initial_commit

34 files changed, 36700 insertions, 0 deletions

diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
new file mode 100644
index 00000000..9ed1bb1f
--- /dev/null
+++ b/fs/ext4/Kconfig
@@ -0,0 +1,85 @@
+config EXT4_FS
+	tristate "The Extended 4 (ext4) filesystem"
+	select JBD2
+	select CRC16
+	help
+	  This is the next generation of the ext3 filesystem.
+
+	  Unlike the change from ext2 filesystem to ext3 filesystem,
+	  the on-disk format of ext4 is not forwards compatible with
+	  ext3; it is based on extent maps and it supports 48-bit
+	  physical block numbers.  The ext4 filesystem also supports delayed
+	  allocation, persistent preallocation, high resolution time stamps,
+	  and a number of other features to improve performance and speed
+	  up fsck time.  For more information, please see the web pages at
+	  http://ext4.wiki.kernel.org.
+
+	  The ext4 filesystem will support mounting an ext3
+	  filesystem; while there will be some performance gains from
+	  the delayed allocation and inode table readahead, the best
+	  performance gains will require enabling ext4 features in the
+	  filesystem, or formatting a new filesystem as an ext4
+	  filesystem initially.
+
+	  To compile this file system support as a module, choose M here. The
+	  module will be called ext4.
+
+	  If unsure, say N.
+
+config EXT4_USE_FOR_EXT23
+	bool "Use ext4 for ext2/ext3 file systems"
+	depends on EXT4_FS
+	depends on EXT3_FS=n || EXT2_FS=n
+	default y
+	help
+	  Allow the ext4 file system driver code to be used for ext2 or
+	  ext3 file system mounts.  This allows users to reduce their
+	  compiled kernel size by using one file system driver for
+	  ext2, ext3, and ext4 file systems.
+
+config EXT4_FS_XATTR
+	bool "Ext4 extended attributes"
+	depends on EXT4_FS
+	default y
+	help
+	  Extended attributes are name:value pairs associated with inodes by
+	  the kernel or by users (see the attr(5) manual page, or visit
+	  <http://acl.bestbits.at/> for details).
+
+	  If unsure, say N.
+
+	  You need this for POSIX ACL support on ext4.
+
+config EXT4_FS_POSIX_ACL
+	bool "Ext4 POSIX Access Control Lists"
+	depends on EXT4_FS_XATTR
+	select FS_POSIX_ACL
+	help
+	  POSIX Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the POSIX ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N
+
+config EXT4_FS_SECURITY
+	bool "Ext4 Security Labels"
+	depends on EXT4_FS_XATTR
+	help
+	  Security labels support alternative access control models
+	  implemented by security modules like SELinux.  This option
+	  enables an extended attribute handler for file security
+	  labels in the ext4 filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.
+
+config EXT4_DEBUG
+	bool "EXT4 debugging support"
+	depends on EXT4_FS
+	help
+	  Enables run-time debugging support for the ext4 filesystem.
+
+	  If you select Y here, then you will be able to turn on debugging
+	  with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
new file mode 100644
index 00000000..04109460
--- /dev/null
+++ b/fs/ext4/Makefile
@@ -0,0 +1,14 @@
+#
+# Makefile for the linux ext4-filesystem routines.
+#
+
+obj-$(CONFIG_EXT4_FS) += ext4.o
+
+ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
+		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
+		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
+		mmp.o
+
+ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
+ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
+ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
new file mode 100644
index 00000000..21eacd7b
--- /dev/null
+++ b/fs/ext4/acl.c
@@ -0,0 +1,479 @@
+/*
+ * linux/fs/ext4/acl.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from filesystem to in-memory representation.
+ */
+static struct posix_acl *
+ext4_acl_from_disk(const void *value, size_t size)
+{
+	const char *end = (char *)value + size;
+	int n, count;
+	struct posix_acl *acl;
+
+	if (!value)
+		return NULL;
+	if (size < sizeof(ext4_acl_header))
+		 return ERR_PTR(-EINVAL);
+	if (((ext4_acl_header *)value)->a_version !=
+	    cpu_to_le32(EXT4_ACL_VERSION))
+		return ERR_PTR(-EINVAL);
+	value = (char *)value + sizeof(ext4_acl_header);
+	count = ext4_acl_count(size);
+	if (count < 0)
+		return ERR_PTR(-EINVAL);
+	if (count == 0)
+		return NULL;
+	acl = posix_acl_alloc(count, GFP_NOFS);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+	for (n = 0; n < count; n++) {
+		ext4_acl_entry *entry =
+			(ext4_acl_entry *)value;
+		if ((char *)value + sizeof(ext4_acl_entry_short) > end)
+			goto fail;
+		acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
+		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+
+		switch (acl->a_entries[n].e_tag) {
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			value = (char *)value +
+				sizeof(ext4_acl_entry_short);
+			acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
+			break;
+
+		case ACL_USER:
+		case ACL_GROUP:
+			value = (char *)value + sizeof(ext4_acl_entry);
+			if ((char *)value > end)
+				goto fail;
+			acl->a_entries[n].e_id =
+				le32_to_cpu(entry->e_id);
+			break;
+
+		default:
+			goto fail;
+		}
+	}
+	if (value != end)
+		goto fail;
+	return acl;
+
+fail:
+	posix_acl_release(acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Convert from in-memory to filesystem representation.
+ */
+static void *
+ext4_acl_to_disk(const struct posix_acl *acl, size_t *size)
+{
+	ext4_acl_header *ext_acl;
+	char *e;
+	size_t n;
+
+	*size = ext4_acl_size(acl->a_count);
+	ext_acl = kmalloc(sizeof(ext4_acl_header) + acl->a_count *
+			sizeof(ext4_acl_entry), GFP_NOFS);
+	if (!ext_acl)
+		return ERR_PTR(-ENOMEM);
+	ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION);
+	e = (char *)ext_acl + sizeof(ext4_acl_header);
+	for (n = 0; n < acl->a_count; n++) {
+		ext4_acl_entry *entry = (ext4_acl_entry *)e;
+		entry->e_tag  = cpu_to_le16(acl->a_entries[n].e_tag);
+		entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
+		switch (acl->a_entries[n].e_tag) {
+		case ACL_USER:
+		case ACL_GROUP:
+			entry->e_id = cpu_to_le32(acl->a_entries[n].e_id);
+			e += sizeof(ext4_acl_entry);
+			break;
+
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			e += sizeof(ext4_acl_entry_short);
+			break;
+
+		default:
+			goto fail;
+		}
+	}
+	return (char *)ext_acl;
+
+fail:
+	kfree(ext_acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Inode operation get_posix_acl().
+ *
+ * inode->i_mutex: don't care
+ */
+static struct posix_acl *
+ext4_get_acl(struct inode *inode, int type)
+{
+	int name_index;
+	char *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return NULL;
+
+	acl = get_cached_acl(inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	retval = ext4_xattr_get(inode, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = ext4_xattr_get(inode, name_index, "", value, retval);
+	}
+	if (retval > 0)
+		acl = ext4_acl_from_disk(value, retval);
+	else if (retval == -ENODATA || retval == -ENOSYS)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
+
+	return acl;
+}
+
+/*
+ * Set the access or default ACL of an inode.
+ *
+ * inode->i_mutex: down unless called from ext4_new_inode
+ */
+static int
+ext4_set_acl(handle_t *handle, struct inode *inode, int type,
+	     struct posix_acl *acl)
+{
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+		if (acl) {
+			mode_t mode = inode->i_mode;
+			error = posix_acl_equiv_mode(acl, &mode);
+			if (error < 0)
+				return error;
+			else {
+				inode->i_mode = mode;
+				inode->i_ctime = ext4_current_time(inode);
+				ext4_mark_inode_dirty(handle, inode);
+				if (error == 0)
+					acl = NULL;
+			}
+		}
+		break;
+
+	case ACL_TYPE_DEFAULT:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		if (!S_ISDIR(inode->i_mode))
+			return acl ? -EACCES : 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (acl) {
+		value = ext4_acl_to_disk(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	error = ext4_xattr_set_handle(handle, inode, name_index, "",
+				      value, size, 0);
+
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+
+	return error;
+}
+
+int
+ext4_check_acl(struct inode *inode, int mask, unsigned int flags)
+{
+	struct posix_acl *acl;
+
+	if (flags & IPERM_FLAG_RCU) {
+		if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+			return -ECHILD;
+		return -EAGAIN;
+	}
+
+	acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl) {
+		int error = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return error;
+	}
+
+	return -EAGAIN;
+}
+
+/*
+ * Initialize the ACLs of a new inode. Called from ext4_new_inode.
+ *
+ * dir->i_mutex: down
+ * inode->i_mutex: up (access to inode is still exclusive)
+ */
+int
+ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+	struct posix_acl *acl = NULL;
+	int error = 0;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (test_opt(dir->i_sb, POSIX_ACL)) {
+			acl = ext4_get_acl(dir, ACL_TYPE_DEFAULT);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		}
+		if (!acl)
+			inode->i_mode &= ~current_umask();
+	}
+	if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
+		struct posix_acl *clone;
+		mode_t mode;
+
+		if (S_ISDIR(inode->i_mode)) {
+			error = ext4_set_acl(handle, inode,
+					     ACL_TYPE_DEFAULT, acl);
+			if (error)
+				goto cleanup;
+		}
+		clone = posix_acl_clone(acl, GFP_NOFS);
+		error = -ENOMEM;
+		if (!clone)
+			goto cleanup;
+
+		mode = inode->i_mode;
+		error = posix_acl_create_masq(clone, &mode);
+		if (error >= 0) {
+			inode->i_mode = mode;
+			if (error > 0) {
+				/* This is an extended ACL */
+				error = ext4_set_acl(handle, inode,
+						     ACL_TYPE_ACCESS, clone);
+			}
+		}
+		posix_acl_release(clone);
+	}
+cleanup:
+	posix_acl_release(acl);
+	return error;
+}
+
+/*
+ * Does chmod for an inode that may have an Access Control List. The
+ * inode->i_mode field must be updated to the desired value by the caller
+ * before calling this function.
+ * Returns 0 on success, or a negative error number.
+ *
+ * We change the ACL rather than storing some ACL entries in the file
+ * mode permission bits (which would be more efficient), because that
+ * would break once additional permissions (like  ACL_APPEND, ACL_DELETE
+ * for directories) are added. There are no more bits available in the
+ * file mode.
+ *
+ * inode->i_mutex: down
+ */
+int
+ext4_acl_chmod(struct inode *inode)
+{
+	struct posix_acl *acl, *clone;
+	int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return 0;
+	acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl) || !acl)
+		return PTR_ERR(acl);
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	posix_acl_release(acl);
+	if (!clone)
+		return -ENOMEM;
+	error = posix_acl_chmod_masq(clone, inode->i_mode);
+	if (!error) {
+		handle_t *handle;
+		int retries = 0;
+
+	retry:
+		handle = ext4_journal_start(inode,
+				EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+		if (IS_ERR(handle)) {
+			error = PTR_ERR(handle);
+			ext4_std_error(inode->i_sb, error);
+			goto out;
+		}
+		error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, clone);
+		ext4_journal_stop(handle);
+		if (error == -ENOSPC &&
+		    ext4_should_retry_alloc(inode->i_sb, &retries))
+			goto retry;
+	}
+out:
+	posix_acl_release(clone);
+	return error;
+}
+
+/*
+ * Extended attribute handlers
+ */
+static size_t
+ext4_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
+			   const char *name, size_t name_len, int type)
+{
+	const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
+
+	if (!test_opt(dentry->d_sb, POSIX_ACL))
+		return 0;
+	if (list && size <= list_len)
+		memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
+	return size;
+}
+
+static size_t
+ext4_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
+			    const char *name, size_t name_len, int type)
+{
+	const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
+
+	if (!test_opt(dentry->d_sb, POSIX_ACL))
+		return 0;
+	if (list && size <= list_len)
+		memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
+	return size;
+}
+
+static int
+ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
+		   size_t size, int type)
+{
+	struct posix_acl *acl;
+	int error;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	if (!test_opt(dentry->d_sb, POSIX_ACL))
+		return -EOPNOTSUPP;
+
+	acl = ext4_get_acl(dentry->d_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
+ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
+		   size_t size, int flags, int type)
+{
+	struct inode *inode = dentry->d_inode;
+	handle_t *handle;
+	struct posix_acl *acl;
+	int error, retries = 0;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return -EOPNOTSUPP;
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+
+	if (value) {
+		acl = posix_acl_from_xattr(value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		else if (acl) {
+			error = posix_acl_valid(acl);
+			if (error)
+				goto release_and_out;
+		}
+	} else
+		acl = NULL;
+
+retry:
+	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	error = ext4_set_acl(handle, inode, type, acl);
+	ext4_journal_stop(handle);
+	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+
+release_and_out:
+	posix_acl_release(acl);
+	return error;
+}
+
+const struct xattr_handler ext4_xattr_acl_access_handler = {
+	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.flags	= ACL_TYPE_ACCESS,
+	.list	= ext4_xattr_list_acl_access,
+	.get	= ext4_xattr_get_acl,
+	.set	= ext4_xattr_set_acl,
+};
+
+const struct xattr_handler ext4_xattr_acl_default_handler = {
+	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.flags	= ACL_TYPE_DEFAULT,
+	.list	= ext4_xattr_list_acl_default,
+	.get	= ext4_xattr_get_acl,
+	.set	= ext4_xattr_set_acl,
+};
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
new file mode 100644
index 00000000..dec82116
--- /dev/null
+++ b/fs/ext4/acl.h
@@ -0,0 +1,77 @@
+/*
+  File: fs/ext4/acl.h
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/posix_acl_xattr.h>
+
+#define EXT4_ACL_VERSION	0x0001
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+	__le32		e_id;
+} ext4_acl_entry;
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+} ext4_acl_entry_short;
+
+typedef struct {
+	__le32		a_version;
+} ext4_acl_header;
+
+static inline size_t ext4_acl_size(int count)
+{
+	if (count <= 4) {
+		return sizeof(ext4_acl_header) +
+		       count * sizeof(ext4_acl_entry_short);
+	} else {
+		return sizeof(ext4_acl_header) +
+		       4 * sizeof(ext4_acl_entry_short) +
+		       (count - 4) * sizeof(ext4_acl_entry);
+	}
+}
+
+static inline int ext4_acl_count(size_t size)
+{
+	ssize_t s;
+	size -= sizeof(ext4_acl_header);
+	s = size - 4 * sizeof(ext4_acl_entry_short);
+	if (s < 0) {
+		if (size % sizeof(ext4_acl_entry_short))
+			return -1;
+		return size / sizeof(ext4_acl_entry_short);
+	} else {
+		if (s % sizeof(ext4_acl_entry))
+			return -1;
+		return s / sizeof(ext4_acl_entry) + 4;
+	}
+}
+
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+
+/* acl.c */
+extern int ext4_check_acl(struct inode *, int, unsigned int);
+extern int ext4_acl_chmod(struct inode *);
+extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
+
+#else  /* CONFIG_EXT4_FS_POSIX_ACL */
+#include <linux/sched.h>
+#define ext4_check_acl NULL
+
+static inline int
+ext4_acl_chmod(struct inode *inode)
+{
+	return 0;
+}
+
+static inline int
+ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+	return 0;
+}
+#endif  /* CONFIG_EXT4_FS_POSIX_ACL */
+
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
new file mode 100644
index 00000000..264f6949
--- /dev/null
+++ b/fs/ext4/balloc.c
@@ -0,0 +1,622 @@
+/*
+ *  linux/fs/ext4/balloc.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  Enhanced block allocation by Stephen Tweedie (sct@redhat.com), 1993
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/time.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include "ext4.h"
+#include "ext4_jbd2.h"
+#include "mballoc.h"
+
+#include <trace/events/ext4.h>
+
+/*
+ * balloc.c contains the blocks allocation and deallocation routines
+ */
+
+/*
+ * Calculate the block group number and offset, given a block number
+ */
+void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
+		ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	ext4_grpblk_t offset;
+
+	blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
+	offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
+	if (offsetp)
+		*offsetp = offset;
+	if (blockgrpp)
+		*blockgrpp = blocknr;
+
+}
+
+static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
+			ext4_group_t block_group)
+{
+	ext4_group_t actual_group;
+	ext4_get_group_no_and_offset(sb, block, &actual_group, NULL);
+	if (actual_group == block_group)
+		return 1;
+	return 0;
+}
+
+static int ext4_group_used_meta_blocks(struct super_block *sb,
+				       ext4_group_t block_group,
+				       struct ext4_group_desc *gdp)
+{
+	ext4_fsblk_t tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	/* block bitmap, inode bitmap, and inode table blocks */
+	int used_blocks = sbi->s_itb_per_group + 2;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
+					block_group))
+			used_blocks--;
+
+		if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
+					block_group))
+			used_blocks--;
+
+		tmp = ext4_inode_table(sb, gdp);
+		for (; tmp < ext4_inode_table(sb, gdp) +
+				sbi->s_itb_per_group; tmp++) {
+			if (!ext4_block_in_group(sb, tmp, block_group))
+				used_blocks -= 1;
+		}
+	}
+	return used_blocks;
+}
+
+/* Initializes an uninitialized block bitmap if given, and returns the
+ * number of blocks free in the group. */
+unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
+		 ext4_group_t block_group, struct ext4_group_desc *gdp)
+{
+	int bit, bit_max;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	unsigned free_blocks, group_blocks;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (bh) {
+		J_ASSERT_BH(bh, buffer_locked(bh));
+
+		/* If checksum is bad mark all blocks used to prevent allocation
+		 * essentially implementing a per-group read-only flag. */
+		if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+			ext4_error(sb, "Checksum bad for group %u",
+					block_group);
+			ext4_free_blks_set(sb, gdp, 0);
+			ext4_free_inodes_set(sb, gdp, 0);
+			ext4_itable_unused_set(sb, gdp, 0);
+			memset(bh->b_data, 0xff, sb->s_blocksize);
+			return 0;
+		}
+		memset(bh->b_data, 0, sb->s_blocksize);
+	}
+
+	/* Check for superblock and gdt backups in this group */
+	bit_max = ext4_bg_has_super(sb, block_group);
+
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+	    block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
+			  sbi->s_desc_per_block) {
+		if (bit_max) {
+			bit_max += ext4_bg_num_gdb(sb, block_group);
+			bit_max +=
+				le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+		}
+	} else { /* For META_BG_BLOCK_GROUPS */
+		bit_max += ext4_bg_num_gdb(sb, block_group);
+	}
+
+	if (block_group == ngroups - 1) {
+		/*
+		 * Even though mke2fs always initialize first and last group
+		 * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
+		 * to make sure we calculate the right free blocks
+		 */
+		group_blocks = ext4_blocks_count(sbi->s_es) -
+			ext4_group_first_block_no(sb, ngroups - 1);
+	} else {
+		group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
+	}
+
+	free_blocks = group_blocks - bit_max;
+
+	if (bh) {
+		ext4_fsblk_t start, tmp;
+		int flex_bg = 0;
+
+		for (bit = 0; bit < bit_max; bit++)
+			ext4_set_bit(bit, bh->b_data);
+
+		start = ext4_group_first_block_no(sb, block_group);
+
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+					      EXT4_FEATURE_INCOMPAT_FLEX_BG))
+			flex_bg = 1;
+
+		/* Set bits for block and inode bitmaps, and inode table */
+		tmp = ext4_block_bitmap(sb, gdp);
+		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+			ext4_set_bit(tmp - start, bh->b_data);
+
+		tmp = ext4_inode_bitmap(sb, gdp);
+		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+			ext4_set_bit(tmp - start, bh->b_data);
+
+		tmp = ext4_inode_table(sb, gdp);
+		for (; tmp < ext4_inode_table(sb, gdp) +
+				sbi->s_itb_per_group; tmp++) {
+			if (!flex_bg ||
+				ext4_block_in_group(sb, tmp, block_group))
+				ext4_set_bit(tmp - start, bh->b_data);
+		}
+		/*
+		 * Also if the number of blocks within the group is
+		 * less than the blocksize * 8 ( which is the size
+		 * of bitmap ), set rest of the block bitmap to 1
+		 */
+		ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
+				     bh->b_data);
+	}
+	return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
+}
+
+
+/*
+ * The free blocks are managed by bitmaps.  A file system contains several
+ * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
+ * block for inodes, N blocks for the inode table and data blocks.
+ *
+ * The file system contains group descriptors which are located after the
+ * super block.  Each descriptor contains the number of the bitmap block and
+ * the free blocks count in the block.  The descriptors are loaded in memory
+ * when a file system is mounted (see ext4_fill_super).
+ */
+
+/**
+ * ext4_get_group_desc() -- load group descriptor from disk
+ * @sb:			super block
+ * @block_group:	given block group
+ * @bh:			pointer to the buffer head to store the block
+ *			group descriptor
+ */
+struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
+					     ext4_group_t block_group,
+					     struct buffer_head **bh)
+{
+	unsigned int group_desc;
+	unsigned int offset;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_group_desc *desc;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (block_group >= ngroups) {
+		ext4_error(sb, "block_group >= groups_count - block_group = %u,"
+			   " groups_count = %u", block_group, ngroups);
+
+		return NULL;
+	}
+
+	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
+	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
+	if (!sbi->s_group_desc[group_desc]) {
+		ext4_error(sb, "Group descriptor not loaded - "
+			   "block_group = %u, group_desc = %u, desc = %u",
+			   block_group, group_desc, offset);
+		return NULL;
+	}
+
+	desc = (struct ext4_group_desc *)(
+		(__u8 *)sbi->s_group_desc[group_desc]->b_data +
+		offset * EXT4_DESC_SIZE(sb));
+	if (bh)
+		*bh = sbi->s_group_desc[group_desc];
+	return desc;
+}
+
+static int ext4_valid_block_bitmap(struct super_block *sb,
+					struct ext4_group_desc *desc,
+					unsigned int block_group,
+					struct buffer_head *bh)
+{
+	ext4_grpblk_t offset;
+	ext4_grpblk_t next_zero_bit;
+	ext4_fsblk_t bitmap_blk;
+	ext4_fsblk_t group_first_block;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		/* with FLEX_BG, the inode/block bitmaps and itable
+		 * blocks may not be in the group at all
+		 * so the bitmap validation will be skipped for those groups
+		 * or it has to also read the block group where the bitmaps
+		 * are located to verify they are set.
+		 */
+		return 1;
+	}
+	group_first_block = ext4_group_first_block_no(sb, block_group);
+
+	/* check whether block bitmap block number is set */
+	bitmap_blk = ext4_block_bitmap(sb, desc);
+	offset = bitmap_blk - group_first_block;
+	if (!ext4_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode bitmap block number is set */
+	bitmap_blk = ext4_inode_bitmap(sb, desc);
+	offset = bitmap_blk - group_first_block;
+	if (!ext4_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode table block number is set */
+	bitmap_blk = ext4_inode_table(sb, desc);
+	offset = bitmap_blk - group_first_block;
+	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
+				offset + EXT4_SB(sb)->s_itb_per_group,
+				offset);
+	if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
+		/* good bitmap for inode tables */
+		return 1;
+
+err_out:
+	ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
+			block_group, bitmap_blk);
+	return 0;
+}
+/**
+ * ext4_read_block_bitmap()
+ * @sb:			super block
+ * @block_group:	given block group
+ *
+ * Read the bitmap for a given block_group,and validate the
+ * bits for block/inode/inode tables are set in the bitmaps
+ *
+ * Return buffer_head on success or NULL in case of failure.
+ */
+struct buffer_head *
+ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
+{
+	struct ext4_group_desc *desc;
+	struct buffer_head *bh = NULL;
+	ext4_fsblk_t bitmap_blk;
+
+	desc = ext4_get_group_desc(sb, block_group, NULL);
+	if (!desc)
+		return NULL;
+	bitmap_blk = ext4_block_bitmap(sb, desc);
+	bh = sb_getblk(sb, bitmap_blk);
+	if (unlikely(!bh)) {
+		ext4_error(sb, "Cannot read block bitmap - "
+			    "block_group = %u, block_bitmap = %llu",
+			    block_group, bitmap_blk);
+		return NULL;
+	}
+
+	if (bitmap_uptodate(bh))
+		return bh;
+
+	lock_buffer(bh);
+	if (bitmap_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	}
+	ext4_lock_group(sb, block_group);
+	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		ext4_init_block_bitmap(sb, bh, block_group, desc);
+		set_bitmap_uptodate(bh);
+		set_buffer_uptodate(bh);
+		ext4_unlock_group(sb, block_group);
+		unlock_buffer(bh);
+		return bh;
+	}
+	ext4_unlock_group(sb, block_group);
+	if (buffer_uptodate(bh)) {
+		/*
+		 * if not uninit if bh is uptodate,
+		 * bitmap is also uptodate
+		 */
+		set_bitmap_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
+	}
+	/*
+	 * submit the buffer_head for read. We can
+	 * safely mark the bitmap as uptodate now.
+	 * We do it here so the bitmap uptodate bit
+	 * get set with buffer lock held.
+	 */
+	trace_ext4_read_block_bitmap_load(sb, block_group);
+	set_bitmap_uptodate(bh);
+	if (bh_submit_read(bh) < 0) {
+		put_bh(bh);
+		ext4_error(sb, "Cannot read block bitmap - "
+			    "block_group = %u, block_bitmap = %llu",
+			    block_group, bitmap_blk);
+		return NULL;
+	}
+	ext4_valid_block_bitmap(sb, desc, block_group, bh);
+	/*
+	 * file system mounted not to panic on error,
+	 * continue with corrupt bitmap
+	 */
+	return bh;
+}
+
+/**
+ * ext4_has_free_blocks()
+ * @sbi:	in-core super block structure.
+ * @nblocks:	number of needed blocks
+ *
+ * Check if filesystem has nblocks free & available for allocation.
+ * On success return 1, return 0 on failure.
+ */
+static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
+				s64 nblocks, unsigned int flags)
+{
+	s64 free_blocks, dirty_blocks, root_blocks;
+	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
+
+	free_blocks  = percpu_counter_read_positive(fbc);
+	dirty_blocks = percpu_counter_read_positive(dbc);
+	root_blocks = ext4_r_blocks_count(sbi->s_es);
+
+	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+						EXT4_FREEBLOCKS_WATERMARK) {
+		free_blocks  = percpu_counter_sum_positive(fbc);
+		dirty_blocks = percpu_counter_sum_positive(dbc);
+	}
+	/* Check whether we have space after
+	 * accounting for current dirty blocks & root reserved blocks.
+	 */
+	if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
+		return 1;
+
+	/* Hm, nope.  Are (enough) root reserved blocks available? */
+	if (sbi->s_resuid == current_fsuid() ||
+	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
+	    capable(CAP_SYS_RESOURCE) ||
+		(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
+
+		if (free_blocks >= (nblocks + dirty_blocks))
+			return 1;
+	}
+
+	return 0;
+}
+
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+			   s64 nblocks, unsigned int flags)
+{
+	if (ext4_has_free_blocks(sbi, nblocks, flags)) {
+		percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
+		return 0;
+	} else
+		return -ENOSPC;
+}
+
+/**
+ * ext4_should_retry_alloc()
+ * @sb:			super block
+ * @retries		number of attemps has been made
+ *
+ * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
+ * it is profitable to retry the operation, this function will wait
+ * for the current or committing transaction to complete, and then
+ * return TRUE.
+ *
+ * if the total number of retries exceed three times, return FALSE.
+ */
+int ext4_should_retry_alloc(struct super_block *sb, int *retries)
+{
+	if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) ||
+	    (*retries)++ > 3 ||
+	    !EXT4_SB(sb)->s_journal)
+		return 0;
+
+	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
+
+	return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+}
+
+/*
+ * ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks
+ *
+ * @handle:             handle to this transaction
+ * @inode:              file inode
+ * @goal:               given target block(filesystem wide)
+ * @count:		pointer to total number of blocks needed
+ * @errp:               error code
+ *
+ * Return 1st allocated block number on success, *count stores total account
+ * error stores in errp pointer
+ */
+ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
+				  ext4_fsblk_t goal, unsigned int flags,
+				  unsigned long *count, int *errp)
+{
+	struct ext4_allocation_request ar;
+	ext4_fsblk_t ret;
+
+	memset(&ar, 0, sizeof(ar));
+	/* Fill with neighbour allocated blocks */
+	ar.inode = inode;
+	ar.goal = goal;
+	ar.len = count ? *count : 1;
+	ar.flags = flags;
+
+	ret = ext4_mb_new_blocks(handle, &ar, errp);
+	if (count)
+		*count = ar.len;
+	/*
+	 * Account for the allocated meta blocks.  We will never
+	 * fail EDQUOT for metdata, but we do account for it.
+	 */
+	if (!(*errp) &&
+	    ext4_test_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED)) {
+		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+		EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
+		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+		dquot_alloc_block_nofail(inode, ar.len);
+	}
+	return ret;
+}
+
+/**
+ * ext4_count_free_blocks() -- count filesystem free blocks
+ * @sb:		superblock
+ *
+ * Adds up the number of free blocks from each block group.
+ */
+ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
+{
+	ext4_fsblk_t desc_count;
+	struct ext4_group_desc *gdp;
+	ext4_group_t i;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+#ifdef EXT4FS_DEBUG
+	struct ext4_super_block *es;
+	ext4_fsblk_t bitmap_count;
+	unsigned int x;
+	struct buffer_head *bitmap_bh = NULL;
+
+	es = EXT4_SB(sb)->s_es;
+	desc_count = 0;
+	bitmap_count = 0;
+	gdp = NULL;
+
+	for (i = 0; i < ngroups; i++) {
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += ext4_free_blks_count(sb, gdp);
+		brelse(bitmap_bh);
+		bitmap_bh = ext4_read_block_bitmap(sb, i);
+		if (bitmap_bh == NULL)
+			continue;
+
+		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
+			i, ext4_free_blks_count(sb, gdp), x);
+		bitmap_count += x;
+	}
+	brelse(bitmap_bh);
+	printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
+		", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+	       desc_count, bitmap_count);
+	return bitmap_count;
+#else
+	desc_count = 0;
+	for (i = 0; i < ngroups; i++) {
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += ext4_free_blks_count(sb, gdp);
+	}
+
+	return desc_count;
+#endif
+}
+
+static inline int test_root(ext4_group_t a, int b)
+{
+	int num = b;
+
+	while (a > num)
+		num *= b;
+	return num == a;
+}
+
+static int ext4_group_sparse(ext4_group_t group)
+{
+	if (group <= 1)
+		return 1;
+	if (!(group & 1))
+		return 0;
+	return (test_root(group, 7) || test_root(group, 5) ||
+		test_root(group, 3));
+}
+
+/**
+ *	ext4_bg_has_super - number of blocks used by the superblock in group
+ *	@sb: superblock for filesystem
+ *	@group: group number to check
+ *
+ *	Return the number of blocks used by the superblock (primary or backup)
+ *	in this group.  Currently this will be only 0 or 1.
+ */
+int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
+{
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
+			!ext4_group_sparse(group))
+		return 0;
+	return 1;
+}
+
+static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
+					ext4_group_t group)
+{
+	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
+	ext4_group_t first = metagroup * EXT4_DESC_PER_BLOCK(sb);
+	ext4_group_t last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
+
+	if (group == first || group == first + 1 || group == last)
+		return 1;
+	return 0;
+}
+
+static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
+					ext4_group_t group)
+{
+	if (!ext4_bg_has_super(sb, group))
+		return 0;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG))
+		return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
+	else
+		return EXT4_SB(sb)->s_gdb_count;
+}
+
+/**
+ *	ext4_bg_num_gdb - number of blocks used by the group table in group
+ *	@sb: superblock for filesystem
+ *	@group: group number to check
+ *
+ *	Return the number of blocks used by the group descriptor table
+ *	(primary or backup) in this group.  In the future there may be a
+ *	different number of descriptor blocks in each group.
+ */
+unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
+{
+	unsigned long first_meta_bg =
+			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
+	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
+
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) ||
+			metagroup < first_meta_bg)
+		return ext4_bg_num_gdb_nometa(sb, group);
+
+	return ext4_bg_num_gdb_meta(sb,group);
+
+}
+
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
new file mode 100644
index 00000000..fa3af81a
--- /dev/null
+++ b/fs/ext4/bitmap.c
@@ -0,0 +1,31 @@
+/*
+ *  linux/fs/ext4/bitmap.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/jbd2.h>
+#include "ext4.h"
+
+#ifdef EXT4FS_DEBUG
+
+static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
+
+unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
+{
+	unsigned int i, sum = 0;
+
+	if (!map)
+		return 0;
+	for (i = 0; i < numchars; i++)
+		sum += nibblemap[map->b_data[i] & 0xf] +
+			nibblemap[(map->b_data[i] >> 4) & 0xf];
+	return sum;
+}
+
+#endif  /*  EXT4FS_DEBUG  */
+
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
new file mode 100644
index 00000000..fac90f3f
--- /dev/null
+++ b/fs/ext4/block_validity.c
@@ -0,0 +1,248 @@
+/*
+ *  linux/fs/ext4/block_validity.c
+ *
+ * Copyright (C) 2009
+ * Theodore Ts'o (tytso@mit.edu)
+ *
+ * Track which blocks in the filesystem are metadata blocks that
+ * should never be used as data blocks by files or directories.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/blkdev.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include "ext4.h"
+
+struct ext4_system_zone {
+	struct rb_node	node;
+	ext4_fsblk_t	start_blk;
+	unsigned int	count;
+};
+
+static struct kmem_cache *ext4_system_zone_cachep;
+
+int __init ext4_init_system_zone(void)
+{
+	ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0);
+	if (ext4_system_zone_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void ext4_exit_system_zone(void)
+{
+	kmem_cache_destroy(ext4_system_zone_cachep);
+}
+
+static inline int can_merge(struct ext4_system_zone *entry1,
+		     struct ext4_system_zone *entry2)
+{
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+		return 1;
+	return 0;
+}
+
+/*
+ * Mark a range of blocks as belonging to the "system zone" --- that
+ * is, filesystem metadata blocks which should never be used by
+ * inodes.
+ */
+static int add_system_zone(struct ext4_sb_info *sbi,
+			   ext4_fsblk_t start_blk,
+			   unsigned int count)
+{
+	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct rb_node **n = &sbi->system_blks.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node = NULL;
+
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_system_zone, node);
+		if (start_blk < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else {
+			if (start_blk + count > (entry->start_blk +
+						 entry->count))
+				entry->count = (start_blk + count -
+						entry->start_blk);
+			new_node = *n;
+			new_entry = rb_entry(new_node, struct ext4_system_zone,
+					     node);
+			break;
+		}
+	}
+
+	if (!new_entry) {
+		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+					     GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		new_entry->start_blk = start_blk;
+		new_entry->count = count;
+		new_node = &new_entry->node;
+
+		rb_link_node(new_node, parent, n);
+		rb_insert_color(new_node, &sbi->system_blks);
+	}
+
+	/* Can we merge to the left? */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &sbi->system_blks);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+
+	/* Can we merge to the right? */
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &sbi->system_blks);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+	return 0;
+}
+
+static void debug_print_tree(struct ext4_sb_info *sbi)
+{
+	struct rb_node *node;
+	struct ext4_system_zone *entry;
+	int first = 1;
+
+	printk(KERN_INFO "System zones: ");
+	node = rb_first(&sbi->system_blks);
+	while (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		printk("%s%llu-%llu", first ? "" : ", ",
+		       entry->start_blk, entry->start_blk + entry->count - 1);
+		first = 0;
+		node = rb_next(node);
+	}
+	printk("\n");
+}
+
+int ext4_setup_system_zone(struct super_block *sb)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp;
+	ext4_group_t i;
+	int flex_size = ext4_flex_bg_size(sbi);
+	int ret;
+
+	if (!test_opt(sb, BLOCK_VALIDITY)) {
+		if (EXT4_SB(sb)->system_blks.rb_node)
+			ext4_release_system_zone(sb);
+		return 0;
+	}
+	if (EXT4_SB(sb)->system_blks.rb_node)
+		return 0;
+
+	for (i=0; i < ngroups; i++) {
+		if (ext4_bg_has_super(sb, i) &&
+		    ((i < 5) || ((i % flex_size) == 0)))
+			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
+					ext4_bg_num_gdb(sb, i) + 1);
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
+		if (ret)
+			return ret;
+		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1);
+		if (ret)
+			return ret;
+		ret = add_system_zone(sbi, ext4_inode_table(sb, gdp),
+				sbi->s_itb_per_group);
+		if (ret)
+			return ret;
+	}
+
+	if (test_opt(sb, DEBUG))
+		debug_print_tree(EXT4_SB(sb));
+	return 0;
+}
+
+/* Called when the filesystem is unmounted */
+void ext4_release_system_zone(struct super_block *sb)
+{
+	struct rb_node	*n = EXT4_SB(sb)->system_blks.rb_node;
+	struct rb_node	*parent;
+	struct ext4_system_zone	*entry;
+
+	while (n) {
+		/* Do the node's children first */
+		if (n->rb_left) {
+			n = n->rb_left;
+			continue;
+		}
+		if (n->rb_right) {
+			n = n->rb_right;
+			continue;
+		}
+		/*
+		 * The node has no children; free it, and then zero
+		 * out parent's link to it.  Finally go to the
+		 * beginning of the loop and try to free the parent
+		 * node.
+		 */
+		parent = rb_parent(n);
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		kmem_cache_free(ext4_system_zone_cachep, entry);
+		if (!parent)
+			EXT4_SB(sb)->system_blks = RB_ROOT;
+		else if (parent->rb_left == n)
+			parent->rb_left = NULL;
+		else if (parent->rb_right == n)
+			parent->rb_right = NULL;
+		n = parent;
+	}
+	EXT4_SB(sb)->system_blks = RB_ROOT;
+}
+
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with filesystem metadata blocks.
+ */
+int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+			  unsigned int count)
+{
+	struct ext4_system_zone *entry;
+	struct rb_node *n = sbi->system_blks.rb_node;
+
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count < start_blk) ||
+	    (start_blk + count > ext4_blocks_count(sbi->s_es))) {
+		sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
+		return 0;
+	}
+	while (n) {
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		if (start_blk + count - 1 < entry->start_blk)
+			n = n->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = n->rb_right;
+		else {
+			sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
+			return 0;
+		}
+	}
+	return 1;
+}
+
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
new file mode 100644
index 00000000..164c5609
--- /dev/null
+++ b/fs/ext4/dir.c
@@ -0,0 +1,542 @@
+/*
+ *  linux/fs/ext4/dir.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/dir.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4 directory handling functions
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ * Hash Tree Directory indexing (c) 2001  Daniel Phillips
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/buffer_head.h>
+#include <linux/slab.h>
+#include <linux/rbtree.h>
+#include "ext4.h"
+
+static unsigned char ext4_filetype_table[] = {
+	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
+};
+
+static int ext4_readdir(struct file *, void *, filldir_t);
+static int ext4_dx_readdir(struct file *filp,
+			   void *dirent, filldir_t filldir);
+static int ext4_release_dir(struct inode *inode,
+				struct file *filp);
+
+const struct file_operations ext4_dir_operations = {
+	.llseek		= ext4_llseek,
+	.read		= generic_read_dir,
+	.readdir	= ext4_readdir,		/* we take BKL. needed?*/
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.fsync		= ext4_sync_file,
+	.release	= ext4_release_dir,
+};
+
+
+static unsigned char get_dtype(struct super_block *sb, int filetype)
+{
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) ||
+	    (filetype >= EXT4_FT_MAX))
+		return DT_UNKNOWN;
+
+	return (ext4_filetype_table[filetype]);
+}
+
+/*
+ * Return 0 if the directory entry is OK, and 1 if there is a problem
+ *
+ * Note: this is the opposite of what ext2 and ext3 historically returned...
+ */
+int __ext4_check_dir_entry(const char *function, unsigned int line,
+			   struct inode *dir, struct file *filp,
+			   struct ext4_dir_entry_2 *de,
+			   struct buffer_head *bh,
+			   unsigned int offset)
+{
+	const char *error_msg = NULL;
+	const int rlen = ext4_rec_len_from_disk(de->rec_len,
+						dir->i_sb->s_blocksize);
+
+	if (unlikely(rlen < EXT4_DIR_REC_LEN(1)))
+		error_msg = "rec_len is smaller than minimal";
+	else if (unlikely(rlen % 4 != 0))
+		error_msg = "rec_len % 4 != 0";
+	else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len)))
+		error_msg = "rec_len is too small for name_len";
+	else if (unlikely(((char *) de - bh->b_data) + rlen >
+			  dir->i_sb->s_blocksize))
+		error_msg = "directory entry across blocks";
+	else if (unlikely(le32_to_cpu(de->inode) >
+			le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
+		error_msg = "inode out of bounds";
+	else
+		return 0;
+
+	if (filp)
+		ext4_error_file(filp, function, line, bh ? bh->b_blocknr : 0,
+				"bad entry in directory: %s - offset=%u(%u), "
+				"inode=%u, rec_len=%d, name_len=%d",
+				error_msg, (unsigned) (offset%bh->b_size),
+				offset, le32_to_cpu(de->inode),
+				rlen, de->name_len);
+	else
+		ext4_error_inode(dir, function, line, bh ? bh->b_blocknr : 0,
+				"bad entry in directory: %s - offset=%u(%u), "
+				"inode=%u, rec_len=%d, name_len=%d",
+				error_msg, (unsigned) (offset%bh->b_size),
+				offset, le32_to_cpu(de->inode),
+				rlen, de->name_len);
+
+	return 1;
+}
+
+static int ext4_readdir(struct file *filp,
+			 void *dirent, filldir_t filldir)
+{
+	int error = 0;
+	unsigned int offset;
+	int i, stored;
+	struct ext4_dir_entry_2 *de;
+	struct super_block *sb;
+	int err;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	int ret = 0;
+	int dir_has_error = 0;
+
+	sb = inode->i_sb;
+
+	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+				    EXT4_FEATURE_COMPAT_DIR_INDEX) &&
+	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
+	     ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+		err = ext4_dx_readdir(filp, dirent, filldir);
+		if (err != ERR_BAD_DX_DIR) {
+			ret = err;
+			goto out;
+		}
+		/*
+		 * We don't set the inode dirty flag since it's not
+		 * critical that it get flushed back to the disk.
+		 */
+		ext4_clear_inode_flag(filp->f_path.dentry->d_inode,
+				      EXT4_INODE_INDEX);
+	}
+	stored = 0;
+	offset = filp->f_pos & (sb->s_blocksize - 1);
+
+	while (!error && !stored && filp->f_pos < inode->i_size) {
+		struct ext4_map_blocks map;
+		struct buffer_head *bh = NULL;
+
+		map.m_lblk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
+		map.m_len = 1;
+		err = ext4_map_blocks(NULL, inode, &map, 0);
+		if (err > 0) {
+			pgoff_t index = map.m_pblk >>
+					(PAGE_CACHE_SHIFT - inode->i_blkbits);
+			if (!ra_has_index(&filp->f_ra, index))
+				page_cache_sync_readahead(
+					sb->s_bdev->bd_inode->i_mapping,
+					&filp->f_ra, filp,
+					index, 1);
+			filp->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
+			bh = ext4_bread(NULL, inode, map.m_lblk, 0, &err);
+		}
+
+		/*
+		 * We ignore I/O errors on directories so users have a chance
+		 * of recovering data when there's a bad sector
+		 */
+		if (!bh) {
+			if (!dir_has_error) {
+				EXT4_ERROR_FILE(filp, 0,
+						"directory contains a "
+						"hole at offset %llu",
+					   (unsigned long long) filp->f_pos);
+				dir_has_error = 1;
+			}
+			/* corrupt size?  Maybe no more blocks to read */
+			if (filp->f_pos > inode->i_blocks << 9)
+				break;
+			filp->f_pos += sb->s_blocksize - offset;
+			continue;
+		}
+
+revalidate:
+		/* If the dir block has changed since the last call to
+		 * readdir(2), then we might be pointing to an invalid
+		 * dirent right now.  Scan from the start of the block
+		 * to make sure. */
+		if (filp->f_version != inode->i_version) {
+			for (i = 0; i < sb->s_blocksize && i < offset; ) {
+				de = (struct ext4_dir_entry_2 *)
+					(bh->b_data + i);
+				/* It's too expensive to do a full
+				 * dirent test each time round this
+				 * loop, but we do have to test at
+				 * least that it is non-zero.  A
+				 * failure will be detected in the
+				 * dirent test below. */
+				if (ext4_rec_len_from_disk(de->rec_len,
+					sb->s_blocksize) < EXT4_DIR_REC_LEN(1))
+					break;
+				i += ext4_rec_len_from_disk(de->rec_len,
+							    sb->s_blocksize);
+			}
+			offset = i;
+			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
+				| offset;
+			filp->f_version = inode->i_version;
+		}
+
+		while (!error && filp->f_pos < inode->i_size
+		       && offset < sb->s_blocksize) {
+			de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
+			if (ext4_check_dir_entry(inode, filp, de,
+						 bh, offset)) {
+				/*
+				 * On error, skip the f_pos to the next block
+				 */
+				filp->f_pos = (filp->f_pos |
+						(sb->s_blocksize - 1)) + 1;
+				brelse(bh);
+				ret = stored;
+				goto out;
+			}
+			offset += ext4_rec_len_from_disk(de->rec_len,
+					sb->s_blocksize);
+			if (le32_to_cpu(de->inode)) {
+				/* We might block in the next section
+				 * if the data destination is
+				 * currently swapped out.  So, use a
+				 * version stamp to detect whether or
+				 * not the directory has been modified
+				 * during the copy operation.
+				 */
+				u64 version = filp->f_version;
+
+				error = filldir(dirent, de->name,
+						de->name_len,
+						filp->f_pos,
+						le32_to_cpu(de->inode),
+						get_dtype(sb, de->file_type));
+				if (error)
+					break;
+				if (version != filp->f_version)
+					goto revalidate;
+				stored++;
+			}
+			filp->f_pos += ext4_rec_len_from_disk(de->rec_len,
+						sb->s_blocksize);
+		}
+		offset = 0;
+		brelse(bh);
+	}
+out:
+	return ret;
+}
+
+/*
+ * These functions convert from the major/minor hash to an f_pos
+ * value.
+ *
+ * Currently we only use major hash numer.  This is unfortunate, but
+ * on 32-bit machines, the same VFS interface is used for lseek and
+ * llseek, so if we use the 64 bit offset, then the 32-bit versions of
+ * lseek/telldir/seekdir will blow out spectacularly, and from within
+ * the ext2 low-level routine, we don't know if we're being called by
+ * a 64-bit version of the system call or the 32-bit version of the
+ * system call.  Worse yet, NFSv2 only allows for a 32-bit readdir
+ * cookie.  Sigh.
+ */
+#define hash2pos(major, minor)	(major >> 1)
+#define pos2maj_hash(pos)	((pos << 1) & 0xffffffff)
+#define pos2min_hash(pos)	(0)
+
+/*
+ * This structure holds the nodes of the red-black tree used to store
+ * the directory entry in hash order.
+ */
+struct fname {
+	__u32		hash;
+	__u32		minor_hash;
+	struct rb_node	rb_hash;
+	struct fname	*next;
+	__u32		inode;
+	__u8		name_len;
+	__u8		file_type;
+	char		name[0];
+};
+
+/*
+ * This functoin implements a non-recursive way of freeing all of the
+ * nodes in the red-black tree.
+ */
+static void free_rb_tree_fname(struct rb_root *root)
+{
+	struct rb_node	*n = root->rb_node;
+	struct rb_node	*parent;
+	struct fname	*fname;
+
+	while (n) {
+		/* Do the node's children first */
+		if (n->rb_left) {
+			n = n->rb_left;
+			continue;
+		}
+		if (n->rb_right) {
+			n = n->rb_right;
+			continue;
+		}
+		/*
+		 * The node has no children; free it, and then zero
+		 * out parent's link to it.  Finally go to the
+		 * beginning of the loop and try to free the parent
+		 * node.
+		 */
+		parent = rb_parent(n);
+		fname = rb_entry(n, struct fname, rb_hash);
+		while (fname) {
+			struct fname *old = fname;
+			fname = fname->next;
+			kfree(old);
+		}
+		if (!parent)
+			*root = RB_ROOT;
+		else if (parent->rb_left == n)
+			parent->rb_left = NULL;
+		else if (parent->rb_right == n)
+			parent->rb_right = NULL;
+		n = parent;
+	}
+}
+
+
+static struct dir_private_info *ext4_htree_create_dir_info(loff_t pos)
+{
+	struct dir_private_info *p;
+
+	p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
+	if (!p)
+		return NULL;
+	p->curr_hash = pos2maj_hash(pos);
+	p->curr_minor_hash = pos2min_hash(pos);
+	return p;
+}
+
+void ext4_htree_free_dir_info(struct dir_private_info *p)
+{
+	free_rb_tree_fname(&p->root);
+	kfree(p);
+}
+
+/*
+ * Given a directory entry, enter it into the fname rb tree.
+ */
+int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
+			     __u32 minor_hash,
+			     struct ext4_dir_entry_2 *dirent)
+{
+	struct rb_node **p, *parent = NULL;
+	struct fname *fname, *new_fn;
+	struct dir_private_info *info;
+	int len;
+
+	info = dir_file->private_data;
+	p = &info->root.rb_node;
+
+	/* Create and allocate the fname structure */
+	len = sizeof(struct fname) + dirent->name_len + 1;
+	new_fn = kzalloc(len, GFP_KERNEL);
+	if (!new_fn)
+		return -ENOMEM;
+	new_fn->hash = hash;
+	new_fn->minor_hash = minor_hash;
+	new_fn->inode = le32_to_cpu(dirent->inode);
+	new_fn->name_len = dirent->name_len;
+	new_fn->file_type = dirent->file_type;
+	memcpy(new_fn->name, dirent->name, dirent->name_len);
+	new_fn->name[dirent->name_len] = 0;
+
+	while (*p) {
+		parent = *p;
+		fname = rb_entry(parent, struct fname, rb_hash);
+
+		/*
+		 * If the hash and minor hash match up, then we put
+		 * them on a linked list.  This rarely happens...
+		 */
+		if ((new_fn->hash == fname->hash) &&
+		    (new_fn->minor_hash == fname->minor_hash)) {
+			new_fn->next = fname->next;
+			fname->next = new_fn;
+			return 0;
+		}
+
+		if (new_fn->hash < fname->hash)
+			p = &(*p)->rb_left;
+		else if (new_fn->hash > fname->hash)
+			p = &(*p)->rb_right;
+		else if (new_fn->minor_hash < fname->minor_hash)
+			p = &(*p)->rb_left;
+		else /* if (new_fn->minor_hash > fname->minor_hash) */
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new_fn->rb_hash, parent, p);
+	rb_insert_color(&new_fn->rb_hash, &info->root);
+	return 0;
+}
+
+
+
+/*
+ * This is a helper function for ext4_dx_readdir.  It calls filldir
+ * for all entres on the fname linked list.  (Normally there is only
+ * one entry on the linked list, unless there are 62 bit hash collisions.)
+ */
+static int call_filldir(struct file *filp, void *dirent,
+			filldir_t filldir, struct fname *fname)
+{
+	struct dir_private_info *info = filp->private_data;
+	loff_t	curr_pos;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct super_block *sb;
+	int error;
+
+	sb = inode->i_sb;
+
+	if (!fname) {
+		printk(KERN_ERR "EXT4-fs: call_filldir: called with "
+		       "null fname?!?\n");
+		return 0;
+	}
+	curr_pos = hash2pos(fname->hash, fname->minor_hash);
+	while (fname) {
+		error = filldir(dirent, fname->name,
+				fname->name_len, curr_pos,
+				fname->inode,
+				get_dtype(sb, fname->file_type));
+		if (error) {
+			filp->f_pos = curr_pos;
+			info->extra_fname = fname;
+			return error;
+		}
+		fname = fname->next;
+	}
+	return 0;
+}
+
+static int ext4_dx_readdir(struct file *filp,
+			 void *dirent, filldir_t filldir)
+{
+	struct dir_private_info *info = filp->private_data;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct fname *fname;
+	int	ret;
+
+	if (!info) {
+		info = ext4_htree_create_dir_info(filp->f_pos);
+		if (!info)
+			return -ENOMEM;
+		filp->private_data = info;
+	}
+
+	if (filp->f_pos == EXT4_HTREE_EOF)
+		return 0;	/* EOF */
+
+	/* Some one has messed with f_pos; reset the world */
+	if (info->last_pos != filp->f_pos) {
+		free_rb_tree_fname(&info->root);
+		info->curr_node = NULL;
+		info->extra_fname = NULL;
+		info->curr_hash = pos2maj_hash(filp->f_pos);
+		info->curr_minor_hash = pos2min_hash(filp->f_pos);
+	}
+
+	/*
+	 * If there are any leftover names on the hash collision
+	 * chain, return them first.
+	 */
+	if (info->extra_fname) {
+		if (call_filldir(filp, dirent, filldir, info->extra_fname))
+			goto finished;
+		info->extra_fname = NULL;
+		goto next_node;
+	} else if (!info->curr_node)
+		info->curr_node = rb_first(&info->root);
+
+	while (1) {
+		/*
+		 * Fill the rbtree if we have no more entries,
+		 * or the inode has changed since we last read in the
+		 * cached entries.
+		 */
+		if ((!info->curr_node) ||
+		    (filp->f_version != inode->i_version)) {
+			info->curr_node = NULL;
+			free_rb_tree_fname(&info->root);
+			filp->f_version = inode->i_version;
+			ret = ext4_htree_fill_tree(filp, info->curr_hash,
+						   info->curr_minor_hash,
+						   &info->next_hash);
+			if (ret < 0)
+				return ret;
+			if (ret == 0) {
+				filp->f_pos = EXT4_HTREE_EOF;
+				break;
+			}
+			info->curr_node = rb_first(&info->root);
+		}
+
+		fname = rb_entry(info->curr_node, struct fname, rb_hash);
+		info->curr_hash = fname->hash;
+		info->curr_minor_hash = fname->minor_hash;
+		if (call_filldir(filp, dirent, filldir, fname))
+			break;
+	next_node:
+		info->curr_node = rb_next(info->curr_node);
+		if (info->curr_node) {
+			fname = rb_entry(info->curr_node, struct fname,
+					 rb_hash);
+			info->curr_hash = fname->hash;
+			info->curr_minor_hash = fname->minor_hash;
+		} else {
+			if (info->next_hash == ~0) {
+				filp->f_pos = EXT4_HTREE_EOF;
+				break;
+			}
+			info->curr_hash = info->next_hash;
+			info->curr_minor_hash = 0;
+		}
+	}
+finished:
+	info->last_pos = filp->f_pos;
+	return 0;
+}
+
+static int ext4_release_dir(struct inode *inode, struct file *filp)
+{
+	if (filp->private_data)
+		ext4_htree_free_dir_info(filp->private_data);
+
+	return 0;
+}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
new file mode 100644
index 00000000..1a34c1c8
--- /dev/null
+++ b/fs/ext4/ext4.h
@@ -0,0 +1,2236 @@
+/*
+ *  ext4.h
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/include/linux/minix_fs.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#ifndef _EXT4_H
+#define _EXT4_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include <linux/magic.h>
+#include <linux/jbd2.h>
+#include <linux/quota.h>
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#ifdef __KERNEL__
+#include <linux/compat.h>
+#endif
+
+/*
+ * The fourth extended filesystem constants/structures
+ */
+
+/*
+ * Define EXT4FS_DEBUG to produce debug messages
+ */
+#undef EXT4FS_DEBUG
+
+/*
+ * Debug code
+ */
+#ifdef EXT4FS_DEBUG
+#define ext4_debug(f, a...)						\
+	do {								\
+		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
+			__FILE__, __LINE__, __func__);			\
+		printk(KERN_DEBUG f, ## a);				\
+	} while (0)
+#else
+#define ext4_debug(f, a...)	do {} while (0)
+#endif
+
+#define EXT4_ERROR_INODE(inode, fmt, a...) \
+	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)
+
+#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...)			\
+	ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)
+
+#define EXT4_ERROR_FILE(file, block, fmt, a...)				\
+	ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
+
+/* data type for block offset of block group */
+typedef int ext4_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long long ext4_fsblk_t;
+
+/* data type for file logical block number */
+typedef __u32 ext4_lblk_t;
+
+/* data type for block group number */
+typedef unsigned int ext4_group_t;
+
+/*
+ * Flags used in mballoc's allocation_context flags field.
+ *
+ * Also used to show what's going on for debugging purposes when the
+ * flag field is exported via the traceport interface
+ */
+
+/* prefer goal again. length */
+#define EXT4_MB_HINT_MERGE		0x0001
+/* blocks already reserved */
+#define EXT4_MB_HINT_RESERVED		0x0002
+/* metadata is being allocated */
+#define EXT4_MB_HINT_METADATA		0x0004
+/* first blocks in the file */
+#define EXT4_MB_HINT_FIRST		0x0008
+/* search for the best chunk */
+#define EXT4_MB_HINT_BEST		0x0010
+/* data is being allocated */
+#define EXT4_MB_HINT_DATA		0x0020
+/* don't preallocate (for tails) */
+#define EXT4_MB_HINT_NOPREALLOC		0x0040
+/* allocate for locality group */
+#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
+/* allocate goal blocks or none */
+#define EXT4_MB_HINT_GOAL_ONLY		0x0100
+/* goal is meaningful */
+#define EXT4_MB_HINT_TRY_GOAL		0x0200
+/* blocks already pre-reserved by delayed allocation */
+#define EXT4_MB_DELALLOC_RESERVED	0x0400
+/* We are doing stream allocation */
+#define EXT4_MB_STREAM_ALLOC		0x0800
+/* Use reserved root blocks if needed */
+#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
+
+struct ext4_allocation_request {
+	/* target inode for block we're allocating */
+	struct inode *inode;
+	/* how many blocks we want to allocate */
+	unsigned int len;
+	/* logical block in target inode */
+	ext4_lblk_t logical;
+	/* the closest logical allocated block to the left */
+	ext4_lblk_t lleft;
+	/* the closest logical allocated block to the right */
+	ext4_lblk_t lright;
+	/* phys. target (a hint) */
+	ext4_fsblk_t goal;
+	/* phys. block for the closest logical allocated block to the left */
+	ext4_fsblk_t pleft;
+	/* phys. block for the closest logical allocated block to the right */
+	ext4_fsblk_t pright;
+	/* flags. see above EXT4_MB_HINT_* */
+	unsigned int flags;
+};
+
+/*
+ * Logical to physical block mapping, used by ext4_map_blocks()
+ *
+ * This structure is used to pass requests into ext4_map_blocks() as
+ * well as to store the information returned by ext4_map_blocks().  It
+ * takes less room on the stack than a struct buffer_head.
+ */
+#define EXT4_MAP_NEW		(1 << BH_New)
+#define EXT4_MAP_MAPPED		(1 << BH_Mapped)
+#define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
+#define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
+#define EXT4_MAP_UNINIT		(1 << BH_Uninit)
+#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
+				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+				 EXT4_MAP_UNINIT)
+
+struct ext4_map_blocks {
+	ext4_fsblk_t m_pblk;
+	ext4_lblk_t m_lblk;
+	unsigned int m_len;
+	unsigned int m_flags;
+};
+
+/*
+ * For delayed allocation tracking
+ */
+struct mpage_da_data {
+	struct inode *inode;
+	sector_t b_blocknr;		/* start block number of extent */
+	size_t b_size;			/* size of extent */
+	unsigned long b_state;		/* state of the extent */
+	unsigned long first_page, next_page;	/* extent of pages */
+	struct writeback_control *wbc;
+	int io_done;
+	int pages_written;
+	int retval;
+};
+
+/*
+ * Flags for ext4_io_end->flags
+ */
+#define	EXT4_IO_END_UNWRITTEN	0x0001
+#define EXT4_IO_END_ERROR	0x0002
+#define EXT4_IO_END_QUEUED	0x0004
+
+struct ext4_io_page {
+	struct page	*p_page;
+	atomic_t	p_count;
+};
+
+#define MAX_IO_PAGES 128
+
+typedef struct ext4_io_end {
+	struct list_head	list;		/* per-file finished IO list */
+	struct inode		*inode;		/* file being written to */
+	unsigned int		flag;		/* unwritten or not */
+	struct page		*page;		/* page struct for buffer write */
+	loff_t			offset;		/* offset in the file */
+	ssize_t			size;		/* size of the extent */
+	struct work_struct	work;		/* data work queue */
+	struct kiocb		*iocb;		/* iocb struct for AIO */
+	int			result;		/* error value for AIO */
+	int			num_io_pages;
+	struct ext4_io_page	*pages[MAX_IO_PAGES];
+} ext4_io_end_t;
+
+struct ext4_io_submit {
+	int			io_op;
+	struct bio		*io_bio;
+	ext4_io_end_t		*io_end;
+	struct ext4_io_page	*io_page;
+	sector_t		io_next_block;
+};
+
+/*
+ * Special inodes numbers
+ */
+#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
+#define EXT4_ROOT_INO		 2	/* Root inode */
+#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
+#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
+#define EXT4_BOOT_LOADER_INO	 5	/* Boot loader inode */
+#define EXT4_UNDEL_DIR_INO	 6	/* Undelete directory inode */
+#define EXT4_RESIZE_INO		 7	/* Reserved group descriptors inode */
+#define EXT4_JOURNAL_INO	 8	/* Journal inode */
+
+/* First non-reserved inode for old ext4 filesystems */
+#define EXT4_GOOD_OLD_FIRST_INO	11
+
+/*
+ * Maximal count of links to a file
+ */
+#define EXT4_LINK_MAX		65000
+
+/*
+ * Macro-instructions used to manage several block sizes
+ */
+#define EXT4_MIN_BLOCK_SIZE		1024
+#define	EXT4_MAX_BLOCK_SIZE		65536
+#define EXT4_MIN_BLOCK_LOG_SIZE		10
+#define EXT4_MAX_BLOCK_LOG_SIZE		16
+#ifdef __KERNEL__
+# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
+#else
+# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
+#endif
+#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
+#ifdef __KERNEL__
+# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
+#else
+# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
+#endif
+#ifdef __KERNEL__
+#define	EXT4_ADDR_PER_BLOCK_BITS(s)	(EXT4_SB(s)->s_addr_per_block_bits)
+#define EXT4_INODE_SIZE(s)		(EXT4_SB(s)->s_inode_size)
+#define EXT4_FIRST_INO(s)		(EXT4_SB(s)->s_first_ino)
+#else
+#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
+				 EXT4_GOOD_OLD_INODE_SIZE : \
+				 (s)->s_inode_size)
+#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
+				 EXT4_GOOD_OLD_FIRST_INO : \
+				 (s)->s_first_ino)
+#endif
+#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
+
+/*
+ * Structure of a blocks group descriptor
+ */
+struct ext4_group_desc
+{
+	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
+	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
+	__le32	bg_inode_table_lo;	/* Inodes table block */
+	__le16	bg_free_blocks_count_lo;/* Free blocks count */
+	__le16	bg_free_inodes_count_lo;/* Free inodes count */
+	__le16	bg_used_dirs_count_lo;	/* Directories count */
+	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
+	__u32	bg_reserved[2];		/* Likely block/inode bitmap checksum */
+	__le16  bg_itable_unused_lo;	/* Unused inodes count */
+	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
+	__le32	bg_block_bitmap_hi;	/* Blocks bitmap block MSB */
+	__le32	bg_inode_bitmap_hi;	/* Inodes bitmap block MSB */
+	__le32	bg_inode_table_hi;	/* Inodes table block MSB */
+	__le16	bg_free_blocks_count_hi;/* Free blocks count MSB */
+	__le16	bg_free_inodes_count_hi;/* Free inodes count MSB */
+	__le16	bg_used_dirs_count_hi;	/* Directories count MSB */
+	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
+	__u32	bg_reserved2[3];
+};
+
+/*
+ * Structure of a flex block group info
+ */
+
+struct flex_groups {
+	atomic_t free_inodes;
+	atomic_t free_blocks;
+	atomic_t used_dirs;
+};
+
+#define EXT4_BG_INODE_UNINIT	0x0001 /* Inode table/bitmap not in use */
+#define EXT4_BG_BLOCK_UNINIT	0x0002 /* Block bitmap not in use */
+#define EXT4_BG_INODE_ZEROED	0x0004 /* On-disk itable initialized to zero */
+
+/*
+ * Macro-instructions used to manage group descriptors
+ */
+#define EXT4_MIN_DESC_SIZE		32
+#define EXT4_MIN_DESC_SIZE_64BIT	64
+#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
+#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
+#ifdef __KERNEL__
+# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
+# define EXT4_DESC_PER_BLOCK(s)		(EXT4_SB(s)->s_desc_per_block)
+# define EXT4_INODES_PER_GROUP(s)	(EXT4_SB(s)->s_inodes_per_group)
+# define EXT4_DESC_PER_BLOCK_BITS(s)	(EXT4_SB(s)->s_desc_per_block_bits)
+#else
+# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
+# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
+# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
+#endif
+
+/*
+ * Constants relative to the data blocks
+ */
+#define	EXT4_NDIR_BLOCKS		12
+#define	EXT4_IND_BLOCK			EXT4_NDIR_BLOCKS
+#define	EXT4_DIND_BLOCK			(EXT4_IND_BLOCK + 1)
+#define	EXT4_TIND_BLOCK			(EXT4_DIND_BLOCK + 1)
+#define	EXT4_N_BLOCKS			(EXT4_TIND_BLOCK + 1)
+
+/*
+ * Inode flags
+ */
+#define	EXT4_SECRM_FL			0x00000001 /* Secure deletion */
+#define	EXT4_UNRM_FL			0x00000002 /* Undelete */
+#define	EXT4_COMPR_FL			0x00000004 /* Compress file */
+#define EXT4_SYNC_FL			0x00000008 /* Synchronous updates */
+#define EXT4_IMMUTABLE_FL		0x00000010 /* Immutable file */
+#define EXT4_APPEND_FL			0x00000020 /* writes to file may only append */
+#define EXT4_NODUMP_FL			0x00000040 /* do not dump file */
+#define EXT4_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define EXT4_DIRTY_FL			0x00000100
+#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
+#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
+#define EXT4_ECOMPR_FL			0x00000800 /* Compression error */
+/* End compression flags --- maybe not all used */
+#define EXT4_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define EXT4_IMAGIC_FL			0x00002000 /* AFS directory */
+#define EXT4_JOURNAL_DATA_FL		0x00004000 /* file data should be journaled */
+#define EXT4_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define EXT4_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define EXT4_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
+#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
+#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
+#define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
+#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
+
+#define EXT4_FL_USER_VISIBLE		0x004BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE		0x004B80FF /* User modifiable flags */
+
+/* Flags that should be inherited by new inodes from their parent. */
+#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
+			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
+			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & EXT4_REG_FLMASK;
+	else
+		return flags & EXT4_OTHER_FLMASK;
+}
+
+/*
+ * Inode flags used for atomic set/get
+ */
+enum {
+	EXT4_INODE_SECRM	= 0,	/* Secure deletion */
+	EXT4_INODE_UNRM		= 1,	/* Undelete */
+	EXT4_INODE_COMPR	= 2,	/* Compress file */
+	EXT4_INODE_SYNC		= 3,	/* Synchronous updates */
+	EXT4_INODE_IMMUTABLE	= 4,	/* Immutable file */
+	EXT4_INODE_APPEND	= 5,	/* writes to file may only append */
+	EXT4_INODE_NODUMP	= 6,	/* do not dump file */
+	EXT4_INODE_NOATIME	= 7,	/* do not update atime */
+/* Reserved for compression usage... */
+	EXT4_INODE_DIRTY	= 8,
+	EXT4_INODE_COMPRBLK	= 9,	/* One or more compressed clusters */
+	EXT4_INODE_NOCOMPR	= 10,	/* Don't compress */
+	EXT4_INODE_ECOMPR	= 11,	/* Compression error */
+/* End compression flags --- maybe not all used */
+	EXT4_INODE_INDEX	= 12,	/* hash-indexed directory */
+	EXT4_INODE_IMAGIC	= 13,	/* AFS directory */
+	EXT4_INODE_JOURNAL_DATA	= 14,	/* file data should be journaled */
+	EXT4_INODE_NOTAIL	= 15,	/* file tail should not be merged */
+	EXT4_INODE_DIRSYNC	= 16,	/* dirsync behaviour (directories only) */
+	EXT4_INODE_TOPDIR	= 17,	/* Top of directory hierarchies*/
+	EXT4_INODE_HUGE_FILE	= 18,	/* Set to each huge file */
+	EXT4_INODE_EXTENTS	= 19,	/* Inode uses extents */
+	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
+	EXT4_INODE_EOFBLOCKS	= 22,	/* Blocks allocated beyond EOF */
+	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
+};
+
+#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
+#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
+	printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
+		EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }
+
+/*
+ * Since it's pretty easy to mix up bit numbers and hex values, and we
+ * can't do a compile-time test for ENUM values, we use a run-time
+ * test to make sure that EXT4_XXX_FL is consistent with respect to
+ * EXT4_INODE_XXX.  If all is well the printk and BUG_ON will all drop
+ * out so it won't cost any extra space in the compiled kernel image.
+ * But it's important that these values are the same, since we are
+ * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL
+ * must be consistent with the values of FS_XXX_FL defined in
+ * include/linux/fs.h and the on-disk values found in ext2, ext3, and
+ * ext4 filesystems, and of course the values defined in e2fsprogs.
+ *
+ * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
+ */
+static inline void ext4_check_flag_values(void)
+{
+	CHECK_FLAG_VALUE(SECRM);
+	CHECK_FLAG_VALUE(UNRM);
+	CHECK_FLAG_VALUE(COMPR);
+	CHECK_FLAG_VALUE(SYNC);
+	CHECK_FLAG_VALUE(IMMUTABLE);
+	CHECK_FLAG_VALUE(APPEND);
+	CHECK_FLAG_VALUE(NODUMP);
+	CHECK_FLAG_VALUE(NOATIME);
+	CHECK_FLAG_VALUE(DIRTY);
+	CHECK_FLAG_VALUE(COMPRBLK);
+	CHECK_FLAG_VALUE(NOCOMPR);
+	CHECK_FLAG_VALUE(ECOMPR);
+	CHECK_FLAG_VALUE(INDEX);
+	CHECK_FLAG_VALUE(IMAGIC);
+	CHECK_FLAG_VALUE(JOURNAL_DATA);
+	CHECK_FLAG_VALUE(NOTAIL);
+	CHECK_FLAG_VALUE(DIRSYNC);
+	CHECK_FLAG_VALUE(TOPDIR);
+	CHECK_FLAG_VALUE(HUGE_FILE);
+	CHECK_FLAG_VALUE(EXTENTS);
+	CHECK_FLAG_VALUE(EA_INODE);
+	CHECK_FLAG_VALUE(EOFBLOCKS);
+	CHECK_FLAG_VALUE(RESERVED);
+}
+
+/* Used to pass group descriptor data when online resize is done */
+struct ext4_new_group_input {
+	__u32 group;		/* Group number for this data */
+	__u64 block_bitmap;	/* Absolute block number of block bitmap */
+	__u64 inode_bitmap;	/* Absolute block number of inode bitmap */
+	__u64 inode_table;	/* Absolute block number of inode table start */
+	__u32 blocks_count;	/* Total number of blocks in this group */
+	__u16 reserved_blocks;	/* Number of reserved blocks in this group */
+	__u16 unused;
+};
+
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+struct compat_ext4_new_group_input {
+	u32 group;
+	compat_u64 block_bitmap;
+	compat_u64 inode_bitmap;
+	compat_u64 inode_table;
+	u32 blocks_count;
+	u16 reserved_blocks;
+	u16 unused;
+};
+#endif
+
+/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
+struct ext4_new_group_data {
+	__u32 group;
+	__u64 block_bitmap;
+	__u64 inode_bitmap;
+	__u64 inode_table;
+	__u32 blocks_count;
+	__u16 reserved_blocks;
+	__u16 unused;
+	__u32 free_blocks_count;
+};
+
+/*
+ * Flags used by ext4_map_blocks()
+ */
+	/* Allocate any needed blocks and/or convert an unitialized
+	   extent to be an initialized ext4 */
+#define EXT4_GET_BLOCKS_CREATE			0x0001
+	/* Request the creation of an unitialized extent */
+#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
+						 EXT4_GET_BLOCKS_CREATE)
+	/* Caller is from the delayed allocation writeout path,
+	   so set the magic i_delalloc_reserve_flag after taking the
+	   inode allocation semaphore for */
+#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
+	/* caller is from the direct IO path, request to creation of an
+	unitialized extents if not allocated, split the uninitialized
+	extent if blocks has been preallocated already*/
+#define EXT4_GET_BLOCKS_PRE_IO			0x0008
+#define EXT4_GET_BLOCKS_CONVERT			0x0010
+#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
+					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+	/* Convert extent to initialized after IO complete */
+#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
+					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+	/* Punch out blocks of an extent */
+#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT		0x0020
+	/* Don't normalize allocation size (used for fallocate) */
+#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
+
+/*
+ * Flags used by ext4_free_blocks
+ */
+#define EXT4_FREE_BLOCKS_METADATA	0x0001
+#define EXT4_FREE_BLOCKS_FORGET		0x0002
+#define EXT4_FREE_BLOCKS_VALIDATED	0x0004
+#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
+
+/*
+ * ioctl commands
+ */
+#define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT4_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
+#define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
+#define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
+#define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
+#ifdef CONFIG_JBD2_DEBUG
+#define EXT4_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
+#endif
+#define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
+#define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
+#define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
+#define EXT4_IOC_GROUP_ADD		_IOW('f', 8, struct ext4_new_group_input)
+#define EXT4_IOC_MIGRATE		_IO('f', 9)
+ /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
+ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
+#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
+#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
+
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT4_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT4_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT4_IOC32_GETVERSION		_IOR('f', 3, int)
+#define EXT4_IOC32_SETVERSION		_IOW('f', 4, int)
+#define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
+#define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
+#define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
+#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
+#ifdef CONFIG_JBD2_DEBUG
+#define EXT4_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
+#endif
+#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
+#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
+#endif
+
+/* Max physical block we can address w/o extents */
+#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF
+
+/*
+ * Structure of an inode on the disk
+ */
+struct ext4_inode {
+	__le16	i_mode;		/* File mode */
+	__le16	i_uid;		/* Low 16 bits of Owner Uid */
+	__le32	i_size_lo;	/* Size in bytes */
+	__le32	i_atime;	/* Access time */
+	__le32	i_ctime;	/* Inode Change time */
+	__le32	i_mtime;	/* Modification time */
+	__le32	i_dtime;	/* Deletion Time */
+	__le16	i_gid;		/* Low 16 bits of Group Id */
+	__le16	i_links_count;	/* Links count */
+	__le32	i_blocks_lo;	/* Blocks count */
+	__le32	i_flags;	/* File flags */
+	union {
+		struct {
+			__le32  l_i_version;
+		} linux1;
+		struct {
+			__u32  h_i_translator;
+		} hurd1;
+		struct {
+			__u32  m_i_reserved1;
+		} masix1;
+	} osd1;				/* OS dependent 1 */
+	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
+	__le32	i_generation;	/* File version (for NFS) */
+	__le32	i_file_acl_lo;	/* File ACL */
+	__le32	i_size_high;
+	__le32	i_obso_faddr;	/* Obsoleted fragment address */
+	union {
+		struct {
+			__le16	l_i_blocks_high; /* were l_i_reserved1 */
+			__le16	l_i_file_acl_high;
+			__le16	l_i_uid_high;	/* these 2 fields */
+			__le16	l_i_gid_high;	/* were reserved2[0] */
+			__u32	l_i_reserved2;
+		} linux2;
+		struct {
+			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
+			__u16	h_i_mode_high;
+			__u16	h_i_uid_high;
+			__u16	h_i_gid_high;
+			__u32	h_i_author;
+		} hurd2;
+		struct {
+			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
+			__le16	m_i_file_acl_high;
+			__u32	m_i_reserved2[2];
+		} masix2;
+	} osd2;				/* OS dependent 2 */
+	__le16	i_extra_isize;
+	__le16	i_pad1;
+	__le32  i_ctime_extra;  /* extra Change time      (nsec << 2 | epoch) */
+	__le32  i_mtime_extra;  /* extra Modification time(nsec << 2 | epoch) */
+	__le32  i_atime_extra;  /* extra Access time      (nsec << 2 | epoch) */
+	__le32  i_crtime;       /* File Creation time */
+	__le32  i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
+	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
+};
+
+struct move_extent {
+	__u32 reserved;		/* should be zero */
+	__u32 donor_fd;		/* donor file descriptor */
+	__u64 orig_start;	/* logical start offset in block for orig */
+	__u64 donor_start;	/* logical start offset in block for donor */
+	__u64 len;		/* block length to be moved */
+	__u64 moved_len;	/* moved block length */
+};
+
+#define EXT4_EPOCH_BITS 2
+#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
+#define EXT4_NSEC_MASK  (~0UL << EXT4_EPOCH_BITS)
+
+/*
+ * Extended fields will fit into an inode if the filesystem was formatted
+ * with large inodes (-I 256 or larger) and there are not currently any EAs
+ * consuming all of the available space. For new inodes we always reserve
+ * enough space for the kernel's known extended fields, but for inodes
+ * created with an old kernel this might not have been the case. None of
+ * the extended inode fields is critical for correct filesystem operation.
+ * This macro checks if a certain field fits in the inode. Note that
+ * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize
+ */
+#define EXT4_FITS_IN_INODE(ext4_inode, einode, field)	\
+	((offsetof(typeof(*ext4_inode), field) +	\
+	  sizeof((ext4_inode)->field))			\
+	<= (EXT4_GOOD_OLD_INODE_SIZE +			\
+	    (einode)->i_extra_isize))			\
+
+static inline __le32 ext4_encode_extra_time(struct timespec *time)
+{
+       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
+			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
+                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
+}
+
+static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
+{
+       if (sizeof(time->tv_sec) > 4)
+	       time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
+			       << 32;
+       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+}
+
+#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)			       \
+do {									       \
+	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	       \
+	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
+		(raw_inode)->xtime ## _extra =				       \
+				ext4_encode_extra_time(&(inode)->xtime);       \
+} while (0)
+
+#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode)			       \
+do {									       \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
+		(raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec);      \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
+		(raw_inode)->xtime ## _extra =				       \
+				ext4_encode_extra_time(&(einode)->xtime);      \
+} while (0)
+
+#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode)			       \
+do {									       \
+	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);       \
+	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
+		ext4_decode_extra_time(&(inode)->xtime,			       \
+				       raw_inode->xtime ## _extra);	       \
+	else								       \
+		(inode)->xtime.tv_nsec = 0;				       \
+} while (0)
+
+#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode)			       \
+do {									       \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
+		(einode)->xtime.tv_sec = 				       \
+			(signed)le32_to_cpu((raw_inode)->xtime);	       \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
+		ext4_decode_extra_time(&(einode)->xtime,		       \
+				       raw_inode->xtime ## _extra);	       \
+	else								       \
+		(einode)->xtime.tv_nsec = 0;				       \
+} while (0)
+
+#define i_disk_version osd1.linux1.l_i_version
+
+#if defined(__KERNEL__) || defined(__linux__)
+#define i_reserved1	osd1.linux1.l_i_reserved1
+#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
+#define i_blocks_high	osd2.linux2.l_i_blocks_high
+#define i_uid_low	i_uid
+#define i_gid_low	i_gid
+#define i_uid_high	osd2.linux2.l_i_uid_high
+#define i_gid_high	osd2.linux2.l_i_gid_high
+#define i_reserved2	osd2.linux2.l_i_reserved2
+
+#elif defined(__GNU__)
+
+#define i_translator	osd1.hurd1.h_i_translator
+#define i_uid_high	osd2.hurd2.h_i_uid_high
+#define i_gid_high	osd2.hurd2.h_i_gid_high
+#define i_author	osd2.hurd2.h_i_author
+
+#elif defined(__masix__)
+
+#define i_reserved1	osd1.masix1.m_i_reserved1
+#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
+#define i_reserved2	osd2.masix2.m_i_reserved2
+
+#endif /* defined(__KERNEL__) || defined(__linux__) */
+
+/*
+ * storage for cached extent
+ * If ec_len == 0, then the cache is invalid.
+ * If ec_start == 0, then the cache represents a gap (null mapping)
+ */
+struct ext4_ext_cache {
+	ext4_fsblk_t	ec_start;
+	ext4_lblk_t	ec_block;
+	__u32		ec_len; /* must be 32bit to return holes */
+};
+
+/*
+ * fourth extended file system inode data in memory
+ */
+struct ext4_inode_info {
+	__le32	i_data[15];	/* unconverted */
+	__u32	i_dtime;
+	ext4_fsblk_t	i_file_acl;
+
+	/*
+	 * i_block_group is the number of the block group which contains
+	 * this file's inode.  Constant across the lifetime of the inode,
+	 * it is ued for making block allocation decisions - we try to
+	 * place a file's data blocks near its inode block, and new inodes
+	 * near to their parent directory's inode.
+	 */
+	ext4_group_t	i_block_group;
+	ext4_lblk_t	i_dir_start_lookup;
+#if (BITS_PER_LONG < 64)
+	unsigned long	i_state_flags;		/* Dynamic state flags */
+#endif
+	unsigned long	i_flags;
+
+#ifdef CONFIG_EXT4_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_mutex even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+
+	struct list_head i_orphan;	/* unlinked but open inodes */
+
+	/*
+	 * i_disksize keeps track of what the inode size is ON DISK, not
+	 * in memory.  During truncate, i_size is set to the new size by
+	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
+	 * set i_disksize to 0 until the truncate is actually under way.
+	 *
+	 * The intent is that i_disksize always represents the blocks which
+	 * are used by this file.  This allows recovery to restart truncate
+	 * on orphans if we crash during truncate.  We actually write i_disksize
+	 * into the on-disk inode when writing inodes out, instead of i_size.
+	 *
+	 * The only time when i_disksize and i_size may be different is when
+	 * a truncate is in progress.  The only things which change i_disksize
+	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
+	 */
+	loff_t	i_disksize;
+
+	/*
+	 * i_data_sem is for serialising ext4_truncate() against
+	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
+	 * data tree are chopped off during truncate. We can't do that in
+	 * ext4 because whenever we perform intermediate commits during
+	 * truncate, the inode and all the metadata blocks *must* be in a
+	 * consistent state which allows truncation of the orphans to restart
+	 * during recovery.  Hence we must fix the get_block-vs-truncate race
+	 * by other means, so we have i_data_sem.
+	 */
+	struct rw_semaphore i_data_sem;
+	struct inode vfs_inode;
+	struct jbd2_inode *jinode;
+
+	struct ext4_ext_cache i_cached_extent;
+	/*
+	 * File creation time. Its function is same as that of
+	 * struct timespec i_{a,c,m}time in the generic inode.
+	 */
+	struct timespec i_crtime;
+
+	/* mballoc */
+	struct list_head i_prealloc_list;
+	spinlock_t i_prealloc_lock;
+
+	/* ialloc */
+	ext4_group_t	i_last_alloc_group;
+
+	/* allocation reservation info for delalloc */
+	unsigned int i_reserved_data_blocks;
+	unsigned int i_reserved_meta_blocks;
+	unsigned int i_allocated_meta_blocks;
+	ext4_lblk_t i_da_metadata_calc_last_lblock;
+	int i_da_metadata_calc_len;
+
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
+#ifdef CONFIG_QUOTA
+	/* quota space reservation, managed internally by quota code */
+	qsize_t i_reserved_quota;
+#endif
+
+	/* completed IOs that might need unwritten extents handling */
+	struct list_head i_completed_io_list;
+	spinlock_t i_completed_io_lock;
+	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
+	/* current io_end structure for async DIO write*/
+	ext4_io_end_t *cur_aio_dio;
+	atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
+
+	spinlock_t i_block_reservation_lock;
+
+	/*
+	 * Transactions that contain inode's metadata needed to complete
+	 * fsync and fdatasync, respectively.
+	 */
+	tid_t i_sync_tid;
+	tid_t i_datasync_tid;
+};
+
+/*
+ * File system states
+ */
+#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
+#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
+#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
+
+/*
+ * Misc. filesystem flags
+ */
+#define EXT2_FLAGS_SIGNED_HASH		0x0001  /* Signed dirhash in use */
+#define EXT2_FLAGS_UNSIGNED_HASH	0x0002  /* Unsigned dirhash in use */
+#define EXT2_FLAGS_TEST_FILESYS		0x0004	/* to test development code */
+
+/*
+ * Mount flags
+ */
+#define EXT4_MOUNT_OLDALLOC		0x00002  /* Don't use the new Orlov allocator */
+#define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
+#define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */
+#define EXT4_MOUNT_ERRORS_CONT		0x00010	/* Continue on errors */
+#define EXT4_MOUNT_ERRORS_RO		0x00020	/* Remount fs ro on errors */
+#define EXT4_MOUNT_ERRORS_PANIC		0x00040	/* Panic on errors */
+#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
+#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
+#define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
+#define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
+#define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */
+#define EXT4_MOUNT_WRITEBACK_DATA	0x00C00	/* No data ordering */
+#define EXT4_MOUNT_UPDATE_JOURNAL	0x01000	/* Update the journal format */
+#define EXT4_MOUNT_NO_UID32		0x02000  /* Disable 32-bit UIDs */
+#define EXT4_MOUNT_XATTR_USER		0x04000	/* Extended user attributes */
+#define EXT4_MOUNT_POSIX_ACL		0x08000	/* POSIX Access Control Lists */
+#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
+#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
+#define EXT4_MOUNT_QUOTA		0x80000 /* Some quota option set */
+#define EXT4_MOUNT_USRQUOTA		0x100000 /* "old" user quota */
+#define EXT4_MOUNT_GRPQUOTA		0x200000 /* "old" group quota */
+#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
+#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
+#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
+#define EXT4_MOUNT_MBLK_IO_SUBMIT	0x4000000 /* multi-block io submits */
+#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
+#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
+#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
+#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
+#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
+
+#define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
+						~EXT4_MOUNT_##opt
+#define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
+						EXT4_MOUNT_##opt
+#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
+					 EXT4_MOUNT_##opt)
+
+#define clear_opt2(sb, opt)		EXT4_SB(sb)->s_mount_opt2 &= \
+						~EXT4_MOUNT2_##opt
+#define set_opt2(sb, opt)		EXT4_SB(sb)->s_mount_opt2 |= \
+						EXT4_MOUNT2_##opt
+#define test_opt2(sb, opt)		(EXT4_SB(sb)->s_mount_opt2 & \
+					 EXT4_MOUNT2_##opt)
+
+#define ext4_set_bit			__test_and_set_bit_le
+#define ext4_set_bit_atomic		ext2_set_bit_atomic
+#define ext4_clear_bit			__test_and_clear_bit_le
+#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
+#define ext4_test_bit			test_bit_le
+#define ext4_find_first_zero_bit	find_first_zero_bit_le
+#define ext4_find_next_zero_bit		find_next_zero_bit_le
+#define ext4_find_next_bit		find_next_bit_le
+
+/*
+ * Maximal mount counts between two filesystem checks
+ */
+#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
+#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
+
+/*
+ * Behaviour when detecting errors
+ */
+#define EXT4_ERRORS_CONTINUE		1	/* Continue execution */
+#define EXT4_ERRORS_RO			2	/* Remount fs read-only */
+#define EXT4_ERRORS_PANIC		3	/* Panic */
+#define EXT4_ERRORS_DEFAULT		EXT4_ERRORS_CONTINUE
+
+/*
+ * Structure of the super block
+ */
+struct ext4_super_block {
+/*00*/	__le32	s_inodes_count;		/* Inodes count */
+	__le32	s_blocks_count_lo;	/* Blocks count */
+	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
+	__le32	s_free_blocks_count_lo;	/* Free blocks count */
+/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
+	__le32	s_first_data_block;	/* First Data Block */
+	__le32	s_log_block_size;	/* Block size */
+	__le32	s_obso_log_frag_size;	/* Obsoleted fragment size */
+/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
+	__le32	s_obso_frags_per_group;	/* Obsoleted fragments per group */
+	__le32	s_inodes_per_group;	/* # Inodes per group */
+	__le32	s_mtime;		/* Mount time */
+/*30*/	__le32	s_wtime;		/* Write time */
+	__le16	s_mnt_count;		/* Mount count */
+	__le16	s_max_mnt_count;	/* Maximal mount count */
+	__le16	s_magic;		/* Magic signature */
+	__le16	s_state;		/* File system state */
+	__le16	s_errors;		/* Behaviour when detecting errors */
+	__le16	s_minor_rev_level;	/* minor revision level */
+/*40*/	__le32	s_lastcheck;		/* time of last check */
+	__le32	s_checkinterval;	/* max. time between checks */
+	__le32	s_creator_os;		/* OS */
+	__le32	s_rev_level;		/* Revision level */
+/*50*/	__le16	s_def_resuid;		/* Default uid for reserved blocks */
+	__le16	s_def_resgid;		/* Default gid for reserved blocks */
+	/*
+	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
+	 *
+	 * Note: the difference between the compatible feature set and
+	 * the incompatible feature set is that if there is a bit set
+	 * in the incompatible feature set that the kernel doesn't
+	 * know about, it should refuse to mount the filesystem.
+	 *
+	 * e2fsck's requirements are more strict; if it doesn't know
+	 * about a feature in either the compatible or incompatible
+	 * feature set, it must abort and not try to meddle with
+	 * things it doesn't understand...
+	 */
+	__le32	s_first_ino;		/* First non-reserved inode */
+	__le16  s_inode_size;		/* size of inode structure */
+	__le16	s_block_group_nr;	/* block group # of this superblock */
+	__le32	s_feature_compat;	/* compatible feature set */
+/*60*/	__le32	s_feature_incompat;	/* incompatible feature set */
+	__le32	s_feature_ro_compat;	/* readonly-compatible feature set */
+/*68*/	__u8	s_uuid[16];		/* 128-bit uuid for volume */
+/*78*/	char	s_volume_name[16];	/* volume name */
+/*88*/	char	s_last_mounted[64];	/* directory where last mounted */
+/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
+	/*
+	 * Performance hints.  Directory preallocation should only
+	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
+	 */
+	__u8	s_prealloc_blocks;	/* Nr of blocks to try to preallocate*/
+	__u8	s_prealloc_dir_blocks;	/* Nr to preallocate for dirs */
+	__le16	s_reserved_gdt_blocks;	/* Per group desc for online growth */
+	/*
+	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
+	 */
+/*D0*/	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
+/*E0*/	__le32	s_journal_inum;		/* inode number of journal file */
+	__le32	s_journal_dev;		/* device number of journal file */
+	__le32	s_last_orphan;		/* start of list of inodes to delete */
+	__le32	s_hash_seed[4];		/* HTREE hash seed */
+	__u8	s_def_hash_version;	/* Default hash version to use */
+	__u8	s_jnl_backup_type;
+	__le16  s_desc_size;		/* size of group descriptor */
+/*100*/	__le32	s_default_mount_opts;
+	__le32	s_first_meta_bg;	/* First metablock block group */
+	__le32	s_mkfs_time;		/* When the filesystem was created */
+	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
+	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+/*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
+	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
+	__le32	s_free_blocks_count_hi;	/* Free blocks count */
+	__le16	s_min_extra_isize;	/* All inodes have at least # bytes */
+	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
+	__le32	s_flags;		/* Miscellaneous flags */
+	__le16  s_raid_stride;		/* RAID stride */
+	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
+	__le64  s_mmp_block;            /* Block for multi-mount protection */
+	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
+	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
+	__u8	s_reserved_char_pad;
+	__le16  s_reserved_pad;
+	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
+	__le32	s_snapshot_inum;	/* Inode number of active snapshot */
+	__le32	s_snapshot_id;		/* sequential ID of active snapshot */
+	__le64	s_snapshot_r_blocks_count; /* reserved blocks for active
+					      snapshot's future use */
+	__le32	s_snapshot_list;	/* inode number of the head of the
+					   on-disk snapshot list */
+#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
+	__le32	s_error_count;		/* number of fs errors */
+	__le32	s_first_error_time;	/* first time an error happened */
+	__le32	s_first_error_ino;	/* inode involved in first error */
+	__le64	s_first_error_block;	/* block involved of first error */
+	__u8	s_first_error_func[32];	/* function where the error happened */
+	__le32	s_first_error_line;	/* line number where error happened */
+	__le32	s_last_error_time;	/* most recent time of an error */
+	__le32	s_last_error_ino;	/* inode involved in last error */
+	__le32	s_last_error_line;	/* line number where error happened */
+	__le64	s_last_error_block;	/* block involved of last error */
+	__u8	s_last_error_func[32];	/* function where the error happened */
+#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
+	__u8	s_mount_opts[64];
+	__le32	s_reserved[112];        /* Padding to the end of the block */
+};
+
+#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
+
+#ifdef __KERNEL__
+
+/*
+ * run-time mount flags
+ */
+#define EXT4_MF_MNTDIR_SAMPLED	0x0001
+#define EXT4_MF_FS_ABORTED	0x0002	/* Fatal error detected */
+
+/*
+ * fourth extended-fs super-block data in memory
+ */
+struct ext4_sb_info {
+	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	ext4_group_t s_groups_count;	/* Number of groups in the fs */
+	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head **s_group_desc;
+	unsigned int s_mount_opt;
+	unsigned int s_mount_opt2;
+	unsigned int s_mount_flags;
+	ext4_fsblk_t s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	unsigned int s_inode_readahead_blks;
+	unsigned int s_inode_goal;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	u32 s_hash_seed[4];
+	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct percpu_counter s_dirtyblocks_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	struct proc_dir_entry *s_proc;
+	struct kobject s_kobj;
+	struct completion s_kobj_unregister;
+
+	/* Journaling */
+	struct journal_s *s_journal;
+	struct list_head s_orphan;
+	struct mutex s_orphan_lock;
+	struct mutex s_resize_lock;
+	unsigned long s_commit_interval;
+	u32 s_max_batch_time;
+	u32 s_min_batch_time;
+	struct block_device *journal_bdev;
+#ifdef CONFIG_JBD2_DEBUG
+	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
+	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
+#endif
+#ifdef CONFIG_QUOTA
+	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	int s_jquota_fmt;			/* Format of quota to use */
+#endif
+	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
+	struct rb_root system_blks;
+
+#ifdef EXTENTS_STATS
+	/* ext4 extents stats */
+	unsigned long s_ext_min;
+	unsigned long s_ext_max;
+	unsigned long s_depth_max;
+	spinlock_t s_ext_stats_lock;
+	unsigned long s_ext_blocks;
+	unsigned long s_ext_extents;
+#endif
+	/* ext4 extent cache stats */
+	unsigned long extent_cache_hits;
+	unsigned long extent_cache_misses;
+
+	/* for buddy allocator */
+	struct ext4_group_info ***s_group_info;
+	struct inode *s_buddy_cache;
+	spinlock_t s_md_lock;
+	unsigned short *s_mb_offsets;
+	unsigned int *s_mb_maxs;
+
+	/* tunables */
+	unsigned long s_stripe;
+	unsigned int s_mb_stream_request;
+	unsigned int s_mb_max_to_scan;
+	unsigned int s_mb_min_to_scan;
+	unsigned int s_mb_stats;
+	unsigned int s_mb_order2_reqs;
+	unsigned int s_mb_group_prealloc;
+	unsigned int s_max_writeback_mb_bump;
+	/* where last allocation was done - for stream allocation */
+	unsigned long s_mb_last_group;
+	unsigned long s_mb_last_start;
+
+	/* stats for buddy allocator */
+	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
+	atomic_t s_bal_success;	/* we found long enough chunks */
+	atomic_t s_bal_allocated;	/* in blocks */
+	atomic_t s_bal_ex_scanned;	/* total extents scanned */
+	atomic_t s_bal_goals;	/* goal hits */
+	atomic_t s_bal_breaks;	/* too long searches */
+	atomic_t s_bal_2orders;	/* 2^order hits */
+	spinlock_t s_bal_lock;
+	unsigned long s_mb_buddies_generated;
+	unsigned long long s_mb_generation_time;
+	atomic_t s_mb_lost_chunks;
+	atomic_t s_mb_preallocated;
+	atomic_t s_mb_discarded;
+	atomic_t s_lock_busy;
+
+	/* locality groups */
+	struct ext4_locality_group __percpu *s_locality_groups;
+
+	/* for write statistics */
+	unsigned long s_sectors_written_start;
+	u64 s_kbytes_written;
+
+	unsigned int s_log_groups_per_flex;
+	struct flex_groups *s_flex_groups;
+
+	/* workqueue for dio unwritten */
+	struct workqueue_struct *dio_unwritten_wq;
+
+	/* timer for periodic error stats printing */
+	struct timer_list s_err_report;
+
+	/* Lazy inode table initialization info */
+	struct ext4_li_request *s_li_request;
+	/* Wait multiplier for lazy initialization thread */
+	unsigned int s_li_wait_mult;
+
+	/* Kernel thread for multiple mount protection */
+	struct task_struct *s_mmp_tsk;
+};
+
+static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
+{
+	return container_of(inode, struct ext4_inode_info, vfs_inode);
+}
+
+static inline struct timespec ext4_current_time(struct inode *inode)
+{
+	return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
+		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
+}
+
+static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
+{
+	return ino == EXT4_ROOT_INO ||
+		ino == EXT4_JOURNAL_INO ||
+		ino == EXT4_RESIZE_INO ||
+		(ino >= EXT4_FIRST_INO(sb) &&
+		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
+}
+
+/*
+ * Inode dynamic state flags
+ */
+enum {
+	EXT4_STATE_JDATA,		/* journaled data exists */
+	EXT4_STATE_NEW,			/* inode is newly created */
+	EXT4_STATE_XATTR,		/* has in-inode xattrs */
+	EXT4_STATE_NO_EXPAND,		/* No space for expansion */
+	EXT4_STATE_DA_ALLOC_CLOSE,	/* Alloc DA blks on close */
+	EXT4_STATE_EXT_MIGRATE,		/* Inode is migrating */
+	EXT4_STATE_DIO_UNWRITTEN,	/* need convert on dio done*/
+	EXT4_STATE_NEWENTRY,		/* File just added to dir */
+	EXT4_STATE_DELALLOC_RESERVED,	/* blks already reserved for delalloc */
+};
+
+#define EXT4_INODE_BIT_FNS(name, field, offset)				\
+static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
+{									\
+	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
+}									\
+static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
+{									\
+	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
+}									\
+static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
+{									\
+	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
+}
+
+EXT4_INODE_BIT_FNS(flag, flags, 0)
+#if (BITS_PER_LONG < 64)
+EXT4_INODE_BIT_FNS(state, state_flags, 0)
+
+static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
+{
+	(ei)->i_state_flags = 0;
+}
+#else
+EXT4_INODE_BIT_FNS(state, flags, 32)
+
+static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
+{
+	/* We depend on the fact that callers will set i_flags */
+}
+#endif
+#else
+/* Assume that user mode programs are passing in an ext4fs superblock, not
+ * a kernel struct super_block.  This will allow us to call the feature-test
+ * macros from user land. */
+#define EXT4_SB(sb)	(sb)
+#endif
+
+#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
+
+/*
+ * Codes for operating systems
+ */
+#define EXT4_OS_LINUX		0
+#define EXT4_OS_HURD		1
+#define EXT4_OS_MASIX		2
+#define EXT4_OS_FREEBSD		3
+#define EXT4_OS_LITES		4
+
+/*
+ * Revision levels
+ */
+#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
+#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
+
+#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
+#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
+
+#define EXT4_GOOD_OLD_INODE_SIZE 128
+
+/*
+ * Feature set definitions
+ */
+
+#define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
+	((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
+#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
+	((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
+#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
+	((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
+#define EXT4_SET_COMPAT_FEATURE(sb,mask)			\
+	EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
+#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
+#define EXT4_SET_INCOMPAT_FEATURE(sb,mask)			\
+	EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
+#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask)			\
+	EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
+#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
+#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
+	EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
+
+#define EXT4_FEATURE_COMPAT_DIR_PREALLOC	0x0001
+#define EXT4_FEATURE_COMPAT_IMAGIC_INODES	0x0002
+#define EXT4_FEATURE_COMPAT_HAS_JOURNAL		0x0004
+#define EXT4_FEATURE_COMPAT_EXT_ATTR		0x0008
+#define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
+#define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
+
+#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
+#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
+#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
+#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
+#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
+#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
+#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
+#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
+
+#define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
+#define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
+#define EXT4_FEATURE_INCOMPAT_RECOVER		0x0004 /* Needs recovery */
+#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008 /* Journal device */
+#define EXT4_FEATURE_INCOMPAT_META_BG		0x0010
+#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
+#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
+#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
+#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
+#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
+#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
+
+#define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
+#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT4_FEATURE_INCOMPAT_META_BG)
+#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
+
+#define EXT3_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
+#define EXT3_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT4_FEATURE_INCOMPAT_RECOVER| \
+					 EXT4_FEATURE_INCOMPAT_META_BG)
+#define EXT3_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
+
+#define EXT4_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
+#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT4_FEATURE_INCOMPAT_RECOVER| \
+					 EXT4_FEATURE_INCOMPAT_META_BG| \
+					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
+					 EXT4_FEATURE_INCOMPAT_64BIT| \
+					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
+					 EXT4_FEATURE_INCOMPAT_MMP)
+#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
+					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
+					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
+					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
+					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
+
+/*
+ * Default values for user and/or group using reserved blocks
+ */
+#define	EXT4_DEF_RESUID		0
+#define	EXT4_DEF_RESGID		0
+
+#define EXT4_DEF_INODE_READAHEAD_BLKS	32
+
+/*
+ * Default mount options
+ */
+#define EXT4_DEFM_DEBUG		0x0001
+#define EXT4_DEFM_BSDGROUPS	0x0002
+#define EXT4_DEFM_XATTR_USER	0x0004
+#define EXT4_DEFM_ACL		0x0008
+#define EXT4_DEFM_UID16		0x0010
+#define EXT4_DEFM_JMODE		0x0060
+#define EXT4_DEFM_JMODE_DATA	0x0020
+#define EXT4_DEFM_JMODE_ORDERED	0x0040
+#define EXT4_DEFM_JMODE_WBACK	0x0060
+#define EXT4_DEFM_NOBARRIER	0x0100
+#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
+#define EXT4_DEFM_DISCARD	0x0400
+#define EXT4_DEFM_NODELALLOC	0x0800
+
+/*
+ * Default journal batch times
+ */
+#define EXT4_DEF_MIN_BATCH_TIME	0
+#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */
+
+/*
+ * Minimum number of groups in a flexgroup before we separate out
+ * directories into the first block group of a flexgroup
+ */
+#define EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME	4
+
+/*
+ * Structure of a directory entry
+ */
+#define EXT4_NAME_LEN 255
+
+struct ext4_dir_entry {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__le16	name_len;		/* Name length */
+	char	name[EXT4_NAME_LEN];	/* File name */
+};
+
+/*
+ * The new version of the directory entry.  Since EXT4 structures are
+ * stored in intel byte order, and the name_len field could never be
+ * bigger than 255 chars, it's safe to reclaim the extra byte for the
+ * file_type field.
+ */
+struct ext4_dir_entry_2 {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__u8	name_len;		/* Name length */
+	__u8	file_type;
+	char	name[EXT4_NAME_LEN];	/* File name */
+};
+
+/*
+ * Ext4 directory file types.  Only the low 3 bits are used.  The
+ * other bits are reserved for now.
+ */
+#define EXT4_FT_UNKNOWN		0
+#define EXT4_FT_REG_FILE	1
+#define EXT4_FT_DIR		2
+#define EXT4_FT_CHRDEV		3
+#define EXT4_FT_BLKDEV		4
+#define EXT4_FT_FIFO		5
+#define EXT4_FT_SOCK		6
+#define EXT4_FT_SYMLINK		7
+
+#define EXT4_FT_MAX		8
+
+/*
+ * EXT4_DIR_PAD defines the directory entries boundaries
+ *
+ * NOTE: It must be a multiple of 4
+ */
+#define EXT4_DIR_PAD			4
+#define EXT4_DIR_ROUND			(EXT4_DIR_PAD - 1)
+#define EXT4_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT4_DIR_ROUND) & \
+					 ~EXT4_DIR_ROUND)
+#define EXT4_MAX_REC_LEN		((1<<16)-1)
+
+/*
+ * If we ever get support for fs block sizes > page_size, we'll need
+ * to remove the #if statements in the next two functions...
+ */
+static inline unsigned int
+ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
+{
+	unsigned len = le16_to_cpu(dlen);
+
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len == EXT4_MAX_REC_LEN || len == 0)
+		return blocksize;
+	return (len & 65532) | ((len & 3) << 16);
+#else
+	return len;
+#endif
+}
+
+static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
+{
+	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
+		BUG();
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len < 65536)
+		return cpu_to_le16(len);
+	if (len == blocksize) {
+		if (blocksize == 65536)
+			return cpu_to_le16(EXT4_MAX_REC_LEN);
+		else
+			return cpu_to_le16(0);
+	}
+	return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
+#else
+	return cpu_to_le16(len);
+#endif
+}
+
+/*
+ * Hash Tree Directory indexing
+ * (c) Daniel Phillips, 2001
+ */
+
+#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
+				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
+		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
+#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
+#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
+
+/* Legal values for the dx_root hash_version field: */
+
+#define DX_HASH_LEGACY		0
+#define DX_HASH_HALF_MD4	1
+#define DX_HASH_TEA		2
+#define DX_HASH_LEGACY_UNSIGNED	3
+#define DX_HASH_HALF_MD4_UNSIGNED	4
+#define DX_HASH_TEA_UNSIGNED		5
+
+#ifdef __KERNEL__
+
+/* hash info structure used by the directory hash */
+struct dx_hash_info
+{
+	u32		hash;
+	u32		minor_hash;
+	int		hash_version;
+	u32		*seed;
+};
+
+#define EXT4_HTREE_EOF	0x7fffffff
+
+/*
+ * Control parameters used by ext4_htree_next_block
+ */
+#define HASH_NB_ALWAYS		1
+
+
+/*
+ * Describe an inode's exact location on disk and in memory
+ */
+struct ext4_iloc
+{
+	struct buffer_head *bh;
+	unsigned long offset;
+	ext4_group_t block_group;
+};
+
+static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
+{
+	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
+}
+
+/*
+ * This structure is stuffed into the struct file's private_data field
+ * for directories.  It is where we put information so that we can do
+ * readdir operations in hash tree order.
+ */
+struct dir_private_info {
+	struct rb_root	root;
+	struct rb_node	*curr_node;
+	struct fname	*extra_fname;
+	loff_t		last_pos;
+	__u32		curr_hash;
+	__u32		curr_minor_hash;
+	__u32		next_hash;
+};
+
+/* calculate the first block number of the group */
+static inline ext4_fsblk_t
+ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
+{
+	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
+		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+}
+
+/*
+ * Special error return code only used by dx_probe() and its callers.
+ */
+#define ERR_BAD_DX_DIR	-75000
+
+void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
+			ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
+
+/*
+ * Timeout and state flag for lazy initialization inode thread.
+ */
+#define EXT4_DEF_LI_WAIT_MULT			10
+#define EXT4_DEF_LI_MAX_START_DELAY		5
+#define EXT4_LAZYINIT_QUIT			0x0001
+#define EXT4_LAZYINIT_RUNNING			0x0002
+
+/*
+ * Lazy inode table initialization info
+ */
+struct ext4_lazy_init {
+	unsigned long		li_state;
+	struct list_head	li_request_list;
+	struct mutex		li_list_mtx;
+};
+
+struct ext4_li_request {
+	struct super_block	*lr_super;
+	struct ext4_sb_info	*lr_sbi;
+	ext4_group_t		lr_next_group;
+	struct list_head	lr_request;
+	unsigned long		lr_next_sched;
+	unsigned long		lr_timeout;
+};
+
+struct ext4_features {
+	struct kobject f_kobj;
+	struct completion f_kobj_unregister;
+};
+
+/*
+ * This structure will be used for multiple mount protection. It will be
+ * written into the block number saved in the s_mmp_block field in the
+ * superblock. Programs that check MMP should assume that if
+ * SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe
+ * to use the filesystem, regardless of how old the timestamp is.
+ */
+#define EXT4_MMP_MAGIC     0x004D4D50U /* ASCII for MMP */
+#define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */
+#define EXT4_MMP_SEQ_FSCK  0xE24D4D50U /* mmp_seq value when being fscked */
+#define EXT4_MMP_SEQ_MAX   0xE24D4D4FU /* maximum valid mmp_seq value */
+
+struct mmp_struct {
+	__le32	mmp_magic;		/* Magic number for MMP */
+	__le32	mmp_seq;		/* Sequence no. updated periodically */
+
+	/*
+	 * mmp_time, mmp_nodename & mmp_bdevname are only used for information
+	 * purposes and do not affect the correctness of the algorithm
+	 */
+	__le64	mmp_time;		/* Time last updated */
+	char	mmp_nodename[64];	/* Node which last updated MMP block */
+	char	mmp_bdevname[32];	/* Bdev which last updated MMP block */
+
+	/*
+	 * mmp_check_interval is used to verify if the MMP block has been
+	 * updated on the block device. The value is updated based on the
+	 * maximum time to write the MMP block during an update cycle.
+	 */
+	__le16	mmp_check_interval;
+
+	__le16	mmp_pad1;
+	__le32	mmp_pad2[227];
+};
+
+/* arguments passed to the mmp thread */
+struct mmpd_data {
+	struct buffer_head *bh; /* bh from initial read_mmp_block() */
+	struct super_block *sb;  /* super block of the fs */
+};
+
+/*
+ * Check interval multiplier
+ * The MMP block is written every update interval and initially checked every
+ * update interval x the multiplier (the value is then adapted based on the
+ * write latency). The reason is that writes can be delayed under load and we
+ * don't want readers to incorrectly assume that the filesystem is no longer
+ * in use.
+ */
+#define EXT4_MMP_CHECK_MULT		2UL
+
+/*
+ * Minimum interval for MMP checking in seconds.
+ */
+#define EXT4_MMP_MIN_CHECK_INTERVAL	5UL
+
+/*
+ * Maximum interval for MMP checking in seconds.
+ */
+#define EXT4_MMP_MAX_CHECK_INTERVAL	300UL
+
+/*
+ * Function prototypes
+ */
+
+/*
+ * Ok, these declarations are also in <linux/kernel.h> but none of the
+ * ext4 source programs needs to include it so they are duplicated here.
+ */
+# define NORET_TYPE	/**/
+# define ATTRIB_NORET	__attribute__((noreturn))
+# define NORET_AND	noreturn,
+
+/* bitmap.c */
+extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+
+/* balloc.c */
+extern unsigned int ext4_block_group(struct super_block *sb,
+			ext4_fsblk_t blocknr);
+extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
+			ext4_fsblk_t blocknr);
+extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
+extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
+			ext4_group_t group);
+extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
+					 ext4_fsblk_t goal,
+					 unsigned int flags,
+					 unsigned long *count,
+					 int *errp);
+extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+				  s64 nblocks, unsigned int flags);
+extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern void ext4_check_blocks_bitmap(struct super_block *);
+extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
+						    ext4_group_t block_group,
+						    struct buffer_head ** bh);
+extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
+struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+				      ext4_group_t block_group);
+extern unsigned ext4_init_block_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
+				       struct ext4_group_desc *desc);
+#define ext4_free_blocks_after_init(sb, group, desc)			\
+		ext4_init_block_bitmap(sb, NULL, group, desc)
+
+/* dir.c */
+extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
+				  struct file *,
+				  struct ext4_dir_entry_2 *,
+				  struct buffer_head *, unsigned int);
+#define ext4_check_dir_entry(dir, filp, de, bh, offset)			\
+	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
+					(de), (bh), (offset)))
+extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
+				    __u32 minor_hash,
+				    struct ext4_dir_entry_2 *dirent);
+extern void ext4_htree_free_dir_info(struct dir_private_info *p);
+
+/* fsync.c */
+extern int ext4_sync_file(struct file *, int);
+extern int ext4_flush_completed_IO(struct inode *);
+
+/* hash.c */
+extern int ext4fs_dirhash(const char *name, int len, struct
+			  dx_hash_info *hinfo);
+
+/* ialloc.c */
+extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
+				    const struct qstr *qstr, __u32 goal);
+extern void ext4_free_inode(handle_t *, struct inode *);
+extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
+extern unsigned long ext4_count_free_inodes(struct super_block *);
+extern unsigned long ext4_count_dirs(struct super_block *);
+extern void ext4_check_inodes_bitmap(struct super_block *);
+extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern int ext4_init_inode_table(struct super_block *sb,
+				 ext4_group_t group, int barrier);
+
+/* mballoc.c */
+extern long ext4_mb_stats;
+extern long ext4_mb_max_to_scan;
+extern int ext4_mb_init(struct super_block *, int);
+extern int ext4_mb_release(struct super_block *);
+extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
+				struct ext4_allocation_request *, int *);
+extern int ext4_mb_reserve_blocks(struct super_block *, int);
+extern void ext4_discard_preallocations(struct inode *);
+extern int __init ext4_init_mballoc(void);
+extern void ext4_exit_mballoc(void);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
+			     struct buffer_head *bh, ext4_fsblk_t block,
+			     unsigned long count, int flags);
+extern int ext4_mb_add_groupinfo(struct super_block *sb,
+		ext4_group_t i, struct ext4_group_desc *desc);
+extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+				ext4_fsblk_t block, unsigned long count);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+
+/* inode.c */
+struct buffer_head *ext4_getblk(handle_t *, struct inode *,
+						ext4_lblk_t, int, int *);
+struct buffer_head *ext4_bread(handle_t *, struct inode *,
+						ext4_lblk_t, int, int *);
+int ext4_get_block(struct inode *inode, sector_t iblock,
+				struct buffer_head *bh_result, int create);
+
+extern struct inode *ext4_iget(struct super_block *, unsigned long);
+extern int  ext4_write_inode(struct inode *, struct writeback_control *);
+extern int  ext4_setattr(struct dentry *, struct iattr *);
+extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
+				struct kstat *stat);
+extern void ext4_evict_inode(struct inode *);
+extern void ext4_clear_inode(struct inode *);
+extern int  ext4_sync_inode(handle_t *, struct inode *);
+extern void ext4_dirty_inode(struct inode *, int);
+extern int ext4_change_inode_journal_flag(struct inode *, int);
+extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_can_truncate(struct inode *inode);
+extern void ext4_truncate(struct inode *);
+extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
+extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
+extern void ext4_set_inode_flags(struct inode *);
+extern void ext4_get_inode_flags(struct ext4_inode_info *);
+extern int ext4_alloc_da_blocks(struct inode *inode);
+extern void ext4_set_aops(struct inode *inode);
+extern int ext4_writepage_trans_blocks(struct inode *);
+extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
+extern int ext4_block_truncate_page(handle_t *handle,
+		struct address_space *mapping, loff_t from);
+extern int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length);
+extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern qsize_t *ext4_get_reserved_space(struct inode *inode);
+extern void ext4_da_update_reserve_space(struct inode *inode,
+					int used, int quota_claim);
+/* ioctl.c */
+extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
+extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
+
+/* migrate.c */
+extern int ext4_ext_migrate(struct inode *);
+
+/* namei.c */
+extern int ext4_orphan_add(handle_t *, struct inode *);
+extern int ext4_orphan_del(handle_t *, struct inode *);
+extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
+				__u32 start_minor_hash, __u32 *next_hash);
+
+/* resize.c */
+extern int ext4_group_add(struct super_block *sb,
+				struct ext4_new_group_data *input);
+extern int ext4_group_extend(struct super_block *sb,
+				struct ext4_super_block *es,
+				ext4_fsblk_t n_blocks_count);
+
+/* super.c */
+extern void __ext4_error(struct super_block *, const char *, unsigned int,
+			 const char *, ...)
+	__attribute__ ((format (printf, 4, 5)));
+#define ext4_error(sb, message...)	__ext4_error(sb, __func__,	\
+						     __LINE__, ## message)
+extern void ext4_error_inode(struct inode *, const char *, unsigned int,
+			     ext4_fsblk_t, const char *, ...)
+	__attribute__ ((format (printf, 5, 6)));
+extern void ext4_error_file(struct file *, const char *, unsigned int,
+			    ext4_fsblk_t, const char *, ...)
+	__attribute__ ((format (printf, 5, 6)));
+extern void __ext4_std_error(struct super_block *, const char *,
+			     unsigned int, int);
+extern void __ext4_abort(struct super_block *, const char *, unsigned int,
+		       const char *, ...)
+	__attribute__ ((format (printf, 4, 5)));
+#define ext4_abort(sb, message...)	__ext4_abort(sb, __func__, \
+						       __LINE__, ## message)
+extern void __ext4_warning(struct super_block *, const char *, unsigned int,
+			  const char *, ...)
+	__attribute__ ((format (printf, 4, 5)));
+#define ext4_warning(sb, message...)	__ext4_warning(sb, __func__, \
+						       __LINE__, ## message)
+extern void ext4_msg(struct super_block *, const char *, const char *, ...)
+	__attribute__ ((format (printf, 3, 4)));
+extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
+			   const char *, unsigned int, const char *);
+#define dump_mmp_msg(sb, mmp, msg)	__dump_mmp_msg(sb, mmp, __func__, \
+						       __LINE__, msg)
+extern void __ext4_grp_locked_error(const char *, unsigned int, \
+				    struct super_block *, ext4_group_t, \
+				    unsigned long, ext4_fsblk_t, \
+				    const char *, ...)
+	__attribute__ ((format (printf, 7, 8)));
+#define ext4_grp_locked_error(sb, grp, message...) \
+	__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
+extern void ext4_update_dynamic_rev(struct super_block *sb);
+extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
+					__u32 compat);
+extern int ext4_update_rocompat_feature(handle_t *handle,
+					struct super_block *sb,	__u32 rocompat);
+extern int ext4_update_incompat_feature(handle_t *handle,
+					struct super_block *sb,	__u32 incompat);
+extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
+				      struct ext4_group_desc *bg);
+extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
+				      struct ext4_group_desc *bg);
+extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
+				     struct ext4_group_desc *bg);
+extern __u32 ext4_free_blks_count(struct super_block *sb,
+				struct ext4_group_desc *bg);
+extern __u32 ext4_free_inodes_count(struct super_block *sb,
+				 struct ext4_group_desc *bg);
+extern __u32 ext4_used_dirs_count(struct super_block *sb,
+				struct ext4_group_desc *bg);
+extern __u32 ext4_itable_unused_count(struct super_block *sb,
+				   struct ext4_group_desc *bg);
+extern void ext4_block_bitmap_set(struct super_block *sb,
+				  struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_inode_bitmap_set(struct super_block *sb,
+				  struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_inode_table_set(struct super_block *sb,
+				 struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_free_blks_set(struct super_block *sb,
+			       struct ext4_group_desc *bg, __u32 count);
+extern void ext4_free_inodes_set(struct super_block *sb,
+				struct ext4_group_desc *bg, __u32 count);
+extern void ext4_used_dirs_set(struct super_block *sb,
+				struct ext4_group_desc *bg, __u32 count);
+extern void ext4_itable_unused_set(struct super_block *sb,
+				   struct ext4_group_desc *bg, __u32 count);
+extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
+				   struct ext4_group_desc *gdp);
+extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
+				       struct ext4_group_desc *gdp);
+
+static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
+{
+	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
+		le32_to_cpu(es->s_blocks_count_lo);
+}
+
+static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
+{
+	return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
+		le32_to_cpu(es->s_r_blocks_count_lo);
+}
+
+static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
+{
+	return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
+		le32_to_cpu(es->s_free_blocks_count_lo);
+}
+
+static inline void ext4_blocks_count_set(struct ext4_super_block *es,
+					 ext4_fsblk_t blk)
+{
+	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
+	es->s_blocks_count_hi = cpu_to_le32(blk >> 32);
+}
+
+static inline void ext4_free_blocks_count_set(struct ext4_super_block *es,
+					      ext4_fsblk_t blk)
+{
+	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
+	es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32);
+}
+
+static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
+					   ext4_fsblk_t blk)
+{
+	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
+	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
+}
+
+static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
+{
+	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
+		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
+			le32_to_cpu(raw_inode->i_size_lo);
+	else
+		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
+}
+
+static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
+{
+	raw_inode->i_size_lo = cpu_to_le32(i_size);
+	raw_inode->i_size_high = cpu_to_le32(i_size >> 32);
+}
+
+static inline
+struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
+					    ext4_group_t group)
+{
+	 struct ext4_group_info ***grp_info;
+	 long indexv, indexh;
+	 grp_info = EXT4_SB(sb)->s_group_info;
+	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
+	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
+	 return grp_info[indexv][indexh];
+}
+
+/*
+ * Reading s_groups_count requires using smp_rmb() afterwards.  See
+ * the locking protocol documented in the comments of ext4_group_add()
+ * in resize.c
+ */
+static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
+{
+	ext4_group_t	ngroups = EXT4_SB(sb)->s_groups_count;
+
+	smp_rmb();
+	return ngroups;
+}
+
+static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
+					     ext4_group_t block_group)
+{
+	return block_group >> sbi->s_log_groups_per_flex;
+}
+
+static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi)
+{
+	return 1 << sbi->s_log_groups_per_flex;
+}
+
+#define ext4_std_error(sb, errno)				\
+do {								\
+	if ((errno))						\
+		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
+} while (0)
+
+#ifdef CONFIG_SMP
+/* Each CPU can accumulate percpu_counter_batch blocks in their local
+ * counters. So we need to make sure we have free blocks more
+ * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
+ */
+#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
+#else
+#define EXT4_FREEBLOCKS_WATERMARK 0
+#endif
+
+static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+	/*
+	 * XXX: replace with spinlock if seen contended -bzzz
+	 */
+	down_write(&EXT4_I(inode)->i_data_sem);
+	if (newsize > EXT4_I(inode)->i_disksize)
+		EXT4_I(inode)->i_disksize = newsize;
+	up_write(&EXT4_I(inode)->i_data_sem);
+	return ;
+}
+
+struct ext4_group_info {
+	unsigned long   bb_state;
+	struct rb_root  bb_free_root;
+	ext4_grpblk_t	bb_first_free;	/* first free block */
+	ext4_grpblk_t	bb_free;	/* total free blocks */
+	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
+	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
+	struct          list_head bb_prealloc_list;
+#ifdef DOUBLE_CHECK
+	void            *bb_bitmap;
+#endif
+	struct rw_semaphore alloc_sem;
+	ext4_grpblk_t	bb_counters[];	/* Nr of free power-of-two-block
+					 * regions, index is order.
+					 * bb_counters[3] = 5 means
+					 * 5 free 8-block regions. */
+};
+
+#define EXT4_GROUP_INFO_NEED_INIT_BIT	0
+
+#define EXT4_MB_GRP_NEED_INIT(grp)	\
+	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+
+#define EXT4_MAX_CONTENTION		8
+#define EXT4_CONTENTION_THRESHOLD	2
+
+static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
+					      ext4_group_t group)
+{
+	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
+}
+
+/*
+ * Returns true if the filesystem is busy enough that attempts to
+ * access the block group locks has run into contention.
+ */
+static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi)
+{
+	return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD);
+}
+
+static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+{
+	spinlock_t *lock = ext4_group_lock_ptr(sb, group);
+	if (spin_trylock(lock))
+		/*
+		 * We're able to grab the lock right away, so drop the
+		 * lock contention counter.
+		 */
+		atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0);
+	else {
+		/*
+		 * The lock is busy, so bump the contention counter,
+		 * and then wait on the spin lock.
+		 */
+		atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1,
+				  EXT4_MAX_CONTENTION);
+		spin_lock(lock);
+	}
+}
+
+static inline void ext4_unlock_group(struct super_block *sb,
+					ext4_group_t group)
+{
+	spin_unlock(ext4_group_lock_ptr(sb, group));
+}
+
+static inline void ext4_mark_super_dirty(struct super_block *sb)
+{
+	if (EXT4_SB(sb)->s_journal == NULL)
+		sb->s_dirt =1;
+}
+
+/*
+ * Inodes and files operations
+ */
+
+/* dir.c */
+extern const struct file_operations ext4_dir_operations;
+
+/* file.c */
+extern const struct inode_operations ext4_file_inode_operations;
+extern const struct file_operations ext4_file_operations;
+extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
+
+/* namei.c */
+extern const struct inode_operations ext4_dir_inode_operations;
+extern const struct inode_operations ext4_special_inode_operations;
+extern struct dentry *ext4_get_parent(struct dentry *child);
+
+/* symlink.c */
+extern const struct inode_operations ext4_symlink_inode_operations;
+extern const struct inode_operations ext4_fast_symlink_inode_operations;
+
+/* block_validity */
+extern void ext4_release_system_zone(struct super_block *sb);
+extern int ext4_setup_system_zone(struct super_block *sb);
+extern int __init ext4_init_system_zone(void);
+extern void ext4_exit_system_zone(void);
+extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
+				 ext4_fsblk_t start_blk,
+				 unsigned int count);
+
+/* extents.c */
+extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
+extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
+extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
+				       int chunk);
+extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
+			       struct ext4_map_blocks *map, int flags);
+extern void ext4_ext_truncate(struct inode *);
+extern int ext4_ext_punch_hole(struct file *file, loff_t offset,
+				loff_t length);
+extern void ext4_ext_init(struct super_block *);
+extern void ext4_ext_release(struct super_block *);
+extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
+			  loff_t len);
+extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
+			  ssize_t len);
+extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
+			   struct ext4_map_blocks *map, int flags);
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+			__u64 start, __u64 len);
+/* move_extent.c */
+extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
+			     __u64 start_orig, __u64 start_donor,
+			     __u64 len, __u64 *moved_len);
+
+/* page-io.c */
+extern int __init ext4_init_pageio(void);
+extern void ext4_exit_pageio(void);
+extern void ext4_ioend_wait(struct inode *);
+extern void ext4_free_io_end(ext4_io_end_t *io);
+extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
+extern int ext4_end_io_nolock(ext4_io_end_t *io);
+extern void ext4_io_submit(struct ext4_io_submit *io);
+extern int ext4_bio_write_page(struct ext4_io_submit *io,
+			       struct page *page,
+			       int len,
+			       struct writeback_control *wbc);
+
+/* mmp.c */
+extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
+
+/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
+enum ext4_state_bits {
+	BH_Uninit	/* blocks are allocated but uninitialized on disk */
+	  = BH_JBDPrivateStart,
+};
+
+BUFFER_FNS(Uninit, uninit)
+TAS_BUFFER_FNS(Uninit, uninit)
+
+/*
+ * Add new method to test wether block and inode bitmaps are properly
+ * initialized. With uninit_bg reading the block from disk is not enough
+ * to mark the bitmap uptodate. We need to also zero-out the bitmap
+ */
+#define BH_BITMAP_UPTODATE BH_JBDPrivateStart
+
+static inline int bitmap_uptodate(struct buffer_head *bh)
+{
+	return (buffer_uptodate(bh) &&
+			test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
+}
+static inline void set_bitmap_uptodate(struct buffer_head *bh)
+{
+	set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
+}
+
+#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
+
+/* For ioend & aio unwritten conversion wait queues */
+#define EXT4_WQ_HASH_SZ		37
+#define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
+					    EXT4_WQ_HASH_SZ])
+#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
+					     EXT4_WQ_HASH_SZ])
+extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
+#endif	/* __KERNEL__ */
+
+#endif	/* _EXT4_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
new file mode 100644
index 00000000..095c36f3
--- /dev/null
+++ b/fs/ext4/ext4_extents.h
@@ -0,0 +1,294 @@
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ */
+
+#ifndef _EXT4_EXTENTS
+#define _EXT4_EXTENTS
+
+#include "ext4.h"
+
+/*
+ * With AGGRESSIVE_TEST defined, the capacity of index/leaf blocks
+ * becomes very small, so index split, in-depth growing and
+ * other hard changes happen much more often.
+ * This is for debug purposes only.
+ */
+#define AGGRESSIVE_TEST_
+
+/*
+ * With EXTENTS_STATS defined, the number of blocks and extents
+ * are collected in the truncate path. They'll be shown at
+ * umount time.
+ */
+#define EXTENTS_STATS__
+
+/*
+ * If CHECK_BINSEARCH is defined, then the results of the binary search
+ * will also be checked by linear search.
+ */
+#define CHECK_BINSEARCH__
+
+/*
+ * Turn on EXT_DEBUG to get lots of info about extents operations.
+ */
+#define EXT_DEBUG__
+#ifdef EXT_DEBUG
+#define ext_debug(a...)		printk(a)
+#else
+#define ext_debug(a...)
+#endif
+
+/*
+ * If EXT_STATS is defined then stats numbers are collected.
+ * These number will be displayed at umount time.
+ */
+#define EXT_STATS_
+
+
+/*
+ * ext4_inode has i_block array (60 bytes total).
+ * The first 12 bytes store ext4_extent_header;
+ * the remainder stores an array of ext4_extent.
+ */
+
+/*
+ * This is the extent on-disk structure.
+ * It's used at the bottom of the tree.
+ */
+struct ext4_extent {
+	__le32	ee_block;	/* first logical block extent covers */
+	__le16	ee_len;		/* number of blocks covered by extent */
+	__le16	ee_start_hi;	/* high 16 bits of physical block */
+	__le32	ee_start_lo;	/* low 32 bits of physical block */
+};
+
+/*
+ * This is index on-disk structure.
+ * It's used at all the levels except the bottom.
+ */
+struct ext4_extent_idx {
+	__le32	ei_block;	/* index covers logical blocks from 'block' */
+	__le32	ei_leaf_lo;	/* pointer to the physical block of the next *
+				 * level. leaf or next index could be there */
+	__le16	ei_leaf_hi;	/* high 16 bits of physical block */
+	__u16	ei_unused;
+};
+
+/*
+ * Each block (leaves and indexes), even inode-stored has header.
+ */
+struct ext4_extent_header {
+	__le16	eh_magic;	/* probably will support different formats */
+	__le16	eh_entries;	/* number of valid entries */
+	__le16	eh_max;		/* capacity of store in entries */
+	__le16	eh_depth;	/* has tree real underlying blocks? */
+	__le32	eh_generation;	/* generation of the tree */
+};
+
+#define EXT4_EXT_MAGIC		cpu_to_le16(0xf30a)
+
+/*
+ * Array of ext4_ext_path contains path to some extent.
+ * Creation/lookup routines use it for traversal/splitting/etc.
+ * Truncate uses it to simulate recursive walking.
+ */
+struct ext4_ext_path {
+	ext4_fsblk_t			p_block;
+	__u16				p_depth;
+	struct ext4_extent		*p_ext;
+	struct ext4_extent_idx		*p_idx;
+	struct ext4_extent_header	*p_hdr;
+	struct buffer_head		*p_bh;
+};
+
+/*
+ * structure for external API
+ */
+
+/*
+ * to be called by ext4_ext_walk_space()
+ * negative retcode - error
+ * positive retcode - signal for ext4_ext_walk_space(), see below
+ * callback must return valid extent (passed or newly created)
+ */
+typedef int (*ext_prepare_callback)(struct inode *, ext4_lblk_t,
+					struct ext4_ext_cache *,
+					struct ext4_extent *, void *);
+
+#define EXT_CONTINUE   0
+#define EXT_BREAK      1
+#define EXT_REPEAT     2
+
+/*
+ * Maximum number of logical blocks in a file; ext4_extent's ee_block is
+ * __le32.
+ */
+#define EXT_MAX_BLOCKS	0xffffffff
+
+/*
+ * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
+ * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
+ * MSB of ee_len field in the extent datastructure to signify if this
+ * particular extent is an initialized extent or an uninitialized (i.e.
+ * preallocated).
+ * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
+ * uninitialized extent.
+ * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
+ * uninitialized one. In other words, if MSB of ee_len is set, it is an
+ * uninitialized extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an uninitialized extent of zero length and
+ * thus we make it as a special case of initialized extent with 0x8000 length.
+ * This way we get better extent-to-group alignment for initialized extents.
+ * Hence, the maximum number of blocks we can have in an *initialized*
+ * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ */
+#define EXT_INIT_MAX_LEN	(1UL << 15)
+#define EXT_UNINIT_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
+
+
+#define EXT_FIRST_EXTENT(__hdr__) \
+	((struct ext4_extent *) (((char *) (__hdr__)) +		\
+				 sizeof(struct ext4_extent_header)))
+#define EXT_FIRST_INDEX(__hdr__) \
+	((struct ext4_extent_idx *) (((char *) (__hdr__)) +	\
+				     sizeof(struct ext4_extent_header)))
+#define EXT_HAS_FREE_INDEX(__path__) \
+	(le16_to_cpu((__path__)->p_hdr->eh_entries) \
+				     < le16_to_cpu((__path__)->p_hdr->eh_max))
+#define EXT_LAST_EXTENT(__hdr__) \
+	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_LAST_INDEX(__hdr__) \
+	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_MAX_EXTENT(__hdr__) \
+	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+#define EXT_MAX_INDEX(__hdr__) \
+	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+
+static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
+{
+	return (struct ext4_extent_header *) EXT4_I(inode)->i_data;
+}
+
+static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh)
+{
+	return (struct ext4_extent_header *) bh->b_data;
+}
+
+static inline unsigned short ext_depth(struct inode *inode)
+{
+	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
+}
+
+static inline void
+ext4_ext_invalidate_cache(struct inode *inode)
+{
+	EXT4_I(inode)->i_cached_extent.ec_len = 0;
+}
+
+static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+{
+	/* We can not have an uninitialized extent of zero length! */
+	BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
+	ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+{
+	/* Extent with ee_len of 0x8000 is treated as an initialized extent */
+	return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
+{
+	return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ?
