* RFC: drop the T10 OSD code and its users
@ 2017-04-12 16:01 Christoph Hellwig
2017-04-12 16:01 ` [PATCH 1/4] block: remove the osdblk driver Christoph Hellwig
` (6 more replies)
0 siblings, 7 replies; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-12 16:01 UTC (permalink / raw)
To: ooo, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
The only real user of the T10 OSD protocol, the pNFS object layout
driver never went to the point of having shipping products, and the
other two users (osdblk and exofs) were simple example of it's usage.
The code has been mostly unmaintained for years and is getting in the
way of block / SCSI changes, so I think it's finally time to drop it.
These patches are against Jens' block for-next tree as that already
has various modifications of the SCSI code.
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH 1/4] block: remove the osdblk driver
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
@ 2017-04-12 16:01 ` Christoph Hellwig
2017-04-19 7:21 ` Boaz Harrosh
2017-04-12 16:01 ` [PATCH 2/4] fs: remove exofs Christoph Hellwig
` (5 subsequent siblings)
6 siblings, 1 reply; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-12 16:01 UTC (permalink / raw)
To: ooo, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
This was just a proof of concept user for the SCSI OSD library, and
never had any real users.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/block/Kconfig | 16 --
drivers/block/Makefile | 1 -
drivers/block/osdblk.c | 693 -------------------------------------------------
3 files changed, 710 deletions(-)
delete mode 100644 drivers/block/osdblk.c
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index a1c2e816128f..58e24c354933 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -312,22 +312,6 @@ config BLK_DEV_SKD
Use device /dev/skd$N amd /dev/skd$Np$M.
-config BLK_DEV_OSD
- tristate "OSD object-as-blkdev support"
- depends on SCSI_OSD_ULD
- ---help---
- Saying Y or M here will allow the exporting of a single SCSI
- OSD (object-based storage) object as a Linux block device.
-
- For example, if you create a 2G object on an OSD device,
- you can then use this module to present that 2G object as
- a Linux block device.
-
- To compile this driver as a module, choose M here: the
- module will be called osdblk.
-
- If unsure, say N.
-
config BLK_DEV_SX8
tristate "Promise SATA SX8 support"
depends on PCI
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index b12c772bbeb3..42e8cee1cbc7 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -22,7 +22,6 @@ obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_MG_DISK) += mg_disk.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_SKD) += skd.o
-obj-$(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
deleted file mode 100644
index 8127b8201a01..000000000000
--- a/drivers/block/osdblk.c
+++ /dev/null
@@ -1,693 +0,0 @@
-
-/*
- 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 <linux/slab.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 const 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_clone_kmalloc(old_chain, gfpmask);
- if (!tmp)
- goto err_out;
-
- tmp->bi_bdev = NULL;
- gfpmask &= ~__GFP_DIRECT_RECLAIM;
- 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;
-
- /* 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 = (req_op(rq) == REQ_OP_FLUSH);
- 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_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, BLK_TAG_ALLOC_FIFO);
- 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_write_cache(q, true, false);
-
- 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,
- struct class_attribute *attr,
- 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,
- struct class_attribute *attr,
- 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,
- struct class_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct osdblk_device *osdev = NULL;
- int target_id, rc;
- unsigned long ul;
- struct list_head *tmp;
-
- rc = kstrtoul(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);
-
--
2.11.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 2/4] fs: remove exofs
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
2017-04-12 16:01 ` [PATCH 1/4] block: remove the osdblk driver Christoph Hellwig
@ 2017-04-12 16:01 ` Christoph Hellwig
2017-04-12 16:01 ` [PATCH 3/4] nfs: remove the objlayout driver Christoph Hellwig
` (4 subsequent siblings)
6 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-12 16:01 UTC (permalink / raw)
To: ooo, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
This was an example for using the SCSI OSD protocol, which we're trying
to remove.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/filesystems/00-INDEX | 2 -
Documentation/filesystems/exofs.txt | 185 -----
Documentation/scsi/osd.txt | 5 -
MAINTAINERS | 1 -
fs/Kconfig | 3 -
fs/Makefile | 1 -
fs/exofs/BUGS | 3 -
fs/exofs/Kbuild | 20 -
fs/exofs/Kconfig | 13 -
fs/exofs/Kconfig.ore | 14 -
fs/exofs/common.h | 262 ------
fs/exofs/dir.c | 661 ---------------
fs/exofs/exofs.h | 241 ------
fs/exofs/file.c | 83 --
fs/exofs/inode.c | 1514 -----------------------------------
fs/exofs/namei.c | 323 --------
fs/exofs/ore.c | 1164 ---------------------------
fs/exofs/ore_raid.c | 721 -----------------
fs/exofs/ore_raid.h | 62 --
fs/exofs/super.c | 1049 ------------------------
fs/exofs/sys.c | 205 -----
21 files changed, 6532 deletions(-)
delete mode 100644 Documentation/filesystems/exofs.txt
delete mode 100644 fs/exofs/BUGS
delete mode 100644 fs/exofs/Kbuild
delete mode 100644 fs/exofs/Kconfig
delete mode 100644 fs/exofs/Kconfig.ore
delete mode 100644 fs/exofs/common.h
delete mode 100644 fs/exofs/dir.c
delete mode 100644 fs/exofs/exofs.h
delete mode 100644 fs/exofs/file.c
delete mode 100644 fs/exofs/inode.c
delete mode 100644 fs/exofs/namei.c
delete mode 100644 fs/exofs/ore.c
delete mode 100644 fs/exofs/ore_raid.c
delete mode 100644 fs/exofs/ore_raid.h
delete mode 100644 fs/exofs/super.c
delete mode 100644 fs/exofs/sys.c
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index b7bd6c9009cc..b3c6b9b1d716 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -51,8 +51,6 @@ ecryptfs.txt
- docs on eCryptfs: stacked cryptographic filesystem for Linux.
efivarfs.txt
- info for the efivarfs filesystem.
-exofs.txt
- - info, usage, mount options, design about EXOFS.
ext2.txt
- info, mount options and specifications for the Ext2 filesystem.
ext3.txt
diff --git a/Documentation/filesystems/exofs.txt b/Documentation/filesystems/exofs.txt
deleted file mode 100644
index 23583a136975..000000000000
--- a/Documentation/filesystems/exofs.txt
+++ /dev/null
@@ -1,185 +0,0 @@
-===============================================================================
-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
- performed 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 exists, it will be deleted and a new one will be created in
- its 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. integer can be
- Hex by pre-pending an 0x to the number.
- osdname=<id> - Mount by a device's osdname.
- osdname is usually a 36 character uuid of the
- form "d2683732-c906-4ee1-9dbd-c10c27bb40df".
- It is one of the device's uuid specified in the
- mkfs.exofs format command.
- If this option is specified then the /dev/osdX
- above can be empty and is ignored.
- 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 are
- created in memory (read from 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/Documentation/scsi/osd.txt b/Documentation/scsi/osd.txt
index 5a9879bad073..2bc2ab06b0c0 100644
--- a/Documentation/scsi/osd.txt
+++ b/Documentation/scsi/osd.txt
@@ -24,11 +24,6 @@ osd-uld:
platform, both for the in-kernel initiator as well as connected targets. It
currently has no useful user-mode API, though it could have if need be.
-exofs:
- Is an OSD based Linux file system. It uses the osd-initiator and osd-uld,
-to export a usable file system for users.
-See Documentation/filesystems/exofs.txt for more details
-
osd target:
There are no current plans for an OSD target implementation in kernel. For all
needs, a user-mode target that is based on the scsi tgt target framework is
diff --git a/MAINTAINERS b/MAINTAINERS
index 882ea01b4efe..0ffaf69becce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9395,7 +9395,6 @@ T: git git://git.open-osd.org/open-osd.git
S: Maintained
F: drivers/scsi/osd/
F: include/scsi/osd_*
-F: fs/exofs/
OVERLAY FILESYSTEM
M: Miklos Szeredi <miklos@szeredi.hu>
diff --git a/fs/Kconfig b/fs/Kconfig
index 83eab52fb3f6..abee7e4468c6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -247,12 +247,9 @@ source "fs/romfs/Kconfig"
source "fs/pstore/Kconfig"
source "fs/sysv/Kconfig"
source "fs/ufs/Kconfig"
-source "fs/exofs/Kconfig"
endif # MISC_FILESYSTEMS
-source "fs/exofs/Kconfig.ore"
-
menuconfig NETWORK_FILESYSTEMS
bool "Network File Systems"
default y
diff --git a/fs/Makefile b/fs/Makefile
index 7bbaca9c67b1..58ae3c3e6792 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -124,7 +124,6 @@ obj-$(CONFIG_OCFS2_FS) += ocfs2/
obj-$(CONFIG_BTRFS_FS) += btrfs/
obj-$(CONFIG_GFS2_FS) += gfs2/
obj-$(CONFIG_F2FS_FS) += f2fs/
-obj-y += exofs/ # Multiple modules
obj-$(CONFIG_CEPH_FS) += ceph/
obj-$(CONFIG_PSTORE) += pstore/
obj-$(CONFIG_EFIVAR_FS) += efivarfs/
diff --git a/fs/exofs/BUGS b/fs/exofs/BUGS
deleted file mode 100644
index 1b2d4c63a579..000000000000
--- a/fs/exofs/BUGS
+++ /dev/null
@@ -1,3 +0,0 @@
-- Out-of-space may cause a severe problem if the object (and directory entry)
- were written, but the inode attributes failed. Then if the filesystem was
- unmounted and mounted the kernel can get into an endless loop doing a readdir.
diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild
deleted file mode 100644
index a364fd0965ec..000000000000
--- a/fs/exofs/Kbuild
+++ /dev/null
@@ -1,20 +0,0 @@
-#
-# Kbuild for the EXOFS module
-#
-# Copyright (C) 2008 Panasas Inc. All rights reserved.
-#
-# Authors:
-# Boaz Harrosh <ooo@electrozaur.com>
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License version 2
-#
-# Kbuild - Gets included from the Kernels Makefile and build system
-#
-
-# ore module library
-libore-y := ore.o ore_raid.o
-obj-$(CONFIG_ORE) += libore.o
-
-exofs-y := inode.o file.o namei.o dir.o super.o sys.o
-obj-$(CONFIG_EXOFS_FS) += exofs.o
diff --git a/fs/exofs/Kconfig b/fs/exofs/Kconfig
deleted file mode 100644
index 86194b2f799d..000000000000
--- a/fs/exofs/Kconfig
+++ /dev/null
@@ -1,13 +0,0 @@
-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/Kconfig.ore b/fs/exofs/Kconfig.ore
deleted file mode 100644
index 2daf2329c28d..000000000000
--- a/fs/exofs/Kconfig.ore
+++ /dev/null
@@ -1,14 +0,0 @@
-# ORE - Objects Raid Engine (libore.ko)
-#
-# Note ORE needs to "select ASYNC_XOR". So Not to force multiple selects
-# for every ORE user we do it like this. Any user should add itself here
-# at the "depends on EXOFS_FS || ..." with an ||. The dependencies are
-# selected here, and we default to "ON". So in effect it is like been
-# selected by any of the users.
-config ORE
- tristate
- depends on EXOFS_FS || PNFS_OBJLAYOUT
- select ASYNC_XOR
- select RAID6_PQ
- select ASYNC_PQ
- default SCSI_OSD_ULD
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
deleted file mode 100644
index 7d88ef566213..000000000000
--- a/fs/exofs/common.h
+++ /dev/null
@@ -1,262 +0,0 @@
-/*
- * common.h - Common definitions for both Kernel and user-mode utilities
- *
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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_DEVTABLE_ID 0x10001 /* object ID for on-disk device table */
-#define EXOFS_ROOT_ID 0x10002 /* object ID for root directory */
-
-/* exofs Application specific page/attribute */
-/* Inode attrs */
-# define EXOFS_APAGE_FS_DATA (OSD_APAGE_APP_DEFINED_FIRST + 3)
-# define EXOFS_ATTR_INODE_DATA 1
-# define EXOFS_ATTR_INODE_FILE_LAYOUT 2
-# define EXOFS_ATTR_INODE_DIR_LAYOUT 3
-/* Partition attrs */
-# define EXOFS_APAGE_SB_DATA (0xF0000000U + 3)
-# define EXOFS_ATTR_SB_STATS 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 object EXOFS_SUPER_ID's data.
- * This is where the in-memory superblock is stored on disk.
- */
-enum {EXOFS_FSCB_VER = 1, EXOFS_DT_VER = 1};
-struct exofs_fscb {
- __le64 s_nextid; /* Only used after mkfs */
- __le64 s_numfiles; /* Only used after mkfs */
- __le32 s_version; /* == EXOFS_FSCB_VER */
- __le16 s_magic; /* Magic signature */
- __le16 s_newfs; /* Non-zero if this is a new fs */
-
- /* From here on it's a static part, only written by mkexofs */
- __le64 s_dev_table_oid; /* Resurved, not used */
- __le64 s_dev_table_count; /* == 0 means no dev_table */
-} __packed;
-
-/*
- * This struct is set on the FS partition's attributes.
- * [EXOFS_APAGE_SB_DATA, EXOFS_ATTR_SB_STATS] and is written together
- * with the create command, to atomically persist the sb writeable information.
- */
-struct exofs_sb_stats {
- __le64 s_nextid; /* Highest object ID used */
- __le64 s_numfiles; /* Number of files on fs */
-} __packed;
-
-/*
- * Describes the raid used in the FS. It is part of the device table.
- * This here is taken from the pNFS-objects definition. In exofs we
- * use one raid policy through-out the filesystem. (NOTE: the funny
- * alignment at beginning. We take care of it at exofs_device_table.
- */
-struct exofs_dt_data_map {
- __le32 cb_num_comps;
- __le64 cb_stripe_unit;
- __le32 cb_group_width;
- __le32 cb_group_depth;
- __le32 cb_mirror_cnt;
- __le32 cb_raid_algorithm;
-} __packed;
-
-/*
- * This is an osd device information descriptor. It is a single entry in
- * the exofs device table. It describes an osd target lun which
- * contains data belonging to this FS. (Same partition_id on all devices)
- */
-struct exofs_dt_device_info {
- __le32 systemid_len;
- u8 systemid[OSD_SYSTEMID_LEN];
- __le64 long_name_offset; /* If !0 then offset-in-file */
- __le32 osdname_len; /* */
- u8 osdname[44]; /* Embbeded, Usually an asci uuid */
-} __packed;
-
-/*
- * The EXOFS device table - stored in object EXOFS_DEVTABLE_ID's data.
- * It contains the raid used for this multy-device FS and an array of
- * participating devices.
- */
-struct exofs_device_table {
- __le32 dt_version; /* == EXOFS_DT_VER */
- struct exofs_dt_data_map dt_data_map; /* Raid policy to use */
-
- /* Resurved space For future use. Total includeing this:
- * (8 * sizeof(le64))
- */
- __le64 __Resurved[4];
-
- __le64 dt_num_devices; /* Array size */
- struct exofs_dt_device_info dt_dev_table[]; /* Array of devices */
-} __packed;
-
-/****************************************************************************
- * 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)
-
-/*
- * The on-disk (optional) layout structure.
- * sits in an EXOFS_ATTR_INODE_FILE_LAYOUT or EXOFS_ATTR_INODE_DIR_LAYOUT
- * attribute, attached to any inode, usually to a directory.
- */
-
-enum exofs_inode_layout_gen_functions {
- LAYOUT_MOVING_WINDOW = 0,
- LAYOUT_IMPLICT = 1,
-};
-
-struct exofs_on_disk_inode_layout {
- __le16 gen_func; /* One of enum exofs_inode_layout_gen_functions */
- __le16 pad;
- union {
- /* gen_func == LAYOUT_MOVING_WINDOW (default) */
- struct exofs_layout_sliding_window {
- __le32 num_devices; /* first n devices in global-table*/
- } sliding_window __packed;
-
- /* gen_func == LAYOUT_IMPLICT */
- struct exofs_layout_implict_list {
- struct exofs_dt_data_map data_map;
- /* Variable array of size data_map.cb_num_comps. These
- * are device indexes of the devices in the global table
- */
- __le32 dev_indexes[];
- } implict __packed;
- };
-} __packed;
-
-static inline size_t exofs_on_disk_inode_layout_size(unsigned max_devs)
-{
- return sizeof(struct exofs_on_disk_inode_layout) +
- max_devs * sizeof(__le32);
-}
-
-#endif /*ifndef __EXOFS_COM_H__*/
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
deleted file mode 100644
index 42f9a0a0c4ca..000000000000
--- a/fs/exofs/dir.c
+++ /dev/null
@@ -1,661 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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);
- put_page(page);
-}
-
-static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr)
-{
- loff_t last_byte = inode->i_size;
-
- last_byte -= page_nr << PAGE_SHIFT;
- if (last_byte > PAGE_SIZE)
- last_byte = PAGE_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 bool 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_SIZE;
- struct exofs_dir_entry *p;
- char *error;
-
- /* if the page is the last one in the directory */
- if ((dir->i_size >> PAGE_SHIFT) == page->index) {
- limit = dir->i_size & ~PAGE_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 true;
-
-Ebadsize:
- EXOFS_ERR("ERROR [exofs_check_page]: "
- "size of directory(0x%lx) is not a multiple of chunk size\n",
- 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(0x%lx): %s - "
- "offset=%lu, inode=0x%llx, rec_len=%d, name_len=%d\n",
- dir->i_ino, error, (page->index<<PAGE_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(0x%lx) spans the page boundary"
- "offset=%lu, inode=0x%llx\n",
- dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
- _LLU(le64_to_cpu(p->inode_no)));
-fail:
- SetPageError(page);
- return false;
-}
-
-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 (unlikely(!PageChecked(page))) {
- if (PageError(page) || !exofs_check_page(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)
-{
- umode_t mode = inode->i_mode;
- de->file_type = exofs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
-}
-
-static int
-exofs_readdir(struct file *file, struct dir_context *ctx)
-{
- loff_t pos = ctx->pos;
- struct inode *inode = file_inode(file);
- unsigned int offset = pos & ~PAGE_MASK;
- unsigned long n = pos >> PAGE_SHIFT;
- unsigned long npages = dir_pages(inode);
- unsigned chunk_mask = ~(exofs_chunk_size(inode)-1);
- int need_revalidate = (file->f_version != inode->i_version);
-
- if (pos > inode->i_size - EXOFS_DIR_REC_LEN(1))
- return 0;
-
- 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 directory(0x%lx)\n",
- inode->i_ino);
- ctx->pos += PAGE_SIZE - offset;
- return PTR_ERR(page);
- }
- kaddr = page_address(page);
- if (unlikely(need_revalidate)) {
- if (offset) {
- offset = exofs_validate_entry(kaddr, offset,
- chunk_mask);
- ctx->pos = (n<<PAGE_SHIFT) + offset;
- }
- file->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 entry in directory(0x%lx)\n",
- inode->i_ino);
- exofs_put_page(page);
- return -EIO;
- }
- if (de->inode_no) {
- unsigned char t;
-
- if (de->file_type < EXOFS_FT_MAX)
- t = exofs_filetype_table[de->file_type];
- else
- t = DT_UNKNOWN;
-
- if (!dir_emit(ctx, de->name, de->name_len,
- le64_to_cpu(de->inode_no),
- t)) {
- exofs_put_page(page);
- return 0;
- }
- }
- ctx->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: zero-length entry in "
- "directory(0x%lx)\n",
- dir->i_ino);
- 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(d_inode(child), &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 FAILED => %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(dir);
- mark_inode_dirty(dir);
- return err;
-}
-
-int exofs_add_link(struct dentry *dentry, struct inode *inode)
-{
- struct inode *dir = d_inode(dentry->d_parent);
- 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_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 entry in directory(0x%lx)\n",
- inode->i_ino);
- 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=0x%lx\n",
- dentry, inode->i_ino);
- 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(rec_len - name_len);
- de->rec_len = cpu_to_le16(name_len);
- de = de1;
- }
- de->name_len = namelen;
- memcpy(de->name, name, namelen);
- de->inode_no = cpu_to_le64(inode->i_ino);
- exofs_set_de_type(de, inode);
- err = exofs_commit_chunk(page, pos, rec_len);
- dir->i_mtime = dir->i_ctime = current_time(dir);
- mark_inode_dirty(dir);
- sbi->s_numfiles++;
-
-out_put:
- exofs_put_page(page);
-out:
- return err;
-out_unlock:
- unlock_page(page);
- goto out_put;
-}
-
-int exofs_delete_entry(struct exofs_dir_entry *dir, struct page *page)
-{
- struct address_space *mapping = page->mapping;
- struct inode *inode = mapping->host;
- struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
- char *kaddr = page_address(page);
- unsigned from = ((char *)dir - kaddr) & ~(exofs_chunk_size(inode)-1);
- unsigned to = ((char *)dir - kaddr) + le16_to_cpu(dir->rec_len);
- loff_t pos;
- struct exofs_dir_entry *pde = NULL;
- struct exofs_dir_entry *de = (struct exofs_dir_entry *) (kaddr + from);
- int err;
-
- while (de < dir) {
- if (de->rec_len == 0) {
- EXOFS_ERR("ERROR: exofs_delete_entry:"
- "zero-length entry in directory(0x%lx)\n",
- inode->i_ino);
- err = -EIO;
- goto out;
- }
- pde = de;
- de = exofs_next_entry(de);
- }
- if (pde)
- from = (char *)pde - (char *)page_address(page);
- pos = page_offset(page) + from;
- lock_page(page);
- err = exofs_write_begin(NULL, page->mapping, pos, to - from, 0,
- &page, NULL);
- if (err)
- EXOFS_ERR("exofs_delete_entry: exofs_write_begin FAILED => %d\n",
- err);
- if (pde)
- pde->rec_len = cpu_to_le16(to - from);
- dir->inode_no = 0;
- if (likely(!err))
- err = exofs_commit_chunk(page, pos, to - from);
- inode->i_ctime = inode->i_mtime = current_time(inode);
- mark_inode_dirty(inode);
- sbi->s_numfiles--;
-out:
- exofs_put_page(page);
- return err;
-}
-
-/* kept aligned on 4 bytes */
-#define THIS_DIR ".\0\0"
-#define PARENT_DIR "..\0"
-
-int exofs_make_empty(struct inode *inode, struct inode *parent)
-{
- struct address_space *mapping = inode->i_mapping;
- struct page *page = grab_cache_page(mapping, 0);
- unsigned chunk_size = exofs_chunk_size(inode);
- struct exofs_dir_entry *de;
- int err;
- void *kaddr;
-
- if (!page)
- return -ENOMEM;
-
- err = exofs_write_begin(NULL, page->mapping, 0, chunk_size, 0,
- &page, NULL);
- if (err) {
- unlock_page(page);
- goto fail;
- }
-
- kaddr = kmap_atomic(page);
- de = (struct exofs_dir_entry *)kaddr;
- de->name_len = 1;
- de->rec_len = cpu_to_le16(EXOFS_DIR_REC_LEN(1));
- memcpy(de->name, THIS_DIR, sizeof(THIS_DIR));
- de->inode_no = cpu_to_le64(inode->i_ino);
- exofs_set_de_type(de, inode);
-
- de = (struct exofs_dir_entry *)(kaddr + EXOFS_DIR_REC_LEN(1));
- de->name_len = 2;
- de->rec_len = cpu_to_le16(chunk_size - EXOFS_DIR_REC_LEN(1));
- de->inode_no = cpu_to_le64(parent->i_ino);
- memcpy(de->name, PARENT_DIR, sizeof(PARENT_DIR));
- exofs_set_de_type(de, inode);
- kunmap_atomic(kaddr);
- err = exofs_commit_chunk(page, 0, chunk_size);
-fail:
- put_page(page);
- return err;
-}
-
-int exofs_empty_dir(struct inode *inode)
-{
- struct page *page = NULL;
- unsigned long i, npages = dir_pages(inode);
-
- for (i = 0; i < npages; i++) {
- char *kaddr;
- struct exofs_dir_entry *de;
- page = exofs_get_page(inode, i);
-
- if (IS_ERR(page))
- continue;
-
- kaddr = page_address(page);
- de = (struct exofs_dir_entry *)kaddr;
- kaddr += exofs_last_byte(inode, i) - EXOFS_DIR_REC_LEN(1);
-
- while ((char *)de <= kaddr) {
- if (de->rec_len == 0) {
- EXOFS_ERR("ERROR: exofs_empty_dir: "
- "zero-length directory entry"
- "kaddr=%p, de=%p\n", kaddr, de);
- goto not_empty;
- }
- if (de->inode_no != 0) {
- /* check for . and .. */
- if (de->name[0] != '.')
- goto not_empty;
- if (de->name_len > 2)
- goto not_empty;
- if (de->name_len < 2) {
- if (le64_to_cpu(de->inode_no) !=
- inode->i_ino)
- goto not_empty;
- } else if (de->name[1] != '.')
