13 files changed, 750 insertions, 34 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index e4b1a3d596cc..494059d60134 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4407,7 +4407,7 @@ W:	http://www.nongnu.org/orinoco/
 S:      Maintained
 F:      drivers/net/wireless/orinoco/
 
-OSD LIBRARY
+OSD LIBRARY and FILESYSTEM
 P:      Boaz Harrosh
 M:      bharrosh@panasas.com
 P:      Benny Halevy
@@ -4416,6 +4416,9 @@ L:	osd-dev@open-osd.org
 W:      http://open-osd.org
 T:      git git://git.open-osd.org/open-osd.git
 S:      Maintained
+F:      drivers/scsi/osd/
+F:      drivers/include/scsi/osd_*
+F:      fs/exofs/
 
 P54 WIRELESS DRIVER
 P:      Michael Wu
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index bb72ada9f074..1d886e079c58 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -298,6 +298,22 @@ config BLK_DEV_NBD
 
           If unsure, say N.
 
+config BLK_DEV_OSD
+        tristate "OSD object-as-blkdev support"
+        depends on SCSI_OSD_ULD
+        ---help---
+          Saying Y or M here will allow the exporting of a single SCSI
+          OSD (object-based storage) object as a Linux block device.
+
+          For example, if you create a 2G object on an OSD device,
+          you can then use this module to present that 2G object as
+          a Linux block device.
+
+          To compile this driver as a module, choose M here: the
+          module will be called osdblk.
+
+          If unsure, say N.
+
 config BLK_DEV_SX8
         tristate "Promise SATA SX8 support"
         depends on PCI
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 7755a5e2a85e..cdaa3f8fddf0 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_XILINX_SYSACE)	+= xsysace.o
 obj-$(CONFIG_CDROM_PKTCDVD)     += pktcdvd.o
 obj-$(CONFIG_MG_DISK)           += mg_disk.o
 obj-$(CONFIG_SUNVDC)            += sunvdc.o
+obj-$(CONFIG_BLK_DEV_OSD)       += osdblk.o
 
 obj-$(CONFIG_BLK_DEV_UMEM)      += umem.o
 obj-$(CONFIG_BLK_DEV_NBD)       += nbd.o
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
new file mode 100644
index 000000000000..13c1aee6aa3f
--- /dev/null
+++ b/drivers/block/osdblk.c
@@ -0,0 +1,701 @@
+
+/*
+   osdblk.c -- Export a single SCSI OSD object as a Linux block device
+
+
+   Copyright 2009 Red Hat, Inc.
+
+   This program 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.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+   Instructions for use
+   --------------------
+
+   1) Map a Linux block device to an existing OSD object.
+
+      In this example, we will use partition id 1234, object id 5678,
+      OSD device /dev/osd1.
+
+      $ echo "1234 5678 /dev/osd1" > /sys/class/osdblk/add
+
+
+   2) List all active blkdev<->object mappings.
+
+      In this example, we have performed step #1 twice, creating two blkdevs,
+      mapped to two separate OSD objects.
+
+      $ cat /sys/class/osdblk/list
+      0 174 1234 5678 /dev/osd1
+      1 179 1994 897123 /dev/osd0
+
+      The columns, in order, are:
+      - blkdev unique id
+      - blkdev assigned major
+      - OSD object partition id
+      - OSD object id
+      - OSD device
+
+
+   3) Remove an active blkdev<->object mapping.
+
+      In this example, we remove the mapping with blkdev unique id 1.
+
+      $ echo 1 > /sys/class/osdblk/remove
+
+
+   NOTE:  The actual creation and deletion of OSD objects is outside the scope
+   of this driver.