+		le16_to_cpu(ext->ee_len) :
+		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
+}
+
+static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
+{
+	ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
+}
+
+/*
+ * ext4_ext_pblock:
+ * combine low and high parts of physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ex->ee_start_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_idx_pblock:
+ * combine low and high parts of a leaf physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ix->ei_leaf_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_ext_store_pblock:
+ * stores a large physical block number into an extent struct,
+ * breaking it into parts
+ */
+static inline void ext4_ext_store_pblock(struct ext4_extent *ex,
+					 ext4_fsblk_t pb)
+{
+	ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				      0xffff);
+}
+
+/*
+ * ext4_idx_store_pblock:
+ * stores a large physical block number into an index struct,
+ * breaking it into parts
+ */
+static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
+					 ext4_fsblk_t pb)
+{
+	ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				     0xffff);
+}
+
+extern int ext4_ext_calc_metadata_amount(struct inode *inode,
+					 ext4_lblk_t lblocks);
+extern int ext4_extent_tree_init(handle_t *, struct inode *);
+extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
+						   int num,
+						   struct ext4_ext_path *path);
+extern int ext4_can_extents_be_merged(struct inode *inode,
+				      struct ext4_extent *ex1,
+				      struct ext4_extent *ex2);
+extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int);
+extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
+							struct ext4_ext_path *);
+extern void ext4_ext_drop_refs(struct ext4_ext_path *);
+extern int ext4_ext_check_inode(struct inode *inode);
+#endif /* _EXT4_EXTENTS */
+
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
new file mode 100644
index 00000000..f5240aa1
--- /dev/null
+++ b/fs/ext4/ext4_jbd2.c
@@ -0,0 +1,152 @@
+/*
+ * Interface between ext4 and JBD
+ */
+
+#include "ext4_jbd2.h"
+
+#include <trace/events/ext4.h>
+
+int __ext4_journal_get_write_access(const char *where, unsigned int line,
+				    handle_t *handle, struct buffer_head *bh)
+{
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_write_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, line, __func__, bh,
+						  handle, err);
+	}
+	return err;
+}
+
+/*
+ * The ext4 forget function must perform a revoke if we are freeing data
+ * which has been journaled.  Metadata (eg. indirect blocks) must be
+ * revoked in all cases.
+ *
+ * "bh" may be NULL: a metadata block may have been freed from memory
+ * but there may still be a record of it in the journal, and that record
+ * still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling, but we still need to
+ * call into ext4_journal_revoke() to put the buffer head.
+ */
+int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
+		  int is_metadata, struct inode *inode,
+		  struct buffer_head *bh, ext4_fsblk_t blocknr)
+{
+	int err;
+
+	might_sleep();
+
+	trace_ext4_forget(inode, is_metadata, blocknr);
+	BUFFER_TRACE(bh, "enter");
+
+	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
+		  "data mode %x\n",
+		  bh, is_metadata, inode->i_mode,
+		  test_opt(inode->i_sb, DATA_FLAGS));
+
+	/* In the no journal case, we can just do a bforget and return */
+	if (!ext4_handle_valid(handle)) {
+		bforget(bh);
+		return 0;
+	}
+
+	/* Never use the revoke function if we are doing full data
+	 * journaling: there is no need to, and a V1 superblock won't
+	 * support it.  Otherwise, only skip the revoke on un-journaled
+	 * data blocks. */
+
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (!is_metadata && !ext4_should_journal_data(inode))) {
+		if (bh) {
+			BUFFER_TRACE(bh, "call jbd2_journal_forget");
+			err = jbd2_journal_forget(handle, bh);
+			if (err)
+				ext4_journal_abort_handle(where, line, __func__,
+							  bh, handle, err);
+			return err;
+		}
+		return 0;
+	}
+
+	/*
+	 * data!=journal && (is_metadata || should_journal_data(inode))
+	 */
+	BUFFER_TRACE(bh, "call jbd2_journal_revoke");
+	err = jbd2_journal_revoke(handle, blocknr, bh);
+	if (err) {
+		ext4_journal_abort_handle(where, line, __func__,
+					  bh, handle, err);
+		__ext4_abort(inode->i_sb, where, line,
+			   "error %d when attempting revoke", err);
+	}
+	BUFFER_TRACE(bh, "exit");
+	return err;
+}
+
+int __ext4_journal_get_create_access(const char *where, unsigned int line,
+				handle_t *handle, struct buffer_head *bh)
+{
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_create_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, line, __func__,
+						  bh, handle, err);
+	}
+	return err;
+}
+
+int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
+				 handle_t *handle, struct inode *inode,
+				 struct buffer_head *bh)
+{
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_dirty_metadata(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, line, __func__,
+						  bh, handle, err);
+	} else {
+		if (inode)
+			mark_buffer_dirty_inode(bh, inode);
+		else
+			mark_buffer_dirty(bh);
+		if (inode && inode_needs_sync(inode)) {
+			sync_dirty_buffer(bh);
+			if (buffer_req(bh) && !buffer_uptodate(bh)) {
+				struct ext4_super_block *es;
+
+				es = EXT4_SB(inode->i_sb)->s_es;
+				es->s_last_error_block =
+					cpu_to_le64(bh->b_blocknr);
+				ext4_error_inode(inode, where, line,
+						 bh->b_blocknr,
+					"IO error syncing itable block");
+				err = -EIO;
+			}
+		}
+	}
+	return err;
+}
+
+int __ext4_handle_dirty_super(const char *where, unsigned int line,
+			      handle_t *handle, struct super_block *sb)
+{
+	struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_dirty_metadata(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, line, __func__,
+						  bh, handle, err);
+	} else
+		sb->s_dirt = 1;
+	return err;
+}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
new file mode 100644
index 00000000..95af6f87
--- /dev/null
+++ b/fs/ext4/ext4_jbd2.h
@@ -0,0 +1,327 @@
+/*
+ * ext4_jbd2.h
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Ext4-specific journaling extensions.
+ */
+
+#ifndef _EXT4_JBD2_H
+#define _EXT4_JBD2_H
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include "ext4.h"
+
+#define EXT4_JOURNAL(inode)	(EXT4_SB((inode)->i_sb)->s_journal)
+
+/* Define the number of blocks we need to account to a transaction to
+ * modify one block of data.
+ *
+ * We may have to touch one inode, one bitmap buffer, up to three
+ * indirection blocks, the group and superblock summaries, and the data
+ * block to complete the transaction.
+ *
+ * For extents-enabled fs we may have to allocate and modify up to
+ * 5 levels of tree + root which are stored in the inode. */
+
+#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
+	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)   \
+	 ? 27U : 8U)
+
+/* Extended attribute operations touch at most two data buffers,
+ * two bitmap buffers, and two group summaries, in addition to the inode
+ * and the superblock, which are already accounted for. */
+
+#define EXT4_XATTR_TRANS_BLOCKS		6U
+
+/* Define the minimum size for a transaction which modifies data.  This
+ * needs to take into account the fact that we may end up modifying two
+ * quota files too (one for the group, one for the user quota).  The
+ * superblock only gets updated once, of course, so don't bother
+ * counting that again for the quota updates. */
+
+#define EXT4_DATA_TRANS_BLOCKS(sb)	(EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
+					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
+					 EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
+
+/*
+ * Define the number of metadata blocks we need to account to modify data.
+ *
+ * This include super block, inode block, quota blocks and xattr blocks
+ */
+#define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
+					EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
+
+/* Delete operations potentially hit one directory's namespace plus an
+ * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
+ * generous.  We can grow the delete transaction later if necessary. */
+
+#define EXT4_DELETE_TRANS_BLOCKS(sb)	(2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64)
+
+/* Define an arbitrary limit for the amount of data we will anticipate
+ * writing to any given transaction.  For unbounded transactions such as
+ * write(2) and truncate(2) we can write more than this, but we always
+ * start off at the maximum transaction size and grow the transaction
+ * optimistically as we go. */
+
+#define EXT4_MAX_TRANS_DATA		64U
+
+/* We break up a large truncate or write transaction once the handle's
+ * buffer credits gets this low, we need either to extend the
+ * transaction or to start a new one.  Reserve enough space here for
+ * inode, bitmap, superblock, group and indirection updates for at least
+ * one block, plus two quota updates.  Quota allocations are not
+ * needed. */
+
+#define EXT4_RESERVE_TRANS_BLOCKS	12U
+
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	8
+
+#ifdef CONFIG_QUOTA
+/* Amount of blocks needed for quota update - we know that the structure was
+ * allocated so we need to update only data block */
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0)
+/* Amount of blocks needed for quota insert/delete - we do some block writes
+ * but inode, sb and group updates are done only once */
+#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
+		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
+
+#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
+		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
+#else
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
+#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
+#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
+#endif
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+
+int
+ext4_mark_iloc_dirty(handle_t *handle,
+		     struct inode *inode,
+		     struct ext4_iloc *iloc);
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh.  This _must_ be cleaned up later.
+ */
+
+int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
+			struct ext4_iloc *iloc);
+
+int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
+
+/*
+ * Wrapper functions with which ext4 calls into JBD.
+ */
+void ext4_journal_abort_handle(const char *caller, unsigned int line,
+			       const char *err_fn,
+		struct buffer_head *bh, handle_t *handle, int err);
+
+int __ext4_journal_get_write_access(const char *where, unsigned int line,
+				    handle_t *handle, struct buffer_head *bh);
+
+int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
+		  int is_metadata, struct inode *inode,
+		  struct buffer_head *bh, ext4_fsblk_t blocknr);
+
+int __ext4_journal_get_create_access(const char *where, unsigned int line,
+				handle_t *handle, struct buffer_head *bh);
+
+int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
+				 handle_t *handle, struct inode *inode,
+				 struct buffer_head *bh);
+
+int __ext4_handle_dirty_super(const char *where, unsigned int line,
+			      handle_t *handle, struct super_block *sb);
+
+#define ext4_journal_get_write_access(handle, bh) \
+	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
+#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
+	__ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \
+		      (bh), (block_nr))
+#define ext4_journal_get_create_access(handle, bh) \
+	__ext4_journal_get_create_access(__func__, __LINE__, (handle), (bh))
+#define ext4_handle_dirty_metadata(handle, inode, bh) \
+	__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
+				     (bh))
+#define ext4_handle_dirty_super(handle, sb) \
+	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
+
+handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
+
+#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
+
+/* Note:  Do not use this for NULL handles.  This is only to determine if
+ * a properly allocated handle is using a journal or not. */
+static inline int ext4_handle_valid(handle_t *handle)
+{
+	if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT)
+		return 0;
+	return 1;
+}
+
+static inline void ext4_handle_sync(handle_t *handle)
+{
+	if (ext4_handle_valid(handle))
+		handle->h_sync = 1;
+}
+
+static inline void ext4_handle_release_buffer(handle_t *handle,
+						struct buffer_head *bh)
+{
+	if (ext4_handle_valid(handle))
+		jbd2_journal_release_buffer(handle, bh);
+}
+
+static inline int ext4_handle_is_aborted(handle_t *handle)
+{
+	if (ext4_handle_valid(handle))
+		return is_handle_aborted(handle);
+	return 0;
+}
+
+static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+{
+	if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
+		return 0;
+	return 1;
+}
+
+static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
+{
+	return ext4_journal_start_sb(inode->i_sb, nblocks);
+}
+
+#define ext4_journal_stop(handle) \
+	__ext4_journal_stop(__func__, __LINE__, (handle))
+
+static inline handle_t *ext4_journal_current_handle(void)
+{
+	return journal_current_handle();
+}
+
+static inline int ext4_journal_extend(handle_t *handle, int nblocks)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_extend(handle, nblocks);
+	return 0;
+}
+
+static inline int ext4_journal_restart(handle_t *handle, int nblocks)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_restart(handle, nblocks);
+	return 0;
+}
+
+static inline int ext4_journal_blocks_per_page(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) != NULL)
+		return jbd2_journal_blocks_per_page(inode);
+	return 0;
+}
+
+static inline int ext4_journal_force_commit(journal_t *journal)
+{
+	if (journal)
+		return jbd2_journal_force_commit(journal);
+	return 0;
+}
+
+static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
+	return 0;
+}
+
+static inline void ext4_update_inode_fsync_trans(handle_t *handle,
+						 struct inode *inode,
+						 int datasync)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		if (datasync)
+			ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+}
+
+/* super.c */
+int ext4_force_commit(struct super_block *sb);
+
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE	0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) == NULL)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	else
+		BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
+}
+
+static inline int ext4_should_order_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
+}
+
+static inline int ext4_should_writeback_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
+}
+
+/*
+ * This function controls whether or not we should try to go down the
+ * dioread_nolock code paths, which makes it safe to avoid taking
+ * i_mutex for direct I/O reads.  This only works for extent-based
+ * files, and it doesn't work if data journaling is enabled, since the
+ * dioread_nolock code uses b_private to pass information back to the
+ * I/O completion handler, and this conflicts with the jbd's use of
+ * b_private.
+ */
+static inline int ext4_should_dioread_nolock(struct inode *inode)
+{
+	if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
+		return 0;
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return 0;
+	if (ext4_should_journal_data(inode))
+		return 0;
+	return 1;
+}
+
+#endif	/* _EXT4_JBD2_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
new file mode 100644
index 00000000..611647b2
--- /dev/null
+++ b/fs/ext4/extents.c
@@ -0,0 +1,4364 @@
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ *
+ * Architecture independence:
+ *   Copyright (c) 2005, Bull S.A.
+ *   Written by Pierre Peiffer <pierre.peiffer@bull.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ */
+
+/*
+ * Extents support for EXT4
+ *
+ * TODO:
+ *   - ext4*_error() should be used in some situations
+ *   - analyze all BUG()/BUG_ON(), use -EIO where appropriate
+ *   - smart tree reduction
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/jbd2.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/falloc.h>
+#include <asm/uaccess.h>
+#include <linux/fiemap.h>
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
+
+#include <trace/events/ext4.h>
+
+static int ext4_split_extent(handle_t *handle,
+				struct inode *inode,
+				struct ext4_ext_path *path,
+				struct ext4_map_blocks *map,
+				int split_flag,
+				int flags);
+
+static int ext4_ext_truncate_extend_restart(handle_t *handle,
+					    struct inode *inode,
+					    int needed)
+{
+	int err;
+
+	if (!ext4_handle_valid(handle))
+		return 0;
+	if (handle->h_buffer_credits > needed)
+		return 0;
+	err = ext4_journal_extend(handle, needed);
+	if (err <= 0)
+		return err;
+	err = ext4_truncate_restart_trans(handle, inode, needed);
+	if (err == 0)
+		err = -EAGAIN;
+
+	return err;
+}
+
+/*
+ * could return:
+ *  - EROFS
+ *  - ENOMEM
+ */
+static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
+				struct ext4_ext_path *path)
+{
+	if (path->p_bh) {
+		/* path points to block */
+		return ext4_journal_get_write_access(handle, path->p_bh);
+	}
+	/* path points to leaf/index in inode body */
+	/* we use in-core data, no need to protect them */
+	return 0;
+}
+
+/*
+ * could return:
+ *  - EROFS
+ *  - ENOMEM
+ *  - EIO
+ */
+static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
+				struct ext4_ext_path *path)
+{
+	int err;
+	if (path->p_bh) {
+		/* path points to block */
+		err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
+	} else {
+		/* path points to leaf/index in inode body */
+		err = ext4_mark_inode_dirty(handle, inode);
+	}
+	return err;
+}
+
+static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
+			      struct ext4_ext_path *path,
+			      ext4_lblk_t block)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
+	ext4_grpblk_t colour;
+	ext4_group_t block_group;
+	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
+	int depth;
+
+	if (path) {
+		struct ext4_extent *ex;
+		depth = path->p_depth;
+
+		/*
+		 * Try to predict block placement assuming that we are
+		 * filling in a file which will eventually be
+		 * non-sparse --- i.e., in the case of libbfd writing
+		 * an ELF object sections out-of-order but in a way
+		 * the eventually results in a contiguous object or
+		 * executable file, or some database extending a table
+		 * space file.  However, this is actually somewhat
+		 * non-ideal if we are writing a sparse file such as
+		 * qemu or KVM writing a raw image file that is going
+		 * to stay fairly sparse, since it will end up
+		 * fragmenting the file system's free space.  Maybe we
+		 * should have some hueristics or some way to allow
+		 * userspace to pass a hint to file system,
+		 * especially if the latter case turns out to be
+		 * common.
+		 */
+		ex = path[depth].p_ext;
+		if (ex) {
+			ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex);
+			ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block);
+
+			if (block > ext_block)
+				return ext_pblk + (block - ext_block);
+			else
+				return ext_pblk - (ext_block - block);
+		}
+
+		/* it looks like index is empty;
+		 * try to find starting block from index itself */
+		if (path[depth].p_bh)
+			return path[depth].p_bh->b_blocknr;
+	}
+
+	/* OK. use inode's group */
+	block_group = ei->i_block_group;
+	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
+		/*
+		 * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
+		 * block groups per flexgroup, reserve the first block
+		 * group for directories and special files.  Regular
+		 * files will start at the second block group.  This
+		 * tends to speed up directory access and improves
+		 * fsck times.
+		 */
+		block_group &= ~(flex_size-1);
+		if (S_ISREG(inode->i_mode))
+			block_group++;
+	}
+	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	/*
+	 * If we are doing delayed allocation, we don't need take
+	 * colour into account.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		return bg_start;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
+			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+	return bg_start + colour + block;
+}
+
+/*
+ * Allocation for a meta data block
+ */
+static ext4_fsblk_t
+ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
+			struct ext4_ext_path *path,
+			struct ext4_extent *ex, int *err, unsigned int flags)
+{
+	ext4_fsblk_t goal, newblock;
+
+	goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
+	newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
+					NULL, err);
+	return newblock;
+}
+
+static inline int ext4_ext_space_block(struct inode *inode, int check)
+{
+	int size;
+
+	size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+			/ sizeof(struct ext4_extent);
+	if (!check) {
+#ifdef AGGRESSIVE_TEST
+		if (size > 6)
+			size = 6;
+#endif
+	}
+	return size;
+}
+
+static inline int ext4_ext_space_block_idx(struct inode *inode, int check)
+{
+	int size;
+
+	size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+			/ sizeof(struct ext4_extent_idx);
+	if (!check) {
+#ifdef AGGRESSIVE_TEST
+		if (size > 5)
+			size = 5;
+#endif
+	}
+	return size;
+}
+
+static inline int ext4_ext_space_root(struct inode *inode, int check)
+{
+	int size;
+
+	size = sizeof(EXT4_I(inode)->i_data);
+	size -= sizeof(struct ext4_extent_header);
+	size /= sizeof(struct ext4_extent);
+	if (!check) {
+#ifdef AGGRESSIVE_TEST
+		if (size > 3)
+			size = 3;
+#endif
+	}
+	return size;
+}
+
+static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
+{
+	int size;
+
+	size = sizeof(EXT4_I(inode)->i_data);
+	size -= sizeof(struct ext4_extent_header);
+	size /= sizeof(struct ext4_extent_idx);
+	if (!check) {
+#ifdef AGGRESSIVE_TEST
+		if (size > 4)
+			size = 4;
+#endif
+	}
+	return size;
+}
+
+/*
+ * Calculate the number of metadata blocks needed
+ * to allocate @blocks
+ * Worse case is one block per extent
+ */
+int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int idxs, num = 0;
+
+	idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+		/ sizeof(struct ext4_extent_idx));
+
+	/*
+	 * If the new delayed allocation block is contiguous with the
+	 * previous da block, it can share index blocks with the
+	 * previous block, so we only need to allocate a new index
+	 * block every idxs leaf blocks.  At ldxs**2 blocks, we need
+	 * an additional index block, and at ldxs**3 blocks, yet
+	 * another index blocks.
+	 */
+	if (ei->i_da_metadata_calc_len &&
+	    ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+		if ((ei->i_da_metadata_calc_len % idxs) == 0)
+			num++;
+		if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
+			num++;
+		if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
+			num++;
+			ei->i_da_metadata_calc_len = 0;
+		} else
+			ei->i_da_metadata_calc_len++;
+		ei->i_da_metadata_calc_last_lblock++;
+		return num;
+	}
+
+	/*
+	 * In the worst case we need a new set of index blocks at
+	 * every level of the inode's extent tree.
+	 */
+	ei->i_da_metadata_calc_len = 1;
+	ei->i_da_metadata_calc_last_lblock = lblock;
+	return ext_depth(inode) + 1;
+}
+
+static int
+ext4_ext_max_entries(struct inode *inode, int depth)
+{
+	int max;
+
+	if (depth == ext_depth(inode)) {
+		if (depth == 0)
+			max = ext4_ext_space_root(inode, 1);
+		else
+			max = ext4_ext_space_root_idx(inode, 1);
+	} else {
+		if (depth == 0)
+			max = ext4_ext_space_block(inode, 1);
+		else
+			max = ext4_ext_space_block_idx(inode, 1);
+	}
+
+	return max;
+}
+
+static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
+{
+	ext4_fsblk_t block = ext4_ext_pblock(ext);
+	int len = ext4_ext_get_actual_len(ext);
+
+	if (len == 0)
+		return 0;
+	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
+}
+
+static int ext4_valid_extent_idx(struct inode *inode,
+				struct ext4_extent_idx *ext_idx)
+{
+	ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
+
+	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
+}
+
+static int ext4_valid_extent_entries(struct inode *inode,
+				struct ext4_extent_header *eh,
+				int depth)
+{
+	struct ext4_extent *ext;
+	struct ext4_extent_idx *ext_idx;
+	unsigned short entries;
+	if (eh->eh_entries == 0)
+		return 1;
+
+	entries = le16_to_cpu(eh->eh_entries);
+
+	if (depth == 0) {
+		/* leaf entries */
+		ext = EXT_FIRST_EXTENT(eh);
+		while (entries) {
+			if (!ext4_valid_extent(inode, ext))
+				return 0;
+			ext++;
+			entries--;
+		}
+	} else {
+		ext_idx = EXT_FIRST_INDEX(eh);
+		while (entries) {
+			if (!ext4_valid_extent_idx(inode, ext_idx))
+				return 0;
+			ext_idx++;
+			entries--;
+		}
+	}
+	return 1;
+}
+
+static int __ext4_ext_check(const char *function, unsigned int line,
+			    struct inode *inode, struct ext4_extent_header *eh,
+			    int depth)
+{
+	const char *error_msg;
+	int max = 0;
+
+	if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) {
+		error_msg = "invalid magic";
+		goto corrupted;
+	}
+	if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) {
+		error_msg = "unexpected eh_depth";
+		goto corrupted;
+	}
+	if (unlikely(eh->eh_max == 0)) {
+		error_msg = "invalid eh_max";
+		goto corrupted;
+	}
+	max = ext4_ext_max_entries(inode, depth);
+	if (unlikely(le16_to_cpu(eh->eh_max) > max)) {
+		error_msg = "too large eh_max";
+		goto corrupted;
+	}
+	if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) {
+		error_msg = "invalid eh_entries";
+		goto corrupted;
+	}
+	if (!ext4_valid_extent_entries(inode, eh, depth)) {
+		error_msg = "invalid extent entries";
+		goto corrupted;
+	}
+	return 0;
+
+corrupted:
+	ext4_error_inode(inode, function, line, 0,
+			"bad header/extent: %s - magic %x, "
+			"entries %u, max %u(%u), depth %u(%u)",
+			error_msg, le16_to_cpu(eh->eh_magic),
+			le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
+			max, le16_to_cpu(eh->eh_depth), depth);
+
+	return -EIO;
+}
+
+#define ext4_ext_check(inode, eh, depth)	\
+	__ext4_ext_check(__func__, __LINE__, inode, eh, depth)
+
+int ext4_ext_check_inode(struct inode *inode)
+{
+	return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode));
+}
+
+#ifdef EXT_DEBUG
+static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
+{
+	int k, l = path->p_depth;
+
+	ext_debug("path:");
+	for (k = 0; k <= l; k++, path++) {
+		if (path->p_idx) {
+		  ext_debug("  %d->%llu", le32_to_cpu(path->p_idx->ei_block),
+			    ext4_idx_pblock(path->p_idx));
+		} else if (path->p_ext) {
+			ext_debug("  %d:[%d]%d:%llu ",
+				  le32_to_cpu(path->p_ext->ee_block),
+				  ext4_ext_is_uninitialized(path->p_ext),
+				  ext4_ext_get_actual_len(path->p_ext),
+				  ext4_ext_pblock(path->p_ext));
+		} else
+			ext_debug("  []");
+	}
+	ext_debug("\n");
+}
+
+static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
+{
+	int depth = ext_depth(inode);
+	struct ext4_extent_header *eh;
+	struct ext4_extent *ex;
+	int i;
+
+	if (!path)
+		return;
+
+	eh = path[depth].p_hdr;
+	ex = EXT_FIRST_EXTENT(eh);
+
+	ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino);
+
+	for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
+		ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
+			  ext4_ext_is_uninitialized(ex),
+			  ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
+	}
+	ext_debug("\n");
+}
+
+static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
+			ext4_fsblk_t newblock, int level)
+{
+	int depth = ext_depth(inode);
+	struct ext4_extent *ex;
+
+	if (depth != level) {
+		struct ext4_extent_idx *idx;
+		idx = path[level].p_idx;
+		while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) {
+			ext_debug("%d: move %d:%llu in new index %llu\n", level,
+					le32_to_cpu(idx->ei_block),
+					ext4_idx_pblock(idx),
+					newblock);
+			idx++;
+		}
+
+		return;
+	}
+
+	ex = path[depth].p_ext;
+	while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) {
+		ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
+				le32_to_cpu(ex->ee_block),
+				ext4_ext_pblock(ex),
+				ext4_ext_is_uninitialized(ex),
+				ext4_ext_get_actual_len(ex),
+				newblock);
+		ex++;
+	}
+}
+
+#else
+#define ext4_ext_show_path(inode, path)
+#define ext4_ext_show_leaf(inode, path)
+#define ext4_ext_show_move(inode, path, newblock, level)
+#endif
+
+void ext4_ext_drop_refs(struct ext4_ext_path *path)
+{
+	int depth = path->p_depth;
+	int i;
+
+	for (i = 0; i <= depth; i++, path++)
+		if (path->p_bh) {
+			brelse(path->p_bh);
+			path->p_bh = NULL;
+		}
+}
+
+/*
+ * ext4_ext_binsearch_idx:
+ * binary search for the closest index of the given block
+ * the header must be checked before calling this
+ */
+static void
+ext4_ext_binsearch_idx(struct inode *inode,
+			struct ext4_ext_path *path, ext4_lblk_t block)
+{
+	struct ext4_extent_header *eh = path->p_hdr;
+	struct ext4_extent_idx *r, *l, *m;
+
+
+	ext_debug("binsearch for %u(idx):  ", block);
+
+	l = EXT_FIRST_INDEX(eh) + 1;
+	r = EXT_LAST_INDEX(eh);
+	while (l <= r) {
+		m = l + (r - l) / 2;
+		if (block < le32_to_cpu(m->ei_block))
+			r = m - 1;
+		else
+			l = m + 1;
+		ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block),
+				m, le32_to_cpu(m->ei_block),
+				r, le32_to_cpu(r->ei_block));
+	}
+
+	path->p_idx = l - 1;
+	ext_debug("  -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block),
+		  ext4_idx_pblock(path->p_idx));
+
+#ifdef CHECK_BINSEARCH
+	{
+		struct ext4_extent_idx *chix, *ix;
+		int k;
+
+		chix = ix = EXT_FIRST_INDEX(eh);
+		for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
+		  if (k != 0 &&
+		      le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
+				printk(KERN_DEBUG "k=%d, ix=0x%p, "
+				       "first=0x%p\n", k,
+				       ix, EXT_FIRST_INDEX(eh));
+				printk(KERN_DEBUG "%u <= %u\n",
+				       le32_to_cpu(ix->ei_block),
+				       le32_to_cpu(ix[-1].ei_block));
+			}
+			BUG_ON(k && le32_to_cpu(ix->ei_block)
+					   <= le32_to_cpu(ix[-1].ei_block));
+			if (block < le32_to_cpu(ix->ei_block))
+				break;
+			chix = ix;
+		}
+		BUG_ON(chix != path->p_idx);
+	}
+#endif
+
+}
+
+/*
+ * ext4_ext_binsearch:
+ * binary search for closest extent of the given block
+ * the header must be checked before calling this
+ */
+static void
+ext4_ext_binsearch(struct inode *inode,
+		struct ext4_ext_path *path, ext4_lblk_t block)
+{
+	struct ext4_extent_header *eh = path->p_hdr;
+	struct ext4_extent *r, *l, *m;
+
+	if (eh->eh_entries == 0) {
+		/*
+		 * this leaf is empty:
+		 * we get such a leaf in split/add case
+		 */
+		return;
+	}
+
+	ext_debug("binsearch for %u:  ", block);
+
+	l = EXT_FIRST_EXTENT(eh) + 1;
+	r = EXT_LAST_EXTENT(eh);
+
+	while (l <= r) {
+		m = l + (r - l) / 2;
+		if (block < le32_to_cpu(m->ee_block))
+			r = m - 1;
+		else
+			l = m + 1;
+		ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block),
+				m, le32_to_cpu(m->ee_block),
+				r, le32_to_cpu(r->ee_block));
+	}
+
+	path->p_ext = l - 1;
+	ext_debug("  -> %d:%llu:[%d]%d ",
+			le32_to_cpu(path->p_ext->ee_block),
+			ext4_ext_pblock(path->p_ext),
+			ext4_ext_is_uninitialized(path->p_ext),
+			ext4_ext_get_actual_len(path->p_ext));
+
+#ifdef CHECK_BINSEARCH
+	{
+		struct ext4_extent *chex, *ex;
+		int k;
+
+		chex = ex = EXT_FIRST_EXTENT(eh);
+		for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) {
+			BUG_ON(k && le32_to_cpu(ex->ee_block)
+					  <= le32_to_cpu(ex[-1].ee_block));
+			if (block < le32_to_cpu(ex->ee_block))
+				break;
+			chex = ex;
+		}
+		BUG_ON(chex != path->p_ext);
+	}
+#endif
+
+}
+
+int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
+{
+	struct ext4_extent_header *eh;
+
+	eh = ext_inode_hdr(inode);
+	eh->eh_depth = 0;
+	eh->eh_entries = 0;
+	eh->eh_magic = EXT4_EXT_MAGIC;
+	eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_ext_invalidate_cache(inode);
+	return 0;
+}
+
+struct ext4_ext_path *
+ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
+					struct ext4_ext_path *path)
+{
+	struct ext4_extent_header *eh;
+	struct buffer_head *bh;
+	short int depth, i, ppos = 0, alloc = 0;
+
+	eh = ext_inode_hdr(inode);
+	depth = ext_depth(inode);
+
+	/* account possible depth increase */
+	if (!path) {
+		path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 2),
+				GFP_NOFS);
+		if (!path)
+			return ERR_PTR(-ENOMEM);
+		alloc = 1;
+	}
+	path[0].p_hdr = eh;
+	path[0].p_bh = NULL;
+
+	i = depth;
+	/* walk through the tree */
+	while (i) {
+		int need_to_validate = 0;
+
+		ext_debug("depth %d: num %d, max %d\n",
+			  ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
+
+		ext4_ext_binsearch_idx(inode, path + ppos, block);
+		path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
+		path[ppos].p_depth = i;
+		path[ppos].p_ext = NULL;
+
+		bh = sb_getblk(inode->i_sb, path[ppos].p_block);
+		if (unlikely(!bh))
+			goto err;
+		if (!bh_uptodate_or_lock(bh)) {
+			trace_ext4_ext_load_extent(inode, block,
+						path[ppos].p_block);
+			if (bh_submit_read(bh) < 0) {
+				put_bh(bh);
+				goto err;
+			}
+			/* validate the extent entries */
+			need_to_validate = 1;
+		}
+		eh = ext_block_hdr(bh);
+		ppos++;
+		if (unlikely(ppos > depth)) {
+			put_bh(bh);
+			EXT4_ERROR_INODE(inode,
+					 "ppos %d > depth %d", ppos, depth);
+			goto err;
+		}
+		path[ppos].p_bh = bh;
+		path[ppos].p_hdr = eh;
+		i--;
+
+		if (need_to_validate && ext4_ext_check(inode, eh, i))
+			goto err;
+	}
+
+	path[ppos].p_depth = i;
+	path[ppos].p_ext = NULL;
+	path[ppos].p_idx = NULL;
+
+	/* find extent */
+	ext4_ext_binsearch(inode, path + ppos, block);
+	/* if not an empty leaf */
+	if (path[ppos].p_ext)
+		path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
+
+	ext4_ext_show_path(inode, path);
+
+	return path;
+
+err:
+	ext4_ext_drop_refs(path);
+	if (alloc)
+		kfree(path);
+	return ERR_PTR(-EIO);
+}
+
+/*
+ * ext4_ext_insert_index:
+ * insert new index [@logical;@ptr] into the block at @curp;
+ * check where to insert: before @curp or after @curp
+ */
+static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
+				 struct ext4_ext_path *curp,
+				 int logical, ext4_fsblk_t ptr)
+{
+	struct ext4_extent_idx *ix;
+	int len, err;
+
+	err = ext4_ext_get_access(handle, inode, curp);
+	if (err)
+		return err;
+
+	if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) {
+		EXT4_ERROR_INODE(inode,
+				 "logical %d == ei_block %d!",
+				 logical, le32_to_cpu(curp->p_idx->ei_block));
+		return -EIO;
+	}
+	len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
+	if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
+		/* insert after */
+		if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
+			len = (len - 1) * sizeof(struct ext4_extent_idx);
+			len = len < 0 ? 0 : len;
+			ext_debug("insert new index %d after: %llu. "
+					"move %d from 0x%p to 0x%p\n",
+					logical, ptr, len,
+					(curp->p_idx + 1), (curp->p_idx + 2));
+			memmove(curp->p_idx + 2, curp->p_idx + 1, len);
+		}
+		ix = curp->p_idx + 1;
+	} else {
+		/* insert before */
+		len = len * sizeof(struct ext4_extent_idx);
+		len = len < 0 ? 0 : len;
+		ext_debug("insert new index %d before: %llu. "
+				"move %d from 0x%p to 0x%p\n",
+				logical, ptr, len,
+				curp->p_idx, (curp->p_idx + 1));
+		memmove(curp->p_idx + 1, curp->p_idx, len);
+		ix = curp->p_idx;
+	}
+
+	ix->ei_block = cpu_to_le32(logical);
+	ext4_idx_store_pblock(ix, ptr);
+	le16_add_cpu(&curp->p_hdr->eh_entries, 1);
+
+	if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
+			     > le16_to_cpu(curp->p_hdr->eh_max))) {
+		EXT4_ERROR_INODE(inode,
+				 "logical %d == ei_block %d!",
+				 logical, le32_to_cpu(curp->p_idx->ei_block));
+		return -EIO;
+	}
+	if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
+		EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
+		return -EIO;
+	}
+
+	err = ext4_ext_dirty(handle, inode, curp);
+	ext4_std_error(inode->i_sb, err);
+
+	return err;
+}
+
+/*
+ * ext4_ext_split:
+ * inserts new subtree into the path, using free index entry
+ * at depth @at:
+ * - allocates all needed blocks (new leaf and all intermediate index blocks)
+ * - makes decision where to split
+ * - moves remaining extents and index entries (right to the split point)
+ *   into the newly allocated blocks
+ * - initializes subtree
+ */
+static int ext4_ext_split(handle_t *handle, struct inode *inode,
+			  unsigned int flags,
+			  struct ext4_ext_path *path,
+			  struct ext4_extent *newext, int at)
+{
+	struct buffer_head *bh = NULL;
+	int depth = ext_depth(inode);
+	struct ext4_extent_header *neh;
+	struct ext4_extent_idx *fidx;
+	int i = at, k, m, a;
+	ext4_fsblk_t newblock, oldblock;
+	__le32 border;
+	ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */
+	int err = 0;
+
+	/* make decision: where to split? */
+	/* FIXME: now decision is simplest: at current extent */
+
+	/* if current leaf will be split, then we should use
+	 * border from split point */
+	if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) {
+		EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!");
+		return -EIO;
+	}
+	if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) {
+		border = path[depth].p_ext[1].ee_block;
+		ext_debug("leaf will be split."
+				" next leaf starts at %d\n",
+				  le32_to_cpu(border));
+	} else {
+		border = newext->ee_block;
+		ext_debug("leaf will be added."
+				" next leaf starts at %d\n",
+				le32_to_cpu(border));
+	}
+
+	/*
+	 * If error occurs, then we break processing
+	 * and mark filesystem read-only. index won't
+	 * be inserted and tree will be in consistent
+	 * state. Next mount will repair buffers too.
+	 */
+
+	/*
+	 * Get array to track all allocated blocks.
+	 * We need this to handle errors and free blocks
+	 * upon them.
+	 */
+	ablocks = kzalloc(sizeof(ext4_fsblk_t) * depth, GFP_NOFS);
+	if (!ablocks)
+		return -ENOMEM;
+
+	/* allocate all needed blocks */
+	ext_debug("allocate %d blocks for indexes/leaf\n", depth - at);
+	for (a = 0; a < depth - at; a++) {
+		newblock = ext4_ext_new_meta_block(handle, inode, path,
+						   newext, &err, flags);
+		if (newblock == 0)
+			goto cleanup;
+		ablocks[a] = newblock;
+	}
+
+	/* initialize new leaf */
+	newblock = ablocks[--a];
+	if (unlikely(newblock == 0)) {
+		EXT4_ERROR_INODE(inode, "newblock == 0!");
+		err = -EIO;
+		goto cleanup;
+	}
+	bh = sb_getblk(inode->i_sb, newblock);
+	if (!bh) {
+		err = -EIO;
+		goto cleanup;
+	}
+	lock_buffer(bh);
+
+	err = ext4_journal_get_create_access(handle, bh);
+	if (err)
+		goto cleanup;
+
+	neh = ext_block_hdr(bh);
+	neh->eh_entries = 0;
+	neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
+	neh->eh_magic = EXT4_EXT_MAGIC;
+	neh->eh_depth = 0;
+
+	/* move remainder of path[depth] to the new leaf */
+	if (unlikely(path[depth].p_hdr->eh_entries !=
+		     path[depth].p_hdr->eh_max)) {
+		EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!",
+				 path[depth].p_hdr->eh_entries,
+				 path[depth].p_hdr->eh_max);
+		err = -EIO;
+		goto cleanup;
+	}
+	/* start copy from next extent */
+	m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++;
+	ext4_ext_show_move(inode, path, newblock, depth);
+	if (m) {
+		struct ext4_extent *ex;
+		ex = EXT_FIRST_EXTENT(neh);
+		memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m);
+		le16_add_cpu(&neh->eh_entries, m);
+	}
+
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
+	if (err)
+		goto cleanup;
+	brelse(bh);
+	bh = NULL;
+
+	/* correct old leaf */
+	if (m) {
+		err = ext4_ext_get_access(handle, inode, path + depth);
+		if (err)
+			goto cleanup;
+		le16_add_cpu(&path[depth].p_hdr->eh_entries, -m);
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		if (err)
+			goto cleanup;
+
+	}
+
+	/* create intermediate indexes */
+	k = depth - at - 1;
+	if (unlikely(k < 0)) {
+		EXT4_ERROR_INODE(inode, "k %d < 0!", k);
+		err = -EIO;
+		goto cleanup;
+	}
+	if (k)
+		ext_debug("create %d intermediate indices\n", k);
+	/* insert new index into current index block */
+	/* current depth stored in i var */
+	i = depth - 1;
+	while (k--) {
+		oldblock = newblock;
+		newblock = ablocks[--a];
+		bh = sb_getblk(inode->i_sb, newblock);
+		if (!bh) {
+			err = -EIO;
+			goto cleanup;
+		}
+		lock_buffer(bh);
+
+		err = ext4_journal_get_create_access(handle, bh);
+		if (err)
+			goto cleanup;
+
+		neh = ext_block_hdr(bh);
+		neh->eh_entries = cpu_to_le16(1);
+		neh->eh_magic = EXT4_EXT_MAGIC;
+		neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
+		neh->eh_depth = cpu_to_le16(depth - i);
+		fidx = EXT_FIRST_INDEX(neh);
+		fidx->ei_block = border;
+		ext4_idx_store_pblock(fidx, oldblock);
+
+		ext_debug("int.index at %d (block %llu): %u -> %llu\n",
+				i, newblock, le32_to_cpu(border), oldblock);
+
+		/* move remainder of path[i] to the new index block */
+		if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) !=
+					EXT_LAST_INDEX(path[i].p_hdr))) {
+			EXT4_ERROR_INODE(inode,
+					 "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!",
+					 le32_to_cpu(path[i].p_ext->ee_block));
+			err = -EIO;
+			goto cleanup;
+		}
+		/* start copy indexes */
+		m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++;
+		ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
+				EXT_MAX_INDEX(path[i].p_hdr));
+		ext4_ext_show_move(inode, path, newblock, i);
+		if (m) {
+			memmove(++fidx, path[i].p_idx,
+				sizeof(struct ext4_extent_idx) * m);
+			le16_add_cpu(&neh->eh_entries, m);
+		}
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
+		if (err)
+			goto cleanup;
+		brelse(bh);
+		bh = NULL;
+
+		/* correct old index */
+		if (m) {
+			err = ext4_ext_get_access(handle, inode, path + i);
+			if (err)
+				goto cleanup;
+			le16_add_cpu(&path[i].p_hdr->eh_entries, -m);
+			err = ext4_ext_dirty(handle, inode, path + i);
+			if (err)
+				goto cleanup;
+		}
+
+		i--;
+	}
+
+	/* insert new index */
+	err = ext4_ext_insert_index(handle, inode, path + at,
+				    le32_to_cpu(border), newblock);
+
+cleanup:
+	if (bh) {
+		if (buffer_locked(bh))
+			unlock_buffer(bh);
+		brelse(bh);
+	}
+
+	if (err) {
+		/* free all allocated blocks in error case */
+		for (i = 0; i < depth; i++) {
+			if (!ablocks[i])
+				continue;
+			ext4_free_blocks(handle, inode, NULL, ablocks[i], 1,
+					 EXT4_FREE_BLOCKS_METADATA);
+		}
+	}
+	kfree(ablocks);
+
+	return err;
+}
+
+/*
+ * ext4_ext_grow_indepth:
+ * implements tree growing procedure:
+ * - allocates new block
+ * - moves top-level data (index block or leaf) into the new block
+ * - initializes new top-level, creating index that points to the
+ *   just created block
+ */
+static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
+				 unsigned int flags,
+				 struct ext4_ext_path *path,
+				 struct ext4_extent *newext)
+{
+	struct ext4_ext_path *curp = path;
+	struct ext4_extent_header *neh;
+	struct buffer_head *bh;
+	ext4_fsblk_t newblock;
+	int err = 0;
+
+	newblock = ext4_ext_new_meta_block(handle, inode, path,
+		newext, &err, flags);
+	if (newblock == 0)
+		return err;
+
+	bh = sb_getblk(inode->i_sb, newblock);
+	if (!bh) {
+		err = -EIO;
+		ext4_std_error(inode->i_sb, err);
+		return err;
+	}
+	lock_buffer(bh);
+
+	err = ext4_journal_get_create_access(handle, bh);
+	if (err) {
+		unlock_buffer(bh);
+		goto out;
+	}
+
+	/* move top-level index/leaf into new block */
+	memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data));
+
+	/* set size of new block */
+	neh = ext_block_hdr(bh);
+	/* old root could have indexes or leaves
+	 * so calculate e_max right way */
+	if (ext_depth(inode))
+		neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
+	else
+		neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
+	neh->eh_magic = EXT4_EXT_MAGIC;
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
+	if (err)
+		goto out;
+
+	/* create index in new top-level index: num,max,pointer */
+	err = ext4_ext_get_access(handle, inode, curp);
+	if (err)
+		goto out;
+
+	curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
+	curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
+	curp->p_hdr->eh_entries = cpu_to_le16(1);
+	curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
+
+	if (path[0].p_hdr->eh_depth)
+		curp->p_idx->ei_block =
+			EXT_FIRST_INDEX(path[0].p_hdr)->ei_block;
+	else
+		curp->p_idx->ei_block =
+			EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
+	ext4_idx_store_pblock(curp->p_idx, newblock);
+
+	neh = ext_inode_hdr(inode);
+	ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
+		  le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
+		  le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
+		  ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
+
+	neh->eh_depth = cpu_to_le16(path->p_depth + 1);
+	err = ext4_ext_dirty(handle, inode, curp);
+out:
+	brelse(bh);
+
+	return err;
+}
+
+/*
+ * ext4_ext_create_new_leaf:
+ * finds empty index and adds new leaf.
+ * if no free index is found, then it requests in-depth growing.
+ */
+static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
+				    unsigned int flags,
+				    struct ext4_ext_path *path,
+				    struct ext4_extent *newext)
+{
+	struct ext4_ext_path *curp;
+	int depth, i, err = 0;
+
+repeat:
+	i = depth = ext_depth(inode);
+
+	/* walk up to the tree and look for free index entry */
+	curp = path + depth;
+	while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) {
+		i--;
+		curp--;
+	}
+
+	/* we use already allocated block for index block,
+	 * so subsequent data blocks should be contiguous */
+	if (EXT_HAS_FREE_INDEX(curp)) {
+		/* if we found index with free entry, then use that
+		 * entry: create all needed subtree and add new leaf */
+		err = ext4_ext_split(handle, inode, flags, path, newext, i);
+		if (err)
+			goto out;
+
+		/* refill path */
+		ext4_ext_drop_refs(path);
+		path = ext4_ext_find_extent(inode,
+				    (ext4_lblk_t)le32_to_cpu(newext->ee_block),
+				    path);
+		if (IS_ERR(path))
+			err = PTR_ERR(path);
+	} else {
+		/* tree is full, time to grow in depth */
+		err = ext4_ext_grow_indepth(handle, inode, flags,
+					    path, newext);
+		if (err)
+			goto out;
+
+		/* refill path */
+		ext4_ext_drop_refs(path);
+		path = ext4_ext_find_extent(inode,
+				   (ext4_lblk_t)le32_to_cpu(newext->ee_block),
+				    path);
+		if (IS_ERR(path)) {
+			err = PTR_ERR(path);
+			goto out;
+		}
+
+		/*
+		 * only first (depth 0 -> 1) produces free space;
+		 * in all other cases we have to split the grown tree
+		 */
+		depth = ext_depth(inode);
+		if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) {
+			/* now we need to split */
+			goto repeat;
+		}
+	}
+
+out:
+	return err;
+}
+
+/*
+ * search the closest allocated block to the left for *logical
+ * and returns it at @logical + it's physical address at @phys
+ * if *logical is the smallest allocated block, the function
+ * returns 0 at @phys
+ * return value contains 0 (success) or error code
+ */
+static int ext4_ext_search_left(struct inode *inode,
+				struct ext4_ext_path *path,
+				ext4_lblk_t *logical, ext4_fsblk_t *phys)
+{
+	struct ext4_extent_idx *ix;
+	struct ext4_extent *ex;
+	int depth, ee_len;
+
+	if (unlikely(path == NULL)) {
+		EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+		return -EIO;
+	}
+	depth = path->p_depth;
+	*phys = 0;
+
+	if (depth == 0 && path->p_ext == NULL)
+		return 0;
+
+	/* usually extent in the path covers blocks smaller
+	 * then *logical, but it can be that extent is the
+	 * first one in the file */
+
+	ex = path[depth].p_ext;
+	ee_len = ext4_ext_get_actual_len(ex);
+	if (*logical < le32_to_cpu(ex->ee_block)) {
+		if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+			EXT4_ERROR_INODE(inode,
+					 "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!",
+					 *logical, le32_to_cpu(ex->ee_block));
+			return -EIO;
+		}
+		while (--depth >= 0) {
+			ix = path[depth].p_idx;
+			if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+				EXT4_ERROR_INODE(inode,
+				  "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
+				  ix != NULL ? ix->ei_block : 0,
+				  EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
+				    EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+				  depth);
+				return -EIO;
+			}
+		}
+		return 0;
+	}
+
+	if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+		EXT4_ERROR_INODE(inode,
+				 "logical %d < ee_block %d + ee_len %d!",
+				 *logical, le32_to_cpu(ex->ee_block), ee_len);
+		return -EIO;
+	}
+
+	*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
+	*phys = ext4_ext_pblock(ex) + ee_len - 1;
+	return 0;
+}
+
+/*
+ * search the closest allocated block to the right for *logical
+ * and returns it at @logical + it's physical address at @phys
+ * if *logical is the smallest allocated block, the function
+ * returns 0 at @phys
+ * return value contains 0 (success) or error code
+ */
+static int ext4_ext_search_right(struct inode *inode,
+				 struct ext4_ext_path *path,
+				 ext4_lblk_t *logical, ext4_fsblk_t *phys)
+{
+	struct buffer_head *bh = NULL;
+	struct ext4_extent_header *eh;
+	struct ext4_extent_idx *ix;
+	struct ext4_extent *ex;
+	ext4_fsblk_t block;
+	int depth;	/* Note, NOT eh_depth; depth from top of tree */
+	int ee_len;
+
+	if (unlikely(path == NULL)) {
+		EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+		return -EIO;
+	}
+	depth = path->p_depth;
+	*phys = 0;
+
+	if (depth == 0 && path->p_ext == NULL)
+		return 0;
+
+	/* usually extent in the path covers blocks smaller
+	 * then *logical, but it can be that extent is the
+	 * first one in the file */
+
+	ex = path[depth].p_ext;
+	ee_len = ext4_ext_get_actual_len(ex);
+	if (*logical < le32_to_cpu(ex->ee_block)) {
+		if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+			EXT4_ERROR_INODE(inode,
+					 "first_extent(path[%d].p_hdr) != ex",
+					 depth);
+			return -EIO;
+		}
+		while (--depth >= 0) {
+			ix = path[depth].p_idx;
+			if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+				EXT4_ERROR_INODE(inode,
+						 "ix != EXT_FIRST_INDEX *logical %d!",
+						 *logical);
+				return -EIO;
+			}
+		}
+		*logical = le32_to_cpu(ex->ee_block);
+		*phys = ext4_ext_pblock(ex);
+		return 0;
+	}
+
+	if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+		EXT4_ERROR_INODE(inode,
+				 "logical %d < ee_block %d + ee_len %d!",
+				 *logical, le32_to_cpu(ex->ee_block), ee_len);
+		return -EIO;
+	}
+
+	if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
+		/* next allocated block in this leaf */
+		ex++;
+		*logical = le32_to_cpu(ex->ee_block);
+		*phys = ext4_ext_pblock(ex);
+		return 0;
+	}
+
+	/* go up and search for index to the right */
+	while (--depth >= 0) {
+		ix = path[depth].p_idx;
+		if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
+			goto got_index;
+	}
+
+	/* we've gone up to the root and found no index to the right */
+	return 0;
+
+got_index:
+	/* we've found index to the right, let's
+	 * follow it and find the closest allocated
+	 * block to the right */
+	ix++;
+	block = ext4_idx_pblock(ix);
+	while (++depth < path->p_depth) {
+		bh = sb_bread(inode->i_sb, block);
+		if (bh == NULL)
+			return -EIO;
+		eh = ext_block_hdr(bh);
+		/* subtract from p_depth to get proper eh_depth */
+		if (ext4_ext_check(inode, eh, path->p_depth - depth)) {
+			put_bh(bh);
+			return -EIO;
+		}
+		ix = EXT_FIRST_INDEX(eh);
+		block = ext4_idx_pblock(ix);
+		put_bh(bh);
+	}
+
+	bh = sb_bread(inode->i_sb, block);
+	if (bh == NULL)
+		return -EIO;
+	eh = ext_block_hdr(bh);
+	if (ext4_ext_check(inode, eh, path->p_depth - depth)) {
+		put_bh(bh);
+		return -EIO;
+	}
+	ex = EXT_FIRST_EXTENT(eh);
+	*logical = le32_to_cpu(ex->ee_block);
+	*phys = ext4_ext_pblock(ex);
+	put_bh(bh);
+	return 0;
+}
+
+/*
+ * ext4_ext_next_allocated_block:
+ * returns allocated block in subsequent extent or EXT_MAX_BLOCKS.
+ * NOTE: it considers block number from index entry as
+ * allocated block. Thus, index entries have to be consistent
+ * with leaves.
+ */
+static ext4_lblk_t
+ext4_ext_next_allocated_block(struct ext4_ext_path *path)
+{
+	int depth;
+
+	BUG_ON(path == NULL);
+	depth = path->p_depth;
+
+	if (depth == 0 && path->p_ext == NULL)
+		return EXT_MAX_BLOCKS;
+
+	while (depth >= 0) {
+		if (depth == path->p_depth) {
+			/* leaf */
+			if (path[depth].p_ext !=
+					EXT_LAST_EXTENT(path[depth].p_hdr))
+			  return le32_to_cpu(path[depth].p_ext[1].ee_block);
+		} else {
+			/* index */
+			if (path[depth].p_idx !=
+					EXT_LAST_INDEX(path[depth].p_hdr))
+			  return le32_to_cpu(path[depth].p_idx[1].ei_block);
+		}
+		depth--;
+	}
+
+	return EXT_MAX_BLOCKS;
+}
+
+/*
+ * ext4_ext_next_leaf_block:
+ * returns first allocated block from next leaf or EXT_MAX_BLOCKS
+ */
+static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
+					struct ext4_ext_path *path)
+{
+	int depth;
+
+	BUG_ON(path == NULL);
+	depth = path->p_depth;
+
+	/* zero-tree has no leaf blocks at all */
+	if (depth == 0)
+		return EXT_MAX_BLOCKS;
+
+	/* go to index block */
+	depth--;
+
+	while (depth >= 0) {
+		if (path[depth].p_idx !=
+				EXT_LAST_INDEX(path[depth].p_hdr))
+			return (ext4_lblk_t)
+				le32_to_cpu(path[depth].p_idx[1].ei_block);
+		depth--;
+	}
+
+	return EXT_MAX_BLOCKS;
+}
+
+/*
+ * ext4_ext_correct_indexes:
+ * if leaf gets modified and modified extent is first in the leaf,
+ * then we have to correct all indexes above.
+ * TODO: do we need to correct tree in all cases?
+ */
+static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
+				struct ext4_ext_path *path)
+{
+	struct ext4_extent_header *eh;
+	int depth = ext_depth(inode);
+	struct ext4_extent *ex;
+	__le32 border;
+	int k, err = 0;
+
+	eh = path[depth].p_hdr;
+	ex = path[depth].p_ext;
+
+	if (unlikely(ex == NULL || eh == NULL)) {
+		EXT4_ERROR_INODE(inode,
+				 "ex %p == NULL or eh %p == NULL", ex, eh);
+		return -EIO;
+	}
+
+	if (depth == 0) {
+		/* there is no tree at all */
+		return 0;
+	}
+
+	if (ex != EXT_FIRST_EXTENT(eh)) {
+		/* we correct tree if first leaf got modified only */
+		return 0;
+	}
+
+	/*
+	 * TODO: we need correction if border is smaller than current one
+	 */
+	k = depth - 1;
+	border = path[depth].p_ext->ee_block;
+	err = ext4_ext_get_access(handle, inode, path + k);
+	if (err)
+		return err;
+	path[k].p_idx->ei_block = border;
+	err = ext4_ext_dirty(handle, inode, path + k);
+	if (err)
+		return err;
+
+	while (k--) {
+		/* change all left-side indexes */
+		if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr))
+			break;
+		err = ext4_ext_get_access(handle, inode, path + k);
+		if (err)
+			break;
+		path[k].p_idx->ei_block = border;
+		err = ext4_ext_dirty(handle, inode, path + k);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+int
+ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
+				struct ext4_extent *ex2)
+{
+	unsigned short ext1_ee_len, ext2_ee_len, max_len;
+
+	/*
+	 * Make sure that either both extents are uninitialized, or
+	 * both are _not_.
+	 */
+	if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
+		return 0;
+
+	if (ext4_ext_is_uninitialized(ex1))
+		max_len = EXT_UNINIT_MAX_LEN;
+	else
+		max_len = EXT_INIT_MAX_LEN;
+
+	ext1_ee_len = ext4_ext_get_actual_len(ex1);
+	ext2_ee_len = ext4_ext_get_actual_len(ex2);
+
+	if (le32_to_cpu(ex1->ee_block) + ext1_ee_len !=
+			le32_to_cpu(ex2->ee_block))
+		return 0;
+
+	/*
+	 * To allow future support for preallocated extents to be added
+	 * as an RO_COMPAT feature, refuse to merge to extents if
+	 * this can result in the top bit of ee_len being set.
+	 */
+	if (ext1_ee_len + ext2_ee_len > max_len)
+		return 0;
+#ifdef AGGRESSIVE_TEST
+	if (ext1_ee_len >= 4)
+		return 0;
+#endif
+
+	if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2))
+		return 1;
+	return 0;
+}
+
+/*
+ * This function tries to merge the "ex" extent to the next extent in the tree.
+ * It always tries to merge towards right. If you want to merge towards
+ * left, pass "ex - 1" as argument instead of "ex".
+ * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns
+ * 1 if they got merged.
+ */
+static int ext4_ext_try_to_merge_right(struct inode *inode,
+				 struct ext4_ext_path *path,
+				 struct ext4_extent *ex)
+{
+	struct ext4_extent_header *eh;
+	unsigned int depth, len;
+	int merge_done = 0;
+	int uninitialized = 0;
+
+	depth = ext_depth(inode);
+	BUG_ON(path[depth].p_hdr == NULL);
+	eh = path[depth].p_hdr;
+
+	while (ex < EXT_LAST_EXTENT(eh)) {
+		if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
+			break;
+		/* merge with next extent! */
+		if (ext4_ext_is_uninitialized(ex))
+			uninitialized = 1;
+		ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+				+ ext4_ext_get_actual_len(ex + 1));
+		if (uninitialized)
+			ext4_ext_mark_uninitialized(ex);
+
+		if (ex + 1 < EXT_LAST_EXTENT(eh)) {
+			len = (EXT_LAST_EXTENT(eh) - ex - 1)
+				* sizeof(struct ext4_extent);
+			memmove(ex + 1, ex + 2, len);
+		}
+		le16_add_cpu(&eh->eh_entries, -1);
+		merge_done = 1;
+		WARN_ON(eh->eh_entries == 0);
+		if (!eh->eh_entries)
+			EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!");
+	}
+
+	return merge_done;
+}
+
+/*
+ * This function tries to merge the @ex extent to neighbours in the tree.
+ * return 1 if merge left else 0.
+ */
+static int ext4_ext_try_to_merge(struct inode *inode,
+				  struct ext4_ext_path *path,
+				  struct ext4_extent *ex) {
+	struct ext4_extent_header *eh;
+	unsigned int depth;
+	int merge_done = 0;
+	int ret = 0;
+
+	depth = ext_depth(inode);
+	BUG_ON(path[depth].p_hdr == NULL);
+	eh = path[depth].p_hdr;
+
+	if (ex > EXT_FIRST_EXTENT(eh))
+		merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1);
+
+	if (!merge_done)
+		ret = ext4_ext_try_to_merge_right(inode, path, ex);
+
+	return ret;
+}
+
+/*
+ * check if a portion of the "newext" extent overlaps with an
+ * existing extent.
+ *
+ * If there is an overlap discovered, it updates the length of the newext
+ * such that there will be no overlap, and then returns 1.
+ * If there is no overlap found, it returns 0.
+ */
+static unsigned int ext4_ext_check_overlap(struct inode *inode,
+					   struct ext4_extent *newext,
+					   struct ext4_ext_path *path)
+{
+	ext4_lblk_t b1, b2;
+	unsigned int depth, len1;
+	unsigned int ret = 0;
+
+	b1 = le32_to_cpu(newext->ee_block);
+	len1 = ext4_ext_get_actual_len(newext);
+	depth = ext_depth(inode);
+	if (!path[depth].p_ext)
+		goto out;
+	b2 = le32_to_cpu(path[depth].p_ext->ee_block);
+
+	/*
+	 * get the next allocated block if the extent in the path
+	 * is before the requested block(s)
+	 */
+	if (b2 < b1) {
+		b2 = ext4_ext_next_allocated_block(path);
+		if (b2 == EXT_MAX_BLOCKS)
+			goto out;
+	}
+
+	/* check for wrap through zero on extent logical start block*/
+	if (b1 + len1 < b1) {
+		len1 = EXT_MAX_BLOCKS - b1;
+		newext->ee_len = cpu_to_le16(len1);
+		ret = 1;
+	}
+
+	/* check for overlap */
+	if (b1 + len1 > b2) {
+		newext->ee_len = cpu_to_le16(b2 - b1);
+		ret = 1;
+	}
+out:
+	return ret;
+}
+
+/*
+ * ext4_ext_insert_extent:
+ * tries to merge requsted extent into the existing extent or
+ * inserts requested extent as new one into the tree,
+ * creating new leaf in the no-space case.
+ */
+int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
+				struct ext4_ext_path *path,
+				struct ext4_extent *newext, int flag)
+{
+	struct ext4_extent_header *eh;
+	struct ext4_extent *ex, *fex;
+	struct ext4_extent *nearex; /* nearest extent */
+	struct ext4_ext_path *npath = NULL;
+	int depth, len, err;
+	ext4_lblk_t next;
+	unsigned uninitialized = 0;
+	int flags = 0;
+
+	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
+		EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
+		return -EIO;
+	}
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	if (unlikely(path[depth].p_hdr == NULL)) {
+		EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+		return -EIO;
+	}
+
+	/* try to insert block into found extent and return */
+	if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
+		&& ext4_can_extents_be_merged(inode, ex, newext)) {
+		ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
+			  ext4_ext_is_uninitialized(newext),
+			  ext4_ext_get_actual_len(newext),
+			  le32_to_cpu(ex->ee_block),
+			  ext4_ext_is_uninitialized(ex),
+			  ext4_ext_get_actual_len(ex),
+			  ext4_ext_pblock(ex));
+		err = ext4_ext_get_access(handle, inode, path + depth);
+		if (err)
+			return err;
+
+		/*
+		 * ext4_can_extents_be_merged should have checked that either
+		 * both extents are uninitialized, or both aren't. Thus we
+		 * need to check only one of them here.
+		 */
+		if (ext4_ext_is_uninitialized(ex))
+			uninitialized = 1;
+		ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+					+ ext4_ext_get_actual_len(newext));
+		if (uninitialized)
+			ext4_ext_mark_uninitialized(ex);
+		eh = path[depth].p_hdr;
+		nearex = ex;
+		goto merge;
+	}
+
+repeat:
+	depth = ext_depth(inode);
+	eh = path[depth].p_hdr;
+	if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max))
+		goto has_space;
+
+	/* probably next leaf has space for us? */
+	fex = EXT_LAST_EXTENT(eh);
+	next = ext4_ext_next_leaf_block(inode, path);
+	if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)
+	    && next != EXT_MAX_BLOCKS) {
+		ext_debug("next leaf block - %d\n", next);
+		BUG_ON(npath != NULL);
+		npath = ext4_ext_find_extent(inode, next, NULL);
+		if (IS_ERR(npath))
+			return PTR_ERR(npath);
+		BUG_ON(npath->p_depth != path->p_depth);
+		eh = npath[depth].p_hdr;
+		if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) {
+			ext_debug("next leaf isn't full(%d)\n",
+				  le16_to_cpu(eh->eh_entries));
+			path = npath;
+			goto repeat;
+		}
+		ext_debug("next leaf has no free space(%d,%d)\n",
+			  le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
+	}
+
+	/*
+	 * There is no free space in the found leaf.
+	 * We're gonna add a new leaf in the tree.
+	 */
+	if (flag & EXT4_GET_BLOCKS_PUNCH_OUT_EXT)
+		flags = EXT4_MB_USE_ROOT_BLOCKS;
+	err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
+	if (err)
+		goto cleanup;
+	depth = ext_depth(inode);
+	eh = path[depth].p_hdr;
+
+has_space:
+	nearex = path[depth].p_ext;
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto cleanup;
+
+	if (!nearex) {
+		/* there is no extent in this leaf, create first one */
+		ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
+				le32_to_cpu(newext->ee_block),
+				ext4_ext_pblock(newext),
+				ext4_ext_is_uninitialized(newext),
+				ext4_ext_get_actual_len(newext));
+		path[depth].p_ext = EXT_FIRST_EXTENT(eh);
+	} else if (le32_to_cpu(newext->ee_block)
+			   > le32_to_cpu(nearex->ee_block)) {
+/*		BUG_ON(newext->ee_block == nearex->ee_block); */
+		if (nearex != EXT_LAST_EXTENT(eh)) {
+			len = EXT_MAX_EXTENT(eh) - nearex;
+			len = (len - 1) * sizeof(struct ext4_extent);
+			len = len < 0 ? 0 : len;
+			ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
+					"move %d from 0x%p to 0x%p\n",
+					le32_to_cpu(newext->ee_block),
+					ext4_ext_pblock(newext),
+					ext4_ext_is_uninitialized(newext),
+					ext4_ext_get_actual_len(newext),
+					nearex, len, nearex + 1, nearex + 2);
+			memmove(nearex + 2, nearex + 1, len);
+		}
+		path[depth].p_ext = nearex + 1;
+	} else {
+		BUG_ON(newext->ee_block == nearex->ee_block);
+		len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent);
+		len = len < 0 ? 0 : len;
+		ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, "
+				"move %d from 0x%p to 0x%p\n",
+				le32_to_cpu(newext->ee_block),
+				ext4_ext_pblock(newext),
+				ext4_ext_is_uninitialized(newext),
+				ext4_ext_get_actual_len(newext),
+				nearex, len, nearex + 1, nearex + 2);
+		memmove(nearex + 1, nearex, len);
+		path[depth].p_ext = nearex;
+	}
+
+	le16_add_cpu(&eh->eh_entries, 1);
+	nearex = path[depth].p_ext;
+	nearex->ee_block = newext->ee_block;
+	ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
+	nearex->ee_len = newext->ee_len;
+
+merge:
+	/* try to merge extents to the right */
+	if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
+		ext4_ext_try_to_merge(inode, path, nearex);
+
+	/* try to merge extents to the left */
+
+	/* time to correct all indexes above */
+	err = ext4_ext_correct_indexes(handle, inode, path);
+	if (err)
+		goto cleanup;
+
+	err = ext4_ext_dirty(handle, inode, path + depth);
+
+cleanup:
+	if (npath) {
+		ext4_ext_drop_refs(npath);
+		kfree(npath);
+	}
+	ext4_ext_invalidate_cache(inode);
+	return err;
+}
+
+static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
+			       ext4_lblk_t num, ext_prepare_callback func,
+			       void *cbdata)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_ext_cache cbex;
+	struct ext4_extent *ex;
+	ext4_lblk_t next, start = 0, end = 0;
+	ext4_lblk_t last = block + num;
+	int depth, exists, err = 0;
+
+	BUG_ON(func == NULL);
+	BUG_ON(inode == NULL);
+
+	while (block < last && block != EXT_MAX_BLOCKS) {
+		num = last - block;
+		/* find extent for this block */
+		down_read(&EXT4_I(inode)->i_data_sem);
+		path = ext4_ext_find_extent(inode, block, path);
+		up_read(&EXT4_I(inode)->i_data_sem);
+		if (IS_ERR(path)) {
+			err = PTR_ERR(path);
+			path = NULL;
+			break;
+		}
+
+		depth = ext_depth(inode);
+		if (unlikely(path[depth].p_hdr == NULL)) {
+			EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+			err = -EIO;
+			break;
+		}
+		ex = path[depth].p_ext;
+		next = ext4_ext_next_allocated_block(path);
+
+		exists = 0;
+		if (!ex) {
+			/* there is no extent yet, so try to allocate
+			 * all requested space */
+			start = block;
+			end = block + num;
+		} else if (le32_to_cpu(ex->ee_block) > block) {
+			/* need to allocate space before found extent */
+			start = block;
+			end = le32_to_cpu(ex->ee_block);
+			if (block + num < end)
+				end = block + num;
+		} else if (block >= le32_to_cpu(ex->ee_block)
+					+ ext4_ext_get_actual_len(ex)) {
+			/* need to allocate space after found extent */
+			start = block;
+			end = block + num;
+			if (end >= next)
+				end = next;
+		} else if (block >= le32_to_cpu(ex->ee_block)) {
+			/*
+			 * some part of requested space is covered
+			 * by found extent
+			 */
+			start = block;
+			end = le32_to_cpu(ex->ee_block)
+				+ ext4_ext_get_actual_len(ex);
+			if (block + num < end)
+				end = block + num;
+			exists = 1;
+		} else {
+			BUG();
+		}
+		BUG_ON(end <= start);
+
+		if (!exists) {
+			cbex.ec_block = start;
+			cbex.ec_len = end - start;
+			cbex.ec_start = 0;
+		} else {
+			cbex.ec_block = le32_to_cpu(ex->ee_block);
+			cbex.ec_len = ext4_ext_get_actual_len(ex);
+			cbex.ec_start = ext4_ext_pblock(ex);
+		}
+
+		if (unlikely(cbex.ec_len == 0)) {
+			EXT4_ERROR_INODE(inode, "cbex.ec_len == 0");
+			err = -EIO;
+			break;
+		}
+		err = func(inode, next, &cbex, ex, cbdata);
+		ext4_ext_drop_refs(path);
+
+		if (err < 0)
+			break;
+
+		if (err == EXT_REPEAT)
+			continue;
+		else if (err == EXT_BREAK) {
+			err = 0;
+			break;
+		}
+
+		if (ext_depth(inode) != depth) {
+			/* depth was changed. we have to realloc path */
+			kfree(path);
+			path = NULL;
+		}
+
+		block = cbex.ec_block + cbex.ec_len;
+	}
+
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+
+	return err;
+}
+
+static void
+ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
+			__u32 len, ext4_fsblk_t start)
+{
+	struct ext4_ext_cache *cex;
+	BUG_ON(len == 0);
+	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+	cex = &EXT4_I(inode)->i_cached_extent;
+	cex->ec_block = block;
+	cex->ec_len = len;
+	cex->ec_start = start;
+	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+}
+
+/*
+ * ext4_ext_put_gap_in_cache:
+ * calculate boundaries of the gap that the requested block fits into
+ * and cache this gap
+ */
+static void
+ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
+				ext4_lblk_t block)
+{
+	int depth = ext_depth(inode);
+	unsigned long len;
+	ext4_lblk_t lblock;
+	struct ext4_extent *ex;
+
+	ex = path[depth].p_ext;
+	if (ex == NULL) {
+		/* there is no extent yet, so gap is [0;-] */
+		lblock = 0;
+		len = EXT_MAX_BLOCKS;
+		ext_debug("cache gap(whole file):");
+	} else if (block < le32_to_cpu(ex->ee_block)) {
+		lblock = block;
+		len = le32_to_cpu(ex->ee_block) - block;
+		ext_debug("cache gap(before): %u [%u:%u]",
+				block,
+				le32_to_cpu(ex->ee_block),
+				 ext4_ext_get_actual_len(ex));
+	} else if (block >= le32_to_cpu(ex->ee_block)
+			+ ext4_ext_get_actual_len(ex)) {
+		ext4_lblk_t next;
+		lblock = le32_to_cpu(ex->ee_block)
+			+ ext4_ext_get_actual_len(ex);
+
+		next = ext4_ext_next_allocated_block(path);
+		ext_debug("cache gap(after): [%u:%u] %u",
+				le32_to_cpu(ex->ee_block),
+				ext4_ext_get_actual_len(ex),
+				block);
+		BUG_ON(next == lblock);
+		len = next - lblock;
+	} else {
+		lblock = len = 0;
+		BUG();
+	}
+
+	ext_debug(" -> %u:%lu\n", lblock, len);
+	ext4_ext_put_in_cache(inode, lblock, len, 0);
+}
+
+/*
+ * ext4_ext_in_cache()
+ * Checks to see if the given block is in the cache.
+ * If it is, the cached extent is stored in the given
+ * cache extent pointer.  If the cached extent is a hole,
+ * this routine should be used instead of
+ * ext4_ext_in_cache if the calling function needs to
+ * know the size of the hole.
+ *
+ * @inode: The files inode
+ * @block: The block to look for in the cache
+ * @ex:    Pointer where the cached extent will be stored
+ *         if it contains block
+ *
+ * Return 0 if cache is invalid; 1 if the cache is valid
+ */
+static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block,
+	struct ext4_ext_cache *ex){
+	struct ext4_ext_cache *cex;
+	struct ext4_sb_info *sbi;
+	int ret = 0;
+
+	/*
+	 * We borrow i_block_reservation_lock to protect i_cached_extent
+	 */
+	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+	cex = &EXT4_I(inode)->i_cached_extent;
+	sbi = EXT4_SB(inode->i_sb);
+
+	/* has cache valid data? */
+	if (cex->ec_len == 0)
+		goto errout;
+
+	if (in_range(block, cex->ec_block, cex->ec_len)) {
+		memcpy(ex, cex, sizeof(struct ext4_ext_cache));
+		ext_debug("%u cached by %u:%u:%llu\n",
+				block,
+				cex->ec_block, cex->ec_len, cex->ec_start);
+		ret = 1;
+	}
+errout:
+	if (!ret)
+		sbi->extent_cache_misses++;
+	else
+		sbi->extent_cache_hits++;
+	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+	return ret;
+}
+
+/*
+ * ext4_ext_in_cache()
+ * Checks to see if the given block is in the cache.
+ * If it is, the cached extent is stored in the given
+ * extent pointer.
+ *
+ * @inode: The files inode
+ * @block: The block to look for in the cache
+ * @ex:    Pointer where the cached extent will be stored
+ *         if it contains block
+ *
+ * Return 0 if cache is invalid; 1 if the cache is valid
+ */
+static int
+ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
+			struct ext4_extent *ex)
+{
+	struct ext4_ext_cache cex;
+	int ret = 0;
+
+	if (ext4_ext_check_cache(inode, block, &cex)) {
+		ex->ee_block = cpu_to_le32(cex.ec_block);
+		ext4_ext_store_pblock(ex, cex.ec_start);
+		ex->ee_len = cpu_to_le16(cex.ec_len);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+
+/*
+ * ext4_ext_rm_idx:
+ * removes index from the index block.
+ * It's used in truncate case only, thus all requests are for
+ * last index in the block only.
+ */
+static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
+			struct ext4_ext_path *path)
+{
+	int err;
+	ext4_fsblk_t leaf;
+
+	/* free index block */
+	path--;
+	leaf = ext4_idx_pblock(path->p_idx);
+	if (unlikely(path->p_hdr->eh_entries == 0)) {
+		EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
+		return -EIO;
+	}
+	err = ext4_ext_get_access(handle, inode, path);
+	if (err)
+		return err;
+	le16_add_cpu(&path->p_hdr->eh_entries, -1);
+	err = ext4_ext_dirty(handle, inode, path);
+	if (err)
+		return err;
+	ext_debug("index is empty, remove it, free block %llu\n", leaf);
+	ext4_free_blocks(handle, inode, NULL, leaf, 1,
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+	return err;
+}
+
+/*
+ * ext4_ext_calc_credits_for_single_extent:
+ * This routine returns max. credits that needed to insert an extent
+ * to the extent tree.
+ * When pass the actual path, the caller should calculate credits
+ * under i_data_sem.
+ */
+int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
+						struct ext4_ext_path *path)
+{
+	if (path) {
+		int depth = ext_depth(inode);
+		int ret = 0;
+
+		/* probably there is space in leaf? */
+		if (le16_to_cpu(path[depth].p_hdr->eh_entries)
+				< le16_to_cpu(path[depth].p_hdr->eh_max)) {
+
+			/*
+			 *  There are some space in the leaf tree, no
+			 *  need to account for leaf block credit
+			 *
+			 *  bitmaps and block group descriptor blocks
+			 *  and other metadat blocks still need to be
+			 *  accounted.
+			 */
+			/* 1 bitmap, 1 block group descriptor */
+			ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb);
+			return ret;
+		}
+	}
+
+	return ext4_chunk_trans_blocks(inode, nrblocks);
+}
+
+/*
+ * How many index/leaf blocks need to change/allocate to modify nrblocks?
+ *
+ * if nrblocks are fit in a single extent (chunk flag is 1), then
+ * in the worse case, each tree level index/leaf need to be changed
+ * if the tree split due to insert a new extent, then the old tree
+ * index/leaf need to be updated too
+ *
+ * If the nrblocks are discontiguous, they could cause
+ * the whole tree split more than once, but this is really rare.
+ */
+int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+{
+	int index;
+	int depth = ext_depth(inode);
+
+	if (chunk)
+		index = depth * 2;
+	else
+		index = depth * 3;
+
+	return index;
+}
+
+static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
+				struct ext4_extent *ex,
+				ext4_lblk_t from, ext4_lblk_t to)
+{
+	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
+	int flags = EXT4_FREE_BLOCKS_FORGET;
+
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		flags |= EXT4_FREE_BLOCKS_METADATA;
+#ifdef EXTENTS_STATS
+	{
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+		spin_lock(&sbi->s_ext_stats_lock);
+		sbi->s_ext_blocks += ee_len;
+		sbi->s_ext_extents++;
+		if (ee_len < sbi->s_ext_min)
+			sbi->s_ext_min = ee_len;
+		if (ee_len > sbi->s_ext_max)
+			sbi->s_ext_max = ee_len;
+		if (ext_depth(inode) > sbi->s_depth_max)
+			sbi->s_depth_max = ext_depth(inode);
+		spin_unlock(&sbi->s_ext_stats_lock);
+	}
+#endif
+	if (from >= le32_to_cpu(ex->ee_block)
+	    && to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
+		/* tail removal */
+		ext4_lblk_t num;
+		ext4_fsblk_t start;
+
+		num = le32_to_cpu(ex->ee_block) + ee_len - from;
+		start = ext4_ext_pblock(ex) + ee_len - num;
+		ext_debug("free last %u blocks starting %llu\n", num, start);
+		ext4_free_blocks(handle, inode, NULL, start, num, flags);
+	} else if (from == le32_to_cpu(ex->ee_block)
+		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
+		/* head removal */
+		ext4_lblk_t num;
+		ext4_fsblk_t start;
+
+		num = to - from;
+		start = ext4_ext_pblock(ex);
+
+		ext_debug("free first %u blocks starting %llu\n", num, start);
+		ext4_free_blocks(handle, inode, 0, start, num, flags);
+
+	} else {
+		printk(KERN_INFO "strange request: removal(2) "
+				"%u-%u from %u:%u\n",
+				from, to, le32_to_cpu(ex->ee_block), ee_len);
+	}
+	return 0;
+}
+
+
+/*
+ * ext4_ext_rm_leaf() Removes the extents associated with the
+ * blocks appearing between "start" and "end", and splits the extents
+ * if "start" and "end" appear in the same extent
+ *
+ * @handle: The journal handle
+ * @inode:  The files inode
+ * @path:   The path to the leaf
+ * @start:  The first block to remove
+ * @end:   The last block to remove
+ */
+static int
+ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
+		struct ext4_ext_path *path, ext4_lblk_t start,
+		ext4_lblk_t end)
+{
+	int err = 0, correct_index = 0;
+	int depth = ext_depth(inode), credits;
+	struct ext4_extent_header *eh;
+	ext4_lblk_t a, b, block;
+	unsigned num;
+	ext4_lblk_t ex_ee_block;
+	unsigned short ex_ee_len;
+	unsigned uninitialized = 0;
+	struct ext4_extent *ex;
+	struct ext4_map_blocks map;
+
+	/* the header must be checked already in ext4_ext_remove_space() */
+	ext_debug("truncate since %u in leaf\n", start);
+	if (!path[depth].p_hdr)
+		path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
+	eh = path[depth].p_hdr;
+	if (unlikely(path[depth].p_hdr == NULL)) {
+		EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+		return -EIO;
+	}
+	/* find where to start removing */
+	ex = EXT_LAST_EXTENT(eh);
+
+	ex_ee_block = le32_to_cpu(ex->ee_block);
+	ex_ee_len = ext4_ext_get_actual_len(ex);
+
+	while (ex >= EXT_FIRST_EXTENT(eh) &&
+			ex_ee_block + ex_ee_len > start) {
+
+		if (ext4_ext_is_uninitialized(ex))
+			uninitialized = 1;
+		else
+			uninitialized = 0;
+
+		ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
+			 uninitialized, ex_ee_len);
+		path[depth].p_ext = ex;
+
+		a = ex_ee_block > start ? ex_ee_block : start;
+		b = ex_ee_block+ex_ee_len - 1 < end ?
+			ex_ee_block+ex_ee_len - 1 : end;
+
+		ext_debug("  border %u:%u\n", a, b);
+
+		/* If this extent is beyond the end of the hole, skip it */
+		if (end <= ex_ee_block) {
+			ex--;
+			ex_ee_block = le32_to_cpu(ex->ee_block);
+			ex_ee_len = ext4_ext_get_actual_len(ex);
+			continue;
+		} else if (a != ex_ee_block &&
+			b != ex_ee_block + ex_ee_len - 1) {
+			/*
+			 * If this is a truncate, then this condition should
+			 * never happen because at least one of the end points
+			 * needs to be on the edge of the extent.
+			 */
+			if (end == EXT_MAX_BLOCKS - 1) {
+				ext_debug("  bad truncate %u:%u\n",
+						start, end);
+				block = 0;
+				num = 0;
+				err = -EIO;
+				goto out;
+			}
+			/*
+			 * else this is a hole punch, so the extent needs to
+			 * be split since neither edge of the hole is on the
+			 * extent edge
+			 */
+			else{
+				map.m_pblk = ext4_ext_pblock(ex);
+				map.m_lblk = ex_ee_block;
+				map.m_len = b - ex_ee_block;
+
+				err = ext4_split_extent(handle,
+					inode, path, &map, 0,
+					EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
+					EXT4_GET_BLOCKS_PRE_IO);
+
+				if (err < 0)
+					goto out;
+
+				ex_ee_len = ext4_ext_get_actual_len(ex);
+
+				b = ex_ee_block+ex_ee_len - 1 < end ?
+					ex_ee_block+ex_ee_len - 1 : end;
+
+				/* Then remove tail of this extent */
+				block = ex_ee_block;
+				num = a - block;
+			}
+		} else if (a != ex_ee_block) {
+			/* remove tail of the extent */
+			block = ex_ee_block;
+			num = a - block;
+		} else if (b != ex_ee_block + ex_ee_len - 1) {
+			/* remove head of the extent */
+			block = b;
+			num =  ex_ee_block + ex_ee_len - b;
+
+			/*
+			 * If this is a truncate, this condition
+			 * should never happen
+			 */
+			if (end == EXT_MAX_BLOCKS - 1) {
+				ext_debug("  bad truncate %u:%u\n",
+					start, end);
+				err = -EIO;
+				goto out;
+			}
+		} else {
+			/* remove whole extent: excellent! */
+			block = ex_ee_block;
+			num = 0;
+			if (a != ex_ee_block) {
+				ext_debug("  bad truncate %u:%u\n",
+					start, end);
+				err = -EIO;
+				goto out;
+			}
+
+			if (b != ex_ee_block + ex_ee_len - 1) {
+				ext_debug("  bad truncate %u:%u\n",
+					start, end);
+				err = -EIO;
+				goto out;
+			}
+		}
+
+		/*
+		 * 3 for leaf, sb, and inode plus 2 (bmap and group
+		 * descriptor) for each block group; assume two block
+		 * groups plus ex_ee_len/blocks_per_block_group for
+		 * the worst case
+		 */
+		credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb));
+		if (ex == EXT_FIRST_EXTENT(eh)) {
+			correct_index = 1;
+			credits += (ext_depth(inode)) + 1;
+		}
+		credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
+
+		err = ext4_ext_truncate_extend_restart(handle, inode, credits);
+		if (err)
+			goto out;
+
+		err = ext4_ext_get_access(handle, inode, path + depth);
+		if (err)
+			goto out;
+
+		err = ext4_remove_blocks(handle, inode, ex, a, b);
+		if (err)
+			goto out;
+
+		if (num == 0) {
+			/* this extent is removed; mark slot entirely unused */
+			ext4_ext_store_pblock(ex, 0);
+		} else if (block != ex_ee_block) {
+			/*
+			 * If this was a head removal, then we need to update
+			 * the physical block since it is now at a different
+			 * location
+			 */
+			ext4_ext_store_pblock(ex, ext4_ext_pblock(ex) + (b-a));
+		}
+
+		ex->ee_block = cpu_to_le32(block);
+		ex->ee_len = cpu_to_le16(num);
+		/*
+		 * Do not mark uninitialized if all the blocks in the
+		 * extent have been removed.
+		 */
+		if (uninitialized && num)
+			ext4_ext_mark_uninitialized(ex);
+
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		if (err)
+			goto out;
+
+		/*
+		 * If the extent was completely released,
+		 * we need to remove it from the leaf
+		 */
+		if (num == 0) {
+			if (end != EXT_MAX_BLOCKS - 1) {
+				/*
+				 * For hole punching, we need to scoot all the
+				 * extents up when an extent is removed so that
+				 * we dont have blank extents in the middle
+				 */
+				memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) *
+					sizeof(struct ext4_extent));
+
+				/* Now get rid of the one at the end */
+				memset(EXT_LAST_EXTENT(eh), 0,
+					sizeof(struct ext4_extent));
+			}
+			le16_add_cpu(&eh->eh_entries, -1);
+		}
+
+		ext_debug("new extent: %u:%u:%llu\n", block, num,
+				ext4_ext_pblock(ex));
+		ex--;
+		ex_ee_block = le32_to_cpu(ex->ee_block);
+		ex_ee_len = ext4_ext_get_actual_len(ex);
+	}
+
+	if (correct_index && eh->eh_entries)
+		err = ext4_ext_correct_indexes(handle, inode, path);
+
+	/* if this leaf is free, then we should
+	 * remove it from index block above */
+	if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
+		err = ext4_ext_rm_idx(handle, inode, path + depth);
+
+out:
+	return err;
+}
+
+/*
+ * ext4_ext_more_to_rm:
+ * returns 1 if current index has to be freed (even partial)
+ */
+static int
+ext4_ext_more_to_rm(struct ext4_ext_path *path)
+{
+	BUG_ON(path->p_idx == NULL);
+
+	if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr))
+		return 0;
+
+	/*
+	 * if truncate on deeper level happened, it wasn't partial,
+	 * so we have to consider current index for truncation
+	 */
+	if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block)
+		return 0;
+	return 1;
+}
+
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+				ext4_lblk_t end)
+{
+	struct super_block *sb = inode->i_sb;
+	int depth = ext_depth(inode);
+	struct ext4_ext_path *path;
+	handle_t *handle;
+	int i, err;
+
+	ext_debug("truncate since %u\n", start);
+
+	/* probably first extent we're gonna free will be last in block */
+	handle = ext4_journal_start(inode, depth + 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+again:
+	ext4_ext_invalidate_cache(inode);
+
+	/*
+	 * We start scanning from right side, freeing all the blocks
+	 * after i_size and walking into the tree depth-wise.
+	 */
+	depth = ext_depth(inode);
+	path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
+	if (path == NULL) {
+		ext4_journal_stop(handle);
+		return -ENOMEM;
+	}
+	path[0].p_depth = depth;
+	path[0].p_hdr = ext_inode_hdr(inode);
+	if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+		err = -EIO;
+		goto out;
+	}
+	i = err = 0;
+
+	while (i >= 0 && err == 0) {
+		if (i == depth) {
+			/* this is leaf block */
+			err = ext4_ext_rm_leaf(handle, inode, path,
+					start, end);
+			/* root level has p_bh == NULL, brelse() eats this */
+			brelse(path[i].p_bh);
+			path[i].p_bh = NULL;
+			i--;
+			continue;
+		}
+
+		/* this is index block */
+		if (!path[i].p_hdr) {
+			ext_debug("initialize header\n");
+			path[i].p_hdr = ext_block_hdr(path[i].p_bh);
+		}
+
+		if (!path[i].p_idx) {
+			/* this level hasn't been touched yet */
+			path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr);
+			path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1;
+			ext_debug("init index ptr: hdr 0x%p, num %d\n",
+				  path[i].p_hdr,
+				  le16_to_cpu(path[i].p_hdr->eh_entries));
+		} else {
+			/* we were already here, see at next index */
+			path[i].p_idx--;
+		}
+
+		ext_debug("level %d - index, first 0x%p, cur 0x%p\n",
+				i, EXT_FIRST_INDEX(path[i].p_hdr),
+				path[i].p_idx);
+		if (ext4_ext_more_to_rm(path + i)) {
+			struct buffer_head *bh;
+			/* go to the next level */
+			ext_debug("move to level %d (block %llu)\n",
+				  i + 1, ext4_idx_pblock(path[i].p_idx));
+			memset(path + i + 1, 0, sizeof(*path));
+			bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx));
+			if (!bh) {
+				/* should we reset i_size? */
+				err = -EIO;
+				break;
+			}
+			if (WARN_ON(i + 1 > depth)) {
+				err = -EIO;
+				break;
+			}
+			if (ext4_ext_check(inode, ext_block_hdr(bh),
+							depth - i - 1)) {
+				err = -EIO;
+				break;
+			}
+			path[i + 1].p_bh = bh;
+
+			/* save actual number of indexes since this
+			 * number is changed at the next iteration */
+			path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries);
+			i++;
+		} else {
+			/* we finished processing this index, go up */
+			if (path[i].p_hdr->eh_entries == 0 && i > 0) {
+				/* index is empty, remove it;
+				 * handle must be already prepared by the
+				 * truncatei_leaf() */
+				err = ext4_ext_rm_idx(handle, inode, path + i);
+			}
+			/* root level has p_bh == NULL, brelse() eats this */
+			brelse(path[i].p_bh);
+			path[i].p_bh = NULL;
+			i--;
+			ext_debug("return to level %d\n", i);
+		}
+	}
+
+	/* TODO: flexible tree reduction should be here */
+	if (path->p_hdr->eh_entries == 0) {
+		/*
+		 * truncate to zero freed all the tree,
+		 * so we need to correct eh_depth
+		 */
+		err = ext4_ext_get_access(handle, inode, path);
+		if (err == 0) {
+			ext_inode_hdr(inode)->eh_depth = 0;
+			ext_inode_hdr(inode)->eh_max =
+				cpu_to_le16(ext4_ext_space_root(inode, 0));
+			err = ext4_ext_dirty(handle, inode, path);
+		}
+	}
+out:
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	if (err == -EAGAIN)
+		goto again;
+	ext4_journal_stop(handle);
+
+	return err;
+}
+
+/*
+ * called at mount time
+ */
+void ext4_ext_init(struct super_block *sb)
+{
+	/*
+	 * possible initialization would be here
+	 */
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
+		printk(KERN_INFO "EXT4-fs: file extents enabled");
+#ifdef AGGRESSIVE_TEST
+		printk(", aggressive tests");
+#endif
+#ifdef CHECK_BINSEARCH
+		printk(", check binsearch");
+#endif
+#ifdef EXTENTS_STATS
+		printk(", stats");
+#endif
+		printk("\n");
+#endif
+#ifdef EXTENTS_STATS
+		spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
+		EXT4_SB(sb)->s_ext_min = 1 << 30;
+		EXT4_SB(sb)->s_ext_max = 0;
+#endif
+	}
+}
+
+/*
+ * called at umount time
+ */
+void ext4_ext_release(struct super_block *sb)
+{
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+		return;
+
+#ifdef EXTENTS_STATS
+	if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) {
+		struct ext4_sb_info *sbi = EXT4_SB(sb);
+		printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n",
+			sbi->s_ext_blocks, sbi->s_ext_extents,
+			sbi->s_ext_blocks / sbi->s_ext_extents);
+		printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n",
+			sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max);
+	}
+#endif
+}
+
+/* FIXME!! we need to try to merge to left or right after zero-out  */
+static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+	ext4_fsblk_t ee_pblock;
+	unsigned int ee_len;
+	int ret;
+
+	ee_len    = ext4_ext_get_actual_len(ex);
+	ee_pblock = ext4_ext_pblock(ex);
+
+	ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS);
+	if (ret > 0)
+		ret = 0;
+
+	return ret;
+}
+
+/*
+ * used by extent splitting.
+ */
+#define EXT4_EXT_MAY_ZEROOUT	0x1  /* safe to zeroout if split fails \
+					due to ENOSPC */
+#define EXT4_EXT_MARK_UNINIT1	0x2  /* mark first half uninitialized */
+#define EXT4_EXT_MARK_UNINIT2	0x4  /* mark second half uninitialized */
+
+/*
+ * ext4_split_extent_at() splits an extent at given block.
+ *
+ * @handle: the journal handle
+ * @inode: the file inode
+ * @path: the path to the extent
+ * @split: the logical block where the extent is splitted.
+ * @split_flags: indicates if the extent could be zeroout if split fails, and
+ *		 the states(init or uninit) of new extents.
+ * @flags: flags used to insert new extent to extent tree.
+ *
+ *
+ * Splits extent [a, b] into two extents [a, @split) and [@split, b], states
+ * of which are deterimined by split_flag.
+ *
+ * There are two cases:
+ *  a> the extent are splitted into two extent.
+ *  b> split is not needed, and just mark the extent.
+ *
+ * return 0 on success.
+ */
+static int ext4_split_extent_at(handle_t *handle,
+			     struct inode *inode,
+			     struct ext4_ext_path *path,
+			     ext4_lblk_t split,
+			     int split_flag,
+			     int flags)
+{
+	ext4_fsblk_t newblock;
+	ext4_lblk_t ee_block;
+	struct ext4_extent *ex, newex, orig_ex;
+	struct ext4_extent *ex2 = NULL;
+	unsigned int ee_len, depth;
+	int err = 0;
+
+	ext_debug("ext4_split_extents_at: inode %lu, logical"
+		"block %llu\n", inode->i_ino, (unsigned long long)split);
+
+	ext4_ext_show_leaf(inode, path);
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+	newblock = split - ee_block + ext4_ext_pblock(ex);
+
+	BUG_ON(split < ee_block || split >= (ee_block + ee_len));
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+
+	if (split == ee_block) {
+		/*
+		 * case b: block @split is the block that the extent begins with
+		 * then we just change the state of the extent, and splitting
+		 * is not needed.
+		 */
+		if (split_flag & EXT4_EXT_MARK_UNINIT2)
+			ext4_ext_mark_uninitialized(ex);
+		else
+			ext4_ext_mark_initialized(ex);
+
+		if (!(flags & EXT4_GET_BLOCKS_PRE_IO))
+			ext4_ext_try_to_merge(inode, path, ex);
+
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		goto out;
+	}
+
+	/* case a */
+	memcpy(&orig_ex, ex, sizeof(orig_ex));
+	ex->ee_len = cpu_to_le16(split - ee_block);
+	if (split_flag & EXT4_EXT_MARK_UNINIT1)
+		ext4_ext_mark_uninitialized(ex);
+
+	/*
+	 * path may lead to new leaf, not to original leaf any more
+	 * after ext4_ext_insert_extent() returns,
+	 */
+	err = ext4_ext_dirty(handle, inode, path + depth);
+	if (err)
+		goto fix_extent_len;
+
+	ex2 = &newex;
+	ex2->ee_block = cpu_to_le32(split);
+	ex2->ee_len   = cpu_to_le16(ee_len - (split - ee_block));
+	ext4_ext_store_pblock(ex2, newblock);
+	if (split_flag & EXT4_EXT_MARK_UNINIT2)
+		ext4_ext_mark_uninitialized(ex2);
+
+	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
+	if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+		err = ext4_ext_zeroout(inode, &orig_ex);
+		if (err)
+			goto fix_extent_len;
+		/* update the extent length and mark as initialized */
+		ex->ee_len = cpu_to_le16(ee_len);
+		ext4_ext_try_to_merge(inode, path, ex);
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		goto out;
+	} else if (err)
+		goto fix_extent_len;
+
+out:
+	ext4_ext_show_leaf(inode, path);
+	return err;
+
+fix_extent_len:
+	ex->ee_len = orig_ex.ee_len;
+	ext4_ext_dirty(handle, inode, path + depth);
+	return err;
+}
+
+/*
+ * ext4_split_extents() splits an extent and mark extent which is covered
+ * by @map as split_flags indicates
+ *
+ * It may result in splitting the extent into multiple extents (upto three)
+ * There are three possibilities:
+ *   a> There is no split required
+ *   b> Splits in two extents: Split is happening at either end of the extent
+ *   c> Splits in three extents: Somone is splitting in middle of the extent
+ *
+ */
+static int ext4_split_extent(handle_t *handle,
+			      struct inode *inode,
+			      struct ext4_ext_path *path,
+			      struct ext4_map_blocks *map,
+			      int split_flag,
+			      int flags)
+{
+	ext4_lblk_t ee_block;
+	struct ext4_extent *ex;
+	unsigned int ee_len, depth;
+	int err = 0;
+	int uninitialized;
+	int split_flag1, flags1;
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+	uninitialized = ext4_ext_is_uninitialized(ex);
+
+	if (map->m_lblk + map->m_len < ee_block + ee_len) {
+		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
+			      EXT4_EXT_MAY_ZEROOUT : 0;
+		flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
+		if (uninitialized)
+			split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
+				       EXT4_EXT_MARK_UNINIT2;
+		err = ext4_split_extent_at(handle, inode, path,
+				map->m_lblk + map->m_len, split_flag1, flags1);
+		if (err)
+			goto out;
+	}
+
+	ext4_ext_drop_refs(path);
+	path = ext4_ext_find_extent(inode, map->m_lblk, path);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	if (map->m_lblk >= ee_block) {
+		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
+			      EXT4_EXT_MAY_ZEROOUT : 0;
+		if (uninitialized)
+			split_flag1 |= EXT4_EXT_MARK_UNINIT1;
+		if (split_flag & EXT4_EXT_MARK_UNINIT2)
+			split_flag1 |= EXT4_EXT_MARK_UNINIT2;
+		err = ext4_split_extent_at(handle, inode, path,
+				map->m_lblk, split_flag1, flags);
+		if (err)
+			goto out;
+	}
+
+	ext4_ext_show_leaf(inode, path);
+out:
+	return err ? err : map->m_len;
+}
+
+#define EXT4_EXT_ZERO_LEN 7
+/*
+ * This function is called by ext4_ext_map_blocks() if someone tries to write
+ * to an uninitialized extent. It may result in splitting the uninitialized
+ * extent into multiple extents (up to three - one initialized and two
+ * uninitialized).
+ * There are three possibilities:
+ *   a> There is no split required: Entire extent should be initialized
+ *   b> Splits in two extents: Write is happening at either end of the extent
+ *   c> Splits in three extents: Somone is writing in middle of the extent
+ */
+static int ext4_ext_convert_to_initialized(handle_t *handle,
+					   struct inode *inode,
+					   struct ext4_map_blocks *map,
+					   struct ext4_ext_path *path)
+{
+	struct ext4_map_blocks split_map;
+	struct ext4_extent zero_ex;
+	struct ext4_extent *ex;
+	ext4_lblk_t ee_block, eof_block;
+	unsigned int allocated, ee_len, depth;
+	int err = 0;
+	int split_flag = 0;
+
+	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
+		"block %llu, max_blocks %u\n", inode->i_ino,
+		(unsigned long long)map->m_lblk, map->m_len);
+
+	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+		inode->i_sb->s_blocksize_bits;
+	if (eof_block < map->m_lblk + map->m_len)
+		eof_block = map->m_lblk + map->m_len;
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+	allocated = ee_len - (map->m_lblk - ee_block);
+
+	WARN_ON(map->m_lblk < ee_block);
+	/*
+	 * It is safe to convert extent to initialized via explicit
+	 * zeroout only if extent is fully insde i_size or new_size.
+	 */
+	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
+
+	/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
+	if (ee_len <= 2*EXT4_EXT_ZERO_LEN &&
+	    (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+		err = ext4_ext_zeroout(inode, ex);
+		if (err)
+			goto out;
+
+		err = ext4_ext_get_access(handle, inode, path + depth);
+		if (err)
+			goto out;
+		ext4_ext_mark_initialized(ex);
+		ext4_ext_try_to_merge(inode, path, ex);
+		err = ext4_ext_dirty(handle, inode, path + depth);
+		goto out;
+	}
+
+	/*
+	 * four cases:
+	 * 1. split the extent into three extents.
+	 * 2. split the extent into two extents, zeroout the first half.
+	 * 3. split the extent into two extents, zeroout the second half.
+	 * 4. split the extent into two extents with out zeroout.
+	 */
+	split_map.m_lblk = map->m_lblk;
+	split_map.m_len = map->m_len;
+
+	if (allocated > map->m_len) {
+		if (allocated <= EXT4_EXT_ZERO_LEN &&
+		    (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+			/* case 3 */
+			zero_ex.ee_block =
+					 cpu_to_le32(map->m_lblk);
+			zero_ex.ee_len = cpu_to_le16(allocated);
+			ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex);
+			if (err)
+				goto out;
+			split_map.m_lblk = map->m_lblk;
+			split_map.m_len = allocated;
+		} else if ((map->m_lblk - ee_block + map->m_len <
+			   EXT4_EXT_ZERO_LEN) &&
+			   (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+			/* case 2 */
+			if (map->m_lblk != ee_block) {
+				zero_ex.ee_block = ex->ee_block;
+				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+							ee_block);
+				ext4_ext_store_pblock(&zero_ex,
+						      ext4_ext_pblock(ex));
+				err = ext4_ext_zeroout(inode, &zero_ex);
+				if (err)
+					goto out;
+			}
+
+			split_map.m_lblk = ee_block;
+			split_map.m_len = map->m_lblk - ee_block + map->m_len;
+			allocated = map->m_len;
+		}
+	}
+
+	allocated = ext4_split_extent(handle, inode, path,
+				       &split_map, split_flag, 0);
+	if (allocated < 0)
+		err = allocated;
+
+out:
+	return err ? err : allocated;
+}
+
+/*
+ * This function is called by ext4_ext_map_blocks() from
+ * ext4_get_blocks_dio_write() when DIO to write
+ * to an uninitialized extent.
+ *
+ * Writing to an uninitialized extent may result in splitting the uninitialized
+ * extent into multiple /initialized uninitialized extents (up to three)
+ * There are three possibilities:
+ *   a> There is no split required: Entire extent should be uninitialized
+ *   b> Splits in two extents: Write is happening at either end of the extent
+ *   c> Splits in three extents: Somone is writing in middle of the extent
+ *
+ * One of more index blocks maybe needed if the extent tree grow after
+ * the uninitialized extent split. To prevent ENOSPC occur at the IO
+ * complete, we need to split the uninitialized extent before DIO submit
+ * the IO. The uninitialized extent called at this time will be split
+ * into three uninitialized extent(at most). After IO complete, the part
+ * being filled will be convert to initialized by the end_io callback function
+ * via ext4_convert_unwritten_extents().
+ *
+ * Returns the size of uninitialized extent to be written on success.
+ */
+static int ext4_split_unwritten_extents(handle_t *handle,
+					struct inode *inode,
+					struct ext4_map_blocks *map,
+					struct ext4_ext_path *path,
+					int flags)
+{
+	ext4_lblk_t eof_block;
+	ext4_lblk_t ee_block;
+	struct ext4_extent *ex;
+	unsigned int ee_len;
+	int split_flag = 0, depth;
+
+	ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
+		"block %llu, max_blocks %u\n", inode->i_ino,
+		(unsigned long long)map->m_lblk, map->m_len);
+
+	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+		inode->i_sb->s_blocksize_bits;
+	if (eof_block < map->m_lblk + map->m_len)
+		eof_block = map->m_lblk + map->m_len;
+	/*
+	 * It is safe to convert extent to initialized via explicit
+	 * zeroout only if extent is fully insde i_size or new_size.
+	 */
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
+
+	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
+	split_flag |= EXT4_EXT_MARK_UNINIT2;
+
+	flags |= EXT4_GET_BLOCKS_PRE_IO;
+	return ext4_split_extent(handle, inode, path, map, split_flag, flags);
+}
+
+static int ext4_convert_unwritten_extents_endio(handle_t *handle,
+					      struct inode *inode,
+					      struct ext4_ext_path *path)
+{
+	struct ext4_extent *ex;
+	struct ext4_extent_header *eh;
+	int depth;
+	int err = 0;
+
+	depth = ext_depth(inode);
+	eh = path[depth].p_hdr;
+	ex = path[depth].p_ext;
+
+	ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
+		"block %llu, max_blocks %u\n", inode->i_ino,
+		(unsigned long long)le32_to_cpu(ex->ee_block),
+		ext4_ext_get_actual_len(ex));
+
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+	/* first mark the extent as initialized */
+	ext4_ext_mark_initialized(ex);
+
+	/* note: ext4_ext_correct_indexes() isn't needed here because
+	 * borders are not changed
+	 */
+	ext4_ext_try_to_merge(inode, path, ex);
+
+	/* Mark modified extent as dirty */
+	err = ext4_ext_dirty(handle, inode, path + depth);
+out:
+	ext4_ext_show_leaf(inode, path);
+	return err;
+}
+
+static void unmap_underlying_metadata_blocks(struct block_device *bdev,
+			sector_t block, int count)
+{
+	int i;
+	for (i = 0; i < count; i++)
+                unmap_underlying_metadata(bdev, block + i);
+}
+
+/*
+ * Handle EOFBLOCKS_FL flag, clearing it if necessary
+ */
+static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
+			      ext4_lblk_t lblk,
+			      struct ext4_ext_path *path,
+			      unsigned int len)
+{
+	int i, depth;
+	struct ext4_extent_header *eh;
+	struct ext4_extent *last_ex;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
+		return 0;
+
+	depth = ext_depth(inode);
+	eh = path[depth].p_hdr;
+
+	if (unlikely(!eh->eh_entries)) {
+		EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
+				 "EOFBLOCKS_FL set");
+		return -EIO;
+	}
+	last_ex = EXT_LAST_EXTENT(eh);
+	/*
+	 * We should clear the EOFBLOCKS_FL flag if we are writing the
+	 * last block in the last extent in the file.  We test this by
+	 * first checking to see if the caller to
+	 * ext4_ext_get_blocks() was interested in the last block (or
+	 * a block beyond the last block) in the current extent.  If
+	 * this turns out to be false, we can bail out from this
+	 * function immediately.
+	 */
+	if (lblk + len < le32_to_cpu(last_ex->ee_block) +
+	    ext4_ext_get_actual_len(last_ex))
+		return 0;
+	/*
+	 * If the caller does appear to be planning to write at or
+	 * beyond the end of the current extent, we then test to see
+	 * if the current extent is the last extent in the file, by
+	 * checking to make sure it was reached via the rightmost node
+	 * at each level of the tree.
+	 */
+	for (i = depth-1; i >= 0; i--)
+		if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
+			return 0;
+	ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+	return ext4_mark_inode_dirty(handle, inode);
+}
+
+static int
+ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
+			struct ext4_map_blocks *map,
+			struct ext4_ext_path *path, int flags,
+			unsigned int allocated, ext4_fsblk_t newblock)
+{
+	int ret = 0;
+	int err = 0;
+	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+
+	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical"
+		  "block %llu, max_blocks %u, flags %d, allocated %u",
+		  inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
+		  flags, allocated);
+	ext4_ext_show_leaf(inode, path);
+
+	/* get_block() before submit the IO, split the extent */
+	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
+		ret = ext4_split_unwritten_extents(handle, inode, map,
+						   path, flags);
+		/*
+		 * Flag the inode(non aio case) or end_io struct (aio case)
+		 * that this IO needs to conversion to written when IO is
+		 * completed
+		 */
+		if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
+			io->flag = EXT4_IO_END_UNWRITTEN;
+			atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+		} else
+			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+		if (ext4_should_dioread_nolock(inode))
+			map->m_flags |= EXT4_MAP_UNINIT;
+		goto out;
+	}
+	/* IO end_io complete, convert the filled extent to written */
+	if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+		ret = ext4_convert_unwritten_extents_endio(handle, inode,
+							path);
+		if (ret >= 0) {
+			ext4_update_inode_fsync_trans(handle, inode, 1);
+			err = check_eofblocks_fl(handle, inode, map->m_lblk,
+						 path, map->m_len);
+		} else
+			err = ret;
+		goto out2;
+	}
+	/* buffered IO case */
+	/*
+	 * repeat fallocate creation request
+	 * we already have an unwritten extent
+	 */
+	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
+		goto map_out;
+
+	/* buffered READ or buffered write_begin() lookup */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		/*
+		 * We have blocks reserved already.  We
+		 * return allocated blocks so that delalloc
+		 * won't do block reservation for us.  But
+		 * the buffer head will be unmapped so that
+		 * a read from the block returns 0s.
+		 */
+		map->m_flags |= EXT4_MAP_UNWRITTEN;
+		goto out1;
+	}
+
+	/* buffered write, writepage time, convert*/
+	ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
+	if (ret >= 0) {
+		ext4_update_inode_fsync_trans(handle, inode, 1);
+		err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
+					 map->m_len);
+		if (err < 0)
+			goto out2;
+	}
+
+out:
+	if (ret <= 0) {
+		err = ret;
+		goto out2;
+	} else
+		allocated = ret;
+	map->m_flags |= EXT4_MAP_NEW;
+	/*
+	 * if we allocated more blocks than requested
+	 * we need to make sure we unmap the extra block
+	 * allocated. The actual needed block will get
+	 * unmapped later when we find the buffer_head marked
+	 * new.
+	 */
+	if (allocated > map->m_len) {
+		unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
+					newblock + map->m_len,
+					allocated - map->m_len);
+		allocated = map->m_len;
+	}
+
+	/*
+	 * If we have done fallocate with the offset that is already
+	 * delayed allocated, we would have block reservation
+	 * and quota reservation done in the delayed write path.
+	 * But fallocate would have already updated quota and block
+	 * count for this offset. So cancel these reservation
+	 */
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ext4_da_update_reserve_space(inode, allocated, 0);
+
+map_out:
+	map->m_flags |= EXT4_MAP_MAPPED;
+out1:
+	if (allocated > map->m_len)
+		allocated = map->m_len;
+	ext4_ext_show_leaf(inode, path);
+	map->m_pblk = newblock;
+	map->m_len = allocated;
+out2:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+	return err ? err : allocated;
+}
+
+/*
+ * Block allocation/map/preallocation routine for extents based files
+ *
+ *
+ * Need to be called with
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
+ * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ *
+ * return > 0, number of of blocks already mapped/allocated
+ *          if create == 0 and these are pre-allocated blocks
+ *          	buffer head is unmapped
+ *          otherwise blocks are mapped
+ *
+ * return = 0, if plain look up failed (blocks have not been allocated)
+ *          buffer head is unmapped
+ *
+ * return < 0, error case.
+ */
+int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
+			struct ext4_map_blocks *map, int flags)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent newex, *ex;
+	ext4_fsblk_t newblock = 0;
+	int err = 0, depth, ret;
+	unsigned int allocated = 0;
+	unsigned int punched_out = 0;
+	unsigned int result = 0;
+	struct ext4_allocation_request ar;
+	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+	struct ext4_map_blocks punch_map;
+
+	ext_debug("blocks %u/%u requested for inode %lu\n",
+		  map->m_lblk, map->m_len, inode->i_ino);
+	trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
+
+	/* check in cache */
+	if (ext4_ext_in_cache(inode, map->m_lblk, &newex) &&
+		((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0)) {
+		if (!newex.ee_start_lo && !newex.ee_start_hi) {
+			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+				/*
+				 * block isn't allocated yet and
+				 * user doesn't want to allocate it
+				 */
+				goto out2;
+			}
+			/* we should allocate requested block */
+		} else {
+			/* block is already allocated */
+			newblock = map->m_lblk
+				   - le32_to_cpu(newex.ee_block)
+				   + ext4_ext_pblock(&newex);
+			/* number of remaining blocks in the extent */
+			allocated = ext4_ext_get_actual_len(&newex) -
+				(map->m_lblk - le32_to_cpu(newex.ee_block));
+			goto out;
+		}
+	}
+
+	/* find extent for this block */
+	path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
+	if (IS_ERR(path)) {
+		err = PTR_ERR(path);
+		path = NULL;
+		goto out2;
+	}
+
+	depth = ext_depth(inode);
+
+	/*
+	 * consistent leaf must not be empty;
+	 * this situation is possible, though, _during_ tree modification;
+	 * this is why assert can't be put in ext4_ext_find_extent()
+	 */
+	if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
+		EXT4_ERROR_INODE(inode, "bad extent address "
+				 "lblock: %lu, depth: %d pblock %lld",
+				 (unsigned long) map->m_lblk, depth,
+				 path[depth].p_block);
+		err = -EIO;
+		goto out2;
+	}
+
+	ex = path[depth].p_ext;
+	if (ex) {
+		ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
+		ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
+		unsigned short ee_len;
+
+		/*
+		 * Uninitialized extents are treated as holes, except that
+		 * we split out initialized portions during a write.
+		 */
+		ee_len = ext4_ext_get_actual_len(ex);
+		/* if found extent covers block, simply return it */
+		if (in_range(map->m_lblk, ee_block, ee_len)) {
+			newblock = map->m_lblk - ee_block + ee_start;
+			/* number of remaining blocks in the extent */
+			allocated = ee_len - (map->m_lblk - ee_block);
+			ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
+				  ee_block, ee_len, newblock);
+
+			if ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0) {
+				/*
+				 * Do not put uninitialized extent
+				 * in the cache
+				 */
+				if (!ext4_ext_is_uninitialized(ex)) {
+					ext4_ext_put_in_cache(inode, ee_block,
+						ee_len, ee_start);
+					goto out;
+				}
+				ret = ext4_ext_handle_uninitialized_extents(
+					handle, inode, map, path, flags,
+					allocated, newblock);
+				return ret;
+			}
+
+			/*
+			 * Punch out the map length, but only to the
+			 * end of the extent
+			 */
+			punched_out = allocated < map->m_len ?
+				allocated : map->m_len;
+
+			/*
+			 * Sense extents need to be converted to
+			 * uninitialized, they must fit in an
+			 * uninitialized extent
+			 */
+			if (punched_out > EXT_UNINIT_MAX_LEN)
+				punched_out = EXT_UNINIT_MAX_LEN;
+
+			punch_map.m_lblk = map->m_lblk;
+			punch_map.m_pblk = newblock;
+			punch_map.m_len = punched_out;
+			punch_map.m_flags = 0;
+
+			/* Check to see if the extent needs to be split */
+			if (punch_map.m_len != ee_len ||
+				punch_map.m_lblk != ee_block) {
+
+				ret = ext4_split_extent(handle, inode,
+				path, &punch_map, 0,
+				EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
+				EXT4_GET_BLOCKS_PRE_IO);
+
+				if (ret < 0) {
+					err = ret;
+					goto out2;
+				}
+				/*
+				 * find extent for the block at
+				 * the start of the hole
+				 */
+				ext4_ext_drop_refs(path);
+				kfree(path);
+
+				path = ext4_ext_find_extent(inode,
+				map->m_lblk, NULL);
+				if (IS_ERR(path)) {
+					err = PTR_ERR(path);
+					path = NULL;
+					goto out2;
+				}
+
+				depth = ext_depth(inode);
+				ex = path[depth].p_ext;
+				ee_len = ext4_ext_get_actual_len(ex);
+				ee_block = le32_to_cpu(ex->ee_block);
+				ee_start = ext4_ext_pblock(ex);
+
+			}
+
+			ext4_ext_mark_uninitialized(ex);
+
+			err = ext4_ext_remove_space(inode, map->m_lblk,
+				map->m_lblk + punched_out);
+
+			goto out2;
+		}
+	}
+
+	/*
+	 * requested block isn't allocated yet;
+	 * we couldn't try to create block if create flag is zero
+	 */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		/*
+		 * put just found gap into cache to speed up
+		 * subsequent requests
+		 */
+		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+		goto out2;
+	}
+	/*
+	 * Okay, we need to do block allocation.
+	 */
+
+	/* find neighbour allocated blocks */
+	ar.lleft = map->m_lblk;
+	err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
+	if (err)
+		goto out2;
+	ar.lright = map->m_lblk;
+	err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+	if (err)
+		goto out2;
+
+	/*
+	 * See if request is beyond maximum number of blocks we can have in
+	 * a single extent. For an initialized extent this limit is
+	 * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
+	 * EXT_UNINIT_MAX_LEN.
+	 */
+	if (map->m_len > EXT_INIT_MAX_LEN &&
+	    !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
+		map->m_len = EXT_INIT_MAX_LEN;
+	else if (map->m_len > EXT_UNINIT_MAX_LEN &&
+		 (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
+		map->m_len = EXT_UNINIT_MAX_LEN;
+
+	/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
+	newex.ee_block = cpu_to_le32(map->m_lblk);
+	newex.ee_len = cpu_to_le16(map->m_len);
+	err = ext4_ext_check_overlap(inode, &newex, path);
+	if (err)
+		allocated = ext4_ext_get_actual_len(&newex);
+	else
+		allocated = map->m_len;
+
+	/* allocate new block */
+	ar.inode = inode;
+	ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
+	ar.logical = map->m_lblk;
+	ar.len = allocated;
+	if (S_ISREG(inode->i_mode))
+		ar.flags = EXT4_MB_HINT_DATA;
+	else
+		/* disable in-core preallocation for non-regular files */
+		ar.flags = 0;
+	if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE)
+		ar.flags |= EXT4_MB_HINT_NOPREALLOC;
+	newblock = ext4_mb_new_blocks(handle, &ar, &err);
+	if (!newblock)
+		goto out2;
+	ext_debug("allocate new block: goal %llu, found %llu/%u\n",
+		  ar.goal, newblock, allocated);
+
+	/* try to insert new extent into found leaf and return */
+	ext4_ext_store_pblock(&newex, newblock);
+	newex.ee_len = cpu_to_le16(ar.len);
+	/* Mark uninitialized */
+	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
+		ext4_ext_mark_uninitialized(&newex);
+		/*
+		 * io_end structure was created for every IO write to an
+		 * uninitialized extent. To avoid unnecessary conversion,
+		 * here we flag the IO that really needs the conversion.
+		 * For non asycn direct IO case, flag the inode state
+		 * that we need to perform conversion when IO is done.
+		 */
+		if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
+			if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
+				io->flag = EXT4_IO_END_UNWRITTEN;
+				atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+			} else
+				ext4_set_inode_state(inode,
+						     EXT4_STATE_DIO_UNWRITTEN);
+		}
+		if (ext4_should_dioread_nolock(inode))
+			map->m_flags |= EXT4_MAP_UNINIT;
+	}
+
+	err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
+	if (!err)
+		err = ext4_ext_insert_extent(handle, inode, path,
+					     &newex, flags);
+	if (err) {
+		int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
+			EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
+		/* free data blocks we just allocated */
+		/* not a good idea to call discard here directly,
+		 * but otherwise we'd need to call it every free() */
+		ext4_discard_preallocations(inode);
+		ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
+				 ext4_ext_get_actual_len(&newex), fb_flags);
+		goto out2;
+	}
+
+	/* previous routine could use block we allocated */
+	newblock = ext4_ext_pblock(&newex);
+	allocated = ext4_ext_get_actual_len(&newex);
+	if (allocated > map->m_len)
+		allocated = map->m_len;
+	map->m_flags |= EXT4_MAP_NEW;
+
+	/*
+	 * Update reserved blocks/metadata blocks after successful
+	 * block allocation which had been deferred till now.
+	 */
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ext4_da_update_reserve_space(inode, allocated, 1);
+
+	/*
+	 * Cache the extent and update transaction to commit on fdatasync only
+	 * when it is _not_ an uninitialized extent.
+	 */
+	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
+		ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock);
+		ext4_update_inode_fsync_trans(handle, inode, 1);
+	} else
+		ext4_update_inode_fsync_trans(handle, inode, 0);
+out:
+	if (allocated > map->m_len)
+		allocated = map->m_len;
+	ext4_ext_show_leaf(inode, path);
+	map->m_flags |= EXT4_MAP_MAPPED;
+	map->m_pblk = newblock;
+	map->m_len = allocated;
+out2:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+		newblock, map->m_len, err ? err : allocated);
+
+	result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
+			punched_out : allocated;
+
+	return err ? err : result;
+}
+
+void ext4_ext_truncate(struct inode *inode)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct super_block *sb = inode->i_sb;
+	ext4_lblk_t last_block;
+	handle_t *handle;
+	int err = 0;
+
+	/*
+	 * finish any pending end_io work so we won't run the risk of
+	 * converting any truncated blocks to initialized later
+	 */
+	ext4_flush_completed_IO(inode);
+
+	/*
+	 * probably first extent we're gonna free will be last in block
+	 */
+	err = ext4_writepage_trans_blocks(inode);
+	handle = ext4_journal_start(inode, err);
+	if (IS_ERR(handle))
+		return;
+
+	if (inode->i_size & (sb->s_blocksize - 1))
+		ext4_block_truncate_page(handle, mapping, inode->i_size);
+
+	if (ext4_orphan_add(handle, inode))
+		goto out_stop;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_ext_invalidate_cache(inode);
+
+	ext4_discard_preallocations(inode);
+
+	/*
+	 * TODO: optimization is possible here.
+	 * Probably we need not scan at all,
+	 * because page truncation is enough.
+	 */
+
+	/* we have to know where to truncate from in crash case */
+	EXT4_I(inode)->i_disksize = inode->i_size;
+	ext4_mark_inode_dirty(handle, inode);
+
+	last_block = (inode->i_size + sb->s_blocksize - 1)
+			>> EXT4_BLOCK_SIZE_BITS(sb);
+	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+
+	/* In a multi-transaction truncate, we only make the final
+	 * transaction synchronous.
+	 */
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+
+	up_write(&EXT4_I(inode)->i_data_sem);
+
+out_stop:
+	/*
+	 * If this was a simple ftruncate() and the file will remain alive,
+	 * then we need to clear up the orphan record which we created above.
+	 * However, if this was a real unlink then we were called by
+	 * ext4_delete_inode(), and we allow that function to clean up the
+	 * orphan info for us.
+	 */
+	if (inode->i_nlink)
+		ext4_orphan_del(handle, inode);
+
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+}
+
+static void ext4_falloc_update_inode(struct inode *inode,
+				int mode, loff_t new_size, int update_ctime)
+{
+	struct timespec now;
+
+	if (update_ctime) {
+		now = current_fs_time(inode->i_sb);
+		if (!timespec_equal(&inode->i_ctime, &now))
+			inode->i_ctime = now;
+	}
+	/*
+	 * Update only when preallocation was requested beyond
+	 * the file size.
+	 */
+	if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+		if (new_size > i_size_read(inode))
+			i_size_write(inode, new_size);
+		if (new_size > EXT4_I(inode)->i_disksize)
+			ext4_update_i_disksize(inode, new_size);
+	} else {
+		/*
+		 * Mark that we allocate beyond EOF so the subsequent truncate
+		 * can proceed even if the new size is the same as i_size.
+		 */
+		if (new_size > i_size_read(inode))
+			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+	}
+
+}
+
+/*
+ * preallocate space for a file. This implements ext4's fallocate file
+ * operation, which gets called from sys_fallocate system call.
+ * For block-mapped files, posix_fallocate should fall back to the method
+ * of writing zeroes to the required new blocks (the same behavior which is
+ * expected for file systems which do not support fallocate() system call).
+ */
+long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	handle_t *handle;
+	loff_t new_size;
+	unsigned int max_blocks;
+	int ret = 0;
+	int ret2 = 0;
+	int retries = 0;
+	struct ext4_map_blocks map;
+	unsigned int credits, blkbits = inode->i_blkbits;
+
+	/*
+	 * currently supporting (pre)allocate mode for extent-based
+	 * files _only_
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return -EOPNOTSUPP;
+
+	/* Return error if mode is not supported */
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		return ext4_punch_hole(file, offset, len);
+
+	trace_ext4_fallocate_enter(inode, offset, len, mode);
+	map.m_lblk = offset >> blkbits;
+	/*
+	 * We can't just convert len to max_blocks because
+	 * If blocksize = 4096 offset = 3072 and len = 2048
+	 */
+	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
+		- map.m_lblk;
+	/*
+	 * credits to insert 1 extent into extent tree
+	 */
+	credits = ext4_chunk_trans_blocks(inode, max_blocks);
+	mutex_lock(&inode->i_mutex);
+	ret = inode_newsize_ok(inode, (len + offset));
+	if (ret) {
+		mutex_unlock(&inode->i_mutex);
+		trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+		return ret;
+	}
+retry:
+	while (ret >= 0 && ret < max_blocks) {
+		map.m_lblk = map.m_lblk + ret;
+		map.m_len = max_blocks = max_blocks - ret;
+		handle = ext4_journal_start(inode, credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			break;
+		}
+		ret = ext4_map_blocks(handle, inode, &map,
+				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+				      EXT4_GET_BLOCKS_NO_NORMALIZE);
+		if (ret <= 0) {
+#ifdef EXT4FS_DEBUG
+			WARN_ON(ret <= 0);
+			printk(KERN_ERR "%s: ext4_ext_map_blocks "
+				    "returned error inode#%lu, block=%u, "
+				    "max_blocks=%u", __func__,
+				    inode->i_ino, map.m_lblk, max_blocks);
+#endif
+			ext4_mark_inode_dirty(handle, inode);
+			ret2 = ext4_journal_stop(handle);
+			break;
+		}
+		if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
+						blkbits) >> blkbits))
+			new_size = offset + len;
+		else
+			new_size = (map.m_lblk + ret) << blkbits;
+
+		ext4_falloc_update_inode(inode, mode, new_size,
+					 (map.m_flags & EXT4_MAP_NEW));
+		ext4_mark_inode_dirty(handle, inode);
+		ret2 = ext4_journal_stop(handle);
+		if (ret2)
+			break;
+	}
+	if (ret == -ENOSPC &&
+			ext4_should_retry_alloc(inode->i_sb, &retries)) {
+		ret = 0;
+		goto retry;
+	}
+	mutex_unlock(&inode->i_mutex);
+	trace_ext4_fallocate_exit(inode, offset, max_blocks,
+				ret > 0 ? ret2 : ret);
+	return ret > 0 ? ret2 : ret;
+}
+
+/*
+ * This function convert a range of blocks to written extents
+ * The caller of this function will pass the start offset and the size.
+ * all unwritten extents within this range will be converted to
+ * written extents.
+ *
+ * This function is called from the direct IO end io call back
+ * function, to convert the fallocated extents after IO is completed.
+ * Returns 0 on success.
+ */
+int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
+				    ssize_t len)
+{
+	handle_t *handle;
+	unsigned int max_blocks;
+	int ret = 0;
+	int ret2 = 0;
+	struct ext4_map_blocks map;
+	unsigned int credits, blkbits = inode->i_blkbits;
+
+	map.m_lblk = offset >> blkbits;
+	/*
+	 * We can't just convert len to max_blocks because
+	 * If blocksize = 4096 offset = 3072 and len = 2048
+	 */
+	max_blocks = ((EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) -
+		      map.m_lblk);
+	/*
+	 * credits to insert 1 extent into extent tree
+	 */
+	credits = ext4_chunk_trans_blocks(inode, max_blocks);
+	while (ret >= 0 && ret < max_blocks) {
+		map.m_lblk += ret;
+		map.m_len = (max_blocks -= ret);
+		handle = ext4_journal_start(inode, credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			break;
+		}
+		ret = ext4_map_blocks(handle, inode, &map,
+				      EXT4_GET_BLOCKS_IO_CONVERT_EXT);
+		if (ret <= 0) {
+			WARN_ON(ret <= 0);
+			printk(KERN_ERR "%s: ext4_ext_map_blocks "
+				    "returned error inode#%lu, block=%u, "
+				    "max_blocks=%u", __func__,
+				    inode->i_ino, map.m_lblk, map.m_len);
+		}
+		ext4_mark_inode_dirty(handle, inode);
+		ret2 = ext4_journal_stop(handle);
+		if (ret <= 0 || ret2 )
+			break;
+	}
+	return ret > 0 ? ret2 : ret;
+}
+
+/*
+ * Callback function called for each extent to gather FIEMAP information.
+ */
+static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next,
+		       struct ext4_ext_cache *newex, struct ext4_extent *ex,
+		       void *data)
+{
+	__u64	logical;
+	__u64	physical;
+	__u64	length;
+	__u32	flags = 0;
+	int		ret = 0;
+	struct fiemap_extent_info *fieinfo = data;
+	unsigned char blksize_bits;
+
+	blksize_bits = inode->i_sb->s_blocksize_bits;
+	logical = (__u64)newex->ec_block << blksize_bits;
+
+	if (newex->ec_start == 0) {
+		/*
+		 * No extent in extent-tree contains block @newex->ec_start,
+		 * then the block may stay in 1)a hole or 2)delayed-extent.
+		 *
+		 * Holes or delayed-extents are processed as follows.
+		 * 1. lookup dirty pages with specified range in pagecache.
+		 *    If no page is got, then there is no delayed-extent and
+		 *    return with EXT_CONTINUE.
+		 * 2. find the 1st mapped buffer,
+		 * 3. check if the mapped buffer is both in the request range
+		 *    and a delayed buffer. If not, there is no delayed-extent,
+		 *    then return.
+		 * 4. a delayed-extent is found, the extent will be collected.
+		 */
+		ext4_lblk_t	end = 0;
+		pgoff_t		last_offset;
+		pgoff_t		offset;
+		pgoff_t		index;
+		pgoff_t		start_index = 0;
+		struct page	**pages = NULL;
+		struct buffer_head *bh = NULL;
+		struct buffer_head *head = NULL;
+		unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *);
+
+		pages = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (pages == NULL)
+			return -ENOMEM;
+
+		offset = logical >> PAGE_SHIFT;
+repeat:
+		last_offset = offset;
+		head = NULL;
+		ret = find_get_pages_tag(inode->i_mapping, &offset,
+					PAGECACHE_TAG_DIRTY, nr_pages, pages);
+
+		if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
+			/* First time, try to find a mapped buffer. */
+			if (ret == 0) {
+out:
+				for (index = 0; index < ret; index++)
+					page_cache_release(pages[index]);
+				/* just a hole. */
+				kfree(pages);
+				return EXT_CONTINUE;
+			}
+			index = 0;
+
+next_page:
+			/* Try to find the 1st mapped buffer. */
+			end = ((__u64)pages[index]->index << PAGE_SHIFT) >>
+				  blksize_bits;
+			if (!page_has_buffers(pages[index]))
+				goto out;
+			head = page_buffers(pages[index]);
+			if (!head)
+				goto out;
+
+			index++;
+			bh = head;
+			do {
+				if (end >= newex->ec_block +
+					newex->ec_len)
+					/* The buffer is out of
+					 * the request range.
+					 */
+					goto out;
+
+				if (buffer_mapped(bh) &&
+				    end >= newex->ec_block) {
+					start_index = index - 1;
+					/* get the 1st mapped buffer. */
+					goto found_mapped_buffer;
+				}
+
+				bh = bh->b_this_page;
+				end++;
+			} while (bh != head);
+
+			/* No mapped buffer in the range found in this page,
+			 * We need to look up next page.
+			 */
+			if (index >= ret) {
+				/* There is no page left, but we need to limit
+				 * newex->ec_len.
+				 */
+				newex->ec_len = end - newex->ec_block;
+				goto out;
+			}
+			goto next_page;
+		} else {
+			/*Find contiguous delayed buffers. */
+			if (ret > 0 && pages[0]->index == last_offset)
+				head = page_buffers(pages[0]);
+			bh = head;
+			index = 1;
+			start_index = 0;
+		}
+
+found_mapped_buffer:
+		if (bh != NULL && buffer_delay(bh)) {
+			/* 1st or contiguous delayed buffer found. */
+			if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
+				/*
+				 * 1st delayed buffer found, record
+				 * the start of extent.
