exofs: Kbuild, Headers and osd utils

This patch includes osd infrastructure that will be used later by
the file system.

Also the declarations of constants, on disk structures,
and prototypes.

And the Kbuild+Kconfig files needed to build the exofs module.

Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>

5 files changed, 493 insertions, 0 deletions

diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild
new file mode 100644
index 000000000000..36d23ca79a58
--- /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
+obj-$(CONFIG_EXOFS_FS) += exofs.o
diff --git a/fs/exofs/Kconfig b/fs/exofs/Kconfig
new file mode 100644
index 000000000000..86194b2f799d
--- /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 000000000000..b1512c4bb8c7
--- /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/exofs.h b/fs/exofs/exofs.h
new file mode 100644
index 000000000000..365376d3f72d
--- /dev/null
+++ b/fs/exofs/exofs.h
@@ -0,0 +1,127 @@
+/*
+ * 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 <linux/fs.h>
+#include <linux/time.h>
+#include "common.h"
+
+#ifndef __EXOFS_H__
+#define __EXOFS_H__
+
+#define EXOFS_ERR(fmt, a...) printk(KERN_ERR "exofs: " fmt, ##a)
+
+#ifdef CONFIG_EXOFS_DEBUG
+#define EXOFS_DBGMSG(fmt, a...) \
+	printk(KERN_NOTICE "exofs @%s:%d: " fmt, __func__, __LINE__, ##a)
+#else
+#define EXOFS_DBGMSG(fmt, a...) \
+	do { if (0) printk(fmt, ##a); } while (0)
+#endif
+
+/* u64 has problems with printk this will cast it to unsigned long long */
+#define _LLU(x) (unsigned long long)(x)
+
+/*
+ * our extension to the in-memory superblock
+ */
+struct exofs_sb_info {
+	struct osd_dev	*s_dev;			/* returned by get_osd_dev    */
+	osd_id		s_pid;			/* partition ID of file system*/
+	int		s_timeout;		/* timeout for OSD operations */
+	uint64_t	s_nextid;		/* highest object ID used     */
+	uint32_t	s_numfiles;		/* number of files on fs      */
+	spinlock_t	s_next_gen_lock;	/* spinlock for gen # update  */
+	u32		s_next_generation;	/* next gen # to use          */
+	atomic_t	s_curr_pending;		/* number of pending commands */
+	uint8_t		s_cred[OSD_CAP_LEN];	/* all-powerful credential    */
+};
+
+/*
+ * our extension to the in-memory inode
+ */
+struct exofs_i_info {
+	unsigned long  i_flags;            /* various atomic flags            */
+	uint32_t       i_data[EXOFS_IDATA];/*short symlink names and device #s*/
+	uint32_t       i_dir_start_lookup; /* which page to start lookup      */
+	wait_queue_head_t i_wq;            /* wait queue for inode            */
+	uint64_t       i_commit_size;      /* the object's written length     */
+	uint8_t        i_cred[OSD_CAP_LEN];/* all-powerful credential         */
+	struct inode   vfs_inode;          /* normal in-memory inode          */
+};
+
+/*
+ * our inode flags
+ */
+#define OBJ_2BCREATED	0	/* object will be created soon*/
+#define OBJ_CREATED	1	/* object has been created on the osd*/
+
+static inline int obj_2bcreated(struct exofs_i_info *oi)
+{
+	return test_bit(OBJ_2BCREATED, &oi->i_flags);
+}
+
+static inline void set_obj_2bcreated(struct exofs_i_info *oi)
+{
+	set_bit(OBJ_2BCREATED, &oi->i_flags);
+}
+
+static inline int obj_created(struct exofs_i_info *oi)
+{
+	return test_bit(OBJ_CREATED, &oi->i_flags);
+}
+
+static inline void set_obj_created(struct exofs_i_info *oi)
+{
+	set_bit(OBJ_CREATED, &oi->i_flags);
+}
+
+int __exofs_wait_obj_created(struct exofs_i_info *oi);
+static inline int wait_obj_created(struct exofs_i_info *oi)
+{
+	if (likely(obj_created(oi)))
+		return 0;
+
