >> (32 - ip->i_depth);
+	error = get_first_leaf(ip, index, &obh);
+	if (error)
+		return error;
+	do {
+		oleaf = (struct gfs2_leaf *)obh->b_data;
+		bn = be64_to_cpu(oleaf->lf_next);
+		if (!bn)
+			break;
+		brelse(obh);
+		error = get_leaf(ip, bn, &obh);
+		if (error)
+			return error;
+	} while(1);
+
+	gfs2_trans_add_bh(ip->i_gl, obh, 1);
+
+	leaf = new_leaf(inode, &bh, be16_to_cpu(oleaf->lf_depth));
+	if (!leaf) {
+		brelse(obh);
+		return -ENOSPC;
+	}
+	oleaf->lf_next = cpu_to_be64(bh->b_blocknr);
+	brelse(bh);
+	brelse(obh);
+
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		return error;
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_add_inode_blocks(&ip->i_inode, 1);
+	gfs2_dinode_out(ip, bh->b_data);
+	brelse(bh);
+	return 0;
+}
+
+/**
+ * gfs2_dir_add - Add new filename into directory
+ * @dip: The GFS2 inode
+ * @filename: The new name
+ * @inode: The inode number of the entry
+ * @type: The type of the entry
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+int gfs2_dir_add(struct inode *inode, const struct qstr *name,
+		 const struct gfs2_inode *nip)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *bh;
+	struct gfs2_dirent *dent;
+	struct gfs2_leaf *leaf;
+	int error;
+
+	while(1) {
+		dent = gfs2_dirent_search(inode, name, gfs2_dirent_find_space,
+					  &bh);
+		if (dent) {
+			if (IS_ERR(dent))
+				return PTR_ERR(dent);
+			dent = gfs2_init_dirent(inode, dent, name, bh);
+			gfs2_inum_out(nip, dent);
+			dent->de_type = cpu_to_be16(IF2DT(nip->i_inode.i_mode));
+			if (ip->i_diskflags & GFS2_DIF_EXHASH) {
+				leaf = (struct gfs2_leaf *)bh->b_data;
+				be16_add_cpu(&leaf->lf_entries, 1);
+			}
+			brelse(bh);
+			error = gfs2_meta_inode_buffer(ip, &bh);
+			if (error)
+				break;
+			gfs2_trans_add_bh(ip->i_gl, bh, 1);
+			ip->i_entries++;
+			ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+			if (S_ISDIR(nip->i_inode.i_mode))
+				inc_nlink(&ip->i_inode);
+			gfs2_dinode_out(ip, bh->b_data);
+			brelse(bh);
+			error = 0;
+			break;
+		}
+		if (!(ip->i_diskflags & GFS2_DIF_EXHASH)) {
+			error = dir_make_exhash(inode);
+			if (error)
+				break;
+			continue;
+		}
+		error = dir_split_leaf(inode, name);
+		if (error == 0)
+			continue;
+		if (error < 0)
+			break;
+		if (ip->i_depth < GFS2_DIR_MAX_DEPTH) {
+			error = dir_double_exhash(ip);
+			if (error)
+				break;
+			error = dir_split_leaf(inode, name);
+			if (error < 0)
+				break;
+			if (error == 0)
+				continue;
+		}
+		error = dir_new_leaf(inode, name);
+		if (!error)
+			continue;
+		error = -ENOSPC;
+		break;
+	}
+	return error;
+}
+
+
+/**
+ * gfs2_dir_del - Delete a directory entry
+ * @dip: The GFS2 inode
+ * @filename: The filename
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
+{
+	const struct qstr *name = &dentry->d_name;
+	struct gfs2_dirent *dent, *prev = NULL;
+	struct buffer_head *bh;
+	int error;
+
+	/* Returns _either_ the entry (if its first in block) or the
+	   previous entry otherwise */
+	dent = gfs2_dirent_search(&dip->i_inode, name, gfs2_dirent_prev, &bh);
+	if (!dent) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+	if (IS_ERR(dent)) {
+		gfs2_consist_inode(dip);
+		return PTR_ERR(dent);
+	}
+	/* If not first in block, adjust pointers accordingly */
+	if (gfs2_dirent_find(dent, name, NULL) == 0) {
+		prev = dent;
+		dent = (struct gfs2_dirent *)((char *)dent + be16_to_cpu(prev->de_rec_len));
+	}
+
+	dirent_del(dip, bh, prev, dent);
+	if (dip->i_diskflags & GFS2_DIF_EXHASH) {
+		struct gfs2_leaf *leaf = (struct gfs2_leaf *)bh->b_data;
+		u16 entries = be16_to_cpu(leaf->lf_entries);
+		if (!entries)
+			gfs2_consist_inode(dip);
+		leaf->lf_entries = cpu_to_be16(--entries);
+	}
+	brelse(bh);
+
+	error = gfs2_meta_inode_buffer(dip, &bh);
+	if (error)
+		return error;
+
+	if (!dip->i_entries)
+		gfs2_consist_inode(dip);
+	gfs2_trans_add_bh(dip->i_gl, bh, 1);
+	dip->i_entries--;
+	dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
+	if (S_ISDIR(dentry->d_inode->i_mode))
+		drop_nlink(&dip->i_inode);
+	gfs2_dinode_out(dip, bh->b_data);
+	brelse(bh);
+	mark_inode_dirty(&dip->i_inode);
+
+	return error;
+}
+
+/**
+ * gfs2_dir_mvino - Change inode number of directory entry
+ * @dip: The GFS2 inode
+ * @filename:
+ * @new_inode:
+ *
+ * This routine changes the inode number of a directory entry.  It's used
+ * by rename to change ".." when a directory is moved.
+ * Assumes a glock is held on dvp.
+ *
+ * Returns: errno
+ */
+
+int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+		   const struct gfs2_inode *nip, unsigned int new_type)
+{
+	struct buffer_head *bh;
+	struct gfs2_dirent *dent;
+	int error;
+
+	dent = gfs2_dirent_search(&dip->i_inode, filename, gfs2_dirent_find, &bh);
+	if (!dent) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+
+	gfs2_trans_add_bh(dip->i_gl, bh, 1);
+	gfs2_inum_out(nip, dent);
+	dent->de_type = cpu_to_be16(new_type);
+
+	if (dip->i_diskflags & GFS2_DIF_EXHASH) {
+		brelse(bh);
+		error = gfs2_meta_inode_buffer(dip, &bh);
+		if (error)
+			return error;
+		gfs2_trans_add_bh(dip->i_gl, bh, 1);
+	}
+
+	dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_dinode_out(dip, bh->b_data);
+	brelse(bh);
+	return 0;
+}
+
+/**
+ * leaf_dealloc - Deallocate a directory leaf
+ * @dip: the directory
+ * @index: the hash table offset in the directory
+ * @len: the number of pointers to this leaf
+ * @leaf_no: the leaf number
+ * @leaf_bh: buffer_head for the starting leaf
+ * last_dealloc: 1 if this is the final dealloc for the leaf, else 0
+ *
+ * Returns: errno
+ */
+
+static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
+			u64 leaf_no, struct buffer_head *leaf_bh,
+			int last_dealloc)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct gfs2_leaf *tmp_leaf;
+	struct gfs2_rgrp_list rlist;
+	struct buffer_head *bh, *dibh;
+	u64 blk, nblk;
+	unsigned int rg_blocks = 0, l_blocks = 0;
+	char *ht;
+	unsigned int x, size = len * sizeof(u64);
+	int error;
+
+	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
+
+	ht = kzalloc(size, GFP_NOFS);
+	if (!ht)
+		return -ENOMEM;
+
+	if (!gfs2_alloc_get(dip)) {
+		error = -ENOMEM;
+		goto out;
+	}
+
+	error = gfs2_quota_hold(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto out_put;
+
+	error = gfs2_rindex_hold(sdp, &dip->i_alloc->al_ri_gh);
+	if (error)
+		goto out_qs;
+
+	/*  Count the number of leaves  */
+	bh = leaf_bh;
+
+	for (blk = leaf_no; blk; blk = nblk) {
+		if (blk != leaf_no) {
+			error = get_leaf(dip, blk, &bh);
+			if (error)
+				goto out_rlist;
+		}
+		tmp_leaf = (struct gfs2_leaf *)bh->b_data;
+		nblk = be64_to_cpu(tmp_leaf->lf_next);
+		if (blk != leaf_no)
+			brelse(bh);
+
+		gfs2_rlist_add(sdp, &rlist, blk);
+		l_blocks++;
+	}
+
+	gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE);
+
+	for (x = 0; x < rlist.rl_rgrps; x++) {
+		struct gfs2_rgrpd *rgd;
+		rgd = rlist.rl_ghs[x].gh_gl->gl_object;
+		rg_blocks += rgd->rd_length;
+	}
+
+	error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs);
+	if (error)
+		goto out_rlist;
+
+	error = gfs2_trans_begin(sdp,
+			rg_blocks + (DIV_ROUND_UP(size, sdp->sd_jbsize) + 1) +
+			RES_DINODE + RES_STATFS + RES_QUOTA, l_blocks);
+	if (error)
+		goto out_rg_gunlock;
+
+	bh = leaf_bh;
+
+	for (blk = leaf_no; blk; blk = nblk) {
+		if (blk != leaf_no) {
+			error = get_leaf(dip, blk, &bh);
+			if (error)
+				goto out_end_trans;
+		}
+		tmp_leaf = (struct gfs2_leaf *)bh->b_data;
+		nblk = be64_to_cpu(tmp_leaf->lf_next);
+		if (blk != leaf_no)
+			brelse(bh);
+
+		gfs2_free_meta(dip, blk, 1);
+		gfs2_add_inode_blocks(&dip->i_inode, -1);
+	}
+
+	error = gfs2_dir_write_data(dip, ht, index * sizeof(u64), size);
+	if (error != size) {
+		if (error >= 0)
+			error = -EIO;
+		goto out_end_trans;
+	}
+
+	error = gfs2_meta_inode_buffer(dip, &dibh);
+	if (error)
+		goto out_end_trans;
+
+	gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+	/* On the last dealloc, make this a regular file in case we crash.
+	   (We don't want to free these blocks a second time.)  */
+	if (last_dealloc)
+		dip->i_inode.i_mode = S_IFREG;
+	gfs2_dinode_out(dip, dibh->b_data);
+	brelse(dibh);
+
+out_end_trans:
+	gfs2_trans_end(sdp);
+out_rg_gunlock:
+	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
+out_rlist:
+	gfs2_rlist_free(&rlist);
+	gfs2_glock_dq_uninit(&dip->i_alloc->al_ri_gh);
+out_qs:
+	gfs2_quota_unhold(dip);
+out_put:
+	gfs2_alloc_put(dip);
+out:
+	kfree(ht);
+	return error;
+}
+
+/**
+ * gfs2_dir_exhash_dealloc - free all the leaf blocks in a directory
+ * @dip: the directory
+ *
+ * Dealloc all on-disk directory leaves to FREEMETA state
+ * Change on-disk inode type to "regular file"
+ *
+ * Returns: errno
+ */
+
+int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct buffer_head *bh;
+	struct gfs2_leaf *leaf;
+	u32 hsize, len;
+	u32 ht_offset, lp_offset, ht_offset_cur = -1;
+	u32 index = 0, next_index;
+	__be64 *lp;
+	u64 leaf_no;
+	int error = 0, last;
+
+	hsize = 1 << dip->i_depth;
+	if (hsize * sizeof(u64) != i_size_read(&dip->i_inode)) {
+		gfs2_consist_inode(dip);
+		return -EIO;
+	}
+
+	lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS);
+	if (!lp)
+		return -ENOMEM;
+
+	while (index < hsize) {
+		lp_offset = index & (sdp->sd_hash_ptrs - 1);
+		ht_offset = index - lp_offset;
+
+		if (ht_offset_cur != ht_offset) {
+			error = gfs2_dir_read_data(dip, (char *)lp,
+						ht_offset * sizeof(__be64),
+						sdp->sd_hash_bsize, 1);
+			if (error != sdp->sd_hash_bsize) {
+				if (error >= 0)
+					error = -EIO;
+				goto out;
+			}
+			ht_offset_cur = ht_offset;
+		}
+
+		leaf_no = be64_to_cpu(lp[lp_offset]);
+		if (leaf_no) {
+			error = get_leaf(dip, leaf_no, &bh);
+			if (error)
+				goto out;
+			leaf = (struct gfs2_leaf *)bh->b_data;
+			len = 1 << (dip->i_depth - be16_to_cpu(leaf->lf_depth));
+
+			next_index = (index & ~(len - 1)) + len;
+			last = ((next_index >= hsize) ? 1 : 0);
+			error = leaf_dealloc(dip, index, len, leaf_no, bh,
+					     last);
+			brelse(bh);
+			if (error)
+				goto out;
+			index = next_index;
+		} else
+			index++;
+	}
+
+	if (index != hsize) {
+		gfs2_consist_inode(dip);
+		error = -EIO;
+	}
+
+out:
+	kfree(lp);
+
+	return error;
+}
+
+/**
+ * gfs2_diradd_alloc_required - find if adding entry will require an allocation
+ * @ip: the file being written to
+ * @filname: the filename that's going to be added
+ *
+ * Returns: 1 if alloc required, 0 if not, -ve on error
+ */
+
+int gfs2_diradd_alloc_required(struct inode *inode, const struct qstr *name)
+{
+	struct gfs2_dirent *dent;
+	struct buffer_head *bh;
+
+	dent = gfs2_dirent_search(inode, name, gfs2_dirent_find_space, &bh);
+	if (!dent) {
+		return 1;
+	}
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	brelse(bh);
+	return 0;
+}
+
diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h
new file mode 100644
index 00000000..e686af11
--- /dev/null
+++ b/fs/gfs2/dir.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+#include <linux/dcache.h>
+#include <linux/crc32.h>
+
+struct inode;
+struct gfs2_inode;
+struct gfs2_inum;
+
+extern struct inode *gfs2_dir_search(struct inode *dir,
+				     const struct qstr *filename);
+extern int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
+			  const struct gfs2_inode *ip);
+extern int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+			const struct gfs2_inode *ip);
+extern int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry);
+extern int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
+			 filldir_t filldir);
+extern int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+			  const struct gfs2_inode *nip, unsigned int new_type);
+
+extern int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+
+extern int gfs2_diradd_alloc_required(struct inode *dir,
+				      const struct qstr *filename);
+extern int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+				   struct buffer_head **bhp);
+
+static inline u32 gfs2_disk_hash(const char *data, int len)
+{
+        return crc32_le((u32)~0, data, len) ^ (u32)~0;
+}
+
+
+static inline void gfs2_str2qstr(struct qstr *name, const char *fname)
+{
+	name->name = fname;
+	name->len = strlen(fname);
+	name->hash = gfs2_disk_hash(name->name, name->len);
+}
+
+/* N.B. This probably ought to take inum & type as args as well */
+static inline void gfs2_qstr2dirent(const struct qstr *name, u16 reclen, struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_addr = cpu_to_be64(0);
+	dent->de_inum.no_formal_ino = cpu_to_be64(0);
+	dent->de_hash = cpu_to_be32(name->hash);
+	dent->de_rec_len = cpu_to_be16(reclen);
+	dent->de_name_len = cpu_to_be16(name->len);
+	dent->de_type = cpu_to_be16(0);
+	memset(dent->__pad, 0, sizeof(dent->__pad));
+	memcpy(dent + 1, name->name, name->len);
+}
+
+extern struct qstr gfs2_qdot;
+extern struct qstr gfs2_qdotdot;
+
+#endif /* __DIR_DOT_H__ */
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
new file mode 100644
index 00000000..fe9945f2
--- /dev/null
+++ b/fs/gfs2/export.c
@@ -0,0 +1,206 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/exportfs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "super.h"
+#include "rgrp.h"
+#include "util.h"
+
+#define GFS2_SMALL_FH_SIZE 4
+#define GFS2_LARGE_FH_SIZE 8
+#define GFS2_OLD_FH_SIZE 10
+
+static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
+			  int connectable)
+{
+	__be32 *fh = (__force __be32 *)p;
+	struct inode *inode = dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (connectable && (*len < GFS2_LARGE_FH_SIZE)) {
+		*len = GFS2_LARGE_FH_SIZE;
+		return 255;
+	} else if (*len < GFS2_SMALL_FH_SIZE) {
+		*len = GFS2_SMALL_FH_SIZE;
+		return 255;
+	}
+
+	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
+	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
+	fh[2] = cpu_to_be32(ip->i_no_addr >> 32);
+	fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
+	*len = GFS2_SMALL_FH_SIZE;
+
+	if (!connectable || inode == sb->s_root->d_inode)
+		return *len;
+
+	spin_lock(&dentry->d_lock);
+	inode = dentry->d_parent->d_inode;
+	ip = GFS2_I(inode);
+	igrab(inode);
+	spin_unlock(&dentry->d_lock);
+
+	fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32);
+	fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
+	fh[6] = cpu_to_be32(ip->i_no_addr >> 32);
+	fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
+	*len = GFS2_LARGE_FH_SIZE;
+
+	iput(inode);
+
+	return *len;
+}
+
+struct get_name_filldir {
+	struct gfs2_inum_host inum;
+	char *name;
+};
+
+static int get_name_filldir(void *opaque, const char *name, int length,
+			    loff_t offset, u64 inum, unsigned int type)
+{
+	struct get_name_filldir *gnfd = opaque;
+
+	if (inum != gnfd->inum.no_addr)
+		return 0;
+
+	memcpy(gnfd->name, name, length);
+	gnfd->name[length] = 0;
+
+	return 1;
+}
+
+static int gfs2_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct inode *dir = parent->d_inode;
+	struct inode *inode = child->d_inode;
+	struct gfs2_inode *dip, *ip;
+	struct get_name_filldir gnfd;
+	struct gfs2_holder gh;
+	u64 offset = 0;
+	int error;
+
+	if (!dir)
+		return -EINVAL;
+
+	if (!S_ISDIR(dir->i_mode) || !inode)
+		return -EINVAL;
+
+	dip = GFS2_I(dir);
+	ip = GFS2_I(inode);
+
+	*name = 0;
+	gnfd.inum.no_addr = ip->i_no_addr;
+	gnfd.inum.no_formal_ino = ip->i_no_formal_ino;
+	gnfd.name = name;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (error)
+		return error;
+
+	error = gfs2_dir_read(dir, &offset, &gnfd, get_name_filldir);
+
+	gfs2_glock_dq_uninit(&gh);
+
+	if (!error && !*name)
+		error = -ENOENT;
+
+	return error;
+}
+
+static struct dentry *gfs2_get_parent(struct dentry *child)
+{
+	return d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
+}
+
+static struct dentry *gfs2_get_dentry(struct super_block *sb,
+				      struct gfs2_inum_host *inum)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct inode *inode;
+
+	inode = gfs2_ilookup(sb, inum->no_addr, 0);
+	if (inode) {
+		if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+		goto out_inode;
+	}
+
+	inode = gfs2_lookup_by_inum(sdp, inum->no_addr, &inum->no_formal_ino,
+				    GFS2_BLKST_DINODE);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+out_inode:
+	return d_obtain_alias(inode);
+}
+
+static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	struct gfs2_inum_host this;
+	__be32 *fh = (__force __be32 *)fid->raw;
+
+	switch (fh_type) {
+	case GFS2_SMALL_FH_SIZE:
+	case GFS2_LARGE_FH_SIZE:
+	case GFS2_OLD_FH_SIZE:
+		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
+		this.no_formal_ino |= be32_to_cpu(fh[1]);
+		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
+		this.no_addr |= be32_to_cpu(fh[3]);
+		return gfs2_get_dentry(sb, &this);
+	default:
+		return NULL;
+	}
+}
+
+static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	struct gfs2_inum_host parent;
+	__be32 *fh = (__force __be32 *)fid->raw;
+
+	switch (fh_type) {
+	case GFS2_LARGE_FH_SIZE:
+	case GFS2_OLD_FH_SIZE:
+		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
+		parent.no_formal_ino |= be32_to_cpu(fh[5]);
+		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
+		parent.no_addr |= be32_to_cpu(fh[7]);
+		return gfs2_get_dentry(sb, &parent);
+	default:
+		return NULL;
+	}
+}
+
+const struct export_operations gfs2_export_ops = {
+	.encode_fh = gfs2_encode_fh,
+	.fh_to_dentry = gfs2_fh_to_dentry,
+	.fh_to_parent = gfs2_fh_to_parent,
+	.get_name = gfs2_get_name,
+	.get_parent = gfs2_get_parent,
+};
+
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
new file mode 100644
index 00000000..a9f5cbe4
--- /dev/null
+++ b/fs/gfs2/file.c
@@ -0,0 +1,1112 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+#include <linux/blkdev.h>
+#include <linux/mm.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/ext2_fs.h>
+#include <linux/falloc.h>
+#include <linux/swap.h>
+#include <linux/crc32.h>
+#include <linux/writeback.h>
+#include <asm/uaccess.h>
+#include <linux/dlm.h>
+#include <linux/dlm_plock.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+
+/**
+ * gfs2_llseek - seek to a location in a file
+ * @file: the file
+ * @offset: the offset
+ * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
+ *
+ * SEEK_END requires the glock for the file because it references the
+ * file's size.
+ *
+ * Returns: The new offset, or errno
+ */
+
+static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	loff_t error;
+
+	if (origin == 2) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (!error) {
+			error = generic_file_llseek_unlocked(file, offset, origin);
+			gfs2_glock_dq_uninit(&i_gh);
+		}
+	} else
+		error = generic_file_llseek_unlocked(file, offset, origin);
+
+	return error;
+}
+
+/**
+ * gfs2_readdir - Read directory entries from a directory
+ * @file: The directory to read from
+ * @dirent: Buffer for dirents
+ * @filldir: Function used to do the copying
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	struct inode *dir = file->f_mapping->host;
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_holder d_gh;
+	u64 offset = file->f_pos;
+	int error;
+
+	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+	error = gfs2_glock_nq(&d_gh);
+	if (error) {
+		gfs2_holder_uninit(&d_gh);
+		return error;
+	}
+
+	error = gfs2_dir_read(dir, &offset, dirent, filldir);
+
+	gfs2_glock_dq_uninit(&d_gh);
+
+	file->f_pos = offset;
+
+	return error;
+}
+
+/**
+ * fsflags_cvt
+ * @table: A table of 32 u32 flags
+ * @val: a 32 bit value to convert
+ *
+ * This function can be used to convert between fsflags values and
+ * GFS2's own flags values.
+ *
+ * Returns: the converted flags
+ */
+static u32 fsflags_cvt(const u32 *table, u32 val)
+{
+	u32 res = 0;
+	while(val) {
+		if (val & 1)
+			res |= *table;
+		table++;
+		val >>= 1;
+	}
+	return res;
+}
+
+static const u32 fsflags_to_gfs2[32] = {
+	[3] = GFS2_DIF_SYNC,
+	[4] = GFS2_DIF_IMMUTABLE,
+	[5] = GFS2_DIF_APPENDONLY,
+	[7] = GFS2_DIF_NOATIME,
+	[12] = GFS2_DIF_EXHASH,
+	[14] = GFS2_DIF_INHERIT_JDATA,
+};
+
+static const u32 gfs2_to_fsflags[32] = {
+	[gfs2fl_Sync] = FS_SYNC_FL,
+	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
+	[gfs2fl_AppendOnly] = FS_APPEND_FL,
+	[gfs2fl_NoAtime] = FS_NOATIME_FL,
+	[gfs2fl_ExHash] = FS_INDEX_FL,
+	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
+};
+
+static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+	u32 fsflags;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	error = gfs2_glock_nq(&gh);
+	if (error)
+		return error;
+
+	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_diskflags);
+	if (!S_ISDIR(inode->i_mode) && ip->i_diskflags & GFS2_DIF_JDATA)
+		fsflags |= FS_JOURNAL_DATA_FL;
+	if (put_user(fsflags, ptr))
+		error = -EFAULT;
+
+	gfs2_glock_dq(&gh);
+	gfs2_holder_uninit(&gh);
+	return error;
+}
+
+void gfs2_set_inode_flags(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned int flags = inode->i_flags;
+
+	flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	if (ip->i_diskflags & GFS2_DIF_IMMUTABLE)
+		flags |= S_IMMUTABLE;
+	if (ip->i_diskflags & GFS2_DIF_APPENDONLY)
+		flags |= S_APPEND;
+	if (ip->i_diskflags & GFS2_DIF_NOATIME)
+		flags |= S_NOATIME;
+	if (ip->i_diskflags & GFS2_DIF_SYNC)
+		flags |= S_SYNC;
+	inode->i_flags = flags;
+}
+
+/* Flags that can be set by user space */
+#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
+			     GFS2_DIF_IMMUTABLE|		\
+			     GFS2_DIF_APPENDONLY|		\
+			     GFS2_DIF_NOATIME|			\
+			     GFS2_DIF_SYNC|			\
+			     GFS2_DIF_SYSTEM|			\
+			     GFS2_DIF_INHERIT_JDATA)
+
+/**
+ * gfs2_set_flags - set flags on an inode
+ * @inode: The inode
+ * @flags: The flags to set
+ * @mask: Indicates which flags are valid
+ *
+ */
+static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *bh;
+	struct gfs2_holder gh;
+	int error;
+	u32 new_flags, flags;
+
+	error = mnt_want_write(filp->f_path.mnt);
+	if (error)
+		return error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (error)
+		goto out_drop_write;
+
+	error = -EACCES;
+	if (!inode_owner_or_capable(inode))
+		goto out;
+
+	error = 0;
+	flags = ip->i_diskflags;
+	new_flags = (flags & ~mask) | (reqflags & mask);
+	if ((new_flags ^ flags) == 0)
+		goto out;
+
+	error = -EINVAL;
+	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
+		goto out;
+
+	error = -EPERM;
+	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
+		goto out;
+	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
+		goto out;
+	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		goto out;
+	if (!IS_IMMUTABLE(inode)) {
+		error = gfs2_permission(inode, MAY_WRITE, 0);
+		if (error)
+			goto out;
+	}
+	if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
+		if (flags & GFS2_DIF_JDATA)
+			gfs2_log_flush(sdp, ip->i_gl);
+		error = filemap_fdatawrite(inode->i_mapping);
+		if (error)
+			goto out;
+		error = filemap_fdatawait(inode->i_mapping);
+		if (error)
+			goto out;
+	}
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		goto out;
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		goto out_trans_end;
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	ip->i_diskflags = new_flags;
+	gfs2_dinode_out(ip, bh->b_data);
+	brelse(bh);
+	gfs2_set_inode_flags(inode);
+	gfs2_set_aops(inode);
+out_trans_end:
+	gfs2_trans_end(sdp);
+out:
+	gfs2_glock_dq_uninit(&gh);
+out_drop_write:
+	mnt_drop_write(filp->f_path.mnt);
+	return error;
+}
+
+static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	u32 fsflags, gfsflags;
+
+	if (get_user(fsflags, ptr))
+		return -EFAULT;
+
+	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
+	if (!S_ISDIR(inode->i_mode)) {
+		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
+			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
+		return do_gfs2_set_flags(filp, gfsflags, ~0);
+	}
+	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
+}
+
+static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch(cmd) {
+	case FS_IOC_GETFLAGS:
+		return gfs2_get_flags(filp, (u32 __user *)arg);
+	case FS_IOC_SETFLAGS:
+		return gfs2_set_flags(filp, (u32 __user *)arg);
+	}
+	return -ENOTTY;
+}
+
+/**
+ * gfs2_allocate_page_backing - Use bmap to allocate blocks
+ * @page: The (locked) page to allocate backing for
+ *
+ * We try to allocate all the blocks required for the page in
+ * one go. This might fail for various reasons, so we keep
+ * trying until all the blocks to back this page are allocated.
+ * If some of the blocks are already allocated, thats ok too.
+ */
+
+static int gfs2_allocate_page_backing(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct buffer_head bh;
+	unsigned long size = PAGE_CACHE_SIZE;
+	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+	do {
+		bh.b_state = 0;
+		bh.b_size = size;
+		gfs2_block_map(inode, lblock, &bh, 1);
+		if (!buffer_mapped(&bh))
+			return -EIO;
+		size -= bh.b_size;
+		lblock += (bh.b_size >> inode->i_blkbits);
+	} while(size > 0);
+	return 0;
+}
+
+/**
+ * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
+ * @vma: The virtual memory area
+ * @page: The page which is about to become writable
+ *
+ * When the page becomes writable, we need to ensure that we have
+ * blocks allocated on disk to back that page.
+ */
+
+static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	unsigned long last_index;
+	u64 pos = page->index << PAGE_CACHE_SHIFT;
+	unsigned int data_blocks, ind_blocks, rblocks;
+	struct gfs2_holder gh;
+	struct gfs2_alloc *al;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out;
+
+	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
+	set_bit(GIF_SW_PAGED, &ip->i_flags);
+
+	if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE))
+		goto out_unlock;
+	ret = -ENOMEM;
+	al = gfs2_alloc_get(ip);
+	if (al == NULL)
+		goto out_unlock;
+
+	ret = gfs2_quota_lock_check(ip);
+	if (ret)
+		goto out_alloc_put;
+	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
+	al->al_requested = data_blocks + ind_blocks;
+	ret = gfs2_inplace_reserve(ip);
+	if (ret)
+		goto out_quota_unlock;
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks) {
+		rblocks += RES_STATFS + RES_QUOTA;
+		rblocks += gfs2_rg_blocks(al);
+	}
+	ret = gfs2_trans_begin(sdp, rblocks, 0);
+	if (ret)
+		goto out_trans_fail;
+
+	lock_page(page);
+	ret = -EINVAL;
+	last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
+	if (page->index > last_index)
+		goto out_unlock_page;
+	ret = 0;
+	if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
+		goto out_unlock_page;
+	if (gfs2_is_stuffed(ip)) {
+		ret = gfs2_unstuff_dinode(ip, page);
+		if (ret)
+			goto out_unlock_page;
+	}
+	ret = gfs2_allocate_page_backing(page);
+
+out_unlock_page:
+	unlock_page(page);
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_quota_unlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&gh);
+out:
+	gfs2_holder_uninit(&gh);
+	if (ret == -ENOMEM)
+		ret = VM_FAULT_OOM;
+	else if (ret)
+		ret = VM_FAULT_SIGBUS;
+	return ret;
+}
+
+static const struct vm_operations_struct gfs2_vm_ops = {
+	.fault = filemap_fault,
+	.page_mkwrite = gfs2_page_mkwrite,
+};
+
+/**
+ * gfs2_mmap -
+ * @file: The file to map
+ * @vma: The VMA which described the mapping
+ *
+ * There is no need to get a lock here unless we should be updating
+ * atime. We ignore any locking errors since the only consequence is
+ * a missed atime update (which will just be deferred until later).
+ *
+ * Returns: 0
+ */
+
+static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+
+	if (!(file->f_flags & O_NOATIME) &&
+	    !IS_NOATIME(&ip->i_inode)) {
+		struct gfs2_holder i_gh;
+		int error;
+
+		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+		error = gfs2_glock_nq(&i_gh);
+		if (error == 0) {
+			file_accessed(file);
+			gfs2_glock_dq(&i_gh);
+		}
+		gfs2_holder_uninit(&i_gh);
+		if (error)
+			return error;
+	}
+	vma->vm_ops = &gfs2_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
+
+	return 0;
+}
+
+/**
+ * gfs2_open - open a file
+ * @inode: the inode to open
+ * @file: the struct file for this opening
+ *
+ * Returns: errno
+ */
+
+static int gfs2_open(struct inode *inode, struct file *file)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder i_gh;
+	struct gfs2_file *fp;
+	int error;
+
+	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
+	if (!fp)
+		return -ENOMEM;
+
+	mutex_init(&fp->f_fl_mutex);
+
+	gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
+	file->private_data = fp;
+
+	if (S_ISREG(ip->i_inode.i_mode)) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (error)
+			goto fail;
+
+		if (!(file->f_flags & O_LARGEFILE) &&
+		    i_size_read(inode) > MAX_NON_LFS) {
+			error = -EOVERFLOW;
+			goto fail_gunlock;
+		}
+
+		gfs2_glock_dq_uninit(&i_gh);
+	}
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&i_gh);
+fail:
+	file->private_data = NULL;
+	kfree(fp);
+	return error;
+}
+
+/**
+ * gfs2_close - called to close a struct file
+ * @inode: the inode the struct file belongs to
+ * @file: the struct file being closed
+ *
+ * Returns: errno
+ */
+
+static int gfs2_close(struct inode *inode, struct file *file)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_file *fp;
+
+	fp = file->private_data;
+	file->private_data = NULL;
+
+	if (gfs2_assert_warn(sdp, fp))
+		return -EIO;
+
+	kfree(fp);
+
+	return 0;
+}
+
+/**
+ * gfs2_fsync - sync the dirty data for a file (across the cluster)
+ * @file: the file that points to the dentry (we ignore this)
+ * @datasync: set if we can ignore timestamp changes
+ *
+ * The VFS will flush data for us. We only need to worry
+ * about metadata here.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_fsync(struct file *file, int datasync)
+{
+	struct inode *inode = file->f_mapping->host;
+	int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int ret;
+
+	if (datasync)
+		sync_state &= ~I_DIRTY_SYNC;
+
+	if (sync_state) {
+		ret = sync_inode_metadata(inode, 1);
+		if (ret)
+			return ret;
+		gfs2_ail_flush(ip->i_gl);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_file_aio_write - Perform a write to a file
+ * @iocb: The io context
+ * @iov: The data to write
+ * @nr_segs: Number of @iov segments
+ * @pos: The file position
+ *
+ * We have to do a lock/unlock here to refresh the inode size for
+ * O_APPEND writes, otherwise we can land up writing at the wrong
+ * offset. There is still a race, but provided the app is using its
+ * own file locking, this will make O_APPEND work as expected.
+ *
+ */
+
+static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+				   unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+
+	if (file->f_flags & O_APPEND) {
+		struct dentry *dentry = file->f_dentry;
+		struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+		struct gfs2_holder gh;
+		int ret;
+
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+		if (ret)
+			return ret;
+		gfs2_glock_dq_uninit(&gh);
+	}
+
+	return generic_file_aio_write(iocb, iov, nr_segs, pos);
+}
+
+static int empty_write_end(struct page *page, unsigned from,
+			   unsigned to, int mode)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *bh;
+	unsigned offset, blksize = 1 << inode->i_blkbits;
+	pgoff_t end_index = i_size_read(inode) >> PAGE_CACHE_SHIFT;
+
+	zero_user(page, from, to-from);
+	mark_page_accessed(page);
+
+	if (page->index < end_index || !(mode & FALLOC_FL_KEEP_SIZE)) {
+		if (!gfs2_is_writeback(ip))
+			gfs2_page_add_databufs(ip, page, from, to);
+
+		block_commit_write(page, from, to);
+		return 0;
+	}
+
+	offset = 0;
+	bh = page_buffers(page);
+	while (offset < to) {
+		if (offset >= from) {
+			set_buffer_uptodate(bh);
+			mark_buffer_dirty(bh);
+			clear_buffer_new(bh);
+			write_dirty_buffer(bh, WRITE);
+		}
+		offset += blksize;
+		bh = bh->b_this_page;
+	}
+
+	offset = 0;
+	bh = page_buffers(page);
+	while (offset < to) {
+		if (offset >= from) {
+			wait_on_buffer(bh);
+			if (!buffer_uptodate(bh))
+				return -EIO;
+		}
+		offset += blksize;
+		bh = bh->b_this_page;
+	}
+	return 0;
+}
+
+static int needs_empty_write(sector_t block, struct inode *inode)
+{
+	int error;
+	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
+
+	bh_map.b_size = 1 << inode->i_blkbits;
+	error = gfs2_block_map(inode, block, &bh_map, 0);
+	if (unlikely(error))
+		return error;
+	return !buffer_mapped(&bh_map);
+}
+
+static int write_empty_blocks(struct page *page, unsigned from, unsigned to,
+			      int mode)
+{
+	struct inode *inode = page->mapping->host;
+	unsigned start, end, next, blksize;
+	sector_t block = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	int ret;
+
+	blksize = 1 << inode->i_blkbits;
+	next = end = 0;
+	while (next < from) {
+		next += blksize;
+		block++;
+	}
+	start = next;
+	do {
+		next += blksize;
+		ret = needs_empty_write(block, inode);
+		if (unlikely(ret < 0))
+			return ret;
+		if (ret == 0) {
+			if (end) {
+				ret = __block_write_begin(page, start, end - start,
+							  gfs2_block_map);
+				if (unlikely(ret))
+					return ret;
+				ret = empty_write_end(page, start, end, mode);
+				if (unlikely(ret))
+					return ret;
+				end = 0;
+			}
+			start = next;
+		}
+		else
+			end = next;
+		block++;
+	} while (next < to);
+
+	if (end) {
+		ret = __block_write_begin(page, start, end - start, gfs2_block_map);
+		if (unlikely(ret))
+			return ret;
+		ret = empty_write_end(page, start, end, mode);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	return 0;
+}
+
+static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
+			   int mode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *dibh;
+	int error;
+	u64 start = offset >> PAGE_CACHE_SHIFT;
+	unsigned int start_offset = offset & ~PAGE_CACHE_MASK;
+	u64 end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+	pgoff_t curr;
+	struct page *page;
+	unsigned int end_offset = (offset + len) & ~PAGE_CACHE_MASK;
+	unsigned int from, to;
+
+	if (!end_offset)
+		end_offset = PAGE_CACHE_SIZE;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (unlikely(error))
+		goto out;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (gfs2_is_stuffed(ip)) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (unlikely(error))
+			goto out;
+	}
+
+	curr = start;
+	offset = start << PAGE_CACHE_SHIFT;
+	from = start_offset;
+	to = PAGE_CACHE_SIZE;
+	while (curr <= end) {
+		page = grab_cache_page_write_begin(inode->i_mapping, curr,
+						   AOP_FLAG_NOFS);
+		if (unlikely(!page)) {
+			error = -ENOMEM;
+			goto out;
+		}
+
+		if (curr == end)
+			to = end_offset;
+		error = write_empty_blocks(page, from, to, mode);
+		if (!error && offset + to > inode->i_size &&
+		    !(mode & FALLOC_FL_KEEP_SIZE)) {
+			i_size_write(inode, offset + to);
+		}
+		unlock_page(page);
+		page_cache_release(page);
+		if (error)
+			goto out;
+		curr++;
+		offset += PAGE_CACHE_SIZE;
+		from = 0;
+	}
+
+	gfs2_dinode_out(ip, dibh->b_data);
+	mark_inode_dirty(inode);
+
+	brelse(dibh);
+
+out:
+	return error;
+}
+
+static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
+			    unsigned int *data_blocks, unsigned int *ind_blocks)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int max_blocks = ip->i_alloc->al_rgd->rd_free_clone;
+	unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
+
+	for (tmp = max_data; tmp > sdp->sd_diptrs;) {
+		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+		max_data -= tmp;
+	}
+	/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
+	   so it might end up with fewer data blocks */
+	if (max_data <= *data_blocks)
+		return;
+	*data_blocks = max_data;
+	*ind_blocks = max_blocks - max_data;
+	*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
+	if (*len > max) {
+		*len = max;
+		gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
+	}
+}
+
+static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
+			   loff_t len)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+	loff_t bytes, max_bytes;
+	struct gfs2_alloc *al;
+	int error;
+	loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
+	loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
+	next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
+
+	/* We only support the FALLOC_FL_KEEP_SIZE mode */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	offset &= bsize_mask;
+
+	len = next - offset;
+	bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
+	if (!bytes)
+		bytes = UINT_MAX;
+	bytes &= bsize_mask;
+	if (bytes == 0)
+		bytes = sdp->sd_sb.sb_bsize;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
+	if (unlikely(error))
+		goto out_uninit;
+
+	if (!gfs2_write_alloc_required(ip, offset, len))
+		goto out_unlock;
+
+	while (len > 0) {
+		if (len < bytes)
+			bytes = len;
+		al = gfs2_alloc_get(ip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_unlock;
+		}
+
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto out_alloc_put;
+
+retry:
+		gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error) {
+			if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
+				bytes >>= 1;
+				bytes &= bsize_mask;
+				if (bytes == 0)
+					bytes = sdp->sd_sb.sb_bsize;
+				goto retry;
+			}
+			goto out_qunlock;
+		}
+		max_bytes = bytes;
+		calc_max_reserv(ip, len, &max_bytes, &data_blocks, &ind_blocks);
+		al->al_requested = data_blocks + ind_blocks;
+
+		rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
+			  RES_RG_HDR + gfs2_rg_blocks(al);
+		if (gfs2_is_jdata(ip))
+			rblocks += data_blocks ? data_blocks : 1;
+
+		error = gfs2_trans_begin(sdp, rblocks,
+					 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+		if (error)
+			goto out_trans_fail;
+
+		error = fallocate_chunk(inode, offset, max_bytes, mode);
+		gfs2_trans_end(sdp);
+
+		if (error)
+			goto out_trans_fail;
+
+		len -= max_bytes;
+		offset += max_bytes;
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	goto out_unlock;
+
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_qunlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
+	return error;
+}
+
+#ifdef CONFIG_GFS2_FS_LOCKING_DLM
+
+/**
+ * gfs2_setlease - acquire/release a file lease
+ * @file: the file pointer
+ * @arg: lease type
+ * @fl: file lock
+ *
+ * We don't currently have a way to enforce a lease across the whole
+ * cluster; until we do, disable leases (by just returning -EINVAL),
+ * unless the administrator has requested purely local locking.
+ *
+ * Locking: called under lock_flocks
+ *
+ * Returns: errno
+ */
+
+static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
+{
+	return -EINVAL;
+}
+
+/**
+ * gfs2_lock - acquire/release a posix lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+
+	if (!(fl->fl_flags & FL_POSIX))
+		return -ENOLCK;
+	if (__mandatory_lock(&ip->i_inode) && fl->fl_type != F_UNLCK)
+		return -ENOLCK;
+
+	if (cmd == F_CANCELLK) {
+		/* Hack: */
+		cmd = F_SETLK;
+		fl->fl_type = F_UNLCK;
+	}
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+	if (IS_GETLK(cmd))
+		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
+	else if (fl->fl_type == F_UNLCK)
+		return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
+	else
+		return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
+}
+
+static int do_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+	struct gfs2_inode *ip = GFS2_I(file->f_path.dentry->d_inode);
+	struct gfs2_glock *gl;
+	unsigned int state;
+	int flags;
+	int error = 0;
+
+	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+
+	mutex_lock(&fp->f_fl_mutex);
+
+	gl = fl_gh->gh_gl;
+	if (gl) {
+		if (fl_gh->gh_state == state)
+			goto out;
+		flock_lock_file_wait(file,
+				     &(struct file_lock){.fl_type = F_UNLCK});
+		gfs2_glock_dq_wait(fl_gh);
+		gfs2_holder_reinit(state, flags, fl_gh);
+	} else {
+		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
+				       &gfs2_flock_glops, CREATE, &gl);
+		if (error)
+			goto out;
+		gfs2_holder_init(gl, state, flags, fl_gh);
+		gfs2_glock_put(gl);
+	}
+	error = gfs2_glock_nq(fl_gh);
+	if (error) {
+		gfs2_holder_uninit(fl_gh);
+		if (error == GLR_TRYFAILED)
+			error = -EAGAIN;
+	} else {
+		error = flock_lock_file_wait(file, fl);
+		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
+	}
+
+out:
+	mutex_unlock(&fp->f_fl_mutex);
+	return error;
+}
+
+static void do_unflock(struct file *file, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+
+	mutex_lock(&fp->f_fl_mutex);
+	flock_lock_file_wait(file, fl);
+	if (fl_gh->gh_gl) {
+		gfs2_glock_dq_wait(fl_gh);
+		gfs2_holder_uninit(fl_gh);
+	}
+	mutex_unlock(&fp->f_fl_mutex);
+}
+
+/**
+ * gfs2_flock - acquire/release a flock lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	if (!(fl->fl_flags & FL_FLOCK))
+		return -ENOLCK;
+	if (fl->fl_type & LOCK_MAND)
+		return -EOPNOTSUPP;
+
+	if (fl->fl_type == F_UNLCK) {
+		do_unflock(file, fl);
+		return 0;
+	} else {
+		return do_flock(file, cmd, fl);
+	}
+}
+
+const struct file_operations gfs2_file_fops = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= gfs2_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.flock		= gfs2_flock,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.setlease	= gfs2_setlease,
+	.fallocate	= gfs2_fallocate,
+};
+
+const struct file_operations gfs2_dir_fops = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.flock		= gfs2_flock,
+	.llseek		= default_llseek,
+};
+
+#endif /* CONFIG_GFS2_FS_LOCKING_DLM */
+
+const struct file_operations gfs2_file_fops_nolock = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= gfs2_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.setlease	= generic_setlease,
+	.fallocate	= gfs2_fallocate,
+};
+
+const struct file_operations gfs2_dir_fops_nolock = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.llseek		= default_llseek,
+};
+
diff --git a/fs/gfs2/gfs2.h b/fs/gfs2/gfs2.h
new file mode 100644
index 00000000..ef606e3a
--- /dev/null
+++ b/fs/gfs2/gfs2.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GFS2_DOT_H__
+#define __GFS2_DOT_H__
+
+enum {
+	NO_CREATE = 0,
+	CREATE = 1,
+};
+
+enum {
+	NO_FORCE = 0,
+	FORCE = 1,
+};
+
+#define GFS2_FAST_NAME_SIZE 8
+
+#endif /* __GFS2_DOT_H__ */
+
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
new file mode 100644
index 00000000..1c1336e7
--- /dev/null
+++ b/fs/gfs2/glock.c
@@ -0,0 +1,1870 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/buffer_head.h>
+#include <linux/delay.h>
+#include <linux/sort.h>
+#include <linux/jhash.h>
+#include <linux/kallsyms.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+#include <linux/module.h>
+#include <asm/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <linux/bit_spinlock.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "super.h"
+#include "util.h"
+#include "bmap.h"
+#define CREATE_TRACE_POINTS
+#include "trace_gfs2.h"
+
+struct gfs2_glock_iter {
+	int hash;			/* hash bucket index         */
+	struct gfs2_sbd *sdp;		/* incore superblock         */
+	struct gfs2_glock *gl;		/* current glock struct      */
+	char string[512];		/* scratch space             */
+};
+
+typedef void (*glock_examiner) (struct gfs2_glock * gl);
+
+static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl);
+#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { __dump_glock(NULL, gl); BUG(); } } while(0)
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
+
+static struct dentry *gfs2_root;
+static struct workqueue_struct *glock_workqueue;
+struct workqueue_struct *gfs2_delete_workqueue;
+static LIST_HEAD(lru_list);
+static atomic_t lru_count = ATOMIC_INIT(0);
+static DEFINE_SPINLOCK(lru_lock);
+
+#define GFS2_GL_HASH_SHIFT      15
+#define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)
+#define GFS2_GL_HASH_MASK       (GFS2_GL_HASH_SIZE - 1)
+
+static struct hlist_bl_head gl_hash_table[GFS2_GL_HASH_SIZE];
+static struct dentry *gfs2_root;
+
+/**
+ * gl_hash() - Turn glock number into hash bucket number
+ * @lock: The glock number
+ *
+ * Returns: The number of the corresponding hash bucket
+ */
+
+static unsigned int gl_hash(const struct gfs2_sbd *sdp,
+			    const struct lm_lockname *name)
+{
+	unsigned int h;
+
+	h = jhash(&name->ln_number, sizeof(u64), 0);
+	h = jhash(&name->ln_type, sizeof(unsigned int), h);
+	h = jhash(&sdp, sizeof(struct gfs2_sbd *), h);
+	h &= GFS2_GL_HASH_MASK;
+
+	return h;
+}
+
+static inline void spin_lock_bucket(unsigned int hash)
+{
+	hlist_bl_lock(&gl_hash_table[hash]);
+}
+
+static inline void spin_unlock_bucket(unsigned int hash)
+{
+	hlist_bl_unlock(&gl_hash_table[hash]);
+}
+
+static void gfs2_glock_dealloc(struct rcu_head *rcu)
+{
+	struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
+
+	if (gl->gl_ops->go_flags & GLOF_ASPACE)
+		kmem_cache_free(gfs2_glock_aspace_cachep, gl);
+	else
+		kmem_cache_free(gfs2_glock_cachep, gl);
+}
+
+void gfs2_glock_free(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
+	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+		wake_up(&sdp->sd_glock_wait);
+}
+
+/**
+ * gfs2_glock_hold() - increment reference count on glock
+ * @gl: The glock to hold
+ *
+ */
+
+void gfs2_glock_hold(struct gfs2_glock *gl)
+{
+	GLOCK_BUG_ON(gl, atomic_read(&gl->gl_ref) == 0);
+	atomic_inc(&gl->gl_ref);
+}
+
+/**
+ * demote_ok - Check to see if it's ok to unlock a glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int demote_ok(const struct gfs2_glock *gl)
+{
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+
+	if (gl->gl_state == LM_ST_UNLOCKED)
+		return 0;
+	if (!list_empty(&gl->gl_holders))
+		return 0;
+	if (glops->go_demote_ok)
+		return glops->go_demote_ok(gl);
+	return 1;
+}
+
+
+void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
+{
+	spin_lock(&lru_lock);
+
+	if (!list_empty(&gl->gl_lru))
+		list_del_init(&gl->gl_lru);
+	else
+		atomic_inc(&lru_count);
+
+	list_add_tail(&gl->gl_lru, &lru_list);
+	set_bit(GLF_LRU, &gl->gl_flags);
+	spin_unlock(&lru_lock);
+}
+
+static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
+{
+	spin_lock(&lru_lock);
+	if (!list_empty(&gl->gl_lru)) {
+		list_del_init(&gl->gl_lru);
+		atomic_dec(&lru_count);
+		clear_bit(GLF_LRU, &gl->gl_flags);
+	}
+	spin_unlock(&lru_lock);
+}
+
+/**
+ * __gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
+ * @gl: the glock
+ *
+ * If the glock is demotable, then we add it (or move it) to the end
+ * of the glock LRU list.
+ */
+
+static void __gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
+{
+	if (demote_ok(gl))
+		gfs2_glock_add_to_lru(gl);
+}
+
+/**
+ * gfs2_glock_put_nolock() - Decrement reference count on glock
+ * @gl: The glock to put
+ *
+ * This function should only be used if the caller has its own reference
+ * to the glock, in addition to the one it is dropping.
+ */
+
+void gfs2_glock_put_nolock(struct gfs2_glock *gl)
+{
+	if (atomic_dec_and_test(&gl->gl_ref))
+		GLOCK_BUG_ON(gl, 1);
+}
+
+/**
+ * gfs2_glock_put() - Decrement reference count on glock
+ * @gl: The glock to put
+ *
+ */
+
+void gfs2_glock_put(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct address_space *mapping = gfs2_glock2aspace(gl);
+
+	if (atomic_dec_and_test(&gl->gl_ref)) {
+		spin_lock_bucket(gl->gl_hash);
+		hlist_bl_del_rcu(&gl->gl_list);
+		spin_unlock_bucket(gl->gl_hash);
+		gfs2_glock_remove_from_lru(gl);
+		GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
+		GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
+		trace_gfs2_glock_put(gl);
+		sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
+	}
+}
+
+/**
+ * search_bucket() - Find struct gfs2_glock by lock number
+ * @bucket: the bucket to search
+ * @name: The lock name
+ *
+ * Returns: NULL, or the struct gfs2_glock with the requested number
+ */
+
+static struct gfs2_glock *search_bucket(unsigned int hash,
+					const struct gfs2_sbd *sdp,
+					const struct lm_lockname *name)
+{
+	struct gfs2_glock *gl;
+	struct hlist_bl_node *h;
+
+	hlist_bl_for_each_entry_rcu(gl, h, &gl_hash_table[hash], gl_list) {
+		if (!lm_name_equal(&gl->gl_name, name))
+			continue;
+		if (gl->gl_sbd != sdp)
+			continue;
+		if (atomic_inc_not_zero(&gl->gl_ref))
+			return gl;
+	}
+
+	return NULL;
+}
+
+/**
+ * may_grant - check if its ok to grant a new lock
+ * @gl: The glock
+ * @gh: The lock request which we wish to grant
+ *
+ * Returns: true if its ok to grant the lock
+ */
+
+static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
+{
+	const struct gfs2_holder *gh_head = list_entry(gl->gl_holders.next, const struct gfs2_holder, gh_list);
+	if ((gh->gh_state == LM_ST_EXCLUSIVE ||
+	     gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
+		return 0;
+	if (gl->gl_state == gh->gh_state)
+		return 1;
+	if (gh->gh_flags & GL_EXACT)
+		return 0;
+	if (gl->gl_state == LM_ST_EXCLUSIVE) {
+		if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
+			return 1;
+		if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
+			return 1;
+	}
+	if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
+		return 1;
+	return 0;
+}
+
+static void gfs2_holder_wake(struct gfs2_holder *gh)
+{
+	clear_bit(HIF_WAIT, &gh->gh_iflags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
+}
+
+/**
+ * do_error - Something unexpected has happened during a lock request
+ *
+ */
+
+static inline void do_error(struct gfs2_glock *gl, const int ret)
+{
+	struct gfs2_holder *gh, *tmp;
+
+	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+			continue;
+		if (ret & LM_OUT_ERROR)
+			gh->gh_error = -EIO;
+		else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+			gh->gh_error = GLR_TRYFAILED;
+		else
+			continue;
+		list_del_init(&gh->gh_list);
+		trace_gfs2_glock_queue(gh, 0);
+		gfs2_holder_wake(gh);
+	}
+}
+
+/**
+ * do_promote - promote as many requests as possible on the current queue
+ * @gl: The glock
+ * 
+ * Returns: 1 if there is a blocked holder at the head of the list, or 2
+ *          if a type specific operation is underway.
+ */
+
+static int do_promote(struct gfs2_glock *gl)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
+{
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	struct gfs2_holder *gh, *tmp;
+	int ret;
+
+restart:
+	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+			continue;
+		if (may_grant(gl, gh)) {
+			if (gh->gh_list.prev == &gl->gl_holders &&
+			    glops->go_lock) {
+				spin_unlock(&gl->gl_spin);
+				/* FIXME: eliminate this eventually */
+				ret = glops->go_lock(gh);
+				spin_lock(&gl->gl_spin);
+				if (ret) {
+					if (ret == 1)
+						return 2;
+					gh->gh_error = ret;
+					list_del_init(&gh->gh_list);
+					trace_gfs2_glock_queue(gh, 0);
+					gfs2_holder_wake(gh);
+					goto restart;
+				}
+				set_bit(HIF_HOLDER, &gh->gh_iflags);
+				trace_gfs2_promote(gh, 1);
+				gfs2_holder_wake(gh);
+				goto restart;
+			}
+			set_bit(HIF_HOLDER, &gh->gh_iflags);
+			trace_gfs2_promote(gh, 0);
+			gfs2_holder_wake(gh);
+			continue;
+		}
+		if (gh->gh_list.prev == &gl->gl_holders)
+			return 1;
+		do_error(gl, 0);
+		break;
+	}
+	return 0;
+}
+
+/**
+ * find_first_waiter - find the first gh that's waiting for the glock
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return gh;
+	}
+	return NULL;
+}
+
+/**
+ * state_change - record that the glock is now in a different state
+ * @gl: the glock
+ * @new_state the new state
+ *
+ */
+
+static void state_change(struct gfs2_glock *gl, unsigned int new_state)
+{
+	int held1, held2;
+
+	held1 = (gl->gl_state != LM_ST_UNLOCKED);
+	held2 = (new_state != LM_ST_UNLOCKED);
+
+	if (held1 != held2) {
+		if (held2)
+			gfs2_glock_hold(gl);
+		else
+			gfs2_glock_put_nolock(gl);
+	}
+	if (held1 && held2 && list_empty(&gl->gl_holders))
+		clear_bit(GLF_QUEUED, &gl->gl_flags);
+
+	gl->gl_state = new_state;
+	gl->gl_tchange = jiffies;
+}
+
+static void gfs2_demote_wake(struct gfs2_glock *gl)
+{
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
+	clear_bit(GLF_DEMOTE, &gl->gl_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
+}
+
+/**
+ * finish_xmote - The DLM has replied to one of our lock requests
+ * @gl: The glock
+ * @ret: The status from the DLM
+ *
+ */
+
+static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
+{
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	struct gfs2_holder *gh;
+	unsigned state = ret & LM_OUT_ST_MASK;
+	int rv;
+
+	spin_lock(&gl->gl_spin);
+	trace_gfs2_glock_state_change(gl, state);
+	state_change(gl, state);
+	gh = find_first_waiter(gl);
+
+	/* Demote to UN request arrived during demote to SH or DF */
+	if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
+	    state != LM_ST_UNLOCKED && gl->gl_demote_state == LM_ST_UNLOCKED)
+		gl->gl_target = LM_ST_UNLOCKED;
+
+	/* Check for state != intended state */
+	if (unlikely(state != gl->gl_target)) {
+		if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) {
+			/* move to back of queue and try next entry */
+			if (ret & LM_OUT_CANCELED) {
+				if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
+					list_move_tail(&gh->gh_list, &gl->gl_holders);
+				gh = find_first_waiter(gl);
+				gl->gl_target = gh->gh_state;
+				goto retry;
+			}
+			/* Some error or failed "try lock" - report it */
+			if ((ret & LM_OUT_ERROR) ||
+			    (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
+				gl->gl_target = gl->gl_state;
+				do_error(gl, ret);
+				goto out;
+			}
+		}
+		switch(state) {
+		/* Unlocked due to conversion deadlock, try again */
+		case LM_ST_UNLOCKED:
+retry:
+			do_xmote(gl, gh, gl->gl_target);
+			break;
+		/* Conversion fails, unlock and try again */
+		case LM_ST_SHARED:
+		case LM_ST_DEFERRED:
+			do_xmote(gl, gh, LM_ST_UNLOCKED);
+			break;
+		default: /* Everything else */
+			printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
+			GLOCK_BUG_ON(gl, 1);
+		}
+		spin_unlock(&gl->gl_spin);
+		return;
+	}
+
+	/* Fast path - we got what we asked for */
+	if (test_and_clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
+		gfs2_demote_wake(gl);
+	if (state != LM_ST_UNLOCKED) {
+		if (glops->go_xmote_bh) {
+			spin_unlock(&gl->gl_spin);
+			rv = glops->go_xmote_bh(gl, gh);
+			spin_lock(&gl->gl_spin);
+			if (rv) {
+				do_error(gl, rv);
+				goto out;
+			}
+		}
+		rv = do_promote(gl);
+		if (rv == 2)
+			goto out_locked;
+	}
+out:
+	clear_bit(GLF_LOCK, &gl->gl_flags);
+out_locked:
+	spin_unlock(&gl->gl_spin);
+}
+
+/**
+ * do_xmote - Calls the DLM to change the state of a lock
+ * @gl: The lock state
+ * @gh: The holder (only for promotes)
+ * @target: The target lock state
+ *
+ */
+
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
+{
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	unsigned int lck_flags = gh ? gh->gh_flags : 0;
+	int ret;
+
+	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
+		      LM_FLAG_PRIORITY);
+	GLOCK_BUG_ON(gl, gl->gl_state == target);
+	GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
+	if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
+	    glops->go_inval) {
+		set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+		do_error(gl, 0); /* Fail queued try locks */
+	}
+	gl->gl_req = target;
+	spin_unlock(&gl->gl_spin);
+	if (glops->go_xmote_th)
+		glops->go_xmote_th(gl);
+	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
+		glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
+	clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+
+	gfs2_glock_hold(gl);
+	if (sdp->sd_lockstruct.ls_ops->lm_lock)	{
+		/* lock_dlm */
+		ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
+		GLOCK_BUG_ON(gl, ret);
+	} else { /* lock_nolock */
+		finish_xmote(gl, target);
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gfs2_glock_put(gl);
+	}
+
+	spin_lock(&gl->gl_spin);
+}
+
+/**
+ * find_first_holder - find the first "holder" gh
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	if (!list_empty(&gl->gl_holders)) {
+		gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return gh;
+	}
+	return NULL;
+}
+
+/**
+ * run_queue - do all outstanding tasks related to a glock
+ * @gl: The glock in question
+ * @nonblock: True if we must not block in run_queue
+ *
+ */
+
+static void run_queue(struct gfs2_glock *gl, const int nonblock)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
+{
+	struct gfs2_holder *gh = NULL;
+	int ret;
+
+	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
+		return;
+
+	GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags));
+
+	if (test_bit(GLF_DEMOTE, &gl->gl_flags) &&
+	    gl->gl_demote_state != gl->gl_state) {
+		if (find_first_holder(gl))
+			goto out_unlock;
+		if (nonblock)
+			goto out_sched;
+		set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
+		GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
+		gl->gl_target = gl->gl_demote_state;
+	} else {
+		if (test_bit(GLF_DEMOTE, &gl->gl_flags))
+			gfs2_demote_wake(gl);
+		ret = do_promote(gl);
+		if (ret == 0)
+			goto out_unlock;
+		if (ret == 2)
+			goto out;
+		gh = find_first_waiter(gl);
+		gl->gl_target = gh->gh_state;
+		if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
+			do_error(gl, 0); /* Fail queued try locks */
+	}
+	do_xmote(gl, gh, gl->gl_target);
+out:
+	return;
+
+out_sched:
+	clear_bit(GLF_LOCK, &gl->gl_flags);
+	smp_mb__after_clear_bit();
+	gfs2_glock_hold(gl);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+		gfs2_glock_put_nolock(gl);
+	return;
+
+out_unlock:
+	clear_bit(GLF_LOCK, &gl->gl_flags);
+	smp_mb__after_clear_bit();
+	return;
+}
+
+static void delete_work_func(struct work_struct *work)
+{
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip;
+	struct inode *inode;
+	u64 no_addr = gl->gl_name.ln_number;
+
+	ip = gl->gl_object;
+	/* Note: Unsafe to dereference ip as we don't hold right refs/locks */
+
+	if (ip)
+		inode = gfs2_ilookup(sdp->sd_vfs, no_addr, 1);
+	else
+		inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED);
+	if (inode && !IS_ERR(inode)) {
+		d_prune_aliases(inode);
+		iput(inode);
+	}
+	gfs2_glock_put(gl);
+}
+
+static void glock_work_func(struct work_struct *work)
+{
+	unsigned long delay = 0;
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+	int drop_ref = 0;
+
+	if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) {
+		finish_xmote(gl, gl->gl_reply);
+		drop_ref = 1;
+	}
+	spin_lock(&gl->gl_spin);
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	    gl->gl_state != LM_ST_UNLOCKED &&
+	    gl->gl_demote_state != LM_ST_EXCLUSIVE) {
+		unsigned long holdtime, now = jiffies;
+
+		holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+		if (time_before(now, holdtime))
+			delay = holdtime - now;
+
+		if (!delay) {
+			clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
+			set_bit(GLF_DEMOTE, &gl->gl_flags);
+		}
+	}
+	run_queue(gl, 0);
+	spin_unlock(&gl->gl_spin);
+	if (!delay ||
+	    queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
+	if (drop_ref)
+		gfs2_glock_put(gl);
+}
+
+/**
+ * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
+ * @sdp: The GFS2 superblock
+ * @number: the lock number
+ * @glops: The glock_operations to use
+ * @create: If 0, don't create the glock if it doesn't exist
+ * @glp: the glock is returned here
+ *
+ * This does not lock a glock, just finds/creates structures for one.
+ *
+ * Returns: errno
+ */
+
+int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
+		   const struct gfs2_glock_operations *glops, int create,
+		   struct gfs2_glock **glp)
+{
+	struct super_block *s = sdp->sd_vfs;
+	struct lm_lockname name = { .ln_number = number, .ln_type = glops->go_type };
+	struct gfs2_glock *gl, *tmp;
+	unsigned int hash = gl_hash(sdp, &name);
+	struct address_space *mapping;
+	struct kmem_cache *cachep;
+
+	rcu_read_lock();
+	gl = search_bucket(hash, sdp, &name);
+	rcu_read_unlock();
+
+	*glp = gl;
+	if (gl)
+		return 0;
+	if (!create)
+		return -ENOENT;
+
+	if (glops->go_flags & GLOF_ASPACE)
+		cachep = gfs2_glock_aspace_cachep;
+	else
+		cachep = gfs2_glock_cachep;
+	gl = kmem_cache_alloc(cachep, GFP_KERNEL);
+	if (!gl)
+		return -ENOMEM;
+
+	atomic_inc(&sdp->sd_glock_disposal);
+	gl->gl_flags = 0;
+	gl->gl_name = name;
+	atomic_set(&gl->gl_ref, 1);
+	gl->gl_state = LM_ST_UNLOCKED;
+	gl->gl_target = LM_ST_UNLOCKED;
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
+	gl->gl_hash = hash;
+	gl->gl_ops = glops;
+	snprintf(gl->gl_strname, GDLM_STRNAME_BYTES, "%8x%16llx", name.ln_type, (unsigned long long)number);
+	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
+	gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
+	gl->gl_tchange = jiffies;
+	gl->gl_object = NULL;
+	gl->gl_sbd = sdp;
+	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
+	INIT_WORK(&gl->gl_delete, delete_work_func);
+
+	mapping = gfs2_glock2aspace(gl);
+	if (mapping) {
+                mapping->a_ops = &gfs2_meta_aops;
+		mapping->host = s->s_bdev->bd_inode;
+		mapping->flags = 0;
+		mapping_set_gfp_mask(mapping, GFP_NOFS);
+		mapping->assoc_mapping = NULL;
+		mapping->backing_dev_info = s->s_bdi;
+		mapping->writeback_index = 0;
+	}
+
+	spin_lock_bucket(hash);
+	tmp = search_bucket(hash, sdp, &name);
+	if (tmp) {
+		spin_unlock_bucket(hash);
+		kmem_cache_free(cachep, gl);
+		atomic_dec(&sdp->sd_glock_disposal);
+		gl = tmp;
+	} else {
+		hlist_bl_add_head_rcu(&gl->gl_list, &gl_hash_table[hash]);
+		spin_unlock_bucket(hash);
+	}
+
+	*glp = gl;
+
+	return 0;
+}
+
+/**
+ * gfs2_holder_init - initialize a struct gfs2_holder in the default way
+ * @gl: the glock
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ */
+
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+		      struct gfs2_holder *gh)
+{
+	INIT_LIST_HEAD(&gh->gh_list);
+	gh->gh_gl = gl;
+	gh->gh_ip = (unsigned long)__builtin_return_address(0);
+	gh->gh_owner_pid = get_pid(task_pid(current));
+	gh->gh_state = state;
+	gh->gh_flags = flags;
+	gh->gh_error = 0;
+	gh->gh_iflags = 0;
+	gfs2_glock_hold(gl);
+}
+
+/**
+ * gfs2_holder_reinit - reinitialize a struct gfs2_holder so we can requeue it
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ * Don't mess with the glock.
+ *
+ */
+
+void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
+{
+	gh->gh_state = state;
+	gh->gh_flags = flags;
+	gh->gh_iflags = 0;
+	gh->gh_ip = (unsigned long)__builtin_return_address(0);
+	if (gh->gh_owner_pid)
+		put_pid(gh->gh_owner_pid);
+	gh->gh_owner_pid = get_pid(task_pid(current));
+}
+
+/**
+ * gfs2_holder_uninit - uninitialize a holder structure (drop glock reference)
+ * @gh: the holder structure
+ *
+ */
+
+void gfs2_holder_uninit(struct gfs2_holder *gh)
+{
+	put_pid(gh->gh_owner_pid);
+	gfs2_glock_put(gh->gh_gl);
+	gh->gh_gl = NULL;
+	gh->gh_ip = 0;
+}
+
+/**
+ * gfs2_glock_holder_wait
+ * @word: unused
+ *
+ * This function and gfs2_glock_demote_wait both show up in the WCHAN
+ * field. Thus I've separated these otherwise identical functions in
+ * order to be more informative to the user.