- goto not_empty;
- }
- de = exofs_next_entry(de);
- }
- exofs_put_page(page);
- }
- return 1;
-
-not_empty:
- exofs_put_page(page);
- return 0;
-}
-
-const struct file_operations exofs_dir_operations = {
- .llseek = generic_file_llseek,
- .read = generic_read_dir,
- .iterate_shared = exofs_readdir,
-};
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
deleted file mode 100644
index 2e86086bc940..000000000000
--- a/fs/exofs/exofs.h
+++ /dev/null
@@ -1,241 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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_H__
-#define __EXOFS_H__
-
-#include <linux/fs.h>
-#include <linux/time.h>
-#include <linux/backing-dev.h>
-#include <scsi/osd_ore.h>
-
-#include "common.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)
-
-struct exofs_dev {
- struct ore_dev ored;
- unsigned did;
- unsigned urilen;
- uint8_t *uri;
- struct kobject ed_kobj;
-};
-/*
- * our extension to the in-memory superblock
- */
-struct exofs_sb_info {
- struct backing_dev_info bdi; /* register our bdi with VFS */
- struct exofs_sb_stats s_ess; /* Written often, pre-allocate*/
- 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 */
-
- struct ore_layout layout; /* Default files layout */
- struct ore_comp one_comp; /* id & cred of partition id=0*/
- struct ore_components oc; /* comps for the partition */
- struct kobject s_kobj; /* holds per-sbi kobject */
-};
-
-/*
- * our extension to the in-memory inode
- */
-struct exofs_i_info {
- struct inode vfs_inode; /* normal in-memory inode */
- wait_queue_head_t i_wq; /* wait queue for inode */
- 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 */
- uint64_t i_commit_size; /* the object's written length */
- struct ore_comp one_comp; /* same component for all devices */
- struct ore_components oc; /* inode view of the device table */
-};
-
-static inline osd_id exofs_oi_objno(struct exofs_i_info *oi)
-{
- return oi->vfs_inode.i_ino + EXOFS_OBJ_OFF;
-}
-
-/*
- * 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);
-}
-
-/*
- * Maximum count of links to a file
- */
-#define EXOFS_LINK_MAX 32000
-
-/*************************
- * function declarations *
- *************************/
-
-/* inode.c */
-unsigned exofs_max_io_pages(struct ore_layout *layout,
- unsigned expected_pages);
-int exofs_setattr(struct dentry *, struct iattr *);
-int exofs_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata);
-extern struct inode *exofs_iget(struct super_block *, unsigned long);
-struct inode *exofs_new_inode(struct inode *, umode_t);
-extern int exofs_write_inode(struct inode *, struct writeback_control *wbc);
-extern void exofs_evict_inode(struct inode *);
-
-/* dir.c: */
-int exofs_add_link(struct dentry *, struct inode *);
-ino_t exofs_inode_by_name(struct inode *, struct dentry *);
-int exofs_delete_entry(struct exofs_dir_entry *, struct page *);
-int exofs_make_empty(struct inode *, struct inode *);
-struct exofs_dir_entry *exofs_find_entry(struct inode *, struct dentry *,
- struct page **);
-int exofs_empty_dir(struct inode *);
-struct exofs_dir_entry *exofs_dotdot(struct inode *, struct page **);
-ino_t exofs_parent_ino(struct dentry *child);
-int exofs_set_link(struct inode *, struct exofs_dir_entry *, struct page *,
- struct inode *);
-
-/* super.c */
-void exofs_make_credential(u8 cred_a[OSD_CAP_LEN],
- const struct osd_obj_id *obj);
-int exofs_sbi_write_stats(struct exofs_sb_info *sbi);
-
-/* sys.c */
-int exofs_sysfs_init(void);
-void exofs_sysfs_uninit(void);
-int exofs_sysfs_sb_add(struct exofs_sb_info *sbi,
- struct exofs_dt_device_info *dt_dev);
-void exofs_sysfs_sb_del(struct exofs_sb_info *sbi);
-int exofs_sysfs_odev_add(struct exofs_dev *edev,
- struct exofs_sb_info *sbi);
-void exofs_sysfs_dbg_print(void);
-
-/*********************
- * operation vectors *
- *********************/
-/* dir.c: */
-extern const struct file_operations exofs_dir_operations;
-
-/* file.c */
-extern const struct inode_operations exofs_file_inode_operations;
-extern const struct file_operations exofs_file_operations;
-
-/* inode.c */
-extern const struct address_space_operations exofs_aops;
-
-/* namei.c */
-extern const struct inode_operations exofs_dir_inode_operations;
-extern const struct inode_operations exofs_special_inode_operations;
-
-/* exofs_init_comps will initialize an ore_components device array
- * pointing to a single ore_comp struct, and a round-robin view
- * of the device table.
- * The first device of each inode is the [inode->ino % num_devices]
- * and the rest of the devices sequentially following where the
- * first device is after the last device.
- * It is assumed that the global device array at @sbi is twice
- * bigger and that the device table repeats twice.
- * See: exofs_read_lookup_dev_table()
- */
-static inline void exofs_init_comps(struct ore_components *oc,
- struct ore_comp *one_comp,
- struct exofs_sb_info *sbi, osd_id oid)
-{
- unsigned dev_mod = (unsigned)oid, first_dev;
-
- one_comp->obj.partition = sbi->one_comp.obj.partition;
- one_comp->obj.id = oid;
- exofs_make_credential(one_comp->cred, &one_comp->obj);
-
- oc->first_dev = 0;
- oc->numdevs = sbi->layout.group_width * sbi->layout.mirrors_p1 *
- sbi->layout.group_count;
- oc->single_comp = EC_SINGLE_COMP;
- oc->comps = one_comp;
-
- /* Round robin device view of the table */
- first_dev = (dev_mod * sbi->layout.mirrors_p1) % sbi->oc.numdevs;
- oc->ods = &sbi->oc.ods[first_dev];
-}
-
-#endif
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
deleted file mode 100644
index 28645f0640f7..000000000000
--- a/fs/exofs/file.c
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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 int exofs_release_file(struct inode *inode, struct file *filp)
-{
- return 0;
-}
-
-/* exofs_file_fsync - flush the inode to disk
- *
- * Note, in exofs all metadata is written as part of inode, regardless.
- * The writeout is synchronous
- */
-static int exofs_file_fsync(struct file *filp, loff_t start, loff_t end,
- int datasync)
-{
- struct inode *inode = filp->f_mapping->host;
- int ret;
-
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (ret)
- return ret;
-
- inode_lock(inode);
- ret = sync_inode_metadata(filp->f_mapping->host, 1);
- inode_unlock(inode);
- return ret;
-}
-
-static int exofs_flush(struct file *file, fl_owner_t id)
-{
- int ret = vfs_fsync(file, 0);
- /* TODO: Flush the OSD target */
- return ret;
-}
-
-const struct file_operations exofs_file_operations = {
- .llseek = generic_file_llseek,
- .read_iter = generic_file_read_iter,
- .write_iter = generic_file_write_iter,
- .mmap = generic_file_mmap,
- .open = generic_file_open,
- .release = exofs_release_file,
- .fsync = exofs_file_fsync,
- .flush = exofs_flush,
- .splice_read = generic_file_splice_read,
- .splice_write = iter_file_splice_write,
-};
-
-const struct inode_operations exofs_file_inode_operations = {
- .setattr = exofs_setattr,
-};
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
deleted file mode 100644
index 0ac62811b341..000000000000
--- a/fs/exofs/inode.c
+++ /dev/null
@@ -1,1514 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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/slab.h>
-
-#include "exofs.h"
-
-#define EXOFS_DBGMSG2(M...) do {} while (0)
-
-unsigned exofs_max_io_pages(struct ore_layout *layout,
- unsigned expected_pages)
-{
- unsigned pages = min_t(unsigned, expected_pages,
- layout->max_io_length / PAGE_SIZE);
-
- return pages;
-}
-
-struct page_collect {
- struct exofs_sb_info *sbi;
- struct inode *inode;
- unsigned expected_pages;
- struct ore_io_state *ios;
-
- struct page **pages;
- unsigned alloc_pages;
- unsigned nr_pages;
- unsigned long length;
- loff_t pg_first; /* keep 64bit also in 32-arches */
- bool read_4_write; /* This means two things: that the read is sync
- * And the pages should not be unlocked.
- */
- struct page *that_locked_page;
-};
-
-static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
- struct inode *inode)
-{
- struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
-
- pcol->sbi = sbi;
- pcol->inode = inode;
- pcol->expected_pages = expected_pages;
-
- pcol->ios = NULL;
- pcol->pages = NULL;
- pcol->alloc_pages = 0;
- pcol->nr_pages = 0;
- pcol->length = 0;
- pcol->pg_first = -1;
- pcol->read_4_write = false;
- pcol->that_locked_page = NULL;
-}
-
-static void _pcol_reset(struct page_collect *pcol)
-{
- pcol->expected_pages -= min(pcol->nr_pages, pcol->expected_pages);
-
- pcol->pages = NULL;
- pcol->alloc_pages = 0;
- pcol->nr_pages = 0;
- pcol->length = 0;
- pcol->pg_first = -1;
- pcol->ios = NULL;
- pcol->that_locked_page = NULL;
-
- /* this is probably the end of the loop but in writes
- * it might not end here. don't be left with nothing
- */
- if (!pcol->expected_pages)
- pcol->expected_pages =
- exofs_max_io_pages(&pcol->sbi->layout, ~0);
-}
-
-static int pcol_try_alloc(struct page_collect *pcol)
-{
- unsigned pages;
-
- /* TODO: easily support bio chaining */
- pages = exofs_max_io_pages(&pcol->sbi->layout, pcol->expected_pages);
-
- for (; pages; pages >>= 1) {
- pcol->pages = kmalloc(pages * sizeof(struct page *),
- GFP_KERNEL);
- if (likely(pcol->pages)) {
- pcol->alloc_pages = pages;
- return 0;
- }
- }
-
- EXOFS_ERR("Failed to kmalloc expected_pages=%u\n",
- pcol->expected_pages);
- return -ENOMEM;
-}
-
-static void pcol_free(struct page_collect *pcol)
-{
- kfree(pcol->pages);
- pcol->pages = NULL;
-
- if (pcol->ios) {
- ore_put_io_state(pcol->ios);
- pcol->ios = NULL;
- }
-}
-
-static int pcol_add_page(struct page_collect *pcol, struct page *page,
- unsigned len)
-{
- if (unlikely(pcol->nr_pages >= pcol->alloc_pages))
- return -ENOMEM;
-
- pcol->pages[pcol->nr_pages++] = page;
- pcol->length += len;
- return 0;
-}
-
-enum {PAGE_WAS_NOT_IN_IO = 17};
-static int update_read_page(struct page *page, int ret)
-{
- switch (ret) {
- case 0:
- /* Everything is OK */
- SetPageUptodate(page);
- if (PageError(page))
- ClearPageError(page);
- break;
- case -EFAULT:
- /* In this case we were trying to read something that wasn't on
- * disk yet - return a page full of zeroes. This should be OK,
- * because the object should be empty (if there was a write
- * before this read, the read would be waiting with the page
- * locked */
- clear_highpage(page);
-
- SetPageUptodate(page);
- if (PageError(page))
- ClearPageError(page);
- EXOFS_DBGMSG("recovered read error\n");
- /* fall through */
- case PAGE_WAS_NOT_IN_IO:
- ret = 0; /* recovered error */
- break;
- default:
- SetPageError(page);
- }
- return ret;
-}
-
-static void update_write_page(struct page *page, int ret)
-{
- if (unlikely(ret == PAGE_WAS_NOT_IN_IO))
- return; /* don't pass start don't collect $200 */
-
- if (ret) {
- mapping_set_error(page->mapping, ret);
- SetPageError(page);
- }
- end_page_writeback(page);
-}
-
-/* Called at the end of reads, to optionally unlock pages and update their
- * status.
- */
-static int __readpages_done(struct page_collect *pcol)
-{
- int i;
- u64 good_bytes;
- u64 length = 0;
- int ret = ore_check_io(pcol->ios, NULL);
-
- if (likely(!ret)) {
- good_bytes = pcol->length;
- ret = PAGE_WAS_NOT_IN_IO;
- } else {
- good_bytes = 0;
- }
-
- EXOFS_DBGMSG2("readpages_done(0x%lx) good_bytes=0x%llx"
- " length=0x%lx nr_pages=%u\n",
- pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
- pcol->nr_pages);
-
- for (i = 0; i < pcol->nr_pages; i++) {
- struct page *page = pcol->pages[i];
- struct inode *inode = page->mapping->host;
- int page_stat;
-
- if (inode != pcol->inode)
- continue; /* osd might add more pages at end */
-
- if (likely(length < good_bytes))
- page_stat = 0;
- else
- page_stat = ret;
-
- EXOFS_DBGMSG2(" readpages_done(0x%lx, 0x%lx) %s\n",
- inode->i_ino, page->index,
- page_stat ? "bad_bytes" : "good_bytes");
-
- ret = update_read_page(page, page_stat);
- if (!pcol->read_4_write)
- unlock_page(page);
- length += PAGE_SIZE;
- }
-
- pcol_free(pcol);
- EXOFS_DBGMSG2("readpages_done END\n");
- return ret;
-}
-
-/* callback of async reads */
-static void readpages_done(struct ore_io_state *ios, void *p)
-{
- struct page_collect *pcol = p;
-
- __readpages_done(pcol);
- atomic_dec(&pcol->sbi->s_curr_pending);
- kfree(pcol);
-}
-
-static void _unlock_pcol_pages(struct page_collect *pcol, int ret, int rw)
-{
- int i;
-
- for (i = 0; i < pcol->nr_pages; i++) {
- struct page *page = pcol->pages[i];
-
- if (rw == READ)
- update_read_page(page, ret);
- else
- update_write_page(page, ret);
-
- unlock_page(page);
- }
-}
-
-static int _maybe_not_all_in_one_io(struct ore_io_state *ios,
- struct page_collect *pcol_src, struct page_collect *pcol)
-{
- /* length was wrong or offset was not page aligned */
- BUG_ON(pcol_src->nr_pages < ios->nr_pages);
-
- if (pcol_src->nr_pages > ios->nr_pages) {
- struct page **src_page;
- unsigned pages_less = pcol_src->nr_pages - ios->nr_pages;
- unsigned long len_less = pcol_src->length - ios->length;
- unsigned i;
- int ret;
-
- /* This IO was trimmed */
- pcol_src->nr_pages = ios->nr_pages;
- pcol_src->length = ios->length;
-
- /* Left over pages are passed to the next io */
- pcol->expected_pages += pages_less;
- pcol->nr_pages = pages_less;
- pcol->length = len_less;
- src_page = pcol_src->pages + pcol_src->nr_pages;
- pcol->pg_first = (*src_page)->index;
-
- ret = pcol_try_alloc(pcol);
- if (unlikely(ret))
- return ret;
-
- for (i = 0; i < pages_less; ++i)
- pcol->pages[i] = *src_page++;
-
- EXOFS_DBGMSG("Length was adjusted nr_pages=0x%x "
- "pages_less=0x%x expected_pages=0x%x "
- "next_offset=0x%llx next_len=0x%lx\n",
- pcol_src->nr_pages, pages_less, pcol->expected_pages,
- pcol->pg_first * PAGE_SIZE, pcol->length);
- }
- return 0;
-}
-
-static int read_exec(struct page_collect *pcol)
-{
- struct exofs_i_info *oi = exofs_i(pcol->inode);
- struct ore_io_state *ios;
- struct page_collect *pcol_copy = NULL;
- int ret;
-
- if (!pcol->pages)
- return 0;
-
- if (!pcol->ios) {
- int ret = ore_get_rw_state(&pcol->sbi->layout, &oi->oc, true,
- pcol->pg_first << PAGE_SHIFT,
- pcol->length, &pcol->ios);
-
- if (ret)
- return ret;
- }
-
- ios = pcol->ios;
- ios->pages = pcol->pages;
-
- if (pcol->read_4_write) {
- ore_read(pcol->ios);
- return __readpages_done(pcol);
- }
-
- pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL);
- if (!pcol_copy) {
- ret = -ENOMEM;
- goto err;
- }
-
- *pcol_copy = *pcol;
- ios->done = readpages_done;
- ios->private = pcol_copy;
-
- /* pages ownership was passed to pcol_copy */
- _pcol_reset(pcol);
-
- ret = _maybe_not_all_in_one_io(ios, pcol_copy, pcol);
- if (unlikely(ret))
- goto err;
-
- EXOFS_DBGMSG2("read_exec(0x%lx) offset=0x%llx length=0x%llx\n",
- pcol->inode->i_ino, _LLU(ios->offset), _LLU(ios->length));
-
- ret = ore_read(ios);
- if (unlikely(ret))
- goto err;
-
- atomic_inc(&pcol->sbi->s_curr_pending);
-
- return 0;
-
-err:
- if (!pcol_copy) /* Failed before ownership transfer */
- pcol_copy = pcol;
- _unlock_pcol_pages(pcol_copy, ret, READ);
- pcol_free(pcol_copy);
- kfree(pcol_copy);
-
- return ret;
-}
-
-/* readpage_strip is called either directly from readpage() or by the VFS from
- * within read_cache_pages(), to add one more page to be read. It will try to
- * collect as many contiguous pages as posible. If a discontinuity is
- * encountered, or it runs out of resources, it will submit the previous segment
- * and will start a new collection. Eventually caller must submit the last
- * segment if present.
- */
-static int readpage_strip(void *data, struct page *page)
-{
- struct page_collect *pcol = data;
- struct inode *inode = pcol->inode;
- struct exofs_i_info *oi = exofs_i(inode);
- loff_t i_size = i_size_read(inode);
- pgoff_t end_index = i_size >> PAGE_SHIFT;
- size_t len;
- int ret;
-
- BUG_ON(!PageLocked(page));
-
- /* FIXME: Just for debugging, will be removed */
- if (PageUptodate(page))
- EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino,
- page->index);
-
- pcol->that_locked_page = page;
-
- if (page->index < end_index)
- len = PAGE_SIZE;
- else if (page->index == end_index)
- len = i_size & ~PAGE_MASK;
- else
- len = 0;
-
- if (!len || !obj_created(oi)) {
- /* this will be out of bounds, or doesn't exist yet.
- * Current page is cleared and the request is split
- */
- clear_highpage(page);
-
- SetPageUptodate(page);
- if (PageError(page))
- ClearPageError(page);
-
- if (!pcol->read_4_write)
- unlock_page(page);
- EXOFS_DBGMSG("readpage_strip(0x%lx) empty page len=%zx "
- "read_4_write=%d index=0x%lx end_index=0x%lx "
- "splitting\n", inode->i_ino, len,
- pcol->read_4_write, page->index, end_index);
-
- return read_exec(pcol);
- }
-
-try_again:
-
- if (unlikely(pcol->pg_first == -1)) {
- pcol->pg_first = page->index;
- } else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
- page->index)) {
- /* Discontinuity detected, split the request */
- ret = read_exec(pcol);
- if (unlikely(ret))
- goto fail;
- goto try_again;
- }
-
- if (!pcol->pages) {
- ret = pcol_try_alloc(pcol);
- if (unlikely(ret))
- goto fail;
- }
-
- if (len != PAGE_SIZE)
- zero_user(page, len, PAGE_SIZE - len);
-
- EXOFS_DBGMSG2(" readpage_strip(0x%lx, 0x%lx) len=0x%zx\n",
- inode->i_ino, page->index, len);
-
- ret = pcol_add_page(pcol, page, len);
- if (ret) {
- EXOFS_DBGMSG2("Failed pcol_add_page pages[i]=%p "
- "this_len=0x%zx nr_pages=%u length=0x%lx\n",
- page, len, pcol->nr_pages, pcol->length);
-
- /* split the request, and start again with current page */
- ret = read_exec(pcol);
- if (unlikely(ret))
- goto fail;
-
- goto try_again;
- }
-
- return 0;
-
-fail:
- /* SetPageError(page); ??? */
- unlock_page(page);
- return ret;
-}
-
-static int exofs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
-{
- struct page_collect pcol;
- int ret;
-
- _pcol_init(&pcol, nr_pages, mapping->host);
-
- ret = read_cache_pages(mapping, pages, readpage_strip, &pcol);
- if (ret) {
- EXOFS_ERR("read_cache_pages => %d\n", ret);
- return ret;
- }
-
- ret = read_exec(&pcol);
- if (unlikely(ret))
- return ret;
-
- return read_exec(&pcol);
-}
-
-static int _readpage(struct page *page, bool read_4_write)
-{
- struct page_collect pcol;
- int ret;
-
- _pcol_init(&pcol, 1, page->mapping->host);
-
- pcol.read_4_write = read_4_write;
- ret = readpage_strip(&pcol, page);
- if (ret) {
- EXOFS_ERR("_readpage => %d\n", ret);
- return ret;
- }
-
- return read_exec(&pcol);
-}
-
-/*
- * We don't need the file
- */
-static int exofs_readpage(struct file *file, struct page *page)
-{
- return _readpage(page, false);
-}
-
-/* Callback for osd_write. All writes are asynchronous */
-static void writepages_done(struct ore_io_state *ios, void *p)
-{
- struct page_collect *pcol = p;
- int i;
- u64 good_bytes;
- u64 length = 0;
- int ret = ore_check_io(ios, NULL);
-
- atomic_dec(&pcol->sbi->s_curr_pending);
-
- if (likely(!ret)) {
- good_bytes = pcol->length;
- ret = PAGE_WAS_NOT_IN_IO;
- } else {
- good_bytes = 0;
- }
-
- EXOFS_DBGMSG2("writepages_done(0x%lx) good_bytes=0x%llx"
- " length=0x%lx nr_pages=%u\n",
- pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
- pcol->nr_pages);
-
- for (i = 0; i < pcol->nr_pages; i++) {
- struct page *page = pcol->pages[i];
- struct inode *inode = page->mapping->host;
- int page_stat;
-
- if (inode != pcol->inode)
- continue; /* osd might add more pages to a bio */
-
- if (likely(length < good_bytes))
- page_stat = 0;
- else
- page_stat = ret;
-
- update_write_page(page, page_stat);
- unlock_page(page);
- EXOFS_DBGMSG2(" writepages_done(0x%lx, 0x%lx) status=%d\n",
- inode->i_ino, page->index, page_stat);
-
- length += PAGE_SIZE;
- }
-
- pcol_free(pcol);
- kfree(pcol);
- EXOFS_DBGMSG2("writepages_done END\n");
-}
-
-static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
-{
- struct page_collect *pcol = priv;
- pgoff_t index = offset / PAGE_SIZE;
-
- if (!pcol->that_locked_page ||
- (pcol->that_locked_page->index != index)) {
- struct page *page;
- loff_t i_size = i_size_read(pcol->inode);
-
- if (offset >= i_size) {
- *uptodate = true;
- EXOFS_DBGMSG2("offset >= i_size index=0x%lx\n", index);
- return ZERO_PAGE(0);
- }
-
- page = find_get_page(pcol->inode->i_mapping, index);
- if (!page) {
- page = find_or_create_page(pcol->inode->i_mapping,
- index, GFP_NOFS);
- if (unlikely(!page)) {
- EXOFS_DBGMSG("grab_cache_page Failed "
- "index=0x%llx\n", _LLU(index));
- return NULL;
- }
- unlock_page(page);
- }
- *uptodate = PageUptodate(page);
- EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate);
- return page;
- } else {
- EXOFS_DBGMSG2("YES that_locked_page index=0x%lx\n",
- pcol->that_locked_page->index);
- *uptodate = true;
- return pcol->that_locked_page;
- }
-}
-
-static void __r4w_put_page(void *priv, struct page *page)
-{
- struct page_collect *pcol = priv;
-
- if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) {
- EXOFS_DBGMSG2("index=0x%lx\n", page->index);
- put_page(page);
- return;
- }
- EXOFS_DBGMSG2("that_locked_page index=0x%lx\n",
- ZERO_PAGE(0) == page ? -1 : page->index);
-}
-
-static const struct _ore_r4w_op _r4w_op = {
- .get_page = &__r4w_get_page,
- .put_page = &__r4w_put_page,
-};
-
-static int write_exec(struct page_collect *pcol)
-{
- struct exofs_i_info *oi = exofs_i(pcol->inode);
- struct ore_io_state *ios;
- struct page_collect *pcol_copy = NULL;
- int ret;
-
- if (!pcol->pages)
- return 0;
-
- BUG_ON(pcol->ios);
- ret = ore_get_rw_state(&pcol->sbi->layout, &oi->oc, false,
- pcol->pg_first << PAGE_SHIFT,
- pcol->length, &pcol->ios);
- if (unlikely(ret))
- goto err;
-
- pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL);
- if (!pcol_copy) {
- EXOFS_ERR("write_exec: Failed to kmalloc(pcol)\n");
- ret = -ENOMEM;
- goto err;
- }
-
- *pcol_copy = *pcol;
-
- ios = pcol->ios;
- ios->pages = pcol_copy->pages;
- ios->done = writepages_done;
- ios->r4w = &_r4w_op;
- ios->private = pcol_copy;
-
- /* pages ownership was passed to pcol_copy */
- _pcol_reset(pcol);
-
- ret = _maybe_not_all_in_one_io(ios, pcol_copy, pcol);
- if (unlikely(ret))
- goto err;
-
- EXOFS_DBGMSG2("write_exec(0x%lx) offset=0x%llx length=0x%llx\n",
- pcol->inode->i_ino, _LLU(ios->offset), _LLU(ios->length));
-
- ret = ore_write(ios);
- if (unlikely(ret)) {
- EXOFS_ERR("write_exec: ore_write() Failed\n");
- goto err;
- }
-
- atomic_inc(&pcol->sbi->s_curr_pending);
- return 0;
-
-err:
- if (!pcol_copy) /* Failed before ownership transfer */
- pcol_copy = pcol;
- _unlock_pcol_pages(pcol_copy, ret, WRITE);
- pcol_free(pcol_copy);
- kfree(pcol_copy);
-
- return ret;
-}
-
-/* writepage_strip is called either directly from writepage() or by the VFS from
- * within write_cache_pages(), to add one more page to be written to storage.
- * It will try to collect as many contiguous pages as possible. If a
- * discontinuity is encountered or it runs out of resources it will submit the
- * previous segment and will start a new collection.
- * Eventually caller must submit the last segment if present.
