Merge branch 'for-linus' of git://git.open-osd.org/linux-open-osd

* 'for-linus' of git://git.open-osd.org/linux-open-osd:
  fs: Add exofs to Kernel build
  exofs: Documentation
  exofs: export_operations
  exofs: super_operations and file_system_type
  exofs: dir_inode and directory operations
  exofs: address_space_operations
  exofs: symlink_inode and fast_symlink_inode operations
  exofs: file and file_inode operations
  exofs: Kbuild, Headers and osd utils

15 files changed, 3773 insertions, 0 deletions

diff --git a/Documentation/filesystems/exofs.txt b/Documentation/filesystems/exofs.txt
new file mode 100644
index 00000000000..0ced74c2f73
--- /dev/null
+++ b/Documentation/filesystems/exofs.txt
@@ -0,0 +1,176 @@
+===============================================================================
+WHAT IS EXOFS?
+===============================================================================
+
+exofs is a file system that uses an OSD and exports the API of a normal Linux
+file system. Users access exofs like any other local file system, and exofs
+will in turn issue commands to the local OSD initiator.
+
+OSD is a new T10 command set that views storage devices not as a large/flat
+array of sectors but as a container of objects, each having a length, quota,
+time attributes and more. Each object is addressed by a 64bit ID, and is
+contained in a 64bit ID partition. Each object has associated attributes
+attached to it, which are integral part of the object and provide metadata about
+the object. The standard defines some common obligatory attributes, but user
+attributes can be added as needed.
+
+===============================================================================
+ENVIRONMENT
+===============================================================================
+
+To use this file system, you need to have an object store to run it on.  You
+may download a target from:
+http://open-osd.org
+
+See Documentation/scsi/osd.txt for how to setup a working osd environment.
+
+===============================================================================
+USAGE
+===============================================================================
+
+1. Download and compile exofs and open-osd initiator:
+  You need an external Kernel source tree or kernel headers from your
+  distribution. (anything based on 2.6.26 or later).
+
+  a. download open-osd including exofs source using:
+     [parent-directory]$ git clone git://git.open-osd.org/open-osd.git
+
+  b. Build the library module like this:
+     [parent-directory]$ make -C KSRC=$(KER_DIR) open-osd
+
+     This will build both the open-osd initiator as well as the exofs kernel
+     module. Use whatever parameters you compiled your Kernel with and
+     $(KER_DIR) above pointing to the Kernel you compile against. See the file
+     open-osd/top-level-Makefile for an example.
+
+2. Get the OSD initiator and target set up properly, and login to the target.
+  See Documentation/scsi/osd.txt for farther instructions. Also see ./do-osd
+  for example script that does all these steps.
+
+3. Insmod the exofs.ko module:
+   [exofs]$ insmod exofs.ko
+
+4. Make sure the directory where you want to mount exists. If not, create it.
+   (For example, mkdir /mnt/exofs)
+
+5. At first run you will need to invoke the mkfs.exofs application
+
+   As an example, this will create the file system on:
+   /dev/osd0 partition ID 65536
+
+   mkfs.exofs --pid=65536 --format /dev/osd0
+
+   The --format is optional if not specified no OSD_FORMAT will be
+   preformed and a clean file system will be created in the specified pid,
+   in the available space of the target. (Use --format=size_in_meg to limit
+   the total LUN space available)
+
+   If pid already exist it will be deleted and a new one will be created in it's
+   place. Be careful.
+
+   An exofs lives inside a single OSD partition. You can create multiple exofs
+   filesystems on the same device using multiple pids.
+
+   (run mkfs.exofs without any parameters for usage help message)
+
+6. Mount the file system.
+
+   For example, to mount /dev/osd0, partition ID 0x10000 on /mnt/exofs:
+
+	mount -t exofs -o pid=65536 /dev/osd0 /mnt/exofs/
+
+7. For reference (See do-exofs example script):
+	do-exofs start - an example of how to perform the above steps.
+	do-exofs stop -  an example of how to unmount the file system.
+	do-exofs format - an example of how to format and mkfs a new exofs.