+ */
+
+static int gfs2_glock_holder_wait(void *word)
+{
+        schedule();
+        return 0;
+}
+
+static int gfs2_glock_demote_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+static void wait_on_holder(struct gfs2_holder *gh)
+{
+	might_sleep();
+	wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE);
+}
+
+static void wait_on_demote(struct gfs2_glock *gl)
+{
+	might_sleep();
+	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE);
+}
+
+/**
+ * handle_callback - process a demote request
+ * @gl: the glock
+ * @state: the state the caller wants us to change to
+ *
+ * There are only two requests that we are going to see in actual
+ * practise: LM_ST_SHARED and LM_ST_UNLOCKED
+ */
+
+static void handle_callback(struct gfs2_glock *gl, unsigned int state,
+			    unsigned long delay)
+{
+	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
+
+	set_bit(bit, &gl->gl_flags);
+	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
+		gl->gl_demote_state = state;
+		gl->gl_demote_time = jiffies;
+	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
+			gl->gl_demote_state != state) {
+		gl->gl_demote_state = LM_ST_UNLOCKED;
+	}
+	if (gl->gl_ops->go_callback)
+		gl->gl_ops->go_callback(gl);
+	trace_gfs2_demote_rq(gl);
+}
+
+/**
+ * gfs2_glock_wait - wait on a glock acquisition
+ * @gh: the glock holder
+ *
+ * Returns: 0 on success
+ */
+
+int gfs2_glock_wait(struct gfs2_holder *gh)
+{
+	wait_on_holder(gh);
+	return gh->gh_error;
+}
+
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	if (seq) {
+		struct gfs2_glock_iter *gi = seq->private;
+		vsprintf(gi->string, fmt, args);
+		seq_printf(seq, gi->string);
+	} else {
+		vaf.fmt = fmt;
+		vaf.va = &args;
+
+		printk(KERN_ERR " %pV", &vaf);
+	}
+
+	va_end(args);
+}
+
+/**
+ * add_to_queue - Add a holder to the wait queue (but look for recursion)
+ * @gh: the holder structure to add
+ *
+ * Eventually we should move the recursive locking trap to a
+ * debugging option or something like that. This is the fast
+ * path and needs to have the minimum number of distractions.
+ * 
+ */
+
+static inline void add_to_queue(struct gfs2_holder *gh)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct list_head *insert_pt = NULL;
+	struct gfs2_holder *gh2;
+	int try_lock = 0;
+
+	BUG_ON(gh->gh_owner_pid == NULL);
+	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
+		BUG();
+
+	if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
+		if (test_bit(GLF_LOCK, &gl->gl_flags))
+			try_lock = 1;
+		if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
+			goto fail;
+	}
+
+	list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
+		if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
+		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
+			goto trap_recursive;
+		if (try_lock &&
+		    !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) &&
+		    !may_grant(gl, gh)) {
+fail:
+			gh->gh_error = GLR_TRYFAILED;
+			gfs2_holder_wake(gh);
+			return;
+		}
+		if (test_bit(HIF_HOLDER, &gh2->gh_iflags))
+			continue;
+		if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
+			insert_pt = &gh2->gh_list;
+	}
+	set_bit(GLF_QUEUED, &gl->gl_flags);
+	trace_gfs2_glock_queue(gh, 1);
+	if (likely(insert_pt == NULL)) {
+		list_add_tail(&gh->gh_list, &gl->gl_holders);
+		if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
+			goto do_cancel;
+		return;
+	}
+	list_add_tail(&gh->gh_list, insert_pt);
+do_cancel:
+	gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+	if (!(gh->gh_flags & LM_FLAG_PRIORITY)) {
+		spin_unlock(&gl->gl_spin);
+		if (sdp->sd_lockstruct.ls_ops->lm_cancel)
+			sdp->sd_lockstruct.ls_ops->lm_cancel(gl);
+		spin_lock(&gl->gl_spin);
+	}
+	return;
+
+trap_recursive:
+	print_symbol(KERN_ERR "original: %s\n", gh2->gh_ip);
+	printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
+	printk(KERN_ERR "lock type: %d req lock state : %d\n",
+	       gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
+	print_symbol(KERN_ERR "new: %s\n", gh->gh_ip);
+	printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
+	printk(KERN_ERR "lock type: %d req lock state : %d\n",
+	       gh->gh_gl->gl_name.ln_type, gh->gh_state);
+	__dump_glock(NULL, gl);
+	BUG();
+}
+
+/**
+ * gfs2_glock_nq - enqueue a struct gfs2_holder onto a glock (acquire a glock)
+ * @gh: the holder structure
+ *
+ * if (gh->gh_flags & GL_ASYNC), this never returns an error
+ *
+ * Returns: 0, GLR_TRYFAILED, or errno on failure
+ */
+
+int gfs2_glock_nq(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	int error = 0;
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	if (test_bit(GLF_LRU, &gl->gl_flags))
+		gfs2_glock_remove_from_lru(gl);
+
+	spin_lock(&gl->gl_spin);
+	add_to_queue(gh);
+	if ((LM_FLAG_NOEXP & gh->gh_flags) &&
+	    test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+		set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+	run_queue(gl, 1);
+	spin_unlock(&gl->gl_spin);
+
+	if (!(gh->gh_flags & GL_ASYNC))
+		error = gfs2_glock_wait(gh);
+
+	return error;
+}
+
+/**
+ * gfs2_glock_poll - poll to see if an async request has been completed
+ * @gh: the holder
+ *
+ * Returns: 1 if the request is ready to be gfs2_glock_wait()ed on
+ */
+
+int gfs2_glock_poll(struct gfs2_holder *gh)
+{
+	return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
+}
+
+/**
+ * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
+ * @gh: the glock holder
+ *
+ */
+
+void gfs2_glock_dq(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	unsigned delay = 0;
+	int fast_path = 0;
+
+	spin_lock(&gl->gl_spin);
+	if (gh->gh_flags & GL_NOCACHE)
+		handle_callback(gl, LM_ST_UNLOCKED, 0);
+
+	list_del_init(&gh->gh_list);
+	if (find_first_holder(gl) == NULL) {
+		if (glops->go_unlock) {
+			GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags));
+			spin_unlock(&gl->gl_spin);
+			glops->go_unlock(gh);
+			spin_lock(&gl->gl_spin);
+			clear_bit(GLF_LOCK, &gl->gl_flags);
+		}
+		if (list_empty(&gl->gl_holders) &&
+		    !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+		    !test_bit(GLF_DEMOTE, &gl->gl_flags))
+			fast_path = 1;
+	}
+	if (!test_bit(GLF_LFLUSH, &gl->gl_flags))
+		__gfs2_glock_schedule_for_reclaim(gl);
+	trace_gfs2_glock_queue(gh, 0);
+	spin_unlock(&gl->gl_spin);
+	if (likely(fast_path))
+		return;
+
+	gfs2_glock_hold(gl);
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
+}
+
+void gfs2_glock_dq_wait(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	gfs2_glock_dq(gh);
+	wait_on_demote(gl);
+}
+
+/**
+ * gfs2_glock_dq_uninit - dequeue a holder from a glock and initialize it
+ * @gh: the holder structure
+ *
+ */
+
+void gfs2_glock_dq_uninit(struct gfs2_holder *gh)
+{
+	gfs2_glock_dq(gh);
+	gfs2_holder_uninit(gh);
+}
+
+/**
+ * gfs2_glock_nq_num - acquire a glock based on lock number
+ * @sdp: the filesystem
+ * @number: the lock number
+ * @glops: the glock operations for the type of glock
+ * @state: the state to acquire the glock in
+ * @flags: modifier flags for the acquisition
+ * @gh: the struct gfs2_holder
+ *
+ * Returns: errno
+ */
+
+int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
+		      const struct gfs2_glock_operations *glops,
+		      unsigned int state, int flags, struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl;
+	int error;
+
+	error = gfs2_glock_get(sdp, number, glops, CREATE, &gl);
+	if (!error) {
+		error = gfs2_glock_nq_init(gl, state, flags, gh);
+		gfs2_glock_put(gl);
+	}
+
+	return error;
+}
+
+/**
+ * glock_compare - Compare two struct gfs2_glock structures for sorting
+ * @arg_a: the first structure
+ * @arg_b: the second structure
+ *
+ */
+
+static int glock_compare(const void *arg_a, const void *arg_b)
+{
+	const struct gfs2_holder *gh_a = *(const struct gfs2_holder **)arg_a;
+	const struct gfs2_holder *gh_b = *(const struct gfs2_holder **)arg_b;
+	const struct lm_lockname *a = &gh_a->gh_gl->gl_name;
+	const struct lm_lockname *b = &gh_b->gh_gl->gl_name;
+
+	if (a->ln_number > b->ln_number)
+		return 1;
+	if (a->ln_number < b->ln_number)
+		return -1;
+	BUG_ON(gh_a->gh_gl->gl_ops->go_type == gh_b->gh_gl->gl_ops->go_type);
+	return 0;
+}
+
+/**
+ * nq_m_sync - synchonously acquire more than one glock in deadlock free order
+ * @num_gh: the number of structures
+ * @ghs: an array of struct gfs2_holder structures
+ *
+ * Returns: 0 on success (all glocks acquired),
+ *          errno on failure (no glocks acquired)
+ */
+
+static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs,
+		     struct gfs2_holder **p)
+{
+	unsigned int x;
+	int error = 0;
+
+	for (x = 0; x < num_gh; x++)
+		p[x] = &ghs[x];
+
+	sort(p, num_gh, sizeof(struct gfs2_holder *), glock_compare, NULL);
+
+	for (x = 0; x < num_gh; x++) {
+		p[x]->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);
+
+		error = gfs2_glock_nq(p[x]);
+		if (error) {
+			while (x--)
+				gfs2_glock_dq(p[x]);
+			break;
+		}
+	}
+
+	return error;
+}
+
+/**
+ * gfs2_glock_nq_m - acquire multiple glocks
+ * @num_gh: the number of structures
+ * @ghs: an array of struct gfs2_holder structures
+ *
+ *
+ * Returns: 0 on success (all glocks acquired),
+ *          errno on failure (no glocks acquired)
+ */
+
+int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
+{
+	struct gfs2_holder *tmp[4];
+	struct gfs2_holder **pph = tmp;
+	int error = 0;
+
+	switch(num_gh) {
+	case 0:
+		return 0;
+	case 1:
+		ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);
+		return gfs2_glock_nq(ghs);
+	default:
+		if (num_gh <= 4)
+			break;
+		pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS);
+		if (!pph)
+			return -ENOMEM;
+	}
+
+	error = nq_m_sync(num_gh, ghs, pph);
+
+	if (pph != tmp)
+		kfree(pph);
+
+	return error;
+}
+
+/**
+ * gfs2_glock_dq_m - release multiple glocks
+ * @num_gh: the number of structures
+ * @ghs: an array of struct gfs2_holder structures
+ *
+ */
+
+void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
+{
+	while (num_gh--)
+		gfs2_glock_dq(&ghs[num_gh]);
+}
+
+/**
+ * gfs2_glock_dq_uninit_m - release multiple glocks
+ * @num_gh: the number of structures
+ * @ghs: an array of struct gfs2_holder structures
+ *
+ */
+
+void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
+{
+	while (num_gh--)
+		gfs2_glock_dq_uninit(&ghs[num_gh]);
+}
+
+void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
+{
+	unsigned long delay = 0;
+	unsigned long holdtime;
+	unsigned long now = jiffies;
+
+	gfs2_glock_hold(gl);
+	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+	if (test_bit(GLF_QUEUED, &gl->gl_flags)) {
+		if (time_before(now, holdtime))
+			delay = holdtime - now;
+		if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+			delay = gl->gl_ops->go_min_hold_time;
+	}
+
+	spin_lock(&gl->gl_spin);
+	handle_callback(gl, state, delay);
+	spin_unlock(&gl->gl_spin);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
+}
+
+/**
+ * gfs2_should_freeze - Figure out if glock should be frozen
+ * @gl: The glock in question
+ *
+ * Glocks are not frozen if (a) the result of the dlm operation is
+ * an error, (b) the locking operation was an unlock operation or
+ * (c) if there is a "noexp" flagged request anywhere in the queue
+ *
+ * Returns: 1 if freezing should occur, 0 otherwise
+ */
+
+static int gfs2_should_freeze(const struct gfs2_glock *gl)
+{
+	const struct gfs2_holder *gh;
+
+	if (gl->gl_reply & ~LM_OUT_ST_MASK)
+		return 0;
+	if (gl->gl_target == LM_ST_UNLOCKED)
+		return 0;
+
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+			continue;
+		if (LM_FLAG_NOEXP & gh->gh_flags)
+			return 0;
+	}
+
+	return 1;
+}
+
+/**
+ * gfs2_glock_complete - Callback used by locking
+ * @gl: Pointer to the glock
+ * @ret: The return value from the dlm
+ *
+ * The gl_reply field is under the gl_spin lock so that it is ok
+ * to use a bitfield shared with other glock state fields.
+ */
+
+void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
+{
+	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+
+	spin_lock(&gl->gl_spin);
+	gl->gl_reply = ret;
+
+	if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))) {
+		if (gfs2_should_freeze(gl)) {
+			set_bit(GLF_FROZEN, &gl->gl_flags);
+			spin_unlock(&gl->gl_spin);
+			return;
+		}
+	}
+
+	spin_unlock(&gl->gl_spin);
+	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+	smp_wmb();
+	gfs2_glock_hold(gl);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+		gfs2_glock_put(gl);
+}
+
+
+static int gfs2_shrink_glock_memory(struct shrinker *shrink,
+				    struct shrink_control *sc)
+{
+	struct gfs2_glock *gl;
+	int may_demote;
+	int nr_skipped = 0;
+	int nr = sc->nr_to_scan;
+	gfp_t gfp_mask = sc->gfp_mask;
+	LIST_HEAD(skipped);
+
+	if (nr == 0)
+		goto out;
+
+	if (!(gfp_mask & __GFP_FS))
+		return -1;
+
+	spin_lock(&lru_lock);
+	while(nr && !list_empty(&lru_list)) {
+		gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
+		list_del_init(&gl->gl_lru);
+		clear_bit(GLF_LRU, &gl->gl_flags);
+		atomic_dec(&lru_count);
+
+		/* Test for being demotable */
+		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+			gfs2_glock_hold(gl);
+			spin_unlock(&lru_lock);
+			spin_lock(&gl->gl_spin);
+			may_demote = demote_ok(gl);
+			if (may_demote) {
+				handle_callback(gl, LM_ST_UNLOCKED, 0);
+				nr--;
+			}
+			clear_bit(GLF_LOCK, &gl->gl_flags);
+			smp_mb__after_clear_bit();
+			if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+				gfs2_glock_put_nolock(gl);
+			spin_unlock(&gl->gl_spin);
+			spin_lock(&lru_lock);
+			continue;
+		}
+		nr_skipped++;
+		list_add(&gl->gl_lru, &skipped);
+		set_bit(GLF_LRU, &gl->gl_flags);
+	}
+	list_splice(&skipped, &lru_list);
+	atomic_add(nr_skipped, &lru_count);
+	spin_unlock(&lru_lock);
+out:
+	return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
+}
+
+static struct shrinker glock_shrinker = {
+	.shrink = gfs2_shrink_glock_memory,
+	.seeks = DEFAULT_SEEKS,
+};
+
+/**
+ * examine_bucket - Call a function for glock in a hash bucket
+ * @examiner: the function
+ * @sdp: the filesystem
+ * @bucket: the bucket
+ *
+ */
+
+static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp,
+			  unsigned int hash)
+{
+	struct gfs2_glock *gl;
+	struct hlist_bl_head *head = &gl_hash_table[hash];
+	struct hlist_bl_node *pos;
+
+	rcu_read_lock();
+	hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) {
+		if ((gl->gl_sbd == sdp) && atomic_read(&gl->gl_ref))
+			examiner(gl);
+	}
+	rcu_read_unlock();
+	cond_resched();
+}
+
+static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
+{
+	unsigned x;
+
+	for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+		examine_bucket(examiner, sdp, x);
+}
+
+
+/**
+ * thaw_glock - thaw out a glock which has an unprocessed reply waiting
+ * @gl: The glock to thaw
+ *
+ * N.B. When we freeze a glock, we leave a ref to the glock outstanding,
+ * so this has to result in the ref count being dropped by one.
+ */
+
+static void thaw_glock(struct gfs2_glock *gl)
+{
+	if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+		return;
+	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+	gfs2_glock_hold(gl);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+		gfs2_glock_put(gl);
+}
+
+/**
+ * clear_glock - look at a glock and see if we can free it from glock cache
+ * @gl: the glock to look at
+ *
+ */
+
+static void clear_glock(struct gfs2_glock *gl)
+{
+	gfs2_glock_remove_from_lru(gl);
+
+	spin_lock(&gl->gl_spin);
+	if (gl->gl_state != LM_ST_UNLOCKED)
+		handle_callback(gl, LM_ST_UNLOCKED, 0);
+	spin_unlock(&gl->gl_spin);
+	gfs2_glock_hold(gl);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+		gfs2_glock_put(gl);
+}
+
+/**
+ * gfs2_glock_thaw - Thaw any frozen glocks
+ * @sdp: The super block
+ *
+ */
+
+void gfs2_glock_thaw(struct gfs2_sbd *sdp)
+{
+	glock_hash_walk(thaw_glock, sdp);
+}
+
+static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
+{
+	int ret;
+	spin_lock(&gl->gl_spin);
+	ret = __dump_glock(seq, gl);
+	spin_unlock(&gl->gl_spin);
+	return ret;
+}
+
+static void dump_glock_func(struct gfs2_glock *gl)
+{
+	dump_glock(NULL, gl);
+}
+
+/**
+ * gfs2_gl_hash_clear - Empty out the glock hash table
+ * @sdp: the filesystem
+ * @wait: wait until it's all gone
+ *
+ * Called when unmounting the filesystem.
+ */
+
+void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
+{
+	glock_hash_walk(clear_glock, sdp);
+	flush_workqueue(glock_workqueue);
+	wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
+	glock_hash_walk(dump_glock_func, sdp);
+}
+
+void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
+{
+	struct gfs2_glock *gl = ip->i_gl;
+	int ret;
+
+	ret = gfs2_truncatei_resume(ip);
+	gfs2_assert_withdraw(gl->gl_sbd, ret == 0);
+
+	spin_lock(&gl->gl_spin);
+	clear_bit(GLF_LOCK, &gl->gl_flags);
+	run_queue(gl, 1);
+	spin_unlock(&gl->gl_spin);
+}
+
+static const char *state2str(unsigned state)
+{
+	switch(state) {
+	case LM_ST_UNLOCKED:
+		return "UN";
+	case LM_ST_SHARED:
+		return "SH";
+	case LM_ST_DEFERRED:
+		return "DF";
+	case LM_ST_EXCLUSIVE:
+		return "EX";
+	}
+	return "??";
+}
+
+static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
+{
+	char *p = buf;
+	if (flags & LM_FLAG_TRY)
+		*p++ = 't';
+	if (flags & LM_FLAG_TRY_1CB)
+		*p++ = 'T';
+	if (flags & LM_FLAG_NOEXP)
+		*p++ = 'e';
+	if (flags & LM_FLAG_ANY)
+		*p++ = 'A';
+	if (flags & LM_FLAG_PRIORITY)
+		*p++ = 'p';
+	if (flags & GL_ASYNC)
+		*p++ = 'a';
+	if (flags & GL_EXACT)
+		*p++ = 'E';
+	if (flags & GL_NOCACHE)
+		*p++ = 'c';
+	if (test_bit(HIF_HOLDER, &iflags))
+		*p++ = 'H';
+	if (test_bit(HIF_WAIT, &iflags))
+		*p++ = 'W';
+	if (test_bit(HIF_FIRST, &iflags))
+		*p++ = 'F';
+	*p = 0;
+	return buf;
+}
+
+/**
+ * dump_holder - print information about a glock holder
+ * @seq: the seq_file struct
+ * @gh: the glock holder
+ *
+ * Returns: 0 on success, -ENOBUFS when we run out of space
+ */
+
+static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
+{
+	struct task_struct *gh_owner = NULL;
+	char flags_buf[32];
+
+	if (gh->gh_owner_pid)
+		gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
+	gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
+		       state2str(gh->gh_state),
+		       hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
+		       gh->gh_error,
+		       gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
+		       gh_owner ? gh_owner->comm : "(ended)",
+		       (void *)gh->gh_ip);
+	return 0;
+}
+
+static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
+{
+	const unsigned long *gflags = &gl->gl_flags;
+	char *p = buf;
+
+	if (test_bit(GLF_LOCK, gflags))
+		*p++ = 'l';
+	if (test_bit(GLF_DEMOTE, gflags))
+		*p++ = 'D';
+	if (test_bit(GLF_PENDING_DEMOTE, gflags))
+		*p++ = 'd';
+	if (test_bit(GLF_DEMOTE_IN_PROGRESS, gflags))
+		*p++ = 'p';
+	if (test_bit(GLF_DIRTY, gflags))
+		*p++ = 'y';
+	if (test_bit(GLF_LFLUSH, gflags))
+		*p++ = 'f';
+	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, gflags))
+		*p++ = 'i';
+	if (test_bit(GLF_REPLY_PENDING, gflags))
+		*p++ = 'r';
+	if (test_bit(GLF_INITIAL, gflags))
+		*p++ = 'I';
+	if (test_bit(GLF_FROZEN, gflags))
+		*p++ = 'F';
+	if (test_bit(GLF_QUEUED, gflags))
+		*p++ = 'q';
+	if (test_bit(GLF_LRU, gflags))
+		*p++ = 'L';
+	if (gl->gl_object)
+		*p++ = 'o';
+	*p = 0;
+	return buf;
+}
+
+/**
+ * __dump_glock - print information about a glock
+ * @seq: The seq_file struct
+ * @gl: the glock
+ *
+ * The file format is as follows:
+ * One line per object, capital letters are used to indicate objects
+ * G = glock, I = Inode, R = rgrp, H = holder. Glocks are not indented,
+ * other objects are indented by a single space and follow the glock to
+ * which they are related. Fields are indicated by lower case letters
+ * followed by a colon and the field value, except for strings which are in
+ * [] so that its possible to see if they are composed of spaces for
+ * example. The field's are n = number (id of the object), f = flags,
+ * t = type, s = state, r = refcount, e = error, p = pid.
+ *
+ * Returns: 0 on success, -ENOBUFS when we run out of space
+ */
+
+static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	unsigned long long dtime;
+	const struct gfs2_holder *gh;
+	char gflags_buf[32];
+	int error = 0;
+
+	dtime = jiffies - gl->gl_demote_time;
+	dtime *= 1000000/HZ; /* demote time in uSec */
+	if (!test_bit(GLF_DEMOTE, &gl->gl_flags))
+		dtime = 0;
+	gfs2_print_dbg(seq, "G:  s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d v:%d r:%d\n",
+		  state2str(gl->gl_state),
+		  gl->gl_name.ln_type,
+		  (unsigned long long)gl->gl_name.ln_number,
+		  gflags2str(gflags_buf, gl),
+		  state2str(gl->gl_target),
+		  state2str(gl->gl_demote_state), dtime,
+		  atomic_read(&gl->gl_ail_count),
+		  atomic_read(&gl->gl_revokes),
+		  atomic_read(&gl->gl_ref));
+
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		error = dump_holder(seq, gh);
+		if (error)
+			goto out;
+	}
+	if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump)
+		error = glops->go_dump(seq, gl);
+out:
+	return error;
+}
+
+
+
+
+int __init gfs2_glock_init(void)
+{
+	unsigned i;
+	for(i = 0; i < GFS2_GL_HASH_SIZE; i++) {
+		INIT_HLIST_BL_HEAD(&gl_hash_table[i]);
+	}
+
+	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
+					  WQ_HIGHPRI | WQ_FREEZABLE, 0);
+	if (IS_ERR(glock_workqueue))
+		return PTR_ERR(glock_workqueue);
+	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
+						WQ_MEM_RECLAIM | WQ_FREEZABLE,
+						0);
+	if (IS_ERR(gfs2_delete_workqueue)) {
+		destroy_workqueue(glock_workqueue);
+		return PTR_ERR(gfs2_delete_workqueue);
+	}
+
+	register_shrinker(&glock_shrinker);
+
+	return 0;
+}
+
+void gfs2_glock_exit(void)
+{
+	unregister_shrinker(&glock_shrinker);
+	destroy_workqueue(glock_workqueue);
+	destroy_workqueue(gfs2_delete_workqueue);
+}
+
+static inline struct gfs2_glock *glock_hash_chain(unsigned hash)
+{
+	return hlist_bl_entry(hlist_bl_first_rcu(&gl_hash_table[hash]),
+			      struct gfs2_glock, gl_list);
+}
+
+static inline struct gfs2_glock *glock_hash_next(struct gfs2_glock *gl)
+{
+	return hlist_bl_entry(rcu_dereference(gl->gl_list.next),
+			      struct gfs2_glock, gl_list);
+}
+
+static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
+{
+	struct gfs2_glock *gl;
+
+	do {
+		gl = gi->gl;
+		if (gl) {
+			gi->gl = glock_hash_next(gl);
+		} else {
+			gi->gl = glock_hash_chain(gi->hash);
+		}
+		while (gi->gl == NULL) {
+			gi->hash++;
+			if (gi->hash >= GFS2_GL_HASH_SIZE) {
+				rcu_read_unlock();
+				return 1;
+			}
+			gi->gl = glock_hash_chain(gi->hash);
+		}
+	/* Skip entries for other sb and dead entries */
+	} while (gi->sdp != gi->gl->gl_sbd || atomic_read(&gi->gl->gl_ref) == 0);
+
+	return 0;
+}
+
+static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct gfs2_glock_iter *gi = seq->private;
+	loff_t n = *pos;
+
+	gi->hash = 0;
+	rcu_read_lock();
+
+	do {
+		if (gfs2_glock_iter_next(gi))
+			return NULL;
+	} while (n--);
+
+	return gi->gl;
+}
+
+static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
+				 loff_t *pos)
+{
+	struct gfs2_glock_iter *gi = seq->private;
+
+	(*pos)++;
+
+	if (gfs2_glock_iter_next(gi))
+		return NULL;
+
+	return gi->gl;
+}
+
+static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
+{
+	struct gfs2_glock_iter *gi = seq->private;
+
+	if (gi->gl)
+		rcu_read_unlock();
+	gi->gl = NULL;
+}
+
+static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+	return dump_glock(seq, iter_ptr);
+}
+
+static const struct seq_operations gfs2_glock_seq_ops = {
+	.start = gfs2_glock_seq_start,
+	.next  = gfs2_glock_seq_next,
+	.stop  = gfs2_glock_seq_stop,
+	.show  = gfs2_glock_seq_show,
+};
+
+static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open_private(file, &gfs2_glock_seq_ops,
+				   sizeof(struct gfs2_glock_iter));
+	if (ret == 0) {
+		struct seq_file *seq = file->private_data;
+		struct gfs2_glock_iter *gi = seq->private;
+		gi->sdp = inode->i_private;
+	}
+	return ret;
+}
+
+static const struct file_operations gfs2_debug_fops = {
+	.owner   = THIS_MODULE,
+	.open    = gfs2_debugfs_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private,
+};
+
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
+{
+	sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root);
+	if (!sdp->debugfs_dir)
+		return -ENOMEM;
+	sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
+							 S_IFREG | S_IRUGO,
+							 sdp->debugfs_dir, sdp,
+							 &gfs2_debug_fops);
+	if (!sdp->debugfs_dentry_glocks)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
+{
+	if (sdp && sdp->debugfs_dir) {
+		if (sdp->debugfs_dentry_glocks) {
+			debugfs_remove(sdp->debugfs_dentry_glocks);
+			sdp->debugfs_dentry_glocks = NULL;
+		}
+		debugfs_remove(sdp->debugfs_dir);
+		sdp->debugfs_dir = NULL;
+	}
+}
+
+int gfs2_register_debugfs(void)
+{
+	gfs2_root = debugfs_create_dir("gfs2", NULL);
+	return gfs2_root ? 0 : -ENOMEM;
+}
+
+void gfs2_unregister_debugfs(void)
+{
+	debugfs_remove(gfs2_root);
+	gfs2_root = NULL;
+}
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
new file mode 100644
index 00000000..6b2f757b
--- /dev/null
+++ b/fs/gfs2/glock.h
@@ -0,0 +1,244 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GLOCK_DOT_H__
+#define __GLOCK_DOT_H__
+
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include "incore.h"
+
+/* Options for hostdata parser */
+
+enum {
+	Opt_jid,
+	Opt_id,
+	Opt_first,
+	Opt_nodir,
+	Opt_err,
+};
+
+/*
+ * lm_lockname types
+ */
+
+#define LM_TYPE_RESERVED	0x00
+#define LM_TYPE_NONDISK		0x01
+#define LM_TYPE_INODE		0x02
+#define LM_TYPE_RGRP		0x03
+#define LM_TYPE_META		0x04
+#define LM_TYPE_IOPEN		0x05
+#define LM_TYPE_FLOCK		0x06
+#define LM_TYPE_PLOCK		0x07
+#define LM_TYPE_QUOTA		0x08
+#define LM_TYPE_JOURNAL		0x09
+
+/*
+ * lm_lock() states
+ *
+ * SHARED is compatible with SHARED, not with DEFERRED or EX.
+ * DEFERRED is compatible with DEFERRED, not with SHARED or EX.
+ */
+
+#define LM_ST_UNLOCKED		0
+#define LM_ST_EXCLUSIVE		1
+#define LM_ST_DEFERRED		2
+#define LM_ST_SHARED		3
+
+/*
+ * lm_lock() flags
+ *
+ * LM_FLAG_TRY
+ * Don't wait to acquire the lock if it can't be granted immediately.
+ *
+ * LM_FLAG_TRY_1CB
+ * Send one blocking callback if TRY is set and the lock is not granted.
+ *
+ * LM_FLAG_NOEXP
+ * GFS sets this flag on lock requests it makes while doing journal recovery.
+ * These special requests should not be blocked due to the recovery like
+ * ordinary locks would be.
+ *
+ * LM_FLAG_ANY
+ * A SHARED request may also be granted in DEFERRED, or a DEFERRED request may
+ * also be granted in SHARED.  The preferred state is whichever is compatible
+ * with other granted locks, or the specified state if no other locks exist.
+ *
+ * LM_FLAG_PRIORITY
+ * Override fairness considerations.  Suppose a lock is held in a shared state
+ * and there is a pending request for the deferred state.  A shared lock
+ * request with the priority flag would be allowed to bypass the deferred
+ * request and directly join the other shared lock.  A shared lock request
+ * without the priority flag might be forced to wait until the deferred
+ * requested had acquired and released the lock.
+ */
+
+#define LM_FLAG_TRY		0x00000001
+#define LM_FLAG_TRY_1CB		0x00000002
+#define LM_FLAG_NOEXP		0x00000004
+#define LM_FLAG_ANY		0x00000008
+#define LM_FLAG_PRIORITY	0x00000010
+#define GL_ASYNC		0x00000040
+#define GL_EXACT		0x00000080
+#define GL_SKIP			0x00000100
+#define GL_NOCACHE		0x00000400
+  
+/*
+ * lm_async_cb return flags
+ *
+ * LM_OUT_ST_MASK
+ * Masks the lower two bits of lock state in the returned value.
+ *
+ * LM_OUT_CANCELED
+ * The lock request was canceled.
+ *
+ */
+
+#define LM_OUT_ST_MASK		0x00000003
+#define LM_OUT_CANCELED		0x00000008
+#define LM_OUT_ERROR		0x00000004
+
+/*
+ * lm_recovery_done() messages
+ */
+
+#define LM_RD_GAVEUP		308
+#define LM_RD_SUCCESS		309
+
+#define GLR_TRYFAILED		13
+
+struct lm_lockops {
+	const char *lm_proto_name;
+	int (*lm_mount) (struct gfs2_sbd *sdp, const char *fsname);
+ 	void (*lm_unmount) (struct gfs2_sbd *sdp);
+	void (*lm_withdraw) (struct gfs2_sbd *sdp);
+	void (*lm_put_lock) (struct gfs2_glock *gl);
+	int (*lm_lock) (struct gfs2_glock *gl, unsigned int req_state,
+			unsigned int flags);
+	void (*lm_cancel) (struct gfs2_glock *gl);
+	const match_table_t *lm_tokens;
+};
+
+extern struct workqueue_struct *gfs2_delete_workqueue;
+static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+	struct pid *pid;
+
+	/* Look in glock's list of holders for one with current task as owner */
+	spin_lock(&gl->gl_spin);
+	pid = task_pid(current);
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			break;
+		if (gh->gh_owner_pid == pid)
+			goto out;
+	}
+	gh = NULL;
+out:
+	spin_unlock(&gl->gl_spin);
+
+	return gh;
+}
+
+static inline int gfs2_glock_is_held_excl(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_EXCLUSIVE;
+}
+
+static inline int gfs2_glock_is_held_dfrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_DEFERRED;
+}
+
+static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_SHARED;
+}
+
+static inline struct address_space *gfs2_glock2aspace(struct gfs2_glock *gl)
+{
+	if (gl->gl_ops->go_flags & GLOF_ASPACE)
+		return (struct address_space *)(gl + 1);
+	return NULL;
+}
+
+int gfs2_glock_get(struct gfs2_sbd *sdp,
+		   u64 number, const struct gfs2_glock_operations *glops,
+		   int create, struct gfs2_glock **glp);
+void gfs2_glock_hold(struct gfs2_glock *gl);
+void gfs2_glock_put_nolock(struct gfs2_glock *gl);
+void gfs2_glock_put(struct gfs2_glock *gl);
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+		      struct gfs2_holder *gh);
+void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			struct gfs2_holder *gh);
+void gfs2_holder_uninit(struct gfs2_holder *gh);
+int gfs2_glock_nq(struct gfs2_holder *gh);
+int gfs2_glock_poll(struct gfs2_holder *gh);
+int gfs2_glock_wait(struct gfs2_holder *gh);
+void gfs2_glock_dq(struct gfs2_holder *gh);
+void gfs2_glock_dq_wait(struct gfs2_holder *gh);
+
+void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
+int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
+		      u64 number, const struct gfs2_glock_operations *glops,
+		      unsigned int state, int flags, struct gfs2_holder *gh);
+
+int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+
+__attribute__ ((format(printf, 2, 3)))
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
+
+/**
+ * gfs2_glock_nq_init - initialize a holder and enqueue it on a glock
+ * @gl: the glock
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ * Returns: 0, GLR_*, or errno
+ */
+
+static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
+				     unsigned int state, int flags,
+				     struct gfs2_holder *gh)
+{
+	int error;
+
+	gfs2_holder_init(gl, state, flags, gh);
+
+	error = gfs2_glock_nq(gh);
+	if (error)
+		gfs2_holder_uninit(gh);
+
+	return error;
+}
+
+extern void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state);
+extern void gfs2_glock_complete(struct gfs2_glock *gl, int ret);
+extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
+extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip);
+extern void gfs2_glock_thaw(struct gfs2_sbd *sdp);
+extern void gfs2_glock_add_to_lru(struct gfs2_glock *gl);
+extern void gfs2_glock_free(struct gfs2_glock *gl);
+
+extern int __init gfs2_glock_init(void);
+extern void gfs2_glock_exit(void);
+
+extern int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
+extern void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
+extern int gfs2_register_debugfs(void);
+extern void gfs2_unregister_debugfs(void);
+
+extern const struct lm_lockops gfs2_dlm_ops;
+
+#endif /* __GLOCK_DOT_H__ */
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
new file mode 100644
index 00000000..2cca2931
--- /dev/null
+++ b/fs/gfs2/glops.c
@@ -0,0 +1,605 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/posix_acl.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "util.h"
+#include "trans.h"
+
+/**
+ * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
+ * @gl: the glock
+ *
+ * None of the buffers should be dirty, locked, or pinned.
+ */
+
+static void __gfs2_ail_flush(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct list_head *head = &gl->gl_ail_list;
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
+
+	spin_lock(&sdp->sd_ail_lock);
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata,
+				bd_ail_gl_list);
+		bh = bd->bd_bh;
+		gfs2_remove_from_ail(bd);
+		bd->bd_bh = NULL;
+		bh->b_private = NULL;
+		spin_unlock(&sdp->sd_ail_lock);
+
+		bd->bd_blkno = bh->b_blocknr;
+		gfs2_log_lock(sdp);
+		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
+		gfs2_trans_add_revoke(sdp, bd);
+		gfs2_log_unlock(sdp);
+
+		spin_lock(&sdp->sd_ail_lock);
+	}
+	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	spin_unlock(&sdp->sd_ail_lock);
+}
+
+
+static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_trans tr;
+
+	memset(&tr, 0, sizeof(tr));
+	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
+
+	if (!tr.tr_revokes)
+		return;
+
+	/* A shortened, inline version of gfs2_trans_begin() */
+	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
+	tr.tr_ip = (unsigned long)__builtin_return_address(0);
+	INIT_LIST_HEAD(&tr.tr_list_buf);
+	gfs2_log_reserve(sdp, tr.tr_reserved);
+	BUG_ON(current->journal_info);
+	current->journal_info = &tr;
+
+	__gfs2_ail_flush(gl);
+
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL);
+}
+
+void gfs2_ail_flush(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	unsigned int revokes = atomic_read(&gl->gl_ail_count);
+	int ret;
+
+	if (!revokes)
+		return;
+
+	ret = gfs2_trans_begin(sdp, 0, revokes);
+	if (ret)
+		return;
+	__gfs2_ail_flush(gl);
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL);
+}
+
+/**
+ * rgrp_go_sync - sync out the metadata for this glock
+ * @gl: the glock
+ *
+ * Called when demoting or unlocking an EX glock.  We must flush
+ * to disk all dirty buffers/pages relating to this glock, and must not
+ * not return to caller to demote/unlock the glock until I/O is complete.
+ */
+
+static void rgrp_go_sync(struct gfs2_glock *gl)
+{
+	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	int error;
+
+	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
+		return;
+	BUG_ON(gl->gl_state != LM_ST_EXCLUSIVE);
+
+	gfs2_log_flush(gl->gl_sbd, gl);
+	filemap_fdatawrite(metamapping);
+	error = filemap_fdatawait(metamapping);
+        mapping_set_error(metamapping, error);
+	gfs2_ail_empty_gl(gl);
+}
+
+/**
+ * rgrp_go_inval - invalidate the metadata for this glock
+ * @gl: the glock
+ * @flags:
+ *
+ * We never used LM_ST_DEFERRED with resource groups, so that we
+ * should always see the metadata flag set here.
+ *
+ */
+
+static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
+{
+	struct address_space *mapping = gfs2_glock2aspace(gl);
+
+	BUG_ON(!(flags & DIO_METADATA));
+	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
+	truncate_inode_pages(mapping, 0);
+
+	if (gl->gl_object) {
+		struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object;
+		rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+	}
+}
+
+/**
+ * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * @gl: the glock protecting the inode
+ *
+ */
+
+static void inode_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	int error;
+
+	if (ip && !S_ISREG(ip->i_inode.i_mode))
+		ip = NULL;
+	if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+		unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
+		return;
+
+	BUG_ON(gl->gl_state != LM_ST_EXCLUSIVE);
+
+	gfs2_log_flush(gl->gl_sbd, gl);
+	filemap_fdatawrite(metamapping);
+	if (ip) {
+		struct address_space *mapping = ip->i_inode.i_mapping;
+		filemap_fdatawrite(mapping);
+		error = filemap_fdatawait(mapping);
+		mapping_set_error(mapping, error);
+	}
+	error = filemap_fdatawait(metamapping);
+	mapping_set_error(metamapping, error);
+	gfs2_ail_empty_gl(gl);
+	/*
+	 * Writeback of the data mapping may cause the dirty flag to be set
+	 * so we have to clear it again here.
+	 */
+	smp_mb__before_clear_bit();
+	clear_bit(GLF_DIRTY, &gl->gl_flags);
+}
+
+/**
+ * inode_go_inval - prepare a inode glock to be released
+ * @gl: the glock
+ * @flags:
+ * 
+ * Normally we invlidate everything, but if we are moving into
+ * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
+ * can keep hold of the metadata, since it won't have changed.
+ *
+ */
+
+static void inode_go_inval(struct gfs2_glock *gl, int flags)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+
+	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
+
+	if (flags & DIO_METADATA) {
+		struct address_space *mapping = gfs2_glock2aspace(gl);
+		truncate_inode_pages(mapping, 0);
+		if (ip) {
+			set_bit(GIF_INVALID, &ip->i_flags);
+			forget_all_cached_acls(&ip->i_inode);
+		}
+	}
+
+	if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) {
+		gfs2_log_flush(gl->gl_sbd, NULL);
+		gl->gl_sbd->sd_rindex_uptodate = 0;
+	}
+	if (ip && S_ISREG(ip->i_inode.i_mode))
+		truncate_inode_pages(ip->i_inode.i_mapping, 0);
+}
+
+/**
+ * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int inode_go_demote_ok(const struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_holder *gh;
+
+	if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
+		return 0;
+
+	if (!list_empty(&gl->gl_holders)) {
+		gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+		if (gh->gh_list.next != &gl->gl_holders)
+			return 0;
+	}
+
+	return 1;
+}
+
+/**
+ * gfs2_set_nlink - Set the inode's link count based on on-disk info
+ * @inode: The inode in question
+ * @nlink: The link count
+ *
+ * If the link count has hit zero, it must never be raised, whatever the
+ * on-disk inode might say. When new struct inodes are created the link
+ * count is set to 1, so that we can safely use this test even when reading
+ * in on disk information for the first time.
+ */
+
+static void gfs2_set_nlink(struct inode *inode, u32 nlink)
+{
+	/*
+	 * We will need to review setting the nlink count here in the
+	 * light of the forthcoming ro bind mount work. This is a reminder
+	 * to do that.
+	 */
+	if ((inode->i_nlink != nlink) && (inode->i_nlink != 0)) {
+		if (nlink == 0)
+			clear_nlink(inode);
+		else
+			inode->i_nlink = nlink;
+	}
+}
+
+static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
+{
+	const struct gfs2_dinode *str = buf;
+	struct timespec atime;
+	u16 height, depth;
+
+	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
+		goto corrupt;
+	ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
+	ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
+	ip->i_inode.i_rdev = 0;
+	switch (ip->i_inode.i_mode & S_IFMT) {
+	case S_IFBLK:
+	case S_IFCHR:
+		ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
+					   be32_to_cpu(str->di_minor));
+		break;
+	};
+
+	ip->i_inode.i_uid = be32_to_cpu(str->di_uid);
+	ip->i_inode.i_gid = be32_to_cpu(str->di_gid);
+	gfs2_set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink));
+	i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
+	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
+	atime.tv_sec = be64_to_cpu(str->di_atime);
+	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+		ip->i_inode.i_atime = atime;
+	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
+	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
+	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
+	ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
+
+	ip->i_goal = be64_to_cpu(str->di_goal_meta);
+	ip->i_generation = be64_to_cpu(str->di_generation);
+
+	ip->i_diskflags = be32_to_cpu(str->di_flags);
+	gfs2_set_inode_flags(&ip->i_inode);
+	height = be16_to_cpu(str->di_height);
+	if (unlikely(height > GFS2_MAX_META_HEIGHT))
+		goto corrupt;
+	ip->i_height = (u8)height;
+
+	depth = be16_to_cpu(str->di_depth);
+	if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
+		goto corrupt;
+	ip->i_depth = (u8)depth;
+	ip->i_entries = be32_to_cpu(str->di_entries);
+
+	ip->i_eattr = be64_to_cpu(str->di_eattr);
+	if (S_ISREG(ip->i_inode.i_mode))
+		gfs2_set_aops(&ip->i_inode);
+
+	return 0;
+corrupt:
+	gfs2_consist_inode(ip);
+	return -EIO;
+}
+
+/**
+ * gfs2_inode_refresh - Refresh the incore copy of the dinode
+ * @ip: The GFS2 inode
+ *
+ * Returns: errno
+ */
+
+int gfs2_inode_refresh(struct gfs2_inode *ip)
+{
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) {
+		brelse(dibh);
+		return -EIO;
+	}
+
+	error = gfs2_dinode_in(ip, dibh->b_data);
+	brelse(dibh);
+	clear_bit(GIF_INVALID, &ip->i_flags);
+
+	return error;
+}
+
+/**
+ * inode_go_lock - operation done after an inode lock is locked by a process
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int inode_go_lock(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = gl->gl_object;
+	int error = 0;
+
+	if (!ip || (gh->gh_flags & GL_SKIP))
+		return 0;
+
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			return error;
+	}
+
+	if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
+	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
+	    (gh->gh_state == LM_ST_EXCLUSIVE)) {
+		spin_lock(&sdp->sd_trunc_lock);
+		if (list_empty(&ip->i_trunc_list))
+			list_add(&sdp->sd_trunc_list, &ip->i_trunc_list);
+		spin_unlock(&sdp->sd_trunc_lock);
+		wake_up(&sdp->sd_quota_wait);
+		return 1;
+	}
+
+	return error;
+}
+
+/**
+ * inode_go_dump - print information about an inode
+ * @seq: The iterator
+ * @ip: the inode
+ *
+ * Returns: 0 on success, -ENOBUFS when we run out of space
+ */
+
+static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_inode *ip = gl->gl_object;
+	if (ip == NULL)
+		return 0;
+	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n",
+		  (unsigned long long)ip->i_no_formal_ino,
+		  (unsigned long long)ip->i_no_addr,
+		  IF2DT(ip->i_inode.i_mode), ip->i_flags,
+		  (unsigned int)ip->i_diskflags,
+		  (unsigned long long)i_size_read(&ip->i_inode));
+	return 0;
+}
+
+/**
+ * rgrp_go_lock - operation done after an rgrp lock is locked by
+ *    a first holder on this node.
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int rgrp_go_lock(struct gfs2_holder *gh)
+{
+	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
+}
+
+/**
+ * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
+ *    a last holder on this node.
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void rgrp_go_unlock(struct gfs2_holder *gh)
+{
+	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
+}
+
+/**
+ * trans_go_sync - promote/demote the transaction glock
+ * @gl: the glock
+ * @state: the requested state
+ * @flags:
+ *
+ */
+
+static void trans_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_syncfs(sdp);
+		gfs2_log_shutdown(sdp);
+	}
+}
+
+/**
+ * trans_go_xmote_bh - After promoting/demoting the transaction glock
+ * @gl: the glock
+ *
+ */
+
+static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+	struct gfs2_glock *j_gl = ip->i_gl;
+	struct gfs2_log_header_host head;
+	int error;
+
+	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
+
+		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+		if (error)
+			gfs2_consist(sdp);
+		if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
+			gfs2_consist(sdp);
+
+		/*  Initialize some head of the log stuff  */
+		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+			sdp->sd_log_sequence = head.lh_sequence + 1;
+			gfs2_log_pointers_init(sdp, head.lh_blkno);
+		}
+	}
+	return 0;
+}
+
+/**
+ * trans_go_demote_ok
+ * @gl: the glock
+ *
+ * Always returns 0
+ */
+
+static int trans_go_demote_ok(const struct gfs2_glock *gl)
+{
+	return 0;
+}
+
+/**
+ * iopen_go_callback - schedule the dcache entry for the inode to be deleted
+ * @gl: the glock
+ *
+ * gl_spin lock is held while calling this
+ */
+static void iopen_go_callback(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (sdp->sd_vfs->s_flags & MS_RDONLY)
+		return;
+
+	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
+	    gl->gl_state == LM_ST_SHARED && ip) {
+		gfs2_glock_hold(gl);
+		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
+			gfs2_glock_put_nolock(gl);
+	}
+}
+
+const struct gfs2_glock_operations gfs2_meta_glops = {
+	.go_type = LM_TYPE_META,
+};
+
+const struct gfs2_glock_operations gfs2_inode_glops = {
+	.go_xmote_th = inode_go_sync,
+	.go_inval = inode_go_inval,
+	.go_demote_ok = inode_go_demote_ok,
+	.go_lock = inode_go_lock,
+	.go_dump = inode_go_dump,
+	.go_type = LM_TYPE_INODE,
+	.go_min_hold_time = HZ / 5,
+	.go_flags = GLOF_ASPACE,
+};
+
+const struct gfs2_glock_operations gfs2_rgrp_glops = {
+	.go_xmote_th = rgrp_go_sync,
+	.go_inval = rgrp_go_inval,
+	.go_lock = rgrp_go_lock,
+	.go_unlock = rgrp_go_unlock,
+	.go_dump = gfs2_rgrp_dump,
+	.go_type = LM_TYPE_RGRP,
+	.go_min_hold_time = HZ / 5,
+	.go_flags = GLOF_ASPACE,
+};
+
+const struct gfs2_glock_operations gfs2_trans_glops = {
+	.go_xmote_th = trans_go_sync,
+	.go_xmote_bh = trans_go_xmote_bh,
+	.go_demote_ok = trans_go_demote_ok,
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_iopen_glops = {
+	.go_type = LM_TYPE_IOPEN,
+	.go_callback = iopen_go_callback,
+};
+
+const struct gfs2_glock_operations gfs2_flock_glops = {
+	.go_type = LM_TYPE_FLOCK,
+};
+
+const struct gfs2_glock_operations gfs2_nondisk_glops = {
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_quota_glops = {
+	.go_type = LM_TYPE_QUOTA,
+};
+
+const struct gfs2_glock_operations gfs2_journal_glops = {
+	.go_type = LM_TYPE_JOURNAL,
+};
+
+const struct gfs2_glock_operations *gfs2_glops_list[] = {
+	[LM_TYPE_META] = &gfs2_meta_glops,
+	[LM_TYPE_INODE] = &gfs2_inode_glops,
+	[LM_TYPE_RGRP] = &gfs2_rgrp_glops,
+	[LM_TYPE_IOPEN] = &gfs2_iopen_glops,
+	[LM_TYPE_FLOCK] = &gfs2_flock_glops,
+	[LM_TYPE_NONDISK] = &gfs2_nondisk_glops,
+	[LM_TYPE_QUOTA] = &gfs2_quota_glops,
+	[LM_TYPE_JOURNAL] = &gfs2_journal_glops,
+};
+
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
new file mode 100644
index 00000000..6fce409b
--- /dev/null
+++ b/fs/gfs2/glops.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GLOPS_DOT_H__
+#define __GLOPS_DOT_H__
+
+#include "incore.h"
+
+extern const struct gfs2_glock_operations gfs2_meta_glops;
+extern const struct gfs2_glock_operations gfs2_inode_glops;
+extern const struct gfs2_glock_operations gfs2_rgrp_glops;
+extern const struct gfs2_glock_operations gfs2_trans_glops;
+extern const struct gfs2_glock_operations gfs2_iopen_glops;
+extern const struct gfs2_glock_operations gfs2_flock_glops;
+extern const struct gfs2_glock_operations gfs2_nondisk_glops;
+extern const struct gfs2_glock_operations gfs2_quota_glops;
+extern const struct gfs2_glock_operations gfs2_journal_glops;
+extern const struct gfs2_glock_operations *gfs2_glops_list[];
+
+extern void gfs2_ail_flush(struct gfs2_glock *gl);
+
+#endif /* __GLOPS_DOT_H__ */
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
new file mode 100644
index 00000000..81206e70
--- /dev/null
+++ b/fs/gfs2/incore.h
@@ -0,0 +1,686 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __INCORE_DOT_H__
+#define __INCORE_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/workqueue.h>
+#include <linux/dlm.h>
+#include <linux/buffer_head.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <linux/completion.h>
+
+#define DIO_WAIT	0x00000010
+#define DIO_METADATA	0x00000020
+
+struct gfs2_log_operations;
+struct gfs2_log_element;
+struct gfs2_holder;
+struct gfs2_glock;
+struct gfs2_quota_data;
+struct gfs2_trans;
+struct gfs2_ail;
+struct gfs2_jdesc;
+struct gfs2_sbd;
+struct lm_lockops;
+
+typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret);
+
+struct gfs2_log_header_host {
+	u64 lh_sequence;	/* Sequence number of this transaction */
+	u32 lh_flags;		/* GFS2_LOG_HEAD_... */
+	u32 lh_tail;		/* Block number of log tail */
+	u32 lh_blkno;
+	u32 lh_hash;
+};
+
+/*
+ * Structure of operations that are associated with each
+ * type of element in the log.
+ */
+
+struct gfs2_log_operations {
+	void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le);
+	void (*lo_before_commit) (struct gfs2_sbd *sdp);
+	void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai);
+	void (*lo_before_scan) (struct gfs2_jdesc *jd,
+				struct gfs2_log_header_host *head, int pass);
+	int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start,
+				 struct gfs2_log_descriptor *ld, __be64 *ptr,
+				 int pass);
+	void (*lo_after_scan) (struct gfs2_jdesc *jd, int error, int pass);
+	const char *lo_name;
+};
+
+struct gfs2_log_element {
+	struct list_head le_list;
+	const struct gfs2_log_operations *le_ops;
+};
+
+#define GBF_FULL 1
+
+struct gfs2_bitmap {
+	struct buffer_head *bi_bh;
+	char *bi_clone;
+	unsigned long bi_flags;
+	u32 bi_offset;
+	u32 bi_start;
+	u32 bi_len;
+};
+
+struct gfs2_rgrpd {
+	struct list_head rd_list;	/* Link with superblock */
+	struct list_head rd_list_mru;
+	struct gfs2_glock *rd_gl;	/* Glock for this rgrp */
+	u64 rd_addr;			/* grp block disk address */
+	u64 rd_data0;			/* first data location */
+	u32 rd_length;			/* length of rgrp header in fs blocks */
+	u32 rd_data;			/* num of data blocks in rgrp */
+	u32 rd_bitbytes;		/* number of bytes in data bitmaps */
+	u32 rd_free;
+	u32 rd_free_clone;
+	u32 rd_dinodes;
+	u64 rd_igeneration;
+	struct gfs2_bitmap *rd_bits;
+	struct mutex rd_mutex;
+	struct gfs2_log_element rd_le;
+	struct gfs2_sbd *rd_sbd;
+	unsigned int rd_bh_count;
+	u32 rd_last_alloc;
+	u32 rd_flags;
+#define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
+#define GFS2_RDF_UPTODATE	0x20000000 /* rg is up to date */
+#define GFS2_RDF_ERROR		0x40000000 /* error in rg */
+#define GFS2_RDF_MASK		0xf0000000 /* mask for internal flags */
+};
+
+enum gfs2_state_bits {
+	BH_Pinned = BH_PrivateStart,
+	BH_Escaped = BH_PrivateStart + 1,
+};
+
+BUFFER_FNS(Pinned, pinned)
+TAS_BUFFER_FNS(Pinned, pinned)
+BUFFER_FNS(Escaped, escaped)
+TAS_BUFFER_FNS(Escaped, escaped)
+
+struct gfs2_bufdata {
+	struct buffer_head *bd_bh;
+	struct gfs2_glock *bd_gl;
+
+	union {
+		struct list_head list_tr;
+		u64 blkno;
+	} u;
+#define bd_list_tr u.list_tr
+#define bd_blkno u.blkno
+
+	struct gfs2_log_element bd_le;
+
+	struct gfs2_ail *bd_ail;
+	struct list_head bd_ail_st_list;
+	struct list_head bd_ail_gl_list;
+};
+
+/*
+ * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a
+ * prefix of lock_dlm_ gets awkward.
+ */
+
+#define GDLM_STRNAME_BYTES	25
+#define GDLM_LVB_SIZE		32
+
+enum {
+	DFL_BLOCK_LOCKS		= 0,
+};
+
+struct lm_lockname {
+	u64 ln_number;
+	unsigned int ln_type;
+};
+
+#define lm_name_equal(name1, name2) \
+        (((name1)->ln_number == (name2)->ln_number) && \
+         ((name1)->ln_type == (name2)->ln_type))
+
+
+struct gfs2_glock_operations {
+	void (*go_xmote_th) (struct gfs2_glock *gl);
+	int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
+	void (*go_inval) (struct gfs2_glock *gl, int flags);
+	int (*go_demote_ok) (const struct gfs2_glock *gl);
+	int (*go_lock) (struct gfs2_holder *gh);
+	void (*go_unlock) (struct gfs2_holder *gh);
+	int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
+	void (*go_callback) (struct gfs2_glock *gl);
+	const int go_type;
+	const unsigned long go_min_hold_time;
+	const unsigned long go_flags;
+#define GLOF_ASPACE 1
+};
+
+enum {
+	/* States */
+	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
+	HIF_FIRST		= 7,
+	HIF_WAIT		= 10,
+};
+
+struct gfs2_holder {
+	struct list_head gh_list;
+
+	struct gfs2_glock *gh_gl;
+	struct pid *gh_owner_pid;
+	unsigned int gh_state;
+	unsigned gh_flags;
+
+	int gh_error;
+	unsigned long gh_iflags; /* HIF_... */
+	unsigned long gh_ip;
+};
+
+enum {
+	GLF_LOCK			= 1,
+	GLF_DEMOTE			= 3,
+	GLF_PENDING_DEMOTE		= 4,
+	GLF_DEMOTE_IN_PROGRESS		= 5,
+	GLF_DIRTY			= 6,
+	GLF_LFLUSH			= 7,
+	GLF_INVALIDATE_IN_PROGRESS	= 8,
+	GLF_REPLY_PENDING		= 9,
+	GLF_INITIAL			= 10,
+	GLF_FROZEN			= 11,
+	GLF_QUEUED			= 12,
+	GLF_LRU				= 13,
+	GLF_OBJECT			= 14, /* Used only for tracing */
+};
+
+struct gfs2_glock {
+	struct hlist_bl_node gl_list;
+	unsigned long gl_flags;		/* GLF_... */
+	struct lm_lockname gl_name;
+	atomic_t gl_ref;
+
+	spinlock_t gl_spin;
+
+	/* State fields protected by gl_spin */
+	unsigned int gl_state:2,	/* Current state */
+		     gl_target:2,	/* Target state */
+		     gl_demote_state:2,	/* State requested by remote node */
+		     gl_req:2,		/* State in last dlm request */
+		     gl_reply:8;	/* Last reply from the dlm */
+
+	unsigned int gl_hash;
+	unsigned long gl_demote_time; /* time of first demote request */
+	struct list_head gl_holders;
+
+	const struct gfs2_glock_operations *gl_ops;
+	char gl_strname[GDLM_STRNAME_BYTES];
+	struct dlm_lksb gl_lksb;
+	char gl_lvb[32];
+	unsigned long gl_tchange;
+	void *gl_object;
+
+	struct list_head gl_lru;
+
+	struct gfs2_sbd *gl_sbd;
+
+	struct list_head gl_ail_list;
+	atomic_t gl_ail_count;
+	atomic_t gl_revokes;
+	struct delayed_work gl_work;
+	struct work_struct gl_delete;
+	struct rcu_head gl_rcu;
+};
+
+#define GFS2_MIN_LVB_SIZE 32	/* Min size of LVB that gfs2 supports */
+
+struct gfs2_alloc {
+	/* Quota stuff */
+
+	struct gfs2_quota_data *al_qd[2*MAXQUOTAS];
+	struct gfs2_holder al_qd_ghs[2*MAXQUOTAS];
+	unsigned int al_qd_num;
+
+	u32 al_requested; /* Filled in by caller of gfs2_inplace_reserve() */
+	u32 al_alloced; /* Filled in by gfs2_alloc_*() */
+
+	/* Filled in by gfs2_inplace_reserve() */
+
+	unsigned int al_line;
+	char *al_file;
+	struct gfs2_holder al_ri_gh;
+	struct gfs2_holder al_rgd_gh;
+	struct gfs2_rgrpd *al_rgd;
+
+};
+
+enum {
+	GIF_INVALID		= 0,
+	GIF_QD_LOCKED		= 1,
+	GIF_SW_PAGED		= 3,
+};
+
+
+struct gfs2_inode {
+	struct inode i_inode;
+	u64 i_no_addr;
+	u64 i_no_formal_ino;
+	u64 i_generation;
+	u64 i_eattr;
+	unsigned long i_flags;		/* GIF_... */
+	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_holder i_iopen_gh;
+	struct gfs2_holder i_gh; /* for prepare/commit_write only */
+	struct gfs2_alloc *i_alloc;
+	u64 i_goal;	/* goal block for allocations */
+	struct rw_semaphore i_rw_mutex;
+	struct list_head i_trunc_list;
+	u32 i_entries;
+	u32 i_diskflags;
+	u8 i_height;
+	u8 i_depth;
+};
+
+/*
+ * Since i_inode is the first element of struct gfs2_inode,
+ * this is effectively a cast.
+ */
+static inline struct gfs2_inode *GFS2_I(struct inode *inode)
+{
+	return container_of(inode, struct gfs2_inode, i_inode);
+}
+
+static inline struct gfs2_sbd *GFS2_SB(const struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
+struct gfs2_file {
+	struct mutex f_fl_mutex;
+	struct gfs2_holder f_fl_gh;
+};
+
+struct gfs2_revoke_replay {
+	struct list_head rr_list;
+	u64 rr_blkno;
+	unsigned int rr_where;
+};
+
+enum {
+	QDF_USER		= 0,
+	QDF_CHANGE		= 1,
+	QDF_LOCKED		= 2,
+	QDF_REFRESH		= 3,
+};
+
+struct gfs2_quota_data {
+	struct list_head qd_list;
+	struct list_head qd_reclaim;
+
+	atomic_t qd_count;
+
+	u32 qd_id;
+	unsigned long qd_flags;		/* QDF_... */
+
+	s64 qd_change;
+	s64 qd_change_sync;
+
+	unsigned int qd_slot;
+	unsigned int qd_slot_count;
+
+	struct buffer_head *qd_bh;
+	struct gfs2_quota_change *qd_bh_qc;
+	unsigned int qd_bh_count;
+
+	struct gfs2_glock *qd_gl;
+	struct gfs2_quota_lvb qd_qb;
+
+	u64 qd_sync_gen;
+	unsigned long qd_last_warn;
+};
+
+struct gfs2_trans {
+	unsigned long tr_ip;
+
+	unsigned int tr_blocks;
+	unsigned int tr_revokes;
+	unsigned int tr_reserved;
+
+	struct gfs2_holder tr_t_gh;
+
+	int tr_touched;
+
+	unsigned int tr_num_buf;
+	unsigned int tr_num_buf_new;
+	unsigned int tr_num_databuf_new;
+	unsigned int tr_num_buf_rm;
+	unsigned int tr_num_databuf_rm;
+	struct list_head tr_list_buf;
+
+	unsigned int tr_num_revoke;
+	unsigned int tr_num_revoke_rm;
+};
+
+struct gfs2_ail {
+	struct list_head ai_list;
+
+	unsigned int ai_first;
+	struct list_head ai_ail1_list;
+	struct list_head ai_ail2_list;
+};
+
+struct gfs2_journal_extent {
+	struct list_head extent_list;
+
+	unsigned int lblock; /* First logical block */
+	u64 dblock; /* First disk block */
+	u64 blocks;
+};
+
+struct gfs2_jdesc {
+	struct list_head jd_list;
+	struct list_head extent_list;
+	struct work_struct jd_work;
+	struct inode *jd_inode;
+	unsigned long jd_flags;
+#define JDF_RECOVERY 1
+	unsigned int jd_jid;
+	unsigned int jd_blocks;
+};
+
+struct gfs2_statfs_change_host {
+	s64 sc_total;
+	s64 sc_free;
+	s64 sc_dinodes;
+};
+
+#define GFS2_QUOTA_DEFAULT	GFS2_QUOTA_OFF
+#define GFS2_QUOTA_OFF		0
+#define GFS2_QUOTA_ACCOUNT	1
+#define GFS2_QUOTA_ON		2
+
+#define GFS2_DATA_DEFAULT	GFS2_DATA_ORDERED
+#define GFS2_DATA_WRITEBACK	1
+#define GFS2_DATA_ORDERED	2
+
+#define GFS2_ERRORS_DEFAULT     GFS2_ERRORS_WITHDRAW
+#define GFS2_ERRORS_WITHDRAW    0
+#define GFS2_ERRORS_CONTINUE    1 /* place holder for future feature */
+#define GFS2_ERRORS_RO          2 /* place holder for future feature */
+#define GFS2_ERRORS_PANIC       3
+
+struct gfs2_args {
+	char ar_lockproto[GFS2_LOCKNAME_LEN];	/* Name of the Lock Protocol */
+	char ar_locktable[GFS2_LOCKNAME_LEN];	/* Name of the Lock Table */
+	char ar_hostdata[GFS2_LOCKNAME_LEN];	/* Host specific data */
+	unsigned int ar_spectator:1;		/* Don't get a journal */
+	unsigned int ar_localflocks:1;		/* Let the VFS do flock|fcntl */
+	unsigned int ar_debug:1;		/* Oops on errors */
+	unsigned int ar_posix_acl:1;		/* Enable posix acls */
+	unsigned int ar_quota:2;		/* off/account/on */
+	unsigned int ar_suiddir:1;		/* suiddir support */
+	unsigned int ar_data:2;			/* ordered/writeback */
+	unsigned int ar_meta:1;			/* mount metafs */
+	unsigned int ar_discard:1;		/* discard requests */
+	unsigned int ar_errors:2;               /* errors=withdraw | panic */
+	unsigned int ar_nobarrier:1;            /* do not send barriers */
+	int ar_commit;				/* Commit interval */
+	int ar_statfs_quantum;			/* The fast statfs interval */
+	int ar_quota_quantum;			/* The quota interval */
+	int ar_statfs_percent;			/* The % change to force sync */
+};
+
+struct gfs2_tune {
+	spinlock_t gt_spin;
+
+	unsigned int gt_logd_secs;
+
+	unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */
+	unsigned int gt_quota_warn_period; /* Secs between quota warn msgs */
+	unsigned int gt_quota_scale_num; /* Numerator */
+	unsigned int gt_quota_scale_den; /* Denominator */
+	unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
+	unsigned int gt_new_files_jdata;
+	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
+	unsigned int gt_complain_secs;
+	unsigned int gt_statfs_quantum;
+	unsigned int gt_statfs_slow;
+};
+
+enum {
+	SDF_JOURNAL_CHECKED	= 0,
+	SDF_JOURNAL_LIVE	= 1,
+	SDF_SHUTDOWN		= 2,
+	SDF_NOBARRIERS		= 3,
+	SDF_NORECOVERY		= 4,
+	SDF_DEMOTE		= 5,
+	SDF_NOJOURNALID		= 6,
+};
+
+#define GFS2_FSNAME_LEN		256
+
+struct gfs2_inum_host {
+	u64 no_formal_ino;
+	u64 no_addr;
+};
+
+struct gfs2_sb_host {
+	u32 sb_magic;
+	u32 sb_type;
+	u32 sb_format;
+
+	u32 sb_fs_format;
+	u32 sb_multihost_format;
+	u32 sb_bsize;
+	u32 sb_bsize_shift;
+
+	struct gfs2_inum_host sb_master_dir;
+	struct gfs2_inum_host sb_root_dir;
+
+	char sb_lockproto[GFS2_LOCKNAME_LEN];
+	char sb_locktable[GFS2_LOCKNAME_LEN];
+};
+
+/*
+ * lm_mount() return values
+ *
+ * ls_jid - the journal ID this node should use
+ * ls_first - this node is the first to mount the file system
+ * ls_lockspace - lock module's context for this file system
+ * ls_ops - lock module's functions
+ */
+
+struct lm_lockstruct {
+	int ls_jid;
+	unsigned int ls_first;
+	unsigned int ls_first_done;
+	unsigned int ls_nodir;
+	const struct lm_lockops *ls_ops;
+	unsigned long ls_flags;
+	dlm_lockspace_t *ls_dlm;
+
+	int ls_recover_jid_done;
+	int ls_recover_jid_status;
+};
+
+struct gfs2_sbd {
+	struct super_block *sd_vfs;
+	struct kobject sd_kobj;
+	unsigned long sd_flags;	/* SDF_... */
+	struct gfs2_sb_host sd_sb;
+
+	/* Constants computed on mount */
+
+	u32 sd_fsb2bb;
+	u32 sd_fsb2bb_shift;
+	u32 sd_diptrs;	/* Number of pointers in a dinode */
+	u32 sd_inptrs;	/* Number of pointers in a indirect block */
+	u32 sd_jbsize;	/* Size of a journaled data block */
+	u32 sd_hash_bsize;	/* sizeof(exhash block) */
+	u32 sd_hash_bsize_shift;
+	u32 sd_hash_ptrs;	/* Number of pointers in a hash block */
+	u32 sd_qc_per_block;
+	u32 sd_max_dirres;	/* Max blocks needed to add a directory entry */
+	u32 sd_max_height;	/* Max height of a file's metadata tree */
+	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
+	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
+	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
+
+	struct gfs2_args sd_args;	/* Mount arguments */
+	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */
+
+	/* Lock Stuff */
+
+	struct lm_lockstruct sd_lockstruct;
+	struct gfs2_holder sd_live_gh;
+	struct gfs2_glock *sd_rename_gl;
+	struct gfs2_glock *sd_trans_gl;
+	wait_queue_head_t sd_glock_wait;
+	atomic_t sd_glock_disposal;
+	struct completion sd_locking_init;
+
+	/* Inode Stuff */
+
+	struct dentry *sd_master_dir;
+	struct dentry *sd_root_dir;
+
+	struct inode *sd_jindex;
+	struct inode *sd_statfs_inode;
+	struct inode *sd_sc_inode;
+	struct inode *sd_qc_inode;
+	struct inode *sd_rindex;
+	struct inode *sd_quota_inode;
+
+	/* StatFS stuff */
+
+	spinlock_t sd_statfs_spin;
+	struct gfs2_statfs_change_host sd_statfs_master;
+	struct gfs2_statfs_change_host sd_statfs_local;
+	int sd_statfs_force_sync;
+
+	/* Resource group stuff */
+
+	int sd_rindex_uptodate;
+	spinlock_t sd_rindex_spin;
+	struct mutex sd_rindex_mutex;
+	struct list_head sd_rindex_list;
+	struct list_head sd_rindex_mru_list;
+	struct gfs2_rgrpd *sd_rindex_forward;
+	unsigned int sd_rgrps;
+	unsigned int sd_max_rg_data;
+
+	/* Journal index stuff */
+
+	struct list_head sd_jindex_list;
+	spinlock_t sd_jindex_spin;
+	struct mutex sd_jindex_mutex;
+	unsigned int sd_journals;
+
+	struct gfs2_jdesc *sd_jdesc;
+	struct gfs2_holder sd_journal_gh;
+	struct gfs2_holder sd_jinode_gh;
+
+	struct gfs2_holder sd_sc_gh;
+	struct gfs2_holder sd_qc_gh;
+
+	/* Daemon stuff */
+
+	struct task_struct *sd_logd_process;
+	struct task_struct *sd_quotad_process;
+
+	/* Quota stuff */
+
+	struct list_head sd_quota_list;
+	atomic_t sd_quota_count;
+	struct mutex sd_quota_mutex;
+	wait_queue_head_t sd_quota_wait;
+	struct list_head sd_trunc_list;
+	spinlock_t sd_trunc_lock;
+
+	unsigned int sd_quota_slots;
+	unsigned int sd_quota_chunks;
+	unsigned char **sd_quota_bitmap;
+
+	u64 sd_quota_sync_gen;
+
+	/* Log stuff */
+
+	spinlock_t sd_log_lock;
+
+	unsigned int sd_log_blks_reserved;
+	unsigned int sd_log_commited_buf;
+	unsigned int sd_log_commited_databuf;
+	int sd_log_commited_revoke;
+
+	atomic_t sd_log_pinned;
+	unsigned int sd_log_num_buf;
+	unsigned int sd_log_num_revoke;
+	unsigned int sd_log_num_rg;
+	unsigned int sd_log_num_databuf;
+
+	struct list_head sd_log_le_buf;
+	struct list_head sd_log_le_revoke;
+	struct list_head sd_log_le_rg;
+	struct list_head sd_log_le_databuf;
+	struct list_head sd_log_le_ordered;
+
+	atomic_t sd_log_thresh1;
+	atomic_t sd_log_thresh2;
+	atomic_t sd_log_blks_free;
+	wait_queue_head_t sd_log_waitq;
+	wait_queue_head_t sd_logd_waitq;
+
+	u64 sd_log_sequence;
+	unsigned int sd_log_head;
+	unsigned int sd_log_tail;
+	int sd_log_idle;
+
+	struct rw_semaphore sd_log_flush_lock;
+	atomic_t sd_log_in_flight;
+	wait_queue_head_t sd_log_flush_wait;
+
+	unsigned int sd_log_flush_head;
+	u64 sd_log_flush_wrapped;
+
+	spinlock_t sd_ail_lock;
+	struct list_head sd_ail1_list;
+	struct list_head sd_ail2_list;
+
+	/* Replay stuff */
+
+	struct list_head sd_revoke_list;
+	unsigned int sd_replay_tail;
+
+	unsigned int sd_found_blocks;
+	unsigned int sd_found_revokes;
+	unsigned int sd_replayed_blocks;
+
+	/* For quiescing the filesystem */
+
+	struct gfs2_holder sd_freeze_gh;
+	struct mutex sd_freeze_lock;
+	unsigned int sd_freeze_count;
+
+	char sd_fsname[GFS2_FSNAME_LEN];
+	char sd_table_name[GFS2_FSNAME_LEN];
+	char sd_proto_name[GFS2_FSNAME_LEN];
+
+	/* Debugging crud */
+
+	unsigned long sd_last_warning;
+	struct dentry *debugfs_dir;    /* debugfs directory */
+	struct dentry *debugfs_dentry_glocks; /* for debugfs */
+};
+
+#endif /* __INCORE_DOT_H__ */
+
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
new file mode 100644
index 00000000..03e0c529
--- /dev/null
+++ b/fs/gfs2/inode.c
@@ -0,0 +1,1892 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/namei.h>
+#include <linux/mm.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/fiemap.h>
+#include <linux/security.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "bmap.h"
+#include "dir.h"
+#include "xattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "super.h"
+#include "glops.h"
+
+struct gfs2_skip_data {
+	u64 no_addr;
+	int skipped;
+	int non_block;
+};
+
+static int iget_test(struct inode *inode, void *opaque)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_skip_data *data = opaque;
+
+	if (ip->i_no_addr == data->no_addr) {
+		if (data->non_block &&
+		    inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
+			data->skipped = 1;
+			return 0;
+		}
+		return 1;
+	}
+	return 0;
+}
+
+static int iget_set(struct inode *inode, void *opaque)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_skip_data *data = opaque;
+
+	if (data->skipped)
+		return -ENOENT;
+	inode->i_ino = (unsigned long)(data->no_addr);
+	ip->i_no_addr = data->no_addr;
+	return 0;
+}
+
+struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int non_block)
+{
+	unsigned long hash = (unsigned long)no_addr;
+	struct gfs2_skip_data data;
+
+	data.no_addr = no_addr;
+	data.skipped = 0;
+	data.non_block = non_block;
+	return ilookup5(sb, hash, iget_test, &data);
+}
+
+static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr,
+			       int non_block)
+{
+	struct gfs2_skip_data data;
+	unsigned long hash = (unsigned long)no_addr;
+
+	data.no_addr = no_addr;
+	data.skipped = 0;
+	data.non_block = non_block;
+	return iget5_locked(sb, hash, iget_test, iget_set, &data);
+}
+
+/**
+ * gfs2_set_iop - Sets inode operations
+ * @inode: The inode with correct i_mode filled in
+ *
+ * GFS2 lookup code fills in vfs inode contents based on info obtained
+ * from directory entry inside gfs2_inode_lookup().