- */
-static int writepage_strip(struct page *page,
- struct writeback_control *wbc_unused, void *data)
-{
- struct page_collect *pcol = data;
- struct inode *inode = pcol->inode;
- struct exofs_i_info *oi = exofs_i(inode);
- loff_t i_size = i_size_read(inode);
- pgoff_t end_index = i_size >> PAGE_SHIFT;
- size_t len;
- int ret;
-
- BUG_ON(!PageLocked(page));
-
- ret = wait_obj_created(oi);
- if (unlikely(ret))
- goto fail;
-
- if (page->index < end_index)
- /* in this case, the page is within the limits of the file */
- len = PAGE_SIZE;
- else {
- len = i_size & ~PAGE_MASK;
-
- if (page->index > end_index || !len) {
- /* in this case, the page is outside the limits
- * (truncate in progress)
- */
- ret = write_exec(pcol);
- if (unlikely(ret))
- goto fail;
- if (PageError(page))
- ClearPageError(page);
- unlock_page(page);
- EXOFS_DBGMSG("writepage_strip(0x%lx, 0x%lx) "
- "outside the limits\n",
- inode->i_ino, page->index);
- return 0;
- }
- }
-
-try_again:
-
- if (unlikely(pcol->pg_first == -1)) {
- pcol->pg_first = page->index;
- } else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
- page->index)) {
- /* Discontinuity detected, split the request */
- ret = write_exec(pcol);
- if (unlikely(ret))
- goto fail;
-
- EXOFS_DBGMSG("writepage_strip(0x%lx, 0x%lx) Discontinuity\n",
- inode->i_ino, page->index);
- goto try_again;
- }
-
- if (!pcol->pages) {
- ret = pcol_try_alloc(pcol);
- if (unlikely(ret))
- goto fail;
- }
-
- EXOFS_DBGMSG2(" writepage_strip(0x%lx, 0x%lx) len=0x%zx\n",
- inode->i_ino, page->index, len);
-
- ret = pcol_add_page(pcol, page, len);
- if (unlikely(ret)) {
- EXOFS_DBGMSG2("Failed pcol_add_page "
- "nr_pages=%u total_length=0x%lx\n",
- pcol->nr_pages, pcol->length);
-
- /* split the request, next loop will start again */
- ret = write_exec(pcol);
- if (unlikely(ret)) {
- EXOFS_DBGMSG("write_exec failed => %d", ret);
- goto fail;
- }
-
- goto try_again;
- }
-
- BUG_ON(PageWriteback(page));
- set_page_writeback(page);
-
- return 0;
-
-fail:
- EXOFS_DBGMSG("Error: writepage_strip(0x%lx, 0x%lx)=>%d\n",
- inode->i_ino, page->index, ret);
- mapping_set_error(page->mapping, -EIO);
- unlock_page(page);
- return ret;
-}
-
-static int exofs_writepages(struct address_space *mapping,
- struct writeback_control *wbc)
-{
- struct page_collect pcol;
- long start, end, expected_pages;
- int ret;
-
- start = wbc->range_start >> PAGE_SHIFT;
- end = (wbc->range_end == LLONG_MAX) ?
- start + mapping->nrpages :
- wbc->range_end >> PAGE_SHIFT;
-
- if (start || end)
- expected_pages = end - start + 1;
- else
- expected_pages = mapping->nrpages;
-
- if (expected_pages < 32L)
- expected_pages = 32L;
-
- EXOFS_DBGMSG2("inode(0x%lx) wbc->start=0x%llx wbc->end=0x%llx "
- "nrpages=%lu start=0x%lx end=0x%lx expected_pages=%ld\n",
- mapping->host->i_ino, wbc->range_start, wbc->range_end,
- mapping->nrpages, start, end, expected_pages);
-
- _pcol_init(&pcol, expected_pages, mapping->host);
-
- ret = write_cache_pages(mapping, wbc, writepage_strip, &pcol);
- if (unlikely(ret)) {
- EXOFS_ERR("write_cache_pages => %d\n", ret);
- return ret;
- }
-
- ret = write_exec(&pcol);
- if (unlikely(ret))
- return ret;
-
- if (wbc->sync_mode == WB_SYNC_ALL) {
- return write_exec(&pcol); /* pump the last reminder */
- } else if (pcol.nr_pages) {
- /* not SYNC let the reminder join the next writeout */
- unsigned i;
-
- for (i = 0; i < pcol.nr_pages; i++) {
- struct page *page = pcol.pages[i];
-
- end_page_writeback(page);
- set_page_dirty(page);
- unlock_page(page);
- }
- }
- return 0;
-}
-
-/*
-static int exofs_writepage(struct page *page, struct writeback_control *wbc)
-{
- struct page_collect pcol;
- int ret;
-
- _pcol_init(&pcol, 1, page->mapping->host);
-
- ret = writepage_strip(page, NULL, &pcol);
- if (ret) {
- EXOFS_ERR("exofs_writepage => %d\n", ret);
- return ret;
- }
-
- return write_exec(&pcol);
-}
-*/
-/* i_mutex held using inode->i_size directly */
-static void _write_failed(struct inode *inode, loff_t to)
-{
- if (to > inode->i_size)
- truncate_pagecache(inode, inode->i_size);
-}
-
-int exofs_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
-{
- int ret = 0;
- struct page *page;
-
- page = *pagep;
- if (page == NULL) {
- page = grab_cache_page_write_begin(mapping, pos >> PAGE_SHIFT,
- flags);
- if (!page) {
- EXOFS_DBGMSG("grab_cache_page_write_begin failed\n");
- return -ENOMEM;
- }
- *pagep = page;
- }
-
- /* read modify write */
- if (!PageUptodate(page) && (len != PAGE_SIZE)) {
- loff_t i_size = i_size_read(mapping->host);
- pgoff_t end_index = i_size >> PAGE_SHIFT;
-
- if (page->index > end_index) {
- clear_highpage(page);
- SetPageUptodate(page);
- } else {
- ret = _readpage(page, true);
- if (ret) {
- unlock_page(page);
- EXOFS_DBGMSG("__readpage failed\n");
- }
- }
- }
- return ret;
-}
-
-static int exofs_write_begin_export(struct file *file,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
-{
- *pagep = NULL;
-
- return exofs_write_begin(file, mapping, pos, len, flags, pagep,
- fsdata);
-}
-
-static int exofs_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
-{
- struct inode *inode = mapping->host;
- loff_t last_pos = pos + copied;
-
- if (!PageUptodate(page)) {
- if (copied < len) {
- _write_failed(inode, pos + len);
- copied = 0;
- goto out;
- }
- SetPageUptodate(page);
- }
- if (last_pos > inode->i_size) {
- i_size_write(inode, last_pos);
- mark_inode_dirty(inode);
- }
- set_page_dirty(page);
-out:
- unlock_page(page);
- put_page(page);
- return copied;
-}
-
-static int exofs_releasepage(struct page *page, gfp_t gfp)
-{
- EXOFS_DBGMSG("page 0x%lx\n", page->index);
- WARN_ON(1);
- return 0;
-}
-
-static void exofs_invalidatepage(struct page *page, unsigned int offset,
- unsigned int length)
-{
- EXOFS_DBGMSG("page 0x%lx offset 0x%x length 0x%x\n",
- page->index, offset, length);
- WARN_ON(1);
-}
-
-
- /* TODO: Should be easy enough to do proprly */
-static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- return 0;
-}
-
-const struct address_space_operations exofs_aops = {
- .readpage = exofs_readpage,
- .readpages = exofs_readpages,
- .writepage = NULL,
- .writepages = exofs_writepages,
- .write_begin = exofs_write_begin_export,
- .write_end = exofs_write_end,
- .releasepage = exofs_releasepage,
- .set_page_dirty = __set_page_dirty_nobuffers,
- .invalidatepage = exofs_invalidatepage,
-
- /* Not implemented Yet */
- .bmap = NULL, /* TODO: use osd's OSD_ACT_READ_MAP */
- .direct_IO = exofs_direct_IO,
-
- /* With these NULL has special meaning or default is not exported */
- .migratepage = NULL,
- .launder_page = NULL,
- .is_partially_uptodate = NULL,
- .error_remove_page = NULL,
-};
-
-/******************************************************************************
- * INODE OPERATIONS
- *****************************************************************************/
-
-/*
- * Test whether an inode is a fast symlink.
- */
-static inline int exofs_inode_is_fast_symlink(struct inode *inode)
-{
- struct exofs_i_info *oi = exofs_i(inode);
-
- return S_ISLNK(inode->i_mode) && (oi->i_data[0] != 0);
-}
-
-static int _do_truncate(struct inode *inode, loff_t newsize)
-{
- struct exofs_i_info *oi = exofs_i(inode);
- struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
- int ret;
-
- inode->i_mtime = inode->i_ctime = current_time(inode);
-
- ret = ore_truncate(&sbi->layout, &oi->oc, (u64)newsize);
- if (likely(!ret))
- truncate_setsize(inode, newsize);
-
- EXOFS_DBGMSG2("(0x%lx) size=0x%llx ret=>%d\n",
- inode->i_ino, newsize, ret);
- return ret;
-}
-
-/*
- * Set inode attributes - update size attribute on OSD if needed,
- * otherwise just call generic functions.
- */
-int exofs_setattr(struct dentry *dentry, struct iattr *iattr)
-{
- struct inode *inode = d_inode(dentry);
- int error;
-
- /* if we are about to modify an object, and it hasn't been
- * created yet, wait
- */
- error = wait_obj_created(exofs_i(inode));
- if (unlikely(error))
- return error;
-
- error = setattr_prepare(dentry, iattr);
- if (unlikely(error))
- return error;
-
- if ((iattr->ia_valid & ATTR_SIZE) &&
- iattr->ia_size != i_size_read(inode)) {
- error = _do_truncate(inode, iattr->ia_size);
- if (unlikely(error))
- return error;
- }
-
- setattr_copy(inode, iattr);
- mark_inode_dirty(inode);
- return 0;
-}
-
-static const struct osd_attr g_attr_inode_file_layout = ATTR_DEF(
- EXOFS_APAGE_FS_DATA,
- EXOFS_ATTR_INODE_FILE_LAYOUT,
- 0);
-static const struct osd_attr g_attr_inode_dir_layout = ATTR_DEF(
- EXOFS_APAGE_FS_DATA,
- EXOFS_ATTR_INODE_DIR_LAYOUT,
- 0);
-
-/*
- * Read the Linux inode info from the OSD, and return it as is. In exofs the
- * inode info is in an application specific page/attribute of the osd-object.
- */
-static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
- struct exofs_fcb *inode)
-{
- struct exofs_sb_info *sbi = sb->s_fs_info;
- struct osd_attr attrs[] = {
- [0] = g_attr_inode_data,
- [1] = g_attr_inode_file_layout,
- [2] = g_attr_inode_dir_layout,
- };
- struct ore_io_state *ios;
- struct exofs_on_disk_inode_layout *layout;
- int ret;
-
- ret = ore_get_io_state(&sbi->layout, &oi->oc, &ios);
- if (unlikely(ret)) {
- EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__);
- return ret;
- }
-
- attrs[1].len = exofs_on_disk_inode_layout_size(sbi->oc.numdevs);
- attrs[2].len = exofs_on_disk_inode_layout_size(sbi->oc.numdevs);
-
- ios->in_attr = attrs;
- ios->in_attr_len = ARRAY_SIZE(attrs);
-
- ret = ore_read(ios);
- if (unlikely(ret)) {
- EXOFS_ERR("object(0x%llx) corrupted, return empty file=>%d\n",
- _LLU(oi->one_comp.obj.id), ret);
- memset(inode, 0, sizeof(*inode));
- inode->i_mode = 0040000 | (0777 & ~022);
- /* If object is lost on target we might as well enable it's
- * delete.
- */
- ret = 0;
- goto out;
- }
-
- ret = extract_attr_from_ios(ios, &attrs[0]);
- if (ret) {
- EXOFS_ERR("%s: extract_attr 0 of inode failed\n", __func__);
- goto out;
- }
- WARN_ON(attrs[0].len != EXOFS_INO_ATTR_SIZE);
- memcpy(inode, attrs[0].val_ptr, EXOFS_INO_ATTR_SIZE);
-
- ret = extract_attr_from_ios(ios, &attrs[1]);
- if (ret) {
- EXOFS_ERR("%s: extract_attr 1 of inode failed\n", __func__);
- goto out;
- }
- if (attrs[1].len) {
- layout = attrs[1].val_ptr;
- if (layout->gen_func != cpu_to_le16(LAYOUT_MOVING_WINDOW)) {
- EXOFS_ERR("%s: unsupported files layout %d\n",
- __func__, layout->gen_func);
- ret = -ENOTSUPP;
- goto out;
- }
- }
-
- ret = extract_attr_from_ios(ios, &attrs[2]);
- if (ret) {
- EXOFS_ERR("%s: extract_attr 2 of inode failed\n", __func__);
- goto out;
- }
- if (attrs[2].len) {
- layout = attrs[2].val_ptr;
- if (layout->gen_func != cpu_to_le16(LAYOUT_MOVING_WINDOW)) {
- EXOFS_ERR("%s: unsupported meta-data layout %d\n",
- __func__, layout->gen_func);
- ret = -ENOTSUPP;
- goto out;
- }
- }
-
-out:
- ore_put_io_state(ios);
- return ret;
-}
-
-static void __oi_init(struct exofs_i_info *oi)
-{
- init_waitqueue_head(&oi->i_wq);
- oi->i_flags = 0;
-}
-/*
- * Fill in an inode read from the OSD and set it up for use
- */
-struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
-{
- struct exofs_i_info *oi;
- struct exofs_fcb fcb;
- struct inode *inode;
- int ret;
-
- inode = iget_locked(sb, ino);
- if (!inode)
- return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW))
- return inode;
- oi = exofs_i(inode);
- __oi_init(oi);
- exofs_init_comps(&oi->oc, &oi->one_comp, sb->s_fs_info,
- exofs_oi_objno(oi));
-
- /* read the inode from the osd */
- ret = exofs_get_inode(sb, oi, &fcb);
- if (ret)
- goto bad_inode;
-
- set_obj_created(oi);
-
- /* copy stuff from on-disk struct to in-memory struct */
- inode->i_mode = le16_to_cpu(fcb.i_mode);
- i_uid_write(inode, le32_to_cpu(fcb.i_uid));
- i_gid_write(inode, le32_to_cpu(fcb.i_gid));
- set_nlink(inode, le16_to_cpu(fcb.i_links_count));
- inode->i_ctime.tv_sec = (signed)le32_to_cpu(fcb.i_ctime);
- inode->i_atime.tv_sec = (signed)le32_to_cpu(fcb.i_atime);
- inode->i_mtime.tv_sec = (signed)le32_to_cpu(fcb.i_mtime);
- inode->i_ctime.tv_nsec =
- inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = 0;
- oi->i_commit_size = le64_to_cpu(fcb.i_size);
- i_size_write(inode, oi->i_commit_size);
- inode->i_blkbits = EXOFS_BLKSHIFT;
- inode->i_generation = le32_to_cpu(fcb.i_generation);
-
- oi->i_dir_start_lookup = 0;
-
- if ((inode->i_nlink == 0) && (inode->i_mode == 0)) {
- ret = -ESTALE;
- goto bad_inode;
- }
-
- if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
- if (fcb.i_data[0])
- inode->i_rdev =
- old_decode_dev(le32_to_cpu(fcb.i_data[0]));
- else
- inode->i_rdev =
- new_decode_dev(le32_to_cpu(fcb.i_data[1]));
- } else {
- memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
- }
-
- if (S_ISREG(inode->i_mode)) {
- inode->i_op = &exofs_file_inode_operations;
- inode->i_fop = &exofs_file_operations;
- inode->i_mapping->a_ops = &exofs_aops;
- } else if (S_ISDIR(inode->i_mode)) {
- inode->i_op = &exofs_dir_inode_operations;
- inode->i_fop = &exofs_dir_operations;
- inode->i_mapping->a_ops = &exofs_aops;
- } else if (S_ISLNK(inode->i_mode)) {
- if (exofs_inode_is_fast_symlink(inode)) {
- inode->i_op = &simple_symlink_inode_operations;
- inode->i_link = (char *)oi->i_data;
- } else {
- inode->i_op = &page_symlink_inode_operations;
- inode_nohighmem(inode);
- inode->i_mapping->a_ops = &exofs_aops;
- }
- } else {
- inode->i_op = &exofs_special_inode_operations;
- if (fcb.i_data[0])
- init_special_inode(inode, inode->i_mode,
- old_decode_dev(le32_to_cpu(fcb.i_data[0])));
- else
- init_special_inode(inode, inode->i_mode,
- new_decode_dev(le32_to_cpu(fcb.i_data[1])));
- }
-
- unlock_new_inode(inode);
- return inode;
-
-bad_inode:
- iget_failed(inode);
- return ERR_PTR(ret);
-}
-
-int __exofs_wait_obj_created(struct exofs_i_info *oi)
-{
- if (!obj_created(oi)) {
- EXOFS_DBGMSG("!obj_created\n");
- BUG_ON(!obj_2bcreated(oi));
- wait_event(oi->i_wq, obj_created(oi));
- EXOFS_DBGMSG("wait_event done\n");
- }
- return unlikely(is_bad_inode(&oi->vfs_inode)) ? -EIO : 0;
-}
-
-/*
- * Callback function from exofs_new_inode(). The important thing is that we
- * set the obj_created flag so that other methods know that the object exists on
- * the OSD.
- */
-static void create_done(struct ore_io_state *ios, void *p)
-{
- struct inode *inode = p;
- struct exofs_i_info *oi = exofs_i(inode);
- struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
- int ret;
-
- ret = ore_check_io(ios, NULL);
- ore_put_io_state(ios);
-
- atomic_dec(&sbi->s_curr_pending);
-
- if (unlikely(ret)) {
- EXOFS_ERR("object=0x%llx creation failed in pid=0x%llx",
- _LLU(exofs_oi_objno(oi)),
- _LLU(oi->one_comp.obj.partition));
- /*TODO: When FS is corrupted creation can fail, object already
- * exist. Get rid of this asynchronous creation, if exist
- * increment the obj counter and try the next object. Until we
- * succeed. All these dangling objects will be made into lost
- * files by chkfs.exofs
- */
- }
-
- set_obj_created(oi);
-
- wake_up(&oi->i_wq);
-}
-
-/*
- * Set up a new inode and create an object for it on the OSD
- */
-struct inode *exofs_new_inode(struct inode *dir, umode_t mode)
-{
- struct super_block *sb = dir->i_sb;
- struct exofs_sb_info *sbi = sb->s_fs_info;
- struct inode *inode;
- struct exofs_i_info *oi;
- struct ore_io_state *ios;
- int ret;
-
- inode = new_inode(sb);
- if (!inode)
- return ERR_PTR(-ENOMEM);
-
- oi = exofs_i(inode);
- __oi_init(oi);
-
- set_obj_2bcreated(oi);
-
- inode_init_owner(inode, dir, mode);
- inode->i_ino = sbi->s_nextid++;
- inode->i_blkbits = EXOFS_BLKSHIFT;
- inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
- oi->i_commit_size = inode->i_size = 0;
- 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);
-
- exofs_init_comps(&oi->oc, &oi->one_comp, sb->s_fs_info,
- exofs_oi_objno(oi));
- exofs_sbi_write_stats(sbi); /* Make sure new sbi->s_nextid is on disk */
-
- mark_inode_dirty(inode);
-
- ret = ore_get_io_state(&sbi->layout, &oi->oc, &ios);
- if (unlikely(ret)) {
- EXOFS_ERR("exofs_new_inode: ore_get_io_state failed\n");
- return ERR_PTR(ret);
- }
-
- ios->done = create_done;
- ios->private = inode;
-
- ret = ore_create(ios);
- if (ret) {
- ore_put_io_state(ios);
- return ERR_PTR(ret);
- }
- atomic_inc(&sbi->s_curr_pending);
-
- return inode;
-}
-
-/*
- * struct to pass two arguments to update_inode's callback
- */
-struct updatei_args {
- struct exofs_sb_info *sbi;
- struct exofs_fcb fcb;
-};
-
-/*
- * Callback function from exofs_update_inode().
- */
-static void updatei_done(struct ore_io_state *ios, void *p)
-{
- struct updatei_args *args = p;
-
- ore_put_io_state(ios);
-
- atomic_dec(&args->sbi->s_curr_pending);
-
- kfree(args);
-}
-
-/*
- * Write the inode to the OSD. Just fill up the struct, and set the attribute
- * synchronously or asynchronously depending on the do_sync flag.
- */
-static int exofs_update_inode(struct inode *inode, int do_sync)
-{
- struct exofs_i_info *oi = exofs_i(inode);
- struct super_block *sb = inode->i_sb;
- struct exofs_sb_info *sbi = sb->s_fs_info;
- struct ore_io_state *ios;
- struct osd_attr attr;
- struct exofs_fcb *fcb;
- struct updatei_args *args;
- int ret;
-
- args = kzalloc(sizeof(*args), GFP_KERNEL);
- if (!args) {
- EXOFS_DBGMSG("Failed kzalloc of args\n");
- return -ENOMEM;
- }
-
- fcb = &args->fcb;
-
- fcb->i_mode = cpu_to_le16(inode->i_mode);
- fcb->i_uid = cpu_to_le32(i_uid_read(inode));
- fcb->i_gid = cpu_to_le32(i_gid_read(inode));
- fcb->i_links_count = cpu_to_le16(inode->i_nlink);
- fcb->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
- fcb->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
- fcb->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
- oi->i_commit_size = i_size_read(inode);
- fcb->i_size = cpu_to_le64(oi->i_commit_size);
- fcb->i_generation = cpu_to_le32(inode->i_generation);
-
- if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
- if (old_valid_dev(inode->i_rdev)) {
- fcb->i_data[0] =
- cpu_to_le32(old_encode_dev(inode->i_rdev));
- fcb->i_data[1] = 0;
- } else {
- fcb->i_data[0] = 0;
- fcb->i_data[1] =
- cpu_to_le32(new_encode_dev(inode->i_rdev));
- fcb->i_data[2] = 0;
- }
- } else
- memcpy(fcb->i_data, oi->i_data, sizeof(fcb->i_data));
-
- ret = ore_get_io_state(&sbi->layout, &oi->oc, &ios);
- if (unlikely(ret)) {
- EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__);
- goto free_args;
- }
-
- attr = g_attr_inode_data;
- attr.val_ptr = fcb;
- ios->out_attr_len = 1;
- ios->out_attr = &attr;
-
- wait_obj_created(oi);
-
- if (!do_sync) {
- args->sbi = sbi;
- ios->done = updatei_done;
- ios->private = args;
- }
-
- ret = ore_write(ios);
- if (!do_sync && !ret) {
- atomic_inc(&sbi->s_curr_pending);
- goto out; /* deallocation in updatei_done */
- }
-
- ore_put_io_state(ios);
-free_args:
- kfree(args);
-out:
- EXOFS_DBGMSG("(0x%lx) do_sync=%d ret=>%d\n",
- inode->i_ino, do_sync, ret);
- return ret;
-}
-
-int exofs_write_inode(struct inode *inode, struct writeback_control *wbc)
-{
- /* FIXME: fix fsync and use wbc->sync_mode == WB_SYNC_ALL */
- return exofs_update_inode(inode, 1);
-}
-
-/*
- * Callback function from exofs_delete_inode() - don't have much cleaning up to
- * do.
- */
-static void delete_done(struct ore_io_state *ios, void *p)
-{
- struct exofs_sb_info *sbi = p;
-
- ore_put_io_state(ios);
-
- atomic_dec(&sbi->s_curr_pending);
-}
-
-/*
- * Called when the refcount of an inode reaches zero. We remove the object
- * from the OSD here. We make sure the object was created before we try and
- * delete it.
- */
-void exofs_evict_inode(struct inode *inode)
-{
- struct exofs_i_info *oi = exofs_i(inode);
- struct super_block *sb = inode->i_sb;
- struct exofs_sb_info *sbi = sb->s_fs_info;
- struct ore_io_state *ios;
- int ret;
-
- truncate_inode_pages_final(&inode->i_data);
-
- /* TODO: should do better here */
- if (inode->i_nlink || is_bad_inode(inode))
- goto no_delete;
-
- inode->i_size = 0;
- clear_inode(inode);
-
- /* if we are deleting an obj that hasn't been created yet, wait.
- * This also makes sure that create_done cannot be called with an
- * already evicted inode.