+
+8. Extra compilation flags (uncomment in fs/exofs/Kbuild):
+	CONFIG_EXOFS_DEBUG - for debug messages and extra checks.
+
+===============================================================================
+exofs mount options
+===============================================================================
+Similar to any mount command:
+	mount -t exofs -o exofs_options /dev/osdX mount_exofs_directory
+
+Where:
+    -t exofs: specifies the exofs file system
+
+    /dev/osdX: X is a decimal number. /dev/osdX was created after a successful
+               login into an OSD target.
+
+    mount_exofs_directory: The directory to mount the file system on
+
+    exofs specific options: Options are separated by commas (,)
+		pid=<integer> - The partition number to mount/create as
+                                container of the filesystem.
+                                This option is mandatory
+                to=<integer>  - Timeout in ticks for a single command
+                                default is (60 * HZ) [for debugging only]
+
+===============================================================================
+DESIGN
+===============================================================================
+
+* The file system control block (AKA on-disk superblock) resides in an object
+  with a special ID (defined in common.h).
+  Information included in the file system control block is used to fill the
+  in-memory superblock structure at mount time. This object is created before
+  the file system is used by mkexofs.c It contains information such as:
+	- The file system's magic number
+	- The next inode number to be allocated
+
+* Each file resides in its own object and contains the data (and it will be
+  possible to extend the file over multiple objects, though this has not been
+  implemented yet).
+
+* A directory is treated as a file, and essentially contains a list of <file
+  name, inode #> pairs for files that are found in that directory. The object
+  IDs correspond to the files' inode numbers and will be allocated according to
+  a bitmap (stored in a separate object). Now they are allocated using a
+  counter.
+
+* Each file's control block (AKA on-disk inode) is stored in its object's
+  attributes. This applies to both regular files and other types (directories,
+  device files, symlinks, etc.).
+
+* Credentials are generated per object (inode and superblock) when they is
+  created in memory (read off disk or created). The credential works for all
+  operations and is used as long as the object remains in memory.
+
+* Async OSD operations are used whenever possible, but the target may execute
+  them out of order. The operations that concern us are create, delete,
+  readpage, writepage, update_inode, and truncate. The following pairs of
+  operations should execute in the order written, and we need to prevent them
+  from executing in reverse order:
+	- The following are handled with the OBJ_CREATED and OBJ_2BCREATED
+	  flags. OBJ_CREATED is set when we know the object exists on the OSD -
+	  in create's callback function, and when we successfully do a read_inode.
+	  OBJ_2BCREATED is set in the beginning of the create function, so we
+	  know that we should wait.
+		- create/delete: delete should wait until the object is created
+		  on the OSD.
+		- create/readpage: readpage should be able to return a page
+		  full of zeroes in this case. If there was a write already
+		  en-route (i.e. create, writepage, readpage) then the page
+		  would be locked, and so it would really be the same as
+		  create/writepage.
+		- create/writepage: if writepage is called for a sync write, it
+		  should wait until the object is created on the OSD.
+		  Otherwise, it should just return.
+		- create/truncate: truncate should wait until the object is
+		  created on the OSD.
+		- create/update_inode: update_inode should wait until the
+		  object is created on the OSD.
+	- Handled by VFS locks:
+		- readpage/delete: shouldn't happen because of page lock.
+		- writepage/delete: shouldn't happen because of page lock.
+		- readpage/writepage: shouldn't happen because of page lock.
+
+===============================================================================
+LICENSE/COPYRIGHT
+===============================================================================
+The exofs file system is based on ext2 v0.5b (distributed with the Linux kernel
+version 2.6.10).  All files include the original copyrights, and the license
+is GPL version 2 (only version 2, as is true for the Linux kernel).  The
+Linux kernel can be downloaded from www.kernel.org.