+ */
+
+static void gfs2_set_iop(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	umode_t mode = inode->i_mode;
+
+	if (S_ISREG(mode)) {
+		inode->i_op = &gfs2_file_iops;
+		if (gfs2_localflocks(sdp))
+			inode->i_fop = &gfs2_file_fops_nolock;
+		else
+			inode->i_fop = &gfs2_file_fops;
+	} else if (S_ISDIR(mode)) {
+		inode->i_op = &gfs2_dir_iops;
+		if (gfs2_localflocks(sdp))
+			inode->i_fop = &gfs2_dir_fops_nolock;
+		else
+			inode->i_fop = &gfs2_dir_fops;
+	} else if (S_ISLNK(mode)) {
+		inode->i_op = &gfs2_symlink_iops;
+	} else {
+		inode->i_op = &gfs2_file_iops;
+		init_special_inode(inode, inode->i_mode, inode->i_rdev);
+	}
+}
+
+/**
+ * gfs2_inode_lookup - Lookup an inode
+ * @sb: The super block
+ * @no_addr: The inode number
+ * @type: The type of the inode
+ * non_block: Can we block on inodes that are being freed?
+ *
+ * Returns: A VFS inode, or an error
+ */
+
+struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
+				u64 no_addr, u64 no_formal_ino, int non_block)
+{
+	struct inode *inode;
+	struct gfs2_inode *ip;
+	struct gfs2_glock *io_gl = NULL;
+	int error;
+
+	inode = gfs2_iget(sb, no_addr, non_block);
+	ip = GFS2_I(inode);
+
+	if (!inode)
+		return ERR_PTR(-ENOBUFS);
+
+	if (inode->i_state & I_NEW) {
+		struct gfs2_sbd *sdp = GFS2_SB(inode);
+		ip->i_no_formal_ino = no_formal_ino;
+
+		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
+		if (unlikely(error))
+			goto fail;
+		ip->i_gl->gl_object = ip;
+
+		error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
+		if (unlikely(error))
+			goto fail_put;
+
+		set_bit(GIF_INVALID, &ip->i_flags);
+		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
+		if (unlikely(error))
+			goto fail_iopen;
+
+		ip->i_iopen_gh.gh_gl->gl_object = ip;
+		gfs2_glock_put(io_gl);
+		io_gl = NULL;
+
+		if (type == DT_UNKNOWN) {
+			/* Inode glock must be locked already */
+			error = gfs2_inode_refresh(GFS2_I(inode));
+			if (error)
+				goto fail_refresh;
+		} else {
+			inode->i_mode = DT2IF(type);
+		}
+
+		gfs2_set_iop(inode);
+		unlock_new_inode(inode);
+	}
+
+	return inode;
+
+fail_refresh:
+	ip->i_iopen_gh.gh_gl->gl_object = NULL;
+	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+fail_iopen:
+	if (io_gl)
+		gfs2_glock_put(io_gl);
+fail_put:
+	ip->i_gl->gl_object = NULL;
+	gfs2_glock_put(ip->i_gl);
+fail:
+	iget_failed(inode);
+	return ERR_PTR(error);
+}
+
+struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
+				  u64 *no_formal_ino, unsigned int blktype)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_holder i_gh;
+	struct inode *inode = NULL;
+	int error;
+
+	/* Must not read in block until block type is verified */
+	error = gfs2_glock_nq_num(sdp, no_addr, &gfs2_inode_glops,
+				  LM_ST_EXCLUSIVE, GL_SKIP, &i_gh);
+	if (error)
+		return ERR_PTR(error);
+
+	error = gfs2_check_blk_type(sdp, no_addr, blktype);
+	if (error)
+		goto fail;
+
+	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, 1);
+	if (IS_ERR(inode))
+		goto fail;
+
+	/* Two extra checks for NFS only */
+	if (no_formal_ino) {
+		error = -ESTALE;
+		if (GFS2_I(inode)->i_no_formal_ino != *no_formal_ino)
+			goto fail_iput;
+
+		error = -EIO;
+		if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM)
+			goto fail_iput;
+
+		error = 0;
+	}
+
+fail:
+	gfs2_glock_dq_uninit(&i_gh);
+	return error ? ERR_PTR(error) : inode;
+fail_iput:
+	iput(inode);
+	goto fail;
+}
+
+
+struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
+{
+	struct qstr qstr;
+	struct inode *inode;
+	gfs2_str2qstr(&qstr, name);
+	inode = gfs2_lookupi(dip, &qstr, 1);
+	/* gfs2_lookupi has inconsistent callers: vfs
+	 * related routines expect NULL for no entry found,
+	 * gfs2_lookup_simple callers expect ENOENT
+	 * and do not check for NULL.
+	 */
+	if (inode == NULL)
+		return ERR_PTR(-ENOENT);
+	else
+		return inode;
+}
+
+
+/**
+ * gfs2_lookupi - Look up a filename in a directory and return its inode
+ * @d_gh: An initialized holder for the directory glock
+ * @name: The name of the inode to look for
+ * @is_root: If 1, ignore the caller's permissions
+ * @i_gh: An uninitialized holder for the new inode glock
+ *
+ * This can be called via the VFS filldir function when NFS is doing
+ * a readdirplus and the inode which its intending to stat isn't
+ * already in cache. In this case we must not take the directory glock
+ * again, since the readdir call will have already taken that lock.
+ *
+ * Returns: errno
+ */
+
+struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+			   int is_root)
+{
+	struct super_block *sb = dir->i_sb;
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_holder d_gh;
+	int error = 0;
+	struct inode *inode = NULL;
+	int unlock = 0;
+
+	if (!name->len || name->len > GFS2_FNAMESIZE)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	if ((name->len == 1 && memcmp(name->name, ".", 1) == 0) ||
+	    (name->len == 2 && memcmp(name->name, "..", 2) == 0 &&
+	     dir == sb->s_root->d_inode)) {
+		igrab(dir);
+		return dir;
+	}
+
+	if (gfs2_glock_is_locked_by_me(dip->i_gl) == NULL) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+		if (error)
+			return ERR_PTR(error);
+		unlock = 1;
+	}
+
+	if (!is_root) {
+		error = gfs2_permission(dir, MAY_EXEC, 0);
+		if (error)
+			goto out;
+	}
+
+	inode = gfs2_dir_search(dir, name);
+	if (IS_ERR(inode))
+		error = PTR_ERR(inode);
+out:
+	if (unlock)
+		gfs2_glock_dq_uninit(&d_gh);
+	if (error == -ENOENT)
+		return NULL;
+	return inode ? inode : ERR_PTR(error);
+}
+
+/**
+ * create_ok - OK to create a new on-disk inode here?
+ * @dip:  Directory in which dinode is to be created
+ * @name:  Name of new dinode
+ * @mode:
+ *
+ * Returns: errno
+ */
+
+static int create_ok(struct gfs2_inode *dip, const struct qstr *name,
+		     unsigned int mode)
+{
+	int error;
+
+	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, 0);
+	if (error)
+		return error;
+
+	/*  Don't create entries in an unlinked directory  */
+	if (!dip->i_inode.i_nlink)
+		return -ENOENT;
+
+	error = gfs2_dir_check(&dip->i_inode, name, NULL);
+	switch (error) {
+	case -ENOENT:
+		error = 0;
+		break;
+	case 0:
+		return -EEXIST;
+	default:
+		return error;
+	}
+
+	if (dip->i_entries == (u32)-1)
+		return -EFBIG;
+	if (S_ISDIR(mode) && dip->i_inode.i_nlink == (u32)-1)
+		return -EMLINK;
+
+	return 0;
+}
+
+static void munge_mode_uid_gid(struct gfs2_inode *dip, unsigned int *mode,
+			       unsigned int *uid, unsigned int *gid)
+{
+	if (GFS2_SB(&dip->i_inode)->sd_args.ar_suiddir &&
+	    (dip->i_inode.i_mode & S_ISUID) && dip->i_inode.i_uid) {
+		if (S_ISDIR(*mode))
+			*mode |= S_ISUID;
+		else if (dip->i_inode.i_uid != current_fsuid())
+			*mode &= ~07111;
+		*uid = dip->i_inode.i_uid;
+	} else
+		*uid = current_fsuid();
+
+	if (dip->i_inode.i_mode & S_ISGID) {
+		if (S_ISDIR(*mode))
+			*mode |= S_ISGID;
+		*gid = dip->i_inode.i_gid;
+	} else
+		*gid = current_fsgid();
+}
+
+static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	int error;
+
+	if (gfs2_alloc_get(dip) == NULL)
+		return -ENOMEM;
+
+	dip->i_alloc->al_requested = RES_DINODE;
+	error = gfs2_inplace_reserve(dip);
+	if (error)
+		goto out;
+
+	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS, 0);
+	if (error)
+		goto out_ipreserv;
+
+	error = gfs2_alloc_di(dip, no_addr, generation);
+
+	gfs2_trans_end(sdp);
+
+out_ipreserv:
+	gfs2_inplace_release(dip);
+out:
+	gfs2_alloc_put(dip);
+	return error;
+}
+
+static void gfs2_init_dir(struct buffer_head *dibh,
+			  const struct gfs2_inode *parent)
+{
+	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+	struct gfs2_dirent *dent = (struct gfs2_dirent *)(di+1);
+
+	gfs2_qstr2dirent(&gfs2_qdot, GFS2_DIRENT_SIZE(gfs2_qdot.len), dent);
+	dent->de_inum = di->di_num; /* already GFS2 endian */
+	dent->de_type = cpu_to_be16(DT_DIR);
+
+	dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1));
+	gfs2_qstr2dirent(&gfs2_qdotdot, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
+	gfs2_inum_out(parent, dent);
+	dent->de_type = cpu_to_be16(DT_DIR);
+	
+}
+
+/**
+ * init_dinode - Fill in a new dinode structure
+ * @dip: The directory this inode is being created in
+ * @gl: The glock covering the new inode
+ * @inum: The inode number
+ * @mode: The file permissions
+ * @uid: The uid of the new inode
+ * @gid: The gid of the new inode
+ * @generation: The generation number of the new inode
+ * @dev: The device number (if a device node)
+ * @symname: The symlink destination (if a symlink)
+ * @size: The inode size (ignored for directories)
+ * @bhp: The buffer head (returned to caller)
+ *
+ */
+
+static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
+			const struct gfs2_inum_host *inum, unsigned int mode,
+			unsigned int uid, unsigned int gid,
+			const u64 *generation, dev_t dev, const char *symname,
+			unsigned size, struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct gfs2_dinode *di;
+	struct buffer_head *dibh;
+	struct timespec tv = CURRENT_TIME;
+
+	dibh = gfs2_meta_new(gl, inum->no_addr);
+	gfs2_trans_add_bh(gl, dibh, 1);
+	gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
+	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
+	di = (struct gfs2_dinode *)dibh->b_data;
+
+	di->di_num.no_formal_ino = cpu_to_be64(inum->no_formal_ino);
+	di->di_num.no_addr = cpu_to_be64(inum->no_addr);
+	di->di_mode = cpu_to_be32(mode);
+	di->di_uid = cpu_to_be32(uid);
+	di->di_gid = cpu_to_be32(gid);
+	di->di_nlink = 0;
+	di->di_size = cpu_to_be64(size);
+	di->di_blocks = cpu_to_be64(1);
+	di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec);
+	di->di_major = cpu_to_be32(MAJOR(dev));
+	di->di_minor = cpu_to_be32(MINOR(dev));
+	di->di_goal_meta = di->di_goal_data = cpu_to_be64(inum->no_addr);
+	di->di_generation = cpu_to_be64(*generation);
+	di->di_flags = 0;
+	di->__pad1 = 0;
+	di->di_payload_format = cpu_to_be32(S_ISDIR(mode) ? GFS2_FORMAT_DE : 0);
+	di->di_height = 0;
+	di->__pad2 = 0;
+	di->__pad3 = 0;
+	di->di_depth = 0;
+	di->di_entries = 0;
+	memset(&di->__pad4, 0, sizeof(di->__pad4));
+	di->di_eattr = 0;
+	di->di_atime_nsec = cpu_to_be32(tv.tv_nsec);
+	di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
+	di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
+	memset(&di->di_reserved, 0, sizeof(di->di_reserved));
+
+	switch(mode & S_IFMT) {	
+	case S_IFREG:
+		if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
+		    gfs2_tune_get(sdp, gt_new_files_jdata))
+			di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
+		break;
+	case S_IFDIR:
+		di->di_flags |= cpu_to_be32(dip->i_diskflags &
+					    GFS2_DIF_INHERIT_JDATA);
+		di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
+		di->di_size = cpu_to_be64(sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
+		di->di_entries = cpu_to_be32(2);
+		gfs2_init_dir(dibh, dip);
+		break;
+	case S_IFLNK:
+		memcpy(dibh->b_data + sizeof(struct gfs2_dinode), symname, size);
+		break;
+	}
+
+	set_buffer_uptodate(dibh);
+
+	*bhp = dibh;
+}
+
+static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
+		       unsigned int mode, const struct gfs2_inum_host *inum,
+		       const u64 *generation, dev_t dev, const char *symname,
+		       unsigned int size, struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	unsigned int uid, gid;
+	int error;
+
+	munge_mode_uid_gid(dip, &mode, &uid, &gid);
+	if (!gfs2_alloc_get(dip))
+		return -ENOMEM;
+
+	error = gfs2_quota_lock(dip, uid, gid);
+	if (error)
+		goto out;
+
+	error = gfs2_quota_check(dip, uid, gid);
+	if (error)
+		goto out_quota;
+
+	error = gfs2_trans_begin(sdp, RES_DINODE + RES_QUOTA, 0);
+	if (error)
+		goto out_quota;
+
+	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, symname, size, bhp);
+	gfs2_quota_change(dip, +1, uid, gid);
+	gfs2_trans_end(sdp);
+
+out_quota:
+	gfs2_quota_unlock(dip);
+out:
+	gfs2_alloc_put(dip);
+	return error;
+}
+
+static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
+		       struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct gfs2_alloc *al;
+	int alloc_required;
+	struct buffer_head *dibh;
+	int error;
+
+	al = gfs2_alloc_get(dip);
+	if (!al)
+		return -ENOMEM;
+
+	error = gfs2_quota_lock(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto fail;
+
+	error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name);
+	if (alloc_required < 0)
+		goto fail_quota_locks;
+	if (alloc_required) {
+		error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid);
+		if (error)
+			goto fail_quota_locks;
+
+		al->al_requested = sdp->sd_max_dirres;
+
+		error = gfs2_inplace_reserve(dip);
+		if (error)
+			goto fail_quota_locks;
+
+		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
+					 al->al_rgd->rd_length +
+					 2 * RES_DINODE +
+					 RES_STATFS + RES_QUOTA, 0);
+		if (error)
+			goto fail_ipreserv;
+	} else {
+		error = gfs2_trans_begin(sdp, RES_LEAF + 2 * RES_DINODE, 0);
+		if (error)
+			goto fail_quota_locks;
+	}
+
+	error = gfs2_dir_add(&dip->i_inode, name, ip);
+	if (error)
+		goto fail_end_trans;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto fail_end_trans;
+	inc_nlink(&ip->i_inode);
+	if (S_ISDIR(ip->i_inode.i_mode))
+		inc_nlink(&ip->i_inode);
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+	return 0;
+
+fail_end_trans:
+	gfs2_trans_end(sdp);
+
+fail_ipreserv:
+	if (dip->i_alloc->al_rgd)
+		gfs2_inplace_release(dip);
+
+fail_quota_locks:
+	gfs2_quota_unlock(dip);
+
+fail:
+	gfs2_alloc_put(dip);
+	return error;
+}
+
+static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
+			      const struct qstr *qstr)
+{
+	int err;
+	size_t len;
+	void *value;
+	char *name;
+
+	err = security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
+					   &name, &value, &len);
+
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	err = __gfs2_xattr_set(&ip->i_inode, name, value, len, 0,
+			       GFS2_EATYPE_SECURITY);
+	kfree(value);
+	kfree(name);
+
+	return err;
+}
+
+/**
+ * gfs2_create_inode - Create a new inode
+ * @dir: The parent directory
+ * @dentry: The new dentry
+ * @mode: The permissions on the new inode
+ * @dev: For device nodes, this is the device number
+ * @symname: For symlinks, this is the link destination
+ * @size: The initial size of the inode (ignored for directories)
+ *
+ * Returns: 0 on success, or error code
+ */
+
+static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
+			     unsigned int mode, dev_t dev, const char *symname,
+			     unsigned int size)
+{
+	const struct qstr *name = &dentry->d_name;
+	struct gfs2_holder ghs[2];
+	struct inode *inode = NULL;
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
+	int error;
+	u64 generation;
+	struct buffer_head *bh = NULL;
+
+	if (!name->len || name->len > GFS2_FNAMESIZE)
+		return -ENAMETOOLONG;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+	if (error)
+		goto fail;
+
+	error = create_ok(dip, name, mode);
+	if (error)
+		goto fail_gunlock;
+
+	error = alloc_dinode(dip, &inum.no_addr, &generation);
+	if (error)
+		goto fail_gunlock;
+	inum.no_formal_ino = generation;
+
+	error = gfs2_glock_nq_num(sdp, inum.no_addr, &gfs2_inode_glops,
+				  LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
+	if (error)
+		goto fail_gunlock;
+
+	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, symname, size, &bh);
+	if (error)
+		goto fail_gunlock2;
+
+	inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
+				  inum.no_formal_ino, 0);
+	if (IS_ERR(inode))
+		goto fail_gunlock2;
+
+	error = gfs2_inode_refresh(GFS2_I(inode));
+	if (error)
+		goto fail_gunlock2;
+
+	error = gfs2_acl_create(dip, inode);
+	if (error)
+		goto fail_gunlock2;
+
+	error = gfs2_security_init(dip, GFS2_I(inode), name);
+	if (error)
+		goto fail_gunlock2;
+
+	error = link_dinode(dip, name, GFS2_I(inode));
+	if (error)
+		goto fail_gunlock2;
+
+	if (bh)
+		brelse(bh);
+
+	gfs2_trans_end(sdp);
+	if (dip->i_alloc->al_rgd)
+		gfs2_inplace_release(dip);
+	gfs2_quota_unlock(dip);
+	gfs2_alloc_put(dip);
+	gfs2_glock_dq_uninit_m(2, ghs);
+	mark_inode_dirty(inode);
+	d_instantiate(dentry, inode);
+	return 0;
+
+fail_gunlock2:
+	gfs2_glock_dq_uninit(ghs + 1);
+	if (inode && !IS_ERR(inode))
+		iput(inode);
+fail_gunlock:
+	gfs2_glock_dq_uninit(ghs);
+fail:
+	if (bh)
+		brelse(bh);
+	return error;
+}
+
+/**
+ * gfs2_create - Create a file
+ * @dir: The directory in which to create the file
+ * @dentry: The dentry of the new file
+ * @mode: The mode of the new file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_create(struct inode *dir, struct dentry *dentry,
+		       int mode, struct nameidata *nd)
+{
+	struct inode *inode;
+	int ret;
+
+	for (;;) {
+		ret = gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0);
+		if (ret != -EEXIST || (nd && (nd->flags & LOOKUP_EXCL)))
+			return ret;
+
+		inode = gfs2_lookupi(dir, &dentry->d_name, 0);
+		if (inode) {
+			if (!IS_ERR(inode))
+				break;
+			return PTR_ERR(inode);
+		}
+	}
+
+	d_instantiate(dentry, inode);
+	return 0;
+}
+
+/**
+ * gfs2_lookup - Look up a filename in a directory and return its inode
+ * @dir: The directory inode
+ * @dentry: The dentry of the new inode
+ * @nd: passed from Linux VFS, ignored by us
+ *
+ * Called by the VFS layer. Lock dir and call gfs2_lookupi()
+ *
+ * Returns: errno
+ */
+
+static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
+				  struct nameidata *nd)
+{
+	struct inode *inode = NULL;
+
+	inode = gfs2_lookupi(dir, &dentry->d_name, 0);
+	if (inode && IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	if (inode) {
+		struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
+		struct gfs2_holder gh;
+		int error;
+		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+		if (error) {
+			iput(inode);
+			return ERR_PTR(error);
+		}
+		gfs2_glock_dq_uninit(&gh);
+		return d_splice_alias(inode, dentry);
+	}
+	d_add(dentry, inode);
+
+	return NULL;
+}
+
+/**
+ * gfs2_link - Link to a file
+ * @old_dentry: The inode to link
+ * @dir: Add link to this directory
+ * @dentry: The name of the link
+ *
+ * Link the inode in "old_dentry" into the directory "dir" with the
+ * name in "dentry".
+ *
+ * Returns: errno
+ */
+
+static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
+		     struct dentry *dentry)
+{
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_sbd *sdp = GFS2_SB(dir);
+	struct inode *inode = old_dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder ghs[2];
+	struct buffer_head *dibh;
+	int alloc_required;
+	int error;
+
+	if (S_ISDIR(inode->i_mode))
+		return -EPERM;
+
+	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
+
+	error = gfs2_glock_nq(ghs); /* parent */
+	if (error)
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = -ENOENT;
+	if (inode->i_nlink == 0)
+		goto out_gunlock;
+
+	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC, 0);
+	if (error)
+		goto out_gunlock;
+
+	error = gfs2_dir_check(dir, &dentry->d_name, NULL);
+	switch (error) {
+	case -ENOENT:
+		break;
+	case 0:
+		error = -EEXIST;
+	default:
+		goto out_gunlock;
+	}
+
+	error = -EINVAL;
+	if (!dip->i_inode.i_nlink)
+		goto out_gunlock;
+	error = -EFBIG;
+	if (dip->i_entries == (u32)-1)
+		goto out_gunlock;
+	error = -EPERM;
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+		goto out_gunlock;
+	error = -EINVAL;
+	if (!ip->i_inode.i_nlink)
+		goto out_gunlock;
+	error = -EMLINK;
+	if (ip->i_inode.i_nlink == (u32)-1)
+		goto out_gunlock;
+
+	alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
+	if (error < 0)
+		goto out_gunlock;
+	error = 0;
+
+	if (alloc_required) {
+		struct gfs2_alloc *al = gfs2_alloc_get(dip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_gunlock;
+		}
+
+		error = gfs2_quota_lock_check(dip);
+		if (error)
+			goto out_alloc;
+
+		al->al_requested = sdp->sd_max_dirres;
+
+		error = gfs2_inplace_reserve(dip);
+		if (error)
+			goto out_gunlock_q;
+
+		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
+					 gfs2_rg_blocks(al) +
+					 2 * RES_DINODE + RES_STATFS +
+					 RES_QUOTA, 0);
+		if (error)
+			goto out_ipres;
+	} else {
+		error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
+		if (error)
+			goto out_ipres;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out_end_trans;
+
+	error = gfs2_dir_add(dir, &dentry->d_name, ip);
+	if (error)
+		goto out_brelse;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	inc_nlink(&ip->i_inode);
+	ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_dinode_out(ip, dibh->b_data);
+	mark_inode_dirty(&ip->i_inode);
+
+out_brelse:
+	brelse(dibh);
+out_end_trans:
+	gfs2_trans_end(sdp);
+out_ipres:
+	if (alloc_required)
+		gfs2_inplace_release(dip);
+out_gunlock_q:
+	if (alloc_required)
+		gfs2_quota_unlock(dip);
+out_alloc:
+	if (alloc_required)
+		gfs2_alloc_put(dip);
+out_gunlock:
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
+	gfs2_holder_uninit(ghs + 1);
+	if (!error) {
+		ihold(inode);
+		d_instantiate(dentry, inode);
+		mark_inode_dirty(inode);
+	}
+	return error;
+}
+
+/*
+ * gfs2_unlink_ok - check to see that a inode is still in a directory
+ * @dip: the directory
+ * @name: the name of the file
+ * @ip: the inode
+ *
+ * Assumes that the lock on (at least) @dip is held.
+ *
+ * Returns: 0 if the parent/child relationship is correct, errno if it isn't
+ */
+
+static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+			  const struct gfs2_inode *ip)
+{
+	int error;
+
+	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
+		return -EPERM;
+
+	if ((dip->i_inode.i_mode & S_ISVTX) &&
+	    dip->i_inode.i_uid != current_fsuid() &&
+	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
+		return -EPERM;
+
+	if (IS_APPEND(&dip->i_inode))
+		return -EPERM;
+
+	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, 0);
+	if (error)
+		return error;
+
+	error = gfs2_dir_check(&dip->i_inode, name, ip);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/**
+ * gfs2_unlink_inode - Removes an inode from its parent dir and unlinks it
+ * @dip: The parent directory
+ * @name: The name of the entry in the parent directory
+ * @bh: The inode buffer for the inode to be removed
+ * @inode: The inode to be removed
+ *
+ * Called with all the locks and in a transaction. This will only be
+ * called for a directory after it has been checked to ensure it is empty.
+ *
+ * Returns: 0 on success, or an error
+ */
+
+static int gfs2_unlink_inode(struct gfs2_inode *dip,
+			     const struct dentry *dentry,
+			     struct buffer_head *bh)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int error;
+
+	error = gfs2_dir_del(dip, dentry);
+	if (error)
+		return error;
+
+	ip->i_entries = 0;
+	inode->i_ctime = CURRENT_TIME;
+	if (S_ISDIR(inode->i_mode))
+		clear_nlink(inode);
+	else
+		drop_nlink(inode);
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_dinode_out(ip, bh->b_data);
+	mark_inode_dirty(inode);
+	if (inode->i_nlink == 0)
+		gfs2_unlink_di(inode);
+	return 0;
+}
+
+
+/**
+ * gfs2_unlink - Unlink an inode (this does rmdir as well)
+ * @dir: The inode of the directory containing the inode to unlink
+ * @dentry: The file itself
+ *
+ * This routine uses the type of the inode as a flag to figure out
+ * whether this is an unlink or an rmdir.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_sbd *sdp = GFS2_SB(dir);
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *bh;
+	struct gfs2_holder ghs[3];
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_holder ri_gh;
+	int error;
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		return error;
+
+	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+	gfs2_holder_init(ip->i_gl,  LM_ST_EXCLUSIVE, 0, ghs + 1);
+
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
+
+
+	error = gfs2_glock_nq(ghs); /* parent */
+	if (error)
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = -ENOENT;
+	if (inode->i_nlink == 0)
+		goto out_rgrp;
+
+	if (S_ISDIR(inode->i_mode)) {
+		error = -ENOTEMPTY;
+		if (ip->i_entries > 2 || inode->i_nlink > 2)
+			goto out_rgrp;
+	}
+
+	error = gfs2_glock_nq(ghs + 2); /* rgrp */
+	if (error)
+		goto out_rgrp;
+
+	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
+	if (error)
+		goto out_gunlock;
+
+	error = gfs2_trans_begin(sdp, 2*RES_DINODE + 3*RES_LEAF + RES_RG_BIT, 0);
+	if (error)
+		goto out_gunlock;
+
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		goto out_end_trans;
+
+	error = gfs2_unlink_inode(dip, dentry, bh);
+	brelse(bh);
+
+out_end_trans:
+	gfs2_trans_end(sdp);
+out_gunlock:
+	gfs2_glock_dq(ghs + 2);
+out_rgrp:
+	gfs2_holder_uninit(ghs + 2);
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
+	gfs2_glock_dq_uninit(&ri_gh);
+	return error;
+}
+
+/**
+ * gfs2_symlink - Create a symlink
+ * @dir: The directory to create the symlink in
+ * @dentry: The dentry to put the symlink in
+ * @symname: The thing which the link points to
+ *
+ * Returns: errno
+ */
+
+static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
+			const char *symname)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(dir);
+	unsigned int size;
+
+	size = strlen(symname);
+	if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode) - 1)
+		return -ENAMETOOLONG;
+
+	return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size);
+}
+
+/**
+ * gfs2_mkdir - Make a directory
+ * @dir: The parent directory of the new one
+ * @dentry: The dentry of the new directory
+ * @mode: The mode of the new directory
+ *
+ * Returns: errno
+ */
+
+static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+	return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0);
+}
+
+/**
+ * gfs2_mknod - Make a special file
+ * @dir: The directory in which the special file will reside
+ * @dentry: The dentry of the special file
+ * @mode: The mode of the special file
+ * @dev: The device specification of the special file
+ *
+ */
+
+static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
+		      dev_t dev)
+{
+	return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0);
+}
+
+/*
+ * gfs2_ok_to_move - check if it's ok to move a directory to another directory
+ * @this: move this
+ * @to: to here
+ *
+ * Follow @to back to the root and make sure we don't encounter @this
+ * Assumes we already hold the rename lock.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
+{
+	struct inode *dir = &to->i_inode;
+	struct super_block *sb = dir->i_sb;
+	struct inode *tmp;
+	int error = 0;
+
+	igrab(dir);
+
+	for (;;) {
+		if (dir == &this->i_inode) {
+			error = -EINVAL;
+			break;
+		}
+		if (dir == sb->s_root->d_inode) {
+			error = 0;
+			break;
+		}
+
+		tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
+		if (IS_ERR(tmp)) {
+			error = PTR_ERR(tmp);
+			break;
+		}
+
+		iput(dir);
+		dir = tmp;
+	}
+
+	iput(dir);
+
+	return error;
+}
+
+/**
+ * gfs2_rename - Rename a file
+ * @odir: Parent directory of old file name
+ * @odentry: The old dentry of the file
+ * @ndir: Parent directory of new file name
+ * @ndentry: The new dentry of the file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_rename(struct inode *odir, struct dentry *odentry,
+		       struct inode *ndir, struct dentry *ndentry)
+{
+	struct gfs2_inode *odip = GFS2_I(odir);
+	struct gfs2_inode *ndip = GFS2_I(ndir);
+	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
+	struct gfs2_inode *nip = NULL;
+	struct gfs2_sbd *sdp = GFS2_SB(odir);
+	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
+	struct gfs2_rgrpd *nrgd;
+	unsigned int num_gh;
+	int dir_rename = 0;
+	int alloc_required = 0;
+	unsigned int x;
+	int error;
+
+	if (ndentry->d_inode) {
+		nip = GFS2_I(ndentry->d_inode);
+		if (ip == nip)
+			return 0;
+	}
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		return error;
+
+	if (odip != ndip) {
+		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
+					   0, &r_gh);
+		if (error)
+			goto out;
+
+		if (S_ISDIR(ip->i_inode.i_mode)) {
+			dir_rename = 1;
+			/* don't move a dirctory into it's subdir */
+			error = gfs2_ok_to_move(ip, ndip);
+			if (error)
+				goto out_gunlock_r;
+		}
+	}
+
+	num_gh = 1;
+	gfs2_holder_init(odip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+	if (odip != ndip) {
+		gfs2_holder_init(ndip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
+		num_gh++;
+	}
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
+	num_gh++;
+
+	if (nip) {
+		gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
+		num_gh++;
+		/* grab the resource lock for unlink flag twiddling 
+		 * this is the case of the target file already existing
+		 * so we unlink before doing the rename
+		 */
+		nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
+		if (nrgd)
+			gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
+	}
+
+	for (x = 0; x < num_gh; x++) {
+		error = gfs2_glock_nq(ghs + x);
+		if (error)
+			goto out_gunlock;
+	}
+
+	error = -ENOENT;
+	if (ip->i_inode.i_nlink == 0)
+		goto out_gunlock;
+
+	/* Check out the old directory */
+
+	error = gfs2_unlink_ok(odip, &odentry->d_name, ip);
+	if (error)
+		goto out_gunlock;
+
+	/* Check out the new directory */
+
+	if (nip) {
+		error = gfs2_unlink_ok(ndip, &ndentry->d_name, nip);
+		if (error)
+			goto out_gunlock;
+
+		if (nip->i_inode.i_nlink == 0) {
+			error = -EAGAIN;
+			goto out_gunlock;
+		}
+
+		if (S_ISDIR(nip->i_inode.i_mode)) {
+			if (nip->i_entries < 2) {
+				gfs2_consist_inode(nip);
+				error = -EIO;
+				goto out_gunlock;
+			}
+			if (nip->i_entries > 2) {
+				error = -ENOTEMPTY;
+				goto out_gunlock;
+			}
+		}
+	} else {
+		error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC, 0);
+		if (error)
+			goto out_gunlock;
+
+		error = gfs2_dir_check(ndir, &ndentry->d_name, NULL);
+		switch (error) {
+		case -ENOENT:
+			error = 0;
+			break;
+		case 0:
+			error = -EEXIST;
+		default:
+			goto out_gunlock;
+		};
+
+		if (odip != ndip) {
+			if (!ndip->i_inode.i_nlink) {
+				error = -ENOENT;
+				goto out_gunlock;
+			}
+			if (ndip->i_entries == (u32)-1) {
+				error = -EFBIG;
+				goto out_gunlock;
+			}
+			if (S_ISDIR(ip->i_inode.i_mode) &&
+			    ndip->i_inode.i_nlink == (u32)-1) {
+				error = -EMLINK;
+				goto out_gunlock;
+			}
+		}
+	}
+
+	/* Check out the dir to be renamed */
+
+	if (dir_rename) {
+		error = gfs2_permission(odentry->d_inode, MAY_WRITE, 0);
+		if (error)
+			goto out_gunlock;
+	}
+
+	if (nip == NULL)
+		alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
+	error = alloc_required;
+	if (error < 0)
+		goto out_gunlock;
+	error = 0;
+
+	if (alloc_required) {
+		struct gfs2_alloc *al = gfs2_alloc_get(ndip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_gunlock;
+		}
+
+		error = gfs2_quota_lock_check(ndip);
+		if (error)
+			goto out_alloc;
+
+		al->al_requested = sdp->sd_max_dirres;
+
+		error = gfs2_inplace_reserve_ri(ndip);
+		if (error)
+			goto out_gunlock_q;
+
+		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
+					 gfs2_rg_blocks(al) +
+					 4 * RES_DINODE + 4 * RES_LEAF +
+					 RES_STATFS + RES_QUOTA + 4, 0);
+		if (error)
+			goto out_ipreserv;
+	} else {
+		error = gfs2_trans_begin(sdp, 4 * RES_DINODE +
+					 5 * RES_LEAF + 4, 0);
+		if (error)
+			goto out_gunlock;
+	}
+
+	/* Remove the target file, if it exists */
+
+	if (nip) {
+		struct buffer_head *bh;
+		error = gfs2_meta_inode_buffer(nip, &bh);
+		if (error)
+			goto out_end_trans;
+		error = gfs2_unlink_inode(ndip, ndentry, bh);
+		brelse(bh);
+	}
+
+	if (dir_rename) {
+		error = gfs2_dir_mvino(ip, &gfs2_qdotdot, ndip, DT_DIR);
+		if (error)
+			goto out_end_trans;
+	} else {
+		struct buffer_head *dibh;
+		error = gfs2_meta_inode_buffer(ip, &dibh);
+		if (error)
+			goto out_end_trans;
+		ip->i_inode.i_ctime = CURRENT_TIME;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	error = gfs2_dir_del(odip, odentry);
+	if (error)
+		goto out_end_trans;
+
+	error = gfs2_dir_add(ndir, &ndentry->d_name, ip);
+	if (error)
+		goto out_end_trans;
+
+out_end_trans:
+	gfs2_trans_end(sdp);
+out_ipreserv:
+	if (alloc_required)
+		gfs2_inplace_release(ndip);
+out_gunlock_q:
+	if (alloc_required)
+		gfs2_quota_unlock(ndip);
+out_alloc:
+	if (alloc_required)
+		gfs2_alloc_put(ndip);
+out_gunlock:
+	while (x--) {
+		gfs2_glock_dq(ghs + x);
+		gfs2_holder_uninit(ghs + x);
+	}
+out_gunlock_r:
+	if (r_gh.gh_gl)
+		gfs2_glock_dq_uninit(&r_gh);
+out:
+	gfs2_glock_dq_uninit(&ri_gh);
+	return error;
+}
+
+/**
+ * gfs2_follow_link - Follow a symbolic link
+ * @dentry: The dentry of the link
+ * @nd: Data that we pass to vfs_follow_link()
+ *
+ * This can handle symlinks of any size.
+ *
+ * Returns: 0 on success or error code
+ */
+
+static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+	struct gfs2_holder i_gh;
+	struct buffer_head *dibh;
+	unsigned int size;
+	char *buf;
+	int error;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+	error = gfs2_glock_nq(&i_gh);
+	if (error) {
+		gfs2_holder_uninit(&i_gh);
+		nd_set_link(nd, ERR_PTR(error));
+		return NULL;
+	}
+
+	size = (unsigned int)i_size_read(&ip->i_inode);
+	if (size == 0) {
+		gfs2_consist_inode(ip);
+		buf = ERR_PTR(-EIO);
+		goto out;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error) {
+		buf = ERR_PTR(error);
+		goto out;
+	}
+
+	buf = kzalloc(size + 1, GFP_NOFS);
+	if (!buf)
+		buf = ERR_PTR(-ENOMEM);
+	else
+		memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), size);
+	brelse(dibh);
+out:
+	gfs2_glock_dq_uninit(&i_gh);
+	nd_set_link(nd, buf);
+	return NULL;
+}
+
+static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+{
+	char *s = nd_get_link(nd);
+	if (!IS_ERR(s))
+		kfree(s);
+}
+
+/**
+ * gfs2_permission -
+ * @inode: The inode
+ * @mask: The mask to be tested
+ * @flags: Indicates whether this is an RCU path walk or not
+ *
+ * This may be called from the VFS directly, or from within GFS2 with the
+ * inode locked, so we look to see if the glock is already locked and only
+ * lock the glock if its not already been done.
+ *
+ * Returns: errno
+ */
+
+int gfs2_permission(struct inode *inode, int mask, unsigned int flags)
+{
+	struct gfs2_inode *ip;
+	struct gfs2_holder i_gh;
+	int error;
+	int unlock = 0;
+
+
+	ip = GFS2_I(inode);
+	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
+		if (flags & IPERM_FLAG_RCU)
+			return -ECHILD;
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+		if (error)
+			return error;
+		unlock = 1;
+	}
+
+	if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
+		error = -EACCES;
+	else
+		error = generic_permission(inode, mask, flags, gfs2_check_acl);
+	if (unlock)
+		gfs2_glock_dq_uninit(&i_gh);
+
+	return error;
+}
+
+static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+{
+	struct inode *inode = &ip->i_inode;
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	setattr_copy(inode, attr);
+	mark_inode_dirty(inode);
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+	return 0;
+}
+
+/**
+ * gfs2_setattr_simple -
+ * @ip:
+ * @attr:
+ *
+ * Returns: errno
+ */
+
+int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+{
+	int error;
+
+	if (current->journal_info)
+		return __gfs2_setattr_simple(ip, attr);
+
+	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE, 0);
+	if (error)
+		return error;
+
+	error = __gfs2_setattr_simple(ip, attr);
+	gfs2_trans_end(GFS2_SB(&ip->i_inode));
+	return error;
+}
+
+static int setattr_chown(struct inode *inode, struct iattr *attr)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	u32 ouid, ogid, nuid, ngid;
+	int error;
+
+	ouid = inode->i_uid;
+	ogid = inode->i_gid;
+	nuid = attr->ia_uid;
+	ngid = attr->ia_gid;
+
+	if (!(attr->ia_valid & ATTR_UID) || ouid == nuid)
+		ouid = nuid = NO_QUOTA_CHANGE;
+	if (!(attr->ia_valid & ATTR_GID) || ogid == ngid)
+		ogid = ngid = NO_QUOTA_CHANGE;
+
+	if (!gfs2_alloc_get(ip))
+		return -ENOMEM;
+
+	error = gfs2_quota_lock(ip, nuid, ngid);
+	if (error)
+		goto out_alloc;
+
+	if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
+		error = gfs2_quota_check(ip, nuid, ngid);
+		if (error)
+			goto out_gunlock_q;
+	}
+
+	error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_QUOTA, 0);
+	if (error)
+		goto out_gunlock_q;
+
+	error = gfs2_setattr_simple(ip, attr);
+	if (error)
+		goto out_end_trans;
+
+	if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
+		u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
+		gfs2_quota_change(ip, -blocks, ouid, ogid);
+		gfs2_quota_change(ip, blocks, nuid, ngid);
+	}
+
+out_end_trans:
+	gfs2_trans_end(sdp);
+out_gunlock_q:
+	gfs2_quota_unlock(ip);
+out_alloc:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+/**
+ * gfs2_setattr - Change attributes on an inode
+ * @dentry: The dentry which is changing
+ * @attr: The structure describing the change
+ *
+ * The VFS layer wants to change one or more of an inodes attributes.  Write
+ * that change out to disk.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder i_gh;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+	if (error)
+		return error;
+
+	error = -EPERM;
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+		goto out;
+
+	error = inode_change_ok(inode, attr);
+	if (error)
+		goto out;
+
+	if (attr->ia_valid & ATTR_SIZE)
+		error = gfs2_setattr_size(inode, attr->ia_size);
+	else if (attr->ia_valid & (ATTR_UID | ATTR_GID))
+		error = setattr_chown(inode, attr);
+	else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
+		error = gfs2_acl_chmod(ip, attr);
+	else
+		error = gfs2_setattr_simple(ip, attr);
+
+out:
+	gfs2_glock_dq_uninit(&i_gh);
+	if (!error)
+		mark_inode_dirty(inode);
+	return error;
+}
+
+/**
+ * gfs2_getattr - Read out an inode's attributes
+ * @mnt: The vfsmount the inode is being accessed from
+ * @dentry: The dentry to stat
+ * @stat: The inode's stats
+ *
+ * This may be called from the VFS directly, or from within GFS2 with the
+ * inode locked, so we look to see if the glock is already locked and only
+ * lock the glock if its not already been done. Note that its the NFS
+ * readdirplus operation which causes this to be called (from filldir)
+ * with the glock already held.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+	int unlock = 0;
+
+	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+		if (error)
+			return error;
+		unlock = 1;
+	}
+
+	generic_fillattr(inode, stat);
+	if (unlock)
+		gfs2_glock_dq_uninit(&gh);
+
+	return 0;
+}
+
+static int gfs2_setxattr(struct dentry *dentry, const char *name,
+			 const void *data, size_t size, int flags)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret == 0) {
+		ret = generic_setxattr(dentry, name, data, size, flags);
+		gfs2_glock_dq(&gh);
+	}
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
+			     void *data, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret == 0) {
+		ret = generic_getxattr(dentry, name, data, size);
+		gfs2_glock_dq(&gh);
+	}
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static int gfs2_removexattr(struct dentry *dentry, const char *name)
+{
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret == 0) {
+		ret = generic_removexattr(dentry, name);
+		gfs2_glock_dq(&gh);
+	}
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+	if (ret)
+		return ret;
+
+	mutex_lock(&inode->i_mutex);
+
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (ret)
+		goto out;
+
+	if (gfs2_is_stuffed(ip)) {
+		u64 phys = ip->i_no_addr << inode->i_blkbits;
+		u64 size = i_size_read(inode);
+		u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
+			    FIEMAP_EXTENT_DATA_INLINE;
+		phys += sizeof(struct gfs2_dinode);
+		phys += start;
+		if (start + len > size)
+			len = size - start;
+		if (start < size)
+			ret = fiemap_fill_next_extent(fieinfo, start, phys,
+						      len, flags);
+		if (ret == 1)
+			ret = 0;
+	} else {
+		ret = __generic_block_fiemap(inode, fieinfo, start, len,
+					     gfs2_block_map);
+	}
+
+	gfs2_glock_dq_uninit(&gh);
+out:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
+}
+
+const struct inode_operations gfs2_file_iops = {
+	.permission = gfs2_permission,
+	.setattr = gfs2_setattr,
+	.getattr = gfs2_getattr,
+	.setxattr = gfs2_setxattr,
+	.getxattr = gfs2_getxattr,
+	.listxattr = gfs2_listxattr,
+	.removexattr = gfs2_removexattr,
+	.fiemap = gfs2_fiemap,
+};
+
+const struct inode_operations gfs2_dir_iops = {
+	.create = gfs2_create,
+	.lookup = gfs2_lookup,
+	.link = gfs2_link,
+	.unlink = gfs2_unlink,
+	.symlink = gfs2_symlink,
+	.mkdir = gfs2_mkdir,
+	.rmdir = gfs2_unlink,
+	.mknod = gfs2_mknod,
+	.rename = gfs2_rename,
+	.permission = gfs2_permission,
+	.setattr = gfs2_setattr,
+	.getattr = gfs2_getattr,
+	.setxattr = gfs2_setxattr,
+	.getxattr = gfs2_getxattr,
+	.listxattr = gfs2_listxattr,
+	.removexattr = gfs2_removexattr,
+	.fiemap = gfs2_fiemap,
+};
+
+const struct inode_operations gfs2_symlink_iops = {
+	.readlink = generic_readlink,
+	.follow_link = gfs2_follow_link,
+	.put_link = gfs2_put_link,
+	.permission = gfs2_permission,
+	.setattr = gfs2_setattr,
+	.getattr = gfs2_getattr,
+	.setxattr = gfs2_setxattr,
+	.getxattr = gfs2_getxattr,
+	.listxattr = gfs2_listxattr,
+	.removexattr = gfs2_removexattr,
+	.fiemap = gfs2_fiemap,
+};
+
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
new file mode 100644
index 00000000..31606076
--- /dev/null
+++ b/fs/gfs2/inode.h
@@ -0,0 +1,143 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __INODE_DOT_H__
+#define __INODE_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include "util.h"
+
+extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      struct file_ra_state *ra_state,
+			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int to);
+extern void gfs2_set_aops(struct inode *inode);
+
+static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
+{
+	return !ip->i_height;
+}
+
+static inline int gfs2_is_jdata(const struct gfs2_inode *ip)
+{
+	return ip->i_diskflags & GFS2_DIF_JDATA;
+}
+
+static inline int gfs2_is_writeback(const struct gfs2_inode *ip)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	return (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK) && !gfs2_is_jdata(ip);
+}
+
+static inline int gfs2_is_ordered(const struct gfs2_inode *ip)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	return (sdp->sd_args.ar_data == GFS2_DATA_ORDERED) && !gfs2_is_jdata(ip);
+}
+
+static inline int gfs2_is_dir(const struct gfs2_inode *ip)
+{
+	return S_ISDIR(ip->i_inode.i_mode);
+}
+
+static inline void gfs2_set_inode_blocks(struct inode *inode, u64 blocks)
+{
+	inode->i_blocks = blocks <<
+		(GFS2_SB(inode)->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT);
+}
+
+static inline u64 gfs2_get_inode_blocks(const struct inode *inode)
+{
+	return inode->i_blocks >>
+		(GFS2_SB(inode)->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT);
+}
+
+static inline void gfs2_add_inode_blocks(struct inode *inode, s64 change)
+{
+	gfs2_assert(GFS2_SB(inode), (change >= 0 || inode->i_blocks > -change));
+	change *= (GFS2_SB(inode)->sd_sb.sb_bsize/GFS2_BASIC_BLOCK);
+	inode->i_blocks += change;
+}
+
+static inline int gfs2_check_inum(const struct gfs2_inode *ip, u64 no_addr,
+				  u64 no_formal_ino)
+{
+	return ip->i_no_addr == no_addr && ip->i_no_formal_ino == no_formal_ino;
+}
+
+static inline void gfs2_inum_out(const struct gfs2_inode *ip,
+				 struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
+	dent->de_inum.no_addr = cpu_to_be64(ip->i_no_addr);
+}
+
+static inline int gfs2_check_internal_file_size(struct inode *inode,
+						u64 minsize, u64 maxsize)
+{
+	u64 size = i_size_read(inode);
+	if (size < minsize || size > maxsize)
+		goto err;
+	if (size & ((1 << inode->i_blkbits) - 1))
+		goto err;
+	return 0;
+err:
+	gfs2_consist_inode(GFS2_I(inode));
+	return -EIO;
+}
+
+extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
+				       u64 no_addr, u64 no_formal_ino,
+				       int non_block);
+extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
+					 u64 *no_formal_ino,
+					 unsigned int blktype);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int nonblock);
+
+extern int gfs2_inode_refresh(struct gfs2_inode *ip);
+
+extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+				  int is_root);
+extern int gfs2_permission(struct inode *inode, int mask, unsigned int flags);
+extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
+extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
+
+extern const struct inode_operations gfs2_file_iops;
+extern const struct inode_operations gfs2_dir_iops;
+extern const struct inode_operations gfs2_symlink_iops;
+extern const struct file_operations gfs2_file_fops_nolock;
+extern const struct file_operations gfs2_dir_fops_nolock;
+
+extern void gfs2_set_inode_flags(struct inode *inode);
+ 
+#ifdef CONFIG_GFS2_FS_LOCKING_DLM
+extern const struct file_operations gfs2_file_fops;
+extern const struct file_operations gfs2_dir_fops;
+
+static inline int gfs2_localflocks(const struct gfs2_sbd *sdp)
+{
+	return sdp->sd_args.ar_localflocks;
+}
+#else /* Single node only */
+#define gfs2_file_fops gfs2_file_fops_nolock
+#define gfs2_dir_fops gfs2_dir_fops_nolock
+
+static inline int gfs2_localflocks(const struct gfs2_sbd *sdp)
+{
+	return 1;
+}
+#endif /* CONFIG_GFS2_FS_LOCKING_DLM */
+
+#endif /* __INODE_DOT_H__ */
+
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
new file mode 100644
index 00000000..98c80d8c
--- /dev/null
+++ b/fs/gfs2/lock_dlm.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2009 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/fs.h>
+#include <linux/dlm.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "incore.h"
+#include "glock.h"
+#include "util.h"
+
+
+static void gdlm_ast(void *arg)
+{
+	struct gfs2_glock *gl = arg;
+	unsigned ret = gl->gl_state;
+
+	BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED);
+
+	if (gl->gl_lksb.sb_flags & DLM_SBF_VALNOTVALID)
+		memset(gl->gl_lvb, 0, GDLM_LVB_SIZE);
+
+	switch (gl->gl_lksb.sb_status) {
+	case -DLM_EUNLOCK: /* Unlocked, so glock can be freed */
+		gfs2_glock_free(gl);
+		return;
+	case -DLM_ECANCEL: /* Cancel while getting lock */
+		ret |= LM_OUT_CANCELED;
+		goto out;
+	case -EAGAIN: /* Try lock fails */
+	case -EDEADLK: /* Deadlock detected */
+		goto out;
+	case -ETIMEDOUT: /* Canceled due to timeout */
+		ret |= LM_OUT_ERROR;
+		goto out;
+	case 0: /* Success */
+		break;
+	default: /* Something unexpected */
+		BUG();
+	}
+
+	ret = gl->gl_req;
+	if (gl->gl_lksb.sb_flags & DLM_SBF_ALTMODE) {
+		if (gl->gl_req == LM_ST_SHARED)
+			ret = LM_ST_DEFERRED;
+		else if (gl->gl_req == LM_ST_DEFERRED)
+			ret = LM_ST_SHARED;
+		else
+			BUG();
+	}
+
+	set_bit(GLF_INITIAL, &gl->gl_flags);
+	gfs2_glock_complete(gl, ret);
+	return;
+out:
+	if (!test_bit(GLF_INITIAL, &gl->gl_flags))
+		gl->gl_lksb.sb_lkid = 0;
+	gfs2_glock_complete(gl, ret);
+}
+
+static void gdlm_bast(void *arg, int mode)
+{
+	struct gfs2_glock *gl = arg;
+
+	switch (mode) {
+	case DLM_LOCK_EX:
+		gfs2_glock_cb(gl, LM_ST_UNLOCKED);
+		break;
+	case DLM_LOCK_CW:
+		gfs2_glock_cb(gl, LM_ST_DEFERRED);
+		break;
+	case DLM_LOCK_PR:
+		gfs2_glock_cb(gl, LM_ST_SHARED);
+		break;
+	default:
+		printk(KERN_ERR "unknown bast mode %d", mode);
+		BUG();
+	}
+}
+
+/* convert gfs lock-state to dlm lock-mode */
+
+static int make_mode(const unsigned int lmstate)
+{
+	switch (lmstate) {
+	case LM_ST_UNLOCKED:
+		return DLM_LOCK_NL;
+	case LM_ST_EXCLUSIVE:
+		return DLM_LOCK_EX;
+	case LM_ST_DEFERRED:
+		return DLM_LOCK_CW;
+	case LM_ST_SHARED:
+		return DLM_LOCK_PR;
+	}
+	printk(KERN_ERR "unknown LM state %d", lmstate);
+	BUG();
+	return -1;
+}
+
+static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
+		      const int req)
+{
+	u32 lkf = 0;
+
+	if (gfs_flags & LM_FLAG_TRY)
+		lkf |= DLM_LKF_NOQUEUE;
+
+	if (gfs_flags & LM_FLAG_TRY_1CB) {
+		lkf |= DLM_LKF_NOQUEUE;
+		lkf |= DLM_LKF_NOQUEUEBAST;
+	}
+
+	if (gfs_flags & LM_FLAG_PRIORITY) {
+		lkf |= DLM_LKF_NOORDER;
+		lkf |= DLM_LKF_HEADQUE;
+	}
+
+	if (gfs_flags & LM_FLAG_ANY) {
+		if (req == DLM_LOCK_PR)
+			lkf |= DLM_LKF_ALTCW;
+		else if (req == DLM_LOCK_CW)
+			lkf |= DLM_LKF_ALTPR;
+		else
+			BUG();
+	}
+
+	if (lkid != 0) 
+		lkf |= DLM_LKF_CONVERT;
+
+	lkf |= DLM_LKF_VALBLK;
+
+	return lkf;
+}
+
+static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
+		     unsigned int flags)
+{
+	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+	int req;
+	u32 lkf;
+
+	req = make_mode(req_state);
+	lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
+
+	/*
+	 * Submit the actual lock request.
+	 */
+
+	return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
+			GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
+}
+
+static void gdlm_put_lock(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	int error;
+
+	if (gl->gl_lksb.sb_lkid == 0) {
+		gfs2_glock_free(gl);
+		return;
+	}
+
+	error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK,
+			   NULL, gl);
+	if (error) {
+		printk(KERN_ERR "gdlm_unlock %x,%llx err=%d\n",
+		       gl->gl_name.ln_type,
+		       (unsigned long long)gl->gl_name.ln_number, error);
+		return;
+	}
+}
+
+static void gdlm_cancel(struct gfs2_glock *gl)
+{
+	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+	dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_CANCEL, NULL, gl);
+}
+
+static int gdlm_mount(struct gfs2_sbd *sdp, const char *fsname)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	int error;
+
+	if (fsname == NULL) {
+		fs_info(sdp, "no fsname found\n");
+		return -EINVAL;
+	}
+
+	error = dlm_new_lockspace(fsname, strlen(fsname), &ls->ls_dlm,
+				  DLM_LSFL_FS | DLM_LSFL_NEWEXCL |
+				  (ls->ls_nodir ? DLM_LSFL_NODIR : 0),
+				  GDLM_LVB_SIZE);
+	if (error)
+		printk(KERN_ERR "dlm_new_lockspace error %d", error);
+
+	return error;
+}
+
+static void gdlm_unmount(struct gfs2_sbd *sdp)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+
+	if (ls->ls_dlm) {
+		dlm_release_lockspace(ls->ls_dlm, 2);
+		ls->ls_dlm = NULL;
+	}
+}
+
+static const match_table_t dlm_tokens = {
+	{ Opt_jid, "jid=%d"},
+	{ Opt_id, "id=%d"},
+	{ Opt_first, "first=%d"},
+	{ Opt_nodir, "nodir=%d"},
+	{ Opt_err, NULL },
+};
+
+const struct lm_lockops gfs2_dlm_ops = {
+	.lm_proto_name = "lock_dlm",
+	.lm_mount = gdlm_mount,
+	.lm_unmount = gdlm_unmount,
+	.lm_put_lock = gdlm_put_lock,
+	.lm_lock = gdlm_lock,
+	.lm_cancel = gdlm_cancel,
+	.lm_tokens = &dlm_tokens,
+};
+
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
new file mode 100644
index 00000000..85c62923
--- /dev/null
+++ b/fs/gfs2/log.c
@@ -0,0 +1,972 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/bio.h>
+#include <linux/writeback.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "util.h"
+#include "dir.h"
+#include "trace_gfs2.h"
+
+#define PULL 1
+
+/**
+ * gfs2_struct2blk - compute stuff
+ * @sdp: the filesystem
+ * @nstruct: the number of structures
+ * @ssize: the size of the structures
+ *
+ * Compute the number of log descriptor blocks needed to hold a certain number
+ * of structures of a certain size.
+ *
+ * Returns: the number of blocks needed (minimum is always 1)
+ */
+
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			     unsigned int ssize)
+{
+	unsigned int blks;
+	unsigned int first, second;
+
+	blks = 1;
+	first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+
+	if (nstruct > first) {
+		second = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / ssize;
+		blks += DIV_ROUND_UP(nstruct - first, second);
+	}
+
+	return blks;
+}
+
+/**
+ * gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
+ * @mapping: The associated mapping (maybe NULL)
+ * @bd: The gfs2_bufdata to remove
+ *
+ * The ail lock _must_ be held when calling this function
+ *
+ */
+
+void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
+{
+	bd->bd_ail = NULL;
+	list_del_init(&bd->bd_ail_st_list);
+	list_del_init(&bd->bd_ail_gl_list);
+	atomic_dec(&bd->bd_gl->gl_ail_count);
+	brelse(bd->bd_bh);
+}
+
+/**
+ * gfs2_ail1_start_one - Start I/O on a part of the AIL
+ * @sdp: the filesystem
+ * @wbc: The writeback control structure
+ * @ai: The ail structure
+ *
+ */
+
+static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
+			       struct writeback_control *wbc,
+			       struct gfs2_ail *ai)
+__releases(&sdp->sd_ail_lock)
+__acquires(&sdp->sd_ail_lock)
+{
+	struct gfs2_glock *gl = NULL;
+	struct address_space *mapping;
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+
+	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, bd_ail_st_list) {
+		bh = bd->bd_bh;
+
+		gfs2_assert(sdp, bd->bd_ail == ai);
+
+		if (!buffer_busy(bh)) {
+			if (!buffer_uptodate(bh))
+				gfs2_io_error_bh(sdp, bh);
+			list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+			continue;
+		}
+
+		if (!buffer_dirty(bh))
+			continue;
+		if (gl == bd->bd_gl)
+			continue;
+		gl = bd->bd_gl;
+		list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+		mapping = bh->b_page->mapping;
+		if (!mapping)
+			continue;
+		spin_unlock(&sdp->sd_ail_lock);
+		generic_writepages(mapping, wbc);
+		spin_lock(&sdp->sd_ail_lock);
+		if (wbc->nr_to_write <= 0)
+			break;
+		return 1;
+	}
+
+	return 0;
+}
+
+
+/**
+ * gfs2_ail1_flush - start writeback of some ail1 entries 
+ * @sdp: The super block
+ * @wbc: The writeback control structure
+ *
+ * Writes back some ail1 entries, according to the limits in the
+ * writeback control structure
+ */
+
+void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
+{
+	struct list_head *head = &sdp->sd_ail1_list;
+	struct gfs2_ail *ai;
+
+	trace_gfs2_ail_flush(sdp, wbc, 1);
+	spin_lock(&sdp->sd_ail_lock);
+restart:
+	list_for_each_entry_reverse(ai, head, ai_list) {
+		if (wbc->nr_to_write <= 0)
+			break;
+		if (gfs2_ail1_start_one(sdp, wbc, ai))
+			goto restart;
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+	trace_gfs2_ail_flush(sdp, wbc, 0);
+}
+
+/**
+ * gfs2_ail1_start - start writeback of all ail1 entries
+ * @sdp: The superblock
+ */
+
+static void gfs2_ail1_start(struct gfs2_sbd *sdp)
+{
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_NONE,
+		.nr_to_write = LONG_MAX,
+		.range_start = 0,
+		.range_end = LLONG_MAX,
+	};
+
+	return gfs2_ail1_flush(sdp, &wbc);
+}
+
+/**
+ * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+
+	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+					 bd_ail_st_list) {
+		bh = bd->bd_bh;
+		gfs2_assert(sdp, bd->bd_ail == ai);
+		if (buffer_busy(bh))
+			continue;
+		if (!buffer_uptodate(bh))
+			gfs2_io_error_bh(sdp, bh);
+		list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+	}
+
+}
+
+/**
+ * gfs2_ail1_empty - Try to empty the ail1 lists
+ * @sdp: The superblock
+ *
+ * Tries to empty the ail1 lists, starting with the oldest first
+ */
+
+static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
+{
+	struct gfs2_ail *ai, *s;
+	int ret;
+
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
+		gfs2_ail1_empty_one(sdp, ai);
+		if (list_empty(&ai->ai_ail1_list))
+			list_move(&ai->ai_list, &sdp->sd_ail2_list);
+		else
+			break;
+	}
+	ret = list_empty(&sdp->sd_ail1_list);
+	spin_unlock(&sdp->sd_ail_lock);
+
+	return ret;
+}
+
+static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
+{
+	struct gfs2_ail *ai;
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
+
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) {
+		list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) {
+			bh = bd->bd_bh;
+			if (!buffer_locked(bh))
+				continue;
+			get_bh(bh);
+			spin_unlock(&sdp->sd_ail_lock);
+			wait_on_buffer(bh);
+			brelse(bh);
+			return;
+		}
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+}
+
+/**
+ * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &ai->ai_ail2_list;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->prev, struct gfs2_bufdata,
+				bd_ail_st_list);
+		gfs2_assert(sdp, bd->bd_ail == ai);
+		gfs2_remove_from_ail(bd);
+	}
+}
+
+static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
+{
+	struct gfs2_ail *ai, *safe;
+	unsigned int old_tail = sdp->sd_log_tail;
+	int wrap = (new_tail < old_tail);
+	int a, b, rm;
+
+	spin_lock(&sdp->sd_ail_lock);
+
+	list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
+		a = (old_tail <= ai->ai_first);
+		b = (ai->ai_first < new_tail);
+		rm = (wrap) ? (a || b) : (a && b);
+		if (!rm)
+			continue;
+
+		gfs2_ail2_empty_one(sdp, ai);
+		list_del(&ai->ai_list);
+		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
+		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
+		kfree(ai);
+	}
+
+	spin_unlock(&sdp->sd_ail_lock);
+}
+
+/**
+ * gfs2_log_reserve - Make a log reservation
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks to reserve
+ *
+ * Note that we never give out the last few blocks of the journal. Thats
+ * due to the fact that there is a small number of header blocks
+ * associated with each log flush. The exact number can't be known until
+ * flush time, so we ensure that we have just enough free blocks at all
+ * times to avoid running out during a log flush.
+ *
+ * We no longer flush the log here, instead we wake up logd to do that
+ * for us. To avoid the thundering herd and to ensure that we deal fairly
+ * with queued waiters, we use an exclusive wait. This means that when we
+ * get woken with enough journal space to get our reservation, we need to
+ * wake the next waiter on the list.
