22 files changed, 3766 insertions, 1758 deletions

diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
new file mode 100644
index 00000000000..14a6780fd03
--- /dev/null
+++ b/fs/ext2/Kconfig
@@ -0,0 +1,55 @@
+config EXT2_FS
+	tristate "Second extended fs support"
+	help
+	  Ext2 is a standard Linux file system for hard disks.
+
+	  To compile this file system support as a module, choose M here: the
+	  module will be called ext2.
+
+	  If unsure, say Y.
+
+config EXT2_FS_XATTR
+	bool "Ext2 extended attributes"
+	depends on EXT2_FS
+	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.
+
+config EXT2_FS_POSIX_ACL
+	bool "Ext2 POSIX Access Control Lists"
+	depends on EXT2_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 EXT2_FS_SECURITY
+	bool "Ext2 Security Labels"
+	depends on EXT2_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 ext2 filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.
+
+config EXT2_FS_XIP
+	bool "Ext2 execute in place support"
+	depends on EXT2_FS && MMU
+	help
+	  Execute in place can be used on memory-backed block devices. If you
+	  enable this option, you can select to mount block devices which are
+	  capable of this feature without using the page cache.
+
+	  If you do not use a block device that is capable of using this,
+	  or if unsure, say N.
diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
index e0b2b43c1fd..f42af45cfd8 100644
--- a/fs/ext2/Makefile
+++ b/fs/ext2/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_EXT2_FS) += ext2.o
 
-ext2-y := balloc.o dir.o file.o fsync.o ialloc.o inode.o \
+ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
 	  ioctl.o namei.o super.o symlink.o
 
 ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 7c420b800c3..27695e6f4e4 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -4,7 +4,6 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
-#include <linux/capability.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -53,16 +52,23 @@ ext2_acl_from_disk(const void *value, size_t size)
 			case ACL_OTHER:
 				value = (char *)value +
 					sizeof(ext2_acl_entry_short);
-				acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
 				break;
 
 			case ACL_USER:
+				value = (char *)value + sizeof(ext2_acl_entry);
+				if ((char *)value > end)
+					goto fail;
+				acl->a_entries[n].e_uid =
+					make_kuid(&init_user_ns,
+						  le32_to_cpu(entry->e_id));
+				break;
 			case ACL_GROUP:
 				value = (char *)value + sizeof(ext2_acl_entry);
 				if ((char *)value > end)
 					goto fail;
-				acl->a_entries[n].e_id =
-					le32_to_cpu(entry->e_id);
+				acl->a_entries[n].e_gid =
+					make_kgid(&init_user_ns,
+						  le32_to_cpu(entry->e_id));
 				break;
 
 			default:
@@ -96,14 +102,19 @@ ext2_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	ext_acl->a_version = cpu_to_le32(EXT2_ACL_VERSION);
 	e = (char *)ext_acl + sizeof(ext2_acl_header);
 	for (n=0; n < acl->a_count; n++) {
+		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
 		ext2_acl_entry *entry = (ext2_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) {
+		entry->e_tag  = cpu_to_le16(acl_e->e_tag);
+		entry->e_perm = cpu_to_le16(acl_e->e_perm);
+		switch(acl_e->e_tag) {
 			case ACL_USER:
+				entry->e_id = cpu_to_le32(
+					from_kuid(&init_user_ns, acl_e->e_uid));
+				e += sizeof(ext2_acl_entry);
+				break;
 			case ACL_GROUP:
-				entry->e_id =
-					cpu_to_le32(acl->a_entries[n].e_id);
+				entry->e_id = cpu_to_le32(
+					from_kgid(&init_user_ns, acl_e->e_gid));
 				e += sizeof(ext2_acl_entry);
 				break;
 
@@ -125,62 +136,26 @@ fail:
 	return ERR_PTR(-EINVAL);
 }
 
-static inline struct posix_acl *
-ext2_iget_acl(struct inode *inode, struct posix_acl **i_acl)
-{
-	struct posix_acl *acl = EXT2_ACL_NOT_CACHED;
-
-	spin_lock(&inode->i_lock);
-	if (*i_acl != EXT2_ACL_NOT_CACHED)
-		acl = posix_acl_dup(*i_acl);
-	spin_unlock(&inode->i_lock);
-
-	return acl;
-}
-
-static inline void
-ext2_iset_acl(struct inode *inode, struct posix_acl **i_acl,
-		   struct posix_acl *acl)
-{
-	spin_lock(&inode->i_lock);
-	if (*i_acl != EXT2_ACL_NOT_CACHED)
-		posix_acl_release(*i_acl);
-	*i_acl = posix_acl_dup(acl);
-	spin_unlock(&inode->i_lock);
-}
-
 /*
  * inode->i_mutex: don't care
  */
-static struct posix_acl *
+struct posix_acl *
 ext2_get_acl(struct inode *inode, int type)
 {
-	struct ext2_inode_info *ei = EXT2_I(inode);
 	int name_index;
 	char *value = NULL;
 	struct posix_acl *acl;
 	int retval;
 
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return NULL;
-
-	switch(type) {
-		case ACL_TYPE_ACCESS:
-			acl = ext2_iget_acl(inode, &ei->i_acl);
-			if (acl != EXT2_ACL_NOT_CACHED)
-				return acl;
-			name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
-			break;
-
-		case ACL_TYPE_DEFAULT:
-			acl = ext2_iget_acl(inode, &ei->i_default_acl);
-			if (acl != EXT2_ACL_NOT_CACHED)
-				return acl;
-			name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT;
-			break;
-
-		default:
-			return ERR_PTR(-EINVAL);
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		BUG();
 	}
 	retval = ext2_xattr_get(inode, name_index, "", NULL, 0);
 	if (retval > 0) {
@@ -197,47 +172,32 @@ ext2_get_acl(struct inode *inode, int type)
 		acl = ERR_PTR(retval);
 	kfree(value);
 
-	if (!IS_ERR(acl)) {
-		switch(type) {
-			case ACL_TYPE_ACCESS:
-				ext2_iset_acl(inode, &ei->i_acl, acl);
-				break;
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
 
-			case ACL_TYPE_DEFAULT:
-				ext2_iset_acl(inode, &ei->i_default_acl, acl);
-				break;
-		}
-	}
 	return acl;
 }
 
 /*
  * inode->i_mutex: down
  */
-static int
-ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+int
+ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-	struct ext2_inode_info *ei = EXT2_I(inode);
 	int name_index;
 	void *value = NULL;
 	size_t size = 0;
 	int error;
 
-	if (S_ISLNK(inode->i_mode))
-		return -EOPNOTSUPP;
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return 0;
-
 	switch(type) {
 		case ACL_TYPE_ACCESS:
 			name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
 			if (acl) {
-				mode_t mode = inode->i_mode;
-				error = posix_acl_equiv_mode(acl, &mode);
+				error = posix_acl_equiv_mode(acl, &inode->i_mode);
 				if (error < 0)
 					return error;
 				else {
-					inode->i_mode = mode;
+					inode->i_ctime = CURRENT_TIME_SEC;
 					mark_inode_dirty(inode);
 					if (error == 0)
 						acl = NULL;
@@ -263,42 +223,11 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 	error = ext2_xattr_set(inode, name_index, "", value, size, 0);
 
 	kfree(value);
-	if (!error) {
-		switch(type) {
-			case ACL_TYPE_ACCESS:
-				ext2_iset_acl(inode, &ei->i_acl, acl);
-				break;
-
-			case ACL_TYPE_DEFAULT:
-				ext2_iset_acl(inode, &ei->i_default_acl, acl);
-				break;
-		}
-	}
+	if (!error)
+		set_cached_acl(inode, type, acl);
 	return error;
 }
 
-static int
-ext2_check_acl(struct inode *inode, int mask)
-{
-	struct posix_acl *acl = ext2_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;
-}
-
-int
-ext2_permission(struct inode *inode, int mask, struct nameidata *nd)
-{
-	return generic_permission(inode, mask, ext2_check_acl);
-}
-
 /*
  * Initialize the ACLs of a new inode. Called from ext2_new_inode.
  *
@@ -308,212 +237,21 @@ ext2_permission(struct inode *inode, int mask, struct nameidata *nd)
 int
 ext2_init_acl(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 = ext2_get_acl(dir, ACL_TYPE_DEFAULT);
-			if (IS_ERR(acl))
-				return PTR_ERR(acl);
-		}
-		if (!acl)
-			inode->i_mode &= ~current->fs->umask;
-	}
-	if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
-               struct posix_acl *clone;
-	       mode_t mode;
-
-		if (S_ISDIR(inode->i_mode)) {
-			error = ext2_set_acl(inode, ACL_TYPE_DEFAULT, acl);
-			if (error)
-				goto cleanup;
-		}
-		clone = posix_acl_clone(acl, GFP_KERNEL);
-		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 = ext2_set_acl(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
-ext2_acl_chmod(struct inode *inode)
-{
-	struct posix_acl *acl, *clone;
-        int error;
-
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return 0;
-	if (S_ISLNK(inode->i_mode))
-		return -EOPNOTSUPP;
-	acl = ext2_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)
-		error = ext2_set_acl(inode, ACL_TYPE_ACCESS, clone);
-	posix_acl_release(clone);
-	return error;
-}
-
-/*
- * Extended attribut handlers
- */
-static size_t
-ext2_xattr_list_acl_access(struct inode *inode, char *list, size_t list_size,
-			   const char *name, size_t name_len)
-{
-	const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
-
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return 0;
-	if (list && size <= list_size)
-		memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
-	return size;
-}
-
-static size_t
-ext2_xattr_list_acl_default(struct inode *inode, char *list, size_t list_size,
-			    const char *name, size_t name_len)
-{
-	const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
-
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return 0;
-	if (list && size <= list_size)
-		memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
-	return size;
-}
-
-static int
-ext2_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
-{
-	struct posix_acl *acl;
+	struct posix_acl *default_acl, *acl;
 	int error;
 
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return -EOPNOTSUPP;
-
-	acl = ext2_get_acl(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
-ext2_xattr_get_acl_access(struct inode *inode, const char *name,
-			  void *buffer, size_t size)
-{
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-	return ext2_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-ext2_xattr_get_acl_default(struct inode *inode, const char *name,
-			   void *buffer, size_t size)
-{
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-	return ext2_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-ext2_xattr_set_acl(struct inode *inode, int type, const void *value,
-		   size_t size)
-{
-	struct posix_acl *acl;
-	int error;
-
-	if (!test_opt(inode->i_sb, POSIX_ACL))
-		return -EOPNOTSUPP;
-	if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-		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;
-
-	error = ext2_set_acl(inode, type, acl);
+	error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+	if (error)
+		return error;
 
-release_and_out:
-	posix_acl_release(acl);
+	if (default_acl) {
+		error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		posix_acl_release(default_acl);
+	}
+	if (acl) {
+		if (!error)
+			error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		posix_acl_release(acl);
+	}
 	return error;
 }
-
-static int
-ext2_xattr_set_acl_access(struct inode *inode, const char *name,
-			  const void *value, size_t size, int flags)
-{
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-	return ext2_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int
-ext2_xattr_set_acl_default(struct inode *inode, const char *name,
-			   const void *value, size_t size, int flags)
-{
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-	return ext2_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
-struct xattr_handler ext2_xattr_acl_access_handler = {
-	.prefix	= POSIX_ACL_XATTR_ACCESS,
-	.list	= ext2_xattr_list_acl_access,
-	.get	= ext2_xattr_get_acl_access,
-	.set	= ext2_xattr_set_acl_access,
-};
-
-struct xattr_handler ext2_xattr_acl_default_handler = {
-	.prefix	= POSIX_ACL_XATTR_DEFAULT,
-	.list	= ext2_xattr_list_acl_default,
-	.get	= ext2_xattr_get_acl_default,
-	.set	= ext2_xattr_set_acl_default,
-};
diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h
index 0bde85bafe3..44937f9fcf3 100644
--- a/fs/ext2/acl.h
+++ b/fs/ext2/acl.h
@@ -53,27 +53,16 @@ static inline int ext2_acl_count(size_t size)
 
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
 
-/* Value for inode->u.ext2_i.i_acl and inode->u.ext2_i.i_default_acl
-   if the ACL has not been cached */
-#define EXT2_ACL_NOT_CACHED ((void *)-1)
-
 /* acl.c */
-extern int ext2_permission (struct inode *, int, struct nameidata *);
-extern int ext2_acl_chmod (struct inode *);
+extern struct posix_acl *ext2_get_acl(struct inode *inode, int type);
+extern int ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 extern int ext2_init_acl (struct inode *, struct inode *);
 
 #else
 #include <linux/sched.h>
-#define ext2_permission NULL
 #define ext2_get_acl	NULL
 #define ext2_set_acl	NULL
 
-static inline int
-ext2_acl_chmod (struct inode *inode)
-{
-	return 0;
-}
-
 static inline int ext2_init_acl (struct inode *inode, struct inode *dir)
 {
 	return 0;
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index b1981d0e95a..9f9992b3792 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -13,6 +13,7 @@
 
 #include "ext2.h"
 #include <linux/quotaops.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/buffer_head.h>
 #include <linux/capability.h>
@@ -29,7 +30,7 @@
  * 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 ext2_read_super).
+ * when a file system is mounted (see ext2_fill_super).
  */
 
 
@@ -69,9 +70,53 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
 	return desc + offset;
 }
 
+static int ext2_valid_block_bitmap(struct super_block *sb,
+					struct ext2_group_desc *desc,
+					unsigned int block_group,
+					struct buffer_head *bh)
+{
+	ext2_grpblk_t offset;
+	ext2_grpblk_t next_zero_bit;
+	ext2_fsblk_t bitmap_blk;
+	ext2_fsblk_t group_first_block;
+
+	group_first_block = ext2_group_first_block_no(sb, block_group);
+
+	/* check whether block bitmap block number is set */
+	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+	offset = bitmap_blk - group_first_block;
+	if (!ext2_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode bitmap block number is set */
+	bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
+	offset = bitmap_blk - group_first_block;
+	if (!ext2_test_bit(offset, bh->b_data))
+		/* bad block bitmap */
+		goto err_out;
+
+	/* check whether the inode table block number is set */
+	bitmap_blk = le32_to_cpu(desc->bg_inode_table);
+	offset = bitmap_blk - group_first_block;
+	next_zero_bit = ext2_find_next_zero_bit(bh->b_data,
+				offset + EXT2_SB(sb)->s_itb_per_group,
+				offset);
+	if (next_zero_bit >= offset + EXT2_SB(sb)->s_itb_per_group)
+		/* good bitmap for inode tables */
+		return 1;
+
+err_out:
+	ext2_error(sb, __func__,
+			"Invalid block bitmap - "
+			"block_group = %d, block = %lu",
+			block_group, bitmap_blk);
+	return 0;
+}
+
 /*
- * Read the bitmap for a given block_group, reading into the specified 
- * slot in the superblock's bitmap cache.
+ * 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.
  */
@@ -80,100 +125,354 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 {
 	struct ext2_group_desc * desc;
 	struct buffer_head * bh = NULL;
-	
-	desc = ext2_get_group_desc (sb, block_group, NULL);
+	ext2_fsblk_t bitmap_blk;
+
+	desc = ext2_get_group_desc(sb, block_group, NULL);
 	if (!desc)
-		goto error_out;
-	bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap));
-	if (!bh)
-		ext2_error (sb, "read_block_bitmap",
+		return NULL;
+	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+	bh = sb_getblk(sb, bitmap_blk);
+	if (unlikely(!bh)) {
+		ext2_error(sb, __func__,
+			    "Cannot read block bitmap - "
+			    "block_group = %d, block_bitmap = %u",
+			    block_group, le32_to_cpu(desc->bg_block_bitmap));
+		return NULL;
+	}
+	if (likely(bh_uptodate_or_lock(bh)))
+		return bh;
+
+	if (bh_submit_read(bh) < 0) {
+		brelse(bh);
+		ext2_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %u",
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
-error_out:
+		return NULL;
+	}
+
+	ext2_valid_block_bitmap(sb, desc, block_group, bh);
+	/*
+	 * file system mounted not to panic on error, continue with corrupt
+	 * bitmap
+	 */
 	return bh;
 }
 
+static void group_adjust_blocks(struct super_block *sb, int group_no,
+	struct ext2_group_desc *desc, struct buffer_head *bh, int count)
+{
+	if (count) {
+		struct ext2_sb_info *sbi = EXT2_SB(sb);
+		unsigned free_blocks;
+
+		spin_lock(sb_bgl_lock(sbi, group_no));
+		free_blocks = le16_to_cpu(desc->bg_free_blocks_count);
+		desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count);
+		spin_unlock(sb_bgl_lock(sbi, group_no));
+		mark_buffer_dirty(bh);
+	}
+}
+
 /*
- * Set sb->s_dirt here because the superblock was "logically" altered.  We
- * need to recalculate its free blocks count and flush it out.
+ * The reservation window structure operations
+ * --------------------------------------------
+ * Operations include:
+ * dump, find, add, remove, is_empty, find_next_reservable_window, etc.
+ *
+ * We use a red-black tree to represent per-filesystem reservation
+ * windows.
+ *
+ */
+
+/**
+ * __rsv_window_dump() -- Dump the filesystem block allocation reservation map
+ * @rb_root:		root of per-filesystem reservation rb tree
+ * @verbose:		verbose mode
+ * @fn:			function which wishes to dump the reservation map
+ *
+ * If verbose is turned on, it will print the whole block reservation
+ * windows(start, end). Otherwise, it will only print out the "bad" windows,
+ * those windows that overlap with their immediate neighbors.
  */
-static int reserve_blocks(struct super_block *sb, int count)
+#if 1
+static void __rsv_window_dump(struct rb_root *root, int verbose,
+			      const char *fn)
 {
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	struct ext2_super_block *es = sbi->s_es;
-	unsigned free_blocks;
-	unsigned root_blocks;
+	struct rb_node *n;
+	struct ext2_reserve_window_node *rsv, *prev;
+	int bad;
+
+restart:
+	n = rb_first(root);
+	bad = 0;
+	prev = NULL;
+
+	printk("Block Allocation Reservation Windows Map (%s):\n", fn);
+	while (n) {
+		rsv = rb_entry(n, struct ext2_reserve_window_node, rsv_node);
+		if (verbose)
+			printk("reservation window 0x%p "
+				"start: %lu, end: %lu\n",
+				rsv, rsv->rsv_start, rsv->rsv_end);
+		if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
+			printk("Bad reservation %p (start >= end)\n",
+			       rsv);
+			bad = 1;
+		}
+		if (prev && prev->rsv_end >= rsv->rsv_start) {
+			printk("Bad reservation %p (prev->end >= start)\n",
+			       rsv);
+			bad = 1;
+		}
+		if (bad) {
+			if (!verbose) {
+				printk("Restarting reservation walk in verbose mode\n");
+				verbose = 1;
+				goto restart;
+			}
+		}
+		n = rb_next(n);
+		prev = rsv;
+	}
+	printk("Window map complete.\n");
+	BUG_ON(bad);
+}
+#define rsv_window_dump(root, verbose) \
+	__rsv_window_dump((root), (verbose), __func__)
+#else
+#define rsv_window_dump(root, verbose) do {} while (0)
+#endif
 
-	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
-	root_blocks = le32_to_cpu(es->s_r_blocks_count);
+/**
+ * goal_in_my_reservation()
+ * @rsv:		inode's reservation window
+ * @grp_goal:		given goal block relative to the allocation block group
+ * @group:		the current allocation block group
+ * @sb:			filesystem super block
+ *
+ * Test if the given goal block (group relative) is within the file's
+ * own block reservation window range.
+ *
+ * If the reservation window is outside the goal allocation group, return 0;
+ * grp_goal (given goal block) could be -1, which means no specific
+ * goal block. In this case, always return 1.
+ * If the goal block is within the reservation window, return 1;
+ * otherwise, return 0;
+ */
+static int
+goal_in_my_reservation(struct ext2_reserve_window *rsv, ext2_grpblk_t grp_goal,
+			unsigned int group, struct super_block * sb)
+{
+	ext2_fsblk_t group_first_block, group_last_block;
 
-	if (free_blocks < count)
-		count = free_blocks;
+	group_first_block = ext2_group_first_block_no(sb, group);
+	group_last_block = group_first_block + EXT2_BLOCKS_PER_GROUP(sb) - 1;
 
-	if (free_blocks < root_blocks + count && !capable(CAP_SYS_RESOURCE) &&
-	    sbi->s_resuid != current->fsuid &&
-	    (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
-		/*
-		 * We are too close to reserve and we are not privileged.
-		 * Can we allocate anything at all?
-		 */
-		if (free_blocks > root_blocks)
-			count = free_blocks - root_blocks;
+	if ((rsv->_rsv_start > group_last_block) ||
+	    (rsv->_rsv_end < group_first_block))
+		return 0;
+	if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
+		|| (grp_goal + group_first_block > rsv->_rsv_end)))
+		return 0;
+	return 1;
+}
+
+/**
+ * search_reserve_window()
+ * @rb_root:		root of reservation tree
+ * @goal:		target allocation block
+ *
+ * Find the reserved window which includes the goal, or the previous one
+ * if the goal is not in any window.
+ * Returns NULL if there are no windows or if all windows start after the goal.
+ */
+static struct ext2_reserve_window_node *
+search_reserve_window(struct rb_root *root, ext2_fsblk_t goal)
+{
+	struct rb_node *n = root->rb_node;
+	struct ext2_reserve_window_node *rsv;
+
+	if (!n)
+		return NULL;
+
+	do {
+		rsv = rb_entry(n, struct ext2_reserve_window_node, rsv_node);
+
+		if (goal < rsv->rsv_start)
+			n = n->rb_left;
+		else if (goal > rsv->rsv_end)
+			n = n->rb_right;
 		else
-			return 0;
+			return rsv;
+	} while (n);
+	/*
+	 * We've fallen off the end of the tree: the goal wasn't inside
+	 * any particular node.  OK, the previous node must be to one
+	 * side of the interval containing the goal.  If it's the RHS,
+	 * we need to back up one.
+	 */
+	if (rsv->rsv_start > goal) {
+		n = rb_prev(&rsv->rsv_node);
+		rsv = rb_entry(n, struct ext2_reserve_window_node, rsv_node);
+	}
+	return rsv;
+}
+
+/*
+ * ext2_rsv_window_add() -- Insert a window to the block reservation rb tree.
+ * @sb:			super block
+ * @rsv:		reservation window to add
+ *
+ * Must be called with rsv_lock held.
+ */
+void ext2_rsv_window_add(struct super_block *sb,
+		    struct ext2_reserve_window_node *rsv)
+{
+	struct rb_root *root = &EXT2_SB(sb)->s_rsv_window_root;
+	struct rb_node *node = &rsv->rsv_node;
+	ext2_fsblk_t start = rsv->rsv_start;
+
+	struct rb_node ** p = &root->rb_node;
+	struct rb_node * parent = NULL;
+	struct ext2_reserve_window_node *this;
+
+	while (*p)
+	{
+		parent = *p;
+		this = rb_entry(parent, struct ext2_reserve_window_node, rsv_node);
+
+		if (start < this->rsv_start)
+			p = &(*p)->rb_left;
+		else if (start > this->rsv_end)
+			p = &(*p)->rb_right;
+		else {
+			rsv_window_dump(root, 1);
+			BUG();
+		}
 	}
 
-	percpu_counter_mod(&sbi->s_freeblocks_counter, -count);
-	sb->s_dirt = 1;
-	return count;
+	rb_link_node(node, parent, p);
+	rb_insert_color(node, root);
 }
 
-static void release_blocks(struct super_block *sb, int count)
+/**
+ * rsv_window_remove() -- unlink a window from the reservation rb tree
+ * @sb:			super block
+ * @rsv:		reservation window to remove
+ *
+ * Mark the block reservation window as not allocated, and unlink it
+ * from the filesystem reservation window rb tree. Must be called with
+ * rsv_lock held.
+ */
+static void rsv_window_remove(struct super_block *sb,
+			      struct ext2_reserve_window_node *rsv)
 {
-	if (count) {
-		struct ext2_sb_info *sbi = EXT2_SB(sb);
+	rsv->rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
+	rsv->rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
+	rsv->rsv_alloc_hit = 0;
+	rb_erase(&rsv->rsv_node, &EXT2_SB(sb)->s_rsv_window_root);
+}
 
-		percpu_counter_mod(&sbi->s_freeblocks_counter, count);
-		sb->s_dirt = 1;
-	}
+/*
+ * rsv_is_empty() -- Check if the reservation window is allocated.
+ * @rsv:		given reservation window to check
+ *
+ * returns 1 if the end block is EXT2_RESERVE_WINDOW_NOT_ALLOCATED.
+ */
+static inline int rsv_is_empty(struct ext2_reserve_window *rsv)
+{
+	/* a valid reservation end block could not be 0 */
+	return (rsv->_rsv_end == EXT2_RESERVE_WINDOW_NOT_ALLOCATED);
 }
 
-static int group_reserve_blocks(struct ext2_sb_info *sbi, int group_no,
-	struct ext2_group_desc *desc, struct buffer_head *bh, int count)
+/**
+ * ext2_init_block_alloc_info()
+ * @inode:		file inode structure
+ *
+ * Allocate and initialize the  reservation window structure, and
+ * link the window to the ext2 inode structure at last
+ *
+ * The reservation window structure is only dynamically allocated
+ * and linked to ext2 inode the first time the open file
+ * needs a new block. So, before every ext2_new_block(s) call, for
+ * regular files, we should check whether the reservation window
+ * structure exists or not. In the latter case, this function is called.
+ * Fail to do so will result in block reservation being turned off for that
+ * open file.
+ *
+ * This function is called from ext2_get_blocks_handle(), also called
+ * when setting the reservation window size through ioctl before the file
+ * is open for write (needs block allocation).
+ *
+ * Needs truncate_mutex protection prior to calling this function.
+ */
+void ext2_init_block_alloc_info(struct inode *inode)
 {
-	unsigned free_blocks;
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	struct ext2_block_alloc_info *block_i;
+	struct super_block *sb = inode->i_sb;
 
-	if (!desc->bg_free_blocks_count)
-		return 0;
+	block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
+	if (block_i) {
+		struct ext2_reserve_window_node *rsv = &block_i->rsv_window_node;
+
+		rsv->rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
+		rsv->rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
 
-	spin_lock(sb_bgl_lock(sbi, group_no));
-	free_blocks = le16_to_cpu(desc->bg_free_blocks_count);
-	if (free_blocks < count)
-		count = free_blocks;
-	desc->bg_free_blocks_count = cpu_to_le16(free_blocks - count);
-	spin_unlock(sb_bgl_lock(sbi, group_no));
-	mark_buffer_dirty(bh);
-	return count;
+	 	/*
+		 * if filesystem is mounted with NORESERVATION, the goal
+		 * reservation window size is set to zero to indicate
+		 * block reservation is off
+		 */
+		if (!test_opt(sb, RESERVATION))
+			rsv->rsv_goal_size = 0;
+		else
+			rsv->rsv_goal_size = EXT2_DEFAULT_RESERVE_BLOCKS;
+		rsv->rsv_alloc_hit = 0;
+		block_i->last_alloc_logical_block = 0;
+		block_i->last_alloc_physical_block = 0;
+	}
+	ei->i_block_alloc_info = block_i;
 }
 
-static void group_release_blocks(struct super_block *sb, int group_no,
-	struct ext2_group_desc *desc, struct buffer_head *bh, int count)
+/**
+ * ext2_discard_reservation()
+ * @inode:		inode
+ *
+ * Discard(free) block reservation window on last file close, or truncate
+ * or at last iput().
+ *
+ * It is being called in three cases:
+ * 	ext2_release_file(): last writer closes the file
+ * 	ext2_clear_inode(): last iput(), when nobody links to this file.
+ * 	ext2_truncate(): when the block indirect map is about to change.
+ */
+void ext2_discard_reservation(struct inode *inode)
 {
-	if (count) {
-		struct ext2_sb_info *sbi = EXT2_SB(sb);
-		unsigned free_blocks;
-
-		spin_lock(sb_bgl_lock(sbi, group_no));
-		free_blocks = le16_to_cpu(desc->bg_free_blocks_count);
-		desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count);
-		spin_unlock(sb_bgl_lock(sbi, group_no));
-		sb->s_dirt = 1;
-		mark_buffer_dirty(bh);
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	struct ext2_block_alloc_info *block_i = ei->i_block_alloc_info;
+	struct ext2_reserve_window_node *rsv;
+	spinlock_t *rsv_lock = &EXT2_SB(inode->i_sb)->s_rsv_window_lock;
+
+	if (!block_i)
+		return;
+
+	rsv = &block_i->rsv_window_node;
+	if (!rsv_is_empty(&rsv->rsv_window)) {
+		spin_lock(rsv_lock);
+		if (!rsv_is_empty(&rsv->rsv_window))
+			rsv_window_remove(inode->i_sb, rsv);
+		spin_unlock(rsv_lock);
 	}
 }
 
-/* Free given blocks, update quota and i_blocks field */
+/**
+ * ext2_free_blocks() -- Free given blocks and update quota and i_blocks
+ * @inode:		inode
+ * @block:		start physical block to free
+ * @count:		number of blocks to free
+ */
 void ext2_free_blocks (struct inode * inode, unsigned long block,
 		       unsigned long count)
 {
@@ -228,16 +527,18 @@ do_more:
 	    in_range (block, le32_to_cpu(desc->bg_inode_table),
 		      sbi->s_itb_per_group) ||
 	    in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table),
-		      sbi->s_itb_per_group))
+		      sbi->s_itb_per_group)) {
 		ext2_error (sb, "ext2_free_blocks",
 			    "Freeing blocks in system zones - "
 			    "Block = %lu, count = %lu",
 			    block, count);
+		goto error_return;
+	}
 
 	for (i = 0, group_freed = 0; i < count; i++) {
 		if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
 						bit + i, bitmap_bh->b_data)) {
-			ext2_error(sb, __FUNCTION__,
+			ext2_error(sb, __func__,
 				"bit already cleared for block %lu", block + i);
 		} else {
 			group_freed++;
@@ -248,7 +549,7 @@ do_more:
 	if (sb->s_flags & MS_SYNCHRONOUS)
 		sync_dirty_buffer(bitmap_bh);
 
-	group_release_blocks(sb, block_group, desc, bh2, group_freed);
+	group_adjust_blocks(sb, block_group, desc, bh2, group_freed);
 	freed += group_freed;
 
 	if (overflow) {
@@ -258,20 +559,53 @@ do_more:
 	}
 error_return:
 	brelse(bitmap_bh);
-	release_blocks(sb, freed);
-	DQUOT_FREE_BLOCK(inode, freed);
+	if (freed) {
+		percpu_counter_add(&sbi->s_freeblocks_counter, freed);
+		dquot_free_block_nodirty(inode, freed);
+		mark_inode_dirty(inode);
+	}
 }
 
-static int grab_block(spinlock_t *lock, char *map, unsigned size, int goal)
+/**
+ * bitmap_search_next_usable_block()
+ * @start:		the starting block (group relative) of the search
+ * @bh:			bufferhead contains the block group bitmap
+ * @maxblocks:		the ending block (group relative) of the reservation
+ *
+ * The bitmap search --- search forward through the actual bitmap on disk until
+ * we find a bit free.
+ */
+static ext2_grpblk_t
+bitmap_search_next_usable_block(ext2_grpblk_t start, struct buffer_head *bh,
+					ext2_grpblk_t maxblocks)
 {
-	int k;
-	char *p, *r;
+	ext2_grpblk_t next;
 
-	if (!ext2_test_bit(goal, map))
-		goto got_it;
+	next = ext2_find_next_zero_bit(bh->b_data, maxblocks, start);
+	if (next >= maxblocks)
+		return -1;
+	return next;
+}
 