- */
- wait_obj_created(oi);
- /* ignore the error, attempt a remove anyway */
-
- /* Now Remove the OSD objects */
- ret = ore_get_io_state(&sbi->layout, &oi->oc, &ios);
- if (unlikely(ret)) {
- EXOFS_ERR("%s: ore_get_io_state failed\n", __func__);
- return;
- }
-
- ios->done = delete_done;
- ios->private = sbi;
-
- ret = ore_remove(ios);
- if (ret) {
- EXOFS_ERR("%s: ore_remove failed\n", __func__);
- ore_put_io_state(ios);
- return;
- }
- atomic_inc(&sbi->s_curr_pending);
-
- return;
-
-no_delete:
- clear_inode(inode);
-}
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
deleted file mode 100644
index 7295cd722770..000000000000
--- a/fs/exofs/namei.c
+++ /dev/null
@@ -1,323 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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 int exofs_add_nondir(struct dentry *dentry, struct inode *inode)
-{
- int err = exofs_add_link(dentry, inode);
- if (!err) {
- d_instantiate(dentry, inode);
- return 0;
- }
- inode_dec_link_count(inode);
- iput(inode);
- return err;
-}
-
-static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry,
- unsigned int flags)
-{
- struct inode *inode;
- ino_t ino;
-
- if (dentry->d_name.len > EXOFS_NAME_LEN)
- return ERR_PTR(-ENAMETOOLONG);
-
- ino = exofs_inode_by_name(dir, dentry);
- inode = ino ? exofs_iget(dir->i_sb, ino) : NULL;
- return d_splice_alias(inode, dentry);
-}
-
-static int exofs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- bool excl)
-{
- struct inode *inode = exofs_new_inode(dir, mode);
- int err = PTR_ERR(inode);
- if (!IS_ERR(inode)) {
- inode->i_op = &exofs_file_inode_operations;
- inode->i_fop = &exofs_file_operations;
- inode->i_mapping->a_ops = &exofs_aops;
- mark_inode_dirty(inode);
- err = exofs_add_nondir(dentry, inode);
- }
- return err;
-}
-
-static int exofs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
- dev_t rdev)
-{
- struct inode *inode;
- int err;
-
- inode = exofs_new_inode(dir, mode);
- err = PTR_ERR(inode);
- if (!IS_ERR(inode)) {
- init_special_inode(inode, inode->i_mode, rdev);
- mark_inode_dirty(inode);
- err = exofs_add_nondir(dentry, inode);
- }
- return err;
-}
-
-static int exofs_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
-{
- struct super_block *sb = dir->i_sb;
- int err = -ENAMETOOLONG;
- unsigned l = strlen(symname)+1;
- struct inode *inode;
- struct exofs_i_info *oi;
-
- if (l > sb->s_blocksize)
- goto out;
-
- inode = exofs_new_inode(dir, S_IFLNK | S_IRWXUGO);
- err = PTR_ERR(inode);
- if (IS_ERR(inode))
- goto out;
-
- oi = exofs_i(inode);
- if (l > sizeof(oi->i_data)) {
- /* slow symlink */
- inode->i_op = &page_symlink_inode_operations;
- inode_nohighmem(inode);
- inode->i_mapping->a_ops = &exofs_aops;
- memset(oi->i_data, 0, sizeof(oi->i_data));
-
- err = page_symlink(inode, symname, l);
- if (err)
- goto out_fail;
- } else {
- /* fast symlink */
- inode->i_op = &simple_symlink_inode_operations;
- inode->i_link = (char *)oi->i_data;
- memcpy(oi->i_data, symname, l);
- inode->i_size = l-1;
- }
- mark_inode_dirty(inode);
-
- err = exofs_add_nondir(dentry, inode);
-out:
- return err;
-
-out_fail:
- inode_dec_link_count(inode);
- iput(inode);
- goto out;
-}
-
-static int exofs_link(struct dentry *old_dentry, struct inode *dir,
- struct dentry *dentry)
-{
- struct inode *inode = d_inode(old_dentry);
-
- inode->i_ctime = current_time(inode);
- inode_inc_link_count(inode);
- ihold(inode);
-
- return exofs_add_nondir(dentry, inode);
-}
-
-static int exofs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
-{
- struct inode *inode;
- int err;
-
- inode_inc_link_count(dir);
-
- inode = exofs_new_inode(dir, S_IFDIR | mode);
- err = PTR_ERR(inode);
- if (IS_ERR(inode))
- goto out_dir;
-
- inode->i_op = &exofs_dir_inode_operations;
- inode->i_fop = &exofs_dir_operations;
- inode->i_mapping->a_ops = &exofs_aops;
-
- inode_inc_link_count(inode);
-
- err = exofs_make_empty(inode, dir);
- if (err)
- goto out_fail;
-
- err = exofs_add_link(dentry, inode);
- if (err)
- goto out_fail;
-
- d_instantiate(dentry, inode);
-out:
- return err;
-
-out_fail:
- inode_dec_link_count(inode);
- inode_dec_link_count(inode);
- iput(inode);
-out_dir:
- inode_dec_link_count(dir);
- goto out;
-}
-
-static int exofs_unlink(struct inode *dir, struct dentry *dentry)
-{
- struct inode *inode = d_inode(dentry);
- struct exofs_dir_entry *de;
- struct page *page;
- int err = -ENOENT;
-
- de = exofs_find_entry(dir, dentry, &page);
- if (!de)
- goto out;
-
- err = exofs_delete_entry(de, page);
- if (err)
- goto out;
-
- inode->i_ctime = dir->i_ctime;
- inode_dec_link_count(inode);
- err = 0;
-out:
- return err;
-}
-
-static int exofs_rmdir(struct inode *dir, struct dentry *dentry)
-{
- struct inode *inode = d_inode(dentry);
- int err = -ENOTEMPTY;
-
- if (exofs_empty_dir(inode)) {
- err = exofs_unlink(dir, dentry);
- if (!err) {
- inode->i_size = 0;
- inode_dec_link_count(inode);
- inode_dec_link_count(dir);
- }
- }
- return err;
-}
-
-static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
-{
- struct inode *old_inode = d_inode(old_dentry);
- struct inode *new_inode = d_inode(new_dentry);
- struct page *dir_page = NULL;
- struct exofs_dir_entry *dir_de = NULL;
- struct page *old_page;
- struct exofs_dir_entry *old_de;
- int err = -ENOENT;
-
- if (flags & ~RENAME_NOREPLACE)
- return -EINVAL;
-
- old_de = exofs_find_entry(old_dir, old_dentry, &old_page);
- if (!old_de)
- goto out;
-
- if (S_ISDIR(old_inode->i_mode)) {
- err = -EIO;
- dir_de = exofs_dotdot(old_inode, &dir_page);
- if (!dir_de)
- goto out_old;
- }
-
- if (new_inode) {
- struct page *new_page;
- struct exofs_dir_entry *new_de;
-
- err = -ENOTEMPTY;
- if (dir_de && !exofs_empty_dir(new_inode))
- goto out_dir;
-
- err = -ENOENT;
- new_de = exofs_find_entry(new_dir, new_dentry, &new_page);
- if (!new_de)
- goto out_dir;
- err = exofs_set_link(new_dir, new_de, new_page, old_inode);
- new_inode->i_ctime = current_time(new_inode);
- if (dir_de)
- drop_nlink(new_inode);
- inode_dec_link_count(new_inode);
- if (err)
- goto out_dir;
- } else {
- err = exofs_add_link(new_dentry, old_inode);
- if (err)
- goto out_dir;
- if (dir_de)
- inode_inc_link_count(new_dir);
- }
-
- old_inode->i_ctime = current_time(old_inode);
-
- exofs_delete_entry(old_de, old_page);
- mark_inode_dirty(old_inode);
-
- if (dir_de) {
- err = exofs_set_link(old_inode, dir_de, dir_page, new_dir);
- inode_dec_link_count(old_dir);
- if (err)
- goto out_dir;
- }
- return 0;
-
-
-out_dir:
- if (dir_de) {
- kunmap(dir_page);
- put_page(dir_page);
- }
-out_old:
- kunmap(old_page);
- put_page(old_page);
-out:
- return err;
-}
-
-const struct inode_operations exofs_dir_inode_operations = {
- .create = exofs_create,
- .lookup = exofs_lookup,
- .link = exofs_link,
- .unlink = exofs_unlink,
- .symlink = exofs_symlink,
- .mkdir = exofs_mkdir,
- .rmdir = exofs_rmdir,
- .mknod = exofs_mknod,
- .rename = exofs_rename,
- .setattr = exofs_setattr,
-};
-
-const struct inode_operations exofs_special_inode_operations = {
- .setattr = exofs_setattr,
-};
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
deleted file mode 100644
index 8bb72807e70d..000000000000
--- a/fs/exofs/ore.c
+++ /dev/null
@@ -1,1164 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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 <linux/slab.h>
-#include <linux/module.h>
-#include <asm/div64.h>
-#include <linux/lcm.h>
-
-#include "ore_raid.h"
-
-MODULE_AUTHOR("Boaz Harrosh <ooo@electrozaur.com>");
-MODULE_DESCRIPTION("Objects Raid Engine ore.ko");
-MODULE_LICENSE("GPL");
-
-/* ore_verify_layout does a couple of things:
- * 1. Given a minimum number of needed parameters fixes up the rest of the
- * members to be operatonals for the ore. The needed parameters are those
- * that are defined by the pnfs-objects layout STD.
- * 2. Check to see if the current ore code actually supports these parameters
- * for example stripe_unit must be a multple of the system PAGE_SIZE,
- * and etc...
- * 3. Cache some havily used calculations that will be needed by users.
- */
-
-enum { BIO_MAX_PAGES_KMALLOC =
- (PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec),};
-
-int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
-{
- u64 stripe_length;
-
- switch (layout->raid_algorithm) {
- case PNFS_OSD_RAID_0:
- layout->parity = 0;
- break;
- case PNFS_OSD_RAID_5:
- layout->parity = 1;
- break;
- case PNFS_OSD_RAID_PQ:
- layout->parity = 2;
- break;
- case PNFS_OSD_RAID_4:
- default:
- ORE_ERR("Only RAID_0/5/6 for now received-enum=%d\n",
- layout->raid_algorithm);
- return -EINVAL;
- }
- if (0 != (layout->stripe_unit & ~PAGE_MASK)) {
- ORE_ERR("Stripe Unit(0x%llx)"
- " must be Multples of PAGE_SIZE(0x%lx)\n",
- _LLU(layout->stripe_unit), PAGE_SIZE);
- return -EINVAL;
- }
- if (layout->group_width) {
- if (!layout->group_depth) {
- ORE_ERR("group_depth == 0 && group_width != 0\n");
- return -EINVAL;
- }
- if (total_comps < (layout->group_width * layout->mirrors_p1)) {
- ORE_ERR("Data Map wrong, "
- "numdevs=%d < group_width=%d * mirrors=%d\n",
- total_comps, layout->group_width,
- layout->mirrors_p1);
- return -EINVAL;
- }
- layout->group_count = total_comps / layout->mirrors_p1 /
- layout->group_width;
- } else {
- if (layout->group_depth) {
- printk(KERN_NOTICE "Warning: group_depth ignored "
- "group_width == 0 && group_depth == %lld\n",
- _LLU(layout->group_depth));
- }
- layout->group_width = total_comps / layout->mirrors_p1;
- layout->group_depth = -1;
- layout->group_count = 1;
- }
-
- stripe_length = (u64)layout->group_width * layout->stripe_unit;
- if (stripe_length >= (1ULL << 32)) {
- ORE_ERR("Stripe_length(0x%llx) >= 32bit is not supported\n",
- _LLU(stripe_length));
- return -EINVAL;
- }
-
- layout->max_io_length =
- (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
- (layout->group_width - layout->parity);
- if (layout->parity) {
- unsigned stripe_length =
- (layout->group_width - layout->parity) *
- layout->stripe_unit;
-
- layout->max_io_length /= stripe_length;
- layout->max_io_length *= stripe_length;
- }
- ORE_DBGMSG("max_io_length=0x%lx\n", layout->max_io_length);
-
- return 0;
-}
-EXPORT_SYMBOL(ore_verify_layout);
-
-static u8 *_ios_cred(struct ore_io_state *ios, unsigned index)
-{
- return ios->oc->comps[index & ios->oc->single_comp].cred;
-}
-
-static struct osd_obj_id *_ios_obj(struct ore_io_state *ios, unsigned index)
-{
- return &ios->oc->comps[index & ios->oc->single_comp].obj;
-}
-
-static struct osd_dev *_ios_od(struct ore_io_state *ios, unsigned index)
-{
- ORE_DBGMSG2("oc->first_dev=%d oc->numdevs=%d i=%d oc->ods=%p\n",
- ios->oc->first_dev, ios->oc->numdevs, index,
- ios->oc->ods);
-
- return ore_comp_dev(ios->oc, index);
-}
-
-int _ore_get_io_state(struct ore_layout *layout,
- struct ore_components *oc, unsigned numdevs,
- unsigned sgs_per_dev, unsigned num_par_pages,
- struct ore_io_state **pios)
-{
- struct ore_io_state *ios;
- struct page **pages;
- struct osd_sg_entry *sgilist;
- struct __alloc_all_io_state {
- struct ore_io_state ios;
- struct ore_per_dev_state per_dev[numdevs];
- union {
- struct osd_sg_entry sglist[sgs_per_dev * numdevs];
- struct page *pages[num_par_pages];
- };
- } *_aios;
-
- if (likely(sizeof(*_aios) <= PAGE_SIZE)) {
- _aios = kzalloc(sizeof(*_aios), GFP_KERNEL);
- if (unlikely(!_aios)) {
- ORE_DBGMSG("Failed kzalloc bytes=%zd\n",
- sizeof(*_aios));
- *pios = NULL;
- return -ENOMEM;
- }
- pages = num_par_pages ? _aios->pages : NULL;
- sgilist = sgs_per_dev ? _aios->sglist : NULL;
- ios = &_aios->ios;
- } else {
- struct __alloc_small_io_state {
- struct ore_io_state ios;
- struct ore_per_dev_state per_dev[numdevs];
- } *_aio_small;
- union __extra_part {
- struct osd_sg_entry sglist[sgs_per_dev * numdevs];
- struct page *pages[num_par_pages];
- } *extra_part;
-
- _aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL);
- if (unlikely(!_aio_small)) {
- ORE_DBGMSG("Failed alloc first part bytes=%zd\n",
- sizeof(*_aio_small));
- *pios = NULL;
- return -ENOMEM;
- }
- extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL);
- if (unlikely(!extra_part)) {
- ORE_DBGMSG("Failed alloc second part bytes=%zd\n",
- sizeof(*extra_part));
- kfree(_aio_small);
- *pios = NULL;
- return -ENOMEM;
- }
-
- pages = num_par_pages ? extra_part->pages : NULL;
- sgilist = sgs_per_dev ? extra_part->sglist : NULL;
- /* In this case the per_dev[0].sgilist holds the pointer to
- * be freed
- */
- ios = &_aio_small->ios;
- ios->extra_part_alloc = true;
- }
-
- if (pages) {
- ios->parity_pages = pages;
- ios->max_par_pages = num_par_pages;
- }
- if (sgilist) {
- unsigned d;
-
- for (d = 0; d < numdevs; ++d) {
- ios->per_dev[d].sglist = sgilist;
- sgilist += sgs_per_dev;
- }
- ios->sgs_per_dev = sgs_per_dev;
- }
-
- ios->layout = layout;
- ios->oc = oc;
- *pios = ios;
- return 0;
-}
-
-/* Allocate an io_state for only a single group of devices
- *
- * If a user needs to call ore_read/write() this version must be used becase it
- * allocates extra stuff for striping and raid.
- * The ore might decide to only IO less then @length bytes do to alignmets
- * and constrains as follows:
- * - The IO cannot cross group boundary.
- * - In raid5/6 The end of the IO must align at end of a stripe eg.
- * (@offset + @length) % strip_size == 0. Or the complete range is within a
- * single stripe.
- * - Memory condition only permitted a shorter IO. (A user can use @length=~0
- * And check the returned ios->length for max_io_size.)
- *
- * The caller must check returned ios->length (and/or ios->nr_pages) and
- * re-issue these pages that fall outside of ios->length
- */
-int ore_get_rw_state(struct ore_layout *layout, struct ore_components *oc,
- bool is_reading, u64 offset, u64 length,
- struct ore_io_state **pios)
-{
- struct ore_io_state *ios;
- unsigned numdevs = layout->group_width * layout->mirrors_p1;
- unsigned sgs_per_dev = 0, max_par_pages = 0;
- int ret;
-
- if (layout->parity && length) {
- unsigned data_devs = layout->group_width - layout->parity;
- unsigned stripe_size = layout->stripe_unit * data_devs;
- unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE;
- u32 remainder;
- u64 num_stripes;
- u64 num_raid_units;
-
- num_stripes = div_u64_rem(length, stripe_size, &remainder);
- if (remainder)
- ++num_stripes;
-
- num_raid_units = num_stripes * layout->parity;
-
- if (is_reading) {
- /* For reads add per_dev sglist array */
- /* TODO: Raid 6 we need twice more. Actually:
- * num_stripes / LCMdP(W,P);
- * if (W%P != 0) num_stripes *= parity;
- */
-
- /* first/last seg is split */
- num_raid_units += layout->group_width;
- sgs_per_dev = div_u64(num_raid_units, data_devs) + 2;
- } else {
- /* For Writes add parity pages array. */
- max_par_pages = num_raid_units * pages_in_unit *
- sizeof(struct page *);
- }
- }
-
- ret = _ore_get_io_state(layout, oc, numdevs, sgs_per_dev, max_par_pages,
- pios);
- if (unlikely(ret))
- return ret;
-
- ios = *pios;
- ios->reading = is_reading;
- ios->offset = offset;
-
- if (length) {
- ore_calc_stripe_info(layout, offset, length, &ios->si);
- ios->length = ios->si.length;
- ios->nr_pages = ((ios->offset & (PAGE_SIZE - 1)) +
- ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
- if (layout->parity)
- _ore_post_alloc_raid_stuff(ios);
- }
-
- return 0;
-}
-EXPORT_SYMBOL(ore_get_rw_state);
-
-/* Allocate an io_state for all the devices in the comps array
- *
- * This version of io_state allocation is used mostly by create/remove
- * and trunc where we currently need all the devices. The only wastful
- * bit is the read/write_attributes with no IO. Those sites should
- * be converted to use ore_get_rw_state() with length=0
- */
-int ore_get_io_state(struct ore_layout *layout, struct ore_components *oc,
- struct ore_io_state **pios)
-{
- return _ore_get_io_state(layout, oc, oc->numdevs, 0, 0, pios);
-}
-EXPORT_SYMBOL(ore_get_io_state);
-
-void ore_put_io_state(struct ore_io_state *ios)
-{
- if (ios) {
- unsigned i;
-
- for (i = 0; i < ios->numdevs; i++) {
- struct ore_per_dev_state *per_dev = &ios->per_dev[i];
-
- if (per_dev->or)
- osd_end_request(per_dev->or);
- if (per_dev->bio)
- bio_put(per_dev->bio);
- }
-
- _ore_free_raid_stuff(ios);
- kfree(ios);
- }
-}
-EXPORT_SYMBOL(ore_put_io_state);
-
-static void _sync_done(struct ore_io_state *ios, void *p)
-{
- struct completion *waiting = p;
-
- complete(waiting);
-}
-
-static void _last_io(struct kref *kref)
-{
- struct ore_io_state *ios = container_of(
- kref, struct ore_io_state, kref);
-
- ios->done(ios, ios->private);
-}
-
-static void _done_io(struct osd_request *or, void *p)
-{
- struct ore_io_state *ios = p;
-
- kref_put(&ios->kref, _last_io);
-}
-
-int ore_io_execute(struct ore_io_state *ios)
-{
- DECLARE_COMPLETION_ONSTACK(wait);
- bool sync = (ios->done == NULL);
- int i, ret;
-
- if (sync) {
- ios->done = _sync_done;
- ios->private = &wait;
- }
-
- for (i = 0; i < ios->numdevs; i++) {
- struct osd_request *or = ios->per_dev[i].or;
- if (unlikely(!or))
- continue;
-
- ret = osd_finalize_request(or, 0, _ios_cred(ios, i), NULL);
- if (unlikely(ret)) {
- ORE_DBGMSG("Failed to osd_finalize_request() => %d\n",
- ret);
- return ret;
- }
- }
-
- kref_init(&ios->kref);
-
- for (i = 0; i < ios->numdevs; i++) {
- struct osd_request *or = ios->per_dev[i].or;
- if (unlikely(!or))
- continue;
-
- kref_get(&ios->kref);
- osd_execute_request_async(or, _done_io, ios);
- }
-
- kref_put(&ios->kref, _last_io);
- ret = 0;
-
- if (sync) {
- wait_for_completion(&wait);
- ret = ore_check_io(ios, NULL);
- }
- return ret;
-}
-
-static void _clear_bio(struct bio *bio)
-{
- struct bio_vec *bv;
- unsigned i;
-
- bio_for_each_segment_all(bv, bio, i) {
- unsigned this_count = bv->bv_len;
-
- if (likely(PAGE_SIZE == this_count))
- clear_highpage(bv->bv_page);
- else
- zero_user(bv->bv_page, bv->bv_offset, this_count);
- }
-}
-
-int ore_check_io(struct ore_io_state *ios, ore_on_dev_error on_dev_error)
-{
- enum osd_err_priority acumulated_osd_err = 0;
- int acumulated_lin_err = 0;
- int i;
-
- for (i = 0; i < ios->numdevs; i++) {
- struct osd_sense_info osi;
- struct ore_per_dev_state *per_dev = &ios->per_dev[i];
- struct osd_request *or = per_dev->or;
- int ret;
-
- if (unlikely(!or))
- continue;
-
- ret = osd_req_decode_sense(or, &osi);
- if (likely(!ret))
- continue;
-
- if ((OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) &&
- per_dev->bio) {
- /* start read offset passed endof file.
- * Note: if we do not have bio it means read-attributes
- * In this case we should return error to caller.
- */
- _clear_bio(per_dev->bio);
- ORE_DBGMSG("start read offset passed end of file "
- "offset=0x%llx, length=0x%llx\n",
- _LLU(per_dev->offset),
- _LLU(per_dev->length));
-
- continue; /* we recovered */
- }
-
- if (on_dev_error) {
- u64 residual = ios->reading ?
- or->in.residual : or->out.residual;
- u64 offset = (ios->offset + ios->length) - residual;
- unsigned dev = per_dev->dev - ios->oc->first_dev;
- struct ore_dev *od = ios->oc->ods[dev];
-
- on_dev_error(ios, od, dev, osi.osd_err_pri,
- offset, residual);
- }
- if (osi.osd_err_pri >= acumulated_osd_err) {
- acumulated_osd_err = osi.osd_err_pri;
- acumulated_lin_err = ret;
- }
- }
-
- return acumulated_lin_err;
-}
-EXPORT_SYMBOL(ore_check_io);
-
-/*
- * L - logical offset into the file
- *
- * D - number of Data devices
- * D = group_width - parity
- *
- * U - The number of bytes in a stripe within a group
- * U = stripe_unit * D
- *
- * T - The number of bytes striped within a group of component objects
- * (before advancing to the next group)
- * T = U * group_depth
- *
- * S - The number of bytes striped across all component objects
- * before the pattern repeats
- * S = T * group_count
- *
- * M - The "major" (i.e., across all components) cycle number
- * M = L / S
- *
- * G - Counts the groups from the beginning of the major cycle
- * G = (L - (M * S)) / T [or (L % S) / T]
- *
- * H - The byte offset within the group
- * H = (L - (M * S)) % T [or (L % S) % T]
- *
- * N - The "minor" (i.e., across the group) stripe number
- * N = H / U
- *
- * C - The component index coresponding to L
- *
- * C = (H - (N * U)) / stripe_unit + G * D
- * [or (L % U) / stripe_unit + G * D]
- *
- * O - The component offset coresponding to L
- * O = L % stripe_unit + N * stripe_unit + M * group_depth * stripe_unit
- *
- * LCMdP – Parity cycle: Lowest Common Multiple of group_width, parity
- * divide by parity
- * LCMdP = lcm(group_width, parity) / parity
- *
- * R - The parity Rotation stripe
- * (Note parity cycle always starts at a group's boundary)
- * R = N % LCMdP
- *
- * I = the first parity device index
- * I = (group_width + group_width - R*parity - parity) % group_width
- *
- * Craid - The component index Rotated
- * Craid = (group_width + C - R*parity) % group_width
- * (We add the group_width to avoid negative numbers modulo math)
- */
-void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
- u64 length, struct ore_striping_info *si)
-{
- u32 stripe_unit = layout->stripe_unit;
- u32 group_width = layout->group_width;
- u64 group_depth = layout->group_depth;
- u32 parity = layout->parity;
-
- u32 D = group_width - parity;
- u32 U = D * stripe_unit;
- u64 T = U * group_depth;
- u64 S = T * layout->group_count;
- u64 M = div64_u64(file_offset, S);
-
- /*
- G = (L - (M * S)) / T
- H = (L - (M * S)) % T
- */
- u64 LmodS = file_offset - M * S;
- u32 G = div64_u64(LmodS, T);
- u64 H = LmodS - G * T;
-
- u32 N = div_u64(H, U);
- u32 Nlast;
-
- /* "H - (N * U)" is just "H % U" so it's bound to u32 */
- u32 C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
- u32 first_dev = C - C % group_width;
-
- div_u64_rem(file_offset, stripe_unit, &si->unit_off);
-
- si->obj_offset = si->unit_off + (N * stripe_unit) +
- (M * group_depth * stripe_unit);
- si->cur_comp = C - first_dev;
- si->cur_pg = si->unit_off / PAGE_SIZE;
-
- if (parity) {
- u32 LCMdP = lcm(group_width, parity) / parity;
- /* R = N % LCMdP; */
- u32 RxP = (N % LCMdP) * parity;
-
- si->par_dev = (group_width + group_width - parity - RxP) %
- group_width + first_dev;
- si->dev = (group_width + group_width + C - RxP) %
- group_width + first_dev;
- si->bytes_in_stripe = U;
- si->first_stripe_start = M * S + G * T + N * U;
- } else {
- /* Make the math correct see _prepare_one_group */
- si->par_dev = group_width;
- si->dev = C;
- }
-
- si->dev *= layout->mirrors_p1;
- si->par_dev *= layout->mirrors_p1;
- si->offset = file_offset;
- si->length = T - H;
- if (si->length > length)
- si->length = length;
-
- Nlast = div_u64(H + si->length + U - 1, U);
- si->maxdevUnits = Nlast - N;
-
- si->M = M;
-}
-EXPORT_SYMBOL(ore_calc_stripe_info);
-
-int _ore_add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg,
- unsigned pgbase, struct page **pages,
- struct ore_per_dev_state *per_dev, int cur_len)
-{
- unsigned pg = *cur_pg;
- struct request_queue *q =
- osd_request_queue(_ios_od(ios, per_dev->dev));
- unsigned len = cur_len;
- int ret;
-
- if (per_dev->bio == NULL) {
- unsigned bio_size;
-
- if (!ios->reading) {
- bio_size = ios->si.maxdevUnits;
- } else {
- bio_size = (ios->si.maxdevUnits + 1) *
- (ios->layout->group_width - ios->layout->parity) /
- ios->layout->group_width;
- }
- bio_size *= (ios->layout->stripe_unit / PAGE_SIZE);
-
- per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
- if (unlikely(!per_dev->bio)) {
- ORE_DBGMSG("Failed to allocate BIO size=%u\n",
- bio_size);
- ret = -ENOMEM;
- goto out;
- }
- }
-
- while (cur_len > 0) {
- unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
- unsigned added_len;
-
- cur_len -= pglen;
-
- added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
- pglen, pgbase);
- if (unlikely(pglen != added_len)) {
- /* If bi_vcnt == bi_max then this is a SW BUG */
- ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=0x%x "
- "bi_max=0x%x BIO_MAX=0x%x cur_len=0x%x\n",
- per_dev->bio->bi_vcnt,
- per_dev->bio->bi_max_vecs,
- BIO_MAX_PAGES_KMALLOC, cur_len);
- ret = -ENOMEM;
- goto out;
- }
- _add_stripe_page(ios->sp2d, &ios->si, pages[pg]);
-
- pgbase = 0;
- ++pg;
- }
- BUG_ON(cur_len);
-
- per_dev->length += len;
- *cur_pg = pg;
- ret = 0;
-out: /* we fail the complete unit on an error eg don't advance
- * per_dev->length and cur_pg. This means that we might have a bigger
- * bio than the CDB requested length (per_dev->length). That's fine
- * only the oposite is fatal.