+ *
+ * Returns: errno
+ */
+
+int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
+{
+	unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize);
+	unsigned wanted = blks + reserved_blks;
+	DEFINE_WAIT(wait);
+	int did_wait = 0;
+	unsigned int free_blocks;
+
+	if (gfs2_assert_warn(sdp, blks) ||
+	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
+		return -EINVAL;
+retry:
+	free_blocks = atomic_read(&sdp->sd_log_blks_free);
+	if (unlikely(free_blocks <= wanted)) {
+		do {
+			prepare_to_wait_exclusive(&sdp->sd_log_waitq, &wait,
+					TASK_UNINTERRUPTIBLE);
+			wake_up(&sdp->sd_logd_waitq);
+			did_wait = 1;
+			if (atomic_read(&sdp->sd_log_blks_free) <= wanted)
+				io_schedule();
+			free_blocks = atomic_read(&sdp->sd_log_blks_free);
+		} while(free_blocks <= wanted);
+		finish_wait(&sdp->sd_log_waitq, &wait);
+	}
+	if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks,
+				free_blocks - blks) != free_blocks)
+		goto retry;
+	trace_gfs2_log_blocks(sdp, -blks);
+
+	/*
+	 * If we waited, then so might others, wake them up _after_ we get
+	 * our share of the log.
+	 */
+	if (unlikely(did_wait))
+		wake_up(&sdp->sd_log_waitq);
+
+	down_read(&sdp->sd_log_flush_lock);
+
+	return 0;
+}
+
+static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
+{
+	struct gfs2_journal_extent *je;
+
+	list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) {
+		if (lbn >= je->lblock && lbn < je->lblock + je->blocks)
+			return je->dblock + lbn - je->lblock;
+	}
+
+	return -1;
+}
+
+/**
+ * log_distance - Compute distance between two journal blocks
+ * @sdp: The GFS2 superblock
+ * @newer: The most recent journal block of the pair
+ * @older: The older journal block of the pair
+ *
+ *   Compute the distance (in the journal direction) between two
+ *   blocks in the journal
+ *
+ * Returns: the distance in blocks
+ */
+
+static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
+					unsigned int older)
+{
+	int dist;
+
+	dist = newer - older;
+	if (dist < 0)
+		dist += sdp->sd_jdesc->jd_blocks;
+
+	return dist;
+}
+
+/**
+ * calc_reserved - Calculate the number of blocks to reserve when
+ *                 refunding a transaction's unused buffers.
+ * @sdp: The GFS2 superblock
+ *
+ * This is complex.  We need to reserve room for all our currently used
+ * metadata buffers (e.g. normal file I/O rewriting file time stamps) and 
+ * all our journaled data buffers for journaled files (e.g. files in the 
+ * meta_fs like rindex, or files for which chattr +j was done.)
+ * If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush
+ * will count it as free space (sd_log_blks_free) and corruption will follow.
+ *
+ * We can have metadata bufs and jdata bufs in the same journal.  So each
+ * type gets its own log header, for which we need to reserve a block.
+ * In fact, each type has the potential for needing more than one header 
+ * in cases where we have more buffers than will fit on a journal page.
+ * Metadata journal entries take up half the space of journaled buffer entries.
+ * Thus, metadata entries have buf_limit (502) and journaled buffers have
+ * databuf_limit (251) before they cause a wrap around.
+ *
+ * Also, we need to reserve blocks for revoke journal entries and one for an
+ * overall header for the lot.
+ *
+ * Returns: the number of blocks reserved
+ */
+static unsigned int calc_reserved(struct gfs2_sbd *sdp)
+{
+	unsigned int reserved = 0;
+	unsigned int mbuf_limit, metabufhdrs_needed;
+	unsigned int dbuf_limit, databufhdrs_needed;
+	unsigned int revokes = 0;
+
+	mbuf_limit = buf_limit(sdp);
+	metabufhdrs_needed = (sdp->sd_log_commited_buf +
+			      (mbuf_limit - 1)) / mbuf_limit;
+	dbuf_limit = databuf_limit(sdp);
+	databufhdrs_needed = (sdp->sd_log_commited_databuf +
+			      (dbuf_limit - 1)) / dbuf_limit;
+
+	if (sdp->sd_log_commited_revoke > 0)
+		revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
+					  sizeof(u64));
+
+	reserved = sdp->sd_log_commited_buf + metabufhdrs_needed +
+		sdp->sd_log_commited_databuf + databufhdrs_needed +
+		revokes;
+	/* One for the overall header */
+	if (reserved)
+		reserved++;
+	return reserved;
+}
+
+static unsigned int current_tail(struct gfs2_sbd *sdp)
+{
+	struct gfs2_ail *ai;
+	unsigned int tail;
+
+	spin_lock(&sdp->sd_ail_lock);
+
+	if (list_empty(&sdp->sd_ail1_list)) {
+		tail = sdp->sd_log_head;
+	} else {
+		ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
+		tail = ai->ai_first;
+	}
+
+	spin_unlock(&sdp->sd_ail_lock);
+
+	return tail;
+}
+
+void gfs2_log_incr_head(struct gfs2_sbd *sdp)
+{
+	if (sdp->sd_log_flush_head == sdp->sd_log_tail)
+		BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);
+
+	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
+		sdp->sd_log_flush_head = 0;
+		sdp->sd_log_flush_wrapped = 1;
+	}
+}
+
+/**
+ * gfs2_log_write_endio - End of I/O for a log buffer
+ * @bh: The buffer head
+ * @uptodate: I/O Status
+ *
+ */
+
+static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
+{
+	struct gfs2_sbd *sdp = bh->b_private;
+	bh->b_private = NULL;
+
+	end_buffer_write_sync(bh, uptodate);
+	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+		wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
+ * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the buffer_head
+ */
+
+struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct buffer_head *bh;
+
+	bh = sb_getblk(sdp->sd_vfs, blkno);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+	gfs2_log_incr_head(sdp);
+	atomic_inc(&sdp->sd_log_in_flight);
+	bh->b_private = sdp;
+	bh->b_end_io = gfs2_log_write_endio;
+
+	return bh;
+}
+
+/**
+ * gfs2_fake_write_endio - 
+ * @bh: The buffer head
+ * @uptodate: The I/O Status
+ *
+ */
+
+static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
+{
+	struct buffer_head *real_bh = bh->b_private;
+	struct gfs2_bufdata *bd = real_bh->b_private;
+	struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
+
+	end_buffer_write_sync(bh, uptodate);
+	free_buffer_head(bh);
+	unlock_buffer(real_bh);
+	brelse(real_bh);
+	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+		wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
+ * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
+ * @sdp: the filesystem
+ * @data: the data the buffer_head should point to
+ *
+ * Returns: the log buffer descriptor
+ */
+
+struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
+				      struct buffer_head *real)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct buffer_head *bh;
+
+	bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
+	atomic_set(&bh->b_count, 1);
+	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
+	set_bh_page(bh, real->b_page, bh_offset(real));
+	bh->b_blocknr = blkno;
+	bh->b_size = sdp->sd_sb.sb_bsize;
+	bh->b_bdev = sdp->sd_vfs->s_bdev;
+	bh->b_private = real;
+	bh->b_end_io = gfs2_fake_write_endio;
+
+	gfs2_log_incr_head(sdp);
+	atomic_inc(&sdp->sd_log_in_flight);
+
+	return bh;
+}
+
+static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
+{
+	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
+
+	ail2_empty(sdp, new_tail);
+
+	atomic_add(dist, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, dist);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+			     sdp->sd_jdesc->jd_blocks);
+
+	sdp->sd_log_tail = new_tail;
+}
+
+/**
+ * log_write_header - Get and initialize a journal header buffer
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the initialized log buffer descriptor
+ */
+
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct buffer_head *bh;
+	struct gfs2_log_header *lh;
+	unsigned int tail;
+	u32 hash;
+
+	bh = sb_getblk(sdp->sd_vfs, blkno);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+
+	gfs2_ail1_empty(sdp);
+	tail = current_tail(sdp);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.__pad0 = cpu_to_be64(0);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
+	lh->lh_flags = cpu_to_be32(flags);
+	lh->lh_tail = cpu_to_be32(tail);
+	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	bh->b_end_io = end_buffer_write_sync;
+	get_bh(bh);
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
+		submit_bh(WRITE_SYNC | REQ_META, bh);
+	else
+		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+	wait_on_buffer(bh);
+
+	if (!buffer_uptodate(bh))
+		gfs2_io_error_bh(sdp, bh);
+	brelse(bh);
+
+	if (sdp->sd_log_tail != tail)
+		log_pull_tail(sdp, tail);
+	else
+		gfs2_assert_withdraw(sdp, !pull);
+
+	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
+	gfs2_log_incr_head(sdp);
+}
+
+static void log_flush_commit(struct gfs2_sbd *sdp)
+{
+	DEFINE_WAIT(wait);
+
+	if (atomic_read(&sdp->sd_log_in_flight)) {
+		do {
+			prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&sdp->sd_log_in_flight))
+				io_schedule();
+		} while(atomic_read(&sdp->sd_log_in_flight));
+		finish_wait(&sdp->sd_log_flush_wait, &wait);
+	}
+
+	log_write_header(sdp, 0, 0);
+}
+
+static void gfs2_ordered_write(struct gfs2_sbd *sdp)
+{
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
+	LIST_HEAD(written);
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
+		list_move(&bd->bd_le.le_list, &written);
+		bh = bd->bd_bh;
+		if (!buffer_dirty(bh))
+			continue;
+		get_bh(bh);
+		gfs2_log_unlock(sdp);
+		lock_buffer(bh);
+		if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
+			bh->b_end_io = end_buffer_write_sync;
+			submit_bh(WRITE_SYNC, bh);
+		} else {
+			unlock_buffer(bh);
+			brelse(bh);
+		}
+		gfs2_log_lock(sdp);
+	}
+	list_splice(&written, &sdp->sd_log_le_ordered);
+	gfs2_log_unlock(sdp);
+}
+
+static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
+{
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list);
+		bh = bd->bd_bh;
+		if (buffer_locked(bh)) {
+			get_bh(bh);
+			gfs2_log_unlock(sdp);
+			wait_on_buffer(bh);
+			brelse(bh);
+			gfs2_log_lock(sdp);
+			continue;
+		}
+		list_del_init(&bd->bd_le.le_list);
+	}
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_flush - flush incore transaction(s)
+ * @sdp: the filesystem
+ * @gl: The glock structure to flush.  If NULL, flush the whole incore log
+ *
+ */
+
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+{
+	struct gfs2_ail *ai;
+
+	down_write(&sdp->sd_log_flush_lock);
+
+	/* Log might have been flushed while we waited for the flush lock */
+	if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags)) {
+		up_write(&sdp->sd_log_flush_lock);
+		return;
+	}
+	trace_gfs2_log_flush(sdp, 1);
+
+	ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
+	INIT_LIST_HEAD(&ai->ai_ail1_list);
+	INIT_LIST_HEAD(&ai->ai_ail2_list);
+
+	if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
+		printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
+		       sdp->sd_log_commited_buf);
+		gfs2_assert_withdraw(sdp, 0);
+	}
+	if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) {
+		printk(KERN_INFO "GFS2: log databuf %u %u\n",
+		       sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf);
+		gfs2_assert_withdraw(sdp, 0);
+	}
+	gfs2_assert_withdraw(sdp,
+			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+	ai->ai_first = sdp->sd_log_flush_head;
+
+	gfs2_ordered_write(sdp);
+	lops_before_commit(sdp);
+	gfs2_ordered_wait(sdp);
+
+	if (sdp->sd_log_head != sdp->sd_log_flush_head)
+		log_flush_commit(sdp);
+	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
+		gfs2_log_lock(sdp);
+		atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+		trace_gfs2_log_blocks(sdp, -1);
+		gfs2_log_unlock(sdp);
+		log_write_header(sdp, 0, PULL);
+	}
+	lops_after_commit(sdp, ai);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_blks_reserved = 0;
+	sdp->sd_log_commited_buf = 0;
+	sdp->sd_log_commited_databuf = 0;
+	sdp->sd_log_commited_revoke = 0;
+
+	spin_lock(&sdp->sd_ail_lock);
+	if (!list_empty(&ai->ai_ail1_list)) {
+		list_add(&ai->ai_list, &sdp->sd_ail1_list);
+		ai = NULL;
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+	trace_gfs2_log_flush(sdp, 0);
+	up_write(&sdp->sd_log_flush_lock);
+
+	kfree(ai);
+}
+
+static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	unsigned int reserved;
+	unsigned int unused;
+
+	gfs2_log_lock(sdp);
+
+	sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
+	sdp->sd_log_commited_databuf += tr->tr_num_databuf_new -
+		tr->tr_num_databuf_rm;
+	gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) ||
+			     (((int)sdp->sd_log_commited_databuf) >= 0));
+	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
+	reserved = calc_reserved(sdp);
+	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved);
+	unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
+	atomic_add(unused, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, unused);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+			     sdp->sd_jdesc->jd_blocks);
+	sdp->sd_log_blks_reserved = reserved;
+
+	gfs2_log_unlock(sdp);
+}
+
+static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head = &tr->tr_list_buf;
+	struct gfs2_bufdata *bd;
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr);
+		list_del_init(&bd->bd_list_tr);
+		tr->tr_num_buf--;
+	}
+	gfs2_log_unlock(sdp);
+	gfs2_assert_warn(sdp, !tr->tr_num_buf);
+}
+
+/**
+ * gfs2_log_commit - Commit a transaction to the log
+ * @sdp: the filesystem
+ * @tr: the transaction
+ *
+ * We wake up gfs2_logd if the number of pinned blocks exceed thresh1
+ * or the total number of used blocks (pinned blocks plus AIL blocks)
+ * is greater than thresh2.
+ *
+ * At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of
+ * journal size.
+ *
+ * Returns: errno
+ */
+
+void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	log_refund(sdp, tr);
+	buf_lo_incore_commit(sdp, tr);
+
+	up_read(&sdp->sd_log_flush_lock);
+
+	if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
+	    ((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
+	    atomic_read(&sdp->sd_log_thresh2)))
+		wake_up(&sdp->sd_logd_waitq);
+}
+
+/**
+ * gfs2_log_shutdown - write a shutdown header into a journal
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_log_shutdown(struct gfs2_sbd *sdp)
+{
+	down_write(&sdp->sd_log_flush_lock);
+
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf);
+	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+
+	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT,
+			 (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL);
+
+	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
+	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
+	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
+
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_tail = sdp->sd_log_head;
+
+	up_write(&sdp->sd_log_flush_lock);
+}
+
+
+/**
+ * gfs2_meta_syncfs - sync all the buffers in a filesystem
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
+{
+	gfs2_log_flush(sdp, NULL);
+	for (;;) {
+		gfs2_ail1_start(sdp);
+		gfs2_ail1_wait(sdp);
+		if (gfs2_ail1_empty(sdp))
+			break;
+	}
+	gfs2_log_flush(sdp, NULL);
+}
+
+static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
+{
+	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+}
+
+static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
+{
+	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
+	return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
+}
+
+/**
+ * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * Also, periodically check to make sure that we're using the most recent
+ * journal index.
+ */
+
+int gfs2_logd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	unsigned long t = 1;
+	DEFINE_WAIT(wait);
+	unsigned preflush;
+
+	while (!kthread_should_stop()) {
+
+		preflush = atomic_read(&sdp->sd_log_pinned);
+		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
+			gfs2_ail1_empty(sdp);
+			gfs2_log_flush(sdp, NULL);
+		}
+
+		if (gfs2_ail_flush_reqd(sdp)) {
+			gfs2_ail1_start(sdp);
+			gfs2_ail1_wait(sdp);
+			gfs2_ail1_empty(sdp);
+			gfs2_log_flush(sdp, NULL);
+		}
+
+		if (!gfs2_ail_flush_reqd(sdp))
+			wake_up(&sdp->sd_log_waitq);
+
+		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
+		if (freezing(current))
+			refrigerator();
+
+		do {
+			prepare_to_wait(&sdp->sd_logd_waitq, &wait,
+					TASK_INTERRUPTIBLE);
+			if (!gfs2_ail_flush_reqd(sdp) &&
+			    !gfs2_jrnl_flush_reqd(sdp) &&
+			    !kthread_should_stop())
+				t = schedule_timeout(t);
+		} while(t && !gfs2_ail_flush_reqd(sdp) &&
+			!gfs2_jrnl_flush_reqd(sdp) &&
+			!kthread_should_stop());
+		finish_wait(&sdp->sd_logd_waitq, &wait);
+	}
+
+	return 0;
+}
+
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
new file mode 100644
index 00000000..ab062169
--- /dev/null
+++ b/fs/gfs2/log.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LOG_DOT_H__
+#define __LOG_DOT_H__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/writeback.h>
+#include "incore.h"
+
+/**
+ * gfs2_log_lock - acquire the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_lock(struct gfs2_sbd *sdp)
+__acquires(&sdp->sd_log_lock)
+{
+	spin_lock(&sdp->sd_log_lock);
+}
+
+/**
+ * gfs2_log_unlock - release the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_unlock(struct gfs2_sbd *sdp)
+__releases(&sdp->sd_log_lock)
+{
+	spin_unlock(&sdp->sd_log_lock);
+}
+
+static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
+					  unsigned int value)
+{
+	if (++value == sdp->sd_jdesc->jd_blocks) {
+		value = 0;
+	}
+	sdp->sd_log_head = sdp->sd_log_tail = value;
+}
+
+extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			    unsigned int ssize);
+
+extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
+extern void gfs2_log_incr_head(struct gfs2_sbd *sdp);
+
+extern struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
+extern struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
+				      struct buffer_head *real);
+extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
+extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
+extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
+
+extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
+extern void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
+extern int gfs2_logd(void *data);
+
+#endif /* __LOG_DOT_H__ */
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
new file mode 100644
index 00000000..05bbb124
--- /dev/null
+++ b/fs/gfs2/lops.c
@@ -0,0 +1,795 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "inode.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+/**
+ * gfs2_pin - Pin a buffer in memory
+ * @sdp: The superblock
+ * @bh: The buffer to be pinned
+ *
+ * The log lock must be held when calling this function
+ */
+static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	BUG_ON(!current->journal_info);
+
+	clear_buffer_dirty(bh);
+	if (test_set_buffer_pinned(bh))
+		gfs2_assert_withdraw(sdp, 0);
+	if (!buffer_uptodate(bh))
+		gfs2_io_error_bh(sdp, bh);
+	bd = bh->b_private;
+	/* If this buffer is in the AIL and it has already been written
+	 * to in-place disk block, remove it from the AIL.
+	 */
+	spin_lock(&sdp->sd_ail_lock);
+	if (bd->bd_ail)
+		list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
+	spin_unlock(&sdp->sd_ail_lock);
+	get_bh(bh);
+	atomic_inc(&sdp->sd_log_pinned);
+	trace_gfs2_pin(bd, 1);
+}
+
+/**
+ * gfs2_unpin - Unpin a buffer
+ * @sdp: the filesystem the buffer belongs to
+ * @bh: The buffer to unpin
+ * @ai:
+ * @flags: The inode dirty flags
+ *
+ */
+
+static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       struct gfs2_ail *ai)
+{
+	struct gfs2_bufdata *bd = bh->b_private;
+
+	BUG_ON(!buffer_uptodate(bh));
+	BUG_ON(!buffer_pinned(bh));
+
+	lock_buffer(bh);
+	mark_buffer_dirty(bh);
+	clear_buffer_pinned(bh);
+
+	spin_lock(&sdp->sd_ail_lock);
+	if (bd->bd_ail) {
+		list_del(&bd->bd_ail_st_list);
+		brelse(bh);
+	} else {
+		struct gfs2_glock *gl = bd->bd_gl;
+		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
+		atomic_inc(&gl->gl_ail_count);
+	}
+	bd->bd_ail = ai;
+	list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+	spin_unlock(&sdp->sd_ail_lock);
+
+	clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	trace_gfs2_pin(bd, 0);
+	unlock_buffer(bh);
+	atomic_dec(&sdp->sd_log_pinned);
+}
+
+
+static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh)
+{
+	return (struct gfs2_log_descriptor *)bh->b_data;
+}
+
+static inline __be64 *bh_log_ptr(struct buffer_head *bh)
+{
+	struct gfs2_log_descriptor *ld = bh_log_desc(bh);
+	return (__force __be64 *)(ld + 1);
+}
+
+static inline __be64 *bh_ptr_end(struct buffer_head *bh)
+{
+	return (__force __be64 *)(bh->b_data + bh->b_size);
+}
+
+
+static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type)
+{
+	struct buffer_head *bh = gfs2_log_get_buf(sdp);
+	struct gfs2_log_descriptor *ld = bh_log_desc(bh);
+	ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
+	ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
+	ld->ld_type = cpu_to_be32(ld_type);
+	ld->ld_length = 0;
+	ld->ld_data1 = 0;
+	ld->ld_data2 = 0;
+	memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
+	return bh;
+}
+
+static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
+	struct gfs2_meta_header *mh;
+	struct gfs2_trans *tr;
+
+	lock_buffer(bd->bd_bh);
+	gfs2_log_lock(sdp);
+	if (!list_empty(&bd->bd_list_tr))
+		goto out;
+	tr = current->journal_info;
+	tr->tr_touched = 1;
+	tr->tr_num_buf++;
+	list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+	if (!list_empty(&le->le_list))
+		goto out;
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+	gfs2_meta_check(sdp, bd->bd_bh);
+	gfs2_pin(sdp, bd->bd_bh);
+	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
+	mh->__pad0 = cpu_to_be64(0);
+	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	sdp->sd_log_num_buf++;
+	list_add(&le->le_list, &sdp->sd_log_le_buf);
+	tr->tr_num_buf_new++;
+out:
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bd->bd_bh);
+}
+
+static void buf_lo_before_commit(struct gfs2_sbd *sdp)
+{
+	struct buffer_head *bh;
+	struct gfs2_log_descriptor *ld;
+	struct gfs2_bufdata *bd1 = NULL, *bd2;
+	unsigned int total;
+	unsigned int limit;
+	unsigned int num;
+	unsigned n;
+	__be64 *ptr;
+
+	limit = buf_limit(sdp);
+	/* for 4k blocks, limit = 503 */
+
+	gfs2_log_lock(sdp);
+	total = sdp->sd_log_num_buf;
+	bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list);
+	while(total) {
+		num = total;
+		if (total > limit)
+			num = limit;
+		gfs2_log_unlock(sdp);
+		bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA);
+		gfs2_log_lock(sdp);
+		ld = bh_log_desc(bh);
+		ptr = bh_log_ptr(bh);
+		ld->ld_length = cpu_to_be32(num + 1);
+		ld->ld_data1 = cpu_to_be32(num);
+
+		n = 0;
+		list_for_each_entry_continue(bd1, &sdp->sd_log_le_buf,
+					     bd_le.le_list) {
+			*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
+			if (++n >= num)
+				break;
+		}
+
+		gfs2_log_unlock(sdp);
+		submit_bh(WRITE_SYNC, bh);
+		gfs2_log_lock(sdp);
+
+		n = 0;
+		list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
+					     bd_le.le_list) {
+			get_bh(bd2->bd_bh);
+			gfs2_log_unlock(sdp);
+			lock_buffer(bd2->bd_bh);
+			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
+			submit_bh(WRITE_SYNC, bh);
+			gfs2_log_lock(sdp);
+			if (++n >= num)
+				break;
+		}
+
+		BUG_ON(total < num);
+		total -= num;
+	}
+	gfs2_log_unlock(sdp);
+}
+
+static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_buf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
+		sdp->sd_log_num_buf--;
+
+		gfs2_unpin(sdp, bd->bd_bh, ai);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_buf);
+}
+
+static void buf_lo_before_scan(struct gfs2_jdesc *jd,
+			       struct gfs2_log_header_host *head, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (pass != 0)
+		return;
+
+	sdp->sd_found_blocks = 0;
+	sdp->sd_replayed_blocks = 0;
+}
+
+static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				struct gfs2_log_descriptor *ld, __be64 *ptr,
+				int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_METADATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+
+		sdp->sd_found_blocks++;
+
+		if (gfs2_revoke_check(sdp, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		if (gfs2_meta_check(sdp, bh_ip))
+			error = -EIO;
+		else
+			mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+
+		if (error)
+			break;
+
+		sdp->sd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
+	        jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+}
+
+static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
+	struct gfs2_glock *gl = bd->bd_gl;
+	struct gfs2_trans *tr;
+
+	tr = current->journal_info;
+	tr->tr_touched = 1;
+	tr->tr_num_revoke++;
+	sdp->sd_log_num_revoke++;
+	atomic_inc(&gl->gl_revokes);
+	set_bit(GLF_LFLUSH, &gl->gl_flags);
+	list_add(&le->le_list, &sdp->sd_log_le_revoke);
+}
+
+static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
+{
+	struct gfs2_log_descriptor *ld;
+	struct gfs2_meta_header *mh;
+	struct buffer_head *bh;
+	unsigned int offset;
+	struct list_head *head = &sdp->sd_log_le_revoke;
+	struct gfs2_bufdata *bd;
+
+	if (!sdp->sd_log_num_revoke)
+		return;
+
+	bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE);
+	ld = bh_log_desc(bh);
+	ld->ld_length = cpu_to_be32(gfs2_struct2blk(sdp, sdp->sd_log_num_revoke,
+						    sizeof(u64)));
+	ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke);
+	offset = sizeof(struct gfs2_log_descriptor);
+
+	list_for_each_entry(bd, head, bd_le.le_list) {
+		sdp->sd_log_num_revoke--;
+
+		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
+			submit_bh(WRITE_SYNC, bh);
+
+			bh = gfs2_log_get_buf(sdp);
+			mh = (struct gfs2_meta_header *)bh->b_data;
+			mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+			mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB);
+			mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB);
+			offset = sizeof(struct gfs2_meta_header);
+		}
+
+		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno);
+		offset += sizeof(u64);
+	}
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
+
+	submit_bh(WRITE_SYNC, bh);
+}
+
+static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_revoke;
+	struct gfs2_bufdata *bd;
+	struct gfs2_glock *gl;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
+		gl = bd->bd_gl;
+		atomic_dec(&gl->gl_revokes);
+		clear_bit(GLF_LFLUSH, &gl->gl_flags);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+}
+
+static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
+				  struct gfs2_log_header_host *head, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (pass != 0)
+		return;
+
+	sdp->sd_found_revokes = 0;
+	sdp->sd_replay_tail = head->lh_tail;
+}
+
+static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				   struct gfs2_log_descriptor *ld, __be64 *ptr,
+				   int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int blks = be32_to_cpu(ld->ld_length);
+	unsigned int revokes = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh;
+	unsigned int offset;
+	u64 blkno;
+	int first = 1;
+	int error;
+
+	if (pass != 0 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_REVOKE)
+		return 0;
+
+	offset = sizeof(struct gfs2_log_descriptor);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+
+		if (!first)
+			gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LB);
+
+		while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
+			blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
+
+			error = gfs2_revoke_add(sdp, blkno, start);
+			if (error < 0) {
+				brelse(bh);
+				return error;
+			}
+			else if (error)
+				sdp->sd_found_revokes++;
+
+			if (!--revokes)
+				break;
+			offset += sizeof(u64);
+		}
+
+		brelse(bh);
+		offset = sizeof(struct gfs2_meta_header);
+		first = 0;
+	}
+
+	return 0;
+}
+
+static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_revoke_clean(sdp);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	fs_info(sdp, "jid=%u: Found %u revoke tags\n",
+	        jd->jd_jid, sdp->sd_found_revokes);
+
+	gfs2_revoke_clean(sdp);
+}
+
+static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_trans *tr = current->journal_info;
+
+	tr->tr_touched = 1;
+
+	rgd = container_of(le, struct gfs2_rgrpd, rd_le);
+
+	gfs2_log_lock(sdp);
+	if (!list_empty(&le->le_list)){
+		gfs2_log_unlock(sdp);
+		return;
+	}
+	gfs2_rgrp_bh_hold(rgd);
+	sdp->sd_log_num_rg++;
+	list_add(&le->le_list, &sdp->sd_log_le_rg);
+	gfs2_log_unlock(sdp);
+}
+
+static void rg_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_rg;
+	struct gfs2_rgrpd *rgd;
+
+	while (!list_empty(head)) {
+		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_le.le_list);
+		list_del_init(&rgd->rd_le.le_list);
+		sdp->sd_log_num_rg--;
+
+		gfs2_rgrp_repolish_clones(rgd);
+		gfs2_rgrp_bh_put(rgd);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_rg);
+}
+
+/**
+ * databuf_lo_add - Add a databuf to the transaction.
+ *
+ * This is used in two distinct cases:
+ * i) In ordered write mode
+ *    We put the data buffer on a list so that we can ensure that its
+ *    synced to disk at the right time
+ * ii) In journaled data mode
+ *    We need to journal the data block in the same way as metadata in
+ *    the functions above. The difference is that here we have a tag
+ *    which is two __be64's being the block number (as per meta data)
+ *    and a flag which says whether the data block needs escaping or
+ *    not. This means we need a new log entry for each 251 or so data
+ *    blocks, which isn't an enormous overhead but twice as much as
+ *    for normal metadata blocks.
+ */
+static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
+	struct gfs2_trans *tr = current->journal_info;
+	struct address_space *mapping = bd->bd_bh->b_page->mapping;
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+
+	lock_buffer(bd->bd_bh);
+	gfs2_log_lock(sdp);
+	if (tr) {
+		if (!list_empty(&bd->bd_list_tr))
+			goto out;
+		tr->tr_touched = 1;
+		if (gfs2_is_jdata(ip)) {
+			tr->tr_num_buf++;
+			list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+		}
+	}
+	if (!list_empty(&le->le_list))
+		goto out;
+
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+	if (gfs2_is_jdata(ip)) {
+		gfs2_pin(sdp, bd->bd_bh);
+		tr->tr_num_databuf_new++;
+		sdp->sd_log_num_databuf++;
+		list_add_tail(&le->le_list, &sdp->sd_log_le_databuf);
+	} else {
+		list_add_tail(&le->le_list, &sdp->sd_log_le_ordered);
+	}
+out:
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bd->bd_bh);
+}
+
+static void gfs2_check_magic(struct buffer_head *bh)
+{
+	void *kaddr;
+	__be32 *ptr;
+
+	clear_buffer_escaped(bh);
+	kaddr = kmap_atomic(bh->b_page, KM_USER0);
+	ptr = kaddr + bh_offset(bh);
+	if (*ptr == cpu_to_be32(GFS2_MAGIC))
+		set_buffer_escaped(bh);
+	kunmap_atomic(kaddr, KM_USER0);
+}
+
+static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			      struct list_head *list, struct list_head *done,
+			      unsigned int n)
+{
+	struct buffer_head *bh1;
+	struct gfs2_log_descriptor *ld;
+	struct gfs2_bufdata *bd;
+	__be64 *ptr;
+
+	if (!bh)
+		return;
+
+	ld = bh_log_desc(bh);
+	ld->ld_length = cpu_to_be32(n + 1);
+	ld->ld_data1 = cpu_to_be32(n);
+
+	ptr = bh_log_ptr(bh);
+	
+	get_bh(bh);
+	submit_bh(WRITE_SYNC, bh);
+	gfs2_log_lock(sdp);
+	while(!list_empty(list)) {
+		bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
+		list_move_tail(&bd->bd_le.le_list, done);
+		get_bh(bd->bd_bh);
+		while (be64_to_cpu(*ptr) != bd->bd_bh->b_blocknr) {
+			gfs2_log_incr_head(sdp);
+			ptr += 2;
+		}
+		gfs2_log_unlock(sdp);
+		lock_buffer(bd->bd_bh);
+		if (buffer_escaped(bd->bd_bh)) {
+			void *kaddr;
+			bh1 = gfs2_log_get_buf(sdp);
+			kaddr = kmap_atomic(bd->bd_bh->b_page, KM_USER0);
+			memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh),
+			       bh1->b_size);
+			kunmap_atomic(kaddr, KM_USER0);
+			*(__be32 *)bh1->b_data = 0;
+			clear_buffer_escaped(bd->bd_bh);
+			unlock_buffer(bd->bd_bh);
+			brelse(bd->bd_bh);
+		} else {
+			bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
+		}
+		submit_bh(WRITE_SYNC, bh1);
+		gfs2_log_lock(sdp);
+		ptr += 2;
+	}
+	gfs2_log_unlock(sdp);
+	brelse(bh);
+}
+
+/**
+ * databuf_lo_before_commit - Scan the data buffers, writing as we go
+ *
+ */
+
+static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
+{
+	struct gfs2_bufdata *bd = NULL;
+	struct buffer_head *bh = NULL;
+	unsigned int n = 0;
+	__be64 *ptr = NULL, *end = NULL;
+	LIST_HEAD(processed);
+	LIST_HEAD(in_progress);
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(&sdp->sd_log_le_databuf)) {
+		if (ptr == end) {
+			gfs2_log_unlock(sdp);
+			gfs2_write_blocks(sdp, bh, &in_progress, &processed, n);
+			n = 0;
+			bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_JDATA);
+			ptr = bh_log_ptr(bh);
+			end = bh_ptr_end(bh) - 1;
+			gfs2_log_lock(sdp);
+			continue;
+		}
+		bd = list_entry(sdp->sd_log_le_databuf.next, struct gfs2_bufdata, bd_le.le_list);
+		list_move_tail(&bd->bd_le.le_list, &in_progress);
+		gfs2_check_magic(bd->bd_bh);
+		*ptr++ = cpu_to_be64(bd->bd_bh->b_blocknr);
+		*ptr++ = cpu_to_be64(buffer_escaped(bh) ? 1 : 0);
+		n++;
+	}
+	gfs2_log_unlock(sdp);
+	gfs2_write_blocks(sdp, bh, &in_progress, &processed, n);
+	gfs2_log_lock(sdp);
+	list_splice(&processed, &sdp->sd_log_le_databuf);
+	gfs2_log_unlock(sdp);
+}
+
+static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				    struct gfs2_log_descriptor *ld,
+				    __be64 *ptr, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	u64 esc;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_JDATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+		esc = be64_to_cpu(*ptr++);
+
+		sdp->sd_found_blocks++;
+
+		if (gfs2_revoke_check(sdp, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		/* Unescape */
+		if (esc) {
+			__be32 *eptr = (__be32 *)bh_ip->b_data;
+			*eptr = cpu_to_be32(GFS2_MAGIC);
+		}
+		mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+		if (error)
+			break;
+
+		sdp->sd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+/* FIXME: sort out accounting for log blocks etc. */
+
+static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	/* data sync? */
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
+		jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+}
+
+static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_databuf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
+		sdp->sd_log_num_databuf--;
+		gfs2_unpin(sdp, bd->bd_bh, ai);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf);
+}
+
+
+const struct gfs2_log_operations gfs2_buf_lops = {
+	.lo_add = buf_lo_add,
+	.lo_before_commit = buf_lo_before_commit,
+	.lo_after_commit = buf_lo_after_commit,
+	.lo_before_scan = buf_lo_before_scan,
+	.lo_scan_elements = buf_lo_scan_elements,
+	.lo_after_scan = buf_lo_after_scan,
+	.lo_name = "buf",
+};
+
+const struct gfs2_log_operations gfs2_revoke_lops = {
+	.lo_add = revoke_lo_add,
+	.lo_before_commit = revoke_lo_before_commit,
+	.lo_after_commit = revoke_lo_after_commit,
+	.lo_before_scan = revoke_lo_before_scan,
+	.lo_scan_elements = revoke_lo_scan_elements,
+	.lo_after_scan = revoke_lo_after_scan,
+	.lo_name = "revoke",
+};
+
+const struct gfs2_log_operations gfs2_rg_lops = {
+	.lo_add = rg_lo_add,
+	.lo_after_commit = rg_lo_after_commit,
+	.lo_name = "rg",
+};
+
+const struct gfs2_log_operations gfs2_databuf_lops = {
+	.lo_add = databuf_lo_add,
+	.lo_before_commit = databuf_lo_before_commit,
+	.lo_after_commit = databuf_lo_after_commit,
+	.lo_scan_elements = databuf_lo_scan_elements,
+	.lo_after_scan = databuf_lo_after_scan,
+	.lo_name = "databuf",
+};
+
+const struct gfs2_log_operations *gfs2_log_ops[] = {
+	&gfs2_databuf_lops,
+	&gfs2_buf_lops,
+	&gfs2_rg_lops,
+	&gfs2_revoke_lops,
+	NULL,
+};
+
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
new file mode 100644
index 00000000..3c0b2737
--- /dev/null
+++ b/fs/gfs2/lops.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LOPS_DOT_H__
+#define __LOPS_DOT_H__
+
+#include <linux/list.h>
+#include "incore.h"
+
+#define BUF_OFFSET \
+	((sizeof(struct gfs2_log_descriptor) + sizeof(__be64) - 1) & \
+	 ~(sizeof(__be64) - 1))
+#define DATABUF_OFFSET \
+	((sizeof(struct gfs2_log_descriptor) + (2 * sizeof(__be64) - 1)) & \
+	 ~(2 * sizeof(__be64) - 1))
+
+extern const struct gfs2_log_operations gfs2_glock_lops;
+extern const struct gfs2_log_operations gfs2_buf_lops;
+extern const struct gfs2_log_operations gfs2_revoke_lops;
+extern const struct gfs2_log_operations gfs2_rg_lops;
+extern const struct gfs2_log_operations gfs2_databuf_lops;
+
+extern const struct gfs2_log_operations *gfs2_log_ops[];
+
+static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
+{
+	unsigned int limit;
+
+	limit = (sdp->sd_sb.sb_bsize - BUF_OFFSET) / sizeof(__be64);
+	return limit;
+}
+
+static inline unsigned int databuf_limit(struct gfs2_sbd *sdp)
+{
+	unsigned int limit;
+
+	limit = (sdp->sd_sb.sb_bsize - DATABUF_OFFSET) / (2 * sizeof(__be64));
+	return limit;
+}
+
+static inline void lops_init_le(struct gfs2_log_element *le,
+				const struct gfs2_log_operations *lops)
+{
+	INIT_LIST_HEAD(&le->le_list);
+	le->le_ops = lops;
+}
+
+static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	if (le->le_ops->lo_add)
+		le->le_ops->lo_add(sdp, le);
+}
+
+static inline void lops_before_commit(struct gfs2_sbd *sdp)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_commit)
+			gfs2_log_ops[x]->lo_before_commit(sdp);
+}
+
+static inline void lops_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_after_commit)
+			gfs2_log_ops[x]->lo_after_commit(sdp, ai);
+}
+
+static inline void lops_before_scan(struct gfs2_jdesc *jd,
+				    struct gfs2_log_header_host *head,
+				    unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_before_scan(jd, head, pass);
+}
+
+static inline int lops_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				     struct gfs2_log_descriptor *ld,
+				     __be64 *ptr,
+				     unsigned int pass)
+{
+	int x, error;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_scan_elements) {
+			error = gfs2_log_ops[x]->lo_scan_elements(jd, start,
+								  ld, ptr, pass);
+			if (error)
+				return error;
+		}
+
+	return 0;
+}
+
+static inline void lops_after_scan(struct gfs2_jdesc *jd, int error,
+				   unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_after_scan(jd, error, pass);
+}
+
+#endif /* __LOPS_DOT_H__ */
+
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
new file mode 100644
index 00000000..c2b34cd2
--- /dev/null
+++ b/fs/gfs2/main.c
@@ -0,0 +1,215 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <asm/atomic.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+#include "glock.h"
+#include "quota.h"
+#include "recovery.h"
+#include "dir.h"
+
+static struct shrinker qd_shrinker = {
+	.shrink = gfs2_shrink_qd_memory,
+	.seeks = DEFAULT_SEEKS,
+};
+
+static void gfs2_init_inode_once(void *foo)
+{
+	struct gfs2_inode *ip = foo;
+
+	inode_init_once(&ip->i_inode);
+	init_rwsem(&ip->i_rw_mutex);
+	INIT_LIST_HEAD(&ip->i_trunc_list);
+	ip->i_alloc = NULL;
+}
+
+static void gfs2_init_glock_once(void *foo)
+{
+	struct gfs2_glock *gl = foo;
+
+	INIT_HLIST_BL_NODE(&gl->gl_list);
+	spin_lock_init(&gl->gl_spin);
+	INIT_LIST_HEAD(&gl->gl_holders);
+	INIT_LIST_HEAD(&gl->gl_lru);
+	INIT_LIST_HEAD(&gl->gl_ail_list);
+	atomic_set(&gl->gl_ail_count, 0);
+	atomic_set(&gl->gl_revokes, 0);
+}
+
+static void gfs2_init_gl_aspace_once(void *foo)
+{
+	struct gfs2_glock *gl = foo;
+	struct address_space *mapping = (struct address_space *)(gl + 1);
+
+	gfs2_init_glock_once(gl);
+	address_space_init_once(mapping);
+}
+
+/**
+ * init_gfs2_fs - Register GFS2 as a filesystem
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int __init init_gfs2_fs(void)
+{
+	int error;
+
+	gfs2_str2qstr(&gfs2_qdot, ".");
+	gfs2_str2qstr(&gfs2_qdotdot, "..");
+
+	error = gfs2_sys_init();
+	if (error)
+		return error;
+
+	error = gfs2_glock_init();
+	if (error)
+		goto fail;
+
+	error = -ENOMEM;
+	gfs2_glock_cachep = kmem_cache_create("gfs2_glock",
+					      sizeof(struct gfs2_glock),
+					      0, 0,
+					      gfs2_init_glock_once);
+	if (!gfs2_glock_cachep)
+		goto fail;
+
+	gfs2_glock_aspace_cachep = kmem_cache_create("gfs2_glock(aspace)",
+					sizeof(struct gfs2_glock) +
+					sizeof(struct address_space),
+					0, 0, gfs2_init_gl_aspace_once);
+
+	if (!gfs2_glock_aspace_cachep)
+		goto fail;
+
+	gfs2_inode_cachep = kmem_cache_create("gfs2_inode",
+					      sizeof(struct gfs2_inode),
+					      0,  SLAB_RECLAIM_ACCOUNT|
+					          SLAB_MEM_SPREAD,
+					      gfs2_init_inode_once);
+	if (!gfs2_inode_cachep)
+		goto fail;
+
+	gfs2_bufdata_cachep = kmem_cache_create("gfs2_bufdata",
+						sizeof(struct gfs2_bufdata),
+					        0, 0, NULL);
+	if (!gfs2_bufdata_cachep)
+		goto fail;
+
+	gfs2_rgrpd_cachep = kmem_cache_create("gfs2_rgrpd",
+					      sizeof(struct gfs2_rgrpd),
+					      0, 0, NULL);
+	if (!gfs2_rgrpd_cachep)
+		goto fail;
+
+	gfs2_quotad_cachep = kmem_cache_create("gfs2_quotad",
+					       sizeof(struct gfs2_quota_data),
+					       0, 0, NULL);
+	if (!gfs2_quotad_cachep)
+		goto fail;
+
+	register_shrinker(&qd_shrinker);
+
+	error = register_filesystem(&gfs2_fs_type);
+	if (error)
+		goto fail;
+
+	error = register_filesystem(&gfs2meta_fs_type);
+	if (error)
+		goto fail_unregister;
+
+	error = -ENOMEM;
+	gfs_recovery_wq = alloc_workqueue("gfs_recovery",
+					  WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
+	if (!gfs_recovery_wq)
+		goto fail_wq;
+
+	gfs2_register_debugfs();
+
+	printk("GFS2 installed\n");
+
+	return 0;
+
+fail_wq:
+	unregister_filesystem(&gfs2meta_fs_type);
+fail_unregister:
+	unregister_filesystem(&gfs2_fs_type);
+fail:
+	unregister_shrinker(&qd_shrinker);
+	gfs2_glock_exit();
+
+	if (gfs2_quotad_cachep)
+		kmem_cache_destroy(gfs2_quotad_cachep);
+
+	if (gfs2_rgrpd_cachep)
+		kmem_cache_destroy(gfs2_rgrpd_cachep);
+
+	if (gfs2_bufdata_cachep)
+		kmem_cache_destroy(gfs2_bufdata_cachep);
+
+	if (gfs2_inode_cachep)
+		kmem_cache_destroy(gfs2_inode_cachep);
+
+	if (gfs2_glock_aspace_cachep)
+		kmem_cache_destroy(gfs2_glock_aspace_cachep);
+
+	if (gfs2_glock_cachep)
+		kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+	return error;
+}
+
+/**
+ * exit_gfs2_fs - Unregister the file system
+ *
+ */
+
+static void __exit exit_gfs2_fs(void)
+{
+	unregister_shrinker(&qd_shrinker);
+	gfs2_glock_exit();
+	gfs2_unregister_debugfs();
+	unregister_filesystem(&gfs2_fs_type);
+	unregister_filesystem(&gfs2meta_fs_type);
+	destroy_workqueue(gfs_recovery_wq);
+
+	rcu_barrier();
+
+	kmem_cache_destroy(gfs2_quotad_cachep);
+	kmem_cache_destroy(gfs2_rgrpd_cachep);
+	kmem_cache_destroy(gfs2_bufdata_cachep);
+	kmem_cache_destroy(gfs2_inode_cachep);
+	kmem_cache_destroy(gfs2_glock_aspace_cachep);
+	kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+}
+
+MODULE_DESCRIPTION("Global File System");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+module_init(init_gfs2_fs);
+module_exit(exit_gfs2_fs);
+
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
new file mode 100644
index 00000000..747238cd
--- /dev/null
+++ b/fs/gfs2/meta_io.c
@@ -0,0 +1,459 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>
+#include <linux/swap.h>
+#include <linux/delay.h>
+#include <linux/bio.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct buffer_head *bh, *head;
+	int nr_underway = 0;
+	int write_op = REQ_META |
+		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(!page_has_buffers(page));
+
+	head = page_buffers(page);
+	bh = head;
+
+	do {
+		if (!buffer_mapped(bh))
+			continue;
+		/*
+		 * If it's a fully non-blocking write attempt and we cannot
+		 * lock the buffer then redirty the page.  Note that this can
+		 * potentially cause a busy-wait loop from pdflush and kswapd
+		 * activity, but those code paths have their own higher-level
+		 * throttling.
+		 */
+		if (wbc->sync_mode != WB_SYNC_NONE) {
+			lock_buffer(bh);
+		} else if (!trylock_buffer(bh)) {
+			redirty_page_for_writepage(wbc, page);
+			continue;
+		}
+		if (test_clear_buffer_dirty(bh)) {
+			mark_buffer_async_write(bh);
+		} else {
+			unlock_buffer(bh);
+		}
+	} while ((bh = bh->b_this_page) != head);
+
+	/*
+	 * The page and its buffers are protected by PageWriteback(), so we can
+	 * drop the bh refcounts early.
+	 */
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+
+	do {
+		struct buffer_head *next = bh->b_this_page;
+		if (buffer_async_write(bh)) {
+			submit_bh(write_op, bh);
+			nr_underway++;
+		}
+		bh = next;
+	} while (bh != head);
+	unlock_page(page);
+
+	if (nr_underway == 0)
+		end_page_writeback(page);
+
+	return 0;
+}
+
+const struct address_space_operations gfs2_meta_aops = {
+	.writepage = gfs2_aspace_writepage,
+	.releasepage = gfs2_releasepage,
+};
+
+/**
+ * gfs2_meta_sync - Sync all buffers associated with a glock
+ * @gl: The glock
+ *
+ */
+
+void gfs2_meta_sync(struct gfs2_glock *gl)
+{
+	struct address_space *mapping = gfs2_glock2aspace(gl);
+	int error;
+
+	filemap_fdatawrite(mapping);
+	error = filemap_fdatawait(mapping);
+
+	if (error)
+		gfs2_io_error(gl->gl_sbd);
+}
+
+/**
+ * gfs2_getbuf - Get a buffer with a given address space
+ * @gl: the glock
+ * @blkno: the block number (filesystem scope)
+ * @create: 1 if the buffer should be created
+ *
+ * Returns: the buffer
+ */
+
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
+{
+	struct address_space *mapping = gfs2_glock2aspace(gl);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct page *page;
+	struct buffer_head *bh;
+	unsigned int shift;
+	unsigned long index;
+	unsigned int bufnum;
+
+	shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
+	index = blkno >> shift;             /* convert block to page */
+	bufnum = blkno - (index << shift);  /* block buf index within page */
+
+	if (create) {
+		for (;;) {
+			page = grab_cache_page(mapping, index);
+			if (page)
+				break;
+			yield();
+		}
+	} else {
+		page = find_lock_page(mapping, index);
+		if (!page)
+			return NULL;
+	}
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
+
+	/* Locate header for our buffer within our page */
+	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
+		/* Do nothing */;
+	get_bh(bh);
+
+	if (!buffer_mapped(bh))
+		map_bh(bh, sdp->sd_vfs, blkno);
+
+	unlock_page(page);
+	mark_page_accessed(page);
+	page_cache_release(page);
+
+	return bh;
+}
+
+static void meta_prep_new(struct buffer_head *bh)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+
+	lock_buffer(bh);
+	clear_buffer_dirty(bh);
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+
+	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+}
+
+/**
+ * gfs2_meta_new - Get a block
+ * @gl: The glock associated with this block
+ * @blkno: The block number
+ *
+ * Returns: The buffer
+ */
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
+{
+	struct buffer_head *bh;
+	bh = gfs2_getbuf(gl, blkno, CREATE);
+	meta_prep_new(bh);
+	return bh;
+}
+
+/**
+ * gfs2_meta_read - Read a block from disk
+ * @gl: The glock covering the block
+ * @blkno: The block number
+ * @flags: flags
+ * @bhp: the place where the buffer is returned (NULL on failure)
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
+		   struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *bh;
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	*bhp = bh = gfs2_getbuf(gl, blkno, CREATE);
+
+	lock_buffer(bh);
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+	bh->b_end_io = end_buffer_read_sync;
+	get_bh(bh);
+	submit_bh(READ_SYNC | REQ_META, bh);
+	if (!(flags & DIO_WAIT))
+		return 0;
+
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh))) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		brelse(bh);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_meta_wait - Reread a block from disk
+ * @sdp: the filesystem
+ * @bh: The block to wait for
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	wait_on_buffer(bh);
+
+	if (!buffer_uptodate(bh)) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		return -EIO;
+	}
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer
+ * @gl: the glock the buffer belongs to
+ * @bh: The buffer to be attached to
+ * @meta: Flag to indicate whether its metadata or not
+ */
+
+void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
+			 int meta)
+{
+	struct gfs2_bufdata *bd;
+
+	if (meta)
+		lock_page(bh->b_page);
+
+	if (bh->b_private) {
+		if (meta)
+			unlock_page(bh->b_page);
+		return;
+	}
+
+	bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
+	bd->bd_bh = bh;
+	bd->bd_gl = gl;
+
+	INIT_LIST_HEAD(&bd->bd_list_tr);
+	if (meta)
+		lops_init_le(&bd->bd_le, &gfs2_buf_lops);
+	else
+		lops_init_le(&bd->bd_le, &gfs2_databuf_lops);
+	bh->b_private = bd;
+
+	if (meta)
+		unlock_page(bh->b_page);
+}
+
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
+{
+	struct address_space *mapping = bh->b_page->mapping;
+	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
+	struct gfs2_bufdata *bd = bh->b_private;
+
+	if (test_clear_buffer_pinned(bh)) {
+		trace_gfs2_pin(bd, 0);
+		atomic_dec(&sdp->sd_log_pinned);
+		list_del_init(&bd->bd_le.le_list);
+		if (meta) {
+			gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
+			sdp->sd_log_num_buf--;
+			tr->tr_num_buf_rm++;
+		} else {
+			gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
+			sdp->sd_log_num_databuf--;
+			tr->tr_num_databuf_rm++;
+		}
+		tr->tr_touched = 1;
+		brelse(bh);
+	}
+	if (bd) {
+		spin_lock(&sdp->sd_ail_lock);
+		if (bd->bd_ail) {
+			gfs2_remove_from_ail(bd);
+			bh->b_private = NULL;
+			bd->bd_bh = NULL;
+			bd->bd_blkno = bh->b_blocknr;
+			gfs2_trans_add_revoke(sdp, bd);
+		}
+		spin_unlock(&sdp->sd_ail_lock);
+	}
+	clear_buffer_dirty(bh);
+	clear_buffer_uptodate(bh);
+}
+
+/**
+ * gfs2_meta_wipe - make inode's buffers so they aren't dirty/pinned anymore
+ * @ip: the inode who owns the buffers
+ * @bstart: the first buffer in the run
+ * @blen: the number of buffers in the run
+ *
+ */
+
+void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh;
+
+	while (blen) {
+		bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
+		if (bh) {
+			lock_buffer(bh);
+			gfs2_log_lock(sdp);
+			gfs2_remove_from_journal(bh, current->journal_info, 1);
+			gfs2_log_unlock(sdp);
+			unlock_buffer(bh);
+			brelse(bh);
+		}
+
+		bstart++;
+		blen--;
+	}
+}
+
+/**
+ * gfs2_meta_indirect_buffer - Get a metadata buffer
+ * @ip: The GFS2 inode
+ * @height: The level of this buf in the metadata (indir addr) tree (if any)
+ * @num: The block number (device relative) of the buffer
+ * @new: Non-zero if we may create a new buffer
+ * @bhp: the buffer is returned here
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      int new, struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	struct buffer_head *bh;
+	int ret = 0;
+
+	if (new) {
+		BUG_ON(height == 0);
+		bh = gfs2_meta_new(gl, num);
+		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
+		gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
+	} else {
+		u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+		ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh);
+		if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
+			brelse(bh);
+			ret = -EIO;
+		}
+	}
+	*bhp = bh;
+	return ret;
+}
+
+/**
+ * gfs2_meta_ra - start readahead on an extent of a file
+ * @gl: the glock the blocks belong to
+ * @dblock: the starting disk block
+ * @extlen: the number of blocks in the extent
+ *
+ * returns: the first buffer in the extent
+ */
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *first_bh, *bh;
+	u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
+			  sdp->sd_sb.sb_bsize_shift;
+
+	BUG_ON(!extlen);
+
+	if (max_ra < 1)
+		max_ra = 1;
+	if (extlen > max_ra)
+		extlen = max_ra;
+
+	first_bh = gfs2_getbuf(gl, dblock, CREATE);
+
+	if (buffer_uptodate(first_bh))
+		goto out;
+	if (!buffer_locked(first_bh))
+		ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh);
+
+	dblock++;
+	extlen--;
+
+	while (extlen) {
+		bh = gfs2_getbuf(gl, dblock, CREATE);
+
+		if (!buffer_uptodate(bh) && !buffer_locked(bh))
+			ll_rw_block(READA, 1, &bh);
+		brelse(bh);
+		dblock++;
+		extlen--;
+		if (!buffer_locked(first_bh) && buffer_uptodate(first_bh))
+			goto out;
+	}
+
+	wait_on_buffer(first_bh);
+out:
+	return first_bh;
+}
+
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
new file mode 100644
index 00000000..22c52659
--- /dev/null
+++ b/fs/gfs2/meta_io.h
@@ -0,0 +1,82 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __DIO_DOT_H__
+#define __DIO_DOT_H__
+
+#include <linux/buffer_head.h>
+#include <linux/string.h>
+#include "incore.h"
+
+static inline void gfs2_buffer_clear(struct buffer_head *bh)
+{
+	memset(bh->b_data, 0, bh->b_size);
+}
+
+static inline void gfs2_buffer_clear_tail(struct buffer_head *bh, int head)
+{
+	BUG_ON(head > bh->b_size);
+	memset(bh->b_data + head, 0, bh->b_size - head);
+}
+
+static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh,
+					 int to_head,
+					 struct buffer_head *from_bh,
+					 int from_head)
+{
+	BUG_ON(from_head < to_head);
+	memcpy(to_bh->b_data + to_head, from_bh->b_data + from_head,
+	       from_bh->b_size - from_head);
+	memset(to_bh->b_data + to_bh->b_size + to_head - from_head,
+	       0, from_head - to_head);
+}
+
+extern const struct address_space_operations gfs2_meta_aops;
+
+static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
+{
+	struct inode *inode = mapping->host;
+	if (mapping->a_ops == &gfs2_meta_aops)
+		return (((struct gfs2_glock *)mapping) - 1)->gl_sbd;
+	else
+		return inode->i_sb->s_fs_info;
+}
+
+void gfs2_meta_sync(struct gfs2_glock *gl);
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno,
+		   int flags, struct buffer_head **bhp);
+int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create);
+
+void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
+			 int meta);
+
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr,
+			      int meta);
+
+void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
+
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      int new, struct buffer_head **bhp);
+
+static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip,
+					 struct buffer_head **bhp)
+{
+	return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, 0, bhp);
+}
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen);
+
+#define buffer_busy(bh) \
+((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock) | (1ul << BH_Pinned)))
+
+#endif /* __DIO_DOT_H__ */
+
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
new file mode 100644
index 00000000..fa780e66
--- /dev/null
+++ b/fs/gfs2/ops_fstype.c
@@ -0,0 +1,1407 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/kthread.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/quotaops.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+#include "log.h"
+#include "quota.h"
+#include "dir.h"
+#include "trace_gfs2.h"
+
+#define DO 0
+#define UNDO 1
+
+/**
+ * gfs2_tune_init - Fill a gfs2_tune structure with default values
+ * @gt: tune
+ *
+ */
+
+static void gfs2_tune_init(struct gfs2_tune *gt)
+{
+	spin_lock_init(&gt->gt_spin);
+
+	gt->gt_quota_simul_sync = 64;
+	gt->gt_quota_warn_period = 10;
+	gt->gt_quota_scale_num = 1;
+	gt->gt_quota_scale_den = 1;
+	gt->gt_new_files_jdata = 0;
+	gt->gt_max_readahead = 1 << 18;
+	gt->gt_complain_secs = 10;
+}
+
+static struct gfs2_sbd *init_sbd(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp;
+
+	sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
+	if (!sdp)
+		return NULL;
+
+	sb->s_fs_info = sdp;
+	sdp->sd_vfs = sb;
+	set_bit(SDF_NOJOURNALID, &sdp->sd_flags);
+	gfs2_tune_init(&sdp->sd_tune);
+
+	init_waitqueue_head(&sdp->sd_glock_wait);
+	atomic_set(&sdp->sd_glock_disposal, 0);
+	init_completion(&sdp->sd_locking_init);
+	spin_lock_init(&sdp->sd_statfs_spin);
+
+	spin_lock_init(&sdp->sd_rindex_spin);
+	mutex_init(&sdp->sd_rindex_mutex);
+	INIT_LIST_HEAD(&sdp->sd_rindex_list);
+	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
+
+	INIT_LIST_HEAD(&sdp->sd_jindex_list);
+	spin_lock_init(&sdp->sd_jindex_spin);
+	mutex_init(&sdp->sd_jindex_mutex);
+
+	INIT_LIST_HEAD(&sdp->sd_quota_list);
+	mutex_init(&sdp->sd_quota_mutex);
+	init_waitqueue_head(&sdp->sd_quota_wait);
+	INIT_LIST_HEAD(&sdp->sd_trunc_list);
+	spin_lock_init(&sdp->sd_trunc_lock);
+
+	spin_lock_init(&sdp->sd_log_lock);
+	atomic_set(&sdp->sd_log_pinned, 0);
+	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
+	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
+	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
+
+	init_waitqueue_head(&sdp->sd_log_waitq);
+	init_waitqueue_head(&sdp->sd_logd_waitq);
+	spin_lock_init(&sdp->sd_ail_lock);
+	INIT_LIST_HEAD(&sdp->sd_ail1_list);
+	INIT_LIST_HEAD(&sdp->sd_ail2_list);
+
+	init_rwsem(&sdp->sd_log_flush_lock);
+	atomic_set(&sdp->sd_log_in_flight, 0);
+	init_waitqueue_head(&sdp->sd_log_flush_wait);
+
+	INIT_LIST_HEAD(&sdp->sd_revoke_list);
+
+	mutex_init(&sdp->sd_freeze_lock);
+
+	return sdp;
+}
+
+
+/**
+ * gfs2_check_sb - Check superblock
+ * @sdp: the filesystem
+ * @sb: The superblock
+ * @silent: Don't print a message if the check fails
+ *
+ * Checks the version code of the FS is one that we understand how to
+ * read and that the sizes of the various on-disk structures have not
+ * changed.
+ */
+
+static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent)
+{
+	struct gfs2_sb_host *sb = &sdp->sd_sb;
+
+	if (sb->sb_magic != GFS2_MAGIC ||
+	    sb->sb_type != GFS2_METATYPE_SB) {
+		if (!silent)
+			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
+		return -EINVAL;
+	}
+
+	/*  If format numbers match exactly, we're done.  */
+
+	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
+	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
+		return 0;
+
+	fs_warn(sdp, "Unknown on-disk format, unable to mount\n");
+
+	return -EINVAL;
+}
+
+static void end_bio_io_page(struct bio *bio, int error)
+{
+	struct page *page = bio->bi_private;
+
+	if (!error)
+		SetPageUptodate(page);
+	else
+		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
+	unlock_page(page);
+}
+
+static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
+{
+	struct gfs2_sb_host *sb = &sdp->sd_sb;
+	struct super_block *s = sdp->sd_vfs;
+	const struct gfs2_sb *str = buf;
+
+	sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
+	sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
+	sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
+	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
+	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
+	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
+	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
+	sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
+	sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
+	sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
+	sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
+
+	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
+	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
+	memcpy(s->s_uuid, str->sb_uuid, 16);
+}
+
+/**
+ * gfs2_read_super - Read the gfs2 super block from disk
+ * @sdp: The GFS2 super block
+ * @sector: The location of the super block
+ * @error: The error code to return
+ *
+ * This uses the bio functions to read the super block from disk
+ * because we want to be 100% sure that we never read cached data.
+ * A super block is read twice only during each GFS2 mount and is
+ * never written to by the filesystem. The first time its read no
+ * locks are held, and the only details which are looked at are those
+ * relating to the locking protocol. Once locking is up and working,
+ * the sb is read again under the lock to establish the location of
+ * the master directory (contains pointers to journals etc) and the
+ * root directory.
+ *
+ * Returns: 0 on success or error
+ */
+
+static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_sb *p;
+	struct page *page;
+	struct bio *bio;
+
+	page = alloc_page(GFP_NOFS);
+	if (unlikely(!page))
+		return -ENOBUFS;
+
+	ClearPageUptodate(page);
+	ClearPageDirty(page);
+	lock_page(page);
+
+	bio = bio_alloc(GFP_NOFS, 1);
+	bio->bi_sector = sector * (sb->s_blocksize >> 9);
+	bio->bi_bdev = sb->s_bdev;
+	bio_add_page(bio, page, PAGE_SIZE, 0);
+
+	bio->bi_end_io = end_bio_io_page;
+	bio->bi_private = page;
+	submit_bio(READ_SYNC | REQ_META, bio);
+	wait_on_page_locked(page);
+	bio_put(bio);
+	if (!PageUptodate(page)) {
+		__free_page(page);
+		return -EIO;
+	}
+	p = kmap(page);
+	gfs2_sb_in(sdp, p);
+	kunmap(page);
+	__free_page(page);
+	return gfs2_check_sb(sdp, silent);
+}
+
+/**
+ * gfs2_read_sb - Read super block
+ * @sdp: The GFS2 superblock
+ * @silent: Don't print message if mount fails
+ *
+ */
+
+static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
+{
+	u32 hash_blocks, ind_blocks, leaf_blocks;
+	u32 tmp_blocks;
+	unsigned int x;
+	int error;
+
+	error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift, silent);
+	if (error) {
+		if (!silent)
+			fs_err(sdp, "can't read superblock\n");
+		return error;
+	}
+
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+			       GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_dinode)) / sizeof(u64);
+	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
+	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
+	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
+	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
+	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_meta_header)) /
+			        sizeof(struct gfs2_quota_change);
+
+	/* Compute maximum reservation required to add a entry to a directory */
+
+	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
+			     sdp->sd_jbsize);
+
+	ind_blocks = 0;
+	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
+		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
+		ind_blocks += tmp_blocks;
+	}
+
+	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
+
+	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
+
+	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_dinode);
+	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_heightsize[x - 1] || m)
+			break;
+		sdp->sd_heightsize[x] = space;
+	}
+	sdp->sd_max_height = x;
+	sdp->sd_heightsize[x] = ~0;
+	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
+
+	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
+				 sizeof(struct gfs2_dinode);
+	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_jheightsize[x - 1] || m)
+			break;
+		sdp->sd_jheightsize[x] = space;
+	}
+	sdp->sd_max_jheight = x;
+	sdp->sd_jheightsize[x] = ~0;
+	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
+
+	return 0;
+}
+
+static int init_names(struct gfs2_sbd *sdp, int silent)
+{
+	char *proto, *table;
+	int error = 0;
+
+	proto = sdp->sd_args.ar_lockproto;
+	table = sdp->sd_args.ar_locktable;
+
+	/*  Try to autodetect  */
+
+	if (!proto[0] || !table[0]) {
+		error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift, silent);
+		if (error)
+			return error;
+
+		if (!proto[0])
+			proto = sdp->sd_sb.sb_lockproto;
+		if (!table[0])
+			table = sdp->sd_sb.sb_locktable;
+	}
+
+	if (!table[0])
+		table = sdp->sd_vfs->s_id;
+
+	strlcpy(sdp->sd_proto_name, proto, GFS2_FSNAME_LEN);
+	strlcpy(sdp->sd_table_name, table, GFS2_FSNAME_LEN);
+
+	table = sdp->sd_table_name;
+	while ((table = strchr(table, '/')))
+		*table = '_';
+
+	return error;
+}
+
+static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
+			int undo)
+{
+	int error = 0;
+
+	if (undo)
+		goto fail_trans;
+
+	error = gfs2_glock_nq_num(sdp,
+				  GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
+				  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
+				  mount_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire mount glock: %d\n", error);
+		goto fail;
+	}
+
+	error = gfs2_glock_nq_num(sdp,
+				  GFS2_LIVE_LOCK, &gfs2_nondisk_glops,
+				  LM_ST_SHARED,
+				  LM_FLAG_NOEXP | GL_EXACT,
+				  &sdp->sd_live_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire live glock: %d\n", error);
+		goto fail_mount;
+	}
+
+	error = gfs2_glock_get(sdp, GFS2_RENAME_LOCK, &gfs2_nondisk_glops,
+			       CREATE, &sdp->sd_rename_gl);
+	if (error) {
+		fs_err(sdp, "can't create rename glock: %d\n", error);
+		goto fail_live;
+	}
+
+	error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
+			       CREATE, &sdp->sd_trans_gl);
+	if (error) {
+		fs_err(sdp, "can't create transaction glock: %d\n", error);
+		goto fail_rename;
+	}
+
+	return 0;
+
+fail_trans:
+	gfs2_glock_put(sdp->sd_trans_gl);
+fail_rename:
+	gfs2_glock_put(sdp->sd_rename_gl);
+fail_live:
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+fail_mount:
+	gfs2_glock_dq_uninit(mount_gh);
+fail:
+	return error;
+}
+
+static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
+			    u64 no_addr, const char *name)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct dentry *dentry;
+	struct inode *inode;
+
+	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+	if (IS_ERR(inode)) {
+		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
+		return PTR_ERR(inode);
+	}
+	dentry = d_alloc_root(inode);
+	if (!dentry) {
+		fs_err(sdp, "can't alloc %s dentry\n", name);
+		iput(inode);
+		return -ENOMEM;
+	}
+	*dptr = dentry;
+	return 0;
+}
+
+static int init_sb(struct gfs2_sbd *sdp, int silent)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_holder sb_gh;
+	u64 no_addr;
+	int ret;
+
+	ret = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
+				LM_ST_SHARED, 0, &sb_gh);
+	if (ret) {
+		fs_err(sdp, "can't acquire superblock glock: %d\n", ret);
+		return ret;
+	}
+
+	ret = gfs2_read_sb(sdp, silent);
+	if (ret) {
+		fs_err(sdp, "can't read superblock: %d\n", ret);
+		goto out;
+	}
+
+	/* Set up the buffer cache and SB for real */
+	if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) {
+		ret = -EINVAL;
+		fs_err(sdp, "FS block size (%u) is too small for device "
+		       "block size (%u)\n",
+		       sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev));
+		goto out;
+	}
+	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
+		ret = -EINVAL;
+		fs_err(sdp, "FS block size (%u) is too big for machine "
+		       "page size (%u)\n",
+		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
+		goto out;
+	}
+	sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);
+
+	/* Get the root inode */
+	no_addr = sdp->sd_sb.sb_root_dir.no_addr;
+	ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
+	if (ret)
+		goto out;
+
+	/* Get the master inode */
+	no_addr = sdp->sd_sb.sb_master_dir.no_addr;
+	ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
+	if (ret) {
+		dput(sdp->sd_root_dir);
+		goto out;
+	}
+	sb->s_root = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
+out:
+	gfs2_glock_dq_uninit(&sb_gh);
+	return ret;
+}
+
+/**
+ * map_journal_extents - create a reusable "extent" mapping from all logical
+ * blocks to all physical blocks for the given journal.  This will save
+ * us time when writing journal blocks.  Most journals will have only one
+ * extent that maps all their logical blocks.  That's because gfs2.mkfs
+ * arranges the journal blocks sequentially to maximize performance.