diff --git a/fs/Kconfig b/fs/Kconfig
index cef8b18ceaa..ae3b34a2ea6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -169,6 +169,8 @@ source "fs/romfs/Kconfig"
 source "fs/sysv/Kconfig"
 source "fs/ufs/Kconfig"
 
+source "fs/exofs/Kconfig"
+
 endif # MISC_FILESYSTEMS
 
 menuconfig NETWORK_FILESYSTEMS
diff --git a/fs/Makefile b/fs/Makefile
index b5cd8e18dd9..15f73014a20 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -120,3 +120,4 @@ obj-$(CONFIG_DEBUG_FS)		+= debugfs/
 obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_BTRFS_FS)		+= btrfs/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
+obj-$(CONFIG_EXOFS_FS)          += exofs/
diff --git a/fs/exofs/BUGS b/fs/exofs/BUGS
new file mode 100644
index 00000000000..1b2d4c63a57
--- /dev/null
+++ b/fs/exofs/BUGS
@@ -0,0 +1,3 @@
+- Out-of-space may cause a severe problem if the object (and directory entry)
+  were written, but the inode attributes failed. Then if the filesystem was
+  unmounted and mounted the kernel can get into an endless loop doing a readdir.
diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild
new file mode 100644
index 00000000000..cc2d22db119
--- /dev/null
+++ b/fs/exofs/Kbuild
@@ -0,0 +1,16 @@
+#
+# Kbuild for the EXOFS module
+#
+# Copyright (C) 2008 Panasas Inc.  All rights reserved.
+#
+# Authors:
+#   Boaz Harrosh <bharrosh@panasas.com>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2
+#
+# Kbuild - Gets included from the Kernels Makefile and build system
+#
+
+exofs-y := osd.o inode.o file.o symlink.o namei.o dir.o super.o
+obj-$(CONFIG_EXOFS_FS) += exofs.o
diff --git a/fs/exofs/Kconfig b/fs/exofs/Kconfig
new file mode 100644
index 00000000000..86194b2f799
--- /dev/null
+++ b/fs/exofs/Kconfig
@@ -0,0 +1,13 @@
+config EXOFS_FS
+	tristate "exofs: OSD based file system support"
+	depends on SCSI_OSD_ULD
+	help
+	  EXOFS is a file system that uses an OSD storage device,
+	  as its backing storage.
+
+# Debugging-related stuff
+config EXOFS_DEBUG
+	bool "Enable debugging"
+	depends on EXOFS_FS
+	help
+	  This option enables EXOFS debug prints.
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
new file mode 100644
index 00000000000..b1512c4bb8c
--- /dev/null
+++ b/fs/exofs/common.h
@@ -0,0 +1,184 @@
+/*
+ * common.h - Common definitions for both Kernel and user-mode utilities
+ *
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#ifndef __EXOFS_COM_H__
+#define __EXOFS_COM_H__
+
+#include <linux/types.h>
+
+#include <scsi/osd_attributes.h>
+#include <scsi/osd_initiator.h>
+#include <scsi/osd_sec.h>
+
+/****************************************************************************
+ * Object ID related defines
+ * NOTE: inode# = object ID - EXOFS_OBJ_OFF
+ ****************************************************************************/
+#define EXOFS_MIN_PID   0x10000	/* Smallest partition ID */
+#define EXOFS_OBJ_OFF	0x10000	/* offset for objects */
+#define EXOFS_SUPER_ID	0x10000	/* object ID for on-disk superblock */
+#define EXOFS_ROOT_ID	0x10002	/* object ID for root directory */
+
+/* exofs Application specific page/attribute */
+# define EXOFS_APAGE_FS_DATA	(OSD_APAGE_APP_DEFINED_FIRST + 3)
+# define EXOFS_ATTR_INODE_DATA	1
+
+/*
+ * The maximum number of files we can have is limited by the size of the
+ * inode number.  This is the largest object ID that the file system supports.
+ * Object IDs 0, 1, and 2 are always in use (see above defines).
+ */
+enum {
+	EXOFS_MAX_INO_ID = (sizeof(ino_t) * 8 == 64) ? ULLONG_MAX :
+					(1ULL << (sizeof(ino_t) * 8ULL - 1ULL)),
+	EXOFS_MAX_ID	 = (EXOFS_MAX_INO_ID - 1 - EXOFS_OBJ_OFF),
+};
+
+/****************************************************************************
+ * Misc.