- */
- return ret;
-}
-
-static int _add_parity_units(struct ore_io_state *ios,
- struct ore_striping_info *si,
- unsigned dev, unsigned first_dev,
- unsigned mirrors_p1, unsigned devs_in_group,
- unsigned cur_len)
-{
- unsigned do_parity;
- int ret = 0;
-
- for (do_parity = ios->layout->parity; do_parity; --do_parity) {
- struct ore_per_dev_state *per_dev;
-
- per_dev = &ios->per_dev[dev - first_dev];
- if (!per_dev->length && !per_dev->offset) {
- /* Only/always the parity unit of the first
- * stripe will be empty. So this is a chance to
- * initialize the per_dev info.
- */
- per_dev->dev = dev;
- per_dev->offset = si->obj_offset - si->unit_off;
- }
-
- ret = _ore_add_parity_unit(ios, si, per_dev, cur_len,
- do_parity == 1);
- if (unlikely(ret))
- break;
-
- if (do_parity != 1) {
- dev = ((dev + mirrors_p1) % devs_in_group) + first_dev;
- si->cur_comp = (si->cur_comp + 1) %
- ios->layout->group_width;
- }
- }
-
- return ret;
-}
-
-static int _prepare_for_striping(struct ore_io_state *ios)
-{
- struct ore_striping_info *si = &ios->si;
- unsigned stripe_unit = ios->layout->stripe_unit;
- unsigned mirrors_p1 = ios->layout->mirrors_p1;
- unsigned group_width = ios->layout->group_width;
- unsigned devs_in_group = group_width * mirrors_p1;
- unsigned dev = si->dev;
- unsigned first_dev = dev - (dev % devs_in_group);
- unsigned cur_pg = ios->pages_consumed;
- u64 length = ios->length;
- int ret = 0;
-
- if (!ios->pages) {
- ios->numdevs = ios->layout->mirrors_p1;
- return 0;
- }
-
- BUG_ON(length > si->length);
-
- while (length) {
- struct ore_per_dev_state *per_dev =
- &ios->per_dev[dev - first_dev];
- unsigned cur_len, page_off = 0;
-
- if (!per_dev->length && !per_dev->offset) {
- /* First time initialize the per_dev info. */
- per_dev->dev = dev;
- if (dev == si->dev) {
- WARN_ON(dev == si->par_dev);
- per_dev->offset = si->obj_offset;
- cur_len = stripe_unit - si->unit_off;
- page_off = si->unit_off & ~PAGE_MASK;
- BUG_ON(page_off && (page_off != ios->pgbase));
- } else {
- per_dev->offset = si->obj_offset - si->unit_off;
- cur_len = stripe_unit;
- }
- } else {
- cur_len = stripe_unit;
- }
- if (cur_len >= length)
- cur_len = length;
-
- ret = _ore_add_stripe_unit(ios, &cur_pg, page_off, ios->pages,
- per_dev, cur_len);
- if (unlikely(ret))
- goto out;
-
- length -= cur_len;
-
- dev = ((dev + mirrors_p1) % devs_in_group) + first_dev;
- si->cur_comp = (si->cur_comp + 1) % group_width;
- if (unlikely((dev == si->par_dev) || (!length && ios->sp2d))) {
- if (!length && ios->sp2d) {
- /* If we are writing and this is the very last
- * stripe. then operate on parity dev.
- */
- dev = si->par_dev;
- /* If last stripe operate on parity comp */
- si->cur_comp = group_width - ios->layout->parity;
- }
-
- /* In writes cur_len just means if it's the
- * last one. See _ore_add_parity_unit.
- */
- ret = _add_parity_units(ios, si, dev, first_dev,
- mirrors_p1, devs_in_group,
- ios->sp2d ? length : cur_len);
- if (unlikely(ret))
- goto out;
-
- /* Rotate next par_dev backwards with wraping */
- si->par_dev = (devs_in_group + si->par_dev -
- ios->layout->parity * mirrors_p1) %
- devs_in_group + first_dev;
- /* Next stripe, start fresh */
- si->cur_comp = 0;
- si->cur_pg = 0;
- si->obj_offset += cur_len;
- si->unit_off = 0;
- }
- }
-out:
- ios->numdevs = devs_in_group;
- ios->pages_consumed = cur_pg;
- return ret;
-}
-
-int ore_create(struct ore_io_state *ios)
-{
- int i, ret;
-
- for (i = 0; i < ios->oc->numdevs; i++) {
- struct osd_request *or;
-
- or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
- if (unlikely(!or)) {
- ORE_ERR("%s: osd_start_request failed\n", __func__);
- ret = -ENOMEM;
- goto out;
- }
- ios->per_dev[i].or = or;
- ios->numdevs++;
-
- osd_req_create_object(or, _ios_obj(ios, i));
- }
- ret = ore_io_execute(ios);
-
-out:
- return ret;
-}
-EXPORT_SYMBOL(ore_create);
-
-int ore_remove(struct ore_io_state *ios)
-{
- int i, ret;
-
- for (i = 0; i < ios->oc->numdevs; i++) {
- struct osd_request *or;
-
- or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
- if (unlikely(!or)) {
- ORE_ERR("%s: osd_start_request failed\n", __func__);
- ret = -ENOMEM;
- goto out;
- }
- ios->per_dev[i].or = or;
- ios->numdevs++;
-
- osd_req_remove_object(or, _ios_obj(ios, i));
- }
- ret = ore_io_execute(ios);
-
-out:
- return ret;
-}
-EXPORT_SYMBOL(ore_remove);
-
-static int _write_mirror(struct ore_io_state *ios, int cur_comp)
-{
- struct ore_per_dev_state *master_dev = &ios->per_dev[cur_comp];
- unsigned dev = ios->per_dev[cur_comp].dev;
- unsigned last_comp = cur_comp + ios->layout->mirrors_p1;
- int ret = 0;
-
- if (ios->pages && !master_dev->length)
- return 0; /* Just an empty slot */
-
- for (; cur_comp < last_comp; ++cur_comp, ++dev) {
- struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
- struct osd_request *or;
-
- or = osd_start_request(_ios_od(ios, dev), GFP_KERNEL);
- if (unlikely(!or)) {
- ORE_ERR("%s: osd_start_request failed\n", __func__);
- ret = -ENOMEM;
- goto out;
- }
- per_dev->or = or;
-
- if (ios->pages) {
- struct bio *bio;
-
- if (per_dev != master_dev) {
- bio = bio_clone_kmalloc(master_dev->bio,
- GFP_KERNEL);
- if (unlikely(!bio)) {
- ORE_DBGMSG(
- "Failed to allocate BIO size=%u\n",
- master_dev->bio->bi_max_vecs);
- ret = -ENOMEM;
- goto out;
- }
-
- bio->bi_bdev = NULL;
- bio->bi_next = NULL;
- per_dev->offset = master_dev->offset;
- per_dev->length = master_dev->length;
- per_dev->bio = bio;
- per_dev->dev = dev;
- } else {
- bio = master_dev->bio;
- /* FIXME: bio_set_dir() */
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- }
-
- osd_req_write(or, _ios_obj(ios, cur_comp),
- per_dev->offset, bio, per_dev->length);
- ORE_DBGMSG("write(0x%llx) offset=0x%llx "
- "length=0x%llx dev=%d\n",
- _LLU(_ios_obj(ios, cur_comp)->id),
- _LLU(per_dev->offset),
- _LLU(per_dev->length), dev);
- } else if (ios->kern_buff) {
- per_dev->offset = ios->si.obj_offset;
- per_dev->dev = ios->si.dev + dev;
-
- /* no cross device without page array */
- BUG_ON((ios->layout->group_width > 1) &&
- (ios->si.unit_off + ios->length >
- ios->layout->stripe_unit));
-
- ret = osd_req_write_kern(or, _ios_obj(ios, cur_comp),
- per_dev->offset,
- ios->kern_buff, ios->length);
- if (unlikely(ret))
- goto out;
- ORE_DBGMSG2("write_kern(0x%llx) offset=0x%llx "
- "length=0x%llx dev=%d\n",
- _LLU(_ios_obj(ios, cur_comp)->id),
- _LLU(per_dev->offset),
- _LLU(ios->length), per_dev->dev);
- } else {
- osd_req_set_attributes(or, _ios_obj(ios, cur_comp));
- ORE_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n",
- _LLU(_ios_obj(ios, cur_comp)->id),
- ios->out_attr_len, dev);
- }
-
- if (ios->out_attr)
- osd_req_add_set_attr_list(or, ios->out_attr,
- ios->out_attr_len);
-
- if (ios->in_attr)
- osd_req_add_get_attr_list(or, ios->in_attr,
- ios->in_attr_len);
- }
-
-out:
- return ret;
-}
-
-int ore_write(struct ore_io_state *ios)
-{
- int i;
- int ret;
-
- if (unlikely(ios->sp2d && !ios->r4w)) {
- /* A library is attempting a RAID-write without providing
- * a pages lock interface.
- */
- WARN_ON_ONCE(1);
- return -ENOTSUPP;
- }
-
- ret = _prepare_for_striping(ios);
- if (unlikely(ret))
- return ret;
-
- for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
- ret = _write_mirror(ios, i);
- if (unlikely(ret))
- return ret;
- }
-
- ret = ore_io_execute(ios);
- return ret;
-}
-EXPORT_SYMBOL(ore_write);
-
-int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp)
-{
- struct osd_request *or;
- struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
- struct osd_obj_id *obj = _ios_obj(ios, cur_comp);
- unsigned first_dev = (unsigned)obj->id;
-
- if (ios->pages && !per_dev->length)
- return 0; /* Just an empty slot */
-
- first_dev = per_dev->dev + first_dev % ios->layout->mirrors_p1;
- or = osd_start_request(_ios_od(ios, first_dev), GFP_KERNEL);
- if (unlikely(!or)) {
- ORE_ERR("%s: osd_start_request failed\n", __func__);
- return -ENOMEM;
- }
- per_dev->or = or;
-
- if (ios->pages) {
- if (per_dev->cur_sg) {
- /* finalize the last sg_entry */
- _ore_add_sg_seg(per_dev, 0, false);
- if (unlikely(!per_dev->cur_sg))
- return 0; /* Skip parity only device */
-
- osd_req_read_sg(or, obj, per_dev->bio,
- per_dev->sglist, per_dev->cur_sg);
- } else {
- /* The no raid case */
- osd_req_read(or, obj, per_dev->offset,
- per_dev->bio, per_dev->length);
- }
-
- ORE_DBGMSG("read(0x%llx) offset=0x%llx length=0x%llx"
- " dev=%d sg_len=%d\n", _LLU(obj->id),
- _LLU(per_dev->offset), _LLU(per_dev->length),
- first_dev, per_dev->cur_sg);
- } else {
- BUG_ON(ios->kern_buff);
-
- osd_req_get_attributes(or, obj);
- ORE_DBGMSG2("obj(0x%llx) get_attributes=%d dev=%d\n",
- _LLU(obj->id),
- ios->in_attr_len, first_dev);
- }
- if (ios->out_attr)
- osd_req_add_set_attr_list(or, ios->out_attr, ios->out_attr_len);
-
- if (ios->in_attr)
- osd_req_add_get_attr_list(or, ios->in_attr, ios->in_attr_len);
-
- return 0;
-}
-
-int ore_read(struct ore_io_state *ios)
-{
- int i;
- int ret;
-
- ret = _prepare_for_striping(ios);
- if (unlikely(ret))
- return ret;
-
- for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
- ret = _ore_read_mirror(ios, i);
- if (unlikely(ret))
- return ret;
- }
-
- ret = ore_io_execute(ios);
- return ret;
-}
-EXPORT_SYMBOL(ore_read);
-
-int extract_attr_from_ios(struct ore_io_state *ios, 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(ios->per_dev[0].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;
-}
-EXPORT_SYMBOL(extract_attr_from_ios);
-
-static int _truncate_mirrors(struct ore_io_state *ios, unsigned cur_comp,
- struct osd_attr *attr)
-{
- int last_comp = cur_comp + ios->layout->mirrors_p1;
-
- for (; cur_comp < last_comp; ++cur_comp) {
- struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
- struct osd_request *or;
-
- or = osd_start_request(_ios_od(ios, cur_comp), GFP_KERNEL);
- if (unlikely(!or)) {
- ORE_ERR("%s: osd_start_request failed\n", __func__);
- return -ENOMEM;
- }
- per_dev->or = or;
-
- osd_req_set_attributes(or, _ios_obj(ios, cur_comp));
- osd_req_add_set_attr_list(or, attr, 1);
- }
-
- return 0;
-}
-
-struct _trunc_info {
- struct ore_striping_info si;
- u64 prev_group_obj_off;
- u64 next_group_obj_off;
-
- unsigned first_group_dev;
- unsigned nex_group_dev;
-};
-
-static void _calc_trunk_info(struct ore_layout *layout, u64 file_offset,
- struct _trunc_info *ti)
-{
- unsigned stripe_unit = layout->stripe_unit;
-
- ore_calc_stripe_info(layout, file_offset, 0, &ti->si);
-
- ti->prev_group_obj_off = ti->si.M * stripe_unit;
- ti->next_group_obj_off = ti->si.M ? (ti->si.M - 1) * stripe_unit : 0;
-
- ti->first_group_dev = ti->si.dev - (ti->si.dev % layout->group_width);
- ti->nex_group_dev = ti->first_group_dev + layout->group_width;
-}
-
-int ore_truncate(struct ore_layout *layout, struct ore_components *oc,
- u64 size)
-{
- struct ore_io_state *ios;
- struct exofs_trunc_attr {
- struct osd_attr attr;
- __be64 newsize;
- } *size_attrs;
- struct _trunc_info ti;
- int i, ret;
-
- ret = ore_get_io_state(layout, oc, &ios);
- if (unlikely(ret))
- return ret;
-
- _calc_trunk_info(ios->layout, size, &ti);
-
- size_attrs = kcalloc(ios->oc->numdevs, sizeof(*size_attrs),
- GFP_KERNEL);
- if (unlikely(!size_attrs)) {
- ret = -ENOMEM;
- goto out;
- }
-
- ios->numdevs = ios->oc->numdevs;
-
- for (i = 0; i < ios->numdevs; ++i) {
- struct exofs_trunc_attr *size_attr = &size_attrs[i];
- u64 obj_size;
-
- if (i < ti.first_group_dev)
- obj_size = ti.prev_group_obj_off;
- else if (i >= ti.nex_group_dev)
- obj_size = ti.next_group_obj_off;
- else if (i < ti.si.dev) /* dev within this group */
- obj_size = ti.si.obj_offset +
- ios->layout->stripe_unit - ti.si.unit_off;
- else if (i == ti.si.dev)
- obj_size = ti.si.obj_offset;
- else /* i > ti.dev */
- obj_size = ti.si.obj_offset - ti.si.unit_off;
-
- size_attr->newsize = cpu_to_be64(obj_size);
- size_attr->attr = g_attr_logical_length;
- size_attr->attr.val_ptr = &size_attr->newsize;
-
- ORE_DBGMSG2("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
- _LLU(oc->comps->obj.id), _LLU(obj_size), i);
- ret = _truncate_mirrors(ios, i * ios->layout->mirrors_p1,
- &size_attr->attr);
- if (unlikely(ret))
- goto out;
- }
- ret = ore_io_execute(ios);
-
-out:
- kfree(size_attrs);
- ore_put_io_state(ios);
- return ret;
-}
-EXPORT_SYMBOL(ore_truncate);
-
-const struct osd_attr g_attr_logical_length = ATTR_DEF(
- OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
-EXPORT_SYMBOL(g_attr_logical_length);
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
deleted file mode 100644
index 27cbdb697649..000000000000
--- a/fs/exofs/ore_raid.c
+++ /dev/null
@@ -1,721 +0,0 @@
-/*
- * Copyright (C) 2011
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * This file is part of the objects raid engine (ore).
- *
- * It is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * You should have received a copy of the GNU General Public License
- * along with "ore". If not, write to the Free Software Foundation, Inc:
- * "Free Software Foundation <info@fsf.org>"
- */
-
-#include <linux/gfp.h>
-#include <linux/async_tx.h>
-
-#include "ore_raid.h"
-
-#undef ORE_DBGMSG2
-#define ORE_DBGMSG2 ORE_DBGMSG
-
-static struct page *_raid_page_alloc(void)
-{
- return alloc_page(GFP_KERNEL);
-}
-
-static void _raid_page_free(struct page *p)
-{
- __free_page(p);
-}
-
-/* This struct is forward declare in ore_io_state, but is private to here.
- * It is put on ios->sp2d for RAID5/6 writes only. See _gen_xor_unit.
- *
- * __stripe_pages_2d is a 2d array of pages, and it is also a corner turn.
- * Ascending page index access is sp2d(p-minor, c-major). But storage is
- * sp2d[p-minor][c-major], so it can be properlly presented to the async-xor
- * API.
- */
-struct __stripe_pages_2d {
- /* Cache some hot path repeated calculations */
- unsigned parity;
- unsigned data_devs;
- unsigned pages_in_unit;
-
- bool needed ;
-
- /* Array size is pages_in_unit (layout->stripe_unit / PAGE_SIZE) */
- struct __1_page_stripe {
- bool alloc;
- unsigned write_count;
- struct async_submit_ctl submit;
- struct dma_async_tx_descriptor *tx;
-
- /* The size of this array is data_devs + parity */
- struct page **pages;
- struct page **scribble;
- /* bool array, size of this array is data_devs */
- char *page_is_read;
- } _1p_stripes[];
-};
-
-/* This can get bigger then a page. So support multiple page allocations
- * _sp2d_free should be called even if _sp2d_alloc fails (by returning
- * none-zero).
- */
-static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width,
- unsigned parity, struct __stripe_pages_2d **psp2d)
-{
- struct __stripe_pages_2d *sp2d;
- unsigned data_devs = group_width - parity;
- struct _alloc_all_bytes {
- struct __alloc_stripe_pages_2d {
- struct __stripe_pages_2d sp2d;
- struct __1_page_stripe _1p_stripes[pages_in_unit];
- } __asp2d;
- struct __alloc_1p_arrays {
- struct page *pages[group_width];
- struct page *scribble[group_width];
- char page_is_read[data_devs];
- } __a1pa[pages_in_unit];
- } *_aab;
- struct __alloc_1p_arrays *__a1pa;
- struct __alloc_1p_arrays *__a1pa_end;
- const unsigned sizeof__a1pa = sizeof(_aab->__a1pa[0]);
- unsigned num_a1pa, alloc_size, i;
-
- /* FIXME: check these numbers in ore_verify_layout */
- BUG_ON(sizeof(_aab->__asp2d) > PAGE_SIZE);
- BUG_ON(sizeof__a1pa > PAGE_SIZE);
-
- if (sizeof(*_aab) > PAGE_SIZE) {
- num_a1pa = (PAGE_SIZE - sizeof(_aab->__asp2d)) / sizeof__a1pa;
- alloc_size = sizeof(_aab->__asp2d) + sizeof__a1pa * num_a1pa;
- } else {
- num_a1pa = pages_in_unit;
- alloc_size = sizeof(*_aab);
- }
-
- _aab = kzalloc(alloc_size, GFP_KERNEL);
- if (unlikely(!_aab)) {
- ORE_DBGMSG("!! Failed to alloc sp2d size=%d\n", alloc_size);
- return -ENOMEM;
- }
-
- sp2d = &_aab->__asp2d.sp2d;
- *psp2d = sp2d; /* From here Just call _sp2d_free */
-
- __a1pa = _aab->__a1pa;
- __a1pa_end = __a1pa + num_a1pa;
-
- for (i = 0; i < pages_in_unit; ++i) {
- if (unlikely(__a1pa >= __a1pa_end)) {
- num_a1pa = min_t(unsigned, PAGE_SIZE / sizeof__a1pa,
- pages_in_unit - i);
-
- __a1pa = kcalloc(num_a1pa, sizeof__a1pa, GFP_KERNEL);
- if (unlikely(!__a1pa)) {
- ORE_DBGMSG("!! Failed to _alloc_1p_arrays=%d\n",
- num_a1pa);
- return -ENOMEM;
- }
- __a1pa_end = __a1pa + num_a1pa;
- /* First *pages is marked for kfree of the buffer */
- sp2d->_1p_stripes[i].alloc = true;
- }
-
- sp2d->_1p_stripes[i].pages = __a1pa->pages;
- sp2d->_1p_stripes[i].scribble = __a1pa->scribble ;
- sp2d->_1p_stripes[i].page_is_read = __a1pa->page_is_read;
- ++__a1pa;
- }
-
- sp2d->parity = parity;
- sp2d->data_devs = data_devs;
- sp2d->pages_in_unit = pages_in_unit;
- return 0;
-}
-
-static void _sp2d_reset(struct __stripe_pages_2d *sp2d,
- const struct _ore_r4w_op *r4w, void *priv)
-{
- unsigned data_devs = sp2d->data_devs;
- unsigned group_width = data_devs + sp2d->parity;
- int p, c;
-
- if (!sp2d->needed)
- return;
-
- for (c = data_devs - 1; c >= 0; --c)
- for (p = sp2d->pages_in_unit - 1; p >= 0; --p) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
- if (_1ps->page_is_read[c]) {
- struct page *page = _1ps->pages[c];
-
- r4w->put_page(priv, page);
- _1ps->page_is_read[c] = false;
- }
- }
-
- for (p = 0; p < sp2d->pages_in_unit; p++) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
- memset(_1ps->pages, 0, group_width * sizeof(*_1ps->pages));
- _1ps->write_count = 0;
- _1ps->tx = NULL;
- }
-
- sp2d->needed = false;
-}
-
-static void _sp2d_free(struct __stripe_pages_2d *sp2d)
-{
- unsigned i;
-
- if (!sp2d)
- return;
-
- for (i = 0; i < sp2d->pages_in_unit; ++i) {
- if (sp2d->_1p_stripes[i].alloc)
- kfree(sp2d->_1p_stripes[i].pages);
- }
-
- kfree(sp2d);
-}
-
-static unsigned _sp2d_min_pg(struct __stripe_pages_2d *sp2d)
-{
- unsigned p;
-
- for (p = 0; p < sp2d->pages_in_unit; p++) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
- if (_1ps->write_count)
- return p;
- }
-
- return ~0;
-}
-
-static unsigned _sp2d_max_pg(struct __stripe_pages_2d *sp2d)
-{
- int p;
-
- for (p = sp2d->pages_in_unit - 1; p >= 0; --p) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
- if (_1ps->write_count)
- return p;
- }
-
- return ~0;
-}
-
-static void _gen_xor_unit(struct __stripe_pages_2d *sp2d)
-{
- unsigned p;
- unsigned tx_flags = ASYNC_TX_ACK;
-
- if (sp2d->parity == 1)
- tx_flags |= ASYNC_TX_XOR_ZERO_DST;
-
- for (p = 0; p < sp2d->pages_in_unit; p++) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
- if (!_1ps->write_count)
- continue;
-
- init_async_submit(&_1ps->submit, tx_flags,
- NULL, NULL, NULL, (addr_conv_t *)_1ps->scribble);
-
- if (sp2d->parity == 1)
- _1ps->tx = async_xor(_1ps->pages[sp2d->data_devs],
- _1ps->pages, 0, sp2d->data_devs,
- PAGE_SIZE, &_1ps->submit);
- else /* parity == 2 */
- _1ps->tx = async_gen_syndrome(_1ps->pages, 0,
- sp2d->data_devs + sp2d->parity,
- PAGE_SIZE, &_1ps->submit);
- }
-
- for (p = 0; p < sp2d->pages_in_unit; p++) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
- /* NOTE: We wait for HW synchronously (I don't have such HW
- * to test with.) Is parallelism needed with today's multi
- * cores?
- */
- async_tx_issue_pending(_1ps->tx);
- }
-}
-
-void _ore_add_stripe_page(struct __stripe_pages_2d *sp2d,
- struct ore_striping_info *si, struct page *page)
-{
- struct __1_page_stripe *_1ps;
-
- sp2d->needed = true;
-
- _1ps = &sp2d->_1p_stripes[si->cur_pg];
- _1ps->pages[si->cur_comp] = page;
- ++_1ps->write_count;
-
- si->cur_pg = (si->cur_pg + 1) % sp2d->pages_in_unit;
- /* si->cur_comp is advanced outside at main loop */
-}
-
-void _ore_add_sg_seg(struct ore_per_dev_state *per_dev, unsigned cur_len,
- bool not_last)
-{
- struct osd_sg_entry *sge;
-
- ORE_DBGMSG("dev=%d cur_len=0x%x not_last=%d cur_sg=%d "
- "offset=0x%llx length=0x%x last_sgs_total=0x%x\n",
- per_dev->dev, cur_len, not_last, per_dev->cur_sg,
- _LLU(per_dev->offset), per_dev->length,
- per_dev->last_sgs_total);
-
- if (!per_dev->cur_sg) {
- sge = per_dev->sglist;
-
- /* First time we prepare two entries */
- if (per_dev->length) {
- ++per_dev->cur_sg;
- sge->offset = per_dev->offset;
- sge->len = per_dev->length;
- } else {
- /* Here the parity is the first unit of this object.