-repeat:
-	if (goal) {
+/**
+ * find_next_usable_block()
+ * @start:		the starting block (group relative) to find next
+ * 			allocatable block in bitmap.
+ * @bh:			bufferhead contains the block group bitmap
+ * @maxblocks:		the ending block (group relative) for the search
+ *
+ * Find an allocatable block in a bitmap.  We perform the "most
+ * appropriate allocation" algorithm of looking for a free block near
+ * the initial goal; then for a free byte somewhere in the bitmap;
+ * then for any free bit in the bitmap.
+ */
+static ext2_grpblk_t
+find_next_usable_block(int start, struct buffer_head *bh, int maxblocks)
+{
+	ext2_grpblk_t here, next;
+	char *p, *r;
+
+	if (start > 0) {
 		/*
 		 * The goal was occupied; search forward for a free 
 		 * block within the next XX blocks.
@@ -280,261 +614,831 @@ repeat:
 		 * less than EXT2_BLOCKS_PER_GROUP. Aligning up to the
 		 * next 64-bit boundary is simple..
 		 */
-		k = (goal + 63) & ~63;
-		goal = ext2_find_next_zero_bit(map, k, goal);
-		if (goal < k)
-			goto got_it;
+		ext2_grpblk_t end_goal = (start + 63) & ~63;
+		if (end_goal > maxblocks)
+			end_goal = maxblocks;
+		here = ext2_find_next_zero_bit(bh->b_data, end_goal, start);
+		if (here < end_goal)
+			return here;
+		ext2_debug("Bit not found near goal\n");
+	}
+
+	here = start;
+	if (here < 0)
+		here = 0;
+
+	p = ((char *)bh->b_data) + (here >> 3);
+	r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3));
+	next = (r - ((char *)bh->b_data)) << 3;
+
+	if (next < maxblocks && next >= here)
+		return next;
+
+	here = bitmap_search_next_usable_block(here, bh, maxblocks);
+	return here;
+}
+
+/**
+ * ext2_try_to_allocate()
+ * @sb:			superblock
+ * @group:		given allocation block group
+ * @bitmap_bh:		bufferhead holds the block bitmap
+ * @grp_goal:		given target block within the group
+ * @count:		target number of blocks to allocate
+ * @my_rsv:		reservation window
+ *
+ * Attempt to allocate blocks within a give range. Set the range of allocation
+ * first, then find the first free bit(s) from the bitmap (within the range),
+ * and at last, allocate the blocks by claiming the found free bit as allocated.
+ *
+ * To set the range of this allocation:
+ * 	if there is a reservation window, only try to allocate block(s)
+ * 	from the file's own reservation window;
+ * 	Otherwise, the allocation range starts from the give goal block,
+ * 	ends at the block group's last block.
+ *
+ * If we failed to allocate the desired block then we may end up crossing to a
+ * new bitmap.
+ */
+static int
+ext2_try_to_allocate(struct super_block *sb, int group,
+			struct buffer_head *bitmap_bh, ext2_grpblk_t grp_goal,
+			unsigned long *count,
+			struct ext2_reserve_window *my_rsv)
+{
+	ext2_fsblk_t group_first_block;
+       	ext2_grpblk_t start, end;
+	unsigned long num = 0;
+
+	/* we do allocation within the reservation window if we have a window */
+	if (my_rsv) {
+		group_first_block = ext2_group_first_block_no(sb, group);
+		if (my_rsv->_rsv_start >= group_first_block)
+			start = my_rsv->_rsv_start - group_first_block;
+		else
+			/* reservation window cross group boundary */
+			start = 0;
+		end = my_rsv->_rsv_end - group_first_block + 1;
+		if (end > EXT2_BLOCKS_PER_GROUP(sb))
+			/* reservation window crosses group boundary */
+			end = EXT2_BLOCKS_PER_GROUP(sb);
+		if ((start <= grp_goal) && (grp_goal < end))
+			start = grp_goal;
+		else
+			grp_goal = -1;
+	} else {
+		if (grp_goal > 0)
+			start = grp_goal;
+		else
+			start = 0;
+		end = EXT2_BLOCKS_PER_GROUP(sb);
+	}
+
+	BUG_ON(start > EXT2_BLOCKS_PER_GROUP(sb));
+
+repeat:
+	if (grp_goal < 0) {
+		grp_goal = find_next_usable_block(start, bitmap_bh, end);
+		if (grp_goal < 0)
+			goto fail_access;
+		if (!my_rsv) {
+			int i;
+
+			for (i = 0; i < 7 && grp_goal > start &&
+					!ext2_test_bit(grp_goal - 1,
+					     		bitmap_bh->b_data);
+			     		i++, grp_goal--)
+				;
+		}
+	}
+	start = grp_goal;
+
+	if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group), grp_goal,
+			       				bitmap_bh->b_data)) {
+		/*
+		 * The block was allocated by another thread, or it was
+		 * allocated and then freed by another thread
+		 */
+		start++;
+		grp_goal++;
+		if (start >= end)
+			goto fail_access;
+		goto repeat;
+	}
+	num++;
+	grp_goal++;
+	while (num < *count && grp_goal < end
+		&& !ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group),
+					grp_goal, bitmap_bh->b_data)) {
+		num++;
+		grp_goal++;
+	}
+	*count = num;
+	return grp_goal - num;
+fail_access:
+	*count = num;
+	return -1;
+}
+
+/**
+ * 	find_next_reservable_window():
+ *		find a reservable space within the given range.
+ *		It does not allocate the reservation window for now:
+ *		alloc_new_reservation() will do the work later.
+ *
+ * 	@search_head: the head of the searching list;
+ *		This is not necessarily the list head of the whole filesystem
+ *
+ *		We have both head and start_block to assist the search
+ *		for the reservable space. The list starts from head,
+ *		but we will shift to the place where start_block is,
+ *		then start from there, when looking for a reservable space.
+ *
+ * 	@size: the target new reservation window size
+ *
+ * 	@group_first_block: the first block we consider to start
+ *			the real search from
+ *
+ * 	@last_block:
+ *		the maximum block number that our goal reservable space
+ *		could start from. This is normally the last block in this
+ *		group. The search will end when we found the start of next
+ *		possible reservable space is out of this boundary.
+ *		This could handle the cross boundary reservation window
+ *		request.
+ *
+ * 	basically we search from the given range, rather than the whole
+ * 	reservation double linked list, (start_block, last_block)
+ * 	to find a free region that is of my size and has not
+ * 	been reserved.
+ *
+ */
+static int find_next_reservable_window(
+				struct ext2_reserve_window_node *search_head,
+				struct ext2_reserve_window_node *my_rsv,
+				struct super_block * sb,
+				ext2_fsblk_t start_block,
+				ext2_fsblk_t last_block)
+{
+	struct rb_node *next;
+	struct ext2_reserve_window_node *rsv, *prev;
+	ext2_fsblk_t cur;
+	int size = my_rsv->rsv_goal_size;
+
+	/* TODO: make the start of the reservation window byte-aligned */
+	/* cur = *start_block & ~7;*/
+	cur = start_block;
+	rsv = search_head;
+	if (!rsv)
+		return -1;
+
+	while (1) {
+		if (cur <= rsv->rsv_end)
+			cur = rsv->rsv_end + 1;
+
+		/* TODO?
+		 * in the case we could not find a reservable space
+		 * that is what is expected, during the re-search, we could
+		 * remember what's the largest reservable space we could have
+		 * and return that one.
+		 *
+		 * For now it will fail if we could not find the reservable
+		 * space with expected-size (or more)...
+		 */
+		if (cur > last_block)
+			return -1;		/* fail */
+
+		prev = rsv;
+		next = rb_next(&rsv->rsv_node);
+		rsv = rb_entry(next,struct ext2_reserve_window_node,rsv_node);
+
 		/*
-		 * Search in the remainder of the current group.
+		 * Reached the last reservation, we can just append to the
+		 * previous one.
 		 */
+		if (!next)
+			break;
+
+		if (cur + size <= rsv->rsv_start) {
+			/*
+			 * Found a reserveable space big enough.  We could
+			 * have a reservation across the group boundary here
+		 	 */
+			break;
+		}
 	}
+	/*
+	 * we come here either :
+	 * when we reach the end of the whole list,
+	 * and there is empty reservable space after last entry in the list.
+	 * append it to the end of the list.
+	 *
+	 * or we found one reservable space in the middle of the list,
+	 * return the reservation window that we could append to.
+	 * succeed.
+	 */
+
+	if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
+		rsv_window_remove(sb, my_rsv);
+
+	/*
+	 * Let's book the whole available window for now.  We will check the
+	 * disk bitmap later and then, if there are free blocks then we adjust
+	 * the window size if it's larger than requested.
+	 * Otherwise, we will remove this node from the tree next time
+	 * call find_next_reservable_window.
+	 */
+	my_rsv->rsv_start = cur;
+	my_rsv->rsv_end = cur + size - 1;
+	my_rsv->rsv_alloc_hit = 0;
+
+	if (prev != my_rsv)
+		ext2_rsv_window_add(sb, my_rsv);
+
+	return 0;
+}
+
+/**
+ * 	alloc_new_reservation()--allocate a new reservation window
+ *
+ *		To make a new reservation, we search part of the filesystem
+ *		reservation list (the list that inside the group). We try to
+ *		allocate a new reservation window near the allocation goal,
+ *		or the beginning of the group, if there is no goal.
+ *
+ *		We first find a reservable space after the goal, then from
+ *		there, we check the bitmap for the first free block after
+ *		it. If there is no free block until the end of group, then the
+ *		whole group is full, we failed. Otherwise, check if the free
+ *		block is inside the expected reservable space, if so, we
+ *		succeed.
+ *		If the first free block is outside the reservable space, then
+ *		start from the first free block, we search for next available
+ *		space, and go on.
+ *
+ *	on succeed, a new reservation will be found and inserted into the list
+ *	It contains at least one free block, and it does not overlap with other
+ *	reservation windows.
+ *
+ *	failed: we failed to find a reservation window in this group
+ *
+ *	@rsv: the reservation
+ *
+ *	@grp_goal: The goal (group-relative).  It is where the search for a
+ *		free reservable space should start from.
+ *		if we have a goal(goal >0 ), then start from there,
+ *		no goal(goal = -1), we start from the first block
+ *		of the group.
+ *
+ *	@sb: the super block
+ *	@group: the group we are trying to allocate in
+ *	@bitmap_bh: the block group block bitmap
+ *
+ */
+static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv,
+		ext2_grpblk_t grp_goal, struct super_block *sb,
+		unsigned int group, struct buffer_head *bitmap_bh)
+{
+	struct ext2_reserve_window_node *search_head;
+	ext2_fsblk_t group_first_block, group_end_block, start_block;
+	ext2_grpblk_t first_free_block;
+	struct rb_root *fs_rsv_root = &EXT2_SB(sb)->s_rsv_window_root;
+	unsigned long size;
+	int ret;
+	spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock;
+
+	group_first_block = ext2_group_first_block_no(sb, group);
+	group_end_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+
+	if (grp_goal < 0)
+		start_block = group_first_block;
+	else
+		start_block = grp_goal + group_first_block;
+
+	size = my_rsv->rsv_goal_size;
 
-	p = map + (goal >> 3);
-	r = memscan(p, 0, (size - goal + 7) >> 3);
-	k = (r - map) << 3;
-	if (k < size) {
-		/* 
-		 * We have succeeded in finding a free byte in the block
-		 * bitmap.  Now search backwards to find the start of this
-		 * group of free blocks - won't take more than 7 iterations.
+	if (!rsv_is_empty(&my_rsv->rsv_window)) {
+		/*
+		 * if the old reservation is cross group boundary
+		 * and if the goal is inside the old reservation window,
+		 * we will come here when we just failed to allocate from
+		 * the first part of the window. We still have another part
+		 * that belongs to the next group. In this case, there is no
+		 * point to discard our window and try to allocate a new one
+		 * in this group(which will fail). we should
+		 * keep the reservation window, just simply move on.
+		 *
+		 * Maybe we could shift the start block of the reservation
+		 * window to the first block of next group.
 		 */
-		for (goal = k; goal && !ext2_test_bit (goal - 1, map); goal--)
-			;
-		goto got_it;
+
+		if ((my_rsv->rsv_start <= group_end_block) &&
+				(my_rsv->rsv_end > group_end_block) &&
+				(start_block >= my_rsv->rsv_start))
+			return -1;
+
+		if ((my_rsv->rsv_alloc_hit >
+		     (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) {
+			/*
+			 * if the previously allocation hit ratio is
+			 * greater than 1/2, then we double the size of
+			 * the reservation window the next time,
+			 * otherwise we keep the same size window
+			 */
+			size = size * 2;
+			if (size > EXT2_MAX_RESERVE_BLOCKS)
+				size = EXT2_MAX_RESERVE_BLOCKS;
+			my_rsv->rsv_goal_size= size;
+		}
 	}
 
-	k = ext2_find_next_zero_bit ((u32 *)map, size, goal);
-	if (k < size) {
-		goal = k;
-		goto got_it;
+	spin_lock(rsv_lock);
+	/*
+	 * shift the search start to the window near the goal block
+	 */
+	search_head = search_reserve_window(fs_rsv_root, start_block);
+
+	/*
+	 * find_next_reservable_window() simply finds a reservable window
+	 * inside the given range(start_block, group_end_block).
+	 *
+	 * To make sure the reservation window has a free bit inside it, we
+	 * need to check the bitmap after we found a reservable window.
+	 */
+retry:
+	ret = find_next_reservable_window(search_head, my_rsv, sb,
+						start_block, group_end_block);
+
+	if (ret == -1) {
+		if (!rsv_is_empty(&my_rsv->rsv_window))
+			rsv_window_remove(sb, my_rsv);
+		spin_unlock(rsv_lock);
+		return -1;
 	}
-	return -1;
-got_it:
-	if (ext2_set_bit_atomic(lock, goal, (void *) map)) 
-		goto repeat;	
-	return goal;
+
+	/*
+	 * On success, find_next_reservable_window() returns the
+	 * reservation window where there is a reservable space after it.
+	 * Before we reserve this reservable space, we need
+	 * to make sure there is at least a free block inside this region.
+	 *
+	 * Search the first free bit on the block bitmap.  Search starts from
+	 * the start block of the reservable space we just found.
+	 */
+	spin_unlock(rsv_lock);
+	first_free_block = bitmap_search_next_usable_block(
+			my_rsv->rsv_start - group_first_block,
+			bitmap_bh, group_end_block - group_first_block + 1);
+
+	if (first_free_block < 0) {
+		/*
+		 * no free block left on the bitmap, no point
+		 * to reserve the space. return failed.
+		 */
+		spin_lock(rsv_lock);
+		if (!rsv_is_empty(&my_rsv->rsv_window))
+			rsv_window_remove(sb, my_rsv);
+		spin_unlock(rsv_lock);
+		return -1;		/* failed */
+	}
+
+	start_block = first_free_block + group_first_block;
+	/*
+	 * check if the first free block is within the
+	 * free space we just reserved
+	 */
+	if (start_block >= my_rsv->rsv_start && start_block <= my_rsv->rsv_end)
+		return 0;		/* success */
+	/*
+	 * if the first free bit we found is out of the reservable space
+	 * continue search for next reservable space,
+	 * start from where the free block is,
+	 * we also shift the list head to where we stopped last time
+	 */
+	search_head = my_rsv;
+	spin_lock(rsv_lock);
+	goto retry;
+}
+
+/**
+ * try_to_extend_reservation()
+ * @my_rsv:		given reservation window
+ * @sb:			super block
+ * @size:		the delta to extend
+ *
+ * Attempt to expand the reservation window large enough to have
+ * required number of free blocks
+ *
+ * Since ext2_try_to_allocate() will always allocate blocks within
+ * the reservation window range, if the window size is too small,
+ * multiple blocks allocation has to stop at the end of the reservation
+ * window. To make this more efficient, given the total number of
+ * blocks needed and the current size of the window, we try to
+ * expand the reservation window size if necessary on a best-effort
+ * basis before ext2_new_blocks() tries to allocate blocks.
+ */
+static void try_to_extend_reservation(struct ext2_reserve_window_node *my_rsv,
+			struct super_block *sb, int size)
+{
+	struct ext2_reserve_window_node *next_rsv;
+	struct rb_node *next;
+	spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock;
+
+	if (!spin_trylock(rsv_lock))
+		return;
+
+	next = rb_next(&my_rsv->rsv_node);
+
+	if (!next)
+		my_rsv->rsv_end += size;
+	else {
+		next_rsv = rb_entry(next, struct ext2_reserve_window_node, rsv_node);
+
+		if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
+			my_rsv->rsv_end += size;
+		else
+			my_rsv->rsv_end = next_rsv->rsv_start - 1;
+	}
+	spin_unlock(rsv_lock);
+}
+
+/**
+ * ext2_try_to_allocate_with_rsv()
+ * @sb:			superblock
+ * @group:		given allocation block group
+ * @bitmap_bh:		bufferhead holds the block bitmap
+ * @grp_goal:		given target block within the group
+ * @count:		target number of blocks to allocate
+ * @my_rsv:		reservation window
+ *
+ * This is the main function used to allocate a new block and its reservation
+ * window.
+ *
+ * Each time when a new block allocation is need, first try to allocate from
+ * its own reservation.  If it does not have a reservation window, instead of
+ * looking for a free bit on bitmap first, then look up the reservation list to
+ * see if it is inside somebody else's reservation window, we try to allocate a
+ * reservation window for it starting from the goal first. Then do the block
+ * allocation within the reservation window.
+ *
+ * This will avoid keeping on searching the reservation list again and
+ * again when somebody is looking for a free block (without
+ * reservation), and there are lots of free blocks, but they are all
+ * being reserved.
+ *
+ * We use a red-black tree for the per-filesystem reservation list.
+ */
+static ext2_grpblk_t
+ext2_try_to_allocate_with_rsv(struct super_block *sb, unsigned int group,
+			struct buffer_head *bitmap_bh, ext2_grpblk_t grp_goal,
+			struct ext2_reserve_window_node * my_rsv,
+			unsigned long *count)
+{
+	ext2_fsblk_t group_first_block, group_last_block;
+	ext2_grpblk_t ret = 0;
+	unsigned long num = *count;
+
+	/*
+	 * we don't deal with reservation when
+	 * filesystem is mounted without reservation
+	 * or the file is not a regular file
+	 * or last attempt to allocate a block with reservation turned on failed
+	 */
+	if (my_rsv == NULL) {
+		return ext2_try_to_allocate(sb, group, bitmap_bh,
+						grp_goal, count, NULL);
+	}
+	/*
+	 * grp_goal is a group relative block number (if there is a goal)
+	 * 0 <= grp_goal < EXT2_BLOCKS_PER_GROUP(sb)
+	 * first block is a filesystem wide block number
+	 * first block is the block number of the first block in this group
+	 */
+	group_first_block = ext2_group_first_block_no(sb, group);
+	group_last_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+
+	/*
+	 * Basically we will allocate a new block from inode's reservation
+	 * window.
+	 *
+	 * We need to allocate a new reservation window, if:
+	 * a) inode does not have a reservation window; or
+	 * b) last attempt to allocate a block from existing reservation
+	 *    failed; or
+	 * c) we come here with a goal and with a reservation window
+	 *
+	 * We do not need to allocate a new reservation window if we come here
+	 * at the beginning with a goal and the goal is inside the window, or
+	 * we don't have a goal but already have a reservation window.
+	 * then we could go to allocate from the reservation window directly.
+	 */
+	while (1) {
+		if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
+			!goal_in_my_reservation(&my_rsv->rsv_window,
+						grp_goal, group, sb)) {
+			if (my_rsv->rsv_goal_size < *count)
+				my_rsv->rsv_goal_size = *count;
+			ret = alloc_new_reservation(my_rsv, grp_goal, sb,
+							group, bitmap_bh);
+			if (ret < 0)
+				break;			/* failed */
+
+			if (!goal_in_my_reservation(&my_rsv->rsv_window,
+							grp_goal, group, sb))
+				grp_goal = -1;
+		} else if (grp_goal >= 0) {
+			int curr = my_rsv->rsv_end -
+					(grp_goal + group_first_block) + 1;
+
+			if (curr < *count)
+				try_to_extend_reservation(my_rsv, sb,
+							*count - curr);
+		}
+
+		if ((my_rsv->rsv_start > group_last_block) ||
+				(my_rsv->rsv_end < group_first_block)) {
+			rsv_window_dump(&EXT2_SB(sb)->s_rsv_window_root, 1);
+			BUG();
+		}
+		ret = ext2_try_to_allocate(sb, group, bitmap_bh, grp_goal,
+					   &num, &my_rsv->rsv_window);
+		if (ret >= 0) {
+			my_rsv->rsv_alloc_hit += num;
+			*count = num;
+			break;				/* succeed */
+		}
+		num = *count;
+	}
+	return ret;
+}
+
+/**
+ * ext2_has_free_blocks()
+ * @sbi:		in-core super block structure.
+ *
+ * Check if filesystem has at least 1 free block available for allocation.
+ */
+static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
+{
+	ext2_fsblk_t free_blocks, root_blocks;
+
+	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
+	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
+		!uid_eq(sbi->s_resuid, current_fsuid()) &&
+		(gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) ||
+		 !in_group_p (sbi->s_resgid))) {
+		return 0;
+	}
+	return 1;
 }
 
 /*
- * ext2_new_block uses a goal block to assist allocation.  If the goal is
+ * ext2_new_blocks() -- core block(s) allocation function
+ * @inode:		file inode
+ * @goal:		given target block(filesystem wide)
+ * @count:		target number of blocks to allocate
+ * @errp:		error code
+ *
+ * ext2_new_blocks uses a goal block to assist allocation.  If the goal is
  * free, or there is a free block within 32 blocks of the goal, that block
  * is allocated.  Otherwise a forward search is made for a free block; within 
  * each block group the search first looks for an entire free byte in the block
  * bitmap, and then for any free bit if that fails.
  * This function also updates quota and i_blocks field.
  */
-int ext2_new_block(struct inode *inode, unsigned long goal,
-			u32 *prealloc_count, u32 *prealloc_block, int *err)
+ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
+		    unsigned long *count, int *errp)
 {
 	struct buffer_head *bitmap_bh = NULL;
-	struct buffer_head *gdp_bh;	/* bh2 */
-	struct ext2_group_desc *desc;
-	int group_no;			/* i */
-	int ret_block;			/* j */
-	int group_idx;			/* k */
-	int target_block;		/* tmp */
-	int block = 0;
-	struct super_block *sb = inode->i_sb;
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	struct ext2_super_block *es = sbi->s_es;
-	unsigned group_size = EXT2_BLOCKS_PER_GROUP(sb);
-	unsigned prealloc_goal = es->s_prealloc_blocks;
-	unsigned group_alloc = 0, es_alloc, dq_alloc;
-	int nr_scanned_groups;
-
-	if (!prealloc_goal--)
-		prealloc_goal = EXT2_DEFAULT_PREALLOC_BLOCKS - 1;
-	if (!prealloc_count || *prealloc_count)
-		prealloc_goal = 0;
-
-	if (DQUOT_ALLOC_BLOCK(inode, 1)) {
-		*err = -EDQUOT;
-		goto out;
-	}
+	struct buffer_head *gdp_bh;
+	int group_no;
+	int goal_group;
+	ext2_grpblk_t grp_target_blk;	/* blockgroup relative goal block */
+	ext2_grpblk_t grp_alloc_blk;	/* blockgroup-relative allocated block*/
+	ext2_fsblk_t ret_block;		/* filesyetem-wide allocated block */
+	int bgi;			/* blockgroup iteration index */
+	int performed_allocation = 0;
+	ext2_grpblk_t free_blocks;	/* number of free blocks in a group */
+	struct super_block *sb;
+	struct ext2_group_desc *gdp;
+	struct ext2_super_block *es;
+	struct ext2_sb_info *sbi;
+	struct ext2_reserve_window_node *my_rsv = NULL;
+	struct ext2_block_alloc_info *block_i;
+	unsigned short windowsz = 0;
+	unsigned long ngroups;
+	unsigned long num = *count;
+	int ret;
 
-	while (prealloc_goal && DQUOT_PREALLOC_BLOCK(inode, prealloc_goal))
-		prealloc_goal--;
+	*errp = -ENOSPC;
+	sb = inode->i_sb;
 
-	dq_alloc = prealloc_goal + 1;
-	es_alloc = reserve_blocks(sb, dq_alloc);
-	if (!es_alloc) {
-		*err = -ENOSPC;
-		goto out_dquot;
+	/*
+	 * Check quota for allocation of this block.
+	 */
+	ret = dquot_alloc_block(inode, num);
+	if (ret) {
+		*errp = ret;
+		return 0;
 	}
 
-	ext2_debug ("goal=%lu.\n", goal);
+	sbi = EXT2_SB(sb);
+	es = EXT2_SB(sb)->s_es;
+	ext2_debug("goal=%lu.\n", goal);
+	/*
+	 * Allocate a block from reservation only when
+	 * filesystem is mounted with reservation(default,-o reservation), and
+	 * it's a regular file, and
+	 * the desired window size is greater than 0 (One could use ioctl
+	 * command EXT2_IOC_SETRSVSZ to set the window size to 0 to turn off
+	 * reservation on that particular file)
+	 */
+	block_i = EXT2_I(inode)->i_block_alloc_info;
+	if (block_i) {
+		windowsz = block_i->rsv_window_node.rsv_goal_size;
+		if (windowsz > 0)
+			my_rsv = &block_i->rsv_window_node;
+	}
+
+	if (!ext2_has_free_blocks(sbi)) {
+		*errp = -ENOSPC;
+		goto out;
+	}
 
+	/*
+	 * First, test whether the goal block is free.
+	 */
 	if (goal < le32_to_cpu(es->s_first_data_block) ||
 	    goal >= le32_to_cpu(es->s_blocks_count))
 		goal = le32_to_cpu(es->s_first_data_block);
-	group_no = (goal - le32_to_cpu(es->s_first_data_block)) / group_size;
-	desc = ext2_get_group_desc (sb, group_no, &gdp_bh);
-	if (!desc) {
-		/*
-		 * gdp_bh may still be uninitialised.  But group_release_blocks
-		 * will not touch it because group_alloc is zero.
-		 */
+	group_no = (goal - le32_to_cpu(es->s_first_data_block)) /
+			EXT2_BLOCKS_PER_GROUP(sb);
+	goal_group = group_no;
+retry_alloc:
+	gdp = ext2_get_group_desc(sb, group_no, &gdp_bh);
+	if (!gdp)
 		goto io_error;
-	}
 
-	group_alloc = group_reserve_blocks(sbi, group_no, desc,
-					gdp_bh, es_alloc);
-	if (group_alloc) {
-		ret_block = ((goal - le32_to_cpu(es->s_first_data_block)) %
-					group_size);
-		brelse(bitmap_bh);
+	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+	/*
+	 * if there is not enough free blocks to make a new resevation
+	 * turn off reservation for this allocation
+	 */
+	if (my_rsv && (free_blocks < windowsz)
+		&& (free_blocks > 0)
+		&& (rsv_is_empty(&my_rsv->rsv_window)))
+		my_rsv = NULL;
+
+	if (free_blocks > 0) {
+		grp_target_blk = ((goal - le32_to_cpu(es->s_first_data_block)) %
+				EXT2_BLOCKS_PER_GROUP(sb));
 		bitmap_bh = read_block_bitmap(sb, group_no);
 		if (!bitmap_bh)
 			goto io_error;
-		
-		ext2_debug("goal is at %d:%d.\n", group_no, ret_block);
-
-		ret_block = grab_block(sb_bgl_lock(sbi, group_no),
-				bitmap_bh->b_data, group_size, ret_block);
-		if (ret_block >= 0)
-			goto got_block;
-		group_release_blocks(sb, group_no, desc, gdp_bh, group_alloc);
-		group_alloc = 0;
+		grp_alloc_blk = ext2_try_to_allocate_with_rsv(sb, group_no,
+					bitmap_bh, grp_target_blk,
+					my_rsv, &num);
+		if (grp_alloc_blk >= 0)
+			goto allocated;
 	}
 
-	ext2_debug ("Bit not found in block group %d.\n", group_no);
+	ngroups = EXT2_SB(sb)->s_groups_count;
+	smp_rmb();
 
 	/*
-	 * Now search the rest of the groups.  We assume that 
-	 * i and desc correctly point to the last group visited.
+	 * Now search the rest of the groups.  We assume that
+	 * group_no and gdp correctly point to the last group visited.
 	 */
-	nr_scanned_groups = 0;
-retry:
-	for (group_idx = 0; !group_alloc &&
-			group_idx < sbi->s_groups_count; group_idx++) {
+	for (bgi = 0; bgi < ngroups; bgi++) {
 		group_no++;
-		if (group_no >= sbi->s_groups_count)
+		if (group_no >= ngroups)
 			group_no = 0;
-		desc = ext2_get_group_desc(sb, group_no, &gdp_bh);
-		if (!desc)
+		gdp = ext2_get_group_desc(sb, group_no, &gdp_bh);
+		if (!gdp)
 			goto io_error;
-		group_alloc = group_reserve_blocks(sbi, group_no, desc,
-						gdp_bh, es_alloc);
-	}
-	if (!group_alloc) {
-		*err = -ENOSPC;
-		goto out_release;
-	}
-	brelse(bitmap_bh);
-	bitmap_bh = read_block_bitmap(sb, group_no);
-	if (!bitmap_bh)
-		goto io_error;
 
-	ret_block = grab_block(sb_bgl_lock(sbi, group_no), bitmap_bh->b_data,
-				group_size, 0);
-	if (ret_block < 0) {
+		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+		/*
+		 * skip this group (and avoid loading bitmap) if there
+		 * are no free blocks
+		 */
+		if (!free_blocks)
+			continue;
 		/*
-		 * If a free block counter is corrupted we can loop inifintely.
-		 * Detect that here.
+		 * skip this group if the number of
+		 * free blocks is less than half of the reservation
+		 * window size.
 		 */
-		nr_scanned_groups++;
-		if (nr_scanned_groups > 2 * sbi->s_groups_count) {
-			ext2_error(sb, "ext2_new_block",
-				"corrupted free blocks counters");
+		if (my_rsv && (free_blocks <= (windowsz/2)))
+			continue;
+
+		brelse(bitmap_bh);
+		bitmap_bh = read_block_bitmap(sb, group_no);
+		if (!bitmap_bh)
 			goto io_error;
-		}
 		/*
-		 * Someone else grabbed the last free block in this blockgroup
-		 * before us.  Retry the scan.
+		 * try to allocate block(s) from this group, without a goal(-1).
 		 */
-		group_release_blocks(sb, group_no, desc, gdp_bh, group_alloc);
-		group_alloc = 0;
-		goto retry;
+		grp_alloc_blk = ext2_try_to_allocate_with_rsv(sb, group_no,
+					bitmap_bh, -1, my_rsv, &num);
+		if (grp_alloc_blk >= 0)
+			goto allocated;
+	}
+	/*
+	 * We may end up a bogus earlier ENOSPC error due to
+	 * filesystem is "full" of reservations, but
+	 * there maybe indeed free blocks available on disk
+	 * In this case, we just forget about the reservations
+	 * just do block allocation as without reservations.
+	 */
+	if (my_rsv) {
+		my_rsv = NULL;
+		windowsz = 0;
+		group_no = goal_group;
+		goto retry_alloc;
 	}
+	/* No space left on the device */
+	*errp = -ENOSPC;
+	goto out;
+
+allocated:
 
-got_block:
 	ext2_debug("using block group %d(%d)\n",
-		group_no, desc->bg_free_blocks_count);
+			group_no, gdp->bg_free_blocks_count);
 