+ * So the extent would map the first block for the entire file length.
+ * However, gfs2_jadd can happen while file activity is happening, so
+ * those journals may not be sequential.  Less likely is the case where
+ * the users created their own journals by mounting the metafs and
+ * laying it out.  But it's still possible.  These journals might have
+ * several extents.
+ *
+ * TODO: This should be done in bigger chunks rather than one block at a time,
+ *       but since it's only done at mount time, I'm not worried about the
+ *       time it takes.
+ */
+static int map_journal_extents(struct gfs2_sbd *sdp)
+{
+	struct gfs2_jdesc *jd = sdp->sd_jdesc;
+	unsigned int lb;
+	u64 db, prev_db; /* logical block, disk block, prev disk block */
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_journal_extent *jext = NULL;
+	struct buffer_head bh;
+	int rc = 0;
+
+	prev_db = 0;
+
+	for (lb = 0; lb < i_size_read(jd->jd_inode) >> sdp->sd_sb.sb_bsize_shift; lb++) {
+		bh.b_state = 0;
+		bh.b_blocknr = 0;
+		bh.b_size = 1 << ip->i_inode.i_blkbits;
+		rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
+		db = bh.b_blocknr;
+		if (rc || !db) {
+			printk(KERN_INFO "GFS2 journal mapping error %d: lb="
+			       "%u db=%llu\n", rc, lb, (unsigned long long)db);
+			break;
+		}
+		if (!prev_db || db != prev_db + 1) {
+			jext = kzalloc(sizeof(struct gfs2_journal_extent),
+				       GFP_KERNEL);
+			if (!jext) {
+				printk(KERN_INFO "GFS2 error: out of memory "
+				       "mapping journal extents.\n");
+				rc = -ENOMEM;
+				break;
+			}
+			jext->dblock = db;
+			jext->lblock = lb;
+			jext->blocks = 1;
+			list_add_tail(&jext->extent_list, &jd->extent_list);
+		} else {
+			jext->blocks++;
+		}
+		prev_db = db;
+	}
+	return rc;
+}
+
+static void gfs2_others_may_mount(struct gfs2_sbd *sdp)
+{
+	char *message = "FIRSTMOUNT=Done";
+	char *envp[] = { message, NULL };
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	ls->ls_first_done = 1;
+	kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
+}
+
+/**
+ * gfs2_jindex_hold - Grab a lock on the jindex
+ * @sdp: The GFS2 superblock
+ * @ji_gh: the holder for the jindex glock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
+{
+	struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
+	struct qstr name;
+	char buf[20];
+	struct gfs2_jdesc *jd;
+	int error;
+
+	name.name = buf;
+
+	mutex_lock(&sdp->sd_jindex_mutex);
+
+	for (;;) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, ji_gh);
+		if (error)
+			break;
+
+		name.len = sprintf(buf, "journal%u", sdp->sd_journals);
+		name.hash = gfs2_disk_hash(name.name, name.len);
+
+		error = gfs2_dir_check(sdp->sd_jindex, &name, NULL);
+		if (error == -ENOENT) {
+			error = 0;
+			break;
+		}
+
+		gfs2_glock_dq_uninit(ji_gh);
+
+		if (error)
+			break;
+
+		error = -ENOMEM;
+		jd = kzalloc(sizeof(struct gfs2_jdesc), GFP_KERNEL);
+		if (!jd)
+			break;
+
+		INIT_LIST_HEAD(&jd->extent_list);
+		INIT_WORK(&jd->jd_work, gfs2_recover_func);
+		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
+		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
+			if (!jd->jd_inode)
+				error = -ENOENT;
+			else
+				error = PTR_ERR(jd->jd_inode);
+			kfree(jd);
+			break;
+		}
+
+		spin_lock(&sdp->sd_jindex_spin);
+		jd->jd_jid = sdp->sd_journals++;
+		list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
+		spin_unlock(&sdp->sd_jindex_spin);
+	}
+
+	mutex_unlock(&sdp->sd_jindex_mutex);
+
+	return error;
+}
+
+static int init_journal(struct gfs2_sbd *sdp, int undo)
+{
+	struct inode *master = sdp->sd_master_dir->d_inode;
+	struct gfs2_holder ji_gh;
+	struct gfs2_inode *ip;
+	int jindex = 1;
+	int error = 0;
+
+	if (undo) {
+		jindex = 0;
+		goto fail_jinode_gh;
+	}
+
+	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
+	if (IS_ERR(sdp->sd_jindex)) {
+		fs_err(sdp, "can't lookup journal index: %d\n", error);
+		return PTR_ERR(sdp->sd_jindex);
+	}
+	ip = GFS2_I(sdp->sd_jindex);
+
+	/* Load in the journal index special file */
+
+	error = gfs2_jindex_hold(sdp, &ji_gh);
+	if (error) {
+		fs_err(sdp, "can't read journal index: %d\n", error);
+		goto fail;
+	}
+
+	error = -EUSERS;
+	if (!gfs2_jindex_size(sdp)) {
+		fs_err(sdp, "no journals!\n");
+		goto fail_jindex;
+	}
+
+	if (sdp->sd_args.ar_spectator) {
+		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
+		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+		atomic_set(&sdp->sd_log_thresh1, 2*sdp->sd_jdesc->jd_blocks/5);
+		atomic_set(&sdp->sd_log_thresh2, 4*sdp->sd_jdesc->jd_blocks/5);
+	} else {
+		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
+			fs_err(sdp, "can't mount journal #%u\n",
+			       sdp->sd_lockstruct.ls_jid);
+			fs_err(sdp, "there are only %u journals (0 - %u)\n",
+			       gfs2_jindex_size(sdp),
+			       gfs2_jindex_size(sdp) - 1);
+			goto fail_jindex;
+		}
+		sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);
+
+		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
+					  &gfs2_journal_glops,
+					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
+					  &sdp->sd_journal_gh);
+		if (error) {
+			fs_err(sdp, "can't acquire journal glock: %d\n", error);
+			goto fail_jindex;
+		}
+
+		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
+					   &sdp->sd_jinode_gh);
+		if (error) {
+			fs_err(sdp, "can't acquire journal inode glock: %d\n",
+			       error);
+			goto fail_journal_gh;
+		}
+
+		error = gfs2_jdesc_check(sdp->sd_jdesc);
+		if (error) {
+			fs_err(sdp, "my journal (%u) is bad: %d\n",
+			       sdp->sd_jdesc->jd_jid, error);
+			goto fail_jinode_gh;
+		}
+		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+		atomic_set(&sdp->sd_log_thresh1, 2*sdp->sd_jdesc->jd_blocks/5);
+		atomic_set(&sdp->sd_log_thresh2, 4*sdp->sd_jdesc->jd_blocks/5);
+
+		/* Map the extents for this journal's blocks */
+		map_journal_extents(sdp);
+	}
+	trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free));
+
+	if (sdp->sd_lockstruct.ls_first) {
+		unsigned int x;
+		for (x = 0; x < sdp->sd_journals; x++) {
+			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x),
+						     true);
+			if (error) {
+				fs_err(sdp, "error recovering journal %u: %d\n",
+				       x, error);
+				goto fail_jinode_gh;
+			}
+		}
+
+		gfs2_others_may_mount(sdp);
+	} else if (!sdp->sd_args.ar_spectator) {
+		error = gfs2_recover_journal(sdp->sd_jdesc, true);
+		if (error) {
+			fs_err(sdp, "error recovering my journal: %d\n", error);
+			goto fail_jinode_gh;
+		}
+	}
+
+	set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
+	gfs2_glock_dq_uninit(&ji_gh);
+	jindex = 0;
+
+	return 0;
+
+fail_jinode_gh:
+	if (!sdp->sd_args.ar_spectator)
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+fail_journal_gh:
+	if (!sdp->sd_args.ar_spectator)
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+fail_jindex:
+	gfs2_jindex_free(sdp);
+	if (jindex)
+		gfs2_glock_dq_uninit(&ji_gh);
+fail:
+	iput(sdp->sd_jindex);
+	return error;
+}
+
+
+static int init_inodes(struct gfs2_sbd *sdp, int undo)
+{
+	int error = 0;
+	struct gfs2_inode *ip;
+	struct inode *master = sdp->sd_master_dir->d_inode;
+
+	if (undo)
+		goto fail_qinode;
+
+	error = init_journal(sdp, undo);
+	if (error)
+		goto fail;
+
+	/* Read in the master statfs inode */
+	sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
+	if (IS_ERR(sdp->sd_statfs_inode)) {
+		error = PTR_ERR(sdp->sd_statfs_inode);
+		fs_err(sdp, "can't read in statfs inode: %d\n", error);
+		goto fail_journal;
+	}
+
+	/* Read in the resource index inode */
+	sdp->sd_rindex = gfs2_lookup_simple(master, "rindex");
+	if (IS_ERR(sdp->sd_rindex)) {
+		error = PTR_ERR(sdp->sd_rindex);
+		fs_err(sdp, "can't get resource index inode: %d\n", error);
+		goto fail_statfs;
+	}
+	ip = GFS2_I(sdp->sd_rindex);
+	sdp->sd_rindex_uptodate = 0;
+
+	/* Read in the quota inode */
+	sdp->sd_quota_inode = gfs2_lookup_simple(master, "quota");
+	if (IS_ERR(sdp->sd_quota_inode)) {
+		error = PTR_ERR(sdp->sd_quota_inode);
+		fs_err(sdp, "can't get quota file inode: %d\n", error);
+		goto fail_rindex;
+	}
+	return 0;
+
+fail_qinode:
+	iput(sdp->sd_quota_inode);
+fail_rindex:
+	gfs2_clear_rgrpd(sdp);
+	iput(sdp->sd_rindex);
+fail_statfs:
+	iput(sdp->sd_statfs_inode);
+fail_journal:
+	init_journal(sdp, UNDO);
+fail:
+	return error;
+}
+
+static int init_per_node(struct gfs2_sbd *sdp, int undo)
+{
+	struct inode *pn = NULL;
+	char buf[30];
+	int error = 0;
+	struct gfs2_inode *ip;
+	struct inode *master = sdp->sd_master_dir->d_inode;
+
+	if (sdp->sd_args.ar_spectator)
+		return 0;
+
+	if (undo)
+		goto fail_qc_gh;
+
+	pn = gfs2_lookup_simple(master, "per_node");
+	if (IS_ERR(pn)) {
+		error = PTR_ERR(pn);
+		fs_err(sdp, "can't find per_node directory: %d\n", error);
+		return error;
+	}
+
+	sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_sc_inode)) {
+		error = PTR_ERR(sdp->sd_sc_inode);
+		fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
+		goto fail;
+	}
+
+	sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_qc_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_qc_inode)) {
+		error = PTR_ERR(sdp->sd_qc_inode);
+		fs_err(sdp, "can't find local \"qc\" file: %d\n", error);
+		goto fail_ut_i;
+	}
+
+	iput(pn);
+	pn = NULL;
+
+	ip = GFS2_I(sdp->sd_sc_inode);
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_sc_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
+		goto fail_qc_i;
+	}
+
+	ip = GFS2_I(sdp->sd_qc_inode);
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_qc_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
+		goto fail_ut_gh;
+	}
+
+	return 0;
+
+fail_qc_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+fail_ut_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+fail_qc_i:
+	iput(sdp->sd_qc_inode);
+fail_ut_i:
+	iput(sdp->sd_sc_inode);
+fail:
+	if (pn)
+		iput(pn);
+	return error;
+}
+
+static int init_threads(struct gfs2_sbd *sdp, int undo)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	if (undo)
+		goto fail_quotad;
+
+	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start logd thread: %d\n", error);
+		return error;
+	}
+	sdp->sd_logd_process = p;
+
+	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start quotad thread: %d\n", error);
+		goto fail;
+	}
+	sdp->sd_quotad_process = p;
+
+	return 0;
+
+
+fail_quotad:
+	kthread_stop(sdp->sd_quotad_process);
+fail:
+	kthread_stop(sdp->sd_logd_process);
+	return error;
+}
+
+static const match_table_t nolock_tokens = {
+	{ Opt_jid, "jid=%d\n", },
+	{ Opt_err, NULL },
+};
+
+static const struct lm_lockops nolock_ops = {
+	.lm_proto_name = "lock_nolock",
+	.lm_put_lock = gfs2_glock_free,
+	.lm_tokens = &nolock_tokens,
+};
+
+/**
+ * gfs2_lm_mount - mount a locking protocol
+ * @sdp: the filesystem
+ * @args: mount arguments
+ * @silent: if 1, don't complain if the FS isn't a GFS2 fs
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
+{
+	const struct lm_lockops *lm;
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	struct gfs2_args *args = &sdp->sd_args;
+	const char *proto = sdp->sd_proto_name;
+	const char *table = sdp->sd_table_name;
+	const char *fsname;
+	char *o, *options;
+	int ret;
+
+	if (!strcmp("lock_nolock", proto)) {
+		lm = &nolock_ops;
+		sdp->sd_args.ar_localflocks = 1;
+#ifdef CONFIG_GFS2_FS_LOCKING_DLM
+	} else if (!strcmp("lock_dlm", proto)) {
+		lm = &gfs2_dlm_ops;
+#endif
+	} else {
+		printk(KERN_INFO "GFS2: can't find protocol %s\n", proto);
+		return -ENOENT;
+	}
+
+	fs_info(sdp, "Trying to join cluster \"%s\", \"%s\"\n", proto, table);
+
+	ls->ls_ops = lm;
+	ls->ls_first = 1;
+
+	for (options = args->ar_hostdata; (o = strsep(&options, ":")); ) {
+		substring_t tmp[MAX_OPT_ARGS];
+		int token, option;
+
+		if (!o || !*o)
+			continue;
+
+		token = match_token(o, *lm->lm_tokens, tmp);
+		switch (token) {
+		case Opt_jid:
+			ret = match_int(&tmp[0], &option);
+			if (ret || option < 0) 
+				goto hostdata_error;
+			if (test_and_clear_bit(SDF_NOJOURNALID, &sdp->sd_flags))
+				ls->ls_jid = option;
+			break;
+		case Opt_id:
+			/* Obsolete, but left for backward compat purposes */
+			break;
+		case Opt_first:
+			ret = match_int(&tmp[0], &option);
+			if (ret || (option != 0 && option != 1))
+				goto hostdata_error;
+			ls->ls_first = option;
+			break;
+		case Opt_nodir:
+			ret = match_int(&tmp[0], &option);
+			if (ret || (option != 0 && option != 1))
+				goto hostdata_error;
+			ls->ls_nodir = option;
+			break;
+		case Opt_err:
+		default:
+hostdata_error:
+			fs_info(sdp, "unknown hostdata (%s)\n", o);
+			return -EINVAL;
+		}
+	}
+
+	if (sdp->sd_args.ar_spectator)
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.s", table);
+	else
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", table,
+			 sdp->sd_lockstruct.ls_jid);
+
+	fsname = strchr(table, ':');
+	if (fsname)
+		fsname++;
+	if (lm->lm_mount == NULL) {
+		fs_info(sdp, "Now mounting FS...\n");
+		complete_all(&sdp->sd_locking_init);
+		return 0;
+	}
+	ret = lm->lm_mount(sdp, fsname);
+	if (ret == 0)
+		fs_info(sdp, "Joined cluster. Now mounting FS...\n");
+	complete_all(&sdp->sd_locking_init);
+	return ret;
+}
+
+void gfs2_lm_unmount(struct gfs2_sbd *sdp)
+{
+	const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
+	    lm->lm_unmount)
+		lm->lm_unmount(sdp);
+}
+
+static int gfs2_journalid_wait(void *word)
+{
+	if (signal_pending(current))
+		return -EINTR;
+	schedule();
+	return 0;
+}
+
+static int wait_on_journal(struct gfs2_sbd *sdp)
+{
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		return 0;
+
+	return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, gfs2_journalid_wait, TASK_INTERRUPTIBLE);
+}
+
+void gfs2_online_uevent(struct gfs2_sbd *sdp)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	char ro[20];
+	char spectator[20];
+	char *envp[] = { ro, spectator, NULL };
+	sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
+	sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);
+	kobject_uevent_env(&sdp->sd_kobj, KOBJ_ONLINE, envp);
+}
+
+/**
+ * fill_super - Read in superblock
+ * @sb: The VFS superblock
+ * @data: Mount options
+ * @silent: Don't complain if it's not a GFS2 filesystem
+ *
+ * Returns: errno
+ */
+
+static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent)
+{
+	struct gfs2_sbd *sdp;
+	struct gfs2_holder mount_gh;
+	int error;
+
+	sdp = init_sbd(sb);
+	if (!sdp) {
+		printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n");
+		return -ENOMEM;
+	}
+	sdp->sd_args = *args;
+
+	if (sdp->sd_args.ar_spectator) {
+                sb->s_flags |= MS_RDONLY;
+		set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	}
+	if (sdp->sd_args.ar_posix_acl)
+		sb->s_flags |= MS_POSIXACL;
+	if (sdp->sd_args.ar_nobarrier)
+		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
+
+	sb->s_magic = GFS2_MAGIC;
+	sb->s_op = &gfs2_super_ops;
+	sb->s_d_op = &gfs2_dops;
+	sb->s_export_op = &gfs2_export_ops;
+	sb->s_xattr = gfs2_xattr_handlers;
+	sb->s_qcop = &gfs2_quotactl_ops;
+	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
+	sb->s_time_gran = 1;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
+	/* Set up the buffer cache and fill in some fake block size values
+	   to allow us to read-in the on-disk superblock. */
+	sdp->sd_sb.sb_bsize = sb_min_blocksize(sb, GFS2_BASIC_BLOCK);
+	sdp->sd_sb.sb_bsize_shift = sb->s_blocksize_bits;
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+                               GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+
+	sdp->sd_tune.gt_logd_secs = sdp->sd_args.ar_commit;
+	sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum;
+	if (sdp->sd_args.ar_statfs_quantum) {
+		sdp->sd_tune.gt_statfs_slow = 0;
+		sdp->sd_tune.gt_statfs_quantum = sdp->sd_args.ar_statfs_quantum;
+	} else {
+		sdp->sd_tune.gt_statfs_slow = 1;
+		sdp->sd_tune.gt_statfs_quantum = 30;
+	}
+
+	error = init_names(sdp, silent);
+	if (error)
+		goto fail;
+
+	gfs2_create_debugfs_file(sdp);
+
+	error = gfs2_sys_fs_add(sdp);
+	if (error)
+		goto fail;
+
+	error = gfs2_lm_mount(sdp, silent);
+	if (error)
+		goto fail_sys;
+
+	error = init_locking(sdp, &mount_gh, DO);
+	if (error)
+		goto fail_lm;
+
+	error = init_sb(sdp, silent);
+	if (error)
+		goto fail_locking;
+
+	error = wait_on_journal(sdp);
+	if (error)
+		goto fail_sb;
+
+	/*
+	 * If user space has failed to join the cluster or some similar
+	 * failure has occurred, then the journal id will contain a
+	 * negative (error) number. This will then be returned to the
+	 * caller (of the mount syscall). We do this even for spectator
+	 * mounts (which just write a jid of 0 to indicate "ok" even though
+	 * the jid is unused in the spectator case)
+	 */
+	if (sdp->sd_lockstruct.ls_jid < 0) {
+		error = sdp->sd_lockstruct.ls_jid;
+		sdp->sd_lockstruct.ls_jid = 0;
+		goto fail_sb;
+	}
+
+	error = init_inodes(sdp, DO);
+	if (error)
+		goto fail_sb;
+
+	error = init_per_node(sdp, DO);
+	if (error)
+		goto fail_inodes;
+
+	error = gfs2_statfs_init(sdp);
+	if (error) {
+		fs_err(sdp, "can't initialize statfs subsystem: %d\n", error);
+		goto fail_per_node;
+	}
+
+	error = init_threads(sdp, DO);
+	if (error)
+		goto fail_per_node;
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		error = gfs2_make_fs_rw(sdp);
+		if (error) {
+			fs_err(sdp, "can't make FS RW: %d\n", error);
+			goto fail_threads;
+		}
+	}
+
+	gfs2_glock_dq_uninit(&mount_gh);
+	gfs2_online_uevent(sdp);
+	return 0;
+
+fail_threads:
+	init_threads(sdp, UNDO);
+fail_per_node:
+	init_per_node(sdp, UNDO);
+fail_inodes:
+	init_inodes(sdp, UNDO);
+fail_sb:
+	if (sdp->sd_root_dir)
+		dput(sdp->sd_root_dir);
+	if (sdp->sd_master_dir)
+		dput(sdp->sd_master_dir);
+	if (sb->s_root)
+		dput(sb->s_root);
+	sb->s_root = NULL;
+fail_locking:
+	init_locking(sdp, &mount_gh, UNDO);
+fail_lm:
+	gfs2_gl_hash_clear(sdp);
+	gfs2_lm_unmount(sdp);
+fail_sys:
+	gfs2_sys_fs_del(sdp);
+fail:
+	gfs2_delete_debugfs_file(sdp);
+	kfree(sdp);
+	sb->s_fs_info = NULL;
+	return error;
+}
+
+static int set_gfs2_super(struct super_block *s, void *data)
+{
+	s->s_bdev = data;
+	s->s_dev = s->s_bdev->bd_dev;
+
+	/*
+	 * We set the bdi here to the queue backing, file systems can
+	 * overwrite this in ->fill_super()
+	 */
+	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
+	return 0;
+}
+
+static int test_gfs2_super(struct super_block *s, void *ptr)
+{
+	struct block_device *bdev = ptr;
+	return (bdev == s->s_bdev);
+}
+
+/**
+ * gfs2_mount - Get the GFS2 superblock
+ * @fs_type: The GFS2 filesystem type
+ * @flags: Mount flags
+ * @dev_name: The name of the device
+ * @data: The mount arguments
+ *
+ * Q. Why not use get_sb_bdev() ?
+ * A. We need to select one of two root directories to mount, independent
+ *    of whether this is the initial, or subsequent, mount of this sb
+ *
+ * Returns: 0 or -ve on error
+ */
+
+static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data)
+{
+	struct block_device *bdev;
+	struct super_block *s;
+	fmode_t mode = FMODE_READ | FMODE_EXCL;
+	int error;
+	struct gfs2_args args;
+	struct gfs2_sbd *sdp;
+
+	if (!(flags & MS_RDONLY))
+		mode |= FMODE_WRITE;
+
+	bdev = blkdev_get_by_path(dev_name, mode, fs_type);
+	if (IS_ERR(bdev))
+		return ERR_CAST(bdev);
+
+	/*
+	 * once the super is inserted into the list by sget, s_umount
+	 * will protect the lockfs code from trying to start a snapshot
+	 * while we are mounting
+	 */
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (bdev->bd_fsfreeze_count > 0) {
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		error = -EBUSY;
+		goto error_bdev;
+	}
+	s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev);
+	mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	error = PTR_ERR(s);
+	if (IS_ERR(s))
+		goto error_bdev;
+
+	if (s->s_root)
+		blkdev_put(bdev, mode);
+
+	memset(&args, 0, sizeof(args));
+	args.ar_quota = GFS2_QUOTA_DEFAULT;
+	args.ar_data = GFS2_DATA_DEFAULT;
+	args.ar_commit = 30;
+	args.ar_statfs_quantum = 30;
+	args.ar_quota_quantum = 60;
+	args.ar_errors = GFS2_ERRORS_DEFAULT;
+
+	error = gfs2_mount_args(&args, data);
+	if (error) {
+		printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
+		goto error_super;
+	}
+
+	if (s->s_root) {
+		error = -EBUSY;
+		if ((flags ^ s->s_flags) & MS_RDONLY)
+			goto error_super;
+	} else {
+		char b[BDEVNAME_SIZE];
+
+		s->s_flags = flags;
+		s->s_mode = mode;
+		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		sb_set_blocksize(s, block_size(bdev));
+		error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0);
+		if (error)
+			goto error_super;
+		s->s_flags |= MS_ACTIVE;
+		bdev->bd_super = s;
+	}
+
+	sdp = s->s_fs_info;
+	if (args.ar_meta)
+		return dget(sdp->sd_master_dir);
+	else
+		return dget(sdp->sd_root_dir);
+
+error_super:
+	deactivate_locked_super(s);
+	return ERR_PTR(error);
+error_bdev:
+	blkdev_put(bdev, mode);
+	return ERR_PTR(error);
+}
+
+static int set_meta_super(struct super_block *s, void *ptr)
+{
+	return -EINVAL;
+}
+
+static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type,
+			int flags, const char *dev_name, void *data)
+{
+	struct super_block *s;
+	struct gfs2_sbd *sdp;
+	struct path path;
+	int error;
+
+	error = kern_path(dev_name, LOOKUP_FOLLOW, &path);
+	if (error) {
+		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
+		       dev_name, error);
+		return ERR_PTR(error);
+	}
+	s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super,
+		 path.dentry->d_inode->i_sb->s_bdev);
+	path_put(&path);
+	if (IS_ERR(s)) {
+		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
+		return ERR_CAST(s);
+	}
+	if ((flags ^ s->s_flags) & MS_RDONLY) {
+		deactivate_locked_super(s);
+		return ERR_PTR(-EBUSY);
+	}
+	sdp = s->s_fs_info;
+	return dget(sdp->sd_master_dir);
+}
+
+static void gfs2_kill_sb(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	if (sdp == NULL) {
+		kill_block_super(sb);
+		return;
+	}
+
+	gfs2_meta_syncfs(sdp);
+	dput(sdp->sd_root_dir);
+	dput(sdp->sd_master_dir);
+	sdp->sd_root_dir = NULL;
+	sdp->sd_master_dir = NULL;
+	shrink_dcache_sb(sb);
+	kill_block_super(sb);
+	gfs2_delete_debugfs_file(sdp);
+	kfree(sdp);
+}
+
+struct file_system_type gfs2_fs_type = {
+	.name = "gfs2",
+	.fs_flags = FS_REQUIRES_DEV,
+	.mount = gfs2_mount,
+	.kill_sb = gfs2_kill_sb,
+	.owner = THIS_MODULE,
+};
+
+struct file_system_type gfs2meta_fs_type = {
+	.name = "gfs2meta",
+	.fs_flags = FS_REQUIRES_DEV,
+	.mount = gfs2_mount_meta,
+	.owner = THIS_MODULE,
+};
+
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
new file mode 100644
index 00000000..42e8d23b
--- /dev/null
+++ b/fs/gfs2/quota.c
@@ -0,0 +1,1644 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+/*
+ * Quota change tags are associated with each transaction that allocates or
+ * deallocates space.  Those changes are accumulated locally to each node (in a
+ * per-node file) and then are periodically synced to the quota file.  This
+ * avoids the bottleneck of constantly touching the quota file, but introduces
+ * fuzziness in the current usage value of IDs that are being used on different
+ * nodes in the cluster simultaneously.  So, it is possible for a user on
+ * multiple nodes to overrun their quota, but that overrun is controlable.
+ * Since quota tags are part of transactions, there is no need for a quota check
+ * program to be run on node crashes or anything like that.
+ *
+ * There are couple of knobs that let the administrator manage the quota
+ * fuzziness.  "quota_quantum" sets the maximum time a quota change can be
+ * sitting on one node before being synced to the quota file.  (The default is
+ * 60 seconds.)  Another knob, "quota_scale" controls how quickly the frequency
+ * of quota file syncs increases as the user moves closer to their limit.  The
+ * more frequent the syncs, the more accurate the quota enforcement, but that
+ * means that there is more contention between the nodes for the quota file.
+ * The default value is one.  This sets the maximum theoretical quota overrun
+ * (with infinite node with infinite bandwidth) to twice the user's limit.  (In
+ * practice, the maximum overrun you see should be much less.)  A "quota_scale"
+ * number greater than one makes quota syncs more frequent and reduces the
+ * maximum overrun.  Numbers less than one (but greater than zero) make quota
+ * syncs less frequent.
+ *
+ * GFS quotas also use per-ID Lock Value Blocks (LVBs) to cache the contents of
+ * the quota file, so it is not being constantly read.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/sort.h>
+#include <linux/fs.h>
+#include <linux/bio.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/quota.h>
+#include <linux/dqblk_xfs.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "super.h"
+#include "trans.h"
+#include "inode.h"
+#include "util.h"
+
+#define QUOTA_USER 1
+#define QUOTA_GROUP 0
+
+struct gfs2_quota_change_host {
+	u64 qc_change;
+	u32 qc_flags; /* GFS2_QCF_... */
+	u32 qc_id;
+};
+
+static LIST_HEAD(qd_lru_list);
+static atomic_t qd_lru_count = ATOMIC_INIT(0);
+static DEFINE_SPINLOCK(qd_lru_lock);
+
+int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
+{
+	struct gfs2_quota_data *qd;
+	struct gfs2_sbd *sdp;
+	int nr_to_scan = sc->nr_to_scan;
+
+	if (nr_to_scan == 0)
+		goto out;
+
+	if (!(sc->gfp_mask & __GFP_FS))
+		return -1;
+
+	spin_lock(&qd_lru_lock);
+	while (nr_to_scan && !list_empty(&qd_lru_list)) {
+		qd = list_entry(qd_lru_list.next,
+				struct gfs2_quota_data, qd_reclaim);
+		sdp = qd->qd_gl->gl_sbd;
+
+		/* Free from the filesystem-specific list */
+		list_del(&qd->qd_list);
+
+		gfs2_assert_warn(sdp, !qd->qd_change);
+		gfs2_assert_warn(sdp, !qd->qd_slot_count);
+		gfs2_assert_warn(sdp, !qd->qd_bh_count);
+
+		gfs2_glock_put(qd->qd_gl);
+		atomic_dec(&sdp->sd_quota_count);
+
+		/* Delete it from the common reclaim list */
+		list_del_init(&qd->qd_reclaim);
+		atomic_dec(&qd_lru_count);
+		spin_unlock(&qd_lru_lock);
+		kmem_cache_free(gfs2_quotad_cachep, qd);
+		spin_lock(&qd_lru_lock);
+		nr_to_scan--;
+	}
+	spin_unlock(&qd_lru_lock);
+
+out:
+	return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100;
+}
+
+static u64 qd2offset(struct gfs2_quota_data *qd)
+{
+	u64 offset;
+
+	offset = 2 * (u64)qd->qd_id + !test_bit(QDF_USER, &qd->qd_flags);
+	offset *= sizeof(struct gfs2_quota);
+
+	return offset;
+}
+
+static int qd_alloc(struct gfs2_sbd *sdp, int user, u32 id,
+		    struct gfs2_quota_data **qdp)
+{
+	struct gfs2_quota_data *qd;
+	int error;
+
+	qd = kmem_cache_zalloc(gfs2_quotad_cachep, GFP_NOFS);
+	if (!qd)
+		return -ENOMEM;
+
+	atomic_set(&qd->qd_count, 1);
+	qd->qd_id = id;
+	if (user)
+		set_bit(QDF_USER, &qd->qd_flags);
+	qd->qd_slot = -1;
+	INIT_LIST_HEAD(&qd->qd_reclaim);
+
+	error = gfs2_glock_get(sdp, 2 * (u64)id + !user,
+			      &gfs2_quota_glops, CREATE, &qd->qd_gl);
+	if (error)
+		goto fail;
+
+	*qdp = qd;
+
+	return 0;
+
+fail:
+	kmem_cache_free(gfs2_quotad_cachep, qd);
+	return error;
+}
+
+static int qd_get(struct gfs2_sbd *sdp, int user, u32 id,
+		  struct gfs2_quota_data **qdp)
+{
+	struct gfs2_quota_data *qd = NULL, *new_qd = NULL;
+	int error, found;
+
+	*qdp = NULL;
+
+	for (;;) {
+		found = 0;
+		spin_lock(&qd_lru_lock);
+		list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
+			if (qd->qd_id == id &&
+			    !test_bit(QDF_USER, &qd->qd_flags) == !user) {
+				if (!atomic_read(&qd->qd_count) &&
+				    !list_empty(&qd->qd_reclaim)) {
+					/* Remove it from reclaim list */
+					list_del_init(&qd->qd_reclaim);
+					atomic_dec(&qd_lru_count);
+				}
+				atomic_inc(&qd->qd_count);
+				found = 1;
+				break;
+			}
+		}
+
+		if (!found)
+			qd = NULL;
+
+		if (!qd && new_qd) {
+			qd = new_qd;
+			list_add(&qd->qd_list, &sdp->sd_quota_list);
+			atomic_inc(&sdp->sd_quota_count);
+			new_qd = NULL;
+		}
+
+		spin_unlock(&qd_lru_lock);
+
+		if (qd) {
+			if (new_qd) {
+				gfs2_glock_put(new_qd->qd_gl);
+				kmem_cache_free(gfs2_quotad_cachep, new_qd);
+			}
+			*qdp = qd;
+			return 0;
+		}
+
+		error = qd_alloc(sdp, user, id, &new_qd);
+		if (error)
+			return error;
+	}
+}
+
+static void qd_hold(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	gfs2_assert(sdp, atomic_read(&qd->qd_count));
+	atomic_inc(&qd->qd_count);
+}
+
+static void qd_put(struct gfs2_quota_data *qd)
+{
+	if (atomic_dec_and_lock(&qd->qd_count, &qd_lru_lock)) {
+		/* Add to the reclaim list */
+		list_add_tail(&qd->qd_reclaim, &qd_lru_list);
+		atomic_inc(&qd_lru_count);
+		spin_unlock(&qd_lru_lock);
+	}
+}
+
+static int slot_get(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	unsigned int c, o = 0, b;
+	unsigned char byte = 0;
+
+	spin_lock(&qd_lru_lock);
+
+	if (qd->qd_slot_count++) {
+		spin_unlock(&qd_lru_lock);
+		return 0;
+	}
+
+	for (c = 0; c < sdp->sd_quota_chunks; c++)
+		for (o = 0; o < PAGE_SIZE; o++) {
+			byte = sdp->sd_quota_bitmap[c][o];
+			if (byte != 0xFF)
+				goto found;
+		}
+
+	goto fail;
+
+found:
+	for (b = 0; b < 8; b++)
+		if (!(byte & (1 << b)))
+			break;
+	qd->qd_slot = c * (8 * PAGE_SIZE) + o * 8 + b;
+
+	if (qd->qd_slot >= sdp->sd_quota_slots)
+		goto fail;
+
+	sdp->sd_quota_bitmap[c][o] |= 1 << b;
+
+	spin_unlock(&qd_lru_lock);
+
+	return 0;
+
+fail:
+	qd->qd_slot_count--;
+	spin_unlock(&qd_lru_lock);
+	return -ENOSPC;
+}
+
+static void slot_hold(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+
+	spin_lock(&qd_lru_lock);
+	gfs2_assert(sdp, qd->qd_slot_count);
+	qd->qd_slot_count++;
+	spin_unlock(&qd_lru_lock);
+}
+
+static void slot_put(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+
+	spin_lock(&qd_lru_lock);
+	gfs2_assert(sdp, qd->qd_slot_count);
+	if (!--qd->qd_slot_count) {
+		gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, qd->qd_slot, 0);
+		qd->qd_slot = -1;
+	}
+	spin_unlock(&qd_lru_lock);
+}
+
+static int bh_get(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
+	unsigned int block, offset;
+	struct buffer_head *bh;
+	int error;
+	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
+
+	mutex_lock(&sdp->sd_quota_mutex);
+
+	if (qd->qd_bh_count++) {
+		mutex_unlock(&sdp->sd_quota_mutex);
+		return 0;
+	}
+
+	block = qd->qd_slot / sdp->sd_qc_per_block;
+	offset = qd->qd_slot % sdp->sd_qc_per_block;
+
+	bh_map.b_size = 1 << ip->i_inode.i_blkbits;
+	error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
+	if (error)
+		goto fail;
+	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh);
+	if (error)
+		goto fail;
+	error = -EIO;
+	if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC))
+		goto fail_brelse;
+
+	qd->qd_bh = bh;
+	qd->qd_bh_qc = (struct gfs2_quota_change *)
+		(bh->b_data + sizeof(struct gfs2_meta_header) +
+		 offset * sizeof(struct gfs2_quota_change));
+
+	mutex_unlock(&sdp->sd_quota_mutex);
+
+	return 0;
+
+fail_brelse:
+	brelse(bh);
+fail:
+	qd->qd_bh_count--;
+	mutex_unlock(&sdp->sd_quota_mutex);
+	return error;
+}
+
+static void bh_put(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+
+	mutex_lock(&sdp->sd_quota_mutex);
+	gfs2_assert(sdp, qd->qd_bh_count);
+	if (!--qd->qd_bh_count) {
+		brelse(qd->qd_bh);
+		qd->qd_bh = NULL;
+		qd->qd_bh_qc = NULL;
+	}
+	mutex_unlock(&sdp->sd_quota_mutex);
+}
+
+static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
+{
+	struct gfs2_quota_data *qd = NULL;
+	int error;
+	int found = 0;
+
+	*qdp = NULL;
+
+	if (sdp->sd_vfs->s_flags & MS_RDONLY)
+		return 0;
+
+	spin_lock(&qd_lru_lock);
+
+	list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
+		if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
+		    !test_bit(QDF_CHANGE, &qd->qd_flags) ||
+		    qd->qd_sync_gen >= sdp->sd_quota_sync_gen)
+			continue;
+
+		list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
+
+		set_bit(QDF_LOCKED, &qd->qd_flags);
+		gfs2_assert_warn(sdp, atomic_read(&qd->qd_count));
+		atomic_inc(&qd->qd_count);
+		qd->qd_change_sync = qd->qd_change;
+		gfs2_assert_warn(sdp, qd->qd_slot_count);
+		qd->qd_slot_count++;
+		found = 1;
+
+		break;
+	}
+
+	if (!found)
+		qd = NULL;
+
+	spin_unlock(&qd_lru_lock);
+
+	if (qd) {
+		gfs2_assert_warn(sdp, qd->qd_change_sync);
+		error = bh_get(qd);
+		if (error) {
+			clear_bit(QDF_LOCKED, &qd->qd_flags);
+			slot_put(qd);
+			qd_put(qd);
+			return error;
+		}
+	}
+
+	*qdp = qd;
+
+	return 0;
+}
+
+static int qd_trylock(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+
+	if (sdp->sd_vfs->s_flags & MS_RDONLY)
+		return 0;
+
+	spin_lock(&qd_lru_lock);
+
+	if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
+	    !test_bit(QDF_CHANGE, &qd->qd_flags)) {
+		spin_unlock(&qd_lru_lock);
+		return 0;
+	}
+
+	list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
+
+	set_bit(QDF_LOCKED, &qd->qd_flags);
+	gfs2_assert_warn(sdp, atomic_read(&qd->qd_count));
+	atomic_inc(&qd->qd_count);
+	qd->qd_change_sync = qd->qd_change;
+	gfs2_assert_warn(sdp, qd->qd_slot_count);
+	qd->qd_slot_count++;
+
+	spin_unlock(&qd_lru_lock);
+
+	gfs2_assert_warn(sdp, qd->qd_change_sync);
+	if (bh_get(qd)) {
+		clear_bit(QDF_LOCKED, &qd->qd_flags);
+		slot_put(qd);
+		qd_put(qd);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void qd_unlock(struct gfs2_quota_data *qd)
+{
+	gfs2_assert_warn(qd->qd_gl->gl_sbd,
+			 test_bit(QDF_LOCKED, &qd->qd_flags));
+	clear_bit(QDF_LOCKED, &qd->qd_flags);
+	bh_put(qd);
+	slot_put(qd);
+	qd_put(qd);
+}
+
+static int qdsb_get(struct gfs2_sbd *sdp, int user, u32 id,
+		    struct gfs2_quota_data **qdp)
+{
+	int error;
+
+	error = qd_get(sdp, user, id, qdp);
+	if (error)
+		return error;
+
+	error = slot_get(*qdp);
+	if (error)
+		goto fail;
+
+	error = bh_get(*qdp);
+	if (error)
+		goto fail_slot;
+
+	return 0;
+
+fail_slot:
+	slot_put(*qdp);
+fail:
+	qd_put(*qdp);
+	return error;
+}
+
+static void qdsb_put(struct gfs2_quota_data *qd)
+{
+	bh_put(qd);
+	slot_put(qd);
+	qd_put(qd);
+}
+
+int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_quota_data **qd = al->al_qd;
+	int error;
+
+	if (gfs2_assert_warn(sdp, !al->al_qd_num) ||
+	    gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
+		return -EIO;
+
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	error = qdsb_get(sdp, QUOTA_USER, ip->i_inode.i_uid, qd);
+	if (error)
+		goto out;
+	al->al_qd_num++;
+	qd++;
+
+	error = qdsb_get(sdp, QUOTA_GROUP, ip->i_inode.i_gid, qd);
+	if (error)
+		goto out;
+	al->al_qd_num++;
+	qd++;
+
+	if (uid != NO_QUOTA_CHANGE && uid != ip->i_inode.i_uid) {
+		error = qdsb_get(sdp, QUOTA_USER, uid, qd);
+		if (error)
+			goto out;
+		al->al_qd_num++;
+		qd++;
+	}
+
+	if (gid != NO_QUOTA_CHANGE && gid != ip->i_inode.i_gid) {
+		error = qdsb_get(sdp, QUOTA_GROUP, gid, qd);
+		if (error)
+			goto out;
+		al->al_qd_num++;
+		qd++;
+	}
+
+out:
+	if (error)
+		gfs2_quota_unhold(ip);
+	return error;
+}
+
+void gfs2_quota_unhold(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+	unsigned int x;
+
+	gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
+
+	for (x = 0; x < al->al_qd_num; x++) {
+		qdsb_put(al->al_qd[x]);
+		al->al_qd[x] = NULL;
+	}
+	al->al_qd_num = 0;
+}
+
+static int sort_qd(const void *a, const void *b)
+{
+	const struct gfs2_quota_data *qd_a = *(const struct gfs2_quota_data **)a;
+	const struct gfs2_quota_data *qd_b = *(const struct gfs2_quota_data **)b;
+
+	if (!test_bit(QDF_USER, &qd_a->qd_flags) !=
+	    !test_bit(QDF_USER, &qd_b->qd_flags)) {
+		if (test_bit(QDF_USER, &qd_a->qd_flags))
+			return -1;
+		else
+			return 1;
+	}
+	if (qd_a->qd_id < qd_b->qd_id)
+		return -1;
+	if (qd_a->qd_id > qd_b->qd_id)
+		return 1;
+
+	return 0;
+}
+
+static void do_qc(struct gfs2_quota_data *qd, s64 change)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
+	struct gfs2_quota_change *qc = qd->qd_bh_qc;
+	s64 x;
+
+	mutex_lock(&sdp->sd_quota_mutex);
+	gfs2_trans_add_bh(ip->i_gl, qd->qd_bh, 1);
+
+	if (!test_bit(QDF_CHANGE, &qd->qd_flags)) {
+		qc->qc_change = 0;
+		qc->qc_flags = 0;
+		if (test_bit(QDF_USER, &qd->qd_flags))
+			qc->qc_flags = cpu_to_be32(GFS2_QCF_USER);
+		qc->qc_id = cpu_to_be32(qd->qd_id);
+	}
+
+	x = be64_to_cpu(qc->qc_change) + change;
+	qc->qc_change = cpu_to_be64(x);
+
+	spin_lock(&qd_lru_lock);
+	qd->qd_change = x;
+	spin_unlock(&qd_lru_lock);
+
+	if (!x) {
+		gfs2_assert_warn(sdp, test_bit(QDF_CHANGE, &qd->qd_flags));
+		clear_bit(QDF_CHANGE, &qd->qd_flags);
+		qc->qc_flags = 0;
+		qc->qc_id = 0;
+		slot_put(qd);
+		qd_put(qd);
+	} else if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) {
+		qd_hold(qd);
+		slot_hold(qd);
+	}
+
+	mutex_unlock(&sdp->sd_quota_mutex);
+}
+
+/**
+ * gfs2_adjust_quota - adjust record of current block usage
+ * @ip: The quota inode
+ * @loc: Offset of the entry in the quota file
+ * @change: The amount of usage change to record
+ * @qd: The quota data
+ * @fdq: The updated limits to record
+ *
+ * This function was mostly borrowed from gfs2_block_truncate_page which was
+ * in turn mostly borrowed from ext3
+ *
+ * Returns: 0 or -ve on error
+ */
+
+static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
+			     s64 change, struct gfs2_quota_data *qd,
+			     struct fs_disk_quota *fdq)
+{
+	struct inode *inode = &ip->i_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long index = loc >> PAGE_CACHE_SHIFT;
+	unsigned offset = loc & (PAGE_CACHE_SIZE - 1);
+	unsigned blocksize, iblock, pos;
+	struct buffer_head *bh, *dibh;
+	struct page *page;
+	void *kaddr, *ptr;
+	struct gfs2_quota q, *qp;
+	int err, nbytes;
+	u64 size;
+
+	if (gfs2_is_stuffed(ip))
+		gfs2_unstuff_dinode(ip, NULL);
+
+	memset(&q, 0, sizeof(struct gfs2_quota));
+	err = gfs2_internal_read(ip, NULL, (char *)&q, &loc, sizeof(q));
+	if (err < 0)
+		return err;
+
+	err = -EIO;
+	qp = &q;
+	qp->qu_value = be64_to_cpu(qp->qu_value);
+	qp->qu_value += change;
+	qp->qu_value = cpu_to_be64(qp->qu_value);
+	qd->qd_qb.qb_value = qp->qu_value;
+	if (fdq) {
+		if (fdq->d_fieldmask & FS_DQ_BSOFT) {
+			qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_warn = qp->qu_warn;
+		}
+		if (fdq->d_fieldmask & FS_DQ_BHARD) {
+			qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_limit = qp->qu_limit;
+		}
+		if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
+			qp->qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_value = qp->qu_value;
+		}
+	}
+
+	/* Write the quota into the quota file on disk */
+	ptr = qp;
+	nbytes = sizeof(struct gfs2_quota);
+get_a_page:
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return -ENOMEM;
+
+	blocksize = inode->i_sb->s_blocksize;
+	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
+
+	bh = page_buffers(page);
+	pos = blocksize;
+	while (offset >= pos) {
+		bh = bh->b_this_page;
+		iblock++;
+		pos += blocksize;
+	}
+
+	if (!buffer_mapped(bh)) {
+		gfs2_block_map(inode, iblock, bh, 1);
+		if (!buffer_mapped(bh))
+			goto unlock_out;
+		/* If it's a newly allocated disk block for quota, zero it */
+		if (buffer_new(bh))
+			zero_user(page, pos - blocksize, bh->b_size);
+	}
+
+	if (PageUptodate(page))
+		set_buffer_uptodate(bh);
+
+	if (!buffer_uptodate(bh)) {
+		ll_rw_block(READ_META, 1, &bh);
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh))
+			goto unlock_out;
+	}
+
+	gfs2_trans_add_bh(ip->i_gl, bh, 0);
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	if (offset + sizeof(struct gfs2_quota) > PAGE_CACHE_SIZE)
+		nbytes = PAGE_CACHE_SIZE - offset;
+	memcpy(kaddr + offset, ptr, nbytes);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr, KM_USER0);
+	unlock_page(page);
+	page_cache_release(page);
+
+	/* If quota straddles page boundary, we need to update the rest of the
+	 * quota at the beginning of the next page */
+	if ((offset + sizeof(struct gfs2_quota)) > PAGE_CACHE_SIZE) {
+		ptr = ptr + nbytes;
+		nbytes = sizeof(struct gfs2_quota) - nbytes;
+		offset = 0;
+		index++;
+		goto get_a_page;
+	}
+
+	/* Update the disk inode timestamp and size (if extended) */
+	err = gfs2_meta_inode_buffer(ip, &dibh);
+	if (err)
+		goto out;
+
+	size = loc + sizeof(struct gfs2_quota);
+	if (size > inode->i_size)
+		i_size_write(inode, size);
+	inode->i_mtime = inode->i_atime = CURRENT_TIME;
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+	mark_inode_dirty(inode);
+
+out:
+	return err;
+unlock_out:
+	unlock_page(page);
+	page_cache_release(page);
+	return err;
+}
+
+static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
+{
+	struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
+	unsigned int data_blocks, ind_blocks;
+	struct gfs2_holder *ghs, i_gh;
+	unsigned int qx, x;
+	struct gfs2_quota_data *qd;
+	loff_t offset;
+	unsigned int nalloc = 0, blocks;
+	struct gfs2_alloc *al = NULL;
+	int error;
+
+	gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
+			      &data_blocks, &ind_blocks);
+
+	ghs = kcalloc(num_qd, sizeof(struct gfs2_holder), GFP_NOFS);
+	if (!ghs)
+		return -ENOMEM;
+
+	sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL);
+	mutex_lock_nested(&ip->i_inode.i_mutex, I_MUTEX_QUOTA);
+	for (qx = 0; qx < num_qd; qx++) {
+		error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE,
+					   GL_NOCACHE, &ghs[qx]);
+		if (error)
+			goto out;
+	}
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+	if (error)
+		goto out;
+
+	for (x = 0; x < num_qd; x++) {
+		offset = qd2offset(qda[x]);
+		if (gfs2_write_alloc_required(ip, offset,
+					      sizeof(struct gfs2_quota)))
+			nalloc++;
+	}
+
+	al = gfs2_alloc_get(ip);
+	if (!al) {
+		error = -ENOMEM;
+		goto out_gunlock;
+	}
+	/* 
+	 * 1 blk for unstuffing inode if stuffed. We add this extra
+	 * block to the reservation unconditionally. If the inode
+	 * doesn't need unstuffing, the block will be released to the 
+	 * rgrp since it won't be allocated during the transaction
+	 */
+	al->al_requested = 1;
+	/* +3 in the end for unstuffing block, inode size update block
+	 * and another block in case quota straddles page boundary and 
+	 * two blocks need to be updated instead of 1 */
+	blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3;
+
+	if (nalloc)
+		al->al_requested += nalloc * (data_blocks + ind_blocks);		
+	error = gfs2_inplace_reserve(ip);
+	if (error)
+		goto out_alloc;
+
+	if (nalloc)
+		blocks += gfs2_rg_blocks(al) + nalloc * ind_blocks + RES_STATFS;
+
+	error = gfs2_trans_begin(sdp, blocks, 0);
+	if (error)
+		goto out_ipres;
+
+	for (x = 0; x < num_qd; x++) {
+		qd = qda[x];
+		offset = qd2offset(qd);
+		error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, qd, NULL);
+		if (error)
+			goto out_end_trans;
+
+		do_qc(qd, -qd->qd_change_sync);
+		set_bit(QDF_REFRESH, &qd->qd_flags);
+	}
+
+	error = 0;
+
+out_end_trans:
+	gfs2_trans_end(sdp);
+out_ipres:
+	gfs2_inplace_release(ip);
+out_alloc:
+	gfs2_alloc_put(ip);
+out_gunlock:
+	gfs2_glock_dq_uninit(&i_gh);
+out:
+	while (qx--)
+		gfs2_glock_dq_uninit(&ghs[qx]);
+	mutex_unlock(&ip->i_inode.i_mutex);
+	kfree(ghs);
+	gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl);
+	return error;
+}
+
+static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd)
+{
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
+	struct gfs2_quota q;
+	struct gfs2_quota_lvb *qlvb;
+	loff_t pos;
+	int error;
+
+	memset(&q, 0, sizeof(struct gfs2_quota));
+	pos = qd2offset(qd);
+	error = gfs2_internal_read(ip, NULL, (char *)&q, &pos, sizeof(q));
+	if (error < 0)
+		return error;
+
+	qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb;
+	qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC);
+	qlvb->__pad = 0;
+	qlvb->qb_limit = q.qu_limit;
+	qlvb->qb_warn = q.qu_warn;
+	qlvb->qb_value = q.qu_value;
+	qd->qd_qb = *qlvb;
+
+	return 0;
+}
+
+static int do_glock(struct gfs2_quota_data *qd, int force_refresh,
+		    struct gfs2_holder *q_gh)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
+	struct gfs2_holder i_gh;
+	int error;
+
+restart:
+	error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh);
+	if (error)
+		return error;
+
+	qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb;
+
+	if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) {
+		gfs2_glock_dq_uninit(q_gh);
+		error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE,
+					   GL_NOCACHE, q_gh);
+		if (error)
+			return error;
+
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+		if (error)
+			goto fail;
+
+		error = update_qd(sdp, qd);
+		if (error)
+			goto fail_gunlock;
+
+		gfs2_glock_dq_uninit(&i_gh);
+		gfs2_glock_dq_uninit(q_gh);
+		force_refresh = 0;
+		goto restart;
+	}
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&i_gh);
+fail:
+	gfs2_glock_dq_uninit(q_gh);
+	return error;
+}
+
+int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_quota_data *qd;
+	unsigned int x;
+	int error = 0;
+
+	gfs2_quota_hold(ip, uid, gid);
+
+	if (capable(CAP_SYS_RESOURCE) ||
+	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+		return 0;
+
+	sort(al->al_qd, al->al_qd_num, sizeof(struct gfs2_quota_data *),
+	     sort_qd, NULL);
+
+	for (x = 0; x < al->al_qd_num; x++) {
+		int force = NO_FORCE;
+		qd = al->al_qd[x];
+		if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags))
+			force = FORCE;
+		error = do_glock(qd, force, &al->al_qd_ghs[x]);
+		if (error)
+			break;
+	}
+
+	if (!error)
+		set_bit(GIF_QD_LOCKED, &ip->i_flags);
+	else {
+		while (x--)
+			gfs2_glock_dq_uninit(&al->al_qd_ghs[x]);
+		gfs2_quota_unhold(ip);
+	}
+
+	return error;
+}
+
+static int need_sync(struct gfs2_quota_data *qd)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	s64 value;
+	unsigned int num, den;
+	int do_sync = 1;
+
+	if (!qd->qd_qb.qb_limit)
+		return 0;
+
+	spin_lock(&qd_lru_lock);
+	value = qd->qd_change;
+	spin_unlock(&qd_lru_lock);
+
+	spin_lock(&gt->gt_spin);
+	num = gt->gt_quota_scale_num;
+	den = gt->gt_quota_scale_den;
+	spin_unlock(&gt->gt_spin);
+
+	if (value < 0)
+		do_sync = 0;
+	else if ((s64)be64_to_cpu(qd->qd_qb.qb_value) >=
+		 (s64)be64_to_cpu(qd->qd_qb.qb_limit))
+		do_sync = 0;
+	else {
+		value *= gfs2_jindex_size(sdp) * num;
+		value = div_s64(value, den);
+		value += (s64)be64_to_cpu(qd->qd_qb.qb_value);
+		if (value < (s64)be64_to_cpu(qd->qd_qb.qb_limit))
+			do_sync = 0;
+	}
+
+	return do_sync;
+}
+
+void gfs2_quota_unlock(struct gfs2_inode *ip)
+{
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_quota_data *qda[4];
+	unsigned int count = 0;
+	unsigned int x;
+
+	if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
+		goto out;
+
+	for (x = 0; x < al->al_qd_num; x++) {
+		struct gfs2_quota_data *qd;
+		int sync;
+
+		qd = al->al_qd[x];
+		sync = need_sync(qd);
+
+		gfs2_glock_dq_uninit(&al->al_qd_ghs[x]);
+
+		if (sync && qd_trylock(qd))
+			qda[count++] = qd;
+	}
+
+	if (count) {
+		do_sync(count, qda);
+		for (x = 0; x < count; x++)
+			qd_unlock(qda[x]);
+	}
+
+out:
+	gfs2_quota_unhold(ip);
+}
+
+#define MAX_LINE 256
+
+static int print_message(struct gfs2_quota_data *qd, char *type)
+{
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+
+	printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\n",
+	       sdp->sd_fsname, type,
+	       (test_bit(QDF_USER, &qd->qd_flags)) ? "user" : "group",
+	       qd->qd_id);
+
+	return 0;
+}
+
+int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_quota_data *qd;
+	s64 value;
+	unsigned int x;
+	int error = 0;
+
+	if (!test_bit(GIF_QD_LOCKED, &ip->i_flags))
+		return 0;
+
+        if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+                return 0;
+
+	for (x = 0; x < al->al_qd_num; x++) {
+		qd = al->al_qd[x];
+
+		if (!((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
+		      (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))))
+			continue;
+
+		value = (s64)be64_to_cpu(qd->qd_qb.qb_value);
+		spin_lock(&qd_lru_lock);
+		value += qd->qd_change;
+		spin_unlock(&qd_lru_lock);
+
+		if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) {
+			print_message(qd, "exceeded");
+			quota_send_warning(test_bit(QDF_USER, &qd->qd_flags) ?
+					   USRQUOTA : GRPQUOTA, qd->qd_id,
+					   sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN);
+
+			error = -EDQUOT;
+			break;
+		} else if (be64_to_cpu(qd->qd_qb.qb_warn) &&
+			   (s64)be64_to_cpu(qd->qd_qb.qb_warn) < value &&
+			   time_after_eq(jiffies, qd->qd_last_warn +
+					 gfs2_tune_get(sdp,
+						gt_quota_warn_period) * HZ)) {
+			quota_send_warning(test_bit(QDF_USER, &qd->qd_flags) ?
+					   USRQUOTA : GRPQUOTA, qd->qd_id,
+					   sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN);
+			error = print_message(qd, "warning");
+			qd->qd_last_warn = jiffies;
+		}
+	}
+
+	return error;
+}
+
+void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
+		       u32 uid, u32 gid)
+{
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_quota_data *qd;
+	unsigned int x;
+
+	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
+		return;
+	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
+		return;
+
+	for (x = 0; x < al->al_qd_num; x++) {
+		qd = al->al_qd[x];
+
+		if ((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
+		    (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))) {
+			do_qc(qd, change);
+		}
+	}
+}
+
+int gfs2_quota_sync(struct super_block *sb, int type, int wait)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_quota_data **qda;
+	unsigned int max_qd = gfs2_tune_get(sdp, gt_quota_simul_sync);
+	unsigned int num_qd;
+	unsigned int x;
+	int error = 0;
+
+	sdp->sd_quota_sync_gen++;
+
+	qda = kcalloc(max_qd, sizeof(struct gfs2_quota_data *), GFP_KERNEL);
+	if (!qda)
+		return -ENOMEM;
+
+	do {
+		num_qd = 0;
+
+		for (;;) {
+			error = qd_fish(sdp, qda + num_qd);
+			if (error || !qda[num_qd])
+				break;
+			if (++num_qd == max_qd)
+				break;
+		}
+
+		if (num_qd) {
+			if (!error)
+				error = do_sync(num_qd, qda);
+			if (!error)
+				for (x = 0; x < num_qd; x++)
+					qda[x]->qd_sync_gen =
+						sdp->sd_quota_sync_gen;
+
+			for (x = 0; x < num_qd; x++)
+				qd_unlock(qda[x]);
+		}
+	} while (!error && num_qd == max_qd);
+
+	kfree(qda);
+
+	return error;
+}
+
+static int gfs2_quota_sync_timeo(struct super_block *sb, int type)
+{
+	return gfs2_quota_sync(sb, type, 0);
+}
+
+int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id)
+{
+	struct gfs2_quota_data *qd;
+	struct gfs2_holder q_gh;
+	int error;
+
+	error = qd_get(sdp, user, id, &qd);
+	if (error)
+		return error;
+
+	error = do_glock(qd, FORCE, &q_gh);
+	if (!error)
+		gfs2_glock_dq_uninit(&q_gh);
+
+	qd_put(qd);
+	return error;
+}
+
+static void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf)
+{
+	const struct gfs2_quota_change *str = buf;
+
+	qc->qc_change = be64_to_cpu(str->qc_change);
+	qc->qc_flags = be32_to_cpu(str->qc_flags);
+	qc->qc_id = be32_to_cpu(str->qc_id);
+}
+
+int gfs2_quota_init(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
+	u64 size = i_size_read(sdp->sd_qc_inode);
+	unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift;
+	unsigned int x, slot = 0;
+	unsigned int found = 0;
+	u64 dblock;
+	u32 extlen = 0;
+	int error;
+
+	if (gfs2_check_internal_file_size(sdp->sd_qc_inode, 1, 64 << 20))
+		return -EIO;
+
+	sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block;
+	sdp->sd_quota_chunks = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * PAGE_SIZE);
+
+	error = -ENOMEM;
+
+	sdp->sd_quota_bitmap = kcalloc(sdp->sd_quota_chunks,
+				       sizeof(unsigned char *), GFP_NOFS);
+	if (!sdp->sd_quota_bitmap)
+		return error;
+
+	for (x = 0; x < sdp->sd_quota_chunks; x++) {
+		sdp->sd_quota_bitmap[x] = kzalloc(PAGE_SIZE, GFP_NOFS);
+		if (!sdp->sd_quota_bitmap[x])
+			goto fail;
+	}
+
+	for (x = 0; x < blocks; x++) {
+		struct buffer_head *bh;
+		unsigned int y;
+
+		if (!extlen) {
+			int new = 0;
+			error = gfs2_extent_map(&ip->i_inode, x, &new, &dblock, &extlen);
+			if (error)
+				goto fail;
+		}
+		error = -EIO;
+		bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
+		if (!bh)
+			goto fail;
+		if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) {
+			brelse(bh);
+			goto fail;
+		}
+
+		for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots;
+		     y++, slot++) {
+			struct gfs2_quota_change_host qc;
+			struct gfs2_quota_data *qd;
+
+			gfs2_quota_change_in(&qc, bh->b_data +
+					  sizeof(struct gfs2_meta_header) +
+					  y * sizeof(struct gfs2_quota_change));
+			if (!qc.qc_change)
+				continue;
+
+			error = qd_alloc(sdp, (qc.qc_flags & GFS2_QCF_USER),
+					 qc.qc_id, &qd);
+			if (error) {
+				brelse(bh);
+				goto fail;
+			}
+
+			set_bit(QDF_CHANGE, &qd->qd_flags);
+			qd->qd_change = qc.qc_change;
+			qd->qd_slot = slot;
+			qd->qd_slot_count = 1;
+
+			spin_lock(&qd_lru_lock);
+			gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, slot, 1);
+			list_add(&qd->qd_list, &sdp->sd_quota_list);
+			atomic_inc(&sdp->sd_quota_count);
+			spin_unlock(&qd_lru_lock);
+
+			found++;
+		}
+
+		brelse(bh);
+		dblock++;
+		extlen--;
+	}
+
+	if (found)
+		fs_info(sdp, "found %u quota changes\n", found);
+
+	return 0;
+
+fail:
+	gfs2_quota_cleanup(sdp);
+	return error;
+}
+
+void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
+{
+	struct list_head *head = &sdp->sd_quota_list;
+	struct gfs2_quota_data *qd;
+	unsigned int x;
+
+	spin_lock(&qd_lru_lock);
+	while (!list_empty(head)) {
+		qd = list_entry(head->prev, struct gfs2_quota_data, qd_list);
+
+		if (atomic_read(&qd->qd_count) > 1 ||
+		    (atomic_read(&qd->qd_count) &&
+		     !test_bit(QDF_CHANGE, &qd->qd_flags))) {
+			list_move(&qd->qd_list, head);
+			spin_unlock(&qd_lru_lock);
+			schedule();
+			spin_lock(&qd_lru_lock);
+			continue;
+		}
+
+		list_del(&qd->qd_list);
+		/* Also remove if this qd exists in the reclaim list */
+		if (!list_empty(&qd->qd_reclaim)) {
+			list_del_init(&qd->qd_reclaim);
+			atomic_dec(&qd_lru_count);
+		}
+		atomic_dec(&sdp->sd_quota_count);
+		spin_unlock(&qd_lru_lock);
+
+		if (!atomic_read(&qd->qd_count)) {
+			gfs2_assert_warn(sdp, !qd->qd_change);
+			gfs2_assert_warn(sdp, !qd->qd_slot_count);
+		} else
+			gfs2_assert_warn(sdp, qd->qd_slot_count == 1);
+		gfs2_assert_warn(sdp, !qd->qd_bh_count);
+
+		gfs2_glock_put(qd->qd_gl);
+		kmem_cache_free(gfs2_quotad_cachep, qd);
+
+		spin_lock(&qd_lru_lock);
+	}
+	spin_unlock(&qd_lru_lock);
+
+	gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count));
+
+	if (sdp->sd_quota_bitmap) {
+		for (x = 0; x < sdp->sd_quota_chunks; x++)
+			kfree(sdp->sd_quota_bitmap[x]);
+		kfree(sdp->sd_quota_bitmap);
+	}
+}
+
+static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
+{
+	if (error == 0 || error == -EROFS)
+		return;
+	if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
+}
+
+static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg,
+			       int (*fxn)(struct super_block *sb, int type),
+			       unsigned long t, unsigned long *timeo,
+			       unsigned int *new_timeo)
+{
+	if (t >= *timeo) {
+		int error = fxn(sdp->sd_vfs, 0);
+		quotad_error(sdp, msg, error);
+		*timeo = gfs2_tune_get_i(&sdp->sd_tune, new_timeo) * HZ;
+	} else {
+		*timeo -= t;
+	}
+}
+
+static void quotad_check_trunc_list(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *ip;
+
+	while(1) {
+		ip = NULL;
+		spin_lock(&sdp->sd_trunc_lock);
+		if (!list_empty(&sdp->sd_trunc_list)) {
+			ip = list_entry(sdp->sd_trunc_list.next,
+					struct gfs2_inode, i_trunc_list);
+			list_del_init(&ip->i_trunc_list);
+		}
+		spin_unlock(&sdp->sd_trunc_lock);
+		if (ip == NULL)
+			return;
+		gfs2_glock_finish_truncate(ip);
+	}
+}
+
+void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) {
+	if (!sdp->sd_statfs_force_sync) {
+		sdp->sd_statfs_force_sync = 1;
+		wake_up(&sdp->sd_quota_wait);
+	}
+}
+
+
+/**
+ * gfs2_quotad - Write cached quota changes into the quota file
+ * @sdp: Pointer to GFS2 superblock
+ *
+ */
+
+int gfs2_quotad(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	struct gfs2_tune *tune = &sdp->sd_tune;
+	unsigned long statfs_timeo = 0;
+	unsigned long quotad_timeo = 0;
+	unsigned long t = 0;
+	DEFINE_WAIT(wait);
+	int empty;
+
+	while (!kthread_should_stop()) {
+
+		/* Update the master statfs file */
+		if (sdp->sd_statfs_force_sync) {
+			int error = gfs2_statfs_sync(sdp->sd_vfs, 0);
+			quotad_error(sdp, "statfs", error);
+			statfs_timeo = gfs2_tune_get(sdp, gt_statfs_quantum) * HZ;
+		}
+		else
+			quotad_check_timeo(sdp, "statfs", gfs2_statfs_sync, t,
+				   	   &statfs_timeo,
+					   &tune->gt_statfs_quantum);
+
+		/* Update quota file */
+		quotad_check_timeo(sdp, "sync", gfs2_quota_sync_timeo, t,
+				   &quotad_timeo, &tune->gt_quota_quantum);
+
+		/* Check for & recover partially truncated inodes */
+		quotad_check_trunc_list(sdp);
+
+		if (freezing(current))
+			refrigerator();
+		t = min(quotad_timeo, statfs_timeo);
+
+		prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE);
+		spin_lock(&sdp->sd_trunc_lock);
+		empty = list_empty(&sdp->sd_trunc_list);
+		spin_unlock(&sdp->sd_trunc_lock);
+		if (empty && !sdp->sd_statfs_force_sync)
+			t -= schedule_timeout(t);
+		else
+			t = 0;
+		finish_wait(&sdp->sd_quota_wait, &wait);
+	}
+
+	return 0;
+}
+
+static int gfs2_quota_get_xstate(struct super_block *sb,
+				 struct fs_quota_stat *fqs)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	memset(fqs, 0, sizeof(struct fs_quota_stat));
+	fqs->qs_version = FS_QSTAT_VERSION;
+
+	switch (sdp->sd_args.ar_quota) {
+	case GFS2_QUOTA_ON:
+		fqs->qs_flags |= (FS_QUOTA_UDQ_ENFD | FS_QUOTA_GDQ_ENFD);
+		/*FALLTHRU*/
+	case GFS2_QUOTA_ACCOUNT:
+		fqs->qs_flags |= (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT);
+		break;
+	case GFS2_QUOTA_OFF:
+		break;
+	}
+
+	if (sdp->sd_quota_inode) {
+		fqs->qs_uquota.qfs_ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr;
+		fqs->qs_uquota.qfs_nblks = sdp->sd_quota_inode->i_blocks;
+	}
+	fqs->qs_uquota.qfs_nextents = 1; /* unsupported */
+	fqs->qs_gquota = fqs->qs_uquota; /* its the same inode in both cases */
+	fqs->qs_incoredqs = atomic_read(&qd_lru_count);
+	return 0;
+}
+
+static int gfs2_get_dqblk(struct super_block *sb, int type, qid_t id,
+			  struct fs_disk_quota *fdq)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_quota_lvb *qlvb;
+	struct gfs2_quota_data *qd;
+	struct gfs2_holder q_gh;
+	int error;
+
+	memset(fdq, 0, sizeof(struct fs_disk_quota));
+
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return -ESRCH; /* Crazy XFS error code */
+
+	if (type == USRQUOTA)
+		type = QUOTA_USER;
+	else if (type == GRPQUOTA)
+		type = QUOTA_GROUP;
+	else
+		return -EINVAL;
+
+	error = qd_get(sdp, type, id, &qd);
+	if (error)
+		return error;
+	error = do_glock(qd, FORCE, &q_gh);
+	if (error)
+		goto out;
+
+	qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb;
+	fdq->d_version = FS_DQUOT_VERSION;
+	fdq->d_flags = (type == QUOTA_USER) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
+	fdq->d_id = id;
+	fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift;
+	fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift;
+	fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift;
+
+	gfs2_glock_dq_uninit(&q_gh);
+out:
+	qd_put(qd);
+	return error;
+}
+
+/* GFS2 only supports a subset of the XFS fields */
+#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
+
+static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
+			  struct fs_disk_quota *fdq)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
+	struct gfs2_quota_data *qd;
+	struct gfs2_holder q_gh, i_gh;
+	unsigned int data_blocks, ind_blocks;
+	unsigned int blocks = 0;
+	int alloc_required;
+	struct gfs2_alloc *al;
+	loff_t offset;
+	int error;
+
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return -ESRCH; /* Crazy XFS error code */
+
+	switch(type) {
+	case USRQUOTA:
+		type = QUOTA_USER;
+		if (fdq->d_flags != FS_USER_QUOTA)
+			return -EINVAL;
+		break;
+	case GRPQUOTA:
+		type = QUOTA_GROUP;
+		if (fdq->d_flags != FS_GROUP_QUOTA)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (fdq->d_fieldmask & ~GFS2_FIELDMASK)
+		return -EINVAL;
+	if (fdq->d_id != id)
+		return -EINVAL;
+
+	error = qd_get(sdp, type, id, &qd);
+	if (error)
+		return error;
+
+	mutex_lock(&ip->i_inode.i_mutex);
+	error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, 0, &q_gh);
+	if (error)
+		goto out_put;
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+	if (error)
+		goto out_q;
+
+	/* Check for existing entry, if none then alloc new blocks */
+	error = update_qd(sdp, qd);
+	if (error)
+		goto out_i;
+
+	/* If nothing has changed, this is a no-op */
+	if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
+	    ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
+		fdq->d_fieldmask ^= FS_DQ_BSOFT;
+
+	if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
+	    ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
+		fdq->d_fieldmask ^= FS_DQ_BHARD;
+
+	if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
+	    ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
+		fdq->d_fieldmask ^= FS_DQ_BCOUNT;
+
+	if (fdq->d_fieldmask == 0)
+		goto out_i;
+
+	offset = qd2offset(qd);
+	alloc_required = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota));
+	if (gfs2_is_stuffed(ip))
+		alloc_required = 1;
+	if (alloc_required) {
+		al = gfs2_alloc_get(ip);
+		if (al == NULL)
+			goto out_i;
+		gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
+				       &data_blocks, &ind_blocks);
+		blocks = al->al_requested = 1 + data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto out_alloc;
+		blocks += gfs2_rg_blocks(al);
+	}
+
+	/* Some quotas span block boundaries and can update two blocks,
+	   adding an extra block to the transaction to handle such quotas */
+	error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 2, 0);
+	if (error)
+		goto out_release;
+
+	/* Apply changes */
+	error = gfs2_adjust_quota(ip, offset, 0, qd, fdq);
+
+	gfs2_trans_end(sdp);
+out_release:
+	if (alloc_required) {
+		gfs2_inplace_release(ip);
+out_alloc:
+		gfs2_alloc_put(ip);
+	}
+out_i:
+	gfs2_glock_dq_uninit(&i_gh);
+out_q:
+	gfs2_glock_dq_uninit(&q_gh);
+out_put:
+	mutex_unlock(&ip->i_inode.i_mutex);
+	qd_put(qd);
+	return error;
+}
+
+const struct quotactl_ops gfs2_quotactl_ops = {
+	.quota_sync     = gfs2_quota_sync,
+	.get_xstate     = gfs2_quota_get_xstate,
+	.get_dqblk	= gfs2_get_dqblk,
+	.set_dqblk	= gfs2_set_dqblk,
+};
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
new file mode 100644
index 00000000..90bf1c30
--- /dev/null
+++ b/fs/gfs2/quota.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __QUOTA_DOT_H__
+#define __QUOTA_DOT_H__
+
+struct gfs2_inode;
+struct gfs2_sbd;
+struct shrink_control;
+
+#define NO_QUOTA_CHANGE ((u32)-1)
+
+extern int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid);
+extern void gfs2_quota_unhold(struct gfs2_inode *ip);
+
+extern int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid);
+extern void gfs2_quota_unlock(struct gfs2_inode *ip);
+
+extern int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid);
+extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
+			      u32 uid, u32 gid);
+
+extern int gfs2_quota_sync(struct super_block *sb, int type, int wait);
+extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id);
+
+extern int gfs2_quota_init(struct gfs2_sbd *sdp);
+extern void gfs2_quota_cleanup(struct gfs2_sbd *sdp);
+extern int gfs2_quotad(void *data);
+
+extern void gfs2_wake_up_statfs(struct gfs2_sbd *sdp);
+
+static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int ret;
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+	ret = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (ret)
+		return ret;
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+		return 0;
+	ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
+	if (ret)
+		gfs2_quota_unlock(ip);
+	return ret;
+}
+
+extern int gfs2_shrink_qd_memory(struct shrinker *shrink,
+				 struct shrink_control *sc);
+extern const struct quotactl_ops gfs2_quotactl_ops;
+
+#endif /* __QUOTA_DOT_H__ */
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
new file mode 100644
index 00000000..f2a02edc
--- /dev/null
+++ b/fs/gfs2/recovery.c
@@ -0,0 +1,610 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "super.h"
+#include "util.h"
+#include "dir.h"
+
+struct workqueue_struct *gfs_recovery_wq;
+
+int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
+			   struct buffer_head **bh)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	int new = 0;
+	u64 dblock;
+	u32 extlen;
+	int error;
+
+	error = gfs2_extent_map(&ip->i_inode, blk, &new, &dblock, &extlen);
+	if (error)
+		return error;
+	if (!dblock) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	*bh = gfs2_meta_ra(gl, dblock, extlen);
+
+	return error;
+}
+
+int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
+{
+	struct list_head *head = &sdp->sd_revoke_list;
+	struct gfs2_revoke_replay *rr;
+	int found = 0;
+
+	list_for_each_entry(rr, head, rr_list) {
+		if (rr->rr_blkno == blkno) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (found) {
+		rr->rr_where = where;
+		return 0;
+	}
+
+	rr = kmalloc(sizeof(struct gfs2_revoke_replay), GFP_NOFS);
+	if (!rr)
+		return -ENOMEM;
+
+	rr->rr_blkno = blkno;
+	rr->rr_where = where;
+	list_add(&rr->rr_list, head);
+
+	return 1;
+}
+
+int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
+{
+	struct gfs2_revoke_replay *rr;
+	int wrap, a, b, revoke;
+	int found = 0;
+
+	list_for_each_entry(rr, &sdp->sd_revoke_list, rr_list) {
+		if (rr->rr_blkno == blkno) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return 0;
+
+	wrap = (rr->rr_where < sdp->sd_replay_tail);
+	a = (sdp->sd_replay_tail < where);
+	b = (where < rr->rr_where);
+	revoke = (wrap) ? (a || b) : (a && b);
+
+	return revoke;
+}
+
+void gfs2_revoke_clean(struct gfs2_sbd *sdp)
+{
+	struct list_head *head = &sdp->sd_revoke_list;
+	struct gfs2_revoke_replay *rr;
+
+	while (!list_empty(head)) {
+		rr = list_entry(head->next, struct gfs2_revoke_replay, rr_list);
+		list_del(&rr->rr_list);
+		kfree(rr);
+	}
+}
+
+static int gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf)
+{
+	const struct gfs2_log_header *str = buf;
+
+	if (str->lh_header.mh_magic != cpu_to_be32(GFS2_MAGIC) ||
+	    str->lh_header.mh_type != cpu_to_be32(GFS2_METATYPE_LH))
+		return 1;
+
+	lh->lh_sequence = be64_to_cpu(str->lh_sequence);
+	lh->lh_flags = be32_to_cpu(str->lh_flags);
+	lh->lh_tail = be32_to_cpu(str->lh_tail);
+	lh->lh_blkno = be32_to_cpu(str->lh_blkno);
+	lh->lh_hash = be32_to_cpu(str->lh_hash);
+	return 0;
+}
+
+/**
+ * get_log_header - read the log header for a given segment
+ * @jd: the journal
+ * @blk: the block to look at
+ * @lh: the log header to return
+ *
+ * Read the log header for a given segement in a given journal.  Do a few
+ * sanity checks on it.