+ ****************************************************************************/
+#define EXOFS_BLKSHIFT	12
+#define EXOFS_BLKSIZE	(1UL << EXOFS_BLKSHIFT)
+
+/****************************************************************************
+ * superblock-related things
+ ****************************************************************************/
+#define EXOFS_SUPER_MAGIC	0x5DF5
+
+/*
+ * The file system control block - stored in an object's data (mainly, the one
+ * with ID EXOFS_SUPER_ID).  This is where the in-memory superblock is stored
+ * on disk.  Right now it just has a magic value, which is basically a sanity
+ * check on our ability to communicate with the object store.
+ */
+struct exofs_fscb {
+	__le64  s_nextid;	/* Highest object ID used */
+	__le32  s_numfiles;	/* Number of files on fs */
+	__le16  s_magic;	/* Magic signature */
+	__le16  s_newfs;	/* Non-zero if this is a new fs */
+};
+
+/****************************************************************************
+ * inode-related things
+ ****************************************************************************/
+#define EXOFS_IDATA		5
+
+/*
+ * The file control block - stored in an object's attributes.  This is where
+ * the in-memory inode is stored on disk.
+ */
+struct exofs_fcb {
+	__le64  i_size;			/* Size of the file */
+	__le16  i_mode;         	/* File mode */
+	__le16  i_links_count;  	/* Links count */
+	__le32  i_uid;          	/* Owner Uid */
+	__le32  i_gid;          	/* Group Id */
+	__le32  i_atime;        	/* Access time */
+	__le32  i_ctime;        	/* Creation time */
+	__le32  i_mtime;        	/* Modification time */
+	__le32  i_flags;        	/* File flags (unused for now)*/
+	__le32  i_generation;   	/* File version (for NFS) */
+	__le32  i_data[EXOFS_IDATA];	/* Short symlink names and device #s */
+};
+
+#define EXOFS_INO_ATTR_SIZE	sizeof(struct exofs_fcb)
+
+/* This is the Attribute the fcb is stored in */
+static const struct __weak osd_attr g_attr_inode_data = ATTR_DEF(
+	EXOFS_APAGE_FS_DATA,
+	EXOFS_ATTR_INODE_DATA,
+	EXOFS_INO_ATTR_SIZE);
+
+/****************************************************************************
+ * dentry-related things
+ ****************************************************************************/
+#define EXOFS_NAME_LEN	255
+
+/*
+ * The on-disk directory entry
+ */
+struct exofs_dir_entry {
+	__le64		inode_no;		/* inode number           */
+	__le16		rec_len;		/* directory entry length */
+	u8		name_len;		/* name length            */
+	u8		file_type;		/* umm...file type        */
+	char		name[EXOFS_NAME_LEN];	/* file name              */
+};
+
+enum {
+	EXOFS_FT_UNKNOWN,
+	EXOFS_FT_REG_FILE,
+	EXOFS_FT_DIR,
+	EXOFS_FT_CHRDEV,
+	EXOFS_FT_BLKDEV,
+	EXOFS_FT_FIFO,
+	EXOFS_FT_SOCK,
+	EXOFS_FT_SYMLINK,
+	EXOFS_FT_MAX
+};
+
+#define EXOFS_DIR_PAD			4
+#define EXOFS_DIR_ROUND			(EXOFS_DIR_PAD - 1)
+#define EXOFS_DIR_REC_LEN(name_len) \
+	(((name_len) + offsetof(struct exofs_dir_entry, name)  + \
+	  EXOFS_DIR_ROUND) & ~EXOFS_DIR_ROUND)
+
+/*************************
+ * function declarations *
+ *************************/
+/* osd.c                 */
+void exofs_make_credential(u8 cred_a[OSD_CAP_LEN],