-	target_block = ret_block + group_no * group_size +
-			le32_to_cpu(es->s_first_data_block);
+	ret_block = grp_alloc_blk + ext2_group_first_block_no(sb, group_no);
 
-	if (target_block == le32_to_cpu(desc->bg_block_bitmap) ||
-	    target_block == le32_to_cpu(desc->bg_inode_bitmap) ||
-	    in_range(target_block, le32_to_cpu(desc->bg_inode_table),
-		      sbi->s_itb_per_group))
-		ext2_error (sb, "ext2_new_block",
+	if (in_range(le32_to_cpu(gdp->bg_block_bitmap), ret_block, num) ||
+	    in_range(le32_to_cpu(gdp->bg_inode_bitmap), ret_block, num) ||
+	    in_range(ret_block, le32_to_cpu(gdp->bg_inode_table),
+		      EXT2_SB(sb)->s_itb_per_group) ||
+	    in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table),
+		      EXT2_SB(sb)->s_itb_per_group)) {
+		ext2_error(sb, "ext2_new_blocks",
 			    "Allocating block in system zone - "
-			    "block = %u", target_block);
+			    "blocks from "E2FSBLK", length %lu",
+			    ret_block, num);
+		/*
+		 * ext2_try_to_allocate marked the blocks we allocated as in
+		 * use.  So we may want to selectively mark some of the blocks
+		 * as free
+		 */
+		goto retry_alloc;
+	}
 
-	if (target_block >= le32_to_cpu(es->s_blocks_count)) {
-		ext2_error (sb, "ext2_new_block",
-			    "block(%d) >= blocks count(%d) - "
+	performed_allocation = 1;
+
+	if (ret_block + num - 1 >= le32_to_cpu(es->s_blocks_count)) {
+		ext2_error(sb, "ext2_new_blocks",
+			    "block("E2FSBLK") >= blocks count(%d) - "
 			    "block_group = %d, es == %p ", ret_block,
 			le32_to_cpu(es->s_blocks_count), group_no, es);
-		goto io_error;
+		goto out;
 	}
-	block = target_block;
 
-	/* OK, we _had_ allocated something */
-	ext2_debug("found bit %d\n", ret_block);
-
-	dq_alloc--;
-	es_alloc--;
-	group_alloc--;
-
-	/*
-	 * Do block preallocation now if required.
-	 */
-	write_lock(&EXT2_I(inode)->i_meta_lock);
-	if (group_alloc && !*prealloc_count) {
-		unsigned n;
-
-		for (n = 0; n < group_alloc && ++ret_block < group_size; n++) {
-			if (ext2_set_bit_atomic(sb_bgl_lock(sbi, group_no),
-						ret_block,
-						(void*) bitmap_bh->b_data))
- 				break;
-		}
-		*prealloc_block = block + 1;
-		*prealloc_count = n;
-		es_alloc -= n;
-		dq_alloc -= n;
-		group_alloc -= n;
-	}
-	write_unlock(&EXT2_I(inode)->i_meta_lock);
+	group_adjust_blocks(sb, group_no, gdp, gdp_bh, -num);
+	percpu_counter_sub(&sbi->s_freeblocks_counter, num);
 
 	mark_buffer_dirty(bitmap_bh);
 	if (sb->s_flags & MS_SYNCHRONOUS)
 		sync_dirty_buffer(bitmap_bh);
 
-	ext2_debug ("allocating block %d. ", block);
+	*errp = 0;
+	brelse(bitmap_bh);
+	if (num < *count) {
+		dquot_free_block_nodirty(inode, *count-num);
+		mark_inode_dirty(inode);
+		*count = num;
+	}
+	return ret_block;
 
-	*err = 0;
-out_release:
-	group_release_blocks(sb, group_no, desc, gdp_bh, group_alloc);
-	release_blocks(sb, es_alloc);
-out_dquot:
-	DQUOT_FREE_BLOCK(inode, dq_alloc);
+io_error:
+	*errp = -EIO;
 out:
+	/*
+	 * Undo the block allocation
+	 */
+	if (!performed_allocation) {
+		dquot_free_block_nodirty(inode, *count);
+		mark_inode_dirty(inode);
+	}
 	brelse(bitmap_bh);
-	return block;
+	return 0;
+}
 
-io_error:
-	*err = -EIO;
-	goto out_release;
+ext2_fsblk_t ext2_new_block(struct inode *inode, unsigned long goal, int *errp)
+{
+	unsigned long count = 1;
+
+	return ext2_new_blocks(inode, goal, &count, errp);
 }
 
 #ifdef EXT2FS_DEBUG
 
-static int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-
-unsigned long ext2_count_free (struct buffer_head * map, unsigned int numchars)
+unsigned long ext2_count_free(struct buffer_head *map, unsigned int numchars)
 {
-	unsigned int i;
-	unsigned long 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);
+	return numchars * BITS_PER_BYTE - memweight(map->b_data, numchars);
 }
 
 #endif  /*  EXT2FS_DEBUG  */
@@ -583,14 +1487,6 @@ unsigned long ext2_count_free_blocks (struct super_block * sb)
 #endif
 }
 
-static inline int
-block_in_use(unsigned long block, struct super_block *sb, unsigned char *map)
-{
-	return ext2_test_bit ((block -
-		le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block)) %
-			 EXT2_BLOCKS_PER_GROUP(sb), map);
-}
-
 static inline int test_root(int a, int b)
 {
 	int num = b;
@@ -635,9 +1531,6 @@ int ext2_bg_has_super(struct super_block *sb, int group)
  */
 unsigned long ext2_bg_num_gdb(struct super_block *sb, int group)
 {
-	if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&&
-	    !ext2_group_sparse(group))
-		return 0;
-	return EXT2_SB(sb)->s_gdb_count;
+	return ext2_bg_has_super(sb, group) ? EXT2_SB(sb)->s_gdb_count : 0;
 }
 
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 92ea8265d7d..6e1d4ab09d7 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -22,12 +22,40 @@
  */
 
 #include "ext2.h"
+#include <linux/buffer_head.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
+#include <linux/swap.h>
 
 typedef struct ext2_dir_entry_2 ext2_dirent;
 
 /*
+ * Tests against MAX_REC_LEN etc were put in place for 64k block
+ * sizes; if that is not possible on this arch, we can skip
+ * those tests and speed things up.
+ */
+static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
+{
+	unsigned len = le16_to_cpu(dlen);
+
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len == EXT2_MAX_REC_LEN)
+		return 1 << 16;
+#endif
+	return len;
+}
+
+static inline __le16 ext2_rec_len_to_disk(unsigned len)
+{
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len == (1 << 16))
+		return cpu_to_le16(EXT2_MAX_REC_LEN);
+	else
+		BUG_ON(len > (1 << 16));
+#endif
+	return cpu_to_le16(len);
+}
+
+/*
  * ext2 uses block-sized chunks. Arguably, sector-sized ones would be
  * more robust, but we have what we have
  */
@@ -62,20 +90,32 @@ ext2_last_byte(struct inode *inode, unsigned long page_nr)
 	return last_byte;
 }
 
-static int ext2_commit_chunk(struct page *page, unsigned from, unsigned to)
+static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
-	struct inode *dir = page->mapping->host;
+	struct address_space *mapping = page->mapping;
+	struct inode *dir = mapping->host;
 	int err = 0;
+
 	dir->i_version++;
-	page->mapping->a_ops->commit_write(NULL, page, from, to);
-	if (IS_DIRSYNC(dir))
+	block_write_end(NULL, mapping, pos, len, len, page, NULL);
+
+	if (pos+len > dir->i_size) {
+		i_size_write(dir, pos+len);
+		mark_inode_dirty(dir);
+	}
+
+	if (IS_DIRSYNC(dir)) {
 		err = write_one_page(page, 1);
-	else
+		if (!err)
+			err = sync_inode_metadata(dir, 1);
+	} else {
 		unlock_page(page);
+	}
+
 	return err;
 }
 
-static void ext2_check_page(struct page *page)
+static void ext2_check_page(struct page *page, int quiet)
 {
 	struct inode *dir = page->mapping->host;
 	struct super_block *sb = dir->i_sb;
@@ -96,17 +136,17 @@ static void ext2_check_page(struct page *page)
 	}
 	for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) {
 		p = (ext2_dirent *)(kaddr + offs);
-		rec_len = le16_to_cpu(p->rec_len);
+		rec_len = ext2_rec_len_from_disk(p->rec_len);
 
-		if (rec_len < EXT2_DIR_REC_LEN(1))
+		if (unlikely(rec_len < EXT2_DIR_REC_LEN(1)))
 			goto Eshort;
-		if (rec_len & 3)
+		if (unlikely(rec_len & 3))
 			goto Ealign;
-		if (rec_len < EXT2_DIR_REC_LEN(p->name_len))
+		if (unlikely(rec_len < EXT2_DIR_REC_LEN(p->name_len)))
 			goto Enamelen;
-		if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
+		if (unlikely(((offs + rec_len - 1) ^ offs) & ~(chunk_size-1)))
 			goto Espan;
-		if (le32_to_cpu(p->inode) > max_inumber)
+		if (unlikely(le32_to_cpu(p->inode) > max_inumber))
 			goto Einumber;
 	}
 	if (offs != limit)
@@ -118,10 +158,10 @@ out:
 	/* Too bad, we had an error */
 
 Ebadsize:
-	ext2_error(sb, "ext2_check_page",
-		"size of directory #%lu is not a multiple of chunk size",
-		dir->i_ino
-	);
+	if (!quiet)
+		ext2_error(sb, __func__,
+			"size of directory #%lu is not a multiple "
+			"of chunk size", dir->i_ino);
 	goto fail;
 Eshort:
 	error = "rec_len is smaller than minimal";
@@ -138,35 +178,36 @@ Espan:
 Einumber:
 	error = "inode out of bounds";
 bad_entry:
-	ext2_error (sb, "ext2_check_page", "bad entry in directory #%lu: %s - "
-		"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-		dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
-		(unsigned long) le32_to_cpu(p->inode),
-		rec_len, p->name_len);
+	if (!quiet)
+		ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - "
+			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+			dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+			(unsigned long) le32_to_cpu(p->inode),
+			rec_len, p->name_len);
 	goto fail;
 Eend:
-	p = (ext2_dirent *)(kaddr + offs);
-	ext2_error (sb, "ext2_check_page",
-		"entry in directory #%lu spans the page boundary"
-		"offset=%lu, inode=%lu",
-		dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
-		(unsigned long) le32_to_cpu(p->inode));
+	if (!quiet) {
+		p = (ext2_dirent *)(kaddr + offs);
+		ext2_error(sb, "ext2_check_page",
+			"entry in directory #%lu spans the page boundary"
+			"offset=%lu, inode=%lu",
+			dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+			(unsigned long) le32_to_cpu(p->inode));
+	}
 fail:
 	SetPageChecked(page);
 	SetPageError(page);
 }
 
-static struct page * ext2_get_page(struct inode *dir, unsigned long n)
+static struct page * ext2_get_page(struct inode *dir, unsigned long n,
+				   int quiet)
 {
 	struct address_space *mapping = dir->i_mapping;
 	struct page *page = read_mapping_page(mapping, n, NULL);
 	if (!IS_ERR(page)) {
-		wait_on_page_locked(page);
 		kmap(page);
-		if (!PageUptodate(page))
-			goto fail;
 		if (!PageChecked(page))
-			ext2_check_page(page);
+			ext2_check_page(page, quiet);
 		if (PageError(page))
 			goto fail;
 	}
@@ -197,7 +238,8 @@ static inline int ext2_match (int len, const char * const name,
  */
 static inline ext2_dirent *ext2_next_entry(ext2_dirent *p)
 {
-	return (ext2_dirent *)((char*)p + le16_to_cpu(p->rec_len));
+	return (ext2_dirent *)((char *)p +
+			ext2_rec_len_from_disk(p->rec_len));
 }
 
 static inline unsigned 
@@ -237,7 +279,7 @@ static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = {
 
 static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
 {
-	mode_t mode = inode->i_mode;
+	umode_t mode = inode->i_mode;
 	if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
 		de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
 	else
@@ -245,17 +287,17 @@ static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
 }
 
 static int
-ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
+ext2_readdir(struct file *file, struct dir_context *ctx)
 {
-	loff_t pos = filp->f_pos;
-	struct inode *inode = filp->f_dentry->d_inode;
+	loff_t pos = ctx->pos;
+	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
 	unsigned int offset = pos & ~PAGE_CACHE_MASK;
 	unsigned long n = pos >> PAGE_CACHE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
 	unsigned char *types = NULL;
-	int need_revalidate = filp->f_version != inode->i_version;
+	int need_revalidate = file->f_version != inode->i_version;
 
 	if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
 		return 0;
@@ -266,50 +308,47 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
 	for ( ; n < npages; n++, offset = 0) {
 		char *kaddr, *limit;
 		ext2_dirent *de;
-		struct page *page = ext2_get_page(inode, n);
+		struct page *page = ext2_get_page(inode, n, 0);
 
 		if (IS_ERR(page)) {
-			ext2_error(sb, __FUNCTION__,
+			ext2_error(sb, __func__,
 				   "bad page in #%lu",
 				   inode->i_ino);
-			filp->f_pos += PAGE_CACHE_SIZE - offset;
-			return -EIO;
+			ctx->pos += PAGE_CACHE_SIZE - offset;
+			return PTR_ERR(page);
 		}
 		kaddr = page_address(page);
 		if (unlikely(need_revalidate)) {
 			if (offset) {
 				offset = ext2_validate_entry(kaddr, offset, chunk_mask);
-				filp->f_pos = (n<<PAGE_CACHE_SHIFT) + offset;
+				ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
 			}
-			filp->f_version = inode->i_version;
+			file->f_version = inode->i_version;
 			need_revalidate = 0;
 		}
 		de = (ext2_dirent *)(kaddr+offset);
 		limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1);
 		for ( ;(char*)de <= limit; de = ext2_next_entry(de)) {
 			if (de->rec_len == 0) {
-				ext2_error(sb, __FUNCTION__,
+				ext2_error(sb, __func__,
 					"zero-length directory entry");
 				ext2_put_page(page);
 				return -EIO;
 			}
 			if (de->inode) {
-				int over;
 				unsigned char d_type = DT_UNKNOWN;
 
 				if (types && de->file_type < EXT2_FT_MAX)
 					d_type = types[de->file_type];
 
-				offset = (char *)de - kaddr;
-				over = filldir(dirent, de->name, de->name_len,
-						(n<<PAGE_CACHE_SHIFT) | offset,
-						le32_to_cpu(de->inode), d_type);
-				if (over) {
+				if (!dir_emit(ctx, de->name, de->name_len,
+						le32_to_cpu(de->inode),
+						d_type)) {
 					ext2_put_page(page);
 					return 0;
 				}
 			}
-			filp->f_pos += le16_to_cpu(de->rec_len);
+			ctx->pos += ext2_rec_len_from_disk(de->rec_len);
 		}
 		ext2_put_page(page);
 	}
@@ -320,21 +359,22 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
  *	ext2_find_entry()
  *
  * finds an entry in the specified directory with the wanted name. It
- * returns the page in which the entry was found, and the entry itself
- * (as a parameter - res_dir). Page is returned mapped and unlocked.
+ * returns the page in which the entry was found (as a parameter - res_page),
+ * and the entry itself. Page is returned mapped and unlocked.
  * Entry is guaranteed to be valid.
  */
-struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
-			struct dentry *dentry, struct page ** res_page)
+struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir,
+			struct qstr *child, struct page ** res_page)
 {
-	const char *name = dentry->d_name.name;
-	int namelen = dentry->d_name.len;
+	const char *name = child->name;
+	int namelen = child->len;
 	unsigned reclen = EXT2_DIR_REC_LEN(namelen);
 	unsigned long start, n;
 	unsigned long npages = dir_pages(dir);
 	struct page *page = NULL;
 	struct ext2_inode_info *ei = EXT2_I(dir);
 	ext2_dirent * de;
+	int dir_has_error = 0;
 
 	if (npages == 0)
 		goto out;
@@ -348,14 +388,14 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
 	n = start;
 	do {
 		char *kaddr;
-		page = ext2_get_page(dir, n);
+		page = ext2_get_page(dir, n, dir_has_error);
 		if (!IS_ERR(page)) {
 			kaddr = page_address(page);
 			de = (ext2_dirent *) kaddr;
 			kaddr += ext2_last_byte(dir, n) - reclen;
 			while ((char *) de <= kaddr) {
 				if (de->rec_len == 0) {
-					ext2_error(dir->i_sb, __FUNCTION__,
+					ext2_error(dir->i_sb, __func__,
 						"zero-length directory entry");
 					ext2_put_page(page);
 					goto out;
@@ -365,9 +405,19 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
 				de = ext2_next_entry(de);
 			}
 			ext2_put_page(page);
-		}
+		} else
+			dir_has_error = 1;
+
 		if (++n >= npages)
 			n = 0;
+		/* next page is past the blocks we've got */
+		if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
+			ext2_error(dir->i_sb, __func__,
+				"dir %lu size %lld exceeds block count %llu",
+				dir->i_ino, dir->i_size,
+				(unsigned long long)dir->i_blocks);
+			goto out;
+		}
 	} while (n != start);
 out:
 	return NULL;
@@ -380,7 +430,7 @@ found:
 
 struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
 {
-	struct page *page = ext2_get_page(dir, 0);
+	struct page *page = ext2_get_page(dir, 0, 0);
 	ext2_dirent *de = NULL;
 
 	if (!IS_ERR(page)) {
@@ -390,13 +440,13 @@ struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
 	return de;
 }
 
-ino_t ext2_inode_by_name(struct inode * dir, struct dentry *dentry)
+ino_t ext2_inode_by_name(struct inode *dir, struct qstr *child)
 {
 	ino_t res = 0;
-	struct ext2_dir_entry_2 * de;
+	struct ext2_dir_entry_2 *de;
 	struct page *page;
 	
-	de = ext2_find_entry (dir, dentry, &page);
+	de = ext2_find_entry (dir, child, &page);
 	if (de) {
 		res = le32_to_cpu(de->inode);
 		ext2_put_page(page);
@@ -404,22 +454,29 @@ ino_t ext2_inode_by_name(struct inode * dir, struct dentry *dentry)
 	return res;
 }
 
+static int ext2_prepare_chunk(struct page *page, loff_t pos, unsigned len)
+{
+	return __block_write_begin(page, pos, len, ext2_get_block);
+}
+
 /* Releases the page */
 void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
-			struct page *page, struct inode *inode)
+		   struct page *page, struct inode *inode, int update_times)
 {
-	unsigned from = (char *) de - (char *) page_address(page);
-	unsigned to = from + le16_to_cpu(de->rec_len);
+	loff_t pos = page_offset(page) +
+			(char *) de - (char *) page_address(page);
+	unsigned len = ext2_rec_len_from_disk(de->rec_len);
 	int err;
 
 	lock_page(page);
-	err = page->mapping->a_ops->prepare_write(NULL, page, from, to);
+	err = ext2_prepare_chunk(page, pos, len);
 	BUG_ON(err);
 	de->inode = cpu_to_le32(inode->i_ino);
-	ext2_set_de_type (de, inode);
-	err = ext2_commit_chunk(page, from, to);
+	ext2_set_de_type(de, inode);
+	err = ext2_commit_chunk(page, pos, len);
 	ext2_put_page(page);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+	if (update_times)
+		dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
 	mark_inode_dirty(dir);
 }
@@ -440,7 +497,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 	unsigned long npages = dir_pages(dir);
 	unsigned long n;
 	char *kaddr;
-	unsigned from, to;
+	loff_t pos;
 	int err;
 
 	/*
@@ -451,7 +508,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 	for (n = 0; n <= npages; n++) {
 		char *dir_end;
 
-		page = ext2_get_page(dir, n);
+		page = ext2_get_page(dir, n, 0);
 		err = PTR_ERR(page);
 		if (IS_ERR(page))
 			goto out;
@@ -465,12 +522,12 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 				/* We hit i_size */
 				name_len = 0;
 				rec_len = chunk_size;
-				de->rec_len = cpu_to_le16(chunk_size);
+				de->rec_len = ext2_rec_len_to_disk(chunk_size);
 				de->inode = 0;
 				goto got_it;
 			}
 			if (de->rec_len == 0) {
-				ext2_error(dir->i_sb, __FUNCTION__,
+				ext2_error(dir->i_sb, __func__,
 					"zero-length directory entry");
 				err = -EIO;
 				goto out_unlock;
@@ -479,7 +536,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 			if (ext2_match (namelen, name, de))
 				goto out_unlock;
 			name_len = EXT2_DIR_REC_LEN(de->name_len);
-			rec_len = le16_to_cpu(de->rec_len);
+			rec_len = ext2_rec_len_from_disk(de->rec_len);
 			if (!de->inode && rec_len >= reclen)
 				goto got_it;
 			if (rec_len >= name_len + reclen)
@@ -493,22 +550,22 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 	return -EINVAL;
 
 got_it:
-	from = (char*)de - (char*)page_address(page);
-	to = from + rec_len;
-	err = page->mapping->a_ops->prepare_write(NULL, page, from, to);
+	pos = page_offset(page) +
+		(char*)de - (char*)page_address(page);
+	err = ext2_prepare_chunk(page, pos, rec_len);
 	if (err)
 		goto out_unlock;
 	if (de->inode) {
 		ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len);
-		de1->rec_len = cpu_to_le16(rec_len - name_len);
-		de->rec_len = cpu_to_le16(name_len);
+		de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len);
+		de->rec_len = ext2_rec_len_to_disk(name_len);
 		de = de1;
 	}
 	de->name_len = namelen;
-	memcpy (de->name, name, namelen);
+	memcpy(de->name, name, namelen);
 	de->inode = cpu_to_le32(inode->i_ino);
 	ext2_set_de_type (de, inode);
-	err = ext2_commit_chunk(page, from, to);
+	err = ext2_commit_chunk(page, pos, rec_len);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
 	mark_inode_dirty(dir);
@@ -528,18 +585,19 @@ out_unlock:
  */
 int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
 {
-	struct address_space *mapping = page->mapping;
-	struct inode *inode = mapping->host;
+	struct inode *inode = page->mapping->host;
 	char *kaddr = page_address(page);
 	unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
-	unsigned to = ((char*)dir - kaddr) + le16_to_cpu(dir->rec_len);
+	unsigned to = ((char *)dir - kaddr) +
+				ext2_rec_len_from_disk(dir->rec_len);
+	loff_t pos;
 	ext2_dirent * pde = NULL;
 	ext2_dirent * de = (ext2_dirent *) (kaddr + from);
 	int err;
 
 	while ((char*)de < (char*)dir) {
 		if (de->rec_len == 0) {
-			ext2_error(inode->i_sb, __FUNCTION__,
+			ext2_error(inode->i_sb, __func__,
 				"zero-length directory entry");
 			err = -EIO;
 			goto out;
@@ -549,13 +607,14 @@ int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
 	}
 	if (pde)
 		from = (char*)pde - (char*)page_address(page);
+	pos = page_offset(page) + from;
 	lock_page(page);
-	err = mapping->a_ops->prepare_write(NULL, page, from, to);
+	err = ext2_prepare_chunk(page, pos, to - from);
 	BUG_ON(err);
 	if (pde)
-		pde->rec_len = cpu_to_le16(to-from);
+		pde->rec_len = ext2_rec_len_to_disk(to - from);
 	dir->inode = 0;
-	err = ext2_commit_chunk(page, from, to);
+	err = ext2_commit_chunk(page, pos, to - from);
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
 	EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL;
 	mark_inode_dirty(inode);
@@ -569,8 +628,7 @@ out:
  */
 int ext2_make_empty(struct inode *inode, struct inode *parent)
 {
-	struct address_space *mapping = inode->i_mapping;
-	struct page *page = grab_cache_page(mapping, 0);
+	struct page *page = grab_cache_page(inode->i_mapping, 0);
 	unsigned chunk_size = ext2_chunk_size(inode);
 	struct ext2_dir_entry_2 * de;
 	int err;
@@ -578,27 +636,28 @@ int ext2_make_empty(struct inode *inode, struct inode *parent)
 
 	if (!page)
 		return -ENOMEM;
-	err = mapping->a_ops->prepare_write(NULL, page, 0, chunk_size);
+
+	err = ext2_prepare_chunk(page, 0, chunk_size);
 	if (err) {
 		unlock_page(page);
 		goto fail;
 	}
-	kaddr = kmap_atomic(page, KM_USER0);
+	kaddr = kmap_atomic(page);
 	memset(kaddr, 0, chunk_size);
 	de = (struct ext2_dir_entry_2 *)kaddr;
 	de->name_len = 1;
-	de->rec_len = cpu_to_le16(EXT2_DIR_REC_LEN(1));
+	de->rec_len = ext2_rec_len_to_disk(EXT2_DIR_REC_LEN(1));
 	memcpy (de->name, ".\0\0", 4);
 	de->inode = cpu_to_le32(inode->i_ino);
 	ext2_set_de_type (de, inode);
 
 	de = (struct ext2_dir_entry_2 *)(kaddr + EXT2_DIR_REC_LEN(1));
 	de->name_len = 2;
-	de->rec_len = cpu_to_le16(chunk_size - EXT2_DIR_REC_LEN(1));
+	de->rec_len = ext2_rec_len_to_disk(chunk_size - EXT2_DIR_REC_LEN(1));
 	de->inode = cpu_to_le32(parent->i_ino);
 	memcpy (de->name, "..\0", 4);
 	ext2_set_de_type (de, inode);
-	kunmap_atomic(kaddr, KM_USER0);
+	kunmap_atomic(kaddr);
 	err = ext2_commit_chunk(page, 0, chunk_size);
 fail:
 	page_cache_release(page);
@@ -612,14 +671,17 @@ int ext2_empty_dir (struct inode * inode)
 {
 	struct page *page = NULL;
 	unsigned long i, npages = dir_pages(inode);
+	int dir_has_error = 0;
 
 	for (i = 0; i < npages; i++) {
 		char *kaddr;
 		ext2_dirent * de;
-		page = ext2_get_page(inode, i);
+		page = ext2_get_page(inode, i, dir_has_error);
 
-		if (IS_ERR(page))
+		if (IS_ERR(page)) {
+			dir_has_error = 1;
 			continue;
+		}
 
 		kaddr = page_address(page);
 		de = (ext2_dirent *)kaddr;
@@ -627,7 +689,7 @@ int ext2_empty_dir (struct inode * inode)
 