+				 */
+				flags |= FIEMAP_EXTENT_DELALLOC;
+				newex->ec_block = end;
+				logical = (__u64)end << blksize_bits;
+			}
+			/* Find contiguous delayed buffers. */
+			do {
+				if (!buffer_delay(bh))
+					goto found_delayed_extent;
+				bh = bh->b_this_page;
+				end++;
+			} while (bh != head);
+
+			for (; index < ret; index++) {
+				if (!page_has_buffers(pages[index])) {
+					bh = NULL;
+					break;
+				}
+				head = page_buffers(pages[index]);
+				if (!head) {
+					bh = NULL;
+					break;
+				}
+
+				if (pages[index]->index !=
+				    pages[start_index]->index + index
+				    - start_index) {
+					/* Blocks are not contiguous. */
+					bh = NULL;
+					break;
+				}
+				bh = head;
+				do {
+					if (!buffer_delay(bh))
+						/* Delayed-extent ends. */
+						goto found_delayed_extent;
+					bh = bh->b_this_page;
+					end++;
+				} while (bh != head);
+			}
+		} else if (!(flags & FIEMAP_EXTENT_DELALLOC))
+			/* a hole found. */
+			goto out;
+
+found_delayed_extent:
+		newex->ec_len = min(end - newex->ec_block,
+						(ext4_lblk_t)EXT_INIT_MAX_LEN);
+		if (ret == nr_pages && bh != NULL &&
+			newex->ec_len < EXT_INIT_MAX_LEN &&
+			buffer_delay(bh)) {
+			/* Have not collected an extent and continue. */
+			for (index = 0; index < ret; index++)
+				page_cache_release(pages[index]);
+			goto repeat;
+		}
+
+		for (index = 0; index < ret; index++)
+			page_cache_release(pages[index]);
+		kfree(pages);
+	}
+
+	physical = (__u64)newex->ec_start << blksize_bits;
+	length =   (__u64)newex->ec_len << blksize_bits;
+
+	if (ex && ext4_ext_is_uninitialized(ex))
+		flags |= FIEMAP_EXTENT_UNWRITTEN;
+
+	if (next == EXT_MAX_BLOCKS)
+		flags |= FIEMAP_EXTENT_LAST;
+
+	ret = fiemap_fill_next_extent(fieinfo, logical, physical,
+					length, flags);
+	if (ret < 0)
+		return ret;
+	if (ret == 1)
+		return EXT_BREAK;
+	return EXT_CONTINUE;
+}
+
+/* fiemap flags we can handle specified here */
+#define EXT4_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
+
+static int ext4_xattr_fiemap(struct inode *inode,
+				struct fiemap_extent_info *fieinfo)
+{
+	__u64 physical = 0;
+	__u64 length;
+	__u32 flags = FIEMAP_EXTENT_LAST;
+	int blockbits = inode->i_sb->s_blocksize_bits;
+	int error = 0;
+
+	/* in-inode? */
+	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
+		struct ext4_iloc iloc;
+		int offset;	/* offset of xattr in inode */
+
+		error = ext4_get_inode_loc(inode, &iloc);
+		if (error)
+			return error;
+		physical = iloc.bh->b_blocknr << blockbits;
+		offset = EXT4_GOOD_OLD_INODE_SIZE +
+				EXT4_I(inode)->i_extra_isize;
+		physical += offset;
+		length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
+		flags |= FIEMAP_EXTENT_DATA_INLINE;
+		brelse(iloc.bh);
+	} else { /* external block */
+		physical = EXT4_I(inode)->i_file_acl << blockbits;
+		length = inode->i_sb->s_blocksize;
+	}
+
+	if (physical)
+		error = fiemap_fill_next_extent(fieinfo, 0, physical,
+						length, flags);
+	return (error < 0 ? error : 0);
+}
+
+/*
+ * ext4_ext_punch_hole
+ *
+ * Punches a hole of "length" bytes in a file starting
+ * at byte "offset"
+ *
+ * @inode:  The inode of the file to punch a hole in
+ * @offset: The starting byte offset of the hole
+ * @length: The length of the hole
+ *
+ * Returns the number of blocks removed or negative on err
+ */
+int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct ext4_ext_cache cache_ex;
+	ext4_lblk_t first_block, last_block, num_blocks, iblock, max_blocks;
+	struct address_space *mapping = inode->i_mapping;
+	struct ext4_map_blocks map;
+	handle_t *handle;
+	loff_t first_block_offset, last_block_offset, block_len;
+	loff_t first_page, last_page, first_page_offset, last_page_offset;
+	int ret, credits, blocks_released, err = 0;
+
+	first_block = (offset + sb->s_blocksize - 1) >>
+		EXT4_BLOCK_SIZE_BITS(sb);
+	last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+	first_block_offset = first_block << EXT4_BLOCK_SIZE_BITS(sb);
+	last_block_offset = last_block << EXT4_BLOCK_SIZE_BITS(sb);
+
+	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
+
+	first_page_offset = first_page << PAGE_CACHE_SHIFT;
+	last_page_offset = last_page << PAGE_CACHE_SHIFT;
+
+	/*
+	 * Write out all dirty pages to avoid race conditions
+	 * Then release them.
+	 */
+	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+		err = filemap_write_and_wait_range(mapping,
+			first_page_offset == 0 ? 0 : first_page_offset-1,
+			last_page_offset);
+
+			if (err)
+				return err;
+	}
+
+	/* Now release the pages */
+	if (last_page_offset > first_page_offset) {
+		truncate_inode_pages_range(mapping, first_page_offset,
+					   last_page_offset-1);
+	}
+
+	/* finish any pending end_io work */
+	ext4_flush_completed_IO(inode);
+
+	credits = ext4_writepage_trans_blocks(inode);
+	handle = ext4_journal_start(inode, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	err = ext4_orphan_add(handle, inode);
+	if (err)
+		goto out;
+
+	/*
+	 * Now we need to zero out the un block aligned data.
+	 * If the file is smaller than a block, just
+	 * zero out the middle
+	 */
+	if (first_block > last_block)
+		ext4_block_zero_page_range(handle, mapping, offset, length);
+	else {
+		/* zero out the head of the hole before the first block */
+		block_len  = first_block_offset - offset;
+		if (block_len > 0)
+			ext4_block_zero_page_range(handle, mapping,
+						   offset, block_len);
+
+		/* zero out the tail of the hole after the last block */
+		block_len = offset + length - last_block_offset;
+		if (block_len > 0) {
+			ext4_block_zero_page_range(handle, mapping,
+					last_block_offset, block_len);
+		}
+	}
+
+	/* If there are no blocks to remove, return now */
+	if (first_block >= last_block)
+		goto out;
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_ext_invalidate_cache(inode);
+	ext4_discard_preallocations(inode);
+
+	/*
+	 * Loop over all the blocks and identify blocks
+	 * that need to be punched out
+	 */
+	iblock = first_block;
+	blocks_released = 0;
+	while (iblock < last_block) {
+		max_blocks = last_block - iblock;
+		num_blocks = 1;
+		memset(&map, 0, sizeof(map));
+		map.m_lblk = iblock;
+		map.m_len = max_blocks;
+		ret = ext4_ext_map_blocks(handle, inode, &map,
+			EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+
+		if (ret > 0) {
+			blocks_released += ret;
+			num_blocks = ret;
+		} else if (ret == 0) {
+			/*
+			 * If map blocks could not find the block,
+			 * then it is in a hole.  If the hole was
+			 * not already cached, then map blocks should
+			 * put it in the cache.  So we can get the hole
+			 * out of the cache
+			 */
+			memset(&cache_ex, 0, sizeof(cache_ex));
+			if ((ext4_ext_check_cache(inode, iblock, &cache_ex)) &&
+				!cache_ex.ec_start) {
+
+				/* The hole is cached */
+				num_blocks = cache_ex.ec_block +
+				cache_ex.ec_len - iblock;
+
+			} else {
+				/* The block could not be identified */
+				err = -EIO;
+				break;
+			}
+		} else {
+			/* Map blocks error */
+			err = ret;
+			break;
+		}
+
+		if (num_blocks == 0) {
+			/* This condition should never happen */
+			ext_debug("Block lookup failed");
+			err = -EIO;
+			break;
+		}
+
+		iblock += num_blocks;
+	}
+
+	if (blocks_released > 0) {
+		ext4_ext_invalidate_cache(inode);
+		ext4_discard_preallocations(inode);
+	}
+
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+
+	up_write(&EXT4_I(inode)->i_data_sem);
+
+out:
+	ext4_orphan_del(handle, inode);
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+	return err;
+}
+int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		__u64 start, __u64 len)
+{
+	ext4_lblk_t start_blk;
+	int error = 0;
+
+	/* fallback to generic here if not in extents fmt */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return generic_block_fiemap(inode, fieinfo, start, len,
+			ext4_get_block);
+
+	if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS))
+		return -EBADR;
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+		error = ext4_xattr_fiemap(inode, fieinfo);
+	} else {
+		ext4_lblk_t len_blks;
+		__u64 last_blk;
+
+		start_blk = start >> inode->i_sb->s_blocksize_bits;
+		last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
+		if (last_blk >= EXT_MAX_BLOCKS)
+			last_blk = EXT_MAX_BLOCKS-1;
+		len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
+
+		/*
+		 * Walk the extent tree gathering extent information.
+		 * ext4_ext_fiemap_cb will push extents back to user.
+		 */
+		error = ext4_ext_walk_space(inode, start_blk, len_blks,
+					  ext4_ext_fiemap_cb, fieinfo);
+	}
+
+	return error;
+}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
new file mode 100644
index 00000000..2c097232
--- /dev/null
+++ b/fs/ext4/file.c
@@ -0,0 +1,286 @@
+/*
+ *  linux/fs/ext4/file.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/file.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4 fs regular file handling primitives
+ *
+ *  64-bit file support on 64-bit platforms by Jakub Jelinek
+ *	(jj@sunsite.ms.mff.cuni.cz)
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/mount.h>
+#include <linux/path.h>
+#include <linux/quotaops.h>
+#include "ext4.h"
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Called when an inode is released. Note that this is different
+ * from ext4_file_open: open gets called at every open, but release
+ * gets called only when /all/ the files are closed.
+ */
+static int ext4_release_file(struct inode *inode, struct file *filp)
+{
+	if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
+		ext4_alloc_da_blocks(inode);
+		ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
+	}
+	/* if we are the last writer on the inode, drop the block reservation */
+	if ((filp->f_mode & FMODE_WRITE) &&
+			(atomic_read(&inode->i_writecount) == 1) &&
+		        !EXT4_I(inode)->i_reserved_data_blocks)
+	{
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ext4_discard_preallocations(inode);
+		up_write(&EXT4_I(inode)->i_data_sem);
+	}
+	if (is_dx(inode) && filp->private_data)
+		ext4_htree_free_dir_info(filp->private_data);
+
+	return 0;
+}
+
+static void ext4_aiodio_wait(struct inode *inode)
+{
+	wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+}
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete.  Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block.  If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+		   unsigned long nr_segs, loff_t pos)
+{
+	struct super_block *sb = inode->i_sb;
+	int blockmask = sb->s_blocksize - 1;
+	size_t count = iov_length(iov, nr_segs);
+	loff_t final_size = pos + count;
+
+	if (pos >= inode->i_size)
+		return 0;
+
+	if ((pos & blockmask) || (final_size & blockmask))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t
+ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
+		unsigned long nr_segs, loff_t pos)
+{
+	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+	int unaligned_aio = 0;
+	int ret;
+
+	/*
+	 * If we have encountered a bitmap-format file, the size limit
+	 * is smaller than s_maxbytes, which is for extent-mapped files.
+	 */
+
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+		size_t length = iov_length(iov, nr_segs);
+
+		if ((pos > sbi->s_bitmap_maxbytes ||
+		    (pos == sbi->s_bitmap_maxbytes && length > 0)))
+			return -EFBIG;
+
+		if (pos + length > sbi->s_bitmap_maxbytes) {
+			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
+					      sbi->s_bitmap_maxbytes - pos);
+		}
+	} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
+		   !is_sync_kiocb(iocb))) {
+		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+	}
+
+	/* Unaligned direct AIO must be serialized; see comment above */
+	if (unaligned_aio) {
+		static unsigned long unaligned_warn_time;
+
+		/* Warn about this once per day */
+		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+			ext4_msg(inode->i_sb, KERN_WARNING,
+				 "Unaligned AIO/DIO on inode %ld by %s; "
+				 "performance will be poor.",
+				 inode->i_ino, current->comm);
+		mutex_lock(ext4_aio_mutex(inode));
+		ext4_aiodio_wait(inode);
+	}
+
+	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+	if (unaligned_aio)
+		mutex_unlock(ext4_aio_mutex(inode));
+
+	return ret;
+}
+
+static const struct vm_operations_struct ext4_file_vm_ops = {
+	.fault		= filemap_fault,
+	.page_mkwrite   = ext4_page_mkwrite,
+};
+
+static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	if (!mapping->a_ops->readpage)
+		return -ENOEXEC;
+	file_accessed(file);
+	vma->vm_ops = &ext4_file_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
+	return 0;
+}
+
+static int ext4_file_open(struct inode * inode, struct file * filp)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct vfsmount *mnt = filp->f_path.mnt;
+	struct path path;
+	char buf[64], *cp;
+
+	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
+		     !(sb->s_flags & MS_RDONLY))) {
+		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+		/*
+		 * Sample where the filesystem has been mounted and
+		 * store it in the superblock for sysadmin convenience
+		 * when trying to sort through large numbers of block
+		 * devices or filesystem images.
+		 */
+		memset(buf, 0, sizeof(buf));
+		path.mnt = mnt;
+		path.dentry = mnt->mnt_root;
+		cp = d_path(&path, buf, sizeof(buf));
+		if (!IS_ERR(cp)) {
+			memcpy(sbi->s_es->s_last_mounted, cp,
+			       sizeof(sbi->s_es->s_last_mounted));
+			ext4_mark_super_dirty(sb);
+		}
+	}
+	/*
+	 * Set up the jbd2_inode if we are opening the inode for
+	 * writing and the journal is present
+	 */
+	if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
+		struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
+
+		spin_lock(&inode->i_lock);
+		if (!ei->jinode) {
+			if (!jinode) {
+				spin_unlock(&inode->i_lock);
+				return -ENOMEM;
+			}
+			ei->jinode = jinode;
+			jbd2_journal_init_jbd_inode(ei->jinode, inode);
+			jinode = NULL;
+		}
+		spin_unlock(&inode->i_lock);
+		if (unlikely(jinode != NULL))
+			jbd2_free_inode(jinode);
+	}
+	return dquot_file_open(inode, filp);
+}
+
+/*
+ * ext4_llseek() copied from generic_file_llseek() to handle both
+ * block-mapped and extent-mapped maxbytes values. This should
+ * otherwise be identical with generic_file_llseek().
+ */
+loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t maxbytes;
+
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
+	else
+		maxbytes = inode->i_sb->s_maxbytes;
+	mutex_lock(&inode->i_mutex);
+	switch (origin) {
+	case SEEK_END:
+		offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		if (offset == 0) {
+			mutex_unlock(&inode->i_mutex);
+			return file->f_pos;
+		}
+		offset += file->f_pos;
+		break;
+	}
+
+	if (offset < 0 || offset > maxbytes) {
+		mutex_unlock(&inode->i_mutex);
+		return -EINVAL;
+	}
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	mutex_unlock(&inode->i_mutex);
+
+	return offset;
+}
+
+const struct file_operations ext4_file_operations = {
+	.llseek		= ext4_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= ext4_file_write,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.mmap		= ext4_file_mmap,
+	.open		= ext4_file_open,
+	.release	= ext4_release_file,
+	.fsync		= ext4_sync_file,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.fallocate	= ext4_fallocate,
+};
+
+const struct inode_operations ext4_file_inode_operations = {
+	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
+#ifdef CONFIG_EXT4_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext4_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.check_acl	= ext4_check_acl,
+	.fiemap		= ext4_fiemap,
+};
+
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
new file mode 100644
index 00000000..ce66d2fe
--- /dev/null
+++ b/fs/ext4/fsync.c
@@ -0,0 +1,225 @@
+/*
+ *  linux/fs/ext4/fsync.c
+ *
+ *  Copyright (C) 1993  Stephen Tweedie (sct@redhat.com)
+ *  from
+ *  Copyright (C) 1992  Remy Card (card@masi.ibp.fr)
+ *                      Laboratoire MASI - Institut Blaise Pascal
+ *                      Universite Pierre et Marie Curie (Paris VI)
+ *  from
+ *  linux/fs/minix/truncate.c   Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4fs fsync primitive
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ *  Removed unnecessary code duplication for little endian machines
+ *  and excessive __inline__s.
+ *        Andi Kleen, 1997
+ *
+ * Major simplications and cleanup - we only need to do the metadata, because
+ * we can depend on generic_block_fdatasync() to sync the data blocks.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
+#include <linux/jbd2.h>
+#include <linux/blkdev.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+
+#include <trace/events/ext4.h>
+
+static void dump_completed_IO(struct inode * inode)
+{
+#ifdef	EXT4FS_DEBUG
+	struct list_head *cur, *before, *after;
+	ext4_io_end_t *io, *io0, *io1;
+	unsigned long flags;
+
+	if (list_empty(&EXT4_I(inode)->i_completed_io_list)){
+		ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
+		return;
+	}
+
+	ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino);
+	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+	list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){
+		cur = &io->list;
+		before = cur->prev;
+		io0 = container_of(before, ext4_io_end_t, list);
+		after = cur->next;
+		io1 = container_of(after, ext4_io_end_t, list);
+
+		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
+			    io, inode->i_ino, io0, io1);
+	}
+	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
+#endif
+}
+
+/*
+ * This function is called from ext4_sync_file().
+ *
+ * When IO is completed, the work to convert unwritten extents to
+ * written is queued on workqueue but may not get immediately
+ * scheduled. When fsync is called, we need to ensure the
+ * conversion is complete before fsync returns.
+ * The inode keeps track of a list of pending/completed IO that
+ * might needs to do the conversion. This function walks through
+ * the list and convert the related unwritten extents for completed IO
+ * to written.
+ * The function return the number of pending IOs on success.
+ */
+extern int ext4_flush_completed_IO(struct inode *inode)
+{
+	ext4_io_end_t *io;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned long flags;
+	int ret = 0;
+	int ret2 = 0;
+
+	if (list_empty(&ei->i_completed_io_list))
+		return ret;
+
+	dump_completed_IO(inode);
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	while (!list_empty(&ei->i_completed_io_list)){
+		io = list_entry(ei->i_completed_io_list.next,
+				ext4_io_end_t, list);
+		/*
+		 * Calling ext4_end_io_nolock() to convert completed
+		 * IO to written.
+		 *
+		 * When ext4_sync_file() is called, run_queue() may already
+		 * about to flush the work corresponding to this io structure.
+		 * It will be upset if it founds the io structure related
+		 * to the work-to-be schedule is freed.
+		 *
+		 * Thus we need to keep the io structure still valid here after
+		 * conversion finished. The io structure has a flag to
+		 * avoid double converting from both fsync and background work
+		 * queue work.
+		 */
+		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+		ret = ext4_end_io_nolock(io);
+		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+		if (ret < 0)
+			ret2 = ret;
+		else
+			list_del_init(&io->list);
+	}
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+	return (ret2 < 0) ? ret2 : 0;
+}
+
+/*
+ * If we're not journaling and this is a just-created file, we have to
+ * sync our parent directory (if it was freshly created) since
+ * otherwise it will only be written by writeback, leaving a huge
+ * window during which a crash may lose the file.  This may apply for
+ * the parent directory's parent as well, and so on recursively, if
+ * they are also freshly created.
+ */
+static int ext4_sync_parent(struct inode *inode)
+{
+	struct writeback_control wbc;
+	struct dentry *dentry = NULL;
+	int ret = 0;
+
+	while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
+		dentry = list_entry(inode->i_dentry.next,
+				    struct dentry, d_alias);
+		if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+			break;
+		inode = dentry->d_parent->d_inode;
+		ret = sync_mapping_buffers(inode->i_mapping);
+		if (ret)
+			break;
+		memset(&wbc, 0, sizeof(wbc));
+		wbc.sync_mode = WB_SYNC_ALL;
+		wbc.nr_to_write = 0;         /* only write out the inode */
+		ret = sync_inode(inode, &wbc);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+/*
+ * akpm: A new design for ext4_sync_file().
+ *
+ * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
+ * There cannot be a transaction open by this task.
+ * Another task could have dirtied this inode.  Its data can be in any
+ * state in the journalling system.
+ *
+ * What we do is just kick off a commit and wait on it.  This will snapshot the
+ * inode to disk.
+ *
+ * i_mutex lock is held when entering and exiting this function
+ */
+
+int ext4_sync_file(struct file *file, int datasync)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+	int ret;
+	tid_t commit_tid;
+	bool needs_barrier = false;
+
+	J_ASSERT(ext4_journal_current_handle() == NULL);
+
+	trace_ext4_sync_file_enter(file, datasync);
+
+	if (inode->i_sb->s_flags & MS_RDONLY)
+		return 0;
+
+	ret = ext4_flush_completed_IO(inode);
+	if (ret < 0)
+		goto out;
+
+	if (!journal) {
+		ret = generic_file_fsync(file, datasync);
+		if (!ret && !list_empty(&inode->i_dentry))
+			ret = ext4_sync_parent(inode);
+		goto out;
+	}
+
+	/*
+	 * data=writeback,ordered:
+	 *  The caller's filemap_fdatawrite()/wait will sync the data.
+	 *  Metadata is in the journal, we wait for proper transaction to
+	 *  commit here.
+	 *
+	 * data=journal:
+	 *  filemap_fdatawrite won't do anything (the buffers are clean).
+	 *  ext4_force_commit will write the file data into the journal and
+	 *  will wait on that.
+	 *  filemap_fdatawait() will encounter a ton of newly-dirtied pages
+	 *  (they were dirtied by commit).  But that's OK - the blocks are
+	 *  safe in-journal, which is all fsync() needs to ensure.
+	 */
+	if (ext4_should_journal_data(inode)) {
+		ret = ext4_force_commit(inode->i_sb);
+		goto out;
+	}
+
+	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+	if (journal->j_flags & JBD2_BARRIER &&
+	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+		needs_barrier = true;
+	jbd2_log_start_commit(journal, commit_tid);
+	ret = jbd2_log_wait_commit(journal, commit_tid);
+	if (needs_barrier)
+		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+ out:
+	trace_ext4_sync_file_exit(inode, ret);
+	return ret;
+}
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
new file mode 100644
index 00000000..ac8f168c
--- /dev/null
+++ b/fs/ext4/hash.c
@@ -0,0 +1,208 @@
+/*
+ *  linux/fs/ext4/hash.c
+ *
+ * Copyright (C) 2002 by Theodore Ts'o
+ *
+ * This file is released under the GPL v2.
+ *
+ * This file may be redistributed under the terms of the GNU Public
+ * License.
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/cryptohash.h>
+#include "ext4.h"
+
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(__u32 buf[4], __u32 const in[])
+{
+	__u32	sum = 0;
+	__u32	b0 = buf[0], b1 = buf[1];
+	__u32	a = in[0], b = in[1], c = in[2], d = in[3];
+	int	n = 16;
+
+	do {
+		sum += DELTA;
+		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+	} while (--n);
+
+	buf[0] += b0;
+	buf[1] += b1;
+}
+
+
+/* The old legacy hash */
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const unsigned char *ucp = (const unsigned char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const signed char *scp = (const signed char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) scp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) ucp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+/*
+ * Returns the hash of a filename.  If len is 0 and name is NULL, then
+ * this function can be used to test whether or not a hash version is
+ * supported.
+ *
+ * The seed is an 4 longword (32 bits) "secret" which can be used to
+ * uniquify a hash.  If the seed is all zero's, then some default seed
+ * may be used.
+ *
+ * A particular hash version specifies whether or not the seed is
+ * represented, and whether or not the returned hash is 32 bits or 64
+ * bits.  32 bit hashes will return 0 for the minor hash.
+ */
+int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
+{
+	__u32	hash;
+	__u32	minor_hash = 0;
+	const char	*p;
+	int		i;
+	__u32		in[8], buf[4];
+	void		(*str2hashbuf)(const char *, int, __u32 *, int) =
+				str2hashbuf_signed;
+
+	/* Initialize the default seed for the hash checksum functions */
+	buf[0] = 0x67452301;
+	buf[1] = 0xefcdab89;
+	buf[2] = 0x98badcfe;
+	buf[3] = 0x10325476;
+
+	/* Check to see if the seed is all zero's */
+	if (hinfo->seed) {
+		for (i = 0; i < 4; i++) {
+			if (hinfo->seed[i])
+				break;
+		}
+		if (i < 4)
+			memcpy(buf, hinfo->seed, sizeof(buf));
+	}
+
+	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY_UNSIGNED:
+		hash = dx_hack_hash_unsigned(name, len);
+		break;
+	case DX_HASH_LEGACY:
+		hash = dx_hack_hash_signed(name, len);
+		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
+	case DX_HASH_HALF_MD4:
+		p = name;
+		while (len > 0) {
+			(*str2hashbuf)(p, len, in, 8);
+			half_md4_transform(buf, in);
+			len -= 32;
+			p += 32;
+		}
+		minor_hash = buf[2];
+		hash = buf[1];
+		break;
+	case DX_HASH_TEA_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
+	case DX_HASH_TEA:
+		p = name;
+		while (len > 0) {
+			(*str2hashbuf)(p, len, in, 4);
+			TEA_transform(buf, in);
+			len -= 16;
+			p += 16;
+		}
+		hash = buf[0];
+		minor_hash = buf[1];
+		break;
+	default:
+		hinfo->hash = 0;
+		return -1;
+	}
+	hash = hash & ~1;
+	if (hash == (EXT4_HTREE_EOF << 1))
+		hash = (EXT4_HTREE_EOF-1) << 1;
+	hinfo->hash = hash;
+	hinfo->minor_hash = minor_hash;
+	return 0;
+}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
new file mode 100644
index 00000000..412469b2
--- /dev/null
+++ b/fs/ext4/ialloc.c
@@ -0,0 +1,1338 @@
+/*
+ *  linux/fs/ext4/ialloc.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  BSD ufs-inspired inode and directory allocation by
+ *  Stephen Tweedie (sct@redhat.com), 1993
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/random.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <asm/byteorder.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+
+#include <trace/events/ext4.h>
+
+/*
+ * ialloc.c contains the inodes allocation and deallocation routines
+ */
+
+/*
+ * The free inodes are managed by bitmaps.  A file system contains several
+ * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
+ * block for inodes, N blocks for the inode table and data blocks.
+ *
+ * The file system contains group descriptors which are located after the
+ * super block.  Each descriptor contains the number of the bitmap block and
+ * the free blocks count in the block.
+ */
+
+/*
+ * To avoid calling the atomic setbit hundreds or thousands of times, we only
+ * need to use it within a single byte (to ensure we get endianness right).
+ * We can use memset for the rest of the bitmap as there are no other users.
+ */
+void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+{
+	int i;
+
+	if (start_bit >= end_bit)
+		return;
+
+	ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
+	for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
+		ext4_set_bit(i, bitmap);
+	if (i < end_bit)
+		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
+}
+
+/* Initializes an uninitialized inode bitmap */
+static unsigned ext4_init_inode_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t block_group,
+				       struct ext4_group_desc *gdp)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	J_ASSERT_BH(bh, buffer_locked(bh));
+
+	/* If checksum is bad mark all blocks and inodes use to prevent
+	 * allocation, essentially implementing a per-group read-only flag. */
+	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+		ext4_error(sb, "Checksum bad for group %u", block_group);
+		ext4_free_blks_set(sb, gdp, 0);
+		ext4_free_inodes_set(sb, gdp, 0);
+		ext4_itable_unused_set(sb, gdp, 0);
+		memset(bh->b_data, 0xff, sb->s_blocksize);
+		return 0;
+	}
+
+	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
+	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+			bh->b_data);
+
+	return EXT4_INODES_PER_GROUP(sb);
+}
+
+/*
+ * Read the inode allocation bitmap for a given block_group, reading
+ * into the specified slot in the superblock's bitmap cache.
+ *
+ * Return buffer_head of bitmap on success or NULL.
+ */
+static struct buffer_head *
+ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
+{
+	struct ext4_group_desc *desc;
+	struct buffer_head *bh = NULL;
+	ext4_fsblk_t bitmap_blk;
+
+	desc = ext4_get_group_desc(sb, block_group, NULL);
+	if (!desc)
+		return NULL;
+
+	bitmap_blk = ext4_inode_bitmap(sb, desc);
+	bh = sb_getblk(sb, bitmap_blk);
+	if (unlikely(!bh)) {
+		ext4_error(sb, "Cannot read inode bitmap - "
+			    "block_group = %u, inode_bitmap = %llu",
+			    block_group, bitmap_blk);
+		return NULL;
+	}
+	if (bitmap_uptodate(bh))
+		return bh;
+
+	lock_buffer(bh);
+	if (bitmap_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	}
+
+	ext4_lock_group(sb, block_group);
+	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+		ext4_init_inode_bitmap(sb, bh, block_group, desc);
+		set_bitmap_uptodate(bh);
+		set_buffer_uptodate(bh);
+		ext4_unlock_group(sb, block_group);
+		unlock_buffer(bh);
+		return bh;
+	}
+	ext4_unlock_group(sb, block_group);
+
+	if (buffer_uptodate(bh)) {
+		/*
+		 * if not uninit if bh is uptodate,
+		 * bitmap is also uptodate
+		 */
+		set_bitmap_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
+	}
+	/*
+	 * submit the buffer_head for read. We can
+	 * safely mark the bitmap as uptodate now.
+	 * We do it here so the bitmap uptodate bit
+	 * get set with buffer lock held.
+	 */
+	trace_ext4_load_inode_bitmap(sb, block_group);
+	set_bitmap_uptodate(bh);
+	if (bh_submit_read(bh) < 0) {
+		put_bh(bh);
+		ext4_error(sb, "Cannot read inode bitmap - "
+			    "block_group = %u, inode_bitmap = %llu",
+			    block_group, bitmap_blk);
+		return NULL;
+	}
+	return bh;
+}
+
+/*
+ * NOTE! When we get the inode, we're the only people
+ * that have access to it, and as such there are no
+ * race conditions we have to worry about. The inode
+ * is not on the hash-lists, and it cannot be reached
+ * through the filesystem because the directory entry
+ * has been deleted earlier.
+ *
+ * HOWEVER: we must make sure that we get no aliases,
+ * which means that we have to call "clear_inode()"
+ * _before_ we mark the inode not in use in the inode
+ * bitmaps. Otherwise a newly created file might use
+ * the same inode number (not actually the same pointer
+ * though), and then we'd have two inodes sharing the
+ * same inode number and space on the harddisk.
+ */
+void ext4_free_inode(handle_t *handle, struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	int is_directory;
+	unsigned long ino;
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *bh2;
+	ext4_group_t block_group;
+	unsigned long bit;
+	struct ext4_group_desc *gdp;
+	struct ext4_super_block *es;
+	struct ext4_sb_info *sbi;
+	int fatal = 0, err, count, cleared;
+
+	if (atomic_read(&inode->i_count) > 1) {
+		printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
+		       atomic_read(&inode->i_count));
+		return;
+	}
+	if (inode->i_nlink) {
+		printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
+		       inode->i_nlink);
+		return;
+	}
+	if (!sb) {
+		printk(KERN_ERR "ext4_free_inode: inode on "
+		       "nonexistent device\n");
+		return;
+	}
+	sbi = EXT4_SB(sb);
+
+	ino = inode->i_ino;
+	ext4_debug("freeing inode %lu\n", ino);
+	trace_ext4_free_inode(inode);
+
+	/*
+	 * Note: we must free any quota before locking the superblock,
+	 * as writing the quota to disk may need the lock as well.
+	 */
+	dquot_initialize(inode);
+	ext4_xattr_delete_inode(handle, inode);
+	dquot_free_inode(inode);
+	dquot_drop(inode);
+
+	is_directory = S_ISDIR(inode->i_mode);
+
+	/* Do this BEFORE marking the inode not in use or returning an error */
+	ext4_clear_inode(inode);
+
+	es = EXT4_SB(sb)->s_es;
+	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
+		ext4_error(sb, "reserved or nonexistent inode %lu", ino);
+		goto error_return;
+	}
+	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+
+	BUFFER_TRACE(bitmap_bh, "get_write_access");
+	fatal = ext4_journal_get_write_access(handle, bitmap_bh);
+	if (fatal)
+		goto error_return;
+
+	fatal = -ESRCH;
+	gdp = ext4_get_group_desc(sb, block_group, &bh2);
+	if (gdp) {
+		BUFFER_TRACE(bh2, "get_write_access");
+		fatal = ext4_journal_get_write_access(handle, bh2);
+	}
+	ext4_lock_group(sb, block_group);
+	cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+	if (fatal || !cleared) {
+		ext4_unlock_group(sb, block_group);
+		goto out;
+	}
+
+	count = ext4_free_inodes_count(sb, gdp) + 1;
+	ext4_free_inodes_set(sb, gdp, count);
+	if (is_directory) {
+		count = ext4_used_dirs_count(sb, gdp) - 1;
+		ext4_used_dirs_set(sb, gdp, count);
+		percpu_counter_dec(&sbi->s_dirs_counter);
+	}
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
+	ext4_unlock_group(sb, block_group);
+
+	percpu_counter_inc(&sbi->s_freeinodes_counter);
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t f = ext4_flex_group(sbi, block_group);
+
+		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+		if (is_directory)
+			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+	}
+	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
+out:
+	if (cleared) {
+		BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+		if (!fatal)
+			fatal = err;
+		ext4_mark_super_dirty(sb);
+	} else
+		ext4_error(sb, "bit already cleared for inode %lu", ino);
+
+error_return:
+	brelse(bitmap_bh);
+	ext4_std_error(sb, fatal);
+}
+
+/*
+ * There are two policies for allocating an inode.  If the new inode is
+ * a directory, then a forward search is made for a block group with both
+ * free space and a low directory-to-inode ratio; if that fails, then of
+ * the groups with above-average free space, that group with the fewest
+ * directories already is chosen.
+ *
+ * For other inodes, search forward from the parent directory\'s block
+ * group to find a free inode.
+ */
+static int find_group_dir(struct super_block *sb, struct inode *parent,
+				ext4_group_t *best_group)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	unsigned int freei, avefreei;
+	struct ext4_group_desc *desc, *best_desc = NULL;
+	ext4_group_t group;
+	int ret = -1;
+
+	freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
+	avefreei = freei / ngroups;
+
+	for (group = 0; group < ngroups; group++) {
+		desc = ext4_get_group_desc(sb, group, NULL);
+		if (!desc || !ext4_free_inodes_count(sb, desc))
+			continue;
+		if (ext4_free_inodes_count(sb, desc) < avefreei)
+			continue;
+		if (!best_desc ||
+		    (ext4_free_blks_count(sb, desc) >
+		     ext4_free_blks_count(sb, best_desc))) {
+			*best_group = group;
+			best_desc = desc;
+			ret = 0;
+		}
+	}
+	return ret;
+}
+
+#define free_block_ratio 10
+
+static int find_group_flex(struct super_block *sb, struct inode *parent,
+			   ext4_group_t *best_group)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *desc;
+	struct flex_groups *flex_group = sbi->s_flex_groups;
+	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
+	ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	int flex_size = ext4_flex_bg_size(sbi);
+	ext4_group_t best_flex = parent_fbg_group;
+	int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
+	int flexbg_free_blocks;
+	int flex_freeb_ratio;
+	ext4_group_t n_fbg_groups;
+	ext4_group_t i;
+
+	n_fbg_groups = (ngroups + flex_size - 1) >>
+		sbi->s_log_groups_per_flex;
+
+find_close_to_parent:
+	flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks);
+	flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+	if (atomic_read(&flex_group[best_flex].free_inodes) &&
+	    flex_freeb_ratio > free_block_ratio)
+		goto found_flexbg;
+
+	if (best_flex && best_flex == parent_fbg_group) {
+		best_flex--;
+		goto find_close_to_parent;
+	}
+
+	for (i = 0; i < n_fbg_groups; i++) {
+		if (i == parent_fbg_group || i == parent_fbg_group - 1)
+			continue;
+
+		flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks);
+		flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+
+		if (flex_freeb_ratio > free_block_ratio &&
+		    (atomic_read(&flex_group[i].free_inodes))) {
+			best_flex = i;
+			goto found_flexbg;
+		}
+
+		if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) ||
+		    ((atomic_read(&flex_group[i].free_blocks) >
+		      atomic_read(&flex_group[best_flex].free_blocks)) &&
+		     atomic_read(&flex_group[i].free_inodes)))
+			best_flex = i;
+	}
+
+	if (!atomic_read(&flex_group[best_flex].free_inodes) ||
+	    !atomic_read(&flex_group[best_flex].free_blocks))
+		return -1;
+
+found_flexbg:
+	for (i = best_flex * flex_size; i < ngroups &&
+		     i < (best_flex + 1) * flex_size; i++) {
+		desc = ext4_get_group_desc(sb, i, NULL);
+		if (ext4_free_inodes_count(sb, desc)) {
+			*best_group = i;
+			goto out;
+		}
+	}
+
+	return -1;
+out:
+	return 0;
+}
+
+struct orlov_stats {
+	__u32 free_inodes;
+	__u32 free_blocks;
+	__u32 used_dirs;
+};
+
+/*
+ * Helper function for Orlov's allocator; returns critical information
+ * for a particular block group or flex_bg.  If flex_size is 1, then g
+ * is a block group number; otherwise it is flex_bg number.
+ */
+static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
+			    int flex_size, struct orlov_stats *stats)
+{
+	struct ext4_group_desc *desc;
+	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
+
+	if (flex_size > 1) {
+		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
+		stats->free_blocks = atomic_read(&flex_group[g].free_blocks);
+		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
+		return;
+	}
+
+	desc = ext4_get_group_desc(sb, g, NULL);
+	if (desc) {
+		stats->free_inodes = ext4_free_inodes_count(sb, desc);
+		stats->free_blocks = ext4_free_blks_count(sb, desc);
+		stats->used_dirs = ext4_used_dirs_count(sb, desc);
+	} else {
+		stats->free_inodes = 0;
+		stats->free_blocks = 0;
+		stats->used_dirs = 0;
+	}
+}
+
+/*
+ * Orlov's allocator for directories.
+ *
+ * We always try to spread first-level directories.
+ *
+ * If there are blockgroups with both free inodes and free blocks counts
+ * not worse than average we return one with smallest directory count.
+ * Otherwise we simply return a random group.
+ *
+ * For the rest rules look so:
+ *
+ * It's OK to put directory into a group unless
+ * it has too many directories already (max_dirs) or
+ * it has too few free inodes left (min_inodes) or
+ * it has too few free blocks left (min_blocks) or
+ * Parent's group is preferred, if it doesn't satisfy these
+ * conditions we search cyclically through the rest. If none
+ * of the groups look good we just look for a group with more
+ * free inodes than average (starting at parent's group).
+ */
+
+static int find_group_orlov(struct super_block *sb, struct inode *parent,
+			    ext4_group_t *group, int mode,
+			    const struct qstr *qstr)
+{
+	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
+	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
+	unsigned int freei, avefreei;
+	ext4_fsblk_t freeb, avefreeb;
+	unsigned int ndirs;
+	int max_dirs, min_inodes;
+	ext4_grpblk_t min_blocks;
+	ext4_group_t i, grp, g, ngroups;
+	struct ext4_group_desc *desc;
+	struct orlov_stats stats;
+	int flex_size = ext4_flex_bg_size(sbi);
+	struct dx_hash_info hinfo;
+
+	ngroups = real_ngroups;
+	if (flex_size > 1) {
+		ngroups = (real_ngroups + flex_size - 1) >>
+			sbi->s_log_groups_per_flex;
+		parent_group >>= sbi->s_log_groups_per_flex;
+	}
+
+	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
+	avefreei = freei / ngroups;
+	freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	avefreeb = freeb;
+	do_div(avefreeb, ngroups);
+	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
+
+	if (S_ISDIR(mode) &&
+	    ((parent == sb->s_root->d_inode) ||
+	     (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
+		int best_ndir = inodes_per_group;
+		int ret = -1;
+
+		if (qstr) {
+			hinfo.hash_version = DX_HASH_HALF_MD4;
+			hinfo.seed = sbi->s_hash_seed;
+			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
+			grp = hinfo.hash;
+		} else
+			get_random_bytes(&grp, sizeof(grp));
+		parent_group = (unsigned)grp % ngroups;
+		for (i = 0; i < ngroups; i++) {
+			g = (parent_group + i) % ngroups;
+			get_orlov_stats(sb, g, flex_size, &stats);
+			if (!stats.free_inodes)
+				continue;
+			if (stats.used_dirs >= best_ndir)
+				continue;
+			if (stats.free_inodes < avefreei)
+				continue;
+			if (stats.free_blocks < avefreeb)
+				continue;
+			grp = g;
+			ret = 0;
+			best_ndir = stats.used_dirs;
+		}
+		if (ret)
+			goto fallback;
+	found_flex_bg:
+		if (flex_size == 1) {
+			*group = grp;
+			return 0;
+		}
+
+		/*
+		 * We pack inodes at the beginning of the flexgroup's
+		 * inode tables.  Block allocation decisions will do
+		 * something similar, although regular files will
+		 * start at 2nd block group of the flexgroup.  See
+		 * ext4_ext_find_goal() and ext4_find_near().
+		 */
+		grp *= flex_size;
+		for (i = 0; i < flex_size; i++) {
+			if (grp+i >= real_ngroups)
+				break;
+			desc = ext4_get_group_desc(sb, grp+i, NULL);
+			if (desc && ext4_free_inodes_count(sb, desc)) {
+				*group = grp+i;
+				return 0;
+			}
+		}
+		goto fallback;
+	}
+
+	max_dirs = ndirs / ngroups + inodes_per_group / 16;
+	min_inodes = avefreei - inodes_per_group*flex_size / 4;
+	if (min_inodes < 1)
+		min_inodes = 1;
+	min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4;
+
+	/*
+	 * Start looking in the flex group where we last allocated an
+	 * inode for this parent directory
+	 */
+	if (EXT4_I(parent)->i_last_alloc_group != ~0) {
+		parent_group = EXT4_I(parent)->i_last_alloc_group;
+		if (flex_size > 1)
+			parent_group >>= sbi->s_log_groups_per_flex;
+	}
+
+	for (i = 0; i < ngroups; i++) {
+		grp = (parent_group + i) % ngroups;
+		get_orlov_stats(sb, grp, flex_size, &stats);
+		if (stats.used_dirs >= max_dirs)
+			continue;
+		if (stats.free_inodes < min_inodes)
+			continue;
+		if (stats.free_blocks < min_blocks)
+			continue;
+		goto found_flex_bg;
+	}
+
+fallback:
+	ngroups = real_ngroups;
+	avefreei = freei / ngroups;
+fallback_retry:
+	parent_group = EXT4_I(parent)->i_block_group;
+	for (i = 0; i < ngroups; i++) {
+		grp = (parent_group + i) % ngroups;
+		desc = ext4_get_group_desc(sb, grp, NULL);
+		if (desc && ext4_free_inodes_count(sb, desc) &&
+		    ext4_free_inodes_count(sb, desc) >= avefreei) {
+			*group = grp;
+			return 0;
+		}
+	}
+
+	if (avefreei) {
+		/*
+		 * The free-inodes counter is approximate, and for really small
+		 * filesystems the above test can fail to find any blockgroups
+		 */
+		avefreei = 0;
+		goto fallback_retry;
+	}
+
+	return -1;
+}
+
+static int find_group_other(struct super_block *sb, struct inode *parent,
+			    ext4_group_t *group, int mode)
+{
+	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
+	ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
+	struct ext4_group_desc *desc;
+	int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
+
+	/*
+	 * Try to place the inode is the same flex group as its
+	 * parent.  If we can't find space, use the Orlov algorithm to
+	 * find another flex group, and store that information in the
+	 * parent directory's inode information so that use that flex
+	 * group for future allocations.
+	 */
+	if (flex_size > 1) {
+		int retry = 0;
+
+	try_again:
+		parent_group &= ~(flex_size-1);
+		last = parent_group + flex_size;
+		if (last > ngroups)
+			last = ngroups;
+		for  (i = parent_group; i < last; i++) {
+			desc = ext4_get_group_desc(sb, i, NULL);
+			if (desc && ext4_free_inodes_count(sb, desc)) {
+				*group = i;
+				return 0;
+			}
+		}
+		if (!retry && EXT4_I(parent)->i_last_alloc_group != ~0) {
+			retry = 1;
+			parent_group = EXT4_I(parent)->i_last_alloc_group;
+			goto try_again;
+		}
+		/*
+		 * If this didn't work, use the Orlov search algorithm
+		 * to find a new flex group; we pass in the mode to
+		 * avoid the topdir algorithms.
+		 */
+		*group = parent_group + flex_size;
+		if (*group > ngroups)
+			*group = 0;
+		return find_group_orlov(sb, parent, group, mode, NULL);
+	}
+
+	/*
+	 * Try to place the inode in its parent directory
+	 */
+	*group = parent_group;
+	desc = ext4_get_group_desc(sb, *group, NULL);
+	if (desc && ext4_free_inodes_count(sb, desc) &&
+			ext4_free_blks_count(sb, desc))
+		return 0;
+
+	/*
+	 * We're going to place this inode in a different blockgroup from its
+	 * parent.  We want to cause files in a common directory to all land in
+	 * the same blockgroup.  But we want files which are in a different
+	 * directory which shares a blockgroup with our parent to land in a
+	 * different blockgroup.
+	 *
+	 * So add our directory's i_ino into the starting point for the hash.
+	 */
+	*group = (*group + parent->i_ino) % ngroups;
+
+	/*
+	 * Use a quadratic hash to find a group with a free inode and some free
+	 * blocks.
+	 */
+	for (i = 1; i < ngroups; i <<= 1) {
+		*group += i;
+		if (*group >= ngroups)
+			*group -= ngroups;
+		desc = ext4_get_group_desc(sb, *group, NULL);
+		if (desc && ext4_free_inodes_count(sb, desc) &&
+				ext4_free_blks_count(sb, desc))
+			return 0;
+	}
+
+	/*
+	 * That failed: try linear search for a free inode, even if that group
+	 * has no free blocks.
+	 */
+	*group = parent_group;
+	for (i = 0; i < ngroups; i++) {
+		if (++*group >= ngroups)
+			*group = 0;
+		desc = ext4_get_group_desc(sb, *group, NULL);
+		if (desc && ext4_free_inodes_count(sb, desc))
+			return 0;
+	}
+
+	return -1;
+}
+
+/*
+ * claim the inode from the inode bitmap. If the group
+ * is uninit we need to take the groups's ext4_group_lock
+ * and clear the uninit flag. The inode bitmap update
+ * and group desc uninit flag clear should be done
+ * after holding ext4_group_lock so that ext4_read_inode_bitmap
+ * doesn't race with the ext4_claim_inode
+ */
+static int ext4_claim_inode(struct super_block *sb,
+			struct buffer_head *inode_bitmap_bh,
+			unsigned long ino, ext4_group_t group, int mode)
+{
+	int free = 0, retval = 0, count;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+
+	/*
+	 * We have to be sure that new inode allocation does not race with
+	 * inode table initialization, because otherwise we may end up
+	 * allocating and writing new inode right before sb_issue_zeroout
+	 * takes place and overwriting our new inode with zeroes. So we
+	 * take alloc_sem to prevent it.
+	 */
+	down_read(&grp->alloc_sem);
+	ext4_lock_group(sb, group);
+	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
+		/* not a free inode */
+		retval = 1;
+		goto err_ret;
+	}
+	ino++;
+	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
+			ino > EXT4_INODES_PER_GROUP(sb)) {
+		ext4_unlock_group(sb, group);
+		up_read(&grp->alloc_sem);
+		ext4_error(sb, "reserved inode or inode > inodes count - "
+			   "block_group = %u, inode=%lu", group,
+			   ino + group * EXT4_INODES_PER_GROUP(sb));
+		return 1;
+	}
+	/* If we didn't allocate from within the initialized part of the inode
+	 * table then we need to initialize up to this inode. */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			/* When marking the block group with
+			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
+			 * on the value of bg_itable_unused even though
+			 * mke2fs could have initialized the same for us.
+			 * Instead we calculated the value below
+			 */
+
+			free = 0;
+		} else {
+			free = EXT4_INODES_PER_GROUP(sb) -
+				ext4_itable_unused_count(sb, gdp);
+		}
+
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to  update the bg_itable_unused count
+		 *
+		 */
+		if (ino > free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - ino));
+	}
+	count = ext4_free_inodes_count(sb, gdp) - 1;
+	ext4_free_inodes_set(sb, gdp, count);
+	if (S_ISDIR(mode)) {
+		count = ext4_used_dirs_count(sb, gdp) + 1;
+		ext4_used_dirs_set(sb, gdp, count);
+		if (sbi->s_log_groups_per_flex) {
+			ext4_group_t f = ext4_flex_group(sbi, group);
+
+			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+		}
+	}
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+err_ret:
+	ext4_unlock_group(sb, group);
+	up_read(&grp->alloc_sem);
+	return retval;
+}
+
+/*
+ * There are two policies for allocating an inode.  If the new inode is
+ * a directory, then a forward search is made for a block group with both
+ * free space and a low directory-to-inode ratio; if that fails, then of
+ * the groups with above-average free space, that group with the fewest
+ * directories already is chosen.
+ *
+ * For other inodes, search forward from the parent directory's block
+ * group to find a free inode.
+ */
+struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
+			     const struct qstr *qstr, __u32 goal)
+{
+	struct super_block *sb;
+	struct buffer_head *inode_bitmap_bh = NULL;
+	struct buffer_head *group_desc_bh;
+	ext4_group_t ngroups, group = 0;
+	unsigned long ino = 0;
+	struct inode *inode;
+	struct ext4_group_desc *gdp = NULL;
+	struct ext4_inode_info *ei;
+	struct ext4_sb_info *sbi;
+	int ret2, err = 0;
+	struct inode *ret;
+	ext4_group_t i;
+	int free = 0;
+	static int once = 1;
+	ext4_group_t flex_group;
+
+	/* Cannot create files in a deleted directory */
+	if (!dir || !dir->i_nlink)
+		return ERR_PTR(-EPERM);
+
+	sb = dir->i_sb;
+	ngroups = ext4_get_groups_count(sb);
+	trace_ext4_request_inode(dir, mode);
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	ei = EXT4_I(inode);
+	sbi = EXT4_SB(sb);
+
+	if (!goal)
+		goal = sbi->s_inode_goal;
+
+	if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) {
+		group = (goal - 1) / EXT4_INODES_PER_GROUP(sb);
+		ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb);
+		ret2 = 0;
+		goto got_group;
+	}
+
+	if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
+		ret2 = find_group_flex(sb, dir, &group);
+		if (ret2 == -1) {
+			ret2 = find_group_other(sb, dir, &group, mode);
+			if (ret2 == 0 && once) {
+				once = 0;
+				printk(KERN_NOTICE "ext4: find_group_flex "
+				       "failed, fallback succeeded dir %lu\n",
+				       dir->i_ino);
+			}
+		}
+		goto got_group;
+	}
+
+	if (S_ISDIR(mode)) {
+		if (test_opt(sb, OLDALLOC))
+			ret2 = find_group_dir(sb, dir, &group);
+		else
+			ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
+	} else
+		ret2 = find_group_other(sb, dir, &group, mode);
+
+got_group:
+	EXT4_I(dir)->i_last_alloc_group = group;
+	err = -ENOSPC;
+	if (ret2 == -1)
+		goto out;
+
+	for (i = 0; i < ngroups; i++, ino = 0) {
+		err = -EIO;
+
+		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+		if (!gdp)
+			goto fail;
+
+		brelse(inode_bitmap_bh);
+		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+		if (!inode_bitmap_bh)
+			goto fail;
+
+repeat_in_this_group:
+		ino = ext4_find_next_zero_bit((unsigned long *)
+					      inode_bitmap_bh->b_data,
+					      EXT4_INODES_PER_GROUP(sb), ino);
+
+		if (ino < EXT4_INODES_PER_GROUP(sb)) {
+
+			BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+			err = ext4_journal_get_write_access(handle,
+							    inode_bitmap_bh);
+			if (err)
+				goto fail;
+
+			BUFFER_TRACE(group_desc_bh, "get_write_access");
+			err = ext4_journal_get_write_access(handle,
+								group_desc_bh);
+			if (err)
+				goto fail;
+			if (!ext4_claim_inode(sb, inode_bitmap_bh,
+						ino, group, mode)) {
+				/* we won it */
+				BUFFER_TRACE(inode_bitmap_bh,
+					"call ext4_handle_dirty_metadata");
+				err = ext4_handle_dirty_metadata(handle,
+								 NULL,
+							inode_bitmap_bh);
+				if (err)
+					goto fail;
+				/* zero bit is inode number 1*/
+				ino++;
+				goto got;
+			}
+			/* we lost it */
+			ext4_handle_release_buffer(handle, inode_bitmap_bh);
+			ext4_handle_release_buffer(handle, group_desc_bh);
+
+			if (++ino < EXT4_INODES_PER_GROUP(sb))
+				goto repeat_in_this_group;
+		}
+
+		/*
+		 * This case is possible in concurrent environment.  It is very
+		 * rare.  We cannot repeat the find_group_xxx() call because
+		 * that will simply return the same blockgroup, because the
+		 * group descriptor metadata has not yet been updated.
+		 * So we just go onto the next blockgroup.
+		 */
+		if (++group == ngroups)
+			group = 0;
+	}
+	err = -ENOSPC;
+	goto out;
+
+got:
+	/* We may have to initialize the block bitmap if it isn't already */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
+	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		struct buffer_head *block_bitmap_bh;
+
+		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
+		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
+		if (err) {
+			brelse(block_bitmap_bh);
+			goto fail;
+		}
+
+		free = 0;
+		ext4_lock_group(sb, group);
+		/* recheck and clear flag under lock if we still need to */
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+			free = ext4_free_blocks_after_init(sb, group, gdp);
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+			ext4_free_blks_set(sb, gdp, free);
+			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
+								gdp);
+		}
+		ext4_unlock_group(sb, group);
+
+		/* Don't need to dirty bitmap block if we didn't change it */
+		if (free) {
+			BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+			err = ext4_handle_dirty_metadata(handle,
+							NULL, block_bitmap_bh);
+		}
+
+		brelse(block_bitmap_bh);
+		if (err)
+			goto fail;
+	}
+	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
+	if (err)
+		goto fail;
+
+	percpu_counter_dec(&sbi->s_freeinodes_counter);
+	if (S_ISDIR(mode))
+		percpu_counter_inc(&sbi->s_dirs_counter);
+	ext4_mark_super_dirty(sb);
+
+	if (sbi->s_log_groups_per_flex) {
+		flex_group = ext4_flex_group(sbi, group);
+		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
+	}
+
+	if (test_opt(sb, GRPID)) {
+		inode->i_mode = mode;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = dir->i_gid;
+	} else
+		inode_init_owner(inode, dir, mode);
+
+	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
+	/* This is the optimal IO size (for stat), not the fs block size */
+	inode->i_blocks = 0;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
+						       ext4_current_time(inode);
+
+	memset(ei->i_data, 0, sizeof(ei->i_data));
+	ei->i_dir_start_lookup = 0;
+	ei->i_disksize = 0;
+
+	/*
+	 * Don't inherit extent flag from directory, amongst others. We set
+	 * extent flag on newly created directory and file only if -o extent
+	 * mount option is specified
+	 */
+	ei->i_flags =
+		ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
+	ei->i_file_acl = 0;
+	ei->i_dtime = 0;
+	ei->i_block_group = group;
+	ei->i_last_alloc_group = ~0;
+
+	ext4_set_inode_flags(inode);
+	if (IS_DIRSYNC(inode))
+		ext4_handle_sync(handle);
+	if (insert_inode_locked(inode) < 0) {
+		/*
+		 * Likely a bitmap corruption causing inode to be allocated
+		 * twice.
+		 */
+		err = -EIO;
+		goto fail;
+	}
+	spin_lock(&sbi->s_next_gen_lock);
+	inode->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+
+	ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
+	ext4_set_inode_state(inode, EXT4_STATE_NEW);
+
+	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
+
+	ret = inode;
+	dquot_initialize(inode);
+	err = dquot_alloc_inode(inode);
+	if (err)
+		goto fail_drop;
+
+	err = ext4_init_acl(handle, inode, dir);
+	if (err)
+		goto fail_free_drop;
+
+	err = ext4_init_security(handle, inode, dir, qstr);
+	if (err)
+		goto fail_free_drop;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+		/* set extent flag only for directory, file and normal symlink*/
+		if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
+			ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
+			ext4_ext_tree_init(handle, inode);
+		}
+	}
+
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto fail_free_drop;
+	}
+
+	ext4_debug("allocating inode %lu\n", inode->i_ino);
+	trace_ext4_allocate_inode(inode, dir, mode);
+	goto really_out;
+fail:
+	ext4_std_error(sb, err);
+out:
+	iput(inode);
+	ret = ERR_PTR(err);
+really_out:
+	brelse(inode_bitmap_bh);
+	return ret;
+
+fail_free_drop:
+	dquot_free_inode(inode);
+
+fail_drop:
+	dquot_drop(inode);
+	inode->i_flags |= S_NOQUOTA;
+	inode->i_nlink = 0;
+	unlock_new_inode(inode);
+	iput(inode);
+	brelse(inode_bitmap_bh);
+	return ERR_PTR(err);
+}
+
+/* Verify that we are loading a valid orphan from disk */
+struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
+{
+	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
+	ext4_group_t block_group;
+	int bit;
+	struct buffer_head *bitmap_bh;
+	struct inode *inode = NULL;
+	long err = -EIO;
+
+	/* Error cases - e2fsck has already cleaned up for us */
+	if (ino > max_ino) {
+		ext4_warning(sb, "bad orphan ino %lu!  e2fsck was run?", ino);
+		goto error;
+	}
+
+	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
+	if (!bitmap_bh) {
+		ext4_warning(sb, "inode bitmap error for orphan %lu", ino);
+		goto error;
+	}
+
+	/* Having the inode bit set should be a 100% indicator that this
+	 * is a valid orphan (no e2fsck run on fs).  Orphans also include
+	 * inodes that were being truncated, so we can't check i_nlink==0.
+	 */
+	if (!ext4_test_bit(bit, bitmap_bh->b_data))
+		goto bad_orphan;
+
+	inode = ext4_iget(sb, ino);
+	if (IS_ERR(inode))
+		goto iget_failed;
+
+	/*
+	 * If the orphans has i_nlinks > 0 then it should be able to be
+	 * truncated, otherwise it won't be removed from the orphan list
+	 * during processing and an infinite loop will result.
+	 */
+	if (inode->i_nlink && !ext4_can_truncate(inode))
+		goto bad_orphan;
+
+	if (NEXT_ORPHAN(inode) > max_ino)
+		goto bad_orphan;
+	brelse(bitmap_bh);
+	return inode;
+
+iget_failed:
+	err = PTR_ERR(inode);
+	inode = NULL;
+bad_orphan:
+	ext4_warning(sb, "bad orphan inode %lu!  e2fsck was run?", ino);
+	printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+	       bit, (unsigned long long)bitmap_bh->b_blocknr,
+	       ext4_test_bit(bit, bitmap_bh->b_data));
+	printk(KERN_NOTICE "inode=%p\n", inode);
+	if (inode) {
+		printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
+		       is_bad_inode(inode));
+		printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
+		       NEXT_ORPHAN(inode));
+		printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
+		printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
+		/* Avoid freeing blocks if we got a bad deleted inode */
+		if (inode->i_nlink == 0)
+			inode->i_blocks = 0;
+		iput(inode);
+	}
+	brelse(bitmap_bh);
+error:
+	return ERR_PTR(err);
+}
+
+unsigned long ext4_count_free_inodes(struct super_block *sb)
+{
+	unsigned long desc_count;
+	struct ext4_group_desc *gdp;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+#ifdef EXT4FS_DEBUG
+	struct ext4_super_block *es;
+	unsigned long bitmap_count, x;
+	struct buffer_head *bitmap_bh = NULL;
+
+	es = EXT4_SB(sb)->s_es;
+	desc_count = 0;
+	bitmap_count = 0;
+	gdp = NULL;
+	for (i = 0; i < ngroups; i++) {
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += ext4_free_inodes_count(sb, gdp);
+		brelse(bitmap_bh);
+		bitmap_bh = ext4_read_inode_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+
+		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
+			(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
+		bitmap_count += x;
+	}
+	brelse(bitmap_bh);
+	printk(KERN_DEBUG "ext4_count_free_inodes: "
+	       "stored = %u, computed = %lu, %lu\n",
+	       le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
+	return desc_count;
+#else
+	desc_count = 0;
+	for (i = 0; i < ngroups; i++) {
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += ext4_free_inodes_count(sb, gdp);
+		cond_resched();
+	}
+	return desc_count;
+#endif
+}
+
+/* Called at mount-time, super-block is locked */
+unsigned long ext4_count_dirs(struct super_block * sb)
+{
+	unsigned long count = 0;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+
+	for (i = 0; i < ngroups; i++) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
+		if (!gdp)
+			continue;
+		count += ext4_used_dirs_count(sb, gdp);
+	}
+	return count;
+}
+
+/*
+ * Zeroes not yet zeroed inode table - just write zeroes through the whole
+ * inode table. Must be called without any spinlock held. The only place
+ * where it is called from on active part of filesystem is ext4lazyinit
+ * thread, so we do not need any special locks, however we have to prevent
+ * inode allocation from the current group, so we take alloc_sem lock, to
+ * block ext4_claim_inode until we are finished.
+ */
+extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+				 int barrier)
+{
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = NULL;
+	struct buffer_head *group_desc_bh;
+	handle_t *handle;
+	ext4_fsblk_t blk;
+	int num, ret = 0, used_blks = 0;
+
+	/* This should not happen, but just to be sure check this */
+	if (sb->s_flags & MS_RDONLY) {
+		ret = 1;
+		goto out;
+	}
+
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp)
+		goto out;
+
+	/*
+	 * We do not need to lock this, because we are the only one
+	 * handling this flag.
+	 */
+	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+		goto out;
+
+	handle = ext4_journal_start_sb(sb, 1);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	down_write(&grp->alloc_sem);
+	/*
+	 * If inode bitmap was already initialized there may be some
+	 * used inodes so we need to skip blocks with used inodes in
+	 * inode table.
+	 */
+	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+		used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
+			    ext4_itable_unused_count(sb, gdp)),
+			    sbi->s_inodes_per_block);
+
+	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+		ext4_error(sb, "Something is wrong with group %u\n"
+			   "Used itable blocks: %d"
+			   "itable unused count: %u\n",
+			   group, used_blks,
+			   ext4_itable_unused_count(sb, gdp));
+		ret = 1;
+		goto out;
+	}
+
+	blk = ext4_inode_table(sb, gdp) + used_blks;
+	num = sbi->s_itb_per_group - used_blks;
+
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	ret = ext4_journal_get_write_access(handle,
+					    group_desc_bh);
+	if (ret)
+		goto err_out;
+
+	/*
+	 * Skip zeroout if the inode table is full. But we set the ZEROED
+	 * flag anyway, because obviously, when it is full it does not need
+	 * further zeroing.
+	 */
+	if (unlikely(num == 0))
+		goto skip_zeroout;
+
+	ext4_debug("going to zero out inode table in group %d\n",
+		   group);
+	ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS);
+	if (ret < 0)
+		goto err_out;
+	if (barrier)
+		blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL);
+
+skip_zeroout:
+	ext4_lock_group(sb, group);
+	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+	ext4_unlock_group(sb, group);
+
+	BUFFER_TRACE(group_desc_bh,
+		     "call ext4_handle_dirty_metadata");
+	ret = ext4_handle_dirty_metadata(handle, NULL,
+					 group_desc_bh);
+
+err_out:
+	up_write(&grp->alloc_sem);
+	ext4_journal_stop(handle);
+out:
+	return ret;
+}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
new file mode 100644
index 00000000..c1e6a726
--- /dev/null
+++ b/fs/ext4/inode.c
@@ -0,0 +1,5957 @@
+/*
+ *  linux/fs/ext4/inode.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/inode.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  Goal-directed block allocation by Stephen Tweedie
+ *	(sct@redhat.com), 1993, 1998
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *  64-bit file support on 64-bit platforms by Jakub Jelinek
+ *	(jj@sunsite.ms.mff.cuni.cz)
+ *
+ *  Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/jbd2.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/uio.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/ratelimit.h>
+
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "ext4_extents.h"
+
+#include <trace/events/ext4.h>
+
+#define MPAGE_DA_EXTENT_TAIL 0x01
+
+static inline int ext4_begin_ordered_truncate(struct inode *inode,
+					      loff_t new_size)
+{
+	trace_ext4_begin_ordered_truncate(inode, new_size);
+	/*
+	 * If jinode is zero, then we never opened the file for
+	 * writing, so there's no need to call
+	 * jbd2_journal_begin_ordered_truncate() since there's no
+	 * outstanding writes we need to flush.
+	 */
+	if (!EXT4_I(inode)->jinode)
+		return 0;
+	return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
+						   EXT4_I(inode)->jinode,
+						   new_size);
+}
+
+static void ext4_invalidatepage(struct page *page, unsigned long offset);
+static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
+				   struct buffer_head *bh_result, int create);
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
+static int __ext4_journalled_writepage(struct page *page, unsigned int len);
+static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
+
+/*
+ * Test whether an inode is a fast symlink.
+ */
+static int ext4_inode_is_fast_symlink(struct inode *inode)
+{
+	int ea_blocks = EXT4_I(inode)->i_file_acl ?
+		(inode->i_sb->s_blocksize >> 9) : 0;
+
+	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
+}
+
+/*
+ * Work out how many blocks we need to proceed with the next chunk of a
+ * truncate transaction.
+ */
+static unsigned long blocks_for_truncate(struct inode *inode)
+{
+	ext4_lblk_t needed;
+
+	needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
+
+	/* Give ourselves just enough room to cope with inodes in which
+	 * i_blocks is corrupt: we've seen disk corruptions in the past
+	 * which resulted in random data in an inode which looked enough
+	 * like a regular file for ext4 to try to delete it.  Things
+	 * will go a bit crazy if that happens, but at least we should
+	 * try not to panic the whole kernel. */
+	if (needed < 2)
+		needed = 2;
+
+	/* But we need to bound the transaction so we don't overflow the
+	 * journal. */
+	if (needed > EXT4_MAX_TRANS_DATA)
+		needed = EXT4_MAX_TRANS_DATA;
+
+	return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
+}
+
+/*
+ * Truncate transactions can be complex and absolutely huge.  So we need to
+ * be able to restart the transaction at a conventient checkpoint to make
+ * sure we don't overflow the journal.
+ *
+ * start_transaction gets us a new handle for a truncate transaction,
+ * and extend_transaction tries to extend the existing one a bit.  If
+ * extend fails, we need to propagate the failure up and restart the
+ * transaction in the top-level truncate loop. --sct
+ */
+static handle_t *start_transaction(struct inode *inode)
+{
+	handle_t *result;
+
+	result = ext4_journal_start(inode, blocks_for_truncate(inode));
+	if (!IS_ERR(result))
+		return result;
+
+	ext4_std_error(inode->i_sb, PTR_ERR(result));
+	return result;
+}
+
+/*
+ * Try to extend this transaction for the purposes of truncation.
+ *
+ * Returns 0 if we managed to create more room.  If we can't create more
+ * room, and the transaction must be restarted we return 1.
+ */
+static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
+{
+	if (!ext4_handle_valid(handle))
+		return 0;
+	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
+		return 0;
+	if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
+		return 0;
+	return 1;
+}
+
+/*
+ * Restart the transaction associated with *handle.  This does a commit,
+ * so before we call here everything must be consistently dirtied against
+ * this transaction.
+ */
+int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+				 int nblocks)
+{
+	int ret;
+
+	/*
+	 * Drop i_data_sem to avoid deadlock with ext4_map_blocks.  At this
+	 * moment, get_block can be called only for blocks inside i_size since
+	 * page cache has been already dropped and writes are blocked by
+	 * i_mutex. So we can safely drop the i_data_sem here.
+	 */
+	BUG_ON(EXT4_JOURNAL(inode) == NULL);
+	jbd_debug(2, "restarting handle %p\n", handle);
+	up_write(&EXT4_I(inode)->i_data_sem);
+	ret = ext4_journal_restart(handle, nblocks);
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_discard_preallocations(inode);
+
+	return ret;
+}
+
+/*
+ * Called at the last iput() if i_nlink is zero.
+ */
+void ext4_evict_inode(struct inode *inode)
+{
+	handle_t *handle;
+	int err;
+
+	trace_ext4_evict_inode(inode);
+
+	ext4_ioend_wait(inode);
+
+	if (inode->i_nlink) {
+		truncate_inode_pages(&inode->i_data, 0);
+		goto no_delete;
+	}
+
+	if (!is_bad_inode(inode))
+		dquot_initialize(inode);
+
+	if (ext4_should_order_data(inode))
+		ext4_begin_ordered_truncate(inode, 0);
+	truncate_inode_pages(&inode->i_data, 0);
+
+	if (is_bad_inode(inode))
+		goto no_delete;
+
+	handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
+	if (IS_ERR(handle)) {
+		ext4_std_error(inode->i_sb, PTR_ERR(handle));
+		/*
+		 * If we're going to skip the normal cleanup, we still need to
+		 * make sure that the in-core orphan linked list is properly
+		 * cleaned up.
+		 */
+		ext4_orphan_del(NULL, inode);
+		goto no_delete;
+	}
+
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+	inode->i_size = 0;
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err) {
+		ext4_warning(inode->i_sb,
+			     "couldn't mark inode dirty (err %d)", err);
+		goto stop_handle;
+	}
+	if (inode->i_blocks)
+		ext4_truncate(inode);
+
+	/*
+	 * ext4_ext_truncate() doesn't reserve any slop when it
+	 * restarts journal transactions; therefore there may not be
+	 * enough credits left in the handle to remove the inode from
+	 * the orphan list and set the dtime field.
+	 */
+	if (!ext4_handle_has_enough_credits(handle, 3)) {
+		err = ext4_journal_extend(handle, 3);
+		if (err > 0)
+			err = ext4_journal_restart(handle, 3);
+		if (err != 0) {
+			ext4_warning(inode->i_sb,
+				     "couldn't extend journal (err %d)", err);
+		stop_handle:
+			ext4_journal_stop(handle);
+			ext4_orphan_del(NULL, inode);
+			goto no_delete;
+		}
+	}
+
+	/*
+	 * Kill off the orphan record which ext4_truncate created.
+	 * AKPM: I think this can be inside the above `if'.
+	 * Note that ext4_orphan_del() has to be able to cope with the
+	 * deletion of a non-existent orphan - this is because we don't
+	 * know if ext4_truncate() actually created an orphan record.
+	 * (Well, we could do this if we need to, but heck - it works)
+	 */
+	ext4_orphan_del(handle, inode);
+	EXT4_I(inode)->i_dtime	= get_seconds();
+
+	/*
+	 * One subtle ordering requirement: if anything has gone wrong
+	 * (transaction abort, IO errors, whatever), then we can still
+	 * do these next steps (the fs will already have been marked as
+	 * having errors), but we can't free the inode if the mark_dirty
+	 * fails.
+	 */
+	if (ext4_mark_inode_dirty(handle, inode))
+		/* If that failed, just do the required in-core inode clear. */
+		ext4_clear_inode(inode);
+	else
+		ext4_free_inode(handle, inode);
+	ext4_journal_stop(handle);
+	return;
+no_delete:
+	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
+}
+
+typedef struct {
+	__le32	*p;
+	__le32	key;
+	struct buffer_head *bh;
+} Indirect;
+
+static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
+{
+	p->key = *(p->p = v);
+	p->bh = bh;
+}
+
+/**
+ *	ext4_block_to_path - parse the block number into array of offsets
+ *	@inode: inode in question (we are only interested in its superblock)
+ *	@i_block: block number to be parsed
+ *	@offsets: array to store the offsets in
+ *	@boundary: set this non-zero if the referred-to block is likely to be
+ *	       followed (on disk) by an indirect block.
+ *
+ *	To store the locations of file's data ext4 uses a data structure common
+ *	for UNIX filesystems - tree of pointers anchored in the inode, with
+ *	data blocks at leaves and indirect blocks in intermediate nodes.
+ *	This function translates the block number into path in that tree -
+ *	return value is the path length and @offsets[n] is the offset of
+ *	pointer to (n+1)th node in the nth one. If @block is out of range
+ *	(negative or too large) warning is printed and zero returned.
+ *
+ *	Note: function doesn't find node addresses, so no IO is needed. All
+ *	we need to know is the capacity of indirect blocks (taken from the
+ *	inode->i_sb).
+ */
+
+/*
+ * Portability note: the last comparison (check that we fit into triple
+ * indirect block) is spelled differently, because otherwise on an
+ * architecture with 32-bit longs and 8Kb pages we might get into trouble
+ * if our filesystem had 8Kb blocks. We might use long long, but that would
+ * kill us on x86. Oh, well, at least the sign propagation does not matter -
+ * i_block would have to be negative in the very beginning, so we would not
+ * get there at all.
+ */
+
+static int ext4_block_to_path(struct inode *inode,
+			      ext4_lblk_t i_block,
+			      ext4_lblk_t offsets[4], int *boundary)
+{
+	int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+	int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
+	const long direct_blocks = EXT4_NDIR_BLOCKS,
+		indirect_blocks = ptrs,
+		double_blocks = (1 << (ptrs_bits * 2));
+	int n = 0;
+	int final = 0;
+
+	if (i_block < direct_blocks) {
+		offsets[n++] = i_block;
+		final = direct_blocks;
+	} else if ((i_block -= direct_blocks) < indirect_blocks) {
+		offsets[n++] = EXT4_IND_BLOCK;
+		offsets[n++] = i_block;
+		final = ptrs;
+	} else if ((i_block -= indirect_blocks) < double_blocks) {
+		offsets[n++] = EXT4_DIND_BLOCK;
+		offsets[n++] = i_block >> ptrs_bits;
+		offsets[n++] = i_block & (ptrs - 1);
+		final = ptrs;
+	} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
+		offsets[n++] = EXT4_TIND_BLOCK;
+		offsets[n++] = i_block >> (ptrs_bits * 2);
+		offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
+		offsets[n++] = i_block & (ptrs - 1);
+		final = ptrs;
+	} else {
+		ext4_warning(inode->i_sb, "block %lu > max in inode %lu",
+			     i_block + direct_blocks +
+			     indirect_blocks + double_blocks, inode->i_ino);
+	}
+	if (boundary)
+		*boundary = final - 1 - (i_block & (ptrs - 1));
+	return n;
+}
+
+static int __ext4_check_blockref(const char *function, unsigned int line,
+				 struct inode *inode,
+				 __le32 *p, unsigned int max)
+{
+	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+	__le32 *bref = p;
+	unsigned int blk;
+
+	while (bref < p+max) {
+		blk = le32_to_cpu(*bref++);
+		if (blk &&
+		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+						    blk, 1))) {
+			es->s_last_error_block = cpu_to_le64(blk);
+			ext4_error_inode(inode, function, line, blk,
+					 "invalid block");
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+
+#define ext4_check_indirect_blockref(inode, bh)                         \
+	__ext4_check_blockref(__func__, __LINE__, inode,		\
+			      (__le32 *)(bh)->b_data,			\
+			      EXT4_ADDR_PER_BLOCK((inode)->i_sb))
+
+#define ext4_check_inode_blockref(inode)                                \
+	__ext4_check_blockref(__func__, __LINE__, inode,		\
+			      EXT4_I(inode)->i_data,			\
+			      EXT4_NDIR_BLOCKS)
+
+/**
+ *	ext4_get_branch - read the chain of indirect blocks leading to data
+ *	@inode: inode in question
+ *	@depth: depth of the chain (1 - direct pointer, etc.)
+ *	@offsets: offsets of pointers in inode/indirect blocks
+ *	@chain: place to store the result
+ *	@err: here we store the error value
+ *
+ *	Function fills the array of triples <key, p, bh> and returns %NULL
+ *	if everything went OK or the pointer to the last filled triple
+ *	(incomplete one) otherwise. Upon the return chain[i].key contains
+ *	the number of (i+1)-th block in the chain (as it is stored in memory,
+ *	i.e. little-endian 32-bit), chain[i].p contains the address of that
+ *	number (it points into struct inode for i==0 and into the bh->b_data
+ *	for i>0) and chain[i].bh points to the buffer_head of i-th indirect
+ *	block for i>0 and NULL for i==0. In other words, it holds the block
+ *	numbers of the chain, addresses they were taken from (and where we can
+ *	verify that chain did not change) and buffer_heads hosting these
+ *	numbers.
+ *
+ *	Function stops when it stumbles upon zero pointer (absent block)
+ *		(pointer to last triple returned, *@err == 0)
+ *	or when it gets an IO error reading an indirect block
+ *		(ditto, *@err == -EIO)
+ *	or when it reads all @depth-1 indirect blocks successfully and finds
+ *	the whole chain, all way to the data (returns %NULL, *err == 0).
+ *
+ *      Need to be called with
+ *      down_read(&EXT4_I(inode)->i_data_sem)
+ */
+static Indirect *ext4_get_branch(struct inode *inode, int depth,
+				 ext4_lblk_t  *offsets,
+				 Indirect chain[4], int *err)
+{
+	struct super_block *sb = inode->i_sb;
+	Indirect *p = chain;
+	struct buffer_head *bh;
+
+	*err = 0;
+	/* i_data is not going away, no lock needed */
+	add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
+	if (!p->key)
+		goto no_block;
+	while (--depth) {
+		bh = sb_getblk(sb, le32_to_cpu(p->key));
+		if (unlikely(!bh))
+			goto failure;
+
+		if (!bh_uptodate_or_lock(bh)) {
+			if (bh_submit_read(bh) < 0) {
+				put_bh(bh);
+				goto failure;
+			}
+			/* validate block references */
+			if (ext4_check_indirect_blockref(inode, bh)) {
+				put_bh(bh);
+				goto failure;
+			}
+		}
+
+		add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
+		/* Reader: end */
+		if (!p->key)
+			goto no_block;
+	}
+	return NULL;
+
+failure:
+	*err = -EIO;
+no_block:
+	return p;
+}
+
+/**
+ *	ext4_find_near - find a place for allocation with sufficient locality
+ *	@inode: owner
+ *	@ind: descriptor of indirect block.
+ *
+ *	This function returns the preferred place for block allocation.
+ *	It is used when heuristic for sequential allocation fails.
+ *	Rules are:
+ *	  + if there is a block to the left of our position - allocate near it.
+ *	  + if pointer will live in indirect block - allocate near that block.
+ *	  + if pointer will live in inode - allocate in the same
+ *	    cylinder group.
+ *
+ * In the latter case we colour the starting block by the callers PID to
+ * prevent it from clashing with concurrent allocations for a different inode
+ * in the same block group.   The PID is used here so that functionally related
+ * files will be close-by on-disk.
+ *
+ *	Caller must make sure that @ind is valid and will stay that way.
+ */
+static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
+	__le32 *p;
+	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
+	ext4_grpblk_t colour;
+	ext4_group_t block_group;
+	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
+
+	/* Try to find previous block */
+	for (p = ind->p - 1; p >= start; p--) {
+		if (*p)
+			return le32_to_cpu(*p);
+	}
+
+	/* No such thing, so let's try location of indirect block */
+	if (ind->bh)
+		return ind->bh->b_blocknr;
+
+	/*
+	 * It is going to be referred to from the inode itself? OK, just put it
+	 * into the same cylinder group then.
+	 */
+	block_group = ei->i_block_group;
+	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
+		block_group &= ~(flex_size-1);
+		if (S_ISREG(inode->i_mode))
+			block_group++;
+	}
+	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	/*
+	 * If we are doing delayed allocation, we don't need take
+	 * colour into account.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		return bg_start;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
+			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+	return bg_start + colour;
+}
+
+/**
+ *	ext4_find_goal - find a preferred place for allocation.
+ *	@inode: owner
+ *	@block:  block we want
+ *	@partial: pointer to the last triple within a chain
+ *
+ *	Normally this function find the preferred place for block allocation,
+ *	returns it.
+ *	Because this is only used for non-extent files, we limit the block nr
+ *	to 32 bits.
+ */
+static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
+				   Indirect *partial)
+{
+	ext4_fsblk_t goal;
+
+	/*
+	 * XXX need to get goal block from mballoc's data structures
+	 */
+
+	goal = ext4_find_near(inode, partial);
+	goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+	return goal;
+}
+
+/**
+ *	ext4_blks_to_allocate - Look up the block map and count the number
+ *	of direct blocks need to be allocated for the given branch.
+ *
+ *	@branch: chain of indirect blocks
+ *	@k: number of blocks need for indirect blocks
+ *	@blks: number of data blocks to be mapped.
+ *	@blocks_to_boundary:  the offset in the indirect block
+ *
+ *	return the total number of blocks to be allocate, including the
+ *	direct and indirect blocks.
+ */
+static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
+				 int blocks_to_boundary)
+{
+	unsigned int count = 0;
+
+	/*
+	 * Simple case, [t,d]Indirect block(s) has not allocated yet
+	 * then it's clear blocks on that path have not allocated
+	 */
+	if (k > 0) {
+		/* right now we don't handle cross boundary allocation */
+		if (blks < blocks_to_boundary + 1)
+			count += blks;
+		else
+			count += blocks_to_boundary + 1;
+		return count;
+	}
+
+	count++;
+	while (count < blks && count <= blocks_to_boundary &&
+		le32_to_cpu(*(branch[0].p + count)) == 0) {
+		count++;
+	}
+	return count;
+}
+
+/**
+ *	ext4_alloc_blocks: multiple allocate blocks needed for a branch
+ *	@handle: handle for this transaction
+ *	@inode: inode which needs allocated blocks
+ *	@iblock: the logical block to start allocated at
+ *	@goal: preferred physical block of allocation
+ *	@indirect_blks: the number of blocks need to allocate for indirect
+ *			blocks
+ *	@blks: number of desired blocks
+ *	@new_blocks: on return it will store the new block numbers for
+ *	the indirect blocks(if needed) and the first direct block,
+ *	@err: on return it will store the error code
+ *
+ *	This function will return the number of blocks allocated as
+ *	requested by the passed-in parameters.
+ */
+static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
+			     ext4_lblk_t iblock, ext4_fsblk_t goal,
+			     int indirect_blks, int blks,
+			     ext4_fsblk_t new_blocks[4], int *err)
+{
+	struct ext4_allocation_request ar;
+	int target, i;
+	unsigned long count = 0, blk_allocated = 0;
+	int index = 0;
+	ext4_fsblk_t current_block = 0;
+	int ret = 0;
+
+	/*
+	 * Here we try to allocate the requested multiple blocks at once,
+	 * on a best-effort basis.
+	 * To build a branch, we should allocate blocks for
+	 * the indirect blocks(if not allocated yet), and at least
+	 * the first direct block of this branch.  That's the
+	 * minimum number of blocks need to allocate(required)
+	 */
+	/* first we try to allocate the indirect blocks */
+	target = indirect_blks;
+	while (target > 0) {
+		count = target;
+		/* allocating blocks for indirect blocks and direct blocks */
+		current_block = ext4_new_meta_blocks(handle, inode, goal,
+						     0, &count, err);
+		if (*err)
+			goto failed_out;
+
+		if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
+			EXT4_ERROR_INODE(inode,
+					 "current_block %llu + count %lu > %d!",
+					 current_block, count,
+					 EXT4_MAX_BLOCK_FILE_PHYS);
+			*err = -EIO;
+			goto failed_out;
+		}
+
+		target -= count;
+		/* allocate blocks for indirect blocks */
+		while (index < indirect_blks && count) {
+			new_blocks[index++] = current_block++;
+			count--;
+		}
+		if (count > 0) {
+			/*
+			 * save the new block number
+			 * for the first direct block
+			 */
+			new_blocks[index] = current_block;
+			printk(KERN_INFO "%s returned more blocks than "
+						"requested\n", __func__);
+			WARN_ON(1);
+			break;
+		}
+	}
+
+	target = blks - count ;
+	blk_allocated = count;
+	if (!target)
+		goto allocated;
+	/* Now allocate data blocks */
+	memset(&ar, 0, sizeof(ar));
+	ar.inode = inode;
+	ar.goal = goal;
+	ar.len = target;
+	ar.logical = iblock;
+	if (S_ISREG(inode->i_mode))
+		/* enable in-core preallocation only for regular files */
+		ar.flags = EXT4_MB_HINT_DATA;
+
+	current_block = ext4_mb_new_blocks(handle, &ar, err);
+	if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
+		EXT4_ERROR_INODE(inode,
+				 "current_block %llu + ar.len %d > %d!",
+				 current_block, ar.len,
+				 EXT4_MAX_BLOCK_FILE_PHYS);
+		*err = -EIO;
+		goto failed_out;
+	}
+
+	if (*err && (target == blks)) {
+		/*
+		 * if the allocation failed and we didn't allocate
+		 * any blocks before
+		 */
+		goto failed_out;
+	}
+	if (!*err) {
+		if (target == blks) {
+			/*
+			 * save the new block number
+			 * for the first direct block
+			 */
+			new_blocks[index] = current_block;
+		}
+		blk_allocated += ar.len;
+	}
+allocated:
+	/* total number of blocks allocated for direct blocks */
+	ret = blk_allocated;
+	*err = 0;
+	return ret;
+failed_out:
+	for (i = 0; i < index; i++)
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
+	return ret;
+}
+
+/**
+ *	ext4_alloc_branch - allocate and set up a chain of blocks.
+ *	@handle: handle for this transaction
+ *	@inode: owner
+ *	@indirect_blks: number of allocated indirect blocks
+ *	@blks: number of allocated direct blocks
+ *	@goal: preferred place for allocation
+ *	@offsets: offsets (in the blocks) to store the pointers to next.
+ *	@branch: place to store the chain in.
+ *
+ *	This function allocates blocks, zeroes out all but the last one,
+ *	links them into chain and (if we are synchronous) writes them to disk.
+ *	In other words, it prepares a branch that can be spliced onto the
+ *	inode. It stores the information about that chain in the branch[], in
+ *	the same format as ext4_get_branch() would do. We are calling it after
+ *	we had read the existing part of chain and partial points to the last
+ *	triple of that (one with zero ->key). Upon the exit we have the same
+ *	picture as after the successful ext4_get_block(), except that in one
+ *	place chain is disconnected - *branch->p is still zero (we did not
+ *	set the last link), but branch->key contains the number that should
+ *	be placed into *branch->p to fill that gap.
+ *
+ *	If allocation fails we free all blocks we've allocated (and forget
+ *	their buffer_heads) and return the error value the from failed
+ *	ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
+ *	as described above and return 0.
+ */
+static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
+			     ext4_lblk_t iblock, int indirect_blks,
+			     int *blks, ext4_fsblk_t goal,
+			     ext4_lblk_t *offsets, Indirect *branch)
+{
+	int blocksize = inode->i_sb->s_blocksize;
+	int i, n = 0;
+	int err = 0;
+	struct buffer_head *bh;
+	int num;
+	ext4_fsblk_t new_blocks[4];
+	ext4_fsblk_t current_block;
+
+	num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks,
+				*blks, new_blocks, &err);
+	if (err)
+		return err;
+
+	branch[0].key = cpu_to_le32(new_blocks[0]);
+	/*
+	 * metadata blocks and data blocks are allocated.
+	 */
+	for (n = 1; n <= indirect_blks;  n++) {
+		/*
+		 * Get buffer_head for parent block, zero it out
+		 * and set the pointer to new one, then send
+		 * parent to disk.
+		 */
+		bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+		if (unlikely(!bh)) {
+			err = -EIO;
+			goto failed;
+		}
+
+		branch[n].bh = bh;
+		lock_buffer(bh);
+		BUFFER_TRACE(bh, "call get_create_access");
+		err = ext4_journal_get_create_access(handle, bh);
+		if (err) {
+			/* Don't brelse(bh) here; it's done in
+			 * ext4_journal_forget() below */
+			unlock_buffer(bh);
+			goto failed;
+		}
+
+		memset(bh->b_data, 0, blocksize);
+		branch[n].p = (__le32 *) bh->b_data + offsets[n];
+		branch[n].key = cpu_to_le32(new_blocks[n]);
+		*branch[n].p = branch[n].key;
+		if (n == indirect_blks) {
+			current_block = new_blocks[n];
+			/*
+			 * End of chain, update the last new metablock of
+			 * the chain to point to the new allocated
+			 * data blocks numbers
+			 */
+			for (i = 1; i < num; i++)
+				*(branch[n].p + i) = cpu_to_le32(++current_block);
+		}
+		BUFFER_TRACE(bh, "marking uptodate");
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+
+		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
+		if (err)
+			goto failed;
+	}
+	*blks = num;
+	return err;
+failed:
+	/* Allocation failed, free what we already allocated */
+	ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
+	for (i = 1; i <= n ; i++) {
+		/*
+		 * branch[i].bh is newly allocated, so there is no
+		 * need to revoke the block, which is why we don't
+		 * need to set EXT4_FREE_BLOCKS_METADATA.
+		 */
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
+				 EXT4_FREE_BLOCKS_FORGET);
+	}
+	for (i = n+1; i < indirect_blks; i++)
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
+
+	ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
+
+	return err;
+}
+
+/**
+ * ext4_splice_branch - splice the allocated branch onto inode.
+ * @handle: handle for this transaction
+ * @inode: owner
+ * @block: (logical) number of block we are adding
+ * @chain: chain of indirect blocks (with a missing link - see
+ *	ext4_alloc_branch)
+ * @where: location of missing link
+ * @num:   number of indirect blocks we are adding
+ * @blks:  number of direct blocks we are adding
+ *
+ * This function fills the missing link and does all housekeeping needed in
+ * inode (->i_blocks, etc.). In case of success we end up with the full
+ * chain to new block and return 0.
+ */
+static int ext4_splice_branch(handle_t *handle, struct inode *inode,
+			      ext4_lblk_t block, Indirect *where, int num,
+			      int blks)
+{
+	int i;
+	int err = 0;
+	ext4_fsblk_t current_block;
+
+	/*
+	 * If we're splicing into a [td]indirect block (as opposed to the
+	 * inode) then we need to get write access to the [td]indirect block
+	 * before the splice.
+	 */
+	if (where->bh) {
+		BUFFER_TRACE(where->bh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, where->bh);
+		if (err)
+			goto err_out;
+	}
+	/* That's it */
+
+	*where->p = where->key;
+
+	/*
+	 * Update the host buffer_head or inode to point to more just allocated
+	 * direct blocks blocks
+	 */
+	if (num == 0 && blks > 1) {
+		current_block = le32_to_cpu(where->key) + 1;
+		for (i = 1; i < blks; i++)
+			*(where->p + i) = cpu_to_le32(current_block++);
+	}
+
+	/* We are done with atomic stuff, now do the rest of housekeeping */
+	/* had we spliced it onto indirect block? */
+	if (where->bh) {
+		/*
+		 * If we spliced it onto an indirect block, we haven't
+		 * altered the inode.  Note however that if it is being spliced
+		 * onto an indirect block at the very end of the file (the
+		 * file is growing) then we *will* alter the inode to reflect
+		 * the new i_size.  But that is not done here - it is done in
+		 * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
+		 */
+		jbd_debug(5, "splicing indirect only\n");
+		BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, inode, where->bh);
+		if (err)
+			goto err_out;
+	} else {
+		/*
+		 * OK, we spliced it into the inode itself on a direct block.
+		 */
+		ext4_mark_inode_dirty(handle, inode);
+		jbd_debug(5, "splicing direct\n");
+	}
+	return err;
+
+err_out:
+	for (i = 1; i <= num; i++) {
+		/*
+		 * branch[i].bh is newly allocated, so there is no
+		 * need to revoke the block, which is why we don't
+		 * need to set EXT4_FREE_BLOCKS_METADATA.
+		 */
+		ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+				 EXT4_FREE_BLOCKS_FORGET);
+	}
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
+			 blks, 0);
+
+	return err;
+}
+
+/*
+ * The ext4_ind_map_blocks() function handles non-extents inodes
+ * (i.e., using the traditional indirect/double-indirect i_blocks
+ * scheme) for ext4_map_blocks().
+ *
+ * Allocation strategy is simple: if we have to allocate something, we will
+ * have to go the whole way to leaf. So let's do it before attaching anything
+ * to tree, set linkage between the newborn blocks, write them if sync is
+ * required, recheck the path, free and repeat if check fails, otherwise
+ * set the last missing link (that will protect us from any truncate-generated
+ * removals - all blocks on the path are immune now) and possibly force the
+ * write on the parent block.
+ * That has a nice additional property: no special recovery from the failed
+ * allocations is needed - we simply release blocks and do not touch anything
+ * reachable from inode.
+ *
+ * `handle' can be NULL if create == 0.
+ *
+ * return > 0, # of blocks mapped or allocated.
+ * return = 0, if plain lookup failed.
+ * return < 0, error case.
+ *
+ * The ext4_ind_get_blocks() function should be called with
+ * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
+ * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
+ * blocks.
+ */
+static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
+			       struct ext4_map_blocks *map,
+			       int flags)
+{
+	int err = -EIO;
+	ext4_lblk_t offsets[4];
+	Indirect chain[4];
+	Indirect *partial;
+	ext4_fsblk_t goal;
+	int indirect_blks;
+	int blocks_to_boundary = 0;
+	int depth;
+	int count = 0;
+	ext4_fsblk_t first_block = 0;
+
+	trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
+	J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
+	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
+	depth = ext4_block_to_path(inode, map->m_lblk, offsets,
+				   &blocks_to_boundary);
+
+	if (depth == 0)
+		goto out;
+
+	partial = ext4_get_branch(inode, depth, offsets, chain, &err);
+
+	/* Simplest case - block found, no allocation needed */
+	if (!partial) {
+		first_block = le32_to_cpu(chain[depth - 1].key);
+		count++;
+		/*map more blocks*/
+		while (count < map->m_len && count <= blocks_to_boundary) {
+			ext4_fsblk_t blk;
+
+			blk = le32_to_cpu(*(chain[depth-1].p + count));
+
+			if (blk == first_block + count)
+				count++;
+			else
+				break;
+		}
+		goto got_it;
+	}
+
+	/* Next simple case - plain lookup or failed read of indirect block */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
+		goto cleanup;
+
+	/*
+	 * Okay, we need to do block allocation.
+	*/
+	goal = ext4_find_goal(inode, map->m_lblk, partial);
+
+	/* the number of blocks need to allocate for [d,t]indirect blocks */
+	indirect_blks = (chain + depth) - partial - 1;
+
+	/*
+	 * Next look up the indirect map to count the totoal number of
+	 * direct blocks to allocate for this branch.
+	 */
+	count = ext4_blks_to_allocate(partial, indirect_blks,
+				      map->m_len, blocks_to_boundary);
+	/*
+	 * Block out ext4_truncate while we alter the tree
+	 */
+	err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
+				&count, goal,
+				offsets + (partial - chain), partial);
+
+	/*
+	 * The ext4_splice_branch call will free and forget any buffers
+	 * on the new chain if there is a failure, but that risks using
+	 * up transaction credits, especially for bitmaps where the
+	 * credits cannot be returned.  Can we handle this somehow?  We
+	 * may need to return -EAGAIN upwards in the worst case.  --sct
+	 */
+	if (!err)
+		err = ext4_splice_branch(handle, inode, map->m_lblk,
+					 partial, indirect_blks, count);
+	if (err)
+		goto cleanup;
+
+	map->m_flags |= EXT4_MAP_NEW;
+
+	ext4_update_inode_fsync_trans(handle, inode, 1);
+got_it:
+	map->m_flags |= EXT4_MAP_MAPPED;
+	map->m_pblk = le32_to_cpu(chain[depth-1].key);
+	map->m_len = count;
+	if (count > blocks_to_boundary)
+		map->m_flags |= EXT4_MAP_BOUNDARY;
+	err = count;
+	/* Clean up and exit */
+	partial = chain + depth - 1;	/* the whole chain */
+cleanup:
+	while (partial > chain) {
+		BUFFER_TRACE(partial->bh, "call brelse");
+		brelse(partial->bh);
+		partial--;
+	}
+out:
+	trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
+				map->m_pblk, map->m_len, err);
+	return err;
+}
+
+#ifdef CONFIG_QUOTA
+qsize_t *ext4_get_reserved_space(struct inode *inode)
+{
+	return &EXT4_I(inode)->i_reserved_quota;
+}
+#endif
+
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate a new block at @lblocks for non extent file based file
+ */
+static int ext4_indirect_calc_metadata_amount(struct inode *inode,
+					      sector_t lblock)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
+	int blk_bits;
+
+	if (lblock < EXT4_NDIR_BLOCKS)
+		return 0;
+
+	lblock -= EXT4_NDIR_BLOCKS;
+
+	if (ei->i_da_metadata_calc_len &&
+	    (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
+		ei->i_da_metadata_calc_len++;
+		return 0;
+	}
+	ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
+	ei->i_da_metadata_calc_len = 1;
+	blk_bits = order_base_2(lblock);
+	return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
+}
+
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate a block located at @lblock
+ */
+static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
+{
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		return ext4_ext_calc_metadata_amount(inode, lblock);
+
+	return ext4_indirect_calc_metadata_amount(inode, lblock);
+}
+
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
+void ext4_da_update_reserve_space(struct inode *inode,
+					int used, int quota_claim)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	spin_lock(&ei->i_block_reservation_lock);
+	trace_ext4_da_update_reserve_space(inode, used);
+	if (unlikely(used > ei->i_reserved_data_blocks)) {
+		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+			 "with only %d reserved data blocks\n",
+			 __func__, inode->i_ino, used,
+			 ei->i_reserved_data_blocks);
+		WARN_ON(1);
+		used = ei->i_reserved_data_blocks;
+	}
+
+	/* Update per-inode reservations */
+	ei->i_reserved_data_blocks -= used;
+	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+			   used + ei->i_allocated_meta_blocks);
+	ei->i_allocated_meta_blocks = 0;
+
+	if (ei->i_reserved_data_blocks == 0) {
+		/*
+		 * We can release all of the reserved metadata blocks
+		 * only when we have written all of the delayed
+		 * allocation blocks.
+		 */
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+				   ei->i_reserved_meta_blocks);
+		ei->i_reserved_meta_blocks = 0;
+		ei->i_da_metadata_calc_len = 0;
+	}
+	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
+	/* Update quota subsystem for data blocks */
+	if (quota_claim)
+		dquot_claim_block(inode, used);
+	else {
+		/*
+		 * We did fallocate with an offset that is already delayed
+		 * allocated. So on delayed allocated writeback we should
+		 * not re-claim the quota for fallocated blocks.
+		 */
+		dquot_release_reservation_block(inode, used);
+	}
+
+	/*
+	 * If we have done all the pending block allocations and if
+	 * there aren't any writers on the inode, we can discard the
+	 * inode's preallocations.
+	 */
+	if ((ei->i_reserved_data_blocks == 0) &&
+	    (atomic_read(&inode->i_writecount) == 0))
+		ext4_discard_preallocations(inode);
+}
+
+static int __check_block_validity(struct inode *inode, const char *func,
+				unsigned int line,
+				struct ext4_map_blocks *map)
+{
+	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
+				   map->m_len)) {
+		ext4_error_inode(inode, func, line, map->m_pblk,
+				 "lblock %lu mapped to illegal pblock "
+				 "(length %d)", (unsigned long) map->m_lblk,
+				 map->m_len);
+		return -EIO;
+	}
+	return 0;
+}
+
+#define check_block_validity(inode, map)	\
+	__check_block_validity((inode), __func__, __LINE__, (map))
+
+/*
+ * Return the number of contiguous dirty pages in a given inode
+ * starting at page frame idx.
+ */
+static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
+				    unsigned int max_pages)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t	index;
+	struct pagevec pvec;
+	pgoff_t num = 0;
+	int i, nr_pages, done = 0;
+
+	if (max_pages == 0)
+		return 0;
+	pagevec_init(&pvec, 0);
+	while (!done) {
+		index = idx;
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					      PAGECACHE_TAG_DIRTY,
+					      (pgoff_t)PAGEVEC_SIZE);
+		if (nr_pages == 0)
+			break;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			struct buffer_head *bh, *head;
+
+			lock_page(page);
+			if (unlikely(page->mapping != mapping) ||
+			    !PageDirty(page) ||
+			    PageWriteback(page) ||
+			    page->index != idx) {
+				done = 1;
+				unlock_page(page);
+				break;
+			}
+			if (page_has_buffers(page)) {
+				bh = head = page_buffers(page);
+				do {
+					if (!buffer_delay(bh) &&
+					    !buffer_unwritten(bh))
+						done = 1;
+					bh = bh->b_this_page;
+				} while (!done && (bh != head));
+			}
+			unlock_page(page);
+			if (done)
+				break;
+			idx++;
+			num++;
+			if (num >= max_pages) {
+				done = 1;
+				break;
+			}
+		}
+		pagevec_release(&pvec);
+	}
+	return num;
+}
+
+/*
+ * The ext4_map_blocks() function tries to look up the requested blocks,
+ * and returns if the blocks are already mapped.
+ *
+ * Otherwise it takes the write lock of the i_data_sem and allocate blocks
+ * and store the allocated blocks in the result buffer head and mark it
+ * mapped.
+ *
+ * If file type is extents based, it will call ext4_ext_map_blocks(),
+ * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
+ * based files
+ *
+ * On success, it returns the number of blocks being mapped or allocate.
+ * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * the result buffer head is unmapped. If the create ==1, it will make sure
+ * the buffer head is mapped.
+ *
+ * It returns 0 if plain look up failed (blocks have not been allocated), in
+ * that casem, buffer head is unmapped
+ *
+ * It returns the error in case of allocation failure.
+ */
+int ext4_map_blocks(handle_t *handle, struct inode *inode,
+		    struct ext4_map_blocks *map, int flags)
+{
+	int retval;
+
+	map->m_flags = 0;
+	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
+		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
+		  (unsigned long) map->m_lblk);
+	/*
+	 * Try to see if we can get the block without requesting a new
+	 * file system block.
+	 */
+	down_read((&EXT4_I(inode)->i_data_sem));
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		retval = ext4_ext_map_blocks(handle, inode, map, 0);
+	} else {
+		retval = ext4_ind_map_blocks(handle, inode, map, 0);
+	}
+	up_read((&EXT4_I(inode)->i_data_sem));
+
+	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+		int ret = check_block_validity(inode, map);
+		if (ret != 0)
+			return ret;
+	}
+
+	/* If it is only a block(s) look up */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
+		return retval;
+
+	/*
+	 * Returns if the blocks have already allocated
+	 *
+	 * Note that if blocks have been preallocated
+	 * ext4_ext_get_block() returns th create = 0
+	 * with buffer head unmapped.
+	 */
+	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+		return retval;
+
+	/*
+	 * When we call get_blocks without the create flag, the
+	 * BH_Unwritten flag could have gotten set if the blocks
+	 * requested were part of a uninitialized extent.  We need to
+	 * clear this flag now that we are committed to convert all or
+	 * part of the uninitialized extent to be an initialized
+	 * extent.  This is because we need to avoid the combination
+	 * of BH_Unwritten and BH_Mapped flags being simultaneously
+	 * set on the buffer_head.
+	 */
+	map->m_flags &= ~EXT4_MAP_UNWRITTEN;
+
+	/*
+	 * New blocks allocate and/or writing to uninitialized extent
+	 * will possibly result in updating i_data, so we take
+	 * the write lock of i_data_sem, and call get_blocks()
+	 * with create == 1 flag.
+	 */
+	down_write((&EXT4_I(inode)->i_data_sem));
+
+	/*
+	 * if the caller is from delayed allocation writeout path
+	 * we have already reserved fs blocks for allocation
+	 * let the underlying get_block() function know to
+	 * avoid double accounting
+	 */
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
+	/*
+	 * We need to check for EXT4 here because migrate
+	 * could have changed the inode type in between
+	 */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		retval = ext4_ext_map_blocks(handle, inode, map, flags);
+	} else {
+		retval = ext4_ind_map_blocks(handle, inode, map, flags);
+
+		if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
+			/*
+			 * We allocated new blocks which will result in
+			 * i_data's format changing.  Force the migrate
+			 * to fail by clearing migrate flags
+			 */
+			ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
+		}
+
+		/*
+		 * Update reserved blocks/metadata blocks after successful
+		 * block allocation which had been deferred till now. We don't
+		 * support fallocate for non extent files. So we can update
+		 * reserve space here.
+		 */
+		if ((retval > 0) &&
+			(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
+			ext4_da_update_reserve_space(inode, retval, 1);
+	}
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+		ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
+
+	up_write((&EXT4_I(inode)->i_data_sem));
+	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+		int ret = check_block_validity(inode, map);
+		if (ret != 0)
+			return ret;
+	}
+	return retval;
+}
+
+/* Maximum number of blocks we map for direct IO at once. */
+#define DIO_MAX_BLOCKS 4096
+
+static int _ext4_get_block(struct inode *inode, sector_t iblock,
+			   struct buffer_head *bh, int flags)
+{
+	handle_t *handle = ext4_journal_current_handle();
+	struct ext4_map_blocks map;
+	int ret = 0, started = 0;
+	int dio_credits;
+
+	map.m_lblk = iblock;
+	map.m_len = bh->b_size >> inode->i_blkbits;
+
+	if (flags && !handle) {
+		/* Direct IO write... */
+		if (map.m_len > DIO_MAX_BLOCKS)
+			map.m_len = DIO_MAX_BLOCKS;
+		dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
+		handle = ext4_journal_start(inode, dio_credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			return ret;
+		}
+		started = 1;
+	}
+
+	ret = ext4_map_blocks(handle, inode, &map, flags);
+	if (ret > 0) {
+		map_bh(bh, inode->i_sb, map.m_pblk);
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
+		ret = 0;
+	}
+	if (started)
+		ext4_journal_stop(handle);
+	return ret;
+}
+
+int ext4_get_block(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh, int create)
+{
+	return _ext4_get_block(inode, iblock, bh,
+			       create ? EXT4_GET_BLOCKS_CREATE : 0);
+}
+
+/*
+ * `handle' can be NULL if create is zero
+ */
+struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
+				ext4_lblk_t block, int create, int *errp)
+{
+	struct ext4_map_blocks map;
+	struct buffer_head *bh;
+	int fatal = 0, err;
+
+	J_ASSERT(handle != NULL || create == 0);
+
+	map.m_lblk = block;
+	map.m_len = 1;
+	err = ext4_map_blocks(handle, inode, &map,
+			      create ? EXT4_GET_BLOCKS_CREATE : 0);
+
+	if (err < 0)
+		*errp = err;
+	if (err <= 0)
+		return NULL;
+	*errp = 0;
+
+	bh = sb_getblk(inode->i_sb, map.m_pblk);
+	if (!bh) {
+		*errp = -EIO;
+		return NULL;
+	}
+	if (map.m_flags & EXT4_MAP_NEW) {
+		J_ASSERT(create != 0);
+		J_ASSERT(handle != NULL);
+
+		/*
+		 * Now that we do not always journal data, we should
+		 * keep in mind whether this should always journal the
+		 * new buffer as metadata.  For now, regular file
+		 * writes use ext4_get_block instead, so it's not a
+		 * problem.
+		 */
+		lock_buffer(bh);
+		BUFFER_TRACE(bh, "call get_create_access");
+		fatal = ext4_journal_get_create_access(handle, bh);
+		if (!fatal && !buffer_uptodate(bh)) {
+			memset(bh->b_data, 0, inode->i_sb->s_blocksize);
+			set_buffer_uptodate(bh);
+		}
+		unlock_buffer(bh);
+		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
+		if (!fatal)
+			fatal = err;
+	} else {
+		BUFFER_TRACE(bh, "not a new buffer");
+	}
+	if (fatal) {
+		*errp = fatal;
+		brelse(bh);
+		bh = NULL;
+	}
+	return bh;
+}
+
+struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
+			       ext4_lblk_t block, int create, int *err)
+{
+	struct buffer_head *bh;
+
+	bh = ext4_getblk(handle, inode, block, create, err);
+	if (!bh)
+		return bh;
+	if (buffer_uptodate(bh))
+		return bh;
+	ll_rw_block(READ_META, 1, &bh);
+	wait_on_buffer(bh);
+	if (buffer_uptodate(bh))
+		return bh;
+	put_bh(bh);
+	*err = -EIO;
+	return NULL;
+}
+
+static int walk_page_buffers(handle_t *handle,
+			     struct buffer_head *head,
+			     unsigned from,
+			     unsigned to,
+			     int *partial,
+			     int (*fn)(handle_t *handle,
+				       struct buffer_head *bh))
+{
+	struct buffer_head *bh;
+	unsigned block_start, block_end;
+	unsigned blocksize = head->b_size;
+	int err, ret = 0;
+	struct buffer_head *next;
+
+	for (bh = head, block_start = 0;
+	     ret == 0 && (bh != head || !block_start);
+	     block_start = block_end, bh = next) {
+		next = bh->b_this_page;
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (partial && !buffer_uptodate(bh))
+				*partial = 1;
+			continue;
+		}
+		err = (*fn)(handle, bh);
+		if (!ret)
+			ret = err;
+	}
+	return ret;
+}
+
+/*
+ * To preserve ordering, it is essential that the hole instantiation and
+ * the data write be encapsulated in a single transaction.  We cannot
+ * close off a transaction and start a new one between the ext4_get_block()
+ * and the commit_write().  So doing the jbd2_journal_start at the start of
+ * prepare_write() is the right place.
+ *
+ * Also, this function can nest inside ext4_writepage() ->
+ * block_write_full_page(). In that case, we *know* that ext4_writepage()
+ * has generated enough buffer credits to do the whole page.  So we won't
+ * block on the journal in that case, which is good, because the caller may
+ * be PF_MEMALLOC.
+ *
+ * By accident, ext4 can be reentered when a transaction is open via
+ * quota file writes.  If we were to commit the transaction while thus
+ * reentered, there can be a deadlock - we would be holding a quota
+ * lock, and the commit would never complete if another thread had a
+ * transaction open and was blocking on the quota lock - a ranking
+ * violation.
+ *
+ * So what we do is to rely on the fact that jbd2_journal_stop/journal_start
+ * will _not_ run commit under these circumstances because handle->h_ref
+ * is elevated.  We'll still have enough credits for the tiny quotafile
+ * write.
+ */
+static int do_journal_get_write_access(handle_t *handle,
+				       struct buffer_head *bh)
+{
+	int dirty = buffer_dirty(bh);
+	int ret;
+
+	if (!buffer_mapped(bh) || buffer_freed(bh))
+		return 0;
+	/*
+	 * __block_write_begin() could have dirtied some buffers. Clean
+	 * the dirty bit as jbd2_journal_get_write_access() could complain
+	 * otherwise about fs integrity issues. Setting of the dirty bit
+	 * by __block_write_begin() isn't a real problem here as we clear
+	 * the bit before releasing a page lock and thus writeback cannot
+	 * ever write the buffer.
+	 */
+	if (dirty)
+		clear_buffer_dirty(bh);
+	ret = ext4_journal_get_write_access(handle, bh);
+	if (!ret && dirty)
+		ret = ext4_handle_dirty_metadata(handle, NULL, bh);
+	return ret;
+}
+
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static void ext4_truncate_failed_write(struct inode *inode)
+{
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext4_truncate(inode);
+}
+
+static int ext4_get_block_write(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create);
+static int ext4_write_begin(struct file *file, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{
+	struct inode *inode = mapping->host;
+	int ret, needed_blocks;
+	handle_t *handle;
+	int retries = 0;
+	struct page *page;
+	pgoff_t index;
+	unsigned from, to;
+
+	trace_ext4_write_begin(inode, pos, len, flags);
+	/*
+	 * Reserve one block more for addition to orphan list in case
+	 * we allocate blocks but write fails for some reason
+	 */
+	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
+	index = pos >> PAGE_CACHE_SHIFT;
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
+retry:
+	handle = ext4_journal_start(inode, needed_blocks);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	/* We cannot recurse into the filesystem as the transaction is already
+	 * started */
+	flags |= AOP_FLAG_NOFS;
+
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page) {
+		ext4_journal_stop(handle);
+		ret = -ENOMEM;
+		goto out;
+	}
+	*pagep = page;
+
+	if (ext4_should_dioread_nolock(inode))
+		ret = __block_write_begin(page, pos, len, ext4_get_block_write);
+	else
+		ret = __block_write_begin(page, pos, len, ext4_get_block);
+
+	if (!ret && ext4_should_journal_data(inode)) {
+		ret = walk_page_buffers(handle, page_buffers(page),
+				from, to, NULL, do_journal_get_write_access);
+	}
+
+	if (ret) {
+		unlock_page(page);
+		page_cache_release(page);
+		/*
+		 * __block_write_begin may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 *
+		 * Add inode to orphan list in case we crash before
+		 * truncate finishes
+		 */
+		if (pos + len > inode->i_size && ext4_can_truncate(inode))
+			ext4_orphan_add(handle, inode);
+
+		ext4_journal_stop(handle);
+		if (pos + len > inode->i_size) {
+			ext4_truncate_failed_write(inode);
+			/*
+			 * If truncate failed early the inode might
+			 * still be on the orphan list; we need to
+			 * make sure the inode is removed from the
+			 * orphan list in that case.
+			 */
+			if (inode->i_nlink)
+				ext4_orphan_del(NULL, inode);
+		}
+	}
+
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+out:
+	return ret;
+}
+
+/* For write_end() in data=journal mode */
+static int write_end_fn(handle_t *handle, struct buffer_head *bh)
+{
+	if (!buffer_mapped(bh) || buffer_freed(bh))
+		return 0;
+	set_buffer_uptodate(bh);
+	return ext4_handle_dirty_metadata(handle, NULL, bh);
+}
+
+static int ext4_generic_write_end(struct file *file,
+				  struct address_space *mapping,
+				  loff_t pos, unsigned len, unsigned copied,
+				  struct page *page, void *fsdata)
+{
+	int i_size_changed = 0;
+	struct inode *inode = mapping->host;
+	handle_t *handle = ext4_journal_current_handle();
+
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	/*
+	 * No need to use i_size_read() here, the i_size
+	 * cannot change under us because we hold i_mutex.
+	 *
+	 * But it's important to update i_size while still holding page lock:
+	 * page writeout could otherwise come in and zero beyond i_size.
+	 */
+	if (pos + copied > inode->i_size) {
+		i_size_write(inode, pos + copied);
+		i_size_changed = 1;
+	}
+
+	if (pos + copied >  EXT4_I(inode)->i_disksize) {
+		/* We need to mark inode dirty even if
+		 * new_i_size is less that inode->i_size
+		 * bu greater than i_disksize.(hint delalloc)
+		 */
+		ext4_update_i_disksize(inode, (pos + copied));
+		i_size_changed = 1;
+	}
+	unlock_page(page);
+	page_cache_release(page);
+
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		ext4_mark_inode_dirty(handle, inode);
+
+	return copied;
+}
+
+/*
+ * We need to pick up the new inode size which generic_commit_write gave us
+ * `file' can be NULL - eg, when called from page_symlink().
+ *
+ * ext4 never places buffers on inode->i_mapping->private_list.  metadata
+ * buffers are managed internally.
+ */
+static int ext4_ordered_write_end(struct file *file,
+				  struct address_space *mapping,
+				  loff_t pos, unsigned len, unsigned copied,
+				  struct page *page, void *fsdata)
+{
+	handle_t *handle = ext4_journal_current_handle();
+	struct inode *inode = mapping->host;
+	int ret = 0, ret2;
+
+	trace_ext4_ordered_write_end(inode, pos, len, copied);
+	ret = ext4_jbd2_file_inode(handle, inode);
+
+	if (ret == 0) {
+		ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+		copied = ret2;
+		if (pos + len > inode->i_size && ext4_can_truncate(inode))
+			/* if we have allocated more blocks and copied
+			 * less. We will have blocks allocated outside
+			 * inode->i_size. So truncate them
+			 */
+			ext4_orphan_add(handle, inode);
+		if (ret2 < 0)
+			ret = ret2;
+	}
+	ret2 = ext4_journal_stop(handle);
+	if (!ret)
+		ret = ret2;
+
+	if (pos + len > inode->i_size) {
+		ext4_truncate_failed_write(inode);
+		/*
+		 * If truncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+
+
+	return ret ? ret : copied;
+}
+
+static int ext4_writeback_write_end(struct file *file,
+				    struct address_space *mapping,
+				    loff_t pos, unsigned len, unsigned copied,
+				    struct page *page, void *fsdata)
+{
+	handle_t *handle = ext4_journal_current_handle();
+	struct inode *inode = mapping->host;
+	int ret = 0, ret2;
+
+	trace_ext4_writeback_write_end(inode, pos, len, copied);
+	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+	copied = ret2;
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+		/* if we have allocated more blocks and copied
+		 * less. We will have blocks allocated outside
+		 * inode->i_size. So truncate them
+		 */
+		ext4_orphan_add(handle, inode);
+
+	if (ret2 < 0)
+		ret = ret2;
+
+	ret2 = ext4_journal_stop(handle);
+	if (!ret)
+		ret = ret2;
+
+	if (pos + len > inode->i_size) {
+		ext4_truncate_failed_write(inode);
+		/*
+		 * If truncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+
+	return ret ? ret : copied;
+}
+
+static int ext4_journalled_write_end(struct file *file,
+				     struct address_space *mapping,
+				     loff_t pos, unsigned len, unsigned copied,
+				     struct page *page, void *fsdata)
+{
+	handle_t *handle = ext4_journal_current_handle();
+	struct inode *inode = mapping->host;
+	int ret = 0, ret2;
+	int partial = 0;
+	unsigned from, to;
+	loff_t new_i_size;
+
+	trace_ext4_journalled_write_end(inode, pos, len, copied);
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + len;
+
+	BUG_ON(!ext4_handle_valid(handle));
+
+	if (copied < len) {
+		if (!PageUptodate(page))
+			copied = 0;
+		page_zero_new_buffers(page, from+copied, to);
+	}
+
+	ret = walk_page_buffers(handle, page_buffers(page), from,
+				to, &partial, write_end_fn);
+	if (!partial)
+		SetPageUptodate(page);
+	new_i_size = pos + copied;
+	if (new_i_size > inode->i_size)
+		i_size_write(inode, pos+copied);
+	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+	if (new_i_size > EXT4_I(inode)->i_disksize) {
+		ext4_update_i_disksize(inode, new_i_size);
+		ret2 = ext4_mark_inode_dirty(handle, inode);
+		if (!ret)
+			ret = ret2;
+	}
+
+	unlock_page(page);
+	page_cache_release(page);
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+		/* if we have allocated more blocks and copied
+		 * less. We will have blocks allocated outside
+		 * inode->i_size. So truncate them
+		 */
+		ext4_orphan_add(handle, inode);
+
+	ret2 = ext4_journal_stop(handle);
+	if (!ret)
+		ret = ret2;
+	if (pos + len > inode->i_size) {
+		ext4_truncate_failed_write(inode);
+		/*
+		 * If truncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+
+	return ret ? ret : copied;
+}
+
+/*
+ * Reserve a single block located at lblock
+ */
+static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
+{
+	int retries = 0;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned long md_needed;
+	int ret;
+
+	/*
+	 * recalculate the amount of metadata blocks to reserve
+	 * in order to allocate nrblocks
+	 * worse case is one extent per block
+	 */
+repeat:
+	spin_lock(&ei->i_block_reservation_lock);
+	md_needed = ext4_calc_metadata_amount(inode, lblock);
+	trace_ext4_da_reserve_space(inode, md_needed);
+	spin_unlock(&ei->i_block_reservation_lock);
+
+	/*
+	 * We will charge metadata quota at writeout time; this saves
+	 * us from metadata over-estimation, though we may go over by
+	 * a small amount in the end.  Here we just reserve for data.
+	 */
+	ret = dquot_reserve_block(inode, 1);
+	if (ret)
+		return ret;
+	/*
+	 * We do still charge estimated metadata to the sb though;
+	 * we cannot afford to run out of free blocks.
+	 */
+	if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
+		dquot_release_reservation_block(inode, 1);
+		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+			yield();
+			goto repeat;
+		}
+		return -ENOSPC;
+	}
+	spin_lock(&ei->i_block_reservation_lock);
+	ei->i_reserved_data_blocks++;
+	ei->i_reserved_meta_blocks += md_needed;
+	spin_unlock(&ei->i_block_reservation_lock);
+
+	return 0;       /* success */
+}
+
+static void ext4_da_release_space(struct inode *inode, int to_free)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!to_free)
+		return;		/* Nothing to release, exit */
+
+	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+
+	trace_ext4_da_release_space(inode, to_free);
+	if (unlikely(to_free > ei->i_reserved_data_blocks)) {
+		/*
+		 * if there aren't enough reserved blocks, then the
+		 * counter is messed up somewhere.  Since this
+		 * function is called from invalidate page, it's
+		 * harmless to return without any action.
+		 */
+		ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+			 "ino %lu, to_free %d with only %d reserved "
+			 "data blocks\n", inode->i_ino, to_free,
+			 ei->i_reserved_data_blocks);
+		WARN_ON(1);
+		to_free = ei->i_reserved_data_blocks;
+	}
+	ei->i_reserved_data_blocks -= to_free;
+
+	if (ei->i_reserved_data_blocks == 0) {
+		/*
+		 * We can release all of the reserved metadata blocks
+		 * only when we have written all of the delayed
+		 * allocation blocks.
+		 */
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+				   ei->i_reserved_meta_blocks);
+		ei->i_reserved_meta_blocks = 0;
+		ei->i_da_metadata_calc_len = 0;
+	}
+
+	/* update fs dirty data blocks counter */
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
+
+	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
+	dquot_release_reservation_block(inode, to_free);
+}
+
+static void ext4_da_page_release_reservation(struct page *page,
+					     unsigned long offset)
+{
+	int to_release = 0;
+	struct buffer_head *head, *bh;
+	unsigned int curr_off = 0;
+
+	head = page_buffers(page);
+	bh = head;
+	do {
+		unsigned int next_off = curr_off + bh->b_size;
+
+		if ((offset <= curr_off) && (buffer_delay(bh))) {
+			to_release++;
+			clear_buffer_delay(bh);
+		}
+		curr_off = next_off;
+	} while ((bh = bh->b_this_page) != head);
+	ext4_da_release_space(page->mapping->host, to_release);
+}
+
+/*
+ * Delayed allocation stuff
+ */
+
+/*
+ * mpage_da_submit_io - walks through extent of pages and try to write
+ * them with writepage() call back
+ *
+ * @mpd->inode: inode
+ * @mpd->first_page: first page of the extent
+ * @mpd->next_page: page after the last page of the extent
+ *
+ * By the time mpage_da_submit_io() is called we expect all blocks
+ * to be allocated. this may be wrong if allocation failed.
+ *
+ * As pages are already locked by write_cache_pages(), we can't use it
+ */
+static int mpage_da_submit_io(struct mpage_da_data *mpd,
+			      struct ext4_map_blocks *map)
+{
+	struct pagevec pvec;
+	unsigned long index, end;
+	int ret = 0, err, nr_pages, i;
+	struct inode *inode = mpd->inode;
+	struct address_space *mapping = inode->i_mapping;
+	loff_t size = i_size_read(inode);
+	unsigned int len, block_start;
+	struct buffer_head *bh, *page_bufs = NULL;
+	int journal_data = ext4_should_journal_data(inode);
+	sector_t pblock = 0, cur_logical = 0;
+	struct ext4_io_submit io_submit;
+
+	BUG_ON(mpd->next_page <= mpd->first_page);
+	memset(&io_submit, 0, sizeof(io_submit));
+	/*
+	 * We need to start from the first_page to the next_page - 1
+	 * to make sure we also write the mapped dirty buffer_heads.
+	 * If we look at mpd->b_blocknr we would only be looking
+	 * at the currently mapped buffer_heads.
+	 */
+	index = mpd->first_page;
+	end = mpd->next_page - 1;
+
+	pagevec_init(&pvec, 0);
+	while (index <= end) {
+		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+		if (nr_pages == 0)
+			break;
+		for (i = 0; i < nr_pages; i++) {
+			int commit_write = 0, skip_page = 0;
+			struct page *page = pvec.pages[i];
+
+			index = page->index;
+			if (index > end)
+				break;
+
+			if (index == size >> PAGE_CACHE_SHIFT)
+				len = size & ~PAGE_CACHE_MASK;
+			else
+				len = PAGE_CACHE_SIZE;
+			if (map) {
+				cur_logical = index << (PAGE_CACHE_SHIFT -
+							inode->i_blkbits);
+				pblock = map->m_pblk + (cur_logical -
+							map->m_lblk);
+			}
+			index++;
+
+			BUG_ON(!PageLocked(page));
+			BUG_ON(PageWriteback(page));
+
+			/*
+			 * If the page does not have buffers (for
+			 * whatever reason), try to create them using
+			 * __block_write_begin.  If this fails,
+			 * skip the page and move on.
+			 */
+			if (!page_has_buffers(page)) {
+				if (__block_write_begin(page, 0, len,
+						noalloc_get_block_write)) {
+				skip_page:
+					unlock_page(page);
+					continue;
+				}
+				commit_write = 1;
+			}
+
+			bh = page_bufs = page_buffers(page);
+			block_start = 0;
+			do {
+				if (!bh)
+					goto skip_page;
+				if (map && (cur_logical >= map->m_lblk) &&
+				    (cur_logical <= (map->m_lblk +
+						     (map->m_len - 1)))) {
+					if (buffer_delay(bh)) {
+						clear_buffer_delay(bh);
+						bh->b_blocknr = pblock;
+					}
+					if (buffer_unwritten(bh) ||
+					    buffer_mapped(bh))
+						BUG_ON(bh->b_blocknr != pblock);
+					if (map->m_flags & EXT4_MAP_UNINIT)
+						set_buffer_uninit(bh);
+					clear_buffer_unwritten(bh);
+				}
+
+				/*
+				 * skip page if block allocation undone and
+				 * block is dirty
+				 */
+				if (ext4_bh_delay_or_unwritten(NULL, bh))
+					skip_page = 1;
+				bh = bh->b_this_page;
+				block_start += bh->b_size;
+				cur_logical++;
+				pblock++;
+			} while (bh != page_bufs);
+
+			if (skip_page)
+				goto skip_page;
+
+			if (commit_write)
+				/* mark the buffer_heads as dirty & uptodate */
+				block_commit_write(page, 0, len);
+
+			clear_page_dirty_for_io(page);
+			/*
+			 * Delalloc doesn't support data journalling,
+			 * but eventually maybe we'll lift this
+			 * restriction.
+			 */
+			if (unlikely(journal_data && PageChecked(page)))
+				err = __ext4_journalled_writepage(page, len);
+			else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
+				err = ext4_bio_write_page(&io_submit, page,
+							  len, mpd->wbc);
+			else if (buffer_uninit(page_bufs)) {
+				ext4_set_bh_endio(page_bufs, inode);
+				err = block_write_full_page_endio(page,
+					noalloc_get_block_write,
+					mpd->wbc, ext4_end_io_buffer_write);
+			} else
+				err = block_write_full_page(page,
+					noalloc_get_block_write, mpd->wbc);
+
+			if (!err)
+				mpd->pages_written++;
+			/*
+			 * In error case, we have to continue because
+			 * remaining pages are still locked
+			 */
+			if (ret == 0)
+				ret = err;
+		}
+		pagevec_release(&pvec);
+	}
+	ext4_io_submit(&io_submit);
+	return ret;
+}
+
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
+{
+	int nr_pages, i;
+	pgoff_t index, end;
+	struct pagevec pvec;
+	struct inode *inode = mpd->inode;
+	struct address_space *mapping = inode->i_mapping;
+
+	index = mpd->first_page;
+	end   = mpd->next_page - 1;
+	while (index <= end) {
+		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+		if (nr_pages == 0)
+			break;
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			if (page->index > end)
+				break;
+			BUG_ON(!PageLocked(page));
+			BUG_ON(PageWriteback(page));
+			block_invalidatepage(page, 0);
+			ClearPageUptodate(page);
+			unlock_page(page);
+		}
+		index = pvec.pages[nr_pages - 1]->index + 1;
+		pagevec_release(&pvec);
+	}
+	return;
+}
+
+static void ext4_print_free_blocks(struct inode *inode)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	printk(KERN_CRIT "Total free blocks count %lld\n",
+	       ext4_count_free_blocks(inode->i_sb));
+	printk(KERN_CRIT "Free/Dirty block details\n");
+	printk(KERN_CRIT "free_blocks=%lld\n",
+	       (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+	printk(KERN_CRIT "dirty_blocks=%lld\n",
+	       (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+	printk(KERN_CRIT "Block reservation details\n");
+	printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
+	       EXT4_I(inode)->i_reserved_data_blocks);
+	printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
+	       EXT4_I(inode)->i_reserved_meta_blocks);
+	return;
+}
+
+/*
+ * mpage_da_map_and_submit - go through given space, map them
+ *       if necessary, and then submit them for I/O
+ *
+ * @mpd - bh describing space
+ *
+ * The function skips space we know is already mapped to disk blocks.
+ *
+ */
+static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
+{
+	int err, blks, get_blocks_flags;
+	struct ext4_map_blocks map, *mapp = NULL;
+	sector_t next = mpd->b_blocknr;
+	unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
+	loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
+	handle_t *handle = NULL;
+
+	/*
+	 * If the blocks are mapped already, or we couldn't accumulate
+	 * any blocks, then proceed immediately to the submission stage.
+	 */
+	if ((mpd->b_size == 0) ||
+	    ((mpd->b_state  & (1 << BH_Mapped)) &&
+	     !(mpd->b_state & (1 << BH_Delay)) &&
+	     !(mpd->b_state & (1 << BH_Unwritten))))
+		goto submit_io;
+
+	handle = ext4_journal_current_handle();
+	BUG_ON(!handle);
+
+	/*
+	 * Call ext4_map_blocks() to allocate any delayed allocation
+	 * blocks, or to convert an uninitialized extent to be
+	 * initialized (in the case where we have written into
+	 * one or more preallocated blocks).
+	 *
+	 * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to
+	 * indicate that we are on the delayed allocation path.  This
+	 * affects functions in many different parts of the allocation
+	 * call path.  This flag exists primarily because we don't
+	 * want to change *many* call functions, so ext4_map_blocks()
+	 * will set the EXT4_STATE_DELALLOC_RESERVED flag once the
+	 * inode's allocation semaphore is taken.
+	 *
+	 * If the blocks in questions were delalloc blocks, set
+	 * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
+	 * variables are updated after the blocks have been allocated.
+	 */
+	map.m_lblk = next;
+	map.m_len = max_blocks;
+	get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
+	if (ext4_should_dioread_nolock(mpd->inode))
+		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
+	if (mpd->b_state & (1 << BH_Delay))
+		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
+	blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
+	if (blks < 0) {
+		struct super_block *sb = mpd->inode->i_sb;
+
+		err = blks;
+		/*
+		 * If get block returns EAGAIN or ENOSPC and there
+		 * appears to be free blocks we will just let
+		 * mpage_da_submit_io() unlock all of the pages.
+		 */
+		if (err == -EAGAIN)
+			goto submit_io;
+
+		if (err == -ENOSPC &&
+		    ext4_count_free_blocks(sb)) {
+			mpd->retval = err;
+			goto submit_io;
+		}
+
+		/*
+		 * get block failure will cause us to loop in
+		 * writepages, because a_ops->writepage won't be able
+		 * to make progress. The page will be redirtied by
+		 * writepage and writepages will again try to write
+		 * the same.
+		 */
+		if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+			ext4_msg(sb, KERN_CRIT,
+				 "delayed block allocation failed for inode %lu "
+				 "at logical offset %llu with max blocks %zd "
+				 "with error %d", mpd->inode->i_ino,
+				 (unsigned long long) next,
+				 mpd->b_size >> mpd->inode->i_blkbits, err);
+			ext4_msg(sb, KERN_CRIT,
+				"This should not happen!! Data will be lost\n");
+			if (err == -ENOSPC)
+				ext4_print_free_blocks(mpd->inode);
+		}
+		/* invalidate all the pages */
+		ext4_da_block_invalidatepages(mpd);
+
+		/* Mark this page range as having been completed */
+		mpd->io_done = 1;
+		return;
+	}
+	BUG_ON(blks == 0);
+
+	mapp = &map;
+	if (map.m_flags & EXT4_MAP_NEW) {
+		struct block_device *bdev = mpd->inode->i_sb->s_bdev;
+		int i;
+
+		for (i = 0; i < map.m_len; i++)
+			unmap_underlying_metadata(bdev, map.m_pblk + i);
+	}
+
+	if (ext4_should_order_data(mpd->inode)) {
+		err = ext4_jbd2_file_inode(handle, mpd->inode);
+		if (err)
+			/* This only happens if the journal is aborted */
+			return;
+	}
+
+	/*
+	 * Update on-disk size along with block allocation.