+
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <scsi/osd_initiator.h>
+#include <scsi/osd_attributes.h>
+#include <scsi/osd_sec.h>
+#include <scsi/scsi_device.h>
+
+#define DRV_NAME "osdblk"
+#define PFX DRV_NAME ": "
+
+/* #define _OSDBLK_DEBUG */
+#ifdef _OSDBLK_DEBUG
+#define OSDBLK_DEBUG(fmt, a...) \
+        printk(KERN_NOTICE "osdblk @%s:%d: " fmt, __func__, __LINE__, ##a)
+#else
+#define OSDBLK_DEBUG(fmt, a...) \
+        do { if (0) printk(fmt, ##a); } while (0)
+#endif
+
+MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
+MODULE_DESCRIPTION("block device inside an OSD object osdblk.ko");
+MODULE_LICENSE("GPL");
+
+struct osdblk_device;
+
+enum {
+        OSDBLK_MINORS_PER_MAJOR = 256,          /* max minors per blkdev */
+        OSDBLK_MAX_REQ          = 32,           /* max parallel requests */
+        OSDBLK_OP_TIMEOUT       = 4 * 60,       /* sync OSD req timeout */
+};
+
+struct osdblk_request {
+        struct request          *rq;            /* blk layer request */
+        struct bio              *bio;           /* cloned bio */
+        struct osdblk_device    *osdev;         /* associated blkdev */
+};
+
+struct osdblk_device {
+        int                     id;             /* blkdev unique id */
+
+        int                     major;          /* blkdev assigned major */
+        struct gendisk          *disk;          /* blkdev's gendisk and rq */
+        struct request_queue    *q;
+
+        struct osd_dev          *osd;           /* associated OSD */
+
+        char                    name[32];       /* blkdev name, e.g. osdblk34 */
+
+        spinlock_t              lock;           /* queue lock */
+
+        struct osd_obj_id       obj;            /* OSD partition, obj id */
+        uint8_t                 obj_cred[OSD_CAP_LEN]; /* OSD cred */
+
+        struct osdblk_request   req[OSDBLK_MAX_REQ]; /* request table */
+
+        struct list_head        node;
+
+        char                    osd_path[0];    /* OSD device path */
+};
+
+static struct class *class_osdblk;              /* /sys/class/osdblk */
+static DEFINE_MUTEX(ctl_mutex); /* Serialize open/close/setup/teardown */
+static LIST_HEAD(osdblkdev_list);
+
+static struct block_device_operations osdblk_bd_ops = {
+        .owner          = THIS_MODULE,
+};
+
+static const struct osd_attr g_attr_logical_length = ATTR_DEF(
+        OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
+
+static void osdblk_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);
+}
+
+/* copied from exofs; move to libosd? */
+/*
+ * Perform a synchronous OSD operation.  copied from exofs; move to libosd?
+ */
+static int osd_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)
+                return ret;
+
+        ret = osd_execute_request(or);
+
+        /* osd_req_decode_sense(or, ret); */
+        return ret;
+}
+
+/*
+ * Perform an asynchronous OSD operation.  copied from exofs; move to libosd?
+ */
+static int osd_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)
+                return ret;
+
+        ret = osd_execute_request_async(or, async_done, caller_context);
+
+        return ret;
+}
+
+/* copied from exofs; move to libosd? */
+static 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;
+}
+
+static int osdblk_get_obj_size(struct osdblk_device *osdev, u64 *size_out)
+{
+        struct osd_request *or;
+        struct osd_attr attr;
+        int ret;
+
+        /* start request */
+        or = osd_start_request(osdev->osd, GFP_KERNEL);
+        if (!or)
+                return -ENOMEM;
+
+        /* create a get-attributes(length) request */
+        osd_req_get_attributes(or, &osdev->obj);
+
+        osd_req_add_get_attr_list(or, &g_attr_logical_length, 1);
+
+        /* execute op synchronously */
+        ret = osd_sync_op(or, OSDBLK_OP_TIMEOUT, osdev->obj_cred);
+        if (ret)
+                goto out;
+
+        /* extract length from returned attribute info */
+        attr = g_attr_logical_length;
+        ret = extract_attr_from_req(or, &attr);
+        if (ret)
+                goto out;
+
+        *size_out = get_unaligned_be64(attr.val_ptr);
+
+out:
+        osd_end_request(or);
+        return ret;
+
+}
+
+static void osdblk_osd_complete(struct osd_request *or, void *private)
+{