 		while ((char *)de <= kaddr) {
 			if (de->rec_len == 0) {
-				ext2_error(inode->i_sb, __FUNCTION__,
+				ext2_error(inode->i_sb, __func__,
 					"zero-length directory entry");
 				printk("kaddr=%p, de=%p\n", kaddr, de);
 				goto not_empty;
@@ -659,7 +721,10 @@ not_empty:
 const struct file_operations ext2_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
-	.readdir	= ext2_readdir,
-	.ioctl		= ext2_ioctl,
-	.fsync		= ext2_sync_file,
+	.iterate	= ext2_readdir,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
+	.fsync		= ext2_fsync,
 };
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index e65a019fc7a..d9a17d0b124 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -1,13 +1,644 @@
+/*
+ * 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
+ */
 #include <linux/fs.h>
 #include <linux/ext2_fs.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#include <linux/rbtree.h>
+
+/* XXX Here for now... not interested in restructing headers JUST now */
+
+/* data type for block offset of block group */
+typedef int ext2_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long ext2_fsblk_t;
+
+#define E2FSBLK "%lu"
+
+struct ext2_reserve_window {
+	ext2_fsblk_t		_rsv_start;	/* First byte reserved */
+	ext2_fsblk_t		_rsv_end;	/* Last byte reserved or 0 */
+};
+
+struct ext2_reserve_window_node {
+	struct rb_node	 	rsv_node;
+	__u32			rsv_goal_size;
+	__u32			rsv_alloc_hit;
+	struct ext2_reserve_window	rsv_window;
+};
+
+struct ext2_block_alloc_info {
+	/* information about reservation window */
+	struct ext2_reserve_window_node	rsv_window_node;
+	/*
+	 * was i_next_alloc_block in ext2_inode_info
+	 * is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	__u32			last_alloc_logical_block;
+	/*
+	 * Was i_next_alloc_goal in ext2_inode_info
+	 * is the *physical* companion to i_next_alloc_block.
+	 * it the the physical block number of the block which was most-recentl
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	ext2_fsblk_t		last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * second extended-fs super-block data in memory
+ */
+struct ext2_sb_info {
+	unsigned long s_frag_size;	/* Size of a fragment in bytes */
+	unsigned long s_frags_per_block;/* Number of fragments per block */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_frags_per_group;/* Number of fragments in a group */
+	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 */
+	unsigned long s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext2_super_block * s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head ** s_group_desc;
+	unsigned long  s_mount_opt;
+	unsigned long s_sb_block;
+	kuid_t s_resuid;
+	kgid_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;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	unsigned long s_dir_count;
+	u8 *s_debts;
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	/* root of the per fs reservation window tree */
+	spinlock_t s_rsv_window_lock;
+	struct rb_root s_rsv_window_root;
+	struct ext2_reserve_window_node s_rsv_window_head;
+	/*
+	 * s_lock protects against concurrent modifications of s_mount_state,
+	 * s_blocks_last, s_overhead_last and the content of superblock's
+	 * buffer pointed to by sbi->s_es.
+	 *
+	 * Note: It is used in ext2_show_options() to provide a consistent view
+	 * of the mount options.
+	 */
+	spinlock_t s_lock;
+};
+
+static inline spinlock_t *
+sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
+}
+
+/*
+ * Define EXT2FS_DEBUG to produce debug messages
+ */
+#undef EXT2FS_DEBUG
+
+/*
+ * Define EXT2_RESERVATION to reserve data blocks for expanding files
+ */
+#define EXT2_DEFAULT_RESERVE_BLOCKS     8
+/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
+#define EXT2_MAX_RESERVE_BLOCKS         1027
+#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0
+/*
+ * The second extended file system version
+ */
+#define EXT2FS_DATE		"95/08/09"
+#define EXT2FS_VERSION		"0.5b"
+
+/*
+ * Debug code
+ */
+#ifdef EXT2FS_DEBUG
+#	define ext2_debug(f, a...)	{ \
+					printk ("EXT2-fs DEBUG (%s, %d): %s:", \
+						__FILE__, __LINE__, __func__); \
+				  	printk (f, ## a); \
+					}
+#else
+#	define ext2_debug(f, a...)	/**/
+#endif
+
+/*
+ * Special inode numbers
+ */
+#define	EXT2_BAD_INO		 1	/* Bad blocks inode */
+#define EXT2_ROOT_INO		 2	/* Root inode */
+#define EXT2_BOOT_LOADER_INO	 5	/* Boot loader inode */
+#define EXT2_UNDEL_DIR_INO	 6	/* Undelete directory inode */
+
+/* First non-reserved inode for old ext2 filesystems */
+#define EXT2_GOOD_OLD_FIRST_INO	11
+
+static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/*
+ * Macro-instructions used to manage several block sizes
+ */
+#define EXT2_MIN_BLOCK_SIZE		1024
+#define	EXT2_MAX_BLOCK_SIZE		4096
+#define EXT2_MIN_BLOCK_LOG_SIZE		  10
+#define EXT2_BLOCK_SIZE(s)		((s)->s_blocksize)
+#define	EXT2_ADDR_PER_BLOCK(s)		(EXT2_BLOCK_SIZE(s) / sizeof (__u32))
+#define EXT2_BLOCK_SIZE_BITS(s)		((s)->s_blocksize_bits)
+#define	EXT2_ADDR_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_addr_per_block_bits)
+#define EXT2_INODE_SIZE(s)		(EXT2_SB(s)->s_inode_size)
+#define EXT2_FIRST_INO(s)		(EXT2_SB(s)->s_first_ino)
+
+/*
+ * Macro-instructions used to manage fragments
+ */
+#define EXT2_MIN_FRAG_SIZE		1024
+#define	EXT2_MAX_FRAG_SIZE		4096
+#define EXT2_MIN_FRAG_LOG_SIZE		  10
+#define EXT2_FRAG_SIZE(s)		(EXT2_SB(s)->s_frag_size)
+#define EXT2_FRAGS_PER_BLOCK(s)		(EXT2_SB(s)->s_frags_per_block)
+
+/*
+ * Structure of a blocks group descriptor
+ */
+struct ext2_group_desc
+{
+	__le32	bg_block_bitmap;		/* Blocks bitmap block */
+	__le32	bg_inode_bitmap;		/* Inodes bitmap block */
+	__le32	bg_inode_table;		/* Inodes table block */
+	__le16	bg_free_blocks_count;	/* Free blocks count */
+	__le16	bg_free_inodes_count;	/* Free inodes count */
+	__le16	bg_used_dirs_count;	/* Directories count */
+	__le16	bg_pad;
+	__le32	bg_reserved[3];
+};
+
+/*
+ * Macro-instructions used to manage group descriptors
+ */
+#define EXT2_BLOCKS_PER_GROUP(s)	(EXT2_SB(s)->s_blocks_per_group)
+#define EXT2_DESC_PER_BLOCK(s)		(EXT2_SB(s)->s_desc_per_block)
+#define EXT2_INODES_PER_GROUP(s)	(EXT2_SB(s)->s_inodes_per_group)
+#define EXT2_DESC_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_desc_per_block_bits)
+
+/*
+ * Constants relative to the data blocks
+ */
+#define	EXT2_NDIR_BLOCKS		12
+#define	EXT2_IND_BLOCK			EXT2_NDIR_BLOCKS
+#define	EXT2_DIND_BLOCK			(EXT2_IND_BLOCK + 1)
+#define	EXT2_TIND_BLOCK			(EXT2_DIND_BLOCK + 1)
+#define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
+
+/*
+ * Inode flags (GETFLAGS/SETFLAGS)
+ */
+#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
+/* Reserved for compression usage... */
+#define EXT2_DIRTY_FL			FS_DIRTY_FL
+#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
+/* End compression flags --- maybe not all used */	
+#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
+
+/* Flags that should be inherited by new inodes from their parent. */
+#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
+			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
+			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
+			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & EXT2_REG_FLMASK;
+	else
+		return flags & EXT2_OTHER_FLMASK;
+}
+
+/*
+ * ioctl commands
+ */
+#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
+#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
+#define	EXT2_IOC_GETRSVSZ		_IOR('f', 5, long)
+#define	EXT2_IOC_SETRSVSZ		_IOW('f', 6, long)
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
+#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
+
+/*
+ * Structure of an inode on the disk
+ */
+struct ext2_inode {
+	__le16	i_mode;		/* File mode */
+	__le16	i_uid;		/* Low 16 bits of Owner Uid */
+	__le32	i_size;		/* Size in bytes */
+	__le32	i_atime;	/* Access time */
+	__le32	i_ctime;	/* Creation 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;	/* Blocks count */
+	__le32	i_flags;	/* File flags */
+	union {
+		struct {
+			__le32  l_i_reserved1;
+		} linux1;
+		struct {
+			__le32  h_i_translator;
+		} hurd1;
+		struct {
+			__le32  m_i_reserved1;
+		} masix1;
+	} osd1;				/* OS dependent 1 */
+	__le32	i_block[EXT2_N_BLOCKS];/* Pointers to blocks */
+	__le32	i_generation;	/* File version (for NFS) */
+	__le32	i_file_acl;	/* File ACL */
+	__le32	i_dir_acl;	/* Directory ACL */
+	__le32	i_faddr;	/* Fragment address */
+	union {
+		struct {
+			__u8	l_i_frag;	/* Fragment number */
+			__u8	l_i_fsize;	/* Fragment size */
+			__u16	i_pad1;
+			__le16	l_i_uid_high;	/* these 2 fields    */
+			__le16	l_i_gid_high;	/* were reserved2[0] */
+			__u32	l_i_reserved2;
+		} linux2;
+		struct {
+			__u8	h_i_frag;	/* Fragment number */
+			__u8	h_i_fsize;	/* Fragment size */
+			__le16	h_i_mode_high;
+			__le16	h_i_uid_high;
+			__le16	h_i_gid_high;
+			__le32	h_i_author;
+		} hurd2;
+		struct {
+			__u8	m_i_frag;	/* Fragment number */
+			__u8	m_i_fsize;	/* Fragment size */
+			__u16	m_pad1;
+			__u32	m_i_reserved2[2];
+		} masix2;
+	} osd2;				/* OS dependent 2 */
+};
+
+#define i_size_high	i_dir_acl
+
+#define i_reserved1	osd1.linux1.l_i_reserved1
+#define i_frag		osd2.linux2.l_i_frag
+#define i_fsize		osd2.linux2.l_i_fsize
+#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
+
+/*
+ * File system states
+ */
+#define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
+#define	EXT2_ERROR_FS			0x0002	/* Errors detected */
+
+/*
+ * Mount flags
+ */
+#define EXT2_MOUNT_CHECK		0x000001  /* Do mount-time checks */
+#define EXT2_MOUNT_OLDALLOC		0x000002  /* Don't use the new Orlov allocator */
+#define EXT2_MOUNT_GRPID		0x000004  /* Create files with directory's group */
+#define EXT2_MOUNT_DEBUG		0x000008  /* Some debugging messages */
+#define EXT2_MOUNT_ERRORS_CONT		0x000010  /* Continue on errors */
+#define EXT2_MOUNT_ERRORS_RO		0x000020  /* Remount fs ro on errors */
+#define EXT2_MOUNT_ERRORS_PANIC		0x000040  /* Panic on errors */
+#define EXT2_MOUNT_MINIX_DF		0x000080  /* Mimics the Minix statfs */
+#define EXT2_MOUNT_NOBH			0x000100  /* No buffer_heads */
+#define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
+#define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
+#define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
+#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
+#define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
+#define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+
+
+#define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
+#define set_opt(o, opt)			o |= EXT2_MOUNT_##opt
+#define test_opt(sb, opt)		(EXT2_SB(sb)->s_mount_opt & \
+					 EXT2_MOUNT_##opt)
+/*
+ * Maximal mount counts between two filesystem checks
+ */
+#define EXT2_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
+#define EXT2_DFL_CHECKINTERVAL		0	/* Don't use interval check */
+
+/*
+ * Behaviour when detecting errors
+ */
+#define EXT2_ERRORS_CONTINUE		1	/* Continue execution */
+#define EXT2_ERRORS_RO			2	/* Remount fs read-only */
+#define EXT2_ERRORS_PANIC		3	/* Panic */
+#define EXT2_ERRORS_DEFAULT		EXT2_ERRORS_CONTINUE
+
+/*
+ * Structure of the super block
+ */
+struct ext2_super_block {
+	__le32	s_inodes_count;		/* Inodes count */
+	__le32	s_blocks_count;		/* Blocks count */
+	__le32	s_r_blocks_count;	/* Reserved blocks count */
+	__le32	s_free_blocks_count;	/* Free blocks count */
+	__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_log_frag_size;	/* Fragment size */
+	__le32	s_blocks_per_group;	/* # Blocks per group */
+	__le32	s_frags_per_group;	/* # Fragments per group */
+	__le32	s_inodes_per_group;	/* # Inodes per group */
+	__le32	s_mtime;		/* Mount time */
+	__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 */
+	__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 */
+	__le16	s_def_resuid;		/* Default uid for reserved blocks */
+	__le16	s_def_resgid;		/* Default gid for reserved blocks */
+	/*
+	 * These fields are for EXT2_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 */
+	__le32	s_feature_incompat; 	/* incompatible feature set */
+	__le32	s_feature_ro_compat; 	/* readonly-compatible feature set */
+	__u8	s_uuid[16];		/* 128-bit uuid for volume */
+	char	s_volume_name[16]; 	/* volume name */
+	char	s_last_mounted[64]; 	/* directory where last mounted */
+	__le32	s_algorithm_usage_bitmap; /* For compression */
+	/*
+	 * Performance hints.  Directory preallocation should only
+	 * happen if the EXT2_COMPAT_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 */
+	__u16	s_padding1;
+	/*
+	 * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set.
+	 */
+	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
+	__u32	s_journal_inum;		/* inode number of journal file */
+	__u32	s_journal_dev;		/* device number of journal file */
+	__u32	s_last_orphan;		/* start of list of inodes to delete */
+	__u32	s_hash_seed[4];		/* HTREE hash seed */
+	__u8	s_def_hash_version;	/* Default hash version to use */
+	__u8	s_reserved_char_pad;
+	__u16	s_reserved_word_pad;
+	__le32	s_default_mount_opts;
+ 	__le32	s_first_meta_bg; 	/* First metablock block group */
+	__u32	s_reserved[190];	/* Padding to the end of the block */
+};
+
+/*
+ * Codes for operating systems
+ */
+#define EXT2_OS_LINUX		0
+#define EXT2_OS_HURD		1
+#define EXT2_OS_MASIX		2
+#define EXT2_OS_FREEBSD		3
+#define EXT2_OS_LITES		4
+
+/*
+ * Revision levels
+ */
+#define EXT2_GOOD_OLD_REV	0	/* The good old (original) format */
+#define EXT2_DYNAMIC_REV	1 	/* V2 format w/ dynamic inode sizes */
+
+#define EXT2_CURRENT_REV	EXT2_GOOD_OLD_REV
+#define EXT2_MAX_SUPP_REV	EXT2_DYNAMIC_REV
+
+#define EXT2_GOOD_OLD_INODE_SIZE 128
+
+/*
+ * Feature set definitions
+ */
+
+#define EXT2_HAS_COMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+#define EXT2_HAS_RO_COMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+#define EXT2_HAS_INCOMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+#define EXT2_SET_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
+#define EXT2_SET_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
+#define EXT2_SET_INCOMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
+#define EXT2_CLEAR_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
+#define EXT2_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
+#define EXT2_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
+
+#define EXT2_FEATURE_COMPAT_DIR_PREALLOC	0x0001
+#define EXT2_FEATURE_COMPAT_IMAGIC_INODES	0x0002
+#define EXT3_FEATURE_COMPAT_HAS_JOURNAL		0x0004
+#define EXT2_FEATURE_COMPAT_EXT_ATTR		0x0008
+#define EXT2_FEATURE_COMPAT_RESIZE_INO		0x0010
+#define EXT2_FEATURE_COMPAT_DIR_INDEX		0x0020
+#define EXT2_FEATURE_COMPAT_ANY			0xffffffff
+
+#define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
+#define EXT2_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
+#define EXT2_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
+#define EXT2_FEATURE_RO_COMPAT_ANY		0xffffffff
+
+#define EXT2_FEATURE_INCOMPAT_COMPRESSION	0x0001
+#define EXT2_FEATURE_INCOMPAT_FILETYPE		0x0002
+#define EXT3_FEATURE_INCOMPAT_RECOVER		0x0004
+#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008
+#define EXT2_FEATURE_INCOMPAT_META_BG		0x0010
+#define EXT2_FEATURE_INCOMPAT_ANY		0xffffffff
+
+#define EXT2_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
+#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT2_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT2_FEATURE_INCOMPAT_META_BG)
+#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT2_FEATURE_RO_COMPAT_BTREE_DIR)
+#define EXT2_FEATURE_RO_COMPAT_UNSUPPORTED	~EXT2_FEATURE_RO_COMPAT_SUPP
+#define EXT2_FEATURE_INCOMPAT_UNSUPPORTED	~EXT2_FEATURE_INCOMPAT_SUPP
+
+/*
+ * Default values for user and/or group using reserved blocks
+ */
+#define	EXT2_DEF_RESUID		0
+#define	EXT2_DEF_RESGID		0
+
+/*
+ * Default mount options
+ */
+#define EXT2_DEFM_DEBUG		0x0001
+#define EXT2_DEFM_BSDGROUPS	0x0002
+#define EXT2_DEFM_XATTR_USER	0x0004
+#define EXT2_DEFM_ACL		0x0008
+#define EXT2_DEFM_UID16		0x0010
+    /* Not used by ext2, but reserved for use by ext3 */
+#define EXT3_DEFM_JMODE		0x0060 
+#define EXT3_DEFM_JMODE_DATA	0x0020
+#define EXT3_DEFM_JMODE_ORDERED	0x0040
+#define EXT3_DEFM_JMODE_WBACK	0x0060
+
+/*
+ * Structure of a directory entry
+ */
+
+struct ext2_dir_entry {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__le16	name_len;		/* Name length */
+	char	name[];			/* File name, up to EXT2_NAME_LEN */
+};
+
+/*
+ * The new version of the directory entry.  Since EXT2 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 ext2_dir_entry_2 {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__u8	name_len;		/* Name length */
+	__u8	file_type;
+	char	name[];			/* File name, up to EXT2_NAME_LEN */
+};
+
+/*
+ * Ext2 directory file types.  Only the low 3 bits are used.  The
+ * other bits are reserved for now.
+ */
+enum {
+	EXT2_FT_UNKNOWN		= 0,
+	EXT2_FT_REG_FILE	= 1,
+	EXT2_FT_DIR		= 2,
+	EXT2_FT_CHRDEV		= 3,
+	EXT2_FT_BLKDEV		= 4,
+	EXT2_FT_FIFO		= 5,
+	EXT2_FT_SOCK		= 6,
+	EXT2_FT_SYMLINK		= 7,
+	EXT2_FT_MAX
+};
+
+/*
+ * EXT2_DIR_PAD defines the directory entries boundaries
+ *
+ * NOTE: It must be a multiple of 4
+ */
+#define EXT2_DIR_PAD		 	4
+#define EXT2_DIR_ROUND 			(EXT2_DIR_PAD - 1)
+#define EXT2_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT2_DIR_ROUND) & \
+					 ~EXT2_DIR_ROUND)
+#define EXT2_MAX_REC_LEN		((1<<16)-1)
+
+static inline void verify_offsets(void)
+{
+#define A(x,y) BUILD_BUG_ON(x != offsetof(struct ext2_super_block, y));
+	A(EXT2_SB_MAGIC_OFFSET, s_magic);
+	A(EXT2_SB_BLOCKS_OFFSET, s_blocks_count);
+	A(EXT2_SB_BSIZE_OFFSET, s_log_block_size);
+#undef A
+}
 
 /*
  * ext2 mount options
  */
 struct ext2_mount_options {
 	unsigned long s_mount_opt;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 };
 
 /*
@@ -27,28 +658,15 @@ struct ext2_inode_info {
 	/*
 	 * 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
+	 * it is used 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.
 	 */
 	__u32	i_block_group;
 
-	/*
-	 * i_next_alloc_block is the logical (file-relative) number of the
-	 * most-recently-allocated block in this file.  Yes, it is misnamed.
-	 * We use this for detecting linearly ascending allocation requests.
-	 */
-	__u32	i_next_alloc_block;
+	/* block reservation info */
+	struct ext2_block_alloc_info *i_block_alloc_info;
 
-	/*
-	 * i_next_alloc_goal is the *physical* companion to i_next_alloc_block.
-	 * it the the physical block number of the block which was most-recently
-	 * allocated to this file.  This give us the goal (target) for the next
-	 * allocation when we detect linearly ascending requests.
-	 */
-	__u32	i_next_alloc_goal;
-	__u32	i_prealloc_block;
-	__u32	i_prealloc_count;
 	__u32	i_dir_start_lookup;
 #ifdef CONFIG_EXT2_FS_XATTR
 	/*
@@ -60,12 +678,17 @@ struct ext2_inode_info {
 	 */
 	struct rw_semaphore xattr_sem;
 #endif
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
-	struct posix_acl	*i_acl;
-	struct posix_acl	*i_default_acl;
-#endif
 	rwlock_t i_meta_lock;
+
+	/*
+	 * truncate_mutex is for serialising ext2_truncate() against
+	 * ext2_getblock().  It also protects the internals of the inode's
+	 * reservation data structures: ext2_reserve_window and
+	 * ext2_reserve_window_node.
+	 */
+	struct mutex truncate_mutex;
 	struct inode	vfs_inode;
+	struct list_head i_orphan;	/* unlinked but open inodes */
 };
 
 /*
@@ -91,8 +714,9 @@ static inline struct ext2_inode_info *EXT2_I(struct inode *inode)
 /* balloc.c */
 extern int ext2_bg_has_super(struct super_block *sb, int group);
 extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group);
-extern int ext2_new_block (struct inode *, unsigned long,
-			   __u32 *, __u32 *, int *);
+extern ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *);
+extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long,
+				unsigned long *, int *);
 extern void ext2_free_blocks (struct inode *, unsigned long,
 			      unsigned long);
 extern unsigned long ext2_count_free_blocks (struct super_block *);
@@ -101,51 +725,51 @@ extern void ext2_check_blocks_bitmap (struct super_block *);
 extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
 						    unsigned int block_group,
 						    struct buffer_head ** bh);
+extern void ext2_discard_reservation (struct inode *);
+extern int ext2_should_retry_alloc(struct super_block *sb, int *retries);
+extern void ext2_init_block_alloc_info(struct inode *);
+extern void ext2_rsv_window_add(struct super_block *sb, struct ext2_reserve_window_node *rsv);
 
 /* dir.c */
 extern int ext2_add_link (struct dentry *, struct inode *);
-extern ino_t ext2_inode_by_name(struct inode *, struct dentry *);
+extern ino_t ext2_inode_by_name(struct inode *, struct qstr *);
 extern int ext2_make_empty(struct inode *, struct inode *);
-extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct dentry *, struct page **);
+extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, struct page **);
 extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
 extern int ext2_empty_dir (struct inode *);
 extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
-extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *);
-
-/* fsync.c */
-extern int ext2_sync_file (struct file *, struct dentry *, int);
+extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int);
 
 /* ialloc.c */
-extern struct inode * ext2_new_inode (struct inode *, int);
+extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *);
 extern void ext2_free_inode (struct inode *);
 extern unsigned long ext2_count_free_inodes (struct super_block *);
 extern void ext2_check_inodes_bitmap (struct super_block *);
 extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
 
 /* inode.c */
-extern void ext2_read_inode (struct inode *);
-extern int ext2_write_inode (struct inode *, int);
-extern void ext2_put_inode (struct inode *);
-extern void ext2_delete_inode (struct inode *);
-extern int ext2_sync_inode (struct inode *);
-extern void ext2_discard_prealloc (struct inode *);
+extern struct inode *ext2_iget (struct super_block *, unsigned long);
+extern int ext2_write_inode (struct inode *, struct writeback_control *);
+extern void ext2_evict_inode(struct inode *);
 extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
-extern void ext2_truncate (struct inode *);
 extern int ext2_setattr (struct dentry *, struct iattr *);
 extern void ext2_set_inode_flags(struct inode *inode);
+extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len);
 
 /* ioctl.c */
-extern int ext2_ioctl (struct inode *, struct file *, unsigned int,
-		       unsigned long);
+extern long ext2_ioctl(struct file *, unsigned int, unsigned long);
+extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* namei.c */
 struct dentry *ext2_get_parent(struct dentry *child);
 
 /* super.c */
-extern void ext2_error (struct super_block *, const char *, const char *, ...)
-	__attribute__ ((format (printf, 3, 4)));
-extern void ext2_warning (struct super_block *, const char *, const char *, ...)
-	__attribute__ ((format (printf, 3, 4)));
+extern __printf(3, 4)
+void ext2_error(struct super_block *, const char *, const char *, ...);
+extern __printf(3, 4)
+void ext2_msg(struct super_block *, const char *, const char *, ...);
 extern void ext2_update_dynamic_rev (struct super_block *sb);
 extern void ext2_write_super (struct super_block *);
 
@@ -157,7 +781,9 @@ extern void ext2_write_super (struct super_block *);
 extern const struct file_operations ext2_dir_operations;
 
 /* file.c */
-extern struct inode_operations ext2_file_inode_operations;
+extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
+		      int datasync);
+extern const struct inode_operations ext2_file_inode_operations;
 extern const struct file_operations ext2_file_operations;
 extern const struct file_operations ext2_xip_file_operations;
 
@@ -167,9 +793,22 @@ extern const struct address_space_operations ext2_aops_xip;
 extern const struct address_space_operations ext2_nobh_aops;
 
 /* namei.c */
-extern struct inode_operations ext2_dir_inode_operations;
-extern struct inode_operations ext2_special_inode_operations;
+extern const struct inode_operations ext2_dir_inode_operations;
+extern const struct inode_operations ext2_special_inode_operations;
 
 /* symlink.c */
-extern struct inode_operations ext2_fast_symlink_inode_operations;
-extern struct inode_operations ext2_symlink_inode_operations;
+extern const struct inode_operations ext2_fast_symlink_inode_operations;
+extern const struct inode_operations ext2_symlink_inode_operations;
+
+static inline ext2_fsblk_t
+ext2_group_first_block_no(struct super_block *sb, unsigned long group_no)
+{
+	return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) +
+		le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block);
+}
+
+#define ext2_set_bit	__test_and_set_bit_le
+#define ext2_clear_bit	__test_and_clear_bit_le
+#define ext2_test_bit	test_bit_le
+#define ext2_find_first_zero_bit	find_first_zero_bit_le
+#define ext2_find_next_zero_bit		find_next_zero_bit_le
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 23e2c7ccec1..7c87b22a722 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -19,42 +19,63 @@
  */
 
 #include <linux/time.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
 
 /*
- * Called when an inode is released. Note that this is different
- * from ext2_open_file: open gets called at every open, but release
- * gets called only when /all/ the files are closed.
+ * Called when filp is released. This happens when all file descriptors
+ * for a single struct file are closed. Note that different open() calls
+ * for the same file yield different struct file structures.
  */
 static int ext2_release_file (struct inode * inode, struct file * filp)
 {
-	if (filp->f_mode & FMODE_WRITE)
-		ext2_discard_prealloc (inode);
+	if (filp->f_mode & FMODE_WRITE) {
+		mutex_lock(&EXT2_I(inode)->truncate_mutex);
+		ext2_discard_reservation(inode);
+		mutex_unlock(&EXT2_I(inode)->truncate_mutex);
+	}
 	return 0;
 }
 
+int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct super_block *sb = file->f_mapping->host->i_sb;
+	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+
+	ret = generic_file_fsync(file, start, end, datasync);
+	if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) {
+		/* We don't really know where the IO error happened... */
+		ext2_error(sb, __func__,
+			   "detected IO error when writing metadata buffers");
+		ret = -EIO;
+	}
+	return ret;
+}
+
 /*
  * We have mostly NULL's here: the current defaults are ok for
  * the ext2 filesystem.
  */
 const struct file_operations ext2_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= generic_file_read,
-	.write		= generic_file_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
-	.ioctl		= ext2_ioctl,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
 	.mmap		= generic_file_mmap,
-	.open		= generic_file_open,
+	.open		= dquot_file_open,
 	.release	= ext2_release_file,
-	.fsync		= ext2_sync_file,
-	.readv		= generic_file_readv,
-	.writev		= generic_file_writev,
-	.sendfile	= generic_file_sendfile,
+	.fsync		= ext2_fsync,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
 
 #ifdef CONFIG_EXT2_FS_XIP
@@ -62,17 +83,18 @@ const struct file_operations ext2_xip_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= xip_file_read,
 	.write		= xip_file_write,
-	.ioctl		= ext2_ioctl,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
 	.mmap		= xip_file_mmap,
-	.open		= generic_file_open,
+	.open		= dquot_file_open,
 	.release	= ext2_release_file,
-	.fsync		= ext2_sync_file,
-	.sendfile	= xip_file_sendfile,
+	.fsync		= ext2_fsync,
 };
 #endif
 
-struct inode_operations ext2_file_inode_operations = {
-	.truncate	= ext2_truncate,
+const struct inode_operations ext2_file_inode_operations = {
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -80,5 +102,7 @@ struct inode_operations ext2_file_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.setattr	= ext2_setattr,
-	.permission	= ext2_permission,
+	.get_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
+	.fiemap		= ext2_fiemap,
 };
diff --git a/fs/ext2/fsync.c b/fs/ext2/fsync.c
deleted file mode 100644
index 7806b9e8155..00000000000
--- a/fs/ext2/fsync.c
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- *  linux/fs/ext2/fsync.c
- *
- *  Copyright (C) 1993  Stephen Tweedie (sct@dcs.ed.ac.uk)
- *  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
- * 
- *  ext2fs 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 "ext2.h"
-#include <linux/smp_lock.h>
-#include <linux/buffer_head.h>		/* for sync_mapping_buffers() */
-
-
-/*
- *	File may be NULL when we are called. Perhaps we shouldn't
- *	even pass file to fsync ?
- */
-
-int ext2_sync_file(struct file *file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int err;
-	int ret;
-
-	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return ret;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return ret;
-
-	err = ext2_sync_inode(inode);
-	if (ret == 0)
-		ret = err;
-	return ret;
-}
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 2cb545bf0f3..7d66fb0e4cc 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -75,15 +75,12 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir)
 	}
 
 	spin_lock(sb_bgl_lock(EXT2_SB(sb), group));
-	desc->bg_free_inodes_count =
-		cpu_to_le16(le16_to_cpu(desc->bg_free_inodes_count) + 1);
+	le16_add_cpu(&desc->bg_free_inodes_count, 1);
 	if (dir)
-		desc->bg_used_dirs_count =
-			cpu_to_le16(le16_to_cpu(desc->bg_used_dirs_count) - 1);
+		le16_add_cpu(&desc->bg_used_dirs_count, -1);
 	spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
 	if (dir)
 		percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
-	sb->s_dirt = 1;
 	mark_buffer_dirty(bh);
 }
 
@@ -108,7 +105,7 @@ void ext2_free_inode (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 *bitmap_bh;
 	unsigned long block_group;
 	unsigned long bit;
 	struct ext2_super_block * es;
@@ -120,31 +117,24 @@ void ext2_free_inode (struct inode * inode)
 	 * Note: we must free any quota before locking the superblock,
 	 * as writing the quota to disk may need the lock as well.
 	 */
-	if (!is_bad_inode(inode)) {
-		/* Quota is already initialized in iput() */
-		ext2_xattr_delete_inode(inode);
-	    	DQUOT_FREE_INODE(inode);
-		DQUOT_DROP(inode);
-	}
+	/* Quota is already initialized in iput() */
+	dquot_free_inode(inode);
+	dquot_drop(inode);
 
 	es = EXT2_SB(sb)->s_es;
 	is_directory = S_ISDIR(inode->i_mode);
 
-	/* Do this BEFORE marking the inode not in use or returning an error */
-	clear_inode (inode);
-
 	if (ino < EXT2_FIRST_INO(sb) ||
 	    ino > le32_to_cpu(es->s_inodes_count)) {
 		ext2_error (sb, "ext2_free_inode",
 			    "reserved or nonexistent inode %lu", ino);
-		goto error_return;
+		return;
 	}
 	block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
 	bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb);
-	brelse(bitmap_bh);
 	bitmap_bh = read_inode_bitmap(sb, block_group);
 	if (!bitmap_bh)
-		goto error_return;
+		return;
 
 	/* Ok, now we can actually update the inode bitmaps.. */
 	if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group),
@@ -156,7 +146,7 @@ void ext2_free_inode (struct inode * inode)
 	mark_buffer_dirty(bitmap_bh);
 	if (sb->s_flags & MS_SYNCHRONOUS)
 		sync_dirty_buffer(bitmap_bh);
-error_return:
+
 	brelse(bitmap_bh);
 }
 
@@ -177,7 +167,6 @@ static void ext2_preread_inode(struct inode *inode)
 	unsigned long block_group;
 	unsigned long offset;
 	unsigned long block;
-	struct buffer_head *bh;
 	struct ext2_group_desc * gdp;
 	struct backing_dev_info *bdi;
 
@@ -188,7 +177,7 @@ static void ext2_preread_inode(struct inode *inode)
 		return;
 
 	block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
-	gdp = ext2_get_group_desc(inode->i_sb, block_group, &bh);
+	gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL);
 	if (gdp == NULL)
 		return;
 
@@ -217,11 +206,10 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
 	int ngroups = EXT2_SB(sb)->s_groups_count;
 	int avefreei = ext2_count_free_inodes(sb) / ngroups;
 	struct ext2_group_desc *desc, *best_desc = NULL;
-	struct buffer_head *bh, *best_bh = NULL;
 	int group, best_group = -1;
 
 	for (group = 0; group < ngroups; group++) {
-		desc = ext2_get_group_desc (sb, group, &bh);
+		desc = ext2_get_group_desc (sb, group, NULL);
 		if (!desc || !desc->bg_free_inodes_count)
 			continue;
 		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
@@ -231,7 +219,6 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
 		     le16_to_cpu(best_desc->bg_free_blocks_count))) {
 			best_group = group;
 			best_desc = desc;
-			best_bh = bh;
 		}
 	}
 	if (!best_desc)
@@ -256,7 +243,7 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
  * it has too few free inodes left (min_inodes) or 
  * it has too few free blocks left (min_blocks) or 
  * it's already running too large debt (max_debt). 
- * Parent's group is prefered, if it doesn't satisfy these 
+ * 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). 
@@ -284,7 +271,6 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 	int max_debt, max_dirs, min_blocks, min_inodes;
 	int group = -1, i;
 	struct ext2_group_desc *desc;
-	struct buffer_head *bh;
 
 	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
 	avefreei = freei / ngroups;
@@ -295,15 +281,14 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 	if ((parent == sb->s_root->d_inode) ||
 	    (EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) {
 		struct ext2_group_desc *best_desc = NULL;
-		struct buffer_head *best_bh = NULL;
 		int best_ndir = inodes_per_group;
 		int best_group = -1;
 
-		get_random_bytes(&group, sizeof(group));
+		group = prandom_u32();
 		parent_group = (unsigned)group % ngroups;
 		for (i = 0; i < ngroups; i++) {
 			group = (parent_group + i) % ngroups;
-			desc = ext2_get_group_desc (sb, group, &bh);
+			desc = ext2_get_group_desc (sb, group, NULL);
 			if (!desc || !desc->bg_free_inodes_count)
 				continue;
 			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
@@ -315,11 +300,9 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 			best_group = group;
 			best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
 			best_desc = desc;
-			best_bh = bh;
 		}
 		if (best_group >= 0) {
 			desc = best_desc;
-			bh = best_bh;
 			group = best_group;
 			goto found;
 		}
@@ -345,7 +328,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 
 	for (i = 0; i < ngroups; i++) {
 		group = (parent_group + i) % ngroups;
-		desc = ext2_get_group_desc (sb, group, &bh);
+		desc = ext2_get_group_desc (sb, group, NULL);
 		if (!desc || !desc->bg_free_inodes_count)
 			continue;
 		if (sbi->s_debts[group] >= max_debt)
@@ -362,7 +345,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 fallback:
 	for (i = 0; i < ngroups; i++) {
 		group = (parent_group + i) % ngroups;
-		desc = ext2_get_group_desc (sb, group, &bh);
+		desc = ext2_get_group_desc (sb, group, NULL);
 		if (!desc || !desc->bg_free_inodes_count)
 			continue;
 		if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
@@ -389,14 +372,13 @@ static int find_group_other(struct super_block *sb, struct inode *parent)
 	int parent_group = EXT2_I(parent)->i_block_group;
 	int ngroups = EXT2_SB(sb)->s_groups_count;
 	struct ext2_group_desc *desc;
-	struct buffer_head *bh;
 	int group, i;
 