+	 */
+	disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits;
+	if (disksize > i_size_read(mpd->inode))
+		disksize = i_size_read(mpd->inode);
+	if (disksize > EXT4_I(mpd->inode)->i_disksize) {
+		ext4_update_i_disksize(mpd->inode, disksize);
+		err = ext4_mark_inode_dirty(handle, mpd->inode);
+		if (err)
+			ext4_error(mpd->inode->i_sb,
+				   "Failed to mark inode %lu dirty",
+				   mpd->inode->i_ino);
+	}
+
+submit_io:
+	mpage_da_submit_io(mpd, mapp);
+	mpd->io_done = 1;
+}
+
+#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
+		(1 << BH_Delay) | (1 << BH_Unwritten))
+
+/*
+ * mpage_add_bh_to_extent - try to add one more block to extent of blocks
+ *
+ * @mpd->lbh - extent of blocks
+ * @logical - logical number of the block in the file
+ * @bh - bh of the block (used to access block's state)
+ *
+ * the function is used to collect contig. blocks in same state
+ */
+static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
+				   sector_t logical, size_t b_size,
+				   unsigned long b_state)
+{
+	sector_t next;
+	int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
+
+	/*
+	 * XXX Don't go larger than mballoc is willing to allocate
+	 * This is a stopgap solution.  We eventually need to fold
+	 * mpage_da_submit_io() into this function and then call
+	 * ext4_map_blocks() multiple times in a loop
+	 */
+	if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
+		goto flush_it;
+
+	/* check if thereserved journal credits might overflow */
+	if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
+		if (nrblocks >= EXT4_MAX_TRANS_DATA) {
+			/*
+			 * With non-extent format we are limited by the journal
+			 * credit available.  Total credit needed to insert
+			 * nrblocks contiguous blocks is dependent on the
+			 * nrblocks.  So limit nrblocks.
+			 */
+			goto flush_it;
+		} else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) >
+				EXT4_MAX_TRANS_DATA) {
+			/*
+			 * Adding the new buffer_head would make it cross the
+			 * allowed limit for which we have journal credit
+			 * reserved. So limit the new bh->b_size
+			 */
+			b_size = (EXT4_MAX_TRANS_DATA - nrblocks) <<
+						mpd->inode->i_blkbits;
+			/* we will do mpage_da_submit_io in the next loop */
+		}
+	}
+	/*
+	 * First block in the extent
+	 */
+	if (mpd->b_size == 0) {
+		mpd->b_blocknr = logical;
+		mpd->b_size = b_size;
+		mpd->b_state = b_state & BH_FLAGS;
+		return;
+	}
+
+	next = mpd->b_blocknr + nrblocks;
+	/*
+	 * Can we merge the block to our big extent?
+	 */
+	if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) {
+		mpd->b_size += b_size;
+		return;
+	}
+
+flush_it:
+	/*
+	 * We couldn't merge the block to our extent, so we
+	 * need to flush current  extent and start new one
+	 */
+	mpage_da_map_and_submit(mpd);
+	return;
+}
+
+static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
+{
+	return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
+}
+
+/*
+ * This is a special get_blocks_t callback which is used by
+ * ext4_da_write_begin().  It will either return mapped block or
+ * reserve space for a single block.
+ *
+ * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
+ * We also have b_blocknr = -1 and b_bdev initialized properly
+ *
+ * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
+ * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
+ * initialized properly.
+ */
+static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
+				  struct buffer_head *bh, int create)
+{
+	struct ext4_map_blocks map;
+	int ret = 0;
+	sector_t invalid_block = ~((sector_t) 0xffff);
+
+	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+		invalid_block = ~0;
+
+	BUG_ON(create == 0);
+	BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
+
+	map.m_lblk = iblock;
+	map.m_len = 1;
+
+	/*
+	 * first, we need to know whether the block is allocated already
+	 * preallocated blocks are unmapped but should treated
+	 * the same as allocated blocks.
+	 */
+	ret = ext4_map_blocks(NULL, inode, &map, 0);
+	if (ret < 0)
+		return ret;
+	if (ret == 0) {
+		if (buffer_delay(bh))
+			return 0; /* Not sure this could or should happen */
+		/*
+		 * XXX: __block_write_begin() unmaps passed block, is it OK?
+		 */
+		ret = ext4_da_reserve_space(inode, iblock);
+		if (ret)
+			/* not enough space to reserve */
+			return ret;
+
+		map_bh(bh, inode->i_sb, invalid_block);
+		set_buffer_new(bh);
+		set_buffer_delay(bh);
+		return 0;
+	}
+
+	map_bh(bh, inode->i_sb, map.m_pblk);
+	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+
+	if (buffer_unwritten(bh)) {
+		/* A delayed write to unwritten bh should be marked
+		 * new and mapped.  Mapped ensures that we don't do
+		 * get_block multiple times when we write to the same
+		 * offset and new ensures that we do proper zero out
+		 * for partial write.
+		 */
+		set_buffer_new(bh);
+		set_buffer_mapped(bh);
+	}
+	return 0;
+}
+
+/*
+ * This function is used as a standard get_block_t calback function
+ * when there is no desire to allocate any blocks.  It is used as a
+ * callback function for block_write_begin() and block_write_full_page().
+ * These functions should only try to map a single block at a time.
+ *
+ * Since this function doesn't do block allocations even if the caller
+ * requests it by passing in create=1, it is critically important that
+ * any caller checks to make sure that any buffer heads are returned
+ * by this function are either all already mapped or marked for
+ * delayed allocation before calling  block_write_full_page().  Otherwise,
+ * b_blocknr could be left unitialized, and the page write functions will
+ * be taken by surprise.
+ */
+static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
+				   struct buffer_head *bh_result, int create)
+{
+	BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+	return _ext4_get_block(inode, iblock, bh_result, 0);
+}
+
+static int bget_one(handle_t *handle, struct buffer_head *bh)
+{
+	get_bh(bh);
+	return 0;
+}
+
+static int bput_one(handle_t *handle, struct buffer_head *bh)
+{
+	put_bh(bh);
+	return 0;
+}
+
+static int __ext4_journalled_writepage(struct page *page,
+				       unsigned int len)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+	struct buffer_head *page_bufs;
+	handle_t *handle = NULL;
+	int ret = 0;
+	int err;
+
+	ClearPageChecked(page);
+	page_bufs = page_buffers(page);
+	BUG_ON(!page_bufs);
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
+	/* As soon as we unlock the page, it can go away, but we have
+	 * references to buffers so we are safe */
+	unlock_page(page);
+
+	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	BUG_ON(!ext4_handle_valid(handle));
+
+	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				do_journal_get_write_access);
+
+	err = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				write_end_fn);
+	if (ret == 0)
+		ret = err;
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
+	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+out:
+	return ret;
+}
+
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
+
+/*
+ * Note that we don't need to start a transaction unless we're journaling data
+ * because we should have holes filled from ext4_page_mkwrite(). We even don't
+ * need to file the inode to the transaction's list in ordered mode because if
+ * we are writing back data added by write(), the inode is already there and if
+ * we are writing back data modified via mmap(), no one guarantees in which
+ * transaction the data will hit the disk. In case we are journaling data, we
+ * cannot start transaction directly because transaction start ranks above page
+ * lock so we have to do some magic.
+ *
+ * This function can get called via...
+ *   - ext4_da_writepages after taking page lock (have journal handle)
+ *   - journal_submit_inode_data_buffers (no journal handle)
+ *   - shrink_page_list via pdflush (no journal handle)
+ *   - grab_page_cache when doing write_begin (have journal handle)
+ *
+ * We don't do any block allocation in this function. If we have page with
+ * multiple blocks we need to write those buffer_heads that are mapped. This
+ * is important for mmaped based write. So if we do with blocksize 1K
+ * truncate(f, 1024);
+ * a = mmap(f, 0, 4096);
+ * a[0] = 'a';
+ * truncate(f, 4096);
+ * we have in the page first buffer_head mapped via page_mkwrite call back
+ * but other bufer_heads would be unmapped but dirty(dirty done via the
+ * do_wp_page). So writepage should write the first block. If we modify
+ * the mmap area beyond 1024 we will again get a page_fault and the
+ * page_mkwrite callback will do the block allocation and mark the
+ * buffer_heads mapped.
+ *
+ * We redirty the page if we have any buffer_heads that is either delay or
+ * unwritten in the page.
+ *
+ * We can get recursively called as show below.
+ *
+ *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
+ *		ext4_writepage()
+ *
+ * But since we don't do any block allocation we should not deadlock.
+ * Page also have the dirty flag cleared so we don't get recurive page_lock.
+ */
+static int ext4_writepage(struct page *page,
+			  struct writeback_control *wbc)
+{
+	int ret = 0, commit_write = 0;
+	loff_t size;
+	unsigned int len;
+	struct buffer_head *page_bufs = NULL;
+	struct inode *inode = page->mapping->host;
+
+	trace_ext4_writepage(page);
+	size = i_size_read(inode);
+	if (page->index == size >> PAGE_CACHE_SHIFT)
+		len = size & ~PAGE_CACHE_MASK;
+	else
+		len = PAGE_CACHE_SIZE;
+
+	/*
+	 * If the page does not have buffers (for whatever reason),
+	 * try to create them using __block_write_begin.  If this
+	 * fails, redirty the page and move on.
+	 */
+	if (!page_has_buffers(page)) {
+		if (__block_write_begin(page, 0, len,
+					noalloc_get_block_write)) {
+		redirty_page:
+			redirty_page_for_writepage(wbc, page);
+			unlock_page(page);
+			return 0;
+		}
+		commit_write = 1;
+	}
+	page_bufs = page_buffers(page);
+	if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+			      ext4_bh_delay_or_unwritten)) {
+		/*
+		 * We don't want to do block allocation, so redirty
+		 * the page and return.  We may reach here when we do
+		 * a journal commit via journal_submit_inode_data_buffers.
+		 * We can also reach here via shrink_page_list
+		 */
+		goto redirty_page;
+	}
+	if (commit_write)
+		/* now mark the buffer_heads as dirty and uptodate */
+		block_commit_write(page, 0, len);
+
+	if (PageChecked(page) && ext4_should_journal_data(inode))
+		/*
+		 * It's mmapped pagecache.  Add buffers and journal it.  There
+		 * doesn't seem much point in redirtying the page here.
+		 */
+		return __ext4_journalled_writepage(page, len);
+
+	if (buffer_uninit(page_bufs)) {
+		ext4_set_bh_endio(page_bufs, inode);
+		ret = block_write_full_page_endio(page, noalloc_get_block_write,
+					    wbc, ext4_end_io_buffer_write);
+	} else
+		ret = block_write_full_page(page, noalloc_get_block_write,
+					    wbc);
+
+	return ret;
+}
+
+/*
+ * This is called via ext4_da_writepages() to
+ * calculate the total number of credits to reserve to fit
+ * a single extent allocation into a single transaction,
+ * ext4_da_writpeages() will loop calling this before
+ * the block allocation.
+ */
+
+static int ext4_da_writepages_trans_blocks(struct inode *inode)
+{
+	int max_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+
+	/*
+	 * With non-extent format the journal credit needed to
+	 * insert nrblocks contiguous block is dependent on
+	 * number of contiguous block. So we will limit
+	 * number of contiguous block to a sane value
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
+	    (max_blocks > EXT4_MAX_TRANS_DATA))
+		max_blocks = EXT4_MAX_TRANS_DATA;
+
+	return ext4_chunk_trans_blocks(inode, max_blocks);
+}
+
+/*
+ * write_cache_pages_da - walk the list of dirty pages of the given
+ * address space and accumulate pages that need writing, and call
+ * mpage_da_map_and_submit to map a single contiguous memory region
+ * and then write them.
+ */
+static int write_cache_pages_da(struct address_space *mapping,
+				struct writeback_control *wbc,
+				struct mpage_da_data *mpd,
+				pgoff_t *done_index)
+{
+	struct buffer_head	*bh, *head;
+	struct inode		*inode = mapping->host;
+	struct pagevec		pvec;
+	unsigned int		nr_pages;
+	sector_t		logical;
+	pgoff_t			index, end;
+	long			nr_to_write = wbc->nr_to_write;
+	int			i, tag, ret = 0;
+
+	memset(mpd, 0, sizeof(struct mpage_da_data));
+	mpd->wbc = wbc;
+	mpd->inode = inode;
+	pagevec_init(&pvec, 0);
+	index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end = wbc->range_end >> PAGE_CACHE_SHIFT;
+
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		tag = PAGECACHE_TAG_TOWRITE;
+	else
+		tag = PAGECACHE_TAG_DIRTY;
+
+	*done_index = index;
+	while (index <= end) {
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
+			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			return 0;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping. However, page->index will not change
+			 * because we have a reference on the page.
+			 */
+			if (page->index > end)
+				goto out;
+
+			*done_index = page->index + 1;
+
+			/*
+			 * If we can't merge this page, and we have
+			 * accumulated an contiguous region, write it
+			 */
+			if ((mpd->next_page != page->index) &&
+			    (mpd->next_page != mpd->first_page)) {
+				mpage_da_map_and_submit(mpd);
+				goto ret_extent_tail;
+			}
+
+			lock_page(page);
+
+			/*
+			 * If the page is no longer dirty, or its
+			 * mapping no longer corresponds to inode we
+			 * are writing (which means it has been
+			 * truncated or invalidated), or the page is
+			 * already under writeback and we are not
+			 * doing a data integrity writeback, skip the page
+			 */
+			if (!PageDirty(page) ||
+			    (PageWriteback(page) &&
+			     (wbc->sync_mode == WB_SYNC_NONE)) ||
+			    unlikely(page->mapping != mapping)) {
+				unlock_page(page);
+				continue;
+			}
+
+			wait_on_page_writeback(page);
+			BUG_ON(PageWriteback(page));
+
+			if (mpd->next_page != page->index)
+				mpd->first_page = page->index;
+			mpd->next_page = page->index + 1;
+			logical = (sector_t) page->index <<
+				(PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+			if (!page_has_buffers(page)) {
+				mpage_add_bh_to_extent(mpd, logical,
+						       PAGE_CACHE_SIZE,
+						       (1 << BH_Dirty) | (1 << BH_Uptodate));
+				if (mpd->io_done)
+					goto ret_extent_tail;
+			} else {
+				/*
+				 * Page with regular buffer heads,
+				 * just add all dirty ones
+				 */
+				head = page_buffers(page);
+				bh = head;
+				do {
+					BUG_ON(buffer_locked(bh));
+					/*
+					 * We need to try to allocate
+					 * unmapped blocks in the same page.
+					 * Otherwise we won't make progress
+					 * with the page in ext4_writepage
+					 */
+					if (ext4_bh_delay_or_unwritten(NULL, bh)) {
+						mpage_add_bh_to_extent(mpd, logical,
+								       bh->b_size,
+								       bh->b_state);
+						if (mpd->io_done)
+							goto ret_extent_tail;
+					} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+						/*
+						 * mapped dirty buffer. We need
+						 * to update the b_state
+						 * because we look at b_state
+						 * in mpage_da_map_blocks.  We
+						 * don't update b_size because
+						 * if we find an unmapped
+						 * buffer_head later we need to
+						 * use the b_state flag of that
+						 * buffer_head.
+						 */
+						if (mpd->b_size == 0)
+							mpd->b_state = bh->b_state & BH_FLAGS;
+					}
+					logical++;
+				} while ((bh = bh->b_this_page) != head);
+			}
+
+			if (nr_to_write > 0) {
+				nr_to_write--;
+				if (nr_to_write == 0 &&
+				    wbc->sync_mode == WB_SYNC_NONE)
+					/*
+					 * We stop writing back only if we are
+					 * not doing integrity sync. In case of
+					 * integrity sync we have to keep going
+					 * because someone may be concurrently
+					 * dirtying pages, and we might have
+					 * synced a lot of newly appeared dirty
+					 * pages, but have not synced all of the
+					 * old dirty pages.
+					 */
+					goto out;
+			}
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+	return 0;
+ret_extent_tail:
+	ret = MPAGE_DA_EXTENT_TAIL;
+out:
+	pagevec_release(&pvec);
+	cond_resched();
+	return ret;
+}
+
+
+static int ext4_da_writepages(struct address_space *mapping,
+			      struct writeback_control *wbc)
+{
+	pgoff_t	index;
+	int range_whole = 0;
+	handle_t *handle = NULL;
+	struct mpage_da_data mpd;
+	struct inode *inode = mapping->host;
+	int pages_written = 0;
+	unsigned int max_pages;
+	int range_cyclic, cycled = 1, io_done = 0;
+	int needed_blocks, ret = 0;
+	long desired_nr_to_write, nr_to_writebump = 0;
+	loff_t range_start = wbc->range_start;
+	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+	pgoff_t done_index = 0;
+	pgoff_t end;
+
+	trace_ext4_da_writepages(inode, wbc);
+
+	/*
+	 * No pages to write? This is mainly a kludge to avoid starting
+	 * a transaction for special inodes like journal inode on last iput()
+	 * because that could violate lock ordering on umount
+	 */
+	if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+		return 0;
+
+	/*
+	 * If the filesystem has aborted, it is read-only, so return
+	 * right away instead of dumping stack traces later on that
+	 * will obscure the real source of the problem.  We test
+	 * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
+	 * the latter could be true if the filesystem is mounted
+	 * read-only, and in that case, ext4_da_writepages should
+	 * *never* be called, so if that ever happens, we would want
+	 * the stack trace.
+	 */
+	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
+		return -EROFS;
+
+	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+		range_whole = 1;
+
+	range_cyclic = wbc->range_cyclic;
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index;
+		if (index)
+			cycled = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = LLONG_MAX;
+		wbc->range_cyclic = 0;
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+	}
+
+	/*
+	 * This works around two forms of stupidity.  The first is in
+	 * the writeback code, which caps the maximum number of pages
+	 * written to be 1024 pages.  This is wrong on multiple
+	 * levels; different architectues have a different page size,
+	 * which changes the maximum amount of data which gets
+	 * written.  Secondly, 4 megabytes is way too small.  XFS
+	 * forces this value to be 16 megabytes by multiplying
+	 * nr_to_write parameter by four, and then relies on its
+	 * allocator to allocate larger extents to make them
+	 * contiguous.  Unfortunately this brings us to the second
+	 * stupidity, which is that ext4's mballoc code only allocates
+	 * at most 2048 blocks.  So we force contiguous writes up to
+	 * the number of dirty blocks in the inode, or
+	 * sbi->max_writeback_mb_bump whichever is smaller.
+	 */
+	max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
+	if (!range_cyclic && range_whole) {
+		if (wbc->nr_to_write == LONG_MAX)
+			desired_nr_to_write = wbc->nr_to_write;
+		else
+			desired_nr_to_write = wbc->nr_to_write * 8;
+	} else
+		desired_nr_to_write = ext4_num_dirty_pages(inode, index,
+							   max_pages);
+	if (desired_nr_to_write > max_pages)
+		desired_nr_to_write = max_pages;
+
+	if (wbc->nr_to_write < desired_nr_to_write) {
+		nr_to_writebump = desired_nr_to_write - wbc->nr_to_write;
+		wbc->nr_to_write = desired_nr_to_write;
+	}
+
+retry:
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		tag_pages_for_writeback(mapping, index, end);
+
+	while (!ret && wbc->nr_to_write > 0) {
+
+		/*
+		 * we  insert one extent at a time. So we need
+		 * credit needed for single extent allocation.
+		 * journalled mode is currently not supported
+		 * by delalloc
+		 */
+		BUG_ON(ext4_should_journal_data(inode));
+		needed_blocks = ext4_da_writepages_trans_blocks(inode);
+
+		/* start a new transaction*/
+		handle = ext4_journal_start(inode, needed_blocks);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
+			       "%ld pages, ino %lu; err %d", __func__,
+				wbc->nr_to_write, inode->i_ino, ret);
+			goto out_writepages;
+		}
+
+		/*
+		 * Now call write_cache_pages_da() to find the next
+		 * contiguous region of logical blocks that need
+		 * blocks to be allocated by ext4 and submit them.
+		 */
+		ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index);
+		/*
+		 * If we have a contiguous extent of pages and we
+		 * haven't done the I/O yet, map the blocks and submit
+		 * them for I/O.
+		 */
+		if (!mpd.io_done && mpd.next_page != mpd.first_page) {
+			mpage_da_map_and_submit(&mpd);
+			ret = MPAGE_DA_EXTENT_TAIL;
+		}
+		trace_ext4_da_write_pages(inode, &mpd);
+		wbc->nr_to_write -= mpd.pages_written;
+
+		ext4_journal_stop(handle);
+
+		if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
+			/* commit the transaction which would
+			 * free blocks released in the transaction
+			 * and try again
+			 */
+			jbd2_journal_force_commit_nested(sbi->s_journal);
+			ret = 0;
+		} else if (ret == MPAGE_DA_EXTENT_TAIL) {
+			/*
+			 * got one extent now try with
+			 * rest of the pages
+			 */
+			pages_written += mpd.pages_written;
+			ret = 0;
+			io_done = 1;
+		} else if (wbc->nr_to_write)
+			/*
+			 * There is no more writeout needed
+			 * or we requested for a noblocking writeout
+			 * and we found the device congested
+			 */
+			break;
+	}
+	if (!io_done && !cycled) {
+		cycled = 1;
+		index = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = mapping->writeback_index - 1;
+		goto retry;
+	}
+
+	/* Update index */
+	wbc->range_cyclic = range_cyclic;
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		/*
+		 * set the writeback_index so that range_cyclic
+		 * mode will write it back later
+		 */
+		mapping->writeback_index = done_index;
+
+out_writepages:
+	wbc->nr_to_write -= nr_to_writebump;
+	wbc->range_start = range_start;
+	trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
+	return ret;
+}
+
+#define FALL_BACK_TO_NONDELALLOC 1
+static int ext4_nonda_switch(struct super_block *sb)
+{
+	s64 free_blocks, dirty_blocks;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	/*
+	 * switch to non delalloc mode if we are running low
+	 * on free block. The free block accounting via percpu
+	 * counters can get slightly wrong with percpu_counter_batch getting
+	 * accumulated on each CPU without updating global counters
+	 * Delalloc need an accurate free block accounting. So switch
+	 * to non delalloc when we are near to error range.
+	 */
+	free_blocks  = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+	if (2 * free_blocks < 3 * dirty_blocks ||
+		free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+		/*
+		 * free block count is less than 150% of dirty blocks
+		 * or free blocks is less than watermark
+		 */
+		return 1;
+	}
+	/*
+	 * Even if we don't switch but are nearing capacity,
+	 * start pushing delalloc when 1/2 of free blocks are dirty.
+	 */
+	if (free_blocks < 2 * dirty_blocks)
+		writeback_inodes_sb_if_idle(sb);
+
+	return 0;
+}
+
+static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
+			       loff_t pos, unsigned len, unsigned flags,
+			       struct page **pagep, void **fsdata)
+{
+	int ret, retries = 0;
+	struct page *page;
+	pgoff_t index;
+	struct inode *inode = mapping->host;
+	handle_t *handle;
+
+	index = pos >> PAGE_CACHE_SHIFT;
+
+	if (ext4_nonda_switch(inode->i_sb)) {
+		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
+		return ext4_write_begin(file, mapping, pos,
+					len, flags, pagep, fsdata);
+	}
+	*fsdata = (void *)0;
+	trace_ext4_da_write_begin(inode, pos, len, flags);
+retry:
+	/*
+	 * With delayed allocation, we don't log the i_disksize update
+	 * if there is delayed block allocation. But we still need
+	 * to journalling the i_disksize update if writes to the end
+	 * of file which has an already mapped buffer.
+	 */
+	handle = ext4_journal_start(inode, 1);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+	/* We cannot recurse into the filesystem as the transaction is already
+	 * started */
+	flags |= AOP_FLAG_NOFS;
+
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page) {
+		ext4_journal_stop(handle);
+		ret = -ENOMEM;
+		goto out;
+	}
+	*pagep = page;
+
+	ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
+	if (ret < 0) {
+		unlock_page(page);
+		ext4_journal_stop(handle);
+		page_cache_release(page);
+		/*
+		 * block_write_begin may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 */
+		if (pos + len > inode->i_size)
+			ext4_truncate_failed_write(inode);
+	}
+
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+out:
+	return ret;
+}
+
+/*
+ * Check if we should update i_disksize
+ * when write to the end of file but not require block allocation
+ */
+static int ext4_da_should_update_i_disksize(struct page *page,
+					    unsigned long offset)
+{
+	struct buffer_head *bh;
+	struct inode *inode = page->mapping->host;
+	unsigned int idx;
+	int i;
+
+	bh = page_buffers(page);
+	idx = offset >> inode->i_blkbits;
+
+	for (i = 0; i < idx; i++)
+		bh = bh->b_this_page;
+
+	if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
+		return 0;
+	return 1;
+}
+
+static int ext4_da_write_end(struct file *file,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len, unsigned copied,
+			     struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	int ret = 0, ret2;
+	handle_t *handle = ext4_journal_current_handle();
+	loff_t new_i_size;
+	unsigned long start, end;
+	int write_mode = (int)(unsigned long)fsdata;
+
+	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
+		switch (ext4_inode_journal_mode(inode)) {
+		case EXT4_INODE_ORDERED_DATA_MODE:
+			return ext4_ordered_write_end(file, mapping, pos,
+					len, copied, page, fsdata);
+		case EXT4_INODE_WRITEBACK_DATA_MODE:
+			return ext4_writeback_write_end(file, mapping, pos,
+					len, copied, page, fsdata);
+		default:
+			BUG();
+		}
+	}
+
+	trace_ext4_da_write_end(inode, pos, len, copied);
+	start = pos & (PAGE_CACHE_SIZE - 1);
+	end = start + copied - 1;
+
+	/*
+	 * generic_write_end() will run mark_inode_dirty() if i_size
+	 * changes.  So let's piggyback the i_disksize mark_inode_dirty
+	 * into that.
+	 */
+
+	new_i_size = pos + copied;
+	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
+		if (ext4_da_should_update_i_disksize(page, end)) {
+			down_write(&EXT4_I(inode)->i_data_sem);
+			if (new_i_size > EXT4_I(inode)->i_disksize) {
+				/*
+				 * Updating i_disksize when extending file
+				 * without needing block allocation
+				 */
+				if (ext4_should_order_data(inode))
+					ret = ext4_jbd2_file_inode(handle,
+								   inode);
+
+				EXT4_I(inode)->i_disksize = new_i_size;
+			}
+			up_write(&EXT4_I(inode)->i_data_sem);
+			/* We need to mark inode dirty even if
+			 * new_i_size is less that inode->i_size
+			 * bu greater than i_disksize.(hint delalloc)
+			 */
+			ext4_mark_inode_dirty(handle, inode);
+		}
+	}
+	ret2 = generic_write_end(file, mapping, pos, len, copied,
+							page, fsdata);
+	copied = ret2;
+	if (ret2 < 0)
+		ret = ret2;
+	ret2 = ext4_journal_stop(handle);
+	if (!ret)
+		ret = ret2;
+
+	return ret ? ret : copied;
+}
+
+static void ext4_da_invalidatepage(struct page *page, unsigned long offset)
+{
+	/*
+	 * Drop reserved blocks
+	 */
+	BUG_ON(!PageLocked(page));
+	if (!page_has_buffers(page))
+		goto out;
+
+	ext4_da_page_release_reservation(page, offset);
+
+out:
+	ext4_invalidatepage(page, offset);
+
+	return;
+}
+
+/*
+ * Force all delayed allocation blocks to be allocated for a given inode.
+ */
+int ext4_alloc_da_blocks(struct inode *inode)
+{
+	trace_ext4_alloc_da_blocks(inode);
+
+	if (!EXT4_I(inode)->i_reserved_data_blocks &&
+	    !EXT4_I(inode)->i_reserved_meta_blocks)
+		return 0;
+
+	/*
+	 * We do something simple for now.  The filemap_flush() will
+	 * also start triggering a write of the data blocks, which is
+	 * not strictly speaking necessary (and for users of
+	 * laptop_mode, not even desirable).  However, to do otherwise
+	 * would require replicating code paths in:
+	 *
+	 * ext4_da_writepages() ->
+	 *    write_cache_pages() ---> (via passed in callback function)
+	 *        __mpage_da_writepage() -->
+	 *           mpage_add_bh_to_extent()
+	 *           mpage_da_map_blocks()
+	 *
+	 * The problem is that write_cache_pages(), located in
+	 * mm/page-writeback.c, marks pages clean in preparation for
+	 * doing I/O, which is not desirable if we're not planning on
+	 * doing I/O at all.
+	 *
+	 * We could call write_cache_pages(), and then redirty all of
+	 * the pages by calling redirty_page_for_writepage() but that
+	 * would be ugly in the extreme.  So instead we would need to
+	 * replicate parts of the code in the above functions,
+	 * simplifying them because we wouldn't actually intend to
+	 * write out the pages, but rather only collect contiguous
+	 * logical block extents, call the multi-block allocator, and
+	 * then update the buffer heads with the block allocations.
+	 *
+	 * For now, though, we'll cheat by calling filemap_flush(),
+	 * which will map the blocks, and start the I/O, but not
+	 * actually wait for the I/O to complete.
+	 */
+	return filemap_flush(inode->i_mapping);
+}
+
+/*
+ * bmap() is special.  It gets used by applications such as lilo and by
+ * the swapper to find the on-disk block of a specific piece of data.
+ *
+ * Naturally, this is dangerous if the block concerned is still in the
+ * journal.  If somebody makes a swapfile on an ext4 data-journaling
+ * filesystem and enables swap, then they may get a nasty shock when the
+ * data getting swapped to that swapfile suddenly gets overwritten by
+ * the original zero's written out previously to the journal and
+ * awaiting writeback in the kernel's buffer cache.
+ *
+ * So, if we see any bmap calls here on a modified, data-journaled file,
+ * take extra steps to flush any blocks which might be in the cache.
+ */
+static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
+{
+	struct inode *inode = mapping->host;
+	journal_t *journal;
+	int err;
+
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+			test_opt(inode->i_sb, DELALLOC)) {
+		/*
+		 * With delalloc we want to sync the file
+		 * so that we can make sure we allocate
+		 * blocks for file
+		 */
+		filemap_write_and_wait(mapping);
+	}
+
+	if (EXT4_JOURNAL(inode) &&
+	    ext4_test_inode_state(inode, EXT4_STATE_JDATA)) {
+		/*
+		 * This is a REALLY heavyweight approach, but the use of
+		 * bmap on dirty files is expected to be extremely rare:
+		 * only if we run lilo or swapon on a freshly made file
+		 * do we expect this to happen.
+		 *
+		 * (bmap requires CAP_SYS_RAWIO so this does not
+		 * represent an unprivileged user DOS attack --- we'd be
+		 * in trouble if mortal users could trigger this path at
+		 * will.)
+		 *
+		 * NB. EXT4_STATE_JDATA is not set on files other than
+		 * regular files.  If somebody wants to bmap a directory
+		 * or symlink and gets confused because the buffer
+		 * hasn't yet been flushed to disk, they deserve
+		 * everything they get.
+		 */
+
+		ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
+		journal = EXT4_JOURNAL(inode);
+		jbd2_journal_lock_updates(journal);
+		err = jbd2_journal_flush(journal);
+		jbd2_journal_unlock_updates(journal);
+
+		if (err)
+			return 0;
+	}
+
+	return generic_block_bmap(mapping, block, ext4_get_block);
+}
+
+static int ext4_readpage(struct file *file, struct page *page)
+{
+	trace_ext4_readpage(page);
+	return mpage_readpage(page, ext4_get_block);
+}
+
+static int
+ext4_readpages(struct file *file, struct address_space *mapping,
+		struct list_head *pages, unsigned nr_pages)
+{
+	return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
+}
+
+static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offset)
+{
+	struct buffer_head *head, *bh;
+	unsigned int curr_off = 0;
+
+	if (!page_has_buffers(page))
+		return;
+	head = bh = page_buffers(page);
+	do {
+		if (offset <= curr_off && test_clear_buffer_uninit(bh)
+					&& bh->b_private) {
+			ext4_free_io_end(bh->b_private);
+			bh->b_private = NULL;
+			bh->b_end_io = NULL;
+		}
+		curr_off = curr_off + bh->b_size;
+		bh = bh->b_this_page;
+	} while (bh != head);
+}
+
+static void ext4_invalidatepage(struct page *page, unsigned long offset)
+{
+	journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+
+	trace_ext4_invalidatepage(page, offset);
+
+	/*
+	 * free any io_end structure allocated for buffers to be discarded
+	 */
+	if (ext4_should_dioread_nolock(page->mapping->host))
+		ext4_invalidatepage_free_endio(page, offset);
+	/*
+	 * If it's a full truncate we just forget about the pending dirtying
+	 */
+	if (offset == 0)
+		ClearPageChecked(page);
+
+	if (journal)
+		jbd2_journal_invalidatepage(journal, page, offset);
+	else
+		block_invalidatepage(page, offset);
+}
+
+static int ext4_releasepage(struct page *page, gfp_t wait)
+{
+	journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+
+	trace_ext4_releasepage(page);
+
+	WARN_ON(PageChecked(page));
+	if (!page_has_buffers(page))
+		return 0;
+	if (journal)
+		return jbd2_journal_try_to_free_buffers(journal, page, wait);
+	else
+		return try_to_free_buffers(page);
+}
+
+/*
+ * O_DIRECT for ext3 (or indirect map) based files
+ *
+ * If the O_DIRECT write will extend the file then add this inode to the
+ * orphan list.  So recovery will truncate it back to the original size
+ * if the machine crashes during the write.
+ *
+ * If the O_DIRECT write is intantiating holes inside i_size and the machine
+ * crashes then stale disk data _may_ be exposed inside the file. But current
+ * VFS code falls back into buffered path in that case so we are safe.
+ */
+static ssize_t ext4_ind_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 ext4_inode_info *ei = EXT4_I(inode);
+	handle_t *handle;
+	ssize_t ret;
+	int orphan = 0;
+	size_t count = iov_length(iov, nr_segs);
+	int retries = 0;
+
+	if (rw == WRITE) {
+		loff_t final_size = offset + count;
+
+		if (final_size > inode->i_size) {
+			/* Credits for sb + inode write */
+			handle = ext4_journal_start(inode, 2);
+			if (IS_ERR(handle)) {
+				ret = PTR_ERR(handle);
+				goto out;
+			}
+			ret = ext4_orphan_add(handle, inode);
+			if (ret) {
+				ext4_journal_stop(handle);
+				goto out;
+			}
+			orphan = 1;
+			ei->i_disksize = inode->i_size;
+			ext4_journal_stop(handle);
+		}
+	}
+
+retry:
+	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+		if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+			mutex_lock(&inode->i_mutex);
+			ext4_flush_completed_IO(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
+		ret = __blockdev_direct_IO(rw, iocb, inode,
+				 inode->i_sb->s_bdev, iov,
+				 offset, nr_segs,
+				 ext4_get_block, NULL, NULL, 0);
+	} else {
+		ret = blockdev_direct_IO(rw, iocb, inode,
+				 inode->i_sb->s_bdev, iov,
+				 offset, nr_segs,
+				 ext4_get_block, NULL);
+
+		if (unlikely((rw & WRITE) && ret < 0)) {
+			loff_t isize = i_size_read(inode);
+			loff_t end = offset + iov_length(iov, nr_segs);
+
+			if (end > isize)
+				ext4_truncate_failed_write(inode);
+		}
+	}
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+
+	if (orphan) {
+		int err;
+
+		/* Credits for sb + inode write */
+		handle = ext4_journal_start(inode, 2);
+		if (IS_ERR(handle)) {
+			/* This is really bad luck. We've written the data
+			 * but cannot extend i_size. Bail out and pretend
+			 * the write failed... */
+			ret = PTR_ERR(handle);
+			if (inode->i_nlink)
+				ext4_orphan_del(NULL, inode);
+
+			goto out;
+		}
+		if (inode->i_nlink)
+			ext4_orphan_del(handle, inode);
+		if (ret > 0) {
+			loff_t end = offset + ret;
+			if (end > inode->i_size) {
+				ei->i_disksize = end;
+				i_size_write(inode, end);
+				/*
+				 * We're going to return a positive `ret'
+				 * here due to non-zero-length I/O, so there's
+				 * no way of reporting error returns from
+				 * ext4_mark_inode_dirty() to userspace.  So
+				 * ignore it.
+				 */
+				ext4_mark_inode_dirty(handle, inode);
+			}
+		}
+		err = ext4_journal_stop(handle);
+		if (ret == 0)
+			ret = err;
+	}
+out:
+	return ret;
+}
+
+/*
+ * ext4_get_block used when preparing for a DIO write or buffer write.
+ * We allocate an uinitialized extent if blocks haven't been allocated.
+ * The extent will be converted to initialized after the IO is complete.
+ */
+static int ext4_get_block_write(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create)
+{
+	ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	return _ext4_get_block(inode, iblock, bh_result,
+			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
+}
+
+static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
+			    ssize_t size, void *private, int ret,
+			    bool is_async)
+{
+        ext4_io_end_t *io_end = iocb->private;
+	struct workqueue_struct *wq;
+	unsigned long flags;
+	struct ext4_inode_info *ei;
+
+	/* if not async direct IO or dio with 0 bytes write, just return */
+	if (!io_end || !size)
+		goto out;
+
+	ext_debug("ext4_end_io_dio(): io_end 0x%p"
+		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
+ 		  iocb->private, io_end->inode->i_ino, iocb, offset,
+		  size);
+
+	/* if not aio dio with unwritten extents, just free io and return */
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+		iocb->private = NULL;
+out:
+		if (is_async)
+			aio_complete(iocb, ret, 0);
+		return;
+	}
+
+	io_end->offset = offset;
+	io_end->size = size;
+	if (is_async) {
+		io_end->iocb = iocb;
+		io_end->result = ret;
+	}
+	wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
+
+	/* Add the io_end to per-inode completed aio dio list*/
+	ei = EXT4_I(io_end->inode);
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	list_add_tail(&io_end->list, &ei->i_completed_io_list);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+
+	/* queue the work to convert unwritten extents to written */
+	queue_work(wq, &io_end->work);
+	iocb->private = NULL;
+}
+
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
+{
+	ext4_io_end_t *io_end = bh->b_private;
+	struct workqueue_struct *wq;
+	struct inode *inode;
+	unsigned long flags;
+
+	if (!test_clear_buffer_uninit(bh) || !io_end)
+		goto out;
+
+	if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
+		printk("sb umounted, discard end_io request for inode %lu\n",
+			io_end->inode->i_ino);
+		ext4_free_io_end(io_end);
+		goto out;
+	}
+
+	/*
+	 * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+	 * but being more careful is always safe for the future change.
+	 */
+	inode = io_end->inode;
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
+
+	/* Add the io_end to per-inode completed io list*/
+	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+	list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
+	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
+
+	wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
+	/* queue the work to convert unwritten extents to written */
+	queue_work(wq, &io_end->work);
+out:
+	bh->b_private = NULL;
+	bh->b_end_io = NULL;
+	clear_buffer_uninit(bh);
+	end_buffer_async_write(bh, uptodate);
+}
+
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
+{
+	ext4_io_end_t *io_end;
+	struct page *page = bh->b_page;
+	loff_t offset = (sector_t)page->index << PAGE_CACHE_SHIFT;
+	size_t size = bh->b_size;
+
+retry:
+	io_end = ext4_init_io_end(inode, GFP_ATOMIC);
+	if (!io_end) {
+		pr_warn_ratelimited("%s: allocation fail\n", __func__);
+		schedule();
+		goto retry;
+	}
+	io_end->offset = offset;
+	io_end->size = size;
+	/*
+	 * We need to hold a reference to the page to make sure it
+	 * doesn't get evicted before ext4_end_io_work() has a chance
+	 * to convert the extent from written to unwritten.
+	 */
+	io_end->page = page;
+	get_page(io_end->page);
+
+	bh->b_private = io_end;
+	bh->b_end_io = ext4_end_io_buffer_write;
+	return 0;
+}
+
+/*
+ * For ext4 extent files, ext4 will do direct-io write to holes,
+ * preallocated extents, and those write extend the file, no need to
+ * fall back to buffered IO.
+ *
+ * For holes, we fallocate those blocks, mark them as uninitialized
+ * If those blocks were preallocated, we mark sure they are splited, but
+ * still keep the range to write as uninitialized.
+ *
+ * The unwrritten extents will be converted to written when DIO is completed.
+ * For async direct IO, since the IO may still pending when return, we
+ * set up an end_io call back function, which will do the conversion
+ * when async direct IO completed.
+ *
+ * If the O_DIRECT write will extend the file then add this inode to the
+ * orphan list.  So recovery will truncate it back to the original size
+ * if the machine crashes during the write.
+ *
+ */
+static ssize_t ext4_ext_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;
+	ssize_t ret;
+	size_t count = iov_length(iov, nr_segs);
+
+	loff_t final_size = offset + count;
+	if (rw == WRITE && final_size <= inode->i_size) {
+		/*
+ 		 * We could direct write to holes and fallocate.
+		 *
+ 		 * Allocated blocks to fill the hole are marked as uninitialized
+ 		 * to prevent parallel buffered read to expose the stale data
+ 		 * before DIO complete the data IO.
+		 *
+ 		 * As to previously fallocated extents, ext4 get_block
+ 		 * will just simply mark the buffer mapped but still
+ 		 * keep the extents uninitialized.
+ 		 *
+		 * for non AIO case, we will convert those unwritten extents
+		 * to written after return back from blockdev_direct_IO.
+		 *
+		 * for async DIO, the conversion needs to be defered when
+		 * the IO is completed. The ext4 end_io callback function
+		 * will be called to take care of the conversion work.
+		 * Here for async case, we allocate an io_end structure to
+		 * hook to the iocb.
+ 		 */
+		iocb->private = NULL;
+		EXT4_I(inode)->cur_aio_dio = NULL;
+		if (!is_sync_kiocb(iocb)) {
+			iocb->private = ext4_init_io_end(inode, GFP_NOFS);
+			if (!iocb->private)
+				return -ENOMEM;
+			/*
+			 * we save the io structure for current async
+			 * direct IO, so that later ext4_map_blocks()
+			 * could flag the io structure whether there
+			 * is a unwritten extents needs to be converted
+			 * when IO is completed.
+			 */
+			EXT4_I(inode)->cur_aio_dio = iocb->private;
+		}
+
+		ret = blockdev_direct_IO(rw, iocb, inode,
+					 inode->i_sb->s_bdev, iov,
+					 offset, nr_segs,
+					 ext4_get_block_write,
+					 ext4_end_io_dio);
+		if (iocb->private)
+			EXT4_I(inode)->cur_aio_dio = NULL;
+		/*
+		 * The io_end structure takes a reference to the inode,
+		 * that structure needs to be destroyed and the
+		 * reference to the inode need to be dropped, when IO is
+		 * complete, even with 0 byte write, or failed.
+		 *
+		 * In the successful AIO DIO case, the io_end structure will be
+		 * desctroyed and the reference to the inode will be dropped
+		 * after the end_io call back function is called.
+		 *
+		 * In the case there is 0 byte write, or error case, since
+		 * VFS direct IO won't invoke the end_io call back function,
+		 * we need to free the end_io structure here.
+		 */
+		if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
+			ext4_free_io_end(iocb->private);
+			iocb->private = NULL;
+		} else if (ret > 0 && ext4_test_inode_state(inode,
+						EXT4_STATE_DIO_UNWRITTEN)) {
+			int err;
+			/*
+			 * for non AIO case, since the IO is already
+			 * completed, we could do the conversion right here
+			 */
+			err = ext4_convert_unwritten_extents(inode,
+							     offset, ret);
+			if (err < 0)
+				ret = err;
+			ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+		}
+		return ret;
+	}
+
+	/* for write the the end of file case, we fall back to old way */
+	return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+}
+
+static ssize_t ext4_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;
+	ssize_t ret;
+
+	trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+	else
+		ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+	trace_ext4_direct_IO_exit(inode, offset,
+				iov_length(iov, nr_segs), rw, ret);
+	return ret;
+}
+
+/*
+ * Pages can be marked dirty completely asynchronously from ext4's journalling
+ * activity.  By filemap_sync_pte(), try_to_unmap_one(), etc.  We cannot do
+ * much here because ->set_page_dirty is called under VFS locks.  The page is
+ * not necessarily locked.
+ *
+ * We cannot just dirty the page and leave attached buffers clean, because the
+ * buffers' dirty state is "definitive".  We cannot just set the buffers dirty
+ * or jbddirty because all the journalling code will explode.
+ *
+ * So what we do is to mark the page "pending dirty" and next time writepage
+ * is called, propagate that into the buffers appropriately.
+ */
+static int ext4_journalled_set_page_dirty(struct page *page)
+{
+	SetPageChecked(page);
+	return __set_page_dirty_nobuffers(page);
+}
+
+static const struct address_space_operations ext4_ordered_aops = {
+	.readpage		= ext4_readpage,
+	.readpages		= ext4_readpages,
+	.writepage		= ext4_writepage,
+	.write_begin		= ext4_write_begin,
+	.write_end		= ext4_ordered_write_end,
+	.bmap			= ext4_bmap,
+	.invalidatepage		= ext4_invalidatepage,
+	.releasepage		= ext4_releasepage,
+	.direct_IO		= ext4_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 ext4_writeback_aops = {
+	.readpage		= ext4_readpage,
+	.readpages		= ext4_readpages,
+	.writepage		= ext4_writepage,
+	.write_begin		= ext4_write_begin,
+	.write_end		= ext4_writeback_write_end,
+	.bmap			= ext4_bmap,
+	.invalidatepage		= ext4_invalidatepage,
+	.releasepage		= ext4_releasepage,
+	.direct_IO		= ext4_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 ext4_journalled_aops = {
+	.readpage		= ext4_readpage,
+	.readpages		= ext4_readpages,
+	.writepage		= ext4_writepage,
+	.write_begin		= ext4_write_begin,
+	.write_end		= ext4_journalled_write_end,
+	.set_page_dirty		= ext4_journalled_set_page_dirty,
+	.bmap			= ext4_bmap,
+	.invalidatepage		= ext4_invalidatepage,
+	.releasepage		= ext4_releasepage,
+	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
+};
+
+static const struct address_space_operations ext4_da_aops = {
+	.readpage		= ext4_readpage,
+	.readpages		= ext4_readpages,
+	.writepage		= ext4_writepage,
+	.writepages		= ext4_da_writepages,
+	.write_begin		= ext4_da_write_begin,
+	.write_end		= ext4_da_write_end,
+	.bmap			= ext4_bmap,
+	.invalidatepage		= ext4_da_invalidatepage,
+	.releasepage		= ext4_releasepage,
+	.direct_IO		= ext4_direct_IO,
+	.migratepage		= buffer_migrate_page,
+	.is_partially_uptodate  = block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
+};
+
+void ext4_set_aops(struct inode *inode)
+{
+	switch (ext4_inode_journal_mode(inode)) {
+	case EXT4_INODE_ORDERED_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_ordered_aops;
+		break;
+	case EXT4_INODE_WRITEBACK_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_writeback_aops;
+		break;
+	case EXT4_INODE_JOURNAL_DATA_MODE:
+		inode->i_mapping->a_ops = &ext4_journalled_aops;
+		break;
+	default:
+		BUG();
+	}
+}
+
+/*
+ * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This required during truncate. We need to physically zero the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ */
+int ext4_block_truncate_page(handle_t *handle,
+		struct address_space *mapping, loff_t from)
+{
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned length;
+	unsigned blocksize;
+	struct inode *inode = mapping->host;
+
+	blocksize = inode->i_sb->s_blocksize;
+	length = blocksize - (offset & (blocksize - 1));
+
+	return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
+/*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
+{
+	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize, max, pos;
+	ext4_lblk_t iblock;
+	struct inode *inode = mapping->host;
+	struct buffer_head *bh;
+	struct page *page;
+	int err = 0;
+
+	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+				   mapping_gfp_mask(mapping) & ~__GFP_FS);
+	if (!page)
+		return -EINVAL;
+
+	blocksize = inode->i_sb->s_blocksize;
+	max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
+	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_freed(bh)) {
+		BUFFER_TRACE(bh, "freed: skip");
+		goto unlock;
+	}
+
+	if (!buffer_mapped(bh)) {
+		BUFFER_TRACE(bh, "unmapped");
+		ext4_get_block(inode, iblock, bh, 0);
+		/* unmapped? It's a hole - nothing to do */
+		if (!buffer_mapped(bh)) {
+			BUFFER_TRACE(bh, "still unmapped");
+			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;
+	}
+
+	if (ext4_should_journal_data(inode)) {
+		BUFFER_TRACE(bh, "get write access");
+		err = ext4_journal_get_write_access(handle, bh);
+		if (err)
+			goto unlock;
+	}
+
+	zero_user(page, offset, length);
+
+	BUFFER_TRACE(bh, "zeroed end of block");
+
+	err = 0;
+	if (ext4_should_journal_data(inode)) {
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
+	} else {
+		if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
+			err = ext4_jbd2_file_inode(handle, inode);
+		mark_buffer_dirty(bh);
+	}
+
+unlock:
+	unlock_page(page);
+	page_cache_release(page);
+	return err;
+}
+
+/*
+ * Probably it should be a library function... search for first non-zero word
+ * or memcmp with zero_page, whatever is better for particular architecture.
+ * Linus?
+ */
+static inline int all_zeroes(__le32 *p, __le32 *q)
+{
+	while (p < q)
+		if (*p++)
+			return 0;
+	return 1;
+}
+
+/**
+ *	ext4_find_shared - find the indirect blocks for partial truncation.
+ *	@inode:	  inode in question
+ *	@depth:	  depth of the affected branch
+ *	@offsets: offsets of pointers in that branch (see ext4_block_to_path)
+ *	@chain:	  place to store the pointers to partial indirect blocks
+ *	@top:	  place to the (detached) top of branch
+ *
+ *	This is a helper function used by ext4_truncate().
+ *
+ *	When we do truncate() we may have to clean the ends of several
+ *	indirect blocks but leave the blocks themselves alive. Block is
+ *	partially truncated if some data below the new i_size is referred
+ *	from it (and it is on the path to the first completely truncated
+ *	data block, indeed).  We have to free the top of that path along
+ *	with everything to the right of the path. Since no allocation
+ *	past the truncation point is possible until ext4_truncate()
+ *	finishes, we may safely do the latter, but top of branch may
+ *	require special attention - pageout below the truncation point
+ *	might try to populate it.
+ *
+ *	We atomically detach the top of branch from the tree, store the
+ *	block number of its root in *@top, pointers to buffer_heads of
+ *	partially truncated blocks - in @chain[].bh and pointers to
+ *	their last elements that should not be removed - in
+ *	@chain[].p. Return value is the pointer to last filled element
+ *	of @chain.
+ *
+ *	The work left to caller to do the actual freeing of subtrees:
+ *		a) free the subtree starting from *@top
+ *		b) free the subtrees whose roots are stored in
+ *			(@chain[i].p+1 .. end of @chain[i].bh->b_data)
+ *		c) free the subtrees growing from the inode past the @chain[0].
+ *			(no partially truncated stuff there).  */
+
+static Indirect *ext4_find_shared(struct inode *inode, int depth,
+				  ext4_lblk_t offsets[4], Indirect chain[4],
+				  __le32 *top)
+{
+	Indirect *partial, *p;
+	int k, err;
+
+	*top = 0;
+	/* Make k index the deepest non-null offset + 1 */
+	for (k = depth; k > 1 && !offsets[k-1]; k--)
+		;
+	partial = ext4_get_branch(inode, k, offsets, chain, &err);
+	/* Writer: pointers */
+	if (!partial)
+		partial = chain + k-1;
+	/*
+	 * If the branch acquired continuation since we've looked at it -
+	 * fine, it should all survive and (new) top doesn't belong to us.
+	 */
+	if (!partial->key && *partial->p)
+		/* Writer: end */
+		goto no_top;
+	for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
+		;
+	/*
+	 * OK, we've found the last block that must survive. The rest of our
+	 * branch should be detached before unlocking. However, if that rest
+	 * of branch is all ours and does not grow immediately from the inode
+	 * it's easier to cheat and just decrement partial->p.
+	 */
+	if (p == chain + k - 1 && p > chain) {
+		p->p--;
+	} else {
+		*top = *p->p;
+		/* Nope, don't do this in ext4.  Must leave the tree intact */
+#if 0
+		*p->p = 0;
+#endif
+	}
+	/* Writer: end */
+
+	while (partial > p) {
+		brelse(partial->bh);
+		partial--;
+	}
+no_top:
+	return partial;
+}
+
+/*
+ * Zero a number of block pointers in either an inode or an indirect block.
+ * If we restart the transaction we must again get write access to the
+ * indirect block for further modification.
+ *
+ * We release `count' blocks on disk, but (last - first) may be greater
+ * than `count' because there can be holes in there.
+ *
+ * Return 0 on success, 1 on invalid block range
+ * and < 0 on fatal error.
+ */
+static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
+			     struct buffer_head *bh,
+			     ext4_fsblk_t block_to_free,
+			     unsigned long count, __le32 *first,
+			     __le32 *last)
+{
+	__le32 *p;
+	int	flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
+	int	err;
+
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		flags |= EXT4_FREE_BLOCKS_METADATA;
+
+	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
+				   count)) {
+		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
+				 "blocks %llu len %lu",
+				 (unsigned long long) block_to_free, count);
+		return 1;
+	}
+
+	if (try_to_extend_transaction(handle, inode)) {
+		if (bh) {
+			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+			err = ext4_handle_dirty_metadata(handle, inode, bh);
+			if (unlikely(err))
+				goto out_err;
+		}
+		err = ext4_mark_inode_dirty(handle, inode);
+		if (unlikely(err))
+			goto out_err;
+		err = ext4_truncate_restart_trans(handle, inode,
+						  blocks_for_truncate(inode));
+		if (unlikely(err))
+			goto out_err;
+		if (bh) {
+			BUFFER_TRACE(bh, "retaking write access");
+			err = ext4_journal_get_write_access(handle, bh);
+			if (unlikely(err))
+				goto out_err;
+		}
+	}
+
+	for (p = first; p < last; p++)
+		*p = 0;
+
+	ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags);
+	return 0;
+out_err:
+	ext4_std_error(inode->i_sb, err);
+	return err;
+}
+
+/**
+ * ext4_free_data - free a list of data blocks
+ * @handle:	handle for this transaction
+ * @inode:	inode we are dealing with
+ * @this_bh:	indirect buffer_head which contains *@first and *@last
+ * @first:	array of block numbers
+ * @last:	points immediately past the end of array
+ *
+ * We are freeing all blocks referred from that array (numbers are stored as
+ * little-endian 32-bit) and updating @inode->i_blocks appropriately.
+ *
+ * We accumulate contiguous runs of blocks to free.  Conveniently, if these
+ * blocks are contiguous then releasing them at one time will only affect one
+ * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
+ * actually use a lot of journal space.
+ *
+ * @this_bh will be %NULL if @first and @last point into the inode's direct
+ * block pointers.
+ */
+static void ext4_free_data(handle_t *handle, struct inode *inode,
+			   struct buffer_head *this_bh,
+			   __le32 *first, __le32 *last)
+{
+	ext4_fsblk_t block_to_free = 0;    /* Starting block # of a run */
+	unsigned long count = 0;	    /* Number of blocks in the run */
+	__le32 *block_to_free_p = NULL;	    /* Pointer into inode/ind
+					       corresponding to
+					       block_to_free */
+	ext4_fsblk_t nr;		    /* Current block # */
+	__le32 *p;			    /* Pointer into inode/ind
+					       for current block */
+	int err = 0;
+
+	if (this_bh) {				/* For indirect block */
+		BUFFER_TRACE(this_bh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, this_bh);
+		/* Important: if we can't update the indirect pointers
+		 * to the blocks, we can't free them. */
+		if (err)
+			return;
+	}
+
+	for (p = first; p < last; p++) {
+		nr = le32_to_cpu(*p);
+		if (nr) {
+			/* accumulate blocks to free if they're contiguous */
+			if (count == 0) {
+				block_to_free = nr;
+				block_to_free_p = p;
+				count = 1;
+			} else if (nr == block_to_free + count) {
+				count++;
+			} else {
+				err = ext4_clear_blocks(handle, inode, this_bh,
+						        block_to_free, count,
+						        block_to_free_p, p);
+				if (err)
+					break;
+				block_to_free = nr;
+				block_to_free_p = p;
+				count = 1;
+			}
+		}
+	}
+
+	if (!err && count > 0)
+		err = ext4_clear_blocks(handle, inode, this_bh, block_to_free,
+					count, block_to_free_p, p);
+	if (err < 0)
+		/* fatal error */
+		return;
+
+	if (this_bh) {
+		BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
+
+		/*
+		 * The buffer head should have an attached journal head at this
+		 * point. However, if the data is corrupted and an indirect
+		 * block pointed to itself, it would have been detached when
+		 * the block was cleared. Check for this instead of OOPSing.
+		 */
+		if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
+			ext4_handle_dirty_metadata(handle, inode, this_bh);
+		else
+			EXT4_ERROR_INODE(inode,
+					 "circular indirect block detected at "
+					 "block %llu",
+				(unsigned long long) this_bh->b_blocknr);
+	}
+}
+
+/**
+ *	ext4_free_branches - free an array of branches
+ *	@handle: JBD handle for this transaction
+ *	@inode:	inode we are dealing with
+ *	@parent_bh: the buffer_head which contains *@first and *@last
+ *	@first:	array of block numbers
+ *	@last:	pointer immediately past the end of array
+ *	@depth:	depth of the branches to free
+ *
+ *	We are freeing all blocks referred from these branches (numbers are
+ *	stored as little-endian 32-bit) and updating @inode->i_blocks
+ *	appropriately.
+ */
+static void ext4_free_branches(handle_t *handle, struct inode *inode,
+			       struct buffer_head *parent_bh,
+			       __le32 *first, __le32 *last, int depth)
+{
+	ext4_fsblk_t nr;
+	__le32 *p;
+
+	if (ext4_handle_is_aborted(handle))
+		return;
+
+	if (depth--) {
+		struct buffer_head *bh;
+		int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+		p = last;
+		while (--p >= first) {
+			nr = le32_to_cpu(*p);
+			if (!nr)
+				continue;		/* A hole */
+
+			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+						   nr, 1)) {
+				EXT4_ERROR_INODE(inode,
+						 "invalid indirect mapped "
+						 "block %lu (level %d)",
+						 (unsigned long) nr, depth);
+				break;
+			}
+
+			/* Go read the buffer for the next level down */
+			bh = sb_bread(inode->i_sb, nr);
+
+			/*
+			 * A read failure? Report error and clear slot
+			 * (should be rare).
+			 */
+			if (!bh) {
+				EXT4_ERROR_INODE_BLOCK(inode, nr,
+						       "Read failure");
+				continue;
+			}
+
+			/* This zaps the entire block.  Bottom up. */
+			BUFFER_TRACE(bh, "free child branches");
+			ext4_free_branches(handle, inode, bh,
+					(__le32 *) bh->b_data,
+					(__le32 *) bh->b_data + addr_per_block,
+					depth);
+			brelse(bh);
+
+			/*
+			 * Everything below this this pointer has been
+			 * released.  Now let this top-of-subtree go.
+			 *
+			 * We want the freeing of this indirect block to be
+			 * atomic in the journal with the updating of the
+			 * bitmap block which owns it.  So make some room in
+			 * the journal.
+			 *
+			 * We zero the parent pointer *after* freeing its
+			 * pointee in the bitmaps, so if extend_transaction()
+			 * for some reason fails to put the bitmap changes and
+			 * the release into the same transaction, recovery
+			 * will merely complain about releasing a free block,
+			 * rather than leaking blocks.
+			 */
+			if (ext4_handle_is_aborted(handle))
+				return;
+			if (try_to_extend_transaction(handle, inode)) {
+				ext4_mark_inode_dirty(handle, inode);
+				ext4_truncate_restart_trans(handle, inode,
+					    blocks_for_truncate(inode));
+			}
+
+			/*
+			 * The forget flag here is critical because if
+			 * we are journaling (and not doing data
+			 * journaling), we have to make sure a revoke
+			 * record is written to prevent the journal
+			 * replay from overwriting the (former)
+			 * indirect block if it gets reallocated as a
+			 * data block.  This must happen in the same
+			 * transaction where the data blocks are
+			 * actually freed.
+			 */
+			ext4_free_blocks(handle, inode, NULL, nr, 1,
+					 EXT4_FREE_BLOCKS_METADATA|
+					 EXT4_FREE_BLOCKS_FORGET);
+
+			if (parent_bh) {
+				/*
+				 * The block which we have just freed is
+				 * pointed to by an indirect block: journal it
+				 */
+				BUFFER_TRACE(parent_bh, "get_write_access");
+				if (!ext4_journal_get_write_access(handle,
+								   parent_bh)){
+					*p = 0;
+					BUFFER_TRACE(parent_bh,
+					"call ext4_handle_dirty_metadata");
+					ext4_handle_dirty_metadata(handle,
+								   inode,
+								   parent_bh);
+				}
+			}
+		}
+	} else {
+		/* We have reached the bottom of the tree. */
+		BUFFER_TRACE(parent_bh, "free data blocks");
+		ext4_free_data(handle, inode, parent_bh, first, last);
+	}
+}
+
+int ext4_can_truncate(struct inode *inode)
+{
+	if (S_ISREG(inode->i_mode))
+		return 1;
+	if (S_ISDIR(inode->i_mode))
+		return 1;
+	if (S_ISLNK(inode->i_mode))
+		return !ext4_inode_is_fast_symlink(inode);
+	return 0;
+}
+
+/*
+ * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * associated with the given offset and length
+ *
+ * @inode:  File inode
+ * @offset: The offset where the hole will begin
+ * @len:    The length of the hole
+ *
+ * Returns: 0 on sucess or negative on failure
+ */
+
+int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	if (!S_ISREG(inode->i_mode))
+		return -ENOTSUPP;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		/* TODO: Add support for non extent hole punching */
+		return -ENOTSUPP;
+	}
+
+	return ext4_ext_punch_hole(file, offset, length);
+}
+
+/*
+ * ext4_truncate()
+ *
+ * We block out ext4_get_block() block instantiations across the entire
+ * transaction, and VFS/VM ensures that ext4_truncate() cannot run
+ * simultaneously on behalf of the same inode.
+ *
+ * As we work through the truncate and commmit bits of it to the journal there
+ * is one core, guiding principle: the file's tree must always be consistent on
+ * disk.  We must be able to restart the truncate after a crash.
+ *
+ * The file's tree may be transiently inconsistent in memory (although it
+ * probably isn't), but whenever we close off and commit a journal transaction,
+ * the contents of (the filesystem + the journal) must be consistent and
+ * restartable.  It's pretty simple, really: bottom up, right to left (although
+ * left-to-right works OK too).
+ *
+ * Note that at recovery time, journal replay occurs *before* the restart of
+ * truncate against the orphan inode list.
+ *
+ * The committed inode has the new, desired i_size (which is the same as
+ * i_disksize in this case).  After a crash, ext4_orphan_cleanup() will see
+ * that this inode's truncate did not complete and it will again call
+ * ext4_truncate() to have another go.  So there will be instantiated blocks
+ * to the right of the truncation point in a crashed ext4 filesystem.  But
+ * that's fine - as long as they are linked from the inode, the post-crash
+ * ext4_truncate() run will find them and release them.
+ */
+void ext4_truncate(struct inode *inode)
+{
+	handle_t *handle;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	__le32 *i_data = ei->i_data;
+	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+	struct address_space *mapping = inode->i_mapping;
+	ext4_lblk_t offsets[4];
+	Indirect chain[4];
+	Indirect *partial;
+	__le32 nr = 0;
+	int n = 0;
+	ext4_lblk_t last_block, max_block;
+	unsigned blocksize = inode->i_sb->s_blocksize;
+
+	trace_ext4_truncate_enter(inode);
+
+	if (!ext4_can_truncate(inode))
+		return;
+
+	ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+
+	if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+		ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		ext4_ext_truncate(inode);
+		trace_ext4_truncate_exit(inode);
+		return;
+	}
+
+	handle = start_transaction(inode);
+	if (IS_ERR(handle))
+		return;		/* AKPM: return what? */
+
+	last_block = (inode->i_size + blocksize-1)
+					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+	max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+
+	if (inode->i_size & (blocksize - 1))
+		if (ext4_block_truncate_page(handle, mapping, inode->i_size))
+			goto out_stop;
+
+	if (last_block != max_block) {
+		n = ext4_block_to_path(inode, last_block, offsets, NULL);
+		if (n == 0)
+			goto out_stop;	/* error */
+	}
+
+	/*
+	 * OK.  This truncate is going to happen.  We add the inode to the
+	 * orphan list, so that if this truncate spans multiple transactions,
+	 * and we crash, we will resume the truncate when the filesystem
+	 * recovers.  It also marks the inode dirty, to catch the new size.
+	 *
+	 * Implication: the file must always be in a sane, consistent
+	 * truncatable state while each transaction commits.
+	 */
+	if (ext4_orphan_add(handle, inode))
+		goto out_stop;
+
+	/*
+	 * From here we block out all ext4_get_block() callers who want to
+	 * modify the block allocation tree.
+	 */
+	down_write(&ei->i_data_sem);
+
+	ext4_discard_preallocations(inode);
+
+	/*
+	 * The orphan list entry will now protect us from any crash which
+	 * occurs before the truncate completes, so it is now safe to propagate
+	 * the new, shorter inode size (held for now in i_size) into the
+	 * on-disk inode. We do this via i_disksize, which is the value which
+	 * ext4 *really* writes onto the disk inode.
+	 */
+	ei->i_disksize = inode->i_size;
+
+	if (last_block == max_block) {
+		/*
+		 * It is unnecessary to free any data blocks if last_block is
+		 * equal to the indirect block limit.
+		 */
+		goto out_unlock;
+	} else if (n == 1) {		/* direct blocks */
+		ext4_free_data(handle, inode, NULL, i_data+offsets[0],
+			       i_data + EXT4_NDIR_BLOCKS);
+		goto do_indirects;
+	}
+
+	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+	/* Kill the top of shared branch (not detached) */
+	if (nr) {
+		if (partial == chain) {
+			/* Shared branch grows from the inode */
+			ext4_free_branches(handle, inode, NULL,
+					   &nr, &nr+1, (chain+n-1) - partial);
+			*partial->p = 0;
+			/*
+			 * We mark the inode dirty prior to restart,
+			 * and prior to stop.  No need for it here.
+			 */
+		} else {
+			/* Shared branch grows from an indirect block */
+			BUFFER_TRACE(partial->bh, "get_write_access");
+			ext4_free_branches(handle, inode, partial->bh,
+					partial->p,
+					partial->p+1, (chain+n-1) - partial);
+		}
+	}
+	/* Clear the ends of indirect blocks on the shared branch */
+	while (partial > chain) {
+		ext4_free_branches(handle, inode, partial->bh, partial->p + 1,
+				   (__le32*)partial->bh->b_data+addr_per_block,
+				   (chain+n-1) - partial);
+		BUFFER_TRACE(partial->bh, "call brelse");
+		brelse(partial->bh);
+		partial--;
+	}
+do_indirects:
+	/* Kill the remaining (whole) subtrees */
+	switch (offsets[0]) {
+	default:
+		nr = i_data[EXT4_IND_BLOCK];
+		if (nr) {
+			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+			i_data[EXT4_IND_BLOCK] = 0;
+		}
+	case EXT4_IND_BLOCK:
+		nr = i_data[EXT4_DIND_BLOCK];
+		if (nr) {
+			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+			i_data[EXT4_DIND_BLOCK] = 0;
+		}
+	case EXT4_DIND_BLOCK:
+		nr = i_data[EXT4_TIND_BLOCK];
+		if (nr) {
+			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+			i_data[EXT4_TIND_BLOCK] = 0;
+		}
+	case EXT4_TIND_BLOCK:
+		;
+	}
+
+out_unlock:
+	up_write(&ei->i_data_sem);
+	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+
+	/*
+	 * In a multi-transaction truncate, we only make the final transaction
+	 * synchronous
+	 */
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+out_stop:
+	/*
+	 * If this was a simple ftruncate(), and the file will remain alive
+	 * then we need to clear up the orphan record which we created above.
+	 * However, if this was a real unlink then we were called by
+	 * ext4_delete_inode(), and we allow that function to clean up the
+	 * orphan info for us.
+	 */
+	if (inode->i_nlink)
+		ext4_orphan_del(handle, inode);
+
+	ext4_journal_stop(handle);
+	trace_ext4_truncate_exit(inode);
+}
+
+/*
+ * ext4_get_inode_loc returns with an extra refcount against the inode's
+ * underlying buffer_head on success. If 'in_mem' is true, we have all
+ * data in memory that is needed to recreate the on-disk version of this
+ * inode.
+ */
+static int __ext4_get_inode_loc(struct inode *inode,
+				struct ext4_iloc *iloc, int in_mem)
+{
+	struct ext4_group_desc	*gdp;
+	struct buffer_head	*bh;
+	struct super_block	*sb = inode->i_sb;
+	ext4_fsblk_t		block;
+	int			inodes_per_block, inode_offset;
+
+	iloc->bh = NULL;
+	if (!ext4_valid_inum(sb, inode->i_ino))
+		return -EIO;
+
+	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
+	if (!gdp)
+		return -EIO;
+
+	/*
+	 * Figure out the offset within the block group inode table
+	 */
+	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+	inode_offset = ((inode->i_ino - 1) %
+			EXT4_INODES_PER_GROUP(sb));
+	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
+	iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
+
+	bh = sb_getblk(sb, block);
+	if (!bh) {
+		EXT4_ERROR_INODE_BLOCK(inode, block,
+				       "unable to read itable block");
+		return -EIO;
+	}
+	if (!buffer_uptodate(bh)) {
+		lock_buffer(bh);
+
+		/*
+		 * If the buffer has the write error flag, we have failed
+		 * to write out another inode in the same block.  In this
+		 * case, we don't have to read the block because we may
+		 * read the old inode data successfully.
+		 */
+		if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+			set_buffer_uptodate(bh);
+
+		if (buffer_uptodate(bh)) {
+			/* someone brought it uptodate while we waited */
+			unlock_buffer(bh);
+			goto has_buffer;
+		}
+
+		/*
+		 * If we have all information of the inode in memory and this
+		 * is the only valid inode in the block, we need not read the
+		 * block.
+		 */
+		if (in_mem) {
+			struct buffer_head *bitmap_bh;
+			int i, start;
+
+			start = inode_offset & ~(inodes_per_block - 1);
+
+			/* Is the inode bitmap in cache? */
+			bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
+			if (!bitmap_bh)
+				goto make_io;
+
+			/*
+			 * If the inode bitmap isn't in cache then the
+			 * optimisation may end up performing two reads instead
+			 * of one, so skip it.
+			 */
+			if (!buffer_uptodate(bitmap_bh)) {
+				brelse(bitmap_bh);
+				goto make_io;
+			}
+			for (i = start; i < start + inodes_per_block; i++) {
+				if (i == inode_offset)
+					continue;
+				if (ext4_test_bit(i, bitmap_bh->b_data))
+					break;
+			}
+			brelse(bitmap_bh);
+			if (i == start + inodes_per_block) {
+				/* all other inodes are free, so skip I/O */
+				memset(bh->b_data, 0, bh->b_size);
+				set_buffer_uptodate(bh);
+				unlock_buffer(bh);
+				goto has_buffer;
+			}
+		}
+
+make_io:
+		/*
+		 * If we need to do any I/O, try to pre-readahead extra
+		 * blocks from the inode table.
+		 */
+		if (EXT4_SB(sb)->s_inode_readahead_blks) {
+			ext4_fsblk_t b, end, table;
+			unsigned num;
+
+			table = ext4_inode_table(sb, gdp);
+			/* s_inode_readahead_blks is always a power of 2 */
+			b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1);
+			if (table > b)
+				b = table;
+			end = b + EXT4_SB(sb)->s_inode_readahead_blks;
+			num = EXT4_INODES_PER_GROUP(sb);
+			if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+				num -= ext4_itable_unused_count(sb, gdp);
+			table += num / inodes_per_block;
+			if (end > table)
+				end = table;
+			while (b <= end)
+				sb_breadahead(sb, b++);
+		}
+
+		/*
+		 * There are other valid inodes in the buffer, this inode
+		 * has in-inode xattrs, or we don't have this inode in memory.
+		 * Read the block from disk.
+		 */
+		trace_ext4_load_inode(inode);
+		get_bh(bh);
+		bh->b_end_io = end_buffer_read_sync;
+		submit_bh(READ_META, bh);
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh)) {
+			EXT4_ERROR_INODE_BLOCK(inode, block,
+					       "unable to read itable block");
+			brelse(bh);
+			return -EIO;
+		}
+	}
+has_buffer:
+	iloc->bh = bh;
+	return 0;
+}
+
+int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
+{
+	/* We have all inode data except xattrs in memory here. */
+	return __ext4_get_inode_loc(inode, iloc,
+		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
+}
+
+void ext4_set_inode_flags(struct inode *inode)
+{
+	unsigned int flags = EXT4_I(inode)->i_flags;
+
+	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	if (flags & EXT4_SYNC_FL)
+		inode->i_flags |= S_SYNC;
+	if (flags & EXT4_APPEND_FL)
+		inode->i_flags |= S_APPEND;
+	if (flags & EXT4_IMMUTABLE_FL)
+		inode->i_flags |= S_IMMUTABLE;
+	if (flags & EXT4_NOATIME_FL)
+		inode->i_flags |= S_NOATIME;
+	if (flags & EXT4_DIRSYNC_FL)
+		inode->i_flags |= S_DIRSYNC;
+}
+
+/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
+void ext4_get_inode_flags(struct ext4_inode_info *ei)
+{
+	unsigned int vfs_fl;
+	unsigned long old_fl, new_fl;
+
+	do {
+		vfs_fl = ei->vfs_inode.i_flags;
+		old_fl = ei->i_flags;
+		new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
+				EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|
+				EXT4_DIRSYNC_FL);
+		if (vfs_fl & S_SYNC)
+			new_fl |= EXT4_SYNC_FL;
+		if (vfs_fl & S_APPEND)
+			new_fl |= EXT4_APPEND_FL;
+		if (vfs_fl & S_IMMUTABLE)
+			new_fl |= EXT4_IMMUTABLE_FL;
+		if (vfs_fl & S_NOATIME)
+			new_fl |= EXT4_NOATIME_FL;
+		if (vfs_fl & S_DIRSYNC)
+			new_fl |= EXT4_DIRSYNC_FL;
+	} while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl);
+}
+
+static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
+				  struct ext4_inode_info *ei)
+{
+	blkcnt_t i_blocks ;
+	struct inode *inode = &(ei->vfs_inode);
+	struct super_block *sb = inode->i_sb;
+
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+		/* we are using combined 48 bit field */
+		i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
+					le32_to_cpu(raw_inode->i_blocks_lo);
+		if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) {
+			/* i_blocks represent file system block size */
+			return i_blocks  << (inode->i_blkbits - 9);
+		} else {
+			return i_blocks;
+		}
+	} else {
+		return le32_to_cpu(raw_inode->i_blocks_lo);
+	}
+}
+
+struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
+{
+	struct ext4_iloc iloc;
+	struct ext4_inode *raw_inode;
+	struct ext4_inode_info *ei;
+	struct inode *inode;
+	journal_t *journal = EXT4_SB(sb)->s_journal;
+	long ret;
+	int block;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	ei = EXT4_I(inode);
+	iloc.bh = NULL;
+
+	ret = __ext4_get_inode_loc(inode, &iloc, 0);
+	if (ret < 0)
+		goto bad_inode;
+	raw_inode = ext4_raw_inode(&iloc);
+	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
+	inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
+	inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
+	if (!(test_opt(inode->i_sb, NO_UID32))) {
+		inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
+		inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
+	}
+	inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+
+	ext4_clear_state_flags(ei);	/* Only relevant on 32-bit archs */
+	ei->i_dir_start_lookup = 0;
+	ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
+	/* We now have enough fields to check if the inode was active or not.
+	 * This is needed because nfsd might try to access dead inodes
+	 * the test is that same one that e2fsck uses
+	 * NeilBrown 1999oct15
+	 */
+	if (inode->i_nlink == 0) {
+		if (inode->i_mode == 0 ||
+		    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
+			/* this inode is deleted */
+			ret = -ESTALE;
+			goto bad_inode;
+		}
+		/* The only unlinked inodes we let through here have
+		 * valid i_mode and are being read by the orphan
+		 * recovery code: that's fine, we're about to complete
+		 * the process of deleting those. */
+	}
+	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
+	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
+	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT))
+		ei->i_file_acl |=
+			((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
+	inode->i_size = ext4_isize(raw_inode);
+	ei->i_disksize = inode->i_size;
+#ifdef CONFIG_QUOTA
+	ei->i_reserved_quota = 0;
+#endif
+	inode->i_generation = le32_to_cpu(raw_inode->i_generation);
+	ei->i_block_group = iloc.block_group;
+	ei->i_last_alloc_group = ~0;
+	/*
+	 * NOTE! The in-memory inode i_data array is in little-endian order
+	 * even on big-endian machines: we do NOT byteswap the block numbers!
+	 */
+	for (block = 0; block < EXT4_N_BLOCKS; block++)
+		ei->i_data[block] = raw_inode->i_block[block];
+	INIT_LIST_HEAD(&ei->i_orphan);
+
+	/*
+	 * Set transaction id's of transactions that have to be committed
+	 * to finish f[data]sync. We set them to currently running transaction
+	 * as we cannot be sure that the inode or some of its metadata isn't
+	 * part of the transaction - the inode could have been reclaimed and
+	 * now it is reread from disk.
+	 */
+	if (journal) {
+		transaction_t *transaction;
+		tid_t tid;
+
+		read_lock(&journal->j_state_lock);
+		if (journal->j_running_transaction)
+			transaction = journal->j_running_transaction;
+		else
+			transaction = journal->j_committing_transaction;
+		if (transaction)
+			tid = transaction->t_tid;
+		else
+			tid = journal->j_commit_sequence;
+		read_unlock(&journal->j_state_lock);
+		ei->i_sync_tid = tid;
+		ei->i_datasync_tid = tid;
+	}
+
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
+		if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
+		    EXT4_INODE_SIZE(inode->i_sb)) {
+			ret = -EIO;
+			goto bad_inode;
+		}
+		if (ei->i_extra_isize == 0) {
+			/* The extra space is currently unused. Use it. */
+			ei->i_extra_isize = sizeof(struct ext4_inode) -
+					    EXT4_GOOD_OLD_INODE_SIZE;
+		} else {
+			__le32 *magic = (void *)raw_inode +
+					EXT4_GOOD_OLD_INODE_SIZE +
+					ei->i_extra_isize;
+			if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
+				ext4_set_inode_state(inode, EXT4_STATE_XATTR);
+		}
+	} else
+		ei->i_extra_isize = 0;
+
+	EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode);
+	EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode);
+	EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
+	EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
+
+	inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+			inode->i_version |=
+			(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+	}
+
+	ret = 0;
+	if (ei->i_file_acl &&
+	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+		EXT4_ERROR_INODE(inode, "bad extended attribute block %llu",
+				 ei->i_file_acl);
+		ret = -EIO;
+		goto bad_inode;
+	} else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		    (S_ISLNK(inode->i_mode) &&
+		     !ext4_inode_is_fast_symlink(inode)))
+			/* Validate extent which is part of inode */
+			ret = ext4_ext_check_inode(inode);
+	} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		   (S_ISLNK(inode->i_mode) &&
+		    !ext4_inode_is_fast_symlink(inode))) {
+		/* Validate block references which are part of inode */
+		ret = ext4_check_inode_blockref(inode);
+	}
+	if (ret)
+		goto bad_inode;
+
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_op = &ext4_file_inode_operations;
+		inode->i_fop = &ext4_file_operations;
+		ext4_set_aops(inode);
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = &ext4_dir_inode_operations;
+		inode->i_fop = &ext4_dir_operations;
+	} else if (S_ISLNK(inode->i_mode)) {
+		if (ext4_inode_is_fast_symlink(inode)) {
+			inode->i_op = &ext4_fast_symlink_inode_operations;
+			nd_terminate_link(ei->i_data, inode->i_size,
+				sizeof(ei->i_data) - 1);
+		} else {
+			inode->i_op = &ext4_symlink_inode_operations;
+			ext4_set_aops(inode);
+		}
+	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
+	      S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
+		inode->i_op = &ext4_special_inode_operations;
+		if (raw_inode->i_block[0])
+			init_special_inode(inode, inode->i_mode,
+			   old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
+		else
+			init_special_inode(inode, inode->i_mode,
+			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
+	} else {
+		ret = -EIO;
+		EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
+		goto bad_inode;
+	}
+	brelse(iloc.bh);
+	ext4_set_inode_flags(inode);
+	unlock_new_inode(inode);
+	return inode;
+
+bad_inode:
+	brelse(iloc.bh);
+	iget_failed(inode);
+	return ERR_PTR(ret);
+}
+
+static int ext4_inode_blocks_set(handle_t *handle,
+				struct ext4_inode *raw_inode,
+				struct ext4_inode_info *ei)
+{
+	struct inode *inode = &(ei->vfs_inode);
+	u64 i_blocks = inode->i_blocks;
+	struct super_block *sb = inode->i_sb;
+
+	if (i_blocks <= ~0U) {
+		/*
+		 * i_blocks can be represnted in a 32 bit variable
+		 * as multiple of 512 bytes
+		 */
+		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
+		raw_inode->i_blocks_high = 0;
+		ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
+		return 0;
+	}
+	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
+		return -EFBIG;
+
+	if (i_blocks <= 0xffffffffffffULL) {
+		/*
+		 * i_blocks can be represented in a 48 bit variable
+		 * as multiple of 512 bytes
+		 */
+		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
+		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
+		ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
+	} else {
+		ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE);
+		/* i_block is stored in file system block size */
+		i_blocks = i_blocks >> (inode->i_blkbits - 9);
+		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
+		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
+	}
+	return 0;
+}
+
+/*
+ * Post the struct inode info into an on-disk inode location in the
+ * buffer-cache.  This gobbles the caller's reference to the
+ * buffer_head in the inode location struct.
+ *
+ * The caller must have write access to iloc->bh.
+ */
+static int ext4_do_update_inode(handle_t *handle,
+				struct inode *inode,
+				struct ext4_iloc *iloc)
+{
+	struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct buffer_head *bh = iloc->bh;
+	int err = 0, rc, block;
+
+	/* For fields not not tracking in the in-memory inode,
+	 * initialise them to zero for new inodes. */
+	if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
+		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
+
+	ext4_get_inode_flags(ei);
+	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
+	if (!(test_opt(inode->i_sb, NO_UID32))) {
+		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
+		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
+/*
+ * Fix up interoperability with old kernels. Otherwise, old inodes get
+ * re-used with the upper 16 bits of the uid/gid intact
+ */
+		if (!ei->i_dtime) {
+			raw_inode->i_uid_high =
+				cpu_to_le16(high_16_bits(inode->i_uid));
+			raw_inode->i_gid_high =
+				cpu_to_le16(high_16_bits(inode->i_gid));
+		} else {
+			raw_inode->i_uid_high = 0;
+			raw_inode->i_gid_high = 0;
+		}
+	} else {
+		raw_inode->i_uid_low =
+			cpu_to_le16(fs_high2lowuid(inode->i_uid));
+		raw_inode->i_gid_low =
+			cpu_to_le16(fs_high2lowgid(inode->i_gid));
+		raw_inode->i_uid_high = 0;
+		raw_inode->i_gid_high = 0;
+	}
+	raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
+
+	EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
+	EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
+	EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
+	EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
+
+	if (ext4_inode_blocks_set(handle, raw_inode, ei))
+		goto out_brelse;
+	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
+	raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
+	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
+	    cpu_to_le32(EXT4_OS_HURD))
+		raw_inode->i_file_acl_high =
+			cpu_to_le16(ei->i_file_acl >> 32);
+	raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
+	ext4_isize_set(raw_inode, ei->i_disksize);
+	if (ei->i_disksize > 0x7fffffffULL) {
+		struct super_block *sb = inode->i_sb;
+		if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
+				EXT4_SB(sb)->s_es->s_rev_level ==
+				cpu_to_le32(EXT4_GOOD_OLD_REV)) {
+			/* If this is the first large file
+			 * created, add a flag to the superblock.
+			 */
+			err = ext4_journal_get_write_access(handle,
+					EXT4_SB(sb)->s_sbh);
+			if (err)
+				goto out_brelse;
+			ext4_update_dynamic_rev(sb);
+			EXT4_SET_RO_COMPAT_FEATURE(sb,
+					EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+			sb->s_dirt = 1;
+			ext4_handle_sync(handle);
+			err = ext4_handle_dirty_metadata(handle, NULL,
+					EXT4_SB(sb)->s_sbh);
+		}
+	}
+	raw_inode->i_generation = cpu_to_le32(inode->i_generation);
+	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+		if (old_valid_dev(inode->i_rdev)) {
+			raw_inode->i_block[0] =
+				cpu_to_le32(old_encode_dev(inode->i_rdev));
+			raw_inode->i_block[1] = 0;
+		} else {
+			raw_inode->i_block[0] = 0;
+			raw_inode->i_block[1] =
+				cpu_to_le32(new_encode_dev(inode->i_rdev));
+			raw_inode->i_block[2] = 0;
+		}
+	} else
+		for (block = 0; block < EXT4_N_BLOCKS; block++)
+			raw_inode->i_block[block] = ei->i_data[block];
+
+	raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+	if (ei->i_extra_isize) {
+		if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+			raw_inode->i_version_hi =
+			cpu_to_le32(inode->i_version >> 32);
+		raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+	}
+
+	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (!err)
+		err = rc;
+	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
+
+	ext4_update_inode_fsync_trans(handle, inode, 0);
+out_brelse:
+	brelse(bh);
+	ext4_std_error(inode->i_sb, err);
+	return err;
+}
+
+/*
+ * ext4_write_inode()
+ *
+ * We are called from a few places:
+ *
+ * - Within generic_file_write() for O_SYNC files.
+ *   Here, there will be no transaction running. We wait for any running
+ *   trasnaction to commit.
+ *
+ * - Within sys_sync(), kupdate and such.
+ *   We wait on commit, if tol to.
+ *
+ * - Within prune_icache() (PF_MEMALLOC == true)
+ *   Here we simply return.  We can't afford to block kswapd on the
+ *   journal commit.
+ *
+ * In all cases it is actually safe for us to return without doing anything,
+ * because the inode has been copied into a raw inode buffer in
+ * ext4_mark_inode_dirty().  This is a correctness thing for O_SYNC and for
+ * knfsd.
+ *
+ * Note that we are absolutely dependent upon all inode dirtiers doing the
+ * right thing: they *must* call mark_inode_dirty() after dirtying info in
+ * which we are interested.
+ *
+ * It would be a bug for them to not do this.  The code:
+ *
+ *	mark_inode_dirty(inode)
+ *	stuff();
+ *	inode->i_size = expr;
+ *
+ * is in error because a kswapd-driven write_inode() could occur while
+ * `stuff()' is running, and the new i_size will be lost.  Plus the inode
+ * will no longer be on the superblock's dirty inode list.
+ */
+int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	int err;
+
+	if (current->flags & PF_MEMALLOC)
+		return 0;
+
+	if (EXT4_SB(inode->i_sb)->s_journal) {
+		if (ext4_journal_current_handle()) {
+			jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
+			dump_stack();
+			return -EIO;
+		}
+
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			return 0;
+
+		err = ext4_force_commit(inode->i_sb);
+	} else {
+		struct ext4_iloc iloc;
+
+		err = __ext4_get_inode_loc(inode, &iloc, 0);
+		if (err)
+			return err;
+		if (wbc->sync_mode == WB_SYNC_ALL)
+			sync_dirty_buffer(iloc.bh);
+		if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
+			EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
+					 "IO error syncing inode");
+			err = -EIO;
+		}
+		brelse(iloc.bh);
+	}
+	return err;
+}
+
+/*
+ * ext4_setattr()
+ *
+ * Called from notify_change.
+ *
+ * We want to trap VFS attempts to truncate the file as soon as
+ * possible.  In particular, we want to make sure that when the VFS
+ * shrinks i_size, we put the inode on the orphan list and modify
+ * i_disksize immediately, so that during the subsequent flushing of
+ * dirty pages and freeing of disk blocks, we can guarantee that any
+ * commit will leave the blocks being flushed in an unused state on
+ * disk.  (On recovery, the inode will get truncated and the blocks will
+ * be freed, so we have a strong guarantee that no future commit will
+ * leave these blocks visible to the user.)
+ *
+ * Another thing we have to assure is that if we are in ordered mode
+ * and inode is still attached to the committing transaction, we must
+ * we start writeout of all the dirty pages which are being truncated.
+ * This way we are sure that all the data written in the previous
+ * transaction are already on disk (truncate waits for pages under
+ * writeback).
+ *
+ * Called with inode->i_mutex down.
+ */
+int ext4_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = dentry->d_inode;
+	int error, rc = 0;
+	int orphan = 0;
+	const unsigned int ia_valid = attr->ia_valid;
+
+	error = inode_change_ok(inode, attr);
+	if (error)
+		return error;
+
+	if (is_quota_modification(inode, attr))
+		dquot_initialize(inode);
+	if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
+		(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+		handle_t *handle;
+
+		/* (user+group)*(old+new) structure, inode write (sb,
+		 * inode block, ? - but truncate inode update has it) */
+		handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
+					EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
+		if (IS_ERR(handle)) {
+			error = PTR_ERR(handle);
+			goto err_out;
+		}
+		error = dquot_transfer(inode, attr);
+		if (error) {
+			ext4_journal_stop(handle);
+			return error;
+		}
+		/* Update corresponding info in inode so that everything is in
+		 * one transaction */
+		if (attr->ia_valid & ATTR_UID)
+			inode->i_uid = attr->ia_uid;
+		if (attr->ia_valid & ATTR_GID)
+			inode->i_gid = attr->ia_gid;
+		error = ext4_mark_inode_dirty(handle, inode);
+		ext4_journal_stop(handle);
+	}
+
+	if (attr->ia_valid & ATTR_SIZE) {
+		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+			if (attr->ia_size > sbi->s_bitmap_maxbytes)
+				return -EFBIG;
+		}
+	}
+
+	if (S_ISREG(inode->i_mode) &&
+	    attr->ia_valid & ATTR_SIZE &&
+	    (attr->ia_size < inode->i_size)) {
+		handle_t *handle;
+
+		handle = ext4_journal_start(inode, 3);
+		if (IS_ERR(handle)) {
+			error = PTR_ERR(handle);
+			goto err_out;
+		}
+		if (ext4_handle_valid(handle)) {
+			error = ext4_orphan_add(handle, inode);
+			orphan = 1;
+		}
+		EXT4_I(inode)->i_disksize = attr->ia_size;
+		rc = ext4_mark_inode_dirty(handle, inode);
+		if (!error)
+			error = rc;
+		ext4_journal_stop(handle);
+
+		if (ext4_should_order_data(inode)) {
+			error = ext4_begin_ordered_truncate(inode,
+							    attr->ia_size);
+			if (error) {
+				/* Do as much error cleanup as possible */
+				handle = ext4_journal_start(inode, 3);
+				if (IS_ERR(handle)) {
+					ext4_orphan_del(NULL, inode);
+					goto err_out;
+				}
+				ext4_orphan_del(handle, inode);
+				orphan = 0;
+				ext4_journal_stop(handle);
+				goto err_out;
+			}
+		}
+	}
+
+	if (attr->ia_valid & ATTR_SIZE) {
+		if (attr->ia_size != i_size_read(inode)) {
+			truncate_setsize(inode, attr->ia_size);
+			ext4_truncate(inode);
+		} else if (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
+			ext4_truncate(inode);
+	}
+
+	if (!rc) {
+		setattr_copy(inode, attr);
+		mark_inode_dirty(inode);
+	}
+
+	/*
+	 * If the call to ext4_truncate failed to get a transaction handle at
+	 * all, we need to clean up the in-core orphan list manually.
+	 */
+	if (orphan && inode->i_nlink)
+		ext4_orphan_del(NULL, inode);
+
+	if (!rc && (ia_valid & ATTR_MODE))
+		rc = ext4_acl_chmod(inode);
+
+err_out:
+	ext4_std_error(inode->i_sb, error);
+	if (!error)
+		error = rc;
+	return error;
+}
+
+int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		 struct kstat *stat)
+{
+	struct inode *inode;
+	unsigned long delalloc_blocks;
+
+	inode = dentry->d_inode;
+	generic_fillattr(inode, stat);
+
+	/*
+	 * We can't update i_blocks if the block allocation is delayed
+	 * otherwise in the case of system crash before the real block
+	 * allocation is done, we will have i_blocks inconsistent with
+	 * on-disk file blocks.
+	 * We always keep i_blocks updated together with real
+	 * allocation. But to not confuse with user, stat
+	 * will return the blocks that include the delayed allocation
+	 * blocks for this file.
+	 */
+	delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+
+	stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+	return 0;
+}
+
+static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
+				      int chunk)
+{
+	int indirects;
+
+	/* if nrblocks are contiguous */
+	if (chunk) {
+		/*
+		 * With N contiguous data blocks, we need at most
+		 * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
+		 * 2 dindirect blocks, and 1 tindirect block
+		 */
+		return DIV_ROUND_UP(nrblocks,
+				    EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
+	}
+	/*
+	 * if nrblocks are not contiguous, worse case, each block touch
+	 * a indirect block, and each indirect block touch a double indirect
+	 * block, plus a triple indirect block
+	 */
+	indirects = nrblocks * 2 + 1;
+	return indirects;
+}
+
+static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+{
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
+	return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
+}
+
+/*
+ * Account for index blocks, block groups bitmaps and block group
+ * descriptor blocks if modify datablocks and index blocks
+ * worse case, the indexs blocks spread over different block groups
+ *
+ * If datablocks are discontiguous, they are possible to spread over
+ * different block groups too. If they are contiuguous, with flexbg,
+ * they could still across block group boundary.
+ *
+ * Also account for superblock, inode, quota and xattr blocks
+ */
+static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+{
+	ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
+	int gdpblocks;
+	int idxblocks;
+	int ret = 0;
+
+	/*
+	 * How many index blocks need to touch to modify nrblocks?
+	 * The "Chunk" flag indicating whether the nrblocks is
+	 * physically contiguous on disk
+	 *
+	 * For Direct IO and fallocate, they calls get_block to allocate
+	 * one single extent at a time, so they could set the "Chunk" flag
+	 */
+	idxblocks = ext4_index_trans_blocks(inode, nrblocks, chunk);
+
+	ret = idxblocks;
+
+	/*
+	 * Now let's see how many group bitmaps and group descriptors need
+	 * to account
+	 */
+	groups = idxblocks;
+	if (chunk)
+		groups += 1;
+	else
+		groups += nrblocks;
+
+	gdpblocks = groups;
+	if (groups > ngroups)
+		groups = ngroups;
+	if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
+		gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
+
+	/* bitmaps and block group descriptor blocks */
+	ret += groups + gdpblocks;
+
+	/* Blocks for super block, inode, quota and xattr blocks */
+	ret += EXT4_META_TRANS_BLOCKS(inode->i_sb);
+
+	return ret;
+}
+
+/*
+ * Calculate the total number of credits to reserve to fit
+ * the modification of a single pages into a single transaction,
+ * which may include multiple chunks of block allocations.
+ *
+ * This could be called via ext4_write_begin()
+ *
+ * We need to consider the worse case, when
+ * one new block per extent.
+ */
+int ext4_writepage_trans_blocks(struct inode *inode)
+{
+	int bpp = ext4_journal_blocks_per_page(inode);
+	int ret;
+
+	ret = ext4_meta_trans_blocks(inode, bpp, 0);
+
+	/* Account for data blocks for journalled mode */
+	if (ext4_should_journal_data(inode))
+		ret += bpp;
+	return ret;
+}
+
+/*
+ * Calculate the journal credits for a chunk of data modification.
+ *
+ * This is called from DIO, fallocate or whoever calling
+ * ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks.
+ *
+ * journal buffers for data blocks are not included here, as DIO
+ * and fallocate do no need to journal data buffers.
+ */
+int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks)
+{
+	return ext4_meta_trans_blocks(inode, nrblocks, 1);
+}
+
+/*
+ * The caller must have previously called ext4_reserve_inode_write().
+ * Give this, we know that the caller already has write access to iloc->bh.
+ */
+int ext4_mark_iloc_dirty(handle_t *handle,
+			 struct inode *inode, struct ext4_iloc *iloc)
+{
+	int err = 0;
+
+	if (test_opt(inode->i_sb, I_VERSION))
+		inode_inc_iversion(inode);
+
+	/* the do_update_inode consumes one bh->b_count */
+	get_bh(iloc->bh);
+
+	/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
+	err = ext4_do_update_inode(handle, inode, iloc);
+	put_bh(iloc->bh);
+	return err;
+}
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh.  This _must_ be cleaned up later.
+ */
+
+int
+ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
+			 struct ext4_iloc *iloc)
+{
+	int err;
+
+	err = ext4_get_inode_loc(inode, iloc);
+	if (!err) {
+		BUFFER_TRACE(iloc->bh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, iloc->bh);
+		if (err) {
+			brelse(iloc->bh);
+			iloc->bh = NULL;
+		}
+	}
+	ext4_std_error(inode->i_sb, err);
+	return err;
+}
+
+/*
+ * Expand an inode by new_extra_isize bytes.
+ * Returns 0 on success or negative error number on failure.
+ */
+static int ext4_expand_extra_isize(struct inode *inode,
+				   unsigned int new_extra_isize,
+				   struct ext4_iloc iloc,
+				   handle_t *handle)
+{
+	struct ext4_inode *raw_inode;
+	struct ext4_xattr_ibody_header *header;
+
+	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+		return 0;
+
+	raw_inode = ext4_raw_inode(&iloc);
+
+	header = IHDR(inode, raw_inode);
+
+	/* No extended attributes present */
+	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
+	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
+			new_extra_isize);
+		EXT4_I(inode)->i_extra_isize = new_extra_isize;
+		return 0;
+	}
+
+	/* try to expand with EAs present */
+	return ext4_expand_extra_isize_ea(inode, new_extra_isize,
+					  raw_inode, handle);
+}
+
+/*
+ * What we do here is to mark the in-core inode as clean with respect to inode
+ * dirtiness (it may still be data-dirty).
+ * This means that the in-core inode may be reaped by prune_icache
+ * without having to perform any I/O.  This is a very good thing,
+ * because *any* task may call prune_icache - even ones which
+ * have a transaction open against a different journal.
+ *
+ * Is this cheating?  Not really.  Sure, we haven't written the
+ * inode out, but prune_icache isn't a user-visible syncing function.
+ * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
+ * we start and wait on commits.
+ *
+ * Is this efficient/effective?  Well, we're being nice to the system
+ * by cleaning up our inodes proactively so they can be reaped
+ * without I/O.  But we are potentially leaving up to five seconds'
+ * worth of inodes floating about which prune_icache wants us to
+ * write out.  One way to fix that would be to get prune_icache()
+ * to do a write_super() to free up some memory.  It has the desired
+ * effect.
+ */
+int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
+{
+	struct ext4_iloc iloc;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	static unsigned int mnt_count;
+	int err, ret;
+
+	might_sleep();
+	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (ext4_handle_valid(handle) &&
+	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
+		/*
+		 * We need extra buffer credits since we may write into EA block
+		 * with this same handle. If journal_extend fails, then it will
+		 * only result in a minor loss of functionality for that inode.
+		 * If this is felt to be critical, then e2fsck should be run to
+		 * force a large enough s_min_extra_isize.
+		 */
+		if ((jbd2_journal_extend(handle,
+			     EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) {
+			ret = ext4_expand_extra_isize(inode,
+						      sbi->s_want_extra_isize,
+						      iloc, handle);
+			if (ret) {
+				ext4_set_inode_state(inode,
+						     EXT4_STATE_NO_EXPAND);
+				if (mnt_count !=
+					le16_to_cpu(sbi->s_es->s_mnt_count)) {
+					ext4_warning(inode->i_sb,
+					"Unable to expand inode %lu. Delete"
+					" some EAs or run e2fsck.",
+					inode->i_ino);
+					mnt_count =
+					  le16_to_cpu(sbi->s_es->s_mnt_count);
+				}
+			}
+		}
+	}
+	if (!err)
+		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+	return err;
+}
+
+/*
+ * ext4_dirty_inode() is called from __mark_inode_dirty()
+ *
+ * We're really interested in the case where a file is being extended.
+ * i_size has been changed by generic_commit_write() and we thus need
+ * to include the updated inode in the current transaction.
+ *
+ * Also, dquot_alloc_block() will always dirty the inode when blocks
+ * are allocated to the file.
+ *
+ * If the inode is marked synchronous, we don't honour that here - doing
+ * so would cause a commit on atime updates, which we don't bother doing.
+ * We handle synchronous inodes at the highest possible level.
+ */
+void ext4_dirty_inode(struct inode *inode, int flags)
+{
+	handle_t *handle;
+
+	handle = ext4_journal_start(inode, 2);
+	if (IS_ERR(handle))
+		goto out;
+
+	ext4_mark_inode_dirty(handle, inode);
+
+	ext4_journal_stop(handle);
+out:
+	return;
+}
+
+#if 0
+/*
+ * Bind an inode's backing buffer_head into this transaction, to prevent
+ * it from being flushed to disk early.  Unlike
+ * ext4_reserve_inode_write, this leaves behind no bh reference and
+ * returns no iloc structure, so the caller needs to repeat the iloc
+ * lookup to mark the inode dirty later.
+ */
+static int ext4_pin_inode(handle_t *handle, struct inode *inode)
+{
+	struct ext4_iloc iloc;
+
+	int err = 0;
+	if (handle) {
+		err = ext4_get_inode_loc(inode, &iloc);
+		if (!err) {
+			BUFFER_TRACE(iloc.bh, "get_write_access");
+			err = jbd2_journal_get_write_access(handle, iloc.bh);
+			if (!err)
+				err = ext4_handle_dirty_metadata(handle,
+								 NULL,
+								 iloc.bh);
+			brelse(iloc.bh);
+		}
+	}
+	ext4_std_error(inode->i_sb, err);
+	return err;
+}
+#endif
+
+int ext4_change_inode_journal_flag(struct inode *inode, int val)
+{
+	journal_t *journal;
+	handle_t *handle;
+	int err;
+
+	/*
+	 * We have to be very careful here: changing a data block's
+	 * journaling status dynamically is dangerous.  If we write a
+	 * data block to the journal, change the status and then delete
+	 * that block, we risk forgetting to revoke the old log record
+	 * from the journal and so a subsequent replay can corrupt data.
+	 * So, first we make sure that the journal is empty and that
+	 * nobody is changing anything.
+	 */
+
+	journal = EXT4_JOURNAL(inode);
+	if (!journal)
+		return 0;
+	if (is_journal_aborted(journal))
+		return -EROFS;
+
+	jbd2_journal_lock_updates(journal);
+	jbd2_journal_flush(journal);
+
+	/*
+	 * OK, there are no updates running now, and all cached data is
+	 * synced to disk.  We are now in a completely consistent state
+	 * which doesn't have anything in the journal, and we know that
+	 * no filesystem updates are running, so it is safe to modify
+	 * the inode's in-core data-journaling state flag now.
+	 */
+
+	if (val)
+		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
+	else
+		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
+	ext4_set_aops(inode);
+
+	jbd2_journal_unlock_updates(journal);
+
+	/* Finally we can mark the inode as dirty. */
+
+	handle = ext4_journal_start(inode, 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	err = ext4_mark_inode_dirty(handle, inode);
+	ext4_handle_sync(handle);
+	ext4_journal_stop(handle);
+	ext4_std_error(inode->i_sb, err);
+
+	return err;
+}
+
+static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh)
+{
+	return !buffer_mapped(bh);
+}
+
+int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	loff_t size;
+	unsigned long len;
+	int ret = -EINVAL;
+	void *fsdata;
+	struct file *file = vma->vm_file;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+
+	/*
+	 * Get i_alloc_sem to stop truncates messing with the inode. We cannot
+	 * get i_mutex because we are already holding mmap_sem.
+	 */
+	down_read(&inode->i_alloc_sem);
+	size = i_size_read(inode);
+	if (page->mapping != mapping || size <= page_offset(page)
+	    || !PageUptodate(page)) {
+		/* page got truncated from under us? */
+		goto out_unlock;
+	}
+	ret = 0;
+
+	lock_page(page);
+	wait_on_page_writeback(page);
+	if (PageMappedToDisk(page)) {
+		up_read(&inode->i_alloc_sem);
+		return VM_FAULT_LOCKED;
+	}
+
+	if (page->index == size >> PAGE_CACHE_SHIFT)
+		len = size & ~PAGE_CACHE_MASK;
+	else
+		len = PAGE_CACHE_SIZE;
+
+	/*
+	 * return if we have all the buffers mapped. This avoid
+	 * the need to call write_begin/write_end which does a
+	 * journal_start/journal_stop which can block and take
+	 * long time
+	 */
+	if (page_has_buffers(page)) {
+		if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
+					ext4_bh_unmapped)) {
+			up_read(&inode->i_alloc_sem);
+			return VM_FAULT_LOCKED;
+		}
+	}
+	unlock_page(page);
+	/*
+	 * OK, we need to fill the hole... Do write_begin write_end
+	 * to do block allocation/reservation.We are not holding
+	 * inode.i__mutex here. That allow * parallel write_begin,
+	 * write_end call. lock_page prevent this from happening
+	 * on the same page though
+	 */
+	ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
+			len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
+	if (ret < 0)
+		goto out_unlock;
+	ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
+			len, len, page, fsdata);
+	if (ret < 0)
+		goto out_unlock;
+	ret = 0;
+
+	/*
+	 * write_begin/end might have created a dirty page and someone
+	 * could wander in and start the IO.  Make sure that hasn't
+	 * happened.
+	 */
+	lock_page(page);
+	wait_on_page_writeback(page);
+	up_read(&inode->i_alloc_sem);
+	return VM_FAULT_LOCKED;
+out_unlock:
+	if (ret)
+		ret = VM_FAULT_SIGBUS;
+	up_read(&inode->i_alloc_sem);
+	return ret;
+}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
new file mode 100644
index 00000000..4cbe1c2c
--- /dev/null
+++ b/fs/ext4/ioctl.c
@@ -0,0 +1,442 @@
+/*
+ * linux/fs/ext4/ioctl.c
+ *
+ * Copyright (C) 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/capability.h>
+#include <linux/time.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/file.h>
+#include <asm/uaccess.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+
+long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int flags;
+
+	ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
+
+	switch (cmd) {
+	case EXT4_IOC_GETFLAGS:
+		ext4_get_inode_flags(ei);
+		flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+		return put_user(flags, (int __user *) arg);
+	case EXT4_IOC_SETFLAGS: {
+		handle_t *handle = NULL;
+		int err, migrate = 0;
+		struct ext4_iloc iloc;
+		unsigned int oldflags, mask, i;
+		unsigned int jflag;
+
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+
+		if (get_user(flags, (int __user *) arg))
+			return -EFAULT;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
+		flags = ext4_mask_flags(inode->i_mode, flags);
+
+		err = -EPERM;
+		mutex_lock(&inode->i_mutex);
+		/* Is it quota file? Do not allow user to mess with it */
+		if (IS_NOQUOTA(inode))
+			goto flags_out;
+
+		oldflags = ei->i_flags;
+
+		/* The JOURNAL_DATA flag is modifiable only by root */
+		jflag = flags & EXT4_JOURNAL_DATA_FL;
+
+		/*
+		 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+		 * the relevant capability.
+		 *
+		 * This test looks nicer. Thanks to Pauline Middelink
+		 */
+		if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
+			if (!capable(CAP_LINUX_IMMUTABLE))
+				goto flags_out;
+		}
+
+		/*
+		 * The JOURNAL_DATA flag can only be changed by
+		 * the relevant capability.
+		 */
+		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+			if (!capable(CAP_SYS_RESOURCE))
+				goto flags_out;
+		}
+		if (oldflags & EXT4_EXTENTS_FL) {
+			/* We don't support clearning extent flags */
+			if (!(flags & EXT4_EXTENTS_FL)) {
+				err = -EOPNOTSUPP;
+				goto flags_out;
+			}
+		} else if (flags & EXT4_EXTENTS_FL) {
+			/* migrate the file */
+			migrate = 1;
+			flags &= ~EXT4_EXTENTS_FL;
+		}
+
+		if (flags & EXT4_EOFBLOCKS_FL) {
+			/* we don't support adding EOFBLOCKS flag */
+			if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
+				err = -EOPNOTSUPP;
+				goto flags_out;
+			}
+		} else if (oldflags & EXT4_EOFBLOCKS_FL)
+			ext4_truncate(inode);
+
+		handle = ext4_journal_start(inode, 1);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto flags_out;
+		}
+		if (IS_SYNC(inode))
+			ext4_handle_sync(handle);
+		err = ext4_reserve_inode_write(handle, inode, &iloc);
+		if (err)
+			goto flags_err;
+
+		for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
+			if (!(mask & EXT4_FL_USER_MODIFIABLE))
+				continue;
+			if (mask & flags)
+				ext4_set_inode_flag(inode, i);
+			else
+				ext4_clear_inode_flag(inode, i);
+		}
+
+		ext4_set_inode_flags(inode);
+		inode->i_ctime = ext4_current_time(inode);
+
+		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+flags_err:
+		ext4_journal_stop(handle);
+		if (err)
+			goto flags_out;
+
+		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
+			err = ext4_change_inode_journal_flag(inode, jflag);
+		if (err)
+			goto flags_out;
+		if (migrate)
+			err = ext4_ext_migrate(inode);
+flags_out:
+		mutex_unlock(&inode->i_mutex);
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
+	}
+	case EXT4_IOC_GETVERSION:
+	case EXT4_IOC_GETVERSION_OLD:
+		return put_user(inode->i_generation, (int __user *) arg);
+	case EXT4_IOC_SETVERSION:
+	case EXT4_IOC_SETVERSION_OLD: {
+		handle_t *handle;
+		struct ext4_iloc iloc;
+		__u32 generation;
+		int err;
+
+		if (!inode_owner_or_capable(inode))
+			return -EPERM;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+		if (get_user(generation, (int __user *) arg)) {
+			err = -EFAULT;
+			goto setversion_out;
+		}
+
+		handle = ext4_journal_start(inode, 1);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto setversion_out;
+		}
+		err = ext4_reserve_inode_write(handle, inode, &iloc);
+		if (err == 0) {
+			inode->i_ctime = ext4_current_time(inode);
+			inode->i_generation = generation;
+			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+		}
+		ext4_journal_stop(handle);
+setversion_out:
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
+	}
+#ifdef CONFIG_JBD2_DEBUG
+	case EXT4_IOC_WAIT_FOR_READONLY:
+		/*
+		 * This is racy - by the time we're woken up and running,
+		 * the superblock could be released.  And the module could
+		 * have been unloaded.  So sue me.
+		 *
+		 * Returns 1 if it slept, else zero.
+		 */
+		{
+			struct super_block *sb = inode->i_sb;
+			DECLARE_WAITQUEUE(wait, current);
+			int ret = 0;
+
+			set_current_state(TASK_INTERRUPTIBLE);
+			add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
+			if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
+				schedule();
+				ret = 1;
+			}
+			remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
+			return ret;
+		}
+#endif
+	case EXT4_IOC_GROUP_EXTEND: {
+		ext4_fsblk_t n_blocks_count;
+		struct super_block *sb = inode->i_sb;
+		int err, err2=0;
+
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (get_user(n_blocks_count, (__u32 __user *)arg))
+			return -EFAULT;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
+		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
+		if (EXT4_SB(sb)->s_journal) {
+			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		}
+		if (err == 0)
+			err = err2;
+		mnt_drop_write(filp->f_path.mnt);
+
+		return err;
+	}
+
+	case EXT4_IOC_MOVE_EXT: {
+		struct move_extent me;
+		struct file *donor_filp;
+		int err;
+
+		if (!(filp->f_mode & FMODE_READ) ||
+		    !(filp->f_mode & FMODE_WRITE))
+			return -EBADF;
+
+		if (copy_from_user(&me,
+			(struct move_extent __user *)arg, sizeof(me)))
+			return -EFAULT;
+		me.moved_len = 0;
+
+		donor_filp = fget(me.donor_fd);
+		if (!donor_filp)
+			return -EBADF;
+
+		if (!(donor_filp->f_mode & FMODE_WRITE)) {
+			err = -EBADF;
+			goto mext_out;
+		}
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			goto mext_out;
+
+		err = ext4_move_extents(filp, donor_filp, me.orig_start,
+					me.donor_start, me.len, &me.moved_len);
+		mnt_drop_write(filp->f_path.mnt);
+		if (me.moved_len > 0)
+			file_remove_suid(donor_filp);
+
+		if (copy_to_user((struct move_extent __user *)arg,
+				 &me, sizeof(me)))
+			err = -EFAULT;
+mext_out:
+		fput(donor_filp);
+		return err;
+	}
+
+	case EXT4_IOC_GROUP_ADD: {
+		struct ext4_new_group_data input;
+		struct super_block *sb = inode->i_sb;
+		int err, err2=0;
+
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
+				sizeof(input)))
+			return -EFAULT;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
+		err = ext4_group_add(sb, &input);
+		if (EXT4_SB(sb)->s_journal) {
+			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		}
+		if (err == 0)
+			err = err2;
+		mnt_drop_write(filp->f_path.mnt);
+
+		return err;
+	}
+
+	case EXT4_IOC_MIGRATE:
+	{
+		int err;
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+		/*
+		 * inode_mutex prevent write and truncate on the file.
+		 * Read still goes through. We take i_data_sem in
+		 * ext4_ext_swap_inode_data before we switch the
+		 * inode format to prevent read.
+		 */
+		mutex_lock(&(inode->i_mutex));
+		err = ext4_ext_migrate(inode);
+		mutex_unlock(&(inode->i_mutex));
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
+	}
+
+	case EXT4_IOC_ALLOC_DA_BLKS:
+	{
+		int err;
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+		err = ext4_alloc_da_blocks(inode);
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
+	}
+
+	case FITRIM:
+	{
+		struct super_block *sb = inode->i_sb;
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+		struct fstrim_range range;
+		int ret = 0;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+
+		if (copy_from_user(&range, (struct fstrim_range *)arg,
+		    sizeof(range)))
+			return -EFAULT;
+
+		range.minlen = max((unsigned int)range.minlen,
+				   q->limits.discard_granularity);
+		ret = ext4_trim_fs(sb, &range);
+		if (ret < 0)
+			return ret;
+
+		if (copy_to_user((struct fstrim_range *)arg, &range,
+		    sizeof(range)))
+			return -EFAULT;
+
+		return 0;
+	}
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	/* These are just misnamed, they actually get/put from/to user an int */
+	switch (cmd) {
+	case EXT4_IOC32_GETFLAGS:
+		cmd = EXT4_IOC_GETFLAGS;
+		break;
+	case EXT4_IOC32_SETFLAGS:
+		cmd = EXT4_IOC_SETFLAGS;
+		break;
+	case EXT4_IOC32_GETVERSION:
+		cmd = EXT4_IOC_GETVERSION;
+		break;
+	case EXT4_IOC32_SETVERSION:
+		cmd = EXT4_IOC_SETVERSION;
+		break;
+	case EXT4_IOC32_GROUP_EXTEND:
+		cmd = EXT4_IOC_GROUP_EXTEND;
+		break;
+	case EXT4_IOC32_GETVERSION_OLD:
+		cmd = EXT4_IOC_GETVERSION_OLD;
+		break;
+	case EXT4_IOC32_SETVERSION_OLD:
+		cmd = EXT4_IOC_SETVERSION_OLD;
+		break;
+#ifdef CONFIG_JBD2_DEBUG
+	case EXT4_IOC32_WAIT_FOR_READONLY:
+		cmd = EXT4_IOC_WAIT_FOR_READONLY;
+		break;
+#endif
+	case EXT4_IOC32_GETRSVSZ:
+		cmd = EXT4_IOC_GETRSVSZ;
+		break;
+	case EXT4_IOC32_SETRSVSZ:
+		cmd = EXT4_IOC_SETRSVSZ;
+		break;
+	case EXT4_IOC32_GROUP_ADD: {
+		struct compat_ext4_new_group_input __user *uinput;
+		struct ext4_new_group_input input;
+		mm_segment_t old_fs;
+		int err;
+
+		uinput = compat_ptr(arg);
+		err = get_user(input.group, &uinput->group);
+		err |= get_user(input.block_bitmap, &uinput->block_bitmap);
+		err |= get_user(input.inode_bitmap, &uinput->inode_bitmap);
+		err |= get_user(input.inode_table, &uinput->inode_table);
+		err |= get_user(input.blocks_count, &uinput->blocks_count);
+		err |= get_user(input.reserved_blocks,
+				&uinput->reserved_blocks);
+		if (err)
+			return -EFAULT;
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		err = ext4_ioctl(file, EXT4_IOC_GROUP_ADD,
+				 (unsigned long) &input);
+		set_fs(old_fs);
+		return err;
+	}
+	case EXT4_IOC_MOVE_EXT:
+	case FITRIM:
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
new file mode 100644
index 00000000..b6adf68a
--- /dev/null
+++ b/fs/ext4/mballoc.c
@@ -0,0 +1,4958 @@
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ */
+
+
+/*
+ * mballoc.c contains the multiblocks allocation routines
+ */
+
+#include "mballoc.h"
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <trace/events/ext4.h>
+
+/*
+ * MUSTDO:
+ *   - test ext4_ext_search_left() and ext4_ext_search_right()
+ *   - search for metadata in few groups
+ *
+ * TODO v4:
+ *   - normalization should take into account whether file is still open
+ *   - discard preallocations if no free space left (policy?)
+ *   - don't normalize tails
+ *   - quota
+ *   - reservation for superuser
+ *
+ * TODO v3:
+ *   - bitmap read-ahead (proposed by Oleg Drokin aka green)
+ *   - track min/max extents in each group for better group selection
+ *   - mb_mark_used() may allocate chunk right after splitting buddy
+ *   - tree of groups sorted by number of free blocks
+ *   - error handling
+ */
+
+/*
+ * The allocation request involve request for multiple number of blocks
+ * near to the goal(block) value specified.
+ *
+ * During initialization phase of the allocator we decide to use the
+ * group preallocation or inode preallocation depending on the size of
+ * the file. The size of the file could be the resulting file size we
+ * would have after allocation, or the current file size, which ever
+ * is larger. If the size is less than sbi->s_mb_stream_request we
+ * select to use the group preallocation. The default value of
+ * s_mb_stream_request is 16 blocks. This can also be tuned via
+ * /sys/fs/ext4/<partition>/mb_stream_req. The value is represented in
+ * terms of number of blocks.
+ *
+ * The main motivation for having small file use group preallocation is to
+ * ensure that we have small files closer together on the disk.
+ *
+ * First stage the allocator looks at the inode prealloc list,
+ * ext4_inode_info->i_prealloc_list, which contains list of prealloc
+ * spaces for this particular inode. The inode prealloc space is
+ * represented as:
+ *
+ * pa_lstart -> the logical start block for this prealloc space
+ * pa_pstart -> the physical start block for this prealloc space
+ * pa_len    -> length for this prealloc space
+ * pa_free   ->  free space available in this prealloc space
+ *
+ * The inode preallocation space is used looking at the _logical_ start
+ * block. If only the logical file block falls within the range of prealloc
+ * space we will consume the particular prealloc space. This make sure that
+ * that the we have contiguous physical blocks representing the file blocks
+ *
+ * The important thing to be noted in case of inode prealloc space is that
+ * we don't modify the values associated to inode prealloc space except
+ * pa_free.
+ *
+ * If we are not able to find blocks in the inode prealloc space and if we
+ * have the group allocation flag set then we look at the locality group
+ * prealloc space. These are per CPU prealloc list repreasented as
+ *
+ * ext4_sb_info.s_locality_groups[smp_processor_id()]
+ *
+ * The reason for having a per cpu locality group is to reduce the contention
+ * between CPUs. It is possible to get scheduled at this point.
+ *
+ * The locality group prealloc space is used looking at whether we have
+ * enough free space (pa_free) within the prealloc space.
+ *
+ * If we can't allocate blocks via inode prealloc or/and locality group
+ * prealloc then we look at the buddy cache. The buddy cache is represented
+ * by ext4_sb_info.s_buddy_cache (struct inode) whose file offset gets
+ * mapped to the buddy and bitmap information regarding different
+ * groups. The buddy information is attached to buddy cache inode so that
+ * we can access them through the page cache. The information regarding
+ * each group is loaded via ext4_mb_load_buddy.  The information involve
+ * block bitmap and buddy information. The information are stored in the
+ * inode as:
+ *
+ *  {                        page                        }
+ *  [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]...
+ *
+ *
+ * one block each for bitmap and buddy information.  So for each group we
+ * take up 2 blocks. A page can contain blocks_per_page (PAGE_CACHE_SIZE /
+ * blocksize) blocks.  So it can have information regarding groups_per_page
+ * which is blocks_per_page/2
+ *
+ * The buddy cache inode is not stored on disk. The inode is thrown
+ * away when the filesystem is unmounted.
+ *
+ * We look for count number of blocks in the buddy cache. If we were able
+ * to locate that many free blocks we return with additional information
+ * regarding rest of the contiguous physical block available
+ *
+ * Before allocating blocks via buddy cache we normalize the request
+ * blocks. This ensure we ask for more blocks that we needed. The extra
+ * blocks that we get after allocation is added to the respective prealloc
+ * list. In case of inode preallocation we follow a list of heuristics
+ * based on file size. This can be found in ext4_mb_normalize_request. If
+ * we are doing a group prealloc we try to normalize the request to
+ * sbi->s_mb_group_prealloc. Default value of s_mb_group_prealloc is
+ * 512 blocks. This can be tuned via
+ * /sys/fs/ext4/<partition/mb_group_prealloc. The value is represented in
+ * terms of number of blocks. If we have mounted the file system with -O
+ * stripe=<value> option the group prealloc request is normalized to the
+ * stripe value (sbi->s_stripe)
+ *
+ * The regular allocator(using the buddy cache) supports few tunables.
+ *
+ * /sys/fs/ext4/<partition>/mb_min_to_scan
+ * /sys/fs/ext4/<partition>/mb_max_to_scan
+ * /sys/fs/ext4/<partition>/mb_order2_req
+ *
+ * The regular allocator uses buddy scan only if the request len is power of
+ * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The
+ * value of s_mb_order2_reqs can be tuned via
+ * /sys/fs/ext4/<partition>/mb_order2_req.  If the request len is equal to
+ * stripe size (sbi->s_stripe), we try to search for contiguous block in
+ * stripe size. This should result in better allocation on RAID setups. If
+ * not, we search in the specific group using bitmap for best extents. The
+ * tunable min_to_scan and max_to_scan control the behaviour here.
+ * min_to_scan indicate how long the mballoc __must__ look for a best
+ * extent and max_to_scan indicates how long the mballoc __can__ look for a
+ * best extent in the found extents. Searching for the blocks starts with
+ * the group specified as the goal value in allocation context via
+ * ac_g_ex. Each group is first checked based on the criteria whether it
+ * can used for allocation. ext4_mb_good_group explains how the groups are
+ * checked.
+ *
+ * Both the prealloc space are getting populated as above. So for the first
+ * request we will hit the buddy cache which will result in this prealloc
+ * space getting filled. The prealloc space is then later used for the
+ * subsequent request.
+ */
+
+/*
+ * mballoc operates on the following data:
+ *  - on-disk bitmap
+ *  - in-core buddy (actually includes buddy and bitmap)
+ *  - preallocation descriptors (PAs)
+ *
+ * there are two types of preallocations:
+ *  - inode
+ *    assiged to specific inode and can be used for this inode only.
+ *    it describes part of inode's space preallocated to specific
+ *    physical blocks. any block from that preallocated can be used
+ *    independent. the descriptor just tracks number of blocks left
+ *    unused. so, before taking some block from descriptor, one must
+ *    make sure corresponded logical block isn't allocated yet. this
+ *    also means that freeing any block within descriptor's range
+ *    must discard all preallocated blocks.
+ *  - locality group
+ *    assigned to specific locality group which does not translate to
+ *    permanent set of inodes: inode can join and leave group. space
+ *    from this type of preallocation can be used for any inode. thus
+ *    it's consumed from the beginning to the end.
+ *
+ * relation between them can be expressed as:
+ *    in-core buddy = on-disk bitmap + preallocation descriptors
+ *
+ * this mean blocks mballoc considers used are:
+ *  - allocated blocks (persistent)
+ *  - preallocated blocks (non-persistent)
+ *
+ * consistency in mballoc world means that at any time a block is either
+ * free or used in ALL structures. notice: "any time" should not be read
+ * literally -- time is discrete and delimited by locks.
+ *
+ *  to keep it simple, we don't use block numbers, instead we count number of
+ *  blocks: how many blocks marked used/free in on-disk bitmap, buddy and PA.
+ *
+ * all operations can be expressed as:
+ *  - init buddy:			buddy = on-disk + PAs
+ *  - new PA:				buddy += N; PA = N
+ *  - use inode PA:			on-disk += N; PA -= N
+ *  - discard inode PA			buddy -= on-disk - PA; PA = 0
+ *  - use locality group PA		on-disk += N; PA -= N
+ *  - discard locality group PA		buddy -= PA; PA = 0
+ *  note: 'buddy -= on-disk - PA' is used to show that on-disk bitmap
+ *        is used in real operation because we can't know actual used
+ *        bits from PA, only from on-disk bitmap
+ *
+ * if we follow this strict logic, then all operations above should be atomic.
+ * given some of them can block, we'd have to use something like semaphores
+ * killing performance on high-end SMP hardware. let's try to relax it using
+ * the following knowledge:
+ *  1) if buddy is referenced, it's already initialized
+ *  2) while block is used in buddy and the buddy is referenced,
+ *     nobody can re-allocate that block
+ *  3) we work on bitmaps and '+' actually means 'set bits'. if on-disk has
+ *     bit set and PA claims same block, it's OK. IOW, one can set bit in
+ *     on-disk bitmap if buddy has same bit set or/and PA covers corresponded
+ *     block
+ *
+ * so, now we're building a concurrency table:
+ *  - init buddy vs.
+ *    - new PA
+ *      blocks for PA are allocated in the buddy, buddy must be referenced
+ *      until PA is linked to allocation group to avoid concurrent buddy init
+ *    - use inode PA
+ *      we need to make sure that either on-disk bitmap or PA has uptodate data
+ *      given (3) we care that PA-=N operation doesn't interfere with init
+ *    - discard inode PA
+ *      the simplest way would be to have buddy initialized by the discard
+ *    - use locality group PA
+ *      again PA-=N must be serialized with init
+ *    - discard locality group PA
+ *      the simplest way would be to have buddy initialized by the discard
+ *  - new PA vs.
+ *    - use inode PA
+ *      i_data_sem serializes them
+ *    - discard inode PA
+ *      discard process must wait until PA isn't used by another process
+ *    - use locality group PA
+ *      some mutex should serialize them
+ *    - discard locality group PA
+ *      discard process must wait until PA isn't used by another process
+ *  - use inode PA
+ *    - use inode PA
+ *      i_data_sem or another mutex should serializes them
+ *    - discard inode PA
+ *      discard process must wait until PA isn't used by another process
+ *    - use locality group PA
+ *      nothing wrong here -- they're different PAs covering different blocks
+ *    - discard locality group PA
+ *      discard process must wait until PA isn't used by another process
+ *
+ * now we're ready to make few consequences:
+ *  - PA is referenced and while it is no discard is possible
+ *  - PA is referenced until block isn't marked in on-disk bitmap
+ *  - PA changes only after on-disk bitmap
+ *  - discard must not compete with init. either init is done before
+ *    any discard or they're serialized somehow
+ *  - buddy init as sum of on-disk bitmap and PAs is done atomically
+ *
+ * a special case when we've used PA to emptiness. no need to modify buddy
+ * in this case, but we should care about concurrent init
+ *
+ */
+
+ /*
+ * Logic in few words:
+ *
+ *  - allocation:
+ *    load group
+ *    find blocks
+ *    mark bits in on-disk bitmap
+ *    release group
+ *
+ *  - use preallocation:
+ *    find proper PA (per-inode or group)
+ *    load group
+ *    mark bits in on-disk bitmap
+ *    release group
+ *    release PA
+ *
+ *  - free:
+ *    load group
+ *    mark bits in on-disk bitmap
+ *    release group
+ *
+ *  - discard preallocations in group:
+ *    mark PAs deleted
+ *    move them onto local list
+ *    load on-disk bitmap
+ *    load group
+ *    remove PA from object (inode or locality group)
+ *    mark free blocks in-core
+ *
+ *  - discard inode's preallocations:
+ */
+
+/*
+ * Locking rules
+ *
+ * Locks:
+ *  - bitlock on a group	(group)
+ *  - object (inode/locality)	(object)
+ *  - per-pa lock		(pa)
+ *
+ * Paths:
+ *  - new pa
+ *    object
+ *    group
+ *
+ *  - find and use pa:
+ *    pa
+ *
+ *  - release consumed pa:
+ *    pa
+ *    group
+ *    object
+ *
+ *  - generate in-core bitmap:
+ *    group
+ *        pa
+ *
+ *  - discard all for given object (inode, locality group):
+ *    object
+ *        pa
+ *    group
+ *
+ *  - discard all for given group:
+ *    group
+ *        pa
+ *    group
+ *        object
+ *
+ */
+static struct kmem_cache *ext4_pspace_cachep;
+static struct kmem_cache *ext4_ac_cachep;
+static struct kmem_cache *ext4_free_ext_cachep;
+
+/* We create slab caches for groupinfo data structures based on the
+ * superblock block size.  There will be one per mounted filesystem for
+ * each unique s_blocksize_bits */
+#define NR_GRPINFO_CACHES 8
+static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
+
+static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
+	"ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k",
+	"ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k",
+	"ext4_groupinfo_64k", "ext4_groupinfo_128k"
+};
+
+static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+					ext4_group_t group);
+static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+						ext4_group_t group);
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
+
+static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
+{
+#if BITS_PER_LONG == 64
+	*bit += ((unsigned long) addr & 7UL) << 3;
+	addr = (void *) ((unsigned long) addr & ~7UL);
+#elif BITS_PER_LONG == 32
+	*bit += ((unsigned long) addr & 3UL) << 3;
+	addr = (void *) ((unsigned long) addr & ~3UL);
+#else
+#error "how many bits you are?!"