+			   const struct osd_obj_id *obj);
+
+int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid);
+static inline int exofs_check_ok(struct osd_request *or)
+{
+	return exofs_check_ok_resid(or, NULL, NULL);
+}
+int exofs_sync_op(struct osd_request *or, int timeout, u8 *cred);
+int exofs_async_op(struct osd_request *or,
+	osd_req_done_fn *async_done, void *caller_context, u8 *cred);
+
+int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr);
+
+int osd_req_read_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
+
+int osd_req_write_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
+
+#endif /*ifndef __EXOFS_COM_H__*/
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
new file mode 100644
index 00000000000..65b0c8c776a
--- /dev/null
+++ b/fs/exofs/dir.c
@@ -0,0 +1,672 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include "exofs.h"
+
+static inline unsigned exofs_chunk_size(struct inode *inode)
+{
+	return inode->i_sb->s_blocksize;
+}
+
+static inline void exofs_put_page(struct page *page)
+{
+	kunmap(page);
+	page_cache_release(page);
+}
+
+/* Accesses dir's inode->i_size must be called under inode lock */
+static inline unsigned long dir_pages(struct inode *inode)
+{
+	return (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+}
+
+static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr)
+{
+	loff_t last_byte = inode->i_size;
+
+	last_byte -= page_nr << PAGE_CACHE_SHIFT;
+	if (last_byte > PAGE_CACHE_SIZE)
+		last_byte = PAGE_CACHE_SIZE;
+	return last_byte;
+}
+
+static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *dir = mapping->host;
+	int err = 0;
+
+	dir->i_version++;
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+
+	if (pos+len > dir->i_size) {
+		i_size_write(dir, pos+len);
+		mark_inode_dirty(dir);
+	}
+	set_page_dirty(page);
+
+	if (IS_DIRSYNC(dir))
+		err = write_one_page(page, 1);
+	else
+		unlock_page(page);
+
+	return err;
+}
+
+static void exofs_check_page(struct page *page)
+{
+	struct inode *dir = page->mapping->host;
+	unsigned chunk_size = exofs_chunk_size(dir);
+	char *kaddr = page_address(page);
+	unsigned offs, rec_len;
+	unsigned limit = PAGE_CACHE_SIZE;
+	struct exofs_dir_entry *p;
+	char *error;
+
+	/* if the page is the last one in the directory */
+	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_CACHE_MASK;
+		if (limit & (chunk_size - 1))
+			goto Ebadsize;
+		if (!limit)
+			goto out;
+	}
+	for (offs = 0; offs <= limit - EXOFS_DIR_REC_LEN(1); offs += rec_len) {
+		p = (struct exofs_dir_entry *)(kaddr + offs);
+		rec_len = le16_to_cpu(p->rec_len);
+
+		if (rec_len < EXOFS_DIR_REC_LEN(1))
+			goto Eshort;
+		if (rec_len & 3)
+			goto Ealign;
+		if (rec_len < EXOFS_DIR_REC_LEN(p->name_len))
+			goto Enamelen;
+		if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
+			goto Espan;
+	}
+	if (offs != limit)
+		goto Eend;
+out:
+	SetPageChecked(page);
+	return;
+
+Ebadsize:
+	EXOFS_ERR("ERROR [exofs_check_page]: "
+		"size of directory #%lu is not a multiple of chunk size",
+		dir->i_ino
+	);
+	goto fail;
+Eshort:
+	error = "rec_len is smaller than minimal";
+	goto bad_entry;
+Ealign:
+	error = "unaligned directory entry";
+	goto bad_entry;
+Enamelen:
+	error = "rec_len is too small for name_len";
+	goto bad_entry;
+Espan:
+	error = "directory entry across blocks";
+	goto bad_entry;
+bad_entry:
+	EXOFS_ERR(
+		"ERROR [exofs_check_page]: bad entry in directory #%lu: %s - "
+		"offset=%lu, inode=%llu, rec_len=%d, name_len=%d",
+		dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		_LLU(le64_to_cpu(p->inode_no)),
+		rec_len, p->name_len);
+	goto fail;
+Eend:
+	p = (struct exofs_dir_entry *)(kaddr + offs);
+	EXOFS_ERR("ERROR [exofs_check_page]: "
+		"entry in directory #%lu spans the page boundary"
+		"offset=%lu, inode=%llu",
+		dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		_LLU(le64_to_cpu(p->inode_no)));
+fail:
+	SetPageChecked(page);
+	SetPageError(page);
+}
+
+static struct page *exofs_get_page(struct inode *dir, unsigned long n)
+{
+	struct address_space *mapping = dir->i_mapping;
+	struct page *page = read_mapping_page(mapping, n, NULL);
+
+	if (!IS_ERR(page)) {
+		kmap(page);
+		if (!PageChecked(page))
+			exofs_check_page(page);
+		if (PageError(page))
+			goto fail;
+	}
+	return page;
+
+fail:
+	exofs_put_page(page);
+	return ERR_PTR(-EIO);
+}
+
+static inline int exofs_match(int len, const unsigned char *name,
+					struct exofs_dir_entry *de)
+{
+	if (len != de->name_len)
+		return 0;
+	if (!de->inode_no)
+		return 0;
+	return !memcmp(name, de->name, len);
+}
+
+static inline
+struct exofs_dir_entry *exofs_next_entry(struct exofs_dir_entry *p)
+{
+	return (struct exofs_dir_entry *)((char *)p + le16_to_cpu(p->rec_len));
+}
+
+static inline unsigned
+exofs_validate_entry(char *base, unsigned offset, unsigned mask)
+{
+	struct exofs_dir_entry *de = (struct exofs_dir_entry *)(base + offset);
+	struct exofs_dir_entry *p =
+			(struct exofs_dir_entry *)(base + (offset&mask));
+	while ((char *)p < (char *)de) {
+		if (p->rec_len == 0)
+			break;
+		p = exofs_next_entry(p);
+	}
+	return (char *)p - base;
+}
+
+static unsigned char exofs_filetype_table[EXOFS_FT_MAX] = {
+	[EXOFS_FT_UNKNOWN]	= DT_UNKNOWN,
+	[EXOFS_FT_REG_FILE]	= DT_REG,
+	[EXOFS_FT_DIR]		= DT_DIR,
+	[EXOFS_FT_CHRDEV]	= DT_CHR,
+	[EXOFS_FT_BLKDEV]	= DT_BLK,
+	[EXOFS_FT_FIFO]		= DT_FIFO,
+	[EXOFS_FT_SOCK]		= DT_SOCK,
+	[EXOFS_FT_SYMLINK]	= DT_LNK,
+};
+
+#define S_SHIFT 12
+static unsigned char exofs_type_by_mode[S_IFMT >> S_SHIFT] = {
+	[S_IFREG >> S_SHIFT]	= EXOFS_FT_REG_FILE,
+	[S_IFDIR >> S_SHIFT]	= EXOFS_FT_DIR,
+	[S_IFCHR >> S_SHIFT]	= EXOFS_FT_CHRDEV,
+	[S_IFBLK >> S_SHIFT]	= EXOFS_FT_BLKDEV,
+	[S_IFIFO >> S_SHIFT]	= EXOFS_FT_FIFO,
+	[S_IFSOCK >> S_SHIFT]	= EXOFS_FT_SOCK,
+	[S_IFLNK >> S_SHIFT]	= EXOFS_FT_SYMLINK,
+};
+
+static inline
+void exofs_set_de_type(struct exofs_dir_entry *de, struct inode *inode)
+{
+	mode_t mode = inode->i_mode;
+	de->file_type = exofs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
+}
+
+static int
+exofs_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	loff_t pos = filp->f_pos;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	unsigned int offset = pos & ~PAGE_CACHE_MASK;
+	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned long npages = dir_pages(inode);
+	unsigned chunk_mask = ~(exofs_chunk_size(inode)-1);
+	unsigned char *types = NULL;