+ *
+ * Returns: 0 on success,
+ *          1 if the header was invalid or incomplete,
+ *          errno on error
+ */
+
+static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk,
+			  struct gfs2_log_header_host *head)
+{
+	struct buffer_head *bh;
+	struct gfs2_log_header_host uninitialized_var(lh);
+	const u32 nothing = 0;
+	u32 hash;
+	int error;
+
+	error = gfs2_replay_read_block(jd, blk, &bh);
+	if (error)
+		return error;
+
+	hash = crc32_le((u32)~0, bh->b_data, sizeof(struct gfs2_log_header) -
+					     sizeof(u32));
+	hash = crc32_le(hash, (unsigned char const *)&nothing, sizeof(nothing));
+	hash ^= (u32)~0;
+	error = gfs2_log_header_in(&lh, bh->b_data);
+	brelse(bh);
+
+	if (error || lh.lh_blkno != blk || lh.lh_hash != hash)
+		return 1;
+
+	*head = lh;
+
+	return 0;
+}
+
+/**
+ * find_good_lh - find a good log header
+ * @jd: the journal
+ * @blk: the segment to start searching from
+ * @lh: the log header to fill in
+ * @forward: if true search forward in the log, else search backward
+ *
+ * Call get_log_header() to get a log header for a segment, but if the
+ * segment is bad, either scan forward or backward until we find a good one.
+ *
+ * Returns: errno
+ */
+
+static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk,
+			struct gfs2_log_header_host *head)
+{
+	unsigned int orig_blk = *blk;
+	int error;
+
+	for (;;) {
+		error = get_log_header(jd, *blk, head);
+		if (error <= 0)
+			return error;
+
+		if (++*blk == jd->jd_blocks)
+			*blk = 0;
+
+		if (*blk == orig_blk) {
+			gfs2_consist_inode(GFS2_I(jd->jd_inode));
+			return -EIO;
+		}
+	}
+}
+
+/**
+ * jhead_scan - make sure we've found the head of the log
+ * @jd: the journal
+ * @head: this is filled in with the log descriptor of the head
+ *
+ * At this point, seg and lh should be either the head of the log or just
+ * before.  Scan forward until we find the head.
+ *
+ * Returns: errno
+ */
+
+static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	unsigned int blk = head->lh_blkno;
+	struct gfs2_log_header_host lh;
+	int error;
+
+	for (;;) {
+		if (++blk == jd->jd_blocks)
+			blk = 0;
+
+		error = get_log_header(jd, blk, &lh);
+		if (error < 0)
+			return error;
+		if (error == 1)
+			continue;
+
+		if (lh.lh_sequence == head->lh_sequence) {
+			gfs2_consist_inode(GFS2_I(jd->jd_inode));
+			return -EIO;
+		}
+		if (lh.lh_sequence < head->lh_sequence)
+			break;
+
+		*head = lh;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_find_jhead - find the head of a log
+ * @jd: the journal
+ * @head: the log descriptor for the head of the log is returned here
+ *
+ * Do a binary search of a journal and find the valid log entry with the
+ * highest sequence number.  (i.e. the log head)
+ *
+ * Returns: errno
+ */
+
+int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	struct gfs2_log_header_host lh_1, lh_m;
+	u32 blk_1, blk_2, blk_m;
+	int error;
+
+	blk_1 = 0;
+	blk_2 = jd->jd_blocks - 1;
+
+	for (;;) {
+		blk_m = (blk_1 + blk_2) / 2;
+
+		error = find_good_lh(jd, &blk_1, &lh_1);
+		if (error)
+			return error;
+
+		error = find_good_lh(jd, &blk_m, &lh_m);
+		if (error)
+			return error;
+
+		if (blk_1 == blk_m || blk_m == blk_2)
+			break;
+
+		if (lh_1.lh_sequence <= lh_m.lh_sequence)
+			blk_1 = blk_m;
+		else
+			blk_2 = blk_m;
+	}
+
+	error = jhead_scan(jd, &lh_1);
+	if (error)
+		return error;
+
+	*head = lh_1;
+
+	return error;
+}
+
+/**
+ * foreach_descriptor - go through the active part of the log
+ * @jd: the journal
+ * @start: the first log header in the active region
+ * @end: the last log header (don't process the contents of this entry))
+ *
+ * Call a given function once for every log descriptor in the active
+ * portion of the log.
+ *
+ * Returns: errno
+ */
+
+static int foreach_descriptor(struct gfs2_jdesc *jd, unsigned int start,
+			      unsigned int end, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct buffer_head *bh;
+	struct gfs2_log_descriptor *ld;
+	int error = 0;
+	u32 length;
+	__be64 *ptr;
+	unsigned int offset = sizeof(struct gfs2_log_descriptor);
+	offset += sizeof(__be64) - 1;
+	offset &= ~(sizeof(__be64) - 1);
+
+	while (start != end) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+		if (gfs2_meta_check(sdp, bh)) {
+			brelse(bh);
+			return -EIO;
+		}
+		ld = (struct gfs2_log_descriptor *)bh->b_data;
+		length = be32_to_cpu(ld->ld_length);
+
+		if (be32_to_cpu(ld->ld_header.mh_type) == GFS2_METATYPE_LH) {
+			struct gfs2_log_header_host lh;
+			error = get_log_header(jd, start, &lh);
+			if (!error) {
+				gfs2_replay_incr_blk(sdp, &start);
+				brelse(bh);
+				continue;
+			}
+			if (error == 1) {
+				gfs2_consist_inode(GFS2_I(jd->jd_inode));
+				error = -EIO;
+			}
+			brelse(bh);
+			return error;
+		} else if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LD)) {
+			brelse(bh);
+			return -EIO;
+		}
+		ptr = (__be64 *)(bh->b_data + offset);
+		error = lops_scan_elements(jd, start, ld, ptr, pass);
+		if (error) {
+			brelse(bh);
+			return error;
+		}
+
+		while (length--)
+			gfs2_replay_incr_blk(sdp, &start);
+
+		brelse(bh);
+	}
+
+	return 0;
+}
+
+/**
+ * clean_journal - mark a dirty journal as being clean
+ * @sdp: the filesystem
+ * @jd: the journal
+ * @gl: the journal's glock
+ * @head: the head journal to start from
+ *
+ * Returns: errno
+ */
+
+static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int lblock;
+	struct gfs2_log_header *lh;
+	u32 hash;
+	struct buffer_head *bh;
+	int error;
+	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
+
+	lblock = head->lh_blkno;
+	gfs2_replay_incr_blk(sdp, &lblock);
+	bh_map.b_size = 1 << ip->i_inode.i_blkbits;
+	error = gfs2_block_map(&ip->i_inode, lblock, &bh_map, 0);
+	if (error)
+		return error;
+	if (!bh_map.b_blocknr) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	bh = sb_getblk(sdp->sd_vfs, bh_map.b_blocknr);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+	unlock_buffer(bh);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.__pad0 = cpu_to_be64(0);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	lh->lh_sequence = cpu_to_be64(head->lh_sequence + 1);
+	lh->lh_flags = cpu_to_be32(GFS2_LOG_HEAD_UNMOUNT);
+	lh->lh_blkno = cpu_to_be32(lblock);
+	hash = gfs2_disk_hash((const char *)lh, sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	set_buffer_dirty(bh);
+	if (sync_dirty_buffer(bh))
+		gfs2_io_error_bh(sdp, bh);
+	brelse(bh);
+
+	return error;
+}
+
+
+static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
+                               unsigned int message)
+{
+	char env_jid[20];
+	char env_status[20];
+	char *envp[] = { env_jid, env_status, NULL };
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+        ls->ls_recover_jid_done = jid;
+        ls->ls_recover_jid_status = message;
+	sprintf(env_jid, "JID=%d", jid);
+	sprintf(env_status, "RECOVERY=%s",
+		message == LM_RD_SUCCESS ? "Done" : "Failed");
+        kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
+}
+
+void gfs2_recover_func(struct work_struct *work)
+{
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_log_header_host head;
+	struct gfs2_holder j_gh, ji_gh, t_gh;
+	unsigned long t;
+	int ro = 0;
+	unsigned int pass;
+	int error;
+	int jlocked = 0;
+
+	if (sdp->sd_args.ar_spectator ||
+	    (jd->jd_jid != sdp->sd_lockstruct.ls_jid)) {
+		fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
+			jd->jd_jid);
+		jlocked = 1;
+		/* Acquire the journal lock so we can do recovery */
+
+		error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops,
+					  LM_ST_EXCLUSIVE,
+					  LM_FLAG_NOEXP | LM_FLAG_TRY | GL_NOCACHE,
+					  &j_gh);
+		switch (error) {
+		case 0:
+			break;
+
+		case GLR_TRYFAILED:
+			fs_info(sdp, "jid=%u: Busy\n", jd->jd_jid);
+			error = 0;
+
+		default:
+			goto fail;
+		};
+
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
+		if (error)
+			goto fail_gunlock_j;
+	} else {
+		fs_info(sdp, "jid=%u, already locked for use\n", jd->jd_jid);
+	}
+
+	fs_info(sdp, "jid=%u: Looking at journal...\n", jd->jd_jid);
+
+	error = gfs2_jdesc_check(jd);
+	if (error)
+		goto fail_gunlock_ji;
+
+	error = gfs2_find_jhead(jd, &head);
+	if (error)
+		goto fail_gunlock_ji;
+
+	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+		fs_info(sdp, "jid=%u: Acquiring the transaction lock...\n",
+			jd->jd_jid);
+
+		t = jiffies;
+
+		/* Acquire a shared hold on the transaction lock */
+
+		error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
+					   GL_NOCACHE, &t_gh);
+		if (error)
+			goto fail_gunlock_ji;
+
+		if (test_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags)) {
+			if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+				ro = 1;
+		} else {
+			if (sdp->sd_vfs->s_flags & MS_RDONLY) {
+				/* check if device itself is read-only */
+				ro = bdev_read_only(sdp->sd_vfs->s_bdev);
+				if (!ro) {
+					fs_info(sdp, "recovery required on "
+						"read-only filesystem.\n");
+					fs_info(sdp, "write access will be "
+						"enabled during recovery.\n");
+				}
+			}
+		}
+
+		if (ro) {
+			fs_warn(sdp, "jid=%u: Can't replay: read-only block "
+				"device\n", jd->jd_jid);
+			error = -EROFS;
+			goto fail_gunlock_tr;
+		}
+
+		fs_info(sdp, "jid=%u: Replaying journal...\n", jd->jd_jid);
+
+		for (pass = 0; pass < 2; pass++) {
+			lops_before_scan(jd, &head, pass);
+			error = foreach_descriptor(jd, head.lh_tail,
+						   head.lh_blkno, pass);
+			lops_after_scan(jd, error, pass);
+			if (error)
+				goto fail_gunlock_tr;
+		}
+
+		error = clean_journal(jd, &head);
+		if (error)
+			goto fail_gunlock_tr;
+
+		gfs2_glock_dq_uninit(&t_gh);
+		t = DIV_ROUND_UP(jiffies - t, HZ);
+		fs_info(sdp, "jid=%u: Journal replayed in %lus\n",
+			jd->jd_jid, t);
+	}
+
+	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS);
+
+	if (jlocked) {
+		gfs2_glock_dq_uninit(&ji_gh);
+		gfs2_glock_dq_uninit(&j_gh);
+	}
+
+	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
+	goto done;
+
+fail_gunlock_tr:
+	gfs2_glock_dq_uninit(&t_gh);
+fail_gunlock_ji:
+	if (jlocked) {
+		gfs2_glock_dq_uninit(&ji_gh);
+fail_gunlock_j:
+		gfs2_glock_dq_uninit(&j_gh);
+	}
+
+	fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done");
+fail:
+	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
+done:
+	clear_bit(JDF_RECOVERY, &jd->jd_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
+}
+
+static int gfs2_recovery_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
+{
+	int rv;
+
+	if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
+		return -EBUSY;
+
+	/* we have JDF_RECOVERY, queue should always succeed */
+	rv = queue_work(gfs_recovery_wq, &jd->jd_work);
+	BUG_ON(!rv);
+
+	if (wait)
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait,
+			    TASK_UNINTERRUPTIBLE);
+
+	return 0;
+}
+
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
new file mode 100644
index 00000000..2226136c
--- /dev/null
+++ b/fs/gfs2/recovery.h
@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __RECOVERY_DOT_H__
+#define __RECOVERY_DOT_H__
+
+#include "incore.h"
+
+extern struct workqueue_struct *gfs_recovery_wq;
+
+static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk)
+{
+	if (++*blk == sdp->sd_jdesc->jd_blocks)
+	        *blk = 0;
+}
+
+extern int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
+			   struct buffer_head **bh);
+
+extern int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where);
+extern int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where);
+extern void gfs2_revoke_clean(struct gfs2_sbd *sdp);
+
+extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
+		    struct gfs2_log_header_host *head);
+extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait);
+extern void gfs2_recover_func(struct work_struct *work);
+
+#endif /* __RECOVERY_DOT_H__ */
+
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
new file mode 100644
index 00000000..9b780df3
--- /dev/null
+++ b/fs/gfs2/rgrp.c
@@ -0,0 +1,1885 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/prefetch.h>
+#include <linux/blkdev.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "glops.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "super.h"
+#include "trans.h"
+#include "util.h"
+#include "log.h"
+#include "inode.h"
+#include "trace_gfs2.h"
+
+#define BFITNOENT ((u32)~0)
+#define NO_BLOCK ((u64)~0)
+
+#if BITS_PER_LONG == 32
+#define LBITMASK   (0x55555555UL)
+#define LBITSKIP55 (0x55555555UL)
+#define LBITSKIP00 (0x00000000UL)
+#else
+#define LBITMASK   (0x5555555555555555UL)
+#define LBITSKIP55 (0x5555555555555555UL)
+#define LBITSKIP00 (0x0000000000000000UL)
+#endif
+
+/*
+ * These routines are used by the resource group routines (rgrp.c)
+ * to keep track of block allocation.  Each block is represented by two
+ * bits.  So, each byte represents GFS2_NBBY (i.e. 4) blocks.
+ *
+ * 0 = Free
+ * 1 = Used (not metadata)
+ * 2 = Unlinked (still in use) inode
+ * 3 = Used (metadata)
+ */
+
+static const char valid_change[16] = {
+	        /* current */
+	/* n */ 0, 1, 1, 1,
+	/* e */ 1, 0, 0, 0,
+	/* w */ 0, 0, 0, 1,
+	        1, 0, 0, 0
+};
+
+static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
+                        unsigned char old_state, unsigned char new_state,
+			unsigned int *n);
+
+/**
+ * gfs2_setbit - Set a bit in the bitmaps
+ * @buffer: the buffer that holds the bitmaps
+ * @buflen: the length (in bytes) of the buffer
+ * @block: the block to set
+ * @new_state: the new state of the block
+ *
+ */
+
+static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1,
+			       unsigned char *buf2, unsigned int offset,
+			       struct gfs2_bitmap *bi, u32 block,
+			       unsigned char new_state)
+{
+	unsigned char *byte1, *byte2, *end, cur_state;
+	unsigned int buflen = bi->bi_len;
+	const unsigned int bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
+
+	byte1 = buf1 + offset + (block / GFS2_NBBY);
+	end = buf1 + offset + buflen;
+
+	BUG_ON(byte1 >= end);
+
+	cur_state = (*byte1 >> bit) & GFS2_BIT_MASK;
+
+	if (unlikely(!valid_change[new_state * 4 + cur_state])) {
+		printk(KERN_WARNING "GFS2: buf_blk = 0x%llx old_state=%d, "
+		       "new_state=%d\n",
+		       (unsigned long long)block, cur_state, new_state);
+		printk(KERN_WARNING "GFS2: rgrp=0x%llx bi_start=0x%lx\n",
+		       (unsigned long long)rgd->rd_addr,
+		       (unsigned long)bi->bi_start);
+		printk(KERN_WARNING "GFS2: bi_offset=0x%lx bi_len=0x%lx\n",
+		       (unsigned long)bi->bi_offset,
+		       (unsigned long)bi->bi_len);
+		dump_stack();
+		gfs2_consist_rgrpd(rgd);
+		return;
+	}
+	*byte1 ^= (cur_state ^ new_state) << bit;
+
+	if (buf2) {
+		byte2 = buf2 + offset + (block / GFS2_NBBY);
+		cur_state = (*byte2 >> bit) & GFS2_BIT_MASK;
+		*byte2 ^= (cur_state ^ new_state) << bit;
+	}
+}
+
+/**
+ * gfs2_testbit - test a bit in the bitmaps
+ * @buffer: the buffer that holds the bitmaps
+ * @buflen: the length (in bytes) of the buffer
+ * @block: the block to read
+ *
+ */
+
+static inline unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd,
+					 const unsigned char *buffer,
+					 unsigned int buflen, u32 block)
+{
+	const unsigned char *byte, *end;
+	unsigned char cur_state;
+	unsigned int bit;
+
+	byte = buffer + (block / GFS2_NBBY);
+	bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
+	end = buffer + buflen;
+
+	gfs2_assert(rgd->rd_sbd, byte < end);
+
+	cur_state = (*byte >> bit) & GFS2_BIT_MASK;
+
+	return cur_state;
+}
+
+/**
+ * gfs2_bit_search
+ * @ptr: Pointer to bitmap data
+ * @mask: Mask to use (normally 0x55555.... but adjusted for search start)
+ * @state: The state we are searching for
+ *
+ * We xor the bitmap data with a patter which is the bitwise opposite
+ * of what we are looking for, this gives rise to a pattern of ones
+ * wherever there is a match. Since we have two bits per entry, we
+ * take this pattern, shift it down by one place and then and it with
+ * the original. All the even bit positions (0,2,4, etc) then represent
+ * successful matches, so we mask with 0x55555..... to remove the unwanted
+ * odd bit positions.
+ *
+ * This allows searching of a whole u64 at once (32 blocks) with a
+ * single test (on 64 bit arches).
+ */
+
+static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state)
+{
+	u64 tmp;
+	static const u64 search[] = {
+		[0] = 0xffffffffffffffffULL,
+		[1] = 0xaaaaaaaaaaaaaaaaULL,
+		[2] = 0x5555555555555555ULL,
+		[3] = 0x0000000000000000ULL,
+	};
+	tmp = le64_to_cpu(*ptr) ^ search[state];
+	tmp &= (tmp >> 1);
+	tmp &= mask;
+	return tmp;
+}
+
+/**
+ * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing
+ *       a block in a given allocation state.
+ * @buffer: the buffer that holds the bitmaps
+ * @len: the length (in bytes) of the buffer
+ * @goal: start search at this block's bit-pair (within @buffer)
+ * @state: GFS2_BLKST_XXX the state of the block we're looking for.
+ *
+ * Scope of @goal and returned block number is only within this bitmap buffer,
+ * not entire rgrp or filesystem.  @buffer will be offset from the actual
+ * beginning of a bitmap block buffer, skipping any header structures, but
+ * headers are always a multiple of 64 bits long so that the buffer is
+ * always aligned to a 64 bit boundary.
+ *
+ * The size of the buffer is in bytes, but is it assumed that it is
+ * always ok to read a complete multiple of 64 bits at the end
+ * of the block in case the end is no aligned to a natural boundary.
+ *
+ * Return: the block number (bitmap buffer scope) that was found
+ */
+
+static u32 gfs2_bitfit(const u8 *buf, const unsigned int len,
+		       u32 goal, u8 state)
+{
+	u32 spoint = (goal << 1) & ((8*sizeof(u64)) - 1);
+	const __le64 *ptr = ((__le64 *)buf) + (goal >> 5);
+	const __le64 *end = (__le64 *)(buf + ALIGN(len, sizeof(u64)));
+	u64 tmp;
+	u64 mask = 0x5555555555555555ULL;
+	u32 bit;
+
+	BUG_ON(state > 3);
+
+	/* Mask off bits we don't care about at the start of the search */
+	mask <<= spoint;
+	tmp = gfs2_bit_search(ptr, mask, state);
+	ptr++;
+	while(tmp == 0 && ptr < end) {
+		tmp = gfs2_bit_search(ptr, 0x5555555555555555ULL, state);
+		ptr++;
+	}
+	/* Mask off any bits which are more than len bytes from the start */
+	if (ptr == end && (len & (sizeof(u64) - 1)))
+		tmp &= (((u64)~0) >> (64 - 8*(len & (sizeof(u64) - 1))));
+	/* Didn't find anything, so return */
+	if (tmp == 0)
+		return BFITNOENT;
+	ptr--;
+	bit = __ffs64(tmp);
+	bit /= 2;	/* two bits per entry in the bitmap */
+	return (((const unsigned char *)ptr - buf) * GFS2_NBBY) + bit;
+}
+
+/**
+ * gfs2_bitcount - count the number of bits in a certain state
+ * @buffer: the buffer that holds the bitmaps
+ * @buflen: the length (in bytes) of the buffer
+ * @state: the state of the block we're looking for
+ *
+ * Returns: The number of bits
+ */
+
+static u32 gfs2_bitcount(struct gfs2_rgrpd *rgd, const u8 *buffer,
+			 unsigned int buflen, u8 state)
+{
+	const u8 *byte = buffer;
+	const u8 *end = buffer + buflen;
+	const u8 state1 = state << 2;
+	const u8 state2 = state << 4;
+	const u8 state3 = state << 6;
+	u32 count = 0;
+
+	for (; byte < end; byte++) {
+		if (((*byte) & 0x03) == state)
+			count++;
+		if (((*byte) & 0x0C) == state1)
+			count++;
+		if (((*byte) & 0x30) == state2)
+			count++;
+		if (((*byte) & 0xC0) == state3)
+			count++;
+	}
+
+	return count;
+}
+
+/**
+ * gfs2_rgrp_verify - Verify that a resource group is consistent
+ * @sdp: the filesystem
+ * @rgd: the rgrp
+ *
+ */
+
+void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	struct gfs2_bitmap *bi = NULL;
+	u32 length = rgd->rd_length;
+	u32 count[4], tmp;
+	int buf, x;
+
+	memset(count, 0, 4 * sizeof(u32));
+
+	/* Count # blocks in each of 4 possible allocation states */
+	for (buf = 0; buf < length; buf++) {
+		bi = rgd->rd_bits + buf;
+		for (x = 0; x < 4; x++)
+			count[x] += gfs2_bitcount(rgd,
+						  bi->bi_bh->b_data +
+						  bi->bi_offset,
+						  bi->bi_len, x);
+	}
+
+	if (count[0] != rgd->rd_free) {
+		if (gfs2_consist_rgrpd(rgd))
+			fs_err(sdp, "free data mismatch:  %u != %u\n",
+			       count[0], rgd->rd_free);
+		return;
+	}
+
+	tmp = rgd->rd_data - rgd->rd_free - rgd->rd_dinodes;
+	if (count[1] != tmp) {
+		if (gfs2_consist_rgrpd(rgd))
+			fs_err(sdp, "used data mismatch:  %u != %u\n",
+			       count[1], tmp);
+		return;
+	}
+
+	if (count[2] + count[3] != rgd->rd_dinodes) {
+		if (gfs2_consist_rgrpd(rgd))
+			fs_err(sdp, "used metadata mismatch:  %u != %u\n",
+			       count[2] + count[3], rgd->rd_dinodes);
+		return;
+	}
+}
+
+static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
+{
+	u64 first = rgd->rd_data0;
+	u64 last = first + rgd->rd_data;
+	return first <= block && block < last;
+}
+
+/**
+ * gfs2_blk2rgrpd - Find resource group for a given data/meta block number
+ * @sdp: The GFS2 superblock
+ * @n: The data block number
+ *
+ * Returns: The resource group, or NULL if not found
+ */
+
+struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
+{
+	struct gfs2_rgrpd *rgd;
+
+	spin_lock(&sdp->sd_rindex_spin);
+
+	list_for_each_entry(rgd, &sdp->sd_rindex_mru_list, rd_list_mru) {
+		if (rgrp_contains_block(rgd, blk)) {
+			list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
+			spin_unlock(&sdp->sd_rindex_spin);
+			return rgd;
+		}
+	}
+
+	spin_unlock(&sdp->sd_rindex_spin);
+
+	return NULL;
+}
+
+/**
+ * gfs2_rgrpd_get_first - get the first Resource Group in the filesystem
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: The first rgrp in the filesystem
+ */
+
+struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
+{
+	gfs2_assert(sdp, !list_empty(&sdp->sd_rindex_list));
+	return list_entry(sdp->sd_rindex_list.next, struct gfs2_rgrpd, rd_list);
+}
+
+/**
+ * gfs2_rgrpd_get_next - get the next RG
+ * @rgd: A RG
+ *
+ * Returns: The next rgrp
+ */
+
+struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
+{
+	if (rgd->rd_list.next == &rgd->rd_sbd->sd_rindex_list)
+		return NULL;
+	return list_entry(rgd->rd_list.next, struct gfs2_rgrpd, rd_list);
+}
+
+static void clear_rgrpdi(struct gfs2_sbd *sdp)
+{
+	struct list_head *head;
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_glock *gl;
+
+	spin_lock(&sdp->sd_rindex_spin);
+	sdp->sd_rindex_forward = NULL;
+	spin_unlock(&sdp->sd_rindex_spin);
+
+	head = &sdp->sd_rindex_list;
+	while (!list_empty(head)) {
+		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_list);
+		gl = rgd->rd_gl;
+
+		list_del(&rgd->rd_list);
+		list_del(&rgd->rd_list_mru);
+
+		if (gl) {
+			gl->gl_object = NULL;
+			gfs2_glock_add_to_lru(gl);
+			gfs2_glock_put(gl);
+		}
+
+		kfree(rgd->rd_bits);
+		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
+	}
+}
+
+void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
+{
+	mutex_lock(&sdp->sd_rindex_mutex);
+	clear_rgrpdi(sdp);
+	mutex_unlock(&sdp->sd_rindex_mutex);
+}
+
+static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd)
+{
+	printk(KERN_INFO "  ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
+	printk(KERN_INFO "  ri_length = %u\n", rgd->rd_length);
+	printk(KERN_INFO "  ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0);
+	printk(KERN_INFO "  ri_data = %u\n", rgd->rd_data);
+	printk(KERN_INFO "  ri_bitbytes = %u\n", rgd->rd_bitbytes);
+}
+
+/**
+ * gfs2_compute_bitstructs - Compute the bitmap sizes
+ * @rgd: The resource group descriptor
+ *
+ * Calculates bitmap descriptors, one for each block that contains bitmap data
+ *
+ * Returns: errno
+ */
+
+static int compute_bitstructs(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	struct gfs2_bitmap *bi;
+	u32 length = rgd->rd_length; /* # blocks in hdr & bitmap */
+	u32 bytes_left, bytes;
+	int x;
+
+	if (!length)
+		return -EINVAL;
+
+	rgd->rd_bits = kcalloc(length, sizeof(struct gfs2_bitmap), GFP_NOFS);
+	if (!rgd->rd_bits)
+		return -ENOMEM;
+
+	bytes_left = rgd->rd_bitbytes;
+
+	for (x = 0; x < length; x++) {
+		bi = rgd->rd_bits + x;
+
+		bi->bi_flags = 0;
+		/* small rgrp; bitmap stored completely in header block */
+		if (length == 1) {
+			bytes = bytes_left;
+			bi->bi_offset = sizeof(struct gfs2_rgrp);
+			bi->bi_start = 0;
+			bi->bi_len = bytes;
+		/* header block */
+		} else if (x == 0) {
+			bytes = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_rgrp);
+			bi->bi_offset = sizeof(struct gfs2_rgrp);
+			bi->bi_start = 0;
+			bi->bi_len = bytes;
+		/* last block */
+		} else if (x + 1 == length) {
+			bytes = bytes_left;
+			bi->bi_offset = sizeof(struct gfs2_meta_header);
+			bi->bi_start = rgd->rd_bitbytes - bytes_left;
+			bi->bi_len = bytes;
+		/* other blocks */
+		} else {
+			bytes = sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_meta_header);
+			bi->bi_offset = sizeof(struct gfs2_meta_header);
+			bi->bi_start = rgd->rd_bitbytes - bytes_left;
+			bi->bi_len = bytes;
+		}
+
+		bytes_left -= bytes;
+	}
+
+	if (bytes_left) {
+		gfs2_consist_rgrpd(rgd);
+		return -EIO;
+	}
+	bi = rgd->rd_bits + (length - 1);
+	if ((bi->bi_start + bi->bi_len) * GFS2_NBBY != rgd->rd_data) {
+		if (gfs2_consist_rgrpd(rgd)) {
+			gfs2_rindex_print(rgd);
+			fs_err(sdp, "start=%u len=%u offset=%u\n",
+			       bi->bi_start, bi->bi_len, bi->bi_offset);
+		}
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_ri_total - Total up the file system space, according to the rindex.
+ *
+ */
+u64 gfs2_ri_total(struct gfs2_sbd *sdp)
+{
+	u64 total_data = 0;	
+	struct inode *inode = sdp->sd_rindex;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	char buf[sizeof(struct gfs2_rindex)];
+	struct file_ra_state ra_state;
+	int error, rgrps;
+
+	mutex_lock(&sdp->sd_rindex_mutex);
+	file_ra_state_init(&ra_state, inode->i_mapping);
+	for (rgrps = 0;; rgrps++) {
+		loff_t pos = rgrps * sizeof(struct gfs2_rindex);
+
+		if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode))
+			break;
+		error = gfs2_internal_read(ip, &ra_state, buf, &pos,
+					   sizeof(struct gfs2_rindex));
+		if (error != sizeof(struct gfs2_rindex))
+			break;
+		total_data += be32_to_cpu(((struct gfs2_rindex *)buf)->ri_data);
+	}
+	mutex_unlock(&sdp->sd_rindex_mutex);
+	return total_data;
+}
+
+static void gfs2_rindex_in(struct gfs2_rgrpd *rgd, const void *buf)
+{
+	const struct gfs2_rindex *str = buf;
+
+	rgd->rd_addr = be64_to_cpu(str->ri_addr);
+	rgd->rd_length = be32_to_cpu(str->ri_length);
+	rgd->rd_data0 = be64_to_cpu(str->ri_data0);
+	rgd->rd_data = be32_to_cpu(str->ri_data);
+	rgd->rd_bitbytes = be32_to_cpu(str->ri_bitbytes);
+}
+
+/**
+ * read_rindex_entry - Pull in a new resource index entry from the disk
+ * @gl: The glock covering the rindex inode
+ *
+ * Returns: 0 on success, error code otherwise
+ */
+
+static int read_rindex_entry(struct gfs2_inode *ip,
+			     struct file_ra_state *ra_state)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex);
+	char buf[sizeof(struct gfs2_rindex)];
+	int error;
+	struct gfs2_rgrpd *rgd;
+
+	error = gfs2_internal_read(ip, ra_state, buf, &pos,
+				   sizeof(struct gfs2_rindex));
+	if (!error)
+		return 0;
+	if (error != sizeof(struct gfs2_rindex)) {
+		if (error > 0)
+			error = -EIO;
+		return error;
+	}
+
+	rgd = kmem_cache_zalloc(gfs2_rgrpd_cachep, GFP_NOFS);
+	error = -ENOMEM;
+	if (!rgd)
+		return error;
+
+	mutex_init(&rgd->rd_mutex);
+	lops_init_le(&rgd->rd_le, &gfs2_rg_lops);
+	rgd->rd_sbd = sdp;
+
+	list_add_tail(&rgd->rd_list, &sdp->sd_rindex_list);
+	list_add_tail(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
+
+	gfs2_rindex_in(rgd, buf);
+	error = compute_bitstructs(rgd);
+	if (error)
+		return error;
+
+	error = gfs2_glock_get(sdp, rgd->rd_addr,
+			       &gfs2_rgrp_glops, CREATE, &rgd->rd_gl);
+	if (error)
+		return error;
+
+	rgd->rd_gl->gl_object = rgd;
+	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+	return error;
+}
+
+/**
+ * gfs2_ri_update - Pull in a new resource index from the disk
+ * @ip: pointer to the rindex inode
+ *
+ * Returns: 0 on successful update, error code otherwise
+ */
+
+int gfs2_ri_update(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct inode *inode = &ip->i_inode;
+	struct file_ra_state ra_state;
+	u64 rgrp_count = i_size_read(inode);
+	struct gfs2_rgrpd *rgd;
+	unsigned int max_data = 0;
+	int error;
+
+	do_div(rgrp_count, sizeof(struct gfs2_rindex));
+	clear_rgrpdi(sdp);
+
+	file_ra_state_init(&ra_state, inode->i_mapping);
+	for (sdp->sd_rgrps = 0; sdp->sd_rgrps < rgrp_count; sdp->sd_rgrps++) {
+		error = read_rindex_entry(ip, &ra_state);
+		if (error) {
+			clear_rgrpdi(sdp);
+			return error;
+		}
+	}
+
+	list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
+		if (rgd->rd_data > max_data)
+			max_data = rgd->rd_data;
+	sdp->sd_max_rg_data = max_data;
+	sdp->sd_rindex_uptodate = 1;
+	return 0;
+}
+
+/**
+ * gfs2_rindex_hold - Grab a lock on the rindex
+ * @sdp: The GFS2 superblock
+ * @ri_gh: the glock holder
+ *
+ * We grab a lock on the rindex inode to make sure that it doesn't
+ * change whilst we are performing an operation. We keep this lock
+ * for quite long periods of time compared to other locks. This
+ * doesn't matter, since it is shared and it is very, very rarely
+ * accessed in the exclusive mode (i.e. only when expanding the filesystem).
+ *
+ * This makes sure that we're using the latest copy of the resource index
+ * special file, which might have been updated if someone expanded the
+ * filesystem (via gfs2_grow utility), which adds new resource groups.
+ *
+ * Returns: 0 on success, error code otherwise
+ */
+
+int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh)
+{
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
+	struct gfs2_glock *gl = ip->i_gl;
+	int error;
+
+	error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, ri_gh);
+	if (error)
+		return error;
+
+	/* Read new copy from disk if we don't have the latest */
+	if (!sdp->sd_rindex_uptodate) {
+		mutex_lock(&sdp->sd_rindex_mutex);
+		if (!sdp->sd_rindex_uptodate) {
+			error = gfs2_ri_update(ip);
+			if (error)
+				gfs2_glock_dq_uninit(ri_gh);
+		}
+		mutex_unlock(&sdp->sd_rindex_mutex);
+	}
+
+	return error;
+}
+
+static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
+{
+	const struct gfs2_rgrp *str = buf;
+	u32 rg_flags;
+
+	rg_flags = be32_to_cpu(str->rg_flags);
+	rg_flags &= ~GFS2_RDF_MASK;
+	rgd->rd_flags &= GFS2_RDF_MASK;
+	rgd->rd_flags |= rg_flags;
+	rgd->rd_free = be32_to_cpu(str->rg_free);
+	rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
+	rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
+}
+
+static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
+{
+	struct gfs2_rgrp *str = buf;
+
+	str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
+	str->rg_free = cpu_to_be32(rgd->rd_free);
+	str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
+	str->__pad = cpu_to_be32(0);
+	str->rg_igeneration = cpu_to_be64(rgd->rd_igeneration);
+	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
+}
+
+/**
+ * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
+ * @rgd: the struct gfs2_rgrpd describing the RG to read in
+ *
+ * Read in all of a Resource Group's header and bitmap blocks.
+ * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps.
+ *
+ * Returns: errno
+ */
+
+int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	struct gfs2_glock *gl = rgd->rd_gl;
+	unsigned int length = rgd->rd_length;
+	struct gfs2_bitmap *bi;
+	unsigned int x, y;
+	int error;
+
+	mutex_lock(&rgd->rd_mutex);
+
+	spin_lock(&sdp->sd_rindex_spin);
+	if (rgd->rd_bh_count) {
+		rgd->rd_bh_count++;
+		spin_unlock(&sdp->sd_rindex_spin);
+		mutex_unlock(&rgd->rd_mutex);
+		return 0;
+	}
+	spin_unlock(&sdp->sd_rindex_spin);
+
+	for (x = 0; x < length; x++) {
+		bi = rgd->rd_bits + x;
+		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
+		if (error)
+			goto fail;
+	}
+
+	for (y = length; y--;) {
+		bi = rgd->rd_bits + y;
+		error = gfs2_meta_wait(sdp, bi->bi_bh);
+		if (error)
+			goto fail;
+		if (gfs2_metatype_check(sdp, bi->bi_bh, y ? GFS2_METATYPE_RB :
+					      GFS2_METATYPE_RG)) {
+			error = -EIO;
+			goto fail;
+		}
+	}
+
+	if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
+		for (x = 0; x < length; x++)
+			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
+		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
+		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
+	}
+
+	spin_lock(&sdp->sd_rindex_spin);
+	rgd->rd_free_clone = rgd->rd_free;
+	rgd->rd_bh_count++;
+	spin_unlock(&sdp->sd_rindex_spin);
+
+	mutex_unlock(&rgd->rd_mutex);
+
+	return 0;
+
+fail:
+	while (x--) {
+		bi = rgd->rd_bits + x;
+		brelse(bi->bi_bh);
+		bi->bi_bh = NULL;
+		gfs2_assert_warn(sdp, !bi->bi_clone);
+	}
+	mutex_unlock(&rgd->rd_mutex);
+
+	return error;
+}
+
+void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+
+	spin_lock(&sdp->sd_rindex_spin);
+	gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count);
+	rgd->rd_bh_count++;
+	spin_unlock(&sdp->sd_rindex_spin);
+}
+
+/**
+ * gfs2_rgrp_bh_put - Release RG bitmaps read in with gfs2_rgrp_bh_get()
+ * @rgd: the struct gfs2_rgrpd describing the RG to read in
+ *
+ */
+
+void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	int x, length = rgd->rd_length;
+
+	spin_lock(&sdp->sd_rindex_spin);
+	gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count);
+	if (--rgd->rd_bh_count) {
+		spin_unlock(&sdp->sd_rindex_spin);
+		return;
+	}
+
+	for (x = 0; x < length; x++) {
+		struct gfs2_bitmap *bi = rgd->rd_bits + x;
+		kfree(bi->bi_clone);
+		bi->bi_clone = NULL;
+		brelse(bi->bi_bh);
+		bi->bi_bh = NULL;
+	}
+
+	spin_unlock(&sdp->sd_rindex_spin);
+}
+
+static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+				    const struct gfs2_bitmap *bi)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct block_device *bdev = sb->s_bdev;
+	const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize /
+					   bdev_logical_block_size(sb->s_bdev);
+	u64 blk;
+	sector_t start = 0;
+	sector_t nr_sects = 0;
+	int rv;
+	unsigned int x;
+
+	for (x = 0; x < bi->bi_len; x++) {
+		const u8 *orig = bi->bi_bh->b_data + bi->bi_offset + x;
+		const u8 *clone = bi->bi_clone + bi->bi_offset + x;
+		u8 diff = ~(*orig | (*orig >> 1)) & (*clone | (*clone >> 1));
+		diff &= 0x55;
+		if (diff == 0)
+			continue;
+		blk = offset + ((bi->bi_start + x) * GFS2_NBBY);
+		blk *= sects_per_blk; /* convert to sectors */
+		while(diff) {
+			if (diff & 1) {
+				if (nr_sects == 0)
+					goto start_new_extent;
+				if ((start + nr_sects) != blk) {
+					rv = blkdev_issue_discard(bdev, start,
+							    nr_sects, GFP_NOFS,
+							    0);
+					if (rv)
+						goto fail;
+					nr_sects = 0;
+start_new_extent:
+					start = blk;
+				}
+				nr_sects += sects_per_blk;
+			}
+			diff >>= 2;
+			blk += sects_per_blk;
+		}
+	}
+	if (nr_sects) {
+		rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0);
+		if (rv)
+			goto fail;
+	}
+	return;
+fail:
+	fs_warn(sdp, "error %d on discard request, turning discards off for this filesystem", rv);
+	sdp->sd_args.ar_discard = 0;
+}
+
+void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	unsigned int length = rgd->rd_length;
+	unsigned int x;
+
+	for (x = 0; x < length; x++) {
+		struct gfs2_bitmap *bi = rgd->rd_bits + x;
+		if (!bi->bi_clone)
+			continue;
+		if (sdp->sd_args.ar_discard)
+			gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi);
+		clear_bit(GBF_FULL, &bi->bi_flags);
+		memcpy(bi->bi_clone + bi->bi_offset,
+		       bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
+	}
+
+	spin_lock(&sdp->sd_rindex_spin);
+	rgd->rd_free_clone = rgd->rd_free;
+	spin_unlock(&sdp->sd_rindex_spin);
+}
+
+/**
+ * gfs2_alloc_get - get the struct gfs2_alloc structure for an inode
+ * @ip: the incore GFS2 inode structure
+ *
+ * Returns: the struct gfs2_alloc
+ */
+
+struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
+{
+	BUG_ON(ip->i_alloc != NULL);
+	ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_NOFS);
+	return ip->i_alloc;
+}
+
+/**
+ * try_rgrp_fit - See if a given reservation will fit in a given RG
+ * @rgd: the RG data
+ * @al: the struct gfs2_alloc structure describing the reservation
+ *
+ * If there's room for the requested blocks to be allocated from the RG:
+ *   Sets the $al_rgd field in @al.
+ *
+ * Returns: 1 on success (it fits), 0 on failure (it doesn't fit)
+ */
+
+static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	int ret = 0;
+
+	if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
+		return 0;
+
+	spin_lock(&sdp->sd_rindex_spin);
+	if (rgd->rd_free_clone >= al->al_requested) {
+		al->al_rgd = rgd;
+		ret = 1;
+	}
+	spin_unlock(&sdp->sd_rindex_spin);
+
+	return ret;
+}
+
+/**
+ * try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes
+ * @rgd: The rgrp
+ *
+ * Returns: 0 if no error
+ *          The inode, if one has been found, in inode.
+ */
+
+static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip)
+{
+	u32 goal = 0, block;
+	u64 no_addr;
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	unsigned int n;
+	struct gfs2_glock *gl;
+	struct gfs2_inode *ip;
+	int error;
+	int found = 0;
+
+	while (goal < rgd->rd_data) {
+		down_write(&sdp->sd_log_flush_lock);
+		n = 1;
+		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
+				     GFS2_BLKST_UNLINKED, &n);
+		up_write(&sdp->sd_log_flush_lock);
+		if (block == BFITNOENT)
+			break;
+		/* rgblk_search can return a block < goal, so we need to
+		   keep it marching forward. */
+		no_addr = block + rgd->rd_data0;
+		goal = max(block + 1, goal + 1);
+		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
+			continue;
+		if (no_addr == skip)
+			continue;
+		*last_unlinked = no_addr;
+
+		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &gl);
+		if (error)
+			continue;
+
+		/* If the inode is already in cache, we can ignore it here
+		 * because the existing inode disposal code will deal with
+		 * it when all refs have gone away. Accessing gl_object like
+		 * this is not safe in general. Here it is ok because we do
+		 * not dereference the pointer, and we only need an approx
+		 * answer to whether it is NULL or not.
+		 */
+		ip = gl->gl_object;
+
+		if (ip || queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
+			gfs2_glock_put(gl);
+		else
+			found++;
+
+		/* Limit reclaim to sensible number of tasks */
+		if (found > NR_CPUS)
+			return;
+	}
+
+	rgd->rd_flags &= ~GFS2_RDF_CHECK;
+	return;
+}
+
+/**
+ * recent_rgrp_next - get next RG from "recent" list
+ * @cur_rgd: current rgrp
+ *
+ * Returns: The next rgrp in the recent list
+ */
+
+static struct gfs2_rgrpd *recent_rgrp_next(struct gfs2_rgrpd *cur_rgd)
+{
+	struct gfs2_sbd *sdp = cur_rgd->rd_sbd;
+	struct list_head *head;
+	struct gfs2_rgrpd *rgd;
+
+	spin_lock(&sdp->sd_rindex_spin);
+	head = &sdp->sd_rindex_mru_list;
+	if (unlikely(cur_rgd->rd_list_mru.next == head)) {
+		spin_unlock(&sdp->sd_rindex_spin);
+		return NULL;
+	}
+	rgd = list_entry(cur_rgd->rd_list_mru.next, struct gfs2_rgrpd, rd_list_mru);
+	spin_unlock(&sdp->sd_rindex_spin);
+	return rgd;
+}
+
+/**
+ * forward_rgrp_get - get an rgrp to try next from full list
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: The rgrp to try next
+ */
+
+static struct gfs2_rgrpd *forward_rgrp_get(struct gfs2_sbd *sdp)
+{
+	struct gfs2_rgrpd *rgd;
+	unsigned int journals = gfs2_jindex_size(sdp);
+	unsigned int rg = 0, x;
+
+	spin_lock(&sdp->sd_rindex_spin);
+
+	rgd = sdp->sd_rindex_forward;
+	if (!rgd) {
+		if (sdp->sd_rgrps >= journals)
+			rg = sdp->sd_rgrps * sdp->sd_jdesc->jd_jid / journals;
+
+		for (x = 0, rgd = gfs2_rgrpd_get_first(sdp); x < rg;
+		     x++, rgd = gfs2_rgrpd_get_next(rgd))
+			/* Do Nothing */;
+
+		sdp->sd_rindex_forward = rgd;
+	}
+
+	spin_unlock(&sdp->sd_rindex_spin);
+
+	return rgd;
+}
+
+/**
+ * forward_rgrp_set - set the forward rgrp pointer
+ * @sdp: the filesystem
+ * @rgd: The new forward rgrp
+ *
+ */
+
+static void forward_rgrp_set(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd)
+{
+	spin_lock(&sdp->sd_rindex_spin);
+	sdp->sd_rindex_forward = rgd;
+	spin_unlock(&sdp->sd_rindex_spin);
+}
+
+/**
+ * get_local_rgrp - Choose and lock a rgrp for allocation
+ * @ip: the inode to reserve space for
+ * @rgp: the chosen and locked rgrp
+ *
+ * Try to acquire rgrp in way which avoids contending with others.
+ *
+ * Returns: errno
+ */
+
+static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrpd *rgd, *begin = NULL;
+	struct gfs2_alloc *al = ip->i_alloc;
+	int flags = LM_FLAG_TRY;
+	int skipped = 0;
+	int loops = 0;
+	int error, rg_locked;
+
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_goal);
+
+	while (rgd) {
+		rg_locked = 0;
+
+		if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) {
+			rg_locked = 1;
+			error = 0;
+		} else {
+			error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+						   LM_FLAG_TRY, &al->al_rgd_gh);
+		}
+		switch (error) {
+		case 0:
+			if (try_rgrp_fit(rgd, al))
+				goto out;
+			if (rgd->rd_flags & GFS2_RDF_CHECK)
+				try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
+			if (!rg_locked)
+				gfs2_glock_dq_uninit(&al->al_rgd_gh);
+			/* fall through */
+		case GLR_TRYFAILED:
+			rgd = recent_rgrp_next(rgd);
+			break;
+
+		default:
+			return error;
+		}
+	}
+
+	/* Go through full list of rgrps */
+
+	begin = rgd = forward_rgrp_get(sdp);
+
+	for (;;) {
+		rg_locked = 0;
+
+		if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) {
+			rg_locked = 1;
+			error = 0;
+		} else {
+			error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags,
+						   &al->al_rgd_gh);
+		}
+		switch (error) {
+		case 0:
+			if (try_rgrp_fit(rgd, al))
+				goto out;
+			if (rgd->rd_flags & GFS2_RDF_CHECK)
+				try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
+			if (!rg_locked)
+				gfs2_glock_dq_uninit(&al->al_rgd_gh);
+			break;
+
+		case GLR_TRYFAILED:
+			skipped++;
+			break;
+
+		default:
+			return error;
+		}
+
+		rgd = gfs2_rgrpd_get_next(rgd);
+		if (!rgd)
+			rgd = gfs2_rgrpd_get_first(sdp);
+
+		if (rgd == begin) {
+			if (++loops >= 3)
+				return -ENOSPC;
+			if (!skipped)
+				loops++;
+			flags = 0;
+			if (loops == 2)
+				gfs2_log_flush(sdp, NULL);
+		}
+	}
+
+out:
+	if (begin) {
+		spin_lock(&sdp->sd_rindex_spin);
+		list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
+		spin_unlock(&sdp->sd_rindex_spin);
+		rgd = gfs2_rgrpd_get_next(rgd);
+		if (!rgd)
+			rgd = gfs2_rgrpd_get_first(sdp);
+		forward_rgrp_set(sdp, rgd);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_inplace_reserve_i - Reserve space in the filesystem
+ * @ip: the inode to reserve space for
+ *
+ * Returns: errno
+ */
+
+int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+			   char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+	int error = 0;
+	u64 last_unlinked = NO_BLOCK;
+	int tries = 0;
+
+	if (gfs2_assert_warn(sdp, al->al_requested))
+		return -EINVAL;
+
+	if (hold_rindex) {
+		/* We need to hold the rindex unless the inode we're using is
+		   the rindex itself, in which case it's already held. */
+		if (ip != GFS2_I(sdp->sd_rindex))
+			error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
+		else if (!sdp->sd_rgrps) /* We may not have the rindex read
+					    in, so: */
+			error = gfs2_ri_update(ip);
+		if (error)
+			return error;
+	}
+
+try_again:
+	do {
+		error = get_local_rgrp(ip, &last_unlinked);
+		/* If there is no space, flushing the log may release some */
+		if (error) {
+			if (ip == GFS2_I(sdp->sd_rindex) &&
+			    !sdp->sd_rindex_uptodate) {
+				error = gfs2_ri_update(ip);
+				if (error)
+					return error;
+				goto try_again;
+			}
+			gfs2_log_flush(sdp, NULL);
+		}
+	} while (error && tries++ < 3);
+
+	if (error) {
+		if (hold_rindex && ip != GFS2_I(sdp->sd_rindex))
+			gfs2_glock_dq_uninit(&al->al_ri_gh);
+		return error;
+	}
+
+	/* no error, so we have the rgrp set in the inode's allocation. */
+	al->al_file = file;
+	al->al_line = line;
+
+	return 0;
+}
+
+/**
+ * gfs2_inplace_release - release an inplace reservation
+ * @ip: the inode the reservation was taken out on
+ *
+ * Release a reservation made by gfs2_inplace_reserve().
+ */
+
+void gfs2_inplace_release(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+
+	if (gfs2_assert_warn(sdp, al->al_alloced <= al->al_requested) == -1)
+		fs_warn(sdp, "al_alloced = %u, al_requested = %u "
+			     "al_file = %s, al_line = %u\n",
+		             al->al_alloced, al->al_requested, al->al_file,
+			     al->al_line);
+
+	al->al_rgd = NULL;
+	if (al->al_rgd_gh.gh_gl)
+		gfs2_glock_dq_uninit(&al->al_rgd_gh);
+	if (ip != GFS2_I(sdp->sd_rindex) && al->al_ri_gh.gh_gl)
+		gfs2_glock_dq_uninit(&al->al_ri_gh);
+}
+
+/**
+ * gfs2_get_block_type - Check a block in a RG is of given type
+ * @rgd: the resource group holding the block
+ * @block: the block number
+ *
+ * Returns: The block type (GFS2_BLKST_*)
+ */
+
+static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block)
+{
+	struct gfs2_bitmap *bi = NULL;
+	u32 length, rgrp_block, buf_block;
+	unsigned int buf;
+	unsigned char type;
+
+	length = rgd->rd_length;
+	rgrp_block = block - rgd->rd_data0;
+
+	for (buf = 0; buf < length; buf++) {
+		bi = rgd->rd_bits + buf;
+		if (rgrp_block < (bi->bi_start + bi->bi_len) * GFS2_NBBY)
+			break;
+	}
+
+	gfs2_assert(rgd->rd_sbd, buf < length);
+	buf_block = rgrp_block - bi->bi_start * GFS2_NBBY;
+
+	type = gfs2_testbit(rgd, bi->bi_bh->b_data + bi->bi_offset,
+			   bi->bi_len, buf_block);
+
+	return type;
+}
+
+/**
+ * rgblk_search - find a block in @old_state, change allocation
+ *           state to @new_state
+ * @rgd: the resource group descriptor
+ * @goal: the goal block within the RG (start here to search for avail block)
+ * @old_state: GFS2_BLKST_XXX the before-allocation state to find
+ * @new_state: GFS2_BLKST_XXX the after-allocation block state
+ * @n: The extent length
+ *
+ * Walk rgrp's bitmap to find bits that represent a block in @old_state.
+ * Add the found bitmap buffer to the transaction.
+ * Set the found bits to @new_state to change block's allocation state.
+ *
+ * This function never fails, because we wouldn't call it unless we
+ * know (from reservation results, etc.) that a block is available.
+ *
+ * Scope of @goal and returned block is just within rgrp, not the whole
+ * filesystem.
+ *
+ * Returns:  the block number allocated
+ */
+
+static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
+			unsigned char old_state, unsigned char new_state,
+			unsigned int *n)
+{
+	struct gfs2_bitmap *bi = NULL;
+	const u32 length = rgd->rd_length;
+	u32 blk = BFITNOENT;
+	unsigned int buf, x;
+	const unsigned int elen = *n;
+	const u8 *buffer = NULL;
+
+	*n = 0;
+	/* Find bitmap block that contains bits for goal block */
+	for (buf = 0; buf < length; buf++) {
+		bi = rgd->rd_bits + buf;
+		/* Convert scope of "goal" from rgrp-wide to within found bit block */
+		if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) {
+			goal -= bi->bi_start * GFS2_NBBY;
+			goto do_search;
+		}
+	}
+	buf = 0;
+	goal = 0;
+
+do_search:
+	/* Search (up to entire) bitmap in this rgrp for allocatable block.
+	   "x <= length", instead of "x < length", because we typically start
+	   the search in the middle of a bit block, but if we can't find an
+	   allocatable block anywhere else, we want to be able wrap around and
+	   search in the first part of our first-searched bit block.  */
+	for (x = 0; x <= length; x++) {
+		bi = rgd->rd_bits + buf;
+
+		if (test_bit(GBF_FULL, &bi->bi_flags) &&
+		    (old_state == GFS2_BLKST_FREE))
+			goto skip;
+
+		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
+		   bitmaps, so we must search the originals for that. */
+		buffer = bi->bi_bh->b_data + bi->bi_offset;
+		if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone)
+			buffer = bi->bi_clone + bi->bi_offset;
+
+		blk = gfs2_bitfit(buffer, bi->bi_len, goal, old_state);
+		if (blk != BFITNOENT)
+			break;
+
+		if ((goal == 0) && (old_state == GFS2_BLKST_FREE))
+			set_bit(GBF_FULL, &bi->bi_flags);
+
+		/* Try next bitmap block (wrap back to rgrp header if at end) */
+skip:
+		buf++;
+		buf %= length;
+		goal = 0;
+	}
+
+	if (blk == BFITNOENT)
+		return blk;
+	*n = 1;
+	if (old_state == new_state)
+		goto out;
+
+	gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+	gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
+		    bi, blk, new_state);
+	goal = blk;
+	while (*n < elen) {
+		goal++;
+		if (goal >= (bi->bi_len * GFS2_NBBY))
+			break;
+		if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
+		    GFS2_BLKST_FREE)
+			break;
+		gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
+			    bi, goal, new_state);
+		(*n)++;
+	}
+out:
+	return (bi->bi_start * GFS2_NBBY) + blk;
+}
+
+/**
+ * rgblk_free - Change alloc state of given block(s)
+ * @sdp: the filesystem
+ * @bstart: the start of a run of blocks to free
+ * @blen: the length of the block run (all must lie within ONE RG!)
+ * @new_state: GFS2_BLKST_XXX the after-allocation block state
+ *
+ * Returns:  Resource group containing the block(s)
+ */
+
+static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
+				     u32 blen, unsigned char new_state)
+{
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_bitmap *bi = NULL;
+	u32 length, rgrp_blk, buf_blk;
+	unsigned int buf;
+
+	rgd = gfs2_blk2rgrpd(sdp, bstart);
+	if (!rgd) {
+		if (gfs2_consist(sdp))
+			fs_err(sdp, "block = %llu\n", (unsigned long long)bstart);
+		return NULL;
+	}
+
+	length = rgd->rd_length;
+
+	rgrp_blk = bstart - rgd->rd_data0;
+
+	while (blen--) {
+		for (buf = 0; buf < length; buf++) {
+			bi = rgd->rd_bits + buf;
+			if (rgrp_blk < (bi->bi_start + bi->bi_len) * GFS2_NBBY)
+				break;
+		}
+
+		gfs2_assert(rgd->rd_sbd, buf < length);
+
+		buf_blk = rgrp_blk - bi->bi_start * GFS2_NBBY;
+		rgrp_blk++;
+
+		if (!bi->bi_clone) {
+			bi->bi_clone = kmalloc(bi->bi_bh->b_size,
+					       GFP_NOFS | __GFP_NOFAIL);
+			memcpy(bi->bi_clone + bi->bi_offset,
+			       bi->bi_bh->b_data + bi->bi_offset,
+			       bi->bi_len);
+		}
+		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+		gfs2_setbit(rgd, bi->bi_bh->b_data, NULL, bi->bi_offset,
+			    bi, buf_blk, new_state);
+	}
+
+	return rgd;
+}
+
+/**
+ * gfs2_rgrp_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
+ *
+ */
+
+int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_rgrpd *rgd = gl->gl_object;
+	if (rgd == NULL)
+		return 0;
+	gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n",
+		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
+		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes);
+	return 0;
+}
+
+static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
+		(unsigned long long)rgd->rd_addr);
+	fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
+	gfs2_rgrp_dump(NULL, rgd->rd_gl);
+	rgd->rd_flags |= GFS2_RDF_ERROR;
+}
+
+/**
+ * gfs2_alloc_block - Allocate one or more blocks
+ * @ip: the inode to allocate the block for
+ * @bn: Used to return the starting block number
+ * @n: requested number of blocks/extent length (value/result)
+ *
+ * Returns: 0 or error
+ */
+
+int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *dibh;
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_rgrpd *rgd;
+	u32 goal, blk;
+	u64 block;
+	int error;
+
+	/* Only happens if there is a bug in gfs2, return something distinctive
+	 * to ensure that it is noticed.