 	/*
 	 * Try to place the inode in its parent directory
 	 */
 	group = parent_group;
-	desc = ext2_get_group_desc (sb, group, &bh);
+	desc = ext2_get_group_desc (sb, group, NULL);
 	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
 			le16_to_cpu(desc->bg_free_blocks_count))
 		goto found;
@@ -420,7 +402,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent)
 		group += i;
 		if (group >= ngroups)
 			group -= ngroups;
-		desc = ext2_get_group_desc (sb, group, &bh);
+		desc = ext2_get_group_desc (sb, group, NULL);
 		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
 				le16_to_cpu(desc->bg_free_blocks_count))
 			goto found;
@@ -434,7 +416,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent)
 	for (i = 0; i < ngroups; i++) {
 		if (++group >= ngroups)
 			group = 0;
-		desc = ext2_get_group_desc (sb, group, &bh);
+		desc = ext2_get_group_desc (sb, group, NULL);
 		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
 			goto found;
 	}
@@ -445,7 +427,8 @@ found:
 	return group;
 }
 
-struct inode *ext2_new_inode(struct inode *dir, int mode)
+struct inode *ext2_new_inode(struct inode *dir, umode_t mode,
+			     const struct qstr *qstr)
 {
 	struct super_block *sb;
 	struct buffer_head *bitmap_bh = NULL;
@@ -542,76 +525,68 @@ got:
 		goto fail;
 	}
 
-	percpu_counter_mod(&sbi->s_freeinodes_counter, -1);
+	percpu_counter_add(&sbi->s_freeinodes_counter, -1);
 	if (S_ISDIR(mode))
 		percpu_counter_inc(&sbi->s_dirs_counter);
 
 	spin_lock(sb_bgl_lock(sbi, group));
-	gdp->bg_free_inodes_count =
-                cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
+	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
 	if (S_ISDIR(mode)) {
 		if (sbi->s_debts[group] < 255)
 			sbi->s_debts[group]++;
-		gdp->bg_used_dirs_count =
-			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
+		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
 	} else {
 		if (sbi->s_debts[group])
 			sbi->s_debts[group]--;
 	}
 	spin_unlock(sb_bgl_lock(sbi, group));
 
-	sb->s_dirt = 1;
 	mark_buffer_dirty(bh2);
-	inode->i_uid = current->fsuid;
-	if (test_opt (sb, GRPID))
+	if (test_opt(sb, GRPID)) {
+		inode->i_mode = mode;
+		inode->i_uid = current_fsuid();
 		inode->i_gid = dir->i_gid;
-	else if (dir->i_mode & S_ISGID) {
-		inode->i_gid = dir->i_gid;
-		if (S_ISDIR(mode))
-			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
-	inode->i_mode = mode;
+		inode_init_owner(inode, dir, mode);
 
 	inode->i_ino = ino;
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	memset(ei->i_data, 0, sizeof(ei->i_data));
-	ei->i_flags = EXT2_I(dir)->i_flags & ~EXT2_BTREE_FL;
-	if (S_ISLNK(mode))
-		ei->i_flags &= ~(EXT2_IMMUTABLE_FL|EXT2_APPEND_FL);
-	/* dirsync is only applied to directories */
-	if (!S_ISDIR(mode))
-		ei->i_flags &= ~EXT2_DIRSYNC_FL;
+	ei->i_flags =
+		ext2_mask_flags(mode, EXT2_I(dir)->i_flags & EXT2_FL_INHERITED);
 	ei->i_faddr = 0;
 	ei->i_frag_no = 0;
 	ei->i_frag_size = 0;
 	ei->i_file_acl = 0;
 	ei->i_dir_acl = 0;
 	ei->i_dtime = 0;
+	ei->i_block_alloc_info = NULL;
 	ei->i_block_group = group;
-	ei->i_next_alloc_block = 0;
-	ei->i_next_alloc_goal = 0;
-	ei->i_prealloc_block = 0;
-	ei->i_prealloc_count = 0;
 	ei->i_dir_start_lookup = 0;
 	ei->i_state = EXT2_STATE_NEW;
 	ext2_set_inode_flags(inode);
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
 	spin_unlock(&sbi->s_next_gen_lock);
-	insert_inode_hash(inode);
+	if (insert_inode_locked(inode) < 0) {
+		ext2_error(sb, "ext2_new_inode",
+			   "inode number already in use - inode=%lu",
+			   (unsigned long) ino);
+		err = -EIO;
+		goto fail;
+	}
 
-	if (DQUOT_ALLOC_INODE(inode)) {
-		err = -EDQUOT;
+	dquot_initialize(inode);
+	err = dquot_alloc_inode(inode);
+	if (err)
 		goto fail_drop;
-	}
 
 	err = ext2_init_acl(inode, dir);
 	if (err)
 		goto fail_free_drop;
 
-	err = ext2_init_security(inode,dir);
+	err = ext2_init_security(inode, dir, qstr);
 	if (err)
 		goto fail_free_drop;
 
@@ -621,12 +596,13 @@ got:
 	return inode;
 
 fail_free_drop:
-	DQUOT_FREE_INODE(inode);
+	dquot_free_inode(inode);
 
 fail_drop:
-	DQUOT_DROP(inode);
+	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
-	inode->i_nlink = 0;
+	clear_nlink(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	return ERR_PTR(err);
 
@@ -667,6 +643,7 @@ unsigned long ext2_count_free_inodes (struct super_block * sb)
 	}
 	brelse(bitmap_bh);
 	printk("ext2_count_free_inodes: stored = %lu, computed = %lu, %lu\n",
+		(unsigned long)
 		percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter),
 		desc_count, bitmap_count);
 	return desc_count;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index dd4e14c221e..36d35c36311 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -22,24 +22,22 @@
  *  Assorted race fixes, rewrite of ext2_get_block() by Al Viro, 2000
  */
 
-#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
-#include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
+#include <linux/fiemap.h>
+#include <linux/namei.h>
+#include <linux/aio.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xip.h"
+#include "xattr.h"
 
-MODULE_AUTHOR("Remy Card and others");
-MODULE_DESCRIPTION("Second Extended Filesystem");
-MODULE_LICENSE("GPL");
-
-static int ext2_update_inode(struct inode * inode, int do_sync);
+static int __ext2_write_inode(struct inode *inode, int do_sync);
 
 /*
  * Test whether an inode is a fast symlink.
@@ -53,95 +51,61 @@ static inline int ext2_inode_is_fast_symlink(struct inode *inode)
 		inode->i_blocks - ea_blocks == 0);
 }
 
-/*
- * Called at each iput().
- *
- * The inode may be "bad" if ext2_read_inode() saw an error from
- * ext2_get_inode(), so we need to check that to avoid freeing random disk
- * blocks.
- */
-void ext2_put_inode(struct inode *inode)
+static void ext2_truncate_blocks(struct inode *inode, loff_t offset);
+
+static void ext2_write_failed(struct address_space *mapping, loff_t to)
 {
-	if (!is_bad_inode(inode))
-		ext2_discard_prealloc(inode);
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, inode->i_size);
+		ext2_truncate_blocks(inode, inode->i_size);
+	}
 }
 
 /*
  * Called at the last iput() if i_nlink is zero.
  */
-void ext2_delete_inode (struct inode * inode)
+void ext2_evict_inode(struct inode * inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	struct ext2_block_alloc_info *rsv;
+	int want_delete = 0;
 
-	if (is_bad_inode(inode))
-		goto no_delete;
-	EXT2_I(inode)->i_dtime	= get_seconds();
-	mark_inode_dirty(inode);
-	ext2_update_inode(inode, inode_needs_sync(inode));
-
-	inode->i_size = 0;
-	if (inode->i_blocks)
-		ext2_truncate (inode);
-	ext2_free_inode (inode);
+	if (!inode->i_nlink && !is_bad_inode(inode)) {
+		want_delete = 1;
+		dquot_initialize(inode);
+	} else {
+		dquot_drop(inode);
+	}
 
-	return;
-no_delete:
-	clear_inode(inode);	/* We must guarantee clearing of inode... */
-}
+	truncate_inode_pages_final(&inode->i_data);
 
-void ext2_discard_prealloc (struct inode * inode)
-{
-#ifdef EXT2_PREALLOCATE
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	write_lock(&ei->i_meta_lock);
-	if (ei->i_prealloc_count) {
-		unsigned short total = ei->i_prealloc_count;
-		unsigned long block = ei->i_prealloc_block;
-		ei->i_prealloc_count = 0;
-		ei->i_prealloc_block = 0;
-		write_unlock(&ei->i_meta_lock);
-		ext2_free_blocks (inode, block, total);
-		return;
-	} else
-		write_unlock(&ei->i_meta_lock);
-#endif
-}
+	if (want_delete) {
+		sb_start_intwrite(inode->i_sb);
+		/* set dtime */
+		EXT2_I(inode)->i_dtime	= get_seconds();
+		mark_inode_dirty(inode);
+		__ext2_write_inode(inode, inode_needs_sync(inode));
+		/* truncate to 0 */
+		inode->i_size = 0;
+		if (inode->i_blocks)
+			ext2_truncate_blocks(inode, 0);
+		ext2_xattr_delete_inode(inode);
+	}
 
-static int ext2_alloc_block (struct inode * inode, unsigned long goal, int *err)
-{
-#ifdef EXT2FS_DEBUG
-	static unsigned long alloc_hits, alloc_attempts;
-#endif
-	unsigned long result;
+	invalidate_inode_buffers(inode);
+	clear_inode(inode);
 
+	ext2_discard_reservation(inode);
+	rsv = EXT2_I(inode)->i_block_alloc_info;
+	EXT2_I(inode)->i_block_alloc_info = NULL;
+	if (unlikely(rsv))
+		kfree(rsv);
 
-#ifdef EXT2_PREALLOCATE
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	write_lock(&ei->i_meta_lock);
-	if (ei->i_prealloc_count &&
-	    (goal == ei->i_prealloc_block || goal + 1 == ei->i_prealloc_block))
-	{
-		result = ei->i_prealloc_block++;
-		ei->i_prealloc_count--;
-		write_unlock(&ei->i_meta_lock);
-		ext2_debug ("preallocation hit (%lu/%lu).\n",
-			    ++alloc_hits, ++alloc_attempts);
-	} else {
-		write_unlock(&ei->i_meta_lock);
-		ext2_discard_prealloc (inode);
-		ext2_debug ("preallocation miss (%lu/%lu).\n",
-			    alloc_hits, ++alloc_attempts);
-		if (S_ISREG(inode->i_mode))
-			result = ext2_new_block (inode, goal, 
-				 &ei->i_prealloc_count,
-				 &ei->i_prealloc_block, err);
-		else
-			result = ext2_new_block(inode, goal, NULL, NULL, err);
+	if (want_delete) {
+		ext2_free_inode(inode);
+		sb_end_intwrite(inode->i_sb);
 	}
-#else
-	result = ext2_new_block (inode, goal, 0, 0, err);
-#endif
-	return result;
 }
 
 typedef struct {
@@ -205,7 +169,8 @@ static int ext2_block_to_path(struct inode *inode,
 	int final = 0;
 
 	if (i_block < 0) {
-		ext2_warning (inode->i_sb, "ext2_block_to_path", "block < 0");
+		ext2_msg(inode->i_sb, KERN_WARNING,
+			"warning: %s: block < 0", __func__);
 	} else if (i_block < direct_blocks) {
 		offsets[n++] = i_block;
 		final = direct_blocks;
@@ -225,10 +190,12 @@ static int ext2_block_to_path(struct inode *inode,
 		offsets[n++] = i_block & (ptrs - 1);
 		final = ptrs;
 	} else {
-		ext2_warning (inode->i_sb, "ext2_block_to_path", "block > big");
+		ext2_msg(inode->i_sb, KERN_WARNING,
+			"warning: %s: block is too big", __func__);
 	}
 	if (boundary)
-		*boundary = (i_block & (ptrs - 1)) == (final - 1);
+		*boundary = final - 1 - (i_block & (ptrs - 1));
+
 	return n;
 }
 
@@ -306,7 +273,7 @@ no_block:
  *	@inode: owner
  *	@ind: descriptor of indirect block.
  *
- *	This function returns the prefered place for block allocation.
+ *	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.
@@ -321,13 +288,13 @@ no_block:
  *	Caller must make sure that @ind is valid and will stay that way.
  */
 
-static unsigned long ext2_find_near(struct inode *inode, Indirect *ind)
+static ext2_fsblk_t ext2_find_near(struct inode *inode, Indirect *ind)
 {
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
 	__le32 *p;
-	unsigned long bg_start;
-	unsigned long colour;
+	ext2_fsblk_t bg_start;
+	ext2_fsblk_t colour;
 
 	/* Try to find previous block */
 	for (p = ind->p - 1; p >= start; p--)
@@ -339,55 +306,143 @@ static unsigned long ext2_find_near(struct inode *inode, Indirect *ind)
 		return ind->bh->b_blocknr;
 
 	/*
-	 * It is going to be refered from inode itself? OK, just put it into
+	 * It is going to be referred from inode itself? OK, just put it into
 	 * the same cylinder group then.
 	 */
-	bg_start = (ei->i_block_group * EXT2_BLOCKS_PER_GROUP(inode->i_sb)) +
-		le32_to_cpu(EXT2_SB(inode->i_sb)->s_es->s_first_data_block);
+	bg_start = ext2_group_first_block_no(inode->i_sb, ei->i_block_group);
 	colour = (current->pid % 16) *
 			(EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16);
 	return bg_start + colour;
 }
 
 /**
- *	ext2_find_goal - find a prefered place for allocation.
+ *	ext2_find_goal - find a preferred place for allocation.
  *	@inode: owner
  *	@block:  block we want
- *	@chain:  chain of indirect blocks
  *	@partial: pointer to the last triple within a chain
- *	@goal:	place to store the result.
  *
- *	Normally this function find the prefered place for block allocation,
- *	stores it in *@goal and returns zero. If the branch had been changed
- *	under us we return -EAGAIN.
+ *	Returns preferred place for a block (the goal).
  */
 
-static inline int ext2_find_goal(struct inode *inode,
-				 long block,
-				 Indirect chain[4],
-				 Indirect *partial,
-				 unsigned long *goal)
+static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block,
+					  Indirect *partial)
 {
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	write_lock(&ei->i_meta_lock);
-	if ((block == ei->i_next_alloc_block + 1) && ei->i_next_alloc_goal) {
-		ei->i_next_alloc_block++;
-		ei->i_next_alloc_goal++;
-	} 
-	if (verify_chain(chain, partial)) {
-		/*
-		 * try the heuristic for sequential allocation,
-		 * failing that at least try to get decent locality.
-		 */
-		if (block == ei->i_next_alloc_block)
-			*goal = ei->i_next_alloc_goal;
-		if (!*goal)
-			*goal = ext2_find_near(inode, partial);
-		write_unlock(&ei->i_meta_lock);
-		return 0;
+	struct ext2_block_alloc_info *block_i;
+
+	block_i = EXT2_I(inode)->i_block_alloc_info;
+
+	/*
+	 * try the heuristic for sequential allocation,
+	 * failing that at least try to get decent locality.
+	 */
+	if (block_i && (block == block_i->last_alloc_logical_block + 1)
+		&& (block_i->last_alloc_physical_block != 0)) {
+		return block_i->last_alloc_physical_block + 1;
+	}
+
+	return ext2_find_near(inode, partial);
+}
+
+/**
+ *	ext2_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
+ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
+		int blocks_to_boundary)
+{
+	unsigned long 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 don't hanel 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;
+}
+
+/**
+ *	ext2_alloc_blocks: multiple allocate blocks needed for a branch
+ *	@indirect_blks: the number of blocks need to allocate for indirect
+ *			blocks
+ *
+ *	@new_blocks: on return it will store the new block numbers for
+ *	the indirect blocks(if needed) and the first direct block,
+ *	@blks:	on return it will store the total number of allocated
+ *		direct blocks
+ */
+static int ext2_alloc_blocks(struct inode *inode,
+			ext2_fsblk_t goal, int indirect_blks, int blks,
+			ext2_fsblk_t new_blocks[4], int *err)
+{
+	int target, i;
+	unsigned long count = 0;
+	int index = 0;
+	ext2_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)
+	 */
+	target = blks + indirect_blks;
+
+	while (1) {
+		count = target;
+		/* allocating blocks for indirect blocks and direct blocks */
+		current_block = ext2_new_blocks(inode,goal,&count,err);
+		if (*err)
+			goto failed_out;
+
+		target -= count;
+		/* allocate blocks for indirect blocks */
+		while (index < indirect_blks && count) {
+			new_blocks[index++] = current_block++;
+			count--;
+		}
+
+		if (count > 0)
+			break;
 	}
-	write_unlock(&ei->i_meta_lock);
-	return -EAGAIN;
+
+	/* save the new block number for the first direct block */
+	new_blocks[index] = current_block;
+
+	/* total number of blocks allocated for direct blocks */
+	ret = count;
+	*err = 0;
+	return ret;
+failed_out:
+	for (i = 0; i <index; i++)
+		ext2_free_blocks(inode, new_blocks[i], 1);
+	if (index)
+		mark_inode_dirty(inode);
+	return ret;
 }
 
 /**
@@ -404,7 +459,7 @@ static inline int ext2_find_goal(struct inode *inode,
  *	the same format as ext2_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 ext2_get_block(), excpet that in one
+ *	picture as after the successful ext2_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.
@@ -416,119 +471,130 @@ static inline int ext2_find_goal(struct inode *inode,
  */
 
 static int ext2_alloc_branch(struct inode *inode,
-			     int num,
-			     unsigned long goal,
-			     int *offsets,
-			     Indirect *branch)
+			int indirect_blks, int *blks, ext2_fsblk_t goal,
+			int *offsets, Indirect *branch)
 {
 	int blocksize = inode->i_sb->s_blocksize;
-	int n = 0;
-	int err;
-	int i;
-	int parent = ext2_alloc_block(inode, goal, &err);
-
-	branch[0].key = cpu_to_le32(parent);
-	if (parent) for (n = 1; n < num; n++) {
-		struct buffer_head *bh;
-		/* Allocate the next block */
-		int nr = ext2_alloc_block(inode, parent, &err);
-		if (!nr)
-			break;
-		branch[n].key = cpu_to_le32(nr);
+	int i, n = 0;
+	int err = 0;
+	struct buffer_head *bh;
+	int num;
+	ext2_fsblk_t new_blocks[4];
+	ext2_fsblk_t current_block;
+
+	num = ext2_alloc_blocks(inode, 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.
+		 * 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, parent);
-		if (!bh) {
-			err = -EIO;
-			break;
+		bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+		if (unlikely(!bh)) {
+			err = -ENOMEM;
+			goto failed;
 		}
+		branch[n].bh = bh;
 		lock_buffer(bh);
 		memset(bh->b_data, 0, blocksize);
-		branch[n].bh = bh;
 		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);
+		}
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
 		mark_buffer_dirty_inode(bh, inode);
 		/* We used to sync bh here if IS_SYNC(inode).
-		 * But we now rely upon generic_osync_inode()
+		 * But we now rely upon generic_write_sync()
 		 * and b_inode_buffers.  But not for directories.
 		 */
 		if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
 			sync_dirty_buffer(bh);
-		parent = nr;
 	}
-	if (n == num)
-		return 0;
+	*blks = num;
+	return err;
 
-	/* Allocation failed, free what we already allocated */
+failed:
 	for (i = 1; i < n; i++)
 		bforget(branch[i].bh);
-	for (i = 0; i < n; i++)
-		ext2_free_blocks(inode, le32_to_cpu(branch[i].key), 1);
+	for (i = 0; i < indirect_blks; i++)
+		ext2_free_blocks(inode, new_blocks[i], 1);
+	ext2_free_blocks(inode, new_blocks[i], num);
 	return err;
 }
 
 /**
- *	ext2_splice_branch - splice the allocated branch onto inode.
- *	@inode: owner
- *	@block: (logical) number of block we are adding
- *	@chain: chain of indirect blocks (with a missing link - see
- *		ext2_alloc_branch)
- *	@where: location of missing link
- *	@num:   number of blocks we are adding
+ * ext2_splice_branch - splice the allocated branch onto inode.
+ * @inode: owner
+ * @block: (logical) number of block we are adding
+ * @where: location of missing link
+ * @num:   number of indirect blocks we are adding
+ * @blks:  number of direct blocks we are adding
  *
- *	This function verifies that chain (up to the missing link) had not
- *	changed, 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. Otherwise (== chain had been changed)
- *	we free the new blocks (forgetting their buffer_heads, indeed) and
- *	return -EAGAIN.
+ * 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 inline int ext2_splice_branch(struct inode *inode,
-				     long block,
-				     Indirect chain[4],
-				     Indirect *where,
-				     int num)
+static void ext2_splice_branch(struct inode *inode,
+			long block, Indirect *where, int num, int blks)
 {
-	struct ext2_inode_info *ei = EXT2_I(inode);
 	int i;
+	struct ext2_block_alloc_info *block_i;
+	ext2_fsblk_t current_block;
 
-	/* Verify that place we are splicing to is still there and vacant */
-
-	write_lock(&ei->i_meta_lock);
-	if (!verify_chain(chain, where-1) || *where->p)
-		goto changed;
+	block_i = EXT2_I(inode)->i_block_alloc_info;
 
+	/* XXX LOCKING probably should have i_meta_lock ?*/
 	/* That's it */
 
 	*where->p = where->key;
-	ei->i_next_alloc_block = block;
-	ei->i_next_alloc_goal = le32_to_cpu(where[num-1].key);
 
-	write_unlock(&ei->i_meta_lock);
+	/*
+	 * 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 */
+	/*
+	 * update the most recently allocated logical & physical block
+	 * in i_block_alloc_info, to assist find the proper goal block for next
+	 * allocation
+	 */
+	if (block_i) {
+		block_i->last_alloc_logical_block = block + blks - 1;
+		block_i->last_alloc_physical_block =
+				le32_to_cpu(where[num].key) + blks - 1;
+	}
 
-	inode->i_ctime = CURRENT_TIME_SEC;
+	/* We are done with atomic stuff, now do the rest of housekeeping */
 
 	/* had we spliced it onto indirect block? */
 	if (where->bh)
 		mark_buffer_dirty_inode(where->bh, inode);
 
+	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-	return 0;
-
-changed:
-	write_unlock(&ei->i_meta_lock);
-	for (i = 1; i < num; i++)
-		bforget(where[i].bh);
-	for (i = 0; i < num; i++)
-		ext2_free_blocks(inode, le32_to_cpu(where[i].key), 1);
-	return -EAGAIN;
 }
 
 /*
@@ -542,64 +608,128 @@ changed:
  * 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.
  */
-
-int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
+static int ext2_get_blocks(struct inode *inode,
+			   sector_t iblock, unsigned long maxblocks,
+			   struct buffer_head *bh_result,
+			   int create)
 {
 	int err = -EIO;
 	int offsets[4];
 	Indirect chain[4];
 	Indirect *partial;
-	unsigned long goal;
-	int left;
-	int boundary = 0;
-	int depth = ext2_block_to_path(inode, iblock, offsets, &boundary);
+	ext2_fsblk_t goal;
+	int indirect_blks;
+	int blocks_to_boundary = 0;
+	int depth;
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	int count = 0;
+	ext2_fsblk_t first_block = 0;
+
+	BUG_ON(maxblocks == 0);
+
+	depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
 
 	if (depth == 0)
-		goto out;
+		return (err);
 
-reread:
 	partial = ext2_get_branch(inode, depth, offsets, chain, &err);
-
 	/* Simplest case - block found, no allocation needed */
 	if (!partial) {
-got_it:
-		map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
-		if (boundary)
-			set_buffer_boundary(bh_result);
-		/* Clean up and exit */
-		partial = chain+depth-1; /* the whole chain */
-		goto cleanup;
+		first_block = le32_to_cpu(chain[depth - 1].key);
+		clear_buffer_new(bh_result); /* What's this do? */
+		count++;
+		/*map more blocks*/
+		while (count < maxblocks && count <= blocks_to_boundary) {
+			ext2_fsblk_t blk;
+
+			if (!verify_chain(chain, chain + depth - 1)) {
+				/*
+				 * Indirect block might be removed by
+				 * truncate while we were reading it.
+				 * Handling of that case: forget what we've
+				 * got now, go to reread.
+				 */
+				err = -EAGAIN;
+				count = 0;
+				break;
+			}
+			blk = le32_to_cpu(*(chain[depth-1].p + count));
+			if (blk == first_block + count)
+				count++;
+			else
+				break;
+		}
+		if (err != -EAGAIN)
+			goto got_it;
 	}
 
 	/* Next simple case - plain lookup or failed read of indirect block */
-	if (!create || err == -EIO) {
-cleanup:
+	if (!create || err == -EIO)
+		goto cleanup;
+
+	mutex_lock(&ei->truncate_mutex);
+	/*
+	 * If the indirect block is missing while we are reading
+	 * the chain(ext2_get_branch() returns -EAGAIN err), or
+	 * if the chain has been changed after we grab the semaphore,
+	 * (either because another process truncated this branch, or
+	 * another get_block allocated this branch) re-grab the chain to see if
+	 * the request block has been allocated or not.
+	 *
+	 * Since we already block the truncate/other get_block
+	 * at this point, we will have the current copy of the chain when we
+	 * splice the branch into the tree.
+	 */
+	if (err == -EAGAIN || !verify_chain(chain, partial)) {
 		while (partial > chain) {
 			brelse(partial->bh);
 			partial--;
 		}
-out:
-		return err;
+		partial = ext2_get_branch(inode, depth, offsets, chain, &err);
+		if (!partial) {
+			count++;
+			mutex_unlock(&ei->truncate_mutex);
+			if (err)
+				goto cleanup;
+			clear_buffer_new(bh_result);
+			goto got_it;
+		}
 	}
 
 	/*
-	 * Indirect block might be removed by truncate while we were
-	 * reading it. Handling of that case (forget what we've got and
-	 * reread) is taken out of the main path.
-	 */
-	if (err == -EAGAIN)
-		goto changed;
+	 * Okay, we need to do block allocation.  Lazily initialize the block
+	 * allocation info here if necessary
+	*/
+	if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
+		ext2_init_block_alloc_info(inode);
 
-	goal = 0;
-	if (ext2_find_goal(inode, iblock, chain, partial, &goal) < 0)
-		goto changed;
+	goal = ext2_find_goal(inode, iblock, partial);
 
-	left = (chain + depth) - partial;
-	err = ext2_alloc_branch(inode, left, goal,
-					offsets+(partial-chain), partial);
-	if (err)
+	/* 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 = ext2_blks_to_allocate(partial, indirect_blks,
+					maxblocks, blocks_to_boundary);
+	/*
+	 * XXX ???? Block out ext2_truncate while we alter the tree
+	 */
+	err = ext2_alloc_branch(inode, indirect_blks, &count, goal,
+				offsets + (partial - chain), partial);
+
+	if (err) {
+		mutex_unlock(&ei->truncate_mutex);
 		goto cleanup;
+	}
 
 	if (ext2_use_xip(inode->i_sb)) {
 		/*
@@ -607,22 +737,48 @@ out:
 		 */
 		err = ext2_clear_xip_target (inode,
 			le32_to_cpu(chain[depth-1].key));
-		if (err)
+		if (err) {
+			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
+		}
 	}
 
-	if (ext2_splice_branch(inode, iblock, chain, partial, left) < 0)
-		goto changed;
-
+	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
+	mutex_unlock(&ei->truncate_mutex);
 	set_buffer_new(bh_result);
-	goto got_it;
-
-changed:
+got_it:
+	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+	if (count > blocks_to_boundary)
+		set_buffer_boundary(bh_result);
+	err = count;
+	/* Clean up and exit */
+	partial = chain + depth - 1;	/* the whole chain */
+cleanup:
 	while (partial > chain) {
 		brelse(partial->bh);
 		partial--;
 	}
-	goto reread;
+	return err;
+}
+
+int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
+{
+	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int ret = ext2_get_blocks(inode, iblock, max_blocks,
+			      bh_result, create);
+	if (ret > 0) {
+		bh_result->b_size = (ret << inode->i_blkbits);
+		ret = 0;
+	}
+	return ret;
+
+}
+
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		u64 start, u64 len)
+{
+	return generic_block_fiemap(inode, fieinfo, start, len,
+				    ext2_get_block);
 }
 
 static int ext2_writepage(struct page *page, struct writeback_control *wbc)
@@ -643,17 +799,43 @@ ext2_readpages(struct file *file, struct address_space *mapping,
 }
 
 static int
-ext2_prepare_write(struct file *file, struct page *page,
-			unsigned from, unsigned to)
+ext2_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
+{
+	int ret;
+
+	ret = block_write_begin(mapping, pos, len, flags, pagep,
+				ext2_get_block);
+	if (ret < 0)
+		ext2_write_failed(mapping, pos + len);
+	return ret;
+}
+
+static int ext2_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
 {
-	return block_prepare_write(page,from,to,ext2_get_block);
+	int ret;
+
+	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	if (ret < len)
+		ext2_write_failed(mapping, pos + len);
+	return ret;
 }
 
 static int
-ext2_nobh_prepare_write(struct file *file, struct page *page,
-			unsigned from, unsigned to)
+ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
 {
-	return nobh_prepare_write(page,from,to,ext2_get_block);
+	int ret;
+
+	ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
+			       ext2_get_block);
+	if (ret < 0)
+		ext2_write_failed(mapping, pos + len);
+	return ret;
 }
 
 static int ext2_nobh_writepage(struct page *page,
@@ -668,14 +850,19 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 }
 
 static ssize_t
-ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs)
+ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+			loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
-
-	return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
-				offset, nr_segs, ext2_get_block, NULL);
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	size_t count = iov_iter_count(iter);
+	ssize_t ret;
+
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
+	if (ret < 0 && (rw & WRITE))
+		ext2_write_failed(mapping, offset + count);
+	return ret;
 }
 
 static int
@@ -688,31 +875,32 @@ const struct address_space_operations ext2_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
 	.writepage		= ext2_writepage,
-	.sync_page		= block_sync_page,
-	.prepare_write		= ext2_prepare_write,
-	.commit_write		= generic_commit_write,
+	.write_begin		= ext2_write_begin,
+	.write_end		= ext2_write_end,
 	.bmap			= ext2_bmap,
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
 	.migratepage		= buffer_migrate_page,
+	.is_partially_uptodate	= block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 const struct address_space_operations ext2_aops_xip = {
 	.bmap			= ext2_bmap,
-	.get_xip_page		= ext2_get_xip_page,
+	.get_xip_mem		= ext2_get_xip_mem,
 };
 
 const struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
 	.writepage		= ext2_nobh_writepage,
-	.sync_page		= block_sync_page,
-	.prepare_write		= ext2_nobh_prepare_write,
-	.commit_write		= nobh_commit_write,
+	.write_begin		= ext2_nobh_write_begin,
+	.write_end		= nobh_write_end,
 	.bmap			= ext2_bmap,
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
 	.migratepage		= buffer_migrate_page,
+	.error_remove_page	= generic_error_remove_page,
 };
 
 /*
@@ -740,7 +928,7 @@ static inline int all_zeroes(__le32 *p, __le32 *q)
  *
  *	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 refered from it (and
+ *	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
@@ -817,7 +1005,7 @@ no_top:
  *	@p:	array of block numbers
  *	@q:	points immediately past the end of array
  *
- *	We are freeing all blocks refered from that array (numbers are
+ *	We are freeing all blocks referred from that array (numbers are
  *	stored as little-endian 32-bit) and updating @inode->i_blocks
  *	appropriately.
  */
@@ -836,8 +1024,8 @@ static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
 			else if (block_to_free == nr - count)
 				count++;
 			else {
-				mark_inode_dirty(inode);
 				ext2_free_blocks (inode, block_to_free, count);
+				mark_inode_dirty(inode);
 			free_this:
 				block_to_free = nr;
 				count = 1;
@@ -845,8 +1033,8 @@ static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
 		}
 	}
 	if (count > 0) {
-		mark_inode_dirty(inode);
 		ext2_free_blocks (inode, block_to_free, count);
+		mark_inode_dirty(inode);
 	}
 }
 