+	int need_revalidate = (filp->f_version != inode->i_version);
+
+	if (pos > inode->i_size - EXOFS_DIR_REC_LEN(1))
+		return 0;
+
+	types = exofs_filetype_table;
+
+	for ( ; n < npages; n++, offset = 0) {
+		char *kaddr, *limit;
+		struct exofs_dir_entry *de;
+		struct page *page = exofs_get_page(inode, n);
+
+		if (IS_ERR(page)) {
+			EXOFS_ERR("ERROR: "
+				   "bad page in #%lu",
+				   inode->i_ino);
+			filp->f_pos += PAGE_CACHE_SIZE - offset;
+			return PTR_ERR(page);
+		}
+		kaddr = page_address(page);
+		if (unlikely(need_revalidate)) {
+			if (offset) {
+				offset = exofs_validate_entry(kaddr, offset,
+								chunk_mask);
+				filp->f_pos = (n<<PAGE_CACHE_SHIFT) + offset;
+			}
+			filp->f_version = inode->i_version;
+			need_revalidate = 0;
+		}
+		de = (struct exofs_dir_entry *)(kaddr + offset);
+		limit = kaddr + exofs_last_byte(inode, n) -
+							EXOFS_DIR_REC_LEN(1);
+		for (; (char *)de <= limit; de = exofs_next_entry(de)) {
+			if (de->rec_len == 0) {
+				EXOFS_ERR("ERROR: "
+					"zero-length directory entry");
+				exofs_put_page(page);
+				return -EIO;
+			}
+			if (de->inode_no) {
+				int over;
+				unsigned char d_type = DT_UNKNOWN;
+
+				if (types && de->file_type < EXOFS_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,
+						le64_to_cpu(de->inode_no),
+						d_type);
+				if (over) {
+					exofs_put_page(page);
+					return 0;
+				}
+			}
+			filp->f_pos += le16_to_cpu(de->rec_len);
+		}
+		exofs_put_page(page);
+	}
+
+	return 0;
+}
+
+struct exofs_dir_entry *exofs_find_entry(struct inode *dir,
+			struct dentry *dentry, struct page **res_page)
+{
+	const unsigned char *name = dentry->d_name.name;
+	int namelen = dentry->d_name.len;
+	unsigned reclen = EXOFS_DIR_REC_LEN(namelen);
+	unsigned long start, n;
+	unsigned long npages = dir_pages(dir);
+	struct page *page = NULL;
+	struct exofs_i_info *oi = exofs_i(dir);
+	struct exofs_dir_entry *de;
+
+	if (npages == 0)
+		goto out;
+
+	*res_page = NULL;
+
+	start = oi->i_dir_start_lookup;
+	if (start >= npages)
+		start = 0;
+	n = start;
+	do {
+		char *kaddr;
+		page = exofs_get_page(dir, n);
+		if (!IS_ERR(page)) {
+			kaddr = page_address(page);
+			de = (struct exofs_dir_entry *) kaddr;
+			kaddr += exofs_last_byte(dir, n) - reclen;
+			while ((char *) de <= kaddr) {
+				if (de->rec_len == 0) {
+					EXOFS_ERR(
+						"ERROR: exofs_find_entry: "
+						"zero-length directory entry");
+					exofs_put_page(page);
+					goto out;
+				}
+				if (exofs_match(namelen, name, de))
+					goto found;
+				de = exofs_next_entry(de);
+			}
+			exofs_put_page(page);
+		}
+		if (++n >= npages)
+			n = 0;
+	} while (n != start);
+out:
+	return NULL;
+
+found:
+	*res_page = page;
+	oi->i_dir_start_lookup = n;
+	return de;
+}
+
+struct exofs_dir_entry *exofs_dotdot(struct inode *dir, struct page **p)
+{
+	struct page *page = exofs_get_page(dir, 0);
+	struct exofs_dir_entry *de = NULL;
+
+	if (!IS_ERR(page)) {
+		de = exofs_next_entry(
+				(struct exofs_dir_entry *)page_address(page));
+		*p = page;
+	}
+	return de;
+}
+
+ino_t exofs_parent_ino(struct dentry *child)
+{
+	struct page *page;
+	struct exofs_dir_entry *de;
+	ino_t ino;
+
+	de = exofs_dotdot(child->d_inode, &page);