- * This happens every time we reach a parity device on
- * the same stripe as the per_dev->offset. We need to
- * just skip this unit.
- */
- per_dev->offset += cur_len;
- return;
- }
- } else {
- /* finalize the last one */
- sge = &per_dev->sglist[per_dev->cur_sg - 1];
- sge->len = per_dev->length - per_dev->last_sgs_total;
- }
-
- if (not_last) {
- /* Partly prepare the next one */
- struct osd_sg_entry *next_sge = sge + 1;
-
- ++per_dev->cur_sg;
- next_sge->offset = sge->offset + sge->len + cur_len;
- /* Save cur len so we know how mutch was added next time */
- per_dev->last_sgs_total = per_dev->length;
- next_sge->len = 0;
- } else if (!sge->len) {
- /* Optimize for when the last unit is a parity */
- --per_dev->cur_sg;
- }
-}
-
-static int _alloc_read_4_write(struct ore_io_state *ios)
-{
- struct ore_layout *layout = ios->layout;
- int ret;
- /* We want to only read those pages not in cache so worst case
- * is a stripe populated with every other page
- */
- unsigned sgs_per_dev = ios->sp2d->pages_in_unit + 2;
-
- ret = _ore_get_io_state(layout, ios->oc,
- layout->group_width * layout->mirrors_p1,
- sgs_per_dev, 0, &ios->ios_read_4_write);
- return ret;
-}
-
-/* @si contains info of the to-be-inserted page. Update of @si should be
- * maintained by caller. Specificaly si->dev, si->obj_offset, ...
- */
-static int _add_to_r4w(struct ore_io_state *ios, struct ore_striping_info *si,
- struct page *page, unsigned pg_len)
-{
- struct request_queue *q;
- struct ore_per_dev_state *per_dev;
- struct ore_io_state *read_ios;
- unsigned first_dev = si->dev - (si->dev %
- (ios->layout->group_width * ios->layout->mirrors_p1));
- unsigned comp = si->dev - first_dev;
- unsigned added_len;
-
- if (!ios->ios_read_4_write) {
- int ret = _alloc_read_4_write(ios);
-
- if (unlikely(ret))
- return ret;
- }
-
- read_ios = ios->ios_read_4_write;
- read_ios->numdevs = ios->layout->group_width * ios->layout->mirrors_p1;
-
- per_dev = &read_ios->per_dev[comp];
- if (!per_dev->length) {
- per_dev->bio = bio_kmalloc(GFP_KERNEL,
- ios->sp2d->pages_in_unit);
- if (unlikely(!per_dev->bio)) {
- ORE_DBGMSG("Failed to allocate BIO size=%u\n",
- ios->sp2d->pages_in_unit);
- return -ENOMEM;
- }
- per_dev->offset = si->obj_offset;
- per_dev->dev = si->dev;
- } else if (si->obj_offset != (per_dev->offset + per_dev->length)) {
- u64 gap = si->obj_offset - (per_dev->offset + per_dev->length);
-
- _ore_add_sg_seg(per_dev, gap, true);
- }
- q = osd_request_queue(ore_comp_dev(read_ios->oc, per_dev->dev));
- added_len = bio_add_pc_page(q, per_dev->bio, page, pg_len,
- si->obj_offset % PAGE_SIZE);
- if (unlikely(added_len != pg_len)) {
- ORE_DBGMSG("Failed to bio_add_pc_page bi_vcnt=%d\n",
- per_dev->bio->bi_vcnt);
- return -ENOMEM;
- }
-
- per_dev->length += pg_len;
- return 0;
-}
-
-/* read the beginning of an unaligned first page */
-static int _add_to_r4w_first_page(struct ore_io_state *ios, struct page *page)
-{
- struct ore_striping_info si;
- unsigned pg_len;
-
- ore_calc_stripe_info(ios->layout, ios->offset, 0, &si);
-
- pg_len = si.obj_offset % PAGE_SIZE;
- si.obj_offset -= pg_len;
-
- ORE_DBGMSG("offset=0x%llx len=0x%x index=0x%lx dev=%x\n",
- _LLU(si.obj_offset), pg_len, page->index, si.dev);
-
- return _add_to_r4w(ios, &si, page, pg_len);
-}
-
-/* read the end of an incomplete last page */
-static int _add_to_r4w_last_page(struct ore_io_state *ios, u64 *offset)
-{
- struct ore_striping_info si;
- struct page *page;
- unsigned pg_len, p, c;
-
- ore_calc_stripe_info(ios->layout, *offset, 0, &si);
-
- p = si.cur_pg;
- c = si.cur_comp;
- page = ios->sp2d->_1p_stripes[p].pages[c];
-
- pg_len = PAGE_SIZE - (si.unit_off % PAGE_SIZE);
- *offset += pg_len;
-
- ORE_DBGMSG("p=%d, c=%d next-offset=0x%llx len=0x%x dev=%x par_dev=%d\n",
- p, c, _LLU(*offset), pg_len, si.dev, si.par_dev);
-
- BUG_ON(!page);
-
- return _add_to_r4w(ios, &si, page, pg_len);
-}
-
-static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret)
-{
- struct bio_vec *bv;
- unsigned i, d;
-
- /* loop on all devices all pages */
- for (d = 0; d < ios->numdevs; d++) {
- struct bio *bio = ios->per_dev[d].bio;
-
- if (!bio)
- continue;
-
- bio_for_each_segment_all(bv, bio, i) {
- struct page *page = bv->bv_page;
-
- SetPageUptodate(page);
- if (PageError(page))
- ClearPageError(page);
- }
- }
-}
-
-/* read_4_write is hacked to read the start of the first stripe and/or
- * the end of the last stripe. If needed, with an sg-gap at each device/page.
- * It is assumed to be called after the to_be_written pages of the first stripe
- * are populating ios->sp2d[][]
- *
- * NOTE: We call ios->r4w->lock_fn for all pages needed for parity calculations
- * These pages are held at sp2d[p].pages[c] but with
- * sp2d[p].page_is_read[c] = true. At _sp2d_reset these pages are
- * ios->r4w->lock_fn(). The ios->r4w->lock_fn might signal that the page is
- * @uptodate=true, so we don't need to read it, only unlock, after IO.
- *
- * TODO: The read_4_write should calc a need_to_read_pages_count, if bigger then
- * to-be-written count, we should consider the xor-in-place mode.
- * need_to_read_pages_count is the actual number of pages not present in cache.
- * maybe "devs_in_group - ios->sp2d[p].write_count" is a good enough
- * approximation? In this mode the read pages are put in the empty places of
- * ios->sp2d[p][*], xor is calculated the same way. These pages are
- * allocated/freed and don't go through cache
- */
-static int _read_4_write_first_stripe(struct ore_io_state *ios)
-{
- struct ore_striping_info read_si;
- struct __stripe_pages_2d *sp2d = ios->sp2d;
- u64 offset = ios->si.first_stripe_start;
- unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1;
-
- if (offset == ios->offset) /* Go to start collect $200 */
- goto read_last_stripe;
-
- min_p = _sp2d_min_pg(sp2d);
- max_p = _sp2d_max_pg(sp2d);
-
- ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n",
- offset, ios->offset, min_p, max_p);
-
- for (c = 0; ; c++) {
- ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
- read_si.obj_offset += min_p * PAGE_SIZE;
- offset += min_p * PAGE_SIZE;
- for (p = min_p; p <= max_p; p++) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
- struct page **pp = &_1ps->pages[c];
- bool uptodate;
-
- if (*pp) {
- if (ios->offset % PAGE_SIZE)
- /* Read the remainder of the page */
- _add_to_r4w_first_page(ios, *pp);
- /* to-be-written pages start here */
- goto read_last_stripe;
- }
-
- *pp = ios->r4w->get_page(ios->private, offset,
- &uptodate);
- if (unlikely(!*pp))
- return -ENOMEM;
-
- if (!uptodate)
- _add_to_r4w(ios, &read_si, *pp, PAGE_SIZE);
-
- /* Mark read-pages to be cache_released */
- _1ps->page_is_read[c] = true;
- read_si.obj_offset += PAGE_SIZE;
- offset += PAGE_SIZE;
- }
- offset += (sp2d->pages_in_unit - p) * PAGE_SIZE;
- }
-
-read_last_stripe:
- return 0;
-}
-
-static int _read_4_write_last_stripe(struct ore_io_state *ios)
-{
- struct ore_striping_info read_si;
- struct __stripe_pages_2d *sp2d = ios->sp2d;
- u64 offset;
- u64 last_stripe_end;
- unsigned bytes_in_stripe = ios->si.bytes_in_stripe;
- unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1;
-
- offset = ios->offset + ios->length;
- if (offset % PAGE_SIZE)
- _add_to_r4w_last_page(ios, &offset);
- /* offset will be aligned to next page */
-
- last_stripe_end = div_u64(offset + bytes_in_stripe - 1, bytes_in_stripe)
- * bytes_in_stripe;
- if (offset == last_stripe_end) /* Optimize for the aligned case */
- goto read_it;
-
- ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
- p = read_si.cur_pg;
- c = read_si.cur_comp;
-
- if (min_p == sp2d->pages_in_unit) {
- /* Didn't do it yet */
- min_p = _sp2d_min_pg(sp2d);
- max_p = _sp2d_max_pg(sp2d);
- }
-
- ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n",
- offset, last_stripe_end, min_p, max_p);
-
- while (offset < last_stripe_end) {
- struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
- if ((min_p <= p) && (p <= max_p)) {
- struct page *page;
- bool uptodate;
-
- BUG_ON(_1ps->pages[c]);
- page = ios->r4w->get_page(ios->private, offset,
- &uptodate);
- if (unlikely(!page))
- return -ENOMEM;
-
- _1ps->pages[c] = page;
- /* Mark read-pages to be cache_released */
- _1ps->page_is_read[c] = true;
- if (!uptodate)
- _add_to_r4w(ios, &read_si, page, PAGE_SIZE);
- }
-
- offset += PAGE_SIZE;
- if (p == (sp2d->pages_in_unit - 1)) {
- ++c;
- p = 0;
- ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
- } else {
- read_si.obj_offset += PAGE_SIZE;
- ++p;
- }
- }
-
-read_it:
- return 0;
-}
-
-static int _read_4_write_execute(struct ore_io_state *ios)
-{
- struct ore_io_state *ios_read;
- unsigned i;
- int ret;
-
- ios_read = ios->ios_read_4_write;
- if (!ios_read)
- return 0;
-
- /* FIXME: Ugly to signal _sbi_read_mirror that we have bio(s). Change
- * to check for per_dev->bio
- */
- ios_read->pages = ios->pages;
-
- /* Now read these devices */
- for (i = 0; i < ios_read->numdevs; i += ios_read->layout->mirrors_p1) {
- ret = _ore_read_mirror(ios_read, i);
- if (unlikely(ret))
- return ret;
- }
-
- ret = ore_io_execute(ios_read); /* Synchronus execution */
- if (unlikely(ret)) {
- ORE_DBGMSG("!! ore_io_execute => %d\n", ret);
- return ret;
- }
-
- _mark_read4write_pages_uptodate(ios_read, ret);
- ore_put_io_state(ios_read);
- ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */
- return 0;
-}
-
-/* In writes @cur_len means length left. .i.e cur_len==0 is the last parity U */
-int _ore_add_parity_unit(struct ore_io_state *ios,
- struct ore_striping_info *si,
- struct ore_per_dev_state *per_dev,
- unsigned cur_len, bool do_xor)
-{
- if (ios->reading) {
- if (per_dev->cur_sg >= ios->sgs_per_dev) {
- ORE_DBGMSG("cur_sg(%d) >= sgs_per_dev(%d)\n" ,
- per_dev->cur_sg, ios->sgs_per_dev);
- return -ENOMEM;
- }
- _ore_add_sg_seg(per_dev, cur_len, true);
- } else {
- struct __stripe_pages_2d *sp2d = ios->sp2d;
- struct page **pages = ios->parity_pages + ios->cur_par_page;
- unsigned num_pages;
- unsigned array_start = 0;
- unsigned i;
- int ret;
-
- si->cur_pg = _sp2d_min_pg(sp2d);
- num_pages = _sp2d_max_pg(sp2d) + 1 - si->cur_pg;
-
- if (!per_dev->length) {
- per_dev->offset += si->cur_pg * PAGE_SIZE;
- /* If first stripe, Read in all read4write pages
- * (if needed) before we calculate the first parity.
- */
- if (do_xor)
- _read_4_write_first_stripe(ios);
- }
- if (!cur_len && do_xor)
- /* If last stripe r4w pages of last stripe */
- _read_4_write_last_stripe(ios);
- _read_4_write_execute(ios);
-
- for (i = 0; i < num_pages; i++) {
- pages[i] = _raid_page_alloc();
- if (unlikely(!pages[i]))
- return -ENOMEM;
-
- ++(ios->cur_par_page);
- }
-
- BUG_ON(si->cur_comp < sp2d->data_devs);
- BUG_ON(si->cur_pg + num_pages > sp2d->pages_in_unit);
-
- ret = _ore_add_stripe_unit(ios, &array_start, 0, pages,
- per_dev, num_pages * PAGE_SIZE);
- if (unlikely(ret))
- return ret;
-
- if (do_xor) {
- _gen_xor_unit(sp2d);
- _sp2d_reset(sp2d, ios->r4w, ios->private);
- }
- }
- return 0;
-}
-
-int _ore_post_alloc_raid_stuff(struct ore_io_state *ios)
-{
- if (ios->parity_pages) {
- struct ore_layout *layout = ios->layout;
- unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE;
-
- if (_sp2d_alloc(pages_in_unit, layout->group_width,
- layout->parity, &ios->sp2d)) {
- return -ENOMEM;
- }
- }
- return 0;
-}
-
-void _ore_free_raid_stuff(struct ore_io_state *ios)
-{
- if (ios->sp2d) { /* writing and raid */
- unsigned i;
-
- for (i = 0; i < ios->cur_par_page; i++) {
- struct page *page = ios->parity_pages[i];
-
- if (page)
- _raid_page_free(page);
- }
- if (ios->extra_part_alloc)
- kfree(ios->parity_pages);
- /* If IO returned an error pages might need unlocking */
- _sp2d_reset(ios->sp2d, ios->r4w, ios->private);
- _sp2d_free(ios->sp2d);
- } else {
- /* Will only be set if raid reading && sglist is big */
- if (ios->extra_part_alloc)
- kfree(ios->per_dev[0].sglist);
- }
- if (ios->ios_read_4_write)
- ore_put_io_state(ios->ios_read_4_write);
-}
diff --git a/fs/exofs/ore_raid.h b/fs/exofs/ore_raid.h
deleted file mode 100644
index a6e746775570..000000000000
--- a/fs/exofs/ore_raid.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Copyright (C) from 2011
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * This file is part of the objects raid engine (ore).
- *
- * It is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * You should have received a copy of the GNU General Public License
- * along with "ore". If not, write to the Free Software Foundation, Inc:
- * "Free Software Foundation <info@fsf.org>"
- */
-
-#include <scsi/osd_ore.h>
-
-#define ORE_ERR(fmt, a...) printk(KERN_ERR "ore: " fmt, ##a)
-
-#ifdef CONFIG_EXOFS_DEBUG
-#define ORE_DBGMSG(fmt, a...) \
- printk(KERN_NOTICE "ore @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define ORE_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)
-
-#define ORE_DBGMSG2(M...) do {} while (0)
-/* #define ORE_DBGMSG2 ORE_DBGMSG */
-
-/* ios_raid.c stuff needed by ios.c */
-int _ore_post_alloc_raid_stuff(struct ore_io_state *ios);
-void _ore_free_raid_stuff(struct ore_io_state *ios);
-
-void _ore_add_sg_seg(struct ore_per_dev_state *per_dev, unsigned cur_len,
- bool not_last);
-int _ore_add_parity_unit(struct ore_io_state *ios, struct ore_striping_info *si,
- struct ore_per_dev_state *per_dev, unsigned cur_len,
- bool do_xor);
-void _ore_add_stripe_page(struct __stripe_pages_2d *sp2d,
- struct ore_striping_info *si, struct page *page);
-static inline void _add_stripe_page(struct __stripe_pages_2d *sp2d,
- struct ore_striping_info *si, struct page *page)
-{
- if (!sp2d) /* Inline the fast path */
- return; /* Hay no raid stuff */
- _ore_add_stripe_page(sp2d, si, page);
-}
-
-/* ios.c stuff needed by ios_raid.c */
-int _ore_get_io_state(struct ore_layout *layout,
- struct ore_components *oc, unsigned numdevs,
- unsigned sgs_per_dev, unsigned num_par_pages,
- struct ore_io_state **pios);
-int _ore_add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg,
- unsigned pgbase, struct page **pages,
- struct ore_per_dev_state *per_dev, int cur_len);
-int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp);
-int ore_io_execute(struct ore_io_state *ios);
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
deleted file mode 100644
index 1076a4233b39..000000000000
--- a/fs/exofs/super.c
+++ /dev/null
@@ -1,1049 +0,0 @@
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.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/string.h>
-#include <linux/parser.h>
-#include <linux/vfs.h>
-#include <linux/random.h>
-#include <linux/module.h>
-#include <linux/exportfs.h>
-#include <linux/slab.h>
-
-#include "exofs.h"
-
-#define EXOFS_DBGMSG2(M...) do {} while (0)
-
-/******************************************************************************
- * MOUNT OPTIONS
- *****************************************************************************/
-
-/*
- * struct to hold what we get from mount options
- */
-struct exofs_mountopt {
- bool is_osdname;
- const char *dev_name;
- uint64_t pid;
- int timeout;
-};
-
-/*
- * exofs-specific mount-time options.
- */
-enum { Opt_name, Opt_pid, Opt_to, Opt_err };
-
-/*
- * Our mount-time options. These should ideally be 64-bit unsigned, but the
- * kernel's parsing functions do not currently support that. 32-bit should be
- * sufficient for most applications now.
- */
-static match_table_t tokens = {
- {Opt_name, "osdname=%s"},
- {Opt_pid, "pid=%u"},
- {Opt_to, "to=%u"},
- {Opt_err, NULL}
-};
-
-/*
- * The main option parsing method. Also makes sure that all of the mandatory
- * mount options were set.
- */
-static int parse_options(char *options, struct exofs_mountopt *opts)
-{
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int option;
- bool s_pid = false;
-
- EXOFS_DBGMSG("parse_options %s\n", options);
- /* defaults */
- memset(opts, 0, sizeof(*opts));
- opts->timeout = BLK_DEFAULT_SG_TIMEOUT;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
- char str[32];
-
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_name:
- opts->dev_name = match_strdup(&args[0]);
- if (unlikely(!opts->dev_name)) {
- EXOFS_ERR("Error allocating dev_name");
- return -ENOMEM;
- }
- opts->is_osdname = true;
- break;
- case Opt_pid:
- if (0 == match_strlcpy(str, &args[0], sizeof(str)))
- return -EINVAL;
- opts->pid = simple_strtoull(str, NULL, 0);
- if (opts->pid < EXOFS_MIN_PID) {
- EXOFS_ERR("Partition ID must be >= %u",
- EXOFS_MIN_PID);
- return -EINVAL;
- }
- s_pid = 1;
- break;
- case Opt_to:
- if (match_int(&args[0], &option))
- return -EINVAL;
- if (option <= 0) {
- EXOFS_ERR("Timeout must be > 0");
- return -EINVAL;
- }
- opts->timeout = option * HZ;
- break;
- }
- }
-
- if (!s_pid) {
- EXOFS_ERR("Need to specify the following options:\n");
- EXOFS_ERR(" -o pid=pid_no_to_use\n");
- return -EINVAL;
- }
-
- return 0;
-}
-
-/******************************************************************************
- * INODE CACHE
- *****************************************************************************/
-
-/*
- * Our inode cache. Isn't it pretty?
- */
-static struct kmem_cache *exofs_inode_cachep;
-
-/*
- * Allocate an inode in the cache
- */
-static struct inode *exofs_alloc_inode(struct super_block *sb)
-{
- struct exofs_i_info *oi;
-
- oi = kmem_cache_alloc(exofs_inode_cachep, GFP_KERNEL);
- if (!oi)
- return NULL;
-
- oi->vfs_inode.i_version = 1;
- return &oi->vfs_inode;
-}
-
-static void exofs_i_callback(struct rcu_head *head)
-{
- struct inode *inode = container_of(head, struct inode, i_rcu);
- kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
-}
-
-/*
- * Remove an inode from the cache
- */
-static void exofs_destroy_inode(struct inode *inode)
-{
- call_rcu(&inode->i_rcu, exofs_i_callback);
-}
-
-/*
- * Initialize the inode
- */
-static void exofs_init_once(void *foo)
-{
- struct exofs_i_info *oi = foo;
-
- inode_init_once(&oi->vfs_inode);
-}
-
-/*
- * Create and initialize the inode cache
- */
-static int init_inodecache(void)
-{
- exofs_inode_cachep = kmem_cache_create("exofs_inode_cache",
- sizeof(struct exofs_i_info), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
- SLAB_ACCOUNT, exofs_init_once);
- if (exofs_inode_cachep == NULL)
- return -ENOMEM;
- return 0;
-}
-
-/*
- * Destroy the inode cache
- */
-static void destroy_inodecache(void)
-{
- /*
- * Make sure all delayed rcu free inodes are flushed before we
- * destroy cache.
- */
- rcu_barrier();
- kmem_cache_destroy(exofs_inode_cachep);
-}
-
-/******************************************************************************
- * Some osd helpers
- *****************************************************************************/
-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);
-}
-
-static int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj,
- u64 offset, void *p, unsigned length)
-{
- struct osd_request *or = osd_start_request(od, GFP_KERNEL);
-/* struct osd_sense_info osi = {.key = 0};*/
- int ret;
-
- if (unlikely(!or)) {
- EXOFS_DBGMSG("%s: osd_start_request failed.\n", __func__);
- return -ENOMEM;
- }
- ret = osd_req_read_kern(or, obj, offset, p, length);
- if (unlikely(ret)) {
- EXOFS_DBGMSG("%s: osd_req_read_kern failed.\n", __func__);
- goto out;
- }
-
- ret = osd_finalize_request(or, 0, cred, NULL);
- if (unlikely(ret)) {
- EXOFS_DBGMSG("Failed to osd_finalize_request() => %d\n", ret);
- goto out;
- }
-
- ret = osd_execute_request(or);
- if (unlikely(ret))
- EXOFS_DBGMSG("osd_execute_request() => %d\n", ret);
- /* osd_req_decode_sense(or, ret); */
-
-out:
- osd_end_request(or);
- EXOFS_DBGMSG2("read_kern(0x%llx) offset=0x%llx "
- "length=0x%llx dev=%p ret=>%d\n",
- _LLU(obj->id), _LLU(offset), _LLU(length), od, ret);
- return ret;
-}
-
-static const struct osd_attr g_attr_sb_stats = ATTR_DEF(
- EXOFS_APAGE_SB_DATA,
- EXOFS_ATTR_SB_STATS,
- sizeof(struct exofs_sb_stats));
-
-static int __sbi_read_stats(struct exofs_sb_info *sbi)
-{
- struct osd_attr attrs[] = {
- [0] = g_attr_sb_stats,
- };
- struct ore_io_state *ios;
- int ret;
-
- ret = ore_get_io_state(&sbi->layout, &sbi->oc, &ios);
- if (unlikely(ret)) {
- EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__);
- return ret;
- }
-
- ios->in_attr = attrs;
- ios->in_attr_len = ARRAY_SIZE(attrs);
-
- ret = ore_read(ios);
- if (unlikely(ret)) {
- EXOFS_ERR("Error reading super_block stats => %d\n", ret);
- goto out;
- }
-
- ret = extract_attr_from_ios(ios, &attrs[0]);
- if (ret) {
- EXOFS_ERR("%s: extract_attr of sb_stats failed\n", __func__);
- goto out;
- }
- if (attrs[0].len) {
- struct exofs_sb_stats *ess;
-
- if (unlikely(attrs[0].len != sizeof(*ess))) {
- EXOFS_ERR("%s: Wrong version of exofs_sb_stats "
- "size(%d) != expected(%zd)\n",
- __func__, attrs[0].len, sizeof(*ess));
- goto out;
- }
-
- ess = attrs[0].val_ptr;
- sbi->s_nextid = le64_to_cpu(ess->s_nextid);
- sbi->s_numfiles = le32_to_cpu(ess->s_numfiles);
- }
-
-out:
- ore_put_io_state(ios);
- return ret;
-}
-
-static void stats_done(struct ore_io_state *ios, void *p)
-{
- ore_put_io_state(ios);
- /* Good thanks nothing to do anymore */
-}
-
-/* Asynchronously write the stats attribute */
-int exofs_sbi_write_stats(struct exofs_sb_info *sbi)
-{
- struct osd_attr attrs[] = {
- [0] = g_attr_sb_stats,
- };
- struct ore_io_state *ios;
- int ret;
-
- ret = ore_get_io_state(&sbi->layout, &sbi->oc, &ios);
- if (unlikely(ret)) {
- EXOFS_ERR("%s: ore_get_io_state failed.\n", __func__);
- return ret;
- }
-
- sbi->s_ess.s_nextid = cpu_to_le64(sbi->s_nextid);
- sbi->s_ess.s_numfiles = cpu_to_le64(sbi->s_numfiles);
- attrs[0].val_ptr = &sbi->s_ess;
-
-
- ios->done = stats_done;
- ios->private = sbi;
- ios->out_attr = attrs;
- ios->out_attr_len = ARRAY_SIZE(attrs);
-
- ret = ore_write(ios);
- if (unlikely(ret)) {
- EXOFS_ERR("%s: ore_write failed.\n", __func__);
- ore_put_io_state(ios);
- }
-
- return ret;
-}
-
-/******************************************************************************
- * SUPERBLOCK FUNCTIONS
- *****************************************************************************/
-static const struct super_operations exofs_sops;
-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)
-{
- struct exofs_sb_info *sbi;
- struct exofs_fscb *fscb;
- struct ore_comp one_comp;
- struct ore_components oc;
- struct ore_io_state *ios;
- int ret = -ENOMEM;
-
- fscb = kmalloc(sizeof(*fscb), GFP_KERNEL);
- if (unlikely(!fscb))
- return -ENOMEM;
-
- sbi = sb->s_fs_info;
-
- /* NOTE: We no longer dirty the super_block anywhere in exofs. The
- * reason we write the fscb here on unmount is so we can stay backwards
- * compatible with fscb->s_version == 1. (What we are not compatible
- * with is if a new version FS crashed and then we try to mount an old
- * version). Otherwise the exofs_fscb is read-only from mkfs time. All
- * the writeable info is set in exofs_sbi_write_stats() above.