@@ -857,7 +1045,7 @@ static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
  *	@q:	pointer immediately past the end of array
  *	@depth:	depth of the branches to free
  *
- *	We are freeing all blocks refered from these branches (numbers are
+ *	We are freeing all blocks referred from these branches (numbers are
  *	stored as little-endian 32-bit) and updating @inode->i_blocks
  *	appropriately.
  */
@@ -896,9 +1084,10 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de
 		ext2_free_data(inode, p, q);
 }
 
-void ext2_truncate (struct inode * inode)
+static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 {
 	__le32 *i_data = EXT2_I(inode)->i_data;
+	struct ext2_inode_info *ei = EXT2_I(inode);
 	int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb);
 	int offsets[4];
 	Indirect chain[4];
@@ -907,33 +1096,19 @@ void ext2_truncate (struct inode * inode)
 	int n;
 	long iblock;
 	unsigned blocksize;
-
-	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-	    S_ISLNK(inode->i_mode)))
-		return;
-	if (ext2_inode_is_fast_symlink(inode))
-		return;
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return;
-
-	ext2_discard_prealloc(inode);
-
 	blocksize = inode->i_sb->s_blocksize;
-	iblock = (inode->i_size + blocksize-1)
-					>> EXT2_BLOCK_SIZE_BITS(inode->i_sb);
-
-	if (mapping_is_xip(inode->i_mapping))
-		xip_truncate_page(inode->i_mapping, inode->i_size);
-	else if (test_opt(inode->i_sb, NOBH))
-		nobh_truncate_page(inode->i_mapping, inode->i_size);
-	else
-		block_truncate_page(inode->i_mapping,
-				inode->i_size, ext2_get_block);
+	iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb);
 
 	n = ext2_block_to_path(inode, iblock, offsets, NULL);
 	if (n == 0)
 		return;
 
+	/*
+	 * From here we block out all ext2_get_block() callers who want to
+	 * modify the block allocation tree.
+	 */
+	mutex_lock(&ei->truncate_mutex);
+
 	if (n == 1) {
 		ext2_free_data(inode, i_data+offsets[0],
 					i_data + EXT2_NDIR_BLOCKS);
@@ -986,13 +1161,69 @@ do_indirects:
 		case EXT2_TIND_BLOCK:
 			;
 	}
+
+	ext2_discard_reservation(inode);
+
+	mutex_unlock(&ei->truncate_mutex);
+}
+
+static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
+{
+	/*
+	 * XXX: it seems like a bug here that we don't allow
+	 * IS_APPEND inode to have blocks-past-i_size trimmed off.
+	 * review and fix this.
+	 *
+	 * Also would be nice to be able to handle IO errors and such,
+	 * but that's probably too much to ask.
+	 */
+	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	    S_ISLNK(inode->i_mode)))
+		return;
+	if (ext2_inode_is_fast_symlink(inode))
+		return;
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+		return;
+	__ext2_truncate_blocks(inode, offset);
+}
+
+static int ext2_setsize(struct inode *inode, loff_t newsize)
+{
+	int error;
+
+	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	    S_ISLNK(inode->i_mode)))
+		return -EINVAL;
+	if (ext2_inode_is_fast_symlink(inode))
+		return -EINVAL;
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+		return -EPERM;
+
+	inode_dio_wait(inode);
+
+	if (mapping_is_xip(inode->i_mapping))
+		error = xip_truncate_page(inode->i_mapping, newsize);
+	else if (test_opt(inode->i_sb, NOBH))
+		error = nobh_truncate_page(inode->i_mapping,
+				newsize, ext2_get_block);
+	else
+		error = block_truncate_page(inode->i_mapping,
+				newsize, ext2_get_block);
+	if (error)
+		return error;
+
+	truncate_setsize(inode, newsize);
+	__ext2_truncate_blocks(inode, newsize);
+
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
 	if (inode_needs_sync(inode)) {
 		sync_mapping_buffers(inode->i_mapping);
-		ext2_sync_inode (inode);
+		sync_inode_metadata(inode, 1);
 	} else {
 		mark_inode_dirty(inode);
 	}
+
+	return 0;
 }
 
 static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino,
@@ -1010,7 +1241,7 @@ static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino,
 		goto Einval;
 
 	block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
-	gdp = ext2_get_group_desc(sb, block_group, &bh);
+	gdp = ext2_get_group_desc(sb, block_group, NULL);
 	if (!gdp)
 		goto Egdp;
 	/*
@@ -1055,33 +1286,65 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_DIRSYNC;
 }
 
-void ext2_read_inode (struct inode * inode)
+/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
+void ext2_get_inode_flags(struct ext2_inode_info *ei)
 {
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	ino_t ino = inode->i_ino;
+	unsigned int flags = ei->vfs_inode.i_flags;
+
+	ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|
+			EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL);
+	if (flags & S_SYNC)
+		ei->i_flags |= EXT2_SYNC_FL;
+	if (flags & S_APPEND)
+		ei->i_flags |= EXT2_APPEND_FL;
+	if (flags & S_IMMUTABLE)
+		ei->i_flags |= EXT2_IMMUTABLE_FL;
+	if (flags & S_NOATIME)
+		ei->i_flags |= EXT2_NOATIME_FL;
+	if (flags & S_DIRSYNC)
+		ei->i_flags |= EXT2_DIRSYNC_FL;
+}
+
+struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
+{
+	struct ext2_inode_info *ei;
 	struct buffer_head * bh;
-	struct ext2_inode * raw_inode = ext2_get_inode(inode->i_sb, ino, &bh);
+	struct ext2_inode *raw_inode;
+	struct inode *inode;
+	long ret = -EIO;
 	int n;
+	uid_t i_uid;
+	gid_t i_gid;
 
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
-	ei->i_acl = EXT2_ACL_NOT_CACHED;
-	ei->i_default_acl = EXT2_ACL_NOT_CACHED;
-#endif
-	if (IS_ERR(raw_inode))
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	ei = EXT2_I(inode);
+	ei->i_block_alloc_info = NULL;
+
+	raw_inode = ext2_get_inode(inode->i_sb, ino, &bh);
+	if (IS_ERR(raw_inode)) {
+		ret = PTR_ERR(raw_inode);
  		goto bad_inode;
+	}
 
 	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);
+	i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
+	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;
+		i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
+		i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
 	}
-	inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+	i_uid_write(inode, i_uid);
+	i_gid_write(inode, i_gid);
+	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
 	inode->i_size = le32_to_cpu(raw_inode->i_size);
-	inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
-	inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
-	inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+	inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
+	inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
+	inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
 	inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 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.
@@ -1092,6 +1355,7 @@ void ext2_read_inode (struct inode * inode)
 	if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) {
 		/* this inode is deleted */
 		brelse (bh);
+		ret = -ESTALE;
 		goto bad_inode;
 	}
 	inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
@@ -1108,9 +1372,6 @@ void ext2_read_inode (struct inode * inode)
 	ei->i_dtime = 0;
 	inode->i_generation = le32_to_cpu(raw_inode->i_generation);
 	ei->i_state = 0;
-	ei->i_next_alloc_block = 0;
-	ei->i_next_alloc_goal = 0;
-	ei->i_prealloc_count = 0;
 	ei->i_block_group = (ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
 	ei->i_dir_start_lookup = 0;
 
@@ -1141,9 +1402,11 @@ void ext2_read_inode (struct inode * inode)
 		else
 			inode->i_mapping->a_ops = &ext2_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (ext2_inode_is_fast_symlink(inode))
+		if (ext2_inode_is_fast_symlink(inode)) {
 			inode->i_op = &ext2_fast_symlink_inode_operations;
-		else {
+			nd_terminate_link(ei->i_data, inode->i_size,
+				sizeof(ei->i_data) - 1);
+		} else {
 			inode->i_op = &ext2_symlink_inode_operations;
 			if (test_opt(inode->i_sb, NOBH))
 				inode->i_mapping->a_ops = &ext2_nobh_aops;
@@ -1161,20 +1424,21 @@ void ext2_read_inode (struct inode * inode)
 	}
 	brelse (bh);
 	ext2_set_inode_flags(inode);
-	return;
+	unlock_new_inode(inode);
+	return inode;
 	
 bad_inode:
-	make_bad_inode(inode);
-	return;
+	iget_failed(inode);
+	return ERR_PTR(ret);
 }
 
-static int ext2_update_inode(struct inode * inode, int do_sync)
+static int __ext2_write_inode(struct inode *inode, int do_sync)
 {
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	struct super_block *sb = inode->i_sb;
 	ino_t ino = inode->i_ino;
-	uid_t uid = inode->i_uid;
-	gid_t gid = inode->i_gid;
+	uid_t uid = i_uid_read(inode);
+	gid_t gid = i_gid_read(inode);
 	struct buffer_head * bh;
 	struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh);
 	int n;
@@ -1188,6 +1452,7 @@ static int ext2_update_inode(struct inode * inode, int do_sync)
 	if (ei->i_state & EXT2_STATE_NEW)
 		memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);
 
+	ext2_get_inode_flags(ei);
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
 	if (!(test_opt(sb, NO_UID32))) {
 		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid));
@@ -1234,11 +1499,11 @@ static int ext2_update_inode(struct inode * inode, int do_sync)
 			       /* If this is the first large file
 				* created, add a flag to the superblock.
 				*/
-				lock_kernel();
+				spin_lock(&EXT2_SB(sb)->s_lock);
 				ext2_update_dynamic_rev(sb);
 				EXT2_SET_RO_COMPAT_FEATURE(sb,
 					EXT2_FEATURE_RO_COMPAT_LARGE_FILE);
-				unlock_kernel();
+				spin_unlock(&EXT2_SB(sb)->s_lock);
 				ext2_write_super(sb);
 			}
 		}
@@ -1272,18 +1537,9 @@ static int ext2_update_inode(struct inode * inode, int do_sync)
 	return err;
 }
 
-int ext2_write_inode(struct inode *inode, int wait)
-{
-	return ext2_update_inode(inode, wait);
-}
-
-int ext2_sync_inode(struct inode *inode)
+int ext2_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = 0,	/* sys_fsync did this */
-	};
-	return sync_inode(inode, &wbc);
+	return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
 }
 
 int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
@@ -1294,14 +1550,24 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
 	error = inode_change_ok(inode, iattr);
 	if (error)
 		return error;
-	if ((iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) ||
-	    (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)) {
-		error = DQUOT_TRANSFER(inode, iattr) ? -EDQUOT : 0;
+
+	if (is_quota_modification(inode, iattr))
+		dquot_initialize(inode);
+	if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
+	    (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
+		error = dquot_transfer(inode, iattr);
 		if (error)
 			return error;
 	}
-	error = inode_setattr(inode, iattr);
-	if (!error && (iattr->ia_valid & ATTR_MODE))
-		error = ext2_acl_chmod(inode);
+	if (iattr->ia_valid & ATTR_SIZE && iattr->ia_size != inode->i_size) {
+		error = ext2_setsize(inode, iattr->ia_size);
+		if (error)
+			return error;
+	}
+	setattr_copy(inode, iattr);
+	if (iattr->ia_valid & ATTR_MODE)
+		error = posix_acl_chmod(inode, inode->i_mode);
+	mark_inode_dirty(inode);
+
 	return error;
 }
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 3ca9afdf713..5d46c09863f 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -11,37 +11,53 @@
 #include <linux/capability.h>
 #include <linux/time.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
 #include <asm/current.h>
 #include <asm/uaccess.h>
 
 
-int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
-		unsigned long arg)
+long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = file_inode(filp);
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	unsigned int flags;
+	unsigned short rsv_window_size;
+	int ret;
 
 	ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
 
 	switch (cmd) {
 	case EXT2_IOC_GETFLAGS:
+		ext2_get_inode_flags(ei);
 		flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
 		return put_user(flags, (int __user *) arg);
 	case EXT2_IOC_SETFLAGS: {
 		unsigned int oldflags;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
 
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
+		if (!inode_owner_or_capable(inode)) {
+			ret = -EACCES;
+			goto setflags_out;
+		}
 
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
+		if (get_user(flags, (int __user *) arg)) {
+			ret = -EFAULT;
+			goto setflags_out;
+		}
 
-		if (!S_ISDIR(inode->i_mode))
-			flags &= ~EXT2_DIRSYNC_FL;
+		flags = ext2_mask_flags(inode->i_mode, flags);
 
+		mutex_lock(&inode->i_mutex);
+		/* Is it quota file? Do not allow user to mess with it */
+		if (IS_NOQUOTA(inode)) {
+			mutex_unlock(&inode->i_mutex);
+			ret = -EPERM;
+			goto setflags_out;
+		}
 		oldflags = ei->i_flags;
 
 		/*
@@ -51,8 +67,11 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		 * This test looks nicer. Thanks to Pauline Middelink
 		 */
 		if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
-			if (!capable(CAP_LINUX_IMMUTABLE))
-				return -EPERM;
+			if (!capable(CAP_LINUX_IMMUTABLE)) {
+				mutex_unlock(&inode->i_mutex);
+				ret = -EPERM;
+				goto setflags_out;
+			}
 		}
 
 		flags = flags & EXT2_FL_USER_MODIFIABLE;
@@ -61,22 +80,109 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 
 		ext2_set_inode_flags(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
+		mutex_unlock(&inode->i_mutex);
+
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write_file(filp);
+		return ret;
 	}
 	case EXT2_IOC_GETVERSION:
 		return put_user(inode->i_generation, (int __user *) arg);
-	case EXT2_IOC_SETVERSION:
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+	case EXT2_IOC_SETVERSION: {
+		__u32 generation;
+
+		if (!inode_owner_or_capable(inode))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(inode->i_generation, (int __user *) arg))
-			return -EFAULT;	
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+		if (get_user(generation, (int __user *) arg)) {
+			ret = -EFAULT;
+			goto setversion_out;
+		}
+
+		mutex_lock(&inode->i_mutex);
 		inode->i_ctime = CURRENT_TIME_SEC;
+		inode->i_generation = generation;
+		mutex_unlock(&inode->i_mutex);
+
 		mark_inode_dirty(inode);
+setversion_out:
+		mnt_drop_write_file(filp);
+		return ret;
+	}
+	case EXT2_IOC_GETRSVSZ:
+		if (test_opt(inode->i_sb, RESERVATION)
+			&& S_ISREG(inode->i_mode)
+			&& ei->i_block_alloc_info) {
+			rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
+			return put_user(rsv_window_size, (int __user *)arg);
+		}
+		return -ENOTTY;
+	case EXT2_IOC_SETRSVSZ: {
+
+		if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
+			return -ENOTTY;
+
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+
+		if (get_user(rsv_window_size, (int __user *)arg))
+			return -EFAULT;
+
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+
+		if (rsv_window_size > EXT2_MAX_RESERVE_BLOCKS)
+			rsv_window_size = EXT2_MAX_RESERVE_BLOCKS;
+
+		/*
+		 * need to allocate reservation structure for this inode
+		 * before set the window size
+		 */
+		/*
+		 * XXX What lock should protect the rsv_goal_size?
+		 * Accessed in ext2_get_block only.  ext3 uses i_truncate.
+		 */
+		mutex_lock(&ei->truncate_mutex);
+		if (!ei->i_block_alloc_info)
+			ext2_init_block_alloc_info(inode);
+
+		if (ei->i_block_alloc_info){
+			struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
+			rsv->rsv_goal_size = rsv_window_size;
+		}
+		mutex_unlock(&ei->truncate_mutex);
+		mnt_drop_write_file(filp);
 		return 0;
+	}
 	default:
 		return -ENOTTY;
 	}
 }
+
+#ifdef CONFIG_COMPAT
+long ext2_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 EXT2_IOC32_GETFLAGS:
+		cmd = EXT2_IOC_GETFLAGS;
+		break;
+	case EXT2_IOC32_SETFLAGS:
+		cmd = EXT2_IOC_SETFLAGS;
+		break;
+	case EXT2_IOC32_GETVERSION:
+		cmd = EXT2_IOC_GETVERSION;
+		break;
+	case EXT2_IOC32_SETVERSION:
+		cmd = EXT2_IOC_SETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return ext2_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 4ca82498532..c268d0af1db 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/quotaops.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
@@ -40,10 +41,12 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = ext2_add_link(dentry, inode);
 	if (!err) {
+		unlock_new_inode(inode);
 		d_instantiate(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	return err;
 }
@@ -52,7 +55,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
  * Methods themselves.
  */
 
-static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
 {
 	struct inode * inode;
 	ino_t ino;
@@ -60,39 +63,27 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, str
 	if (dentry->d_name.len > EXT2_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	ino = ext2_inode_by_name(dir, dentry);
+	ino = ext2_inode_by_name(dir, &dentry->d_name);
 	inode = NULL;
 	if (ino) {
-		inode = iget(dir->i_sb, ino);
-		if (!inode)
-			return ERR_PTR(-EACCES);
+		inode = ext2_iget(dir->i_sb, ino);
+		if (inode == ERR_PTR(-ESTALE)) {
+			ext2_error(dir->i_sb, __func__,
+					"deleted inode referenced: %lu",
+					(unsigned long) ino);
+			return ERR_PTR(-EIO);
+		}
 	}
 	return d_splice_alias(inode, dentry);
 }
 
 struct dentry *ext2_get_parent(struct dentry *child)
 {
-	unsigned long ino;
-	struct dentry *parent;
-	struct inode *inode;
-	struct dentry dotdot;
-
-	dotdot.d_name.name = "..";
-	dotdot.d_name.len = 2;
-
-	ino = ext2_inode_by_name(child->d_inode, &dotdot);
+	struct qstr dotdot = QSTR_INIT("..", 2);
+	unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
 	if (!ino)
 		return ERR_PTR(-ENOENT);
-	inode = iget(child->d_inode->i_sb, ino);
-
-	if (!inode)
-		return ERR_PTR(-EACCES);
-	parent = d_alloc_anon(inode);
-	if (!parent) {
-		iput(inode);
-		parent = ERR_PTR(-ENOMEM);
-	}
-	return parent;
+	return d_obtain_alias(ext2_iget(child->d_inode->i_sb, ino));
 } 
 
 /*
@@ -103,29 +94,55 @@ struct dentry *ext2_get_parent(struct dentry *child)
  * If the create succeeds, we fill in the inode information
  * with d_instantiate(). 
  */
-static int ext2_create (struct inode * dir, struct dentry * dentry, int mode, struct nameidata *nd)
+static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
 {
-	struct inode * inode = ext2_new_inode (dir, mode);
-	int err = PTR_ERR(inode);
-	if (!IS_ERR(inode)) {
-		inode->i_op = &ext2_file_inode_operations;
-		if (ext2_use_xip(inode->i_sb)) {
-			inode->i_mapping->a_ops = &ext2_aops_xip;
-			inode->i_fop = &ext2_xip_file_operations;
-		} else if (test_opt(inode->i_sb, NOBH)) {
-			inode->i_mapping->a_ops = &ext2_nobh_aops;
-			inode->i_fop = &ext2_file_operations;
-		} else {
-			inode->i_mapping->a_ops = &ext2_aops;
-			inode->i_fop = &ext2_file_operations;
-		}
-		mark_inode_dirty(inode);
-		err = ext2_add_nondir(dentry, inode);
+	struct inode *inode;
+
+	dquot_initialize(dir);
+
+	inode = ext2_new_inode(dir, mode, &dentry->d_name);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &ext2_file_inode_operations;
+	if (ext2_use_xip(inode->i_sb)) {
+		inode->i_mapping->a_ops = &ext2_aops_xip;
+		inode->i_fop = &ext2_xip_file_operations;
+	} else if (test_opt(inode->i_sb, NOBH)) {
+		inode->i_mapping->a_ops = &ext2_nobh_aops;
+		inode->i_fop = &ext2_file_operations;
+	} else {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_file_operations;
 	}
-	return err;
+	mark_inode_dirty(inode);
+	return ext2_add_nondir(dentry, inode);
 }
 
-static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, dev_t rdev)
+static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct inode *inode = ext2_new_inode(dir, mode, NULL);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &ext2_file_inode_operations;
+	if (ext2_use_xip(inode->i_sb)) {
+		inode->i_mapping->a_ops = &ext2_aops_xip;
+		inode->i_fop = &ext2_xip_file_operations;
+	} else if (test_opt(inode->i_sb, NOBH)) {
+		inode->i_mapping->a_ops = &ext2_nobh_aops;
+		inode->i_fop = &ext2_file_operations;
+	} else {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_file_operations;
+	}
+	mark_inode_dirty(inode);
+	d_tmpfile(dentry, inode);
+	unlock_new_inode(inode);
+	return 0;
+}
+
+static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 {
 	struct inode * inode;
 	int err;
@@ -133,7 +150,9 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, dev_
 	if (!new_valid_dev(rdev))
 		return -EINVAL;
 
-	inode = ext2_new_inode (dir, mode);
+	dquot_initialize(dir);
+
+	inode = ext2_new_inode (dir, mode, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
@@ -157,7 +176,9 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry,
 	if (l > sb->s_blocksize)
 		goto out;
 
-	inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO);
+	dquot_initialize(dir);
+
+	inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out;
@@ -186,6 +207,7 @@ out:
 
 out_fail:
 	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
 	iput (inode);
 	goto out;
 }
@@ -194,28 +216,34 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
 	struct dentry *dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
+	int err;
 
-	if (inode->i_nlink >= EXT2_LINK_MAX)
-		return -EMLINK;
+	dquot_initialize(dir);
 
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
-	return ext2_add_nondir(dentry, inode);
+	err = ext2_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
+		return 0;
+	}
+	inode_dec_link_count(inode);
+	iput(inode);
+	return err;
 }
 
-static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 {
 	struct inode * inode;
-	int err = -EMLINK;
+	int err;
 
-	if (dir->i_nlink >= EXT2_LINK_MAX)
-		goto out;
+	dquot_initialize(dir);
 
 	inode_inc_link_count(dir);
 
-	inode = ext2_new_inode (dir, S_IFDIR | mode);
+	inode = ext2_new_inode(dir, S_IFDIR | mode, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_dir;
@@ -237,6 +265,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 	if (err)
 		goto out_fail;
 
+	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
 out:
 	return err;
@@ -244,6 +273,7 @@ out:
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 out_dir:
 	inode_dec_link_count(dir);
@@ -257,7 +287,9 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry)
 	struct page * page;
 	int err = -ENOENT;
 
-	de = ext2_find_entry (dir, dentry, &page);
+	dquot_initialize(dir);
+
+	de = ext2_find_entry (dir, &dentry->d_name, &page);
 	if (!de)
 		goto out;
 
@@ -299,7 +331,10 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
 	struct ext2_dir_entry_2 * old_de;
 	int err = -ENOENT;
 
-	old_de = ext2_find_entry (old_dir, old_dentry, &old_page);
+	dquot_initialize(old_dir);
+	dquot_initialize(new_dir);
+
+	old_de = ext2_find_entry (old_dir, &old_dentry->d_name, &old_page);
 	if (!old_de)
 		goto out;
 
@@ -319,27 +354,18 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
 			goto out_dir;
 
 		err = -ENOENT;
-		new_de = ext2_find_entry (new_dir, new_dentry, &new_page);
+		new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page);
 		if (!new_de)
 			goto out_dir;
-		inode_inc_link_count(old_inode);
-		ext2_set_link(new_dir, new_de, new_page, old_inode);
+		ext2_set_link(new_dir, new_de, new_page, old_inode, 1);
 		new_inode->i_ctime = CURRENT_TIME_SEC;
 		if (dir_de)
-			new_inode->i_nlink--;
+			drop_nlink(new_inode);
 		inode_dec_link_count(new_inode);
 	} else {
-		if (dir_de) {
-			err = -EMLINK;
-			if (new_dir->i_nlink >= EXT2_LINK_MAX)
-				goto out_dir;
-		}
-		inode_inc_link_count(old_inode);
 		err = ext2_add_link(new_dentry, old_inode);
-		if (err) {
-			inode_dec_link_count(old_inode);
+		if (err)
 			goto out_dir;
-		}
 		if (dir_de)
 			inode_inc_link_count(new_dir);
 	}
@@ -347,15 +373,19 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
 	/*
 	 * Like most other Unix systems, set the ctime for inodes on a
  	 * rename.
-	 * inode_dec_link_count() will mark the inode dirty.
 	 */
 	old_inode->i_ctime = CURRENT_TIME_SEC;
+	mark_inode_dirty(old_inode);
 
 	ext2_delete_entry (old_de, old_page);
-	inode_dec_link_count(old_inode);
 
 	if (dir_de) {
-		ext2_set_link(old_inode, dir_de, dir_page, new_dir);
+		if (old_dir != new_dir)
+			ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
+		else {
+			kunmap(dir_page);
+			page_cache_release(dir_page);
+		}
 		inode_dec_link_count(old_dir);
 	}
 	return 0;
@@ -373,7 +403,7 @@ out:
 	return err;
 }
 
-struct inode_operations ext2_dir_inode_operations = {
+const struct inode_operations ext2_dir_inode_operations = {
 	.create		= ext2_create,
 	.lookup		= ext2_lookup,
 	.link		= ext2_link,
@@ -390,10 +420,12 @@ struct inode_operations ext2_dir_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.setattr	= ext2_setattr,
-	.permission	= ext2_permission,
+	.get_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
+	.tmpfile	= ext2_tmpfile,
 };
 
-struct inode_operations ext2_special_inode_operations = {
+const struct inode_operations ext2_special_inode_operations = {
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -401,5 +433,6 @@ struct inode_operations ext2_special_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.setattr	= ext2_setattr,
-	.permission	= ext2_permission,
+	.get_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
 };
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 513cd421ac0..3750031cfa2 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -25,10 +25,12 @@
 #include <linux/parser.h>
 #include <linux/random.h>
 #include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
+#include <linux/exportfs.h>
 #include <linux/vfs.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
+#include <linux/log2.h>
+#include <linux/quotaops.h>
 #include <asm/uaccess.h>
 #include "ext2.h"
 #include "xattr.h"
@@ -36,51 +38,67 @@
 #include "xip.h"
 
 static void ext2_sync_super(struct super_block *sb,
-			    struct ext2_super_block *es);
+			    struct ext2_super_block *es, int wait);
 static int ext2_remount (struct super_block * sb, int * flags, char * data);
 static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
+static int ext2_sync_fs(struct super_block *sb, int wait);
+static int ext2_freeze(struct super_block *sb);
+static int ext2_unfreeze(struct super_block *sb);
 
-void ext2_error (struct super_block * sb, const char * function,
-		 const char * fmt, ...)
+void ext2_error(struct super_block *sb, const char *function,
+		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	struct ext2_super_block *es = sbi->s_es;
 
 	if (!(sb->s_flags & MS_RDONLY)) {
+		spin_lock(&sbi->s_lock);
 		sbi->s_mount_state |= EXT2_ERROR_FS;
-		es->s_state =
-			cpu_to_le16(le16_to_cpu(es->s_state) | EXT2_ERROR_FS);
-		ext2_sync_super(sb, es);
+		es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
+		spin_unlock(&sbi->s_lock);
+		ext2_sync_super(sb, es, 1);
 	}
 
 	va_start(args, fmt);
-	printk(KERN_CRIT "EXT2-fs error (device %s): %s: ",sb->s_id, function);
-	vprintk(fmt, args);
-	printk("\n");
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_CRIT "EXT2-fs (%s): error: %s: %pV\n",
+	       sb->s_id, function, &vaf);
+
 	va_end(args);
 
 	if (test_opt(sb, ERRORS_PANIC))
-		panic("EXT2-fs panic from previous error\n");
+		panic("EXT2-fs: panic from previous error\n");
 	if (test_opt(sb, ERRORS_RO)) {
-		printk("Remounting filesystem read-only\n");
+		ext2_msg(sb, KERN_CRIT,
+			     "error: remounting filesystem read-only");
 		sb->s_flags |= MS_RDONLY;
 	}
 }
 
-void ext2_warning (struct super_block * sb, const char * function,
-		   const char * fmt, ...)
+void ext2_msg(struct super_block *sb, const char *prefix,
+		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	printk(KERN_WARNING "EXT2-fs warning (device %s): %s: ",
-	       sb->s_id, function);
-	vprintk(fmt, args);
-	printk("\n");
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk("%sEXT2-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
+
 	va_end(args);
 }
 
+/*
+ * This must be called with sbi->s_lock held.
+ */
 void ext2_update_dynamic_rev(struct super_block *sb)
 {
 	struct ext2_super_block *es = EXT2_SB(sb)->s_es;
@@ -88,9 +106,9 @@ void ext2_update_dynamic_rev(struct super_block *sb)
 	if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV)
 		return;
 
-	ext2_warning(sb, __FUNCTION__,
-		     "updating to rev %d because of new feature flag, "
-		     "running e2fsck is recommended",
+	ext2_msg(sb, KERN_WARNING,
+		     "warning: updating to rev %d because of "
+		     "new feature flag, running e2fsck is recommended",
 		     EXT2_DYNAMIC_REV);
 
 	es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO);
@@ -112,12 +130,16 @@ static void ext2_put_super (struct super_block * sb)
 	int i;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 
+	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+
 	ext2_xattr_put_super(sb);
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
 
+		spin_lock(&sbi->s_lock);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
-		ext2_sync_super(sb, es);
+		spin_unlock(&sbi->s_lock);
+		ext2_sync_super(sb, es, 1);
 	}
 	db_count = sbi->s_gdb_count;
 	for (i = 0; i < db_count; i++)
@@ -130,53 +152,53 @@ static void ext2_put_super (struct super_block * sb)
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	brelse (sbi->s_sbh);
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-
-	return;
 }
 
-static kmem_cache_t * ext2_inode_cachep;
+static struct kmem_cache * ext2_inode_cachep;
 
 static struct inode *ext2_alloc_inode(struct super_block *sb)
 {
 	struct ext2_inode_info *ei;
-	ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, SLAB_KERNEL);
+	ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
-	ei->i_acl = EXT2_ACL_NOT_CACHED;
-	ei->i_default_acl = EXT2_ACL_NOT_CACHED;
-#endif
+	ei->i_block_alloc_info = NULL;
 	ei->vfs_inode.i_version = 1;
 	return &ei->vfs_inode;
 }
 
-static void ext2_destroy_inode(struct inode *inode)
+static void ext2_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
 }
 
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void ext2_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, ext2_i_callback);
+}
+
+static void init_once(void *foo)
 {
 	struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;
 
-	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
-	    SLAB_CTOR_CONSTRUCTOR) {
-		rwlock_init(&ei->i_meta_lock);
+	rwlock_init(&ei->i_meta_lock);
 #ifdef CONFIG_EXT2_FS_XATTR
-		init_rwsem(&ei->xattr_sem);
+	init_rwsem(&ei->xattr_sem);
 #endif
-		inode_init_once(&ei->vfs_inode);
-	}
+	mutex_init(&ei->truncate_mutex);
+	inode_init_once(&ei->vfs_inode);
 }
- 
-static int init_inodecache(void)
+
+static int __init init_inodecache(void)
 {
 	ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
 					     sizeof(struct ext2_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
 						SLAB_MEM_SPREAD),
-					     init_once, NULL);
+					     init_once);
 	if (ext2_inode_cachep == NULL)
 		return -ENOMEM;
 	return 0;
@@ -184,31 +206,79 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ext2_inode_cachep);
 }
 