+#endif
+	return addr;
+}
+
+static inline int mb_test_bit(int bit, void *addr)
+{
+	/*
+	 * ext4_test_bit on architecture like powerpc
+	 * needs unsigned long aligned address
+	 */
+	addr = mb_correct_addr_and_bit(&bit, addr);
+	return ext4_test_bit(bit, addr);
+}
+
+static inline void mb_set_bit(int bit, void *addr)
+{
+	addr = mb_correct_addr_and_bit(&bit, addr);
+	ext4_set_bit(bit, addr);
+}
+
+static inline void mb_clear_bit(int bit, void *addr)
+{
+	addr = mb_correct_addr_and_bit(&bit, addr);
+	ext4_clear_bit(bit, addr);
+}
+
+static inline int mb_find_next_zero_bit(void *addr, int max, int start)
+{
+	int fix = 0, ret, tmpmax;
+	addr = mb_correct_addr_and_bit(&fix, addr);
+	tmpmax = max + fix;
+	start += fix;
+
+	ret = ext4_find_next_zero_bit(addr, tmpmax, start) - fix;
+	if (ret > max)
+		return max;
+	return ret;
+}
+
+static inline int mb_find_next_bit(void *addr, int max, int start)
+{
+	int fix = 0, ret, tmpmax;
+	addr = mb_correct_addr_and_bit(&fix, addr);
+	tmpmax = max + fix;
+	start += fix;
+
+	ret = ext4_find_next_bit(addr, tmpmax, start) - fix;
+	if (ret > max)
+		return max;
+	return ret;
+}
+
+static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
+{
+	char *bb;
+
+	BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
+	BUG_ON(max == NULL);
+
+	if (order > e4b->bd_blkbits + 1) {
+		*max = 0;
+		return NULL;
+	}
+
+	/* at order 0 we see each particular block */
+	if (order == 0) {
+		*max = 1 << (e4b->bd_blkbits + 3);
+		return EXT4_MB_BITMAP(e4b);
+	}
+
+	bb = EXT4_MB_BUDDY(e4b) + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order];
+	*max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order];
+
+	return bb;
+}
+
+#ifdef DOUBLE_CHECK
+static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
+			   int first, int count)
+{
+	int i;
+	struct super_block *sb = e4b->bd_sb;
+
+	if (unlikely(e4b->bd_info->bb_bitmap == NULL))
+		return;
+	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
+	for (i = 0; i < count; i++) {
+		if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) {
+			ext4_fsblk_t blocknr;
+
+			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
+			blocknr += first + i;
+			ext4_grp_locked_error(sb, e4b->bd_group,
+					      inode ? inode->i_ino : 0,
+					      blocknr,
+					      "freeing block already freed "
+					      "(bit %u)",
+					      first + i);
+		}
+		mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
+	}
+}
+
+static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count)
+{
+	int i;
+
+	if (unlikely(e4b->bd_info->bb_bitmap == NULL))
+		return;
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
+	for (i = 0; i < count; i++) {
+		BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap));
+		mb_set_bit(first + i, e4b->bd_info->bb_bitmap);
+	}
+}
+
+static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap)
+{
+	if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) {
+		unsigned char *b1, *b2;
+		int i;
+		b1 = (unsigned char *) e4b->bd_info->bb_bitmap;
+		b2 = (unsigned char *) bitmap;
+		for (i = 0; i < e4b->bd_sb->s_blocksize; i++) {
+			if (b1[i] != b2[i]) {
+				printk(KERN_ERR "corruption in group %u "
+				       "at byte %u(%u): %x in copy != %x "
+				       "on disk/prealloc\n",
+				       e4b->bd_group, i, i * 8, b1[i], b2[i]);
+				BUG();
+			}
+		}
+	}
+}
+
+#else
+static inline void mb_free_blocks_double(struct inode *inode,
+				struct ext4_buddy *e4b, int first, int count)
+{
+	return;
+}
+static inline void mb_mark_used_double(struct ext4_buddy *e4b,
+						int first, int count)
+{
+	return;
+}
+static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap)
+{
+	return;
+}
+#endif
+
+#ifdef AGGRESSIVE_CHECK
+
+#define MB_CHECK_ASSERT(assert)						\
+do {									\
+	if (!(assert)) {						\
+		printk(KERN_EMERG					\
+			"Assertion failure in %s() at %s:%d: \"%s\"\n",	\
+			function, file, line, # assert);		\
+		BUG();							\
+	}								\
+} while (0)
+
+static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
+				const char *function, int line)
+{
+	struct super_block *sb = e4b->bd_sb;
+	int order = e4b->bd_blkbits + 1;
+	int max;
+	int max2;
+	int i;
+	int j;
+	int k;
+	int count;
+	struct ext4_group_info *grp;
+	int fragments = 0;
+	int fstart;
+	struct list_head *cur;
+	void *buddy;
+	void *buddy2;
+
+	{
+		static int mb_check_counter;
+		if (mb_check_counter++ % 100 != 0)
+			return 0;
+	}
+
+	while (order > 1) {
+		buddy = mb_find_buddy(e4b, order, &max);
+		MB_CHECK_ASSERT(buddy);
+		buddy2 = mb_find_buddy(e4b, order - 1, &max2);
+		MB_CHECK_ASSERT(buddy2);
+		MB_CHECK_ASSERT(buddy != buddy2);
+		MB_CHECK_ASSERT(max * 2 == max2);
+
+		count = 0;
+		for (i = 0; i < max; i++) {
+
+			if (mb_test_bit(i, buddy)) {
+				/* only single bit in buddy2 may be 1 */
+				if (!mb_test_bit(i << 1, buddy2)) {
+					MB_CHECK_ASSERT(
+						mb_test_bit((i<<1)+1, buddy2));
+				} else if (!mb_test_bit((i << 1) + 1, buddy2)) {
+					MB_CHECK_ASSERT(
+						mb_test_bit(i << 1, buddy2));
+				}
+				continue;
+			}
+
+			/* both bits in buddy2 must be 0 */
+			MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2));
+			MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2));
+
+			for (j = 0; j < (1 << order); j++) {
+				k = (i * (1 << order)) + j;
+				MB_CHECK_ASSERT(
+					!mb_test_bit(k, EXT4_MB_BITMAP(e4b)));
+			}
+			count++;
+		}
+		MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count);
+		order--;
+	}
+
+	fstart = -1;
+	buddy = mb_find_buddy(e4b, 0, &max);
+	for (i = 0; i < max; i++) {
+		if (!mb_test_bit(i, buddy)) {
+			MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free);
+			if (fstart == -1) {
+				fragments++;
+				fstart = i;
+			}
+			continue;
+		}
+		fstart = -1;
+		/* check used bits only */
+		for (j = 0; j < e4b->bd_blkbits + 1; j++) {
+			buddy2 = mb_find_buddy(e4b, j, &max2);
+			k = i >> j;
+			MB_CHECK_ASSERT(k < max2);
+			MB_CHECK_ASSERT(mb_test_bit(k, buddy2));
+		}
+	}
+	MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info));
+	MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments);
+
+	grp = ext4_get_group_info(sb, e4b->bd_group);
+	list_for_each(cur, &grp->bb_prealloc_list) {
+		ext4_group_t groupnr;
+		struct ext4_prealloc_space *pa;
+		pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list);
+		ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k);
+		MB_CHECK_ASSERT(groupnr == e4b->bd_group);
+		for (i = 0; i < pa->pa_len; i++)
+			MB_CHECK_ASSERT(mb_test_bit(k + i, buddy));
+	}
+	return 0;
+}
+#undef MB_CHECK_ASSERT
+#define mb_check_buddy(e4b) __mb_check_buddy(e4b,	\
+					__FILE__, __func__, __LINE__)
+#else
+#define mb_check_buddy(e4b)
+#endif
+
+/*
+ * Divide blocks started from @first with length @len into
+ * smaller chunks with power of 2 blocks.
+ * Clear the bits in bitmap which the blocks of the chunk(s) covered,
+ * then increase bb_counters[] for corresponded chunk size.
+ */
+static void ext4_mb_mark_free_simple(struct super_block *sb,
+				void *buddy, ext4_grpblk_t first, ext4_grpblk_t len,
+					struct ext4_group_info *grp)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_grpblk_t min;
+	ext4_grpblk_t max;
+	ext4_grpblk_t chunk;
+	unsigned short border;
+
+	BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb));
+
+	border = 2 << sb->s_blocksize_bits;
+
+	while (len > 0) {
+		/* find how many blocks can be covered since this position */
+		max = ffs(first | border) - 1;
+
+		/* find how many blocks of power 2 we need to mark */
+		min = fls(len) - 1;
+
+		if (max < min)
+			min = max;
+		chunk = 1 << min;
+
+		/* mark multiblock chunks only */
+		grp->bb_counters[min]++;
+		if (min > 0)
+			mb_clear_bit(first >> min,
+				     buddy + sbi->s_mb_offsets[min]);
+
+		len -= chunk;
+		first += chunk;
+	}
+}
+
+/*
+ * Cache the order of the largest free extent we have available in this block
+ * group.
+ */
+static void
+mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
+{
+	int i;
+	int bits;
+
+	grp->bb_largest_free_order = -1; /* uninit */
+
+	bits = sb->s_blocksize_bits + 1;
+	for (i = bits; i >= 0; i--) {
+		if (grp->bb_counters[i] > 0) {
+			grp->bb_largest_free_order = i;
+			break;
+		}
+	}
+}
+
+static noinline_for_stack
+void ext4_mb_generate_buddy(struct super_block *sb,
+				void *buddy, void *bitmap, ext4_group_t group)
+{
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb);
+	ext4_grpblk_t i = 0;
+	ext4_grpblk_t first;
+	ext4_grpblk_t len;
+	unsigned free = 0;
+	unsigned fragments = 0;
+	unsigned long long period = get_cycles();
+
+	/* initialize buddy from bitmap which is aggregation
+	 * of on-disk bitmap and preallocations */
+	i = mb_find_next_zero_bit(bitmap, max, 0);
+	grp->bb_first_free = i;
+	while (i < max) {
+		fragments++;
+		first = i;
+		i = mb_find_next_bit(bitmap, max, i);
+		len = i - first;
+		free += len;
+		if (len > 1)
+			ext4_mb_mark_free_simple(sb, buddy, first, len, grp);
+		else
+			grp->bb_counters[0]++;
+		if (i < max)
+			i = mb_find_next_zero_bit(bitmap, max, i);
+	}
+	grp->bb_fragments = fragments;
+
+	if (free != grp->bb_free) {
+		ext4_grp_locked_error(sb, group, 0, 0,
+				      "%u blocks in bitmap, %u in gd",
+				      free, grp->bb_free);
+		/*
+		 * If we intent to continue, we consider group descritor
+		 * corrupt and update bb_free using bitmap value
+		 */
+		grp->bb_free = free;
+	}
+	mb_set_largest_free_order(sb, grp);
+
+	clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
+
+	period = get_cycles() - period;
+	spin_lock(&EXT4_SB(sb)->s_bal_lock);
+	EXT4_SB(sb)->s_mb_buddies_generated++;
+	EXT4_SB(sb)->s_mb_generation_time += period;
+	spin_unlock(&EXT4_SB(sb)->s_bal_lock);
+}
+
+/* The buddy information is attached the buddy cache inode
+ * for convenience. The information regarding each group
+ * is loaded via ext4_mb_load_buddy. The information involve
+ * block bitmap and buddy information. The information are
+ * stored in the inode as
+ *
+ * {                        page                        }
+ * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]...
+ *
+ *
+ * one block each for bitmap and buddy information.
+ * So for each group we take up 2 blocks. A page can
+ * contain blocks_per_page (PAGE_CACHE_SIZE / blocksize)  blocks.
+ * So it can have information regarding groups_per_page which
+ * is blocks_per_page/2
+ *
+ * Locking note:  This routine takes the block group lock of all groups
+ * for this page; do not hold this lock when calling this routine!
+ */
+
+static int ext4_mb_init_cache(struct page *page, char *incore)
+{
+	ext4_group_t ngroups;
+	int blocksize;
+	int blocks_per_page;
+	int groups_per_page;
+	int err = 0;
+	int i;
+	ext4_group_t first_group;
+	int first_block;
+	struct super_block *sb;
+	struct buffer_head *bhs;
+	struct buffer_head **bh;
+	struct inode *inode;
+	char *data;
+	char *bitmap;
+	struct ext4_group_info *grinfo;
+
+	mb_debug(1, "init page %lu\n", page->index);
+
+	inode = page->mapping->host;
+	sb = inode->i_sb;
+	ngroups = ext4_get_groups_count(sb);
+	blocksize = 1 << inode->i_blkbits;
+	blocks_per_page = PAGE_CACHE_SIZE / blocksize;
+
+	groups_per_page = blocks_per_page >> 1;
+	if (groups_per_page == 0)
+		groups_per_page = 1;
+
+	/* allocate buffer_heads to read bitmaps */
+	if (groups_per_page > 1) {
+		err = -ENOMEM;
+		i = sizeof(struct buffer_head *) * groups_per_page;
+		bh = kzalloc(i, GFP_NOFS);
+		if (bh == NULL)
+			goto out;
+	} else
+		bh = &bhs;
+
+	first_group = page->index * blocks_per_page / 2;
+
+	/* read all groups the page covers into the cache */
+	for (i = 0; i < groups_per_page; i++) {
+		struct ext4_group_desc *desc;
+
+		if (first_group + i >= ngroups)
+			break;
+
+		grinfo = ext4_get_group_info(sb, first_group + i);
+		/*
+		 * If page is uptodate then we came here after online resize
+		 * which added some new uninitialized group info structs, so
+		 * we must skip all initialized uptodate buddies on the page,
+		 * which may be currently in use by an allocating task.
+		 */
+		if (PageUptodate(page) && !EXT4_MB_GRP_NEED_INIT(grinfo)) {
+			bh[i] = NULL;
+			continue;
+		}
+
+		err = -EIO;
+		desc = ext4_get_group_desc(sb, first_group + i, NULL);
+		if (desc == NULL)
+			goto out;
+
+		err = -ENOMEM;
+		bh[i] = sb_getblk(sb, ext4_block_bitmap(sb, desc));
+		if (bh[i] == NULL)
+			goto out;
+
+		if (bitmap_uptodate(bh[i]))
+			continue;
+
+		lock_buffer(bh[i]);
+		if (bitmap_uptodate(bh[i])) {
+			unlock_buffer(bh[i]);
+			continue;
+		}
+		ext4_lock_group(sb, first_group + i);
+		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+			ext4_init_block_bitmap(sb, bh[i],
+						first_group + i, desc);
+			set_bitmap_uptodate(bh[i]);
+			set_buffer_uptodate(bh[i]);
+			ext4_unlock_group(sb, first_group + i);
+			unlock_buffer(bh[i]);
+			continue;
+		}
+		ext4_unlock_group(sb, first_group + i);
+		if (buffer_uptodate(bh[i])) {
+			/*
+			 * if not uninit if bh is uptodate,
+			 * bitmap is also uptodate
+			 */
+			set_bitmap_uptodate(bh[i]);
+			unlock_buffer(bh[i]);
+			continue;
+		}
+		get_bh(bh[i]);
+		/*
+		 * submit the buffer_head for read. We can
+		 * safely mark the bitmap as uptodate now.
+		 * We do it here so the bitmap uptodate bit
+		 * get set with buffer lock held.
+		 */
+		set_bitmap_uptodate(bh[i]);
+		bh[i]->b_end_io = end_buffer_read_sync;
+		submit_bh(READ, bh[i]);
+		mb_debug(1, "read bitmap for group %u\n", first_group + i);
+	}
+
+	/* wait for I/O completion */
+	for (i = 0; i < groups_per_page; i++)
+		if (bh[i])
+			wait_on_buffer(bh[i]);
+
+	err = -EIO;
+	for (i = 0; i < groups_per_page; i++)
+		if (bh[i] && !buffer_uptodate(bh[i]))
+			goto out;
+
+	err = 0;
+	first_block = page->index * blocks_per_page;
+	for (i = 0; i < blocks_per_page; i++) {
+		int group;
+
+		group = (first_block + i) >> 1;
+		if (group >= ngroups)
+			break;
+
+		if (!bh[group - first_group])
+			/* skip initialized uptodate buddy */
+			continue;
+
+		/*
+		 * data carry information regarding this
+		 * particular group in the format specified
+		 * above
+		 *
+		 */
+		data = page_address(page) + (i * blocksize);
+		bitmap = bh[group - first_group]->b_data;
+
+		/*
+		 * We place the buddy block and bitmap block
+		 * close together
+		 */
+		if ((first_block + i) & 1) {
+			/* this is block of buddy */
+			BUG_ON(incore == NULL);
+			mb_debug(1, "put buddy for group %u in page %lu/%x\n",
+				group, page->index, i * blocksize);
+			trace_ext4_mb_buddy_bitmap_load(sb, group);
+			grinfo = ext4_get_group_info(sb, group);
+			grinfo->bb_fragments = 0;
+			memset(grinfo->bb_counters, 0,
+			       sizeof(*grinfo->bb_counters) *
+				(sb->s_blocksize_bits+2));
+			/*
+			 * incore got set to the group block bitmap below
+			 */
+			ext4_lock_group(sb, group);
+			/* init the buddy */
+			memset(data, 0xff, blocksize);
+			ext4_mb_generate_buddy(sb, data, incore, group);
+			ext4_unlock_group(sb, group);
+			incore = NULL;
+		} else {
+			/* this is block of bitmap */
+			BUG_ON(incore != NULL);
+			mb_debug(1, "put bitmap for group %u in page %lu/%x\n",
+				group, page->index, i * blocksize);
+			trace_ext4_mb_bitmap_load(sb, group);
+
+			/* see comments in ext4_mb_put_pa() */
+			ext4_lock_group(sb, group);
+			memcpy(data, bitmap, blocksize);
+
+			/* mark all preallocated blks used in in-core bitmap */
+			ext4_mb_generate_from_pa(sb, data, group);
+			ext4_mb_generate_from_freelist(sb, data, group);
+			ext4_unlock_group(sb, group);
+
+			/* set incore so that the buddy information can be
+			 * generated using this
+			 */
+			incore = data;
+		}
+	}
+	SetPageUptodate(page);
+
+out:
+	if (bh) {
+		for (i = 0; i < groups_per_page; i++)
+			brelse(bh[i]);
+		if (bh != &bhs)
+			kfree(bh);
+	}
+	return err;
+}
+
+/*
+ * Lock the buddy and bitmap pages. This make sure other parallel init_group
+ * on the same buddy page doesn't happen whild holding the buddy page lock.
+ * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap
+ * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
+ */
+static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
+		ext4_group_t group, struct ext4_buddy *e4b)
+{
+	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
+	int block, pnum, poff;
+	int blocks_per_page;
+	struct page *page;
+
+	e4b->bd_buddy_page = NULL;
+	e4b->bd_bitmap_page = NULL;
+
+	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+	/*
+	 * the buddy cache inode stores the block bitmap
+	 * and buddy information in consecutive blocks.
+	 * So for each group we need two blocks.
+	 */
+	block = group * 2;
+	pnum = block / blocks_per_page;
+	poff = block % blocks_per_page;
+	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	if (!page)
+		return -EIO;
+	BUG_ON(page->mapping != inode->i_mapping);
+	e4b->bd_bitmap_page = page;
+	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
+
+	if (blocks_per_page >= 2) {
+		/* buddy and bitmap are on the same page */
+		return 0;
+	}
+
+	block++;
+	pnum = block / blocks_per_page;
+	poff = block % blocks_per_page;
+	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	if (!page)
+		return -EIO;
+	BUG_ON(page->mapping != inode->i_mapping);
+	e4b->bd_buddy_page = page;
+	return 0;
+}
+
+static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
+{
+	if (e4b->bd_bitmap_page) {
+		unlock_page(e4b->bd_bitmap_page);
+		page_cache_release(e4b->bd_bitmap_page);
+	}
+	if (e4b->bd_buddy_page) {
+		unlock_page(e4b->bd_buddy_page);
+		page_cache_release(e4b->bd_buddy_page);
+	}
+}
+
+/*
+ * Locking note:  This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
+static noinline_for_stack
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+{
+
+	struct ext4_group_info *this_grp;
+	struct ext4_buddy e4b;
+	struct page *page;
+	int ret = 0;
+
+	mb_debug(1, "init group %u\n", group);
+	this_grp = ext4_get_group_info(sb, group);
+	/*
+	 * This ensures that we don't reinit the buddy cache
+	 * page which map to the group from which we are already
+	 * allocating. If we are looking at the buddy cache we would
+	 * have taken a reference using ext4_mb_load_buddy and that
+	 * would have pinned buddy page to page cache.
+	 */
+	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
+		/*
+		 * somebody initialized the group
+		 * return without doing anything
+		 */
+		goto err;
+	}
+
+	page = e4b.bd_bitmap_page;
+	ret = ext4_mb_init_cache(page, NULL);
+	if (ret)
+		goto err;
+	if (!PageUptodate(page)) {
+		ret = -EIO;
+		goto err;
+	}
+	mark_page_accessed(page);
+
+	if (e4b.bd_buddy_page == NULL) {
+		/*
+		 * If both the bitmap and buddy are in
+		 * the same page we don't need to force
+		 * init the buddy
+		 */
+		ret = 0;
+		goto err;
+	}
+	/* init buddy cache */
+	page = e4b.bd_buddy_page;
+	ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+	if (ret)
+		goto err;
+	if (!PageUptodate(page)) {
+		ret = -EIO;
+		goto err;
+	}
+	mark_page_accessed(page);
+err:
+	ext4_mb_put_buddy_page_lock(&e4b);
+	return ret;
+}
+
+/*
+ * Locking note:  This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
+static noinline_for_stack int
+ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
+					struct ext4_buddy *e4b)
+{
+	int blocks_per_page;
+	int block;
+	int pnum;
+	int poff;
+	struct page *page;
+	int ret;
+	struct ext4_group_info *grp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct inode *inode = sbi->s_buddy_cache;
+
+	mb_debug(1, "load group %u\n", group);
+
+	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+	grp = ext4_get_group_info(sb, group);
+
+	e4b->bd_blkbits = sb->s_blocksize_bits;
+	e4b->bd_info = ext4_get_group_info(sb, group);
+	e4b->bd_sb = sb;
+	e4b->bd_group = group;
+	e4b->bd_buddy_page = NULL;
+	e4b->bd_bitmap_page = NULL;
+
+	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+		/*
+		 * we need full data about the group
+		 * to make a good selection
+		 */
+		ret = ext4_mb_init_group(sb, group);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * the buddy cache inode stores the block bitmap
+	 * and buddy information in consecutive blocks.
+	 * So for each group we need two blocks.
+	 */
+	block = group * 2;
+	pnum = block / blocks_per_page;
+	poff = block % blocks_per_page;
+
+	/* we could use find_or_create_page(), but it locks page
+	 * what we'd like to avoid in fast path ... */
+	page = find_get_page(inode->i_mapping, pnum);
+	if (page == NULL || !PageUptodate(page)) {
+		if (page)
+			/*
+			 * drop the page reference and try
+			 * to get the page with lock. If we
+			 * are not uptodate that implies
+			 * somebody just created the page but
+			 * is yet to initialize the same. So
+			 * wait for it to initialize.
+			 */
+			page_cache_release(page);
+		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+		if (page) {
+			BUG_ON(page->mapping != inode->i_mapping);
+			if (!PageUptodate(page)) {
+				ret = ext4_mb_init_cache(page, NULL);
+				if (ret) {
+					unlock_page(page);
+					goto err;
+				}
+				mb_cmp_bitmaps(e4b, page_address(page) +
+					       (poff * sb->s_blocksize));
+			}
+			unlock_page(page);
+		}
+	}
+	if (page == NULL || !PageUptodate(page)) {
+		ret = -EIO;
+		goto err;
+	}
+	e4b->bd_bitmap_page = page;
+	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
+	mark_page_accessed(page);
+
+	block++;
+	pnum = block / blocks_per_page;
+	poff = block % blocks_per_page;
+
+	page = find_get_page(inode->i_mapping, pnum);
+	if (page == NULL || !PageUptodate(page)) {
+		if (page)
+			page_cache_release(page);
+		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+		if (page) {
+			BUG_ON(page->mapping != inode->i_mapping);
+			if (!PageUptodate(page)) {
+				ret = ext4_mb_init_cache(page, e4b->bd_bitmap);
+				if (ret) {
+					unlock_page(page);
+					goto err;
+				}
+			}
+			unlock_page(page);
+		}
+	}
+	if (page == NULL || !PageUptodate(page)) {
+		ret = -EIO;
+		goto err;
+	}
+	e4b->bd_buddy_page = page;
+	e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
+	mark_page_accessed(page);
+
+	BUG_ON(e4b->bd_bitmap_page == NULL);
+	BUG_ON(e4b->bd_buddy_page == NULL);
+
+	return 0;
+
+err:
+	if (page)
+		page_cache_release(page);
+	if (e4b->bd_bitmap_page)
+		page_cache_release(e4b->bd_bitmap_page);
+	if (e4b->bd_buddy_page)
+		page_cache_release(e4b->bd_buddy_page);
+	e4b->bd_buddy = NULL;
+	e4b->bd_bitmap = NULL;
+	return ret;
+}
+
+static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
+{
+	if (e4b->bd_bitmap_page)
+		page_cache_release(e4b->bd_bitmap_page);
+	if (e4b->bd_buddy_page)
+		page_cache_release(e4b->bd_buddy_page);
+}
+
+
+static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
+{
+	int order = 1;
+	void *bb;
+
+	BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
+	BUG_ON(block >= (1 << (e4b->bd_blkbits + 3)));
+
+	bb = EXT4_MB_BUDDY(e4b);
+	while (order <= e4b->bd_blkbits + 1) {
+		block = block >> 1;
+		if (!mb_test_bit(block, bb)) {
+			/* this block is part of buddy of order 'order' */
+			return order;
+		}
+		bb += 1 << (e4b->bd_blkbits - order);
+		order++;
+	}
+	return 0;
+}
+
+static void mb_clear_bits(void *bm, int cur, int len)
+{
+	__u32 *addr;
+
+	len = cur + len;
+	while (cur < len) {
+		if ((cur & 31) == 0 && (len - cur) >= 32) {
+			/* fast path: clear whole word at once */
+			addr = bm + (cur >> 3);
+			*addr = 0;
+			cur += 32;
+			continue;
+		}
+		mb_clear_bit(cur, bm);
+		cur++;
+	}
+}
+
+static void mb_set_bits(void *bm, int cur, int len)
+{
+	__u32 *addr;
+
+	len = cur + len;
+	while (cur < len) {
+		if ((cur & 31) == 0 && (len - cur) >= 32) {
+			/* fast path: set whole word at once */
+			addr = bm + (cur >> 3);
+			*addr = 0xffffffff;
+			cur += 32;
+			continue;
+		}
+		mb_set_bit(cur, bm);
+		cur++;
+	}
+}
+
+static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
+			  int first, int count)
+{
+	int block = 0;
+	int max = 0;
+	int order;
+	void *buddy;
+	void *buddy2;
+	struct super_block *sb = e4b->bd_sb;
+
+	BUG_ON(first + count > (sb->s_blocksize << 3));
+	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
+	mb_check_buddy(e4b);
+	mb_free_blocks_double(inode, e4b, first, count);
+
+	e4b->bd_info->bb_free += count;
+	if (first < e4b->bd_info->bb_first_free)
+		e4b->bd_info->bb_first_free = first;
+
+	/* let's maintain fragments counter */
+	if (first != 0)
+		block = !mb_test_bit(first - 1, EXT4_MB_BITMAP(e4b));
+	if (first + count < EXT4_SB(sb)->s_mb_maxs[0])
+		max = !mb_test_bit(first + count, EXT4_MB_BITMAP(e4b));
+	if (block && max)
+		e4b->bd_info->bb_fragments--;
+	else if (!block && !max)
+		e4b->bd_info->bb_fragments++;
+
+	/* let's maintain buddy itself */
+	while (count-- > 0) {
+		block = first++;
+		order = 0;
+
+		if (!mb_test_bit(block, EXT4_MB_BITMAP(e4b))) {
+			ext4_fsblk_t blocknr;
+
+			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
+			blocknr += block;
+			ext4_grp_locked_error(sb, e4b->bd_group,
+					      inode ? inode->i_ino : 0,
+					      blocknr,
+					      "freeing already freed block "
+					      "(bit %u)", block);
+		}
+		mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
+		e4b->bd_info->bb_counters[order]++;
+
+		/* start of the buddy */
+		buddy = mb_find_buddy(e4b, order, &max);
+
+		do {
+			block &= ~1UL;
+			if (mb_test_bit(block, buddy) ||
+					mb_test_bit(block + 1, buddy))
+				break;
+
+			/* both the buddies are free, try to coalesce them */
+			buddy2 = mb_find_buddy(e4b, order + 1, &max);
+
+			if (!buddy2)
+				break;
+
+			if (order > 0) {
+				/* for special purposes, we don't set
+				 * free bits in bitmap */
+				mb_set_bit(block, buddy);
+				mb_set_bit(block + 1, buddy);
+			}
+			e4b->bd_info->bb_counters[order]--;
+			e4b->bd_info->bb_counters[order]--;
+
+			block = block >> 1;
+			order++;
+			e4b->bd_info->bb_counters[order]++;
+
+			mb_clear_bit(block, buddy2);
+			buddy = buddy2;
+		} while (1);
+	}
+	mb_set_largest_free_order(sb, e4b->bd_info);
+	mb_check_buddy(e4b);
+}
+
+static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
+				int needed, struct ext4_free_extent *ex)
+{
+	int next = block;
+	int max;
+	int ord;
+	void *buddy;
+
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
+	BUG_ON(ex == NULL);
+
+	buddy = mb_find_buddy(e4b, order, &max);
+	BUG_ON(buddy == NULL);
+	BUG_ON(block >= max);
+	if (mb_test_bit(block, buddy)) {
+		ex->fe_len = 0;
+		ex->fe_start = 0;
+		ex->fe_group = 0;
+		return 0;
+	}
+
+	/* FIXME dorp order completely ? */
+	if (likely(order == 0)) {
+		/* find actual order */
+		order = mb_find_order_for_block(e4b, block);
+		block = block >> order;
+	}
+
+	ex->fe_len = 1 << order;
+	ex->fe_start = block << order;
+	ex->fe_group = e4b->bd_group;
+
+	/* calc difference from given start */
+	next = next - ex->fe_start;
+	ex->fe_len -= next;
+	ex->fe_start += next;
+
+	while (needed > ex->fe_len &&
+	       (buddy = mb_find_buddy(e4b, order, &max))) {
+
+		if (block + 1 >= max)
+			break;
+
+		next = (block + 1) * (1 << order);
+		if (mb_test_bit(next, EXT4_MB_BITMAP(e4b)))
+			break;
+
+		ord = mb_find_order_for_block(e4b, next);
+
+		order = ord;
+		block = next >> order;
+		ex->fe_len += 1 << order;
+	}
+
+	BUG_ON(ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3)));
+	return ex->fe_len;
+}
+
+static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
+{
+	int ord;
+	int mlen = 0;
+	int max = 0;
+	int cur;
+	int start = ex->fe_start;
+	int len = ex->fe_len;
+	unsigned ret = 0;
+	int len0 = len;
+	void *buddy;
+
+	BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3));
+	BUG_ON(e4b->bd_group != ex->fe_group);
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
+	mb_check_buddy(e4b);
+	mb_mark_used_double(e4b, start, len);
+
+	e4b->bd_info->bb_free -= len;
+	if (e4b->bd_info->bb_first_free == start)
+		e4b->bd_info->bb_first_free += len;
+
+	/* let's maintain fragments counter */
+	if (start != 0)
+		mlen = !mb_test_bit(start - 1, EXT4_MB_BITMAP(e4b));
+	if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0])
+		max = !mb_test_bit(start + len, EXT4_MB_BITMAP(e4b));
+	if (mlen && max)
+		e4b->bd_info->bb_fragments++;
+	else if (!mlen && !max)
+		e4b->bd_info->bb_fragments--;
+
+	/* let's maintain buddy itself */
+	while (len) {
+		ord = mb_find_order_for_block(e4b, start);
+
+		if (((start >> ord) << ord) == start && len >= (1 << ord)) {
+			/* the whole chunk may be allocated at once! */
+			mlen = 1 << ord;
+			buddy = mb_find_buddy(e4b, ord, &max);
+			BUG_ON((start >> ord) >= max);
+			mb_set_bit(start >> ord, buddy);
+			e4b->bd_info->bb_counters[ord]--;
+			start += mlen;
+			len -= mlen;
+			BUG_ON(len < 0);
+			continue;
+		}
+
+		/* store for history */
+		if (ret == 0)
+			ret = len | (ord << 16);
+
+		/* we have to split large buddy */
+		BUG_ON(ord <= 0);
+		buddy = mb_find_buddy(e4b, ord, &max);
+		mb_set_bit(start >> ord, buddy);
+		e4b->bd_info->bb_counters[ord]--;
+
+		ord--;
+		cur = (start >> ord) & ~1U;
+		buddy = mb_find_buddy(e4b, ord, &max);
+		mb_clear_bit(cur, buddy);
+		mb_clear_bit(cur + 1, buddy);
+		e4b->bd_info->bb_counters[ord]++;
+		e4b->bd_info->bb_counters[ord]++;
+	}
+	mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
+
+	mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+	mb_check_buddy(e4b);
+
+	return ret;
+}
+
+/*
+ * Must be called under group lock!
+ */
+static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
+					struct ext4_buddy *e4b)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	int ret;
+
+	BUG_ON(ac->ac_b_ex.fe_group != e4b->bd_group);
+	BUG_ON(ac->ac_status == AC_STATUS_FOUND);
+
+	ac->ac_b_ex.fe_len = min(ac->ac_b_ex.fe_len, ac->ac_g_ex.fe_len);
+	ac->ac_b_ex.fe_logical = ac->ac_g_ex.fe_logical;
+	ret = mb_mark_used(e4b, &ac->ac_b_ex);
+
+	/* preallocation can change ac_b_ex, thus we store actually
+	 * allocated blocks for history */
+	ac->ac_f_ex = ac->ac_b_ex;
+
+	ac->ac_status = AC_STATUS_FOUND;
+	ac->ac_tail = ret & 0xffff;
+	ac->ac_buddy = ret >> 16;
+
+	/*
+	 * take the page reference. We want the page to be pinned
+	 * so that we don't get a ext4_mb_init_cache_call for this
+	 * group until we update the bitmap. That would mean we
+	 * double allocate blocks. The reference is dropped
+	 * in ext4_mb_release_context
+	 */
+	ac->ac_bitmap_page = e4b->bd_bitmap_page;
+	get_page(ac->ac_bitmap_page);
+	ac->ac_buddy_page = e4b->bd_buddy_page;
+	get_page(ac->ac_buddy_page);
+	/* store last allocated for subsequent stream allocation */
+	if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
+		spin_lock(&sbi->s_md_lock);
+		sbi->s_mb_last_group = ac->ac_f_ex.fe_group;
+		sbi->s_mb_last_start = ac->ac_f_ex.fe_start;
+		spin_unlock(&sbi->s_md_lock);
+	}
+}
+
+/*
+ * regular allocator, for general purposes allocation
+ */
+
+static void ext4_mb_check_limits(struct ext4_allocation_context *ac,
+					struct ext4_buddy *e4b,
+					int finish_group)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_free_extent *bex = &ac->ac_b_ex;
+	struct ext4_free_extent *gex = &ac->ac_g_ex;
+	struct ext4_free_extent ex;
+	int max;
+
+	if (ac->ac_status == AC_STATUS_FOUND)
+		return;
+	/*
+	 * We don't want to scan for a whole year
+	 */
+	if (ac->ac_found > sbi->s_mb_max_to_scan &&
+			!(ac->ac_flags & EXT4_MB_HINT_FIRST)) {
+		ac->ac_status = AC_STATUS_BREAK;
+		return;
+	}
+
+	/*
+	 * Haven't found good chunk so far, let's continue
+	 */
+	if (bex->fe_len < gex->fe_len)
+		return;
+
+	if ((finish_group || ac->ac_found > sbi->s_mb_min_to_scan)
+			&& bex->fe_group == e4b->bd_group) {
+		/* recheck chunk's availability - we don't know
+		 * when it was found (within this lock-unlock
+		 * period or not) */
+		max = mb_find_extent(e4b, 0, bex->fe_start, gex->fe_len, &ex);
+		if (max >= gex->fe_len) {
+			ext4_mb_use_best_found(ac, e4b);
+			return;
+		}
+	}
+}
+
+/*
+ * The routine checks whether found extent is good enough. If it is,
+ * then the extent gets marked used and flag is set to the context
+ * to stop scanning. Otherwise, the extent is compared with the
+ * previous found extent and if new one is better, then it's stored
+ * in the context. Later, the best found extent will be used, if
+ * mballoc can't find good enough extent.
+ *
+ * FIXME: real allocation policy is to be designed yet!
+ */
+static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
+					struct ext4_free_extent *ex,
+					struct ext4_buddy *e4b)
+{
+	struct ext4_free_extent *bex = &ac->ac_b_ex;
+	struct ext4_free_extent *gex = &ac->ac_g_ex;
+
+	BUG_ON(ex->fe_len <= 0);
+	BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+	BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+	BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
+
+	ac->ac_found++;
+
+	/*
+	 * The special case - take what you catch first
+	 */
+	if (unlikely(ac->ac_flags & EXT4_MB_HINT_FIRST)) {
+		*bex = *ex;
+		ext4_mb_use_best_found(ac, e4b);
+		return;
+	}
+
+	/*
+	 * Let's check whether the chuck is good enough
+	 */
+	if (ex->fe_len == gex->fe_len) {
+		*bex = *ex;
+		ext4_mb_use_best_found(ac, e4b);
+		return;
+	}
+
+	/*
+	 * If this is first found extent, just store it in the context
+	 */
+	if (bex->fe_len == 0) {
+		*bex = *ex;
+		return;
+	}
+
+	/*
+	 * If new found extent is better, store it in the context
+	 */
+	if (bex->fe_len < gex->fe_len) {
+		/* if the request isn't satisfied, any found extent
+		 * larger than previous best one is better */
+		if (ex->fe_len > bex->fe_len)
+			*bex = *ex;
+	} else if (ex->fe_len > gex->fe_len) {
+		/* if the request is satisfied, then we try to find
+		 * an extent that still satisfy the request, but is
+		 * smaller than previous one */
+		if (ex->fe_len < bex->fe_len)
+			*bex = *ex;
+	}
+
+	ext4_mb_check_limits(ac, e4b, 0);
+}
+
+static noinline_for_stack
+int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
+					struct ext4_buddy *e4b)
+{
+	struct ext4_free_extent ex = ac->ac_b_ex;
+	ext4_group_t group = ex.fe_group;
+	int max;
+	int err;
+
+	BUG_ON(ex.fe_len <= 0);
+	err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
+	if (err)
+		return err;
+
+	ext4_lock_group(ac->ac_sb, group);
+	max = mb_find_extent(e4b, 0, ex.fe_start, ex.fe_len, &ex);
+
+	if (max > 0) {
+		ac->ac_b_ex = ex;
+		ext4_mb_use_best_found(ac, e4b);
+	}
+
+	ext4_unlock_group(ac->ac_sb, group);
+	ext4_mb_unload_buddy(e4b);
+
+	return 0;
+}
+
+static noinline_for_stack
+int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
+				struct ext4_buddy *e4b)
+{
+	ext4_group_t group = ac->ac_g_ex.fe_group;
+	int max;
+	int err;
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_free_extent ex;
+
+	if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL))
+		return 0;
+
+	err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
+	if (err)
+		return err;
+
+	ext4_lock_group(ac->ac_sb, group);
+	max = mb_find_extent(e4b, 0, ac->ac_g_ex.fe_start,
+			     ac->ac_g_ex.fe_len, &ex);
+
+	if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
+		ext4_fsblk_t start;
+
+		start = ext4_group_first_block_no(ac->ac_sb, e4b->bd_group) +
+			ex.fe_start;
+		/* use do_div to get remainder (would be 64-bit modulo) */
+		if (do_div(start, sbi->s_stripe) == 0) {
+			ac->ac_found++;
+			ac->ac_b_ex = ex;
+			ext4_mb_use_best_found(ac, e4b);
+		}
+	} else if (max >= ac->ac_g_ex.fe_len) {
+		BUG_ON(ex.fe_len <= 0);
+		BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group);
+		BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start);
+		ac->ac_found++;
+		ac->ac_b_ex = ex;
+		ext4_mb_use_best_found(ac, e4b);
+	} else if (max > 0 && (ac->ac_flags & EXT4_MB_HINT_MERGE)) {
+		/* Sometimes, caller may want to merge even small
+		 * number of blocks to an existing extent */
+		BUG_ON(ex.fe_len <= 0);
+		BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group);
+		BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start);
+		ac->ac_found++;
+		ac->ac_b_ex = ex;
+		ext4_mb_use_best_found(ac, e4b);
+	}
+	ext4_unlock_group(ac->ac_sb, group);
+	ext4_mb_unload_buddy(e4b);
+
+	return 0;
+}
+
+/*
+ * The routine scans buddy structures (not bitmap!) from given order
+ * to max order and tries to find big enough chunk to satisfy the req
+ */
+static noinline_for_stack
+void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
+					struct ext4_buddy *e4b)
+{
+	struct super_block *sb = ac->ac_sb;
+	struct ext4_group_info *grp = e4b->bd_info;
+	void *buddy;
+	int i;
+	int k;
+	int max;
+
+	BUG_ON(ac->ac_2order <= 0);
+	for (i = ac->ac_2order; i <= sb->s_blocksize_bits + 1; i++) {
+		if (grp->bb_counters[i] == 0)
+			continue;
+
+		buddy = mb_find_buddy(e4b, i, &max);
+		BUG_ON(buddy == NULL);
+
+		k = mb_find_next_zero_bit(buddy, max, 0);
+		BUG_ON(k >= max);
+
+		ac->ac_found++;
+
+		ac->ac_b_ex.fe_len = 1 << i;
+		ac->ac_b_ex.fe_start = k << i;
+		ac->ac_b_ex.fe_group = e4b->bd_group;
+
+		ext4_mb_use_best_found(ac, e4b);
+
+		BUG_ON(ac->ac_b_ex.fe_len != ac->ac_g_ex.fe_len);
+
+		if (EXT4_SB(sb)->s_mb_stats)
+			atomic_inc(&EXT4_SB(sb)->s_bal_2orders);
+
+		break;
+	}
+}
+
+/*
+ * The routine scans the group and measures all found extents.
+ * In order to optimize scanning, caller must pass number of
+ * free blocks in the group, so the routine can know upper limit.
+ */
+static noinline_for_stack
+void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
+					struct ext4_buddy *e4b)
+{
+	struct super_block *sb = ac->ac_sb;
+	void *bitmap = EXT4_MB_BITMAP(e4b);
+	struct ext4_free_extent ex;
+	int i;
+	int free;
+
+	free = e4b->bd_info->bb_free;
+	BUG_ON(free <= 0);
+
+	i = e4b->bd_info->bb_first_free;
+
+	while (free && ac->ac_status == AC_STATUS_CONTINUE) {
+		i = mb_find_next_zero_bit(bitmap,
+						EXT4_BLOCKS_PER_GROUP(sb), i);
+		if (i >= EXT4_BLOCKS_PER_GROUP(sb)) {
+			/*
+			 * IF we have corrupt bitmap, we won't find any
+			 * free blocks even though group info says we
+			 * we have free blocks
+			 */
+			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
+					"%d free blocks as per "
+					"group info. But bitmap says 0",
+					free);
+			break;
+		}
+
+		mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex);
+		BUG_ON(ex.fe_len <= 0);
+		if (free < ex.fe_len) {
+			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
+					"%d free blocks as per "
+					"group info. But got %d blocks",
+					free, ex.fe_len);
+			/*
+			 * The number of free blocks differs. This mostly
+			 * indicate that the bitmap is corrupt. So exit
+			 * without claiming the space.
+			 */
+			break;
+		}
+
+		ext4_mb_measure_extent(ac, &ex, e4b);
+
+		i += ex.fe_len;
+		free -= ex.fe_len;
+	}
+
+	ext4_mb_check_limits(ac, e4b, 1);
+}
+
+/*
+ * This is a special case for storages like raid5
+ * we try to find stripe-aligned chunks for stripe-size-multiple requests
+ */
+static noinline_for_stack
+void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
+				 struct ext4_buddy *e4b)
+{
+	struct super_block *sb = ac->ac_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	void *bitmap = EXT4_MB_BITMAP(e4b);
+	struct ext4_free_extent ex;
+	ext4_fsblk_t first_group_block;
+	ext4_fsblk_t a;
+	ext4_grpblk_t i;
+	int max;
+
+	BUG_ON(sbi->s_stripe == 0);
+
+	/* find first stripe-aligned block in group */
+	first_group_block = ext4_group_first_block_no(sb, e4b->bd_group);
+
+	a = first_group_block + sbi->s_stripe - 1;
+	do_div(a, sbi->s_stripe);
+	i = (a * sbi->s_stripe) - first_group_block;
+
+	while (i < EXT4_BLOCKS_PER_GROUP(sb)) {
+		if (!mb_test_bit(i, bitmap)) {
+			max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex);
+			if (max >= sbi->s_stripe) {
+				ac->ac_found++;
+				ac->ac_b_ex = ex;
+				ext4_mb_use_best_found(ac, e4b);
+				break;
+			}
+		}
+		i += sbi->s_stripe;
+	}
+}
+
+/* This is now called BEFORE we load the buddy bitmap. */
+static int ext4_mb_good_group(struct ext4_allocation_context *ac,
+				ext4_group_t group, int cr)
+{
+	unsigned free, fragments;
+	int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
+	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
+
+	BUG_ON(cr < 0 || cr >= 4);
+
+	/* We only do this if the grp has never been initialized */
+	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+		int ret = ext4_mb_init_group(ac->ac_sb, group);
+		if (ret)
+			return 0;
+	}
+
+	free = grp->bb_free;
+	fragments = grp->bb_fragments;
+	if (free == 0)
+		return 0;
+	if (fragments == 0)
+		return 0;
+
+	switch (cr) {
+	case 0:
+		BUG_ON(ac->ac_2order == 0);
+
+		if (grp->bb_largest_free_order < ac->ac_2order)
+			return 0;
+
+		/* Avoid using the first bg of a flexgroup for data files */
+		if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
+		    (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) &&
+		    ((group % flex_size) == 0))
+			return 0;
+
+		return 1;
+	case 1:
+		if ((free / fragments) >= ac->ac_g_ex.fe_len)
+			return 1;
+		break;
+	case 2:
+		if (free >= ac->ac_g_ex.fe_len)
+			return 1;
+		break;
+	case 3:
+		return 1;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static noinline_for_stack int
+ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
+{
+	ext4_group_t ngroups, group, i;
+	int cr;
+	int err = 0;
+	struct ext4_sb_info *sbi;
+	struct super_block *sb;
+	struct ext4_buddy e4b;
+
+	sb = ac->ac_sb;
+	sbi = EXT4_SB(sb);
+	ngroups = ext4_get_groups_count(sb);
+	/* non-extent files are limited to low blocks/groups */
+	if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)))
+		ngroups = sbi->s_blockfile_groups;
+
+	BUG_ON(ac->ac_status == AC_STATUS_FOUND);
+
+	/* first, try the goal */
+	err = ext4_mb_find_by_goal(ac, &e4b);
+	if (err || ac->ac_status == AC_STATUS_FOUND)
+		goto out;
+
+	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+		goto out;
+
+	/*
+	 * ac->ac2_order is set only if the fe_len is a power of 2
+	 * if ac2_order is set we also set criteria to 0 so that we
+	 * try exact allocation using buddy.
+	 */
+	i = fls(ac->ac_g_ex.fe_len);
+	ac->ac_2order = 0;
+	/*
+	 * We search using buddy data only if the order of the request
+	 * is greater than equal to the sbi_s_mb_order2_reqs
+	 * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req
+	 */
+	if (i >= sbi->s_mb_order2_reqs) {
+		/*
+		 * This should tell if fe_len is exactly power of 2
+		 */
+		if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0)
+			ac->ac_2order = i - 1;
+	}
+
+	/* if stream allocation is enabled, use global goal */
+	if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
+		/* TBD: may be hot point */
+		spin_lock(&sbi->s_md_lock);
+		ac->ac_g_ex.fe_group = sbi->s_mb_last_group;
+		ac->ac_g_ex.fe_start = sbi->s_mb_last_start;
+		spin_unlock(&sbi->s_md_lock);
+	}
+
+	/* Let's just scan groups to find more-less suitable blocks */
+	cr = ac->ac_2order ? 0 : 1;
+	/*
+	 * cr == 0 try to get exact allocation,
+	 * cr == 3  try to get anything
+	 */
+repeat:
+	for (; cr < 4 && ac->ac_status == AC_STATUS_CONTINUE; cr++) {
+		ac->ac_criteria = cr;
+		/*
+		 * searching for the right group start
+		 * from the goal value specified
+		 */
+		group = ac->ac_g_ex.fe_group;
+
+		for (i = 0; i < ngroups; group++, i++) {
+			if (group == ngroups)
+				group = 0;
+
+			/* This now checks without needing the buddy page */
+			if (!ext4_mb_good_group(ac, group, cr))
+				continue;
+
+			err = ext4_mb_load_buddy(sb, group, &e4b);
+			if (err)
+				goto out;
+
+			ext4_lock_group(sb, group);
+
+			/*
+			 * We need to check again after locking the
+			 * block group
+			 */
+			if (!ext4_mb_good_group(ac, group, cr)) {
+				ext4_unlock_group(sb, group);
+				ext4_mb_unload_buddy(&e4b);
+				continue;
+			}
+
+			ac->ac_groups_scanned++;
+			if (cr == 0)
+				ext4_mb_simple_scan_group(ac, &e4b);
+			else if (cr == 1 && sbi->s_stripe &&
+					!(ac->ac_g_ex.fe_len % sbi->s_stripe))
+				ext4_mb_scan_aligned(ac, &e4b);
+			else
+				ext4_mb_complex_scan_group(ac, &e4b);
+
+			ext4_unlock_group(sb, group);
+			ext4_mb_unload_buddy(&e4b);
+
+			if (ac->ac_status != AC_STATUS_CONTINUE)
+				break;
+		}
+	}
+
+	if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND &&
+	    !(ac->ac_flags & EXT4_MB_HINT_FIRST)) {
+		/*
+		 * We've been searching too long. Let's try to allocate
+		 * the best chunk we've found so far
+		 */
+
+		ext4_mb_try_best_found(ac, &e4b);
+		if (ac->ac_status != AC_STATUS_FOUND) {
+			/*
+			 * Someone more lucky has already allocated it.
+			 * The only thing we can do is just take first
+			 * found block(s)
+			printk(KERN_DEBUG "EXT4-fs: someone won our chunk\n");
+			 */
+			ac->ac_b_ex.fe_group = 0;
+			ac->ac_b_ex.fe_start = 0;
+			ac->ac_b_ex.fe_len = 0;
+			ac->ac_status = AC_STATUS_CONTINUE;
+			ac->ac_flags |= EXT4_MB_HINT_FIRST;
+			cr = 3;
+			atomic_inc(&sbi->s_mb_lost_chunks);
+			goto repeat;
+		}
+	}
+out:
+	return err;
+}
+
+static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
+{
+	struct super_block *sb = seq->private;
+	ext4_group_t group;
+
+	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
+		return NULL;
+	group = *pos + 1;
+	return (void *) ((unsigned long) group);
+}
+
+static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct super_block *sb = seq->private;
+	ext4_group_t group;
+
+	++*pos;
+	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
+		return NULL;
+	group = *pos + 1;
+	return (void *) ((unsigned long) group);
+}
+
+static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
+{
+	struct super_block *sb = seq->private;
+	ext4_group_t group = (ext4_group_t) ((unsigned long) v);
+	int i;
+	int err;
+	struct ext4_buddy e4b;
+	struct sg {
+		struct ext4_group_info info;
+		ext4_grpblk_t counters[16];
+	} sg;
+
+	group--;
+	if (group == 0)
+		seq_printf(seq, "#%-5s: %-5s %-5s %-5s "
+				"[ %-5s %-5s %-5s %-5s %-5s %-5s %-5s "
+				  "%-5s %-5s %-5s %-5s %-5s %-5s %-5s ]\n",
+			   "group", "free", "frags", "first",
+			   "2^0", "2^1", "2^2", "2^3", "2^4", "2^5", "2^6",
+			   "2^7", "2^8", "2^9", "2^10", "2^11", "2^12", "2^13");
+
+	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
+		sizeof(struct ext4_group_info);
+	err = ext4_mb_load_buddy(sb, group, &e4b);
+	if (err) {
+		seq_printf(seq, "#%-5u: I/O error\n", group);
+		return 0;
+	}
+	ext4_lock_group(sb, group);
+	memcpy(&sg, ext4_get_group_info(sb, group), i);
+	ext4_unlock_group(sb, group);
+	ext4_mb_unload_buddy(&e4b);
+
+	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
+			sg.info.bb_fragments, sg.info.bb_first_free);
+	for (i = 0; i <= 13; i++)
+		seq_printf(seq, " %-5u", i <= sb->s_blocksize_bits + 1 ?
+				sg.info.bb_counters[i] : 0);
+	seq_printf(seq, " ]\n");
+
+	return 0;
+}
+
+static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations ext4_mb_seq_groups_ops = {
+	.start  = ext4_mb_seq_groups_start,
+	.next   = ext4_mb_seq_groups_next,
+	.stop   = ext4_mb_seq_groups_stop,
+	.show   = ext4_mb_seq_groups_show,
+};
+
+static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file)
+{
+	struct super_block *sb = PDE(inode)->data;
+	int rc;
+
+	rc = seq_open(file, &ext4_mb_seq_groups_ops);
+	if (rc == 0) {
+		struct seq_file *m = file->private_data;
+		m->private = sb;
+	}
+	return rc;
+
+}
+
+static const struct file_operations ext4_mb_seq_groups_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ext4_mb_seq_groups_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static struct kmem_cache *get_groupinfo_cache(int blocksize_bits)
+{
+	int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+	struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index];
+
+	BUG_ON(!cachep);
+	return cachep;
+}
+
+/* Create and initialize ext4_group_info data for the given group. */
+int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
+			  struct ext4_group_desc *desc)
+{
+	int i;
+	int metalen = 0;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_info **meta_group_info;
+	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
+
+	/*
+	 * First check if this group is the first of a reserved block.
+	 * If it's true, we have to allocate a new table of pointers
+	 * to ext4_group_info structures
+	 */
+	if (group % EXT4_DESC_PER_BLOCK(sb) == 0) {
+		metalen = sizeof(*meta_group_info) <<
+			EXT4_DESC_PER_BLOCK_BITS(sb);
+		meta_group_info = kmalloc(metalen, GFP_KERNEL);
+		if (meta_group_info == NULL) {
+			printk(KERN_ERR "EXT4-fs: can't allocate mem for a "
+			       "buddy group\n");
+			goto exit_meta_group_info;
+		}
+		sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] =
+			meta_group_info;
+	}
+
+	meta_group_info =
+		sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)];
+	i = group & (EXT4_DESC_PER_BLOCK(sb) - 1);
+
+	meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
+	if (meta_group_info[i] == NULL) {
+		printk(KERN_ERR "EXT4-fs: can't allocate buddy mem\n");
+		goto exit_group_info;
+	}
+	memset(meta_group_info[i], 0, kmem_cache_size(cachep));
+	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT,
+		&(meta_group_info[i]->bb_state));
+
+	/*
+	 * initialize bb_free to be able to skip
+	 * empty groups without initialization
+	 */
+	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		meta_group_info[i]->bb_free =
+			ext4_free_blocks_after_init(sb, group, desc);
+	} else {
+		meta_group_info[i]->bb_free =
+			ext4_free_blks_count(sb, desc);
+	}
+
+	INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
+	init_rwsem(&meta_group_info[i]->alloc_sem);
+	meta_group_info[i]->bb_free_root = RB_ROOT;
+	meta_group_info[i]->bb_largest_free_order = -1;  /* uninit */
+
+#ifdef DOUBLE_CHECK
+	{
+		struct buffer_head *bh;
+		meta_group_info[i]->bb_bitmap =
+			kmalloc(sb->s_blocksize, GFP_KERNEL);
+		BUG_ON(meta_group_info[i]->bb_bitmap == NULL);
+		bh = ext4_read_block_bitmap(sb, group);
+		BUG_ON(bh == NULL);
+		memcpy(meta_group_info[i]->bb_bitmap, bh->b_data,
+			sb->s_blocksize);
+		put_bh(bh);
+	}
+#endif
+
+	return 0;
+
+exit_group_info:
+	/* If a meta_group_info table has been allocated, release it now */
+	if (group % EXT4_DESC_PER_BLOCK(sb) == 0)
+		kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]);
+exit_meta_group_info:
+	return -ENOMEM;
+} /* ext4_mb_add_groupinfo */
+
+static int ext4_mb_init_backend(struct super_block *sb)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	ext4_group_t i;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	int num_meta_group_infos;
+	int num_meta_group_infos_max;
+	int array_size;
+	struct ext4_group_desc *desc;
+	struct kmem_cache *cachep;
+
+	/* This is the number of blocks used by GDT */
+	num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
+				1) >> EXT4_DESC_PER_BLOCK_BITS(sb);
+
+	/*
+	 * This is the total number of blocks used by GDT including
+	 * the number of reserved blocks for GDT.
+	 * The s_group_info array is allocated with this value
+	 * to allow a clean online resize without a complex
+	 * manipulation of pointer.
+	 * The drawback is the unused memory when no resize
+	 * occurs but it's very low in terms of pages
+	 * (see comments below)
+	 * Need to handle this properly when META_BG resizing is allowed
+	 */
+	num_meta_group_infos_max = num_meta_group_infos +
+				le16_to_cpu(es->s_reserved_gdt_blocks);
+
+	/*
+	 * array_size is the size of s_group_info array. We round it
+	 * to the next power of two because this approximation is done
+	 * internally by kmalloc so we can have some more memory
+	 * for free here (e.g. may be used for META_BG resize).
+	 */
+	array_size = 1;
+	while (array_size < sizeof(*sbi->s_group_info) *
+	       num_meta_group_infos_max)
+		array_size = array_size << 1;
+	/* An 8TB filesystem with 64-bit pointers requires a 4096 byte
+	 * kmalloc. A 128kb malloc should suffice for a 256TB filesystem.
+	 * So a two level scheme suffices for now. */
+	sbi->s_group_info = kzalloc(array_size, GFP_KERNEL);
+	if (sbi->s_group_info == NULL) {
+		printk(KERN_ERR "EXT4-fs: can't allocate buddy meta group\n");
+		return -ENOMEM;
+	}
+	sbi->s_buddy_cache = new_inode(sb);
+	if (sbi->s_buddy_cache == NULL) {
+		printk(KERN_ERR "EXT4-fs: can't get new inode\n");
+		goto err_freesgi;
+	}
+	sbi->s_buddy_cache->i_ino = get_next_ino();
+	EXT4_I(sbi->s_buddy_cache)->i_disksize = 0;
+	for (i = 0; i < ngroups; i++) {
+		desc = ext4_get_group_desc(sb, i, NULL);
+		if (desc == NULL) {
+			printk(KERN_ERR
+				"EXT4-fs: can't read descriptor %u\n", i);
+			goto err_freebuddy;
+		}
+		if (ext4_mb_add_groupinfo(sb, i, desc) != 0)
+			goto err_freebuddy;
+	}
+
+	return 0;
+
+err_freebuddy:
+	cachep = get_groupinfo_cache(sb->s_blocksize_bits);
+	while (i-- > 0)
+		kmem_cache_free(cachep, ext4_get_group_info(sb, i));
+	i = num_meta_group_infos;
+	while (i-- > 0)
+		kfree(sbi->s_group_info[i]);
+	iput(sbi->s_buddy_cache);
+err_freesgi:
+	kfree(sbi->s_group_info);
+	return -ENOMEM;
+}
+
+static void ext4_groupinfo_destroy_slabs(void)
+{
+	int i;
+
+	for (i = 0; i < NR_GRPINFO_CACHES; i++) {
+		if (ext4_groupinfo_caches[i])
+			kmem_cache_destroy(ext4_groupinfo_caches[i]);
+		ext4_groupinfo_caches[i] = NULL;
+	}
+}
+
+static int ext4_groupinfo_create_slab(size_t size)
+{
+	static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex);
+	int slab_size;
+	int blocksize_bits = order_base_2(size);
+	int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+	struct kmem_cache *cachep;
+
+	if (cache_index >= NR_GRPINFO_CACHES)
+		return -EINVAL;
+
+	if (unlikely(cache_index < 0))
+		cache_index = 0;
+
+	mutex_lock(&ext4_grpinfo_slab_create_mutex);
+	if (ext4_groupinfo_caches[cache_index]) {
+		mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+		return 0;	/* Already created */
+	}
+
+	slab_size = offsetof(struct ext4_group_info,
+				bb_counters[blocksize_bits + 2]);
+
+	cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index],
+					slab_size, 0, SLAB_RECLAIM_ACCOUNT,
+					NULL);
+
+	mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+	if (!cachep) {
+		printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n");
+		return -ENOMEM;
+	}
+
+	ext4_groupinfo_caches[cache_index] = cachep;
+
+	return 0;
+}
+
+int ext4_mb_init(struct super_block *sb, int needs_recovery)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	unsigned i, j;
+	unsigned offset;
+	unsigned max;
+	int ret;
+
+	i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
+
+	sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL);
+	if (sbi->s_mb_offsets == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs);
+	sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
+	if (sbi->s_mb_maxs == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = ext4_groupinfo_create_slab(sb->s_blocksize);
+	if (ret < 0)
+		goto out;
+
+	/* order 0 is regular bitmap */
+	sbi->s_mb_maxs[0] = sb->s_blocksize << 3;
+	sbi->s_mb_offsets[0] = 0;
+
+	i = 1;
+	offset = 0;
+	max = sb->s_blocksize << 2;
+	do {
+		sbi->s_mb_offsets[i] = offset;
+		sbi->s_mb_maxs[i] = max;
+		offset += 1 << (sb->s_blocksize_bits - i);
+		max = max >> 1;
+		i++;
+	} while (i <= sb->s_blocksize_bits + 1);
+
+	/* init file for buddy data */
+	ret = ext4_mb_init_backend(sb);
+	if (ret != 0) {
+		goto out;
+	}
+
+	spin_lock_init(&sbi->s_md_lock);
+	spin_lock_init(&sbi->s_bal_lock);
+
+	sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
+	sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN;
+	sbi->s_mb_stats = MB_DEFAULT_STATS;
+	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
+	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
+	sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
+
+	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
+	if (sbi->s_locality_groups == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for_each_possible_cpu(i) {
+		struct ext4_locality_group *lg;
+		lg = per_cpu_ptr(sbi->s_locality_groups, i);
+		mutex_init(&lg->lg_mutex);
+		for (j = 0; j < PREALLOC_TB_SIZE; j++)
+			INIT_LIST_HEAD(&lg->lg_prealloc_list[j]);
+		spin_lock_init(&lg->lg_prealloc_lock);
+	}
+
+	if (sbi->s_proc)
+		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
+				 &ext4_mb_seq_groups_fops, sb);
+
+	if (sbi->s_journal)
+		sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+out:
+	if (ret) {
+		kfree(sbi->s_mb_offsets);
+		kfree(sbi->s_mb_maxs);
+	}
+	return ret;
+}
+
+/* need to called with the ext4 group lock held */
+static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
+{
+	struct ext4_prealloc_space *pa;
+	struct list_head *cur, *tmp;
+	int count = 0;
+
+	list_for_each_safe(cur, tmp, &grp->bb_prealloc_list) {
+		pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list);
+		list_del(&pa->pa_group_list);
+		count++;
+		kmem_cache_free(ext4_pspace_cachep, pa);
+	}
+	if (count)
+		mb_debug(1, "mballoc: %u PAs left\n", count);
+
+}
+
+int ext4_mb_release(struct super_block *sb)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	ext4_group_t i;
+	int num_meta_group_infos;
+	struct ext4_group_info *grinfo;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
+
+	if (sbi->s_proc)
+		remove_proc_entry("mb_groups", sbi->s_proc);
+
+	if (sbi->s_group_info) {
+		for (i = 0; i < ngroups; i++) {
+			grinfo = ext4_get_group_info(sb, i);
+#ifdef DOUBLE_CHECK
+			kfree(grinfo->bb_bitmap);
+#endif
+			ext4_lock_group(sb, i);
+			ext4_mb_cleanup_pa(grinfo);
+			ext4_unlock_group(sb, i);
+			kmem_cache_free(cachep, grinfo);
+		}
+		num_meta_group_infos = (ngroups +
+				EXT4_DESC_PER_BLOCK(sb) - 1) >>
+			EXT4_DESC_PER_BLOCK_BITS(sb);
+		for (i = 0; i < num_meta_group_infos; i++)
+			kfree(sbi->s_group_info[i]);
+		kfree(sbi->s_group_info);
+	}
+	kfree(sbi->s_mb_offsets);
+	kfree(sbi->s_mb_maxs);
+	if (sbi->s_buddy_cache)
+		iput(sbi->s_buddy_cache);
+	if (sbi->s_mb_stats) {
+		printk(KERN_INFO
+		       "EXT4-fs: mballoc: %u blocks %u reqs (%u success)\n",
+				atomic_read(&sbi->s_bal_allocated),
+				atomic_read(&sbi->s_bal_reqs),
+				atomic_read(&sbi->s_bal_success));
+		printk(KERN_INFO
+		      "EXT4-fs: mballoc: %u extents scanned, %u goal hits, "
+				"%u 2^N hits, %u breaks, %u lost\n",
+				atomic_read(&sbi->s_bal_ex_scanned),
+				atomic_read(&sbi->s_bal_goals),
+				atomic_read(&sbi->s_bal_2orders),
+				atomic_read(&sbi->s_bal_breaks),
+				atomic_read(&sbi->s_mb_lost_chunks));
+		printk(KERN_INFO
+		       "EXT4-fs: mballoc: %lu generated and it took %Lu\n",
+				sbi->s_mb_buddies_generated++,
+				sbi->s_mb_generation_time);
+		printk(KERN_INFO
+		       "EXT4-fs: mballoc: %u preallocated, %u discarded\n",
+				atomic_read(&sbi->s_mb_preallocated),
+				atomic_read(&sbi->s_mb_discarded));
+	}
+
+	free_percpu(sbi->s_locality_groups);
+
+	return 0;
+}
+
+static inline int ext4_issue_discard(struct super_block *sb,
+		ext4_group_t block_group, ext4_grpblk_t block, int count)
+{
+	ext4_fsblk_t discard_block;
+
+	discard_block = block + ext4_group_first_block_no(sb, block_group);
+	trace_ext4_discard_blocks(sb,
+			(unsigned long long) discard_block, count);
+	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+}
+
+/*
+ * This function is called by the jbd2 layer once the commit has finished,
+ * so we know we can free the blocks that were released with that commit.
+ */
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
+{
+	struct super_block *sb = journal->j_private;
+	struct ext4_buddy e4b;
+	struct ext4_group_info *db;
+	int err, count = 0, count2 = 0;
+	struct ext4_free_data *entry;
+	struct list_head *l, *ltmp;
+
+	list_for_each_safe(l, ltmp, &txn->t_private_list) {
+		entry = list_entry(l, struct ext4_free_data, list);
+
+		mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
+			 entry->count, entry->group, entry);
+
+		if (test_opt(sb, DISCARD))
+			ext4_issue_discard(sb, entry->group,
+					   entry->start_blk, entry->count);
+
+		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
+		/* we expect to find existing buddy because it's pinned */
+		BUG_ON(err != 0);
+
+		db = e4b.bd_info;
+		/* there are blocks to put in buddy to make them really free */
+		count += entry->count;
+		count2++;
+		ext4_lock_group(sb, entry->group);
+		/* Take it out of per group rb tree */
+		rb_erase(&entry->node, &(db->bb_free_root));
+		mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+
+		if (!db->bb_free_root.rb_node) {
+			/* No more items in the per group rb tree
+			 * balance refcounts from ext4_mb_free_metadata()
+			 */
+			page_cache_release(e4b.bd_buddy_page);
+			page_cache_release(e4b.bd_bitmap_page);
+		}
+		ext4_unlock_group(sb, entry->group);
+		kmem_cache_free(ext4_free_ext_cachep, entry);
+		ext4_mb_unload_buddy(&e4b);
+	}
+
+	mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
+}
+
+#ifdef CONFIG_EXT4_DEBUG
+u8 mb_enable_debug __read_mostly;
+
+static struct dentry *debugfs_dir;
+static struct dentry *debugfs_debug;
+
+static void __init ext4_create_debugfs_entry(void)
+{
+	debugfs_dir = debugfs_create_dir("ext4", NULL);
+	if (debugfs_dir)
+		debugfs_debug = debugfs_create_u8("mballoc-debug",
+						  S_IRUGO | S_IWUSR,
+						  debugfs_dir,
+						  &mb_enable_debug);
+}
+
+static void ext4_remove_debugfs_entry(void)
+{
+	debugfs_remove(debugfs_debug);
+	debugfs_remove(debugfs_dir);
+}
+
+#else
+
+static void __init ext4_create_debugfs_entry(void)
+{
+}
+
+static void ext4_remove_debugfs_entry(void)
+{
+}
+
+#endif
+
+int __init ext4_init_mballoc(void)
+{
+	ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space,
+					SLAB_RECLAIM_ACCOUNT);
+	if (ext4_pspace_cachep == NULL)
+		return -ENOMEM;
+
+	ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context,
+				    SLAB_RECLAIM_ACCOUNT);
+	if (ext4_ac_cachep == NULL) {
+		kmem_cache_destroy(ext4_pspace_cachep);
+		return -ENOMEM;
+	}
+
+	ext4_free_ext_cachep = KMEM_CACHE(ext4_free_data,
+					  SLAB_RECLAIM_ACCOUNT);
+	if (ext4_free_ext_cachep == NULL) {
+		kmem_cache_destroy(ext4_pspace_cachep);
+		kmem_cache_destroy(ext4_ac_cachep);
+		return -ENOMEM;
+	}
+	ext4_create_debugfs_entry();
+	return 0;
+}
+
+void ext4_exit_mballoc(void)
+{
+	/*
+	 * Wait for completion of call_rcu()'s on ext4_pspace_cachep
+	 * before destroying the slab cache.
+	 */
+	rcu_barrier();
+	kmem_cache_destroy(ext4_pspace_cachep);
+	kmem_cache_destroy(ext4_ac_cachep);
+	kmem_cache_destroy(ext4_free_ext_cachep);
+	ext4_groupinfo_destroy_slabs();
+	ext4_remove_debugfs_entry();
+}
+
+
+/*
+ * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps
+ * Returns 0 if success or error code
+ */
+static noinline_for_stack int
+ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
+				handle_t *handle, unsigned int reserv_blks)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	struct ext4_sb_info *sbi;
+	struct super_block *sb;
+	ext4_fsblk_t block;
+	int err, len;
+
+	BUG_ON(ac->ac_status != AC_STATUS_FOUND);
+	BUG_ON(ac->ac_b_ex.fe_len <= 0);
+
+	sb = ac->ac_sb;
+	sbi = EXT4_SB(sb);
+
+	err = -EIO;
+	bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group);
+	if (!bitmap_bh)
+		goto out_err;
+
+	err = ext4_journal_get_write_access(handle, bitmap_bh);
+	if (err)
+		goto out_err;
+
+	err = -EIO;
+	gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, &gdp_bh);
+	if (!gdp)
+		goto out_err;
+
+	ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
+			ext4_free_blks_count(sb, gdp));
+
+	err = ext4_journal_get_write_access(handle, gdp_bh);
+	if (err)
+		goto out_err;
+
+	block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
+
+	len = ac->ac_b_ex.fe_len;
+	if (!ext4_data_block_valid(sbi, block, len)) {
+		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
+			   "fs metadata\n", block, block+len);
+		/* File system mounted not to panic on error
+		 * Fix the bitmap and repeat the block allocation
+		 * We leak some of the blocks here.
+		 */
+		ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+		mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+			    ac->ac_b_ex.fe_len);
+		ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+		if (!err)
+			err = -EAGAIN;
+		goto out_err;
+	}
+
+	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+#ifdef AGGRESSIVE_CHECK
+	{
+		int i;
+		for (i = 0; i < ac->ac_b_ex.fe_len; i++) {
+			BUG_ON(mb_test_bit(ac->ac_b_ex.fe_start + i,
+						bitmap_bh->b_data));
+		}
+	}
+#endif
+	mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len);
+	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+		ext4_free_blks_set(sb, gdp,
+					ext4_free_blocks_after_init(sb,
+					ac->ac_b_ex.fe_group, gdp));
+	}
+	len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
+	ext4_free_blks_set(sb, gdp, len);
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
+
+	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+	percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
+	/*
+	 * Now reduce the dirty block count also. Should not go negative
+	 */
+	if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
+		/* release all the reserved blocks if non delalloc */
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi,
+							  ac->ac_b_ex.fe_group);
+		atomic_sub(ac->ac_b_ex.fe_len,
+			   &sbi->s_flex_groups[flex_group].free_blocks);
+	}
+
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+	if (err)
+		goto out_err;
+	err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
+
+out_err:
+	ext4_mark_super_dirty(sb);
+	brelse(bitmap_bh);
+	return err;
+}
+
+/*
+ * here we normalize request for locality group
+ * Group request are normalized to s_strip size if we set the same via mount
+ * option. If not we set it to s_mb_group_prealloc which can be configured via
+ * /sys/fs/ext4/<partition>/mb_group_prealloc
+ *
+ * XXX: should we try to preallocate more than the group has now?
+ */
+static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac)
+{
+	struct super_block *sb = ac->ac_sb;
+	struct ext4_locality_group *lg = ac->ac_lg;
+
+	BUG_ON(lg == NULL);
+	if (EXT4_SB(sb)->s_stripe)
+		ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_stripe;
+	else
+		ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc;
+	mb_debug(1, "#%u: goal %u blocks for locality group\n",
+		current->pid, ac->ac_g_ex.fe_len);
+}
+
+/*
+ * Normalization means making request better in terms of
+ * size and alignment
+ */
+static noinline_for_stack void
+ext4_mb_normalize_request(struct ext4_allocation_context *ac,
+				struct ext4_allocation_request *ar)
+{
+	int bsbits, max;
+	ext4_lblk_t end;
+	loff_t size, orig_size, start_off;
+	ext4_lblk_t start;
+	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
+	struct ext4_prealloc_space *pa;
+
+	/* do normalize only data requests, metadata requests
+	   do not need preallocation */
+	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
+		return;
+
+	/* sometime caller may want exact blocks */
+	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+		return;
+
+	/* caller may indicate that preallocation isn't
+	 * required (it's a tail, for example) */
+	if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC)
+		return;
+
+	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) {
+		ext4_mb_normalize_group_request(ac);
+		return ;
+	}
+
+	bsbits = ac->ac_sb->s_blocksize_bits;
+
+	/* first, let's learn actual file size
+	 * given current request is allocated */
+	size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+	size = size << bsbits;
+	if (size < i_size_read(ac->ac_inode))
+		size = i_size_read(ac->ac_inode);
+	orig_size = size;
+
+	/* max size of free chunks */
+	max = 2 << bsbits;
+
+#define NRL_CHECK_SIZE(req, size, max, chunk_size)	\
+		(req <= (size) || max <= (chunk_size))
+
+	/* first, try to predict filesize */
+	/* XXX: should this table be tunable? */
+	start_off = 0;
+	if (size <= 16 * 1024) {
+		size = 16 * 1024;
+	} else if (size <= 32 * 1024) {
+		size = 32 * 1024;
+	} else if (size <= 64 * 1024) {
+		size = 64 * 1024;
+	} else if (size <= 128 * 1024) {
+		size = 128 * 1024;
+	} else if (size <= 256 * 1024) {
+		size = 256 * 1024;
+	} else if (size <= 512 * 1024) {
+		size = 512 * 1024;
+	} else if (size <= 1024 * 1024) {
+		size = 1024 * 1024;
+	} else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) {
+		start_off = ((loff_t)ac->ac_o_ex.fe_logical >>
+						(21 - bsbits)) << 21;
+		size = 2 * 1024 * 1024;
+	} else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) {
+		start_off = ((loff_t)ac->ac_o_ex.fe_logical >>
+							(22 - bsbits)) << 22;
+		size = 4 * 1024 * 1024;
+	} else if (NRL_CHECK_SIZE(ac->ac_o_ex.fe_len,
+					(8<<20)>>bsbits, max, 8 * 1024)) {
+		start_off = ((loff_t)ac->ac_o_ex.fe_logical >>
+							(23 - bsbits)) << 23;
+		size = 8 * 1024 * 1024;
+	} else {
+		start_off = (loff_t)ac->ac_o_ex.fe_logical << bsbits;
+		size	  = ac->ac_o_ex.fe_len << bsbits;
+	}
+	size = size >> bsbits;
+	start = start_off >> bsbits;
+
+	/* don't cover already allocated blocks in selected range */
+	if (ar->pleft && start <= ar->lleft) {
+		size -= ar->lleft + 1 - start;
+		start = ar->lleft + 1;
+	}
+	if (ar->pright && start + size - 1 >= ar->lright)
+		size -= start + size - ar->lright;
+
+	end = start + size;
+
+	/* check we don't cross already preallocated blocks */
+	rcu_read_lock();
+	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
+		ext4_lblk_t pa_end;
+
+		if (pa->pa_deleted)
+			continue;
+		spin_lock(&pa->pa_lock);
+		if (pa->pa_deleted) {
+			spin_unlock(&pa->pa_lock);
+			continue;
+		}
+
+		pa_end = pa->pa_lstart + pa->pa_len;
+
+		/* PA must not overlap original request */
+		BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
+			ac->ac_o_ex.fe_logical < pa->pa_lstart));
+
+		/* skip PAs this normalized request doesn't overlap with */
+		if (pa->pa_lstart >= end || pa_end <= start) {
+			spin_unlock(&pa->pa_lock);
+			continue;
+		}
+		BUG_ON(pa->pa_lstart <= start && pa_end >= end);
+
+		/* adjust start or end to be adjacent to this pa */
+		if (pa_end <= ac->ac_o_ex.fe_logical) {
+			BUG_ON(pa_end < start);
+			start = pa_end;
+		} else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) {
+			BUG_ON(pa->pa_lstart > end);
+			end = pa->pa_lstart;
+		}
+		spin_unlock(&pa->pa_lock);
+	}
+	rcu_read_unlock();
+	size = end - start;
+
+	/* XXX: extra loop to check we really don't overlap preallocations */
+	rcu_read_lock();
+	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
+		ext4_lblk_t pa_end;
+		spin_lock(&pa->pa_lock);
+		if (pa->pa_deleted == 0) {
+			pa_end = pa->pa_lstart + pa->pa_len;
+			BUG_ON(!(start >= pa_end || end <= pa->pa_lstart));
+		}
+		spin_unlock(&pa->pa_lock);
+	}
+	rcu_read_unlock();
+
+	if (start + size <= ac->ac_o_ex.fe_logical &&
+			start > ac->ac_o_ex.fe_logical) {
+		printk(KERN_ERR "start %lu, size %lu, fe_logical %lu\n",
+			(unsigned long) start, (unsigned long) size,
+			(unsigned long) ac->ac_o_ex.fe_logical);
+	}
+	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
+			start > ac->ac_o_ex.fe_logical);
+	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+
+	/* now prepare goal request */
+
+	/* XXX: is it better to align blocks WRT to logical
+	 * placement or satisfy big request as is */
+	ac->ac_g_ex.fe_logical = start;
+	ac->ac_g_ex.fe_len = size;
+
+	/* define goal start in order to merge */
+	if (ar->pright && (ar->lright == (start + size))) {
+		/* merge to the right */
+		ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size,
+						&ac->ac_f_ex.fe_group,
+						&ac->ac_f_ex.fe_start);
+		ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
+	}
+	if (ar->pleft && (ar->lleft + 1 == start)) {
+		/* merge to the left */
+		ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1,
+						&ac->ac_f_ex.fe_group,
+						&ac->ac_f_ex.fe_start);
+		ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
+	}
+
+	mb_debug(1, "goal: %u(was %u) blocks at %u\n", (unsigned) size,
+		(unsigned) orig_size, (unsigned) start);
+}
+
+static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+
+	if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) {
+		atomic_inc(&sbi->s_bal_reqs);
+		atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated);
+		if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len)
+			atomic_inc(&sbi->s_bal_success);
+		atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned);
+		if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start &&
+				ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group)
+			atomic_inc(&sbi->s_bal_goals);
+		if (ac->ac_found > sbi->s_mb_max_to_scan)
+			atomic_inc(&sbi->s_bal_breaks);
+	}
+
+	if (ac->ac_op == EXT4_MB_HISTORY_ALLOC)
+		trace_ext4_mballoc_alloc(ac);
+	else
+		trace_ext4_mballoc_prealloc(ac);
+}
+
+/*
+ * Called on failure; free up any blocks from the inode PA for this
+ * context.  We don't need this for MB_GROUP_PA because we only change
+ * pa_free in ext4_mb_release_context(), but on failure, we've already
+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed.
+ */
+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
+{
+	struct ext4_prealloc_space *pa = ac->ac_pa;
+	int len;
+
+	if (pa && pa->pa_type == MB_INODE_PA) {
+		len = ac->ac_b_ex.fe_len;
+		pa->pa_free += len;
+	}
+
+}
+
+/*
+ * use blocks preallocated to inode
+ */
+static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
+				struct ext4_prealloc_space *pa)
+{
+	ext4_fsblk_t start;
+	ext4_fsblk_t end;
+	int len;
+
+	/* found preallocated blocks, use them */
+	start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart);
+	end = min(pa->pa_pstart + pa->pa_len, start + ac->ac_o_ex.fe_len);
+	len = end - start;
+	ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group,
+					&ac->ac_b_ex.fe_start);
+	ac->ac_b_ex.fe_len = len;
+	ac->ac_status = AC_STATUS_FOUND;
+	ac->ac_pa = pa;
+
+	BUG_ON(start < pa->pa_pstart);
+	BUG_ON(start + len > pa->pa_pstart + pa->pa_len);
+	BUG_ON(pa->pa_free < len);
+	pa->pa_free -= len;
+
+	mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa);
+}
+
+/*
+ * use blocks preallocated to locality group
+ */
+static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
+				struct ext4_prealloc_space *pa)
+{
+	unsigned int len = ac->ac_o_ex.fe_len;
+
+	ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart,
+					&ac->ac_b_ex.fe_group,
+					&ac->ac_b_ex.fe_start);
+	ac->ac_b_ex.fe_len = len;
+	ac->ac_status = AC_STATUS_FOUND;
+	ac->ac_pa = pa;
+
+	/* we don't correct pa_pstart or pa_plen here to avoid
+	 * possible race when the group is being loaded concurrently
+	 * instead we correct pa later, after blocks are marked
+	 * in on-disk bitmap -- see ext4_mb_release_context()
+	 * Other CPUs are prevented from allocating from this pa by lg_mutex
+	 */
+	mb_debug(1, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa);
+}
+
+/*
+ * Return the prealloc space that have minimal distance
+ * from the goal block. @cpa is the prealloc
+ * space that is having currently known minimal distance
+ * from the goal block.
+ */
+static struct ext4_prealloc_space *
+ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
+			struct ext4_prealloc_space *pa,
+			struct ext4_prealloc_space *cpa)
+{
+	ext4_fsblk_t cur_distance, new_distance;
+
+	if (cpa == NULL) {
+		atomic_inc(&pa->pa_count);
+		return pa;
+	}
+	cur_distance = abs(goal_block - cpa->pa_pstart);
+	new_distance = abs(goal_block - pa->pa_pstart);
+
+	if (cur_distance <= new_distance)
+		return cpa;
+
+	/* drop the previous reference */
+	atomic_dec(&cpa->pa_count);
+	atomic_inc(&pa->pa_count);
+	return pa;
+}
+
+/*
+ * search goal blocks in preallocated space
+ */
+static noinline_for_stack int
+ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
+{
+	int order, i;
+	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
+	struct ext4_locality_group *lg;
+	struct ext4_prealloc_space *pa, *cpa = NULL;
+	ext4_fsblk_t goal_block;
+
+	/* only data can be preallocated */
+	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
+		return 0;
+
+	/* first, try per-file preallocation */
+	rcu_read_lock();
+	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
+
+		/* all fields in this condition don't change,
+		 * so we can skip locking for them */
+		if (ac->ac_o_ex.fe_logical < pa->pa_lstart ||
+			ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len)
+			continue;
+
+		/* non-extent files can't have physical blocks past 2^32 */
+		if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
+			pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
+			continue;
+
+		/* found preallocated blocks, use them */
+		spin_lock(&pa->pa_lock);
+		if (pa->pa_deleted == 0 && pa->pa_free) {
+			atomic_inc(&pa->pa_count);
+			ext4_mb_use_inode_pa(ac, pa);
+			spin_unlock(&pa->pa_lock);
+			ac->ac_criteria = 10;
+			rcu_read_unlock();
+			return 1;
+		}
+		spin_unlock(&pa->pa_lock);
+	}
+	rcu_read_unlock();
+
+	/* can we use group allocation? */
+	if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC))
+		return 0;
+
+	/* inode may have no locality group for some reason */
+	lg = ac->ac_lg;
+	if (lg == NULL)
+		return 0;
+	order  = fls(ac->ac_o_ex.fe_len) - 1;
+	if (order > PREALLOC_TB_SIZE - 1)
+		/* The max size of hash table is PREALLOC_TB_SIZE */
+		order = PREALLOC_TB_SIZE - 1;
+
+	goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex);
+	/*
+	 * search for the prealloc space that is having
+	 * minimal distance from the goal block.
+	 */
+	for (i = order; i < PREALLOC_TB_SIZE; i++) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[i],
+					pa_inode_list) {
+			spin_lock(&pa->pa_lock);
+			if (pa->pa_deleted == 0 &&
+					pa->pa_free >= ac->ac_o_ex.fe_len) {
+
+				cpa = ext4_mb_check_group_pa(goal_block,
+								pa, cpa);
+			}
+			spin_unlock(&pa->pa_lock);
+		}
+		rcu_read_unlock();
+	}
+	if (cpa) {
+		ext4_mb_use_group_pa(ac, cpa);
+		ac->ac_criteria = 20;
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * the function goes through all block freed in the group
+ * but not yet committed and marks them used in in-core bitmap.
+ * buddy must be generated from this bitmap
+ * Need to be called with the ext4 group lock held
+ */
+static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+						ext4_group_t group)
+{
+	struct rb_node *n;
+	struct ext4_group_info *grp;
+	struct ext4_free_data *entry;
+
+	grp = ext4_get_group_info(sb, group);
+	n = rb_first(&(grp->bb_free_root));
+
+	while (n) {
+		entry = rb_entry(n, struct ext4_free_data, node);
+		mb_set_bits(bitmap, entry->start_blk, entry->count);
+		n = rb_next(n);
+	}
+	return;
+}
+
+/*
+ * the function goes through all preallocation in this group and marks them
+ * used in in-core bitmap. buddy must be generated from this bitmap
+ * Need to be called with ext4 group lock held
+ */
+static noinline_for_stack
+void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+					ext4_group_t group)
+{
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_prealloc_space *pa;
+	struct list_head *cur;
+	ext4_group_t groupnr;
+	ext4_grpblk_t start;
+	int preallocated = 0;
+	int count = 0;
+	int len;
+
+	/* all form of preallocation discards first load group,
+	 * so the only competing code is preallocation use.
+	 * we don't need any locking here
+	 * notice we do NOT ignore preallocations with pa_deleted
+	 * otherwise we could leave used blocks available for
+	 * allocation in buddy when concurrent ext4_mb_put_pa()
+	 * is dropping preallocation
+	 */
+	list_for_each(cur, &grp->bb_prealloc_list) {
+		pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list);
+		spin_lock(&pa->pa_lock);
+		ext4_get_group_no_and_offset(sb, pa->pa_pstart,
+					     &groupnr, &start);
+		len = pa->pa_len;
+		spin_unlock(&pa->pa_lock);
+		if (unlikely(len == 0))
+			continue;
+		BUG_ON(groupnr != group);
+		mb_set_bits(bitmap, start, len);
+		preallocated += len;
+		count++;
+	}
+	mb_debug(1, "prellocated %u for group %u\n", preallocated, group);
+}
+
+static void ext4_mb_pa_callback(struct rcu_head *head)
+{
+	struct ext4_prealloc_space *pa;
+	pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+	kmem_cache_free(ext4_pspace_cachep, pa);
+}
+
+/*
+ * drops a reference to preallocated space descriptor
+ * if this was the last reference and the space is consumed
+ */
+static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
+			struct super_block *sb, struct ext4_prealloc_space *pa)
+{
+	ext4_group_t grp;
+	ext4_fsblk_t grp_blk;
+
+	if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
+		return;
+
+	/* in this short window concurrent discard can set pa_deleted */
+	spin_lock(&pa->pa_lock);
+	if (pa->pa_deleted == 1) {
+		spin_unlock(&pa->pa_lock);
+		return;
+	}
+
+	pa->pa_deleted = 1;
+	spin_unlock(&pa->pa_lock);
+
+	grp_blk = pa->pa_pstart;
+	/*
+	 * If doing group-based preallocation, pa_pstart may be in the
+	 * next group when pa is used up
+	 */
+	if (pa->pa_type == MB_GROUP_PA)
+		grp_blk--;
+
+	ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL);
+
+	/*
+	 * possible race:
+	 *
+	 *  P1 (buddy init)			P2 (regular allocation)
+	 *					find block B in PA
+	 *  copy on-disk bitmap to buddy
+	 *  					mark B in on-disk bitmap
+	 *					drop PA from group
+	 *  mark all PAs in buddy
+	 *
+	 * thus, P1 initializes buddy with B available. to prevent this
+	 * we make "copy" and "mark all PAs" atomic and serialize "drop PA"
+	 * against that pair
+	 */
+	ext4_lock_group(sb, grp);
+	list_del(&pa->pa_group_list);
+	ext4_unlock_group(sb, grp);
+
+	spin_lock(pa->pa_obj_lock);
+	list_del_rcu(&pa->pa_inode_list);
+	spin_unlock(pa->pa_obj_lock);
+
+	call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+}
+
+/*
+ * creates new preallocated space for given inode
+ */
+static noinline_for_stack int
+ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
+{
+	struct super_block *sb = ac->ac_sb;
+	struct ext4_prealloc_space *pa;
+	struct ext4_group_info *grp;
+	struct ext4_inode_info *ei;
+
+	/* preallocate only when found space is larger then requested */
+	BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len);
+	BUG_ON(ac->ac_status != AC_STATUS_FOUND);
+	BUG_ON(!S_ISREG(ac->ac_inode->i_mode));
+
+	pa = kmem_cache_alloc(ext4_pspace_cachep, GFP_NOFS);
+	if (pa == NULL)
+		return -ENOMEM;
+
+	if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) {
+		int winl;
+		int wins;
+		int win;
+		int offs;
+
+		/* we can't allocate as much as normalizer wants.
+		 * so, found space must get proper lstart
+		 * to cover original request */
+		BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
+		BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
+
+		/* we're limited by original request in that
+		 * logical block must be covered any way
+		 * winl is window we can move our chunk within */
+		winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
+
+		/* also, we should cover whole original request */
+		wins = ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len;
+
+		/* the smallest one defines real window */
+		win = min(winl, wins);
+
+		offs = ac->ac_o_ex.fe_logical % ac->ac_b_ex.fe_len;
+		if (offs && offs < win)
+			win = offs;
+
+		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - win;
+		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
+		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
+	}
+
+	/* preallocation can change ac_b_ex, thus we store actually
+	 * allocated blocks for history */
+	ac->ac_f_ex = ac->ac_b_ex;
+
+	pa->pa_lstart = ac->ac_b_ex.fe_logical;
+	pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
+	pa->pa_len = ac->ac_b_ex.fe_len;
+	pa->pa_free = pa->pa_len;
+	atomic_set(&pa->pa_count, 1);
+	spin_lock_init(&pa->pa_lock);
+	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_group_list);
+	pa->pa_deleted = 0;
+	pa->pa_type = MB_INODE_PA;
+
+	mb_debug(1, "new inode pa %p: %llu/%u for %u\n", pa,
+			pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+	trace_ext4_mb_new_inode_pa(ac, pa);
+
+	ext4_mb_use_inode_pa(ac, pa);
+	atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
+
+	ei = EXT4_I(ac->ac_inode);
+	grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
+
+	pa->pa_obj_lock = &ei->i_prealloc_lock;
+	pa->pa_inode = ac->ac_inode;
+
+	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+	list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
+	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+
+	spin_lock(pa->pa_obj_lock);
+	list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list);
+	spin_unlock(pa->pa_obj_lock);
+
+	return 0;
+}
+
+/*
+ * creates new preallocated space for locality group inodes belongs to
+ */
+static noinline_for_stack int
+ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
+{
+	struct super_block *sb = ac->ac_sb;
+	struct ext4_locality_group *lg;
+	struct ext4_prealloc_space *pa;
+	struct ext4_group_info *grp;
+
+	/* preallocate only when found space is larger then requested */
+	BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len);
+	BUG_ON(ac->ac_status != AC_STATUS_FOUND);
+	BUG_ON(!S_ISREG(ac->ac_inode->i_mode));
+
+	BUG_ON(ext4_pspace_cachep == NULL);
+	pa = kmem_cache_alloc(ext4_pspace_cachep, GFP_NOFS);
+	if (pa == NULL)
+		return -ENOMEM;
+
+	/* preallocation can change ac_b_ex, thus we store actually
+	 * allocated blocks for history */
+	ac->ac_f_ex = ac->ac_b_ex;
+
+	pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
+	pa->pa_lstart = pa->pa_pstart;
+	pa->pa_len = ac->ac_b_ex.fe_len;
+	pa->pa_free = pa->pa_len;
+	atomic_set(&pa->pa_count, 1);
+	spin_lock_init(&pa->pa_lock);
+	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_group_list);
+	pa->pa_deleted = 0;
+	pa->pa_type = MB_GROUP_PA;
+
+	mb_debug(1, "new group pa %p: %llu/%u for %u\n", pa,
+			pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+	trace_ext4_mb_new_group_pa(ac, pa);
+
+	ext4_mb_use_group_pa(ac, pa);
+	atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
+
+	grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
+	lg = ac->ac_lg;
+	BUG_ON(lg == NULL);
+
+	pa->pa_obj_lock = &lg->lg_prealloc_lock;
+	pa->pa_inode = NULL;
+
+	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+	list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
+	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+
+	/*
+	 * We will later add the new pa to the right bucket
+	 * after updating the pa_free in ext4_mb_release_context
+	 */
+	return 0;
+}
+
+static int ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
+{
+	int err;
+
+	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
+		err = ext4_mb_new_group_pa(ac);
+	else
+		err = ext4_mb_new_inode_pa(ac);
+	return err;
+}
+
+/*
+ * finds all unused blocks in on-disk bitmap, frees them in
+ * in-core bitmap and buddy.
+ * @pa must be unlinked from inode and group lists, so that
+ * nobody else can find/use it.
+ * the caller MUST hold group/inode locks.
+ * TODO: optimize the case when there are no in-core structures yet
+ */
+static noinline_for_stack int
+ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
+			struct ext4_prealloc_space *pa)
+{
+	struct super_block *sb = e4b->bd_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	unsigned int end;
+	unsigned int next;
+	ext4_group_t group;
+	ext4_grpblk_t bit;
+	unsigned long long grp_blk_start;
+	int err = 0;
+	int free = 0;
+
+	BUG_ON(pa->pa_deleted == 0);
+	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
+	grp_blk_start = pa->pa_pstart - bit;
+	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
+	end = bit + pa->pa_len;
+
+	while (bit < end) {
+		bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit);
+		if (bit >= end)
+			break;
+		next = mb_find_next_bit(bitmap_bh->b_data, end, bit);
+		mb_debug(1, "    free preallocated %u/%u in group %u\n",
+			 (unsigned) ext4_group_first_block_no(sb, group) + bit,
+			 (unsigned) next - bit, (unsigned) group);
+		free += next - bit;
+
+		trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit);
+		trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit,
+					       next - bit);
+		mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
+		bit = next + 1;
+	}
+	if (free != pa->pa_free) {
+		printk(KERN_CRIT "pa %p: logic %lu, phys. %lu, len %lu\n",
+			pa, (unsigned long) pa->pa_lstart,
+			(unsigned long) pa->pa_pstart,
+			(unsigned long) pa->pa_len);
+		ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u",
+					free, pa->pa_free);
+		/*
+		 * pa is already deleted so we use the value obtained
+		 * from the bitmap and continue.
+		 */
+	}
+	atomic_add(free, &sbi->s_mb_discarded);
+
+	return err;
+}
+
+static noinline_for_stack int
+ext4_mb_release_group_pa(struct ext4_buddy *e4b,
+				struct ext4_prealloc_space *pa)
+{
+	struct super_block *sb = e4b->bd_sb;
+	ext4_group_t group;
+	ext4_grpblk_t bit;
+
+	trace_ext4_mb_release_group_pa(pa);
+	BUG_ON(pa->pa_deleted == 0);
+	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
+	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
+	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
+	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
+	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
+
+	return 0;
+}
+
+/*
+ * releases all preallocations in given group
+ *
+ * first, we need to decide discard policy:
+ * - when do we discard
+ *   1) ENOSPC
+ * - how many do we discard
+ *   1) how many requested
+ */
+static noinline_for_stack int
+ext4_mb_discard_group_preallocations(struct super_block *sb,
+					ext4_group_t group, int needed)
+{
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext4_prealloc_space *pa, *tmp;
+	struct list_head list;
+	struct ext4_buddy e4b;
+	int err;
+	int busy = 0;
+	int free = 0;
+
+	mb_debug(1, "discard preallocation for group %u\n", group);
+
+	if (list_empty(&grp->bb_prealloc_list))
+		return 0;
+
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (bitmap_bh == NULL) {
+		ext4_error(sb, "Error reading block bitmap for %u", group);
+		return 0;
+	}
+
+	err = ext4_mb_load_buddy(sb, group, &e4b);
+	if (err) {
+		ext4_error(sb, "Error loading buddy information for %u", group);
+		put_bh(bitmap_bh);
+		return 0;
+	}
+
+	if (needed == 0)
+		needed = EXT4_BLOCKS_PER_GROUP(sb) + 1;
+
+	INIT_LIST_HEAD(&list);
+repeat:
+	ext4_lock_group(sb, group);
+	list_for_each_entry_safe(pa, tmp,
+				&grp->bb_prealloc_list, pa_group_list) {
+		spin_lock(&pa->pa_lock);
+		if (atomic_read(&pa->pa_count)) {
+			spin_unlock(&pa->pa_lock);
+			busy = 1;
+			continue;
+		}
+		if (pa->pa_deleted) {
+			spin_unlock(&pa->pa_lock);
+			continue;
+		}
+
+		/* seems this one can be freed ... */
+		pa->pa_deleted = 1;
+
+		/* we can trust pa_free ... */
+		free += pa->pa_free;
+
+		spin_unlock(&pa->pa_lock);
+
+		list_del(&pa->pa_group_list);
+		list_add(&pa->u.pa_tmp_list, &list);
+	}
+
+	/* if we still need more blocks and some PAs were used, try again */
+	if (free < needed && busy) {
+		busy = 0;
+		ext4_unlock_group(sb, group);
+		/*
+		 * Yield the CPU here so that we don't get soft lockup
+		 * in non preempt case.
+		 */
+		yield();
+		goto repeat;
+	}
+
+	/* found anything to free? */
+	if (list_empty(&list)) {
+		BUG_ON(free != 0);
+		goto out;
+	}
+
+	/* now free all selected PAs */
+	list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) {
+
+		/* remove from object (inode or locality group) */
+		spin_lock(pa->pa_obj_lock);
+		list_del_rcu(&pa->pa_inode_list);
+		spin_unlock(pa->pa_obj_lock);
+
+		if (pa->pa_type == MB_GROUP_PA)
+			ext4_mb_release_group_pa(&e4b, pa);
+		else
+			ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
+
+		list_del(&pa->u.pa_tmp_list);
+		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+	}
+
+out:
+	ext4_unlock_group(sb, group);
+	ext4_mb_unload_buddy(&e4b);
+	put_bh(bitmap_bh);
+	return free;
+}
+
+/*
+ * releases all non-used preallocated blocks for given inode
+ *
+ * It's important to discard preallocations under i_data_sem
+ * We don't want another block to be served from the prealloc
+ * space when we are discarding the inode prealloc space.
+ *
+ * FIXME!! Make sure it is valid at all the call sites
+ */
+void ext4_discard_preallocations(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct super_block *sb = inode->i_sb;
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext4_prealloc_space *pa, *tmp;
+	ext4_group_t group = 0;
+	struct list_head list;
+	struct ext4_buddy e4b;
+	int err;
+
+	if (!S_ISREG(inode->i_mode)) {
+		/*BUG_ON(!list_empty(&ei->i_prealloc_list));*/
+		return;
+	}
+
+	mb_debug(1, "discard preallocation for inode %lu\n", inode->i_ino);
+	trace_ext4_discard_preallocations(inode);
+
+	INIT_LIST_HEAD(&list);
+
+repeat:
+	/* first, collect all pa's in the inode */
+	spin_lock(&ei->i_prealloc_lock);
+	while (!list_empty(&ei->i_prealloc_list)) {
+		pa = list_entry(ei->i_prealloc_list.next,
+				struct ext4_prealloc_space, pa_inode_list);
+		BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock);
+		spin_lock(&pa->pa_lock);
+		if (atomic_read(&pa->pa_count)) {
+			/* this shouldn't happen often - nobody should
+			 * use preallocation while we're discarding it */
+			spin_unlock(&pa->pa_lock);
+			spin_unlock(&ei->i_prealloc_lock);
+			printk(KERN_ERR "uh-oh! used pa while discarding\n");
+			WARN_ON(1);
+			schedule_timeout_uninterruptible(HZ);
+			goto repeat;
+
+		}
+		if (pa->pa_deleted == 0) {
+			pa->pa_deleted = 1;
+			spin_unlock(&pa->pa_lock);
+			list_del_rcu(&pa->pa_inode_list);
+			list_add(&pa->u.pa_tmp_list, &list);
+			continue;
+		}
+
+		/* someone is deleting pa right now */
+		spin_unlock(&pa->pa_lock);
+		spin_unlock(&ei->i_prealloc_lock);
+
+		/* we have to wait here because pa_deleted
+		 * doesn't mean pa is already unlinked from
+		 * the list. as we might be called from
+		 * ->clear_inode() the inode will get freed
+		 * and concurrent thread which is unlinking
+		 * pa from inode's list may access already
+		 * freed memory, bad-bad-bad */
+
+		/* XXX: if this happens too often, we can
+		 * add a flag to force wait only in case
+		 * of ->clear_inode(), but not in case of
+		 * regular truncate */
+		schedule_timeout_uninterruptible(HZ);
+		goto repeat;
+	}
+	spin_unlock(&ei->i_prealloc_lock);
+
+	list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) {
+		BUG_ON(pa->pa_type != MB_INODE_PA);
+		ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
+
+		err = ext4_mb_load_buddy(sb, group, &e4b);
+		if (err) {
+			ext4_error(sb, "Error loading buddy information for %u",
+					group);
+			continue;
+		}
+
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (bitmap_bh == NULL) {
+			ext4_error(sb, "Error reading block bitmap for %u",
+					group);
+			ext4_mb_unload_buddy(&e4b);
+			continue;
+		}
+
+		ext4_lock_group(sb, group);
+		list_del(&pa->pa_group_list);
+		ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
+		ext4_unlock_group(sb, group);
+
+		ext4_mb_unload_buddy(&e4b);
+		put_bh(bitmap_bh);
+
+		list_del(&pa->u.pa_tmp_list);
+		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+	}
+}
+
+#ifdef CONFIG_EXT4_DEBUG
+static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
+{
+	struct super_block *sb = ac->ac_sb;
+	ext4_group_t ngroups, i;
+
+	if (!mb_enable_debug ||
+	    (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
+		return;
+
+	printk(KERN_ERR "EXT4-fs: Can't allocate:"
+			" Allocation context details:\n");
+	printk(KERN_ERR "EXT4-fs: status %d flags %d\n",
+			ac->ac_status, ac->ac_flags);
+	printk(KERN_ERR "EXT4-fs: orig %lu/%lu/%lu@%lu, goal %lu/%lu/%lu@%lu, "
+			"best %lu/%lu/%lu@%lu cr %d\n",
+			(unsigned long)ac->ac_o_ex.fe_group,
+			(unsigned long)ac->ac_o_ex.fe_start,
+			(unsigned long)ac->ac_o_ex.fe_len,
+			(unsigned long)ac->ac_o_ex.fe_logical,
+			(unsigned long)ac->ac_g_ex.fe_group,
+			(unsigned long)ac->ac_g_ex.fe_start,
+			(unsigned long)ac->ac_g_ex.fe_len,
+			(unsigned long)ac->ac_g_ex.fe_logical,
+			(unsigned long)ac->ac_b_ex.fe_group,
+			(unsigned long)ac->ac_b_ex.fe_start,
+			(unsigned long)ac->ac_b_ex.fe_len,
+			(unsigned long)ac->ac_b_ex.fe_logical,
+			(int)ac->ac_criteria);
+	printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned,
+		ac->ac_found);
+	printk(KERN_ERR "EXT4-fs: groups: \n");
+	ngroups = ext4_get_groups_count(sb);
+	for (i = 0; i < ngroups; i++) {
+		struct ext4_group_info *grp = ext4_get_group_info(sb, i);
+		struct ext4_prealloc_space *pa;
+		ext4_grpblk_t start;
+		struct list_head *cur;
+		ext4_lock_group(sb, i);
+		list_for_each(cur, &grp->bb_prealloc_list) {
+			pa = list_entry(cur, struct ext4_prealloc_space,
+					pa_group_list);
+			spin_lock(&pa->pa_lock);
+			ext4_get_group_no_and_offset(sb, pa->pa_pstart,
+						     NULL, &start);
+			spin_unlock(&pa->pa_lock);
+			printk(KERN_ERR "PA:%u:%d:%u \n", i,
+			       start, pa->pa_len);
+		}
+		ext4_unlock_group(sb, i);
+
+		if (grp->bb_free == 0)
+			continue;
+		printk(KERN_ERR "%u: %d/%d \n",
+		       i, grp->bb_free, grp->bb_fragments);
+	}
+	printk(KERN_ERR "\n");
+}
+#else
+static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac)
+{
+	return;
+}
+#endif
+
+/*
+ * We use locality group preallocation for small size file. The size of the
+ * file is determined by the current size or the resulting size after
+ * allocation which ever is larger
+ *
+ * One can tune this size via /sys/fs/ext4/<partition>/mb_stream_req
+ */
+static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	int bsbits = ac->ac_sb->s_blocksize_bits;
+	loff_t size, isize;
+
+	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
+		return;
+
+	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+		return;
+
+	size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
+		>> bsbits;
+
+	if ((size == isize) &&
+	    !ext4_fs_is_busy(sbi) &&
+	    (atomic_read(&ac->ac_inode->i_writecount) == 0)) {
+		ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
+		return;
+	}
+
+	/* don't use group allocation for large files */
+	size = max(size, isize);
+	if (size > sbi->s_mb_stream_request) {
+		ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
+		return;
+	}
+
+	BUG_ON(ac->ac_lg != NULL);
+	/*
+	 * locality group prealloc space are per cpu. The reason for having
+	 * per cpu locality group is to reduce the contention between block
+	 * request from multiple CPUs.
+	 */
+	ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
+
+	/* we're going to use group allocation */
+	ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
+
+	/* serialize all allocations in the group */
+	mutex_lock(&ac->ac_lg->lg_mutex);
+}
+
+static noinline_for_stack int
+ext4_mb_initialize_context(struct ext4_allocation_context *ac,
+				struct ext4_allocation_request *ar)
+{
+	struct super_block *sb = ar->inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	ext4_group_t group;
+	unsigned int len;
+	ext4_fsblk_t goal;
+	ext4_grpblk_t block;
+
+	/* we can't allocate > group size */
+	len = ar->len;
+
+	/* just a dirty hack to filter too big requests  */
+	if (len >= EXT4_BLOCKS_PER_GROUP(sb) - 10)
+		len = EXT4_BLOCKS_PER_GROUP(sb) - 10;
+
+	/* start searching from the goal */
+	goal = ar->goal;
+	if (goal < le32_to_cpu(es->s_first_data_block) ||
+			goal >= ext4_blocks_count(es))
+		goal = le32_to_cpu(es->s_first_data_block);
+	ext4_get_group_no_and_offset(sb, goal, &group, &block);
+
+	/* set up allocation goals */
+	memset(ac, 0, sizeof(struct ext4_allocation_context));
+	ac->ac_b_ex.fe_logical = ar->logical;
+	ac->ac_status = AC_STATUS_CONTINUE;
+	ac->ac_sb = sb;
+	ac->ac_inode = ar->inode;
+	ac->ac_o_ex.fe_logical = ar->logical;
+	ac->ac_o_ex.fe_group = group;
+	ac->ac_o_ex.fe_start = block;
+	ac->ac_o_ex.fe_len = len;
+	ac->ac_g_ex.fe_logical = ar->logical;
+	ac->ac_g_ex.fe_group = group;
+	ac->ac_g_ex.fe_start = block;
+	ac->ac_g_ex.fe_len = len;
+	ac->ac_flags = ar->flags;
+
+	/* we have to define context: we'll we work with a file or
+	 * locality group. this is a policy, actually */
+	ext4_mb_group_or_file(ac);
+
+	mb_debug(1, "init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, "
+			"left: %u/%u, right %u/%u to %swritable\n",
+			(unsigned) ar->len, (unsigned) ar->logical,
+			(unsigned) ar->goal, ac->ac_flags, ac->ac_2order,
+			(unsigned) ar->lleft, (unsigned) ar->pleft,
+			(unsigned) ar->lright, (unsigned) ar->pright,
+			atomic_read(&ar->inode->i_writecount) ? "" : "non-");
+	return 0;
+
+}
+
+static noinline_for_stack void
+ext4_mb_discard_lg_preallocations(struct super_block *sb,
+					struct ext4_locality_group *lg,
+					int order, int total_entries)
+{
+	ext4_group_t group = 0;
+	struct ext4_buddy e4b;
+	struct list_head discard_list;
+	struct ext4_prealloc_space *pa, *tmp;
+
+	mb_debug(1, "discard locality group preallocation\n");
+
+	INIT_LIST_HEAD(&discard_list);
+
+	spin_lock(&lg->lg_prealloc_lock);
+	list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order],
+						pa_inode_list) {
+		spin_lock(&pa->pa_lock);
+		if (atomic_read(&pa->pa_count)) {
+			/*
+			 * This is the pa that we just used
+			 * for block allocation. So don't
+			 * free that
+			 */
+			spin_unlock(&pa->pa_lock);
+			continue;
+		}
+		if (pa->pa_deleted) {
+			spin_unlock(&pa->pa_lock);
+			continue;
+		}
+		/* only lg prealloc space */
+		BUG_ON(pa->pa_type != MB_GROUP_PA);
+
+		/* seems this one can be freed ... */
+		pa->pa_deleted = 1;
+		spin_unlock(&pa->pa_lock);
+
+		list_del_rcu(&pa->pa_inode_list);
+		list_add(&pa->u.pa_tmp_list, &discard_list);
+
+		total_entries--;
+		if (total_entries <= 5) {
+			/*
+			 * we want to keep only 5 entries
+			 * allowing it to grow to 8. This
+			 * mak sure we don't call discard
+			 * soon for this list.
+			 */
+			break;
+		}
+	}
+	spin_unlock(&lg->lg_prealloc_lock);
+
+	list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) {
+
+		ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
+		if (ext4_mb_load_buddy(sb, group, &e4b)) {
+			ext4_error(sb, "Error loading buddy information for %u",
+					group);
+			continue;
+		}
+		ext4_lock_group(sb, group);
+		list_del(&pa->pa_group_list);
+		ext4_mb_release_group_pa(&e4b, pa);
+		ext4_unlock_group(sb, group);
+
+		ext4_mb_unload_buddy(&e4b);
+		list_del(&pa->u.pa_tmp_list);
+		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+	}
+}
+
+/*
+ * We have incremented pa_count. So it cannot be freed at this
+ * point. Also we hold lg_mutex. So no parallel allocation is
+ * possible from this lg. That means pa_free cannot be updated.
+ *
+ * A parallel ext4_mb_discard_group_preallocations is possible.
+ * which can cause the lg_prealloc_list to be updated.
+ */
+
+static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
+{
+	int order, added = 0, lg_prealloc_count = 1;
+	struct super_block *sb = ac->ac_sb;
+	struct ext4_locality_group *lg = ac->ac_lg;
+	struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa;
+
+	order = fls(pa->pa_free) - 1;
+	if (order > PREALLOC_TB_SIZE - 1)
+		/* The max size of hash table is PREALLOC_TB_SIZE */
+		order = PREALLOC_TB_SIZE - 1;
+	/* Add the prealloc space to lg */
+	rcu_read_lock();
+	list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order],
+						pa_inode_list) {
+		spin_lock(&tmp_pa->pa_lock);
+		if (tmp_pa->pa_deleted) {
+			spin_unlock(&tmp_pa->pa_lock);
+			continue;
+		}
+		if (!added && pa->pa_free < tmp_pa->pa_free) {
+			/* Add to the tail of the previous entry */
+			list_add_tail_rcu(&pa->pa_inode_list,
+						&tmp_pa->pa_inode_list);
+			added = 1;
+			/*
+			 * we want to count the total
+			 * number of entries in the list
+			 */
+		}
+		spin_unlock(&tmp_pa->pa_lock);
+		lg_prealloc_count++;
+	}
+	if (!added)
+		list_add_tail_rcu(&pa->pa_inode_list,
+					&lg->lg_prealloc_list[order]);
+	rcu_read_unlock();
+
+	/* Now trim the list to be not more than 8 elements */
+	if (lg_prealloc_count > 8) {
+		ext4_mb_discard_lg_preallocations(sb, lg,
+						order, lg_prealloc_count);
+		return;
+	}
+	return ;
+}
+
+/*
+ * release all resource we used in allocation
+ */
+static int ext4_mb_release_context(struct ext4_allocation_context *ac)
+{
+	struct ext4_prealloc_space *pa = ac->ac_pa;
+	if (pa) {
+		if (pa->pa_type == MB_GROUP_PA) {
+			/* see comment in ext4_mb_use_group_pa() */
+			spin_lock(&pa->pa_lock);
+			pa->pa_pstart += ac->ac_b_ex.fe_len;
+			pa->pa_lstart += ac->ac_b_ex.fe_len;
+			pa->pa_free -= ac->ac_b_ex.fe_len;
+			pa->pa_len -= ac->ac_b_ex.fe_len;
+			spin_unlock(&pa->pa_lock);
+		}
+	}
+	if (pa) {
+		/*
+		 * We want to add the pa to the right bucket.
+		 * Remove it from the list and while adding
+		 * make sure the list to which we are adding
+		 * doesn't grow big.
+		 */
+		if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) {
+			spin_lock(pa->pa_obj_lock);
+			list_del_rcu(&pa->pa_inode_list);
+			spin_unlock(pa->pa_obj_lock);
+			ext4_mb_add_n_trim(ac);
+		}
+		ext4_mb_put_pa(ac, ac->ac_sb, pa);
+	}
+	if (ac->ac_bitmap_page)
+		page_cache_release(ac->ac_bitmap_page);
+	if (ac->ac_buddy_page)
+		page_cache_release(ac->ac_buddy_page);
+	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
+		mutex_unlock(&ac->ac_lg->lg_mutex);
+	ext4_mb_collect_stats(ac);
+	return 0;
+}
+
+static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
+{
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+	int ret;
+	int freed = 0;
+
+	trace_ext4_mb_discard_preallocations(sb, needed);
+	for (i = 0; i < ngroups && needed > 0; i++) {
+		ret = ext4_mb_discard_group_preallocations(sb, i, needed);
+		freed += ret;
+		needed -= ret;
+	}
+
+	return freed;
+}
+
+/*
+ * Main entry point into mballoc to allocate blocks
+ * it tries to use preallocation first, then falls back
+ * to usual allocation
+ */
+ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp)
+{
+	int freed;
+	struct ext4_allocation_context *ac = NULL;
+	struct ext4_sb_info *sbi;
+	struct super_block *sb;
+	ext4_fsblk_t block = 0;
+	unsigned int inquota = 0;
+	unsigned int reserv_blks = 0;
+
+	sb = ar->inode->i_sb;
+	sbi = EXT4_SB(sb);
+
+	trace_ext4_request_blocks(ar);
+
+	/*
+	 * For delayed allocation, we could skip the ENOSPC and
+	 * EDQUOT check, as blocks and quotas have been already
+	 * reserved when data being copied into pagecache.
+	 */
+	if (ext4_test_inode_state(ar->inode, EXT4_STATE_DELALLOC_RESERVED))
+		ar->flags |= EXT4_MB_DELALLOC_RESERVED;
+	else {
+		/* Without delayed allocation we need to verify
+		 * there is enough free blocks to do block allocation
+		 * and verify allocation doesn't exceed the quota limits.
+		 */
+		while (ar->len &&
+			ext4_claim_free_blocks(sbi, ar->len, ar->flags)) {
+
+			/* let others to free the space */
+			yield();
+			ar->len = ar->len >> 1;
+		}
+		if (!ar->len) {
+			*errp = -ENOSPC;
+			return 0;
+		}
+		reserv_blks = ar->len;
+		if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) {
+			dquot_alloc_block_nofail(ar->inode, ar->len);
+		} else {
+			while (ar->len &&
+				dquot_alloc_block(ar->inode, ar->len)) {
+
+				ar->flags |= EXT4_MB_HINT_NOPREALLOC;
+				ar->len--;
+			}
+		}
+		inquota = ar->len;
+		if (ar->len == 0) {
+			*errp = -EDQUOT;
+			goto out;
+		}
+	}
+
+	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+	if (!ac) {
+		ar->len = 0;
+		*errp = -ENOMEM;
+		goto out;
+	}
+
+	*errp = ext4_mb_initialize_context(ac, ar);
+	if (*errp) {
+		ar->len = 0;
+		goto out;
+	}
+
+	ac->ac_op = EXT4_MB_HISTORY_PREALLOC;
+	if (!ext4_mb_use_preallocated(ac)) {
+		ac->ac_op = EXT4_MB_HISTORY_ALLOC;
+		ext4_mb_normalize_request(ac, ar);
+repeat:
+		/* allocate space in core */
+		*errp = ext4_mb_regular_allocator(ac);
+		if (*errp)
+			goto errout;
+
+		/* as we've just preallocated more space than
+		 * user requested orinally, we store allocated
+		 * space in a special descriptor */
+		if (ac->ac_status == AC_STATUS_FOUND &&
+				ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len)
+			ext4_mb_new_preallocation(ac);
+	}
+	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
+		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
+		if (*errp == -EAGAIN) {
+			/*
+			 * drop the reference that we took
+			 * in ext4_mb_use_best_found
+			 */
+			ext4_mb_release_context(ac);
+			ac->ac_b_ex.fe_group = 0;
+			ac->ac_b_ex.fe_start = 0;
+			ac->ac_b_ex.fe_len = 0;
+			ac->ac_status = AC_STATUS_CONTINUE;
+			goto repeat;
+		} else if (*errp)
+		errout:
+			ext4_discard_allocated_blocks(ac);
+		else {
+			block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
+			ar->len = ac->ac_b_ex.fe_len;
+		}
+	} else {
+		freed  = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len);
+		if (freed)
+			goto repeat;
+		*errp = -ENOSPC;
+	}
+
+	if (*errp) {
+		ac->ac_b_ex.fe_len = 0;
+		ar->len = 0;
+		ext4_mb_show_ac(ac);
+	}
+	ext4_mb_release_context(ac);
+out:
+	if (ac)
+		kmem_cache_free(ext4_ac_cachep, ac);
+	if (inquota && ar->len < inquota)
+		dquot_free_block(ar->inode, inquota - ar->len);
+	if (!ar->len) {
+		if (!ext4_test_inode_state(ar->inode,
+					   EXT4_STATE_DELALLOC_RESERVED))
+			/* release all the reserved blocks if non delalloc */
+			percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+						reserv_blks);
+	}
+
+	trace_ext4_allocate_blocks(ar, (unsigned long long)block);
+
+	return block;
+}
+
+/*
+ * We can merge two free data extents only if the physical blocks
+ * are contiguous, AND the extents were freed by the same transaction,
+ * AND the blocks are associated with the same group.
+ */
+static int can_merge(struct ext4_free_data *entry1,
+			struct ext4_free_data *entry2)
+{
+	if ((entry1->t_tid == entry2->t_tid) &&
+	    (entry1->group == entry2->group) &&
+	    ((entry1->start_blk + entry1->count) == entry2->start_blk))
+		return 1;
+	return 0;
+}
+
+static noinline_for_stack int
+ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
+		      struct ext4_free_data *new_entry)
+{
+	ext4_group_t group = e4b->bd_group;
+	ext4_grpblk_t block;
+	struct ext4_free_data *entry;
+	struct ext4_group_info *db = e4b->bd_info;
+	struct super_block *sb = e4b->bd_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct rb_node **n = &db->bb_free_root.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node;
+
+	BUG_ON(!ext4_handle_valid(handle));
+	BUG_ON(e4b->bd_bitmap_page == NULL);
+	BUG_ON(e4b->bd_buddy_page == NULL);
+
+	new_node = &new_entry->node;
+	block = new_entry->start_blk;
+
+	if (!*n) {
+		/* first free block exent. We need to
+		   protect buddy cache from being freed,
+		 * otherwise we'll refresh it from
+		 * on-disk bitmap and lose not-yet-available
+		 * blocks */
+		page_cache_get(e4b->bd_buddy_page);
+		page_cache_get(e4b->bd_bitmap_page);
+	}
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_free_data, node);
+		if (block < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (block >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else {
+			ext4_grp_locked_error(sb, group, 0,
+				ext4_group_first_block_no(sb, group) + block,
+				"Block already on to-be-freed list");
+			return 0;
+		}
+	}
+
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &db->bb_free_root);
+
+	/* Now try to see the extent can be merged to left and right */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_free_data, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &(db->bb_free_root));
+			spin_lock(&sbi->s_md_lock);
+			list_del(&entry->list);
+			spin_unlock(&sbi->s_md_lock);
+			kmem_cache_free(ext4_free_ext_cachep, entry);
+		}
+	}
+
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_free_data, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &(db->bb_free_root));
+			spin_lock(&sbi->s_md_lock);
+			list_del(&entry->list);
+			spin_unlock(&sbi->s_md_lock);
+			kmem_cache_free(ext4_free_ext_cachep, entry);
+		}
+	}
+	/* Add the extent to transaction's private list */
+	spin_lock(&sbi->s_md_lock);
+	list_add(&new_entry->list, &handle->h_transaction->t_private_list);
+	spin_unlock(&sbi->s_md_lock);
+	return 0;
+}
+
+/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle:		handle for this transaction
+ * @inode:		inode
+ * @block:		start physical block to free
+ * @count:		number of blocks to count
+ * @flags:		flags used by ext4_free_blocks
+ */
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+		      struct buffer_head *bh, ext4_fsblk_t block,
+		      unsigned long count, int flags)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct super_block *sb = inode->i_sb;
+	struct ext4_group_desc *gdp;
+	unsigned long freed = 0;
+	unsigned int overflow;
+	ext4_grpblk_t bit;
+	struct buffer_head *gd_bh;
+	ext4_group_t block_group;
+	struct ext4_sb_info *sbi;
+	struct ext4_buddy e4b;
+	int err = 0;
+	int ret;
+
+	if (bh) {
+		if (block)
+			BUG_ON(block != bh->b_blocknr);
+		else
+			block = bh->b_blocknr;
+	}
+
+	sbi = EXT4_SB(sb);
+	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
+	    !ext4_data_block_valid(sbi, block, count)) {
+		ext4_error(sb, "Freeing blocks not in datazone - "
+			   "block = %llu, count = %lu", block, count);
+		goto error_return;
+	}
+
+	ext4_debug("freeing block %llu\n", block);
+	trace_ext4_free_blocks(inode, block, count, flags);
+
+	if (flags & EXT4_FREE_BLOCKS_FORGET) {
+		struct buffer_head *tbh = bh;
+		int i;
+
+		BUG_ON(bh && (count > 1));
+
+		for (i = 0; i < count; i++) {
+			if (!bh)
+				tbh = sb_find_get_block(inode->i_sb,
+							block + i);
+			if (unlikely(!tbh))
+				continue;
+			ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
+				    inode, tbh, block + i);
+		}
+	}
+
+	/*
+	 * We need to make sure we don't reuse the freed block until
+	 * after the transaction is committed, which we can do by
+	 * treating the block as metadata, below.  We make an
+	 * exception if the inode is to be written in writeback mode
+	 * since writeback mode has weak data consistency guarantees.
+	 */
+	if (!ext4_should_writeback_data(inode))
+		flags |= EXT4_FREE_BLOCKS_METADATA;
+
+do_more:
+	overflow = 0;
+	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+
+	/*
+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 */
+	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
+		overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
+		count -= overflow;
+	}
+	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
+	if (!bitmap_bh) {
+		err = -EIO;
+		goto error_return;
+	}
+	gdp = ext4_get_group_desc(sb, block_group, &gd_bh);
+	if (!gdp) {
+		err = -EIO;
+		goto error_return;
+	}
+
+	if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
+	    in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
+	    in_range(block, ext4_inode_table(sb, gdp),
+		      EXT4_SB(sb)->s_itb_per_group) ||
+	    in_range(block + count - 1, ext4_inode_table(sb, gdp),
+		      EXT4_SB(sb)->s_itb_per_group)) {
+
+		ext4_error(sb, "Freeing blocks in system zone - "
+			   "Block = %llu, count = %lu", block, count);
+		/* err = 0. ext4_std_error should be a no op */
+		goto error_return;
+	}
+
+	BUFFER_TRACE(bitmap_bh, "getting write access");
+	err = ext4_journal_get_write_access(handle, bitmap_bh);
+	if (err)
+		goto error_return;
+
+	/*
+	 * We are about to modify some metadata.  Call the journal APIs
+	 * to unshare ->b_data if a currently-committing transaction is
+	 * using it
+	 */
+	BUFFER_TRACE(gd_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, gd_bh);
+	if (err)
+		goto error_return;
+#ifdef AGGRESSIVE_CHECK
+	{
+		int i;
+		for (i = 0; i < count; i++)
+			BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
+	}
+#endif
+	trace_ext4_mballoc_free(sb, inode, block_group, bit, count);
+
+	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	if (err)
+		goto error_return;
+
+	if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
+		struct ext4_free_data *new_entry;
+		/*
+		 * blocks being freed are metadata. these blocks shouldn't
+		 * be used until this transaction is committed
+		 */
+		new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+		if (!new_entry) {
+			ext4_mb_unload_buddy(&e4b);
+			err = -ENOMEM;
+			goto error_return;
+		}
+		new_entry->start_blk = bit;
+		new_entry->group  = block_group;
+		new_entry->count = count;
+		new_entry->t_tid = handle->h_transaction->t_tid;
+
+		ext4_lock_group(sb, block_group);
+		mb_clear_bits(bitmap_bh->b_data, bit, count);
+		ext4_mb_free_metadata(handle, &e4b, new_entry);
+	} else {
+		/* need to update group_info->bb_free and bitmap
+		 * with group lock held. generate_buddy look at
+		 * them with group lock_held
+		 */
+		ext4_lock_group(sb, block_group);
+		mb_clear_bits(bitmap_bh->b_data, bit, count);
+		mb_free_blocks(inode, &e4b, bit, count);
+	}
+
+	ret = ext4_free_blks_count(sb, gdp) + count;
+	ext4_free_blks_set(sb, gdp, ret);
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
+	ext4_unlock_group(sb, block_group);
+	percpu_counter_add(&sbi->s_freeblocks_counter, count);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
+		atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
+	}
+
+	ext4_mb_unload_buddy(&e4b);
+
+	freed += count;
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
+	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+	if (!err)
+		err = ret;
+
+	if (overflow && !err) {
+		block += count;
+		count = overflow;
+		put_bh(bitmap_bh);
+		goto do_more;
+	}
+	ext4_mark_super_dirty(sb);
+error_return:
+	if (freed && !(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+		dquot_free_block(inode, freed);
+	brelse(bitmap_bh);
+	ext4_std_error(sb, err);
+	return;
+}
+
+/**
+ * ext4_add_groupblocks() -- Add given blocks to an existing group
+ * @handle:			handle to this transaction
+ * @sb:				super block
+ * @block:			start physcial block to add to the block group
+ * @count:			number of blocks to free
+ *
+ * This marks the blocks as free in the bitmap and buddy.
+ */
+void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+			 ext4_fsblk_t block, unsigned long count)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gd_bh;
+	ext4_group_t block_group;
+	ext4_grpblk_t bit;
+	unsigned int i;
+	struct ext4_group_desc *desc;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_buddy e4b;
+	int err = 0, ret, blk_free_count;
+	ext4_grpblk_t blocks_freed;
+	struct ext4_group_info *grp;
+
+	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
+
+	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+	grp = ext4_get_group_info(sb, block_group);
+	/*
+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 */
+	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb))
+		goto error_return;
+
+	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
+	if (!desc)
+		goto error_return;
+
+	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
+	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
+	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
+	    in_range(block + count - 1, ext4_inode_table(sb, desc),
+		     sbi->s_itb_per_group)) {
+		ext4_error(sb, "Adding blocks in system zones - "
+			   "Block = %llu, count = %lu",
+			   block, count);
+		goto error_return;
+	}
+
+	BUFFER_TRACE(bitmap_bh, "getting write access");
+	err = ext4_journal_get_write_access(handle, bitmap_bh);
+	if (err)
+		goto error_return;
+
+	/*
+	 * We are about to modify some metadata.  Call the journal APIs
+	 * to unshare ->b_data if a currently-committing transaction is
+	 * using it
+	 */
+	BUFFER_TRACE(gd_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, gd_bh);
+	if (err)
+		goto error_return;
+
+	for (i = 0, blocks_freed = 0; i < count; i++) {
+		BUFFER_TRACE(bitmap_bh, "clear bit");
+		if (!mb_test_bit(bit + i, bitmap_bh->b_data)) {
+			ext4_error(sb, "bit already cleared for block %llu",
+				   (ext4_fsblk_t)(block + i));
+			BUFFER_TRACE(bitmap_bh, "bit already cleared");
+		} else {
+			blocks_freed++;
+		}
+	}
+
+	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	if (err)
+		goto error_return;
+
+	/*
+	 * need to update group_info->bb_free and bitmap
+	 * with group lock held. generate_buddy look at
+	 * them with group lock_held
+	 */
+	ext4_lock_group(sb, block_group);
+	mb_clear_bits(bitmap_bh->b_data, bit, count);
+	mb_free_blocks(NULL, &e4b, bit, count);
+	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
+	ext4_free_blks_set(sb, desc, blk_free_count);
+	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
+	ext4_unlock_group(sb, block_group);
+	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
+		atomic_add(blocks_freed,
+			   &sbi->s_flex_groups[flex_group].free_blocks);
+	}
+
+	ext4_mb_unload_buddy(&e4b);
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
+	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+	if (!err)
+		err = ret;
+
+error_return:
+	brelse(bitmap_bh);
+	ext4_std_error(sb, err);
+	return;
+}
+
+/**
+ * ext4_trim_extent -- function to TRIM one single free extent in the group
+ * @sb:		super block for the file system
+ * @start:	starting block of the free extent in the alloc. group
+ * @count:	number of blocks to TRIM
+ * @group:	alloc. group we are working with
+ * @e4b:	ext4 buddy for the group
+ *
+ * Trim "count" blocks starting at "start" in the "group". To assure that no
+ * one will allocate those blocks, mark it as used in buddy bitmap. This must
+ * be called with under the group lock.
+ */
+static void ext4_trim_extent(struct super_block *sb, int start, int count,
+			     ext4_group_t group, struct ext4_buddy *e4b)
+{
+	struct ext4_free_extent ex;
+
+	assert_spin_locked(ext4_group_lock_ptr(sb, group));
+
+	ex.fe_start = start;
+	ex.fe_group = group;
+	ex.fe_len = count;
+
+	/*
+	 * Mark blocks used, so no one can reuse them while
+	 * being trimmed.
+	 */
+	mb_mark_used(e4b, &ex);
+	ext4_unlock_group(sb, group);
+	ext4_issue_discard(sb, group, start, count);
+	ext4_lock_group(sb, group);
+	mb_free_blocks(NULL, e4b, start, ex.fe_len);
+}
+
+/**
+ * ext4_trim_all_free -- function to trim all free space in alloc. group
+ * @sb:			super block for file system
+ * @e4b:		ext4 buddy
+ * @start:		first group block to examine
+ * @max:		last group block to examine
+ * @minblocks:		minimum extent block count
+ *
+ * ext4_trim_all_free walks through group's buddy bitmap searching for free
+ * extents. When the free block is found, ext4_trim_extent is called to TRIM
+ * the extent.
+ *
+ *
+ * ext4_trim_all_free walks through group's block bitmap searching for free
+ * extents. When the free extent is found, mark it as used in group buddy
+ * bitmap. Then issue a TRIM command on this extent and free the extent in
+ * the group buddy bitmap. This is done until whole group is scanned.
+ */
+static ext4_grpblk_t
+ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
+		   ext4_grpblk_t start, ext4_grpblk_t max,
+		   ext4_grpblk_t minblocks)
+{
+	void *bitmap;
+	ext4_grpblk_t next, count = 0;
+	struct ext4_buddy e4b;
+	int ret;
+
+	ret = ext4_mb_load_buddy(sb, group, &e4b);
+	if (ret) {
+		ext4_error(sb, "Error in loading buddy "
+				"information for %u", group);
+		return ret;
+	}
+	bitmap = e4b.bd_bitmap;
+
+	ext4_lock_group(sb, group);
+	start = (e4b.bd_info->bb_first_free > start) ?
+		e4b.bd_info->bb_first_free : start;
+
+	while (start < max) {
+		start = mb_find_next_zero_bit(bitmap, max, start);
+		if (start >= max)
+			break;
+		next = mb_find_next_bit(bitmap, max, start);
+
+		if ((next - start) >= minblocks) {
+			ext4_trim_extent(sb, start,
+					 next - start, group, &e4b);
+			count += next - start;
+		}
+		start = next + 1;
+
+		if (fatal_signal_pending(current)) {
+			count = -ERESTARTSYS;
+			break;
+		}
+
+		if (need_resched()) {
+			ext4_unlock_group(sb, group);
+			cond_resched();
+			ext4_lock_group(sb, group);
+		}
+
+		if ((e4b.bd_info->bb_free - count) < minblocks)
+			break;
+	}
+	ext4_unlock_group(sb, group);
+	ext4_mb_unload_buddy(&e4b);
+
+	ext4_debug("trimmed %d blocks in the group %d\n",
+		count, group);
+
+	return count;
+}
+
+/**
+ * ext4_trim_fs() -- trim ioctl handle function
+ * @sb:			superblock for filesystem
+ * @range:		fstrim_range structure
+ *
+ * start:	First Byte to trim
+ * len:		number of Bytes to trim from start
+ * minlen:	minimum extent length in Bytes
+ * ext4_trim_fs goes through all allocation groups containing Bytes from
+ * start to start+len. For each such a group ext4_trim_all_free function
+ * is invoked to trim all free space.