+        struct osdblk_request *orq = private;
+        struct osd_sense_info osi;
+        int ret = osd_req_decode_sense(or, &osi);
+
+        if (ret) {
+                ret = -EIO;
+                OSDBLK_DEBUG("osdblk_osd_complete with err=%d\n", ret);
+        }
+
+        /* complete OSD request */
+        osd_end_request(or);
+
+        /* complete request passed to osdblk by block layer */
+        __blk_end_request_all(orq->rq, ret);
+}
+
+static void bio_chain_put(struct bio *chain)
+{
+        struct bio *tmp;
+
+        while (chain) {
+                tmp = chain;
+                chain = chain->bi_next;
+
+                bio_put(tmp);
+        }
+}
+
+static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
+{
+        struct bio *tmp, *new_chain = NULL, *tail = NULL;
+
+        while (old_chain) {
+                tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs);
+                if (!tmp)
+                        goto err_out;
+
+                __bio_clone(tmp, old_chain);
+                tmp->bi_bdev = NULL;
+                gfpmask &= ~__GFP_WAIT;
+                tmp->bi_next = NULL;
+
+                if (!new_chain)
+                        new_chain = tail = tmp;
+                else {
+                        tail->bi_next = tmp;
+                        tail = tmp;
+                }
+
+                old_chain = old_chain->bi_next;
+        }
+
+        return new_chain;
+
+err_out:
+        OSDBLK_DEBUG("bio_chain_clone with err\n");
+        bio_chain_put(new_chain);
+        return NULL;
+}
+
+static void osdblk_rq_fn(struct request_queue *q)
+{
+        struct osdblk_device *osdev = q->queuedata;
+
+        while (1) {
+                struct request *rq;
+                struct osdblk_request *orq;
+                struct osd_request *or;
+                struct bio *bio;
+                bool do_write, do_flush;
+
+                /* peek at request from block layer */
+                rq = blk_fetch_request(q);
+                if (!rq)
+                        break;
+
+                /* filter out block requests we don't understand */
+                if (!blk_fs_request(rq) && !blk_barrier_rq(rq)) {
+                        blk_end_request_all(rq, 0);
+                        continue;
+                }
+
+                /* deduce our operation (read, write, flush) */
+                /* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
+                 * into a clearly defined set of RPC commands:
+                 * read, write, flush, scsi command, power mgmt req,
+                 * driver-specific, etc.
+                 */
+
+                do_flush = (rq->special == (void *) 0xdeadbeefUL);
+                do_write = (rq_data_dir(rq) == WRITE);
+
+                if (!do_flush) { /* osd_flush does not use a bio */
+                        /* a bio clone to be passed down to OSD request */
+                        bio = bio_chain_clone(rq->bio, GFP_ATOMIC);
+                        if (!bio)
+                                break;
+                } else
+                        bio = NULL;
+
+                /* alloc internal OSD request, for OSD command execution */
+                or = osd_start_request(osdev->osd, GFP_ATOMIC);
+                if (!or) {
+                        bio_chain_put(bio);
+                        OSDBLK_DEBUG("osd_start_request with err\n");
+                        break;
+                }
+
+                orq = &osdev->req[rq->tag];
+                orq->rq = rq;
+                orq->bio = bio;
+                orq->osdev = osdev;
+
+                /* init OSD command: flush, write or read */
+                if (do_flush)
+                        osd_req_flush_object(or, &osdev->obj,
+                                             OSD_CDB_FLUSH_ALL, 0, 0);
+                else if (do_write)
+                        osd_req_write(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
+                                      bio, blk_rq_bytes(rq));
+                else
+                        osd_req_read(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
+                                     bio, blk_rq_bytes(rq));
+
+                OSDBLK_DEBUG("%s 0x%x bytes at 0x%llx\n",
+                        do_flush ? "flush" : do_write ?