+	return __exofs_wait_obj_created(oi);
+}
+
+/*
+ * get to our inode from the vfs inode
+ */
+static inline struct exofs_i_info *exofs_i(struct inode *inode)
+{
+	return container_of(inode, struct exofs_i_info, vfs_inode);
+}
+
+#endif
diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c
new file mode 100644
index 000000000000..b249ae97fb15
--- /dev/null
+++ b/fs/exofs/osd.c
@@ -0,0 +1,153 @@
+/*
+ * 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>
+ *
+ * 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 <scsi/scsi_device.h>
+#include <scsi/osd_sense.h>
+
+#include "exofs.h"
+
+int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid)
+{
+	struct osd_sense_info osi;
+	int ret = osd_req_decode_sense(or, &osi);
+
+	if (ret) { /* translate to Linux codes */
+		if (osi.additional_code == scsi_invalid_field_in_cdb) {
+			if (osi.cdb_field_offset == OSD_CFO_STARTING_BYTE)
+				ret = -EFAULT;
+			if (osi.cdb_field_offset == OSD_CFO_OBJECT_ID)
+				ret = -ENOENT;
+			else
+				ret = -EINVAL;
+		} else if (osi.additional_code == osd_quota_error)
+			ret = -ENOSPC;
+		else
+			ret = -EIO;
+	}
+
+	/* FIXME: should be include in osd_sense_info */
+	if (in_resid)
+		*in_resid = or->in.req ? or->in.req->data_len : 0;
+
+	if (out_resid)
+		*out_resid = or->out.req ? or->out.req->data_len : 0;
+
+	return ret;
+}
+
+void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj)
+{
+	osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
+}
+
+/*
+ * Perform a synchronous OSD operation.
+ */
+int exofs_sync_op(struct osd_request *or, int timeout, uint8_t *credential)
+{
+	int ret;
+
+	or->timeout = timeout;
+	ret = osd_finalize_request(or, 0, credential, NULL);
+	if (ret) {
+		EXOFS_DBGMSG("Faild to osd_finalize_request() => %d\n", ret);
+		return ret;
+	}
+
+	ret = osd_execute_request(or);
+
+	if (ret)
+		EXOFS_DBGMSG("osd_execute_request() => %d\n", ret);
+	/* osd_req_decode_sense(or, ret); */
+	return ret;
+}
+
+/*
+ * Perform an asynchronous OSD operation.
+ */
+int exofs_async_op(struct osd_request *or, osd_req_done_fn *async_done,
+		   void *caller_context, u8 *cred)
+{
+	int ret;
+
+	ret = osd_finalize_request(or, 0, cred, NULL);
+	if (ret) {
+		EXOFS_DBGMSG("Faild to osd_finalize_request() => %d\n", ret);
+		return ret;
+	}
+
+	ret = osd_execute_request_async(or, async_done, caller_context);
+
+	if (ret)
+		EXOFS_DBGMSG("osd_execute_request_async() => %d\n", ret);
+	return ret;
+}
+
+int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
+{
+	struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
+	void *iter = NULL;
+	int nelem;
+
+	do {
+		nelem = 1;
+		osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter);
+		if ((cur_attr.attr_page == attr->attr_page) &&
+		    (cur_attr.attr_id == attr->attr_id)) {
+			attr->len = cur_attr.len;
+			attr->val_ptr = cur_attr.val_ptr;
+			return 0;
+		}
+	} while (iter);
+
+	return -EIO;
+}
+
+int osd_req_read_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void* buff, u64 len)
+{
+	struct request_queue *req_q = or->osd_dev->scsi_device->request_queue;
+	struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
+
+	if (!bio)
+		return -ENOMEM;
+
+	osd_req_read(or, obj, bio, offset);
+	return 0;
+}
+
+int osd_req_write_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void* buff, u64 len)
+{
+	struct request_queue *req_q = or->osd_dev->scsi_device->request_queue;
+	struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
+
+	if (!bio)
+		return -ENOMEM;
+
+	osd_req_write(or, obj, bio, offset);
+	return 0;
+}