+ */
+int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
+{
+	struct ext4_group_info *grp;
+	ext4_group_t first_group, last_group;
+	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
+	ext4_grpblk_t cnt = 0, first_block, last_block;
+	uint64_t start, len, minlen, trimmed = 0;
+	ext4_fsblk_t first_data_blk =
+			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+	int ret = 0;
+
+	start = range->start >> sb->s_blocksize_bits;
+	len = range->len >> sb->s_blocksize_bits;
+	minlen = range->minlen >> sb->s_blocksize_bits;
+
+	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+		return -EINVAL;
+	if (start < first_data_blk) {
+		len -= first_data_blk - start;
+		start = first_data_blk;
+	}
+
+	/* Determine first and last group to examine based on start and len */
+	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
+				     &first_group, &first_block);
+	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
+				     &last_group, &last_block);
+	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
+	last_block = EXT4_BLOCKS_PER_GROUP(sb);
+
+	if (first_group > last_group)
+		return -EINVAL;
+
+	for (group = first_group; group <= last_group; group++) {
+		grp = ext4_get_group_info(sb, group);
+		/* We only do this if the grp has never been initialized */
+		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+			ret = ext4_mb_init_group(sb, group);
+			if (ret)
+				break;
+		}
+
+		/*
+		 * For all the groups except the last one, last block will
+		 * always be EXT4_BLOCKS_PER_GROUP(sb), so we only need to
+		 * change it for the last group in which case start +
+		 * len < EXT4_BLOCKS_PER_GROUP(sb).
+		 */
+		if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb))
+			last_block = first_block + len;
+		len -= last_block - first_block;
+
+		if (grp->bb_free >= minlen) {
+			cnt = ext4_trim_all_free(sb, group, first_block,
+						last_block, minlen);
+			if (cnt < 0) {
+				ret = cnt;
+				break;
+			}
+		}
+		trimmed += cnt;
+		first_block = 0;
+	}
+	range->len = trimmed * sb->s_blocksize;
+
+	return ret;
+}
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
new file mode 100644
index 00000000..20b5e7bf
--- /dev/null
+++ b/fs/ext4/mballoc.h
@@ -0,0 +1,222 @@
+/*
+ *  fs/ext4/mballoc.h
+ *
+ *  Written by: Alex Tomas <alex@clusterfs.com>
+ *
+ */
+#ifndef _EXT4_MBALLOC_H
+#define _EXT4_MBALLOC_H
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/proc_fs.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/blkdev.h>
+#include <linux/mutex.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+
+/*
+ * with AGGRESSIVE_CHECK allocator runs consistency checks over
+ * structures. these checks slow things down a lot
+ */
+#define AGGRESSIVE_CHECK__
+
+/*
+ * with DOUBLE_CHECK defined mballoc creates persistent in-core
+ * bitmaps, maintains and uses them to check for double allocations
+ */
+#define DOUBLE_CHECK__
+
+/*
+ */
+#ifdef CONFIG_EXT4_DEBUG
+extern u8 mb_enable_debug;
+
+#define mb_debug(n, fmt, a...)	                                        \
+	do {								\
+		if ((n) <= mb_enable_debug) {		        	\
+			printk(KERN_DEBUG "(%s, %d): %s: ",		\
+			       __FILE__, __LINE__, __func__);		\
+			printk(fmt, ## a);				\
+		}							\
+	} while (0)
+#else
+#define mb_debug(n, fmt, a...)
+#endif
+
+#define EXT4_MB_HISTORY_ALLOC		1	/* allocation */
+#define EXT4_MB_HISTORY_PREALLOC	2	/* preallocated blocks used */
+
+/*
+ * How long mballoc can look for a best extent (in found extents)
+ */
+#define MB_DEFAULT_MAX_TO_SCAN		200
+
+/*
+ * How long mballoc must look for a best extent
+ */
+#define MB_DEFAULT_MIN_TO_SCAN		10
+
+/*
+ * How many groups mballoc will scan looking for the best chunk
+ */
+#define MB_DEFAULT_MAX_GROUPS_TO_SCAN	5
+
+/*
+ * with 'ext4_mb_stats' allocator will collect stats that will be
+ * shown at umount. The collecting costs though!
+ */
+#define MB_DEFAULT_STATS		0
+
+/*
+ * files smaller than MB_DEFAULT_STREAM_THRESHOLD are served
+ * by the stream allocator, which purpose is to pack requests
+ * as close each to other as possible to produce smooth I/O traffic
+ * We use locality group prealloc space for stream request.
+ * We can tune the same via /proc/fs/ext4/<parition>/stream_req
+ */
+#define MB_DEFAULT_STREAM_THRESHOLD	16	/* 64K */
+
+/*
+ * for which requests use 2^N search using buddies
+ */
+#define MB_DEFAULT_ORDER2_REQS		2
+
+/*
+ * default group prealloc size 512 blocks
+ */
+#define MB_DEFAULT_GROUP_PREALLOC	512
+
+
+struct ext4_free_data {
+	/* this links the free block information from group_info */
+	struct rb_node node;
+
+	/* this links the free block information from ext4_sb_info */
+	struct list_head list;
+
+	/* group which free block extent belongs */
+	ext4_group_t group;
+
+	/* free block extent */
+	ext4_grpblk_t start_blk;
+	ext4_grpblk_t count;
+
+	/* transaction which freed this extent */
+	tid_t	t_tid;
+};
+
+struct ext4_prealloc_space {
+	struct list_head	pa_inode_list;
+	struct list_head	pa_group_list;
+	union {
+		struct list_head pa_tmp_list;
+		struct rcu_head	pa_rcu;
+	} u;
+	spinlock_t		pa_lock;
+	atomic_t		pa_count;
+	unsigned		pa_deleted;
+	ext4_fsblk_t		pa_pstart;	/* phys. block */
+	ext4_lblk_t		pa_lstart;	/* log. block */
+	ext4_grpblk_t		pa_len;		/* len of preallocated chunk */
+	ext4_grpblk_t		pa_free;	/* how many blocks are free */
+	unsigned short		pa_type;	/* pa type. inode or group */
+	spinlock_t		*pa_obj_lock;
+	struct inode		*pa_inode;	/* hack, for history only */
+};
+
+enum {
+	MB_INODE_PA = 0,
+	MB_GROUP_PA = 1
+};
+
+struct ext4_free_extent {
+	ext4_lblk_t fe_logical;
+	ext4_grpblk_t fe_start;
+	ext4_group_t fe_group;
+	ext4_grpblk_t fe_len;
+};
+
+/*
+ * Locality group:
+ *   we try to group all related changes together
+ *   so that writeback can flush/allocate them together as well
+ *   Size of lg_prealloc_list hash is determined by MB_DEFAULT_GROUP_PREALLOC
+ *   (512). We store prealloc space into the hash based on the pa_free blocks
+ *   order value.ie, fls(pa_free)-1;
+ */
+#define PREALLOC_TB_SIZE 10
+struct ext4_locality_group {
+	/* for allocator */
+	/* to serialize allocates */
+	struct mutex		lg_mutex;
+	/* list of preallocations */
+	struct list_head	lg_prealloc_list[PREALLOC_TB_SIZE];
+	spinlock_t		lg_prealloc_lock;
+};
+
+struct ext4_allocation_context {
+	struct inode *ac_inode;
+	struct super_block *ac_sb;
+
+	/* original request */
+	struct ext4_free_extent ac_o_ex;
+
+	/* goal request (normalized ac_o_ex) */
+	struct ext4_free_extent ac_g_ex;
+
+	/* the best found extent */
+	struct ext4_free_extent ac_b_ex;
+
+	/* copy of the bext found extent taken before preallocation efforts */
+	struct ext4_free_extent ac_f_ex;
+
+	/* number of iterations done. we have to track to limit searching */
+	unsigned long ac_ex_scanned;
+	__u16 ac_groups_scanned;
+	__u16 ac_found;
+	__u16 ac_tail;
+	__u16 ac_buddy;
+	__u16 ac_flags;		/* allocation hints */
+	__u8 ac_status;
+	__u8 ac_criteria;
+	__u8 ac_repeats;
+	__u8 ac_2order;		/* if request is to allocate 2^N blocks and
+				 * N > 0, the field stores N, otherwise 0 */
+	__u8 ac_op;		/* operation, for history only */
+	struct page *ac_bitmap_page;
+	struct page *ac_buddy_page;
+	struct ext4_prealloc_space *ac_pa;
+	struct ext4_locality_group *ac_lg;
+};
+
+#define AC_STATUS_CONTINUE	1
+#define AC_STATUS_FOUND		2
+#define AC_STATUS_BREAK		3
+
+struct ext4_buddy {
+	struct page *bd_buddy_page;
+	void *bd_buddy;
+	struct page *bd_bitmap_page;
+	void *bd_bitmap;
+	struct ext4_group_info *bd_info;
+	struct super_block *bd_sb;
+	__u16 bd_blkbits;
+	ext4_group_t bd_group;
+};
+#define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
+#define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)
+
+static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
+					struct ext4_free_extent *fex)
+{
+	return ext4_group_first_block_no(sb, fex->fe_group) + fex->fe_start;
+}
+#endif
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
new file mode 100644
index 00000000..b57b98fb
--- /dev/null
+++ b/fs/ext4/migrate.c
@@ -0,0 +1,634 @@
+/*
+ * Copyright IBM Corporation, 2007
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
+
+/*
+ * The contiguous blocks details which can be
+ * represented by a single extent
+ */
+struct list_blocks_struct {
+	ext4_lblk_t first_block, last_block;
+	ext4_fsblk_t first_pblock, last_pblock;
+};
+
+static int finish_range(handle_t *handle, struct inode *inode,
+				struct list_blocks_struct *lb)
+
+{
+	int retval = 0, needed;
+	struct ext4_extent newext;
+	struct ext4_ext_path *path;
+	if (lb->first_pblock == 0)
+		return 0;
+
+	/* Add the extent to temp inode*/
+	newext.ee_block = cpu_to_le32(lb->first_block);
+	newext.ee_len   = cpu_to_le16(lb->last_block - lb->first_block + 1);
+	ext4_ext_store_pblock(&newext, lb->first_pblock);
+	path = ext4_ext_find_extent(inode, lb->first_block, NULL);
+
+	if (IS_ERR(path)) {
+		retval = PTR_ERR(path);
+		path = NULL;
+		goto err_out;
+	}
+
+	/*
+	 * Calculate the credit needed to inserting this extent
+	 * Since we are doing this in loop we may accumalate extra
+	 * credit. But below we try to not accumalate too much
+	 * of them by restarting the journal.
+	 */
+	needed = ext4_ext_calc_credits_for_single_extent(inode,
+		    lb->last_block - lb->first_block + 1, path);
+
+	/*
+	 * Make sure the credit we accumalated is not really high
+	 */
+	if (needed && ext4_handle_has_enough_credits(handle,
+						EXT4_RESERVE_TRANS_BLOCKS)) {
+		retval = ext4_journal_restart(handle, needed);
+		if (retval)
+			goto err_out;
+	} else if (needed) {
+		retval = ext4_journal_extend(handle, needed);
+		if (retval) {
+			/*
+			 * IF not able to extend the journal restart the journal
+			 */
+			retval = ext4_journal_restart(handle, needed);
+			if (retval)
+				goto err_out;
+		}
+	}
+	retval = ext4_ext_insert_extent(handle, inode, path, &newext, 0);
+err_out:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+	lb->first_pblock = 0;
+	return retval;
+}
+
+static int update_extent_range(handle_t *handle, struct inode *inode,
+				ext4_fsblk_t pblock, ext4_lblk_t blk_num,
+				struct list_blocks_struct *lb)
+{
+	int retval;
+	/*
+	 * See if we can add on to the existing range (if it exists)
+	 */
+	if (lb->first_pblock &&
+		(lb->last_pblock+1 == pblock) &&
+		(lb->last_block+1 == blk_num)) {
+		lb->last_pblock = pblock;
+		lb->last_block = blk_num;
+		return 0;
+	}
+	/*
+	 * Start a new range.
+	 */
+	retval = finish_range(handle, inode, lb);
+	lb->first_pblock = lb->last_pblock = pblock;
+	lb->first_block = lb->last_block = blk_num;
+
+	return retval;
+}
+
+static int update_ind_extent_range(handle_t *handle, struct inode *inode,
+				   ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
+				   struct list_blocks_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	ext4_lblk_t blk_count = *blk_nump;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	if (!pblock) {
+		/* Only update the file block number */
+		*blk_nump += max_entries;
+		return 0;
+	}
+
+	bh = sb_bread(inode->i_sb, pblock);
+	if (!bh)
+		return -EIO;
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++, blk_count++) {
+		if (i_data[i]) {
+			retval = update_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]),
+						blk_count, lb);
+			if (retval)
+				break;
+		}
+	}
+
+	/* Update the file block number */
+	*blk_nump = blk_count;
+	put_bh(bh);
+	return retval;
+
+}
+
+static int update_dind_extent_range(handle_t *handle, struct inode *inode,
+				    ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
+				    struct list_blocks_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	ext4_lblk_t blk_count = *blk_nump;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	if (!pblock) {
+		/* Only update the file block number */
+		*blk_nump += max_entries * max_entries;
+		return 0;
+	}
+	bh = sb_bread(inode->i_sb, pblock);
+	if (!bh)
+		return -EIO;
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_ind_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]),
+						&blk_count, lb);
+			if (retval)
+				break;
+		} else {
+			/* Only update the file block number */
+			blk_count += max_entries;
+		}
+	}
+
+	/* Update the file block number */
+	*blk_nump = blk_count;
+	put_bh(bh);
+	return retval;
+
+}
+
+static int update_tind_extent_range(handle_t *handle, struct inode *inode,
+				     ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
+				     struct list_blocks_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	ext4_lblk_t blk_count = *blk_nump;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	if (!pblock) {
+		/* Only update the file block number */
+		*blk_nump += max_entries * max_entries * max_entries;
+		return 0;
+	}
+	bh = sb_bread(inode->i_sb, pblock);
+	if (!bh)
+		return -EIO;
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_dind_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]),
+						&blk_count, lb);
+			if (retval)
+				break;
+		} else
+			/* Only update the file block number */
+			blk_count += max_entries * max_entries;
+	}
+	/* Update the file block number */
+	*blk_nump = blk_count;
+	put_bh(bh);
+	return retval;
+
+}
+
+static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
+{
+	int retval = 0, needed;
+
+	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
+		return 0;
+	/*
+	 * We are freeing a blocks. During this we touch
+	 * superblock, group descriptor and block bitmap.
+	 * So allocate a credit of 3. We may update
+	 * quota (user and group).
+	 */
+	needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
+
+	if (ext4_journal_extend(handle, needed) != 0)
+		retval = ext4_journal_restart(handle, needed);
+
+	return retval;
+}
+
+static int free_dind_blocks(handle_t *handle,
+				struct inode *inode, __le32 i_data)
+{
+	int i;
+	__le32 *tmp_idata;
+	struct buffer_head *bh;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = sb_bread(inode->i_sb, le32_to_cpu(i_data));
+	if (!bh)
+		return -EIO;
+
+	tmp_idata = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (tmp_idata[i]) {
+			extend_credit_for_blkdel(handle, inode);
+			ext4_free_blocks(handle, inode, NULL,
+					 le32_to_cpu(tmp_idata[i]), 1,
+					 EXT4_FREE_BLOCKS_METADATA |
+					 EXT4_FREE_BLOCKS_FORGET);
+		}
+	}
+	put_bh(bh);
+	extend_credit_for_blkdel(handle, inode);
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
+			 EXT4_FREE_BLOCKS_METADATA |
+			 EXT4_FREE_BLOCKS_FORGET);
+	return 0;
+}
+
+static int free_tind_blocks(handle_t *handle,
+				struct inode *inode, __le32 i_data)
+{
+	int i, retval = 0;
+	__le32 *tmp_idata;
+	struct buffer_head *bh;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = sb_bread(inode->i_sb, le32_to_cpu(i_data));
+	if (!bh)
+		return -EIO;
+
+	tmp_idata = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (tmp_idata[i]) {
+			retval = free_dind_blocks(handle,
+					inode, tmp_idata[i]);
+			if (retval) {
+				put_bh(bh);
+				return retval;
+			}
+		}
+	}
+	put_bh(bh);
+	extend_credit_for_blkdel(handle, inode);
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
+			 EXT4_FREE_BLOCKS_METADATA |
+			 EXT4_FREE_BLOCKS_FORGET);
+	return 0;
+}
+
+static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
+{
+	int retval;
+
+	/* ei->i_data[EXT4_IND_BLOCK] */
+	if (i_data[0]) {
+		extend_credit_for_blkdel(handle, inode);
+		ext4_free_blocks(handle, inode, NULL,
+				le32_to_cpu(i_data[0]), 1,
+				 EXT4_FREE_BLOCKS_METADATA |
+				 EXT4_FREE_BLOCKS_FORGET);
+	}
+
+	/* ei->i_data[EXT4_DIND_BLOCK] */
+	if (i_data[1]) {
+		retval = free_dind_blocks(handle, inode, i_data[1]);
+		if (retval)
+			return retval;
+	}
+
+	/* ei->i_data[EXT4_TIND_BLOCK] */
+	if (i_data[2]) {
+		retval = free_tind_blocks(handle, inode, i_data[2]);
+		if (retval)
+			return retval;
+	}
+	return 0;
+}
+
+static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
+						struct inode *tmp_inode)
+{
+	int retval;
+	__le32	i_data[3];
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
+
+	/*
+	 * One credit accounted for writing the
+	 * i_data field of the original inode
+	 */
+	retval = ext4_journal_extend(handle, 1);
+	if (retval) {
+		retval = ext4_journal_restart(handle, 1);
+		if (retval)
+			goto err_out;
+	}
+
+	i_data[0] = ei->i_data[EXT4_IND_BLOCK];
+	i_data[1] = ei->i_data[EXT4_DIND_BLOCK];
+	i_data[2] = ei->i_data[EXT4_TIND_BLOCK];
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	/*
+	 * if EXT4_STATE_EXT_MIGRATE is cleared a block allocation
+	 * happened after we started the migrate. We need to
+	 * fail the migrate
+	 */
+	if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) {
+		retval = -EAGAIN;
+		up_write(&EXT4_I(inode)->i_data_sem);
+		goto err_out;
+	} else
+		ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
+	/*
+	 * We have the extent map build with the tmp inode.
+	 * Now copy the i_data across
+	 */
+	ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
+	memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
+
+	/*
+	 * Update i_blocks with the new blocks that got
+	 * allocated while adding extents for extent index
+	 * blocks.
+	 *
+	 * While converting to extents we need not
+	 * update the orignal inode i_blocks for extent blocks
+	 * via quota APIs. The quota update happened via tmp_inode already.
+	 */
+	spin_lock(&inode->i_lock);
+	inode->i_blocks += tmp_inode->i_blocks;
+	spin_unlock(&inode->i_lock);
+	up_write(&EXT4_I(inode)->i_data_sem);
+
+	/*
+	 * We mark the inode dirty after, because we decrement the
+	 * i_blocks when freeing the indirect meta-data blocks
+	 */
+	retval = free_ind_block(handle, inode, i_data);
+	ext4_mark_inode_dirty(handle, inode);
+
+err_out:
+	return retval;
+}
+
+static int free_ext_idx(handle_t *handle, struct inode *inode,
+					struct ext4_extent_idx *ix)
+{
+	int i, retval = 0;
+	ext4_fsblk_t block;
+	struct buffer_head *bh;
+	struct ext4_extent_header *eh;
+
+	block = ext4_idx_pblock(ix);
+	bh = sb_bread(inode->i_sb, block);
+	if (!bh)
+		return -EIO;
+
+	eh = (struct ext4_extent_header *)bh->b_data;
+	if (eh->eh_depth != 0) {
+		ix = EXT_FIRST_INDEX(eh);
+		for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
+			retval = free_ext_idx(handle, inode, ix);
+			if (retval)
+				break;
+		}
+	}
+	put_bh(bh);
+	extend_credit_for_blkdel(handle, inode);
+	ext4_free_blocks(handle, inode, NULL, block, 1,
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+	return retval;
+}
+
+/*
+ * Free the extent meta data blocks only
+ */
+static int free_ext_block(handle_t *handle, struct inode *inode)
+{
+	int i, retval = 0;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_extent_header *eh = (struct ext4_extent_header *)ei->i_data;
+	struct ext4_extent_idx *ix;
+	if (eh->eh_depth == 0)
+		/*
+		 * No extra blocks allocated for extent meta data
+		 */
+		return 0;
+	ix = EXT_FIRST_INDEX(eh);
+	for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
+		retval = free_ext_idx(handle, inode, ix);
+		if (retval)
+			return retval;
+	}
+	return retval;
+
+}
+
+int ext4_ext_migrate(struct inode *inode)
+{
+	handle_t *handle;
+	int retval = 0, i;
+	__le32 *i_data;
+	ext4_lblk_t blk_count = 0;
+	struct ext4_inode_info *ei;
+	struct inode *tmp_inode = NULL;
+	struct list_blocks_struct lb;
+	unsigned long max_entries;
+	__u32 goal;
+
+	/*
+	 * If the filesystem does not support extents, or the inode
+	 * already is extent-based, error out.
+	 */
+	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
+				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return -EINVAL;
+
+	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
+		/*
+		 * don't migrate fast symlink
+		 */
+		return retval;
+
+	handle = ext4_journal_start(inode,
+					EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+					EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
+					+ 1);
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		return retval;
+	}
+	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
+		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
+	tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
+				   S_IFREG, NULL, goal);
+	if (IS_ERR(tmp_inode)) {
+		retval = -ENOMEM;
+		ext4_journal_stop(handle);
+		return retval;
+	}
+	i_size_write(tmp_inode, i_size_read(inode));
+	/*
+	 * Set the i_nlink to zero so it will be deleted later
+	 * when we drop inode reference.
+	 */
+	tmp_inode->i_nlink = 0;
+
+	ext4_ext_tree_init(handle, tmp_inode);
+	ext4_orphan_add(handle, tmp_inode);
+	ext4_journal_stop(handle);
+
+	/*
+	 * start with one credit accounted for
+	 * superblock modification.
+	 *
+	 * For the tmp_inode we already have committed the
+	 * trascation that created the inode. Later as and
+	 * when we add extents we extent the journal
+	 */
+	/*
+	 * Even though we take i_mutex we can still cause block
+	 * allocation via mmap write to holes. If we have allocated
+	 * new blocks we fail migrate.  New block allocation will
+	 * clear EXT4_STATE_EXT_MIGRATE flag.  The flag is updated
+	 * with i_data_sem held to prevent racing with block
+	 * allocation.
+	 */
+	down_read((&EXT4_I(inode)->i_data_sem));
+	ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
+	up_read((&EXT4_I(inode)->i_data_sem));
+
+	handle = ext4_journal_start(inode, 1);
+	if (IS_ERR(handle)) {
+		/*
+		 * It is impossible to update on-disk structures without
+		 * a handle, so just rollback in-core changes and live other
+		 * work to orphan_list_cleanup()
+		 */
+		ext4_orphan_del(NULL, tmp_inode);
+		retval = PTR_ERR(handle);
+		goto out;
+	}
+
+	ei = EXT4_I(inode);
+	i_data = ei->i_data;
+	memset(&lb, 0, sizeof(lb));
+
+	/* 32 bit block address 4 bytes */
+	max_entries = inode->i_sb->s_blocksize >> 2;
+	for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
+		if (i_data[i]) {
+			retval = update_extent_range(handle, tmp_inode,
+						le32_to_cpu(i_data[i]),
+						blk_count, &lb);
+			if (retval)
+				goto err_out;
+		}
+	}
+	if (i_data[EXT4_IND_BLOCK]) {
+		retval = update_ind_extent_range(handle, tmp_inode,
+					le32_to_cpu(i_data[EXT4_IND_BLOCK]),
+					&blk_count, &lb);
+			if (retval)
+				goto err_out;
+	} else
+		blk_count +=  max_entries;
+	if (i_data[EXT4_DIND_BLOCK]) {
+		retval = update_dind_extent_range(handle, tmp_inode,
+					le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
+					&blk_count, &lb);
+			if (retval)
+				goto err_out;
+	} else
+		blk_count += max_entries * max_entries;
+	if (i_data[EXT4_TIND_BLOCK]) {
+		retval = update_tind_extent_range(handle, tmp_inode,
+					le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
+					&blk_count, &lb);
+			if (retval)
+				goto err_out;
+	}
+	/*
+	 * Build the last extent
+	 */
+	retval = finish_range(handle, tmp_inode, &lb);
+err_out:
+	if (retval)
+		/*
+		 * Failure case delete the extent information with the
+		 * tmp_inode
+		 */
+		free_ext_block(handle, tmp_inode);
+	else {
+		retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode);
+		if (retval)
+			/*
+			 * if we fail to swap inode data free the extent
+			 * details of the tmp inode
+			 */
+			free_ext_block(handle, tmp_inode);
+	}
+
+	/* We mark the tmp_inode dirty via ext4_ext_tree_init. */
+	if (ext4_journal_extend(handle, 1) != 0)
+		ext4_journal_restart(handle, 1);
+
+	/*
+	 * Mark the tmp_inode as of size zero
+	 */
+	i_size_write(tmp_inode, 0);
+
+	/*
+	 * set the  i_blocks count to zero
+	 * so that the ext4_delete_inode does the
+	 * right job
+	 *
+	 * We don't need to take the i_lock because
+	 * the inode is not visible to user space.
+	 */
+	tmp_inode->i_blocks = 0;
+
+	/* Reset the extent details */
+	ext4_ext_tree_init(handle, tmp_inode);
+	ext4_journal_stop(handle);
+out:
+	unlock_new_inode(tmp_inode);
+	iput(tmp_inode);
+
+	return retval;
+}
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
new file mode 100644
index 00000000..9bdef3f5
--- /dev/null
+++ b/fs/ext4/mmp.c
@@ -0,0 +1,351 @@
+#include <linux/fs.h>
+#include <linux/random.h>
+#include <linux/buffer_head.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+
+#include "ext4.h"
+
+/*
+ * Write the MMP block using WRITE_SYNC to try to get the block on-disk
+ * faster.
+ */
+static int write_mmp_block(struct buffer_head *bh)
+{
+	mark_buffer_dirty(bh);
+	lock_buffer(bh);
+	bh->b_end_io = end_buffer_write_sync;
+	get_bh(bh);
+	submit_bh(WRITE_SYNC, bh);
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh)))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Read the MMP block. It _must_ be read from disk and hence we clear the
+ * uptodate flag on the buffer.
+ */
+static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
+			  ext4_fsblk_t mmp_block)
+{
+	struct mmp_struct *mmp;
+
+	if (*bh)
+		clear_buffer_uptodate(*bh);
+
+	/* This would be sb_bread(sb, mmp_block), except we need to be sure
+	 * that the MD RAID device cache has been bypassed, and that the read
+	 * is not blocked in the elevator. */
+	if (!*bh)
+		*bh = sb_getblk(sb, mmp_block);
+	if (*bh) {
+		get_bh(*bh);
+		lock_buffer(*bh);
+		(*bh)->b_end_io = end_buffer_read_sync;
+		submit_bh(READ_SYNC, *bh);
+		wait_on_buffer(*bh);
+		if (!buffer_uptodate(*bh)) {
+			brelse(*bh);
+			*bh = NULL;
+		}
+	}
+	if (!*bh) {
+		ext4_warning(sb, "Error while reading MMP block %llu",
+			     mmp_block);
+		return -EIO;
+	}
+
+	mmp = (struct mmp_struct *)((*bh)->b_data);
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC)
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Dump as much information as possible to help the admin.
+ */
+void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
+		    const char *function, unsigned int line, const char *msg)
+{
+	__ext4_warning(sb, function, line, msg);
+	__ext4_warning(sb, function, line,
+		       "MMP failure info: last update time: %llu, last update "
+		       "node: %s, last update device: %s\n",
+		       (long long unsigned int) le64_to_cpu(mmp->mmp_time),
+		       mmp->mmp_nodename, mmp->mmp_bdevname);
+}
+
+/*
+ * kmmpd will update the MMP sequence every s_mmp_update_interval seconds
+ */
+static int kmmpd(void *data)
+{
+	struct super_block *sb = ((struct mmpd_data *) data)->sb;
+	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct mmp_struct *mmp;
+	ext4_fsblk_t mmp_block;
+	u32 seq = 0;
+	unsigned long failed_writes = 0;
+	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned mmp_check_interval;
+	unsigned long last_update_time;
+	unsigned long diff;
+	int retval;
+
+	mmp_block = le64_to_cpu(es->s_mmp_block);
+	mmp = (struct mmp_struct *)(bh->b_data);
+	mmp->mmp_time = cpu_to_le64(get_seconds());
+	/*
+	 * Start with the higher mmp_check_interval and reduce it if
+	 * the MMP block is being updated on time.
+	 */
+	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
+				 EXT4_MMP_MIN_CHECK_INTERVAL);
+	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	bdevname(bh->b_bdev, mmp->mmp_bdevname);
+
+	memcpy(mmp->mmp_nodename, init_utsname()->sysname,
+	       sizeof(mmp->mmp_nodename));
+
+	while (!kthread_should_stop()) {
+		if (++seq > EXT4_MMP_SEQ_MAX)
+			seq = 1;
+
+		mmp->mmp_seq = cpu_to_le32(seq);
+		mmp->mmp_time = cpu_to_le64(get_seconds());
+		last_update_time = jiffies;
+
+		retval = write_mmp_block(bh);
+		/*
+		 * Don't spew too many error messages. Print one every
+		 * (s_mmp_update_interval * 60) seconds.
+		 */
+		if (retval && (failed_writes % 60) == 0) {
+			ext4_error(sb, "Error writing to MMP block");
+			failed_writes++;
+		}
+
+		if (!(le32_to_cpu(es->s_feature_incompat) &
+		    EXT4_FEATURE_INCOMPAT_MMP)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			EXT4_SB(sb)->s_mmp_tsk = NULL;
+			goto failed;
+		}
+
+		if (sb->s_flags & MS_RDONLY) {
+			ext4_warning(sb, "kmmpd being stopped since filesystem "
+				     "has been remounted as readonly.");
+			EXT4_SB(sb)->s_mmp_tsk = NULL;
+			goto failed;
+		}
+
+		diff = jiffies - last_update_time;
+		if (diff < mmp_update_interval * HZ)
+			schedule_timeout_interruptible(mmp_update_interval *
+						       HZ - diff);
+
+		/*
+		 * We need to make sure that more than mmp_check_interval
+		 * seconds have not passed since writing. If that has happened
+		 * we need to check if the MMP block is as we left it.
+		 */
+		diff = jiffies - last_update_time;
+		if (diff > mmp_check_interval * HZ) {
+			struct buffer_head *bh_check = NULL;
+			struct mmp_struct *mmp_check;
+
+			retval = read_mmp_block(sb, &bh_check, mmp_block);
+			if (retval) {
+				ext4_error(sb, "error reading MMP data: %d",
+					   retval);
+
+				EXT4_SB(sb)->s_mmp_tsk = NULL;
+				goto failed;
+			}
+
+			mmp_check = (struct mmp_struct *)(bh_check->b_data);
+			if (mmp->mmp_seq != mmp_check->mmp_seq ||
+			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
+				   sizeof(mmp->mmp_nodename))) {
+				dump_mmp_msg(sb, mmp_check,
+					     "Error while updating MMP info. "
+					     "The filesystem seems to have been"
+					     " multiply mounted.");
+				ext4_error(sb, "abort");
+				goto failed;
+			}
+			put_bh(bh_check);
+		}
+
+		 /*
+		 * Adjust the mmp_check_interval depending on how much time
+		 * it took for the MMP block to be written.
+		 */
+		mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
+					     EXT4_MMP_MAX_CHECK_INTERVAL),
+					 EXT4_MMP_MIN_CHECK_INTERVAL);
+		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	}
+
+	/*
+	 * Unmount seems to be clean.
+	 */
+	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
+	mmp->mmp_time = cpu_to_le64(get_seconds());
+
+	retval = write_mmp_block(bh);
+
+failed:
+	kfree(data);
+	brelse(bh);
+	return retval;
+}
+
+/*
+ * Get a random new sequence number but make sure it is not greater than
+ * EXT4_MMP_SEQ_MAX.
+ */
+static unsigned int mmp_new_seq(void)
+{
+	u32 new_seq;
+
+	do {
+		get_random_bytes(&new_seq, sizeof(u32));
+	} while (new_seq > EXT4_MMP_SEQ_MAX);
+
+	return new_seq;
+}
+
+/*
+ * Protect the filesystem from being mounted more than once.
+ */
+int ext4_multi_mount_protect(struct super_block *sb,
+				    ext4_fsblk_t mmp_block)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = NULL;
+	struct mmp_struct *mmp = NULL;
+	struct mmpd_data *mmpd_data;
+	u32 seq;
+	unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned int wait_time = 0;
+	int retval;
+
+	if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
+	    mmp_block >= ext4_blocks_count(es)) {
+		ext4_warning(sb, "Invalid MMP block in superblock");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+
+	mmp = (struct mmp_struct *)(bh->b_data);
+
+	if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
+		mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
+
+	/*
+	 * If check_interval in MMP block is larger, use that instead of
+	 * update_interval from the superblock.
+	 */
+	if (mmp->mmp_check_interval > mmp_check_interval)
+		mmp_check_interval = mmp->mmp_check_interval;
+
+	seq = le32_to_cpu(mmp->mmp_seq);
+	if (seq == EXT4_MMP_SEQ_CLEAN)
+		goto skip;
+
+	if (seq == EXT4_MMP_SEQ_FSCK) {
+		dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
+		goto failed;
+	}
+
+	wait_time = min(mmp_check_interval * 2 + 1,
+			mmp_check_interval + 60);
+
+	/* Print MMP interval if more than 20 secs. */
+	if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
+		ext4_warning(sb, "MMP interval %u higher than expected, please"
+			     " wait.\n", wait_time * 2);
+
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		goto failed;
+	}
+
+skip:
+	/*
+	 * write a new random sequence number.
+	 */
+	mmp->mmp_seq = seq = cpu_to_le32(mmp_new_seq());
+
+	retval = write_mmp_block(bh);
+	if (retval)
+		goto failed;
+
+	/*
+	 * wait for MMP interval and check mmp_seq.
+	 */
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		goto failed;
+	}
+
+	mmpd_data = kmalloc(sizeof(struct mmpd_data), GFP_KERNEL);
+	if (!mmpd_data) {
+		ext4_warning(sb, "not enough memory for mmpd_data");
+		goto failed;
+	}
+	mmpd_data->sb = sb;
+	mmpd_data->bh = bh;
+
+	/*
+	 * Start a kernel thread to update the MMP block periodically.
+	 */
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
+					     bdevname(bh->b_bdev,
+						      mmp->mmp_bdevname));
+	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
+		EXT4_SB(sb)->s_mmp_tsk = NULL;
+		kfree(mmpd_data);
+		ext4_warning(sb, "Unable to create kmmpd thread for %s.",
+			     sb->s_id);
+		goto failed;
+	}
+
+	return 0;
+
+failed:
+	brelse(bh);
+	return 1;
+}
+
+
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
new file mode 100644
index 00000000..f57455a1
--- /dev/null
+++ b/fs/ext4/move_extent.c
@@ -0,0 +1,1424 @@
+/*
+ * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd.
+ * Written by Takashi Sato <t-sato@yk.jp.nec.com>
+ *            Akira Fujita <a-fujita@rs.jp.nec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/fs.h>
+#include <linux/quotaops.h>
+#include <linux/slab.h>
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
+#include "ext4.h"
+
+/**
+ * get_ext_path - Find an extent path for designated logical block number.
+ *
+ * @inode:	an inode which is searched
+ * @lblock:	logical block number to find an extent path
+ * @path:	pointer to an extent path pointer (for output)
+ *
+ * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value
+ * on failure.
+ */
+static inline int
+get_ext_path(struct inode *inode, ext4_lblk_t lblock,
+		struct ext4_ext_path **path)
+{
+	int ret = 0;
+
+	*path = ext4_ext_find_extent(inode, lblock, *path);
+	if (IS_ERR(*path)) {
+		ret = PTR_ERR(*path);
+		*path = NULL;
+	} else if ((*path)[ext_depth(inode)].p_ext == NULL)
+		ret = -ENODATA;
+
+	return ret;
+}
+
+/**
+ * copy_extent_status - Copy the extent's initialization status
+ *
+ * @src:	an extent for getting initialize status
+ * @dest:	an extent to be set the status
+ */
+static void
+copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
+{
+	if (ext4_ext_is_uninitialized(src))
+		ext4_ext_mark_uninitialized(dest);
+	else
+		dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
+}
+
+/**
+ * mext_next_extent - Search for the next extent and set it to "extent"
+ *
+ * @inode:	inode which is searched
+ * @path:	this will obtain data for the next extent
+ * @extent:	pointer to the next extent we have just gotten
+ *
+ * Search the next extent in the array of ext4_ext_path structure (@path)
+ * and set it to ext4_extent structure (@extent). In addition, the member of
+ * @path (->p_ext) also points the next extent. Return 0 on success, 1 if
+ * ext4_ext_path structure refers to the last extent, or a negative error
+ * value on failure.
+ */
+static int
+mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
+		      struct ext4_extent **extent)
+{
+	struct ext4_extent_header *eh;
+	int ppos, leaf_ppos = path->p_depth;
+
+	ppos = leaf_ppos;
+	if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
+		/* leaf block */
+		*extent = ++path[ppos].p_ext;
+		path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
+		return 0;
+	}
+
+	while (--ppos >= 0) {
+		if (EXT_LAST_INDEX(path[ppos].p_hdr) >
+		    path[ppos].p_idx) {
+			int cur_ppos = ppos;
+
+			/* index block */
+			path[ppos].p_idx++;
+			path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
+			if (path[ppos+1].p_bh)
+				brelse(path[ppos+1].p_bh);
+			path[ppos+1].p_bh =
+				sb_bread(inode->i_sb, path[ppos].p_block);
+			if (!path[ppos+1].p_bh)
+				return -EIO;
+			path[ppos+1].p_hdr =
+				ext_block_hdr(path[ppos+1].p_bh);
+
+			/* Halfway index block */
+			while (++cur_ppos < leaf_ppos) {
+				path[cur_ppos].p_idx =
+					EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
+				path[cur_ppos].p_block =
+					ext4_idx_pblock(path[cur_ppos].p_idx);
+				if (path[cur_ppos+1].p_bh)
+					brelse(path[cur_ppos+1].p_bh);
+				path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
+					path[cur_ppos].p_block);
+				if (!path[cur_ppos+1].p_bh)
+					return -EIO;
+				path[cur_ppos+1].p_hdr =
+					ext_block_hdr(path[cur_ppos+1].p_bh);
+			}
+
+			path[leaf_ppos].p_ext = *extent = NULL;
+
+			eh = path[leaf_ppos].p_hdr;
+			if (le16_to_cpu(eh->eh_entries) == 0)
+				/* empty leaf is found */
+				return -ENODATA;
+
+			/* leaf block */
+			path[leaf_ppos].p_ext = *extent =
+				EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
+			path[leaf_ppos].p_block =
+					ext4_ext_pblock(path[leaf_ppos].p_ext);
+			return 0;
+		}
+	}
+	/* We found the last extent */
+	return 1;
+}
+
+/**
+ * mext_check_null_inode - NULL check for two inodes
+ *
+ * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
+ */
+static int
+mext_check_null_inode(struct inode *inode1, struct inode *inode2,
+		      const char *function, unsigned int line)
+{
+	int ret = 0;
+
+	if (inode1 == NULL) {
+		__ext4_error(inode2->i_sb, function, line,
+			"Both inodes should not be NULL: "
+			"inode1 NULL inode2 %lu", inode2->i_ino);
+		ret = -EIO;
+	} else if (inode2 == NULL) {
+		__ext4_error(inode1->i_sb, function, line,
+			"Both inodes should not be NULL: "
+			"inode1 %lu inode2 NULL", inode1->i_ino);
+		ret = -EIO;
+	}
+	return ret;
+}
+
+/**
+ * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
+ *
+ * @orig_inode:		original inode structure
+ * @donor_inode:	donor inode structure
+ * Acquire write lock of i_data_sem of the two inodes (orig and donor) by
+ * i_ino order.
+ */
+static void
+double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
+{
+	struct inode *first = orig_inode, *second = donor_inode;
+
+	/*
+	 * Use the inode number to provide the stable locking order instead
+	 * of its address, because the C language doesn't guarantee you can
+	 * compare pointers that don't come from the same array.
+	 */
+	if (donor_inode->i_ino < orig_inode->i_ino) {
+		first = donor_inode;
+		second = orig_inode;
+	}
+
+	down_write(&EXT4_I(first)->i_data_sem);
+	down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
+}
+
+/**
+ * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
+ *
+ * @orig_inode:		original inode structure to be released its lock first
+ * @donor_inode:	donor inode structure to be released its lock second
+ * Release write lock of i_data_sem of two inodes (orig and donor).
+ */
+static void
+double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
+{
+	up_write(&EXT4_I(orig_inode)->i_data_sem);
+	up_write(&EXT4_I(donor_inode)->i_data_sem);
+}
+
+/**
+ * mext_insert_across_blocks - Insert extents across leaf block
+ *
+ * @handle:		journal handle
+ * @orig_inode:		original inode
+ * @o_start:		first original extent to be changed
+ * @o_end:		last original extent to be changed
+ * @start_ext:		first new extent to be inserted
+ * @new_ext:		middle of new extent to be inserted
+ * @end_ext:		last new extent to be inserted
+ *
+ * Allocate a new leaf block and insert extents into it. Return 0 on success,
+ * or a negative error value on failure.
+ */
+static int
+mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
+		struct ext4_extent *o_start, struct ext4_extent *o_end,
+		struct ext4_extent *start_ext, struct ext4_extent *new_ext,
+		struct ext4_extent *end_ext)
+{
+	struct ext4_ext_path *orig_path = NULL;
+	ext4_lblk_t eblock = 0;
+	int new_flag = 0;
+	int end_flag = 0;
+	int err = 0;
+
+	if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) {
+		if (o_start == o_end) {
+
+			/*       start_ext   new_ext    end_ext
+			 * donor |---------|-----------|--------|
+			 * orig  |------------------------------|
+			 */
+			end_flag = 1;
+		} else {
+
+			/*       start_ext   new_ext   end_ext
+			 * donor |---------|----------|---------|
+			 * orig  |---------------|--------------|
+			 */
+			o_end->ee_block = end_ext->ee_block;
+			o_end->ee_len = end_ext->ee_len;
+			ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
+		}
+
+		o_start->ee_len = start_ext->ee_len;
+		eblock = le32_to_cpu(start_ext->ee_block);
+		new_flag = 1;
+
+	} else if (start_ext->ee_len && new_ext->ee_len &&
+		   !end_ext->ee_len && o_start == o_end) {
+
+		/*	 start_ext	new_ext
+		 * donor |--------------|---------------|
+		 * orig  |------------------------------|
+		 */
+		o_start->ee_len = start_ext->ee_len;
+		eblock = le32_to_cpu(start_ext->ee_block);
+		new_flag = 1;
+
+	} else if (!start_ext->ee_len && new_ext->ee_len &&
+		   end_ext->ee_len && o_start == o_end) {
+
+		/*	  new_ext	end_ext
+		 * donor |--------------|---------------|
+		 * orig  |------------------------------|
+		 */
+		o_end->ee_block = end_ext->ee_block;
+		o_end->ee_len = end_ext->ee_len;
+		ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
+
+		/*
+		 * Set 0 to the extent block if new_ext was
+		 * the first block.
+		 */
+		if (new_ext->ee_block)
+			eblock = le32_to_cpu(new_ext->ee_block);
+
+		new_flag = 1;
+	} else {
+		ext4_debug("ext4 move extent: Unexpected insert case\n");
+		return -EIO;
+	}
+
+	if (new_flag) {
+		err = get_ext_path(orig_inode, eblock, &orig_path);
+		if (err)
+			goto out;
+
+		if (ext4_ext_insert_extent(handle, orig_inode,
+					orig_path, new_ext, 0))
+			goto out;
+	}
+
+	if (end_flag) {
+		err = get_ext_path(orig_inode,
+				le32_to_cpu(end_ext->ee_block) - 1, &orig_path);
+		if (err)
+			goto out;
+
+		if (ext4_ext_insert_extent(handle, orig_inode,
+					   orig_path, end_ext, 0))
+			goto out;
+	}
+out:
+	if (orig_path) {
+		ext4_ext_drop_refs(orig_path);
+		kfree(orig_path);
+	}
+
+	return err;
+
+}
+
+/**
+ * mext_insert_inside_block - Insert new extent to the extent block
+ *
+ * @o_start:		first original extent to be moved
+ * @o_end:		last original extent to be moved
+ * @start_ext:		first new extent to be inserted
+ * @new_ext:		middle of new extent to be inserted
+ * @end_ext:		last new extent to be inserted
+ * @eh:			extent header of target leaf block
+ * @range_to_move:	used to decide how to insert extent
+ *
+ * Insert extents into the leaf block. The extent (@o_start) is overwritten
+ * by inserted extents.
+ */
+static void
+mext_insert_inside_block(struct ext4_extent *o_start,
+			      struct ext4_extent *o_end,
+			      struct ext4_extent *start_ext,
+			      struct ext4_extent *new_ext,
+			      struct ext4_extent *end_ext,
+			      struct ext4_extent_header *eh,
+			      int range_to_move)
+{
+	int i = 0;
+	unsigned long len;
+
+	/* Move the existing extents */
+	if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) {
+		len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) -
+			(unsigned long)(o_end + 1);
+		memmove(o_end + 1 + range_to_move, o_end + 1, len);
+	}
+
+	/* Insert start entry */
+	if (start_ext->ee_len)
+		o_start[i++].ee_len = start_ext->ee_len;
+
+	/* Insert new entry */
+	if (new_ext->ee_len) {
+		o_start[i] = *new_ext;
+		ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
+	}
+
+	/* Insert end entry */
+	if (end_ext->ee_len)
+		o_start[i] = *end_ext;
+
+	/* Increment the total entries counter on the extent block */
+	le16_add_cpu(&eh->eh_entries, range_to_move);
+}
+
+/**
+ * mext_insert_extents - Insert new extent
+ *
+ * @handle:	journal handle
+ * @orig_inode:	original inode
+ * @orig_path:	path indicates first extent to be changed
+ * @o_start:	first original extent to be changed
+ * @o_end:	last original extent to be changed
+ * @start_ext:	first new extent to be inserted
+ * @new_ext:	middle of new extent to be inserted
+ * @end_ext:	last new extent to be inserted
+ *
+ * Call the function to insert extents. If we cannot add more extents into
+ * the leaf block, we call mext_insert_across_blocks() to create a
+ * new leaf block. Otherwise call mext_insert_inside_block(). Return 0
+ * on success, or a negative error value on failure.
+ */
+static int
+mext_insert_extents(handle_t *handle, struct inode *orig_inode,
+			 struct ext4_ext_path *orig_path,
+			 struct ext4_extent *o_start,
+			 struct ext4_extent *o_end,
+			 struct ext4_extent *start_ext,
+			 struct ext4_extent *new_ext,
+			 struct ext4_extent *end_ext)
+{
+	struct  ext4_extent_header *eh;
+	unsigned long need_slots, slots_range;
+	int	range_to_move, depth, ret;
+
+	/*
+	 * The extents need to be inserted
+	 * start_extent + new_extent + end_extent.
+	 */
+	need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) +
+		(new_ext->ee_len ? 1 : 0);
+
+	/* The number of slots between start and end */
+	slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1)
+		/ sizeof(struct ext4_extent);
+
+	/* Range to move the end of extent */
+	range_to_move = need_slots - slots_range;
+	depth = orig_path->p_depth;
+	orig_path += depth;
+	eh = orig_path->p_hdr;
+
+	if (depth) {
+		/* Register to journal */
+		ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
+		if (ret)
+			return ret;
+	}
+
+	/* Expansion */
+	if (range_to_move > 0 &&
+		(range_to_move > le16_to_cpu(eh->eh_max)
+			- le16_to_cpu(eh->eh_entries))) {
+
+		ret = mext_insert_across_blocks(handle, orig_inode, o_start,
+					o_end, start_ext, new_ext, end_ext);
+		if (ret < 0)
+			return ret;
+	} else
+		mext_insert_inside_block(o_start, o_end, start_ext, new_ext,
+						end_ext, eh, range_to_move);
+
+	if (depth) {
+		ret = ext4_handle_dirty_metadata(handle, orig_inode,
+						 orig_path->p_bh);
+		if (ret)
+			return ret;
+	} else {
+		ret = ext4_mark_inode_dirty(handle, orig_inode);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * mext_leaf_block - Move one leaf extent block into the inode.
+ *
+ * @handle:		journal handle
+ * @orig_inode:		original inode
+ * @orig_path:		path indicates first extent to be changed
+ * @dext:		donor extent
+ * @from:		start offset on the target file
+ *
+ * In order to insert extents into the leaf block, we must divide the extent
+ * in the leaf block into three extents. The one is located to be inserted
+ * extents, and the others are located around it.
+ *
+ * Therefore, this function creates structures to save extents of the leaf
+ * block, and inserts extents by calling mext_insert_extents() with
+ * created extents. Return 0 on success, or a negative error value on failure.
+ */
+static int
+mext_leaf_block(handle_t *handle, struct inode *orig_inode,
+		     struct ext4_ext_path *orig_path, struct ext4_extent *dext,
+		     ext4_lblk_t *from)
+{
+	struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
+	struct ext4_extent new_ext, start_ext, end_ext;
+	ext4_lblk_t new_ext_end;
+	int oext_alen, new_ext_alen, end_ext_alen;
+	int depth = ext_depth(orig_inode);
+	int ret;
+
+	start_ext.ee_block = end_ext.ee_block = 0;
+	o_start = o_end = oext = orig_path[depth].p_ext;
+	oext_alen = ext4_ext_get_actual_len(oext);
+	start_ext.ee_len = end_ext.ee_len = 0;
+
+	new_ext.ee_block = cpu_to_le32(*from);
+	ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
+	new_ext.ee_len = dext->ee_len;
+	new_ext_alen = ext4_ext_get_actual_len(&new_ext);
+	new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
+
+	/*
+	 * Case: original extent is first
+	 * oext      |--------|
+	 * new_ext      |--|
+	 * start_ext |--|
+	 */
+	if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) &&
+		le32_to_cpu(new_ext.ee_block) <
+		le32_to_cpu(oext->ee_block) + oext_alen) {
+		start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
+					       le32_to_cpu(oext->ee_block));
+		start_ext.ee_block = oext->ee_block;
+		copy_extent_status(oext, &start_ext);
+	} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
+		prev_ext = oext - 1;
+		/*
+		 * We can merge new_ext into previous extent,
+		 * if these are contiguous and same extent type.
+		 */
+		if (ext4_can_extents_be_merged(orig_inode, prev_ext,
+					       &new_ext)) {
+			o_start = prev_ext;
+			start_ext.ee_len = cpu_to_le16(
+				ext4_ext_get_actual_len(prev_ext) +
+				new_ext_alen);
+			start_ext.ee_block = oext->ee_block;
+			copy_extent_status(prev_ext, &start_ext);
+			new_ext.ee_len = 0;
+		}
+	}
+
+	/*
+	 * Case: new_ext_end must be less than oext
+	 * oext      |-----------|
+	 * new_ext       |-------|
+	 */
+	if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
+		EXT4_ERROR_INODE(orig_inode,
+			"new_ext_end(%u) should be less than or equal to "
+			"oext->ee_block(%u) + oext_alen(%d) - 1",
+			new_ext_end, le32_to_cpu(oext->ee_block),
+			oext_alen);
+		ret = -EIO;
+		goto out;
+	}
+
+	/*
+	 * Case: new_ext is smaller than original extent
+	 * oext    |---------------|
+	 * new_ext |-----------|
+	 * end_ext             |---|
+	 */
+	if (le32_to_cpu(oext->ee_block) <= new_ext_end &&
+		new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) {
+		end_ext.ee_len =
+			cpu_to_le16(le32_to_cpu(oext->ee_block) +
+			oext_alen - 1 - new_ext_end);
+		copy_extent_status(oext, &end_ext);
+		end_ext_alen = ext4_ext_get_actual_len(&end_ext);
+		ext4_ext_store_pblock(&end_ext,
+			(ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
+		end_ext.ee_block =
+			cpu_to_le32(le32_to_cpu(o_end->ee_block) +
+			oext_alen - end_ext_alen);
+	}
+
+	ret = mext_insert_extents(handle, orig_inode, orig_path, o_start,
+				o_end, &start_ext, &new_ext, &end_ext);
+out:
+	return ret;
+}
+
+/**
+ * mext_calc_swap_extents - Calculate extents for extent swapping.
+ *
+ * @tmp_dext:		the extent that will belong to the original inode
+ * @tmp_oext:		the extent that will belong to the donor inode
+ * @orig_off:		block offset of original inode
+ * @donor_off:		block offset of donor inode
+ * @max_count:		the maximum length of extents
+ *
+ * Return 0 on success, or a negative error value on failure.
+ */
+static int
+mext_calc_swap_extents(struct ext4_extent *tmp_dext,
+			      struct ext4_extent *tmp_oext,
+			      ext4_lblk_t orig_off, ext4_lblk_t donor_off,
+			      ext4_lblk_t max_count)
+{
+	ext4_lblk_t diff, orig_diff;
+	struct ext4_extent dext_old, oext_old;
+
+	BUG_ON(orig_off != donor_off);
+
+	/* original and donor extents have to cover the same block offset */
+	if (orig_off < le32_to_cpu(tmp_oext->ee_block) ||
+	    le32_to_cpu(tmp_oext->ee_block) +
+			ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off)
+		return -ENODATA;
+
+	if (orig_off < le32_to_cpu(tmp_dext->ee_block) ||
+	    le32_to_cpu(tmp_dext->ee_block) +
+			ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off)
+		return -ENODATA;
+
+	dext_old = *tmp_dext;
+	oext_old = *tmp_oext;
+
+	/* When tmp_dext is too large, pick up the target range. */
+	diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
+
+	ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
+	tmp_dext->ee_block =
+			cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff);
+	tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff);
+
+	if (max_count < ext4_ext_get_actual_len(tmp_dext))
+		tmp_dext->ee_len = cpu_to_le16(max_count);
+
+	orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
+	ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
+
+	/* Adjust extent length if donor extent is larger than orig */
+	if (ext4_ext_get_actual_len(tmp_dext) >
+	    ext4_ext_get_actual_len(tmp_oext) - orig_diff)
+		tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) -
+						orig_diff);
+
+	tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext));
+
+	copy_extent_status(&oext_old, tmp_dext);
+	copy_extent_status(&dext_old, tmp_oext);
+
+	return 0;
+}
+
+/**
+ * mext_replace_branches - Replace original extents with new extents
+ *
+ * @handle:		journal handle
+ * @orig_inode:		original inode
+ * @donor_inode:	donor inode
+ * @from:		block offset of orig_inode
+ * @count:		block count to be replaced
+ * @err:		pointer to save return value
+ *
+ * Replace original inode extents and donor inode extents page by page.
+ * We implement this replacement in the following three steps:
+ * 1. Save the block information of original and donor inodes into
+ *    dummy extents.
+ * 2. Change the block information of original inode to point at the
+ *    donor inode blocks.
+ * 3. Change the block information of donor inode to point at the saved
+ *    original inode blocks in the dummy extents.
+ *
+ * Return replaced block count.
+ */
+static int
+mext_replace_branches(handle_t *handle, struct inode *orig_inode,
+			   struct inode *donor_inode, ext4_lblk_t from,
+			   ext4_lblk_t count, int *err)
+{
+	struct ext4_ext_path *orig_path = NULL;
+	struct ext4_ext_path *donor_path = NULL;
+	struct ext4_extent *oext, *dext;
+	struct ext4_extent tmp_dext, tmp_oext;
+	ext4_lblk_t orig_off = from, donor_off = from;
+	int depth;
+	int replaced_count = 0;
+	int dext_alen;
+
+	/* Protect extent trees against block allocations via delalloc */
+	double_down_write_data_sem(orig_inode, donor_inode);
+
+	/* Get the original extent for the block "orig_off" */
+	*err = get_ext_path(orig_inode, orig_off, &orig_path);
+	if (*err)
+		goto out;
+
+	/* Get the donor extent for the head */
+	*err = get_ext_path(donor_inode, donor_off, &donor_path);
+	if (*err)
+		goto out;
+	depth = ext_depth(orig_inode);
+	oext = orig_path[depth].p_ext;
+	tmp_oext = *oext;
+
+	depth = ext_depth(donor_inode);
+	dext = donor_path[depth].p_ext;
+	tmp_dext = *dext;
+
+	*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+				      donor_off, count);
+	if (*err)
+		goto out;
+
+	/* Loop for the donor extents */
+	while (1) {
+		/* The extent for donor must be found. */
+		if (!dext) {
+			EXT4_ERROR_INODE(donor_inode,
+				   "The extent for donor must be found");
+			*err = -EIO;
+			goto out;
+		} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
+			EXT4_ERROR_INODE(donor_inode,
+				"Donor offset(%u) and the first block of donor "
+				"extent(%u) should be equal",
+				donor_off,
+				le32_to_cpu(tmp_dext.ee_block));
+			*err = -EIO;
+			goto out;
+		}
+
+		/* Set donor extent to orig extent */
+		*err = mext_leaf_block(handle, orig_inode,
+					   orig_path, &tmp_dext, &orig_off);
+		if (*err)
+			goto out;
+
+		/* Set orig extent to donor extent */
+		*err = mext_leaf_block(handle, donor_inode,
+					   donor_path, &tmp_oext, &donor_off);
+		if (*err)
+			goto out;
+
+		dext_alen = ext4_ext_get_actual_len(&tmp_dext);
+		replaced_count += dext_alen;
+		donor_off += dext_alen;
+		orig_off += dext_alen;
+
+		/* Already moved the expected blocks */
+		if (replaced_count >= count)
+			break;
+
+		if (orig_path)
+			ext4_ext_drop_refs(orig_path);
+		*err = get_ext_path(orig_inode, orig_off, &orig_path);
+		if (*err)
+			goto out;
+		depth = ext_depth(orig_inode);
+		oext = orig_path[depth].p_ext;
+		tmp_oext = *oext;
+
+		if (donor_path)
+			ext4_ext_drop_refs(donor_path);
+		*err = get_ext_path(donor_inode, donor_off, &donor_path);
+		if (*err)
+			goto out;
+		depth = ext_depth(donor_inode);
+		dext = donor_path[depth].p_ext;
+		tmp_dext = *dext;
+
+		*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+					   donor_off, count - replaced_count);
+		if (*err)
+			goto out;
+	}
+
+out:
+	if (orig_path) {
+		ext4_ext_drop_refs(orig_path);
+		kfree(orig_path);
+	}
+	if (donor_path) {
+		ext4_ext_drop_refs(donor_path);
+		kfree(donor_path);
+	}
+
+	ext4_ext_invalidate_cache(orig_inode);
+	ext4_ext_invalidate_cache(donor_inode);
+
+	double_up_write_data_sem(orig_inode, donor_inode);
+
+	return replaced_count;
+}
+
+/**
+ * move_extent_per_page - Move extent data per page
+ *
+ * @o_filp:			file structure of original file
+ * @donor_inode:		donor inode
+ * @orig_page_offset:		page index on original file
+ * @data_offset_in_page:	block index where data swapping starts
+ * @block_len_in_page:		the number of blocks to be swapped
+ * @uninit:			orig extent is uninitialized or not
+ * @err:			pointer to save return value
+ *
+ * Save the data in original inode blocks and replace original inode extents
+ * with donor inode extents by calling mext_replace_branches().
+ * Finally, write out the saved data in new original inode blocks. Return
+ * replaced block count.
+ */
+static int
+move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
+		  pgoff_t orig_page_offset, int data_offset_in_page,
+		  int block_len_in_page, int uninit, int *err)
+{
+	struct inode *orig_inode = o_filp->f_dentry->d_inode;
+	struct address_space *mapping = orig_inode->i_mapping;
+	struct buffer_head *bh;
+	struct page *page = NULL;
+	const struct address_space_operations *a_ops = mapping->a_ops;
+	handle_t *handle;
+	ext4_lblk_t orig_blk_offset;
+	long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
+	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
+	unsigned int w_flags = 0;
+	unsigned int tmp_data_size, data_size, replaced_size;
+	void *fsdata;
+	int i, jblocks;
+	int err2 = 0;
+	int replaced_count = 0;
+	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
+
+	/*
+	 * It needs twice the amount of ordinary journal buffers because
+	 * inode and donor_inode may change each different metadata blocks.
+	 */
+	jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
+	handle = ext4_journal_start(orig_inode, jblocks);
+	if (IS_ERR(handle)) {
+		*err = PTR_ERR(handle);
+		return 0;
+	}
+
+	if (segment_eq(get_fs(), KERNEL_DS))
+		w_flags |= AOP_FLAG_UNINTERRUPTIBLE;
+
+	orig_blk_offset = orig_page_offset * blocks_per_page +
+		data_offset_in_page;
+
+	/*
+	 * If orig extent is uninitialized one,
+	 * it's not necessary force the page into memory
+	 * and then force it to be written out again.
+	 * Just swap data blocks between orig and donor.
+	 */
+	if (uninit) {
+		replaced_count = mext_replace_branches(handle, orig_inode,
+						donor_inode, orig_blk_offset,
+						block_len_in_page, err);
+		goto out2;
+	}
+
+	offs = (long long)orig_blk_offset << orig_inode->i_blkbits;
+
+	/* Calculate data_size */
+	if ((orig_blk_offset + block_len_in_page - 1) ==
+	    ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
+		/* Replace the last block */
+		tmp_data_size = orig_inode->i_size & (blocksize - 1);
+		/*
+		 * If data_size equal zero, it shows data_size is multiples of
+		 * blocksize. So we set appropriate value.
+		 */
+		if (tmp_data_size == 0)
+			tmp_data_size = blocksize;
+
+		data_size = tmp_data_size +
+			((block_len_in_page - 1) << orig_inode->i_blkbits);
+	} else
+		data_size = block_len_in_page << orig_inode->i_blkbits;
+
+	replaced_size = data_size;
+
+	*err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags,
+				 &page, &fsdata);
+	if (unlikely(*err < 0))
+		goto out;
+
+	if (!PageUptodate(page)) {
+		mapping->a_ops->readpage(o_filp, page);
+		lock_page(page);
+	}
+
+	/*
+	 * try_to_release_page() doesn't call releasepage in writeback mode.
+	 * We should care about the order of writing to the same file
+	 * by multiple move extent processes.
+	 * It needs to call wait_on_page_writeback() to wait for the
+	 * writeback of the page.
+	 */
+	wait_on_page_writeback(page);
+
+	/* Release old bh and drop refs */
+	try_to_release_page(page, 0);
+
+	replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
+					orig_blk_offset, block_len_in_page,
+					&err2);
+	if (err2) {
+		if (replaced_count) {
+			block_len_in_page = replaced_count;
+			replaced_size =
+				block_len_in_page << orig_inode->i_blkbits;
+		} else
+			goto out;
+	}
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0);
+
+	bh = page_buffers(page);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode,
+				(sector_t)(orig_blk_offset + i), bh, 0);
+		if (*err < 0)
+			goto out;
+
+		if (bh->b_this_page != NULL)
+			bh = bh->b_this_page;
+	}
+
+	*err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size,
+			       page, fsdata);
+	page = NULL;
+
+out:
+	if (unlikely(page)) {
+		if (PageLocked(page))
+			unlock_page(page);
+		page_cache_release(page);
+		ext4_journal_stop(handle);
+	}
+out2:
+	ext4_journal_stop(handle);
+
+	if (err2)
+		*err = err2;
+
+	return replaced_count;
+}
+
+/**
+ * mext_check_arguments - Check whether move extent can be done
+ *
+ * @orig_inode:		original inode
+ * @donor_inode:	donor inode
+ * @orig_start:		logical start offset in block for orig
+ * @donor_start:	logical start offset in block for donor
+ * @len:		the number of blocks to be moved
+ *
+ * Check the arguments of ext4_move_extents() whether the files can be
+ * exchanged with each other.
+ * Return 0 on success, or a negative error value on failure.
+ */
+static int
+mext_check_arguments(struct inode *orig_inode,
+		     struct inode *donor_inode, __u64 orig_start,
+		     __u64 donor_start, __u64 *len)
+{
+	ext4_lblk_t orig_blocks, donor_blocks;
+	unsigned int blkbits = orig_inode->i_blkbits;
+	unsigned int blocksize = 1 << blkbits;
+
+	if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
+		ext4_debug("ext4 move extent: suid or sgid is set"
+			   " to donor file [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
+		return -EPERM;
+
+	/* Ext4 move extent does not support swapfile */
+	if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
+		ext4_debug("ext4 move extent: The argument files should "
+			"not be swapfile [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* Files should be in the same ext4 FS */
+	if (orig_inode->i_sb != donor_inode->i_sb) {
+		ext4_debug("ext4 move extent: The argument files "
+			"should be in same FS [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* Ext4 move extent supports only extent based file */
+	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
+		ext4_debug("ext4 move extent: orig file is not extents "
+			"based file [ino:orig %lu]\n", orig_inode->i_ino);
+		return -EOPNOTSUPP;
+	} else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
+		ext4_debug("ext4 move extent: donor file is not extents "
+			"based file [ino:donor %lu]\n", donor_inode->i_ino);
+		return -EOPNOTSUPP;
+	}
+
+	if ((!orig_inode->i_size) || (!donor_inode->i_size)) {
+		ext4_debug("ext4 move extent: File size is 0 byte\n");
+		return -EINVAL;
+	}
+
+	/* Start offset should be same */
+	if (orig_start != donor_start) {
+		ext4_debug("ext4 move extent: orig and donor's start "
+			"offset are not same [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if ((orig_start >= EXT_MAX_BLOCKS) ||
+	    (donor_start >= EXT_MAX_BLOCKS) ||
+	    (*len > EXT_MAX_BLOCKS) ||
+	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
+		ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
+			"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if (orig_inode->i_size > donor_inode->i_size) {
+		donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits;
+		/* TODO: eliminate this artificial restriction */
+		if (orig_start >= donor_blocks) {
+			ext4_debug("ext4 move extent: orig start offset "
+			"[%llu] should be less than donor file blocks "
+			"[%u] [ino:orig %lu, donor %lu]\n",
+			orig_start, donor_blocks,
+			orig_inode->i_ino, donor_inode->i_ino);
+			return -EINVAL;
+		}
+
+		/* TODO: eliminate this artificial restriction */
+		if (orig_start + *len > donor_blocks) {
+			ext4_debug("ext4 move extent: End offset [%llu] should "
+				"be less than donor file blocks [%u]."
+				"So adjust length from %llu to %llu "
+				"[ino:orig %lu, donor %lu]\n",
+				orig_start + *len, donor_blocks,
+				*len, donor_blocks - orig_start,
+				orig_inode->i_ino, donor_inode->i_ino);
+			*len = donor_blocks - orig_start;
+		}
+	} else {
+		orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits;
+		if (orig_start >= orig_blocks) {
+			ext4_debug("ext4 move extent: start offset [%llu] "
+				"should be less than original file blocks "
+				"[%u] [ino:orig %lu, donor %lu]\n",
+				 orig_start, orig_blocks,
+				orig_inode->i_ino, donor_inode->i_ino);
+			return -EINVAL;
+		}
+
+		if (orig_start + *len > orig_blocks) {
+			ext4_debug("ext4 move extent: Adjust length "
+				"from %llu to %llu. Because it should be "
+				"less than original file blocks "
+				"[ino:orig %lu, donor %lu]\n",
+				*len, orig_blocks - orig_start,
+				orig_inode->i_ino, donor_inode->i_ino);
+			*len = orig_blocks - orig_start;
+		}
+	}
+
+	if (!*len) {
+		ext4_debug("ext4 move extent: len should not be 0 "
+			"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
+			donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
+ *
+ * @inode1:	the inode structure
+ * @inode2:	the inode structure
+ *
+ * Lock two inodes' i_mutex by i_ino order.
+ * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
+ */
+static int
+mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
+{
+	int ret = 0;
+
+	BUG_ON(inode1 == NULL && inode2 == NULL);
+
+	ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
+	if (ret < 0)
+		goto out;
+
+	if (inode1 == inode2) {
+		mutex_lock(&inode1->i_mutex);
+		goto out;
+	}
+
+	if (inode1->i_ino < inode2->i_ino) {
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+	} else {
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
+	}
+
+out:
+	return ret;
+}
+
+/**
+ * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
+ *
+ * @inode1:     the inode that is released first
+ * @inode2:     the inode that is released second
+ *
+ * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0.
+ */
+
+static int
+mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
+{
+	int ret = 0;
+
+	BUG_ON(inode1 == NULL && inode2 == NULL);
+
+	ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
+	if (ret < 0)
+		goto out;
+
+	if (inode1)
+		mutex_unlock(&inode1->i_mutex);
+
+	if (inode2 && inode2 != inode1)
+		mutex_unlock(&inode2->i_mutex);
+
+out:
+	return ret;
+}
+
+/**
+ * ext4_move_extents - Exchange the specified range of a file
+ *
+ * @o_filp:		file structure of the original file
+ * @d_filp:		file structure of the donor file
+ * @orig_start:		start offset in block for orig
+ * @donor_start:	start offset in block for donor
+ * @len:		the number of blocks to be moved
+ * @moved_len:		moved block length
+ *
+ * This function returns 0 and moved block length is set in moved_len
+ * if succeed, otherwise returns error value.
+ *
+ * Note: ext4_move_extents() proceeds the following order.
+ * 1:ext4_move_extents() calculates the last block number of moving extent
+ *   function by the start block number (orig_start) and the number of blocks
+ *   to be moved (len) specified as arguments.
+ *   If the {orig, donor}_start points a hole, the extent's start offset
+ *   pointed by ext_cur (current extent), holecheck_path, orig_path are set
+ *   after hole behind.
+ * 2:Continue step 3 to step 5, until the holecheck_path points to last_extent
+ *   or the ext_cur exceeds the block_end which is last logical block number.
+ * 3:To get the length of continues area, call mext_next_extent()
+ *   specified with the ext_cur (initial value is holecheck_path) re-cursive,
+ *   until find un-continuous extent, the start logical block number exceeds
+ *   the block_end or the extent points to the last extent.
+ * 4:Exchange the original inode data with donor inode data
+ *   from orig_page_offset to seq_end_page.
+ *   The start indexes of data are specified as arguments.
+ *   That of the original inode is orig_page_offset,
+ *   and the donor inode is also orig_page_offset
+ *   (To easily handle blocksize != pagesize case, the offset for the
+ *   donor inode is block unit).
+ * 5:Update holecheck_path and orig_path to points a next proceeding extent,
+ *   then returns to step 2.
+ * 6:Release holecheck_path, orig_path and set the len to moved_len
+ *   which shows the number of moved blocks.
+ *   The moved_len is useful for the command to calculate the file offset
+ *   for starting next move extent ioctl.
+ * 7:Return 0 on success, or a negative error value on failure.
+ */
+int
+ext4_move_extents(struct file *o_filp, struct file *d_filp,
+		 __u64 orig_start, __u64 donor_start, __u64 len,
+		 __u64 *moved_len)
+{
+	struct inode *orig_inode = o_filp->f_dentry->d_inode;
+	struct inode *donor_inode = d_filp->f_dentry->d_inode;
+	struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL;
+	struct ext4_extent *ext_prev, *ext_cur, *ext_dummy;
+	ext4_lblk_t block_start = orig_start;
+	ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0;
+	ext4_lblk_t rest_blocks;
+	pgoff_t orig_page_offset = 0, seq_end_page;
+	int ret1, ret2, depth, last_extent = 0;
+	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
+	int data_offset_in_page;
+	int block_len_in_page;
+	int uninit;
+
+	/* orig and donor should be different file */
+	if (orig_inode->i_ino == donor_inode->i_ino) {
+		ext4_debug("ext4 move extent: The argument files should not "
+			"be same file [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* Regular file check */
+	if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
+		ext4_debug("ext4 move extent: The argument files should be "
+			"regular file [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* Protect orig and donor inodes against a truncate */
+	ret1 = mext_inode_double_lock(orig_inode, donor_inode);
+	if (ret1 < 0)
+		return ret1;
+
+	/* Protect extent tree against block allocations via delalloc */
+	double_down_write_data_sem(orig_inode, donor_inode);
+	/* Check the filesystem environment whether move_extent can be done */
+	ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
+				    donor_start, &len);
+	if (ret1)
+		goto out;
+
+	file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
+	block_end = block_start + len - 1;
+	if (file_end < block_end)
+		len -= block_end - file_end;
+
+	ret1 = get_ext_path(orig_inode, block_start, &orig_path);
+	if (ret1)
+		goto out;
+
+	/* Get path structure to check the hole */
+	ret1 = get_ext_path(orig_inode, block_start, &holecheck_path);
+	if (ret1)
+		goto out;
+
+	depth = ext_depth(orig_inode);
+	ext_cur = holecheck_path[depth].p_ext;
+
+	/*
+	 * Get proper starting location of block replacement if block_start was
+	 * within the hole.
+	 */
+	if (le32_to_cpu(ext_cur->ee_block) +
+		ext4_ext_get_actual_len(ext_cur) - 1 < block_start) {
+		/*
+		 * The hole exists between extents or the tail of
+		 * original file.
+		 */
+		last_extent = mext_next_extent(orig_inode,
+					holecheck_path, &ext_cur);
+		if (last_extent < 0) {
+			ret1 = last_extent;
+			goto out;
+		}
+		last_extent = mext_next_extent(orig_inode, orig_path,
+							&ext_dummy);
+		if (last_extent < 0) {
+			ret1 = last_extent;
+			goto out;
+		}
+		seq_start = le32_to_cpu(ext_cur->ee_block);
+	} else if (le32_to_cpu(ext_cur->ee_block) > block_start)
+		/* The hole exists at the beginning of original file. */
+		seq_start = le32_to_cpu(ext_cur->ee_block);
+	else
+		seq_start = block_start;
+
+	/* No blocks within the specified range. */
+	if (le32_to_cpu(ext_cur->ee_block) > block_end) {
+		ext4_debug("ext4 move extent: The specified range of file "
+							"may be the hole\n");
+		ret1 = -EINVAL;
+		goto out;
+	}
+
+	/* Adjust start blocks */
+	add_blocks = min(le32_to_cpu(ext_cur->ee_block) +
+			 ext4_ext_get_actual_len(ext_cur), block_end + 1) -
+		     max(le32_to_cpu(ext_cur->ee_block), block_start);
+
+	while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) {
+		seq_blocks += add_blocks;
+
+		/* Adjust tail blocks */
+		if (seq_start + seq_blocks - 1 > block_end)
+			seq_blocks = block_end - seq_start + 1;
+
+		ext_prev = ext_cur;
+		last_extent = mext_next_extent(orig_inode, holecheck_path,
+						&ext_cur);
+		if (last_extent < 0) {
+			ret1 = last_extent;
+			break;
+		}
+		add_blocks = ext4_ext_get_actual_len(ext_cur);
+
+		/*
+		 * Extend the length of contiguous block (seq_blocks)
+		 * if extents are contiguous.
+		 */
+		if (ext4_can_extents_be_merged(orig_inode,
+					       ext_prev, ext_cur) &&
+		    block_end >= le32_to_cpu(ext_cur->ee_block) &&
+		    !last_extent)
+			continue;
+
+		/* Is original extent is uninitialized */
+		uninit = ext4_ext_is_uninitialized(ext_prev);
+
+		data_offset_in_page = seq_start % blocks_per_page;
+
+		/*
+		 * Calculate data blocks count that should be swapped
+		 * at the first page.
+		 */
+		if (data_offset_in_page + seq_blocks > blocks_per_page) {
+			/* Swapped blocks are across pages */
+			block_len_in_page =
+					blocks_per_page - data_offset_in_page;
+		} else {
+			/* Swapped blocks are in a page */
+			block_len_in_page = seq_blocks;
+		}
+
+		orig_page_offset = seq_start >>
+				(PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
+		seq_end_page = (seq_start + seq_blocks - 1) >>
+				(PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
+		seq_start = le32_to_cpu(ext_cur->ee_block);
+		rest_blocks = seq_blocks;
+
+		/*
+		 * Up semaphore to avoid following problems:
+		 * a. transaction deadlock among ext4_journal_start,
+		 *    ->write_begin via pagefault, and jbd2_journal_commit
+		 * b. racing with ->readpage, ->write_begin, and ext4_get_block
+		 *    in move_extent_per_page
+		 */
+		double_up_write_data_sem(orig_inode, donor_inode);
+
+		while (orig_page_offset <= seq_end_page) {
+
+			/* Swap original branches with new branches */
+			block_len_in_page = move_extent_per_page(
+						o_filp, donor_inode,
+						orig_page_offset,
+						data_offset_in_page,
+						block_len_in_page, uninit,
+						&ret1);
+
+			/* Count how many blocks we have exchanged */
+			*moved_len += block_len_in_page;
+			if (ret1 < 0)
+				break;
+			if (*moved_len > len) {
+				EXT4_ERROR_INODE(orig_inode,
+					"We replaced blocks too much! "
+					"sum of replaced: %llu requested: %llu",
+					*moved_len, len);
+				ret1 = -EIO;
+				break;
+			}
+
+			orig_page_offset++;
+			data_offset_in_page = 0;
+			rest_blocks -= block_len_in_page;
+			if (rest_blocks > blocks_per_page)
+				block_len_in_page = blocks_per_page;
+			else
+				block_len_in_page = rest_blocks;
+		}
+
+		double_down_write_data_sem(orig_inode, donor_inode);
+		if (ret1 < 0)
+			break;
+
+		/* Decrease buffer counter */
+		if (holecheck_path)
+			ext4_ext_drop_refs(holecheck_path);
+		ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path);
+		if (ret1)
+			break;
+		depth = holecheck_path->p_depth;
+
+		/* Decrease buffer counter */
+		if (orig_path)
+			ext4_ext_drop_refs(orig_path);
+		ret1 = get_ext_path(orig_inode, seq_start, &orig_path);
+		if (ret1)
+			break;
+
+		ext_cur = holecheck_path[depth].p_ext;
+		add_blocks = ext4_ext_get_actual_len(ext_cur);
+		seq_blocks = 0;
+
+	}
+out:
+	if (*moved_len) {
+		ext4_discard_preallocations(orig_inode);
+		ext4_discard_preallocations(donor_inode);
+	}
+
+	if (orig_path) {
+		ext4_ext_drop_refs(orig_path);
+		kfree(orig_path);
+	}
+	if (holecheck_path) {
+		ext4_ext_drop_refs(holecheck_path);
+		kfree(holecheck_path);
+	}
+	double_up_write_data_sem(orig_inode, donor_inode);
+	ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
+
+	if (ret1)
+		return ret1;
+	else if (ret2)
+		return ret2;
+
+	return 0;
+}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
new file mode 100644
index 00000000..3d36d5a1
--- /dev/null
+++ b/fs/ext4/namei.c
@@ -0,0 +1,2612 @@
+/*
+ *  linux/fs/ext4/namei.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/namei.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *  Directory entry file type support and forward compatibility hooks
+ *	for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998
+ *  Hash Tree Directory indexing (c)
+ *	Daniel Phillips, 2001
+ *  Hash Tree Directory indexing porting
+ *	Christopher Li, 2002
+ *  Hash Tree Directory indexing cleanup
+ *	Theodore Ts'o, 2002
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/jbd2.h>
+#include <linux/time.h>
+#include <linux/fcntl.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/bio.h>
+#include "ext4.h"
+#include "ext4_jbd2.h"
+
+#include "xattr.h"
+#include "acl.h"
+
+#include <trace/events/ext4.h>
+/*
+ * define how far ahead to read directories while searching them.
+ */
+#define NAMEI_RA_CHUNKS  2
+#define NAMEI_RA_BLOCKS  4
+#define NAMEI_RA_SIZE	     (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
+#define NAMEI_RA_INDEX(c,b)  (((c) * NAMEI_RA_BLOCKS) + (b))
+
+static struct buffer_head *ext4_append(handle_t *handle,
+					struct inode *inode,
+					ext4_lblk_t *block, int *err)
+{
+	struct buffer_head *bh;
+
+	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
+
+	bh = ext4_bread(handle, inode, *block, 1, err);
+	if (bh) {
+		inode->i_size += inode->i_sb->s_blocksize;
+		EXT4_I(inode)->i_disksize = inode->i_size;
+		*err = ext4_journal_get_write_access(handle, bh);
+		if (*err) {
+			brelse(bh);
+			bh = NULL;
+		}
+	}
+	return bh;
+}
+
+#ifndef assert
+#define assert(test) J_ASSERT(test)
+#endif
+
+#ifdef DX_DEBUG
+#define dxtrace(command) command
+#else
+#define dxtrace(command)
+#endif
+
+struct fake_dirent
+{
+	__le32 inode;
+	__le16 rec_len;
+	u8 name_len;
+	u8 file_type;
+};
+
+struct dx_countlimit
+{
+	__le16 limit;
+	__le16 count;
+};
+
+struct dx_entry
+{
+	__le32 hash;
+	__le32 block;
+};
+
+/*
+ * dx_root_info is laid out so that if it should somehow get overlaid by a
+ * dirent the two low bits of the hash version will be zero.  Therefore, the
+ * hash version mod 4 should never be 0.  Sincerely, the paranoia department.
+ */
+
+struct dx_root
+{
+	struct fake_dirent dot;
+	char dot_name[4];
+	struct fake_dirent dotdot;
+	char dotdot_name[4];
+	struct dx_root_info
+	{
+		__le32 reserved_zero;
+		u8 hash_version;
+		u8 info_length; /* 8 */
+		u8 indirect_levels;
+		u8 unused_flags;
+	}
+	info;
+	struct dx_entry	entries[0];
+};
+
+struct dx_node
+{
+	struct fake_dirent fake;
+	struct dx_entry	entries[0];
+};
+
+
+struct dx_frame
+{
+	struct buffer_head *bh;
+	struct dx_entry *entries;
+	struct dx_entry *at;
+};
+
+struct dx_map_entry
+{
+	u32 hash;
+	u16 offs;
+	u16 size;
+};
+
+static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
+static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
+static inline unsigned dx_get_hash(struct dx_entry *entry);
+static void dx_set_hash(struct dx_entry *entry, unsigned value);
+static unsigned dx_get_count(struct dx_entry *entries);
+static unsigned dx_get_limit(struct dx_entry *entries);
+static void dx_set_count(struct dx_entry *entries, unsigned value);
+static void dx_set_limit(struct dx_entry *entries, unsigned value);
+static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
+static unsigned dx_node_limit(struct inode *dir);
+static struct dx_frame *dx_probe(const struct qstr *d_name,
+				 struct inode *dir,
+				 struct dx_hash_info *hinfo,
+				 struct dx_frame *frame,
+				 int *err);
+static void dx_release(struct dx_frame *frames);
+static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
+		       struct dx_hash_info *hinfo, struct dx_map_entry map[]);
+static void dx_sort_map(struct dx_map_entry *map, unsigned count);
+static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
+		struct dx_map_entry *offsets, int count, unsigned blocksize);
+static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize);
+static void dx_insert_block(struct dx_frame *frame,
+					u32 hash, ext4_lblk_t block);
+static int ext4_htree_next_block(struct inode *dir, __u32 hash,
+				 struct dx_frame *frame,
+				 struct dx_frame *frames,
+				 __u32 *start_hash);
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
+		const struct qstr *d_name,
+		struct ext4_dir_entry_2 **res_dir,
+		int *err);
+static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
+			     struct inode *inode);
+
+/*
+ * p is at least 6 bytes before the end of page
+ */
+static inline struct ext4_dir_entry_2 *
+ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize)
+{
+	return (struct ext4_dir_entry_2 *)((char *)p +
+		ext4_rec_len_from_disk(p->rec_len, blocksize));
+}
+
+/*
+ * Future: use high four bits of block for coalesce-on-delete flags
+ * Mask them off for now.
+ */
+
+static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
+{
+	return le32_to_cpu(entry->block) & 0x00ffffff;
+}
+
+static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
+{
+	entry->block = cpu_to_le32(value);
+}
+
+static inline unsigned dx_get_hash(struct dx_entry *entry)
+{
+	return le32_to_cpu(entry->hash);
+}
+
+static inline void dx_set_hash(struct dx_entry *entry, unsigned value)
+{
+	entry->hash = cpu_to_le32(value);
+}
+
+static inline unsigned dx_get_count(struct dx_entry *entries)
+{
+	return le16_to_cpu(((struct dx_countlimit *) entries)->count);
+}
+
+static inline unsigned dx_get_limit(struct dx_entry *entries)
+{
+	return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
+}
+
+static inline void dx_set_count(struct dx_entry *entries, unsigned value)
+{
+	((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
+}
+
+static inline void dx_set_limit(struct dx_entry *entries, unsigned value)
+{
+	((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
+}
+
+static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
+{
+	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
+		EXT4_DIR_REC_LEN(2) - infosize;
+	return entry_space / sizeof(struct dx_entry);
+}
+
+static inline unsigned dx_node_limit(struct inode *dir)
+{
+	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
+	return entry_space / sizeof(struct dx_entry);
+}
+
+/*
+ * Debug
+ */
+#ifdef DX_DEBUG
+static void dx_show_index(char * label, struct dx_entry *entries)
+{
+	int i, n = dx_get_count (entries);
+	printk(KERN_DEBUG "%s index ", label);
+	for (i = 0; i < n; i++) {
+		printk("%x->%lu ", i ? dx_get_hash(entries + i) :
+				0, (unsigned long)dx_get_block(entries + i));
+	}
+	printk("\n");
+}
+
+struct stats
+{
+	unsigned names;
+	unsigned space;
+	unsigned bcount;
+};
+
+static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de,
+				 int size, int show_names)
+{
+	unsigned names = 0, space = 0;
+	char *base = (char *) de;
+	struct dx_hash_info h = *hinfo;
+
+	printk("names: ");
+	while ((char *) de < base + size)
+	{
+		if (de->inode)
+		{
+			if (show_names)
+			{
+				int len = de->name_len;
+				char *name = de->name;
+				while (len--) printk("%c", *name++);
+				ext4fs_dirhash(de->name, de->name_len, &h);
+				printk(":%x.%u ", h.hash,
+				       ((char *) de - base));
+			}
+			space += EXT4_DIR_REC_LEN(de->name_len);
+			names++;
+		}
+		de = ext4_next_entry(de, size);
+	}
+	printk("(%i)\n", names);
+	return (struct stats) { names, space, 1 };
+}
+
+struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
+			     struct dx_entry *entries, int levels)
+{
+	unsigned blocksize = dir->i_sb->s_blocksize;
+	unsigned count = dx_get_count(entries), names = 0, space = 0, i;
+	unsigned bcount = 0;
+	struct buffer_head *bh;
+	int err;
+	printk("%i indexed blocks...\n", count);
+	for (i = 0; i < count; i++, entries++)
+	{
+		ext4_lblk_t block = dx_get_block(entries);
+		ext4_lblk_t hash  = i ? dx_get_hash(entries): 0;
+		u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
+		struct stats stats;
+		printk("%s%3u:%03u hash %8x/%8x ",levels?"":"   ", i, block, hash, range);
+		if (!(bh = ext4_bread (NULL,dir, block, 0,&err))) continue;
+		stats = levels?
+		   dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
+		   dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0);
+		names += stats.names;
+		space += stats.space;
+		bcount += stats.bcount;
+		brelse(bh);
+	}
+	if (bcount)
+		printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n",
+		       levels ? "" : "   ", names, space/bcount,
+		       (space/bcount)*100/blocksize);
+	return (struct stats) { names, space, bcount};
+}
+#endif /* DX_DEBUG */
+
+/*
+ * Probe for a directory leaf block to search.
+ *
+ * dx_probe can return ERR_BAD_DX_DIR, which means there was a format
+ * error in the directory index, and the caller should fall back to
+ * searching the directory normally.  The callers of dx_probe **MUST**
+ * check for this error code, and make sure it never gets reflected
+ * back to userspace.
+ */
+static struct dx_frame *
+dx_probe(const struct qstr *d_name, struct inode *dir,
+	 struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
+{
+	unsigned count, indirect;
+	struct dx_entry *at, *entries, *p, *q, *m;
+	struct dx_root *root;
+	struct buffer_head *bh;
+	struct dx_frame *frame = frame_in;
+	u32 hash;
+
+	frame->bh = NULL;
+	if (!(bh = ext4_bread (NULL,dir, 0, 0, err)))
+		goto fail;
+	root = (struct dx_root *) bh->b_data;
+	if (root->info.hash_version != DX_HASH_TEA &&
+	    root->info.hash_version != DX_HASH_HALF_MD4 &&
+	    root->info.hash_version != DX_HASH_LEGACY) {
+		ext4_warning(dir->i_sb, "Unrecognised inode hash code %d",
+			     root->info.hash_version);
+		brelse(bh);
+		*err = ERR_BAD_DX_DIR;
+		goto fail;
+	}
+	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
+	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+	if (d_name)
+		ext4fs_dirhash(d_name->name, d_name->len, hinfo);
+	hash = hinfo->hash;
+
+	if (root->info.unused_flags & 1) {
+		ext4_warning(dir->i_sb, "Unimplemented inode hash flags: %#06x",
+			     root->info.unused_flags);
+		brelse(bh);
+		*err = ERR_BAD_DX_DIR;
+		goto fail;
+	}
+
+	if ((indirect = root->info.indirect_levels) > 1) {
+		ext4_warning(dir->i_sb, "Unimplemented inode hash depth: %#06x",
+			     root->info.indirect_levels);
+		brelse(bh);
+		*err = ERR_BAD_DX_DIR;
+		goto fail;
+	}
+
+	entries = (struct dx_entry *) (((char *)&root->info) +
+				       root->info.info_length);
+
+	if (dx_get_limit(entries) != dx_root_limit(dir,
+						   root->info.info_length)) {
+		ext4_warning(dir->i_sb, "dx entry: limit != root limit");
+		brelse(bh);
+		*err = ERR_BAD_DX_DIR;
+		goto fail;
+	}
+
+	dxtrace(printk("Look up %x", hash));
+	while (1)
+	{
+		count = dx_get_count(entries);
+		if (!count || count > dx_get_limit(entries)) {
+			ext4_warning(dir->i_sb,
+				     "dx entry: no count or count > limit");
+			brelse(bh);
+			*err = ERR_BAD_DX_DIR;
+			goto fail2;
+		}
+
+		p = entries + 1;
+		q = entries + count - 1;
+		while (p <= q)
+		{
+			m = p + (q - p)/2;
+			dxtrace(printk("."));
+			if (dx_get_hash(m) > hash)
+				q = m - 1;
+			else
+				p = m + 1;
+		}
+
+		if (0) // linear search cross check
+		{
+			unsigned n = count - 1;
+			at = entries;
+			while (n--)
+			{
+				dxtrace(printk(","));
+				if (dx_get_hash(++at) > hash)
+				{
+					at--;
+					break;
+				}
+			}
+			assert (at == p - 1);
+		}
+
+		at = p - 1;
+		dxtrace(printk(" %x->%u\n", at == entries? 0: dx_get_hash(at), dx_get_block(at)));
+		frame->bh = bh;
+		frame->entries = entries;
+		frame->at = at;
+		if (!indirect--) return frame;
+		if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err)))
+			goto fail2;
+		at = entries = ((struct dx_node *) bh->b_data)->entries;
+		if (dx_get_limit(entries) != dx_node_limit (dir)) {
+			ext4_warning(dir->i_sb,
+				     "dx entry: limit != node limit");
+			brelse(bh);
+			*err = ERR_BAD_DX_DIR;
+			goto fail2;
+		}
+		frame++;
+		frame->bh = NULL;
+	}
+fail2:
+	while (frame >= frame_in) {
+		brelse(frame->bh);
+		frame--;
+	}
+fail:
+	if (*err == ERR_BAD_DX_DIR)
+		ext4_warning(dir->i_sb,
+			     "Corrupt dir inode %ld, running e2fsck is "
+			     "recommended.", dir->i_ino);
+	return NULL;
+}
+
+static void dx_release (struct dx_frame *frames)
+{
+	if (frames[0].bh == NULL)
+		return;
+
+	if (((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels)
+		brelse(frames[1].bh);
+	brelse(frames[0].bh);
+}
+
+/*
+ * This function increments the frame pointer to search the next leaf
+ * block, and reads in the necessary intervening nodes if the search
+ * should be necessary.  Whether or not the search is necessary is
+ * controlled by the hash parameter.  If the hash value is even, then
+ * the search is only continued if the next block starts with that
+ * hash value.  This is used if we are searching for a specific file.
+ *
+ * If the hash value is HASH_NB_ALWAYS, then always go to the next block.
+ *
+ * This function returns 1 if the caller should continue to search,
+ * or 0 if it should not.  If there is an error reading one of the
+ * index blocks, it will a negative error code.
+ *
+ * If start_hash is non-null, it will be filled in with the starting
+ * hash of the next page.
+ */
+static int ext4_htree_next_block(struct inode *dir, __u32 hash,
+				 struct dx_frame *frame,
+				 struct dx_frame *frames,
+				 __u32 *start_hash)
+{
+	struct dx_frame *p;
+	struct buffer_head *bh;
+	int err, num_frames = 0;
+	__u32 bhash;
+
+	p = frame;
+	/*
+	 * Find the next leaf page by incrementing the frame pointer.
+	 * If we run out of entries in the interior node, loop around and
+	 * increment pointer in the parent node.  When we break out of
+	 * this loop, num_frames indicates the number of interior
+	 * nodes need to be read.
+	 */
+	while (1) {
+		if (++(p->at) < p->entries + dx_get_count(p->entries))
+			break;
+		if (p == frames)
+			return 0;
+		num_frames++;
+		p--;
+	}
+
+	/*
+	 * If the hash is 1, then continue only if the next page has a
+	 * continuation hash of any value.  This is used for readdir
+	 * handling.  Otherwise, check to see if the hash matches the
+	 * desired contiuation hash.  If it doesn't, return since
+	 * there's no point to read in the successive index pages.
+	 */
+	bhash = dx_get_hash(p->at);
+	if (start_hash)
+		*start_hash = bhash;
+	if ((hash & 1) == 0) {
+		if ((bhash & ~1) != hash)
+			return 0;
+	}
+	/*
+	 * If the hash is HASH_NB_ALWAYS, we always go to the next
+	 * block so no check is necessary
+	 */
+	while (num_frames--) {
+		if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at),
+				      0, &err)))
+			return err; /* Failure */
+		p++;
+		brelse(p->bh);
+		p->bh = bh;
+		p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
+	}
+	return 1;
+}
+
+
+/*
+ * This function fills a red-black tree with information from a
+ * directory block.  It returns the number directory entries loaded
+ * into the tree.  If there is an error it is returned in err.
+ */
+static int htree_dirblock_to_tree(struct file *dir_file,
+				  struct inode *dir, ext4_lblk_t block,
+				  struct dx_hash_info *hinfo,
+				  __u32 start_hash, __u32 start_minor_hash)
+{
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de, *top;
+	int err, count = 0;
+
+	dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
+							(unsigned long)block));
+	if (!(bh = ext4_bread (NULL, dir, block, 0, &err)))
+		return err;
+
+	de = (struct ext4_dir_entry_2 *) bh->b_data;
+	top = (struct ext4_dir_entry_2 *) ((char *) de +
+					   dir->i_sb->s_blocksize -
+					   EXT4_DIR_REC_LEN(0));
+	for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
+		if (ext4_check_dir_entry(dir, NULL, de, bh,
+				(block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
+					 + ((char *)de - bh->b_data))) {
+			/* On error, skip the f_pos to the next block. */
+			dir_file->f_pos = (dir_file->f_pos |
+					(dir->i_sb->s_blocksize - 1)) + 1;
+			brelse(bh);
+			return count;
+		}
+		ext4fs_dirhash(de->name, de->name_len, hinfo);
+		if ((hinfo->hash < start_hash) ||
+		    ((hinfo->hash == start_hash) &&
+		     (hinfo->minor_hash < start_minor_hash)))
+			continue;
+		if (de->inode == 0)
+			continue;
+		if ((err = ext4_htree_store_dirent(dir_file,
+				   hinfo->hash, hinfo->minor_hash, de)) != 0) {
+			brelse(bh);
+			return err;
+		}
+		count++;
+	}
+	brelse(bh);
+	return count;
+}
+
+
+/*
+ * This function fills a red-black tree with information from a
+ * directory.  We start scanning the directory in hash order, starting
+ * at start_hash and start_minor_hash.
+ *
+ * This function returns the number of entries inserted into the tree,
+ * or a negative error code.
+ */
+int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
+			 __u32 start_minor_hash, __u32 *next_hash)
+{
+	struct dx_hash_info hinfo;
+	struct ext4_dir_entry_2 *de;
+	struct dx_frame frames[2], *frame;
+	struct inode *dir;
+	ext4_lblk_t block;
+	int count = 0;
+	int ret, err;
+	__u32 hashval;
+
+	dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
+		       start_hash, start_minor_hash));
+	dir = dir_file->f_path.dentry->d_inode;
+	if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
+		hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT4_SB(dir->i_sb)->s_hash_unsigned;
+		hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
+					       start_hash, start_minor_hash);
+		*next_hash = ~0;
+		return count;
+	}
+	hinfo.hash = start_hash;
+	hinfo.minor_hash = 0;
+	frame = dx_probe(NULL, dir, &hinfo, frames, &err);
+	if (!frame)
+		return err;
+
+	/* Add '.' and '..' from the htree header */
+	if (!start_hash && !start_minor_hash) {
+		de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
+		if ((err = ext4_htree_store_dirent(dir_file, 0, 0, de)) != 0)
+			goto errout;
+		count++;
+	}
+	if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) {
+		de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
+		de = ext4_next_entry(de, dir->i_sb->s_blocksize);
+		if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0)
+			goto errout;
+		count++;
+	}
+
+	while (1) {
+		block = dx_get_block(frame->at);
+		ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo,
+					     start_hash, start_minor_hash);
+		if (ret < 0) {
+			err = ret;
+			goto errout;
+		}
+		count += ret;
+		hashval = ~0;
+		ret = ext4_htree_next_block(dir, HASH_NB_ALWAYS,
+					    frame, frames, &hashval);
+		*next_hash = hashval;
+		if (ret < 0) {
+			err = ret;
+			goto errout;
+		}
+		/*
+		 * Stop if:  (a) there are no more entries, or
+		 * (b) we have inserted at least one entry and the
+		 * next hash value is not a continuation
+		 */
+		if ((ret == 0) ||
+		    (count && ((hashval & 1) == 0)))
+			break;
+	}
+	dx_release(frames);
+	dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, "
+		       "next hash: %x\n", count, *next_hash));
+	return count;
+errout:
+	dx_release(frames);
+	return (err);
+}
+
+
+/*
+ * Directory block splitting, compacting
+ */
+
+/*
+ * Create map of hash values, offsets, and sizes, stored at end of block.
+ * Returns number of entries mapped.
+ */
+static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
+		       struct dx_hash_info *hinfo,
+		       struct dx_map_entry *map_tail)
+{
+	int count = 0;
+	char *base = (char *) de;
+	struct dx_hash_info h = *hinfo;
+
+	while ((char *) de < base + blocksize) {
+		if (de->name_len && de->inode) {
+			ext4fs_dirhash(de->name, de->name_len, &h);
+			map_tail--;
+			map_tail->hash = h.hash;
+			map_tail->offs = ((char *) de - base)>>2;
+			map_tail->size = le16_to_cpu(de->rec_len);
+			count++;
+			cond_resched();
+		}
+		/* XXX: do we need to check rec_len == 0 case? -Chris */
+		de = ext4_next_entry(de, blocksize);
+	}
+	return count;
+}
+
+/* Sort map by hash value */
+static void dx_sort_map (struct dx_map_entry *map, unsigned count)
+{
+	struct dx_map_entry *p, *q, *top = map + count - 1;
+	int more;
+	/* Combsort until bubble sort doesn't suck */
+	while (count > 2) {
+		count = count*10/13;
+		if (count - 9 < 2) /* 9, 10 -> 11 */
+			count = 11;
+		for (p = top, q = p - count; q >= map; p--, q--)
+			if (p->hash < q->hash)
+				swap(*p, *q);
+	}
+	/* Garden variety bubble sort */
+	do {
+		more = 0;
+		q = top;
+		while (q-- > map) {
+			if (q[1].hash >= q[0].hash)
+				continue;
+			swap(*(q+1), *q);
+			more = 1;
+		}
+	} while(more);
+}
+
+static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
+{
+	struct dx_entry *entries = frame->entries;
+	struct dx_entry *old = frame->at, *new = old + 1;
+	int count = dx_get_count(entries);
+
+	assert(count < dx_get_limit(entries));
+	assert(old < entries + count);
+	memmove(new + 1, new, (char *)(entries + count) - (char *)(new));
+	dx_set_hash(new, hash);
+	dx_set_block(new, block);
+	dx_set_count(entries, count + 1);
+}
+
+static void ext4_update_dx_flag(struct inode *inode)
+{
+	if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+				     EXT4_FEATURE_COMPAT_DIR_INDEX))
+		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+}
+
+/*
+ * NOTE! unlike strncmp, ext4_match returns 1 for success, 0 for failure.
+ *
+ * `len <= EXT4_NAME_LEN' is guaranteed by caller.
+ * `de != NULL' is guaranteed by caller.
+ */
+static inline int ext4_match (int len, const char * const name,
+			      struct ext4_dir_entry_2 * de)
+{
+	if (len != de->name_len)
+		return 0;
+	if (!de->inode)
+		return 0;
+	return !memcmp(name, de->name, len);
+}
+
+/*
+ * Returns 0 if not found, -1 on failure, and 1 on success
+ */
+static inline int search_dirblock(struct buffer_head *bh,
+				  struct inode *dir,
+				  const struct qstr *d_name,
+				  unsigned int offset,
+				  struct ext4_dir_entry_2 ** res_dir)
+{
+	struct ext4_dir_entry_2 * de;
+	char * dlimit;
+	int de_len;
+	const char *name = d_name->name;
+	int namelen = d_name->len;
+
+	de = (struct ext4_dir_entry_2 *) bh->b_data;
+	dlimit = bh->b_data + dir->i_sb->s_blocksize;
+	while ((char *) de < dlimit) {
+		/* this code is executed quadratically often */
+		/* do minimal checking `by hand' */
+
+		if ((char *) de + namelen <= dlimit &&
+		    ext4_match (namelen, name, de)) {
+			/* found a match - just to be sure, do a full check */
+			if (ext4_check_dir_entry(dir, NULL, de, bh, offset))
+				return -1;
+			*res_dir = de;
+			return 1;
+		}
+		/* prevent looping on a bad block */
+		de_len = ext4_rec_len_from_disk(de->rec_len,
+						dir->i_sb->s_blocksize);
+		if (de_len <= 0)
+			return -1;
+		offset += de_len;
+		de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
+	}
+	return 0;
+}
+
+
+/*
+ *	ext4_find_entry()
+ *
+ * finds an entry in the specified directory with the wanted name. It
+ * returns the cache buffer in which the entry was found, and the entry
+ * itself (as a parameter - res_dir). It does NOT read the inode of the
+ * entry - you'll have to do that yourself if you want to.
+ *
+ * The returned buffer_head has ->b_count elevated.  The caller is expected
+ * to brelse() it when appropriate.
+ */
+static struct buffer_head * ext4_find_entry (struct inode *dir,
+					const struct qstr *d_name,
+					struct ext4_dir_entry_2 ** res_dir)
+{
+	struct super_block *sb;
+	struct buffer_head *bh_use[NAMEI_RA_SIZE];
+	struct buffer_head *bh, *ret = NULL;
+	ext4_lblk_t start, block, b;
+	const u8 *name = d_name->name;
+	int ra_max = 0;		/* Number of bh's in the readahead
+				   buffer, bh_use[] */
+	int ra_ptr = 0;		/* Current index into readahead
+				   buffer */
+	int num = 0;
+	ext4_lblk_t  nblocks;
+	int i, err;
+	int namelen;
+
+	*res_dir = NULL;
+	sb = dir->i_sb;
+	namelen = d_name->len;
+	if (namelen > EXT4_NAME_LEN)
+		return NULL;
+	if ((namelen <= 2) && (name[0] == '.') &&
+	    (name[1] == '.' || name[1] == '\0')) {
+		/*
+		 * "." or ".." will only be in the first block
+		 * NFS may look up ".."; "." should be handled by the VFS
+		 */
+		block = start = 0;
+		nblocks = 1;
+		goto restart;
+	}
+	if (is_dx(dir)) {
+		bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
+		/*
+		 * On success, or if the error was file not found,
+		 * return.  Otherwise, fall back to doing a search the
+		 * old fashioned way.
+		 */
+		if (bh || (err != ERR_BAD_DX_DIR))
+			return bh;
+		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
+			       "falling back\n"));
+	}
+	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
+	start = EXT4_I(dir)->i_dir_start_lookup;
+	if (start >= nblocks)
+		start = 0;
+	block = start;
+restart:
+	do {
+		/*
+		 * We deal with the read-ahead logic here.
+		 */
+		if (ra_ptr >= ra_max) {
+			/* Refill the readahead buffer */
+			ra_ptr = 0;
+			b = block;
+			for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
+				/*
+				 * Terminate if we reach the end of the
+				 * directory and must wrap, or if our
+				 * search has finished at this block.
+				 */
+				if (b >= nblocks || (num && block == start)) {
+					bh_use[ra_max] = NULL;
+					break;
+				}
+				num++;
+				bh = ext4_getblk(NULL, dir, b++, 0, &err);
+				bh_use[ra_max] = bh;
+				if (bh)
+					ll_rw_block(READ_META, 1, &bh);
+			}
+		}
+		if ((bh = bh_use[ra_ptr++]) == NULL)
+			goto next;
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh)) {
+			/* read error, skip block & hope for the best */
+			EXT4_ERROR_INODE(dir, "reading directory lblock %lu",
+					 (unsigned long) block);
+			brelse(bh);
+			goto next;
+		}
+		i = search_dirblock(bh, dir, d_name,
+			    block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
+		if (i == 1) {
+			EXT4_I(dir)->i_dir_start_lookup = block;
+			ret = bh;
+			goto cleanup_and_exit;
+		} else {
+			brelse(bh);
+			if (i < 0)
+				goto cleanup_and_exit;
+		}
+	next:
+		if (++block >= nblocks)
+			block = 0;
+	} while (block != start);
+
+	/*
+	 * If the directory has grown while we were searching, then
+	 * search the last part of the directory before giving up.
+	 */
+	block = nblocks;
+	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
+	if (block < nblocks) {
+		start = 0;
+		goto restart;
+	}
+
+cleanup_and_exit:
+	/* Clean up the read-ahead blocks */
+	for (; ra_ptr < ra_max; ra_ptr++)
+		brelse(bh_use[ra_ptr]);
+	return ret;
+}
+
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
+		       struct ext4_dir_entry_2 **res_dir, int *err)
+{
+	struct super_block * sb = dir->i_sb;
+	struct dx_hash_info	hinfo;
+	struct dx_frame frames[2], *frame;
+	struct buffer_head *bh;
+	ext4_lblk_t block;
+	int retval;
+
+	if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
+		return NULL;
+	do {
+		block = dx_get_block(frame->at);
+		if (!(bh = ext4_bread(NULL, dir, block, 0, err)))
+			goto errout;
+
+		retval = search_dirblock(bh, dir, d_name,
+					 block << EXT4_BLOCK_SIZE_BITS(sb),
+					 res_dir);
+		if (retval == 1) { 	/* Success! */
+			dx_release(frames);
+			return bh;
+		}
+		brelse(bh);
+		if (retval == -1) {
+			*err = ERR_BAD_DX_DIR;
+			goto errout;
+		}
+
+		/* Check to see if we should continue to search */
+		retval = ext4_htree_next_block(dir, hinfo.hash, frame,
+					       frames, NULL);
+		if (retval < 0) {
+			ext4_warning(sb,
+			     "error reading index page in directory #%lu",
+			     dir->i_ino);
+			*err = retval;
+			goto errout;
+		}
+	} while (retval == 1);
+
+	*err = -ENOENT;
+errout:
+	dxtrace(printk(KERN_DEBUG "%s not found\n", name));
+	dx_release (frames);
+	return NULL;
+}
+
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+{
+	struct inode *inode;
+	struct ext4_dir_entry_2 *de;
+	struct buffer_head *bh;
+
+	if (dentry->d_name.len > EXT4_NAME_LEN)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	bh = ext4_find_entry(dir, &dentry->d_name, &de);
+	inode = NULL;
+	if (bh) {
+		__u32 ino = le32_to_cpu(de->inode);
+		brelse(bh);
+		if (!ext4_valid_inum(dir->i_sb, ino)) {
+			EXT4_ERROR_INODE(dir, "bad inode number: %u", ino);
+			return ERR_PTR(-EIO);
+		}
+		inode = ext4_iget(dir->i_sb, ino);
+		if (IS_ERR(inode)) {
+			if (PTR_ERR(inode) == -ESTALE) {
+				EXT4_ERROR_INODE(dir,
+						 "deleted inode referenced: %u",
+						 ino);
+				return ERR_PTR(-EIO);
+			} else {
+				return ERR_CAST(inode);
+			}
+		}
+	}
+	return d_splice_alias(inode, dentry);
+}
+
+
+struct dentry *ext4_get_parent(struct dentry *child)
+{
+	__u32 ino;
+	static const struct qstr dotdot = {
+		.name = "..",
+		.len = 2,
+	};
+	struct ext4_dir_entry_2 * de;
+	struct buffer_head *bh;
+
+	bh = ext4_find_entry(child->d_inode, &dotdot, &de);
+	if (!bh)
+		return ERR_PTR(-ENOENT);
+	ino = le32_to_cpu(de->inode);
+	brelse(bh);
+
+	if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
+		EXT4_ERROR_INODE(child->d_inode,
+				 "bad parent inode number: %u", ino);
+		return ERR_PTR(-EIO);
+	}
+
+	return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino));
+}
+
+#define S_SHIFT 12
+static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
+	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,
+	[S_IFDIR >> S_SHIFT]	= EXT4_FT_DIR,
+	[S_IFCHR >> S_SHIFT]	= EXT4_FT_CHRDEV,
+	[S_IFBLK >> S_SHIFT]	= EXT4_FT_BLKDEV,
+	[S_IFIFO >> S_SHIFT]	= EXT4_FT_FIFO,
+	[S_IFSOCK >> S_SHIFT]	= EXT4_FT_SOCK,
+	[S_IFLNK >> S_SHIFT]	= EXT4_FT_SYMLINK,
+};
+
+static inline void ext4_set_de_type(struct super_block *sb,
+				struct ext4_dir_entry_2 *de,
+				umode_t mode) {
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE))
+		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
+}
+
+/*
+ * Move count entries from end of map between two memory locations.
+ * Returns pointer to last entry moved.
+ */
+static struct ext4_dir_entry_2 *
+dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
+		unsigned blocksize)
+{
+	unsigned rec_len = 0;
+
+	while (count--) {
+		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)
+						(from + (map->offs<<2));
+		rec_len = EXT4_DIR_REC_LEN(de->name_len);
+		memcpy (to, de, rec_len);
+		((struct ext4_dir_entry_2 *) to)->rec_len =
+				ext4_rec_len_to_disk(rec_len, blocksize);
+		de->inode = 0;
+		map++;
+		to += rec_len;
+	}
+	return (struct ext4_dir_entry_2 *) (to - rec_len);
+}
+
+/*
+ * Compact each dir entry in the range to the minimal rec_len.
+ * Returns pointer to last entry in range.
+ */
+static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize)
+{
+	struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base;
+	unsigned rec_len = 0;
+
+	prev = to = de;
+	while ((char*)de < base + blocksize) {
+		next = ext4_next_entry(de, blocksize);
+		if (de->inode && de->name_len) {
+			rec_len = EXT4_DIR_REC_LEN(de->name_len);
+			if (de > to)
+				memmove(to, de, rec_len);
+			to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize);
+			prev = to;
+			to = (struct ext4_dir_entry_2 *) (((char *) to) + rec_len);
+		}
+		de = next;
+	}
+	return prev;
+}
+
+/*
+ * Split a full leaf block to make room for a new dir entry.
+ * Allocate a new block, and move entries so that they are approx. equally full.
+ * Returns pointer to de in block into which the new entry will be inserted.
+ */
+static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
+			struct buffer_head **bh,struct dx_frame *frame,
+			struct dx_hash_info *hinfo, int *error)
+{
+	unsigned blocksize = dir->i_sb->s_blocksize;
+	unsigned count, continued;
+	struct buffer_head *bh2;
+	ext4_lblk_t newblock;
+	u32 hash2;
+	struct dx_map_entry *map;
+	char *data1 = (*bh)->b_data, *data2;
+	unsigned split, move, size;
+	struct ext4_dir_entry_2 *de = NULL, *de2;
+	int	err = 0, i;
+
+	bh2 = ext4_append (handle, dir, &newblock, &err);
+	if (!(bh2)) {
+		brelse(*bh);
+		*bh = NULL;
+		goto errout;
+	}
+
+	BUFFER_TRACE(*bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, *bh);
+	if (err)
+		goto journal_error;
+
+	BUFFER_TRACE(frame->bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, frame->bh);
+	if (err)
+		goto journal_error;
+
+	data2 = bh2->b_data;
+
+	/* create map in the end of data2 block */
+	map = (struct dx_map_entry *) (data2 + blocksize);
+	count = dx_make_map((struct ext4_dir_entry_2 *) data1,
+			     blocksize, hinfo, map);
+	map -= count;
+	dx_sort_map(map, count);
+	/* Split the existing block in the middle, size-wise */
+	size = 0;
+	move = 0;
+	for (i = count-1; i >= 0; i--) {
+		/* is more than half of this entry in 2nd half of the block? */
+		if (size + map[i].size/2 > blocksize/2)
+			break;
+		size += map[i].size;
+		move++;
+	}
+	/* map index at which we will split */
+	split = count - move;
+	hash2 = map[split].hash;
+	continued = hash2 == map[split - 1].hash;
+	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
+			(unsigned long)dx_get_block(frame->at),
+					hash2, split, count-split));
+
+	/* Fancy dance to stay within two buffers */
+	de2 = dx_move_dirents(data1, data2, map + split, count - split, blocksize);
+	de = dx_pack_dirents(data1, blocksize);
+	de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de,
+					   blocksize);
+	de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2,
+					    blocksize);
+	dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
+	dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
+
+	/* Which block gets the new entry? */
+	if (hinfo->hash >= hash2)
+	{
+		swap(*bh, bh2);
+		de = de2;
+	}
+	dx_insert_block(frame, hash2 + continued, newblock);
+	err = ext4_handle_dirty_metadata(handle, dir, bh2);
+	if (err)
+		goto journal_error;
+	err = ext4_handle_dirty_metadata(handle, dir, frame->bh);
+	if (err)
+		goto journal_error;
+	brelse(bh2);
+	dxtrace(dx_show_index("frame", frame->entries));
+	return de;
+
+journal_error:
+	brelse(*bh);
+	brelse(bh2);
+	*bh = NULL;
+	ext4_std_error(dir->i_sb, err);
+errout:
+	*error = err;
+	return NULL;
+}
+
+/*
+ * Add a new entry into a directory (leaf) block.  If de is non-NULL,
+ * it points to a directory entry which is guaranteed to be large
+ * enough for new directory entry.  If de is NULL, then
+ * add_dirent_to_buf will attempt search the directory block for
+ * space.  It will return -ENOSPC if no space is available, and -EIO
+ * and -EEXIST if directory entry already exists.
+ */
+static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
+			     struct inode *inode, struct ext4_dir_entry_2 *de,
+			     struct buffer_head *bh)
+{
+	struct inode	*dir = dentry->d_parent->d_inode;
+	const char	*name = dentry->d_name.name;
+	int		namelen = dentry->d_name.len;
+	unsigned int	offset = 0;
+	unsigned int	blocksize = dir->i_sb->s_blocksize;
+	unsigned short	reclen;
+	int		nlen, rlen, err;
+	char		*top;
+
+	reclen = EXT4_DIR_REC_LEN(namelen);
+	if (!de) {
+		de = (struct ext4_dir_entry_2 *)bh->b_data;
+		top = bh->b_data + blocksize - reclen;
+		while ((char *) de <= top) {
+			if (ext4_check_dir_entry(dir, NULL, de, bh, offset))
+				return -EIO;
+			if (ext4_match(namelen, name, de))
+				return -EEXIST;
+			nlen = EXT4_DIR_REC_LEN(de->name_len);
+			rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
+			if ((de->inode? rlen - nlen: rlen) >= reclen)
+				break;
+			de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
+			offset += rlen;
+		}
+		if ((char *) de > top)
+			return -ENOSPC;
+	}
+	BUFFER_TRACE(bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, bh);
+	if (err) {
+		ext4_std_error(dir->i_sb, err);
+		return err;
+	}
+
+	/* By now the buffer is marked for journaling */
+	nlen = EXT4_DIR_REC_LEN(de->name_len);
+	rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
+	if (de->inode) {
+		struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen);
+		de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, blocksize);
+		de->rec_len = ext4_rec_len_to_disk(nlen, blocksize);
+		de = de1;
+	}
+	de->file_type = EXT4_FT_UNKNOWN;
+	if (inode) {
+		de->inode = cpu_to_le32(inode->i_ino);
+		ext4_set_de_type(dir->i_sb, de, inode->i_mode);
+	} else
+		de->inode = 0;
+	de->name_len = namelen;
+	memcpy(de->name, name, namelen);
+	/*
+	 * XXX shouldn't update any times until successful
+	 * completion of syscall, but too many callers depend
+	 * on this.
+	 *
+	 * XXX similarly, too many callers depend on
+	 * ext4_new_inode() setting the times, but error
+	 * recovery deletes the inode, so the worst that can
+	 * happen is that the times are slightly out of date
+	 * and/or different from the directory change time.
+	 */
+	dir->i_mtime = dir->i_ctime = ext4_current_time(dir);
+	ext4_update_dx_flag(dir);
+	dir->i_version++;
+	ext4_mark_inode_dirty(handle, dir);
+	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(handle, dir, bh);
+	if (err)
+		ext4_std_error(dir->i_sb, err);
+	return 0;
+}
+
+/*
+ * This converts a one block unindexed directory to a 3 block indexed
+ * directory, and adds the dentry to the indexed directory.
+ */
+static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
+			    struct inode *inode, struct buffer_head *bh)
+{
+	struct inode	*dir = dentry->d_parent->d_inode;
+	const char	*name = dentry->d_name.name;
+	int		namelen = dentry->d_name.len;
+	struct buffer_head *bh2;
+	struct dx_root	*root;
+	struct dx_frame	frames[2], *frame;
+	struct dx_entry *entries;
+	struct ext4_dir_entry_2	*de, *de2;
+	char		*data1, *top;
+	unsigned	len;
+	int		retval;
+	unsigned	blocksize;
+	struct dx_hash_info hinfo;
+	ext4_lblk_t  block;
+	struct fake_dirent *fde;
+
+	blocksize =  dir->i_sb->s_blocksize;
+	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
+	retval = ext4_journal_get_write_access(handle, bh);
+	if (retval) {
+		ext4_std_error(dir->i_sb, retval);
+		brelse(bh);
+		return retval;
+	}
+	root = (struct dx_root *) bh->b_data;
+
+	/* The 0th block becomes the root, move the dirents out */
+	fde = &root->dotdot;
+	de = (struct ext4_dir_entry_2 *)((char *)fde +
+		ext4_rec_len_from_disk(fde->rec_len, blocksize));
+	if ((char *) de >= (((char *) root) + blocksize)) {
+		EXT4_ERROR_INODE(dir, "invalid rec_len for '..'");
+		brelse(bh);
+		return -EIO;
+	}
+	len = ((char *) root) + blocksize - (char *) de;
+
+	/* Allocate new block for the 0th block's dirents */
+	bh2 = ext4_append(handle, dir, &block, &retval);
+	if (!(bh2)) {
+		brelse(bh);
+		return retval;
+	}
+	ext4_set_inode_flag(dir, EXT4_INODE_INDEX);
+	data1 = bh2->b_data;
+
+	memcpy (data1, de, len);
+	de = (struct ext4_dir_entry_2 *) data1;
+	top = data1 + len;
+	while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top)
+		de = de2;
+	de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de,
+					   blocksize);
+	/* Initialize the root; the dot dirents already exist */
+	de = (struct ext4_dir_entry_2 *) (&root->dotdot);
+	de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2),
+					   blocksize);
+	memset (&root->info, 0, sizeof(root->info));
+	root->info.info_length = sizeof(root->info);
+	root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+	entries = root->entries;
+	dx_set_block(entries, 1);
+	dx_set_count(entries, 1);
+	dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info)));
+
+	/* Initialize as for dx_probe */
+	hinfo.hash_version = root->info.hash_version;
+	if (hinfo.hash_version <= DX_HASH_TEA)
+		hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
+	hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+	ext4fs_dirhash(name, namelen, &hinfo);
+	frame = frames;
+	frame->entries = entries;
+	frame->at = entries;
+	frame->bh = bh;
+	bh = bh2;
+
+	ext4_handle_dirty_metadata(handle, dir, frame->bh);
+	ext4_handle_dirty_metadata(handle, dir, bh);
+
+	de = do_split(handle,dir, &bh, frame, &hinfo, &retval);
+	if (!de) {
+		/*
+		 * Even if the block split failed, we have to properly write
+		 * out all the changes we did so far. Otherwise we can end up
+		 * with corrupted filesystem.
+		 */
+		ext4_mark_inode_dirty(handle, dir);
+		dx_release(frames);
+		return retval;
+	}
+	dx_release(frames);
+
+	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	brelse(bh);
+	return retval;
+}
+
+/*
+ *	ext4_add_entry()
+ *
+ * adds a file entry to the specified directory, using the same
+ * semantics as ext4_find_entry(). It returns NULL if it failed.
+ *
+ * NOTE!! The inode part of 'de' is left at 0 - which means you
+ * may not sleep between calling this and putting something into
+ * the entry, as someone else might have used it while you slept.
+ */
+static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
+			  struct inode *inode)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
+	struct super_block *sb;
+	int	retval;
+	int	dx_fallback=0;
+	unsigned blocksize;
+	ext4_lblk_t block, blocks;
+
+	sb = dir->i_sb;
+	blocksize = sb->s_blocksize;
+	if (!dentry->d_name.len)
+		return -EINVAL;
+	if (is_dx(dir)) {
+		retval = ext4_dx_add_entry(handle, dentry, inode);
+		if (!retval || (retval != ERR_BAD_DX_DIR))
+			return retval;
+		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
+		dx_fallback++;
+		ext4_mark_inode_dirty(handle, dir);
+	}
+	blocks = dir->i_size >> sb->s_blocksize_bits;
+	for (block = 0; block < blocks; block++) {
+		bh = ext4_bread(handle, dir, block, 0, &retval);
+		if(!bh)
+			return retval;
+		retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
+		if (retval != -ENOSPC) {
+			brelse(bh);
+			return retval;
+		}
+
+		if (blocks == 1 && !dx_fallback &&
+		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
+			return make_indexed_dir(handle, dentry, inode, bh);
+		brelse(bh);
+	}
+	bh = ext4_append(handle, dir, &block, &retval);
+	if (!bh)
+		return retval;
+	de = (struct ext4_dir_entry_2 *) bh->b_data;
+	de->inode = 0;
+	de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
+	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	brelse(bh);
+	if (retval == 0)
+		ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
+	return retval;
+}
+
+/*
+ * Returns 0 for success, or a negative error value
+ */
+static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
+			     struct inode *inode)
+{
+	struct dx_frame frames[2], *frame;
+	struct dx_entry *entries, *at;
+	struct dx_hash_info hinfo;
+	struct buffer_head *bh;
+	struct inode *dir = dentry->d_parent->d_inode;
+	struct super_block *sb = dir->i_sb;
+	struct ext4_dir_entry_2 *de;
+	int err;
+
+	frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
+	if (!frame)
+		return err;
+	entries = frame->entries;
+	at = frame->at;
+
+	if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err)))
+		goto cleanup;
+
+	BUFFER_TRACE(bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, bh);
+	if (err)
+		goto journal_error;
+
+	err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
+	if (err != -ENOSPC)
+		goto cleanup;
+
+	/* Block full, should compress but for now just split */
+	dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
+		       dx_get_count(entries), dx_get_limit(entries)));
+	/* Need to split index? */
+	if (dx_get_count(entries) == dx_get_limit(entries)) {
+		ext4_lblk_t newblock;
+		unsigned icount = dx_get_count(entries);
+		int levels = frame - frames;
+		struct dx_entry *entries2;
+		struct dx_node *node2;
+		struct buffer_head *bh2;
+
+		if (levels && (dx_get_count(frames->entries) ==
+			       dx_get_limit(frames->entries))) {
+			ext4_warning(sb, "Directory index full!");
+			err = -ENOSPC;
+			goto cleanup;
+		}
+		bh2 = ext4_append (handle, dir, &newblock, &err);
+		if (!(bh2))
+			goto cleanup;
+		node2 = (struct dx_node *)(bh2->b_data);
+		entries2 = node2->entries;
+		memset(&node2->fake, 0, sizeof(struct fake_dirent));
+		node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize,
+							   sb->s_blocksize);
+		BUFFER_TRACE(frame->bh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, frame->bh);
+		if (err)
+			goto journal_error;
+		if (levels) {
+			unsigned icount1 = icount/2, icount2 = icount - icount1;
+			unsigned hash2 = dx_get_hash(entries + icount1);
+			dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
+				       icount1, icount2));
+
+			BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
+			err = ext4_journal_get_write_access(handle,
+							     frames[0].bh);
+			if (err)
+				goto journal_error;
+
+			memcpy((char *) entries2, (char *) (entries + icount1),
+			       icount2 * sizeof(struct dx_entry));
+			dx_set_count(entries, icount1);
+			dx_set_count(entries2, icount2);
+			dx_set_limit(entries2, dx_node_limit(dir));
+
+			/* Which index block gets the new entry? */
+			if (at - entries >= icount1) {
+				frame->at = at = at - entries - icount1 + entries2;
+				frame->entries = entries = entries2;
+				swap(frame->bh, bh2);
+			}
+			dx_insert_block(frames + 0, hash2, newblock);
+			dxtrace(dx_show_index("node", frames[1].entries));
+			dxtrace(dx_show_index("node",
+			       ((struct dx_node *) bh2->b_data)->entries));
+			err = ext4_handle_dirty_metadata(handle, dir, bh2);
+			if (err)
+				goto journal_error;
+			brelse (bh2);
+		} else {
+			dxtrace(printk(KERN_DEBUG
+				       "Creating second level index...\n"));
+			memcpy((char *) entries2, (char *) entries,
+			       icount * sizeof(struct dx_entry));
+			dx_set_limit(entries2, dx_node_limit(dir));
+
+			/* Set up root */
+			dx_set_count(entries, 1);
+			dx_set_block(entries + 0, newblock);
+			((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1;
+
+			/* Add new access path frame */
+			frame = frames + 1;
+			frame->at = at = at - entries + entries2;
+			frame->entries = entries = entries2;
+			frame->bh = bh2;
+			err = ext4_journal_get_write_access(handle,
+							     frame->bh);
+			if (err)
+				goto journal_error;
+		}
+		err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
+		if (err) {
+			ext4_std_error(inode->i_sb, err);
+			goto cleanup;
+		}
+	}
+	de = do_split(handle, dir, &bh, frame, &hinfo, &err);
+	if (!de)
+		goto cleanup;
+	err = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	goto cleanup;
+
+journal_error:
+	ext4_std_error(dir->i_sb, err);
+cleanup:
+	if (bh)
+		brelse(bh);
+	dx_release(frames);
+	return err;
+}
+
+/*
+ * ext4_delete_entry deletes a directory entry by merging it with the
+ * previous entry
+ */
+static int ext4_delete_entry(handle_t *handle,
+			     struct inode *dir,
+			     struct ext4_dir_entry_2 *de_del,
+			     struct buffer_head *bh)
+{
+	struct ext4_dir_entry_2 *de, *pde;
+	unsigned int blocksize = dir->i_sb->s_blocksize;
+	int i, err;
+
+	i = 0;
+	pde = NULL;
+	de = (struct ext4_dir_entry_2 *) bh->b_data;
+	while (i < bh->b_size) {
+		if (ext4_check_dir_entry(dir, NULL, de, bh, i))
+			return -EIO;
+		if (de == de_del)  {
+			BUFFER_TRACE(bh, "get_write_access");
+			err = ext4_journal_get_write_access(handle, bh);
+			if (unlikely(err)) {
+				ext4_std_error(dir->i_sb, err);
+				return err;
+			}
+			if (pde)
+				pde->rec_len = ext4_rec_len_to_disk(
+					ext4_rec_len_from_disk(pde->rec_len,
+							       blocksize) +
+					ext4_rec_len_from_disk(de->rec_len,
+							       blocksize),
+					blocksize);
+			else
+				de->inode = 0;
+			dir->i_version++;
+			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+			err = ext4_handle_dirty_metadata(handle, dir, bh);
+			if (unlikely(err)) {
+				ext4_std_error(dir->i_sb, err);
+				return err;
+			}
+			return 0;
+		}
+		i += ext4_rec_len_from_disk(de->rec_len, blocksize);
+		pde = de;
+		de = ext4_next_entry(de, blocksize);
+	}
+	return -ENOENT;
+}
+
+/*
+ * DIR_NLINK feature is set if 1) nlinks > EXT4_LINK_MAX or 2) nlinks == 2,
+ * since this indicates that nlinks count was previously 1.
+ */
+static void ext4_inc_count(handle_t *handle, struct inode *inode)
+{
+	inc_nlink(inode);
+	if (is_dx(inode) && inode->i_nlink > 1) {
+		/* limit is 16-bit i_links_count */
+		if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) {
+			inode->i_nlink = 1;
+			EXT4_SET_RO_COMPAT_FEATURE(inode->i_sb,
+					      EXT4_FEATURE_RO_COMPAT_DIR_NLINK);
+		}
+	}
+}
+
+/*
+ * If a directory had nlink == 1, then we should let it be 1. This indicates
+ * directory has >EXT4_LINK_MAX subdirs.
+ */
+static void ext4_dec_count(handle_t *handle, struct inode *inode)
+{
+	drop_nlink(inode);
+	if (S_ISDIR(inode->i_mode) && inode->i_nlink == 0)
+		inc_nlink(inode);
+}
+
+
+static int ext4_add_nondir(handle_t *handle,
+		struct dentry *dentry, struct inode *inode)
+{
+	int err = ext4_add_entry(handle, dentry, inode);
+	if (!err) {
+		ext4_mark_inode_dirty(handle, inode);
+		d_instantiate(dentry, inode);
+		unlock_new_inode(inode);
+		return 0;
+	}
+	drop_nlink(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return err;
+}
+
+/*
+ * By the time this is called, we already have created
+ * the directory cache entry for the new file, but it
+ * is so far negative - it has no inode.
+ *
+ * If the create succeeds, we fill in the inode information
+ * with d_instantiate().