+                                "write" : "read", blk_rq_bytes(rq),
+                        blk_rq_pos(rq) * 512ULL);
+
+                /* begin OSD command execution */
+                if (osd_async_op(or, osdblk_osd_complete, orq,
+                                 osdev->obj_cred)) {
+                        osd_end_request(or);
+                        blk_requeue_request(q, rq);
+                        bio_chain_put(bio);
+                        OSDBLK_DEBUG("osd_execute_request_async with err\n");
+                        break;
+                }
+
+                /* remove the special 'flush' marker, now that the command
+                 * is executing
+                 */
+                rq->special = NULL;
+        }
+}
+
+static void osdblk_prepare_flush(struct request_queue *q, struct request *rq)
+{
+        /* add driver-specific marker, to indicate that this request
+         * is a flush command
+         */
+        rq->special = (void *) 0xdeadbeefUL;
+}
+
+static void osdblk_free_disk(struct osdblk_device *osdev)
+{
+        struct gendisk *disk = osdev->disk;
+
+        if (!disk)
+                return;
+
+        if (disk->flags & GENHD_FL_UP)
+                del_gendisk(disk);
+        if (disk->queue)
+                blk_cleanup_queue(disk->queue);
+        put_disk(disk);
+}
+
+static int osdblk_init_disk(struct osdblk_device *osdev)
+{
+        struct gendisk *disk;
+        struct request_queue *q;
+        int rc;
+        u64 obj_size = 0;
+
+        /* contact OSD, request size info about the object being mapped */
+        rc = osdblk_get_obj_size(osdev, &obj_size);
+        if (rc)
+                return rc;
+
+        /* create gendisk info */
+        disk = alloc_disk(OSDBLK_MINORS_PER_MAJOR);
+        if (!disk)
+                return -ENOMEM;
+
+        sprintf(disk->disk_name, DRV_NAME "%d", osdev->id);
+        disk->major = osdev->major;
+        disk->first_minor = 0;
+        disk->fops = &osdblk_bd_ops;
+        disk->private_data = osdev;
+
+        /* init rq */
+        q = blk_init_queue(osdblk_rq_fn, &osdev->lock);
+        if (!q) {
+                put_disk(disk);
+                return -ENOMEM;
+        }
+
+        /* switch queue to TCQ mode; allocate tag map */
+        rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL);
+        if (rc) {
+                blk_cleanup_queue(q);
+                put_disk(disk);
+                return rc;
+        }
+
+        /* Set our limits to the lower device limits, because osdblk cannot
+         * sleep when allocating a lower-request and therefore cannot be
+         * bouncing.
+         */
+        blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
+
+        blk_queue_prep_rq(q, blk_queue_start_tag);
+        blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, osdblk_prepare_flush);
+
+        disk->queue = q;
+
+        q->queuedata = osdev;
+
+        osdev->disk = disk;
+        osdev->q = q;
+
+        /* finally, announce the disk to the world */
+        set_capacity(disk, obj_size / 512ULL);
+        add_disk(disk);
+
+        printk(KERN_INFO "%s: Added of size 0x%llx\n",
+                disk->disk_name, (unsigned long long)obj_size);
+
+        return 0;
+}
+
+/********************************************************************
+ * /sys/class/osdblk/
+ *                   add        map OSD object to blkdev
+ *                   remove     unmap OSD object
+ *                   list       show mappings
+ *******************************************************************/
+
+static void class_osdblk_release(struct class *cls)
+{
+        kfree(cls);
+}
+
+static ssize_t class_osdblk_list(struct class *c, char *data)
+{
+        int n = 0;
+        struct list_head *tmp;
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        list_for_each(tmp, &osdblkdev_list) {
+                struct osdblk_device *osdev;
+
+                osdev = list_entry(tmp, struct osdblk_device, node);
+
+                n += sprintf(data+n, "%d %d %llu %llu %s\n",
+                        osdev->id,
+                        osdev->major,
+                        osdev->obj.partition,
+                        osdev->obj.id,
+                        osdev->osd_path);
+        }
+
+        mutex_unlock(&ctl_mutex);
+        return n;
+}
+