+	if (!de)
+		return 0;
+
+	ino = le64_to_cpu(de->inode_no);
+	exofs_put_page(page);
+	return ino;
+}
+
+ino_t exofs_inode_by_name(struct inode *dir, struct dentry *dentry)
+{
+	ino_t res = 0;
+	struct exofs_dir_entry *de;
+	struct page *page;
+
+	de = exofs_find_entry(dir, dentry, &page);
+	if (de) {
+		res = le64_to_cpu(de->inode_no);
+		exofs_put_page(page);
+	}
+	return res;
+}
+
+int exofs_set_link(struct inode *dir, struct exofs_dir_entry *de,
+			struct page *page, struct inode *inode)
+{
+	loff_t pos = page_offset(page) +
+			(char *) de - (char *) page_address(page);
+	unsigned len = le16_to_cpu(de->rec_len);
+	int err;
+
+	lock_page(page);
+	err = exofs_write_begin(NULL, page->mapping, pos, len,
+				AOP_FLAG_UNINTERRUPTIBLE, &page, NULL);
+	if (err)
+		EXOFS_ERR("exofs_set_link: exofs_write_begin FAILD => %d\n",
+			  err);
+
+	de->inode_no = cpu_to_le64(inode->i_ino);
+	exofs_set_de_type(de, inode);
+	if (likely(!err))
+		err = exofs_commit_chunk(page, pos, len);
+	exofs_put_page(page);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	mark_inode_dirty(dir);
+	return err;
+}
+
+int exofs_add_link(struct dentry *dentry, struct inode *inode)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	const unsigned char *name = dentry->d_name.name;
+	int namelen = dentry->d_name.len;
+	unsigned chunk_size = exofs_chunk_size(dir);
+	unsigned reclen = EXOFS_DIR_REC_LEN(namelen);
+	unsigned short rec_len, name_len;
+	struct page *page = NULL;
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	struct exofs_dir_entry *de;
+	unsigned long npages = dir_pages(dir);
+	unsigned long n;
+	char *kaddr;
+	loff_t pos;
+	int err;
+
+	for (n = 0; n <= npages; n++) {
+		char *dir_end;
+
+		page = exofs_get_page(dir, n);
+		err = PTR_ERR(page);
+		if (IS_ERR(page))
+			goto out;
+		lock_page(page);
+		kaddr = page_address(page);
+		dir_end = kaddr + exofs_last_byte(dir, n);
+		de = (struct exofs_dir_entry *)kaddr;
+		kaddr += PAGE_CACHE_SIZE - reclen;
+		while ((char *)de <= kaddr) {
+			if ((char *)de == dir_end) {
+				name_len = 0;
+				rec_len = chunk_size;
+				de->rec_len = cpu_to_le16(chunk_size);
+				de->inode_no = 0;
+				goto got_it;
+			}
+			if (de->rec_len == 0) {
+				EXOFS_ERR("ERROR: exofs_add_link: "
+					"zero-length directory entry");
+				err = -EIO;
+				goto out_unlock;
+			}
+			err = -EEXIST;
+			if (exofs_match(namelen, name, de))
+				goto out_unlock;
+			name_len = EXOFS_DIR_REC_LEN(de->name_len);
+			rec_len = le16_to_cpu(de->rec_len);
+			if (!de->inode_no && rec_len >= reclen)
+				goto got_it;
+			if (rec_len >= name_len + reclen)
+				goto got_it;
+			de = (struct exofs_dir_entry *) ((char *) de + rec_len);
+		}
+		unlock_page(page);
+		exofs_put_page(page);
+	}
+
+	EXOFS_ERR("exofs_add_link: BAD dentry=%p or inode=%p", dentry, inode);
+	return -EINVAL;
+
+got_it:
+	pos = page_offset(page) +
+		(char *)de - (char *)page_address(page);
+	err = exofs_write_begin(NULL, page->mapping, pos, rec_len, 0,
+							&page, NULL);
+	if (err)
+		goto out_unlock;
+	if (de->inode_no) {
+		struct exofs_dir_entry *de1 =
+			(struct exofs_dir_entry *)((char *)de + name_len);
+		de1->rec_len = cpu_to_le16(r