+ */
+static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
+		       struct nameidata *nd)
+{
+	handle_t *handle;
+	struct inode *inode;
+	int err, retries = 0;
+
+	dquot_initialize(dir);
+
+retry:
+	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+	err = PTR_ERR(inode);
+	if (!IS_ERR(inode)) {
+		inode->i_op = &ext4_file_inode_operations;
+		inode->i_fop = &ext4_file_operations;
+		ext4_set_aops(inode);
+		err = ext4_add_nondir(handle, dentry, inode);
+	}
+	ext4_journal_stop(handle);
+	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+		goto retry;
+	return err;
+}
+
+static int ext4_mknod(struct inode *dir, struct dentry *dentry,
+		      int mode, dev_t rdev)
+{
+	handle_t *handle;
+	struct inode *inode;
+	int err, retries = 0;
+
+	if (!new_valid_dev(rdev))
+		return -EINVAL;
+
+	dquot_initialize(dir);
+
+retry:
+	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+	err = PTR_ERR(inode);
+	if (!IS_ERR(inode)) {
+		init_special_inode(inode, inode->i_mode, rdev);
+#ifdef CONFIG_EXT4_FS_XATTR
+		inode->i_op = &ext4_special_inode_operations;
+#endif
+		err = ext4_add_nondir(handle, dentry, inode);
+	}
+	ext4_journal_stop(handle);
+	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+		goto retry;
+	return err;
+}
+
+static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+	handle_t *handle;
+	struct inode *inode;
+	struct buffer_head *dir_block = NULL;
+	struct ext4_dir_entry_2 *de;
+	unsigned int blocksize = dir->i_sb->s_blocksize;
+	int err, retries = 0;
+
+	if (EXT4_DIR_LINK_MAX(dir))
+		return -EMLINK;
+
+	dquot_initialize(dir);
+
+retry:
+	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
+			       &dentry->d_name, 0);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out_stop;
+
+	inode->i_op = &ext4_dir_inode_operations;
+	inode->i_fop = &ext4_dir_operations;
+	inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
+	dir_block = ext4_bread(handle, inode, 0, 1, &err);
+	if (!dir_block)
+		goto out_clear_inode;
+	BUFFER_TRACE(dir_block, "get_write_access");
+	err = ext4_journal_get_write_access(handle, dir_block);
+	if (err)
+		goto out_clear_inode;
+	de = (struct ext4_dir_entry_2 *) dir_block->b_data;
+	de->inode = cpu_to_le32(inode->i_ino);
+	de->name_len = 1;
+	de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len),
+					   blocksize);
+	strcpy(de->name, ".");
+	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
+	de = ext4_next_entry(de, blocksize);
+	de->inode = cpu_to_le32(dir->i_ino);
+	de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(1),
+					   blocksize);
+	de->name_len = 2;
+	strcpy(de->name, "..");
+	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
+	inode->i_nlink = 2;
+	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(handle, inode, dir_block);
+	if (err)
+		goto out_clear_inode;
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (!err)
+		err = ext4_add_entry(handle, dentry, inode);
+	if (err) {
+out_clear_inode:
+		clear_nlink(inode);
+		unlock_new_inode(inode);
+		ext4_mark_inode_dirty(handle, inode);
+		iput(inode);
+		goto out_stop;
+	}
+	ext4_inc_count(handle, dir);
+	ext4_update_dx_flag(dir);
+	err = ext4_mark_inode_dirty(handle, dir);
+	if (err)
+		goto out_clear_inode;
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+out_stop:
+	brelse(dir_block);
+	ext4_journal_stop(handle);
+	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+		goto retry;
+	return err;
+}
+
+/*
+ * routine to check that the specified directory is empty (for rmdir)
+ */
+static int empty_dir(struct inode *inode)
+{
+	unsigned int offset;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de, *de1;
+	struct super_block *sb;
+	int err = 0;
+
+	sb = inode->i_sb;
+	if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
+	    !(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
+		if (err)
+			EXT4_ERROR_INODE(inode,
+				"error %d reading directory lblock 0", err);
+		else
+			ext4_warning(inode->i_sb,
+				     "bad directory (dir #%lu) - no data block",
+				     inode->i_ino);
+		return 1;
+	}
+	de = (struct ext4_dir_entry_2 *) bh->b_data;
+	de1 = ext4_next_entry(de, sb->s_blocksize);
+	if (le32_to_cpu(de->inode) != inode->i_ino ||
+			!le32_to_cpu(de1->inode) ||
+			strcmp(".", de->name) ||
+			strcmp("..", de1->name)) {
+		ext4_warning(inode->i_sb,
+			     "bad directory (dir #%lu) - no `.' or `..'",
+			     inode->i_ino);
+		brelse(bh);
+		return 1;
+	}
+	offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) +
+		 ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
+	de = ext4_next_entry(de1, sb->s_blocksize);
+	while (offset < inode->i_size) {
+		if (!bh ||
+		    (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+			unsigned int lblock;
+			err = 0;
+			brelse(bh);
+			lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+			bh = ext4_bread(NULL, inode, lblock, 0, &err);
+			if (!bh) {
+				if (err)
+					EXT4_ERROR_INODE(inode,
+						"error %d reading directory "
+						"lblock %u", err, lblock);
+				offset += sb->s_blocksize;
+				continue;
+			}
+			de = (struct ext4_dir_entry_2 *) bh->b_data;
+		}
+		if (ext4_check_dir_entry(inode, NULL, de, bh, offset)) {
+			de = (struct ext4_dir_entry_2 *)(bh->b_data +
+							 sb->s_blocksize);
+			offset = (offset | (sb->s_blocksize - 1)) + 1;
+			continue;
+		}
+		if (le32_to_cpu(de->inode)) {
+			brelse(bh);
+			return 0;
+		}
+		offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
+		de = ext4_next_entry(de, sb->s_blocksize);
+	}
+	brelse(bh);
+	return 1;
+}
+
+/* ext4_orphan_add() links an unlinked or truncated inode into a list of
+ * such inodes, starting at the superblock, in case we crash before the
+ * file is closed/deleted, or in case the inode truncate spans multiple
+ * transactions and the last transaction is not recovered after a crash.
+ *
+ * At filesystem recovery time, we walk this list deleting unlinked
+ * inodes and truncating linked inodes in ext4_orphan_cleanup().
+ */
+int ext4_orphan_add(handle_t *handle, struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ext4_iloc iloc;
+	int err = 0, rc;
+
+	if (!ext4_handle_valid(handle))
+		return 0;
+
+	mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
+	if (!list_empty(&EXT4_I(inode)->i_orphan))
+		goto out_unlock;
+
+	/* Orphan handling is only valid for files with data blocks
+	 * being truncated, or files being unlinked. */
+
+	/* @@@ FIXME: Observation from aviro:
+	 * I think I can trigger J_ASSERT in ext4_orphan_add().  We block
+	 * here (on s_orphan_lock), so race with ext4_link() which might bump
+	 * ->i_nlink. For, say it, character device. Not a regular file,
+	 * not a directory, not a symlink and ->i_nlink > 0.
+	 *
+	 * tytso, 4/25/2009: I'm not sure how that could happen;
+	 * shouldn't the fs core protect us from these sort of
+	 * unlink()/link() races?
+	 */
+	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
+
+	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+	if (err)
+		goto out_unlock;
+
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto out_unlock;
+	/*
+	 * Due to previous errors inode may be already a part of on-disk
+	 * orphan list. If so skip on-disk list modification.
+	 */
+	if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
+		(le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
+			goto mem_insert;
+
+	/* Insert this inode at the head of the on-disk orphan list... */
+	NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
+	EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+	err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
+	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+	if (!err)
+		err = rc;
+
+	/* Only add to the head of the in-memory list if all the
+	 * previous operations succeeded.  If the orphan_add is going to
+	 * fail (possibly taking the journal offline), we can't risk
+	 * leaving the inode on the orphan list: stray orphan-list
+	 * entries can cause panics at unmount time.
+	 *
+	 * This is safe: on error we're going to ignore the orphan list
+	 * anyway on the next recovery. */
+mem_insert:
+	if (!err)
+		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
+
+	jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
+	jbd_debug(4, "orphan inode %lu will point to %d\n",
+			inode->i_ino, NEXT_ORPHAN(inode));
+out_unlock:
+	mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
+	ext4_std_error(inode->i_sb, err);
+	return err;
+}
+
+/*
+ * ext4_orphan_del() removes an unlinked or truncated inode from the list
+ * of such inodes stored on disk, because it is finally being cleaned up.
+ */
+int ext4_orphan_del(handle_t *handle, struct inode *inode)
+{
+	struct list_head *prev;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi;
+	__u32 ino_next;
+	struct ext4_iloc iloc;
+	int err = 0;
+
+	/* ext4_handle_valid() assumes a valid handle_t pointer */
+	if (handle && !ext4_handle_valid(handle))
+		return 0;
+
+	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+	if (list_empty(&ei->i_orphan))
+		goto out;
+
+	ino_next = NEXT_ORPHAN(inode);
+	prev = ei->i_orphan.prev;
+	sbi = EXT4_SB(inode->i_sb);
+
+	jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
+
+	list_del_init(&ei->i_orphan);
+
+	/* If we're on an error path, we may not have a valid
+	 * transaction handle with which to update the orphan list on
+	 * disk, but we still need to remove the inode from the linked
+	 * list in memory. */
+	if (sbi->s_journal && !handle)
+		goto out;
+
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto out_err;
+
+	if (prev == &sbi->s_orphan) {
+		jbd_debug(4, "superblock will point to %u\n", ino_next);
+		BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+		if (err)
+			goto out_brelse;
+		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
+	} else {
+		struct ext4_iloc iloc2;
+		struct inode *i_prev =
+			&list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
+
+		jbd_debug(4, "orphan inode %lu will point to %u\n",
+			  i_prev->i_ino, ino_next);
+		err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
+		if (err)
+			goto out_brelse;
+		NEXT_ORPHAN(i_prev) = ino_next;
+		err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+	}
+	if (err)
+		goto out_brelse;
+	NEXT_ORPHAN(inode) = 0;
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+
+out_err:
+	ext4_std_error(inode->i_sb, err);
+out:
+	mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+	return err;
+
+out_brelse:
+	brelse(iloc.bh);
+	goto out_err;
+}
+
+static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	int retval;
+	struct inode *inode;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
+	handle_t *handle;
+
+	/* Initialize quotas before so that eventual writes go in
+	 * separate transaction */
+	dquot_initialize(dir);
+	dquot_initialize(dentry->d_inode);
+
+	handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	retval = -ENOENT;
+	bh = ext4_find_entry(dir, &dentry->d_name, &de);
+	if (!bh)
+		goto end_rmdir;
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	inode = dentry->d_inode;
+
+	retval = -EIO;
+	if (le32_to_cpu(de->inode) != inode->i_ino)
+		goto end_rmdir;
+
+	retval = -ENOTEMPTY;
+	if (!empty_dir(inode))
+		goto end_rmdir;
+
+	retval = ext4_delete_entry(handle, dir, de, bh);
+	if (retval)
+		goto end_rmdir;
+	if (!EXT4_DIR_LINK_EMPTY(inode))
+		ext4_warning(inode->i_sb,
+			     "empty directory has too many links (%d)",
+			     inode->i_nlink);
+	inode->i_version++;
+	clear_nlink(inode);
+	/* There's no need to set i_disksize: the fact that i_nlink is
+	 * zero will ensure that the right thing happens during any
+	 * recovery. */
+	inode->i_size = 0;
+	ext4_orphan_add(handle, inode);
+	inode->i_ctime = dir->i_ctime = dir->i_mtime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_dec_count(handle, dir);
+	ext4_update_dx_flag(dir);
+	ext4_mark_inode_dirty(handle, dir);
+
+end_rmdir:
+	ext4_journal_stop(handle);
+	brelse(bh);
+	return retval;
+}
+
+static int ext4_unlink(struct inode *dir, struct dentry *dentry)
+{
+	int retval;
+	struct inode *inode;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
+	handle_t *handle;
+
+	trace_ext4_unlink_enter(dir, dentry);
+	/* Initialize quotas before so that eventual writes go
+	 * in separate transaction */
+	dquot_initialize(dir);
+	dquot_initialize(dentry->d_inode);
+
+	handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	retval = -ENOENT;
+	bh = ext4_find_entry(dir, &dentry->d_name, &de);
+	if (!bh)
+		goto end_unlink;
+
+	inode = dentry->d_inode;
+
+	retval = -EIO;
+	if (le32_to_cpu(de->inode) != inode->i_ino)
+		goto end_unlink;
+
+	if (!inode->i_nlink) {
+		ext4_warning(inode->i_sb,
+			     "Deleting nonexistent file (%lu), %d",
+			     inode->i_ino, inode->i_nlink);
+		inode->i_nlink = 1;
+	}
+	retval = ext4_delete_entry(handle, dir, de, bh);
+	if (retval)
+		goto end_unlink;
+	dir->i_ctime = dir->i_mtime = ext4_current_time(dir);
+	ext4_update_dx_flag(dir);
+	ext4_mark_inode_dirty(handle, dir);
+	drop_nlink(inode);
+	if (!inode->i_nlink)
+		ext4_orphan_add(handle, inode);
+	inode->i_ctime = ext4_current_time(inode);
+	ext4_mark_inode_dirty(handle, inode);
+	retval = 0;
+
+end_unlink:
+	ext4_journal_stop(handle);
+	brelse(bh);
+	trace_ext4_unlink_exit(dentry, retval);
+	return retval;
+}
+
+static int ext4_symlink(struct inode *dir,
+			struct dentry *dentry, const char *symname)
+{
+	handle_t *handle;
+	struct inode *inode;
+	int l, err, retries = 0;
+	int credits;
+
+	l = strlen(symname)+1;
+	if (l > dir->i_sb->s_blocksize)
+		return -ENAMETOOLONG;
+
+	dquot_initialize(dir);
+
+	if (l > EXT4_N_BLOCKS * 4) {
+		/*
+		 * For non-fast symlinks, we just allocate inode and put it on
+		 * orphan list in the first transaction => we need bitmap,
+		 * group descriptor, sb, inode block, quota blocks, and
+		 * possibly selinux xattr blocks.
+		 */
+		credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+			  EXT4_XATTR_TRANS_BLOCKS;
+	} else {
+		/*
+		 * Fast symlink. We have to add entry to directory
+		 * (EXT4_DATA_TRANS_BLOCKS + EXT4_INDEX_EXTRA_TRANS_BLOCKS),
+		 * allocate new inode (bitmap, group descriptor, inode block,
+		 * quota blocks, sb is already counted in previous macros).
+		 */
+		credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+			  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+			  EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+	}
+retry:
+	handle = ext4_journal_start(dir, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
+			       &dentry->d_name, 0);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out_stop;
+
+	if (l > EXT4_N_BLOCKS * 4) {
+		inode->i_op = &ext4_symlink_inode_operations;
+		ext4_set_aops(inode);
+		/*
+		 * We cannot call page_symlink() with transaction started
+		 * because it calls into ext4_write_begin() which can wait
+		 * for transaction commit if we are running out of space
+		 * and thus we deadlock. So we have to stop transaction now
+		 * and restart it when symlink contents is written.
+		 * 
+		 * To keep fs consistent in case of crash, we have to put inode
+		 * to orphan list in the mean time.
+		 */
+		drop_nlink(inode);
+		err = ext4_orphan_add(handle, inode);
+		ext4_journal_stop(handle);
+		if (err)
+			goto err_drop_inode;
+		err = __page_symlink(inode, symname, l, 1);
+		if (err)
+			goto err_drop_inode;
+		/*
+		 * Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS
+		 * + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified
+		 */
+		handle = ext4_journal_start(dir,
+				EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+				EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto err_drop_inode;
+		}
+		inc_nlink(inode);
+		err = ext4_orphan_del(handle, inode);
+		if (err) {
+			ext4_journal_stop(handle);
+			clear_nlink(inode);
+			goto err_drop_inode;
+		}
+	} else {
+		/* clear the extent format for fast symlink */
+		ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
+		inode->i_op = &ext4_fast_symlink_inode_operations;
+		memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
+		inode->i_size = l-1;
+	}
+	EXT4_I(inode)->i_disksize = inode->i_size;
+	err = ext4_add_nondir(handle, dentry, inode);
+out_stop:
+	ext4_journal_stop(handle);
+	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+		goto retry;
+	return err;
+err_drop_inode:
+	unlock_new_inode(inode);
+	iput(inode);
+	return err;
+}
+
+static int ext4_link(struct dentry *old_dentry,
+		     struct inode *dir, struct dentry *dentry)
+{
+	handle_t *handle;
+	struct inode *inode = old_dentry->d_inode;
+	int err, retries = 0;
+
+	if (inode->i_nlink >= EXT4_LINK_MAX)
+		return -EMLINK;
+
+	dquot_initialize(dir);
+
+retry:
+	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(dir))
+		ext4_handle_sync(handle);
+
+	inode->i_ctime = ext4_current_time(inode);
+	ext4_inc_count(handle, inode);
+	ihold(inode);
+
+	err = ext4_add_entry(handle, dentry, inode);
+	if (!err) {
+		ext4_mark_inode_dirty(handle, inode);
+		d_instantiate(dentry, inode);
+	} else {
+		drop_nlink(inode);
+		iput(inode);
+	}
+	ext4_journal_stop(handle);
+	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+		goto retry;
+	return err;
+}
+
+#define PARENT_INO(buffer, size) \
+	(ext4_next_entry((struct ext4_dir_entry_2 *)(buffer), size)->inode)
+
+/*
+ * Anybody can rename anything with this: the permission checks are left to the
+ * higher-level routines.
+ */
+static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
+		       struct inode *new_dir, struct dentry *new_dentry)
+{
+	handle_t *handle;
+	struct inode *old_inode, *new_inode;
+	struct buffer_head *old_bh, *new_bh, *dir_bh;
+	struct ext4_dir_entry_2 *old_de, *new_de;
+	int retval, force_da_alloc = 0;
+
+	dquot_initialize(old_dir);
+	dquot_initialize(new_dir);
+
+	old_bh = new_bh = dir_bh = NULL;
+
+	/* Initialize quotas before so that eventual writes go
+	 * in separate transaction */
+	if (new_dentry->d_inode)
+		dquot_initialize(new_dentry->d_inode);
+	handle = ext4_journal_start(old_dir, 2 *
+					EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
+					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+		ext4_handle_sync(handle);
+
+	old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
+	/*
+	 *  Check for inode number is _not_ due to possible IO errors.
+	 *  We might rmdir the source, keep it as pwd of some process
+	 *  and merrily kill the link to whatever was created under the
+	 *  same name. Goodbye sticky bit ;-<
+	 */
+	old_inode = old_dentry->d_inode;
+	retval = -ENOENT;
+	if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
+		goto end_rename;
+
+	new_inode = new_dentry->d_inode;
+	new_bh = ext4_find_entry(new_dir, &new_dentry->d_name, &new_de);
+	if (new_bh) {
+		if (!new_inode) {
+			brelse(new_bh);
+			new_bh = NULL;
+		}
+	}
+	if (S_ISDIR(old_inode->i_mode)) {
+		if (new_inode) {
+			retval = -ENOTEMPTY;
+			if (!empty_dir(new_inode))
+				goto end_rename;
+		}
+		retval = -EIO;
+		dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval);
+		if (!dir_bh)
+			goto end_rename;
+		if (le32_to_cpu(PARENT_INO(dir_bh->b_data,
+				old_dir->i_sb->s_blocksize)) != old_dir->i_ino)
+			goto end_rename;
+		retval = -EMLINK;
+		if (!new_inode && new_dir != old_dir &&
+		    EXT4_DIR_LINK_MAX(new_dir))
+			goto end_rename;
+		BUFFER_TRACE(dir_bh, "get_write_access");
+		retval = ext4_journal_get_write_access(handle, dir_bh);
+		if (retval)
+			goto end_rename;
+	}
+	if (!new_bh) {
+		retval = ext4_add_entry(handle, new_dentry, old_inode);
+		if (retval)
+			goto end_rename;
+	} else {
+		BUFFER_TRACE(new_bh, "get write access");
+		retval = ext4_journal_get_write_access(handle, new_bh);
+		if (retval)
+			goto end_rename;
+		new_de->inode = cpu_to_le32(old_inode->i_ino);
+		if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
+					      EXT4_FEATURE_INCOMPAT_FILETYPE))
+			new_de->file_type = old_de->file_type;
+		new_dir->i_version++;
+		new_dir->i_ctime = new_dir->i_mtime =
+					ext4_current_time(new_dir);
+		ext4_mark_inode_dirty(handle, new_dir);
+		BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
+		retval = ext4_handle_dirty_metadata(handle, new_dir, new_bh);
+		if (unlikely(retval)) {
+			ext4_std_error(new_dir->i_sb, retval);
+			goto end_rename;
+		}
+		brelse(new_bh);
+		new_bh = NULL;
+	}
+
+	/*
+	 * Like most other Unix systems, set the ctime for inodes on a
+	 * rename.
+	 */
+	old_inode->i_ctime = ext4_current_time(old_inode);
+	ext4_mark_inode_dirty(handle, old_inode);
+
+	/*
+	 * ok, that's it
+	 */
+	if (le32_to_cpu(old_de->inode) != old_inode->i_ino ||
+	    old_de->name_len != old_dentry->d_name.len ||
+	    strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) ||
+	    (retval = ext4_delete_entry(handle, old_dir,
+					old_de, old_bh)) == -ENOENT) {
+		/* old_de could have moved from under us during htree split, so
+		 * make sure that we are deleting the right entry.  We might
+		 * also be pointing to a stale entry in the unused part of
+		 * old_bh so just checking inum and the name isn't enough. */
+		struct buffer_head *old_bh2;
+		struct ext4_dir_entry_2 *old_de2;
+
+		old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de2);
+		if (old_bh2) {
+			retval = ext4_delete_entry(handle, old_dir,
+						   old_de2, old_bh2);
+			brelse(old_bh2);
+		}
+	}
+	if (retval) {
+		ext4_warning(old_dir->i_sb,
+				"Deleting old file (%lu), %d, error=%d",
+				old_dir->i_ino, old_dir->i_nlink, retval);
+	}
+
+	if (new_inode) {
+		ext4_dec_count(handle, new_inode);
+		new_inode->i_ctime = ext4_current_time(new_inode);
+	}
+	old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir);
+	ext4_update_dx_flag(old_dir);
+	if (dir_bh) {
+		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
+						cpu_to_le32(new_dir->i_ino);
+		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
+		retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
+		if (retval) {
+			ext4_std_error(old_dir->i_sb, retval);
+			goto end_rename;
+		}
+		ext4_dec_count(handle, old_dir);
+		if (new_inode) {
+			/* checked empty_dir above, can't have another parent,
+			 * ext4_dec_count() won't work for many-linked dirs */
+			new_inode->i_nlink = 0;
+		} else {
+			ext4_inc_count(handle, new_dir);
+			ext4_update_dx_flag(new_dir);
+			ext4_mark_inode_dirty(handle, new_dir);
+		}
+	}
+	ext4_mark_inode_dirty(handle, old_dir);
+	if (new_inode) {
+		ext4_mark_inode_dirty(handle, new_inode);
+		if (!new_inode->i_nlink)
+			ext4_orphan_add(handle, new_inode);
+		if (!test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC))
+			force_da_alloc = 1;
+	}
+	retval = 0;
+
+end_rename:
+	brelse(dir_bh);
+	brelse(old_bh);
+	brelse(new_bh);
+	ext4_journal_stop(handle);
+	if (retval == 0 && force_da_alloc)
+		ext4_alloc_da_blocks(old_inode);
+	return retval;
+}
+
+/*
+ * directories can handle most operations...
+ */
+const struct inode_operations ext4_dir_inode_operations = {
+	.create		= ext4_create,
+	.lookup		= ext4_lookup,
+	.link		= ext4_link,
+	.unlink		= ext4_unlink,
+	.symlink	= ext4_symlink,
+	.mkdir		= ext4_mkdir,
+	.rmdir		= ext4_rmdir,
+	.mknod		= ext4_mknod,
+	.rename		= ext4_rename,
+	.setattr	= ext4_setattr,
+#ifdef CONFIG_EXT4_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext4_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.check_acl	= ext4_check_acl,
+	.fiemap         = ext4_fiemap,
+};
+
+const struct inode_operations ext4_special_inode_operations = {
+	.setattr	= ext4_setattr,
+#ifdef CONFIG_EXT4_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext4_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.check_acl	= ext4_check_acl,
+};
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
new file mode 100644
index 00000000..d99d74ac
--- /dev/null
+++ b/fs/ext4/page-io.c
@@ -0,0 +1,447 @@
+/*
+ * linux/fs/ext4/page-io.c
+ *
+ * This contains the new page_io functions for ext4
+ *
+ * Written by Theodore Ts'o, 2010.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/jbd2.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/uio.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "ext4_extents.h"
+
+static struct kmem_cache *io_page_cachep, *io_end_cachep;
+
+int __init ext4_init_pageio(void)
+{
+	io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
+	if (io_page_cachep == NULL)
+		return -ENOMEM;
+	io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
+	if (io_end_cachep == NULL) {
+		kmem_cache_destroy(io_page_cachep);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void ext4_exit_pageio(void)
+{
+	kmem_cache_destroy(io_end_cachep);
+	kmem_cache_destroy(io_page_cachep);
+}
+
+void ext4_ioend_wait(struct inode *inode)
+{
+	wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
+}
+
+static void put_io_page(struct ext4_io_page *io_page)
+{
+	if (atomic_dec_and_test(&io_page->p_count)) {
+		end_page_writeback(io_page->p_page);
+		put_page(io_page->p_page);
+		kmem_cache_free(io_page_cachep, io_page);
+	}
+}
+
+void ext4_free_io_end(ext4_io_end_t *io)
+{
+	int i;
+	wait_queue_head_t *wq;
+
+	BUG_ON(!io);
+	if (io->page)
+		put_page(io->page);
+	for (i = 0; i < io->num_io_pages; i++)
+		put_io_page(io->pages[i]);
+	io->num_io_pages = 0;
+	wq = ext4_ioend_wq(io->inode);
+	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
+	    waitqueue_active(wq))
+		wake_up_all(wq);
+	kmem_cache_free(io_end_cachep, io);
+}
+
+/*
+ * check a range of space and convert unwritten extents to written.
+ */
+int ext4_end_io_nolock(ext4_io_end_t *io)
+{
+	struct inode *inode = io->inode;
+	loff_t offset = io->offset;
+	ssize_t size = io->size;
+	wait_queue_head_t *wq;
+	int ret = 0;
+
+	ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
+		   "list->prev 0x%p\n",
+		   io, inode->i_ino, io->list.next, io->list.prev);
+
+	if (list_empty(&io->list))
+		return ret;
+
+	if (!(io->flag & EXT4_IO_END_UNWRITTEN))
+		return ret;
+
+	ret = ext4_convert_unwritten_extents(inode, offset, size);
+	if (ret < 0) {
+		printk(KERN_EMERG "%s: failed to convert unwritten "
+			"extents to written extents, error is %d "
+			"io is still on inode %lu aio dio list\n",
+		       __func__, ret, inode->i_ino);
+		return ret;
+	}
+
+	if (io->iocb)
+		aio_complete(io->iocb, io->result, 0);
+	/* clear the DIO AIO unwritten flag */
+	if (io->flag & EXT4_IO_END_UNWRITTEN) {
+		io->flag &= ~EXT4_IO_END_UNWRITTEN;
+		/* Wake up anyone waiting on unwritten extent conversion */
+		wq = ext4_ioend_wq(io->inode);
+		if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
+		    waitqueue_active(wq)) {
+			wake_up_all(wq);
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * work on completed aio dio IO, to convert unwritten extents to extents
+ */
+static void ext4_end_io_work(struct work_struct *work)
+{
+	ext4_io_end_t		*io = container_of(work, ext4_io_end_t, work);
+	struct inode		*inode = io->inode;
+	struct ext4_inode_info	*ei = EXT4_I(inode);
+	unsigned long		flags;
+	int			ret;
+
+	if (!mutex_trylock(&inode->i_mutex)) {
+		/*
+		 * Requeue the work instead of waiting so that the work
+		 * items queued after this can be processed.
+		 */
+		queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+		/*
+		 * To prevent the ext4-dio-unwritten thread from keeping
+		 * requeueing end_io requests and occupying cpu for too long,
+		 * yield the cpu if it sees an end_io request that has already
+		 * been requeued.
+		 */
+		if (io->flag & EXT4_IO_END_QUEUED)
+			yield();
+		io->flag |= EXT4_IO_END_QUEUED;
+		return;
+	}
+	ret = ext4_end_io_nolock(io);
+	if (ret < 0) {
+		mutex_unlock(&inode->i_mutex);
+		return;
+	}
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	if (!list_empty(&io->list))
+		list_del_init(&io->list);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+	mutex_unlock(&inode->i_mutex);
+	ext4_free_io_end(io);
+}
+
+ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
+{
+	ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
+	if (io) {
+		atomic_inc(&EXT4_I(inode)->i_ioend_count);
+		io->inode = inode;
+		INIT_WORK(&io->work, ext4_end_io_work);
+		INIT_LIST_HEAD(&io->list);
+	}
+	return io;
+}
+
+/*
+ * Print an buffer I/O error compatible with the fs/buffer.c.  This
+ * provides compatibility with dmesg scrapers that look for a specific
+ * buffer I/O error message.  We really need a unified error reporting
+ * structure to userspace ala Digital Unix's uerf system, but it's
+ * probably not going to happen in my lifetime, due to LKML politics...
+ */
+static void buffer_io_error(struct buffer_head *bh)
+{
+	char b[BDEVNAME_SIZE];
+	printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
+			bdevname(bh->b_bdev, b),
+			(unsigned long long)bh->b_blocknr);
+}
+
+static void ext4_end_bio(struct bio *bio, int error)
+{
+	ext4_io_end_t *io_end = bio->bi_private;
+	struct workqueue_struct *wq;
+	struct inode *inode;
+	unsigned long flags;
+	int i;
+	sector_t bi_sector = bio->bi_sector;
+
+	BUG_ON(!io_end);
+	bio->bi_private = NULL;
+	bio->bi_end_io = NULL;
+	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+		error = 0;
+	bio_put(bio);
+
+	for (i = 0; i < io_end->num_io_pages; i++) {
+		struct page *page = io_end->pages[i]->p_page;
+		struct buffer_head *bh, *head;
+		loff_t offset;
+		loff_t io_end_offset;
+
+		if (error) {
+			SetPageError(page);
+			set_bit(AS_EIO, &page->mapping->flags);
+			head = page_buffers(page);
+			BUG_ON(!head);
+
+			io_end_offset = io_end->offset + io_end->size;
+
+			offset = (sector_t) page->index << PAGE_CACHE_SHIFT;
+			bh = head;
+			do {
+				if ((offset >= io_end->offset) &&
+				    (offset+bh->b_size <= io_end_offset))
+					buffer_io_error(bh);
+
+				offset += bh->b_size;
+				bh = bh->b_this_page;
+			} while (bh != head);
+		}
+
+		put_io_page(io_end->pages[i]);
+	}
+	io_end->num_io_pages = 0;
+	inode = io_end->inode;
+
+	if (error) {
+		io_end->flag |= EXT4_IO_END_ERROR;
+		ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
+			     "(offset %llu size %ld starting block %llu)",
+			     inode->i_ino,
+			     (unsigned long long) io_end->offset,
+			     (long) io_end->size,
+			     (unsigned long long)
+			     bi_sector >> (inode->i_blkbits - 9));
+	}
+
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+		return;
+	}
+
+	/* Add the io_end to per-inode completed io list*/
+	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+	list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
+	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
+
+	wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
+	/* queue the work to convert unwritten extents to written */
+	queue_work(wq, &io_end->work);
+}
+
+void ext4_io_submit(struct ext4_io_submit *io)
+{
+	struct bio *bio = io->io_bio;
+
+	if (bio) {
+		bio_get(io->io_bio);
+		submit_bio(io->io_op, io->io_bio);
+		BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
+		bio_put(io->io_bio);
+	}
+	io->io_bio = NULL;
+	io->io_op = 0;
+	io->io_end = NULL;
+}
+
+static int io_submit_init(struct ext4_io_submit *io,
+			  struct inode *inode,
+			  struct writeback_control *wbc,
+			  struct buffer_head *bh)
+{
+	ext4_io_end_t *io_end;
+	struct page *page = bh->b_page;
+	int nvecs = bio_get_nr_vecs(bh->b_bdev);
+	struct bio *bio;
+
+	io_end = ext4_init_io_end(inode, GFP_NOFS);
+	if (!io_end)
+		return -ENOMEM;
+	do {
+		bio = bio_alloc(GFP_NOIO, nvecs);
+		nvecs >>= 1;
+	} while (bio == NULL);
+
+	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_bdev = bh->b_bdev;
+	bio->bi_private = io->io_end = io_end;
+	bio->bi_end_io = ext4_end_bio;
+
+	io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
+
+	io->io_bio = bio;
+	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
+	io->io_next_block = bh->b_blocknr;
+	return 0;
+}
+
+static int io_submit_add_bh(struct ext4_io_submit *io,
+			    struct ext4_io_page *io_page,
+			    struct inode *inode,
+			    struct writeback_control *wbc,
+			    struct buffer_head *bh)
+{
+	ext4_io_end_t *io_end;
+	int ret;
+
+	if (buffer_new(bh)) {
+		clear_buffer_new(bh);
+		unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
+	}
+
+	if (!buffer_mapped(bh) || buffer_delay(bh)) {
+		if (!buffer_mapped(bh))
+			clear_buffer_dirty(bh);
+		if (io->io_bio)
+			ext4_io_submit(io);
+		return 0;
+	}
+
+	if (io->io_bio && bh->b_blocknr != io->io_next_block) {
+submit_and_retry:
+		ext4_io_submit(io);
+	}
+	if (io->io_bio == NULL) {
+		ret = io_submit_init(io, inode, wbc, bh);
+		if (ret)
+			return ret;
+	}
+	io_end = io->io_end;
+	if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
+	    (io_end->pages[io_end->num_io_pages-1] != io_page))
+		goto submit_and_retry;
+	if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
+	io->io_end->size += bh->b_size;
+	io->io_next_block++;
+	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+	if (ret != bh->b_size)
+		goto submit_and_retry;
+	if ((io_end->num_io_pages == 0) ||
+	    (io_end->pages[io_end->num_io_pages-1] != io_page)) {
+		io_end->pages[io_end->num_io_pages++] = io_page;
+		atomic_inc(&io_page->p_count);
+	}
+	return 0;
+}
+
+int ext4_bio_write_page(struct ext4_io_submit *io,
+			struct page *page,
+			int len,
+			struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	unsigned block_start, block_end, blocksize;
+	struct ext4_io_page *io_page;
+	struct buffer_head *bh, *head;
+	int ret = 0;
+
+	blocksize = 1 << inode->i_blkbits;
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(PageWriteback(page));
+
+	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
+	if (!io_page) {
+		set_page_dirty(page);
+		unlock_page(page);
+		return -ENOMEM;
+	}
+	io_page->p_page = page;
+	atomic_set(&io_page->p_count, 1);
+	get_page(page);
+	set_page_writeback(page);
+	ClearPageError(page);
+
+	for (bh = head = page_buffers(page), block_start = 0;
+	     bh != head || !block_start;
+	     block_start = block_end, bh = bh->b_this_page) {
+
+		block_end = block_start + blocksize;
+		if (block_start >= len) {
+			/*
+			 * Comments copied from block_write_full_page_endio:
+			 *
+			 * The page straddles i_size.  It must be zeroed out on
+			 * each and every writepage invocation because it may
+			 * be mmapped.  "A file is mapped in multiples of the
+			 * page size.  For a file that is not a multiple of
+			 * the  page size, the remaining memory is zeroed when
+			 * mapped, and writes to that region are not written
+			 * out to the file."
+			 */
+			zero_user_segment(page, block_start, block_end);
+			clear_buffer_dirty(bh);
+			set_buffer_uptodate(bh);
+			continue;
+		}
+		clear_buffer_dirty(bh);
+		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
+		if (ret) {
+			/*
+			 * We only get here on ENOMEM.  Not much else
+			 * we can do but mark the page as dirty, and
+			 * better luck next time.
+			 */
+			set_page_dirty(page);
+			break;
+		}
+	}
+	unlock_page(page);
+	/*
+	 * If the page was truncated before we could do the writeback,
+	 * or we had a memory allocation error while trying to write
+	 * the first buffer head, we won't have submitted any pages for
+	 * I/O.  In that case we need to make sure we've cleared the
+	 * PageWriteback bit from the page to prevent the system from
+	 * wedging later on.
+	 */
+	put_io_page(io_page);
+	return ret;
+}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
new file mode 100644
index 00000000..80bbc9c6
--- /dev/null
+++ b/fs/ext4/resize.c
@@ -0,0 +1,1076 @@
+/*
+ *  linux/fs/ext4/resize.c
+ *
+ * Support for resizing an ext4 filesystem while it is mounted.
+ *
+ * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
+ *
+ * This could probably be made into a module, because it is not often in use.
+ */
+
+
+#define EXT4FS_DEBUG
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "ext4_jbd2.h"
+
+#define outside(b, first, last)	((b) < (first) || (b) >= (last))
+#define inside(b, first, last)	((b) >= (first) && (b) < (last))
+
+static int verify_group_input(struct super_block *sb,
+			      struct ext4_new_group_data *input)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	ext4_fsblk_t start = ext4_blocks_count(es);
+	ext4_fsblk_t end = start + input->blocks_count;
+	ext4_group_t group = input->group;
+	ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
+	unsigned overhead = ext4_bg_has_super(sb, group) ?
+		(1 + ext4_bg_num_gdb(sb, group) +
+		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+	ext4_fsblk_t metaend = start + overhead;
+	struct buffer_head *bh = NULL;
+	ext4_grpblk_t free_blocks_count, offset;
+	int err = -EINVAL;
+
+	input->free_blocks_count = free_blocks_count =
+		input->blocks_count - 2 - overhead - sbi->s_itb_per_group;
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks "
+		       "(%d free, %u reserved)\n",
+		       ext4_bg_has_super(sb, input->group) ? "normal" :
+		       "no-super", input->group, input->blocks_count,
+		       free_blocks_count, input->reserved_blocks);
+
+	ext4_get_group_no_and_offset(sb, start, NULL, &offset);
+	if (group != sbi->s_groups_count)
+		ext4_warning(sb, "Cannot add at group %u (only %u groups)",
+			     input->group, sbi->s_groups_count);
+	else if (offset != 0)
+			ext4_warning(sb, "Last group not full");
+	else if (input->reserved_blocks > input->blocks_count / 5)
+		ext4_warning(sb, "Reserved blocks too high (%u)",
+			     input->reserved_blocks);
+	else if (free_blocks_count < 0)
+		ext4_warning(sb, "Bad blocks count %u",
+			     input->blocks_count);
+	else if (!(bh = sb_bread(sb, end - 1)))
+		ext4_warning(sb, "Cannot read last block (%llu)",
+			     end - 1);
+	else if (outside(input->block_bitmap, start, end))
+		ext4_warning(sb, "Block bitmap not in group (block %llu)",
+			     (unsigned long long)input->block_bitmap);
+	else if (outside(input->inode_bitmap, start, end))
+		ext4_warning(sb, "Inode bitmap not in group (block %llu)",
+			     (unsigned long long)input->inode_bitmap);
+	else if (outside(input->inode_table, start, end) ||
+		 outside(itend - 1, start, end))
+		ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
+			     (unsigned long long)input->inode_table, itend - 1);
+	else if (input->inode_bitmap == input->block_bitmap)
+		ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
+			     (unsigned long long)input->block_bitmap);
+	else if (inside(input->block_bitmap, input->inode_table, itend))
+		ext4_warning(sb, "Block bitmap (%llu) in inode table "
+			     "(%llu-%llu)",
+			     (unsigned long long)input->block_bitmap,
+			     (unsigned long long)input->inode_table, itend - 1);
+	else if (inside(input->inode_bitmap, input->inode_table, itend))
+		ext4_warning(sb, "Inode bitmap (%llu) in inode table "
+			     "(%llu-%llu)",
+			     (unsigned long long)input->inode_bitmap,
+			     (unsigned long long)input->inode_table, itend - 1);
+	else if (inside(input->block_bitmap, start, metaend))
+		ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
+			     (unsigned long long)input->block_bitmap,
+			     start, metaend - 1);
+	else if (inside(input->inode_bitmap, start, metaend))
+		ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
+			     (unsigned long long)input->inode_bitmap,
+			     start, metaend - 1);
+	else if (inside(input->inode_table, start, metaend) ||
+		 inside(itend - 1, start, metaend))
+		ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
+			     "(%llu-%llu)",
+			     (unsigned long long)input->inode_table,
+			     itend - 1, start, metaend - 1);
+	else
+		err = 0;
+	brelse(bh);
+
+	return err;
+}
+
+static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
+				  ext4_fsblk_t blk)
+{
+	struct buffer_head *bh;
+	int err;
+
+	bh = sb_getblk(sb, blk);
+	if (!bh)
+		return ERR_PTR(-EIO);
+	if ((err = ext4_journal_get_write_access(handle, bh))) {
+		brelse(bh);
+		bh = ERR_PTR(err);
+	} else {
+		lock_buffer(bh);
+		memset(bh->b_data, 0, sb->s_blocksize);
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+	}
+
+	return bh;
+}
+
+/*
+ * If we have fewer than thresh credits, extend by EXT4_MAX_TRANS_DATA.
+ * If that fails, restart the transaction & regain write access for the
+ * buffer head which is used for block_bitmap modifications.
+ */
+static int extend_or_restart_transaction(handle_t *handle, int thresh,
+					 struct buffer_head *bh)
+{
+	int err;
+
+	if (ext4_handle_has_enough_credits(handle, thresh))
+		return 0;
+
+	err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
+	if (err < 0)
+		return err;
+	if (err) {
+		if ((err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
+			return err;
+		if ((err = ext4_journal_get_write_access(handle, bh)))
+			return err;
+	}
+
+	return 0;
+}
+
+/*
+ * Set up the block and inode bitmaps, and the inode table for the new group.
+ * This doesn't need to be part of the main transaction, since we are only
+ * changing blocks outside the actual filesystem.  We still do journaling to
+ * ensure the recovery is correct in case of a failure just after resize.
+ * If any part of this fails, we simply abort the resize.
+ */
+static int setup_new_group_blocks(struct super_block *sb,
+				  struct ext4_new_group_data *input)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t start = ext4_group_first_block_no(sb, input->group);
+	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
+		le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0;
+	unsigned long gdblocks = ext4_bg_num_gdb(sb, input->group);
+	struct buffer_head *bh;
+	handle_t *handle;
+	ext4_fsblk_t block;
+	ext4_grpblk_t bit;
+	int i;
+	int err = 0, err2;
+
+	/* This transaction may be extended/restarted along the way */
+	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
+
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	mutex_lock(&sbi->s_resize_lock);
+	if (input->group != sbi->s_groups_count) {
+		err = -EBUSY;
+		goto exit_journal;
+	}
+
+	if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) {
+		err = PTR_ERR(bh);
+		goto exit_journal;
+	}
+
+	if (ext4_bg_has_super(sb, input->group)) {
+		ext4_debug("mark backup superblock %#04llx (+0)\n", start);
+		ext4_set_bit(0, bh->b_data);
+	}
+
+	/* Copy all of the GDT blocks into the backup in this group */
+	for (i = 0, bit = 1, block = start + 1;
+	     i < gdblocks; i++, block++, bit++) {
+		struct buffer_head *gdb;
+
+		ext4_debug("update backup group %#04llx (+%d)\n", block, bit);
+
+		if ((err = extend_or_restart_transaction(handle, 1, bh)))
+			goto exit_bh;
+
+		gdb = sb_getblk(sb, block);
+		if (!gdb) {
+			err = -EIO;
+			goto exit_bh;
+		}
+		if ((err = ext4_journal_get_write_access(handle, gdb))) {
+			brelse(gdb);
+			goto exit_bh;
+		}
+		lock_buffer(gdb);
+		memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
+		set_buffer_uptodate(gdb);
+		unlock_buffer(gdb);
+		err = ext4_handle_dirty_metadata(handle, NULL, gdb);
+		if (unlikely(err)) {
+			brelse(gdb);
+			goto exit_bh;
+		}
+		ext4_set_bit(bit, bh->b_data);
+		brelse(gdb);
+	}
+
+	/* Zero out all of the reserved backup group descriptor table blocks */
+	ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
+			block, sbi->s_itb_per_group);
+	err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
+			       GFP_NOFS);
+	if (err)
+		goto exit_bh;
+	for (i = 0, bit = gdblocks + 1; i < reserved_gdb; i++, bit++)
+		ext4_set_bit(bit, bh->b_data);
+
+	ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
+		   input->block_bitmap - start);
+	ext4_set_bit(input->block_bitmap - start, bh->b_data);
+	ext4_debug("mark inode bitmap %#04llx (+%llu)\n", input->inode_bitmap,
+		   input->inode_bitmap - start);
+	ext4_set_bit(input->inode_bitmap - start, bh->b_data);
+
+	/* Zero out all of the inode table blocks */
+	block = input->inode_table;
+	ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
+			block, sbi->s_itb_per_group);
+	err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
+	if (err)
+		goto exit_bh;
+	for (i = 0, bit = input->inode_table - start;
+	     i < sbi->s_itb_per_group; i++, bit++)
+		ext4_set_bit(bit, bh->b_data);
+
+	if ((err = extend_or_restart_transaction(handle, 2, bh)))
+		goto exit_bh;
+
+	ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8,
+			     bh->b_data);
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (unlikely(err)) {
+		ext4_std_error(sb, err);
+		goto exit_bh;
+	}
+	brelse(bh);
+	/* Mark unused entries in inode bitmap used */
+	ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
+		   input->inode_bitmap, input->inode_bitmap - start);
+	if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
+		err = PTR_ERR(bh);
+		goto exit_journal;
+	}
+
+	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+			     bh->b_data);
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (unlikely(err))
+		ext4_std_error(sb, err);
+exit_bh:
+	brelse(bh);
+
+exit_journal:
+	mutex_unlock(&sbi->s_resize_lock);
+	if ((err2 = ext4_journal_stop(handle)) && !err)
+		err = err2;
+
+	return err;
+}
+
+/*
+ * Iterate through the groups which hold BACKUP superblock/GDT copies in an
+ * ext4 filesystem.  The counters should be initialized to 1, 5, and 7 before
+ * calling this for the first time.  In a sparse filesystem it will be the
+ * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ...
+ * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ...
+ */
+static unsigned ext4_list_backups(struct super_block *sb, unsigned *three,
+				  unsigned *five, unsigned *seven)
+{
+	unsigned *min = three;
+	int mult = 3;
+	unsigned ret;
+
+	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
+		ret = *min;
+		*min += 1;
+		return ret;
+	}
+
+	if (*five < *min) {
+		min = five;
+		mult = 5;
+	}
+	if (*seven < *min) {
+		min = seven;
+		mult = 7;
+	}
+
+	ret = *min;
+	*min *= mult;
+
+	return ret;
+}
+
+/*
+ * Check that all of the backup GDT blocks are held in the primary GDT block.
+ * It is assumed that they are stored in group order.  Returns the number of
+ * groups in current filesystem that have BACKUPS, or -ve error code.
+ */
+static int verify_reserved_gdb(struct super_block *sb,
+			       struct buffer_head *primary)
+{
+	const ext4_fsblk_t blk = primary->b_blocknr;
+	const ext4_group_t end = EXT4_SB(sb)->s_groups_count;
+	unsigned three = 1;
+	unsigned five = 5;
+	unsigned seven = 7;
+	unsigned grp;
+	__le32 *p = (__le32 *)primary->b_data;
+	int gdbackups = 0;
+
+	while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
+		if (le32_to_cpu(*p++) !=
+		    grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
+			ext4_warning(sb, "reserved GDT %llu"
+				     " missing grp %d (%llu)",
+				     blk, grp,
+				     grp *
+				     (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
+				     blk);
+			return -EINVAL;
+		}
+		if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb))
+			return -EFBIG;
+	}
+
+	return gdbackups;
+}
+
+/*
+ * Called when we need to bring a reserved group descriptor table block into
+ * use from the resize inode.  The primary copy of the new GDT block currently
+ * is an indirect block (under the double indirect block in the resize inode).
+ * The new backup GDT blocks will be stored as leaf blocks in this indirect
+ * block, in group order.  Even though we know all the block numbers we need,
+ * we check to ensure that the resize inode has actually reserved these blocks.
+ *
+ * Don't need to update the block bitmaps because the blocks are still in use.
+ *
+ * We get all of the error cases out of the way, so that we are sure to not
+ * fail once we start modifying the data on disk, because JBD has no rollback.
+ */
+static int add_new_gdb(handle_t *handle, struct inode *inode,
+		       struct ext4_new_group_data *input,
+		       struct buffer_head **primary)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	unsigned long gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
+	ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
+	struct buffer_head **o_group_desc, **n_group_desc;
+	struct buffer_head *dind;
+	int gdbackups;
+	struct ext4_iloc iloc;
+	__le32 *data;
+	int err;
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG
+		       "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
+		       gdb_num);
+
+	/*
+	 * If we are not using the primary superblock/GDT copy don't resize,
+         * because the user tools have no way of handling this.  Probably a
+         * bad time to do it anyways.
+         */
+	if (EXT4_SB(sb)->s_sbh->b_blocknr !=
+	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
+		ext4_warning(sb, "won't resize using backup superblock at %llu",
+			(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
+		return -EPERM;
+	}
+
+	*primary = sb_bread(sb, gdblock);
+	if (!*primary)
+		return -EIO;
+
+	if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) {
+		err = gdbackups;
+		goto exit_bh;
+	}
+
+	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
+	dind = sb_bread(sb, le32_to_cpu(*data));
+	if (!dind) {
+		err = -EIO;
+		goto exit_bh;
+	}
+
+	data = (__le32 *)dind->b_data;
+	if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
+		ext4_warning(sb, "new group %u GDT block %llu not reserved",
+			     input->group, gdblock);
+		err = -EINVAL;
+		goto exit_dind;
+	}
+
+	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+	if (unlikely(err))
+		goto exit_dind;
+
+	err = ext4_journal_get_write_access(handle, *primary);
+	if (unlikely(err))
+		goto exit_sbh;
+
+	err = ext4_journal_get_write_access(handle, dind);
+	if (unlikely(err))
+		ext4_std_error(sb, err);
+
+	/* ext4_reserve_inode_write() gets a reference on the iloc */
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (unlikely(err))
+		goto exit_dindj;
+
+	n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
+			GFP_NOFS);
+	if (!n_group_desc) {
+		err = -ENOMEM;
+		ext4_warning(sb,
+			      "not enough memory for %lu groups", gdb_num + 1);
+		goto exit_inode;
+	}
+
+	/*
+	 * Finally, we have all of the possible failures behind us...
+	 *
+	 * Remove new GDT block from inode double-indirect block and clear out
+	 * the new GDT block for use (which also "frees" the backup GDT blocks
+	 * from the reserved inode).  We don't need to change the bitmaps for
+	 * these blocks, because they are marked as in-use from being in the
+	 * reserved inode, and will become GDT blocks (primary and backup).
+	 */
+	data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
+	err = ext4_handle_dirty_metadata(handle, NULL, dind);
+	if (unlikely(err)) {
+		ext4_std_error(sb, err);
+		goto exit_inode;
+	}
+	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
+	ext4_mark_iloc_dirty(handle, inode, &iloc);
+	memset((*primary)->b_data, 0, sb->s_blocksize);
+	err = ext4_handle_dirty_metadata(handle, NULL, *primary);
+	if (unlikely(err)) {
+		ext4_std_error(sb, err);
+		goto exit_inode;
+	}
+	brelse(dind);
+
+	o_group_desc = EXT4_SB(sb)->s_group_desc;
+	memcpy(n_group_desc, o_group_desc,
+	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+	n_group_desc[gdb_num] = *primary;
+	EXT4_SB(sb)->s_group_desc = n_group_desc;
+	EXT4_SB(sb)->s_gdb_count++;
+	kfree(o_group_desc);
+
+	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
+	err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
+	if (err)
+		ext4_std_error(sb, err);
+
+	return err;
+
+exit_inode:
+	/* ext4_handle_release_buffer(handle, iloc.bh); */
+	brelse(iloc.bh);
+exit_dindj:
+	/* ext4_handle_release_buffer(handle, dind); */
+exit_sbh:
+	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
+exit_dind:
+	brelse(dind);
+exit_bh:
+	brelse(*primary);
+
+	ext4_debug("leaving with error %d\n", err);
+	return err;
+}
+
+/*
+ * Called when we are adding a new group which has a backup copy of each of
+ * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
+ * We need to add these reserved backup GDT blocks to the resize inode, so
+ * that they are kept for future resizing and not allocated to files.
+ *
+ * Each reserved backup GDT block will go into a different indirect block.
+ * The indirect blocks are actually the primary reserved GDT blocks,
+ * so we know in advance what their block numbers are.  We only get the
+ * double-indirect block to verify it is pointing to the primary reserved
+ * GDT blocks so we don't overwrite a data block by accident.  The reserved
+ * backup GDT blocks are stored in their reserved primary GDT block.
+ */
+static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
+			      struct ext4_new_group_data *input)
+{
+	struct super_block *sb = inode->i_sb;
+	int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
+	struct buffer_head **primary;
+	struct buffer_head *dind;
+	struct ext4_iloc iloc;
+	ext4_fsblk_t blk;
+	__le32 *data, *end;
+	int gdbackups = 0;
+	int res, i;
+	int err;
+
+	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_NOFS);
+	if (!primary)
+		return -ENOMEM;
+
+	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
+	dind = sb_bread(sb, le32_to_cpu(*data));
+	if (!dind) {
+		err = -EIO;
+		goto exit_free;
+	}
+
+	blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
+	data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
+					 EXT4_ADDR_PER_BLOCK(sb));
+	end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
+
+	/* Get each reserved primary GDT block and verify it holds backups */
+	for (res = 0; res < reserved_gdb; res++, blk++) {
+		if (le32_to_cpu(*data) != blk) {
+			ext4_warning(sb, "reserved block %llu"
+				     " not at offset %ld",
+				     blk,
+				     (long)(data - (__le32 *)dind->b_data));
+			err = -EINVAL;
+			goto exit_bh;
+		}
+		primary[res] = sb_bread(sb, blk);
+		if (!primary[res]) {
+			err = -EIO;
+			goto exit_bh;
+		}
+		if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) {
+			brelse(primary[res]);
+			err = gdbackups;
+			goto exit_bh;
+		}
+		if (++data >= end)
+			data = (__le32 *)dind->b_data;
+	}
+
+	for (i = 0; i < reserved_gdb; i++) {
+		if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
+			/*
+			int j;
+			for (j = 0; j < i; j++)
+				ext4_handle_release_buffer(handle, primary[j]);
+			 */
+			goto exit_bh;
+		}
+	}
+
+	if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
+		goto exit_bh;
+
+	/*
+	 * Finally we can add each of the reserved backup GDT blocks from
+	 * the new group to its reserved primary GDT block.
+	 */
+	blk = input->group * EXT4_BLOCKS_PER_GROUP(sb);
+	for (i = 0; i < reserved_gdb; i++) {
+		int err2;
+		data = (__le32 *)primary[i]->b_data;
+		/* printk("reserving backup %lu[%u] = %lu\n",
+		       primary[i]->b_blocknr, gdbackups,
+		       blk + primary[i]->b_blocknr); */
+		data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
+		err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
+		if (!err)
+			err = err2;
+	}
+	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
+	ext4_mark_iloc_dirty(handle, inode, &iloc);
+
+exit_bh:
+	while (--res >= 0)
+		brelse(primary[res]);
+	brelse(dind);
+
+exit_free:
+	kfree(primary);
+
+	return err;
+}
+
+/*
+ * Update the backup copies of the ext4 metadata.  These don't need to be part
+ * of the main resize transaction, because e2fsck will re-write them if there
+ * is a problem (basically only OOM will cause a problem).  However, we
+ * _should_ update the backups if possible, in case the primary gets trashed
+ * for some reason and we need to run e2fsck from a backup superblock.  The
+ * important part is that the new block and inode counts are in the backup
+ * superblocks, and the location of the new group metadata in the GDT backups.
+ *
+ * We do not need take the s_resize_lock for this, because these
+ * blocks are not otherwise touched by the filesystem code when it is
+ * mounted.  We don't need to worry about last changing from
+ * sbi->s_groups_count, because the worst that can happen is that we
+ * do not copy the full number of backups at this time.  The resize
+ * which changed s_groups_count will backup again.
+ */
+static void update_backups(struct super_block *sb,
+			   int blk_off, char *data, int size)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	const ext4_group_t last = sbi->s_groups_count;
+	const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
+	unsigned three = 1;
+	unsigned five = 5;
+	unsigned seven = 7;
+	ext4_group_t group;
+	int rest = sb->s_blocksize - size;
+	handle_t *handle;
+	int err = 0, err2;
+
+	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
+	if (IS_ERR(handle)) {
+		group = 1;
+		err = PTR_ERR(handle);
+		goto exit_err;
+	}
+
+	while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) {
+		struct buffer_head *bh;
+
+		/* Out of journal space, and can't get more - abort - so sad */
+		if (ext4_handle_valid(handle) &&
+		    handle->h_buffer_credits == 0 &&
+		    ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
+		    (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
+			break;
+
+		bh = sb_getblk(sb, group * bpg + blk_off);
+		if (!bh) {
+			err = -EIO;
+			break;
+		}
+		ext4_debug("update metadata backup %#04lx\n",
+			  (unsigned long)bh->b_blocknr);
+		if ((err = ext4_journal_get_write_access(handle, bh)))
+			break;
+		lock_buffer(bh);
+		memcpy(bh->b_data, data, size);
+		if (rest)
+			memset(bh->b_data + size, 0, rest);
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		if (unlikely(err))
+			ext4_std_error(sb, err);
+		brelse(bh);
+	}
+	if ((err2 = ext4_journal_stop(handle)) && !err)
+		err = err2;
+
+	/*
+	 * Ugh! Need to have e2fsck write the backup copies.  It is too
+	 * late to revert the resize, we shouldn't fail just because of
+	 * the backup copies (they are only needed in case of corruption).
+	 *
+	 * However, if we got here we have a journal problem too, so we
+	 * can't really start a transaction to mark the superblock.
+	 * Chicken out and just set the flag on the hope it will be written
+	 * to disk, and if not - we will simply wait until next fsck.
+	 */
+exit_err:
+	if (err) {
+		ext4_warning(sb, "can't update backup for group %u (err %d), "
+			     "forcing fsck on next reboot", group, err);
+		sbi->s_mount_state &= ~EXT4_VALID_FS;
+		sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
+		mark_buffer_dirty(sbi->s_sbh);
+	}
+}
+
+/* Add group descriptor data to an existing or new group descriptor block.
+ * Ensure we handle all possible error conditions _before_ we start modifying
+ * the filesystem, because we cannot abort the transaction and not have it
+ * write the data to disk.
+ *
+ * If we are on a GDT block boundary, we need to get the reserved GDT block.
+ * Otherwise, we may need to add backup GDT blocks for a sparse group.
+ *
+ * We only need to hold the superblock lock while we are actually adding
+ * in the new group's counts to the superblock.  Prior to that we have
+ * not really "added" the group at all.  We re-check that we are still
+ * adding in the last group in case things have changed since verifying.
+ */
+int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
+		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
+	struct buffer_head *primary = NULL;
+	struct ext4_group_desc *gdp;
+	struct inode *inode = NULL;
+	handle_t *handle;
+	int gdb_off, gdb_num;
+	int err, err2;
+
+	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
+	gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
+
+	if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
+		ext4_warning(sb, "Can't resize non-sparse filesystem further");
+		return -EPERM;
+	}
+
+	if (ext4_blocks_count(es) + input->blocks_count <
+	    ext4_blocks_count(es)) {
+		ext4_warning(sb, "blocks_count overflow");
+		return -EINVAL;
+	}
+
+	if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_warning(sb, "inodes_count overflow");
+		return -EINVAL;
+	}
+
+	if (reserved_gdb || gdb_off == 0) {
+		if (!EXT4_HAS_COMPAT_FEATURE(sb,
+					     EXT4_FEATURE_COMPAT_RESIZE_INODE)
+		    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
+			ext4_warning(sb,
+				     "No reserved GDT blocks, can't resize");
+			return -EPERM;
+		}
+		inode = ext4_iget(sb, EXT4_RESIZE_INO);
+		if (IS_ERR(inode)) {
+			ext4_warning(sb, "Error opening resize inode");
+			return PTR_ERR(inode);
+		}
+	}
+
+
+	if ((err = verify_group_input(sb, input)))
+		goto exit_put;
+
+	if ((err = setup_new_group_blocks(sb, input)))
+		goto exit_put;
+
+	/*
+	 * We will always be modifying at least the superblock and a GDT
+	 * block.  If we are adding a group past the last current GDT block,
+	 * we will also modify the inode and the dindirect block.  If we
+	 * are adding a group with superblock/GDT backups  we will also
+	 * modify each of the reserved GDT dindirect blocks.
+	 */
+	handle = ext4_journal_start_sb(sb,
+				       ext4_bg_has_super(sb, input->group) ?
+				       3 + reserved_gdb : 4);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto exit_put;
+	}
+
+	mutex_lock(&sbi->s_resize_lock);
+	if (input->group != sbi->s_groups_count) {
+		ext4_warning(sb, "multiple resizers run on filesystem!");
+		err = -EBUSY;
+		goto exit_journal;
+	}
+
+	if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh)))
+		goto exit_journal;
+
+        /*
+         * We will only either add reserved group blocks to a backup group
+         * or remove reserved blocks for the first group in a new group block.
+         * Doing both would be mean more complex code, and sane people don't
+         * use non-sparse filesystems anymore.  This is already checked above.
+         */
+	if (gdb_off) {
+		primary = sbi->s_group_desc[gdb_num];
+		if ((err = ext4_journal_get_write_access(handle, primary)))
+			goto exit_journal;
+
+		if (reserved_gdb && ext4_bg_num_gdb(sb, input->group) &&
+		    (err = reserve_backup_gdb(handle, inode, input)))
+			goto exit_journal;
+	} else if ((err = add_new_gdb(handle, inode, input, &primary)))
+		goto exit_journal;
+
+        /*
+         * OK, now we've set up the new group.  Time to make it active.
+         *
+         * We do not lock all allocations via s_resize_lock
+         * so we have to be safe wrt. concurrent accesses the group
+         * data.  So we need to be careful to set all of the relevant
+         * group descriptor data etc. *before* we enable the group.
+         *
+         * The key field here is sbi->s_groups_count: as long as
+         * that retains its old value, nobody is going to access the new
+         * group.
+         *
+         * So first we update all the descriptor metadata for the new
+         * group; then we update the total disk blocks count; then we
+         * update the groups count to enable the group; then finally we
+         * update the free space counts so that the system can start
+         * using the new disk blocks.
+         */
+
+	/* Update group descriptor block for new group */
+	gdp = (struct ext4_group_desc *)((char *)primary->b_data +
+					 gdb_off * EXT4_DESC_SIZE(sb));
+
+	memset(gdp, 0, EXT4_DESC_SIZE(sb));
+	ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
+	ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
+	ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
+	ext4_free_blks_set(sb, gdp, input->free_blocks_count);
+	ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
+	gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
+
+	/*
+	 * We can allocate memory for mb_alloc based on the new group
+	 * descriptor
+	 */
+	err = ext4_mb_add_groupinfo(sb, input->group, gdp);
+	if (err)
+		goto exit_journal;
+
+	/*
+	 * Make the new blocks and inodes valid next.  We do this before
+	 * increasing the group count so that once the group is enabled,
+	 * all of its blocks and inodes are already valid.
+	 *
+	 * We always allocate group-by-group, then block-by-block or
+	 * inode-by-inode within a group, so enabling these
+	 * blocks/inodes before the group is live won't actually let us
+	 * allocate the new space yet.
+	 */
+	ext4_blocks_count_set(es, ext4_blocks_count(es) +
+		input->blocks_count);
+	le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb));
+
+	/*
+	 * We need to protect s_groups_count against other CPUs seeing
+	 * inconsistent state in the superblock.
+	 *
+	 * The precise rules we use are:
+	 *
+	 * * Writers of s_groups_count *must* hold s_resize_lock
+	 * AND
+	 * * Writers must perform a smp_wmb() after updating all dependent
+	 *   data and before modifying the groups count
+	 *
+	 * * Readers must hold s_resize_lock over the access
+	 * OR
+	 * * Readers must perform an smp_rmb() after reading the groups count
+	 *   and before reading any dependent data.
+	 *
+	 * NB. These rules can be relaxed when checking the group count
+	 * while freeing data, as we can only allocate from a block
+	 * group after serialising against the group count, and we can
+	 * only then free after serialising in turn against that
+	 * allocation.
+	 */
+	smp_wmb();
+
+	/* Update the global fs size fields */
+	sbi->s_groups_count++;
+
+	err = ext4_handle_dirty_metadata(handle, NULL, primary);
+	if (unlikely(err)) {
+		ext4_std_error(sb, err);
+		goto exit_journal;
+	}
+
+	/* Update the reserved block counts only once the new group is
+	 * active. */
+	ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
+		input->reserved_blocks);
+
+	/* Update the free space counts */
+	percpu_counter_add(&sbi->s_freeblocks_counter,
+			   input->free_blocks_count);
+	percpu_counter_add(&sbi->s_freeinodes_counter,
+			   EXT4_INODES_PER_GROUP(sb));
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
+	    sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group;
+		flex_group = ext4_flex_group(sbi, input->group);
+		atomic_add(input->free_blocks_count,
+			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic_add(EXT4_INODES_PER_GROUP(sb),
+			   &sbi->s_flex_groups[flex_group].free_inodes);
+	}
+
+	ext4_handle_dirty_super(handle, sb);
+
+exit_journal:
+	mutex_unlock(&sbi->s_resize_lock);
+	if ((err2 = ext4_journal_stop(handle)) && !err)
+		err = err2;
+	if (!err) {
+		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
+			       sizeof(struct ext4_super_block));
+		update_backups(sb, primary->b_blocknr, primary->b_data,
+			       primary->b_size);
+	}
+exit_put:
+	iput(inode);
+	return err;
+} /* ext4_group_add */
+
+/*
+ * Extend the filesystem to the new number of blocks specified.  This entry
+ * point is only used to extend the current filesystem to the end of the last
+ * existing group.  It can be accessed via ioctl, or by "remount,resize=<size>"
+ * for emergencies (because it has no dependencies on reserved blocks).
+ *
+ * If we _really_ wanted, we could use default values to call ext4_group_add()
+ * allow the "remount" trick to work for arbitrary resizing, assuming enough
+ * GDT blocks are reserved to grow to the desired size.
+ */
+int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
+		      ext4_fsblk_t n_blocks_count)
+{
+	ext4_fsblk_t o_blocks_count;
+	ext4_grpblk_t last;
+	ext4_grpblk_t add;
+	struct buffer_head *bh;
+	handle_t *handle;
+	int err;
+	ext4_group_t group;
+
+	/* We don't need to worry about locking wrt other resizers just
+	 * yet: we're going to revalidate es->s_blocks_count after
+	 * taking the s_resize_lock below. */
+	o_blocks_count = ext4_blocks_count(es);
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT4-fs: extending last group from %llu uto %llu blocks\n",
+		       o_blocks_count, n_blocks_count);
+
+	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
+		return 0;
+
+	if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+		printk(KERN_ERR "EXT4-fs: filesystem on %s:"
+			" too large to resize to %llu blocks safely\n",
+			sb->s_id, n_blocks_count);
+		if (sizeof(sector_t) < 8)
+			ext4_warning(sb, "CONFIG_LBDAF not enabled");
+		return -EINVAL;
+	}
+
+	if (n_blocks_count < o_blocks_count) {
+		ext4_warning(sb, "can't shrink FS - resize aborted");
+		return -EBUSY;
+	}
+
+	/* Handle the remaining blocks in the last group only. */
+	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
+
+	if (last == 0) {
+		ext4_warning(sb, "need to use ext2online to resize further");
+		return -EPERM;
+	}
+
+	add = EXT4_BLOCKS_PER_GROUP(sb) - last;
+
+	if (o_blocks_count + add < o_blocks_count) {
+		ext4_warning(sb, "blocks_count overflow");
+		return -EINVAL;
+	}
+
+	if (o_blocks_count + add > n_blocks_count)
+		add = n_blocks_count - o_blocks_count;
+
+	if (o_blocks_count + add < n_blocks_count)
+		ext4_warning(sb, "will only finish group (%llu blocks, %u new)",
+			     o_blocks_count + add, add);
+
+	/* See if the device is actually as big as what was requested */
+	bh = sb_bread(sb, o_blocks_count + add - 1);
+	if (!bh) {
+		ext4_warning(sb, "can't read last block, resize aborted");
+		return -ENOSPC;
+	}
+	brelse(bh);
+
+	/* We will update the superblock, one block bitmap, and
+	 * one group descriptor via ext4_free_blocks().
+	 */
+	handle = ext4_journal_start_sb(sb, 3);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		ext4_warning(sb, "error %d on journal start", err);
+		goto exit_put;
+	}
+
+	mutex_lock(&EXT4_SB(sb)->s_resize_lock);
+	if (o_blocks_count != ext4_blocks_count(es)) {
+		ext4_warning(sb, "multiple resizers run on filesystem!");
+		mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
+		ext4_journal_stop(handle);
+		err = -EBUSY;
+		goto exit_put;
+	}
+
+	if ((err = ext4_journal_get_write_access(handle,
+						 EXT4_SB(sb)->s_sbh))) {
+		ext4_warning(sb, "error %d on journal write access", err);
+		mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
+		ext4_journal_stop(handle);
+		goto exit_put;
+	}
+	ext4_blocks_count_set(es, o_blocks_count + add);
+	mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
+	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
+		   o_blocks_count + add);
+	/* We add the blocks to the bitmap and set the group need init bit */
+	ext4_add_groupblocks(handle, sb, o_blocks_count, add);
+	ext4_handle_dirty_super(handle, sb);
+	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
+		   o_blocks_count + add);
+	if ((err = ext4_journal_stop(handle)))
+		goto exit_put;
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n",
+		       ext4_blocks_count(es));
+	update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
+		       sizeof(struct ext4_super_block));
+exit_put:
+	return err;
+} /* ext4_group_extend */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
new file mode 100644
index 00000000..113b1076
--- /dev/null
+++ b/fs/ext4/super.c
@@ -0,0 +1,5027 @@
+/*
+ *  linux/fs/ext4/super.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/inode.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/vmalloc.h>
+#include <linux/jbd2.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/parser.h>
+#include <linux/buffer_head.h>
+#include <linux/exportfs.h>
+#include <linux/vfs.h>
+#include <linux/random.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/ctype.h>
+#include <linux/log2.h>
+#include <linux/crc16.h>
+#include <linux/cleancache.h>
+#include <asm/uaccess.h>
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "mballoc.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/ext4.h>
+
+static struct proc_dir_entry *ext4_proc_root;
+static struct kset *ext4_kset;
+static struct ext4_lazy_init *ext4_li_info;
+static struct mutex ext4_li_mtx;
+static struct ext4_features *ext4_feat;
+
+static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
+			     unsigned long journal_devnum);
+static int ext4_commit_super(struct super_block *sb, int sync);
+static void ext4_mark_recovery_complete(struct super_block *sb,
+					struct ext4_super_block *es);
+static void ext4_clear_journal_err(struct super_block *sb,
+				   struct ext4_super_block *es);
+static int ext4_sync_fs(struct super_block *sb, int wait);
+static const char *ext4_decode_error(struct super_block *sb, int errno,
+				     char nbuf[16]);
+static int ext4_remount(struct super_block *sb, int *flags, char *data);
+static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
+static int ext4_unfreeze(struct super_block *sb);
+static void ext4_write_super(struct super_block *sb);
+static int ext4_freeze(struct super_block *sb);
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data);
+static inline int ext2_feature_set_ok(struct super_block *sb);
+static inline int ext3_feature_set_ok(struct super_block *sb);
+static int ext4_feature_set_ok(struct super_block *sb, int readonly);
+static void ext4_destroy_lazyinit_thread(void);
+static void ext4_unregister_li_request(struct super_block *sb);
+static void ext4_clear_request_list(void);
+
+#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext2_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext2",
+	.mount		= ext4_mount,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
+#else
+#define IS_EXT2_SB(sb) (0)
+#endif
+
+
+#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext3_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext3",
+	.mount		= ext4_mount,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
+#else
+#define IS_EXT3_SB(sb) (0)
+#endif
+
+ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
+			       struct ext4_group_desc *bg)
+{
+	return le32_to_cpu(bg->bg_block_bitmap_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
+}
+
+ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
+			       struct ext4_group_desc *bg)
+{
+	return le32_to_cpu(bg->bg_inode_bitmap_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
+}
+
+ext4_fsblk_t ext4_inode_table(struct super_block *sb,
+			      struct ext4_group_desc *bg)
+{
+	return le32_to_cpu(bg->bg_inode_table_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
+}
+
+__u32 ext4_free_blks_count(struct super_block *sb,
+			      struct ext4_group_desc *bg)
+{
+	return le16_to_cpu(bg->bg_free_blocks_count_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
+}
+
+__u32 ext4_free_inodes_count(struct super_block *sb,
+			      struct ext4_group_desc *bg)
+{
+	return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+}
+
+__u32 ext4_used_dirs_count(struct super_block *sb,
+			      struct ext4_group_desc *bg)
+{
+	return le16_to_cpu(bg->bg_used_dirs_count_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
+}
+
+__u32 ext4_itable_unused_count(struct super_block *sb,
+			      struct ext4_group_desc *bg)
+{
+	return le16_to_cpu(bg->bg_itable_unused_lo) |
+		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+		 (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
+}
+
+void ext4_block_bitmap_set(struct super_block *sb,
+			   struct ext4_group_desc *bg, ext4_fsblk_t blk)
+{
+	bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
+}
+
+void ext4_inode_bitmap_set(struct super_block *sb,
+			   struct ext4_group_desc *bg, ext4_fsblk_t blk)
+{
+	bg->bg_inode_bitmap_lo  = cpu_to_le32((u32)blk);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
+}
+
+void ext4_inode_table_set(struct super_block *sb,
+			  struct ext4_group_desc *bg, ext4_fsblk_t blk)
+{
+	bg->bg_inode_table_lo = cpu_to_le32((u32)blk);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
+}
+
+void ext4_free_blks_set(struct super_block *sb,
+			  struct ext4_group_desc *bg, __u32 count)
+{
+	bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
+}
+
+void ext4_free_inodes_set(struct super_block *sb,
+			  struct ext4_group_desc *bg, __u32 count)
+{
+	bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+}
+
+void ext4_used_dirs_set(struct super_block *sb,
+			  struct ext4_group_desc *bg, __u32 count)
+{
+	bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
+}
+
+void ext4_itable_unused_set(struct super_block *sb,
+			  struct ext4_group_desc *bg, __u32 count)
+{
+	bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
+	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
+}
+
+
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+	handle_t *handle = current->journal_info;
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
+
+	ref_cnt++;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+	return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt == 0);
+
+	ref_cnt--;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+}
+
+/*
+ * Wrappers for jbd2_journal_start/end.
+ *
+ * The only special thing we need to do here is to make sure that all
+ * journal_end calls result in the superblock being marked dirty, so
+ * that sync() will call the filesystem's write_super callback if
+ * appropriate.
+ *
+ * To avoid j_barrier hold in userspace when a user calls freeze(),
+ * ext4 prevents a new handle from being started by s_frozen, which
+ * is in an upper layer.
+ */
+handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
+{
+	journal_t *journal;
+	handle_t  *handle;
+
+	if (sb->s_flags & MS_RDONLY)
+		return ERR_PTR(-EROFS);
+
+	journal = EXT4_SB(sb)->s_journal;
+	handle = ext4_journal_current_handle();
+
+	/*
+	 * If a handle has been started, it should be allowed to
+	 * finish, otherwise deadlock could happen between freeze
+	 * and others(e.g. truncate) due to the restart of the
+	 * journal handle if the filesystem is forzen and active
+	 * handles are not stopped.
+	 */
+	if (!handle)
+		vfs_check_frozen(sb, SB_FREEZE_TRANS);
+
+	if (!journal)
+		return ext4_get_nojournal();
+	/*
+	 * Special case here: if the journal has aborted behind our
+	 * backs (eg. EIO in the commit thread), then we still need to
+	 * take the FS itself readonly cleanly.
+	 */
+	if (is_journal_aborted(journal)) {
+		ext4_abort(sb, "Detected aborted journal");
+		return ERR_PTR(-EROFS);
+	}
+	return jbd2_journal_start(journal, nblocks);
+}
+
+/*
+ * The only special thing we need to do here is to make sure that all
+ * jbd2_journal_stop calls result in the superblock being marked dirty, so
+ * that sync() will call the filesystem's write_super callback if
+ * appropriate.
+ */
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
+{
+	struct super_block *sb;
+	int err;
+	int rc;
+
+	if (!ext4_handle_valid(handle)) {
+		ext4_put_nojournal(handle);
+		return 0;
+	}
+	sb = handle->h_transaction->t_journal->j_private;
+	err = handle->h_err;
+	rc = jbd2_journal_stop(handle);
+
+	if (!err)
+		err = rc;
+	if (err)
+		__ext4_std_error(sb, where, line, err);
+	return err;
+}
+
+void ext4_journal_abort_handle(const char *caller, unsigned int line,
+			       const char *err_fn, struct buffer_head *bh,
+			       handle_t *handle, int err)
+{
+	char nbuf[16];
+	const char *errstr = ext4_decode_error(NULL, err, nbuf);
+
+	BUG_ON(!ext4_handle_valid(handle));
+
+	if (bh)
+		BUFFER_TRACE(bh, "abort");
+
+	if (!handle->h_err)
+		handle->h_err = err;
+
+	if (is_handle_aborted(handle))
+		return;
+
+	printk(KERN_ERR "%s:%d: aborting transaction: %s in %s\n",
+	       caller, line, errstr, err_fn);
+
+	jbd2_journal_abort_handle(handle);
+}
+
+static void __save_error_info(struct super_block *sb, const char *func,
+			    unsigned int line)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+	es->s_last_error_time = cpu_to_le32(get_seconds());
+	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
+	es->s_last_error_line = cpu_to_le32(line);
+	if (!es->s_first_error_time) {
+		es->s_first_error_time = es->s_last_error_time;
+		strncpy(es->s_first_error_func, func,
+			sizeof(es->s_first_error_func));
+		es->s_first_error_line = cpu_to_le32(line);
+		es->s_first_error_ino = es->s_last_error_ino;
+		es->s_first_error_block = es->s_last_error_block;
+	}
+	/*
+	 * Start the daily error reporting function if it hasn't been
+	 * started already
+	 */
+	if (!es->s_error_count)
+		mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
+	es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
+}
+
+static void save_error_info(struct super_block *sb, const char *func,
+			    unsigned int line)
+{
+	__save_error_info(sb, func, line);
+	ext4_commit_super(sb, 1);
+}
+
+
+/* Deal with the reporting of failure conditions on a filesystem such as
+ * inconsistencies detected or read IO failures.
+ *
+ * On ext2, we can store the error state of the filesystem in the
+ * superblock.  That is not possible on ext4, because we may have other
+ * write ordering constraints on the superblock which prevent us from
+ * writing it out straight away; and given that the journal is about to
+ * be aborted, we can't rely on the current, or future, transactions to
+ * write out the superblock safely.
+ *
+ * We'll just use the jbd2_journal_abort() error code to record an error in
+ * the journal instead.  On recovery, the journal will complain about
+ * that error until we've noted it down and cleared it.
+ */
+
+static void ext4_handle_error(struct super_block *sb)
+{
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	if (!test_opt(sb, ERRORS_CONT)) {
+		journal_t *journal = EXT4_SB(sb)->s_journal;
+
+		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		if (journal)
+			jbd2_journal_abort(journal, -EIO);
+	}
+	if (test_opt(sb, ERRORS_RO)) {
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+		sb->s_flags |= MS_RDONLY;
+	}
+	if (test_opt(sb, ERRORS_PANIC))
+		panic("EXT4-fs (device %s): panic forced after error\n",
+			sb->s_id);
+}
+
+void __ext4_error(struct super_block *sb, const char *function,
+		  unsigned int line, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
+	       sb->s_id, function, line, current->comm, &vaf);
+	va_end(args);
+	save_error_info(sb, function, line);
+
+	ext4_handle_error(sb);
+}
+
+void ext4_error_inode(struct inode *inode, const char *function,
+		      unsigned int line, ext4_fsblk_t block,
+		      const char *fmt, ...)
+{
+	va_list args;
+	struct va_format vaf;
+	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+
+	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+	es->s_last_error_block = cpu_to_le64(block);
+	save_error_info(inode->i_sb, function, line);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
+	       inode->i_sb->s_id, function, line, inode->i_ino);
+	if (block)
+		printk(KERN_CONT "block %llu: ", block);
+	printk(KERN_CONT "comm %s: %pV\n", current->comm, &vaf);
+	va_end(args);
+
+	ext4_handle_error(inode->i_sb);
+}
+
+void ext4_error_file(struct file *file, const char *function,
+		     unsigned int line, ext4_fsblk_t block,
+		     const char *fmt, ...)
+{
+	va_list args;
+	struct va_format vaf;
+	struct ext4_super_block *es;
+	struct inode *inode = file->f_dentry->d_inode;
+	char pathname[80], *path;
+
+	es = EXT4_SB(inode->i_sb)->s_es;
+	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+	save_error_info(inode->i_sb, function, line);
+	path = d_path(&(file->f_path), pathname, sizeof(pathname));
+	if (IS_ERR(path))
+		path = "(unknown)";
+	printk(KERN_CRIT
+	       "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
+	       inode->i_sb->s_id, function, line, inode->i_ino);
+	if (block)
+		printk(KERN_CONT "block %llu: ", block);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk(KERN_CONT "comm %s: path %s: %pV\n", current->comm, path, &vaf);
+	va_end(args);
+
+	ext4_handle_error(inode->i_sb);
+}
+
+static const char *ext4_decode_error(struct super_block *sb, int errno,
+				     char nbuf[16])
+{
+	char *errstr = NULL;
+
+	switch (errno) {
+	case -EIO:
+		errstr = "IO failure";
+		break;
+	case -ENOMEM:
+		errstr = "Out of memory";
+		break;
+	case -EROFS:
+		if (!sb || (EXT4_SB(sb)->s_journal &&
+			    EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT))
+			errstr = "Journal has aborted";
+		else
+			errstr = "Readonly filesystem";
+		break;
+	default:
+		/* If the caller passed in an extra buffer for unknown
+		 * errors, textualise them now.  Else we just return
+		 * NULL. */
+		if (nbuf) {
+			/* Check for truncated error codes... */
+			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
+				errstr = nbuf;
+		}
+		break;
+	}
+
+	return errstr;
+}
+
+/* __ext4_std_error decodes expected errors from journaling functions
+ * automatically and invokes the appropriate error response.  */
+
+void __ext4_std_error(struct super_block *sb, const char *function,
+		      unsigned int line, int errno)
+{
+	char nbuf[16];
+	const char *errstr;
+
+	/* Special case: if the error is EROFS, and we're not already
+	 * inside a transaction, then there's really no point in logging
+	 * an error. */
+	if (errno == -EROFS && journal_current_handle() == NULL &&
+	    (sb->s_flags & MS_RDONLY))
+		return;
+
+	errstr = ext4_decode_error(sb, errno, nbuf);
+	printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
+	       sb->s_id, function, line, errstr);
+	save_error_info(sb, function, line);
+
+	ext4_handle_error(sb);
+}
+
+/*
+ * ext4_abort is a much stronger failure handler than ext4_error.  The
+ * abort function may be used to deal with unrecoverable failures such
+ * as journal IO errors or ENOMEM at a critical moment in log management.
+ *
+ * We unconditionally force the filesystem into an ABORT|READONLY state,
+ * unless the error response on the fs has been set to panic in which
+ * case we take the easy way out and panic immediately.
+ */
+
+void __ext4_abort(struct super_block *sb, const char *function,
+		unsigned int line, const char *fmt, ...)
+{
+	va_list args;
+
+	save_error_info(sb, function, line);
+	va_start(args, fmt);
+	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
+	       function, line);
+	vprintk(fmt, args);
+	printk("\n");
+	va_end(args);
+
+	if ((sb->s_flags & MS_RDONLY) == 0) {
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+		sb->s_flags |= MS_RDONLY;
+		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		if (EXT4_SB(sb)->s_journal)
+			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+		save_error_info(sb, function, line);
+	}
+	if (test_opt(sb, ERRORS_PANIC))
+		panic("EXT4-fs panic from previous error\n");
+}
+
+void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
+	va_end(args);
+}
+
+void __ext4_warning(struct super_block *sb, const char *function,
+		    unsigned int line, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n",
+	       sb->s_id, function, line, &vaf);
+	va_end(args);
+}
+
+void __ext4_grp_locked_error(const char *function, unsigned int line,
+			     struct super_block *sb, ext4_group_t grp,
+			     unsigned long ino, ext4_fsblk_t block,
+			     const char *fmt, ...)
+__releases(bitlock)
+__acquires(bitlock)
+{
+	struct va_format vaf;
+	va_list args;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	es->s_last_error_ino = cpu_to_le32(ino);
+	es->s_last_error_block = cpu_to_le64(block);
+	__save_error_info(sb, function, line);
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
+	       sb->s_id, function, line, grp);
+	if (ino)
+		printk(KERN_CONT "inode %lu: ", ino);
+	if (block)
+		printk(KERN_CONT "block %llu:", (unsigned long long) block);
+	printk(KERN_CONT "%pV\n", &vaf);
+	va_end(args);
+
+	if (test_opt(sb, ERRORS_CONT)) {
+		ext4_commit_super(sb, 0);
+		return;
+	}
+
+	ext4_unlock_group(sb, grp);
+	ext4_handle_error(sb);
+	/*
+	 * We only get here in the ERRORS_RO case; relocking the group
+	 * may be dangerous, but nothing bad will happen since the
+	 * filesystem will have already been marked read/only and the
+	 * journal has been aborted.  We return 1 as a hint to callers
+	 * who might what to use the return value from
+	 * ext4_grp_locked_error() to distinguish between the
+	 * ERRORS_CONT and ERRORS_RO case, and perhaps return more
+	 * aggressively from the ext4 function in question, with a
+	 * more appropriate error code.
+	 */
+	ext4_lock_group(sb, grp);
+	return;
+}
+
+void ext4_update_dynamic_rev(struct super_block *sb)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
+		return;
+
+	ext4_warning(sb,
+		     "updating to rev %d because of new feature flag, "
+		     "running e2fsck is recommended",
+		     EXT4_DYNAMIC_REV);
+
+	es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO);
+	es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE);
+	es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV);
+	/* leave es->s_feature_*compat flags alone */
+	/* es->s_uuid will be set by e2fsck if empty */
+
+	/*
+	 * The rest of the superblock fields should be zero, and if not it
+	 * means they are likely already in use, so leave them alone.  We
+	 * can leave it up to e2fsck to clean up any inconsistencies there.
+	 */
+}
+
+/*
+ * Open the external journal device
+ */
+static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
+{
+	struct block_device *bdev;
+	char b[BDEVNAME_SIZE];
+
+	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
+	if (IS_ERR(bdev))
+		goto fail;
+	return bdev;
+
+fail:
+	ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
+			__bdevname(dev, b), PTR_ERR(bdev));
+	return NULL;
+}
+
+/*
+ * Release the journal device
+ */
+static int ext4_blkdev_put(struct block_device *bdev)
+{
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+}
+
+static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
+{
+	struct block_device *bdev;
+	int ret = -ENODEV;
+
+	bdev = sbi->journal_bdev;
+	if (bdev) {
+		ret = ext4_blkdev_put(bdev);
+		sbi->journal_bdev = NULL;
+	}
+	return ret;
+}
+
+static inline struct inode *orphan_list_entry(struct list_head *l)
+{
+	return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode;
+}
+
+static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
+{
+	struct list_head *l;
+
+	ext4_msg(sb, KERN_ERR, "sb orphan head is %d",
+		 le32_to_cpu(sbi->s_es->s_last_orphan));
+
+	printk(KERN_ERR "sb_info orphan list:\n");
+	list_for_each(l, &sbi->s_orphan) {
+		struct inode *inode = orphan_list_entry(l);
+		printk(KERN_ERR "  "
+		       "inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
+		       inode->i_sb->s_id, inode->i_ino, inode,
+		       inode->i_mode, inode->i_nlink,
+		       NEXT_ORPHAN(inode));
+	}
+}
+
+static void ext4_put_super(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	int i, err;
+
+	ext4_unregister_li_request(sb);
+	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+
+	flush_workqueue(sbi->dio_unwritten_wq);
+	destroy_workqueue(sbi->dio_unwritten_wq);
+
+	lock_super(sb);
+	if (sb->s_dirt)
+		ext4_commit_super(sb, 1);
+
+	if (sbi->s_journal) {
+		err = jbd2_journal_destroy(sbi->s_journal);
+		sbi->s_journal = NULL;
+		if (err < 0)
+			ext4_abort(sb, "Couldn't clean up the journal");
+	}
+
+	del_timer(&sbi->s_err_report);
+	ext4_release_system_zone(sb);
+	ext4_mb_release(sb);
+	ext4_ext_release(sb);
+	ext4_xattr_put_super(sb);
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+		es->s_state = cpu_to_le16(sbi->s_mount_state);
+		ext4_commit_super(sb, 1);
+	}
+	if (sbi->s_proc) {
+		remove_proc_entry(sb->s_id, ext4_proc_root);
+	}
+	kobject_del(&sbi->s_kobj);
+
+	for (i = 0; i < sbi->s_gdb_count; i++)
+		brelse(sbi->s_group_desc[i]);
+	kfree(sbi->s_group_desc);
+	if (is_vmalloc_addr(sbi->s_flex_groups))
+		vfree(sbi->s_flex_groups);
+	else
+		kfree(sbi->s_flex_groups);
+	percpu_counter_destroy(&sbi->s_freeblocks_counter);
+	percpu_counter_destroy(&sbi->s_freeinodes_counter);
+	percpu_counter_destroy(&sbi->s_dirs_counter);
+	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+	brelse(sbi->s_sbh);
+#ifdef CONFIG_QUOTA
+	for (i = 0; i < MAXQUOTAS; i++)
+		kfree(sbi->s_qf_names[i]);
+#endif
+
+	/* Debugging code just in case the in-memory inode orphan list
+	 * isn't empty.  The on-disk one can be non-empty if we've
+	 * detected an error and taken the fs readonly, but the
+	 * in-memory list had better be clean by this point. */
+	if (!list_empty(&sbi->s_orphan))
+		dump_orphan_list(sb, sbi);
+	J_ASSERT(list_empty(&sbi->s_orphan));
+
+	invalidate_bdev(sb->s_bdev);
+	if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
+		/*
+		 * Invalidate the journal device's buffers.  We don't want them
+		 * floating about in memory - the physical journal device may
+		 * hotswapped, and it breaks the `ro-after' testing code.
+		 */
+		sync_blockdev(sbi->journal_bdev);
+		invalidate_bdev(sbi->journal_bdev);
+		ext4_blkdev_remove(sbi);
+	}
+	if (sbi->s_mmp_tsk)
+		kthread_stop(sbi->s_mmp_tsk);
+	sb->s_fs_info = NULL;
+	/*
+	 * Now that we are completely done shutting down the
+	 * superblock, we need to actually destroy the kobject.
+	 */
+	unlock_super(sb);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
+	kfree(sbi->s_blockgroup_lock);
+	kfree(sbi);
+}
+
+static struct kmem_cache *ext4_inode_cachep;
+
+/*
+ * Called inside transaction, so use GFP_NOFS
+ */
+static struct inode *ext4_alloc_inode(struct super_block *sb)
+{
+	struct ext4_inode_info *ei;
+
+	ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
+	if (!ei)
+		return NULL;
+
+	ei->vfs_inode.i_version = 1;
+	ei->vfs_inode.i_data.writeback_index = 0;
+	memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
+	INIT_LIST_HEAD(&ei->i_prealloc_list);
+	spin_lock_init(&ei->i_prealloc_lock);
+	ei->i_reserved_data_blocks = 0;
+	ei->i_reserved_meta_blocks = 0;
+	ei->i_allocated_meta_blocks = 0;
+	ei->i_da_metadata_calc_len = 0;
+	spin_lock_init(&(ei->i_block_reservation_lock));
+#ifdef CONFIG_QUOTA
+	ei->i_reserved_quota = 0;
+#endif
+	ei->jinode = NULL;
+	INIT_LIST_HEAD(&ei->i_completed_io_list);
+	spin_lock_init(&ei->i_completed_io_lock);
+	ei->cur_aio_dio = NULL;
+	ei->i_sync_tid = 0;
+	ei->i_datasync_tid = 0;
+	atomic_set(&ei->i_ioend_count, 0);
+	atomic_set(&ei->i_aiodio_unwritten, 0);
+
+	return &ei->vfs_inode;
+}
+
+static int ext4_drop_inode(struct inode *inode)
+{
+	int drop = generic_drop_inode(inode);
+
+	trace_ext4_drop_inode(inode, drop);
+	return drop;
+}
+
+static void ext4_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(ext4_inode_cachep, EXT4_I(inode));
+}
+
+static void ext4_destroy_inode(struct inode *inode)
+{
+	if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
+		ext4_msg(inode->i_sb, KERN_ERR,
+			 "Inode %lu (%p): orphan list check failed!",
+			 inode->i_ino, EXT4_I(inode));
+		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
+				EXT4_I(inode), sizeof(struct ext4_inode_info),
+				true);
+		dump_stack();
+	}
+	call_rcu(&inode->i_rcu, ext4_i_callback);
+}
+
+static void init_once(void *foo)
+{
+	struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
+
+	INIT_LIST_HEAD(&ei->i_orphan);
+#ifdef CONFIG_EXT4_FS_XATTR
+	init_rwsem(&ei->xattr_sem);
+#endif
+	init_rwsem(&ei->i_data_sem);
+	inode_init_once(&ei->vfs_inode);
+}
+
+static int init_inodecache(void)
+{
+	ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
+					     sizeof(struct ext4_inode_info),
+					     0, (SLAB_RECLAIM_ACCOUNT|
+						SLAB_MEM_SPREAD),
+					     init_once);
+	if (ext4_inode_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+static void destroy_inodecache(void)
+{
+	kmem_cache_destroy(ext4_inode_cachep);
+}
+
+void ext4_clear_inode(struct inode *inode)
+{
+	invalidate_inode_buffers(inode);
+	end_writeback(inode);
+	dquot_drop(inode);
+	ext4_discard_preallocations(inode);
+	if (EXT4_I(inode)->jinode) {
+		jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
+					       EXT4_I(inode)->jinode);
+		jbd2_free_inode(EXT4_I(inode)->jinode);
+		EXT4_I(inode)->jinode = NULL;
+	}
+}
+
+static inline void ext4_show_quota_options(struct seq_file *seq,
+					   struct super_block *sb)
+{
+#if defined(CONFIG_QUOTA)
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (sbi->s_jquota_fmt) {
+		char *fmtname = "";
+
+		switch (sbi->s_jquota_fmt) {
+		case QFMT_VFS_OLD:
+			fmtname = "vfsold";
+			break;
+		case QFMT_VFS_V0:
+			fmtname = "vfsv0";
+			break;
+		case QFMT_VFS_V1:
+			fmtname = "vfsv1";
+			break;
+		}
+		seq_printf(seq, ",jqfmt=%s", fmtname);
+	}
+
+	if (sbi->s_qf_names[USRQUOTA])
+		seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
+
+	if (sbi->s_qf_names[GRPQUOTA])
+		seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
+
+	if (test_opt(sb, USRQUOTA))
+		seq_puts(seq, ",usrquota");
+
+	if (test_opt(sb, GRPQUOTA))
+		seq_puts(seq, ",grpquota");
+#endif
+}
+
+/*
+ * Show an option if
+ *  - it's set to a non-default value OR
+ *  - if the per-sb default is different from the global default
+ */
+static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
+{
+	int def_errors;
+	unsigned long def_mount_opts;
+	struct super_block *sb = vfs->mnt_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+
+	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+	def_errors     = le16_to_cpu(es->s_errors);
+
+	if (sbi->s_sb_block != 1)
+		seq_printf(seq, ",sb=%llu", sbi->s_sb_block);
+	if (test_opt(sb, MINIX_DF))
+		seq_puts(seq, ",minixdf");
+	if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS))
+		seq_puts(seq, ",grpid");
+	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS))
+		seq_puts(seq, ",nogrpid");
+	if (sbi->s_resuid != EXT4_DEF_RESUID ||
+	    le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) {
+		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
+	}
+	if (sbi->s_resgid != EXT4_DEF_RESGID ||
+	    le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) {
+		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
+	}
+	if (test_opt(sb, ERRORS_RO)) {
+		if (def_errors == EXT4_ERRORS_PANIC ||
+		    def_errors == EXT4_ERRORS_CONTINUE) {
+			seq_puts(seq, ",errors=remount-ro");
+		}
+	}
+	if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
+		seq_puts(seq, ",errors=continue");
+	if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
+		seq_puts(seq, ",errors=panic");
+	if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16))
+		seq_puts(seq, ",nouid32");
+	if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
+		seq_puts(seq, ",debug");
+	if (test_opt(sb, OLDALLOC))
+		seq_puts(seq, ",oldalloc");
+#ifdef CONFIG_EXT4_FS_XATTR
+	if (test_opt(sb, XATTR_USER))
+		seq_puts(seq, ",user_xattr");
+	if (!test_opt(sb, XATTR_USER))
+		seq_puts(seq, ",nouser_xattr");
+#endif
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
+		seq_puts(seq, ",acl");
+	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
+		seq_puts(seq, ",noacl");
+#endif
+	if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
+		seq_printf(seq, ",commit=%u",
+			   (unsigned) (sbi->s_commit_interval / HZ));
+	}
+	if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
+		seq_printf(seq, ",min_batch_time=%u",
+			   (unsigned) sbi->s_min_batch_time);
+	}
+	if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
+		seq_printf(seq, ",max_batch_time=%u",
+			   (unsigned) sbi->s_min_batch_time);
+	}
+
+	/*
+	 * We're changing the default of barrier mount option, so
+	 * let's always display its mount state so it's clear what its
+	 * status is.
+	 */
+	seq_puts(seq, ",barrier=");
+	seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
+	if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
+		seq_puts(seq, ",journal_async_commit");
+	else if (test_opt(sb, JOURNAL_CHECKSUM))
+		seq_puts(seq, ",journal_checksum");
+	if (test_opt(sb, I_VERSION))
+		seq_puts(seq, ",i_version");
+	if (!test_opt(sb, DELALLOC) &&
+	    !(def_mount_opts & EXT4_DEFM_NODELALLOC))
+		seq_puts(seq, ",nodelalloc");
+
+	if (!test_opt(sb, MBLK_IO_SUBMIT))
+		seq_puts(seq, ",nomblk_io_submit");
+	if (sbi->s_stripe)
+		seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
+	/*
+	 * journal mode get enabled in different ways
+	 * So just print the value even if we didn't specify it
+	 */
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		seq_puts(seq, ",data=journal");
+	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		seq_puts(seq, ",data=ordered");
+	else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		seq_puts(seq, ",data=writeback");
+
+	if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
+		seq_printf(seq, ",inode_readahead_blks=%u",
+			   sbi->s_inode_readahead_blks);
+
+	if (test_opt(sb, DATA_ERR_ABORT))
+		seq_puts(seq, ",data_err=abort");
+
+	if (test_opt(sb, NO_AUTO_DA_ALLOC))
+		seq_puts(seq, ",noauto_da_alloc");
+
+	if (test_opt(sb, DISCARD) && !(def_mount_opts & EXT4_DEFM_DISCARD))
+		seq_puts(seq, ",discard");
+
+	if (test_opt(sb, NOLOAD))
+		seq_puts(seq, ",norecovery");
+
+	if (test_opt(sb, DIOREAD_NOLOCK))
+		seq_puts(seq, ",dioread_nolock");
+
+	if (test_opt(sb, BLOCK_VALIDITY) &&
+	    !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
+		seq_puts(seq, ",block_validity");
+
+	if (!test_opt(sb, INIT_INODE_TABLE))
+		seq_puts(seq, ",noinit_itable");
+	else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
+		seq_printf(seq, ",init_itable=%u",
+			   (unsigned) sbi->s_li_wait_mult);
+
+	ext4_show_quota_options(seq, sb);
+
+	return 0;
+}
+
+static struct inode *ext4_nfs_get_inode(struct super_block *sb,
+					u64 ino, u32 generation)
+{
+	struct inode *inode;
+
+	if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
+		return ERR_PTR(-ESTALE);
+	if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+		return ERR_PTR(-ESTALE);
+
+	/* iget isn't really right if the inode is currently unallocated!!
+	 *
+	 * ext4_read_inode will return a bad_inode if the inode had been
+	 * deleted, so we should be safe.
+	 *
+	 * Currently we don't know the generation for parent directory, so
+	 * a generation of 0 means "accept any"
+	 */
+	inode = ext4_iget(sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	if (generation && inode->i_generation != generation) {
+		iput(inode);
+		return ERR_PTR(-ESTALE);
+	}
+
+	return inode;
+}
+
+static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid,
+					int fh_len, int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    ext4_nfs_get_inode);
+}
+
+static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
+					int fh_len, int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    ext4_nfs_get_inode);
+}
+
+/*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device.  Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd2 layer's try_to_free_buffers() function to release them.
+ */
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+				 gfp_t wait)
+{
+	journal_t *journal = EXT4_SB(sb)->s_journal;
+
+	WARN_ON(PageChecked(page));
+	if (!page_has_buffers(page))
+		return 0;
+	if (journal)
+		return jbd2_journal_try_to_free_buffers(journal, page,
+							wait & ~__GFP_WAIT);
+	return try_to_free_buffers(page);
+}
+
+#ifdef CONFIG_QUOTA
+#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
+#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
+
+static int ext4_write_dquot(struct dquot *dquot);
+static int ext4_acquire_dquot(struct dquot *dquot);
+static int ext4_release_dquot(struct dquot *dquot);
+static int ext4_mark_dquot_dirty(struct dquot *dquot);
+static int ext4_write_info(struct super_block *sb, int type);
+static int ext4_quota_on(struct super_block *sb, int type, int format_id,
+			 struct path *path);
+static int ext4_quota_off(struct super_block *sb, int type);
+static int ext4_quota_on_mount(struct super_block *sb, int type);
+static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
+			       size_t len, loff_t off);
+static ssize_t ext4_quota_write(struct super_block *sb, int type,
+				const char *data, size_t len, loff_t off);
+
+static const struct dquot_operations ext4_quota_operations = {
+	.get_reserved_space = ext4_get_reserved_space,
+	.write_dquot	= ext4_write_dquot,
+	.acquire_dquot	= ext4_acquire_dquot,
+	.release_dquot	= ext4_release_dquot,
+	.mark_dirty	= ext4_mark_dquot_dirty,
+	.write_info	= ext4_write_info,
+	.alloc_dquot	= dquot_alloc,
+	.destroy_dquot	= dquot_destroy,
+};
+
+static const struct quotactl_ops ext4_qctl_operations = {
+	.quota_on	= ext4_quota_on,
+	.quota_off	= ext4_quota_off,
+	.quota_sync	= dquot_quota_sync,
+	.get_info	= dquot_get_dqinfo,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk
+};
+#endif
+
+static const struct super_operations ext4_sops = {
+	.alloc_inode	= ext4_alloc_inode,
+	.destroy_inode	= ext4_destroy_inode,
+	.write_inode	= ext4_write_inode,
+	.dirty_inode	= ext4_dirty_inode,
+	.drop_inode	= ext4_drop_inode,
+	.evict_inode	= ext4_evict_inode,
+	.put_super	= ext4_put_super,
+	.sync_fs	= ext4_sync_fs,
+	.freeze_fs	= ext4_freeze,
+	.unfreeze_fs	= ext4_unfreeze,
+	.statfs		= ext4_statfs,
+	.remount_fs	= ext4_remount,
+	.show_options	= ext4_show_options,
+#ifdef CONFIG_QUOTA
+	.quota_read	= ext4_quota_read,
+	.quota_write	= ext4_quota_write,
+#endif
+	.bdev_try_to_free_page = bdev_try_to_free_page,
+};
+
+static const struct super_operations ext4_nojournal_sops = {
+	.alloc_inode	= ext4_alloc_inode,
+	.destroy_inode	= ext4_destroy_inode,
+	.write_inode	= ext4_write_inode,
+	.dirty_inode	= ext4_dirty_inode,
+	.drop_inode	= ext4_drop_inode,
+	.evict_inode	= ext4_evict_inode,
+	.write_super	= ext4_write_super,
+	.put_super	= ext4_put_super,
+	.statfs		= ext4_statfs,
+	.remount_fs	= ext4_remount,
+	.show_options	= ext4_show_options,
+#ifdef CONFIG_QUOTA
+	.quota_read	= ext4_quota_read,
+	.quota_write	= ext4_quota_write,
+#endif
+	.bdev_try_to_free_page = bdev_try_to_free_page,
+};
+
+static const struct export_operations ext4_export_ops = {
+	.fh_to_dentry = ext4_fh_to_dentry,
+	.fh_to_parent = ext4_fh_to_parent,
+	.get_parent = ext4_get_parent,
+};
+
+enum {
+	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
+	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
+	Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
+	Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
+	Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_nobh, Opt_bh,
+	Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
+	Opt_journal_update, Opt_journal_dev,
+	Opt_journal_checksum, Opt_journal_async_commit,
+	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+	Opt_data_err_abort, Opt_data_err_ignore,
+	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
+	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
+	Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
+	Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
+	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
+	Opt_inode_readahead_blks, Opt_journal_ioprio,
+	Opt_dioread_nolock, Opt_dioread_lock,
+	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
+};
+
+static const match_table_t tokens = {
+	{Opt_bsd_df, "bsddf"},
+	{Opt_minix_df, "minixdf"},
+	{Opt_grpid, "grpid"},
+	{Opt_grpid, "bsdgroups"},
+	{Opt_nogrpid, "nogrpid"},
+	{Opt_nogrpid, "sysvgroups"},
+	{Opt_resgid, "resgid=%u"},
+	{Opt_resuid, "resuid=%u"},
+	{Opt_sb, "sb=%u"},
+	{Opt_err_cont, "errors=continue"},
+	{Opt_err_panic, "errors=panic"},
+	{Opt_err_ro, "errors=remount-ro"},
+	{Opt_nouid32, "nouid32"},
+	{Opt_debug, "debug"},
+	{Opt_oldalloc, "oldalloc"},
+	{Opt_orlov, "orlov"},
+	{Opt_user_xattr, "user_xattr"},
+	{Opt_nouser_xattr, "nouser_xattr"},
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+	{Opt_noload, "noload"},
+	{Opt_noload, "norecovery"},
+	{Opt_nobh, "nobh"},
+	{Opt_bh, "bh"},
+	{Opt_commit, "commit=%u"},
+	{Opt_min_batch_time, "min_batch_time=%u"},
+	{Opt_max_batch_time, "max_batch_time=%u"},
+	{Opt_journal_update, "journal=update"},
+	{Opt_journal_dev, "journal_dev=%u"},
+	{Opt_journal_checksum, "journal_checksum"},
+	{Opt_journal_async_commit, "journal_async_commit"},
+	{Opt_abort, "abort"},
+	{Opt_data_journal, "data=journal"},
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_err_abort, "data_err=abort"},
+	{Opt_data_err_ignore, "data_err=ignore"},
+	{Opt_offusrjquota, "usrjquota="},
+	{Opt_usrjquota, "usrjquota=%s"},
+	{Opt_offgrpjquota, "grpjquota="},
+	{Opt_grpjquota, "grpjquota=%s"},
+	{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
+	{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+	{Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
+	{Opt_grpquota, "grpquota"},
+	{Opt_noquota, "noquota"},
+	{Opt_quota, "quota"},
+	{Opt_usrquota, "usrquota"},
+	{Opt_barrier, "barrier=%u"},
+	{Opt_barrier, "barrier"},
+	{Opt_nobarrier, "nobarrier"},
+	{Opt_i_version, "i_version"},
+	{Opt_stripe, "stripe=%u"},
+	{Opt_resize, "resize"},
+	{Opt_delalloc, "delalloc"},
+	{Opt_nodelalloc, "nodelalloc"},
+	{Opt_mblk_io_submit, "mblk_io_submit"},
+	{Opt_nomblk_io_submit, "nomblk_io_submit"},
+	{Opt_block_validity, "block_validity"},
+	{Opt_noblock_validity, "noblock_validity"},
+	{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
+	{Opt_journal_ioprio, "journal_ioprio=%u"},
+	{Opt_auto_da_alloc, "auto_da_alloc=%u"},
+	{Opt_auto_da_alloc, "auto_da_alloc"},
+	{Opt_noauto_da_alloc, "noauto_da_alloc"},
+	{Opt_dioread_nolock, "dioread_nolock"},
+	{Opt_dioread_lock, "dioread_lock"},
+	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
+	{Opt_init_itable, "init_itable=%u"},
+	{Opt_init_itable, "init_itable"},
+	{Opt_noinit_itable, "noinit_itable"},
+	{Opt_err, NULL},
+};
+
+static ext4_fsblk_t get_sb_block(void **data)
+{
+	ext4_fsblk_t	sb_block;
+	char		*options = (char *) *data;
+
+	if (!options || strncmp(options, "sb=", 3) != 0)
+		return 1;	/* Default location */
+
+	options += 3;
+	/* TODO: use simple_strtoll with >32bit ext4 */
+	sb_block = simple_strtoul(options, &options, 0);
+	if (*options && *options != ',') {
+		printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
+		       (char *) *data);
+		return 1;
+	}
+	if (*options == ',')
+		options++;
+	*data = (void *) options;
+
+	return sb_block;
+}
+
+#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n"
+	"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
+
+#ifdef CONFIG_QUOTA
+static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	char *qname;
+
+	if (sb_any_quota_loaded(sb) &&
+		!sbi->s_qf_names[qtype]) {
+		ext4_msg(sb, KERN_ERR,
+			"Cannot change journaled "
+			"quota options when quota turned on");
+		return 0;
+	}
+	qname = match_strdup(args);
+	if (!qname) {
+		ext4_msg(sb, KERN_ERR,
+			"Not enough memory for storing quotafile name");
+		return 0;
+	}
+	if (sbi->s_qf_names[qtype] &&
+		strcmp(sbi->s_qf_names[qtype], qname)) {
+		ext4_msg(sb, KERN_ERR,
+			"%s quota file already specified", QTYPE2NAME(qtype));
+		kfree(qname);
+		return 0;
+	}
+	sbi->s_qf_names[qtype] = qname;
+	if (strchr(sbi->s_qf_names[qtype], '/')) {
+		ext4_msg(sb, KERN_ERR,
+			"quotafile must be on filesystem root");
+		kfree(sbi->s_qf_names[qtype]);
+		sbi->s_qf_names[qtype] = NULL;
+		return 0;
+	}
+	set_opt(sb, QUOTA);
+	return 1;
+}
+
+static int clear_qf_name(struct super_block *sb, int qtype)
+{
+
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (sb_any_quota_loaded(sb) &&
+		sbi->s_qf_names[qtype]) {
+		ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
+			" when quota turned on");
+		return 0;
+	}
+	/*
+	 * The space will be released later when all options are confirmed
+	 * to be correct
+	 */
+	sbi->s_qf_names[qtype] = NULL;
+	return 1;
+}
+#endif
+
+static int parse_options(char *options, struct super_block *sb,
+			 unsigned long *journal_devnum,
+			 unsigned int *journal_ioprio,
+			 ext4_fsblk_t *n_blocks_count, int is_remount)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int data_opt = 0;
+	int option;
+#ifdef CONFIG_QUOTA
+	int qfmt;
+#endif
+
+	if (!options)
+		return 1;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		if (!*p)
+			continue;
+
+		/*
+		 * Initialize args struct so we know whether arg was
+		 * found; some options take optional arguments.
+		 */
+		args[0].to = args[0].from = NULL;
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_bsd_df:
+			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
+			clear_opt(sb, MINIX_DF);
+			break;
+		case Opt_minix_df:
+			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
+			set_opt(sb, MINIX_DF);
+
+			break;
+		case Opt_grpid:
+			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
+			set_opt(sb, GRPID);
+
+			break;
+		case Opt_nogrpid:
+			ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
+			clear_opt(sb, GRPID);
+
+			break;
+		case Opt_resuid:
+			if (match_int(&args[0], &option))
+				return 0;
+			sbi->s_resuid = option;
+			break;
+		case Opt_resgid:
+			if (match_int(&args[0], &option))
+				return 0;
+			sbi->s_resgid = option;
+			break;
+		case Opt_sb:
+			/* handled by get_sb_block() instead of here */
+			/* *sb_block = match_int(&args[0]); */
+			break;
+		case Opt_err_panic:
+			clear_opt(sb, ERRORS_CONT);
+			clear_opt(sb, ERRORS_RO);
+			set_opt(sb, ERRORS_PANIC);
+			break;
+		case Opt_err_ro:
+			clear_opt(sb, ERRORS_CONT);
+			clear_opt(sb, ERRORS_PANIC);
+			set_opt(sb, ERRORS_RO);
+			break;
+		case Opt_err_cont:
+			clear_opt(sb, ERRORS_RO);
+			clear_opt(sb, ERRORS_PANIC);
+			set_opt(sb, ERRORS_CONT);
+			break;
+		case Opt_nouid32:
+			set_opt(sb, NO_UID32);
+			break;
+		case Opt_debug:
+			set_opt(sb, DEBUG);
+			break;
+		case Opt_oldalloc:
+			set_opt(sb, OLDALLOC);
+			break;
+		case Opt_orlov:
+			clear_opt(sb, OLDALLOC);
+			break;
+#ifdef CONFIG_EXT4_FS_XATTR
+		case Opt_user_xattr:
+			set_opt(sb, XATTR_USER);
+			break;
+		case Opt_nouser_xattr:
+			clear_opt(sb, XATTR_USER);
+			break;
+#else
+		case Opt_user_xattr:
+		case Opt_nouser_xattr:
+			ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported");
+			break;
+#endif
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+		case Opt_acl:
+			set_opt(sb, POSIX_ACL);
+			break;
+		case Opt_noacl:
+			clear_opt(sb, POSIX_ACL);
+			break;
+#else
+		case Opt_acl:
+		case Opt_noacl:
+			ext4_msg(sb, KERN_ERR, "(no)acl options not supported");
+			break;
+#endif
+		case Opt_journal_update:
+			/* @@@ FIXME */
+			/* Eventually we will want to be able to create
+			   a journal file here.  For now, only allow the
+			   user to specify an existing inode to be the
+			   journal file. */
+			if (is_remount) {
+				ext4_msg(sb, KERN_ERR,
+					 "Cannot specify journal on remount");
+				return 0;
+			}
+			set_opt(sb, UPDATE_JOURNAL);
+			break;
+		case Opt_journal_dev:
+			if (is_remount) {
+				ext4_msg(sb, KERN_ERR,
+					"Cannot specify journal on remount");
+				return 0;
+			}
+			if (match_int(&args[0], &option))
+				return 0;
+			*journal_devnum = option;
+			break;
+		case Opt_journal_checksum:
+			set_opt(sb, JOURNAL_CHECKSUM);
+			break;
+		case Opt_journal_async_commit:
+			set_opt(sb, JOURNAL_ASYNC_COMMIT);
+			set_opt(sb, JOURNAL_CHECKSUM);
+			break;
+		case Opt_noload:
+			set_opt(sb, NOLOAD);
+			break;
+		case Opt_commit:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0)
+				return 0;
+			if (option == 0)
+				option = JBD2_DEFAULT_MAX_COMMIT_AGE;
+			sbi->s_commit_interval = HZ * option;
+			break;
+		case Opt_max_batch_time:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0)
+				return 0;
+			if (option == 0)
+				option = EXT4_DEF_MAX_BATCH_TIME;
+			sbi->s_max_batch_time = option;
+			break;
+		case Opt_min_batch_time:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0)
+				return 0;
+			sbi->s_min_batch_time = option;
+			break;
+		case Opt_data_journal:
+			data_opt = EXT4_MOUNT_JOURNAL_DATA;
+			goto datacheck;
+		case Opt_data_ordered:
+			data_opt = EXT4_MOUNT_ORDERED_DATA;
+			goto datacheck;
+		case Opt_data_writeback:
+			data_opt = EXT4_MOUNT_WRITEBACK_DATA;
+		datacheck:
+			if (is_remount) {
+				if (test_opt(sb, DATA_FLAGS) != data_opt) {
+					ext4_msg(sb, KERN_ERR,
+						"Cannot change data mode on remount");
+					return 0;
+				}
+			} else {
+				clear_opt(sb, DATA_FLAGS);
+				sbi->s_mount_opt |= data_opt;
+			}
+			break;
+		case Opt_data_err_abort:
+			set_opt(sb, DATA_ERR_ABORT);
+			break;
+		case Opt_data_err_ignore:
+			clear_opt(sb, DATA_ERR_ABORT);
+			break;
+#ifdef CONFIG_QUOTA
+		case Opt_usrjquota:
+			if (!set_qf_name(sb, USRQUOTA, &args[0]))
+				return 0;
+			break;
+		case Opt_grpjquota:
+			if (!set_qf_name(sb, GRPQUOTA, &args[0]))
+				return 0;
+			break;
+		case Opt_offusrjquota:
+			if (!clear_qf_name(sb, USRQUOTA))
+				return 0;
+			break;
+		case Opt_offgrpjquota:
+			if (!clear_qf_name(sb, GRPQUOTA))
+				return 0;
+			break;
+
+		case Opt_jqfmt_vfsold:
+			qfmt = QFMT_VFS_OLD;
+			goto set_qf_format;
+		case Opt_jqfmt_vfsv0:
+			qfmt = QFMT_VFS_V0;
+			goto set_qf_format;
+		case Opt_jqfmt_vfsv1:
+			qfmt = QFMT_VFS_V1;
+set_qf_format:
+			if (sb_any_quota_loaded(sb) &&
+			    sbi->s_jquota_fmt != qfmt) {
+				ext4_msg(sb, KERN_ERR, "Cannot change "
+					"journaled quota options when "
+					"quota turned on");
+				return 0;
+			}
+			sbi->s_jquota_fmt = qfmt;
+			break;
+		case Opt_quota:
+		case Opt_usrquota:
+			set_opt(sb, QUOTA);
+			set_opt(sb, USRQUOTA);
+			break;
+		case Opt_grpquota:
+			set_opt(sb, QUOTA);
+			set_opt(sb, GRPQUOTA);
+			break;
+		case Opt_noquota:
+			if (sb_any_quota_loaded(sb)) {
+				ext4_msg(sb, KERN_ERR, "Cannot change quota "
+					"options when quota turned on");
+				return 0;
+			}
+			clear_opt(sb, QUOTA);
+			clear_opt(sb, USRQUOTA);
+			clear_opt(sb, GRPQUOTA);
+			break;
+#else
+		case Opt_quota:
+		case Opt_usrquota:
+		case Opt_grpquota:
+			ext4_msg(sb, KERN_ERR,
+				"quota options not supported");
+			break;
+		case Opt_usrjquota:
+		case Opt_grpjquota:
+		case Opt_offusrjquota:
+		case Opt_offgrpjquota:
+		case Opt_jqfmt_vfsold:
+		case Opt_jqfmt_vfsv0:
+		case Opt_jqfmt_vfsv1:
+			ext4_msg(sb, KERN_ERR,
+				"journaled quota options not supported");
+			break;
+		case Opt_noquota:
+			break;
+#endif
+		case Opt_abort:
+			sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+			break;
+		case Opt_nobarrier:
+			clear_opt(sb, BARRIER);
+			break;
+		case Opt_barrier:
+			if (args[0].from) {
+				if (match_int(&args[0], &option))
+					return 0;
+			} else
+				option = 1;	/* No argument, default to 1 */
+			if (option)
+				set_opt(sb, BARRIER);
+			else
+				clear_opt(sb, BARRIER);
+			break;
+		case Opt_ignore:
+			break;
+		case Opt_resize:
+			if (!is_remount) {
+				ext4_msg(sb, KERN_ERR,
+					"resize option only available "
+					"for remount");
+				return 0;
+			}
+			if (match_int(&args[0], &option) != 0)
+				return 0;
+			*n_blocks_count = option;
+			break;
+		case Opt_nobh:
+			ext4_msg(sb, KERN_WARNING,
+				 "Ignoring deprecated nobh option");
+			break;
+		case Opt_bh:
+			ext4_msg(sb, KERN_WARNING,
+				 "Ignoring deprecated bh option");
+			break;
+		case Opt_i_version:
+			set_opt(sb, I_VERSION);
+			sb->s_flags |= MS_I_VERSION;
+			break;
+		case Opt_nodelalloc:
+			clear_opt(sb, DELALLOC);
+			break;
+		case Opt_mblk_io_submit:
+			set_opt(sb, MBLK_IO_SUBMIT);
+			break;
+		case Opt_nomblk_io_submit:
+			clear_opt(sb, MBLK_IO_SUBMIT);
+			break;
+		case Opt_stripe:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0)
+				return 0;
+			sbi->s_stripe = option;
+			break;
+		case Opt_delalloc:
+			set_opt(sb, DELALLOC);
+			break;
+		case Opt_block_validity:
+			set_opt(sb, BLOCK_VALIDITY);
+			break;
+		case Opt_noblock_validity:
+			clear_opt(sb, BLOCK_VALIDITY);
+			break;
+		case Opt_inode_readahead_blks:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0 || option > (1 << 30))
+				return 0;
+			if (option && !is_power_of_2(option)) {
+				ext4_msg(sb, KERN_ERR,
+					 "EXT4-fs: inode_readahead_blks"
+					 " must be a power of 2");
+				return 0;
+			}
+			sbi->s_inode_readahead_blks = option;
+			break;
+		case Opt_journal_ioprio:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0 || option > 7)
+				break;
+			*journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
+							    option);
+			break;
+		case Opt_noauto_da_alloc:
+			set_opt(sb, NO_AUTO_DA_ALLOC);
+			break;
+		case Opt_auto_da_alloc:
+			if (args[0].from) {
+				if (match_int(&args[0], &option))
+					return 0;
+			} else
+				option = 1;	/* No argument, default to 1 */
+			if (option)
+				clear_opt(sb, NO_AUTO_DA_ALLOC);
+			else
+				set_opt(sb,NO_AUTO_DA_ALLOC);
+			break;
+		case Opt_discard:
+			set_opt(sb, DISCARD);
+			break;
+		case Opt_nodiscard:
+			clear_opt(sb, DISCARD);
+			break;
+		case Opt_dioread_nolock:
+			set_opt(sb, DIOREAD_NOLOCK);
+			break;
+		case Opt_dioread_lock:
+			clear_opt(sb, DIOREAD_NOLOCK);
+			break;
+		case Opt_init_itable:
+			set_opt(sb, INIT_INODE_TABLE);
+			if (args[0].from) {
+				if (match_int(&args[0], &option))
+					return 0;
+			} else
+				option = EXT4_DEF_LI_WAIT_MULT;
+			if (option < 0)
+				return 0;
+			sbi->s_li_wait_mult = option;
+			break;
+		case Opt_noinit_itable:
+			clear_opt(sb, INIT_INODE_TABLE);
+			break;
+		default:
+			ext4_msg(sb, KERN_ERR,
+			       "Unrecognized mount option \"%s\" "
+			       "or missing value", p);
+			return 0;
+		}
+	}
+#ifdef CONFIG_QUOTA
+	if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+		if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
+			clear_opt(sb, USRQUOTA);
+
+		if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
+			clear_opt(sb, GRPQUOTA);
+
+		if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
+			ext4_msg(sb, KERN_ERR, "old and new quota "
+					"format mixing");
+			return 0;
+		}
+
+		if (!sbi->s_jquota_fmt) {
+			ext4_msg(sb, KERN_ERR, "journaled quota format "
+					"not specified");
+			return 0;
+		}
+	} else {
+		if (sbi->s_jquota_fmt) {
+			ext4_msg(sb, KERN_ERR, "journaled quota format "
+					"specified with no journaling "
+					"enabled");
+			return 0;
+		}
+	}
+#endif
+	return 1;
+}
+
+static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
+			    int read_only)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int res = 0;
+
+	if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
+		ext4_msg(sb, KERN_ERR, "revision level too high, "
+			 "forcing read-only mode");
+		res = MS_RDONLY;
+	}
+	if (read_only)
+		return res;
+	if (!(sbi->s_mount_state & EXT4_VALID_FS))
+		ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
+			 "running e2fsck is recommended");
+	else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+		ext4_msg(sb, KERN_WARNING,
+			 "warning: mounting fs with errors, "
+			 "running e2fsck is recommended");
+	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 &&
+		 le16_to_cpu(es->s_mnt_count) >=
+		 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
+		ext4_msg(sb, KERN_WARNING,
+			 "warning: maximal mount count reached, "
+			 "running e2fsck is recommended");
+	else if (le32_to_cpu(es->s_checkinterval) &&
+		(le32_to_cpu(es->s_lastcheck) +
+			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+		ext4_msg(sb, KERN_WARNING,
+			 "warning: checktime reached, "
+			 "running e2fsck is recommended");
+	if (!sbi->s_journal)
+		es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
+	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
+		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
+	le16_add_cpu(&es->s_mnt_count, 1);
+	es->s_mtime = cpu_to_le32(get_seconds());
+	ext4_update_dynamic_rev(sb);
+	if (sbi->s_journal)
+		EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+
+	ext4_commit_super(sb, 1);
+	if (test_opt(sb, DEBUG))
+		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
+				"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
+			sb->s_blocksize,
+			sbi->s_groups_count,
+			EXT4_BLOCKS_PER_GROUP(sb),
+			EXT4_INODES_PER_GROUP(sb),
+			sbi->s_mount_opt, sbi->s_mount_opt2);
+
+	cleancache_init_fs(sb);
+	return res;
+}
+
+static int ext4_fill_flex_info(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = NULL;
+	ext4_group_t flex_group_count;
+	ext4_group_t flex_group;
+	unsigned int groups_per_flex = 0;
+	size_t size;
+	int i;
+
+	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+	if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
+		sbi->s_log_groups_per_flex = 0;
+		return 1;
+	}
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+	/* We allocate both existing and potentially added groups */
+	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
+			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
+			      EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
+	size = flex_group_count * sizeof(struct flex_groups);
+	sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
+	if (sbi->s_flex_groups == NULL) {
+		sbi->s_flex_groups = vzalloc(size);
+		if (sbi->s_flex_groups == NULL) {
+			ext4_msg(sb, KERN_ERR,
+				 "not enough memory for %u flex groups",
+				 flex_group_count);
+			goto failed;
+		}
+	}
+
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		gdp = ext4_get_group_desc(sb, i, NULL);
+
+		flex_group = ext4_flex_group(sbi, i);
+		atomic_add(ext4_free_inodes_count(sb, gdp),
+			   &sbi->s_flex_groups[flex_group].free_inodes);
+		atomic_add(ext4_free_blks_count(sb, gdp),
+			   &sbi->s_flex_groups[flex_group].free_blocks);
+		atomic_add(ext4_used_dirs_count(sb, gdp),
+			   &sbi->s_flex_groups[flex_group].used_dirs);
+	}
+
+	return 1;
+failed:
+	return 0;
+}
+
+__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
+			    struct ext4_group_desc *gdp)
+{
+	__u16 crc = 0;
+
+	if (sbi->s_es->s_feature_ro_compat &
+	    cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+		int offset = offsetof(struct ext4_group_desc, bg_checksum);
+		__le32 le_group = cpu_to_le32(block_group);
+
+		crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
+		crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
+		crc = crc16(crc, (__u8 *)gdp, offset);
+		offset += sizeof(gdp->bg_checksum); /* skip checksum */
+		/* for checksum of struct ext4_group_desc do the rest...*/
+		if ((sbi->s_es->s_feature_incompat &
+		     cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
+		    offset < le16_to_cpu(sbi->s_es->s_desc_size))
+			crc = crc16(crc, (__u8 *)gdp + offset,
+				    le16_to_cpu(sbi->s_es->s_desc_size) -
+					offset);
+	}
+
+	return cpu_to_le16(crc);
+}
+
+int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
+				struct ext4_group_desc *gdp)
+{
+	if ((sbi->s_es->s_feature_ro_compat &
+	     cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) &&
+	    (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp)))
+		return 0;
+
+	return 1;
+}
+
+/* Called at mount-time, super-block is locked */
+static int ext4_check_descriptors(struct super_block *sb,
+				  ext4_group_t *first_not_zeroed)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
+	ext4_fsblk_t last_block;
+	ext4_fsblk_t block_bitmap;
+	ext4_fsblk_t inode_bitmap;
+	ext4_fsblk_t inode_table;
+	int flexbg_flag = 0;
+	ext4_group_t i, grp = sbi->s_groups_count;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+		flexbg_flag = 1;
+
+	ext4_debug("Checking group descriptors");
+
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
+
+		if (i == sbi->s_groups_count - 1 || flexbg_flag)
+			last_block = ext4_blocks_count(sbi->s_es) - 1;
+		else
+			last_block = first_block +
+				(EXT4_BLOCKS_PER_GROUP(sb) - 1);
+
+		if ((grp == sbi->s_groups_count) &&
+		   !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			grp = i;
+
+		block_bitmap = ext4_block_bitmap(sb, gdp);
+		if (block_bitmap < first_block || block_bitmap > last_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+			       "Block bitmap for group %u not in group "
+			       "(block %llu)!", i, block_bitmap);
+			return 0;
+		}
+		inode_bitmap = ext4_inode_bitmap(sb, gdp);
+		if (inode_bitmap < first_block || inode_bitmap > last_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+			       "Inode bitmap for group %u not in group "
+			       "(block %llu)!", i, inode_bitmap);
+			return 0;
+		}
+		inode_table = ext4_inode_table(sb, gdp);
+		if (inode_table < first_block ||
+		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+			       "Inode table for group %u not in group "
+			       "(block %llu)!", i, inode_table);
+			return 0;
+		}
+		ext4_lock_group(sb, i);
+		if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Checksum for group %u failed (%u!=%u)",
+				 i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
+				     gdp)), le16_to_cpu(gdp->bg_checksum));
+			if (!(sb->s_flags & MS_RDONLY)) {
+				ext4_unlock_group(sb, i);
+				return 0;
+			}
+		}
+		ext4_unlock_group(sb, i);
+		if (!flexbg_flag)
+			first_block += EXT4_BLOCKS_PER_GROUP(sb);
+	}
+	if (NULL != first_not_zeroed)
+		*first_not_zeroed = grp;
+
+	ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
+	sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
+	return 1;
+}
+
+/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
+ * the superblock) which were deleted from all directories, but held open by
+ * a process at the time of a crash.  We walk the list and try to delete these
+ * inodes at recovery time (only with a read-write filesystem).
+ *
+ * In order to keep the orphan inode chain consistent during traversal (in
+ * case of crash during recovery), we link each inode into the superblock
+ * orphan list_head and handle it the same way as an inode deletion during
+ * normal operation (which journals the operations for us).
+ *
+ * We only do an iget() and an iput() on each inode, which is very safe if we
+ * accidentally point at an in-use or already deleted inode.  The worst that
+ * can happen in this case is that we get a "bit already cleared" message from
+ * ext4_free_inode().  The only reason we would point at a wrong inode is if
+ * e2fsck was run on this filesystem, and it must have already done the orphan
+ * inode cleanup for us, so we can safely abort without any further action.
+ */
+static void ext4_orphan_cleanup(struct super_block *sb,
+				struct ext4_super_block *es)
+{
+	unsigned int s_flags = sb->s_flags;
+	int nr_orphans = 0, nr_truncates = 0;
+#ifdef CONFIG_QUOTA
+	int i;
+#endif
+	if (!es->s_last_orphan) {
+		jbd_debug(4, "no orphan inodes to clean up\n");
+		return;
+	}
+
+	if (bdev_read_only(sb->s_bdev)) {
+		ext4_msg(sb, KERN_ERR, "write access "
+			"unavailable, skipping orphan cleanup");
+		return;
+	}
+
+	/* Check if feature set would not allow a r/w mount */
+	if (!ext4_feature_set_ok(sb, 0)) {
+		ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
+			 "unknown ROCOMPAT features");
+		return;
+	}
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+		if (es->s_last_orphan)
+			jbd_debug(1, "Errors on filesystem, "
+				  "clearing orphan list.\n");
+		es->s_last_orphan = 0;
+		jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
+		return;
+	}
+
+	if (s_flags & MS_RDONLY) {
+		ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
+		sb->s_flags &= ~MS_RDONLY;
+	}
+#ifdef CONFIG_QUOTA
+	/* Needed for iput() to work correctly and not trash data */
+	sb->s_flags |= MS_ACTIVE;
+	/* Turn on quotas so that they are updated correctly */
+	for (i = 0; i < MAXQUOTAS; i++) {
+		if (EXT4_SB(sb)->s_qf_names[i]) {
+			int ret = ext4_quota_on_mount(sb, i);
+			if (ret < 0)
+				ext4_msg(sb, KERN_ERR,
+					"Cannot turn on journaled "
+					"quota: error %d", ret);
+		}
+	}
+#endif
+
+	while (es->s_last_orphan) {
+		struct inode *inode;
+
+		inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
+		if (IS_ERR(inode)) {
+			es->s_last_orphan = 0;
+			break;
+		}
+
+		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
+		dquot_initialize(inode);
+		if (inode->i_nlink) {
+			ext4_msg(sb, KERN_DEBUG,
+				"%s: truncating inode %lu to %lld bytes",
+				__func__, inode->i_ino, inode->i_size);
+			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
+				  inode->i_ino, inode->i_size);
+			ext4_truncate(inode);
+			nr_truncates++;
+		} else {
+			ext4_msg(sb, KERN_DEBUG,
+				"%s: deleting unreferenced inode %lu",
+				__func__, inode->i_ino);
+			jbd_debug(2, "deleting unreferenced inode %lu\n",
+				  inode->i_ino);
+			nr_orphans++;
+		}
+		iput(inode);  /* The delete magic happens here! */
+	}
+
+#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
+
+	if (nr_orphans)
+		ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
+		       PLURAL(nr_orphans));
+	if (nr_truncates)
+		ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
+		       PLURAL(nr_truncates));
+#ifdef CONFIG_QUOTA
+	/* Turn quotas off */
+	for (i = 0; i < MAXQUOTAS; i++) {
+		if (sb_dqopt(sb)->files[i])
+			dquot_quota_off(sb, i);
+	}
+#endif
+	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+}
+
+/*
+ * Maximal extent format file size.
+ * Resulting logical blkno at s_maxbytes must fit in our on-disk
+ * extent format containers, within a sector_t, and within i_blocks
+ * in the vfs.  ext4 inode has 48 bits of i_block in fsblock units,
+ * so that won't be a limiting factor.
+ *
+ * However there is other limiting factor. We do store extents in the form
+ * of starting block and length, hence the resulting length of the extent
+ * covering maximum file size must fit into on-disk format containers as
+ * well. Given that length is always by 1 unit bigger than max unit (because
+ * we count 0 as well) we have to lower the s_maxbytes by one fs block.
+ *
+ * Note, this does *not* consider any metadata overhead for vfs i_blocks.