- */
-
- exofs_init_comps(&oc, &one_comp, sbi, EXOFS_SUPER_ID);
-
- ret = ore_get_io_state(&sbi->layout, &oc, &ios);
- if (unlikely(ret))
- goto out;
-
- ios->length = offsetof(struct exofs_fscb, s_dev_table_oid);
- memset(fscb, 0, ios->length);
- fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
- fscb->s_numfiles = cpu_to_le64(sbi->s_numfiles);
- fscb->s_magic = cpu_to_le16(sb->s_magic);
- fscb->s_newfs = 0;
- fscb->s_version = EXOFS_FSCB_VER;
-
- ios->offset = 0;
- ios->kern_buff = fscb;
-
- ret = ore_write(ios);
- if (unlikely(ret))
- EXOFS_ERR("%s: ore_write failed.\n", __func__);
-
-out:
- EXOFS_DBGMSG("s_nextid=0x%llx ret=%d\n", _LLU(sbi->s_nextid), ret);
- ore_put_io_state(ios);
- kfree(fscb);
- return ret;
-}
-
-static void _exofs_print_device(const char *msg, const char *dev_path,
- struct osd_dev *od, u64 pid)
-{
- const struct osd_dev_info *odi = osduld_device_info(od);
-
- printk(KERN_NOTICE "exofs: %s %s osd_name-%s pid-0x%llx\n",
- msg, dev_path ?: "", odi->osdname, _LLU(pid));
-}
-
-static void exofs_free_sbi(struct exofs_sb_info *sbi)
-{
- unsigned numdevs = sbi->oc.numdevs;
-
- while (numdevs) {
- unsigned i = --numdevs;
- struct osd_dev *od = ore_comp_dev(&sbi->oc, i);
-
- if (od) {
- ore_comp_set_dev(&sbi->oc, i, NULL);
- osduld_put_device(od);
- }
- }
- kfree(sbi->oc.ods);
- kfree(sbi);
-}
-
-/*
- * This function is called when the vfs is freeing the superblock. We just
- * need to free our own part.
- */
-static void exofs_put_super(struct super_block *sb)
-{
- int num_pend;
- struct exofs_sb_info *sbi = sb->s_fs_info;
-
- /* make sure there are no pending commands */
- for (num_pend = atomic_read(&sbi->s_curr_pending); num_pend > 0;
- num_pend = atomic_read(&sbi->s_curr_pending)) {
- wait_queue_head_t wq;
-
- printk(KERN_NOTICE "%s: !!Pending operations in flight. "
- "This is a BUG. please report to osd-dev@open-osd.org\n",
- __func__);
- init_waitqueue_head(&wq);
- wait_event_timeout(wq,
- (atomic_read(&sbi->s_curr_pending) == 0),
- msecs_to_jiffies(100));
- }
-
- _exofs_print_device("Unmounting", NULL, ore_comp_dev(&sbi->oc, 0),
- sbi->one_comp.obj.partition);
-
- exofs_sysfs_sb_del(sbi);
- bdi_destroy(&sbi->bdi);
- exofs_free_sbi(sbi);
- sb->s_fs_info = NULL;
-}
-
-static int _read_and_match_data_map(struct exofs_sb_info *sbi, unsigned numdevs,
- struct exofs_device_table *dt)
-{
- int ret;
-
- sbi->layout.stripe_unit =
- le64_to_cpu(dt->dt_data_map.cb_stripe_unit);
- sbi->layout.group_width =
- le32_to_cpu(dt->dt_data_map.cb_group_width);
- sbi->layout.group_depth =
- le32_to_cpu(dt->dt_data_map.cb_group_depth);
- sbi->layout.mirrors_p1 =
- le32_to_cpu(dt->dt_data_map.cb_mirror_cnt) + 1;
- sbi->layout.raid_algorithm =
- le32_to_cpu(dt->dt_data_map.cb_raid_algorithm);
-
- ret = ore_verify_layout(numdevs, &sbi->layout);
-
- EXOFS_DBGMSG("exofs: layout: "
- "num_comps=%u stripe_unit=0x%x group_width=%u "
- "group_depth=0x%llx mirrors_p1=%u raid_algorithm=%u\n",
- numdevs,
- sbi->layout.stripe_unit,
- sbi->layout.group_width,
- _LLU(sbi->layout.group_depth),
- sbi->layout.mirrors_p1,
- sbi->layout.raid_algorithm);
- return ret;
-}
-
-static unsigned __ra_pages(struct ore_layout *layout)
-{
- const unsigned _MIN_RA = 32; /* min 128K read-ahead */
- unsigned ra_pages = layout->group_width * layout->stripe_unit /
- PAGE_SIZE;
- unsigned max_io_pages = exofs_max_io_pages(layout, ~0);
-
- ra_pages *= 2; /* two stripes */
- if (ra_pages < _MIN_RA)
- ra_pages = roundup(_MIN_RA, ra_pages / 2);
-
- if (ra_pages > max_io_pages)
- ra_pages = max_io_pages;
-
- return ra_pages;
-}
-
-/* @odi is valid only as long as @fscb_dev is valid */
-static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev,
- struct osd_dev_info *odi)
-{
- odi->systemid_len = le32_to_cpu(dt_dev->systemid_len);
- if (likely(odi->systemid_len))
- memcpy(odi->systemid, dt_dev->systemid, OSD_SYSTEMID_LEN);
-
- odi->osdname_len = le32_to_cpu(dt_dev->osdname_len);
- odi->osdname = dt_dev->osdname;
-
- /* FIXME support long names. Will need a _put function */
- if (dt_dev->long_name_offset)
- return -EINVAL;
-
- /* Make sure osdname is printable!
- * mkexofs should give us space for a null-terminator else the
- * device-table is invalid.
- */
- if (unlikely(odi->osdname_len >= sizeof(dt_dev->osdname)))
- odi->osdname_len = sizeof(dt_dev->osdname) - 1;
- dt_dev->osdname[odi->osdname_len] = 0;
-
- /* If it's all zeros something is bad we read past end-of-obj */
- return !(odi->systemid_len || odi->osdname_len);
-}
-
-static int __alloc_dev_table(struct exofs_sb_info *sbi, unsigned numdevs,
- struct exofs_dev **peds)
-{
- struct __alloc_ore_devs_and_exofs_devs {
- /* Twice bigger table: See exofs_init_comps() and comment at
- * exofs_read_lookup_dev_table()
- */
- struct ore_dev *oreds[numdevs * 2 - 1];
- struct exofs_dev eds[numdevs];
- } *aoded;
- struct exofs_dev *eds;
- unsigned i;
-
- aoded = kzalloc(sizeof(*aoded), GFP_KERNEL);
- if (unlikely(!aoded)) {
- EXOFS_ERR("ERROR: failed allocating Device array[%d]\n",
- numdevs);
- return -ENOMEM;
- }
-
- sbi->oc.ods = aoded->oreds;
- *peds = eds = aoded->eds;
- for (i = 0; i < numdevs; ++i)
- aoded->oreds[i] = &eds[i].ored;
- return 0;
-}
-
-static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi,
- struct osd_dev *fscb_od,
- unsigned table_count)
-{
- struct ore_comp comp;
- struct exofs_device_table *dt;
- struct exofs_dev *eds;
- unsigned table_bytes = table_count * sizeof(dt->dt_dev_table[0]) +
- sizeof(*dt);
- unsigned numdevs, i;
- int ret;
-
- dt = kmalloc(table_bytes, GFP_KERNEL);
- if (unlikely(!dt)) {
- EXOFS_ERR("ERROR: allocating %x bytes for device table\n",
- table_bytes);
- return -ENOMEM;
- }
-
- sbi->oc.numdevs = 0;
-
- comp.obj.partition = sbi->one_comp.obj.partition;
- comp.obj.id = EXOFS_DEVTABLE_ID;
- exofs_make_credential(comp.cred, &comp.obj);
-
- ret = exofs_read_kern(fscb_od, comp.cred, &comp.obj, 0, dt,
- table_bytes);
- if (unlikely(ret)) {
- EXOFS_ERR("ERROR: reading device table\n");
- goto out;
- }
-
- numdevs = le64_to_cpu(dt->dt_num_devices);
- if (unlikely(!numdevs)) {
- ret = -EINVAL;
- goto out;
- }
- WARN_ON(table_count != numdevs);
-
- ret = _read_and_match_data_map(sbi, numdevs, dt);
- if (unlikely(ret))
- goto out;
-
- ret = __alloc_dev_table(sbi, numdevs, &eds);
- if (unlikely(ret))
- goto out;
- /* exofs round-robins the device table view according to inode
- * number. We hold a: twice bigger table hence inodes can point
- * to any device and have a sequential view of the table
- * starting at this device. See exofs_init_comps()
- */
- memcpy(&sbi->oc.ods[numdevs], &sbi->oc.ods[0],
- (numdevs - 1) * sizeof(sbi->oc.ods[0]));
-
- /* create sysfs subdir under which we put the device table
- * And cluster layout. A Superblock is identified by the string:
- * "dev[0].osdname"_"pid"
- */
- exofs_sysfs_sb_add(sbi, &dt->dt_dev_table[0]);
-
- for (i = 0; i < numdevs; i++) {
- struct exofs_fscb fscb;
- struct osd_dev_info odi;
- struct osd_dev *od;
-
- if (exofs_devs_2_odi(&dt->dt_dev_table[i], &odi)) {
- EXOFS_ERR("ERROR: Read all-zeros device entry\n");
- ret = -EINVAL;
- goto out;
- }
-
- printk(KERN_NOTICE "Add device[%d]: osd_name-%s\n",
- i, odi.osdname);
-
- /* the exofs id is currently the table index */
- eds[i].did = i;
-
- /* On all devices the device table is identical. The user can
- * specify any one of the participating devices on the command
- * line. We always keep them in device-table order.
- */
- if (fscb_od && osduld_device_same(fscb_od, &odi)) {
- eds[i].ored.od = fscb_od;
- ++sbi->oc.numdevs;
- fscb_od = NULL;
- exofs_sysfs_odev_add(&eds[i], sbi);
- continue;
- }
-
- od = osduld_info_lookup(&odi);
- if (IS_ERR(od)) {
- ret = PTR_ERR(od);
- EXOFS_ERR("ERROR: device requested is not found "
- "osd_name-%s =>%d\n", odi.osdname, ret);
- goto out;
- }
-
- eds[i].ored.od = od;
- ++sbi->oc.numdevs;
-
- /* Read the fscb of the other devices to make sure the FS
- * partition is there.
- */
- ret = exofs_read_kern(od, comp.cred, &comp.obj, 0, &fscb,
- sizeof(fscb));
- if (unlikely(ret)) {
- EXOFS_ERR("ERROR: Malformed participating device "
- "error reading fscb osd_name-%s\n",
- odi.osdname);
- goto out;
- }
- exofs_sysfs_odev_add(&eds[i], sbi);
-
- /* TODO: verify other information is correct and FS-uuid
- * matches. Benny what did you say about device table
- * generation and old devices?
- */
- }
-
-out:
- kfree(dt);
- if (unlikely(fscb_od && !ret)) {
- EXOFS_ERR("ERROR: Bad device-table container device not present\n");
- osduld_put_device(fscb_od);
- return -EINVAL;
- }
- return ret;
-}
-
-/*
- * Read the superblock from the OSD and fill in the fields
- */
-static int exofs_fill_super(struct super_block *sb, void *data, int silent)
-{
- struct inode *root;
- struct exofs_mountopt *opts = data;
- struct exofs_sb_info *sbi; /*extended info */
- struct osd_dev *od; /* Master device */
- struct exofs_fscb fscb; /*on-disk superblock info */
- struct ore_comp comp;
- unsigned table_count;
- int ret;
-
- sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
- if (!sbi)
- return -ENOMEM;
-
- /* use mount options to fill superblock */
- if (opts->is_osdname) {
- struct osd_dev_info odi = {.systemid_len = 0};
-
- odi.osdname_len = strlen(opts->dev_name);
- odi.osdname = (u8 *)opts->dev_name;
- od = osduld_info_lookup(&odi);
- kfree(opts->dev_name);
- opts->dev_name = NULL;
- } else {
- od = osduld_path_lookup(opts->dev_name);
- }
- if (IS_ERR(od)) {
- ret = -EINVAL;
- goto free_sbi;
- }
-
- /* Default layout in case we do not have a device-table */
- sbi->layout.stripe_unit = PAGE_SIZE;
- sbi->layout.mirrors_p1 = 1;
- sbi->layout.group_width = 1;
- sbi->layout.group_depth = -1;
- sbi->layout.group_count = 1;
- sbi->s_timeout = opts->timeout;
-
- sbi->one_comp.obj.partition = opts->pid;
- sbi->one_comp.obj.id = 0;
- exofs_make_credential(sbi->one_comp.cred, &sbi->one_comp.obj);
- sbi->oc.single_comp = EC_SINGLE_COMP;
- sbi->oc.comps = &sbi->one_comp;
-
- /* fill in some other data by hand */
- memset(sb->s_id, 0, sizeof(sb->s_id));
- strcpy(sb->s_id, "exofs");
- sb->s_blocksize = EXOFS_BLKSIZE;
- sb->s_blocksize_bits = EXOFS_BLKSHIFT;
- sb->s_maxbytes = MAX_LFS_FILESIZE;
- sb->s_max_links = EXOFS_LINK_MAX;
- atomic_set(&sbi->s_curr_pending, 0);
- sb->s_bdev = NULL;
- sb->s_dev = 0;
-
- comp.obj.partition = sbi->one_comp.obj.partition;
- comp.obj.id = EXOFS_SUPER_ID;
- exofs_make_credential(comp.cred, &comp.obj);
-
- ret = exofs_read_kern(od, comp.cred, &comp.obj, 0, &fscb, sizeof(fscb));
- if (unlikely(ret))
- goto free_sbi;
-
- sb->s_magic = le16_to_cpu(fscb.s_magic);
- /* NOTE: we read below to be backward compatible with old versions */
- sbi->s_nextid = le64_to_cpu(fscb.s_nextid);
- sbi->s_numfiles = le32_to_cpu(fscb.s_numfiles);
-
- /* make sure what we read from the object store is correct */
- if (sb->s_magic != EXOFS_SUPER_MAGIC) {
- if (!silent)
- EXOFS_ERR("ERROR: Bad magic value\n");
- ret = -EINVAL;
- goto free_sbi;
- }
- if (le32_to_cpu(fscb.s_version) > EXOFS_FSCB_VER) {
- EXOFS_ERR("ERROR: Bad FSCB version expected-%d got-%d\n",
- EXOFS_FSCB_VER, le32_to_cpu(fscb.s_version));
- ret = -EINVAL;
- goto free_sbi;
- }
-
- /* start generation numbers from a random point */
- get_random_bytes(&sbi->s_next_generation, sizeof(u32));
- spin_lock_init(&sbi->s_next_gen_lock);
-
- table_count = le64_to_cpu(fscb.s_dev_table_count);
- if (table_count) {
- ret = exofs_read_lookup_dev_table(sbi, od, table_count);
- if (unlikely(ret))
- goto free_sbi;
- } else {
- struct exofs_dev *eds;
-
- ret = __alloc_dev_table(sbi, 1, &eds);
- if (unlikely(ret))
- goto free_sbi;
-
- ore_comp_set_dev(&sbi->oc, 0, od);
- sbi->oc.numdevs = 1;
- }
-
- __sbi_read_stats(sbi);
-
- /* set up operation vectors */
- sbi->bdi.ra_pages = __ra_pages(&sbi->layout);
- sb->s_bdi = &sbi->bdi;
- sb->s_fs_info = sbi;
- sb->s_op = &exofs_sops;
- sb->s_export_op = &exofs_export_ops;
- root = exofs_iget(sb, EXOFS_ROOT_ID - EXOFS_OBJ_OFF);
- if (IS_ERR(root)) {
- EXOFS_ERR("ERROR: exofs_iget failed\n");
- ret = PTR_ERR(root);
- goto free_sbi;
- }
- sb->s_root = d_make_root(root);
- if (!sb->s_root) {
- EXOFS_ERR("ERROR: get root inode failed\n");
- ret = -ENOMEM;
- goto free_sbi;
- }
-
- if (!S_ISDIR(root->i_mode)) {
- dput(sb->s_root);
- sb->s_root = NULL;
- EXOFS_ERR("ERROR: corrupt root inode (mode = %hd)\n",
- root->i_mode);
- ret = -EINVAL;
- goto free_sbi;
- }
-
- ret = bdi_setup_and_register(&sbi->bdi, "exofs");
- if (ret) {
- EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
- dput(sb->s_root);
- sb->s_root = NULL;
- goto free_sbi;
- }
-
- exofs_sysfs_dbg_print();
- _exofs_print_device("Mounting", opts->dev_name,
- ore_comp_dev(&sbi->oc, 0),
- sbi->one_comp.obj.partition);
- return 0;
-
-free_sbi:
- EXOFS_ERR("Unable to mount exofs on %s pid=0x%llx err=%d\n",
- opts->dev_name, sbi->one_comp.obj.partition, ret);
- exofs_free_sbi(sbi);
- return ret;
-}
-
-/*
- * Set up the superblock (calls exofs_fill_super eventually)
- */
-static struct dentry *exofs_mount(struct file_system_type *type,
- int flags, const char *dev_name,
- void *data)
-{
- struct exofs_mountopt opts;
- int ret;
-
- ret = parse_options(data, &opts);
- if (ret)
- return ERR_PTR(ret);
-
- if (!opts.dev_name)
- opts.dev_name = dev_name;
- return mount_nodev(type, flags, &opts, exofs_fill_super);
-}
-
-/*
- * Return information about the file system state in the buffer. This is used
- * by the 'df' command, for example.
- */
-static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf)
-{
- struct super_block *sb = dentry->d_sb;
- struct exofs_sb_info *sbi = sb->s_fs_info;
- struct ore_io_state *ios;
- struct osd_attr attrs[] = {
- ATTR_DEF(OSD_APAGE_PARTITION_QUOTAS,
- OSD_ATTR_PQ_CAPACITY_QUOTA, sizeof(__be64)),
- ATTR_DEF(OSD_APAGE_PARTITION_INFORMATION,
- OSD_ATTR_PI_USED_CAPACITY, sizeof(__be64)),
- };
- uint64_t capacity = ULLONG_MAX;
- uint64_t used = ULLONG_MAX;
- int ret;
-
- ret = ore_get_io_state(&sbi->layout, &sbi->oc, &ios);
- if (ret) {
- EXOFS_DBGMSG("ore_get_io_state failed.\n");
- return ret;
- }
-
- ios->in_attr = attrs;
- ios->in_attr_len = ARRAY_SIZE(attrs);
-
- ret = ore_read(ios);
- if (unlikely(ret))
- goto out;
-
- ret = extract_attr_from_ios(ios, &attrs[0]);
- if (likely(!ret)) {
- capacity = get_unaligned_be64(attrs[0].val_ptr);
- if (unlikely(!capacity))
- capacity = ULLONG_MAX;
- } else
- EXOFS_DBGMSG("exofs_statfs: get capacity failed.\n");
-
- ret = extract_attr_from_ios(ios, &attrs[1]);
- if (likely(!ret))
- used = get_unaligned_be64(attrs[1].val_ptr);
- else
- EXOFS_DBGMSG("exofs_statfs: get used-space failed.\n");
-
- /* fill in the stats buffer */
- buf->f_type = EXOFS_SUPER_MAGIC;
- buf->f_bsize = EXOFS_BLKSIZE;
- buf->f_blocks = capacity >> 9;
- buf->f_bfree = (capacity - used) >> 9;
- buf->f_bavail = buf->f_bfree;
- buf->f_files = sbi->s_numfiles;
- buf->f_ffree = EXOFS_MAX_ID - sbi->s_numfiles;
- buf->f_namelen = EXOFS_NAME_LEN;
-
-out:
- ore_put_io_state(ios);
- return ret;
-}
-
-static const struct super_operations exofs_sops = {
- .alloc_inode = exofs_alloc_inode,
- .destroy_inode = exofs_destroy_inode,
- .write_inode = exofs_write_inode,
- .evict_inode = exofs_evict_inode,
- .put_super = exofs_put_super,
- .sync_fs = exofs_sync_fs,
- .statfs = exofs_statfs,
-};
-
-/******************************************************************************
- * EXPORT OPERATIONS
- *****************************************************************************/
-
-static struct dentry *exofs_get_parent(struct dentry *child)
-{
- unsigned long ino = exofs_parent_ino(child);
-
- if (!ino)
- return ERR_PTR(-ESTALE);
-
- return d_obtain_alias(exofs_iget(child->d_sb, ino));
-}
-
-static struct inode *exofs_nfs_get_inode(struct super_block *sb,
- u64 ino, u32 generation)
-{
- struct inode *inode;
-
- inode = exofs_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);
- }
- return inode;
-}
-
-static struct dentry *exofs_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,
- exofs_nfs_get_inode);
-}
-
-static struct dentry *exofs_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,
- exofs_nfs_get_inode);
-}
-
-static const struct export_operations exofs_export_ops = {
- .fh_to_dentry = exofs_fh_to_dentry,
- .fh_to_parent = exofs_fh_to_parent,
- .get_parent = exofs_get_parent,
-};
-
-/******************************************************************************
- * INSMOD/RMMOD
- *****************************************************************************/
-
-/*
- * struct that describes this file system
- */
-static struct file_system_type exofs_type = {
- .owner = THIS_MODULE,
- .name = "exofs",
- .mount = exofs_mount,
- .kill_sb = generic_shutdown_super,
-};
-MODULE_ALIAS_FS("exofs");
-
-static int __init init_exofs(void)
-{
- int err;
-
- err = init_inodecache();
- if (err)
- goto out;
-
- err = register_filesystem(&exofs_type);
- if (err)
- goto out_d;
-
- /* We don't fail if sysfs creation failed */
- exofs_sysfs_init();
-
- return 0;
-out_d:
- destroy_inodecache();
-out:
- return err;
-}
-
-static void __exit exit_exofs(void)
-{
- exofs_sysfs_uninit();
- unregister_filesystem(&exofs_type);
- destroy_inodecache();
-}
-
-MODULE_AUTHOR("Avishay Traeger <avishay@gmail.com>");
-MODULE_DESCRIPTION("exofs");
-MODULE_LICENSE("GPL");
-
-module_init(init_exofs)
-module_exit(exit_exofs)
diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c
deleted file mode 100644
index 1f7d5e46cdda..000000000000
--- a/fs/exofs/sys.c
+++ /dev/null
@@ -1,205 +0,0 @@
-/*
- * Copyright (C) 2012
- * Sachin Bhamare <sbhamare@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.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 2 as published by
- * the Free Software Foundation.
- *
- * 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 <licensing@fsf.org>
- */
-
-#include <linux/kobject.h>
-#include <linux/device.h>
-
-#include "exofs.h"
-
-struct odev_attr {
- struct attribute attr;
- ssize_t (*show)(struct exofs_dev *, char *);
- ssize_t (*store)(struct exofs_dev *, const char *, size_t);
-};
-
-static ssize_t odev_attr_show(struct kobject *kobj, struct attribute *attr,
- char *buf)
-{
- struct exofs_dev *edp = container_of(kobj, struct exofs_dev, ed_kobj);
- struct odev_attr *a = container_of(attr, struct odev_attr, attr);
-
- return a->show ? a->show(edp, buf) : 0;
-}
-
-static ssize_t odev_attr_store(struct kobject *kobj, struct attribute *attr,
- const char *buf, size_t len)
-{
- struct exofs_dev *edp = container_of(kobj, struct exofs_dev, ed_kobj);
- struct odev_attr *a = container_of(attr, struct odev_attr, attr);
-
- return a->store ? a->store(edp, buf, len) : len;
-}
-
-static const struct sysfs_ops odev_attr_ops = {
- .show = odev_attr_show,
- .store = odev_attr_store,
-};
-
-
-static struct kset *exofs_kset;
-
-static ssize_t osdname_show(struct exofs_dev *edp, char *buf)
-{
- struct osd_dev *odev = edp->ored.od;
- const struct osd_dev_info *odi = osduld_device_info(odev);
-
- return snprintf(buf, odi->osdname_len + 1, "%s", odi->osdname);
-}
-
-static ssize_t systemid_show(struct exofs_dev *edp, char *buf)
-{
- struct osd_dev *odev = edp->ored.od;
- const struct osd_dev_info *odi = osduld_device_info(odev);
-
- memcpy(buf, odi->systemid, odi->systemid_len);
- return odi->systemid_len;
-}
-
-static ssize_t uri_show(struct exofs_dev *edp, char *buf)
-{
- return snprintf(buf, edp->urilen, "%s", edp->uri);
-}
-
-static ssize_t uri_store(struct exofs_dev *edp, const char *buf, size_t len)
-{
- uint8_t *new_uri;
-
- edp->urilen = strlen(buf) + 1;
- new_uri = krealloc(edp->uri, edp->urilen, GFP_KERNEL);
- if (new_uri == NULL)
- return -ENOMEM;
- edp->uri = new_uri;
- strncpy(edp->uri, buf, edp->urilen);
- return edp->urilen;
-}
-
-#define OSD_ATTR(name, mode, show, store) \
- static struct odev_attr odev_attr_##name = \
- __ATTR(name, mode, show, store)
-
-OSD_ATTR(osdname, S_IRUGO, osdname_show, NULL);
-OSD_ATTR(systemid, S_IRUGO, systemid_show, NULL);
-OSD_ATTR(uri, S_IRWXU, uri_show, uri_store);
-
-static struct attribute *odev_attrs[] = {
- &odev_attr_osdname.attr,
- &odev_attr_systemid.attr,
- &odev_attr_uri.attr,
- NULL,
-};
-
-static struct kobj_type odev_ktype = {
- .default_attrs = odev_attrs,
- .sysfs_ops = &odev_attr_ops,
-};
-
-static struct kobj_type uuid_ktype = {
-};
-
-void exofs_sysfs_dbg_print(void)
-{
-#ifdef CONFIG_EXOFS_DEBUG
- struct kobject *k_name, *k_tmp;
-
- list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) {
- printk(KERN_INFO "%s: name %s ref %d\n",
- __func__, kobject_name(k_name),
- (int)kref_read(&k_name->kref));
- }
-#endif
-}
-/*
- * This function removes all kobjects under exofs_kset
- * At the end of it, exofs_kset kobject will have a refcount
- * of 1 which gets decremented only on exofs module unload
- */
-void exofs_sysfs_sb_del(struct exofs_sb_info *sbi)
-{
- struct kobject *k_name, *k_tmp;
- struct kobject *s_kobj = &sbi->s_kobj;
-
- list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) {
- /* Remove all that are children of this SBI */
- if (k_name->parent == s_kobj)
- kobject_put(k_name);
- }
- kobject_put(s_kobj);
-}
-
-/*
- * This function creates sysfs entries to hold the current exofs cluster
- * instance (uniquely identified by osdname,pid tuple).