+	 */
+	if (al == NULL)
+		return -ECANCELED;
+
+	rgd = al->al_rgd;
+
+	if (rgrp_contains_block(rgd, ip->i_goal))
+		goal = ip->i_goal - rgd->rd_data0;
+	else
+		goal = rgd->rd_last_alloc;
+
+	blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED, n);
+
+	/* Since all blocks are reserved in advance, this shouldn't happen */
+	if (blk == BFITNOENT)
+		goto rgrp_error;
+
+	rgd->rd_last_alloc = blk;
+	block = rgd->rd_data0 + blk;
+	ip->i_goal = block;
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error == 0) {
+		struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_goal);
+		brelse(dibh);
+	}
+	if (rgd->rd_free < *n)
+		goto rgrp_error;
+
+	rgd->rd_free -= *n;
+
+	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+
+	al->al_alloced += *n;
+
+	gfs2_statfs_change(sdp, 0, -(s64)*n, 0);
+	gfs2_quota_change(ip, *n, ip->i_inode.i_uid, ip->i_inode.i_gid);
+
+	spin_lock(&sdp->sd_rindex_spin);
+	rgd->rd_free_clone -= *n;
+	spin_unlock(&sdp->sd_rindex_spin);
+	trace_gfs2_block_alloc(ip, block, *n, GFS2_BLKST_USED);
+	*bn = block;
+	return 0;
+
+rgrp_error:
+	gfs2_rgrp_error(rgd);
+	return -EIO;
+}
+
+/**
+ * gfs2_alloc_di - Allocate a dinode
+ * @dip: the directory that the inode is going in
+ * @bn: the block number which is allocated
+ * @generation: the generation number of the inode
+ *
+ * Returns: 0 on success or error
+ */
+
+int gfs2_alloc_di(struct gfs2_inode *dip, u64 *bn, u64 *generation)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct gfs2_alloc *al = dip->i_alloc;
+	struct gfs2_rgrpd *rgd = al->al_rgd;
+	u32 blk;
+	u64 block;
+	unsigned int n = 1;
+
+	blk = rgblk_search(rgd, rgd->rd_last_alloc,
+			   GFS2_BLKST_FREE, GFS2_BLKST_DINODE, &n);
+
+	/* Since all blocks are reserved in advance, this shouldn't happen */
+	if (blk == BFITNOENT)
+		goto rgrp_error;
+
+	rgd->rd_last_alloc = blk;
+	block = rgd->rd_data0 + blk;
+	if (rgd->rd_free == 0)
+		goto rgrp_error;
+
+	rgd->rd_free--;
+	rgd->rd_dinodes++;
+	*generation = rgd->rd_igeneration++;
+	if (*generation == 0)
+		*generation = rgd->rd_igeneration++;
+	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+
+	al->al_alloced++;
+
+	gfs2_statfs_change(sdp, 0, -1, +1);
+	gfs2_trans_add_unrevoke(sdp, block, 1);
+
+	spin_lock(&sdp->sd_rindex_spin);
+	rgd->rd_free_clone--;
+	spin_unlock(&sdp->sd_rindex_spin);
+	trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE);
+	*bn = block;
+	return 0;
+
+rgrp_error:
+	gfs2_rgrp_error(rgd);
+	return -EIO;
+}
+
+/**
+ * gfs2_free_data - free a contiguous run of data block(s)
+ * @ip: the inode these blocks are being freed from
+ * @bstart: first block of a run of contiguous blocks
+ * @blen: the length of the block run
+ *
+ */
+
+void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrpd *rgd;
+
+	rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
+	if (!rgd)
+		return;
+	trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
+	rgd->rd_free += blen;
+
+	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+
+	gfs2_trans_add_rg(rgd);
+
+	/* Directories keep their data in the metadata address space */
+	if (ip->i_depth)
+		gfs2_meta_wipe(ip, bstart, blen);
+}
+
+/**
+ * gfs2_free_data - free a contiguous run of data block(s)
+ * @ip: the inode these blocks are being freed from
+ * @bstart: first block of a run of contiguous blocks
+ * @blen: the length of the block run
+ *
+ */
+
+void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	__gfs2_free_data(ip, bstart, blen);
+	gfs2_statfs_change(sdp, 0, +blen, 0);
+	gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid);
+}
+
+/**
+ * gfs2_free_meta - free a contiguous run of data block(s)
+ * @ip: the inode these blocks are being freed from
+ * @bstart: first block of a run of contiguous blocks
+ * @blen: the length of the block run
+ *
+ */
+
+void __gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrpd *rgd;
+
+	rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
+	if (!rgd)
+		return;
+	trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
+	rgd->rd_free += blen;
+
+	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+
+	gfs2_trans_add_rg(rgd);
+	gfs2_meta_wipe(ip, bstart, blen);
+}
+
+/**
+ * gfs2_free_meta - free a contiguous run of data block(s)
+ * @ip: the inode these blocks are being freed from
+ * @bstart: first block of a run of contiguous blocks
+ * @blen: the length of the block run
+ *
+ */
+
+void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	__gfs2_free_meta(ip, bstart, blen);
+	gfs2_statfs_change(sdp, 0, +blen, 0);
+	gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid);
+}
+
+void gfs2_unlink_di(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_rgrpd *rgd;
+	u64 blkno = ip->i_no_addr;
+
+	rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED);
+	if (!rgd)
+		return;
+	trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED);
+	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	gfs2_trans_add_rg(rgd);
+}
+
+static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	struct gfs2_rgrpd *tmp_rgd;
+
+	tmp_rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_FREE);
+	if (!tmp_rgd)
+		return;
+	gfs2_assert_withdraw(sdp, rgd == tmp_rgd);
+
+	if (!rgd->rd_dinodes)
+		gfs2_consist_rgrpd(rgd);
+	rgd->rd_dinodes--;
+	rgd->rd_free++;
+
+	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+
+	gfs2_statfs_change(sdp, 0, +1, -1);
+	gfs2_trans_add_rg(rgd);
+}
+
+
+void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
+{
+	gfs2_free_uninit_di(rgd, ip->i_no_addr);
+	trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE);
+	gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid);
+	gfs2_meta_wipe(ip, ip->i_no_addr, 1);
+}
+
+/**
+ * gfs2_check_blk_type - Check the type of a block
+ * @sdp: The superblock
+ * @no_addr: The block number to check
+ * @type: The block type we are looking for
+ *
+ * Returns: 0 if the block type matches the expected type
+ *          -ESTALE if it doesn't match
+ *          or -ve errno if something went wrong while checking
+ */
+
+int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
+{
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_holder ri_gh, rgd_gh;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
+	int ri_locked = 0;
+	int error;
+
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		error = gfs2_rindex_hold(sdp, &ri_gh);
+		if (error)
+			goto fail;
+		ri_locked = 1;
+	}
+
+	error = -EINVAL;
+	rgd = gfs2_blk2rgrpd(sdp, no_addr);
+	if (!rgd)
+		goto fail_rindex;
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
+	if (error)
+		goto fail_rindex;
+
+	if (gfs2_get_block_type(rgd, no_addr) != type)
+		error = -ESTALE;
+
+	gfs2_glock_dq_uninit(&rgd_gh);
+fail_rindex:
+	if (ri_locked)
+		gfs2_glock_dq_uninit(&ri_gh);
+fail:
+	return error;
+}
+
+/**
+ * gfs2_rlist_add - add a RG to a list of RGs
+ * @sdp: the filesystem
+ * @rlist: the list of resource groups
+ * @block: the block
+ *
+ * Figure out what RG a block belongs to and add that RG to the list
+ *
+ * FIXME: Don't use NOFAIL
+ *
+ */
+
+void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+		    u64 block)
+{
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_rgrpd **tmp;
+	unsigned int new_space;
+	unsigned int x;
+
+	if (gfs2_assert_warn(sdp, !rlist->rl_ghs))
+		return;
+
+	rgd = gfs2_blk2rgrpd(sdp, block);
+	if (!rgd) {
+		if (gfs2_consist(sdp))
+			fs_err(sdp, "block = %llu\n", (unsigned long long)block);
+		return;
+	}
+
+	for (x = 0; x < rlist->rl_rgrps; x++)
+		if (rlist->rl_rgd[x] == rgd)
+			return;
+
+	if (rlist->rl_rgrps == rlist->rl_space) {
+		new_space = rlist->rl_space + 10;
+
+		tmp = kcalloc(new_space, sizeof(struct gfs2_rgrpd *),
+			      GFP_NOFS | __GFP_NOFAIL);
+
+		if (rlist->rl_rgd) {
+			memcpy(tmp, rlist->rl_rgd,
+			       rlist->rl_space * sizeof(struct gfs2_rgrpd *));
+			kfree(rlist->rl_rgd);
+		}
+
+		rlist->rl_space = new_space;
+		rlist->rl_rgd = tmp;
+	}
+
+	rlist->rl_rgd[rlist->rl_rgrps++] = rgd;
+}
+
+/**
+ * gfs2_rlist_alloc - all RGs have been added to the rlist, now allocate
+ *      and initialize an array of glock holders for them
+ * @rlist: the list of resource groups
+ * @state: the lock state to acquire the RG lock in
+ * @flags: the modifier flags for the holder structures
+ *
+ * FIXME: Don't use NOFAIL
+ *
+ */
+
+void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state)
+{
+	unsigned int x;
+
+	rlist->rl_ghs = kcalloc(rlist->rl_rgrps, sizeof(struct gfs2_holder),
+				GFP_NOFS | __GFP_NOFAIL);
+	for (x = 0; x < rlist->rl_rgrps; x++)
+		gfs2_holder_init(rlist->rl_rgd[x]->rd_gl,
+				state, 0,
+				&rlist->rl_ghs[x]);
+}
+
+/**
+ * gfs2_rlist_free - free a resource group list
+ * @list: the list of resource groups
+ *
+ */
+
+void gfs2_rlist_free(struct gfs2_rgrp_list *rlist)
+{
+	unsigned int x;
+
+	kfree(rlist->rl_rgd);
+
+	if (rlist->rl_ghs) {
+		for (x = 0; x < rlist->rl_rgrps; x++)
+			gfs2_holder_uninit(&rlist->rl_ghs[x]);
+		kfree(rlist->rl_ghs);
+	}
+}
+
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
new file mode 100644
index 00000000..a80e3034
--- /dev/null
+++ b/fs/gfs2/rgrp.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __RGRP_DOT_H__
+#define __RGRP_DOT_H__
+
+#include <linux/slab.h>
+
+struct gfs2_rgrpd;
+struct gfs2_sbd;
+struct gfs2_holder;
+
+extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
+
+struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
+struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
+struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
+
+extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
+extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
+
+extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
+
+extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
+
+extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
+static inline void gfs2_alloc_put(struct gfs2_inode *ip)
+{
+	BUG_ON(ip->i_alloc == NULL);
+	kfree(ip->i_alloc);
+	ip->i_alloc = NULL;
+}
+
+extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+				  char *file, unsigned int line);
+#define gfs2_inplace_reserve(ip) \
+	gfs2_inplace_reserve_i((ip), 1, __FILE__, __LINE__)
+#define gfs2_inplace_reserve_ri(ip) \
+	gfs2_inplace_reserve_i((ip), 0, __FILE__, __LINE__)
+
+extern void gfs2_inplace_release(struct gfs2_inode *ip);
+
+extern int gfs2_ri_update(struct gfs2_inode *ip);
+extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
+extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);
+
+extern void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void __gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
+extern void gfs2_unlink_di(struct inode *inode);
+extern int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr,
+			       unsigned int type);
+
+struct gfs2_rgrp_list {
+	unsigned int rl_rgrps;
+	unsigned int rl_space;
+	struct gfs2_rgrpd **rl_rgd;
+	struct gfs2_holder *rl_ghs;
+};
+
+extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+			   u64 block);
+extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
+extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
+extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
+extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
+
+#endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
new file mode 100644
index 00000000..fb0edf73
--- /dev/null
+++ b/fs/gfs2/super.c
@@ -0,0 +1,1585 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/bio.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/time.h>
+#include <linux/wait.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "trans.h"
+#include "util.h"
+#include "sys.h"
+#include "xattr.h"
+
+#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
+
+enum {
+	Opt_lockproto,
+	Opt_locktable,
+	Opt_hostdata,
+	Opt_spectator,
+	Opt_ignore_local_fs,
+	Opt_localflocks,
+	Opt_localcaching,
+	Opt_debug,
+	Opt_nodebug,
+	Opt_upgrade,
+	Opt_acl,
+	Opt_noacl,
+	Opt_quota_off,
+	Opt_quota_account,
+	Opt_quota_on,
+	Opt_quota,
+	Opt_noquota,
+	Opt_suiddir,
+	Opt_nosuiddir,
+	Opt_data_writeback,
+	Opt_data_ordered,
+	Opt_meta,
+	Opt_discard,
+	Opt_nodiscard,
+	Opt_commit,
+	Opt_err_withdraw,
+	Opt_err_panic,
+	Opt_statfs_quantum,
+	Opt_statfs_percent,
+	Opt_quota_quantum,
+	Opt_barrier,
+	Opt_nobarrier,
+	Opt_error,
+};
+
+static const match_table_t tokens = {
+	{Opt_lockproto, "lockproto=%s"},
+	{Opt_locktable, "locktable=%s"},
+	{Opt_hostdata, "hostdata=%s"},
+	{Opt_spectator, "spectator"},
+	{Opt_spectator, "norecovery"},
+	{Opt_ignore_local_fs, "ignore_local_fs"},
+	{Opt_localflocks, "localflocks"},
+	{Opt_localcaching, "localcaching"},
+	{Opt_debug, "debug"},
+	{Opt_nodebug, "nodebug"},
+	{Opt_upgrade, "upgrade"},
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+	{Opt_quota_off, "quota=off"},
+	{Opt_quota_account, "quota=account"},
+	{Opt_quota_on, "quota=on"},
+	{Opt_quota, "quota"},
+	{Opt_noquota, "noquota"},
+	{Opt_suiddir, "suiddir"},
+	{Opt_nosuiddir, "nosuiddir"},
+	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_meta, "meta"},
+	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
+	{Opt_commit, "commit=%d"},
+	{Opt_err_withdraw, "errors=withdraw"},
+	{Opt_err_panic, "errors=panic"},
+	{Opt_statfs_quantum, "statfs_quantum=%d"},
+	{Opt_statfs_percent, "statfs_percent=%d"},
+	{Opt_quota_quantum, "quota_quantum=%d"},
+	{Opt_barrier, "barrier"},
+	{Opt_nobarrier, "nobarrier"},
+	{Opt_error, NULL}
+};
+
+/**
+ * gfs2_mount_args - Parse mount options
+ * @args: The structure into which the parsed options will be written
+ * @options: The options to parse
+ *
+ * Return: errno
+ */
+
+int gfs2_mount_args(struct gfs2_args *args, char *options)
+{
+	char *o;
+	int token;
+	substring_t tmp[MAX_OPT_ARGS];
+	int rv;
+
+	/* Split the options into tokens with the "," character and
+	   process them */
+
+	while (1) {
+		o = strsep(&options, ",");
+		if (o == NULL)
+			break;
+		if (*o == '\0')
+			continue;
+
+		token = match_token(o, tokens, tmp);
+		switch (token) {
+		case Opt_lockproto:
+			match_strlcpy(args->ar_lockproto, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_locktable:
+			match_strlcpy(args->ar_locktable, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_hostdata:
+			match_strlcpy(args->ar_hostdata, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_spectator:
+			args->ar_spectator = 1;
+			break;
+		case Opt_ignore_local_fs:
+			/* Retained for backwards compat only */
+			break;
+		case Opt_localflocks:
+			args->ar_localflocks = 1;
+			break;
+		case Opt_localcaching:
+			/* Retained for backwards compat only */
+			break;
+		case Opt_debug:
+			if (args->ar_errors == GFS2_ERRORS_PANIC) {
+				printk(KERN_WARNING "GFS2: -o debug and -o errors=panic "
+				       "are mutually exclusive.\n");
+				return -EINVAL;
+			}
+			args->ar_debug = 1;
+			break;
+		case Opt_nodebug:
+			args->ar_debug = 0;
+			break;
+		case Opt_upgrade:
+			/* Retained for backwards compat only */
+			break;
+		case Opt_acl:
+			args->ar_posix_acl = 1;
+			break;
+		case Opt_noacl:
+			args->ar_posix_acl = 0;
+			break;
+		case Opt_quota_off:
+		case Opt_noquota:
+			args->ar_quota = GFS2_QUOTA_OFF;
+			break;
+		case Opt_quota_account:
+			args->ar_quota = GFS2_QUOTA_ACCOUNT;
+			break;
+		case Opt_quota_on:
+		case Opt_quota:
+			args->ar_quota = GFS2_QUOTA_ON;
+			break;
+		case Opt_suiddir:
+			args->ar_suiddir = 1;
+			break;
+		case Opt_nosuiddir:
+			args->ar_suiddir = 0;
+			break;
+		case Opt_data_writeback:
+			args->ar_data = GFS2_DATA_WRITEBACK;
+			break;
+		case Opt_data_ordered:
+			args->ar_data = GFS2_DATA_ORDERED;
+			break;
+		case Opt_meta:
+			args->ar_meta = 1;
+			break;
+		case Opt_discard:
+			args->ar_discard = 1;
+			break;
+		case Opt_nodiscard:
+			args->ar_discard = 0;
+			break;
+		case Opt_commit:
+			rv = match_int(&tmp[0], &args->ar_commit);
+			if (rv || args->ar_commit <= 0) {
+				printk(KERN_WARNING "GFS2: commit mount option requires a positive numeric argument\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
+		case Opt_statfs_quantum:
+			rv = match_int(&tmp[0], &args->ar_statfs_quantum);
+			if (rv || args->ar_statfs_quantum < 0) {
+				printk(KERN_WARNING "GFS2: statfs_quantum mount option requires a non-negative numeric argument\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
+		case Opt_quota_quantum:
+			rv = match_int(&tmp[0], &args->ar_quota_quantum);
+			if (rv || args->ar_quota_quantum <= 0) {
+				printk(KERN_WARNING "GFS2: quota_quantum mount option requires a positive numeric argument\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
+		case Opt_statfs_percent:
+			rv = match_int(&tmp[0], &args->ar_statfs_percent);
+			if (rv || args->ar_statfs_percent < 0 ||
+			    args->ar_statfs_percent > 100) {
+				printk(KERN_WARNING "statfs_percent mount option requires a numeric argument between 0 and 100\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
+		case Opt_err_withdraw:
+			args->ar_errors = GFS2_ERRORS_WITHDRAW;
+			break;
+		case Opt_err_panic:
+			if (args->ar_debug) {
+				printk(KERN_WARNING "GFS2: -o debug and -o errors=panic "
+					"are mutually exclusive.\n");
+				return -EINVAL;
+			}
+			args->ar_errors = GFS2_ERRORS_PANIC;
+			break;
+		case Opt_barrier:
+			args->ar_nobarrier = 0;
+			break;
+		case Opt_nobarrier:
+			args->ar_nobarrier = 1;
+			break;
+		case Opt_error:
+		default:
+			printk(KERN_WARNING "GFS2: invalid mount option: %s\n", o);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_jindex_free - Clear all the journal index information
+ * @sdp: The GFS2 superblock
+ *
+ */
+
+void gfs2_jindex_free(struct gfs2_sbd *sdp)
+{
+	struct list_head list, *head;
+	struct gfs2_jdesc *jd;
+	struct gfs2_journal_extent *jext;
+
+	spin_lock(&sdp->sd_jindex_spin);
+	list_add(&list, &sdp->sd_jindex_list);
+	list_del_init(&sdp->sd_jindex_list);
+	sdp->sd_journals = 0;
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	while (!list_empty(&list)) {
+		jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
+		head = &jd->extent_list;
+		while (!list_empty(head)) {
+			jext = list_entry(head->next,
+					  struct gfs2_journal_extent,
+					  extent_list);
+			list_del(&jext->extent_list);
+			kfree(jext);
+		}
+		list_del(&jd->jd_list);
+		iput(jd->jd_inode);
+		kfree(jd);
+	}
+}
+
+static struct gfs2_jdesc *jdesc_find_i(struct list_head *head, unsigned int jid)
+{
+	struct gfs2_jdesc *jd;
+	int found = 0;
+
+	list_for_each_entry(jd, head, jd_list) {
+		if (jd->jd_jid == jid) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		jd = NULL;
+
+	return jd;
+}
+
+struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid)
+{
+	struct gfs2_jdesc *jd;
+
+	spin_lock(&sdp->sd_jindex_spin);
+	jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	return jd;
+}
+
+int gfs2_jdesc_check(struct gfs2_jdesc *jd)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	u64 size = i_size_read(jd->jd_inode);
+
+	if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, 1 << 30))
+		return -EIO;
+
+	jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;
+
+	if (gfs2_write_alloc_required(ip, 0, size)) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+	struct gfs2_glock *j_gl = ip->i_gl;
+	struct gfs2_holder t_gh;
+	struct gfs2_log_header_host head;
+	int error;
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh);
+	if (error)
+		return error;
+
+	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
+
+	error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+	if (error)
+		goto fail;
+
+	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+		gfs2_consist(sdp);
+		error = -EIO;
+		goto fail;
+	}
+
+	/*  Initialize some head of the log stuff  */
+	sdp->sd_log_sequence = head.lh_sequence + 1;
+	gfs2_log_pointers_init(sdp, head.lh_blkno);
+
+	error = gfs2_quota_init(sdp);
+	if (error)
+		goto fail;
+
+	set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	gfs2_glock_dq_uninit(&t_gh);
+
+	return 0;
+
+fail:
+	t_gh.gh_flags |= GL_NOCACHE;
+	gfs2_glock_dq_uninit(&t_gh);
+
+	return error;
+}
+
+void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
+{
+	const struct gfs2_statfs_change *str = buf;
+
+	sc->sc_total = be64_to_cpu(str->sc_total);
+	sc->sc_free = be64_to_cpu(str->sc_free);
+	sc->sc_dinodes = be64_to_cpu(str->sc_dinodes);
+}
+
+static void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf)
+{
+	struct gfs2_statfs_change *str = buf;
+
+	str->sc_total = cpu_to_be64(sc->sc_total);
+	str->sc_free = cpu_to_be64(sc->sc_free);
+	str->sc_dinodes = cpu_to_be64(sc->sc_dinodes);
+}
+
+int gfs2_statfs_init(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct buffer_head *m_bh, *l_bh;
+	struct gfs2_holder gh;
+	int error;
+
+	error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
+				   &gh);
+	if (error)
+		return error;
+
+	error = gfs2_meta_inode_buffer(m_ip, &m_bh);
+	if (error)
+		goto out;
+
+	if (sdp->sd_args.ar_spectator) {
+		spin_lock(&sdp->sd_statfs_spin);
+		gfs2_statfs_change_in(m_sc, m_bh->b_data +
+				      sizeof(struct gfs2_dinode));
+		spin_unlock(&sdp->sd_statfs_spin);
+	} else {
+		error = gfs2_meta_inode_buffer(l_ip, &l_bh);
+		if (error)
+			goto out_m_bh;
+
+		spin_lock(&sdp->sd_statfs_spin);
+		gfs2_statfs_change_in(m_sc, m_bh->b_data +
+				      sizeof(struct gfs2_dinode));
+		gfs2_statfs_change_in(l_sc, l_bh->b_data +
+				      sizeof(struct gfs2_dinode));
+		spin_unlock(&sdp->sd_statfs_spin);
+
+		brelse(l_bh);
+	}
+
+out_m_bh:
+	brelse(m_bh);
+out:
+	gfs2_glock_dq_uninit(&gh);
+	return 0;
+}
+
+void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
+			s64 dinodes)
+{
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct buffer_head *l_bh;
+	s64 x, y;
+	int need_sync = 0;
+	int error;
+
+	error = gfs2_meta_inode_buffer(l_ip, &l_bh);
+	if (error)
+		return;
+
+	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+
+	spin_lock(&sdp->sd_statfs_spin);
+	l_sc->sc_total += total;
+	l_sc->sc_free += free;
+	l_sc->sc_dinodes += dinodes;
+	gfs2_statfs_change_out(l_sc, l_bh->b_data + sizeof(struct gfs2_dinode));
+	if (sdp->sd_args.ar_statfs_percent) {
+		x = 100 * l_sc->sc_free;
+		y = m_sc->sc_free * sdp->sd_args.ar_statfs_percent;
+		if (x >= y || x <= -y)
+			need_sync = 1;
+	}
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	brelse(l_bh);
+	if (need_sync)
+		gfs2_wake_up_statfs(sdp);
+}
+
+void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
+		   struct buffer_head *l_bh)
+{
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+
+	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+
+	spin_lock(&sdp->sd_statfs_spin);
+	m_sc->sc_total += l_sc->sc_total;
+	m_sc->sc_free += l_sc->sc_free;
+	m_sc->sc_dinodes += l_sc->sc_dinodes;
+	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
+	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
+	       0, sizeof(struct gfs2_statfs_change));
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
+	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+}
+
+int gfs2_statfs_sync(struct super_block *sb, int type)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct gfs2_holder gh;
+	struct buffer_head *m_bh, *l_bh;
+	int error;
+
+	error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
+				   &gh);
+	if (error)
+		return error;
+
+	error = gfs2_meta_inode_buffer(m_ip, &m_bh);
+	if (error)
+		goto out;
+
+	spin_lock(&sdp->sd_statfs_spin);
+	gfs2_statfs_change_in(m_sc, m_bh->b_data +
+			      sizeof(struct gfs2_dinode));
+	if (!l_sc->sc_total && !l_sc->sc_free && !l_sc->sc_dinodes) {
+		spin_unlock(&sdp->sd_statfs_spin);
+		goto out_bh;
+	}
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	error = gfs2_meta_inode_buffer(l_ip, &l_bh);
+	if (error)
+		goto out_bh;
+
+	error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
+	if (error)
+		goto out_bh2;
+
+	update_statfs(sdp, m_bh, l_bh);
+	sdp->sd_statfs_force_sync = 0;
+
+	gfs2_trans_end(sdp);
+
+out_bh2:
+	brelse(l_bh);
+out_bh:
+	brelse(m_bh);
+out:
+	gfs2_glock_dq_uninit(&gh);
+	return error;
+}
+
+struct lfcc {
+	struct list_head list;
+	struct gfs2_holder gh;
+};
+
+/**
+ * gfs2_lock_fs_check_clean - Stop all writes to the FS and check that all
+ *                            journals are clean
+ * @sdp: the file system
+ * @state: the state to put the transaction lock into
+ * @t_gh: the hold on the transaction lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
+				    struct gfs2_holder *t_gh)
+{
+	struct gfs2_inode *ip;
+	struct gfs2_jdesc *jd;
+	struct lfcc *lfcc;
+	LIST_HEAD(list);
+	struct gfs2_log_header_host lh;
+	int error;
+
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL);
+		if (!lfcc) {
+			error = -ENOMEM;
+			goto out;
+		}
+		ip = GFS2_I(jd->jd_inode);
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &lfcc->gh);
+		if (error) {
+			kfree(lfcc);
+			goto out;
+		}
+		list_add(&lfcc->list, &list);
+	}
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
+				   GL_NOCACHE, t_gh);
+
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		error = gfs2_jdesc_check(jd);
+		if (error)
+			break;
+		error = gfs2_find_jhead(jd, &lh);
+		if (error)
+			break;
+		if (!(lh.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+			error = -EBUSY;
+			break;
+		}
+	}
+
+	if (error)
+		gfs2_glock_dq_uninit(t_gh);
+
+out:
+	while (!list_empty(&list)) {
+		lfcc = list_entry(list.next, struct lfcc, list);
+		list_del(&lfcc->list);
+		gfs2_glock_dq_uninit(&lfcc->gh);
+		kfree(lfcc);
+	}
+	return error;
+}
+
+/**
+ * gfs2_freeze_fs - freezes the file system
+ * @sdp: the file system
+ *
+ * This function flushes data and meta data for all machines by
+ * acquiring the transaction log exclusively.  All journals are
+ * ensured to be in a clean state as well.
+ *
+ * Returns: errno
+ */
+
+int gfs2_freeze_fs(struct gfs2_sbd *sdp)
+{
+	int error = 0;
+
+	mutex_lock(&sdp->sd_freeze_lock);
+
+	if (!sdp->sd_freeze_count++) {
+		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
+		if (error)
+			sdp->sd_freeze_count--;
+	}
+
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	return error;
+}
+
+/**
+ * gfs2_unfreeze_fs - unfreezes the file system
+ * @sdp: the file system
+ *
+ * This function allows the file system to proceed by unlocking
+ * the exclusively held transaction lock.  Other GFS2 nodes are
+ * now free to acquire the lock shared and go on with their lives.
+ *
+ */
+
+void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
+{
+	mutex_lock(&sdp->sd_freeze_lock);
+
+	if (sdp->sd_freeze_count && !--sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+
+	mutex_unlock(&sdp->sd_freeze_lock);
+}
+
+void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
+{
+	struct gfs2_dinode *str = buf;
+
+	str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
+	str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
+	str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
+	str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
+	str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
+	str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
+	str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
+	str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
+	str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
+	str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
+	str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
+	str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
+	str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);
+
+	str->di_goal_meta = cpu_to_be64(ip->i_goal);
+	str->di_goal_data = cpu_to_be64(ip->i_goal);
+	str->di_generation = cpu_to_be64(ip->i_generation);
+
+	str->di_flags = cpu_to_be32(ip->i_diskflags);
+	str->di_height = cpu_to_be16(ip->i_height);
+	str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
+					     !(ip->i_diskflags & GFS2_DIF_EXHASH) ?
+					     GFS2_FORMAT_DE : 0);
+	str->di_depth = cpu_to_be16(ip->i_depth);
+	str->di_entries = cpu_to_be32(ip->i_entries);
+
+	str->di_eattr = cpu_to_be64(ip->i_eattr);
+	str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
+	str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec);
+	str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec);
+}
+
+/**
+ * gfs2_write_inode - Make sure the inode is stable on the disk
+ * @inode: The inode
+ * @wbc: The writeback control structure
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
+	struct backing_dev_info *bdi = metamapping->backing_dev_info;
+	struct gfs2_holder gh;
+	struct buffer_head *bh;
+	struct timespec atime;
+	struct gfs2_dinode *di;
+	int ret = -EAGAIN;
+	int unlock_required = 0;
+
+	/* Skip timestamp update, if this is from a memalloc */
+	if (current->flags & PF_MEMALLOC)
+		goto do_flush;
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+		if (ret)
+			goto do_flush;
+		unlock_required = 1;
+	}
+	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (ret)
+		goto do_unlock;
+	ret = gfs2_meta_inode_buffer(ip, &bh);
+	if (ret == 0) {
+		di = (struct gfs2_dinode *)bh->b_data;
+		atime.tv_sec = be64_to_cpu(di->di_atime);
+		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
+		if (timespec_compare(&inode->i_atime, &atime) > 0) {
+			gfs2_trans_add_bh(ip->i_gl, bh, 1);
+			gfs2_dinode_out(ip, bh->b_data);
+		}
+		brelse(bh);
+	}
+	gfs2_trans_end(sdp);
+do_unlock:
+	if (unlock_required)
+		gfs2_glock_dq_uninit(&gh);
+do_flush:
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	filemap_fdatawrite(metamapping);
+	if (bdi->dirty_exceeded)
+		gfs2_ail1_flush(sdp, wbc);
+	if (!ret && (wbc->sync_mode == WB_SYNC_ALL))
+		ret = filemap_fdatawait(metamapping);
+	if (ret)
+		mark_inode_dirty_sync(inode);
+	return ret;
+}
+
+/**
+ * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+{
+	struct gfs2_holder t_gh;
+	int error;
+
+	flush_workqueue(gfs2_delete_workqueue);
+	gfs2_quota_sync(sdp->sd_vfs, 0, 1);
+	gfs2_statfs_sync(sdp->sd_vfs, 0);
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
+				   &t_gh);
+	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return error;
+
+	gfs2_meta_syncfs(sdp);
+	gfs2_log_shutdown(sdp);
+
+	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	if (t_gh.gh_gl)
+		gfs2_glock_dq_uninit(&t_gh);
+
+	gfs2_quota_cleanup(sdp);
+
+	return error;
+}
+
+static int gfs2_umount_recovery_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+/**
+ * gfs2_put_super - Unmount the filesystem
+ * @sb: The VFS superblock
+ *
+ */
+
+static void gfs2_put_super(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+	struct gfs2_jdesc *jd;
+
+	/*  Unfreeze the filesystem, if we need to  */
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	if (sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	/* No more recovery requests */
+	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	smp_mb();
+
+	/* Wait on outstanding recovery */
+restart:
+	spin_lock(&sdp->sd_jindex_spin);
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
+			continue;
+		spin_unlock(&sdp->sd_jindex_spin);
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
+			    gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE);
+		goto restart;
+	}
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		error = gfs2_make_fs_ro(sdp);
+		if (error)
+			gfs2_io_error(sdp);
+	}
+	/*  At this point, we're through modifying the disk  */
+
+	/*  Release stuff  */
+
+	iput(sdp->sd_jindex);
+	iput(sdp->sd_statfs_inode);
+	iput(sdp->sd_rindex);
+	iput(sdp->sd_quota_inode);
+
+	gfs2_glock_put(sdp->sd_rename_gl);
+	gfs2_glock_put(sdp->sd_trans_gl);
+
+	if (!sdp->sd_args.ar_spectator) {
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+		iput(sdp->sd_sc_inode);
+		iput(sdp->sd_qc_inode);
+	}
+
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+	gfs2_clear_rgrpd(sdp);
+	gfs2_jindex_free(sdp);
+	/*  Take apart glock structures and buffer lists  */
+	gfs2_gl_hash_clear(sdp);
+	/*  Unmount the locking protocol  */
+	gfs2_lm_unmount(sdp);
+
+	/*  At this point, we're through participating in the lockspace  */
+	gfs2_sys_fs_del(sdp);
+}
+
+/**
+ * gfs2_sync_fs - sync the filesystem
+ * @sb: the superblock
+ *
+ * Flushes the log to disk.
+ */
+
+static int gfs2_sync_fs(struct super_block *sb, int wait)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	if (wait && sdp)
+		gfs2_log_flush(sdp, NULL);
+	return 0;
+}
+
+/**
+ * gfs2_freeze - prevent further writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static int gfs2_freeze(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return -EINVAL;
+
+	for (;;) {
+		error = gfs2_freeze_fs(sdp);
+		if (!error)
+			break;
+
+		switch (error) {
+		case -EBUSY:
+			fs_err(sdp, "waiting for recovery before freeze\n");
+			break;
+
+		default:
+			fs_err(sdp, "error freezing FS: %d\n", error);
+			break;
+		}
+
+		fs_err(sdp, "retrying...\n");
+		msleep(1000);
+	}
+	return 0;
+}
+
+/**
+ * gfs2_unfreeze - reallow writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static int gfs2_unfreeze(struct super_block *sb)
+{
+	gfs2_unfreeze_fs(sb->s_fs_info);
+	return 0;
+}
+
+/**
+ * statfs_fill - fill in the sg for a given RG
+ * @rgd: the RG
+ * @sc: the sc structure
+ *
+ * Returns: 0 on success, -ESTALE if the LVB is invalid
+ */
+
+static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
+			    struct gfs2_statfs_change_host *sc)
+{
+	gfs2_rgrp_verify(rgd);
+	sc->sc_total += rgd->rd_data;
+	sc->sc_free += rgd->rd_free;
+	sc->sc_dinodes += rgd->rd_dinodes;
+	return 0;
+}
+
+/**
+ * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
+ * @sdp: the filesystem
+ * @sc: the sc info that will be returned
+ *
+ * Any error (other than a signal) will cause this routine to fall back
+ * to the synchronous version.
+ *
+ * FIXME: This really shouldn't busy wait like this.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_holder ri_gh;
+	struct gfs2_rgrpd *rgd_next;
+	struct gfs2_holder *gha, *gh;
+	unsigned int slots = 64;
+	unsigned int x;
+	int done;
+	int error = 0, err;
+
+	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
+	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
+	if (!gha)
+		return -ENOMEM;
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto out;
+
+	rgd_next = gfs2_rgrpd_get_first(sdp);
+
+	for (;;) {
+		done = 1;
+
+		for (x = 0; x < slots; x++) {
+			gh = gha + x;
+
+			if (gh->gh_gl && gfs2_glock_poll(gh)) {
+				err = gfs2_glock_wait(gh);
+				if (err) {
+					gfs2_holder_uninit(gh);
+					error = err;
+				} else {
+					if (!error)
+						error = statfs_slow_fill(
+							gh->gh_gl->gl_object, sc);
+					gfs2_glock_dq_uninit(gh);
+				}
+			}
+
+			if (gh->gh_gl)
+				done = 0;
+			else if (rgd_next && !error) {
+				error = gfs2_glock_nq_init(rgd_next->rd_gl,
+							   LM_ST_SHARED,
+							   GL_ASYNC,
+							   gh);
+				rgd_next = gfs2_rgrpd_get_next(rgd_next);
+				done = 0;
+			}
+
+			if (signal_pending(current))
+				error = -ERESTARTSYS;
+		}
+
+		if (done)
+			break;
+
+		yield();
+	}
+
+	gfs2_glock_dq_uninit(&ri_gh);
+
+out:
+	kfree(gha);
+	return error;
+}
+
+/**
+ * gfs2_statfs_i - Do a statfs
+ * @sdp: the filesystem
+ * @sg: the sg structure
+ *
+ * Returns: errno
+ */
+
+static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+
+	spin_lock(&sdp->sd_statfs_spin);
+
+	*sc = *m_sc;
+	sc->sc_total += l_sc->sc_total;
+	sc->sc_free += l_sc->sc_free;
+	sc->sc_dinodes += l_sc->sc_dinodes;
+
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	if (sc->sc_free < 0)
+		sc->sc_free = 0;
+	if (sc->sc_free > sc->sc_total)
+		sc->sc_free = sc->sc_total;
+	if (sc->sc_dinodes < 0)
+		sc->sc_dinodes = 0;
+
+	return 0;
+}
+
+/**
+ * gfs2_statfs - Gather and return stats about the filesystem
+ * @sb: The superblock
+ * @statfsbuf: The buffer
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_statfs_change_host sc;
+	int error;
+
+	if (gfs2_tune_get(sdp, gt_statfs_slow))
+		error = gfs2_statfs_slow(sdp, &sc);
+	else
+		error = gfs2_statfs_i(sdp, &sc);
+
+	if (error)
+		return error;
+
+	buf->f_type = GFS2_MAGIC;
+	buf->f_bsize = sdp->sd_sb.sb_bsize;
+	buf->f_blocks = sc.sc_total;
+	buf->f_bfree = sc.sc_free;
+	buf->f_bavail = sc.sc_free;
+	buf->f_files = sc.sc_dinodes + sc.sc_free;
+	buf->f_ffree = sc.sc_free;
+	buf->f_namelen = GFS2_FNAMESIZE;
+
+	return 0;
+}
+
+/**
+ * gfs2_remount_fs - called when the FS is remounted
+ * @sb:  the filesystem
+ * @flags:  the remount flags
+ * @data:  extra data passed in (not used right now)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	int error;
+
+	spin_lock(&gt->gt_spin);
+	args.ar_commit = gt->gt_logd_secs;
+	args.ar_quota_quantum = gt->gt_quota_quantum;
+	if (gt->gt_statfs_slow)
+		args.ar_statfs_quantum = 0;
+	else
+		args.ar_statfs_quantum = gt->gt_statfs_quantum;
+	spin_unlock(&gt->gt_spin);
+	error = gfs2_mount_args(&args, data);
+	if (error)
+		return error;
+
+	/* Not allowed to change locking details */
+	if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) ||
+	    strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) ||
+	    strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata))
+		return -EINVAL;
+
+	/* Some flags must not be changed */
+	if (args_neq(&args, &sdp->sd_args, spectator) ||
+	    args_neq(&args, &sdp->sd_args, localflocks) ||
+	    args_neq(&args, &sdp->sd_args, meta))
+		return -EINVAL;
+
+	if (sdp->sd_args.ar_spectator)
+		*flags |= MS_RDONLY;
+
+	if ((sb->s_flags ^ *flags) & MS_RDONLY) {
+		if (*flags & MS_RDONLY)
+			error = gfs2_make_fs_ro(sdp);
+		else
+			error = gfs2_make_fs_rw(sdp);
+		if (error)
+			return error;
+	}
+
+	sdp->sd_args = args;
+	if (sdp->sd_args.ar_posix_acl)
+		sb->s_flags |= MS_POSIXACL;
+	else
+		sb->s_flags &= ~MS_POSIXACL;
+	if (sdp->sd_args.ar_nobarrier)
+		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
+	else
+		clear_bit(SDF_NOBARRIERS, &sdp->sd_flags);
+	spin_lock(&gt->gt_spin);
+	gt->gt_logd_secs = args.ar_commit;
+	gt->gt_quota_quantum = args.ar_quota_quantum;
+	if (args.ar_statfs_quantum) {
+		gt->gt_statfs_slow = 0;
+		gt->gt_statfs_quantum = args.ar_statfs_quantum;
+	}
+	else {
+		gt->gt_statfs_slow = 1;
+		gt->gt_statfs_quantum = 30;
+	}
+	spin_unlock(&gt->gt_spin);
+
+	gfs2_online_uevent(sdp);
+	return 0;
+}
+
+/**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+
+static int gfs2_drop_inode(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (inode->i_nlink) {
+		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+			clear_nlink(inode);
+	}
+	return generic_drop_inode(inode);
+}
+
+static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
+{
+	do {
+		if (d1 == d2)
+			return 1;
+		d1 = d1->d_parent;
+	} while (!IS_ROOT(d1));
+	return 0;
+}
+
+/**
+ * gfs2_show_options - Show mount options for /proc/mounts
+ * @s: seq_file structure
+ * @mnt: vfsmount
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+{
+	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
+	struct gfs2_args *args = &sdp->sd_args;
+	int val;
+
+	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
+		seq_printf(s, ",meta");
+	if (args->ar_lockproto[0])
+		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
+	if (args->ar_locktable[0])
+		seq_printf(s, ",locktable=%s", args->ar_locktable);
+	if (args->ar_hostdata[0])
+		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
+	if (args->ar_spectator)
+		seq_printf(s, ",spectator");
+	if (args->ar_localflocks)
+		seq_printf(s, ",localflocks");
+	if (args->ar_debug)
+		seq_printf(s, ",debug");
+	if (args->ar_posix_acl)
+		seq_printf(s, ",acl");
+	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
+		char *state;
+		switch (args->ar_quota) {
+		case GFS2_QUOTA_OFF:
+			state = "off";
+			break;
+		case GFS2_QUOTA_ACCOUNT:
+			state = "account";
+			break;
+		case GFS2_QUOTA_ON:
+			state = "on";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",quota=%s", state);
+	}
+	if (args->ar_suiddir)
+		seq_printf(s, ",suiddir");
+	if (args->ar_data != GFS2_DATA_DEFAULT) {
+		char *state;
+		switch (args->ar_data) {
+		case GFS2_DATA_WRITEBACK:
+			state = "writeback";
+			break;
+		case GFS2_DATA_ORDERED:
+			state = "ordered";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",data=%s", state);
+	}
+	if (args->ar_discard)
+		seq_printf(s, ",discard");
+	val = sdp->sd_tune.gt_logd_secs;
+	if (val != 30)
+		seq_printf(s, ",commit=%d", val);
+	val = sdp->sd_tune.gt_statfs_quantum;
+	if (val != 30)
+		seq_printf(s, ",statfs_quantum=%d", val);
+	val = sdp->sd_tune.gt_quota_quantum;
+	if (val != 60)
+		seq_printf(s, ",quota_quantum=%d", val);
+	if (args->ar_statfs_percent)
+		seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent);
+	if (args->ar_errors != GFS2_ERRORS_DEFAULT) {
+		const char *state;
+
+		switch (args->ar_errors) {
+		case GFS2_ERRORS_WITHDRAW:
+			state = "withdraw";
+			break;
+		case GFS2_ERRORS_PANIC:
+			state = "panic";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",errors=%s", state);
+	}
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
+		seq_printf(s, ",nobarrier");
+	if (test_bit(SDF_DEMOTE, &sdp->sd_flags))
+		seq_printf(s, ",demote_interface_used");
+	return 0;
+}
+
+static void gfs2_final_release_pages(struct gfs2_inode *ip)
+{
+	struct inode *inode = &ip->i_inode;
+	struct gfs2_glock *gl = ip->i_gl;
+
+	truncate_inode_pages(gfs2_glock2aspace(ip->i_gl), 0);
+	truncate_inode_pages(&inode->i_data, 0);
+
+	if (atomic_read(&gl->gl_revokes) == 0) {
+		clear_bit(GLF_LFLUSH, &gl->gl_flags);
+		clear_bit(GLF_DIRTY, &gl->gl_flags);
+	}
+}
+
+static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al;
+	struct gfs2_rgrpd *rgd;
+	int error;
+
+	if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	al = gfs2_alloc_get(ip);
+	if (!al)
+		return -ENOMEM;
+
+	error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto out;
+
+	error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
+	if (error)
+		goto out_qs;
+
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+	if (!rgd) {
+		gfs2_consist_inode(ip);
+		error = -EIO;
+		goto out_rindex_relse;
+	}
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
+				   &al->al_rgd_gh);
+	if (error)
+		goto out_rindex_relse;
+
+	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
+				 sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_rg_gunlock;
+
+	gfs2_free_di(rgd, ip);
+
+	gfs2_final_release_pages(ip);
+
+	gfs2_trans_end(sdp);
+
+out_rg_gunlock:
+	gfs2_glock_dq_uninit(&al->al_rgd_gh);
+out_rindex_relse:
+	gfs2_glock_dq_uninit(&al->al_ri_gh);
+out_qs:
+	gfs2_quota_unhold(ip);
+out:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+/**
+ * gfs2_evict_inode - Remove an inode from cache
+ * @inode: The inode to evict
+ *
+ * There are three cases to consider:
+ * 1. i_nlink == 0, we are final opener (and must deallocate)
+ * 2. i_nlink == 0, we are not the final opener (and cannot deallocate)
+ * 3. i_nlink > 0
+ *
+ * If the fs is read only, then we have to treat all cases as per #3
+ * since we are unable to do any deallocation. The inode will be
+ * deallocated by the next read/write node to attempt an allocation
+ * in the same resource group
+ *
+ * We have to (at the moment) hold the inodes main lock to cover
+ * the gap between unlocking the shared lock on the iopen lock and
+ * taking the exclusive lock. I'd rather do a shared -> exclusive
+ * conversion on the iopen lock, but we can change that later. This
+ * is safe, just less efficient.
+ */
+
+static void gfs2_evict_inode(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+
+	if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
+		goto out;
+
+	/* Must not read inode block until block type has been verified */
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
+	if (unlikely(error)) {
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		goto out;
+	}
+
+	error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+	if (error)
+		goto out_truncate;
+
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			goto out_truncate;
+	}
+
+	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+	gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
+	error = gfs2_glock_nq(&ip->i_iopen_gh);
+	if (error)
+		goto out_truncate;
+
+	/* Case 1 starts here */
+
+	if (S_ISDIR(inode->i_mode) &&
+	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
+		error = gfs2_dir_exhash_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (ip->i_eattr) {
+		error = gfs2_ea_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (!gfs2_is_stuffed(ip)) {
+		error = gfs2_file_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	error = gfs2_dinode_dealloc(ip);
+	goto out_unlock;
+
+out_truncate:
+	/* Case 2 starts here */
+	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_unlock;
+	/* Needs to be done before glock release & also in a transaction */
+	truncate_inode_pages(&inode->i_data, 0);
+	gfs2_trans_end(sdp);
+
+out_unlock:
+	/* Error path for case 1 */
+	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
+		gfs2_glock_dq(&ip->i_iopen_gh);
+	gfs2_holder_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_uninit(&gh);
+	if (error && error != GLR_TRYFAILED && error != -EROFS)
+		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
+out:
+	/* Case 3 starts here */
+	truncate_inode_pages(&inode->i_data, 0);
+	end_writeback(inode);
+
+	ip->i_gl->gl_object = NULL;
+	gfs2_glock_add_to_lru(ip->i_gl);
+	gfs2_glock_put(ip->i_gl);
+	ip->i_gl = NULL;
+	if (ip->i_iopen_gh.gh_gl) {
+		ip->i_iopen_gh.gh_gl->gl_object = NULL;
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	}
+}
+
+static struct inode *gfs2_alloc_inode(struct super_block *sb)
+{
+	struct gfs2_inode *ip;
+
+	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
+	if (ip) {
+		ip->i_flags = 0;
+		ip->i_gl = NULL;
+	}
+	return &ip->i_inode;
+}
+
+static void gfs2_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(gfs2_inode_cachep, inode);
+}
+
+static void gfs2_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, gfs2_i_callback);
+}
+
+const struct super_operations gfs2_super_ops = {
+	.alloc_inode		= gfs2_alloc_inode,
+	.destroy_inode		= gfs2_destroy_inode,
+	.write_inode		= gfs2_write_inode,
+	.evict_inode		= gfs2_evict_inode,
+	.put_super		= gfs2_put_super,
+	.sync_fs		= gfs2_sync_fs,
+	.freeze_fs 		= gfs2_freeze,
+	.unfreeze_fs		= gfs2_unfreeze,
+	.statfs			= gfs2_statfs,
+	.remount_fs		= gfs2_remount_fs,
+	.drop_inode		= gfs2_drop_inode,
+	.show_options		= gfs2_show_options,
+};
+
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
new file mode 100644
index 00000000..a0464680
--- /dev/null
+++ b/fs/gfs2/super.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __SUPER_DOT_H__
+#define __SUPER_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/dcache.h>
+#include "incore.h"
+
+extern void gfs2_lm_unmount(struct gfs2_sbd *sdp);
+
+static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
+{
+	unsigned int x;
+	spin_lock(&sdp->sd_jindex_spin);
+	x = sdp->sd_journals;
+	spin_unlock(&sdp->sd_jindex_spin);
+	return x;
+}
+
+extern void gfs2_jindex_free(struct gfs2_sbd *sdp);
+
+extern int gfs2_mount_args(struct gfs2_args *args, char *data);
+
+extern struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid);
+extern int gfs2_jdesc_check(struct gfs2_jdesc *jd);
+
+extern int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
+				     struct gfs2_inode **ipp);
+
+extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
+extern void gfs2_online_uevent(struct gfs2_sbd *sdp);
+extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
+extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
+			       s64 dinodes);
+extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc,
+				  const void *buf);
+extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
+			  struct buffer_head *l_bh);
+extern int gfs2_statfs_sync(struct super_block *sb, int type);
+
+extern int gfs2_freeze_fs(struct gfs2_sbd *sdp);
+extern void gfs2_unfreeze_fs(struct gfs2_sbd *sdp);
+
+extern struct file_system_type gfs2_fs_type;
+extern struct file_system_type gfs2meta_fs_type;
+extern const struct export_operations gfs2_export_ops;
+extern const struct super_operations gfs2_super_ops;
+extern const struct dentry_operations gfs2_dops;
+extern const struct xattr_handler *gfs2_xattr_handlers[];
+
+#endif /* __SUPER_DOT_H__ */
+
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
new file mode 100644
index 00000000..443cabcf
--- /dev/null
+++ b/fs/gfs2/sys.c
@@ -0,0 +1,653 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <asm/uaccess.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/genhd.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "sys.h"
+#include "super.h"
+#include "glock.h"
+#include "quota.h"
+#include "util.h"
+#include "glops.h"
+#include "recovery.h"
+
+struct gfs2_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
+};
+
+static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->show ? a->show(sdp, buf) : 0;
+}
+
+static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->store ? a->store(sdp, buf, len) : len;
+}
+
+static const struct sysfs_ops gfs2_attr_ops = {
+	.show  = gfs2_attr_show,
+	.store = gfs2_attr_store,
+};
+
+
+static struct kset *gfs2_kset;
+
+static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u:%u\n",
+			MAJOR(sdp->sd_vfs->s_dev), MINOR(sdp->sd_vfs->s_dev));
+}
+
+static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname);
+}
+
+static int gfs2_uuid_valid(const u8 *uuid)
+{
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		if (uuid[i])
+			return 1;
+	}
+	return 0;
+}
+
+static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct super_block *s = sdp->sd_vfs;
+	const u8 *uuid = s->s_uuid;
+	buf[0] = '\0';
+	if (!gfs2_uuid_valid(uuid))
+		return 0;
+	return snprintf(buf, PAGE_SIZE, "%pUB\n", uuid);
+}
+
+static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
+{
+	unsigned int count;
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	count = sdp->sd_freeze_count;
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", count);
+}
+
+static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int error = 0;
+	int n = simple_strtol(buf, NULL, 0);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	switch (n) {
+	case 0:
+		gfs2_unfreeze_fs(sdp);
+		break;
+	case 1:
+		error = gfs2_freeze_fs(sdp);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (error)
+		fs_warn(sdp, "freeze %d error %d", n, error);
+
+	return ret;
+}
+
+static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
+{
+	unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags);
+	return snprintf(buf, PAGE_SIZE, "%u\n", b);
+}
+
+static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: withdrawing from cluster at user's request\n",
+		sdp->sd_fsname);
+	return len;
+}
+
+static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf,
+				 size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_statfs_sync(sdp->sd_vfs, 0);
+	return len;
+}
+
+static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf,
+				size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_quota_sync(sdp->sd_vfs, 0, 1);
+	return len;
+}
+
+static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf,
+					size_t len)
+{
+	int error;
+	u32 id;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	id = simple_strtoul(buf, NULL, 0);
+
+	error = gfs2_quota_refresh(sdp, 1, id);
+	return error ? error : len;
+}
+
+static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf,
+					 size_t len)
+{
+	int error;
+	u32 id;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	id = simple_strtoul(buf, NULL, 0);
+
+	error = gfs2_quota_refresh(sdp, 0, id);
+	return error ? error : len;
+}
+
+static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	struct gfs2_glock *gl;
+	const struct gfs2_glock_operations *glops;
+	unsigned int glmode;
+	unsigned int gltype;
+	unsigned long long glnum;
+	char mode[16];
+	int rv;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum,
+		    mode);
+	if (rv != 3)
+		return -EINVAL;
+
+	if (strcmp(mode, "EX") == 0)
+		glmode = LM_ST_UNLOCKED;
+	else if ((strcmp(mode, "CW") == 0) || (strcmp(mode, "DF") == 0))
+		glmode = LM_ST_DEFERRED;
+	else if ((strcmp(mode, "PR") == 0) || (strcmp(mode, "SH") == 0))
+		glmode = LM_ST_SHARED;
+	else
+		return -EINVAL;
+
+	if (gltype > LM_TYPE_JOURNAL)
+		return -EINVAL;
+	if (gltype == LM_TYPE_NONDISK && glnum == GFS2_TRANS_LOCK)
+		glops = &gfs2_trans_glops;
+	else
+		glops = gfs2_glops_list[gltype];
+	if (glops == NULL)
+		return -EINVAL;
+	if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
+		fs_info(sdp, "demote interface used\n");
+	rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl);
+	if (rv)
+		return rv;
+	gfs2_glock_cb(gl, glmode);
+	gfs2_glock_put(gl);
+	return len;
+}
+
+
+#define GFS2_ATTR(name, mode, show, store) \
+static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store)
+
+GFS2_ATTR(id,                  0444, id_show,       NULL);
+GFS2_ATTR(fsname,              0444, fsname_show,   NULL);
+GFS2_ATTR(uuid,                0444, uuid_show,     NULL);
+GFS2_ATTR(freeze,              0644, freeze_show,   freeze_store);
+GFS2_ATTR(withdraw,            0644, withdraw_show, withdraw_store);
+GFS2_ATTR(statfs_sync,         0200, NULL,          statfs_sync_store);
+GFS2_ATTR(quota_sync,          0200, NULL,          quota_sync_store);
+GFS2_ATTR(quota_refresh_user,  0200, NULL,          quota_refresh_user_store);
+GFS2_ATTR(quota_refresh_group, 0200, NULL,          quota_refresh_group_store);
+GFS2_ATTR(demote_rq,           0200, NULL,	    demote_rq_store);
+
+static struct attribute *gfs2_attrs[] = {
+	&gfs2_attr_id.attr,
+	&gfs2_attr_fsname.attr,
+	&gfs2_attr_uuid.attr,
+	&gfs2_attr_freeze.attr,
+	&gfs2_attr_withdraw.attr,
+	&gfs2_attr_statfs_sync.attr,
+	&gfs2_attr_quota_sync.attr,
+	&gfs2_attr_quota_refresh_user.attr,
+	&gfs2_attr_quota_refresh_group.attr,
+	&gfs2_attr_demote_rq.attr,
+	NULL,
+};
+
+static struct kobj_type gfs2_ktype = {
+	.default_attrs = gfs2_attrs,
+	.sysfs_ops     = &gfs2_attr_ops,
+};
+
+
+/*
+ * lock_module. Originally from lock_dlm
+ */
+
+static ssize_t proto_name_show(struct gfs2_sbd *sdp, char *buf)
+{
+	const struct lm_lockops *ops = sdp->sd_lockstruct.ls_ops;
+	return sprintf(buf, "%s\n", ops->lm_proto_name);
+}
+
+static ssize_t block_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	ssize_t ret;
+	int val = 0;
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))
+		val = 1;
+	ret = sprintf(buf, "%d\n", val);
+	return ret;
+}
+
+static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if (val == 1)
+		set_bit(DFL_BLOCK_LOCKS, &ls->ls_flags);
+	else if (val == 0) {
+		clear_bit(DFL_BLOCK_LOCKS, &ls->ls_flags);
+		smp_mb__after_clear_bit();
+		gfs2_glock_thaw(sdp);
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_first);
+}
+
+static ssize_t lkfirst_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	unsigned first;
+	int rv;
+
+	rv = sscanf(buf, "%u", &first);
+	if (rv != 1 || first > 1)
+		return -EINVAL;
+	rv = wait_for_completion_killable(&sdp->sd_locking_init);
+	if (rv)
+		return rv;
+	spin_lock(&sdp->sd_jindex_spin);
+	rv = -EBUSY;
+	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+		goto out;
+	rv = -EINVAL;
+	if (sdp->sd_args.ar_spectator)
+		goto out;
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		goto out;
+        sdp->sd_lockstruct.ls_first = first;
+        rv = 0;
+out:
+        spin_unlock(&sdp->sd_jindex_spin);
+        return rv ? rv : len;
+}
+
+static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_first_done);
+}
+
+static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	unsigned jid;
+	struct gfs2_jdesc *jd;
+	int rv;
+
+	rv = sscanf(buf, "%u", &jid);
+	if (rv != 1)
+		return -EINVAL;
+
+	rv = -ESHUTDOWN;
+	spin_lock(&sdp->sd_jindex_spin);
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags))
+		goto out;
+	rv = -EBUSY;
+	if (sdp->sd_jdesc->jd_jid == jid)
+		goto out;
+	rv = -ENOENT;
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (jd->jd_jid != jid)
+			continue;
+		rv = gfs2_recover_journal(jd, false);
+		break;
+	}
+out:
+	spin_unlock(&sdp->sd_jindex_spin);
+	return rv ? rv : len;
+}
+
+static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_recover_jid_done);
+}
+
+static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_recover_jid_status);
+}
+
+static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return sprintf(buf, "%d\n", sdp->sd_lockstruct.ls_jid);
+}
+
+static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+        int jid;
+	int rv;
+
+	rv = sscanf(buf, "%d", &jid);
+	if (rv != 1)
+		return -EINVAL;
+	rv = wait_for_completion_killable(&sdp->sd_locking_init);
+	if (rv)
+		return rv;
+	spin_lock(&sdp->sd_jindex_spin);
+	rv = -EINVAL;
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		goto out;
+	rv = -EBUSY;
+	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+		goto out;
+	rv = 0;
+	if (sdp->sd_args.ar_spectator && jid > 0)
+		rv = jid = -EINVAL;
+	sdp->sd_lockstruct.ls_jid = jid;
+	clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
+out:
+	spin_unlock(&sdp->sd_jindex_spin);
+	return rv ? rv : len;
+}
+
+#define GDLM_ATTR(_name,_mode,_show,_store) \
+static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
+
+GDLM_ATTR(proto_name,		0444, proto_name_show,		NULL);
+GDLM_ATTR(block,		0644, block_show,		block_store);
+GDLM_ATTR(withdraw,		0644, withdraw_show,		withdraw_store);
+GDLM_ATTR(jid,			0644, jid_show,			jid_store);
+GDLM_ATTR(first,		0644, lkfirst_show,		lkfirst_store);
+GDLM_ATTR(first_done,		0444, first_done_show,		NULL);
+GDLM_ATTR(recover,		0600, NULL,			recover_store);
+GDLM_ATTR(recover_done,		0444, recover_done_show,	NULL);
+GDLM_ATTR(recover_status,	0444, recover_status_show,	NULL);
+
+static struct attribute *lock_module_attrs[] = {
+	&gdlm_attr_proto_name.attr,
+	&gdlm_attr_block.attr,
+	&gdlm_attr_withdraw.attr,
+	&gdlm_attr_jid.attr,
+	&gdlm_attr_first.attr,
+	&gdlm_attr_first_done.attr,
+	&gdlm_attr_recover.attr,
+	&gdlm_attr_recover_done.attr,
+	&gdlm_attr_recover_status.attr,
+	NULL,
+};
+
+/*
+ * get and set struct gfs2_tune fields
+ */
+
+static ssize_t quota_scale_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u %u\n",
+			sdp->sd_tune.gt_quota_scale_num,
+			sdp->sd_tune.gt_quota_scale_den);
+}
+
+static ssize_t quota_scale_store(struct gfs2_sbd *sdp, const char *buf,
+				 size_t len)
+{
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	unsigned int x, y;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (sscanf(buf, "%u %u", &x, &y) != 2 || !y)
+		return -EINVAL;
+
+	spin_lock(&gt->gt_spin);
+	gt->gt_quota_scale_num = x;
+	gt->gt_quota_scale_den = y;
+	spin_unlock(&gt->gt_spin);
+	return len;
+}
+
+static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field,
+			int check_zero, const char *buf, size_t len)
+{
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	unsigned int x;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	x = simple_strtoul(buf, NULL, 0);
+
+	if (check_zero && !x)
+		return -EINVAL;
+
+	spin_lock(&gt->gt_spin);
+	*field = x;
+	spin_unlock(&gt->gt_spin);
+	return len;
+}
+
+#define TUNE_ATTR_3(name, show, store)                                        \
+static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store)
+
+#define TUNE_ATTR_2(name, store)                                              \
+static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                   \
+{                                                                             \
+	return snprintf(buf, PAGE_SIZE, "%u\n", sdp->sd_tune.gt_##name);      \
+}                                                                             \
+TUNE_ATTR_3(name, name##_show, store)
+
+#define TUNE_ATTR(name, check_zero)                                           \
+static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
+{                                                                             \
+	return tune_set(sdp, &sdp->sd_tune.gt_##name, check_zero, buf, len);  \
+}                                                                             \
+TUNE_ATTR_2(name, name##_store)
+
+TUNE_ATTR(quota_warn_period, 0);
+TUNE_ATTR(quota_quantum, 0);
+TUNE_ATTR(max_readahead, 0);
+TUNE_ATTR(complain_secs, 0);
+TUNE_ATTR(statfs_slow, 0);
+TUNE_ATTR(new_files_jdata, 0);
+TUNE_ATTR(quota_simul_sync, 1);
+TUNE_ATTR(statfs_quantum, 1);
+TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);
+
+static struct attribute *tune_attrs[] = {
+	&tune_attr_quota_warn_period.attr,
+	&tune_attr_quota_quantum.attr,
+	&tune_attr_max_readahead.attr,
+	&tune_attr_complain_secs.attr,
+	&tune_attr_statfs_slow.attr,
+	&tune_attr_quota_simul_sync.attr,
+	&tune_attr_statfs_quantum.attr,
+	&tune_attr_quota_scale.attr,
+	&tune_attr_new_files_jdata.attr,
+	NULL,
+};
+
+static struct attribute_group tune_group = {
+	.name = "tune",
+	.attrs = tune_attrs,
+};
+
+static struct attribute_group lock_module_group = {
+	.name = "lock_module",
+	.attrs = lock_module_attrs,
+};
+
+int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	int error;
+	char ro[20];
+	char spectator[20];
+	char *envp[] = { ro, spectator, NULL };
+
+	sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
+	sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);
+
+	sdp->sd_kobj.kset = gfs2_kset;
+	error = kobject_init_and_add(&sdp->sd_kobj, &gfs2_ktype, NULL,
+				     "%s", sdp->sd_table_name);
+	if (error)
+		goto fail;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
+	if (error)
+		goto fail_reg;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group);
+	if (error)
+		goto fail_tune;
+
+	error = sysfs_create_link(&sdp->sd_kobj,
+				  &disk_to_dev(sb->s_bdev->bd_disk)->kobj,
+				  "device");
+	if (error)
+		goto fail_lock_module;
+
+	kobject_uevent_env(&sdp->sd_kobj, KOBJ_ADD, envp);
+	return 0;
+
+fail_lock_module:
+	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
+fail_tune:
+	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
+fail_reg:
+	kobject_put(&sdp->sd_kobj);
+fail:
+	fs_err(sdp, "error %d adding sysfs files", error);
+	return error;
+}
+
+void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
+{
+	sysfs_remove_link(&sdp->sd_kobj, "device");
+	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
+	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
+	kobject_put(&sdp->sd_kobj);
+}
+
+static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
+		       struct kobj_uevent_env *env)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct super_block *s = sdp->sd_vfs;
+	const u8 *uuid = s->s_uuid;
+
+	add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
+	add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
+	if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
+		add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid);
+	if (gfs2_uuid_valid(uuid))
+		add_uevent_var(env, "UUID=%pUB", uuid);
+	return 0;
+}
+
+static const struct kset_uevent_ops gfs2_uevent_ops = {
+	.uevent = gfs2_uevent,
+};
+
+int gfs2_sys_init(void)
+{
+	gfs2_kset = kset_create_and_add("gfs2", &gfs2_uevent_ops, fs_kobj);
+	if (!gfs2_kset)
+		return -ENOMEM;
+	return 0;
+}
+
+void gfs2_sys_uninit(void)
+{
+	kset_unregister(gfs2_kset);
+}
+
diff --git a/fs/gfs2/sys.h b/fs/gfs2/sys.h
new file mode 100644
index 00000000..e94560e8
--- /dev/null
+++ b/fs/gfs2/sys.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __SYS_DOT_H__
+#define __SYS_DOT_H__
+
+#include <linux/spinlock.h>
+struct gfs2_sbd;
+
+int gfs2_sys_fs_add(struct gfs2_sbd *sdp);
+void gfs2_sys_fs_del(struct gfs2_sbd *sdp);
+
+int gfs2_sys_init(void);
+void gfs2_sys_uninit(void);
+
+#endif /* __SYS_DOT_H__ */
+
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
new file mode 100644
index 00000000..5d07609e
--- /dev/null
+++ b/fs/gfs2/trace_gfs2.h
@@ -0,0 +1,438 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gfs2
+
+#if !defined(_TRACE_GFS2_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_GFS2_H
+
+#include <linux/tracepoint.h>
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/dlmconstants.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/writeback.h>
+#include "incore.h"
+#include "glock.h"
+
+#define dlm_state_name(nn) { DLM_LOCK_##nn, #nn }
+#define glock_trace_name(x) __print_symbolic(x,		\
+			    dlm_state_name(IV),		\
+			    dlm_state_name(NL),		\
+			    dlm_state_name(CR),		\
+			    dlm_state_name(CW),		\
+			    dlm_state_name(PR),		\
+			    dlm_state_name(PW),		\
+			    dlm_state_name(EX))
+
+#define block_state_name(x) __print_symbolic(x,			\
+			    { GFS2_BLKST_FREE, "free" },	\
+			    { GFS2_BLKST_USED, "used" },	\
+			    { GFS2_BLKST_DINODE, "dinode" },	\
+			    { GFS2_BLKST_UNLINKED, "unlinked" })
+
+#define show_glock_flags(flags) __print_flags(flags, "",	\
+	{(1UL << GLF_LOCK),			"l" },		\
+	{(1UL << GLF_DEMOTE),			"D" },		\
+	{(1UL << GLF_PENDING_DEMOTE),		"d" },		\
+	{(1UL << GLF_DEMOTE_IN_PROGRESS),	"p" },		\
+	{(1UL << GLF_DIRTY),			"y" },		\
+	{(1UL << GLF_LFLUSH),			"f" },		\
+	{(1UL << GLF_INVALIDATE_IN_PROGRESS),	"i" },		\
+	{(1UL << GLF_REPLY_PENDING),		"r" },		\
+	{(1UL << GLF_INITIAL),			"I" },		\
+	{(1UL << GLF_FROZEN),			"F" },		\
+	{(1UL << GLF_QUEUED),			"q" },		\
+	{(1UL << GLF_LRU),			"L" },		\
+	{(1UL << GLF_OBJECT),			"o" })
+
+#ifndef NUMPTY
+#define NUMPTY
+static inline u8 glock_trace_state(unsigned int state)
+{
+	switch(state) {
+	case LM_ST_SHARED:
+		return DLM_LOCK_PR;
+	case LM_ST_DEFERRED:
+		return DLM_LOCK_CW;
+	case LM_ST_EXCLUSIVE:
+		return DLM_LOCK_EX;
+	}
+	return DLM_LOCK_NL;
+}
+#endif
+
+/* Section 1 - Locking
+ *
+ * Objectives:
+ * Latency: Remote demote request to state change
+ * Latency: Local lock request to state change
+ * Latency: State change to lock grant
+ * Correctness: Ordering of local lock state vs. I/O requests
+ * Correctness: Responses to remote demote requests
+ */
+
+/* General glock state change (DLM lock request completes) */
+TRACE_EVENT(gfs2_glock_state_change,
+
+	TP_PROTO(const struct gfs2_glock *gl, unsigned int new_state),
+
+	TP_ARGS(gl, new_state),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	u8,	cur_state		)
+		__field(	u8,	new_state		)
+		__field(	u8,	dmt_state		)
+		__field(	u8,	tgt_state		)
+		__field(	unsigned long,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum		= gl->gl_name.ln_number;
+		__entry->gltype		= gl->gl_name.ln_type;
+		__entry->cur_state	= glock_trace_state(gl->gl_state);
+		__entry->new_state	= glock_trace_state(new_state);
+		__entry->tgt_state	= glock_trace_state(gl->gl_target);
+		__entry->dmt_state	= glock_trace_state(gl->gl_demote_state);
+		__entry->flags		= gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+	),
+
+	TP_printk("%u,%u glock %d:%lld state %s to %s tgt:%s dmt:%s flags:%s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		 (unsigned long long)__entry->glnum,
+		  glock_trace_name(__entry->cur_state),
+		  glock_trace_name(__entry->new_state),
+		  glock_trace_name(__entry->tgt_state),
+		  glock_trace_name(__entry->dmt_state),
+		  show_glock_flags(__entry->flags))
+);
+
+/* State change -> unlocked, glock is being deallocated */
+TRACE_EVENT(gfs2_glock_put,
+
+	TP_PROTO(const struct gfs2_glock *gl),
+
+	TP_ARGS(gl),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	u8,	cur_state		)
+		__field(	unsigned long,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->gltype		= gl->gl_name.ln_type;
+		__entry->glnum		= gl->gl_name.ln_number;
+		__entry->cur_state	= glock_trace_state(gl->gl_state);
+		__entry->flags		= gl->gl_flags  | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+	),
+
+	TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->gltype, (unsigned long long)__entry->glnum,
+                  glock_trace_name(__entry->cur_state),
+		  glock_trace_name(DLM_LOCK_IV),
+		  show_glock_flags(__entry->flags))
+
+);
+
+/* Callback (local or remote) requesting lock demotion */
+TRACE_EVENT(gfs2_demote_rq,
+
+	TP_PROTO(const struct gfs2_glock *gl),
+
+	TP_ARGS(gl),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	u8,	cur_state		)
+		__field(	u8,	dmt_state		)
+		__field(	unsigned long,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->gltype		= gl->gl_name.ln_type;
+		__entry->glnum		= gl->gl_name.ln_number;
+		__entry->cur_state	= glock_trace_state(gl->gl_state);
+		__entry->dmt_state	= glock_trace_state(gl->gl_demote_state);
+		__entry->flags		= gl->gl_flags  | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+	),
+
+	TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+                  glock_trace_name(__entry->cur_state),
+                  glock_trace_name(__entry->dmt_state),
+		  show_glock_flags(__entry->flags))
+
+);
+
+/* Promotion/grant of a glock */
+TRACE_EVENT(gfs2_promote,
+
+	TP_PROTO(const struct gfs2_holder *gh, int first),
+
+	TP_ARGS(gh, first),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	int,	first			)
+		__field(	u8,	state			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum	= gh->gh_gl->gl_name.ln_number;
+		__entry->gltype	= gh->gh_gl->gl_name.ln_type;
+		__entry->first	= first;
+		__entry->state	= glock_trace_state(gh->gh_state);
+	),
+
+	TP_printk("%u,%u glock %u:%llu promote %s %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+		  __entry->first ? "first": "other",
+		  glock_trace_name(__entry->state))
+);
+
+/* Queue/dequeue a lock request */
+TRACE_EVENT(gfs2_glock_queue,
+
+	TP_PROTO(const struct gfs2_holder *gh, int queue),
+
+	TP_ARGS(gh, queue),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	int,	queue			)
+		__field(	u8,	state			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum	= gh->gh_gl->gl_name.ln_number;
+		__entry->gltype	= gh->gh_gl->gl_name.ln_type;
+		__entry->queue	= queue;
+		__entry->state	= glock_trace_state(gh->gh_state);
+	),
+
+	TP_printk("%u,%u glock %u:%llu %squeue %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+		  __entry->queue ? "" : "de",
+		  glock_trace_name(__entry->state))
+);
+
+/* Section 2 - Log/journal
+ *
+ * Objectives:
+ * Latency: Log flush time
+ * Correctness: pin/unpin vs. disk I/O ordering
+ * Performance: Log usage stats
+ */
+
+/* Pin/unpin a block in the log */
+TRACE_EVENT(gfs2_pin,
+
+	TP_PROTO(const struct gfs2_bufdata *bd, int pin),
+
+	TP_ARGS(bd, pin),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	int,	pin			)
+		__field(	u32,	len			)
+		__field(	sector_t,	block		)
+		__field(	u64,	ino			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bd->bd_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->pin		= pin;
+		__entry->len		= bd->bd_bh->b_size;
+		__entry->block		= bd->bd_bh->b_blocknr;
+		__entry->ino		= bd->bd_gl->gl_name.ln_number;
+	),
+
+	TP_printk("%u,%u log %s %llu/%lu inode %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->pin ? "pin" : "unpin",
+		  (unsigned long long)__entry->block,
+		  (unsigned long)__entry->len,
+		  (unsigned long long)__entry->ino)
+);
+
+/* Flushing the log */
+TRACE_EVENT(gfs2_log_flush,
+
+	TP_PROTO(const struct gfs2_sbd *sdp, int start),
+
+	TP_ARGS(sdp, start),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	int,	start			)
+		__field(	u64,	log_seq			)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = sdp->sd_vfs->s_dev;
+		__entry->start		= start;
+		__entry->log_seq	= sdp->sd_log_sequence;
+	),
+
+	TP_printk("%u,%u log flush %s %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->start ? "start" : "end",
+		  (unsigned long long)__entry->log_seq)
+);
+
+/* Reserving/releasing blocks in the log */
+TRACE_EVENT(gfs2_log_blocks,
+
+	TP_PROTO(const struct gfs2_sbd *sdp, int blocks),
+
+	TP_ARGS(sdp, blocks),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	int,	blocks			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sdp->sd_vfs->s_dev;
+		__entry->blocks		= blocks;
+	),
+
+	TP_printk("%u,%u log reserve %d", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), __entry->blocks)
+);
+
+/* Writing back the AIL */
+TRACE_EVENT(gfs2_ail_flush,
+
+	TP_PROTO(const struct gfs2_sbd *sdp, const struct writeback_control *wbc, int start),
+
+	TP_ARGS(sdp, wbc, start),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int, start			)
+		__field(	int, sync_mode			)
+		__field(	long, nr_to_write		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sdp->sd_vfs->s_dev;
+		__entry->start		= start;
+		__entry->sync_mode	= wbc->sync_mode;
+		__entry->nr_to_write	= wbc->nr_to_write;
+	),
+
+	TP_printk("%u,%u ail flush %s %s %ld", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), __entry->start ? "start" : "end",
+		  __entry->sync_mode == WB_SYNC_ALL ? "all" : "none",
+		  __entry->nr_to_write)
+);
+
+/* Section 3 - bmap
+ *
+ * Objectives:
+ * Latency: Bmap request time
+ * Performance: Block allocator tracing
+ * Correctness: Test of disard generation vs. blocks allocated
+ */
+
+/* Map an extent of blocks, possibly a new allocation */
+TRACE_EVENT(gfs2_bmap,
+
+	TP_PROTO(const struct gfs2_inode *ip, const struct buffer_head *bh,
+		sector_t lblock, int create, int errno),
+
+	TP_ARGS(ip, bh, lblock, create, errno),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	sector_t, lblock		)
+		__field(	sector_t, pblock		)
+		__field(	u64,	inum			)
+		__field(	unsigned long, state		)
+		__field(	u32,	len			)
+		__field(	int,	create			)
+		__field(	int,	errno			)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = ip->i_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->lblock		= lblock;
+		__entry->pblock		= buffer_mapped(bh) ?  bh->b_blocknr : 0;
+		__entry->inum		= ip->i_no_addr;
+		__entry->state		= bh->b_state;
+		__entry->len		= bh->b_size;
+		__entry->create		= create;
+		__entry->errno		= errno;
+	),
+
+	TP_printk("%u,%u bmap %llu map %llu/%lu to %llu flags:%08lx %s %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->lblock,
+		  (unsigned long)__entry->len,
+		  (unsigned long long)__entry->pblock,
+		  __entry->state, __entry->create ? "create " : "nocreate",
+		  __entry->errno)
+);
+
+/* Keep track of blocks as they are allocated/freed */
+TRACE_EVENT(gfs2_block_alloc,
+
+	TP_PROTO(const struct gfs2_inode *ip, u64 block, unsigned len,
+		u8 block_state),
+
+	TP_ARGS(ip, block, len, block_state),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	start			)
+		__field(	u64,	inum			)
+		__field(	u32,	len			)
+		__field(	u8,	block_state		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ip->i_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->start		= block;
+		__entry->inum		= ip->i_no_addr;
+		__entry->len		= len;
+		__entry->block_state	= block_state;
+	),
+
+	TP_printk("%u,%u bmap %llu alloc %llu/%lu %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->start,
+		  (unsigned long)__entry->len,
+		  block_state_name(__entry->block_state))
+);
+
+#endif /* _TRACE_GFS2_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_gfs2
+#include <trace/define_trace.h>
+
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
new file mode 100644
index 00000000..9ec73a85
--- /dev/null
+++ b/fs/gfs2/trans.c
@@ -0,0 +1,192 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/kallsyms.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+		     unsigned int revokes)
+{
+	struct gfs2_trans *tr;
+	int error;
+
+	BUG_ON(current->journal_info);
+	BUG_ON(blocks == 0 && revokes == 0);
+
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+		return -EROFS;
+
+	tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
+	if (!tr)
+		return -ENOMEM;
+
+	tr->tr_ip = (unsigned long)__builtin_return_address(0);
+	tr->tr_blocks = blocks;
+	tr->tr_revokes = revokes;
+	tr->tr_reserved = 1;
+	if (blocks)
+		tr->tr_reserved += 6 + blocks;
+	if (revokes)
+		tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
+						   sizeof(u64));
+	INIT_LIST_HEAD(&tr->tr_list_buf);
+
+	gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh);
+
+	error = gfs2_glock_nq(&tr->tr_t_gh);
+	if (error)
+		goto fail_holder_uninit;
+
+	error = gfs2_log_reserve(sdp, tr->tr_reserved);
+	if (error)
+		goto fail_gunlock;
+
+	current->journal_info = tr;
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq(&tr->tr_t_gh);
+
+fail_holder_uninit:
+	gfs2_holder_uninit(&tr->tr_t_gh);
+	kfree(tr);
+
+	return error;
+}
+
+/**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+	atomic_add(blks, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, blks);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+				  sdp->sd_jdesc->jd_blocks);
+	up_read(&sdp->sd_log_flush_lock);
+}
+
+void gfs2_trans_end(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr = current->journal_info;
+
+	BUG_ON(!tr);
+	current->journal_info = NULL;
+
+	if (!tr->tr_touched) {
+		gfs2_log_release(sdp, tr->tr_reserved);
+		if (tr->tr_t_gh.gh_gl) {
+			gfs2_glock_dq(&tr->tr_t_gh);
+			gfs2_holder_uninit(&tr->tr_t_gh);
+			kfree(tr);
+		}
+		return;
+	}
+
+	if (gfs2_assert_withdraw(sdp, tr->tr_num_buf <= tr->tr_blocks)) {
+		fs_err(sdp, "tr_num_buf = %u, tr_blocks = %u ",
+		       tr->tr_num_buf, tr->tr_blocks);
+		print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip);
+	}
+	if (gfs2_assert_withdraw(sdp, tr->tr_num_revoke <= tr->tr_revokes)) {
+		fs_err(sdp, "tr_num_revoke = %u, tr_revokes = %u ",
+		       tr->tr_num_revoke, tr->tr_revokes);
+		print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip);
+	}
+
+	gfs2_log_commit(sdp, tr);
+	if (tr->tr_t_gh.gh_gl) {
+		gfs2_glock_dq(&tr->tr_t_gh);
+		gfs2_holder_uninit(&tr->tr_t_gh);
+		kfree(tr);
+	}
+
+	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
+		gfs2_log_flush(sdp, NULL);
+}
+
+/**
+ * gfs2_trans_add_bh - Add a to-be-modified buffer to the current transaction
+ * @gl: the glock the buffer belongs to
+ * @bh: The buffer to add
+ * @meta: True in the case of adding metadata
+ *
+ */
+
+void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_bufdata *bd;
+
+	bd = bh->b_private;
+	if (bd)
+		gfs2_assert(sdp, bd->bd_gl == gl);
+	else {
+		gfs2_attach_bufdata(gl, bh, meta);
+		bd = bh->b_private;
+	}
+	lops_add(sdp, &bd->bd_le);
+}
+
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
+{
+	BUG_ON(!list_empty(&bd->bd_le.le_list));
+	BUG_ON(!list_empty(&bd->bd_ail_st_list));
+	BUG_ON(!list_empty(&bd->bd_ail_gl_list));
+	lops_init_le(&bd->bd_le, &gfs2_revoke_lops);
+	lops_add(sdp, &bd->bd_le);
+}
+
+void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
+{
+	struct gfs2_bufdata *bd, *tmp;
+	struct gfs2_trans *tr = current->journal_info;
+	unsigned int n = len;
+
+	gfs2_log_lock(sdp);
+	list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_le.le_list) {
+		if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) {
+			list_del_init(&bd->bd_le.le_list);
+			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
+			sdp->sd_log_num_revoke--;
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+			tr->tr_num_revoke_rm++;
+			if (--n == 0)
+				break;
+		}
+	}
+	gfs2_log_unlock(sdp);
+}
+
+void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd)
+{
+	lops_add(rgd->rd_sbd, &rgd->rd_le);
+}
+
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
new file mode 100644
index 00000000..fb56b783
--- /dev/null
+++ b/fs/gfs2/trans.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __TRANS_DOT_H__
+#define __TRANS_DOT_H__
+
+#include <linux/buffer_head.h>
+struct gfs2_sbd;
+struct gfs2_rgrpd;
+struct gfs2_glock;
+
+#define RES_DINODE	1
+#define RES_INDIRECT	1
+#define RES_JDATA	1
+#define RES_DATA	1
+#define RES_LEAF	1
+#define RES_RG_HDR	1
+#define RES_RG_BIT	2
+#define RES_EATTR	1
+#define RES_STATFS	1
+#define RES_QUOTA	2
+
+/* reserve either the number of blocks to be allocated plus the rg header
+ * block, or all of the blocks in the rg, whichever is smaller */
+static inline unsigned int gfs2_rg_blocks(const struct gfs2_alloc *al)
+{
+	return (al->al_requested < al->al_rgd->rd_length)?