+ */
+static loff_t ext4_max_size(int blkbits, int has_huge_files)
+{
+	loff_t res;
+	loff_t upper_limit = MAX_LFS_FILESIZE;
+
+	/* small i_blocks in vfs inode? */
+	if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
+		/*
+		 * CONFIG_LBDAF is not enabled implies the inode
+		 * i_block represent total blocks in 512 bytes
+		 * 32 == size of vfs inode i_blocks * 8
+		 */
+		upper_limit = (1LL << 32) - 1;
+
+		/* total blocks in file system block size */
+		upper_limit >>= (blkbits - 9);
+		upper_limit <<= blkbits;
+	}
+
+	/*
+	 * 32-bit extent-start container, ee_block. We lower the maxbytes
+	 * by one fs block, so ee_len can cover the extent of maximum file
+	 * size
+	 */
+	res = (1LL << 32) - 1;
+	res <<= blkbits;
+
+	/* Sanity check against vm- & vfs- imposed limits */
+	if (res > upper_limit)
+		res = upper_limit;
+
+	return res;
+}
+
+/*
+ * Maximal bitmap file size.  There is a direct, and {,double-,triple-}indirect
+ * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks.
+ * We need to be 1 filesystem block less than the 2^48 sector limit.
+ */
+static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
+{
+	loff_t res = EXT4_NDIR_BLOCKS;
+	int meta_blocks;
+	loff_t upper_limit;
+	/* This is calculated to be the largest file size for a dense, block
+	 * mapped file such that the file's total number of 512-byte sectors,
+	 * including data and all indirect blocks, does not exceed (2^48 - 1).
+	 *
+	 * __u32 i_blocks_lo and _u16 i_blocks_high represent the total
+	 * number of 512-byte sectors of the file.
+	 */
+
+	if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
+		/*
+		 * !has_huge_files or CONFIG_LBDAF not enabled implies that
+		 * the inode i_block field represents total file blocks in
+		 * 2^32 512-byte sectors == size of vfs inode i_blocks * 8
+		 */
+		upper_limit = (1LL << 32) - 1;
+
+		/* total blocks in file system block size */
+		upper_limit >>= (bits - 9);
+
+	} else {
+		/*
+		 * We use 48 bit ext4_inode i_blocks
+		 * With EXT4_HUGE_FILE_FL set the i_blocks
+		 * represent total number of blocks in
+		 * file system block size
+		 */
+		upper_limit = (1LL << 48) - 1;
+
+	}
+
+	/* indirect blocks */
+	meta_blocks = 1;
+	/* double indirect blocks */
+	meta_blocks += 1 + (1LL << (bits-2));
+	/* tripple indirect blocks */
+	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
+
+	upper_limit -= meta_blocks;
+	upper_limit <<= bits;
+
+	res += 1LL << (bits-2);
+	res += 1LL << (2*(bits-2));
+	res += 1LL << (3*(bits-2));
+	res <<= bits;
+	if (res > upper_limit)
+		res = upper_limit;
+
+	if (res > MAX_LFS_FILESIZE)
+		res = MAX_LFS_FILESIZE;
+
+	return res;
+}
+
+static ext4_fsblk_t descriptor_loc(struct super_block *sb,
+				   ext4_fsblk_t logical_sb_block, int nr)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_group_t bg, first_meta_bg;
+	int has_super = 0;
+
+	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
+
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+	    nr < first_meta_bg)
+		return logical_sb_block + nr + 1;
+	bg = sbi->s_desc_per_block * nr;
+	if (ext4_bg_has_super(sb, bg))
+		has_super = 1;
+
+	return (has_super + ext4_group_first_block_no(sb, bg));
+}
+
+/**
+ * ext4_get_stripe_size: Get the stripe size.
+ * @sbi: In memory super block info
+ *
+ * If we have specified it via mount option, then
+ * use the mount option value. If the value specified at mount time is
+ * greater than the blocks per group use the super block value.
+ * If the super block value is greater than blocks per group return 0.
+ * Allocator needs it be less than blocks per group.
+ *
+ */
+static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
+{
+	unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
+	unsigned long stripe_width =
+			le32_to_cpu(sbi->s_es->s_raid_stripe_width);
+
+	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
+		return sbi->s_stripe;
+
+	if (stripe_width <= sbi->s_blocks_per_group)
+		return stripe_width;
+
+	if (stride <= sbi->s_blocks_per_group)
+		return stride;
+
+	return 0;
+}
+
+/* sysfs supprt */
+
+struct ext4_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
+	ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
+			 const char *, size_t);
+	int offset;
+};
+
+static int parse_strtoul(const char *buf,
+		unsigned long max, unsigned long *value)
+{
+	char *endp;
+
+	*value = simple_strtoul(skip_spaces(buf), &endp, 0);
+	endp = skip_spaces(endp);
+	if (*endp || *value > max)
+		return -EINVAL;
+
+	return 0;
+}
+
+static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a,
+					      struct ext4_sb_info *sbi,
+					      char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+}
+
+static ssize_t session_write_kbytes_show(struct ext4_attr *a,
+					 struct ext4_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->s_buddy_cache->i_sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+	return snprintf(buf, PAGE_SIZE, "%lu\n",
+			(part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			 sbi->s_sectors_written_start) >> 1);
+}
+
+static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
+					  struct ext4_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->s_buddy_cache->i_sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(unsigned long long)(sbi->s_kbytes_written +
+			((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
+}
+
+static ssize_t extent_cache_hits_show(struct ext4_attr *a,
+				      struct ext4_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", sbi->extent_cache_hits);
+}
+
+static ssize_t extent_cache_misses_show(struct ext4_attr *a,
+					struct ext4_sb_info *sbi, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", sbi->extent_cache_misses);
+}
+
+static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
+					  struct ext4_sb_info *sbi,
+					  const char *buf, size_t count)
+{
+	unsigned long t;
+
+	if (parse_strtoul(buf, 0x40000000, &t))
+		return -EINVAL;
+
+	if (t && !is_power_of_2(t))
+		return -EINVAL;
+
+	sbi->s_inode_readahead_blks = t;
+	return count;
+}
+
+static ssize_t sbi_ui_show(struct ext4_attr *a,
+			   struct ext4_sb_info *sbi, char *buf)
+{
+	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
+static ssize_t sbi_ui_store(struct ext4_attr *a,
+			    struct ext4_sb_info *sbi,
+			    const char *buf, size_t count)
+{
+	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+	unsigned long t;
+
+	if (parse_strtoul(buf, 0xffffffff, &t))
+		return -EINVAL;
+	*ui = t;
+	return count;
+}
+
+#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
+static struct ext4_attr ext4_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.show	= _show,					\
+	.store	= _store,					\
+	.offset = offsetof(struct ext4_sb_info, _elname),	\
+}
+#define EXT4_ATTR(name, mode, show, store) \
+static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
+
+#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
+#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
+#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
+#define EXT4_RW_ATTR_SBI_UI(name, elname)	\
+	EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
+#define ATTR_LIST(name) &ext4_attr_##name.attr
+
+EXT4_RO_ATTR(delayed_allocation_blocks);
+EXT4_RO_ATTR(session_write_kbytes);
+EXT4_RO_ATTR(lifetime_write_kbytes);
+EXT4_RO_ATTR(extent_cache_hits);
+EXT4_RO_ATTR(extent_cache_misses);
+EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
+		 inode_readahead_blks_store, s_inode_readahead_blks);
+EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
+EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
+EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
+EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
+EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
+EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
+EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
+EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+
+static struct attribute *ext4_attrs[] = {
+	ATTR_LIST(delayed_allocation_blocks),
+	ATTR_LIST(session_write_kbytes),
+	ATTR_LIST(lifetime_write_kbytes),
+	ATTR_LIST(extent_cache_hits),
+	ATTR_LIST(extent_cache_misses),
+	ATTR_LIST(inode_readahead_blks),
+	ATTR_LIST(inode_goal),
+	ATTR_LIST(mb_stats),
+	ATTR_LIST(mb_max_to_scan),
+	ATTR_LIST(mb_min_to_scan),
+	ATTR_LIST(mb_order2_req),
+	ATTR_LIST(mb_stream_req),
+	ATTR_LIST(mb_group_prealloc),
+	ATTR_LIST(max_writeback_mb_bump),
+	NULL,
+};
+
+/* Features this copy of ext4 supports */
+EXT4_INFO_ATTR(lazy_itable_init);
+EXT4_INFO_ATTR(batched_discard);
+
+static struct attribute *ext4_feat_attrs[] = {
+	ATTR_LIST(lazy_itable_init),
+	ATTR_LIST(batched_discard),
+	NULL,
+};
+
+static ssize_t ext4_attr_show(struct kobject *kobj,
+			      struct attribute *attr, char *buf)
+{
+	struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
+						s_kobj);
+	struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
+
+	return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static ssize_t ext4_attr_store(struct kobject *kobj,
+			       struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
+						s_kobj);
+	struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
+
+	return a->store ? a->store(a, sbi, buf, len) : 0;
+}
+
+static void ext4_sb_release(struct kobject *kobj)
+{
+	struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
+						s_kobj);
+	complete(&sbi->s_kobj_unregister);
+}
+
+static const struct sysfs_ops ext4_attr_ops = {
+	.show	= ext4_attr_show,
+	.store	= ext4_attr_store,
+};
+
+static struct kobj_type ext4_ktype = {
+	.default_attrs	= ext4_attrs,
+	.sysfs_ops	= &ext4_attr_ops,
+	.release	= ext4_sb_release,
+};
+
+static void ext4_feat_release(struct kobject *kobj)
+{
+	complete(&ext4_feat->f_kobj_unregister);
+}
+
+static struct kobj_type ext4_feat_ktype = {
+	.default_attrs	= ext4_feat_attrs,
+	.sysfs_ops	= &ext4_attr_ops,
+	.release	= ext4_feat_release,
+};
+
+/*
+ * Check whether this filesystem can be mounted based on
+ * the features present and the RDONLY/RDWR mount requested.
+ * Returns 1 if this filesystem can be mounted as requested,
+ * 0 if it cannot be.
+ */
+static int ext4_feature_set_ok(struct super_block *sb, int readonly)
+{
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) {
+		ext4_msg(sb, KERN_ERR,
+			"Couldn't mount because of "
+			"unsupported optional features (%x)",
+			(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
+			~EXT4_FEATURE_INCOMPAT_SUPP));
+		return 0;
+	}
+
+	if (readonly)
+		return 1;
+
+	/* Check that feature set is OK for a read-write mount */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) {
+		ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
+			 "unsupported optional features (%x)",
+			 (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
+				~EXT4_FEATURE_RO_COMPAT_SUPP));
+		return 0;
+	}
+	/*
+	 * Large file size enabled file system can only be mounted
+	 * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF
+	 */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+		if (sizeof(blkcnt_t) < sizeof(u64)) {
+			ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
+				 "cannot be mounted RDWR without "
+				 "CONFIG_LBDAF");
+			return 0;
+		}
+	}
+	return 1;
+}
+
+/*
+ * This function is called once a day if we have errors logged
+ * on the file system
+ */
+static void print_daily_error_info(unsigned long arg)
+{
+	struct super_block *sb = (struct super_block *) arg;
+	struct ext4_sb_info *sbi;
+	struct ext4_super_block *es;
+
+	sbi = EXT4_SB(sb);
+	es = sbi->s_es;
+
+	if (es->s_error_count)
+		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+			 le32_to_cpu(es->s_error_count));
+	if (es->s_first_error_time) {
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		       sb->s_id, le32_to_cpu(es->s_first_error_time),
+		       (int) sizeof(es->s_first_error_func),
+		       es->s_first_error_func,
+		       le32_to_cpu(es->s_first_error_line));
+		if (es->s_first_error_ino)
+			printk(": inode %u",
+			       le32_to_cpu(es->s_first_error_ino));
+		if (es->s_first_error_block)
+			printk(": block %llu", (unsigned long long)
+			       le64_to_cpu(es->s_first_error_block));
+		printk("\n");
+	}
+	if (es->s_last_error_time) {
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		       sb->s_id, le32_to_cpu(es->s_last_error_time),
+		       (int) sizeof(es->s_last_error_func),
+		       es->s_last_error_func,
+		       le32_to_cpu(es->s_last_error_line));
+		if (es->s_last_error_ino)
+			printk(": inode %u",
+			       le32_to_cpu(es->s_last_error_ino));
+		if (es->s_last_error_block)
+			printk(": block %llu", (unsigned long long)
+			       le64_to_cpu(es->s_last_error_block));
+		printk("\n");
+	}
+	mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ);  /* Once a day */
+}
+
+/* Find next suitable group and run ext4_init_inode_table */
+static int ext4_run_li_request(struct ext4_li_request *elr)
+{
+	struct ext4_group_desc *gdp = NULL;
+	ext4_group_t group, ngroups;
+	struct super_block *sb;
+	unsigned long timeout = 0;
+	int ret = 0;
+
+	sb = elr->lr_super;
+	ngroups = EXT4_SB(sb)->s_groups_count;
+
+	for (group = elr->lr_next_group; group < ngroups; group++) {
+		gdp = ext4_get_group_desc(sb, group, NULL);
+		if (!gdp) {
+			ret = 1;
+			break;
+		}
+
+		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			break;
+	}
+
+	if (group == ngroups)
+		ret = 1;
+
+	if (!ret) {
+		timeout = jiffies;
+		ret = ext4_init_inode_table(sb, group,
+					    elr->lr_timeout ? 0 : 1);
+		if (elr->lr_timeout == 0) {
+			timeout = (jiffies - timeout) *
+				  elr->lr_sbi->s_li_wait_mult;
+			elr->lr_timeout = timeout;
+		}
+		elr->lr_next_sched = jiffies + elr->lr_timeout;
+		elr->lr_next_group = group + 1;
+	}
+
+	return ret;
+}
+
+/*
+ * Remove lr_request from the list_request and free the
+ * request structure. Should be called with li_list_mtx held
+ */
+static void ext4_remove_li_request(struct ext4_li_request *elr)
+{
+	struct ext4_sb_info *sbi;
+
+	if (!elr)
+		return;
+
+	sbi = elr->lr_sbi;
+
+	list_del(&elr->lr_request);
+	sbi->s_li_request = NULL;
+	kfree(elr);
+}
+
+static void ext4_unregister_li_request(struct super_block *sb)
+{
+	mutex_lock(&ext4_li_mtx);
+	if (!ext4_li_info) {
+		mutex_unlock(&ext4_li_mtx);
+		return;
+	}
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	ext4_remove_li_request(EXT4_SB(sb)->s_li_request);
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+	mutex_unlock(&ext4_li_mtx);
+}
+
+static struct task_struct *ext4_lazyinit_task;
+
+/*
+ * This is the function where ext4lazyinit thread lives. It walks
+ * through the request list searching for next scheduled filesystem.
+ * When such a fs is found, run the lazy initialization request
+ * (ext4_rn_li_request) and keep track of the time spend in this
+ * function. Based on that time we compute next schedule time of
+ * the request. When walking through the list is complete, compute
+ * next waking time and put itself into sleep.
+ */
+static int ext4_lazyinit_thread(void *arg)
+{
+	struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+	struct list_head *pos, *n;
+	struct ext4_li_request *elr;
+	unsigned long next_wakeup, cur;
+
+	BUG_ON(NULL == eli);
+
+cont_thread:
+	while (true) {
+		next_wakeup = MAX_JIFFY_OFFSET;
+
+		mutex_lock(&eli->li_list_mtx);
+		if (list_empty(&eli->li_request_list)) {
+			mutex_unlock(&eli->li_list_mtx);
+			goto exit_thread;
+		}
+
+		list_for_each_safe(pos, n, &eli->li_request_list) {
+			elr = list_entry(pos, struct ext4_li_request,
+					 lr_request);
+
+			if (time_after_eq(jiffies, elr->lr_next_sched)) {
+				if (ext4_run_li_request(elr) != 0) {
+					/* error, remove the lazy_init job */
+					ext4_remove_li_request(elr);
+					continue;
+				}
+			}
+
+			if (time_before(elr->lr_next_sched, next_wakeup))
+				next_wakeup = elr->lr_next_sched;
+		}
+		mutex_unlock(&eli->li_list_mtx);
+
+		if (freezing(current))
+			refrigerator();
+
+		cur = jiffies;
+		if ((time_after_eq(cur, next_wakeup)) ||
+		    (MAX_JIFFY_OFFSET == next_wakeup)) {
+			cond_resched();
+			continue;
+		}
+
+		schedule_timeout_interruptible(next_wakeup - cur);
+
+		if (kthread_should_stop()) {
+			ext4_clear_request_list();
+			goto exit_thread;
+		}
+	}
+
+exit_thread:
+	/*
+	 * It looks like the request list is empty, but we need
+	 * to check it under the li_list_mtx lock, to prevent any
+	 * additions into it, and of course we should lock ext4_li_mtx
+	 * to atomically free the list and ext4_li_info, because at
+	 * this point another ext4 filesystem could be registering
+	 * new one.
+	 */
+	mutex_lock(&ext4_li_mtx);
+	mutex_lock(&eli->li_list_mtx);
+	if (!list_empty(&eli->li_request_list)) {
+		mutex_unlock(&eli->li_list_mtx);
+		mutex_unlock(&ext4_li_mtx);
+		goto cont_thread;
+	}
+	mutex_unlock(&eli->li_list_mtx);
+	kfree(ext4_li_info);
+	ext4_li_info = NULL;
+	mutex_unlock(&ext4_li_mtx);
+
+	return 0;
+}
+
+static void ext4_clear_request_list(void)
+{
+	struct list_head *pos, *n;
+	struct ext4_li_request *elr;
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
+		elr = list_entry(pos, struct ext4_li_request,
+				 lr_request);
+		ext4_remove_li_request(elr);
+	}
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static int ext4_run_lazyinit_thread(void)
+{
+	ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
+					 ext4_li_info, "ext4lazyinit");
+	if (IS_ERR(ext4_lazyinit_task)) {
+		int err = PTR_ERR(ext4_lazyinit_task);
+		ext4_clear_request_list();
+		kfree(ext4_li_info);
+		ext4_li_info = NULL;
+		printk(KERN_CRIT "EXT4: error %d creating inode table "
+				 "initialization thread\n",
+				 err);
+		return err;
+	}
+	ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
+	return 0;
+}
+
+/*
+ * Check whether it make sense to run itable init. thread or not.
+ * If there is at least one uninitialized inode table, return
+ * corresponding group number, else the loop goes through all
+ * groups and return total number of groups.
+ */
+static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
+{
+	ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
+	struct ext4_group_desc *gdp = NULL;
+
+	for (group = 0; group < ngroups; group++) {
+		gdp = ext4_get_group_desc(sb, group, NULL);
+		if (!gdp)
+			continue;
+
+		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			break;
+	}
+
+	return group;
+}
+
+static int ext4_li_info_new(void)
+{
+	struct ext4_lazy_init *eli = NULL;
+
+	eli = kzalloc(sizeof(*eli), GFP_KERNEL);
+	if (!eli)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&eli->li_request_list);
+	mutex_init(&eli->li_list_mtx);
+
+	eli->li_state |= EXT4_LAZYINIT_QUIT;
+
+	ext4_li_info = eli;
+
+	return 0;
+}
+
+static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
+					    ext4_group_t start)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_li_request *elr;
+	unsigned long rnd;
+
+	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
+	if (!elr)
+		return NULL;
+
+	elr->lr_super = sb;
+	elr->lr_sbi = sbi;
+	elr->lr_next_group = start;
+
+	/*
+	 * Randomize first schedule time of the request to
+	 * spread the inode table initialization requests
+	 * better.
+	 */
+	get_random_bytes(&rnd, sizeof(rnd));
+	elr->lr_next_sched = jiffies + (unsigned long)rnd %
+			     (EXT4_DEF_LI_MAX_START_DELAY * HZ);
+
+	return elr;
+}
+
+static int ext4_register_li_request(struct super_block *sb,
+				    ext4_group_t first_not_zeroed)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_li_request *elr;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	int ret = 0;
+
+	if (sbi->s_li_request != NULL) {
+		/*
+		 * Reset timeout so it can be computed again, because
+		 * s_li_wait_mult might have changed.
+		 */
+		sbi->s_li_request->lr_timeout = 0;
+		return 0;
+	}
+
+	if (first_not_zeroed == ngroups ||
+	    (sb->s_flags & MS_RDONLY) ||
+	    !test_opt(sb, INIT_INODE_TABLE))
+		return 0;
+
+	elr = ext4_li_request_new(sb, first_not_zeroed);
+	if (!elr)
+		return -ENOMEM;
+
+	mutex_lock(&ext4_li_mtx);
+
+	if (NULL == ext4_li_info) {
+		ret = ext4_li_info_new();
+		if (ret)
+			goto out;
+	}
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	list_add(&elr->lr_request, &ext4_li_info->li_request_list);
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+
+	sbi->s_li_request = elr;
+	/*
+	 * set elr to NULL here since it has been inserted to
+	 * the request_list and the removal and free of it is
+	 * handled by ext4_clear_request_list from now on.
+	 */
+	elr = NULL;
+
+	if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
+		ret = ext4_run_lazyinit_thread();
+		if (ret)
+			goto out;
+	}
+out:
+	mutex_unlock(&ext4_li_mtx);
+	if (ret)
+		kfree(elr);
+	return ret;
+}
+
+/*
+ * We do not need to lock anything since this is called on
+ * module unload.
+ */
+static void ext4_destroy_lazyinit_thread(void)
+{
+	/*
+	 * If thread exited earlier
+	 * there's nothing to be done.
+	 */
+	if (!ext4_li_info || !ext4_lazyinit_task)
+		return;
+
+	kthread_stop(ext4_lazyinit_task);
+}
+
+static int ext4_fill_super(struct super_block *sb, void *data, int silent)
+				__releases(kernel_lock)
+				__acquires(kernel_lock)
+{
+	char *orig_data = kstrdup(data, GFP_KERNEL);
+	struct buffer_head *bh;
+	struct ext4_super_block *es = NULL;
+	struct ext4_sb_info *sbi;
+	ext4_fsblk_t block;
+	ext4_fsblk_t sb_block = get_sb_block(&data);
+	ext4_fsblk_t logical_sb_block;
+	unsigned long offset = 0;
+	unsigned long journal_devnum = 0;
+	unsigned long def_mount_opts;
+	struct inode *root;
+	char *cp;
+	const char *descr;
+	int ret = -ENOMEM;
+	int blocksize;
+	unsigned int db_count;
+	unsigned int i;
+	int needs_recovery, has_huge_files;
+	__u64 blocks_count;
+	int err;
+	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	ext4_group_t first_not_zeroed;
+
+	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	if (!sbi)
+		goto out_free_orig;
+
+	sbi->s_blockgroup_lock =
+		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
+	if (!sbi->s_blockgroup_lock) {
+		kfree(sbi);
+		goto out_free_orig;
+	}
+	sb->s_fs_info = sbi;
+	sbi->s_mount_opt = 0;
+	sbi->s_resuid = EXT4_DEF_RESUID;
+	sbi->s_resgid = EXT4_DEF_RESGID;
+	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
+	sbi->s_sb_block = sb_block;
+	if (sb->s_bdev->bd_part)
+		sbi->s_sectors_written_start =
+			part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+
+	/* Cleanup superblock name */
+	for (cp = sb->s_id; (cp = strchr(cp, '/'));)
+		*cp = '!';
+
+	ret = -EINVAL;
+	blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
+	if (!blocksize) {
+		ext4_msg(sb, KERN_ERR, "unable to set blocksize");
+		goto out_fail;
+	}
+
+	/*
+	 * The ext4 superblock will not be buffer aligned for other than 1kB
+	 * block sizes.  We need to calculate the offset from buffer start.
+	 */
+	if (blocksize != EXT4_MIN_BLOCK_SIZE) {
+		logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
+		offset = do_div(logical_sb_block, blocksize);
+	} else {
+		logical_sb_block = sb_block;
+	}
+
+	if (!(bh = sb_bread(sb, logical_sb_block))) {
+		ext4_msg(sb, KERN_ERR, "unable to read superblock");
+		goto out_fail;
+	}
+	/*
+	 * Note: s_es must be initialized as soon as possible because
+	 *       some ext4 macro-instructions depend on its value
+	 */
+	es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
+	sbi->s_es = es;
+	sb->s_magic = le16_to_cpu(es->s_magic);
+	if (sb->s_magic != EXT4_SUPER_MAGIC)
+		goto cantfind_ext4;
+	sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written);
+
+	/* Set defaults before we parse the mount options */
+	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+	set_opt(sb, INIT_INODE_TABLE);
+	if (def_mount_opts & EXT4_DEFM_DEBUG)
+		set_opt(sb, DEBUG);
+	if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
+		ext4_msg(sb, KERN_WARNING, deprecated_msg, "bsdgroups",
+			"2.6.38");
+		set_opt(sb, GRPID);
+	}
+	if (def_mount_opts & EXT4_DEFM_UID16)
+		set_opt(sb, NO_UID32);
+	/* xattr user namespace & acls are now defaulted on */
+#ifdef CONFIG_EXT4_FS_XATTR
+	set_opt(sb, XATTR_USER);
+#endif
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	set_opt(sb, POSIX_ACL);
+#endif
+	set_opt(sb, MBLK_IO_SUBMIT);
+	if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
+		set_opt(sb, JOURNAL_DATA);
+	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
+		set_opt(sb, ORDERED_DATA);
+	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
+		set_opt(sb, WRITEBACK_DATA);
+
+	if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
+		set_opt(sb, ERRORS_PANIC);
+	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE)
+		set_opt(sb, ERRORS_CONT);
+	else
+		set_opt(sb, ERRORS_RO);
+	if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
+		set_opt(sb, BLOCK_VALIDITY);
+	if (def_mount_opts & EXT4_DEFM_DISCARD)
+		set_opt(sb, DISCARD);
+
+	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
+	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+	sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
+	sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
+	sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
+
+	if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0)
+		set_opt(sb, BARRIER);
+
+	/*
+	 * enable delayed allocation by default
+	 * Use -o nodelalloc to turn it off
+	 */
+	if (!IS_EXT3_SB(sb) &&
+	    ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
+		set_opt(sb, DELALLOC);
+
+	/*
+	 * set default s_li_wait_mult for lazyinit, for the case there is
+	 * no mount option specified.
+	 */
+	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
+
+	if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
+			   &journal_devnum, &journal_ioprio, NULL, 0)) {
+		ext4_msg(sb, KERN_WARNING,
+			 "failed to parse options in superblock: %s",
+			 sbi->s_es->s_mount_opts);
+	}
+	if (!parse_options((char *) data, sb, &journal_devnum,
+			   &journal_ioprio, NULL, 0))
+		goto failed_mount;
+
+	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+		(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
+
+	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
+	    (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
+	     EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
+	     EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
+		ext4_msg(sb, KERN_WARNING,
+		       "feature flags set on rev 0 fs, "
+		       "running e2fsck is recommended");
+
+	if (IS_EXT2_SB(sb)) {
+		if (ext2_feature_set_ok(sb))
+			ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
+				 "using the ext4 subsystem");
+		else {
+			ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due "
+				 "to feature incompatibilities");
+			goto failed_mount;
+		}
+	}
+
+	if (IS_EXT3_SB(sb)) {
+		if (ext3_feature_set_ok(sb))
+			ext4_msg(sb, KERN_INFO, "mounting ext3 file system "
+				 "using the ext4 subsystem");
+		else {
+			ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due "
+				 "to feature incompatibilities");
+			goto failed_mount;
+		}
+	}
+
+	/*
+	 * Check feature flags regardless of the revision level, since we
+	 * previously didn't change the revision level when setting the flags,
+	 * so there is a chance incompat flags are set on a rev 0 filesystem.
+	 */
+	if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
+		goto failed_mount;
+
+	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+
+	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
+	    blocksize > EXT4_MAX_BLOCK_SIZE) {
+		ext4_msg(sb, KERN_ERR,
+		       "Unsupported filesystem blocksize %d", blocksize);
+		goto failed_mount;
+	}
+
+	if (sb->s_blocksize != blocksize) {
+		/* Validate the filesystem blocksize */
+		if (!sb_set_blocksize(sb, blocksize)) {
+			ext4_msg(sb, KERN_ERR, "bad block size %d",
+					blocksize);
+			goto failed_mount;
+		}
+
+		brelse(bh);
+		logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
+		offset = do_div(logical_sb_block, blocksize);
+		bh = sb_bread(sb, logical_sb_block);
+		if (!bh) {
+			ext4_msg(sb, KERN_ERR,
+			       "Can't read superblock on 2nd try");
+			goto failed_mount;
+		}
+		es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
+		sbi->s_es = es;
+		if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
+			ext4_msg(sb, KERN_ERR,
+			       "Magic mismatch, very weird!");
+			goto failed_mount;
+		}
+	}
+
+	has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
+	sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
+						      has_huge_files);
+	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
+
+	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
+		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
+		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
+	} else {
+		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
+		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
+		    (!is_power_of_2(sbi->s_inode_size)) ||
+		    (sbi->s_inode_size > blocksize)) {
+			ext4_msg(sb, KERN_ERR,
+			       "unsupported inode size: %d",
+			       sbi->s_inode_size);
+			goto failed_mount;
+		}
+		if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
+			sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
+	}
+
+	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
+		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
+		    sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
+		    !is_power_of_2(sbi->s_desc_size)) {
+			ext4_msg(sb, KERN_ERR,
+			       "unsupported descriptor size %lu",
+			       sbi->s_desc_size);
+			goto failed_mount;
+		}
+	} else
+		sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
+
+	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
+	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
+	if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
+		goto cantfind_ext4;
+
+	sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
+	if (sbi->s_inodes_per_block == 0)
+		goto cantfind_ext4;
+	sbi->s_itb_per_group = sbi->s_inodes_per_group /
+					sbi->s_inodes_per_block;
+	sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
+	sbi->s_sbh = bh;
+	sbi->s_mount_state = le16_to_cpu(es->s_state);
+	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
+	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
+
+	for (i = 0; i < 4; i++)
+		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
+	sbi->s_def_hash_version = es->s_def_hash_version;
+	i = le32_to_cpu(es->s_flags);
+	if (i & EXT2_FLAGS_UNSIGNED_HASH)
+		sbi->s_hash_unsigned = 3;
+	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+		sbi->s_hash_unsigned = 3;
+#else
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+		sb->s_dirt = 1;
+	}
+
+	if (sbi->s_blocks_per_group > blocksize * 8) {
+		ext4_msg(sb, KERN_ERR,
+		       "#blocks per group too big: %lu",
+		       sbi->s_blocks_per_group);
+		goto failed_mount;
+	}
+	if (sbi->s_inodes_per_group > blocksize * 8) {
+		ext4_msg(sb, KERN_ERR,
+		       "#inodes per group too big: %lu",
+		       sbi->s_inodes_per_group);
+		goto failed_mount;
+	}
+
+	/*
+	 * Test whether we have more sectors than will fit in sector_t,
+	 * and whether the max offset is addressable by the page cache.
+	 */
+	err = generic_check_addressable(sb->s_blocksize_bits,
+					ext4_blocks_count(es));
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "filesystem"
+			 " too large to mount safely on this system");
+		if (sizeof(sector_t) < 8)
+			ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
+		ret = err;
+		goto failed_mount;
+	}
+
+	if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
+		goto cantfind_ext4;
+
+	/* check blocks count against device size */
+	blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+	if (blocks_count && ext4_blocks_count(es) > blocks_count) {
+		ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu "
+		       "exceeds size of device (%llu blocks)",
+		       ext4_blocks_count(es), blocks_count);
+		goto failed_mount;
+	}
+
+	/*
+	 * It makes no sense for the first data block to be beyond the end
+	 * of the filesystem.
+	 */
+	if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
+                ext4_msg(sb, KERN_WARNING, "bad geometry: first data"
+			 "block %u is beyond end of filesystem (%llu)",
+			 le32_to_cpu(es->s_first_data_block),
+			 ext4_blocks_count(es));
+		goto failed_mount;
+	}
+	blocks_count = (ext4_blocks_count(es) -
+			le32_to_cpu(es->s_first_data_block) +
+			EXT4_BLOCKS_PER_GROUP(sb) - 1);
+	do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
+	if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
+		ext4_msg(sb, KERN_WARNING, "groups count too large: %u "
+		       "(block count %llu, first data block %u, "
+		       "blocks per group %lu)", sbi->s_groups_count,
+		       ext4_blocks_count(es),
+		       le32_to_cpu(es->s_first_data_block),
+		       EXT4_BLOCKS_PER_GROUP(sb));
+		goto failed_mount;
+	}
+	sbi->s_groups_count = blocks_count;
+	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
+	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
+		   EXT4_DESC_PER_BLOCK(sb);
+	sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
+				    GFP_KERNEL);
+	if (sbi->s_group_desc == NULL) {
+		ext4_msg(sb, KERN_ERR, "not enough memory");
+		goto failed_mount;
+	}
+
+#ifdef CONFIG_PROC_FS
+	if (ext4_proc_root)
+		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
+#endif
+
+	bgl_lock_init(sbi->s_blockgroup_lock);
+
+	for (i = 0; i < db_count; i++) {
+		block = descriptor_loc(sb, logical_sb_block, i);
+		sbi->s_group_desc[i] = sb_bread(sb, block);
+		if (!sbi->s_group_desc[i]) {
+			ext4_msg(sb, KERN_ERR,
+			       "can't read group descriptor %d", i);
+			db_count = i;
+			goto failed_mount2;
+		}
+	}
+	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
+		goto failed_mount2;
+	}
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+		if (!ext4_fill_flex_info(sb)) {
+			ext4_msg(sb, KERN_ERR,
+			       "unable to initialize "
+			       "flex_bg meta info!");
+			goto failed_mount2;
+		}
+
+	sbi->s_gdb_count = db_count;
+	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
+	spin_lock_init(&sbi->s_next_gen_lock);
+
+	init_timer(&sbi->s_err_report);
+	sbi->s_err_report.function = print_daily_error_info;
+	sbi->s_err_report.data = (unsigned long) sb;
+
+	err = percpu_counter_init(&sbi->s_freeblocks_counter,
+			ext4_count_free_blocks(sb));
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_freeinodes_counter,
+				ext4_count_free_inodes(sb));
+	}
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_dirs_counter,
+				ext4_count_dirs(sb));
+	}
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+	}
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "insufficient memory");
+		goto failed_mount3;
+	}
+
+	sbi->s_stripe = ext4_get_stripe_size(sbi);
+	sbi->s_max_writeback_mb_bump = 128;
+
+	/*
+	 * set up enough so that it can read an inode
+	 */
+	if (!test_opt(sb, NOLOAD) &&
+	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		sb->s_op = &ext4_sops;
+	else
+		sb->s_op = &ext4_nojournal_sops;
+	sb->s_export_op = &ext4_export_ops;
+	sb->s_xattr = ext4_xattr_handlers;
+#ifdef CONFIG_QUOTA
+	sb->s_qcop = &ext4_qctl_operations;
+	sb->dq_op = &ext4_quota_operations;
+#endif
+	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+
+	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
+	mutex_init(&sbi->s_orphan_lock);
+	mutex_init(&sbi->s_resize_lock);
+
+	sb->s_root = NULL;
+
+	needs_recovery = (es->s_last_orphan != 0 ||
+			  EXT4_HAS_INCOMPAT_FEATURE(sb,
+				    EXT4_FEATURE_INCOMPAT_RECOVER));
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
+	    !(sb->s_flags & MS_RDONLY))
+		if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
+			goto failed_mount3;
+
+	/*
+	 * The first inode we look at is the journal inode.  Don't try
+	 * root first: it may be modified in the journal!
+	 */
+	if (!test_opt(sb, NOLOAD) &&
+	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+		if (ext4_load_journal(sb, es, journal_devnum))
+			goto failed_mount3;
+	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
+	      EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+		ext4_msg(sb, KERN_ERR, "required journal recovery "
+		       "suppressed and not mounted read-only");
+		goto failed_mount_wq;
+	} else {
+		clear_opt(sb, DATA_FLAGS);
+		sbi->s_journal = NULL;
+		needs_recovery = 0;
+		goto no_journal;
+	}
+
+	if (ext4_blocks_count(es) > 0xffffffffULL &&
+	    !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+				       JBD2_FEATURE_INCOMPAT_64BIT)) {
+		ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
+		goto failed_mount_wq;
+	}
+
+	if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+		jbd2_journal_set_features(sbi->s_journal,
+				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+	} else if (test_opt(sb, JOURNAL_CHECKSUM)) {
+		jbd2_journal_set_features(sbi->s_journal,
+				JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
+		jbd2_journal_clear_features(sbi->s_journal, 0, 0,
+				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+	} else {
+		jbd2_journal_clear_features(sbi->s_journal,
+				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+	}
+
+	/* We have now updated the journal if required, so we can
+	 * validate the data journaling mode. */
+	switch (test_opt(sb, DATA_FLAGS)) {
+	case 0:
+		/* No mode set, assume a default based on the journal
+		 * capabilities: ORDERED_DATA if the journal can
+		 * cope, else JOURNAL_DATA
+		 */
+		if (jbd2_journal_check_available_features
+		    (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
+			set_opt(sb, ORDERED_DATA);
+		else
+			set_opt(sb, JOURNAL_DATA);
+		break;
+
+	case EXT4_MOUNT_ORDERED_DATA:
+	case EXT4_MOUNT_WRITEBACK_DATA:
+		if (!jbd2_journal_check_available_features
+		    (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
+			ext4_msg(sb, KERN_ERR, "Journal does not support "
+			       "requested data journaling mode");
+			goto failed_mount_wq;
+		}
+	default:
+		break;
+	}
+	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+
+	/*
+	 * The journal may have updated the bg summary counts, so we
+	 * need to update the global counters.
+	 */
+	percpu_counter_set(&sbi->s_freeblocks_counter,
+			   ext4_count_free_blocks(sb));
+	percpu_counter_set(&sbi->s_freeinodes_counter,
+			   ext4_count_free_inodes(sb));
+	percpu_counter_set(&sbi->s_dirs_counter,
+			   ext4_count_dirs(sb));
+	percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
+
+no_journal:
+	/*
+	 * The maximum number of concurrent works can be high and
+	 * concurrency isn't really necessary.  Limit it to 1.
+	 */
+	EXT4_SB(sb)->dio_unwritten_wq =
+		alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+	if (!EXT4_SB(sb)->dio_unwritten_wq) {
+		printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+		goto failed_mount_wq;
+	}
+
+	/*
+	 * The jbd2_journal_load will have done any necessary log recovery,
+	 * so we can safely mount the rest of the filesystem now.
+	 */
+
+	root = ext4_iget(sb, EXT4_ROOT_INO);
+	if (IS_ERR(root)) {
+		ext4_msg(sb, KERN_ERR, "get root inode failed");
+		ret = PTR_ERR(root);
+		root = NULL;
+		goto failed_mount4;
+	}
+	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
+		ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
+		goto failed_mount4;
+	}
+	sb->s_root = d_alloc_root(root);
+	if (!sb->s_root) {
+		ext4_msg(sb, KERN_ERR, "get root dentry failed");
+		ret = -ENOMEM;
+		goto failed_mount4;
+	}
+
+	if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
+		sb->s_flags |= MS_RDONLY;
+
+	/* determine the minimum size of new large inodes, if present */
+	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
+		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+						     EXT4_GOOD_OLD_INODE_SIZE;
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+				       EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE)) {
+			if (sbi->s_want_extra_isize <
+			    le16_to_cpu(es->s_want_extra_isize))
+				sbi->s_want_extra_isize =
+					le16_to_cpu(es->s_want_extra_isize);
+			if (sbi->s_want_extra_isize <
+			    le16_to_cpu(es->s_min_extra_isize))
+				sbi->s_want_extra_isize =
+					le16_to_cpu(es->s_min_extra_isize);
+		}
+	}
+	/* Check if enough inode space is available */
+	if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
+							sbi->s_inode_size) {
+		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+						       EXT4_GOOD_OLD_INODE_SIZE;
+		ext4_msg(sb, KERN_INFO, "required extra inode space not"
+			 "available");
+	}
+
+	if (test_opt(sb, DELALLOC) &&
+	    (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
+		ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
+			 "requested data journaling mode");
+		clear_opt(sb, DELALLOC);
+	}
+	if (test_opt(sb, DIOREAD_NOLOCK)) {
+		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+			ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+				"option - requested data journaling mode");
+			clear_opt(sb, DIOREAD_NOLOCK);
+		}
+		if (sb->s_blocksize < PAGE_SIZE) {
+			ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+				"option - block size is too small");
+			clear_opt(sb, DIOREAD_NOLOCK);
+		}
+	}
+
+	err = ext4_setup_system_zone(sb);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to initialize system "
+			 "zone (%d)", err);
+		goto failed_mount4;
+	}
+
+	ext4_ext_init(sb);
+	err = ext4_mb_init(sb, needs_recovery);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
+			 err);
+		goto failed_mount4;
+	}
+
+	err = ext4_register_li_request(sb, first_not_zeroed);
+	if (err)
+		goto failed_mount4;
+
+	sbi->s_kobj.kset = ext4_kset;
+	init_completion(&sbi->s_kobj_unregister);
+	err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
+				   "%s", sb->s_id);
+	if (err) {
+		ext4_mb_release(sb);
+		ext4_ext_release(sb);
+		goto failed_mount4;
+	};
+
+	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
+	ext4_orphan_cleanup(sb, es);
+	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
+	if (needs_recovery) {
+		ext4_msg(sb, KERN_INFO, "recovery complete");
+		ext4_mark_recovery_complete(sb, es);
+	}
+	if (EXT4_SB(sb)->s_journal) {
+		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+			descr = " journalled data mode";
+		else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+			descr = " ordered data mode";
+		else
+			descr = " writeback data mode";
+	} else
+		descr = "out journal";
+
+	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
+		 "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
+		 *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
+
+	if (es->s_error_count)
+		mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
+
+	kfree(orig_data);
+	return 0;
+
+cantfind_ext4:
+	if (!silent)
+		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
+	goto failed_mount;
+
+failed_mount4:
+	iput(root);
+	sb->s_root = NULL;
+	ext4_msg(sb, KERN_ERR, "mount failed");
+	destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
+failed_mount_wq:
+	ext4_release_system_zone(sb);
+	if (sbi->s_journal) {
+		jbd2_journal_destroy(sbi->s_journal);
+		sbi->s_journal = NULL;
+	}
+failed_mount3:
+	del_timer(&sbi->s_err_report);
+	if (sbi->s_flex_groups) {
+		if (is_vmalloc_addr(sbi->s_flex_groups))
+			vfree(sbi->s_flex_groups);
+		else
+			kfree(sbi->s_flex_groups);
+	}
+	percpu_counter_destroy(&sbi->s_freeblocks_counter);
+	percpu_counter_destroy(&sbi->s_freeinodes_counter);
+	percpu_counter_destroy(&sbi->s_dirs_counter);
+	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+	if (sbi->s_mmp_tsk)
+		kthread_stop(sbi->s_mmp_tsk);
+failed_mount2:
+	for (i = 0; i < db_count; i++)
+		brelse(sbi->s_group_desc[i]);
+	kfree(sbi->s_group_desc);
+failed_mount:
+	if (sbi->s_proc) {
+		remove_proc_entry(sb->s_id, ext4_proc_root);
+	}
+#ifdef CONFIG_QUOTA
+	for (i = 0; i < MAXQUOTAS; i++)
+		kfree(sbi->s_qf_names[i]);
+#endif
+	ext4_blkdev_remove(sbi);
+	brelse(bh);
+out_fail:
+	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
+	kfree(sbi);
+out_free_orig:
+	kfree(orig_data);
+	return ret;
+}
+
+/*
+ * Setup any per-fs journal parameters now.  We'll do this both on
+ * initial mount, once the journal has been initialised but before we've
+ * done any recovery; and again on any subsequent remount.
+ */
+static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	journal->j_commit_interval = sbi->s_commit_interval;
+	journal->j_min_batch_time = sbi->s_min_batch_time;
+	journal->j_max_batch_time = sbi->s_max_batch_time;
+
+	write_lock(&journal->j_state_lock);
+	if (test_opt(sb, BARRIER))
+		journal->j_flags |= JBD2_BARRIER;
+	else
+		journal->j_flags &= ~JBD2_BARRIER;
+	if (test_opt(sb, DATA_ERR_ABORT))
+		journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
+	else
+		journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
+	write_unlock(&journal->j_state_lock);
+}
+
+static journal_t *ext4_get_journal(struct super_block *sb,
+				   unsigned int journal_inum)
+{
+	struct inode *journal_inode;
+	journal_t *journal;
+
+	BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
+	/* First, test for the existence of a valid inode on disk.  Bad
+	 * things happen if we iget() an unused inode, as the subsequent
+	 * iput() will try to delete it. */
+
+	journal_inode = ext4_iget(sb, journal_inum);
+	if (IS_ERR(journal_inode)) {
+		ext4_msg(sb, KERN_ERR, "no journal found");
+		return NULL;
+	}
+	if (!journal_inode->i_nlink) {
+		make_bad_inode(journal_inode);
+		iput(journal_inode);
+		ext4_msg(sb, KERN_ERR, "journal inode is deleted");
+		return NULL;
+	}
+
+	jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
+		  journal_inode, journal_inode->i_size);
+	if (!S_ISREG(journal_inode->i_mode)) {
+		ext4_msg(sb, KERN_ERR, "invalid journal inode");
+		iput(journal_inode);
+		return NULL;
+	}
+
+	journal = jbd2_journal_init_inode(journal_inode);
+	if (!journal) {
+		ext4_msg(sb, KERN_ERR, "Could not load journal inode");
+		iput(journal_inode);
+		return NULL;
+	}
+	journal->j_private = sb;
+	ext4_init_journal_params(sb, journal);
+	return journal;
+}
+
+static journal_t *ext4_get_dev_journal(struct super_block *sb,
+				       dev_t j_dev)
+{
+	struct buffer_head *bh;
+	journal_t *journal;
+	ext4_fsblk_t start;
+	ext4_fsblk_t len;
+	int hblock, blocksize;
+	ext4_fsblk_t sb_block;
+	unsigned long offset;
+	struct ext4_super_block *es;
+	struct block_device *bdev;
+
+	BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
+	bdev = ext4_blkdev_get(j_dev, sb);
+	if (bdev == NULL)
+		return NULL;
+
+	blocksize = sb->s_blocksize;
+	hblock = bdev_logical_block_size(bdev);
+	if (blocksize < hblock) {
+		ext4_msg(sb, KERN_ERR,
+			"blocksize too small for journal device");
+		goto out_bdev;
+	}
+
+	sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
+	offset = EXT4_MIN_BLOCK_SIZE % blocksize;
+	set_blocksize(bdev, blocksize);
+	if (!(bh = __bread(bdev, sb_block, blocksize))) {
+		ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
+		       "external journal");
+		goto out_bdev;
+	}
+
+	es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
+	if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
+	    !(le32_to_cpu(es->s_feature_incompat) &
+	      EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
+		ext4_msg(sb, KERN_ERR, "external journal has "
+					"bad superblock");
+		brelse(bh);
+		goto out_bdev;
+	}
+
+	if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
+		ext4_msg(sb, KERN_ERR, "journal UUID does not match");
+		brelse(bh);
+		goto out_bdev;
+	}
+
+	len = ext4_blocks_count(es);
+	start = sb_block + 1;
+	brelse(bh);	/* we're done with the superblock */
+
+	journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
+					start, len, blocksize);
+	if (!journal) {
+		ext4_msg(sb, KERN_ERR, "failed to create device journal");
+		goto out_bdev;
+	}
+	journal->j_private = sb;
+	ll_rw_block(READ, 1, &journal->j_sb_buffer);
+	wait_on_buffer(journal->j_sb_buffer);
+	if (!buffer_uptodate(journal->j_sb_buffer)) {
+		ext4_msg(sb, KERN_ERR, "I/O error on journal device");
+		goto out_journal;
+	}
+	if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
+		ext4_msg(sb, KERN_ERR, "External journal has more than one "
+					"user (unsupported) - %d",
+			be32_to_cpu(journal->j_superblock->s_nr_users));
+		goto out_journal;
+	}
+	EXT4_SB(sb)->journal_bdev = bdev;
+	ext4_init_journal_params(sb, journal);
+	return journal;
+
+out_journal:
+	jbd2_journal_destroy(journal);
+out_bdev:
+	ext4_blkdev_put(bdev);
+	return NULL;
+}
+
+static int ext4_load_journal(struct super_block *sb,
+			     struct ext4_super_block *es,
+			     unsigned long journal_devnum)
+{
+	journal_t *journal;
+	unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
+	dev_t journal_dev;
+	int err = 0;
+	int really_read_only;
+
+	BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
+	if (journal_devnum &&
+	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
+		ext4_msg(sb, KERN_INFO, "external journal device major/minor "
+			"numbers have changed");
+		journal_dev = new_decode_dev(journal_devnum);
+	} else
+		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
+
+	really_read_only = bdev_read_only(sb->s_bdev);
+
+	/*
+	 * Are we loading a blank journal or performing recovery after a
+	 * crash?  For recovery, we need to check in advance whether we
+	 * can get read-write access to the device.
+	 */
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+		if (sb->s_flags & MS_RDONLY) {
+			ext4_msg(sb, KERN_INFO, "INFO: recovery "
+					"required on readonly filesystem");
+			if (really_read_only) {
+				ext4_msg(sb, KERN_ERR, "write access "
+					"unavailable, cannot proceed");
+				return -EROFS;
+			}
+			ext4_msg(sb, KERN_INFO, "write access will "
+			       "be enabled during recovery");
+		}
+	}
+
+	if (journal_inum && journal_dev) {
+		ext4_msg(sb, KERN_ERR, "filesystem has both journal "
+		       "and inode journals!");
+		return -EINVAL;
+	}
+
+	if (journal_inum) {
+		if (!(journal = ext4_get_journal(sb, journal_inum)))
+			return -EINVAL;
+	} else {
+		if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
+			return -EINVAL;
+	}
+
+	if (!(journal->j_flags & JBD2_BARRIER))
+		ext4_msg(sb, KERN_INFO, "barriers disabled");
+
+	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
+		err = jbd2_journal_update_format(journal);
+		if (err)  {
+			ext4_msg(sb, KERN_ERR, "error updating journal");
+			jbd2_journal_destroy(journal);
+			return err;
+		}
+	}
+
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
+		err = jbd2_journal_wipe(journal, !really_read_only);
+	if (!err) {
+		char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
+		if (save)
+			memcpy(save, ((char *) es) +
+			       EXT4_S_ERR_START, EXT4_S_ERR_LEN);
+		err = jbd2_journal_load(journal);
+		if (save)
+			memcpy(((char *) es) + EXT4_S_ERR_START,
+			       save, EXT4_S_ERR_LEN);
+		kfree(save);
+	}
+
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "error loading journal");
+		jbd2_journal_destroy(journal);
+		return err;
+	}
+
+	EXT4_SB(sb)->s_journal = journal;
+	ext4_clear_journal_err(sb, es);
+
+	if (!really_read_only && journal_devnum &&
+	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
+		es->s_journal_dev = cpu_to_le32(journal_devnum);
+
+		/* Make sure we flush the recovery flag to disk. */
+		ext4_commit_super(sb, 1);
+	}
+
+	return 0;
+}
+
+static int ext4_commit_super(struct super_block *sb, int sync)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+	int error = 0;
+
+	if (!sbh)
+		return error;
+	if (buffer_write_io_error(sbh)) {
+		/*
+		 * Oh, dear.  A previous attempt to write the
+		 * superblock failed.  This could happen because the
+		 * USB device was yanked out.  Or it could happen to
+		 * be a transient write error and maybe the block will
+		 * be remapped.  Nothing we can do but to retry the
+		 * write and hope for the best.
+		 */
+		ext4_msg(sb, KERN_ERR, "previous I/O error to "
+		       "superblock detected");
+		clear_buffer_write_io_error(sbh);
+		set_buffer_uptodate(sbh);
+	}
+	/*
+	 * If the file system is mounted read-only, don't update the
+	 * superblock write time.  This avoids updating the superblock
+	 * write time when we are mounting the root file system
+	 * read/only but we need to replay the journal; at that point,
+	 * for people who are east of GMT and who make their clock
+	 * tick in localtime for Windows bug-for-bug compatibility,
+	 * the clock is set in the future, and this will cause e2fsck
+	 * to complain and force a full file system check.
+	 */
+	if (!(sb->s_flags & MS_RDONLY))
+		es->s_wtime = cpu_to_le32(get_seconds());
+	if (sb->s_bdev->bd_part)
+		es->s_kbytes_written =
+			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+			    ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
+	else
+		es->s_kbytes_written =
+			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
+	ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
+					   &EXT4_SB(sb)->s_freeblocks_counter));
+	es->s_free_inodes_count =
+		cpu_to_le32(percpu_counter_sum_positive(
+				&EXT4_SB(sb)->s_freeinodes_counter));
+	sb->s_dirt = 0;
+	BUFFER_TRACE(sbh, "marking dirty");
+	mark_buffer_dirty(sbh);
+	if (sync) {
+		error = sync_dirty_buffer(sbh);
+		if (error)
+			return error;
+
+		error = buffer_write_io_error(sbh);
+		if (error) {
+			ext4_msg(sb, KERN_ERR, "I/O error while writing "
+			       "superblock");
+			clear_buffer_write_io_error(sbh);
+			set_buffer_uptodate(sbh);
+		}
+	}
+	return error;
+}
+
+/*
+ * Have we just finished recovery?  If so, and if we are mounting (or
+ * remounting) the filesystem readonly, then we will end up with a
+ * consistent fs on disk.  Record that fact.
+ */
+static void ext4_mark_recovery_complete(struct super_block *sb,
+					struct ext4_super_block *es)
+{
+	journal_t *journal = EXT4_SB(sb)->s_journal;
+
+	if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+		BUG_ON(journal != NULL);
+		return;
+	}
+	jbd2_journal_lock_updates(journal);
+	if (jbd2_journal_flush(journal) < 0)
+		goto out;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
+	    sb->s_flags & MS_RDONLY) {
+		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+		ext4_commit_super(sb, 1);
+	}
+
+out:
+	jbd2_journal_unlock_updates(journal);
+}
+
+/*
+ * If we are mounting (or read-write remounting) a filesystem whose journal
+ * has recorded an error from a previous lifetime, move that error to the
+ * main filesystem now.
+ */
+static void ext4_clear_journal_err(struct super_block *sb,
+				   struct ext4_super_block *es)
+{
+	journal_t *journal;
+	int j_errno;
+	const char *errstr;
+
+	BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
+	journal = EXT4_SB(sb)->s_journal;
+
+	/*
+	 * Now check for any error status which may have been recorded in the
+	 * journal by a prior ext4_error() or ext4_abort()
+	 */
+
+	j_errno = jbd2_journal_errno(journal);
+	if (j_errno) {
+		char nbuf[16];
+
+		errstr = ext4_decode_error(sb, j_errno, nbuf);
+		ext4_warning(sb, "Filesystem error recorded "
+			     "from previous mount: %s", errstr);
+		ext4_warning(sb, "Marking fs in need of filesystem check.");
+
+		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+		ext4_commit_super(sb, 1);
+
+		jbd2_journal_clear_err(journal);
+	}
+}
+
+/*
+ * Force the running and committing transactions to commit,
+ * and wait on the commit.
+ */
+int ext4_force_commit(struct super_block *sb)
+{
+	journal_t *journal;
+	int ret = 0;
+
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	journal = EXT4_SB(sb)->s_journal;
+	if (journal) {
+		vfs_check_frozen(sb, SB_FREEZE_TRANS);
+		ret = ext4_journal_force_commit(journal);
+	}
+
+	return ret;
+}
+
+static void ext4_write_super(struct super_block *sb)
+{
+	lock_super(sb);
+	ext4_commit_super(sb, 1);
+	unlock_super(sb);
+}
+
+static int ext4_sync_fs(struct super_block *sb, int wait)
+{
+	int ret = 0;
+	tid_t target;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	trace_ext4_sync_fs(sb, wait);
+	flush_workqueue(sbi->dio_unwritten_wq);
+	if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
+		if (wait)
+			jbd2_log_wait_commit(sbi->s_journal, target);
+	}
+	return ret;
+}
+
+/*
+ * LVM calls this function before a (read-only) snapshot is created.  This
+ * gives us a chance to flush the journal completely and mark the fs clean.
+ *
+ * Note that only this function cannot bring a filesystem to be in a clean
+ * state independently, because ext4 prevents a new handle from being started
+ * by @sb->s_frozen, which stays in an upper layer.  It thus needs help from
+ * the upper layer.
+ */
+static int ext4_freeze(struct super_block *sb)
+{
+	int error = 0;
+	journal_t *journal;
+
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	journal = EXT4_SB(sb)->s_journal;
+
+	/* Now we set up the journal barrier. */
+	jbd2_journal_lock_updates(journal);
+
+	/*
+	 * Don't clear the needs_recovery flag if we failed to flush
+	 * the journal.
+	 */
+	error = jbd2_journal_flush(journal);
+	if (error < 0)
+		goto out;
+
+	/* Journal blocked and flushed, clear needs_recovery flag. */
+	EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+	error = ext4_commit_super(sb, 1);
+out:
+	/* we rely on s_frozen to stop further updates */
+	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+	return error;
+}
+
+/*
+ * Called by LVM after the snapshot is done.  We need to reset the RECOVER
+ * flag here, even though the filesystem is not technically dirty yet.
+ */
+static int ext4_unfreeze(struct super_block *sb)
+{
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	lock_super(sb);
+	/* Reset the needs_recovery flag before the fs is unlocked. */
+	EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+	ext4_commit_super(sb, 1);
+	unlock_super(sb);
+	return 0;
+}
+
+/*
+ * Structure to save mount options for ext4_remount's benefit
+ */
+struct ext4_mount_options {
+	unsigned long s_mount_opt;
+	unsigned long s_mount_opt2;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned long s_commit_interval;
+	u32 s_min_batch_time, s_max_batch_time;
+#ifdef CONFIG_QUOTA
+	int s_jquota_fmt;
+	char *s_qf_names[MAXQUOTAS];
+#endif
+};
+
+static int ext4_remount(struct super_block *sb, int *flags, char *data)
+{
+	struct ext4_super_block *es;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t n_blocks_count = 0;
+	unsigned long old_sb_flags;
+	struct ext4_mount_options old_opts;
+	int enable_quota = 0;
+	ext4_group_t g;
+	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	int err = 0;
+#ifdef CONFIG_QUOTA
+	int i;
+#endif
+	char *orig_data = kstrdup(data, GFP_KERNEL);
+
+	/* Store the original options */
+	lock_super(sb);
+	old_sb_flags = sb->s_flags;
+	old_opts.s_mount_opt = sbi->s_mount_opt;
+	old_opts.s_mount_opt2 = sbi->s_mount_opt2;
+	old_opts.s_resuid = sbi->s_resuid;
+	old_opts.s_resgid = sbi->s_resgid;
+	old_opts.s_commit_interval = sbi->s_commit_interval;
+	old_opts.s_min_batch_time = sbi->s_min_batch_time;
+	old_opts.s_max_batch_time = sbi->s_max_batch_time;
+#ifdef CONFIG_QUOTA
+	old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
+	for (i = 0; i < MAXQUOTAS; i++)
+		old_opts.s_qf_names[i] = sbi->s_qf_names[i];
+#endif
+	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
+		journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
+
+	/*
+	 * Allow the "check" option to be passed as a remount option.
+	 */
+	if (!parse_options(data, sb, NULL, &journal_ioprio,
+			   &n_blocks_count, 1)) {
+		err = -EINVAL;
+		goto restore_opts;
+	}
+
+	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+		ext4_abort(sb, "Abort forced by user");
+
+	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+		(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
+
+	es = sbi->s_es;
+
+	if (sbi->s_journal) {
+		ext4_init_journal_params(sb, sbi->s_journal);
+		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+	}
+
+	if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
+		n_blocks_count > ext4_blocks_count(es)) {
+		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
+			err = -EROFS;
+			goto restore_opts;
+		}
+
+		if (*flags & MS_RDONLY) {
+			err = dquot_suspend(sb, -1);
+			if (err < 0)
+				goto restore_opts;
+
+			/*
+			 * First of all, the unconditional stuff we have to do
+			 * to disable replay of the journal when we next remount
+			 */
+			sb->s_flags |= MS_RDONLY;
+
+			/*
+			 * OK, test if we are remounting a valid rw partition
+			 * readonly, and if so set the rdonly flag and then
+			 * mark the partition as valid again.
+			 */
+			if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) &&
+			    (sbi->s_mount_state & EXT4_VALID_FS))
+				es->s_state = cpu_to_le16(sbi->s_mount_state);
+
+			if (sbi->s_journal)
+				ext4_mark_recovery_complete(sb, es);
+		} else {
+			/* Make sure we can mount this feature set readwrite */
+			if (!ext4_feature_set_ok(sb, 0)) {
+				err = -EROFS;
+				goto restore_opts;
+			}
+			/*
+			 * Make sure the group descriptor checksums
+			 * are sane.  If they aren't, refuse to remount r/w.
+			 */
+			for (g = 0; g < sbi->s_groups_count; g++) {
+				struct ext4_group_desc *gdp =
+					ext4_get_group_desc(sb, g, NULL);
+
+				if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
+					ext4_msg(sb, KERN_ERR,
+	       "ext4_remount: Checksum for group %u failed (%u!=%u)",
+		g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
+					       le16_to_cpu(gdp->bg_checksum));
+					err = -EINVAL;
+					goto restore_opts;
+				}
+			}
+
+			/*
+			 * If we have an unprocessed orphan list hanging
+			 * around from a previously readonly bdev mount,
+			 * require a full umount/remount for now.
+			 */
+			if (es->s_last_orphan) {
+				ext4_msg(sb, KERN_WARNING, "Couldn't "
+				       "remount RDWR because of unprocessed "
+				       "orphan inode list.  Please "
+				       "umount/remount instead");
+				err = -EINVAL;
+				goto restore_opts;
+			}
+
+			/*
+			 * Mounting a RDONLY partition read-write, so reread
+			 * and store the current valid flag.  (It may have
+			 * been changed by e2fsck since we originally mounted
+			 * the partition.)
+			 */
+			if (sbi->s_journal)
+				ext4_clear_journal_err(sb, es);
+			sbi->s_mount_state = le16_to_cpu(es->s_state);
+			if ((err = ext4_group_extend(sb, es, n_blocks_count)))
+				goto restore_opts;
+			if (!ext4_setup_super(sb, es, 0))
+				sb->s_flags &= ~MS_RDONLY;
+			if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+						     EXT4_FEATURE_INCOMPAT_MMP))
+				if (ext4_multi_mount_protect(sb,
+						le64_to_cpu(es->s_mmp_block))) {
+					err = -EROFS;
+					goto restore_opts;
+				}
+			enable_quota = 1;
+		}
+	}
+
+	/*
+	 * Reinitialize lazy itable initialization thread based on
+	 * current settings
+	 */
+	if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
+		ext4_unregister_li_request(sb);
+	else {
+		ext4_group_t first_not_zeroed;
+		first_not_zeroed = ext4_has_uninit_itable(sb);
+		ext4_register_li_request(sb, first_not_zeroed);
+	}
+
+	ext4_setup_system_zone(sb);
+	if (sbi->s_journal == NULL)
+		ext4_commit_super(sb, 1);
+
+#ifdef CONFIG_QUOTA
+	/* Release old quota file names */
+	for (i = 0; i < MAXQUOTAS; i++)
+		if (old_opts.s_qf_names[i] &&
+		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
+			kfree(old_opts.s_qf_names[i]);
+#endif
+	unlock_super(sb);
+	if (enable_quota)
+		dquot_resume(sb, -1);
+
+	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
+	kfree(orig_data);
+	return 0;
+
+restore_opts:
+	sb->s_flags = old_sb_flags;
+	sbi->s_mount_opt = old_opts.s_mount_opt;
+	sbi->s_mount_opt2 = old_opts.s_mount_opt2;
+	sbi->s_resuid = old_opts.s_resuid;
+	sbi->s_resgid = old_opts.s_resgid;
+	sbi->s_commit_interval = old_opts.s_commit_interval;
+	sbi->s_min_batch_time = old_opts.s_min_batch_time;
+	sbi->s_max_batch_time = old_opts.s_max_batch_time;
+#ifdef CONFIG_QUOTA
+	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
+	for (i = 0; i < MAXQUOTAS; i++) {
+		if (sbi->s_qf_names[i] &&
+		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
+			kfree(sbi->s_qf_names[i]);
+		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
+	}
+#endif
+	unlock_super(sb);
+	kfree(orig_data);
+	return err;
+}
+
+static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	u64 fsid;
+	s64 bfree;
+
+	if (test_opt(sb, MINIX_DF)) {
+		sbi->s_overhead_last = 0;
+	} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
+		ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+		ext4_fsblk_t overhead = 0;
+
+		/*
+		 * Compute the overhead (FS structures).  This is constant
+		 * for a given filesystem unless the number of block groups
+		 * changes so we cache the previous value until it does.
+		 */
+
+		/*
+		 * All of the blocks before first_data_block are
+		 * overhead
+		 */
+		overhead = le32_to_cpu(es->s_first_data_block);
+
+		/*
+		 * Add the overhead attributed to the superblock and
+		 * block group descriptors.  If the sparse superblocks
+		 * feature is turned on, then not all groups have this.
+		 */
+		for (i = 0; i < ngroups; i++) {
+			overhead += ext4_bg_has_super(sb, i) +
+				ext4_bg_num_gdb(sb, i);
+			cond_resched();
+		}
+
+		/*
+		 * Every block group has an inode bitmap, a block
+		 * bitmap, and an inode table.
+		 */
+		overhead += ngroups * (2 + sbi->s_itb_per_group);
+		sbi->s_overhead_last = overhead;
+		smp_wmb();
+		sbi->s_blocks_last = ext4_blocks_count(es);
+	}
+
+	buf->f_type = EXT4_SUPER_MAGIC;
+	buf->f_bsize = sb->s_blocksize;
+	buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
+	bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+		       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
+	/* prevent underflow in case that few free space is available */
+	buf->f_bfree = max_t(s64, bfree, 0);
+	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
+	if (buf->f_bfree < ext4_r_blocks_count(es))
+		buf->f_bavail = 0;
+	buf->f_files = le32_to_cpu(es->s_inodes_count);
+	buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
+	buf->f_namelen = EXT4_NAME_LEN;
+	fsid = le64_to_cpup((void *)es->s_uuid) ^
+	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
+	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
+	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+
+	return 0;
+}
+
+/* Helper function for writing quotas on sync - we need to start transaction
+ * before quota file is locked for write. Otherwise the are possible deadlocks:
+ * Process 1                         Process 2
+ * ext4_create()                     quota_sync()
+ *   jbd2_journal_start()                  write_dquot()
+ *   dquot_initialize()                         down(dqio_mutex)
+ *     down(dqio_mutex)                    jbd2_journal_start()
+ *
+ */
+
+#ifdef CONFIG_QUOTA
+
+static inline struct inode *dquot_to_inode(struct dquot *dquot)
+{
+	return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
+}
+
+static int ext4_write_dquot(struct dquot *dquot)
+{
+	int ret, err;
+	handle_t *handle;
+	struct inode *inode;
+
+	inode = dquot_to_inode(dquot);
+	handle = ext4_journal_start(inode,
+				    EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ret = dquot_commit(dquot);
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+	return ret;
+}
+
+static int ext4_acquire_dquot(struct dquot *dquot)
+{
+	int ret, err;
+	handle_t *handle;
+
+	handle = ext4_journal_start(dquot_to_inode(dquot),
+				    EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ret = dquot_acquire(dquot);
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+	return ret;
+}
+
+static int ext4_release_dquot(struct dquot *dquot)
+{
+	int ret, err;
+	handle_t *handle;
+
+	handle = ext4_journal_start(dquot_to_inode(dquot),
+				    EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+	if (IS_ERR(handle)) {
+		/* Release dquot anyway to avoid endless cycle in dqput() */
+		dquot_release(dquot);
+		return PTR_ERR(handle);
+	}
+	ret = dquot_release(dquot);
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+	return ret;
+}
+
+static int ext4_mark_dquot_dirty(struct dquot *dquot)
+{
+	/* Are we journaling quotas? */
+	if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
+	    EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
+		dquot_mark_dquot_dirty(dquot);
+		return ext4_write_dquot(dquot);
+	} else {
+		return dquot_mark_dquot_dirty(dquot);
+	}
+}
+
+static int ext4_write_info(struct super_block *sb, int type)
+{
+	int ret, err;
+	handle_t *handle;
+
+	/* Data block + inode block */
+	handle = ext4_journal_start(sb->s_root->d_inode, 2);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ret = dquot_commit_info(sb, type);
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+	return ret;
+}
+
+/*
+ * Turn on quotas during mount time - we need to find
+ * the quota file and such...
+ */
+static int ext4_quota_on_mount(struct super_block *sb, int type)
+{
+	return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
+					EXT4_SB(sb)->s_jquota_fmt, type);
+}
+
+/*
+ * Standard function to be called on quota_on
+ */
+static int ext4_quota_on(struct super_block *sb, int type, int format_id,
+			 struct path *path)
+{
+	int err;
+
+	if (!test_opt(sb, QUOTA))
+		return -EINVAL;
+
+	/* Quotafile not on the same filesystem? */
+	if (path->mnt->mnt_sb != sb)
+		return -EXDEV;
+	/* Journaling quota? */
+	if (EXT4_SB(sb)->s_qf_names[type]) {
+		/* Quotafile not in fs root? */
+		if (path->dentry->d_parent != sb->s_root)
+			ext4_msg(sb, KERN_WARNING,
+				"Quota file not on filesystem root. "
+				"Journaled quota will not work");
+	}
+
+	/*
+	 * When we journal data on quota file, we have to flush journal to see
+	 * all updates to the file when we bypass pagecache...
+	 */
+	if (EXT4_SB(sb)->s_journal &&
+	    ext4_should_journal_data(path->dentry->d_inode)) {
+		/*
+		 * We don't need to lock updates but journal_flush() could
+		 * otherwise be livelocked...
+		 */
+		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		if (err)
+			return err;
+	}
+
+	return dquot_quota_on(sb, type, format_id, path);
+}
+
+static int ext4_quota_off(struct super_block *sb, int type)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	handle_t *handle;
+
+	/* Force all delayed allocation blocks to be allocated.
+	 * Caller already holds s_umount sem */
+	if (test_opt(sb, DELALLOC))
+		sync_filesystem(sb);
+
+	if (!inode)
+		goto out;
+
+	/* Update modification times of quota files when userspace can
+	 * start looking at them */
+	handle = ext4_journal_start(inode, 1);
+	if (IS_ERR(handle))
+		goto out;
+	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+
+out:
+	return dquot_quota_off(sb, type);
+}
+
+/* Read data from quotafile - avoid pagecache and such because we cannot afford
+ * acquiring the locks... As quota files are never truncated and quota code
+ * itself serializes the operations (and no one else should touch the files)
+ * we don't have to be afraid of races */
+static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
+			       size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
+	int err = 0;
+	int offset = off & (sb->s_blocksize - 1);
+	int tocopy;
+	size_t toread;
+	struct buffer_head *bh;
+	loff_t i_size = i_size_read(inode);
+
+	if (off > i_size)
+		return 0;
+	if (off+len > i_size)
+		len = i_size-off;
+	toread = len;
+	while (toread > 0) {
+		tocopy = sb->s_blocksize - offset < toread ?
+				sb->s_blocksize - offset : toread;
+		bh = ext4_bread(NULL, inode, blk, 0, &err);
+		if (err)
+			return err;
+		if (!bh)	/* A hole? */
+			memset(data, 0, tocopy);
+		else
+			memcpy(data, bh->b_data+offset, tocopy);
+		brelse(bh);
+		offset = 0;
+		toread -= tocopy;
+		data += tocopy;
+		blk++;
+	}
+	return len;
+}
+
+/* Write to quotafile (we know the transaction is already started and has
+ * enough credits) */
+static ssize_t ext4_quota_write(struct super_block *sb, int type,
+				const char *data, size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
+	int err = 0;
+	int offset = off & (sb->s_blocksize - 1);
+	struct buffer_head *bh;
+	handle_t *handle = journal_current_handle();
+
+	if (EXT4_SB(sb)->s_journal && !handle) {
+		ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+			" cancelled because transaction is not started",
+			(unsigned long long)off, (unsigned long long)len);
+		return -EIO;
+	}
+	/*
+	 * Since we account only one data block in transaction credits,
+	 * then it is impossible to cross a block boundary.
+	 */
+	if (sb->s_blocksize - offset < len) {
+		ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+			" cancelled because not block aligned",
+			(unsigned long long)off, (unsigned long long)len);
+		return -EIO;
+	}
+
+	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
+	bh = ext4_bread(handle, inode, blk, 1, &err);
+	if (!bh)
+		goto out;
+	err = ext4_journal_get_write_access(handle, bh);
+	if (err) {
+		brelse(bh);
+		goto out;
+	}
+	lock_buffer(bh);
+	memcpy(bh->b_data+offset, data, len);
+	flush_dcache_page(bh->b_page);
+	unlock_buffer(bh);
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	brelse(bh);
+out:
+	if (err) {
+		mutex_unlock(&inode->i_mutex);
+		return err;
+	}
+	if (inode->i_size < off + len) {
+		i_size_write(inode, off + len);
+		EXT4_I(inode)->i_disksize = inode->i_size;
+		ext4_mark_inode_dirty(handle, inode);
+	}
+	mutex_unlock(&inode->i_mutex);
+	return len;
+}
+
+#endif
+
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data)
+{
+	return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super);
+}
+
+#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static inline void register_as_ext2(void)
+{
+	int err = register_filesystem(&ext2_fs_type);
+	if (err)
+		printk(KERN_WARNING
+		       "EXT4-fs: Unable to register as ext2 (%d)\n", err);
+}
+
+static inline void unregister_as_ext2(void)
+{
+	unregister_filesystem(&ext2_fs_type);
+}
+
+static inline int ext2_feature_set_ok(struct super_block *sb)
+{
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP))
+		return 0;
+	if (sb->s_flags & MS_RDONLY)
+		return 1;
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))
+		return 0;
+	return 1;
+}
+MODULE_ALIAS("ext2");
+#else
+static inline void register_as_ext2(void) { }
+static inline void unregister_as_ext2(void) { }
+static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; }
+#endif
+
+#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static inline void register_as_ext3(void)
+{
+	int err = register_filesystem(&ext3_fs_type);
+	if (err)
+		printk(KERN_WARNING
+		       "EXT4-fs: Unable to register as ext3 (%d)\n", err);
+}
+
+static inline void unregister_as_ext3(void)
+{
+	unregister_filesystem(&ext3_fs_type);
+}
+
+static inline int ext3_feature_set_ok(struct super_block *sb)
+{
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP))
+		return 0;
+	if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		return 0;
+	if (sb->s_flags & MS_RDONLY)
+		return 1;
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))
+		return 0;
+	return 1;
+}
+MODULE_ALIAS("ext3");
+#else
+static inline void register_as_ext3(void) { }
+static inline void unregister_as_ext3(void) { }
+static inline int ext3_feature_set_ok(struct super_block *sb) { return 0; }
+#endif
+
+static struct file_system_type ext4_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext4",
+	.mount		= ext4_mount,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+
+static int __init ext4_init_feat_adverts(void)
+{
+	struct ext4_features *ef;
+	int ret = -ENOMEM;
+
+	ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
+	if (!ef)
+		goto out;
+
+	ef->f_kobj.kset = ext4_kset;
+	init_completion(&ef->f_kobj_unregister);
+	ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
+				   "features");
+	if (ret) {
+		kfree(ef);
+		goto out;
+	}
+
+	ext4_feat = ef;
+	ret = 0;
+out:
+	return ret;
+}
+
+static void ext4_exit_feat_adverts(void)
+{
+	kobject_put(&ext4_feat->f_kobj);
+	wait_for_completion(&ext4_feat->f_kobj_unregister);
+	kfree(ext4_feat);
+}
+
+/* Shared across all ext4 file systems */
+wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
+static int __init ext4_init_fs(void)
+{
+	int i, err;
+
+	ext4_check_flag_values();
+
+	for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
+		mutex_init(&ext4__aio_mutex[i]);
+		init_waitqueue_head(&ext4__ioend_wq[i]);
+	}
+
+	err = ext4_init_pageio();
+	if (err)
+		return err;
+	err = ext4_init_system_zone();
+	if (err)
+		goto out7;
+	ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
+	if (!ext4_kset)
+		goto out6;
+	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+	if (!ext4_proc_root)
+		goto out5;
+
+	err = ext4_init_feat_adverts();
+	if (err)
+		goto out4;
+
+	err = ext4_init_mballoc();
+	if (err)
+		goto out3;
+
+	err = ext4_init_xattr();
+	if (err)
+		goto out2;
+	err = init_inodecache();
+	if (err)
+		goto out1;
+	register_as_ext3();
+	register_as_ext2();
+	err = register_filesystem(&ext4_fs_type);
+	if (err)
+		goto out;
+
+	ext4_li_info = NULL;
+	mutex_init(&ext4_li_mtx);
+	return 0;
+out:
+	unregister_as_ext2();
+	unregister_as_ext3();
+	destroy_inodecache();
+out1:
+	ext4_exit_xattr();
+out2:
+	ext4_exit_mballoc();
+out3:
+	ext4_exit_feat_adverts();
+out4:
+	remove_proc_entry("fs/ext4", NULL);
+out5:
+	kset_unregister(ext4_kset);
+out6:
+	ext4_exit_system_zone();
+out7:
+	ext4_exit_pageio();
+	return err;
+}
+
+static void __exit ext4_exit_fs(void)
+{
+	ext4_destroy_lazyinit_thread();
+	unregister_as_ext2();
+	unregister_as_ext3();
+	unregister_filesystem(&ext4_fs_type);
+	destroy_inodecache();
+	ext4_exit_xattr();
+	ext4_exit_mballoc();
+	ext4_exit_feat_adverts();
+	remove_proc_entry("fs/ext4", NULL);
+	kset_unregister(ext4_kset);
+	ext4_exit_system_zone();
+	ext4_exit_pageio();
+}
+
+MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
+MODULE_DESCRIPTION("Fourth Extended Filesystem");
+MODULE_LICENSE("GPL");
+module_init(ext4_init_fs)
+module_exit(ext4_exit_fs)
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
new file mode 100644
index 00000000..ed9354af
--- /dev/null
+++ b/fs/ext4/symlink.c
@@ -0,0 +1,56 @@
+/*
+ *  linux/fs/ext4/symlink.c
+ *
+ * Only fast symlinks left here - the rest is done by generic code. AV, 1999
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/symlink.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4 symlink handling code
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/namei.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
+	nd_set_link(nd, (char *) ei->i_data);
+	return NULL;
+}
+
+const struct inode_operations ext4_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+	.setattr	= ext4_setattr,
+#ifdef CONFIG_EXT4_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext4_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+
+const struct inode_operations ext4_fast_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= ext4_follow_link,
+	.setattr	= ext4_setattr,
+#ifdef CONFIG_EXT4_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext4_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
new file mode 100644
index 00000000..c2865cc3
--- /dev/null
+++ b/fs/ext4/xattr.c
@@ -0,0 +1,1612 @@
+/*
+ * linux/fs/ext4/xattr.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ *
+ * Fix by Harrison Xing <harrison@mountainviewdata.com>.
+ * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>.
+ * Extended attributes for symlinks and special files added per
+ *  suggestion of Luka Renko <luka.renko@hermes.si>.
+ * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
+ *  Red Hat Inc.
+ * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz
+ *  and Andreas Gruenbacher <agruen@suse.de>.
+ */
+
+/*
+ * Extended attributes are stored directly in inodes (on file systems with
+ * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl
+ * field contains the block number if an inode uses an additional block. All
+ * attributes must fit in the inode and one additional block. Blocks that
+ * contain the identical set of attributes may be shared among several inodes.
+ * Identical blocks are detected by keeping a cache of blocks that have
+ * recently been accessed.
+ *
+ * The attributes in inodes and on blocks have a different header; the entries
+ * are stored in the same format:
+ *
+ *   +------------------+
+ *   | header           |
+ *   | entry 1          | |
+ *   | entry 2          | | growing downwards
+ *   | entry 3          | v
+ *   | four null bytes  |
+ *   | . . .            |
+ *   | value 1          | ^
+ *   | value 3          | | growing upwards
+ *   | value 2          | |
+ *   +------------------+
+ *
+ * The header is followed by multiple entry descriptors. In disk blocks, the
+ * entry descriptors are kept sorted. In inodes, they are unsorted. The
+ * attribute values are aligned to the end of the block in no specific order.
+ *
+ * Locking strategy
+ * ----------------
+ * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem.
+ * EA blocks are only changed if they are exclusive to an inode, so
+ * holding xattr_sem also means that nothing but the EA block's reference
+ * count can change. Multiple writers to the same block are synchronized
+ * by the buffer lock.
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/mbcache.h>
+#include <linux/quotaops.h>
+#include <linux/rwsem.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+#include "acl.h"
+
+#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
+#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
+#define BFIRST(bh) ENTRY(BHDR(bh)+1)
+#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
+
+#ifdef EXT4_XATTR_DEBUG
+# define ea_idebug(inode, f...) do { \
+		printk(KERN_DEBUG "inode %s:%lu: ", \
+			inode->i_sb->s_id, inode->i_ino); \
+		printk(f); \
+		printk("\n"); \
+	} while (0)
+# define ea_bdebug(bh, f...) do { \
+		char b[BDEVNAME_SIZE]; \
+		printk(KERN_DEBUG "block %s:%lu: ", \
+			bdevname(bh->b_bdev, b), \
+			(unsigned long) bh->b_blocknr); \
+		printk(f); \
+		printk("\n"); \
+	} while (0)
+#else
+# define ea_idebug(f...)
+# define ea_bdebug(f...)
+#endif
+
+static void ext4_xattr_cache_insert(struct buffer_head *);
+static struct buffer_head *ext4_xattr_cache_find(struct inode *,
+						 struct ext4_xattr_header *,
+						 struct mb_cache_entry **);
+static void ext4_xattr_rehash(struct ext4_xattr_header *,
+			      struct ext4_xattr_entry *);
+static int ext4_xattr_list(struct dentry *dentry, char *buffer,
+			   size_t buffer_size);
+
+static struct mb_cache *ext4_xattr_cache;
+
+static const struct xattr_handler *ext4_xattr_handler_map[] = {
+	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &ext4_xattr_acl_access_handler,
+	[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler,
+#endif
+	[EXT4_XATTR_INDEX_TRUSTED]	     = &ext4_xattr_trusted_handler,
+#ifdef CONFIG_EXT4_FS_SECURITY
+	[EXT4_XATTR_INDEX_SECURITY]	     = &ext4_xattr_security_handler,
+#endif
+};
+
+const struct xattr_handler *ext4_xattr_handlers[] = {
+	&ext4_xattr_user_handler,
+	&ext4_xattr_trusted_handler,
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	&ext4_xattr_acl_access_handler,
+	&ext4_xattr_acl_default_handler,
+#endif
+#ifdef CONFIG_EXT4_FS_SECURITY
+	&ext4_xattr_security_handler,
+#endif
+	NULL
+};
+
+static inline const struct xattr_handler *
+ext4_xattr_handler(int name_index)
+{
+	const struct xattr_handler *handler = NULL;
+
+	if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
+		handler = ext4_xattr_handler_map[name_index];
+	return handler;
+}
+
+/*
+ * Inode operation listxattr()
+ *
+ * dentry->d_inode->i_mutex: don't care
+ */
+ssize_t
+ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+	return ext4_xattr_list(dentry, buffer, size);
+}
+
+static int
+ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
+{
+	while (!IS_LAST_ENTRY(entry)) {
+		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
+		if ((void *)next >= end)
+			return -EIO;
+		entry = next;
+	}
+	return 0;
+}
+
+static inline int
+ext4_xattr_check_block(struct buffer_head *bh)
+{
+	int error;
+
+	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
+	    BHDR(bh)->h_blocks != cpu_to_le32(1))
+		return -EIO;
+	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
+	return error;
+}
+
+static inline int
+ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
+{
+	size_t value_size = le32_to_cpu(entry->e_value_size);
+
+	if (entry->e_value_block != 0 || value_size > size ||
+	    le16_to_cpu(entry->e_value_offs) + value_size > size)
+		return -EIO;
+	return 0;
+}
+
+static int
+ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
+		      const char *name, size_t size, int sorted)
+{
+	struct ext4_xattr_entry *entry;
+	size_t name_len;
+	int cmp = 1;
+
+	if (name == NULL)
+		return -EINVAL;
+	name_len = strlen(name);
+	entry = *pentry;
+	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+		cmp = name_index - entry->e_name_index;
+		if (!cmp)
+			cmp = name_len - entry->e_name_len;
+		if (!cmp)
+			cmp = memcmp(name, entry->e_name, name_len);
+		if (cmp <= 0 && (sorted || cmp == 0))
+			break;
+	}
+	*pentry = entry;
+	if (!cmp && ext4_xattr_check_entry(entry, size))
+			return -EIO;
+	return cmp ? -ENODATA : 0;
+}
+
+static int
+ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
+		     void *buffer, size_t buffer_size)
+{
+	struct buffer_head *bh = NULL;
+	struct ext4_xattr_entry *entry;
+	size_t size;
+	int error;
+
+	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
+		  name_index, name, buffer, (long)buffer_size);
+
+	error = -ENODATA;
+	if (!EXT4_I(inode)->i_file_acl)
+		goto cleanup;
+	ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+	if (!bh)
+		goto cleanup;
+	ea_bdebug(bh, "b_count=%d, refcount=%d",
+		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
+	if (ext4_xattr_check_block(bh)) {
+bad_block:
+		EXT4_ERROR_INODE(inode, "bad block %llu",
+				 EXT4_I(inode)->i_file_acl);
+		error = -EIO;
+		goto cleanup;
+	}
+	ext4_xattr_cache_insert(bh);
+	entry = BFIRST(bh);
+	error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
+	if (error == -EIO)
+		goto bad_block;
+	if (error)
+		goto cleanup;
+	size = le32_to_cpu(entry->e_value_size);
+	if (buffer) {
+		error = -ERANGE;
+		if (size > buffer_size)
+			goto cleanup;
+		memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs),
+		       size);
+	}
+	error = size;
+
+cleanup:
+	brelse(bh);
+	return error;
+}
+
+static int
+ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
+		     void *buffer, size_t buffer_size)
+{
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_xattr_entry *entry;
+	struct ext4_inode *raw_inode;
+	struct ext4_iloc iloc;
+	size_t size;
+	void *end;
+	int error;
+
+	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
+		return -ENODATA;
+	error = ext4_get_inode_loc(inode, &iloc);
+	if (error)
+		return error;
+	raw_inode = ext4_raw_inode(&iloc);
+	header = IHDR(inode, raw_inode);
+	entry = IFIRST(header);
+	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+	error = ext4_xattr_check_names(entry, end);
+	if (error)
+		goto cleanup;
+	error = ext4_xattr_find_entry(&entry, name_index, name,
+				      end - (void *)entry, 0);
+	if (error)
+		goto cleanup;
+	size = le32_to_cpu(entry->e_value_size);
+	if (buffer) {
+		error = -ERANGE;
+		if (size > buffer_size)
+			goto cleanup;
+		memcpy(buffer, (void *)IFIRST(header) +
+		       le16_to_cpu(entry->e_value_offs), size);
+	}
+	error = size;
+
+cleanup:
+	brelse(iloc.bh);
+	return error;
+}
+
+/*
+ * ext4_xattr_get()
+ *
+ * Copy an extended attribute into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+int
+ext4_xattr_get(struct inode *inode, int name_index, const char *name,
+	       void *buffer, size_t buffer_size)
+{
+	int error;
+
+	down_read(&EXT4_I(inode)->xattr_sem);
+	error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
+				     buffer_size);
+	if (error == -ENODATA)
+		error = ext4_xattr_block_get(inode, name_index, name, buffer,
+					     buffer_size);
+	up_read(&EXT4_I(inode)->xattr_sem);
+	return error;
+}
+
+static int
+ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
+			char *buffer, size_t buffer_size)
+{
+	size_t rest = buffer_size;
+
+	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+		const struct xattr_handler *handler =
+			ext4_xattr_handler(entry->e_name_index);
+
+		if (handler) {
+			size_t size = handler->list(dentry, buffer, rest,
+						    entry->e_name,
+						    entry->e_name_len,
+						    handler->flags);
+			if (buffer) {
+				if (size > rest)
+					return -ERANGE;
+				buffer += size;
+			}
+			rest -= size;
+		}
+	}
+	return buffer_size - rest;
+}
+
+static int
+ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct buffer_head *bh = NULL;
+	int error;
+
+	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
+		  buffer, (long)buffer_size);
+
+	error = 0;
+	if (!EXT4_I(inode)->i_file_acl)
+		goto cleanup;
+	ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+	error = -EIO;
+	if (!bh)
+		goto cleanup;
+	ea_bdebug(bh, "b_count=%d, refcount=%d",
+		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
+	if (ext4_xattr_check_block(bh)) {
+		EXT4_ERROR_INODE(inode, "bad block %llu",
+				 EXT4_I(inode)->i_file_acl);
+		error = -EIO;
+		goto cleanup;
+	}
+	ext4_xattr_cache_insert(bh);
+	error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
+
+cleanup:
+	brelse(bh);
+
+	return error;
+}
+
+static int
+ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_inode *raw_inode;
+	struct ext4_iloc iloc;
+	void *end;
+	int error;
+
+	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
+		return 0;
+	error = ext4_get_inode_loc(inode, &iloc);
+	if (error)
+		return error;
+	raw_inode = ext4_raw_inode(&iloc);
+	header = IHDR(inode, raw_inode);
+	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+	error = ext4_xattr_check_names(IFIRST(header), end);
+	if (error)
+		goto cleanup;
+	error = ext4_xattr_list_entries(dentry, IFIRST(header),
+					buffer, buffer_size);
+
+cleanup:
+	brelse(iloc.bh);
+	return error;
+}
+
+/*
+ * ext4_xattr_list()
+ *
+ * Copy a list of attribute names into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+static int
+ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	int ret, ret2;
+
+	down_read(&EXT4_I(dentry->d_inode)->xattr_sem);
+	ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
+	if (ret < 0)
+		goto errout;
+	if (buffer) {
+		buffer += ret;
+		buffer_size -= ret;
+	}
+	ret = ext4_xattr_block_list(dentry, buffer, buffer_size);
+	if (ret < 0)
+		goto errout;
+	ret += ret2;
+errout:
+	up_read(&EXT4_I(dentry->d_inode)->xattr_sem);
+	return ret;
+}
+
+/*
+ * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is
+ * not set, set it.
+ */
+static void ext4_xattr_update_super_block(handle_t *handle,
+					  struct super_block *sb)
+{
+	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
+		return;
+
+	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+		EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
+		ext4_handle_dirty_super(handle, sb);
+	}
+}
+
+/*
+ * Release the xattr block BH: If the reference count is > 1, decrement
+ * it; otherwise free the block.
+ */
+static void
+ext4_xattr_release_block(handle_t *handle, struct inode *inode,
+			 struct buffer_head *bh)
+{
+	struct mb_cache_entry *ce = NULL;
+	int error = 0;
+
+	ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr);
+	error = ext4_journal_get_write_access(handle, bh);
+	if (error)
+		goto out;
+
+	lock_buffer(bh);
+	if (BHDR(bh)->h_refcount == cpu_to_le32(1)) {
+		ea_bdebug(bh, "refcount now=0; freeing");
+		if (ce)
+			mb_cache_entry_free(ce);
+		get_bh(bh);
+		ext4_free_blocks(handle, inode, bh, 0, 1,
+				 EXT4_FREE_BLOCKS_METADATA |
+				 EXT4_FREE_BLOCKS_FORGET);
+		unlock_buffer(bh);
+	} else {
+		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
+		if (ce)
+			mb_cache_entry_release(ce);
+		unlock_buffer(bh);
+		error = ext4_handle_dirty_metadata(handle, inode, bh);
+		if (IS_SYNC(inode))
+			ext4_handle_sync(handle);
+		dquot_free_block(inode, 1);
+		ea_bdebug(bh, "refcount now=%d; releasing",
+			  le32_to_cpu(BHDR(bh)->h_refcount));
+	}
+out:
+	ext4_std_error(inode->i_sb, error);
+	return;
+}
+
+/*
+ * Find the available free space for EAs. This also returns the total number of
+ * bytes used by EA entries.
+ */
+static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
+				    size_t *min_offs, void *base, int *total)
+{
+	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+		*total += EXT4_XATTR_LEN(last->e_name_len);
+		if (!last->e_value_block && last->e_value_size) {
+			size_t offs = le16_to_cpu(last->e_value_offs);
+			if (offs < *min_offs)
+				*min_offs = offs;
+		}
+	}
+	return (*min_offs - ((void *)last - base) - sizeof(__u32));
+}
+
+struct ext4_xattr_info {
+	int name_index;
+	const char *name;
+	const void *value;
+	size_t value_len;
+};
+
+struct ext4_xattr_search {
+	struct ext4_xattr_entry *first;
+	void *base;
+	void *end;
+	struct ext4_xattr_entry *here;
+	int not_found;
+};
+
+static int
+ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
+{
+	struct ext4_xattr_entry *last;
+	size_t free, min_offs = s->end - s->base, name_len = strlen(i->name);
+
+	/* Compute min_offs and last. */
+	last = s->first;
+	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+		if (!last->e_value_block && last->e_value_size) {
+			size_t offs = le16_to_cpu(last->e_value_offs);
+			if (offs < min_offs)
+				min_offs = offs;
+		}
+	}
+	free = min_offs - ((void *)last - s->base) - sizeof(__u32);
+	if (!s->not_found) {
+		if (!s->here->e_value_block && s->here->e_value_size) {
+			size_t size = le32_to_cpu(s->here->e_value_size);
+			free += EXT4_XATTR_SIZE(size);
+		}
+		free += EXT4_XATTR_LEN(name_len);
+	}
+	if (i->value) {
+		if (free < EXT4_XATTR_SIZE(i->value_len) ||
+		    free < EXT4_XATTR_LEN(name_len) +
+			   EXT4_XATTR_SIZE(i->value_len))
+			return -ENOSPC;
+	}
+
+	if (i->value && s->not_found) {
+		/* Insert the new name. */
+		size_t size = EXT4_XATTR_LEN(name_len);
+		size_t rest = (void *)last - (void *)s->here + sizeof(__u32);
+		memmove((void *)s->here + size, s->here, rest);
+		memset(s->here, 0, size);
+		s->here->e_name_index = i->name_index;
+		s->here->e_name_len = name_len;
+		memcpy(s->here->e_name, i->name, name_len);
+	} else {
+		if (!s->here->e_value_block && s->here->e_value_size) {
+			void *first_val = s->base + min_offs;
+			size_t offs = le16_to_cpu(s->here->e_value_offs);
+			void *val = s->base + offs;
+			size_t size = EXT4_XATTR_SIZE(
+				le32_to_cpu(s->here->e_value_size));
+
+			if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) {
+				/* The old and the new value have the same
+				   size. Just replace. */
+				s->here->e_value_size =
+					cpu_to_le32(i->value_len);
+				memset(val + size - EXT4_XATTR_PAD, 0,
+				       EXT4_XATTR_PAD); /* Clear pad bytes. */
+				memcpy(val, i->value, i->value_len);
+				return 0;
+			}
+
+			/* Remove the old value. */
+			memmove(first_val + size, first_val, val - first_val);
+			memset(first_val, 0, size);
+			s->here->e_value_size = 0;
+			s->here->e_value_offs = 0;
+			min_offs += size;
+
+			/* Adjust all value offsets. */
+			last = s->first;
+			while (!IS_LAST_ENTRY(last)) {
+				size_t o = le16_to_cpu(last->e_value_offs);
+				if (!last->e_value_block &&
+				    last->e_value_size && o < offs)
+					last->e_value_offs =
+						cpu_to_le16(o + size);
+				last = EXT4_XATTR_NEXT(last);
+			}
+		}
+		if (!i->value) {
+			/* Remove the old name. */
+			size_t size = EXT4_XATTR_LEN(name_len);
+			last = ENTRY((void *)last - size);
+			memmove(s->here, (void *)s->here + size,
+				(void *)last - (void *)s->here + sizeof(__u32));
+			memset(last, 0, size);
+		}
+	}
+
+	if (i->value) {
+		/* Insert the new value. */
+		s->here->e_value_size = cpu_to_le32(i->value_len);
+		if (i->value_len) {
+			size_t size = EXT4_XATTR_SIZE(i->value_len);
+			void *val = s->base + min_offs - size;
+			s->here->e_value_offs = cpu_to_le16(min_offs - size);
+			memset(val + size - EXT4_XATTR_PAD, 0,
+			       EXT4_XATTR_PAD); /* Clear the pad bytes. */
+			memcpy(val, i->value, i->value_len);
+		}
+	}
+	return 0;
+}
+
+struct ext4_xattr_block_find {
+	struct ext4_xattr_search s;
+	struct buffer_head *bh;
+};
+
+static int
+ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
+		      struct ext4_xattr_block_find *bs)
+{
+	struct super_block *sb = inode->i_sb;
+	int error;
+
+	ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
+		  i->name_index, i->name, i->value, (long)i->value_len);
+
+	if (EXT4_I(inode)->i_file_acl) {
+		/* The inode already has an extended attribute block. */
+		bs->bh = sb_bread(sb, EXT4_I(inode)->i_file_acl);
+		error = -EIO;
+		if (!bs->bh)
+			goto cleanup;
+		ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
+			atomic_read(&(bs->bh->b_count)),
+			le32_to_cpu(BHDR(bs->bh)->h_refcount));
+		if (ext4_xattr_check_block(bs->bh)) {
+			EXT4_ERROR_INODE(inode, "bad block %llu",
+					 EXT4_I(inode)->i_file_acl);
+			error = -EIO;
+			goto cleanup;
+		}
+		/* Find the named attribute. */
+		bs->s.base = BHDR(bs->bh);
+		bs->s.first = BFIRST(bs->bh);
+		bs->s.end = bs->bh->b_data + bs->bh->b_size;
+		bs->s.here = bs->s.first;
+		error = ext4_xattr_find_entry(&bs->s.here, i->name_index,
+					      i->name, bs->bh->b_size, 1);
+		if (error && error != -ENODATA)
+			goto cleanup;
+		bs->s.not_found = error;
+	}
+	error = 0;
+
+cleanup:
+	return error;
+}
+
+static int
+ext4_xattr_block_set(handle_t *handle, struct inode *inode,
+		     struct ext4_xattr_info *i,
+		     struct ext4_xattr_block_find *bs)
+{
+	struct super_block *sb = inode->i_sb;
+	struct buffer_head *new_bh = NULL;
+	struct ext4_xattr_search *s = &bs->s;
+	struct mb_cache_entry *ce = NULL;
+	int error = 0;
+
+#define header(x) ((struct ext4_xattr_header *)(x))
+
+	if (i->value && i->value_len > sb->s_blocksize)
+		return -ENOSPC;
+	if (s->base) {
+		ce = mb_cache_entry_get(ext4_xattr_cache, bs->bh->b_bdev,
+					bs->bh->b_blocknr);
+		error = ext4_journal_get_write_access(handle, bs->bh);
+		if (error)
+			goto cleanup;
+		lock_buffer(bs->bh);
+
+		if (header(s->base)->h_refcount == cpu_to_le32(1)) {
+			if (ce) {
+				mb_cache_entry_free(ce);
+				ce = NULL;
+			}
+			ea_bdebug(bs->bh, "modifying in-place");
+			error = ext4_xattr_set_entry(i, s);
+			if (!error) {
+				if (!IS_LAST_ENTRY(s->first))
+					ext4_xattr_rehash(header(s->base),
+							  s->here);
+				ext4_xattr_cache_insert(bs->bh);
+			}
+			unlock_buffer(bs->bh);
+			if (error == -EIO)
+				goto bad_block;
+			if (!error)
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   bs->bh);
+			if (error)
+				goto cleanup;
+			goto inserted;
+		} else {
+			int offset = (char *)s->here - bs->bh->b_data;
+
+			unlock_buffer(bs->bh);
+			ext4_handle_release_buffer(handle, bs->bh);
+			if (ce) {
+				mb_cache_entry_release(ce);
+				ce = NULL;
+			}
+			ea_bdebug(bs->bh, "cloning");
+			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
+			error = -ENOMEM;
+			if (s->base == NULL)
+				goto cleanup;
+			memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
+			s->first = ENTRY(header(s->base)+1);
+			header(s->base)->h_refcount = cpu_to_le32(1);
+			s->here = ENTRY(s->base + offset);
+			s->end = s->base + bs->bh->b_size;
+		}
+	} else {
+		/* Allocate a buffer where we construct the new block. */
+		s->base = kzalloc(sb->s_blocksize, GFP_NOFS);
+		/* assert(header == s->base) */
+		error = -ENOMEM;
+		if (s->base == NULL)
+			goto cleanup;
+		header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
+		header(s->base)->h_blocks = cpu_to_le32(1);
+		header(s->base)->h_refcount = cpu_to_le32(1);
+		s->first = ENTRY(header(s->base)+1);
+		s->here = ENTRY(header(s->base)+1);
+		s->end = s->base + sb->s_blocksize;
+	}
+
+	error = ext4_xattr_set_entry(i, s);
+	if (error == -EIO)
+		goto bad_block;
+	if (error)
+		goto cleanup;
+	if (!IS_LAST_ENTRY(s->first))
+		ext4_xattr_rehash(header(s->base), s->here);
+
+inserted:
+	if (!IS_LAST_ENTRY(s->first)) {
+		new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce);
+		if (new_bh) {
+			/* We found an identical block in the cache. */
+			if (new_bh == bs->bh)
+				ea_bdebug(new_bh, "keeping");
+			else {
+				/* The old block is released after updating
+				   the inode. */
+				error = dquot_alloc_block(inode, 1);
+				if (error)
+					goto cleanup;
+				error = ext4_journal_get_write_access(handle,
+								      new_bh);
+				if (error)
+					goto cleanup_dquot;
+				lock_buffer(new_bh);
+				le32_add_cpu(&BHDR(new_bh)->h_refcount, 1);
+				ea_bdebug(new_bh, "reusing; refcount now=%d",
+					le32_to_cpu(BHDR(new_bh)->h_refcount));
+				unlock_buffer(new_bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   new_bh);
+				if (error)
+					goto cleanup_dquot;
+			}
+			mb_cache_entry_release(ce);
+			ce = NULL;
+		} else if (bs->bh && s->base == bs->bh->b_data) {
+			/* We were modifying this block in-place. */
+			ea_bdebug(bs->bh, "keeping this block");
+			new_bh = bs->bh;
+			get_bh(new_bh);
+		} else {
+			/* We need to allocate a new block */
+			ext4_fsblk_t goal, block;
+
+			goal = ext4_group_first_block_no(sb,
+						EXT4_I(inode)->i_block_group);
+
+			/* non-extent files can't have physical blocks past 2^32 */
+			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+
+			/*
+			 * take i_data_sem because we will test
+			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
+			 */
+			down_read((&EXT4_I(inode)->i_data_sem));
+			block = ext4_new_meta_blocks(handle, inode, goal, 0,
+						     NULL, &error);
+			up_read((&EXT4_I(inode)->i_data_sem));
+			if (error)
+				goto cleanup;
+
+			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+				BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
+
+			ea_idebug(inode, "creating block %d", block);
+
+			new_bh = sb_getblk(sb, block);
+			if (!new_bh) {
+getblk_failed:
+				ext4_free_blocks(handle, inode, NULL, block, 1,
+						 EXT4_FREE_BLOCKS_METADATA);
+				error = -EIO;
+				goto cleanup;
+			}
+			lock_buffer(new_bh);
+			error = ext4_journal_get_create_access(handle, new_bh);
+			if (error) {
+				unlock_buffer(new_bh);
+				goto getblk_failed;
+			}
+			memcpy(new_bh->b_data, s->base, new_bh->b_size);
+			set_buffer_uptodate(new_bh);
+			unlock_buffer(new_bh);
+			ext4_xattr_cache_insert(new_bh);
+			error = ext4_handle_dirty_metadata(handle,
+							   inode, new_bh);
+			if (error)
+				goto cleanup;
+		}
+	}
+
+	/* Update the inode. */
+	EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
+
+	/* Drop the previous xattr block. */
+	if (bs->bh && bs->bh != new_bh)
+		ext4_xattr_release_block(handle, inode, bs->bh);
+	error = 0;
+
+cleanup:
+	if (ce)
+		mb_cache_entry_release(ce);
+	brelse(new_bh);
+	if (!(bs->bh && s->base == bs->bh->b_data))
+		kfree(s->base);
+
+	return error;
+
+cleanup_dquot:
+	dquot_free_block(inode, 1);
+	goto cleanup;
+
+bad_block:
+	EXT4_ERROR_INODE(inode, "bad block %llu",
+			 EXT4_I(inode)->i_file_acl);
+	goto cleanup;
+
+#undef header
+}
+
+struct ext4_xattr_ibody_find {
+	struct ext4_xattr_search s;
+	struct ext4_iloc iloc;
+};
+
+static int
+ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
+		      struct ext4_xattr_ibody_find *is)
+{
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_inode *raw_inode;
+	int error;
+
+	if (EXT4_I(inode)->i_extra_isize == 0)
+		return 0;
+	raw_inode = ext4_raw_inode(&is->iloc);
+	header = IHDR(inode, raw_inode);
+	is->s.base = is->s.first = IFIRST(header);
+	is->s.here = is->s.first;
+	is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
+		error = ext4_xattr_check_names(IFIRST(header), is->s.end);
+		if (error)
+			return error;
+		/* Find the named attribute. */
+		error = ext4_xattr_find_entry(&is->s.here, i->name_index,
+					      i->name, is->s.end -
+					      (void *)is->s.base, 0);
+		if (error && error != -ENODATA)
+			return error;
+		is->s.not_found = error;
+	}
+	return 0;
+}
+
+static int
+ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+		     struct ext4_xattr_info *i,
+		     struct ext4_xattr_ibody_find *is)
+{
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_xattr_search *s = &is->s;
+	int error;
+
+	if (EXT4_I(inode)->i_extra_isize == 0)
+		return -ENOSPC;
+	error = ext4_xattr_set_entry(i, s);
+	if (error)
+		return error;
+	header = IHDR(inode, ext4_raw_inode(&is->iloc));
+	if (!IS_LAST_ENTRY(s->first)) {
+		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
+		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
+	} else {
+		header->h_magic = cpu_to_le32(0);
+		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
+	}
+	return 0;
+}
+
+/*
+ * ext4_xattr_set_handle()
+ *
+ * Create, replace or remove an extended attribute for this inode.  Value
+ * is NULL to remove an existing extended attribute, and non-NULL to
+ * either replace an existing extended attribute, or create a new extended
+ * attribute. The flags XATTR_REPLACE and XATTR_CREATE
+ * specify that an extended attribute must exist and must not exist
+ * previous to the call, respectively.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int
+ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
+		      const char *name, const void *value, size_t value_len,
+		      int flags)
+{
+	struct ext4_xattr_info i = {
+		.name_index = name_index,
+		.name = name,
+		.value = value,
+		.value_len = value_len,
+
+	};
+	struct ext4_xattr_ibody_find is = {
+		.s = { .not_found = -ENODATA, },
+	};
+	struct ext4_xattr_block_find bs = {
+		.s = { .not_found = -ENODATA, },
+	};
+	unsigned long no_expand;
+	int error;
+
+	if (!name)
+		return -EINVAL;
+	if (strlen(name) > 255)
+		return -ERANGE;
+	down_write(&EXT4_I(inode)->xattr_sem);
+	no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+
+	error = ext4_get_inode_loc(inode, &is.iloc);
+	if (error)
+		goto cleanup;
+
+	error = ext4_journal_get_write_access(handle, is.iloc.bh);
+	if (error)
+		goto cleanup;
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) {
+		struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
+		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
+		ext4_clear_inode_state(inode, EXT4_STATE_NEW);
+	}
+
+	error = ext4_xattr_ibody_find(inode, &i, &is);
+	if (error)
+		goto cleanup;
+	if (is.s.not_found)
+		error = ext4_xattr_block_find(inode, &i, &bs);
+	if (error)
+		goto cleanup;
+	if (is.s.not_found && bs.s.not_found) {
+		error = -ENODATA;
+		if (flags & XATTR_REPLACE)
+			goto cleanup;
+		error = 0;
+		if (!value)
+			goto cleanup;
+	} else {
+		error = -EEXIST;
+		if (flags & XATTR_CREATE)
+			goto cleanup;
+	}
+	if (!value) {
+		if (!is.s.not_found)
+			error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+		else if (!bs.s.not_found)
+			error = ext4_xattr_block_set(handle, inode, &i, &bs);
+	} else {
+		error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+		if (!error && !bs.s.not_found) {
+			i.value = NULL;
+			error = ext4_xattr_block_set(handle, inode, &i, &bs);
+		} else if (error == -ENOSPC) {
+			if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
+				error = ext4_xattr_block_find(inode, &i, &bs);
+				if (error)
+					goto cleanup;
+			}
+			error = ext4_xattr_block_set(handle, inode, &i, &bs);
+			if (error)
+				goto cleanup;
+			if (!is.s.not_found) {
+				i.value = NULL;
+				error = ext4_xattr_ibody_set(handle, inode, &i,
+							     &is);
+			}
+		}
+	}
+	if (!error) {
+		ext4_xattr_update_super_block(handle, inode->i_sb);
+		inode->i_ctime = ext4_current_time(inode);
+		if (!value)
+			ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
+		/*
+		 * The bh is consumed by ext4_mark_iloc_dirty, even with
+		 * error != 0.
+		 */
+		is.iloc.bh = NULL;
+		if (IS_SYNC(inode))
+			ext4_handle_sync(handle);
+	}
+
+cleanup:
+	brelse(is.iloc.bh);
+	brelse(bs.bh);
+	if (no_expand == 0)
+		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	up_write(&EXT4_I(inode)->xattr_sem);
+	return error;
+}
+
+/*
+ * ext4_xattr_set()
+ *
+ * Like ext4_xattr_set_handle, but start from an inode. This extended
+ * attribute modification is a filesystem transaction by itself.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int
+ext4_xattr_set(struct inode *inode, int name_index, const char *name,
+	       const void *value, size_t value_len, int flags)
+{
+	handle_t *handle;
+	int error, retries = 0;
+
+retry:
+	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+	if (IS_ERR(handle)) {
+		error = PTR_ERR(handle);
+	} else {
+		int error2;
+
+		error = ext4_xattr_set_handle(handle, inode, name_index, name,
+					      value, value_len, flags);
+		error2 = ext4_journal_stop(handle);
+		if (error == -ENOSPC &&
+		    ext4_should_retry_alloc(inode->i_sb, &retries))
+			goto retry;
+		if (error == 0)
+			error = error2;
+	}
+
+	return error;
+}
+
+/*
+ * Shift the EA entries in the inode to create space for the increased
+ * i_extra_isize.
+ */
+static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
+				     int value_offs_shift, void *to,
+				     void *from, size_t n, int blocksize)
+{
+	struct ext4_xattr_entry *last = entry;
+	int new_offs;
+
+	/* Adjust the value offsets of the entries */
+	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+		if (!last->e_value_block && last->e_value_size) {
+			new_offs = le16_to_cpu(last->e_value_offs) +
+							value_offs_shift;
+			BUG_ON(new_offs + le32_to_cpu(last->e_value_size)
+				 > blocksize);
+			last->e_value_offs = cpu_to_le16(new_offs);
+		}
+	}
+	/* Shift the entries by n bytes */
+	memmove(to, from, n);
+}
+
+/*
+ * Expand an inode by new_extra_isize bytes when EAs are present.
+ * Returns 0 on success or negative error number on failure.
+ */
+int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
+			       struct ext4_inode *raw_inode, handle_t *handle)
+{
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_xattr_entry *entry, *last, *first;
+	struct buffer_head *bh = NULL;
+	struct ext4_xattr_ibody_find *is = NULL;
+	struct ext4_xattr_block_find *bs = NULL;
+	char *buffer = NULL, *b_entry_name = NULL;
+	size_t min_offs, free;
+	int total_ino, total_blk;
+	void *base, *start, *end;
+	int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+
+	down_write(&EXT4_I(inode)->xattr_sem);
+retry:
+	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
+		up_write(&EXT4_I(inode)->xattr_sem);
+		return 0;
+	}
+
+	header = IHDR(inode, raw_inode);
+	entry = IFIRST(header);
+
+	/*
+	 * Check if enough free space is available in the inode to shift the
+	 * entries ahead by new_extra_isize.
+	 */
+
+	base = start = entry;
+	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+	min_offs = end - base;
+	last = entry;
+	total_ino = sizeof(struct ext4_xattr_ibody_header);
+
+	free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
+	if (free >= new_extra_isize) {
+		entry = IFIRST(header);
+		ext4_xattr_shift_entries(entry,	EXT4_I(inode)->i_extra_isize
+				- new_extra_isize, (void *)raw_inode +
+				EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
+				(void *)header, total_ino,
+				inode->i_sb->s_blocksize);
+		EXT4_I(inode)->i_extra_isize = new_extra_isize;
+		error = 0;
+		goto cleanup;
+	}
+
+	/*
+	 * Enough free space isn't available in the inode, check if
+	 * EA block can hold new_extra_isize bytes.
+	 */
+	if (EXT4_I(inode)->i_file_acl) {
+		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+		error = -EIO;
+		if (!bh)
+			goto cleanup;
+		if (ext4_xattr_check_block(bh)) {
+			EXT4_ERROR_INODE(inode, "bad block %llu",
+					 EXT4_I(inode)->i_file_acl);
+			error = -EIO;
+			goto cleanup;
+		}
+		base = BHDR(bh);
+		first = BFIRST(bh);
+		end = bh->b_data + bh->b_size;
+		min_offs = end - base;
+		free = ext4_xattr_free_space(first, &min_offs, base,
+					     &total_blk);
+		if (free < new_extra_isize) {
+			if (!tried_min_extra_isize && s_min_extra_isize) {
+				tried_min_extra_isize++;
+				new_extra_isize = s_min_extra_isize;
+				brelse(bh);
+				goto retry;
+			}
+			error = -1;
+			goto cleanup;
+		}
+	} else {
+		free = inode->i_sb->s_blocksize;
+	}
+
+	while (new_extra_isize > 0) {
+		size_t offs, size, entry_size;
+		struct ext4_xattr_entry *small_entry = NULL;
+		struct ext4_xattr_info i = {
+			.value = NULL,
+			.value_len = 0,
+		};
+		unsigned int total_size;  /* EA entry size + value size */
+		unsigned int shift_bytes; /* No. of bytes to shift EAs by? */
+		unsigned int min_total_size = ~0U;
+
+		is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
+		bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
+		if (!is || !bs) {
+			error = -ENOMEM;
+			goto cleanup;
+		}
+
+		is->s.not_found = -ENODATA;
+		bs->s.not_found = -ENODATA;
+		is->iloc.bh = NULL;
+		bs->bh = NULL;
+
+		last = IFIRST(header);
+		/* Find the entry best suited to be pushed into EA block */
+		entry = NULL;
+		for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+			total_size =
+			EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
+					EXT4_XATTR_LEN(last->e_name_len);
+			if (total_size <= free && total_size < min_total_size) {
+				if (total_size < new_extra_isize) {
+					small_entry = last;
+				} else {
+					entry = last;
+					min_total_size = total_size;
+				}
+			}
+		}
+
+		if (entry == NULL) {
+			if (small_entry) {
+				entry = small_entry;
+			} else {
+				if (!tried_min_extra_isize &&
+				    s_min_extra_isize) {
+					tried_min_extra_isize++;
+					new_extra_isize = s_min_extra_isize;
+					goto retry;
+				}
+				error = -1;
+				goto cleanup;
+			}
+		}
+		offs = le16_to_cpu(entry->e_value_offs);
+		size = le32_to_cpu(entry->e_value_size);
+		entry_size = EXT4_XATTR_LEN(entry->e_name_len);
+		i.name_index = entry->e_name_index,
+		buffer = kmalloc(EXT4_XATTR_SIZE(size), GFP_NOFS);
+		b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
+		if (!buffer || !b_entry_name) {
+			error = -ENOMEM;
+			goto cleanup;
+		}
+		/* Save the entry name and the entry value */
+		memcpy(buffer, (void *)IFIRST(header) + offs,
+		       EXT4_XATTR_SIZE(size));
+		memcpy(b_entry_name, entry->e_name, entry->e_name_len);
+		b_entry_name[entry->e_name_len] = '\0';
+		i.name = b_entry_name;
+
+		error = ext4_get_inode_loc(inode, &is->iloc);
+		if (error)
+			goto cleanup;
+
+		error = ext4_xattr_ibody_find(inode, &i, is);
+		if (error)
+			goto cleanup;
+
+		/* Remove the chosen entry from the inode */
+		error = ext4_xattr_ibody_set(handle, inode, &i, is);
+		if (error)
+			goto cleanup;
+
+		entry = IFIRST(header);
+		if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
+			shift_bytes = new_extra_isize;
+		else
+			shift_bytes = entry_size + size;
+		/* Adjust the offsets and shift the remaining entries ahead */
+		ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
+			shift_bytes, (void *)raw_inode +
+			EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
+			(void *)header, total_ino - entry_size,
+			inode->i_sb->s_blocksize);
+
+		extra_isize += shift_bytes;
+		new_extra_isize -= shift_bytes;
+		EXT4_I(inode)->i_extra_isize = extra_isize;
+
+		i.name = b_entry_name;
+		i.value = buffer;
+		i.value_len = size;
+		error = ext4_xattr_block_find(inode, &i, bs);
+		if (error)
+			goto cleanup;
+
+		/* Add entry which was removed from the inode into the block */
+		error = ext4_xattr_block_set(handle, inode, &i, bs);
+		if (error)
+			goto cleanup;
+		kfree(b_entry_name);
+		kfree(buffer);
+		b_entry_name = NULL;
+		buffer = NULL;
+		brelse(is->iloc.bh);
+		kfree(is);
+		kfree(bs);
+	}
+	brelse(bh);
+	up_write(&EXT4_I(inode)->xattr_sem);
+	return 0;
+
+cleanup:
+	kfree(b_entry_name);
+	kfree(buffer);
+	if (is)
+		brelse(is->iloc.bh);
+	kfree(is);
+	kfree(bs);
+	brelse(bh);
+	up_write(&EXT4_I(inode)->xattr_sem);
+	return error;
+}
+
+
+
+/*
+ * ext4_xattr_delete_inode()
+ *
+ * Free extended attribute resources associated with this inode. This
+ * is called immediately before an inode is freed. We have exclusive
+ * access to the inode.
+ */
+void
+ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
+{
+	struct buffer_head *bh = NULL;
+
+	if (!EXT4_I(inode)->i_file_acl)
+		goto cleanup;
+	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+	if (!bh) {
+		EXT4_ERROR_INODE(inode, "block %llu read error",
+				 EXT4_I(inode)->i_file_acl);
+		goto cleanup;
+	}
+	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
+	    BHDR(bh)->h_blocks != cpu_to_le32(1)) {
+		EXT4_ERROR_INODE(inode, "bad block %llu",
+				 EXT4_I(inode)->i_file_acl);
+		goto cleanup;
+	}
+	ext4_xattr_release_block(handle, inode, bh);
+	EXT4_I(inode)->i_file_acl = 0;
+
+cleanup:
+	brelse(bh);
+}
+
+/*
+ * ext4_xattr_put_super()
+ *
+ * This is called when a file system is unmounted.
+ */
+void
+ext4_xattr_put_super(struct super_block *sb)
+{
+	mb_cache_shrink(sb->s_bdev);
+}
+
+/*
+ * ext4_xattr_cache_insert()
+ *
+ * Create a new entry in the extended attribute cache, and insert
+ * it unless such an entry is already in the cache.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+static void
+ext4_xattr_cache_insert(struct buffer_head *bh)
+{
+	__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
+	struct mb_cache_entry *ce;
+	int error;
+
+	ce = mb_cache_entry_alloc(ext4_xattr_cache, GFP_NOFS);
+	if (!ce) {
+		ea_bdebug(bh, "out of memory");
+		return;
+	}
+	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	if (error) {
+		mb_cache_entry_free(ce);
+		if (error == -EBUSY) {
+			ea_bdebug(bh, "already in cache");
+			error = 0;
+		}
+	} else {
+		ea_bdebug(bh, "inserting [%x]", (int)hash);
+		mb_cache_entry_release(ce);
+	}
+}
+
+/*
+ * ext4_xattr_cmp()
+ *
+ * Compare two extended attribute blocks for equality.
+ *
+ * Returns 0 if the blocks are equal, 1 if they differ, and
+ * a negative error number on errors.
+ */
+static int
+ext4_xattr_cmp(struct ext4_xattr_header *header1,
+	       struct ext4_xattr_header *header2)
+{
+	struct ext4_xattr_entry *entry1, *entry2;
+
+	entry1 = ENTRY(header1+1);
+	entry2 = ENTRY(header2+1);
+	while (!IS_LAST_ENTRY(entry1)) {
+		if (IS_LAST_ENTRY(entry2))
+			return 1;
+		if (entry1->e_hash != entry2->e_hash ||
+		    entry1->e_name_index != entry2->e_name_index ||
+		    entry1->e_name_len != entry2->e_name_len ||
+		    entry1->e_value_size != entry2->e_value_size ||
+		    memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len))
+			return 1;
+		if (entry1->e_value_block != 0 || entry2->e_value_block != 0)
+			return -EIO;
+		if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
+			   (char *)header2 + le16_to_cpu(entry2->e_value_offs),
+			   le32_to_cpu(entry1->e_value_size)))
+			return 1;
+
+		entry1 = EXT4_XATTR_NEXT(entry1);
+		entry2 = EXT4_XATTR_NEXT(entry2);
+	}
+	if (!IS_LAST_ENTRY(entry2))
+		return 1;
+	return 0;
+}
+
+/*
+ * ext4_xattr_cache_find()
+ *
+ * Find an identical extended attribute block.
+ *
+ * Returns a pointer to the block found, or NULL if such a block was
+ * not found or an error occurred.
+ */
+static struct buffer_head *
+ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
+		      struct mb_cache_entry **pce)
+{
+	__u32 hash = le32_to_cpu(header->h_hash);
+	struct mb_cache_entry *ce;
+
+	if (!header->h_hash)
+		return NULL;  /* never share */
+	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
+again:
+	ce = mb_cache_entry_find_first(ext4_xattr_cache, inode->i_sb->s_bdev,
+				       hash);
+	while (ce) {
+		struct buffer_head *bh;
+
+		if (IS_ERR(ce)) {
+			if (PTR_ERR(ce) == -EAGAIN)
+				goto again;
+			break;
+		}
+		bh = sb_bread(inode->i_sb, ce->e_block);
+		if (!bh) {
+			EXT4_ERROR_INODE(inode, "block %lu read error",
+					 (unsigned long) ce->e_block);
+		} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
+				EXT4_XATTR_REFCOUNT_MAX) {
+			ea_idebug(inode, "block %lu refcount %d>=%d",
+				  (unsigned long) ce->e_block,
+				  le32_to_cpu(BHDR(bh)->h_refcount),
+					  EXT4_XATTR_REFCOUNT_MAX);
+		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
+			*pce = ce;
+			return bh;
+		}
+		brelse(bh);
+		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+	}
+	return NULL;
+}
+
+#define NAME_HASH_SHIFT 5
+#define VALUE_HASH_SHIFT 16
+
+/*
+ * ext4_xattr_hash_entry()
+ *
+ * Compute the hash of an extended attribute.
+ */
+static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
+					 struct ext4_xattr_entry *entry)
+{
+	__u32 hash = 0;
+	char *name = entry->e_name;
+	int n;
+
+	for (n = 0; n < entry->e_name_len; n++) {
+		hash = (hash << NAME_HASH_SHIFT) ^
+		       (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
+		       *name++;
+	}
+
+	if (entry->e_value_block == 0 && entry->e_value_size != 0) {
+		__le32 *value = (__le32 *)((char *)header +
+			le16_to_cpu(entry->e_value_offs));
+		for (n = (le32_to_cpu(entry->e_value_size) +
+		     EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
+			hash = (hash << VALUE_HASH_SHIFT) ^
+			       (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
+			       le32_to_cpu(*value++);
+		}
+	}
+	entry->e_hash = cpu_to_le32(hash);
+}
+
+#undef NAME_HASH_SHIFT
+#undef VALUE_HASH_SHIFT
+
+#define BLOCK_HASH_SHIFT 16
+
+/*
+ * ext4_xattr_rehash()
+ *
+ * Re-compute the extended attribute hash value after an entry has changed.
+ */
+static void ext4_xattr_rehash(struct ext4_xattr_header *header,
+			      struct ext4_xattr_entry *entry)
+{
+	struct ext4_xattr_entry *here;
+	__u32 hash = 0;
+
+	ext4_xattr_hash_entry(header, entry);
+	here = ENTRY(header+1);
+	while (!IS_LAST_ENTRY(here)) {
+		if (!here->e_hash) {
+			/* Block is not shared if an entry's hash value == 0 */
+			hash = 0;
+			break;
+		}
+		hash = (hash << BLOCK_HASH_SHIFT) ^
+		       (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^
+		       le32_to_cpu(here->e_hash);
+		here = EXT4_XATTR_NEXT(here);
+	}
+	header->h_hash = cpu_to_le32(hash);
+}
+
+#undef BLOCK_HASH_SHIFT
+
+int __init
+ext4_init_xattr(void)
+{
+	ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
+	if (!ext4_xattr_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void
+ext4_exit_xattr(void)
+{
+	if (ext4_xattr_cache)
+		mb_cache_destroy(ext4_xattr_cache);
+	ext4_xattr_cache = NULL;
+}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
new file mode 100644
index 00000000..25b7387f
--- /dev/null
+++ b/fs/ext4/xattr.h
@@ -0,0 +1,155 @@
+/*
+  File: fs/ext4/xattr.h
+
+  On-disk format of extended attributes for the ext4 filesystem.
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/xattr.h>
+
+/* Magic value in attribute blocks */
+#define EXT4_XATTR_MAGIC		0xEA020000
+
+/* Maximum number of references to one attribute block */
+#define EXT4_XATTR_REFCOUNT_MAX		1024
+
+/* Name indexes */
+#define EXT4_XATTR_INDEX_USER			1
+#define EXT4_XATTR_INDEX_POSIX_ACL_ACCESS	2
+#define EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT	3
+#define EXT4_XATTR_INDEX_TRUSTED		4
+#define	EXT4_XATTR_INDEX_LUSTRE			5
+#define EXT4_XATTR_INDEX_SECURITY	        6
+
+struct ext4_xattr_header {
+	__le32	h_magic;	/* magic number for identification */
+	__le32	h_refcount;	/* reference count */
+	__le32	h_blocks;	/* number of disk blocks used */
+	__le32	h_hash;		/* hash value of all attributes */
+	__u32	h_reserved[4];	/* zero right now */
+};
+
+struct ext4_xattr_ibody_header {
+	__le32	h_magic;	/* magic number for identification */
+};
+
+struct ext4_xattr_entry {
+	__u8	e_name_len;	/* length of name */
+	__u8	e_name_index;	/* attribute name index */
+	__le16	e_value_offs;	/* offset in disk block of value */
+	__le32	e_value_block;	/* disk block attribute is stored on (n/i) */
+	__le32	e_value_size;	/* size of attribute value */
+	__le32	e_hash;		/* hash value of name and value */
+	char	e_name[0];	/* attribute name */
+};
+
+#define EXT4_XATTR_PAD_BITS		2
+#define EXT4_XATTR_PAD		(1<<EXT4_XATTR_PAD_BITS)
+#define EXT4_XATTR_ROUND		(EXT4_XATTR_PAD-1)
+#define EXT4_XATTR_LEN(name_len) \
+	(((name_len) + EXT4_XATTR_ROUND + \
+	sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND)
+#define EXT4_XATTR_NEXT(entry) \
+	((struct ext4_xattr_entry *)( \
+	 (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)))
+#define EXT4_XATTR_SIZE(size) \
+	(((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
+
+#define IHDR(inode, raw_inode) \
+	((struct ext4_xattr_ibody_header *) \
+		((void *)raw_inode + \
+		EXT4_GOOD_OLD_INODE_SIZE + \
+		EXT4_I(inode)->i_extra_isize))
+#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
+
+# ifdef CONFIG_EXT4_FS_XATTR
+
+extern const struct xattr_handler ext4_xattr_user_handler;
+extern const struct xattr_handler ext4_xattr_trusted_handler;
+extern const struct xattr_handler ext4_xattr_acl_access_handler;
+extern const struct xattr_handler ext4_xattr_acl_default_handler;
+extern const struct xattr_handler ext4_xattr_security_handler;
+
+extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
+
+extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
+extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
+extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
+
+extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
+extern void ext4_xattr_put_super(struct super_block *);
+
+extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
+			    struct ext4_inode *raw_inode, handle_t *handle);
+
+extern int __init ext4_init_xattr(void);
+extern void ext4_exit_xattr(void);
+
+extern const struct xattr_handler *ext4_xattr_handlers[];
+
+# else  /* CONFIG_EXT4_FS_XATTR */
+
+static inline int
+ext4_xattr_get(struct inode *inode, int name_index, const char *name,
+	       void *buffer, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ext4_xattr_set(struct inode *inode, int name_index, const char *name,
+	       const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
+	       const char *name, const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
+{
+}
+
+static inline void
+ext4_xattr_put_super(struct super_block *sb)
+{
+}
+
+static __init inline int
+ext4_init_xattr(void)
+{
+	return 0;
+}
+
+static inline void
+ext4_exit_xattr(void)
+{
+}
+
+static inline int
+ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
+			    struct ext4_inode *raw_inode, handle_t *handle)
+{
+	return -EOPNOTSUPP;
+}
+
+#define ext4_xattr_handlers	NULL
+
+# endif  /* CONFIG_EXT4_FS_XATTR */
+
+#ifdef CONFIG_EXT4_FS_SECURITY
+extern int ext4_init_security(handle_t *handle, struct inode *inode,
+			      struct inode *dir, const struct qstr *qstr);
+#else
+static inline int ext4_init_security(handle_t *handle, struct inode *inode,
+				     struct inode *dir, const struct qstr *qstr)
+{
+	return 0;
+}
+#endif
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
new file mode 100644
index 00000000..007c3bfb
--- /dev/null
+++ b/fs/ext4/xattr_security.c
@@ -0,0 +1,78 @@
+/*
+ * linux/fs/ext4/xattr_security.c
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+static size_t
+ext4_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+		const char *name, size_t name_len, int type)
+{
+	const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+	const size_t total_len = prefix_len + name_len + 1;
+
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int
+ext4_xattr_security_get(struct dentry *dentry, const char *name,
+		       void *buffer, size_t size, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_security_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+			      name, value, size, flags);
+}
+
+int
+ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
+{
+	int err;
+	size_t len;
+	void *value;
+	char *name;
+
+	err = security_inode_init_security(inode, dir, qstr, &name, &value, &len);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+	err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY,
+				    name, value, len, 0);
+	kfree(name);
+	kfree(value);
+	return err;
+}
+
+const struct xattr_handler ext4_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.list	= ext4_xattr_security_list,
+	.get	= ext4_xattr_security_get,
+	.set	= ext4_xattr_security_set,
+};
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
new file mode 100644
index 00000000..37e6ebca
--- /dev/null
+++ b/fs/ext4/xattr_trusted.c
@@ -0,0 +1,59 @@
+/*
+ * linux/fs/ext4/xattr_trusted.c
+ * Handler for trusted extended attributes.
+ *
+ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+static size_t
+ext4_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+		const char *name, size_t name_len, int type)
+{
+	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+	const size_t total_len = prefix_len + name_len + 1;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int
+ext4_xattr_trusted_get(struct dentry *dentry, const char *name, void *buffer,
+		size_t size, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_trusted_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+			      name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.list	= ext4_xattr_trusted_list,
+	.get	= ext4_xattr_trusted_get,
+	.set	= ext4_xattr_trusted_set,
+};
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
new file mode 100644
index 00000000..98c37535
--- /dev/null
+++ b/fs/ext4/xattr_user.c
@@ -0,0 +1,62 @@
+/*
+ * linux/fs/ext4/xattr_user.c
+ * Handler for extended user attributes.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+static size_t
+ext4_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+		     const char *name, size_t name_len, int type)
+{
+	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
+	const size_t total_len = prefix_len + name_len + 1;
+
+	if (!test_opt(dentry->d_sb, XATTR_USER))
+		return 0;
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_USER_PREFIX, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int
+ext4_xattr_user_get(struct dentry *dentry, const char *name,
+		    void *buffer, size_t size, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!test_opt(dentry->d_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_user_set(struct dentry *dentry, const char *name,
+		    const void *value, size_t size, int flags, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!test_opt(dentry->d_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+			      name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.list	= ext4_xattr_user_list,
+	.get	= ext4_xattr_user_get,
+	.set	= ext4_xattr_user_set,
+};