+static ssize_t class_osdblk_add(struct class *c, const char *buf, size_t count)
+{
+        struct osdblk_device *osdev;
+        ssize_t rc;
+        int irc, new_id = 0;
+        struct list_head *tmp;
+
+        if (!try_module_get(THIS_MODULE))
+                return -ENODEV;
+
+        /* new osdblk_device object */
+        osdev = kzalloc(sizeof(*osdev) + strlen(buf) + 1, GFP_KERNEL);
+        if (!osdev) {
+                rc = -ENOMEM;
+                goto err_out_mod;
+        }
+
+        /* static osdblk_device initialization */
+        spin_lock_init(&osdev->lock);
+        INIT_LIST_HEAD(&osdev->node);
+
+        /* generate unique id: find highest unique id, add one */
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        list_for_each(tmp, &osdblkdev_list) {
+                struct osdblk_device *osdev;
+
+                osdev = list_entry(tmp, struct osdblk_device, node);
+                if (osdev->id > new_id)
+                        new_id = osdev->id + 1;
+        }
+
+        osdev->id = new_id;
+
+        /* add to global list */
+        list_add_tail(&osdev->node, &osdblkdev_list);
+
+        mutex_unlock(&ctl_mutex);
+
+        /* parse add command */
+        if (sscanf(buf, "%llu %llu %s", &osdev->obj.partition, &osdev->obj.id,
+                   osdev->osd_path) != 3) {
+                rc = -EINVAL;
+                goto err_out_slot;
+        }
+
+        /* initialize rest of new object */
+        sprintf(osdev->name, DRV_NAME "%d", osdev->id);
+
+        /* contact requested OSD */
+        osdev->osd = osduld_path_lookup(osdev->osd_path);
+        if (IS_ERR(osdev->osd)) {
+                rc = PTR_ERR(osdev->osd);
+                goto err_out_slot;
+        }
+
+        /* build OSD credential */
+        osdblk_make_credential(osdev->obj_cred, &osdev->obj);
+
+        /* register our block device */
+        irc = register_blkdev(0, osdev->name);
+        if (irc < 0) {
+                rc = irc;
+                goto err_out_osd;
+        }
+
+        osdev->major = irc;
+
+        /* set up and announce blkdev mapping */
+        rc = osdblk_init_disk(osdev);
+        if (rc)
+                goto err_out_blkdev;
+
+        return count;
+
+err_out_blkdev:
+        unregister_blkdev(osdev->major, osdev->name);
+err_out_osd:
+        osduld_put_device(osdev->osd);
+err_out_slot:
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+        list_del_init(&osdev->node);
+        mutex_unlock(&ctl_mutex);
+
+        kfree(osdev);
+err_out_mod:
+        OSDBLK_DEBUG("Error adding device %s\n", buf);
+        module_put(THIS_MODULE);
+        return rc;
+}
+
+static ssize_t class_osdblk_remove(struct class *c, const char *buf,
+                                        size_t count)
+{
+        struct osdblk_device *osdev = NULL;
+        int target_id, rc;
+        unsigned long ul;
+        struct list_head *tmp;
+
+        rc = strict_strtoul(buf, 10, &ul);
+        if (rc)
+                return rc;
+
+        /* convert to int; abort if we lost anything in the conversion */
+        target_id = (int) ul;
+        if (target_id != ul)
+                return -EINVAL;
+
+        /* remove object from list immediately */
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        list_for_each(tmp, &osdblkdev_list) {
+                osdev = list_entry(tmp, struct osdblk_device, node);
+                if (osdev->id == target_id) {
+                        list_del_init(&osdev->node);
+                        break;
+                }
+                osdev = NULL;
+        }
+
+        mutex_unlock(&ctl_mutex);
+
+        if (!osdev)
+                return -ENOENT;
+
+        /* clean up and free blkdev and associated OSD connection */
+        osdblk_free_disk(osdev);
+        unregister_blkdev(osdev->major, osdev->name);
+        osduld_put_device(osdev->osd);
+        kfree(osdev);
+
+        /* release module ref */
+        module_put(THIS_MODULE);
+
+        return count;
+}
+
+static struct class_attribute class_osdblk_attrs[] = {
+        __ATTR(add,     0200, NULL, class_osdblk_add),
+        __ATTR(remove,  0200, NULL, class_osdblk_remove),
+        __ATTR(list,    0444, class_osdblk_list, NULL),
+        __ATTR_NULL
+};
+
+static int osdblk_sysfs_init(void)
+{
+        int ret = 0;
+
+        /*
+         * create control files in sysfs
+         * /sys/class/osdblk/...