-static void ext2_clear_inode(struct inode *inode)
+static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 {
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
-	struct ext2_inode_info *ei = EXT2_I(inode);
+	struct super_block *sb = root->d_sb;
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+	struct ext2_super_block *es = sbi->s_es;
+	unsigned long def_mount_opts;
+
+	spin_lock(&sbi->s_lock);
+	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+
+	if (sbi->s_sb_block != 1)
+		seq_printf(seq, ",sb=%lu", sbi->s_sb_block);
+	if (test_opt(sb, MINIX_DF))
+		seq_puts(seq, ",minixdf");
+	if (test_opt(sb, GRPID))
+		seq_puts(seq, ",grpid");
+	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS))
+		seq_puts(seq, ",nogrpid");
+	if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) ||
+	    le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) {
+		seq_printf(seq, ",resuid=%u",
+				from_kuid_munged(&init_user_ns, sbi->s_resuid));
+	}
+	if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) ||
+	    le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) {
+		seq_printf(seq, ",resgid=%u",
+				from_kgid_munged(&init_user_ns, sbi->s_resgid));
+	}
+	if (test_opt(sb, ERRORS_RO)) {
+		int def_errors = le16_to_cpu(es->s_errors);
 
-	if (ei->i_acl && ei->i_acl != EXT2_ACL_NOT_CACHED) {
-		posix_acl_release(ei->i_acl);
-		ei->i_acl = EXT2_ACL_NOT_CACHED;
+		if (def_errors == EXT2_ERRORS_PANIC ||
+		    def_errors == EXT2_ERRORS_CONTINUE) {
+			seq_puts(seq, ",errors=remount-ro");
+		}
 	}
-	if (ei->i_default_acl && ei->i_default_acl != EXT2_ACL_NOT_CACHED) {
-		posix_acl_release(ei->i_default_acl);
-		ei->i_default_acl = EXT2_ACL_NOT_CACHED;
+	if (test_opt(sb, ERRORS_CONT))
+		seq_puts(seq, ",errors=continue");
+	if (test_opt(sb, ERRORS_PANIC))
+		seq_puts(seq, ",errors=panic");
+	if (test_opt(sb, NO_UID32))
+		seq_puts(seq, ",nouid32");
+	if (test_opt(sb, DEBUG))
+		seq_puts(seq, ",debug");
+	if (test_opt(sb, OLDALLOC))
+		seq_puts(seq, ",oldalloc");
+
+#ifdef CONFIG_EXT2_FS_XATTR
+	if (test_opt(sb, XATTR_USER))
+		seq_puts(seq, ",user_xattr");
+	if (!test_opt(sb, XATTR_USER) &&
+	    (def_mount_opts & EXT2_DEFM_XATTR_USER)) {
+		seq_puts(seq, ",nouser_xattr");
 	}
 #endif
-}
 
-static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(vfs->mnt_sb);
+#ifdef CONFIG_EXT2_FS_POSIX_ACL
+	if (test_opt(sb, POSIX_ACL))
+		seq_puts(seq, ",acl");
+	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL))
+		seq_puts(seq, ",noacl");
+#endif
 
-	if (sbi->s_mount_opt & EXT2_MOUNT_GRPID)
-		seq_puts(seq, ",grpid");
+	if (test_opt(sb, NOBH))
+		seq_puts(seq, ",nobh");
 
 #if defined(CONFIG_QUOTA)
 	if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA)
@@ -223,6 +293,10 @@ static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",xip");
 #endif
 
+	if (!test_opt(sb, RESERVATION))
+		seq_puts(seq, ",noreservation");
+
+	spin_unlock(&sbi->s_lock);
 	return 0;
 }
 
@@ -231,18 +305,17 @@ static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, siz
 static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
 #endif
 
-static struct super_operations ext2_sops = {
+static const struct super_operations ext2_sops = {
 	.alloc_inode	= ext2_alloc_inode,
 	.destroy_inode	= ext2_destroy_inode,
-	.read_inode	= ext2_read_inode,
 	.write_inode	= ext2_write_inode,
-	.put_inode	= ext2_put_inode,
-	.delete_inode	= ext2_delete_inode,
+	.evict_inode	= ext2_evict_inode,
 	.put_super	= ext2_put_super,
-	.write_super	= ext2_write_super,
+	.sync_fs	= ext2_sync_fs,
+	.freeze_fs	= ext2_freeze,
+	.unfreeze_fs	= ext2_unfreeze,
 	.statfs		= ext2_statfs,
 	.remount_fs	= ext2_remount,
-	.clear_inode	= ext2_clear_inode,
 	.show_options	= ext2_show_options,
 #ifdef CONFIG_QUOTA
 	.quota_read	= ext2_quota_read,
@@ -250,52 +323,50 @@ static struct super_operations ext2_sops = {
 #endif
 };
 
-static struct dentry *ext2_get_dentry(struct super_block *sb, void *vobjp)
+static struct inode *ext2_nfs_get_inode(struct super_block *sb,
+		u64 ino, u32 generation)
 {
-	__u32 *objp = vobjp;
-	unsigned long ino = objp[0];
-	__u32 generation = objp[1];
 	struct inode *inode;
-	struct dentry *result;
 
 	if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO)
 		return ERR_PTR(-ESTALE);
 	if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
 		return ERR_PTR(-ESTALE);
 
-	/* iget isn't really right if the inode is currently unallocated!!
-	 * ext2_read_inode currently does appropriate checks, but
-	 * it might be "neater" to call ext2_get_inode first and check
-	 * if the inode is valid.....
+	/*
+	 * ext2_iget isn't quite right if the inode is currently unallocated!
+	 * However ext2_iget currently does appropriate checks to handle stale
+	 * inodes so everything is OK.
 	 */
-	inode = iget(sb, ino);
-	if (inode == NULL)
-		return ERR_PTR(-ENOMEM);
-	if (is_bad_inode(inode) ||
-	    (generation && inode->i_generation != generation)) {
+	inode = ext2_iget(sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	if (generation && inode->i_generation != generation) {
 		/* we didn't find the right inode.. */
 		iput(inode);
 		return ERR_PTR(-ESTALE);
 	}
-	/* now to find a dentry.
-	 * If possible, get a well-connected one
-	 */
-	result = d_alloc_anon(inode);
-	if (!result) {
-		iput(inode);
-		return ERR_PTR(-ENOMEM);
-	}
-	return result;
+	return inode;
 }
 
-/* Yes, most of these are left as NULL!!
- * A NULL value implies the default, which works with ext2-like file
- * systems, but can be improved upon.
- * Currently only get_parent is required.
- */
-static struct export_operations ext2_export_ops = {
+static struct dentry *ext2_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,
+				    ext2_nfs_get_inode);
+}
+
+static struct dentry *ext2_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,
+				    ext2_nfs_get_inode);
+}
+
+static const struct export_operations ext2_export_ops = {
+	.fh_to_dentry = ext2_fh_to_dentry,
+	.fh_to_parent = ext2_fh_to_parent,
 	.get_parent = ext2_get_parent,
-	.get_dentry = ext2_get_dentry,
 };
 
 static unsigned long get_sb_block(void **data)
@@ -324,10 +395,10 @@ enum {
 	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
 	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
 	Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
-	Opt_usrquota, Opt_grpquota
+	Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
 	{Opt_bsd_df, "bsddf"},
 	{Opt_minix_df, "minixdf"},
 	{Opt_grpid, "grpid"},
@@ -356,16 +427,19 @@ static match_table_t tokens = {
 	{Opt_ignore, "noquota"},
 	{Opt_quota, "quota"},
 	{Opt_usrquota, "usrquota"},
+	{Opt_reservation, "reservation"},
+	{Opt_noreservation, "noreservation"},
 	{Opt_err, NULL}
 };
 
-static int parse_options (char * options,
-			  struct ext2_sb_info *sbi)
+static int parse_options(char *options, struct super_block *sb)
 {
-	char * p;
+	char *p;
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	substring_t args[MAX_OPT_ARGS];
-	unsigned long kind = EXT2_MOUNT_ERRORS_CONT;
 	int option;
+	kuid_t uid;
+	kgid_t gid;
 
 	if (!options)
 		return 1;
@@ -392,25 +466,42 @@ static int parse_options (char * options,
 		case Opt_resuid:
 			if (match_int(&args[0], &option))
 				return 0;
-			sbi->s_resuid = option;
+			uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(uid)) {
+				ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option);
+				return 0;
+
+			}
+			sbi->s_resuid = uid;
 			break;
 		case Opt_resgid:
 			if (match_int(&args[0], &option))
 				return 0;
-			sbi->s_resgid = option;
+			gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(gid)) {
+				ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option);
+				return 0;
+			}
+			sbi->s_resgid = gid;
 			break;
 		case Opt_sb:
 			/* handled by get_sb_block() instead of here */
 			/* *sb_block = match_int(&args[0]); */
 			break;
 		case Opt_err_panic:
-			kind = EXT2_MOUNT_ERRORS_PANIC;
+			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
+			clear_opt (sbi->s_mount_opt, ERRORS_RO);
+			set_opt (sbi->s_mount_opt, ERRORS_PANIC);
 			break;
 		case Opt_err_ro:
-			kind = EXT2_MOUNT_ERRORS_RO;
+			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
+			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
+			set_opt (sbi->s_mount_opt, ERRORS_RO);
 			break;
 		case Opt_err_cont:
-			kind = EXT2_MOUNT_ERRORS_CONT;
+			clear_opt (sbi->s_mount_opt, ERRORS_RO);
+			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
+			set_opt (sbi->s_mount_opt, ERRORS_CONT);
 			break;
 		case Opt_nouid32:
 			set_opt (sbi->s_mount_opt, NO_UID32);
@@ -440,7 +531,8 @@ static int parse_options (char * options,
 #else
 		case Opt_user_xattr:
 		case Opt_nouser_xattr:
-			printk("EXT2 (no)user_xattr options not supported\n");
+			ext2_msg(sb, KERN_INFO, "(no)user_xattr options"
+				"not supported");
 			break;
 #endif
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
@@ -453,14 +545,15 @@ static int parse_options (char * options,
 #else
 		case Opt_acl:
 		case Opt_noacl:
-			printk("EXT2 (no)acl options not supported\n");
+			ext2_msg(sb, KERN_INFO,
+				"(no)acl options not supported");
 			break;
 #endif
 		case Opt_xip:
 #ifdef CONFIG_EXT2_FS_XIP
 			set_opt (sbi->s_mount_opt, XIP);
 #else
-			printk("EXT2 xip option not supported\n");
+			ext2_msg(sb, KERN_INFO, "xip option not supported");
 #endif
 			break;
 
@@ -477,19 +570,25 @@ static int parse_options (char * options,
 		case Opt_quota:
 		case Opt_usrquota:
 		case Opt_grpquota:
-			printk(KERN_ERR
-				"EXT2-fs: quota operations not supported.\n");
-
+			ext2_msg(sb, KERN_INFO,
+				"quota operations not supported");
 			break;
 #endif
 
+		case Opt_reservation:
+			set_opt(sbi->s_mount_opt, RESERVATION);
+			ext2_msg(sb, KERN_INFO, "reservations ON");
+			break;
+		case Opt_noreservation:
+			clear_opt(sbi->s_mount_opt, RESERVATION);
+			ext2_msg(sb, KERN_INFO, "reservations OFF");
+			break;
 		case Opt_ignore:
 			break;
 		default:
 			return 0;
 		}
 	}
-	sbi->s_mount_opt |= kind;
 	return 1;
 }
 
@@ -501,34 +600,39 @@ static int ext2_setup_super (struct super_block * sb,
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 
 	if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) {
-		printk ("EXT2-fs warning: revision level too high, "
-			"forcing read-only mode\n");
+		ext2_msg(sb, KERN_ERR,
+			"error: revision level too high, "
+			"forcing read-only mode");
 		res = MS_RDONLY;
 	}
 	if (read_only)
 		return res;
 	if (!(sbi->s_mount_state & EXT2_VALID_FS))
-		printk ("EXT2-fs warning: mounting unchecked fs, "
-			"running e2fsck is recommended\n");
+		ext2_msg(sb, KERN_WARNING,
+			"warning: mounting unchecked fs, "
+			"running e2fsck is recommended");
 	else if ((sbi->s_mount_state & EXT2_ERROR_FS))
-		printk ("EXT2-fs warning: mounting fs with errors, "
-			"running e2fsck is recommended\n");
+		ext2_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))
-		printk ("EXT2-fs warning: maximal mount count reached, "
-			"running e2fsck is recommended\n");
+		ext2_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()))
-		printk ("EXT2-fs warning: checktime reached, "
-			"running e2fsck is recommended\n");
+		(le32_to_cpu(es->s_lastcheck) +
+			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+		ext2_msg(sb, KERN_WARNING,
+			"warning: checktime reached, "
+			"running e2fsck is recommended");
 	if (!le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
-	es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
-	ext2_write_super(sb);
+	le16_add_cpu(&es->s_mnt_count, 1);
 	if (test_opt (sb, DEBUG))
-		printk ("[EXT II FS %s, %s, bs=%lu, fs=%lu, gc=%lu, "
-			"bpg=%lu, ipg=%lu, mo=%04lx]\n",
+		ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, "
+			"bpg=%lu, ipg=%lu, mo=%04lx]",
 			EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
 			sbi->s_frag_size,
 			sbi->s_groups_count,
@@ -538,27 +642,24 @@ static int ext2_setup_super (struct super_block * sb,
 	return res;
 }
 
-static int ext2_check_descriptors (struct super_block * sb)
+static int ext2_check_descriptors(struct super_block *sb)
 {
 	int i;
-	int desc_block = 0;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	unsigned long first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
-	unsigned long last_block;
-	struct ext2_group_desc * gdp = NULL;
 
 	ext2_debug ("Checking group descriptors");
 
-	for (i = 0; i < sbi->s_groups_count; i++)
-	{
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
+		ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
+		ext2_fsblk_t last_block;
+
 		if (i == sbi->s_groups_count - 1)
 			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
 		else
 			last_block = first_block +
 				(EXT2_BLOCKS_PER_GROUP(sb) - 1);
 
-		if ((i % EXT2_DESC_PER_BLOCK(sb)) == 0)
-			gdp = (struct ext2_group_desc *) sbi->s_group_desc[desc_block++]->b_data;
 		if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
 		    le32_to_cpu(gdp->bg_block_bitmap) > last_block)
 		{
@@ -578,7 +679,7 @@ static int ext2_check_descriptors (struct super_block * sb)
 			return 0;
 		}
 		if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
-		    le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >
+		    le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 >
 		    last_block)
 		{
 			ext2_error (sb, "ext2_check_descriptors",
@@ -587,14 +688,10 @@ static int ext2_check_descriptors (struct super_block * sb)
 				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_table));
 			return 0;
 		}
-		first_block += EXT2_BLOCKS_PER_GROUP(sb);
-		gdp++;
 	}
 	return 1;
 }
 
-#define log2(n) ffz(~(n))
- 
 /*
  * Maximal file size.  There is a direct, and {,double-,triple-}indirect
  * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
@@ -603,11 +700,31 @@ static int ext2_check_descriptors (struct super_block * sb)
 static loff_t ext2_max_size(int bits)
 {
 	loff_t res = EXT2_NDIR_BLOCKS;
-	/* This constant is calculated to be the largest file size for a
-	 * dense, 4k-blocksize file such that the total number of
+	int meta_blocks;
+	loff_t upper_limit;
+
+	/* This is calculated to be the largest file size for a
+	 * dense, file such that the total number of
 	 * sectors in the file, including data and all indirect blocks,
-	 * does not exceed 2^32. */
-	const loff_t upper_limit = 0x1ff7fffd000LL;
+	 * does not exceed 2^32 -1
+	 * __u32 i_blocks representing the total number of
+	 * 512 bytes blocks of the file
+	 */
+	upper_limit = (1LL << 32) - 1;
+
+	/* total blocks in file system block size */
+	upper_limit >>= (bits - 9);
+
+
+	/* 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));
@@ -615,6 +732,10 @@ static loff_t ext2_max_size(int bits)
 	res <<= bits;
 	if (res > upper_limit)
 		res = upper_limit;
+
+	if (res > MAX_LFS_FILESIZE)
+		res = MAX_LFS_FILESIZE;
+
 	return res;
 }
 
@@ -623,10 +744,9 @@ static unsigned long descriptor_loc(struct super_block *sb,
 				    int nr)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	unsigned long bg, first_data_block, first_meta_bg;
+	unsigned long bg, first_meta_bg;
 	int has_super = 0;
 	
-	first_data_block = le32_to_cpu(sbi->s_es->s_first_data_block);
 	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
 
 	if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) ||
@@ -635,7 +755,8 @@ static unsigned long descriptor_loc(struct super_block *sb,
 	bg = sbi->s_desc_per_block * nr;
 	if (ext2_bg_has_super(sb, bg))
 		has_super = 1;
-	return (first_data_block + has_super + (bg * sbi->s_blocks_per_group));
+
+	return ext2_group_first_block_no(sb, bg) + has_super;
 }
 
 static int ext2_fill_super(struct super_block *sb, void *data, int silent)
@@ -649,15 +770,28 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned long logic_sb_block;
 	unsigned long offset = 0;
 	unsigned long def_mount_opts;
+	long ret = -EINVAL;
 	int blocksize = BLOCK_SIZE;
 	int db_count;
 	int i, j;
 	__le32 features;
+	int err;
 
+	err = -ENOMEM;
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
-		return -ENOMEM;
+		goto failed;
+
+	sbi->s_blockgroup_lock =
+		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
+	if (!sbi->s_blockgroup_lock) {
+		kfree(sbi);
+		goto failed;
+	}
 	sb->s_fs_info = sbi;
+	sbi->s_sb_block = sb_block;
+
+	spin_lock_init(&sbi->s_lock);
 
 	/*
 	 * See what the current blocksize for the device is, and
@@ -668,7 +802,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
 	if (!blocksize) {
-		printk ("EXT2-fs: unable to set blocksize\n");
+		ext2_msg(sb, KERN_ERR, "error: unable to set blocksize");
 		goto failed_sbi;
 	}
 
@@ -684,7 +818,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	if (!(bh = sb_bread(sb, logic_sb_block))) {
-		printk ("EXT2-fs: unable to read superblock\n");
+		ext2_msg(sb, KERN_ERR, "error: unable to read superblock");
 		goto failed_sbi;
 	}
 	/*
@@ -706,20 +840,28 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		set_opt(sbi->s_mount_opt, GRPID);
 	if (def_mount_opts & EXT2_DEFM_UID16)
 		set_opt(sbi->s_mount_opt, NO_UID32);
+#ifdef CONFIG_EXT2_FS_XATTR
 	if (def_mount_opts & EXT2_DEFM_XATTR_USER)
 		set_opt(sbi->s_mount_opt, XATTR_USER);
+#endif
+#ifdef CONFIG_EXT2_FS_POSIX_ACL
 	if (def_mount_opts & EXT2_DEFM_ACL)
 		set_opt(sbi->s_mount_opt, POSIX_ACL);
+#endif
 	
 	if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
 		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
-	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_RO)
+	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE)
+		set_opt(sbi->s_mount_opt, ERRORS_CONT);
+	else
 		set_opt(sbi->s_mount_opt, ERRORS_RO);
 
-	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
-	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+	sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
+	sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
 	
-	if (!parse_options ((char *) data, sbi))
+	set_opt(sbi->s_mount_opt, RESERVATION);
+
+	if (!parse_options((char *) data, sb))
 		goto failed_mount;
 
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
@@ -733,8 +875,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U)))
-		printk("EXT2-fs warning: feature flags set on rev 0 fs, "
-		       "running e2fsck is recommended\n");
+		ext2_msg(sb, KERN_WARNING,
+			"warning: feature flags set on rev 0 fs, "
+			"running e2fsck is recommended");
 	/*
 	 * Check feature flags regardless of the revision level, since we
 	 * previously didn't change the revision level when setting the flags,
@@ -742,25 +885,25 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP);
 	if (features) {
-		printk("EXT2-fs: %s: couldn't mount because of "
-		       "unsupported optional features (%x).\n",
-		       sb->s_id, le32_to_cpu(features));
+		ext2_msg(sb, KERN_ERR,	"error: couldn't mount because of "
+		       "unsupported optional features (%x)",
+			le32_to_cpu(features));
 		goto failed_mount;
 	}
 	if (!(sb->s_flags & MS_RDONLY) &&
 	    (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
-		printk("EXT2-fs: %s: couldn't mount RDWR because of "
-		       "unsupported optional features (%x).\n",
-		       sb->s_id, le32_to_cpu(features));
+		ext2_msg(sb, KERN_ERR, "error: couldn't mount RDWR because of "
+		       "unsupported optional features (%x)",
+		       le32_to_cpu(features));
 		goto failed_mount;
 	}
 
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
-	if ((ext2_use_xip(sb)) && ((blocksize != PAGE_SIZE) ||
-				  (sb->s_blocksize != blocksize))) {
+	if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
 		if (!silent)
-			printk("XIP: Unsupported blocksize\n");
+			ext2_msg(sb, KERN_ERR,
+				"error: unsupported blocksize for xip");
 		goto failed_mount;
 	}
 
@@ -769,7 +912,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		brelse(bh);
 
 		if (!sb_set_blocksize(sb, blocksize)) {
-			printk(KERN_ERR "EXT2-fs: blocksize too small for device.\n");
+			ext2_msg(sb, KERN_ERR,
+				"error: bad blocksize %d", blocksize);
 			goto failed_sbi;
 		}
 
@@ -777,19 +921,20 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		offset = (sb_block*BLOCK_SIZE) % blocksize;
 		bh = sb_bread(sb, logic_sb_block);
 		if(!bh) {
-			printk("EXT2-fs: Couldn't read superblock on "
-			       "2nd try.\n");
+			ext2_msg(sb, KERN_ERR, "error: couldn't read"
+				"superblock on 2nd try");
 			goto failed_sbi;
 		}
 		es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
 		sbi->s_es = es;
 		if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) {
-			printk ("EXT2-fs: Magic mismatch, very weird !\n");
+			ext2_msg(sb, KERN_ERR, "error: magic mismatch");
 			goto failed_mount;
 		}
 	}
 
 	sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);
+	sb->s_max_links = EXT2_LINK_MAX;
 
 	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
 		sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
@@ -798,9 +943,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		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 < EXT2_GOOD_OLD_INODE_SIZE) ||
-		    (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
+		    !is_power_of_2(sbi->s_inode_size) ||
 		    (sbi->s_inode_size > blocksize)) {
-			printk ("EXT2-fs: unsupported inode size: %d\n",
+			ext2_msg(sb, KERN_ERR,
+				"error: unsupported inode size: %d",
 				sbi->s_inode_size);
 			goto failed_mount;
 		}
@@ -828,38 +974,42 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sbh = bh;
 	sbi->s_mount_state = le16_to_cpu(es->s_state);
 	sbi->s_addr_per_block_bits =
-		log2 (EXT2_ADDR_PER_BLOCK(sb));
+		ilog2 (EXT2_ADDR_PER_BLOCK(sb));
 	sbi->s_desc_per_block_bits =
-		log2 (EXT2_DESC_PER_BLOCK(sb));
+		ilog2 (EXT2_DESC_PER_BLOCK(sb));
 
 	if (sb->s_magic != EXT2_SUPER_MAGIC)
 		goto cantfind_ext2;
 
 	if (sb->s_blocksize != bh->b_size) {
 		if (!silent)
-			printk ("VFS: Unsupported blocksize on dev "
-				"%s.\n", sb->s_id);
+			ext2_msg(sb, KERN_ERR, "error: unsupported blocksize");
 		goto failed_mount;
 	}
 
 	if (sb->s_blocksize != sbi->s_frag_size) {
-		printk ("EXT2-fs: fragsize %lu != blocksize %lu (not supported yet)\n",
+		ext2_msg(sb, KERN_ERR,
+			"error: fragsize %lu != blocksize %lu"
+			"(not supported yet)",
 			sbi->s_frag_size, sb->s_blocksize);
 		goto failed_mount;
 	}
 
 	if (sbi->s_blocks_per_group > sb->s_blocksize * 8) {
-		printk ("EXT2-fs: #blocks per group too big: %lu\n",
+		ext2_msg(sb, KERN_ERR,
+			"error: #blocks per group too big: %lu",
 			sbi->s_blocks_per_group);
 		goto failed_mount;
 	}
 	if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
-		printk ("EXT2-fs: #fragments per group too big: %lu\n",
+		ext2_msg(sb, KERN_ERR,
+			"error: #fragments per group too big: %lu",
 			sbi->s_frags_per_group);
 		goto failed_mount;
 	}
 	if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
-		printk ("EXT2-fs: #inodes per group too big: %lu\n",
+		ext2_msg(sb, KERN_ERR,
+			"error: #inodes per group too big: %lu",
 			sbi->s_inodes_per_group);
 		goto failed_mount;
 	}
@@ -873,70 +1023,105 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		   EXT2_DESC_PER_BLOCK(sb);
 	sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
 	if (sbi->s_group_desc == NULL) {
-		printk ("EXT2-fs: not enough memory\n");
+		ext2_msg(sb, KERN_ERR, "error: not enough memory");
 		goto failed_mount;
 	}
-	bgl_lock_init(&sbi->s_blockgroup_lock);
-	sbi->s_debts = kmalloc(sbi->s_groups_count * sizeof(*sbi->s_debts),
-			       GFP_KERNEL);
+	bgl_lock_init(sbi->s_blockgroup_lock);
+	sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
 	if (!sbi->s_debts) {
-		printk ("EXT2-fs: not enough memory\n");
+		ext2_msg(sb, KERN_ERR, "error: not enough memory");
 		goto failed_mount_group_desc;
 	}
-	memset(sbi->s_debts, 0, sbi->s_groups_count * sizeof(*sbi->s_debts));
 	for (i = 0; i < db_count; i++) {
 		block = descriptor_loc(sb, logic_sb_block, i);
 		sbi->s_group_desc[i] = sb_bread(sb, block);
 		if (!sbi->s_group_desc[i]) {
 			for (j = 0; j < i; j++)
 				brelse (sbi->s_group_desc[j]);
-			printk ("EXT2-fs: unable to read group descriptors\n");
+			ext2_msg(sb, KERN_ERR,
+				"error: unable to read group descriptors");
 			goto failed_mount_group_desc;
 		}
 	}
 	if (!ext2_check_descriptors (sb)) {
-		printk ("EXT2-fs: group descriptors corrupted!\n");
+		ext2_msg(sb, KERN_ERR, "group descriptors corrupted");
 		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);
 
-	percpu_counter_init(&sbi->s_freeblocks_counter,
+	/* per fileystem reservation list head & lock */
+	spin_lock_init(&sbi->s_rsv_window_lock);
+	sbi->s_rsv_window_root = RB_ROOT;
+	/*
+	 * Add a single, static dummy reservation to the start of the
+	 * reservation window list --- it gives us a placeholder for
+	 * append-at-start-of-list which makes the allocation logic
+	 * _much_ simpler.
+	 */
+	sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
+	sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
+	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
+	sbi->s_rsv_window_head.rsv_goal_size = 0;
+	ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);
+
+	err = percpu_counter_init(&sbi->s_freeblocks_counter,
 				ext2_count_free_blocks(sb));
-	percpu_counter_init(&sbi->s_freeinodes_counter,
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_freeinodes_counter,
 				ext2_count_free_inodes(sb));
-	percpu_counter_init(&sbi->s_dirs_counter,
+	}
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_dirs_counter,
 				ext2_count_dirs(sb));
+	}
+	if (err) {
+		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
+		goto failed_mount3;
+	}
 	/*
 	 * set up enough so that it can read an inode
 	 */
 	sb->s_op = &ext2_sops;
 	sb->s_export_op = &ext2_export_ops;
 	sb->s_xattr = ext2_xattr_handlers;
-	root = iget(sb, EXT2_ROOT_INO);
-	sb->s_root = d_alloc_root(root);
-	if (!sb->s_root) {
-		iput(root);
-		printk(KERN_ERR "EXT2-fs: get root inode failed\n");
+
+#ifdef CONFIG_QUOTA
+	sb->dq_op = &dquot_operations;
+	sb->s_qcop = &dquot_quotactl_ops;
+#endif
+
+	root = ext2_iget(sb, EXT2_ROOT_INO);
+	if (IS_ERR(root)) {
+		ret = PTR_ERR(root);
 		goto failed_mount3;
 	}
 	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
-		dput(sb->s_root);
-		sb->s_root = NULL;
-		printk(KERN_ERR "EXT2-fs: corrupt root inode, run e2fsck\n");
+		iput(root);
+		ext2_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck");
+		goto failed_mount3;
+	}
+
+	sb->s_root = d_make_root(root);
+	if (!sb->s_root) {
+		ext2_msg(sb, KERN_ERR, "error: get root inode failed");
+		ret = -ENOMEM;
 		goto failed_mount3;
 	}
 	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
-		ext2_warning(sb, __FUNCTION__,
-			"mounting ext3 filesystem as ext2");
-	ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
+		ext2_msg(sb, KERN_WARNING,
+			"warning: mounting ext3 filesystem as ext2");
+	if (ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY))
+		sb->s_flags |= MS_RDONLY;
+	ext2_write_super(sb);
 	return 0;
 
 cantfind_ext2:
 	if (!silent)
-		printk("VFS: Can't find an ext2 filesystem on dev %s.\n",
-		       sb->s_id);
+		ext2_msg(sb, KERN_ERR,
+			"error: can't find an ext2 filesystem on dev %s.",
+			sb->s_id);
 	goto failed_mount;
 failed_mount3:
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
@@ -952,26 +1137,45 @@ failed_mount:
 	brelse(bh);
 failed_sbi:
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-	return -EINVAL;
+failed:
+	return ret;
 }
 
-static void ext2_commit_super (struct super_block * sb,
-			       struct ext2_super_block * es)
+static void ext2_clear_super_error(struct super_block *sb)
 {
-	es->s_wtime = cpu_to_le32(get_seconds());
-	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
-	sb->s_dirt = 0;
+	struct buffer_head *sbh = EXT2_SB(sb)->s_sbh;
+
+	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.
+		 */
+		ext2_msg(sb, KERN_ERR,
+		       "previous I/O error to superblock detected\n");
+		clear_buffer_write_io_error(sbh);
+		set_buffer_uptodate(sbh);
+	}
 }
 
-static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
+static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
+			    int wait)
 {
+	ext2_clear_super_error(sb);
+	spin_lock(&EXT2_SB(sb)->s_lock);
 	es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
 	es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
 	es->s_wtime = cpu_to_le32(get_seconds());
+	/* unlock before we do IO */
+	spin_unlock(&EXT2_SB(sb)->s_lock);
 	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
-	sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
-	sb->s_dirt = 0;
+	if (wait)
+		sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
 }
 
 /*
@@ -984,27 +1188,61 @@ static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
  * may have been checked while mounted and e2fsck may have
  * set s_state to EXT2_VALID_FS after some corrections.
  */
+static int ext2_sync_fs(struct super_block *sb, int wait)
+{
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+	struct ext2_super_block *es = EXT2_SB(sb)->s_es;
+
+	/*
+	 * Write quota structures to quota file, sync_blockdev() will write
+	 * them to disk later
+	 */
+	dquot_writeback_dquots(sb, -1);
+
+	spin_lock(&sbi->s_lock);
+	if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
+		ext2_debug("setting valid to 0\n");
+		es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
+	}
+	spin_unlock(&sbi->s_lock);
+	ext2_sync_super(sb, es, wait);
+	return 0;
+}
 