+	       al->al_requested + 1 : al->al_rgd->rd_length;
+}
+
+int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+		     unsigned int revokes);
+
+void gfs2_trans_end(struct gfs2_sbd *sdp);
+
+void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
+void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
+
+#endif /* __TRANS_DOT_H__ */
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
new file mode 100644
index 00000000..53511291
--- /dev/null
+++ b/fs/gfs2/util.c
@@ -0,0 +1,285 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/crc32.h>
+#include <linux/gfs2_ondisk.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "util.h"
+
+struct kmem_cache *gfs2_glock_cachep __read_mostly;
+struct kmem_cache *gfs2_glock_aspace_cachep __read_mostly;
+struct kmem_cache *gfs2_inode_cachep __read_mostly;
+struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
+struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
+struct kmem_cache *gfs2_quotad_cachep __read_mostly;
+
+void gfs2_assert_i(struct gfs2_sbd *sdp)
+{
+	printk(KERN_EMERG "GFS2: fsid=%s: fatal assertion failed\n",
+	       sdp->sd_fsname);
+}
+
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	const struct lm_lockops *lm = ls->ls_ops;
+	va_list args;
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
+	    test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return 0;
+
+	va_start(args, fmt);
+	vprintk(fmt, args);
+	va_end(args);
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
+		fs_err(sdp, "about to withdraw this file system\n");
+		BUG_ON(sdp->sd_args.ar_debug);
+
+		kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE);
+
+		if (lm->lm_unmount) {
+			fs_err(sdp, "telling LM to unmount\n");
+			lm->lm_unmount(sdp);
+		}
+		fs_err(sdp, "withdrawn\n");
+		dump_stack();
+	}
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
+		panic("GFS2: fsid=%s: panic requested.\n", sdp->sd_fsname);
+
+	return -1;
+}
+
+/**
+ * gfs2_assert_withdraw_i - Cause the machine to withdraw if @assertion is false
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
+			   const char *function, char *file, unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: assertion \"%s\" failed\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname, assertion,
+		sdp->sd_fsname, function, file, line);
+	dump_stack();
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_assert_warn_i - Print a message to the console if @assertion is false
+ * Returns: -1 if we printed something
+ *          -2 if we didn't
+ */
+
+int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
+		       const char *function, char *file, unsigned int line)
+{
+	if (time_before(jiffies,
+			sdp->sd_last_warning +
+			gfs2_tune_get(sdp, gt_complain_secs) * HZ))
+		return -2;
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW)
+		printk(KERN_WARNING
+		       "GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
+		       "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		       sdp->sd_fsname, assertion,
+		       sdp->sd_fsname, function, file, line);
+
+	if (sdp->sd_args.ar_debug)
+		BUG();
+	else
+		dump_stack();
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
+		panic("GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
+		      "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		      sdp->sd_fsname, assertion,
+		      sdp->sd_fsname, function, file, line);
+
+	sdp->sd_last_warning = jiffies;
+
+	return -1;
+}
+
+/**
+ * gfs2_consist_i - Flag a filesystem consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide, const char *function,
+		   char *file, unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: filesystem consistency error\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_consist_inode_i - Flag an inode consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
+			 const char *function, char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: filesystem consistency error\n"
+		"GFS2: fsid=%s:   inode = %llu %llu\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)ip->i_no_formal_ino,
+		(unsigned long long)ip->i_no_addr,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_consist_rgrpd_i - Flag a RG consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
+			 const char *function, char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: filesystem consistency error\n"
+		"GFS2: fsid=%s:   RG = %llu\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)rgd->rd_addr,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_meta_check_ii - Flag a magic number consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *type, const char *function, char *file,
+		       unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: invalid metadata block\n"
+		"GFS2: fsid=%s:   bh = %llu (%s)\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)bh->b_blocknr, type,
+		sdp->sd_fsname, function, file, line);
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_metatype_check_ii - Flag a metadata type consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			   u16 type, u16 t, const char *function,
+			   char *file, unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: invalid metadata block\n"
+		"GFS2: fsid=%s:   bh = %llu (type: exp=%u, found=%u)\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)bh->b_blocknr, type, t,
+		sdp->sd_fsname, function, file, line);
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_io_error_i - Flag an I/O error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
+		    unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: I/O error\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_io_error_bh_i - Flag a buffer I/O error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *function, char *file, unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: I/O error\n"
+		"GFS2: fsid=%s:   block = %llu\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)bh->b_blocknr,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+void gfs2_icbit_munge(struct gfs2_sbd *sdp, unsigned char **bitmap,
+		      unsigned int bit, int new_value)
+{
+	unsigned int c, o, b = bit;
+	int old_value;
+
+	c = b / (8 * PAGE_SIZE);
+	b %= 8 * PAGE_SIZE;
+	o = b / 8;
+	b %= 8;
+
+	old_value = (bitmap[c][o] & (1 << b));
+	gfs2_assert_withdraw(sdp, !old_value != !new_value);
+
+	if (new_value)
+		bitmap[c][o] |= 1 << b;
+	else
+		bitmap[c][o] &= ~(1 << b);
+}
+
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
new file mode 100644
index 00000000..b432e046
--- /dev/null
+++ b/fs/gfs2/util.h
@@ -0,0 +1,172 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __UTIL_DOT_H__
+#define __UTIL_DOT_H__
+
+#include "incore.h"
+
+#define fs_printk(level, fs, fmt, arg...) \
+	printk(level "GFS2: fsid=%s: " fmt , (fs)->sd_fsname , ## arg)
+
+#define fs_info(fs, fmt, arg...) \
+	fs_printk(KERN_INFO , fs , fmt , ## arg)
+
+#define fs_warn(fs, fmt, arg...) \
+	fs_printk(KERN_WARNING , fs , fmt , ## arg)
+
+#define fs_err(fs, fmt, arg...) \
+	fs_printk(KERN_ERR, fs , fmt , ## arg)
+
+
+void gfs2_assert_i(struct gfs2_sbd *sdp);
+
+#define gfs2_assert(sdp, assertion) \
+do { \
+	if (unlikely(!(assertion))) { \
+		gfs2_assert_i(sdp); \
+		BUG(); \
+        } \
+} while (0)
+
+
+int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
+			   const char *function, char *file, unsigned int line);
+
+#define gfs2_assert_withdraw(sdp, assertion) \
+((likely(assertion)) ? 0 : gfs2_assert_withdraw_i((sdp), #assertion, \
+					__func__, __FILE__, __LINE__))
+
+
+int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
+		       const char *function, char *file, unsigned int line);
+
+#define gfs2_assert_warn(sdp, assertion) \
+((likely(assertion)) ? 0 : gfs2_assert_warn_i((sdp), #assertion, \
+					__func__, __FILE__, __LINE__))
+
+
+int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide,
+		   const char *function, char *file, unsigned int line);
+
+#define gfs2_consist(sdp) \
+gfs2_consist_i((sdp), 0, __func__, __FILE__, __LINE__)
+
+
+int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
+			 const char *function, char *file, unsigned int line);
+
+#define gfs2_consist_inode(ip) \
+gfs2_consist_inode_i((ip), 0, __func__, __FILE__, __LINE__)
+
+
+int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
+			 const char *function, char *file, unsigned int line);
+
+#define gfs2_consist_rgrpd(rgd) \
+gfs2_consist_rgrpd_i((rgd), 0, __func__, __FILE__, __LINE__)
+
+
+int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *type, const char *function,
+		       char *file, unsigned int line);
+
+static inline int gfs2_meta_check_i(struct gfs2_sbd *sdp,
+				    struct buffer_head *bh,
+				    const char *function,
+				    char *file, unsigned int line)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+	u32 magic = be32_to_cpu(mh->mh_magic);
+	if (unlikely(magic != GFS2_MAGIC))
+		return gfs2_meta_check_ii(sdp, bh, "magic number", function,
+					  file, line);
+	return 0;
+}
+
+#define gfs2_meta_check(sdp, bh) \
+gfs2_meta_check_i((sdp), (bh), __func__, __FILE__, __LINE__)
+
+
+int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			   u16 type, u16 t,
+			   const char *function,
+			   char *file, unsigned int line);
+
+static inline int gfs2_metatype_check_i(struct gfs2_sbd *sdp,
+					struct buffer_head *bh,
+					u16 type,
+					const char *function,
+					char *file, unsigned int line)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+	u32 magic = be32_to_cpu(mh->mh_magic);
+	u16 t = be32_to_cpu(mh->mh_type);
+	if (unlikely(magic != GFS2_MAGIC))
+		return gfs2_meta_check_ii(sdp, bh, "magic number", function,
+					  file, line);
+        if (unlikely(t != type))
+		return gfs2_metatype_check_ii(sdp, bh, type, t, function,
+					      file, line);
+	return 0;
+}
+
+#define gfs2_metatype_check(sdp, bh, type) \
+gfs2_metatype_check_i((sdp), (bh), (type), __func__, __FILE__, __LINE__)
+
+static inline void gfs2_metatype_set(struct buffer_head *bh, u16 type,
+				     u16 format)
+{
+	struct gfs2_meta_header *mh;
+	mh = (struct gfs2_meta_header *)bh->b_data;
+	mh->mh_type = cpu_to_be32(type);
+	mh->mh_format = cpu_to_be32(format);
+}
+
+
+int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
+		    char *file, unsigned int line);
+
+#define gfs2_io_error(sdp) \
+gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__);
+
+
+int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *function, char *file, unsigned int line);
+
+#define gfs2_io_error_bh(sdp, bh) \
+gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__);
+
+
+extern struct kmem_cache *gfs2_glock_cachep;
+extern struct kmem_cache *gfs2_glock_aspace_cachep;
+extern struct kmem_cache *gfs2_inode_cachep;
+extern struct kmem_cache *gfs2_bufdata_cachep;
+extern struct kmem_cache *gfs2_rgrpd_cachep;
+extern struct kmem_cache *gfs2_quotad_cachep;
+
+static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
+					   unsigned int *p)
+{
+	unsigned int x;
+	spin_lock(&gt->gt_spin);
+	x = *p;
+	spin_unlock(&gt->gt_spin);
+	return x;
+}
+
+#define gfs2_tune_get(sdp, field) \
+gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
+
+void gfs2_icbit_munge(struct gfs2_sbd *sdp, unsigned char **bitmap,
+		      unsigned int bit, int new_value);
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...);
+
+#endif /* __UTIL_DOT_H__ */
+
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
new file mode 100644
index 00000000..439b61c0
--- /dev/null
+++ b/fs/gfs2/xattr.c
@@ -0,0 +1,1549 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/xattr.h>
+#include <linux/gfs2_ondisk.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "xattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+
+/**
+ * ea_calc_size - returns the acutal number of bytes the request will take up
+ *                (not counting any unstuffed data blocks)
+ * @sdp:
+ * @er:
+ * @size:
+ *
+ * Returns: 1 if the EA should be stuffed
+ */
+
+static int ea_calc_size(struct gfs2_sbd *sdp, unsigned int nsize, size_t dsize,
+			unsigned int *size)
+{
+	unsigned int jbsize = sdp->sd_jbsize;
+
+	/* Stuffed */
+	*size = ALIGN(sizeof(struct gfs2_ea_header) + nsize + dsize, 8);
+
+	if (*size <= jbsize)
+		return 1;
+
+	/* Unstuffed */
+	*size = ALIGN(sizeof(struct gfs2_ea_header) + nsize +
+		      (sizeof(__be64) * DIV_ROUND_UP(dsize, jbsize)), 8);
+
+	return 0;
+}
+
+static int ea_check_size(struct gfs2_sbd *sdp, unsigned int nsize, size_t dsize)
+{
+	unsigned int size;
+
+	if (dsize > GFS2_EA_MAX_DATA_LEN)
+		return -ERANGE;
+
+	ea_calc_size(sdp, nsize, dsize, &size);
+
+	/* This can only happen with 512 byte blocks */
+	if (size > sdp->sd_jbsize)
+		return -ERANGE;
+
+	return 0;
+}
+
+typedef int (*ea_call_t) (struct gfs2_inode *ip, struct buffer_head *bh,
+			  struct gfs2_ea_header *ea,
+			  struct gfs2_ea_header *prev, void *private);
+
+static int ea_foreach_i(struct gfs2_inode *ip, struct buffer_head *bh,
+			ea_call_t ea_call, void *data)
+{
+	struct gfs2_ea_header *ea, *prev = NULL;
+	int error = 0;
+
+	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_EA))
+		return -EIO;
+
+	for (ea = GFS2_EA_BH2FIRST(bh);; prev = ea, ea = GFS2_EA2NEXT(ea)) {
+		if (!GFS2_EA_REC_LEN(ea))
+			goto fail;
+		if (!(bh->b_data <= (char *)ea && (char *)GFS2_EA2NEXT(ea) <=
+						  bh->b_data + bh->b_size))
+			goto fail;
+		if (!GFS2_EATYPE_VALID(ea->ea_type))
+			goto fail;
+
+		error = ea_call(ip, bh, ea, prev, data);
+		if (error)
+			return error;
+
+		if (GFS2_EA_IS_LAST(ea)) {
+			if ((char *)GFS2_EA2NEXT(ea) !=
+			    bh->b_data + bh->b_size)
+				goto fail;
+			break;
+		}
+	}
+
+	return error;
+
+fail:
+	gfs2_consist_inode(ip);
+	return -EIO;
+}
+
+static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data)
+{
+	struct buffer_head *bh, *eabh;
+	__be64 *eablk, *end;
+	int error;
+
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &bh);
+	if (error)
+		return error;
+
+	if (!(ip->i_diskflags & GFS2_DIF_EA_INDIRECT)) {
+		error = ea_foreach_i(ip, bh, ea_call, data);
+		goto out;
+	}
+
+	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_IN)) {
+		error = -EIO;
+		goto out;
+	}
+
+	eablk = (__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header));
+	end = eablk + GFS2_SB(&ip->i_inode)->sd_inptrs;
+
+	for (; eablk < end; eablk++) {
+		u64 bn;
+
+		if (!*eablk)
+			break;
+		bn = be64_to_cpu(*eablk);
+
+		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, &eabh);
+		if (error)
+			break;
+		error = ea_foreach_i(ip, eabh, ea_call, data);
+		brelse(eabh);
+		if (error)
+			break;
+	}
+out:
+	brelse(bh);
+	return error;
+}
+
+struct ea_find {
+	int type;
+	const char *name;
+	size_t namel;
+	struct gfs2_ea_location *ef_el;
+};
+
+static int ea_find_i(struct gfs2_inode *ip, struct buffer_head *bh,
+		     struct gfs2_ea_header *ea, struct gfs2_ea_header *prev,
+		     void *private)
+{
+	struct ea_find *ef = private;
+
+	if (ea->ea_type == GFS2_EATYPE_UNUSED)
+		return 0;
+
+	if (ea->ea_type == ef->type) {
+		if (ea->ea_name_len == ef->namel &&
+		    !memcmp(GFS2_EA2NAME(ea), ef->name, ea->ea_name_len)) {
+			struct gfs2_ea_location *el = ef->ef_el;
+			get_bh(bh);
+			el->el_bh = bh;
+			el->el_ea = ea;
+			el->el_prev = prev;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name,
+			struct gfs2_ea_location *el)
+{
+	struct ea_find ef;
+	int error;
+
+	ef.type = type;
+	ef.name = name;
+	ef.namel = strlen(name);
+	ef.ef_el = el;
+
+	memset(el, 0, sizeof(struct gfs2_ea_location));
+
+	error = ea_foreach(ip, ea_find_i, &ef);
+	if (error > 0)
+		return 0;
+
+	return error;
+}
+
+/**
+ * ea_dealloc_unstuffed -
+ * @ip:
+ * @bh:
+ * @ea:
+ * @prev:
+ * @private:
+ *
+ * Take advantage of the fact that all unstuffed blocks are
+ * allocated from the same RG.  But watch, this may not always
+ * be true.
+ *
+ * Returns: errno
+ */
+
+static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh,
+				struct gfs2_ea_header *ea,
+				struct gfs2_ea_header *prev, void *private)
+{
+	int *leave = private;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_holder rg_gh;
+	struct buffer_head *dibh;
+	__be64 *dataptrs;
+	u64 bn = 0;
+	u64 bstart = 0;
+	unsigned int blen = 0;
+	unsigned int blks = 0;
+	unsigned int x;
+	int error;
+
+	if (GFS2_EA_IS_STUFFED(ea))
+		return 0;
+
+	dataptrs = GFS2_EA2DATAPTRS(ea);
+	for (x = 0; x < ea->ea_num_ptrs; x++, dataptrs++) {
+		if (*dataptrs) {
+			blks++;
+			bn = be64_to_cpu(*dataptrs);
+		}
+	}
+	if (!blks)
+		return 0;
+
+	rgd = gfs2_blk2rgrpd(sdp, bn);
+	if (!rgd) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &rg_gh);
+	if (error)
+		return error;
+
+	error = gfs2_trans_begin(sdp, rgd->rd_length + RES_DINODE +
+				 RES_EATTR + RES_STATFS + RES_QUOTA, blks);
+	if (error)
+		goto out_gunlock;
+
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+
+	dataptrs = GFS2_EA2DATAPTRS(ea);
+	for (x = 0; x < ea->ea_num_ptrs; x++, dataptrs++) {
+		if (!*dataptrs)
+			break;
+		bn = be64_to_cpu(*dataptrs);
+
+		if (bstart + blen == bn)
+			blen++;
+		else {
+			if (bstart)
+				gfs2_free_meta(ip, bstart, blen);
+			bstart = bn;
+			blen = 1;
+		}
+
+		*dataptrs = 0;
+		gfs2_add_inode_blocks(&ip->i_inode, -1);
+	}
+	if (bstart)
+		gfs2_free_meta(ip, bstart, blen);
+
+	if (prev && !leave) {
+		u32 len;
+
+		len = GFS2_EA_REC_LEN(prev) + GFS2_EA_REC_LEN(ea);
+		prev->ea_rec_len = cpu_to_be32(len);
+
+		if (GFS2_EA_IS_LAST(ea))
+			prev->ea_flags |= GFS2_EAFLAG_LAST;
+	} else {
+		ea->ea_type = GFS2_EATYPE_UNUSED;
+		ea->ea_num_ptrs = 0;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		ip->i_inode.i_ctime = CURRENT_TIME;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(sdp);
+
+out_gunlock:
+	gfs2_glock_dq_uninit(&rg_gh);
+	return error;
+}
+
+static int ea_remove_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh,
+			       struct gfs2_ea_header *ea,
+			       struct gfs2_ea_header *prev, int leave)
+{
+	struct gfs2_alloc *al;
+	int error;
+
+	al = gfs2_alloc_get(ip);
+	if (!al)
+		return -ENOMEM;
+
+	error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto out_alloc;
+
+	error = gfs2_rindex_hold(GFS2_SB(&ip->i_inode), &al->al_ri_gh);
+	if (error)
+		goto out_quota;
+
+	error = ea_dealloc_unstuffed(ip, bh, ea, prev, (leave) ? &error : NULL);
+
+	gfs2_glock_dq_uninit(&al->al_ri_gh);
+
+out_quota:
+	gfs2_quota_unhold(ip);
+out_alloc:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+struct ea_list {
+	struct gfs2_ea_request *ei_er;
+	unsigned int ei_size;
+};
+
+static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
+{
+	switch (ea->ea_type) {
+	case GFS2_EATYPE_USR:
+		return 5 + ea->ea_name_len + 1;
+	case GFS2_EATYPE_SYS:
+		return 7 + ea->ea_name_len + 1;
+	case GFS2_EATYPE_SECURITY:
+		return 9 + ea->ea_name_len + 1;
+	default:
+		return 0;
+	}
+}
+
+static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh,
+		     struct gfs2_ea_header *ea, struct gfs2_ea_header *prev,
+		     void *private)
+{
+	struct ea_list *ei = private;
+	struct gfs2_ea_request *er = ei->ei_er;
+	unsigned int ea_size = gfs2_ea_strlen(ea);
+
+	if (ea->ea_type == GFS2_EATYPE_UNUSED)
+		return 0;
+
+	if (er->er_data_len) {
+		char *prefix = NULL;
+		unsigned int l = 0;
+		char c = 0;
+
+		if (ei->ei_size + ea_size > er->er_data_len)
+			return -ERANGE;
+
+		switch (ea->ea_type) {
+		case GFS2_EATYPE_USR:
+			prefix = "user.";
+			l = 5;
+			break;
+		case GFS2_EATYPE_SYS:
+			prefix = "system.";
+			l = 7;
+			break;
+		case GFS2_EATYPE_SECURITY:
+			prefix = "security.";
+			l = 9;
+			break;
+		}
+
+		BUG_ON(l == 0);
+
+		memcpy(er->er_data + ei->ei_size, prefix, l);
+		memcpy(er->er_data + ei->ei_size + l, GFS2_EA2NAME(ea),
+		       ea->ea_name_len);
+		memcpy(er->er_data + ei->ei_size + ea_size - 1, &c, 1);
+	}
+
+	ei->ei_size += ea_size;
+
+	return 0;
+}
+
+/**
+ * gfs2_listxattr - List gfs2 extended attributes
+ * @dentry: The dentry whose inode we are interested in
+ * @buffer: The buffer to write the results
+ * @size: The size of the buffer
+ *
+ * Returns: actual size of data on success, -errno on error
+ */
+
+ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+	struct gfs2_ea_request er;
+	struct gfs2_holder i_gh;
+	int error;
+
+	memset(&er, 0, sizeof(struct gfs2_ea_request));
+	if (size) {
+		er.er_data = buffer;
+		er.er_data_len = size;
+	}
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return error;
+
+	if (ip->i_eattr) {
+		struct ea_list ei = { .ei_er = &er, .ei_size = 0 };
+
+		error = ea_foreach(ip, ea_list_i, &ei);
+		if (!error)
+			error = ei.ei_size;
+	}
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return error;
+}
+
+/**
+ * ea_get_unstuffed - actually copies the unstuffed data into the
+ *                    request buffer
+ * @ip: The GFS2 inode
+ * @ea: The extended attribute header structure
+ * @data: The data to be copied
+ *
+ * Returns: errno
+ */
+
+static int ea_get_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
+			    char *data)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head **bh;
+	unsigned int amount = GFS2_EA_DATA_LEN(ea);
+	unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize);
+	__be64 *dataptrs = GFS2_EA2DATAPTRS(ea);
+	unsigned int x;
+	int error = 0;
+
+	bh = kcalloc(nptrs, sizeof(struct buffer_head *), GFP_NOFS);
+	if (!bh)
+		return -ENOMEM;
+
+	for (x = 0; x < nptrs; x++) {
+		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0,
+				       bh + x);
+		if (error) {
+			while (x--)
+				brelse(bh[x]);
+			goto out;
+		}
+		dataptrs++;
+	}
+
+	for (x = 0; x < nptrs; x++) {
+		error = gfs2_meta_wait(sdp, bh[x]);
+		if (error) {
+			for (; x < nptrs; x++)
+				brelse(bh[x]);
+			goto out;
+		}
+		if (gfs2_metatype_check(sdp, bh[x], GFS2_METATYPE_ED)) {
+			for (; x < nptrs; x++)
+				brelse(bh[x]);
+			error = -EIO;
+			goto out;
+		}
+
+		memcpy(data, bh[x]->b_data + sizeof(struct gfs2_meta_header),
+		       (sdp->sd_jbsize > amount) ? amount : sdp->sd_jbsize);
+
+		amount -= sdp->sd_jbsize;
+		data += sdp->sd_jbsize;
+
+		brelse(bh[x]);
+	}
+
+out:
+	kfree(bh);
+	return error;
+}
+
+static int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el,
+			    char *data, size_t size)
+{
+	int ret;
+	size_t len = GFS2_EA_DATA_LEN(el->el_ea);
+	if (len > size)
+		return -ERANGE;
+
+	if (GFS2_EA_IS_STUFFED(el->el_ea)) {
+		memcpy(data, GFS2_EA2DATA(el->el_ea), len);
+		return len;
+	}
+	ret = ea_get_unstuffed(ip, el->el_ea, data);
+	if (ret < 0)
+		return ret;
+	return len;
+}
+
+int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **ppdata)
+{
+	struct gfs2_ea_location el;
+	int error;
+	int len;
+	char *data;
+
+	error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, name, &el);
+	if (error)
+		return error;
+	if (!el.el_ea)
+		goto out;
+	if (!GFS2_EA_DATA_LEN(el.el_ea))
+		goto out;
+
+	len = GFS2_EA_DATA_LEN(el.el_ea);
+	data = kmalloc(len, GFP_NOFS);
+	error = -ENOMEM;
+	if (data == NULL)
+		goto out;
+
+	error = gfs2_ea_get_copy(ip, &el, data, len);
+	if (error == 0)
+		error = len;
+	*ppdata = data;
+out:
+	brelse(el.el_bh);
+	return error;
+}
+
+/**
+ * gfs2_xattr_get - Get a GFS2 extended attribute
+ * @inode: The inode
+ * @name: The name of the extended attribute
+ * @buffer: The buffer to write the result into
+ * @size: The size of the buffer
+ * @type: The type of extended attribute
+ *
+ * Returns: actual size of data on success, -errno on error
+ */
+static int gfs2_xattr_get(struct dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
+{
+	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+	struct gfs2_ea_location el;
+	int error;
+
+	if (!ip->i_eattr)
+		return -ENODATA;
+	if (strlen(name) > GFS2_EA_MAX_NAME_LEN)
+		return -EINVAL;
+
+	error = gfs2_ea_find(ip, type, name, &el);
+	if (error)
+		return error;
+	if (!el.el_ea)
+		return -ENODATA;
+	if (size)
+		error = gfs2_ea_get_copy(ip, &el, buffer, size);
+	else
+		error = GFS2_EA_DATA_LEN(el.el_ea);
+	brelse(el.el_bh);
+
+	return error;
+}
+
+/**
+ * ea_alloc_blk - allocates a new block for extended attributes.
+ * @ip: A pointer to the inode that's getting extended attributes
+ * @bhp: Pointer to pointer to a struct buffer_head
+ *
+ * Returns: errno
+ */
+
+static int ea_alloc_blk(struct gfs2_inode *ip, struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_ea_header *ea;
+	unsigned int n = 1;
+	u64 block;
+	int error;
+
+	error = gfs2_alloc_block(ip, &block, &n);
+	if (error)
+		return error;
+	gfs2_trans_add_unrevoke(sdp, block, 1);
+	*bhp = gfs2_meta_new(ip->i_gl, block);
+	gfs2_trans_add_bh(ip->i_gl, *bhp, 1);
+	gfs2_metatype_set(*bhp, GFS2_METATYPE_EA, GFS2_FORMAT_EA);
+	gfs2_buffer_clear_tail(*bhp, sizeof(struct gfs2_meta_header));
+
+	ea = GFS2_EA_BH2FIRST(*bhp);
+	ea->ea_rec_len = cpu_to_be32(sdp->sd_jbsize);
+	ea->ea_type = GFS2_EATYPE_UNUSED;
+	ea->ea_flags = GFS2_EAFLAG_LAST;
+	ea->ea_num_ptrs = 0;
+
+	gfs2_add_inode_blocks(&ip->i_inode, 1);
+
+	return 0;
+}
+
+/**
+ * ea_write - writes the request info to an ea, creating new blocks if
+ *            necessary
+ * @ip: inode that is being modified
+ * @ea: the location of the new ea in a block
+ * @er: the write request
+ *
+ * Note: does not update ea_rec_len or the GFS2_EAFLAG_LAST bin of ea_flags
+ *
+ * returns : errno
+ */
+
+static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
+		    struct gfs2_ea_request *er)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int error;
+
+	ea->ea_data_len = cpu_to_be32(er->er_data_len);
+	ea->ea_name_len = er->er_name_len;
+	ea->ea_type = er->er_type;
+	ea->__pad = 0;
+
+	memcpy(GFS2_EA2NAME(ea), er->er_name, er->er_name_len);
+
+	if (GFS2_EAREQ_SIZE_STUFFED(er) <= sdp->sd_jbsize) {
+		ea->ea_num_ptrs = 0;
+		memcpy(GFS2_EA2DATA(ea), er->er_data, er->er_data_len);
+	} else {
+		__be64 *dataptr = GFS2_EA2DATAPTRS(ea);
+		const char *data = er->er_data;
+		unsigned int data_len = er->er_data_len;
+		unsigned int copy;
+		unsigned int x;
+
+		ea->ea_num_ptrs = DIV_ROUND_UP(er->er_data_len, sdp->sd_jbsize);
+		for (x = 0; x < ea->ea_num_ptrs; x++) {
+			struct buffer_head *bh;
+			u64 block;
+			int mh_size = sizeof(struct gfs2_meta_header);
+			unsigned int n = 1;
+
+			error = gfs2_alloc_block(ip, &block, &n);
+			if (error)
+				return error;
+			gfs2_trans_add_unrevoke(sdp, block, 1);
+			bh = gfs2_meta_new(ip->i_gl, block);
+			gfs2_trans_add_bh(ip->i_gl, bh, 1);
+			gfs2_metatype_set(bh, GFS2_METATYPE_ED, GFS2_FORMAT_ED);
+
+			gfs2_add_inode_blocks(&ip->i_inode, 1);
+
+			copy = data_len > sdp->sd_jbsize ? sdp->sd_jbsize :
+							   data_len;
+			memcpy(bh->b_data + mh_size, data, copy);
+			if (copy < sdp->sd_jbsize)
+				memset(bh->b_data + mh_size + copy, 0,
+				       sdp->sd_jbsize - copy);
+
+			*dataptr++ = cpu_to_be64(bh->b_blocknr);
+			data += copy;
+			data_len -= copy;
+
+			brelse(bh);
+		}
+
+		gfs2_assert_withdraw(sdp, !data_len);
+	}
+
+	return 0;
+}
+
+typedef int (*ea_skeleton_call_t) (struct gfs2_inode *ip,
+				   struct gfs2_ea_request *er, void *private);
+
+static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er,
+			     unsigned int blks,
+			     ea_skeleton_call_t skeleton_call, void *private)
+{
+	struct gfs2_alloc *al;
+	struct buffer_head *dibh;
+	int error;
+
+	al = gfs2_alloc_get(ip);
+	if (!al)
+		return -ENOMEM;
+
+	error = gfs2_quota_lock_check(ip);
+	if (error)
+		goto out;
+
+	al->al_requested = blks;
+
+	error = gfs2_inplace_reserve(ip);
+	if (error)
+		goto out_gunlock_q;
+
+	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode),
+				 blks + gfs2_rg_blocks(al) +
+				 RES_DINODE + RES_STATFS + RES_QUOTA, 0);
+	if (error)
+		goto out_ipres;
+
+	error = skeleton_call(ip, er, private);
+	if (error)
+		goto out_end_trans;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		ip->i_inode.i_ctime = CURRENT_TIME;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+out_end_trans:
+	gfs2_trans_end(GFS2_SB(&ip->i_inode));
+out_ipres:
+	gfs2_inplace_release(ip);
+out_gunlock_q:
+	gfs2_quota_unlock(ip);
+out:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+static int ea_init_i(struct gfs2_inode *ip, struct gfs2_ea_request *er,
+		     void *private)
+{
+	struct buffer_head *bh;
+	int error;
+
+	error = ea_alloc_blk(ip, &bh);
+	if (error)
+		return error;
+
+	ip->i_eattr = bh->b_blocknr;
+	error = ea_write(ip, GFS2_EA_BH2FIRST(bh), er);
+
+	brelse(bh);
+
+	return error;
+}
+
+/**
+ * ea_init - initializes a new eattr block
+ * @ip:
+ * @er:
+ *
+ * Returns: errno
+ */
+
+static int ea_init(struct gfs2_inode *ip, int type, const char *name,
+		   const void *data, size_t size)
+{
+	struct gfs2_ea_request er;
+	unsigned int jbsize = GFS2_SB(&ip->i_inode)->sd_jbsize;
+	unsigned int blks = 1;
+
+	er.er_type = type;
+	er.er_name = name;
+	er.er_name_len = strlen(name);
+	er.er_data = (void *)data;
+	er.er_data_len = size;
+
+	if (GFS2_EAREQ_SIZE_STUFFED(&er) > jbsize)
+		blks += DIV_ROUND_UP(er.er_data_len, jbsize);
+
+	return ea_alloc_skeleton(ip, &er, blks, ea_init_i, NULL);
+}
+
+static struct gfs2_ea_header *ea_split_ea(struct gfs2_ea_header *ea)
+{
+	u32 ea_size = GFS2_EA_SIZE(ea);
+	struct gfs2_ea_header *new = (struct gfs2_ea_header *)((char *)ea +
+				     ea_size);
+	u32 new_size = GFS2_EA_REC_LEN(ea) - ea_size;
+	int last = ea->ea_flags & GFS2_EAFLAG_LAST;
+
+	ea->ea_rec_len = cpu_to_be32(ea_size);
+	ea->ea_flags ^= last;
+
+	new->ea_rec_len = cpu_to_be32(new_size);
+	new->ea_flags = last;
+
+	return new;
+}
+
+static void ea_set_remove_stuffed(struct gfs2_inode *ip,
+				  struct gfs2_ea_location *el)
+{
+	struct gfs2_ea_header *ea = el->el_ea;
+	struct gfs2_ea_header *prev = el->el_prev;
+	u32 len;
+
+	gfs2_trans_add_bh(ip->i_gl, el->el_bh, 1);
+
+	if (!prev || !GFS2_EA_IS_STUFFED(ea)) {
+		ea->ea_type = GFS2_EATYPE_UNUSED;
+		return;
+	} else if (GFS2_EA2NEXT(prev) != ea) {
+		prev = GFS2_EA2NEXT(prev);
+		gfs2_assert_withdraw(GFS2_SB(&ip->i_inode), GFS2_EA2NEXT(prev) == ea);
+	}
+
+	len = GFS2_EA_REC_LEN(prev) + GFS2_EA_REC_LEN(ea);
+	prev->ea_rec_len = cpu_to_be32(len);
+
+	if (GFS2_EA_IS_LAST(ea))
+		prev->ea_flags |= GFS2_EAFLAG_LAST;
+}
+
+struct ea_set {
+	int ea_split;
+
+	struct gfs2_ea_request *es_er;
+	struct gfs2_ea_location *es_el;
+
+	struct buffer_head *es_bh;
+	struct gfs2_ea_header *es_ea;
+};
+
+static int ea_set_simple_noalloc(struct gfs2_inode *ip, struct buffer_head *bh,
+				 struct gfs2_ea_header *ea, struct ea_set *es)
+{
+	struct gfs2_ea_request *er = es->es_er;
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + 2 * RES_EATTR, 0);
+	if (error)
+		return error;
+
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+
+	if (es->ea_split)
+		ea = ea_split_ea(ea);
+
+	ea_write(ip, ea, er);
+
+	if (es->es_el)
+		ea_set_remove_stuffed(ip, es->es_el);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out;
+	ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+out:
+	gfs2_trans_end(GFS2_SB(&ip->i_inode));
+	return error;
+}
+
+static int ea_set_simple_alloc(struct gfs2_inode *ip,
+			       struct gfs2_ea_request *er, void *private)
+{
+	struct ea_set *es = private;
+	struct gfs2_ea_header *ea = es->es_ea;
+	int error;
+
+	gfs2_trans_add_bh(ip->i_gl, es->es_bh, 1);
+
+	if (es->ea_split)
+		ea = ea_split_ea(ea);
+
+	error = ea_write(ip, ea, er);
+	if (error)
+		return error;
+
+	if (es->es_el)
+		ea_set_remove_stuffed(ip, es->es_el);
+
+	return 0;
+}
+
+static int ea_set_simple(struct gfs2_inode *ip, struct buffer_head *bh,
+			 struct gfs2_ea_header *ea, struct gfs2_ea_header *prev,
+			 void *private)
+{
+	struct ea_set *es = private;
+	unsigned int size;
+	int stuffed;
+	int error;
+
+	stuffed = ea_calc_size(GFS2_SB(&ip->i_inode), es->es_er->er_name_len,
+			       es->es_er->er_data_len, &size);
+
+	if (ea->ea_type == GFS2_EATYPE_UNUSED) {
+		if (GFS2_EA_REC_LEN(ea) < size)
+			return 0;
+		if (!GFS2_EA_IS_STUFFED(ea)) {
+			error = ea_remove_unstuffed(ip, bh, ea, prev, 1);
+			if (error)
+				return error;
+		}
+		es->ea_split = 0;
+	} else if (GFS2_EA_REC_LEN(ea) - GFS2_EA_SIZE(ea) >= size)
+		es->ea_split = 1;
+	else
+		return 0;
+
+	if (stuffed) {
+		error = ea_set_simple_noalloc(ip, bh, ea, es);
+		if (error)
+			return error;
+	} else {
+		unsigned int blks;
+
+		es->es_bh = bh;
+		es->es_ea = ea;
+		blks = 2 + DIV_ROUND_UP(es->es_er->er_data_len,
+					GFS2_SB(&ip->i_inode)->sd_jbsize);
+
+		error = ea_alloc_skeleton(ip, es->es_er, blks,
+					  ea_set_simple_alloc, es);
+		if (error)
+			return error;
+	}
+
+	return 1;
+}
+
+static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er,
+			void *private)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *indbh, *newbh;
+	__be64 *eablk;
+	int error;
+	int mh_size = sizeof(struct gfs2_meta_header);
+
+	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
+		__be64 *end;
+
+		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT,
+				       &indbh);
+		if (error)
+			return error;
+
+		if (gfs2_metatype_check(sdp, indbh, GFS2_METATYPE_IN)) {
+			error = -EIO;
+			goto out;
+		}
+
+		eablk = (__be64 *)(indbh->b_data + mh_size);
+		end = eablk + sdp->sd_inptrs;
+
+		for (; eablk < end; eablk++)
+			if (!*eablk)
+				break;
+
+		if (eablk == end) {
+			error = -ENOSPC;
+			goto out;
+		}
+
+		gfs2_trans_add_bh(ip->i_gl, indbh, 1);
+	} else {
+		u64 blk;
+		unsigned int n = 1;
+		error = gfs2_alloc_block(ip, &blk, &n);
+		if (error)
+			return error;
+		gfs2_trans_add_unrevoke(sdp, blk, 1);
+		indbh = gfs2_meta_new(ip->i_gl, blk);
+		gfs2_trans_add_bh(ip->i_gl, indbh, 1);
+		gfs2_metatype_set(indbh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
+		gfs2_buffer_clear_tail(indbh, mh_size);
+
+		eablk = (__be64 *)(indbh->b_data + mh_size);
+		*eablk = cpu_to_be64(ip->i_eattr);
+		ip->i_eattr = blk;
+		ip->i_diskflags |= GFS2_DIF_EA_INDIRECT;
+		gfs2_add_inode_blocks(&ip->i_inode, 1);
+
+		eablk++;
+	}
+
+	error = ea_alloc_blk(ip, &newbh);
+	if (error)
+		goto out;
+
+	*eablk = cpu_to_be64((u64)newbh->b_blocknr);
+	error = ea_write(ip, GFS2_EA_BH2FIRST(newbh), er);
+	brelse(newbh);
+	if (error)
+		goto out;
+
+	if (private)
+		ea_set_remove_stuffed(ip, private);
+
+out:
+	brelse(indbh);
+	return error;
+}
+
+static int ea_set_i(struct gfs2_inode *ip, int type, const char *name,
+		    const void *value, size_t size, struct gfs2_ea_location *el)
+{
+	struct gfs2_ea_request er;
+	struct ea_set es;
+	unsigned int blks = 2;
+	int error;
+
+	er.er_type = type;
+	er.er_name = name;
+	er.er_data = (void *)value;
+	er.er_name_len = strlen(name);
+	er.er_data_len = size;
+
+	memset(&es, 0, sizeof(struct ea_set));
+	es.es_er = &er;
+	es.es_el = el;
+
+	error = ea_foreach(ip, ea_set_simple, &es);
+	if (error > 0)
+		return 0;
+	if (error)
+		return error;
+
+	if (!(ip->i_diskflags & GFS2_DIF_EA_INDIRECT))
+		blks++;
+	if (GFS2_EAREQ_SIZE_STUFFED(&er) > GFS2_SB(&ip->i_inode)->sd_jbsize)
+		blks += DIV_ROUND_UP(er.er_data_len, GFS2_SB(&ip->i_inode)->sd_jbsize);
+
+	return ea_alloc_skeleton(ip, &er, blks, ea_set_block, el);
+}
+
+static int ea_set_remove_unstuffed(struct gfs2_inode *ip,
+				   struct gfs2_ea_location *el)
+{
+	if (el->el_prev && GFS2_EA2NEXT(el->el_prev) != el->el_ea) {
+		el->el_prev = GFS2_EA2NEXT(el->el_prev);
+		gfs2_assert_withdraw(GFS2_SB(&ip->i_inode),
+				     GFS2_EA2NEXT(el->el_prev) == el->el_ea);
+	}
+
+	return ea_remove_unstuffed(ip, el->el_bh, el->el_ea, el->el_prev, 0);
+}
+
+static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el)
+{
+	struct gfs2_ea_header *ea = el->el_ea;
+	struct gfs2_ea_header *prev = el->el_prev;
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + RES_EATTR, 0);
+	if (error)
+		return error;
+
+	gfs2_trans_add_bh(ip->i_gl, el->el_bh, 1);
+
+	if (prev) {
+		u32 len;
+
+		len = GFS2_EA_REC_LEN(prev) + GFS2_EA_REC_LEN(ea);
+		prev->ea_rec_len = cpu_to_be32(len);
+
+		if (GFS2_EA_IS_LAST(ea))
+			prev->ea_flags |= GFS2_EAFLAG_LAST;
+	} else {
+		ea->ea_type = GFS2_EATYPE_UNUSED;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		ip->i_inode.i_ctime = CURRENT_TIME;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(GFS2_SB(&ip->i_inode));
+
+	return error;
+}
+
+/**
+ * gfs2_xattr_remove - Remove a GFS2 extended attribute
+ * @ip: The inode
+ * @type: The type of the extended attribute
+ * @name: The name of the extended attribute
+ *
+ * This is not called directly by the VFS since we use the (common)
+ * scheme of making a "set with NULL data" mean a remove request. Note
+ * that this is different from a set with zero length data.
+ *
+ * Returns: 0, or errno on failure
+ */
+
+static int gfs2_xattr_remove(struct gfs2_inode *ip, int type, const char *name)
+{
+	struct gfs2_ea_location el;
+	int error;
+
+	if (!ip->i_eattr)
+		return -ENODATA;
+
+	error = gfs2_ea_find(ip, type, name, &el);
+	if (error)
+		return error;
+	if (!el.el_ea)
+		return -ENODATA;
+
+	if (GFS2_EA_IS_STUFFED(el.el_ea))
+		error = ea_remove_stuffed(ip, &el);
+	else
+		error = ea_remove_unstuffed(ip, el.el_bh, el.el_ea, el.el_prev, 0);
+
+	brelse(el.el_bh);
+
+	return error;
+}
+
+/**
+ * __gfs2_xattr_set - Set (or remove) a GFS2 extended attribute
+ * @ip: The inode
+ * @name: The name of the extended attribute
+ * @value: The value of the extended attribute (NULL for remove)
+ * @size: The size of the @value argument
+ * @flags: Create or Replace
+ * @type: The type of the extended attribute
+ *
+ * See gfs2_xattr_remove() for details of the removal of xattrs.
+ *
+ * Returns: 0 or errno on failure
+ */
+
+int __gfs2_xattr_set(struct inode *inode, const char *name,
+		   const void *value, size_t size, int flags, int type)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_ea_location el;
+	unsigned int namel = strlen(name);
+	int error;
+
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+		return -EPERM;
+	if (namel > GFS2_EA_MAX_NAME_LEN)
+		return -ERANGE;
+
+	if (value == NULL)
+		return gfs2_xattr_remove(ip, type, name);
+
+	if (ea_check_size(sdp, namel, size))
+		return -ERANGE;
+
+	if (!ip->i_eattr) {
+		if (flags & XATTR_REPLACE)
+			return -ENODATA;
+		return ea_init(ip, type, name, value, size);
+	}
+
+	error = gfs2_ea_find(ip, type, name, &el);
+	if (error)
+		return error;
+
+	if (el.el_ea) {
+		if (ip->i_diskflags & GFS2_DIF_APPENDONLY) {
+			brelse(el.el_bh);
+			return -EPERM;
+		}
+
+		error = -EEXIST;
+		if (!(flags & XATTR_CREATE)) {
+			int unstuffed = !GFS2_EA_IS_STUFFED(el.el_ea);
+			error = ea_set_i(ip, type, name, value, size, &el);
+			if (!error && unstuffed)
+				ea_set_remove_unstuffed(ip, &el);
+		}
+
+		brelse(el.el_bh);
+		return error;
+	}
+
+	error = -ENODATA;
+	if (!(flags & XATTR_REPLACE))
+		error = ea_set_i(ip, type, name, value, size, NULL);
+
+	return error;
+}
+
+static int gfs2_xattr_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	return __gfs2_xattr_set(dentry->d_inode, name, value,
+				size, flags, type);
+}
+
+static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip,
+				  struct gfs2_ea_header *ea, char *data)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head **bh;
+	unsigned int amount = GFS2_EA_DATA_LEN(ea);
+	unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize);
+	__be64 *dataptrs = GFS2_EA2DATAPTRS(ea);
+	unsigned int x;
+	int error;
+
+	bh = kcalloc(nptrs, sizeof(struct buffer_head *), GFP_NOFS);
+	if (!bh)
+		return -ENOMEM;
+
+	error = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0);
+	if (error)
+		goto out;
+
+	for (x = 0; x < nptrs; x++) {
+		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0,
+				       bh + x);
+		if (error) {
+			while (x--)
+				brelse(bh[x]);
+			goto fail;
+		}
+		dataptrs++;
+	}
+
+	for (x = 0; x < nptrs; x++) {
+		error = gfs2_meta_wait(sdp, bh[x]);
+		if (error) {
+			for (; x < nptrs; x++)
+				brelse(bh[x]);
+			goto fail;
+		}
+		if (gfs2_metatype_check(sdp, bh[x], GFS2_METATYPE_ED)) {
+			for (; x < nptrs; x++)
+				brelse(bh[x]);
+			error = -EIO;
+			goto fail;
+		}
+
+		gfs2_trans_add_bh(ip->i_gl, bh[x], 1);
+
+		memcpy(bh[x]->b_data + sizeof(struct gfs2_meta_header), data,
+		       (sdp->sd_jbsize > amount) ? amount : sdp->sd_jbsize);
+
+		amount -= sdp->sd_jbsize;
+		data += sdp->sd_jbsize;
+
+		brelse(bh[x]);
+	}
+
+out:
+	kfree(bh);
+	return error;
+
+fail:
+	gfs2_trans_end(sdp);
+	kfree(bh);
+	return error;
+}
+
+int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_ea_location el;
+	int error;
+
+	error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el);
+	if (error)
+		return error;
+
+	if (GFS2_EA_IS_STUFFED(el.el_ea)) {
+		error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0);
+		if (error == 0) {
+			gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1);
+			memcpy(GFS2_EA2DATA(el.el_ea), data,
+			       GFS2_EA_DATA_LEN(el.el_ea));
+		}
+	} else {
+		error = ea_acl_chmod_unstuffed(ip, el.el_ea, data);
+	}
+
+	brelse(el.el_bh);
+	if (error)
+		return error;
+
+	error = gfs2_setattr_simple(ip, attr);
+	gfs2_trans_end(sdp);
+	return error;
+}
+
+static int ea_dealloc_indirect(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrp_list rlist;
+	struct buffer_head *indbh, *dibh;
+	__be64 *eablk, *end;
+	unsigned int rg_blocks = 0;
+	u64 bstart = 0;
+	unsigned int blen = 0;
+	unsigned int blks = 0;
+	unsigned int x;
+	int error;
+
+	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
+
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &indbh);
+	if (error)
+		return error;
+
+	if (gfs2_metatype_check(sdp, indbh, GFS2_METATYPE_IN)) {
+		error = -EIO;
+		goto out;
+	}
+
+	eablk = (__be64 *)(indbh->b_data + sizeof(struct gfs2_meta_header));
+	end = eablk + sdp->sd_inptrs;
+
+	for (; eablk < end; eablk++) {
+		u64 bn;
+
+		if (!*eablk)
+			break;
+		bn = be64_to_cpu(*eablk);
+
+		if (bstart + blen == bn)
+			blen++;
+		else {
+			if (bstart)
+				gfs2_rlist_add(sdp, &rlist, bstart);
+			bstart = bn;
+			blen = 1;
+		}
+		blks++;
+	}
+	if (bstart)
+		gfs2_rlist_add(sdp, &rlist, bstart);
+	else
+		goto out;
+
+	gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE);
+
+	for (x = 0; x < rlist.rl_rgrps; x++) {
+		struct gfs2_rgrpd *rgd;
+		rgd = rlist.rl_ghs[x].gh_gl->gl_object;
+		rg_blocks += rgd->rd_length;
+	}
+
+	error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs);
+	if (error)
+		goto out_rlist_free;
+
+	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE + RES_INDIRECT +
+				 RES_STATFS + RES_QUOTA, blks);
+	if (error)
+		goto out_gunlock;
+
+	gfs2_trans_add_bh(ip->i_gl, indbh, 1);
+
+	eablk = (__be64 *)(indbh->b_data + sizeof(struct gfs2_meta_header));
+	bstart = 0;
+	blen = 0;
+
+	for (; eablk < end; eablk++) {
+		u64 bn;
+
+		if (!*eablk)
+			break;
+		bn = be64_to_cpu(*eablk);
+
+		if (bstart + blen == bn)
+			blen++;
+		else {
+			if (bstart)
+				gfs2_free_meta(ip, bstart, blen);
+			bstart = bn;
+			blen = 1;
+		}
+
+		*eablk = 0;
+		gfs2_add_inode_blocks(&ip->i_inode, -1);
+	}
+	if (bstart)
+		gfs2_free_meta(ip, bstart, blen);
+
+	ip->i_diskflags &= ~GFS2_DIF_EA_INDIRECT;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(sdp);
+
+out_gunlock:
+	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
+out_rlist_free:
+	gfs2_rlist_free(&rlist);
+out:
+	brelse(indbh);
+	return error;
+}
+
+static int ea_dealloc_block(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_alloc *al = ip->i_alloc;
+	struct gfs2_rgrpd *rgd;
+	struct buffer_head *dibh;
+	int error;
+
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_eattr);
+	if (!rgd) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
+				   &al->al_rgd_gh);
+	if (error)
+		return error;
+
+	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_DINODE + RES_STATFS +
+				 RES_QUOTA, 1);
+	if (error)
+		goto out_gunlock;
+
+	gfs2_free_meta(ip, ip->i_eattr, 1);
+
+	ip->i_eattr = 0;
+	gfs2_add_inode_blocks(&ip->i_inode, -1);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(sdp);
+
+out_gunlock:
+	gfs2_glock_dq_uninit(&al->al_rgd_gh);
+	return error;
+}
+
+/**
+ * gfs2_ea_dealloc - deallocate the extended attribute fork
+ * @ip: the inode
+ *
+ * Returns: errno
+ */
+
+int gfs2_ea_dealloc(struct gfs2_inode *ip)
+{
+	struct gfs2_alloc *al;
+	int error;
+
+	al = gfs2_alloc_get(ip);
+	if (!al)
+		return -ENOMEM;
+
+	error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto out_alloc;
+
+	error = gfs2_rindex_hold(GFS2_SB(&ip->i_inode), &al->al_ri_gh);
+	if (error)
+		goto out_quota;
+
+	error = ea_foreach(ip, ea_dealloc_unstuffed, NULL);
+	if (error)
+		goto out_rindex;
+
+	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
+		error = ea_dealloc_indirect(ip);
+		if (error)
+			goto out_rindex;
+	}
+
+	error = ea_dealloc_block(ip);
+
+out_rindex:
+	gfs2_glock_dq_uninit(&al->al_ri_gh);
+out_quota:
+	gfs2_quota_unhold(ip);
+out_alloc:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+static const struct xattr_handler gfs2_xattr_user_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.flags  = GFS2_EATYPE_USR,
+	.get    = gfs2_xattr_get,
+	.set    = gfs2_xattr_set,
+};
+
+static const struct xattr_handler gfs2_xattr_security_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.flags  = GFS2_EATYPE_SECURITY,
+	.get    = gfs2_xattr_get,
+	.set    = gfs2_xattr_set,
+};
+
+const struct xattr_handler *gfs2_xattr_handlers[] = {
+	&gfs2_xattr_user_handler,
+	&gfs2_xattr_security_handler,
+	&gfs2_xattr_system_handler,
+	NULL,
+};
+
diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h
new file mode 100644
index 00000000..d392f835
--- /dev/null
+++ b/fs/gfs2/xattr.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __EATTR_DOT_H__
+#define __EATTR_DOT_H__
+
+struct gfs2_inode;
+struct iattr;
+
+#define GFS2_EA_REC_LEN(ea) be32_to_cpu((ea)->ea_rec_len)
+#define GFS2_EA_DATA_LEN(ea) be32_to_cpu((ea)->ea_data_len)
+
+#define GFS2_EA_SIZE(ea) \
+ALIGN(sizeof(struct gfs2_ea_header) + (ea)->ea_name_len + \
+      ((GFS2_EA_IS_STUFFED(ea)) ? GFS2_EA_DATA_LEN(ea) : \
+				  (sizeof(__be64) * (ea)->ea_num_ptrs)), 8)
+
+#define GFS2_EA_IS_STUFFED(ea) (!(ea)->ea_num_ptrs)
+#define GFS2_EA_IS_LAST(ea) ((ea)->ea_flags & GFS2_EAFLAG_LAST)
+
+#define GFS2_EAREQ_SIZE_STUFFED(er) \
+ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + (er)->er_data_len, 8)
+
+#define GFS2_EA2NAME(ea) ((char *)((struct gfs2_ea_header *)(ea) + 1))
+#define GFS2_EA2DATA(ea) (GFS2_EA2NAME(ea) + (ea)->ea_name_len)
+
+#define GFS2_EA2DATAPTRS(ea) \
+((__be64 *)(GFS2_EA2NAME(ea) + ALIGN((ea)->ea_name_len, 8)))
+
+#define GFS2_EA2NEXT(ea) \
+((struct gfs2_ea_header *)((char *)(ea) + GFS2_EA_REC_LEN(ea)))
+
+#define GFS2_EA_BH2FIRST(bh) \
+((struct gfs2_ea_header *)((bh)->b_data + sizeof(struct gfs2_meta_header)))
+
+struct gfs2_ea_request {
+	const char *er_name;
+	char *er_data;
+	unsigned int er_name_len;
+	unsigned int er_data_len;
+	unsigned int er_type; /* GFS2_EATYPE_... */
+};
+
+struct gfs2_ea_location {
+	struct buffer_head *el_bh;
+	struct gfs2_ea_header *el_ea;
+	struct gfs2_ea_header *el_prev;
+};
+
+extern int __gfs2_xattr_set(struct inode *inode, const char *name,
+			    const void *value, size_t size,
+			    int flags, int type);
+extern ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size);
+extern int gfs2_ea_dealloc(struct gfs2_inode *ip);
+
+/* Exported to acl.c */
+
+extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data);
+extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data);
+
+#endif /* __EATTR_DOT_H__ */