+         */
+        class_osdblk = kzalloc(sizeof(*class_osdblk), GFP_KERNEL);
+        if (!class_osdblk)
+                return -ENOMEM;
+
+        class_osdblk->name = DRV_NAME;
+        class_osdblk->owner = THIS_MODULE;
+        class_osdblk->class_release = class_osdblk_release;
+        class_osdblk->class_attrs = class_osdblk_attrs;
+
+        ret = class_register(class_osdblk);
+        if (ret) {
+                kfree(class_osdblk);
+                class_osdblk = NULL;
+                printk(PFX "failed to create class osdblk\n");
+                return ret;
+        }
+
+        return 0;
+}
+
+static void osdblk_sysfs_cleanup(void)
+{
+        if (class_osdblk)
+                class_destroy(class_osdblk);
+        class_osdblk = NULL;
+}
+
+static int __init osdblk_init(void)
+{
+        int rc;
+
+        rc = osdblk_sysfs_init();
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static void __exit osdblk_exit(void)
+{
+        osdblk_sysfs_cleanup();
+}
+
+module_init(osdblk_init);
+module_exit(osdblk_exit);
+
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
index 24667eedc023..c6718e4817fe 100644
--- a/fs/exofs/common.h
+++ b/fs/exofs/common.h
@@ -2,9 +2,7 @@
  * 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
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 65b0c8c776a1..4cfab1cc75c0 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 0fd4c7859679..5ec72e020b22 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
@@ -156,6 +154,9 @@ ino_t exofs_parent_ino(struct dentry *child);
 int exofs_set_link(struct inode *, struct exofs_dir_entry *, struct page *,
                     struct inode *);
 
+/* super.c               */
+int exofs_sync_fs(struct super_block *sb, int wait);
+
 /*********************
  * operation vectors *
  *********************/
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
index 6ed7fe484752..839b9dc1e70f 100644
--- a/fs/exofs/file.c
+++ b/fs/exofs/file.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
@@ -47,16 +45,23 @@ static int exofs_file_fsync(struct file *filp, struct dentry *dentry,
 {
         int ret;
         struct address_space *mapping = filp->f_mapping;
+        struct inode *inode = dentry->d_inode;
+        struct super_block *sb;
 
         ret = filemap_write_and_wait(mapping);
         if (ret)
                 return ret;
 
-        /*Note: file_fsync below also calles sync_blockdev, which is a no-op
-         *      for exofs, but other then that it does sync_inode and
-         *      sync_superblock which is what we need here.
-         */
-        return file_fsync(filp, dentry, datasync);
+        /* sync the inode attributes */
+        ret = write_inode_now(inode, 1);
+
+        /* This is a good place to write the sb */
+        /* TODO: Sechedule an sb-sync on create */
+        sb = inode->i_sb;
+        if (sb->s_dirt)
+                exofs_sync_fs(sb, 1);
+
+        return ret;
 }
 
 static int exofs_flush(struct file *file, fl_owner_t id)
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 77d0a295eb1c..6c10f7476699 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
@@ -295,6 +293,9 @@ static int read_exec(struct page_collect *pcol, bool is_sync)
 err:
         if (!is_sync)
                 _unlock_pcol_pages(pcol, ret, READ);
+        else /* Pages unlocked by caller in sync mode only free bio */
+                pcol_free(pcol);
+
         kfree(pcol_copy);
         if (or)
                 osd_end_request(or);
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index 77fdd765e76d..b7dd0c236863 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c
index b3d2ccb87aaa..4372542df284 100644
--- a/fs/exofs/osd.c
+++ b/fs/exofs/osd.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 8216c5b77b53..a343b4ea62f6 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *
@@ -200,7 +198,7 @@ static const struct export_operations exofs_export_ops;
 /*
  * Write the superblock to the OSD
  */
-static int exofs_sync_fs(struct super_block *sb, int wait)
+int exofs_sync_fs(struct super_block *sb, int wait)
 {
         struct exofs_sb_info *sbi;
         struct exofs_fscb *fscb;
diff --git a/fs/exofs/symlink.c b/fs/exofs/symlink.c
index 36e2d7bc7f7b..4dd687c3e747 100644
--- a/fs/exofs/symlink.c
+++ b/fs/exofs/symlink.c
@@ -1,8 +1,6 @@
 /*
  * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
- * Copyright (C) 2005, 2006
- * International Business Machines
+ * Avishay Traeger (avishay@gmail.com)
  * Copyright (C) 2008, 2009
  * Boaz Harrosh <bharrosh@panasas.com>
  *