-void ext2_write_super (struct super_block * sb)
+static int ext2_freeze(struct super_block *sb)
 {
-	struct ext2_super_block * es;
-	lock_kernel();
-	if (!(sb->s_flags & MS_RDONLY)) {
-		es = EXT2_SB(sb)->s_es;
-
-		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS) {
-			ext2_debug ("setting valid to 0\n");
-			es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) &
-						  ~EXT2_VALID_FS);
-			es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
-			es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
-			es->s_mtime = cpu_to_le32(get_seconds());
-			ext2_sync_super(sb, es);
-		} else
-			ext2_commit_super (sb, es);
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+	/*
+	 * Open but unlinked files present? Keep EXT2_VALID_FS flag cleared
+	 * because we have unattached inodes and thus filesystem is not fully
+	 * consistent.
+	 */
+	if (atomic_long_read(&sb->s_remove_count)) {
+		ext2_sync_fs(sb, 1);
+		return 0;
 	}
-	sb->s_dirt = 0;
-	unlock_kernel();
+	/* Set EXT2_FS_VALID flag */
+	spin_lock(&sbi->s_lock);
+	sbi->s_es->s_state = cpu_to_le16(sbi->s_mount_state);
+	spin_unlock(&sbi->s_lock);
+	ext2_sync_super(sb, sbi->s_es, 1);
+
+	return 0;
+}
+
+static int ext2_unfreeze(struct super_block *sb)
+{
+	/* Just write sb to clear EXT2_VALID_FS flag */
+	ext2_write_super(sb);
+
+	return 0;
+}
+
+void ext2_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		ext2_sync_fs(sb, 1);
 }
 
 static int ext2_remount (struct super_block * sb, int * flags, char * data)
@@ -1016,6 +1254,9 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	unsigned long old_sb_flags;
 	int err;
 
+	sync_filesystem(sb);
+	spin_lock(&sbi->s_lock);
+
 	/* Store the old options */
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
@@ -1025,7 +1266,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	/*
 	 * Allow the "check" option to be passed as a remount option.
 	 */
-	if (!parse_options (data, sbi)) {
+	if (!parse_options(data, sb)) {
 		err = -EINVAL;
 		goto restore_opts;
 	}
@@ -1033,31 +1274,57 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
+	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
+				    EXT2_MOUNT_XIP if not */
+
+	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
+		ext2_msg(sb, KERN_WARNING,
+			"warning: unsupported blocksize for xip");
+		err = -EINVAL;
+		goto restore_opts;
+	}
+
 	es = sbi->s_es;
-	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
-	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
-	    invalidate_inodes(sb))
-		ext2_warning(sb, __FUNCTION__, "busy inodes while remounting "\
-			     "xip remain in cache (no functional problem)");
-	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
+	if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) {
+		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
+			 "xip flag with busy inodes while remounting");
+		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
+		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
+	}
+	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
+		spin_unlock(&sbi->s_lock);
 		return 0;
+	}
 	if (*flags & MS_RDONLY) {
 		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
-		    !(sbi->s_mount_state & EXT2_VALID_FS))
+		    !(sbi->s_mount_state & EXT2_VALID_FS)) {
+			spin_unlock(&sbi->s_lock);
 			return 0;
+		}
+
 		/*
 		 * OK, we are remounting a valid rw partition rdonly, so set
 		 * the rdonly flag and then mark the partition as valid again.
 		 */
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 		es->s_mtime = cpu_to_le32(get_seconds());
+		spin_unlock(&sbi->s_lock);
+
+		err = dquot_suspend(sb, -1);
+		if (err < 0) {
+			spin_lock(&sbi->s_lock);
+			goto restore_opts;
+		}
+
+		ext2_sync_super(sb, es, 1);
 	} else {
 		__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
 					       ~EXT2_FEATURE_RO_COMPAT_SUPP);
 		if (ret) {
-			printk("EXT2-fs: %s: couldn't remount RDWR because of "
-			       "unsupported optional features (%x).\n",
-			       sb->s_id, le32_to_cpu(ret));
+			ext2_msg(sb, KERN_WARNING,
+				"warning: couldn't remount RDWR because of "
+				"unsupported optional features (%x).",
+				le32_to_cpu(ret));
 			err = -EROFS;
 			goto restore_opts;
 		}
@@ -1069,14 +1336,20 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 		sbi->s_mount_state = le16_to_cpu(es->s_state);
 		if (!ext2_setup_super (sb, es, 0))
 			sb->s_flags &= ~MS_RDONLY;
+		spin_unlock(&sbi->s_lock);
+
+		ext2_write_super(sb);
+
+		dquot_resume(sb, -1);
 	}
-	ext2_sync_super(sb, es);
+
 	return 0;
 restore_opts:
 	sbi->s_mount_opt = old_opts.s_mount_opt;
 	sbi->s_resuid = old_opts.s_resuid;
 	sbi->s_resgid = old_opts.s_resgid;
 	sb->s_flags = old_sb_flags;
+	spin_unlock(&sbi->s_lock);
 	return err;
 }
 
@@ -1084,21 +1357,28 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	unsigned long overhead;
-	int i;
+	struct ext2_super_block *es = sbi->s_es;
+	u64 fsid;
+
+	spin_lock(&sbi->s_lock);
 
 	if (test_opt (sb, MINIX_DF))
-		overhead = 0;
-	else {
+		sbi->s_overhead_last = 0;
+	else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
+		unsigned long i, overhead = 0;
+		smp_rmb();
+
 		/*
-		 * Compute the overhead (FS structures)
+		 * 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(sbi->s_es->s_first_data_block);
+		overhead = le32_to_cpu(es->s_first_data_block);
 
 		/*
 		 * Add the overhead attributed to the superblock and
@@ -1115,32 +1395,42 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
 		 */
 		overhead += (sbi->s_groups_count *
 			     (2 + sbi->s_itb_per_group));
+		sbi->s_overhead_last = overhead;
+		smp_wmb();
+		sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
 	}
 
 	buf->f_type = EXT2_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_blocks = le32_to_cpu(sbi->s_es->s_blocks_count) - overhead;
+	buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
 	buf->f_bfree = ext2_count_free_blocks(sb);
-	buf->f_bavail = buf->f_bfree - le32_to_cpu(sbi->s_es->s_r_blocks_count);
-	if (buf->f_bfree < le32_to_cpu(sbi->s_es->s_r_blocks_count))
+	es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
+	buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
+	if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
 		buf->f_bavail = 0;
-	buf->f_files = le32_to_cpu(sbi->s_es->s_inodes_count);
-	buf->f_ffree = ext2_count_free_inodes (sb);
+	buf->f_files = le32_to_cpu(es->s_inodes_count);
+	buf->f_ffree = ext2_count_free_inodes(sb);
+	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
 	buf->f_namelen = EXT2_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;
+	spin_unlock(&sbi->s_lock);
 	return 0;
 }
 
-static int ext2_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *ext2_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, ext2_fill_super, mnt);
+	return mount_bdev(fs_type, flags, dev_name, data, ext2_fill_super);
 }
 
 #ifdef CONFIG_QUOTA
 
 /* 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 noone else should touch the files)
+ * itself serializes the operations (and no one else should touch the files)
  * we don't have to be afraid of races */
 static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off)
@@ -1165,8 +1455,9 @@ static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
 				sb->s_blocksize - offset : toread;
 
 		tmp_bh.b_state = 0;
+		tmp_bh.b_size = sb->s_blocksize;
 		err = ext2_get_block(inode, blk, &tmp_bh, 0);
-		if (err)
+		if (err < 0)
 			return err;
 		if (!buffer_mapped(&tmp_bh))	/* A hole? */
 			memset(data, 0, tocopy);
@@ -1198,20 +1489,20 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
 	struct buffer_head tmp_bh;
 	struct buffer_head *bh;
 
-	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
 	while (towrite > 0) {
 		tocopy = sb->s_blocksize - offset < towrite ?
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
+		tmp_bh.b_size = sb->s_blocksize;
 		err = ext2_get_block(inode, blk, &tmp_bh, 1);
-		if (err)
+		if (err < 0)
 			goto out;
 		if (offset || tocopy != EXT2_BLOCK_SIZE(sb))
 			bh = sb_bread(sb, tmp_bh.b_blocknr);
 		else
 			bh = sb_getblk(sb, tmp_bh.b_blocknr);
-		if (!bh) {
+		if (unlikely(!bh)) {
 			err = -EIO;
 			goto out;
 		}
@@ -1235,7 +1526,6 @@ out:
 	inode->i_version++;
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(inode);
-	mutex_unlock(&inode->i_mutex);
 	return len - towrite;
 }
 
@@ -1244,10 +1534,11 @@ out:
 static struct file_system_type ext2_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "ext2",
-	.get_sb		= ext2_get_sb,
+	.mount		= ext2_mount,
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ext2");
 
 static int __init init_ext2_fs(void)
 {
@@ -1275,5 +1566,8 @@ static void __exit exit_ext2_fs(void)
 	exit_ext2_xattr();
 }
 
+MODULE_AUTHOR("Remy Card and others");
+MODULE_DESCRIPTION("Second Extended Filesystem");
+MODULE_LICENSE("GPL");
 module_init(init_ext2_fs)
 module_exit(exit_ext2_fs)
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index 1e67d87cfa9..565cf817bbf 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -28,10 +28,11 @@ static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
 	return NULL;
 }
 
-struct inode_operations ext2_symlink_inode_operations = {
+const struct inode_operations ext2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
+	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -40,9 +41,10 @@ struct inode_operations ext2_symlink_inode_operations = {
 #endif
 };
  
-struct inode_operations ext2_fast_symlink_inode_operations = {
+const struct inode_operations ext2_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= ext2_follow_link,
+	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index af52a7f8b29..91426141c33 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -35,7 +35,7 @@
  *   +------------------+
  *
  * The block header is followed by multiple entry descriptors. These entry
- * descriptors are variable in size, and alligned to EXT2_XATTR_PAD
+ * descriptors are variable in size, and aligned to EXT2_XATTR_PAD
  * byte boundaries. The entry descriptors are sorted by attribute name,
  * so that two extended attribute blocks can be compared efficiently.
  *
@@ -54,12 +54,12 @@
  */
 
 #include <linux/buffer_head.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mbcache.h>
 #include <linux/quotaops.h>
 #include <linux/rwsem.h>
+#include <linux/security.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
@@ -100,11 +100,11 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *,
 
 static struct mb_cache *ext2_xattr_cache;
 
-static struct xattr_handler *ext2_xattr_handler_map[] = {
+static const struct xattr_handler *ext2_xattr_handler_map[] = {
 	[EXT2_XATTR_INDEX_USER]		     = &ext2_xattr_user_handler,
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
-	[EXT2_XATTR_INDEX_POSIX_ACL_ACCESS]  = &ext2_xattr_acl_access_handler,
-	[EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext2_xattr_acl_default_handler,
+	[EXT2_XATTR_INDEX_POSIX_ACL_ACCESS]  = &posix_acl_access_xattr_handler,
+	[EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
 #endif
 	[EXT2_XATTR_INDEX_TRUSTED]	     = &ext2_xattr_trusted_handler,
 #ifdef CONFIG_EXT2_FS_SECURITY
@@ -112,12 +112,12 @@ static struct xattr_handler *ext2_xattr_handler_map[] = {
 #endif
 };
 
-struct xattr_handler *ext2_xattr_handlers[] = {
+const struct xattr_handler *ext2_xattr_handlers[] = {
 	&ext2_xattr_user_handler,
 	&ext2_xattr_trusted_handler,
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
-	&ext2_xattr_acl_access_handler,
-	&ext2_xattr_acl_default_handler,
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
 #endif
 #ifdef CONFIG_EXT2_FS_SECURITY
 	&ext2_xattr_security_handler,
@@ -125,10 +125,10 @@ struct xattr_handler *ext2_xattr_handlers[] = {
 	NULL
 };
 
-static inline struct xattr_handler *
+static inline const struct xattr_handler *
 ext2_xattr_handler(int name_index)
 {
-	struct xattr_handler *handler = NULL;
+	const struct xattr_handler *handler = NULL;
 
 	if (name_index > 0 && name_index < ARRAY_SIZE(ext2_xattr_handler_map))
 		handler = ext2_xattr_handler_map[name_index];
@@ -160,6 +160,10 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
 
 	if (name == NULL)
 		return -EINVAL;
+	name_len = strlen(name);
+	if (name_len > 255)
+		return -ERANGE;
+
 	down_read(&EXT2_I(inode)->xattr_sem);
 	error = -ENODATA;
 	if (!EXT2_I(inode)->i_file_acl)
@@ -180,12 +184,8 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 		error = -EIO;
 		goto cleanup;
 	}
-	/* find named attribute */
-	name_len = strlen(name);
 
-	error = -ERANGE;
-	if (name_len > 255)
-		goto cleanup;
+	/* find named attribute */
 	entry = FIRST_ENTRY(bh);
 	while (!IS_LAST_ENTRY(entry)) {
 		struct ext2_xattr_entry *next =
@@ -198,14 +198,6 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 			goto found;
 		entry = next;
 	}
-	/* Check the remaining name entries */
-	while (!IS_LAST_ENTRY(entry)) {
-		struct ext2_xattr_entry *next =
-			EXT2_XATTR_NEXT(entry);
-		if ((char *)next >= end)
-			goto bad_block;
-		entry = next;
-	}
 	if (ext2_xattr_cache_insert(bh))
 		ea_idebug(inode, "cache insert failed");
 	error = -ENODATA;
@@ -249,8 +241,9 @@ cleanup:
  * used / required on success.
  */
 static int
-ext2_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
+	struct inode *inode = dentry->d_inode;
 	struct buffer_head *bh = NULL;
 	struct ext2_xattr_entry *entry;
 	char *end;
@@ -296,13 +289,14 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 	/* list the attribute names */
 	for (entry = FIRST_ENTRY(bh); !IS_LAST_ENTRY(entry);
 	     entry = EXT2_XATTR_NEXT(entry)) {
-		struct xattr_handler *handler =
+		const struct xattr_handler *handler =
 			ext2_xattr_handler(entry->e_name_index);
 
 		if (handler) {
-			size_t size = handler->list(inode, buffer, rest,
+			size_t size = handler->list(dentry, buffer, rest,
 						    entry->e_name,
-						    entry->e_name_len);
+						    entry->e_name_len,
+						    handler->flags);
 			if (buffer) {
 				if (size > rest) {
 					error = -ERANGE;
@@ -330,7 +324,7 @@ cleanup:
 ssize_t
 ext2_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
-	return ext2_xattr_list(dentry->d_inode, buffer, size);
+	return ext2_xattr_list(dentry, buffer, size);
 }
 
 /*
@@ -342,18 +336,16 @@ static void ext2_xattr_update_super_block(struct super_block *sb)
 	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR))
 		return;
 
-	lock_super(sb);
-	EXT2_SB(sb)->s_es->s_feature_compat |=
-		cpu_to_le32(EXT2_FEATURE_COMPAT_EXT_ATTR);
-	sb->s_dirt = 1;
+	spin_lock(&EXT2_SB(sb)->s_lock);
+	EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR);
+	spin_unlock(&EXT2_SB(sb)->s_lock);
 	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
-	unlock_super(sb);
 }
 
 /*
  * ext2_xattr_set()
  *
- * Create, replace or remove an extended attribute for this inode. Buffer
+ * 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
@@ -644,13 +636,12 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 				   the inode.  */
 				ea_bdebug(new_bh, "reusing block");
 
-				error = -EDQUOT;
-				if (DQUOT_ALLOC_BLOCK(inode, 1)) {
+				error = dquot_alloc_block(inode, 1);
+				if (error) {
 					unlock_buffer(new_bh);
 					goto cleanup;
 				}
-				HDR(new_bh)->h_refcount = cpu_to_le32(1 +
-					le32_to_cpu(HDR(new_bh)->h_refcount));
+				le32_add_cpu(&HDR(new_bh)->h_refcount, 1);
 				ea_bdebug(new_bh, "refcount now=%d",
 					le32_to_cpu(HDR(new_bh)->h_refcount));
 			}
@@ -663,20 +654,18 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			ext2_xattr_cache_insert(new_bh);
 		} else {
 			/* We need to allocate a new block */
-			int goal = le32_to_cpu(EXT2_SB(sb)->s_es->
-						           s_first_data_block) +
-				   EXT2_I(inode)->i_block_group *
-				   EXT2_BLOCKS_PER_GROUP(sb);
-			int block = ext2_new_block(inode, goal,
-						   NULL, NULL, &error);
+			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
+						EXT2_I(inode)->i_block_group);
+			int block = ext2_new_block(inode, goal, &error);
 			if (error)
 				goto cleanup;
 			ea_idebug(inode, "creating block %d", block);
 
 			new_bh = sb_getblk(sb, block);
-			if (!new_bh) {
+			if (unlikely(!new_bh)) {
 				ext2_free_blocks(inode, block, 1);
-				error = -EIO;
+				mark_inode_dirty(inode);
+				error = -ENOMEM;
 				goto cleanup;
 			}
 			lock_buffer(new_bh);
@@ -700,13 +689,15 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	EXT2_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
 	inode->i_ctime = CURRENT_TIME_SEC;
 	if (IS_SYNC(inode)) {
-		error = ext2_sync_inode (inode);
+		error = sync_inode_metadata(inode, 1);
 		/* In case sync failed due to ENOSPC the inode was actually
 		 * written (only some dirty data were not) so we just proceed
 		 * as if nothing happened and cleanup the unused block */
 		if (error && error != -ENOSPC) {
-			if (new_bh && new_bh != old_bh)
-				DQUOT_FREE_BLOCK(inode, 1);
+			if (new_bh && new_bh != old_bh) {
+				dquot_free_block_nodirty(inode, 1);
+				mark_inode_dirty(inode);
+			}
 			goto cleanup;
 		}
 	} else
@@ -729,17 +720,18 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 				mb_cache_entry_free(ce);
 			ea_bdebug(old_bh, "freeing");
 			ext2_free_blocks(inode, old_bh->b_blocknr, 1);
+			mark_inode_dirty(inode);
 			/* We let our caller release old_bh, so we
 			 * need to duplicate the buffer before. */
 			get_bh(old_bh);
 			bforget(old_bh);
 		} else {
 			/* Decrement the refcount only. */
-			HDR(old_bh)->h_refcount = cpu_to_le32(
-				le32_to_cpu(HDR(old_bh)->h_refcount) - 1);
+			le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
 			if (ce)
 				mb_cache_entry_release(ce);
-			DQUOT_FREE_BLOCK(inode, 1);
+			dquot_free_block_nodirty(inode, 1);
+			mark_inode_dirty(inode);
 			mark_buffer_dirty(old_bh);
 			ea_bdebug(old_bh, "refcount now=%d",
 				le32_to_cpu(HDR(old_bh)->h_refcount));
@@ -793,8 +785,7 @@ ext2_xattr_delete_inode(struct inode *inode)
 		bforget(bh);
 		unlock_buffer(bh);
 	} else {
-		HDR(bh)->h_refcount = cpu_to_le32(
-			le32_to_cpu(HDR(bh)->h_refcount) - 1);
+		le32_add_cpu(&HDR(bh)->h_refcount, -1);
 		if (ce)
 			mb_cache_entry_release(ce);
 		ea_bdebug(bh, "refcount now=%d",
@@ -803,7 +794,7 @@ ext2_xattr_delete_inode(struct inode *inode)
 		mark_buffer_dirty(bh);
 		if (IS_SYNC(inode))
 			sync_dirty_buffer(bh);
-		DQUOT_FREE_BLOCK(inode, 1);
+		dquot_free_block_nodirty(inode, 1);
 	}
 	EXT2_I(inode)->i_file_acl = 0;
 
@@ -839,10 +830,10 @@ ext2_xattr_cache_insert(struct buffer_head *bh)
 	struct mb_cache_entry *ce;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext2_xattr_cache);
+	ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS);
 	if (!ce)
 		return -ENOMEM;
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, &hash);
+	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
 	if (error) {
 		mb_cache_entry_free(ce);
 		if (error == -EBUSY) {
@@ -916,8 +907,8 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext2_xattr_cache, 0,
-				       inode->i_sb->s_bdev, hash);
+	ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev,
+				       hash);
 	while (ce) {
 		struct buffer_head *bh;
 
@@ -949,7 +940,7 @@ again:
 			unlock_buffer(bh);
 			brelse(bh);
 		}
-		ce = mb_cache_entry_find_next(ce, 0, inode->i_sb->s_bdev, hash);
+		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
 	}
 	return NULL;
 }
@@ -1025,9 +1016,7 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *header,
 int __init
 init_ext2_xattr(void)
 {
-	ext2_xattr_cache = mb_cache_create("ext2_xattr", NULL,
-		sizeof(struct mb_cache_entry) +
-		sizeof(((struct mb_cache_entry *) 0)->e_indexes[0]), 1, 6);
+	ext2_xattr_cache = mb_cache_create("ext2_xattr", 6);
 	if (!ext2_xattr_cache)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h
index bf8175b2ced..60edf298644 100644
--- a/fs/ext2/xattr.h
+++ b/fs/ext2/xattr.h
@@ -55,11 +55,9 @@ struct ext2_xattr_entry {
 
 # ifdef CONFIG_EXT2_FS_XATTR
 
-extern struct xattr_handler ext2_xattr_user_handler;
-extern struct xattr_handler ext2_xattr_trusted_handler;
-extern struct xattr_handler ext2_xattr_acl_access_handler;
-extern struct xattr_handler ext2_xattr_acl_default_handler;
-extern struct xattr_handler ext2_xattr_security_handler;
+extern const struct xattr_handler ext2_xattr_user_handler;
+extern const struct xattr_handler ext2_xattr_trusted_handler;
+extern const struct xattr_handler ext2_xattr_security_handler;
 
 extern ssize_t ext2_listxattr(struct dentry *, char *, size_t);
 
@@ -72,7 +70,7 @@ extern void ext2_xattr_put_super(struct super_block *);
 extern int init_ext2_xattr(void);
 extern void exit_ext2_xattr(void);
 
-extern struct xattr_handler *ext2_xattr_handlers[];
+extern const struct xattr_handler *ext2_xattr_handlers[];
 
 # else  /* CONFIG_EXT2_FS_XATTR */
 
@@ -116,9 +114,11 @@ exit_ext2_xattr(void)
 # endif  /* CONFIG_EXT2_FS_XATTR */
 
 #ifdef CONFIG_EXT2_FS_SECURITY
-extern int ext2_init_security(struct inode *inode, struct inode *dir);
+extern int ext2_init_security(struct inode *inode, struct inode *dir,
+			      const struct qstr *qstr);
 #else
-static inline int ext2_init_security(struct inode *inode, struct inode *dir)
+static inline int ext2_init_security(struct inode *inode, struct inode *dir,
+				     const struct qstr *qstr)
 {
 	return 0;
 }
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index a2661279847..c0ebc4db884 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -3,19 +3,15 @@
  * Handler for storing security labels as extended attributes.
  */
 
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/smp_lock.h>
-#include <linux/ext2_fs.h>
+#include "ext2.h"
 #include <linux/security.h>
 #include "xattr.h"
 
 static size_t
-ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
-			 const char *name, size_t name_len)
+ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+			 const char *name, size_t name_len, int type)
 {
-	const int prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+	const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
 	if (list && total_len <= list_size) {
@@ -27,47 +23,50 @@ ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
 }
 
 static int
-ext2_xattr_security_get(struct inode *inode, const char *name,
-		       void *buffer, size_t size)
+ext2_xattr_security_get(struct dentry *dentry, const char *name,
+		       void *buffer, size_t size, int type)
 {
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
-	return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name,
+	return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
 			      buffer, size);
 }
 
 static int
-ext2_xattr_security_set(struct inode *inode, const char *name,
-		       const void *value, size_t size, int flags)
+ext2_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 ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
+	return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
 			      value, size, flags);
 }
 
-int
-ext2_init_security(struct inode *inode, struct inode *dir)
+static int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+			   void *fs_info)
 {
-	int err;
-	size_t len;
-	void *value;
-	char *name;
+	const struct xattr *xattr;
+	int err = 0;
 
-	err = security_inode_init_security(inode, dir, &name, &value, &len);
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			return 0;
-		return err;
+	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+		err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY,
+				     xattr->name, xattr->value,
+				     xattr->value_len, 0);
+		if (err < 0)
+			break;
 	}
-	err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY,
-			     name, value, len, 0);
-	kfree(name);
-	kfree(value);
 	return err;
 }
 
-struct xattr_handler ext2_xattr_security_handler = {
+int
+ext2_init_security(struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
+{
+	return security_inode_init_security(inode, dir, qstr,
+					    &ext2_initxattrs, NULL);
+}
+
+const struct xattr_handler ext2_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
 	.list	= ext2_xattr_security_list,
 	.get	= ext2_xattr_security_get,
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index f28a6a499c9..7e192574c00 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -5,21 +5,14 @@
  * 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 <linux/smp_lock.h>
-#include <linux/ext2_fs.h>
+#include "ext2.h"
 #include "xattr.h"
 
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static size_t
-ext2_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
-			const char *name, size_t name_len)
+ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+		const char *name, size_t name_len, int type)
 {
-	const int prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+	const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -34,26 +27,26 @@ ext2_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
 }
 
 static int
-ext2_xattr_trusted_get(struct inode *inode, const char *name,
-		       void *buffer, size_t size)
+ext2_xattr_trusted_get(struct dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
 {
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
-	return ext2_xattr_get(inode, EXT2_XATTR_INDEX_TRUSTED, name,
+	return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
 			      buffer, size);
 }
 
 static int
-ext2_xattr_trusted_set(struct inode *inode, const char *name,
-		       const void *value, size_t size, int flags)
+ext2_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 ext2_xattr_set(inode, EXT2_XATTR_INDEX_TRUSTED, name,
+	return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
 			      value, size, flags);
 }
 
-struct xattr_handler ext2_xattr_trusted_handler = {
+const struct xattr_handler ext2_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
 	.list	= ext2_xattr_trusted_list,
 	.get	= ext2_xattr_trusted_get,
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index f383e7c3a7b..f470e44c4b8 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -6,21 +6,18 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/string.h>
 #include "ext2.h"
 #include "xattr.h"
 
-#define XATTR_USER_PREFIX "user."
-
 static size_t
-ext2_xattr_user_list(struct inode *inode, char *list, size_t list_size,
-		     const char *name, size_t name_len)
+ext2_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 = sizeof(XATTR_USER_PREFIX)-1;
+	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
-	if (!test_opt(inode->i_sb, XATTR_USER))
+	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return 0;
 
 	if (list && total_len <= list_size) {
@@ -32,30 +29,31 @@ ext2_xattr_user_list(struct inode *inode, char *list, size_t list_size,
 }
 
 static int
-ext2_xattr_user_get(struct inode *inode, const char *name,
-		    void *buffer, size_t size)
+ext2_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(inode->i_sb, XATTR_USER))
+	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
-	return ext2_xattr_get(inode, EXT2_XATTR_INDEX_USER, name, buffer, size);
+	return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+			      name, buffer, size);
 }
 
 static int
-ext2_xattr_user_set(struct inode *inode, const char *name,
-		    const void *value, size_t size, int flags)
+ext2_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(inode->i_sb, XATTR_USER))
+	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 
-	return ext2_xattr_set(inode, EXT2_XATTR_INDEX_USER, name,
-			      value, size, flags);
+	return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+			      name, value, size, flags);
 }
 
-struct xattr_handler ext2_xattr_user_handler = {
+const struct xattr_handler ext2_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
 	.list	= ext2_xattr_user_list,
 	.get	= ext2_xattr_user_get,
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index ca7f0031238..e98171a11cf 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -9,30 +9,34 @@
 #include <linux/fs.h>
 #include <linux/genhd.h>
 #include <linux/buffer_head.h>
-#include <linux/ext2_fs_sb.h>
-#include <linux/ext2_fs.h>
+#include <linux/blkdev.h>
 #include "ext2.h"
 #include "xip.h"
 
 static inline int
-__inode_direct_access(struct inode *inode, sector_t sector,
-		      unsigned long *data)
+__inode_direct_access(struct inode *inode, sector_t block,
+		      void **kaddr, unsigned long *pfn)
 {
-	BUG_ON(!inode->i_sb->s_bdev->bd_disk->fops->direct_access);
-	return inode->i_sb->s_bdev->bd_disk->fops
-		->direct_access(inode->i_sb->s_bdev,sector,data);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	sector_t sector;
+
+	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
+
+	BUG_ON(!ops->direct_access);
+	return ops->direct_access(bdev, sector, kaddr, pfn);
 }
 
 static inline int
-__ext2_get_sector(struct inode *inode, sector_t offset, int create,
+__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
 		   sector_t *result)
 {
 	struct buffer_head tmp;
 	int rc;
 
 	memset(&tmp, 0, sizeof(struct buffer_head));
-	rc = ext2_get_block(inode, offset/ (PAGE_SIZE/512), &tmp,
-			    create);
+	tmp.b_size = 1 << inode->i_blkbits;
+	rc = ext2_get_block(inode, pgoff, &tmp, create);
 	*result = tmp.b_blocknr;
 
 	/* did we get a sparse block (hole in the file)? */
@@ -45,15 +49,15 @@ __ext2_get_sector(struct inode *inode, sector_t offset, int create,
 }
 
 int
-ext2_clear_xip_target(struct inode *inode, int block)
+ext2_clear_xip_target(struct inode *inode, sector_t block)
 {
-	sector_t sector = block * (PAGE_SIZE/512);
-	unsigned long data;
+	void *kaddr;
+	unsigned long pfn;
 	int rc;
 
-	rc = __inode_direct_access(inode, sector, &data);
+	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
 	if (!rc)
-		clear_page((void*)data);
+		clear_page(kaddr);
 	return rc;
 }
 
@@ -64,30 +68,24 @@ void ext2_xip_verify_sb(struct super_block *sb)
 	if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
 	    !sb->s_bdev->bd_disk->fops->direct_access) {
 		sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
-		ext2_warning(sb, __FUNCTION__,
-			     "ignoring xip option - not supported by bdev");
+		ext2_msg(sb, KERN_WARNING,
+			     "warning: ignoring xip option - "
+			     "not supported by bdev");
 	}
 }
 
-struct page *
-ext2_get_xip_page(struct address_space *mapping, sector_t offset,
-		   int create)
+int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
+				void **kmem, unsigned long *pfn)
 {
 	int rc;
-	unsigned long data;
-	sector_t sector;
+	sector_t block;
 
 	/* first, retrieve the sector number */
-	rc = __ext2_get_sector(mapping->host, offset, create, &sector);
+	rc = __ext2_get_block(mapping->host, pgoff, create, &block);
 	if (rc)
-		goto error;
+		return rc;
 
 	/* retrieve address of the target data */
-	rc = __inode_direct_access
-		(mapping->host, sector * (PAGE_SIZE/512), &data);
-	if (!rc)
-		return virt_to_page(data);
-
- error:
-	return ERR_PTR(rc);
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
+	return rc;
 }
diff --git a/fs/ext2/xip.h b/fs/ext2/xip.h
index aa85331d6c5..18b34d2f31b 100644
--- a/fs/ext2/xip.h
+++ b/fs/ext2/xip.h
@@ -7,19 +7,20 @@
 
 #ifdef CONFIG_EXT2_FS_XIP
 extern void ext2_xip_verify_sb (struct super_block *);
-extern int ext2_clear_xip_target (struct inode *, int);
+extern int ext2_clear_xip_target (struct inode *, sector_t);
 
 static inline int ext2_use_xip (struct super_block *sb)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
 }
-struct page* ext2_get_xip_page (struct address_space *, sector_t, int);
-#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_page)
+int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
+				void **, unsigned long *);
+#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
 #else
 #define mapping_is_xip(map)			0
 #define ext2_xip_verify_sb(sb)			do { } while (0)
 #define ext2_use_xip(sb)			0
 #define ext2_clear_xip_target(inode, chain)	0
-#define ext2_get_xip_page			NULL
+#define ext2_get_xip_mem			NULL
 #endif