- * This function gets called once per exofs mount instance.
- */
-int exofs_sysfs_sb_add(struct exofs_sb_info *sbi,
- struct exofs_dt_device_info *dt_dev)
-{
- struct kobject *s_kobj;
- int retval = 0;
- uint64_t pid = sbi->one_comp.obj.partition;
-
- /* allocate new uuid dirent */
- s_kobj = &sbi->s_kobj;
- s_kobj->kset = exofs_kset;
- retval = kobject_init_and_add(s_kobj, &uuid_ktype,
- &exofs_kset->kobj, "%s_%llx", dt_dev->osdname, pid);
- if (retval) {
- EXOFS_ERR("ERROR: Failed to create sysfs entry for "
- "uuid-%s_%llx => %d\n", dt_dev->osdname, pid, retval);
- return -ENOMEM;
- }
- return 0;
-}
-
-int exofs_sysfs_odev_add(struct exofs_dev *edev, struct exofs_sb_info *sbi)
-{
- struct kobject *d_kobj;
- int retval = 0;
-
- /* create osd device group which contains following attributes
- * osdname, systemid & uri
- */
- d_kobj = &edev->ed_kobj;
- d_kobj->kset = exofs_kset;
- retval = kobject_init_and_add(d_kobj, &odev_ktype,
- &sbi->s_kobj, "dev%u", edev->did);
- if (retval) {
- EXOFS_ERR("ERROR: Failed to create sysfs entry for "
- "device dev%u\n", edev->did);
- return retval;
- }
- return 0;
-}
-
-int exofs_sysfs_init(void)
-{
- exofs_kset = kset_create_and_add("exofs", NULL, fs_kobj);
- if (!exofs_kset) {
- EXOFS_ERR("ERROR: kset_create_and_add exofs failed\n");
- return -ENOMEM;
- }
- return 0;
-}
-
-void exofs_sysfs_uninit(void)
-{
- kset_unregister(exofs_kset);
-}
--
2.11.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 3/4] nfs: remove the objlayout driver
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
2017-04-12 16:01 ` [PATCH 1/4] block: remove the osdblk driver Christoph Hellwig
2017-04-12 16:01 ` [PATCH 2/4] fs: remove exofs Christoph Hellwig
@ 2017-04-12 16:01 ` Christoph Hellwig
2017-04-20 20:18 ` Trond Myklebust
2017-04-21 7:27 ` Valentin Rothberg
2017-04-12 16:01 ` [PATCH 4/4] scsi: remove the SCSI OSD library Christoph Hellwig
` (3 subsequent siblings)
6 siblings, 2 replies; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-12 16:01 UTC (permalink / raw)
To: ooo, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
The objlayout code has been in the tree, but it's been unmaintained and
no server product for it actually ever shipped.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/admin-guide/kernel-parameters.txt | 6 -
Documentation/filesystems/nfs/pnfs.txt | 37 --
fs/nfs/Kconfig | 5 -
fs/nfs/Makefile | 1 -
fs/nfs/objlayout/Kbuild | 5 -
fs/nfs/objlayout/objio_osd.c | 675 ----------------------
fs/nfs/objlayout/objlayout.c | 706 ------------------------
fs/nfs/objlayout/objlayout.h | 183 ------
fs/nfs/objlayout/pnfs_osd_xdr_cli.c | 415 --------------
9 files changed, 2033 deletions(-)
delete mode 100644 fs/nfs/objlayout/Kbuild
delete mode 100644 fs/nfs/objlayout/objio_osd.c
delete mode 100644 fs/nfs/objlayout/objlayout.c
delete mode 100644 fs/nfs/objlayout/objlayout.h
delete mode 100644 fs/nfs/objlayout/pnfs_osd_xdr_cli.c
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index facc20a3f962..17156d66b124 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2419,12 +2419,6 @@
and gids from such clients. This is intended to ease
migration from NFSv2/v3.
- objlayoutdriver.osd_login_prog=
- [NFS] [OBJLAYOUT] sets the pathname to the program which
- is used to automatically discover and login into new
- osd-targets. Please see:
- Documentation/filesystems/pnfs.txt for more explanations
-
nmi_debug= [KNL,AVR32,SH] Specify one or more actions to take
when a NMI is triggered.
Format: [state][,regs][,debounce][,die]
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
index 8de578a98222..80dc0bdc302a 100644
--- a/Documentation/filesystems/nfs/pnfs.txt
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -64,46 +64,9 @@ table which are called by the nfs-client pnfs-core to implement the
different layout types.
Files-layout-driver code is in: fs/nfs/filelayout/.. directory
-Objects-layout-driver code is in: fs/nfs/objlayout/.. directory
Blocks-layout-driver code is in: fs/nfs/blocklayout/.. directory
Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
-objects-layout setup
---------------------
-
-As part of the full STD implementation the objlayoutdriver.ko needs, at times,
-to automatically login to yet undiscovered iscsi/osd devices. For this the
-driver makes up-calles to a user-mode script called *osd_login*
-
-The path_name of the script to use is by default:
- /sbin/osd_login.
-This name can be overridden by the Kernel module parameter:
- objlayoutdriver.osd_login_prog
-
-If Kernel does not find the osd_login_prog path it will zero it out
-and will not attempt farther logins. An admin can then write new value
-to the objlayoutdriver.osd_login_prog Kernel parameter to re-enable it.
-
-The /sbin/osd_login is part of the nfs-utils package, and should usually
-be installed on distributions that support this Kernel version.
-
-The API to the login script is as follows:
- Usage: $0 -u <URI> -o <OSDNAME> -s <SYSTEMID>
- Options:
- -u target uri e.g. iscsi://<ip>:<port>
- (always exists)
- (More protocols can be defined in the future.
- The client does not interpret this string it is
- passed unchanged as received from the Server)
- -o osdname of the requested target OSD
- (Might be empty)
- (A string which denotes the OSD name, there is a
- limit of 64 chars on this string)
- -s systemid of the requested target OSD
- (Might be empty)
- (This string, if not empty is always an hex
- representation of the 20 bytes osd_system_id)
-
blocks-layout setup
-------------------
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f31fd0dd92c6..69d02cf8cf37 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -123,11 +123,6 @@ config PNFS_BLOCK
depends on NFS_V4_1 && BLK_DEV_DM
default NFS_V4
-config PNFS_OBJLAYOUT
- tristate
- depends on NFS_V4_1 && SCSI_OSD_ULD
- default NFS_V4
-
config PNFS_FLEXFILE_LAYOUT
tristate
depends on NFS_V4_1 && NFS_V3
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 6abdda209642..98f4e5728a67 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -31,6 +31,5 @@ nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o pnfs_nfs.o
nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o
obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/
diff --git a/fs/nfs/objlayout/Kbuild b/fs/nfs/objlayout/Kbuild
deleted file mode 100644
index ed30ea072bb8..000000000000
--- a/fs/nfs/objlayout/Kbuild
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the pNFS Objects Layout Driver kernel module
-#
-objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
deleted file mode 100644
index 049c1b1f2932..000000000000
--- a/fs/nfs/objlayout/objio_osd.c
+++ /dev/null
@@ -1,675 +0,0 @@
-/*
- * pNFS Objects layout implementation over open-osd initiator library
- *
- * Copyright (C) 2009 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.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
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/module.h>
-#include <scsi/osd_ore.h>
-
-#include "objlayout.h"
-#include "../internal.h"
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-struct objio_dev_ent {
- struct nfs4_deviceid_node id_node;
- struct ore_dev od;
-};
-
-static void
-objio_free_deviceid_node(struct nfs4_deviceid_node *d)
-{
- struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
-
- dprintk("%s: free od=%p\n", __func__, de->od.od);
- osduld_put_device(de->od.od);
- kfree_rcu(d, rcu);
-}
-
-struct objio_segment {
- struct pnfs_layout_segment lseg;
-
- struct ore_layout layout;
- struct ore_components oc;
-};
-
-static inline struct objio_segment *
-OBJIO_LSEG(struct pnfs_layout_segment *lseg)
-{
- return container_of(lseg, struct objio_segment, lseg);
-}
-
-struct objio_state {
- /* Generic layer */
- struct objlayout_io_res oir;
-
- bool sync;
- /*FIXME: Support for extra_bytes at ore_get_rw_state() */
- struct ore_io_state *ios;
-};
-
-/* Send and wait for a get_device_info of devices in the layout,
- then look them up with the osd_initiator library */
-struct nfs4_deviceid_node *
-objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
- gfp_t gfp_flags)
-{
- struct pnfs_osd_deviceaddr *deviceaddr;
- struct objio_dev_ent *ode = NULL;
- struct osd_dev *od;
- struct osd_dev_info odi;
- bool retry_flag = true;
- __be32 *p;
- int err;
-
- deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags);
- if (!deviceaddr)
- return NULL;
-
- p = page_address(pdev->pages[0]);
- pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p);
-
- odi.systemid_len = deviceaddr->oda_systemid.len;
- if (odi.systemid_len > sizeof(odi.systemid)) {
- dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n",
- __func__, sizeof(odi.systemid));
- err = -EINVAL;
- goto out;
- } else if (odi.systemid_len)
- memcpy(odi.systemid, deviceaddr->oda_systemid.data,
- odi.systemid_len);
- odi.osdname_len = deviceaddr->oda_osdname.len;
- odi.osdname = (u8 *)deviceaddr->oda_osdname.data;
-
- if (!odi.osdname_len && !odi.systemid_len) {
- dprintk("%s: !odi.osdname_len && !odi.systemid_len\n",
- __func__);
- err = -ENODEV;
- goto out;
- }
-
-retry_lookup:
- od = osduld_info_lookup(&odi);
- if (IS_ERR(od)) {
- err = PTR_ERR(od);
- dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
- if (err == -ENODEV && retry_flag) {
- err = objlayout_autologin(deviceaddr);
- if (likely(!err)) {
- retry_flag = false;
- goto retry_lookup;
- }
- }
- goto out;
- }
-
- dprintk("Adding new dev_id(%llx:%llx)\n",
- _DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id));
-
- ode = kzalloc(sizeof(*ode), gfp_flags);
- if (!ode) {
- dprintk("%s: -ENOMEM od=%p\n", __func__, od);
- goto out;
- }
-
- nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id);
- kfree(deviceaddr);
-
- ode->od.od = od;
- return &ode->id_node;
-
-out:
- kfree(deviceaddr);
- return NULL;
-}
-
-static void copy_single_comp(struct ore_components *oc, unsigned c,
- struct pnfs_osd_object_cred *src_comp)
-{
- struct ore_comp *ocomp = &oc->comps[c];
-
- WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */
- WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred));
-
- ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id;
- ocomp->obj.id = src_comp->oc_object_id.oid_object_id;
-
- memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
-}
-
-static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
- struct objio_segment **pseg)
-{
-/* This is the in memory structure of the objio_segment
- *
- * struct __alloc_objio_segment {
- * struct objio_segment olseg;
- * struct ore_dev *ods[numdevs];
- * struct ore_comp comps[numdevs];
- * } *aolseg;
- * NOTE: The code as above compiles and runs perfectly. It is elegant,
- * type safe and compact. At some Past time Linus has decided he does not
- * like variable length arrays, For the sake of this principal we uglify
- * the code as below.
- */
- struct objio_segment *lseg;
- size_t lseg_size = sizeof(*lseg) +
- numdevs * sizeof(lseg->oc.ods[0]) +
- numdevs * sizeof(*lseg->oc.comps);
-
- lseg = kzalloc(lseg_size, gfp_flags);
- if (unlikely(!lseg)) {
- dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__,
- numdevs, lseg_size);
- return -ENOMEM;
- }
-
- lseg->oc.numdevs = numdevs;
- lseg->oc.single_comp = EC_MULTPLE_COMPS;
- lseg->oc.ods = (void *)(lseg + 1);
- lseg->oc.comps = (void *)(lseg->oc.ods + numdevs);
-
- *pseg = lseg;
- return 0;
-}
-
-int objio_alloc_lseg(struct pnfs_layout_segment **outp,
- struct pnfs_layout_hdr *pnfslay,
- struct pnfs_layout_range *range,
- struct xdr_stream *xdr,
- gfp_t gfp_flags)
-{
- struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode);
- struct objio_segment *objio_seg;
- struct pnfs_osd_xdr_decode_layout_iter iter;
- struct pnfs_osd_layout layout;
- struct pnfs_osd_object_cred src_comp;
- unsigned cur_comp;
- int err;
-
- err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
- if (unlikely(err))
- return err;
-
- err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg);
- if (unlikely(err))
- return err;
-
- objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit;
- objio_seg->layout.group_width = layout.olo_map.odm_group_width;
- objio_seg->layout.group_depth = layout.olo_map.odm_group_depth;
- objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
- objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm;
-
- err = ore_verify_layout(layout.olo_map.odm_num_comps,
- &objio_seg->layout);
- if (unlikely(err))
- goto err;
-
- objio_seg->oc.first_dev = layout.olo_comps_index;
- cur_comp = 0;
- while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
- struct nfs4_deviceid_node *d;
- struct objio_dev_ent *ode;
-
- copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
-
- d = nfs4_find_get_deviceid(server,
- &src_comp.oc_object_id.oid_device_id,
- pnfslay->plh_lc_cred, gfp_flags);
- if (!d) {
- err = -ENXIO;
- goto err;
- }
-
- ode = container_of(d, struct objio_dev_ent, id_node);
- objio_seg->oc.ods[cur_comp++] = &ode->od;
- }
- /* pnfs_osd_xdr_decode_layout_comp returns false on error */
- if (unlikely(err))
- goto err;
-
- *outp = &objio_seg->lseg;
- return 0;
-
-err:
- kfree(objio_seg);
- dprintk("%s: Error: return %d\n", __func__, err);
- *outp = NULL;
- return err;
-}
-
-void objio_free_lseg(struct pnfs_layout_segment *lseg)
-{
- int i;
- struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
-
- for (i = 0; i < objio_seg->oc.numdevs; i++) {
- struct ore_dev *od = objio_seg->oc.ods[i];
- struct objio_dev_ent *ode;
-
- if (!od)
- break;
- ode = container_of(od, typeof(*ode), od);
- nfs4_put_deviceid_node(&ode->id_node);
- }
- kfree(objio_seg);
-}
-
-static int
-objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading,
- struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase,
- loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags,
- struct objio_state **outp)
-{
- struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
- struct ore_io_state *ios;
- int ret;
- struct __alloc_objio_state {
- struct objio_state objios;
- struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs];
- } *aos;
-
- aos = kzalloc(sizeof(*aos), gfp_flags);
- if (unlikely(!aos))
- return -ENOMEM;
-
- objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs,
- aos->ioerrs, rpcdata, pnfs_layout_type);
-
- ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading,
- offset, count, &ios);
- if (unlikely(ret)) {
- kfree(aos);
- return ret;
- }
-
- ios->pages = pages;
- ios->pgbase = pgbase;
- ios->private = aos;
- BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT);
-
- aos->objios.sync = 0;
- aos->objios.ios = ios;
- *outp = &aos->objios;
- return 0;
-}
-
-void objio_free_result(struct objlayout_io_res *oir)
-{
- struct objio_state *objios = container_of(oir, struct objio_state, oir);
-
- ore_put_io_state(objios->ios);
- kfree(objios);
-}
-
-static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
-{
- switch (oep) {
- case OSD_ERR_PRI_NO_ERROR:
- return (enum pnfs_osd_errno)0;
-
- case OSD_ERR_PRI_CLEAR_PAGES:
- BUG_ON(1);
- return 0;
-
- case OSD_ERR_PRI_RESOURCE:
- return PNFS_OSD_ERR_RESOURCE;
- case OSD_ERR_PRI_BAD_CRED:
- return PNFS_OSD_ERR_BAD_CRED;
- case OSD_ERR_PRI_NO_ACCESS:
- return PNFS_OSD_ERR_NO_ACCESS;
- case OSD_ERR_PRI_UNREACHABLE:
- return PNFS_OSD_ERR_UNREACHABLE;
- case OSD_ERR_PRI_NOT_FOUND:
- return PNFS_OSD_ERR_NOT_FOUND;
- case OSD_ERR_PRI_NO_SPACE:
- return PNFS_OSD_ERR_NO_SPACE;
- default:
- WARN_ON(1);
- /* fallthrough */
- case OSD_ERR_PRI_EIO:
- return PNFS_OSD_ERR_EIO;
- }
-}
-
-static void __on_dev_error(struct ore_io_state *ios,
- struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep,
- u64 dev_offset, u64 dev_len)
-{
- struct objio_state *objios = ios->private;
- struct pnfs_osd_objid pooid;
- struct objio_dev_ent *ode = container_of(od, typeof(*ode), od);
- /* FIXME: what to do with more-then-one-group layouts. We need to
- * translate from ore_io_state index to oc->comps index
- */
- unsigned comp = dev_index;
-
- pooid.oid_device_id = ode->id_node.deviceid;
- pooid.oid_partition_id = ios->oc->comps[comp].obj.partition;
- pooid.oid_object_id = ios->oc->comps[comp].obj.id;
-
- objlayout_io_set_result(&objios->oir, comp,
- &pooid, osd_pri_2_pnfs_err(oep),
- dev_offset, dev_len, !ios->reading);
-}
-
-/*
- * read
- */
-static void _read_done(struct ore_io_state *ios, void *private)
-{
- struct objio_state *objios = private;
- ssize_t status;
- int ret = ore_check_io(ios, &__on_dev_error);
-
- /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
-
- if (likely(!ret))
- status = ios->length;
- else
- status = ret;
-
- objlayout_read_done(&objios->oir, status, objios->sync);
-}
-
-int objio_read_pagelist(struct nfs_pgio_header *hdr)
-{
- struct objio_state *objios;
- int ret;
-
- ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
- hdr->lseg, hdr->args.pages, hdr->args.pgbase,
- hdr->args.offset, hdr->args.count, hdr,
- GFP_KERNEL, &objios);
- if (unlikely(ret))
- return ret;
-
- objios->ios->done = _read_done;
- dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
- hdr->args.offset, hdr->args.count);
- ret = ore_read(objios->ios);
- if (unlikely(ret))
- objio_free_result(&objios->oir);
- return ret;
-}
-
-/*
- * write
- */
-static void _write_done(struct ore_io_state *ios, void *private)
-{
- struct objio_state *objios = private;
- ssize_t status;
- int ret = ore_check_io(ios, &__on_dev_error);
-
- /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
-
- if (likely(!ret)) {
- /* FIXME: should be based on the OSD's persistence model
- * See OSD2r05 Section 4.13 Data persistence model */
- objios->oir.committed = NFS_FILE_SYNC;
- status = ios->length;
- } else {
- status = ret;
- }
-
- objlayout_write_done(&objios->oir, status, objios->sync);
-}
-
-static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
-{
- struct objio_state *objios = priv;
- struct nfs_pgio_header *hdr = objios->oir.rpcdata;
- struct address_space *mapping = hdr->inode->i_mapping;
- pgoff_t index = offset / PAGE_SIZE;
- struct page *page;
- loff_t i_size = i_size_read(hdr->inode);
-
- if (offset >= i_size) {
- *uptodate = true;
- dprintk("%s: g_zero_page index=0x%lx\n", __func__, index);
- return ZERO_PAGE(0);
- }
-
- page = find_get_page(mapping, index);
- if (!page) {
- page = find_or_create_page(mapping, index, GFP_NOFS);
- if (unlikely(!page)) {
- dprintk("%s: grab_cache_page Failed index=0x%lx\n",
- __func__, index);
- return NULL;
- }
- unlock_page(page);
- }
- *uptodate = PageUptodate(page);
- dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
- return page;
-}
-
-static void __r4w_put_page(void *priv, struct page *page)
-{
- dprintk("%s: index=0x%lx\n", __func__,
- (page == ZERO_PAGE(0)) ? -1UL : page->index);
- if (ZERO_PAGE(0) != page)
- put_page(page);
- return;
-}
-
-static const struct _ore_r4w_op _r4w_op = {
- .get_page = &__r4w_get_page,
- .put_page = &__r4w_put_page,
-};
-
-int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
-{
- struct objio_state *objios;
- int ret;
-
- ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
- hdr->lseg, hdr->args.pages, hdr->args.pgbase,
- hdr->args.offset, hdr->args.count, hdr, GFP_NOFS,
- &objios);
- if (unlikely(ret))
- return ret;
-
- objios->sync = 0 != (how & FLUSH_SYNC);
- objios->ios->r4w = &_r4w_op;
-
- if (!objios->sync)
- objios->ios->done = _write_done;
-
- dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
- hdr->args.offset, hdr->args.count);
- ret = ore_write(objios->ios);
- if (unlikely(ret)) {
- objio_free_result(&objios->oir);
- return ret;
- }
-
- if (objios->sync)
- _write_done(objios->ios, objios);
-
- return 0;
-}
-
-/*
- * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
- * of bytes (maximum @req->wb_bytes) that can be coalesced.
- */
-static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
- struct nfs_page *prev, struct nfs_page *req)
-{
- struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
- unsigned int size;
-
- size = pnfs_generic_pg_test(pgio, prev, req);
-
- if (!size || mirror->pg_count + req->wb_bytes >
- (unsigned long)pgio->pg_layout_private)
- return 0;
-
- return min(size, req->wb_bytes);
-}
-
-static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
- pnfs_generic_pg_init_read(pgio, req);
- if (unlikely(pgio->pg_lseg == NULL))
- return; /* Not pNFS */
-
- pgio->pg_layout_private = (void *)
- OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
-}
-
-static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
- unsigned long *stripe_end)
-{
- u32 stripe_off;
- unsigned stripe_size;
-
- if (layout->raid_algorithm == PNFS_OSD_RAID_0)
- return true;
-
- stripe_size = layout->stripe_unit *
- (layout->group_width - layout->parity);
-
- div_u64_rem(offset, stripe_size, &stripe_off);
- if (!stripe_off)
- return true;
-
- *stripe_end = stripe_size - stripe_off;
- return false;
-}
-
-static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
- unsigned long stripe_end = 0;
- u64 wb_size;
-
- if (pgio->pg_dreq == NULL)
- wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
- else
- wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
- pnfs_generic_pg_init_write(pgio, req, wb_size);
- if (unlikely(pgio->pg_lseg == NULL))
- return; /* Not pNFS */
-
- if (req->wb_offset ||
- !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE,
- &OBJIO_LSEG(pgio->pg_lseg)->layout,
- &stripe_end)) {
- pgio->pg_layout_private = (void *)stripe_end;
- } else {
- pgio->pg_layout_private = (void *)
- OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
- }
-}
-
-static const struct nfs_pageio_ops objio_pg_read_ops = {
- .pg_init = objio_init_read,
- .pg_test = objio_pg_test,
- .pg_doio = pnfs_generic_pg_readpages,
- .pg_cleanup = pnfs_generic_pg_cleanup,
-};
-
-static const struct nfs_pageio_ops objio_pg_write_ops = {
- .pg_init = objio_init_write,
- .pg_test = objio_pg_test,
- .pg_doio = pnfs_generic_pg_writepages,
- .pg_cleanup = pnfs_generic_pg_cleanup,
-};
-
-static struct pnfs_layoutdriver_type objlayout_type = {
- .id = LAYOUT_OSD2_OBJECTS,
- .name = "LAYOUT_OSD2_OBJECTS",
- .flags = PNFS_LAYOUTRET_ON_SETATTR |
- PNFS_LAYOUTRET_ON_ERROR,
-
- .max_deviceinfo_size = PAGE_SIZE,
- .owner = THIS_MODULE,
- .alloc_layout_hdr = objlayout_alloc_layout_hdr,
- .free_layout_hdr = objlayout_free_layout_hdr,
-
- .alloc_lseg = objlayout_alloc_lseg,
- .free_lseg = objlayout_free_lseg,
-
- .read_pagelist = objlayout_read_pagelist,
- .write_pagelist = objlayout_write_pagelist,
- .pg_read_ops = &objio_pg_read_ops,
- .pg_write_ops = &objio_pg_write_ops,
-
- .sync = pnfs_generic_sync,
-
- .free_deviceid_node = objio_free_deviceid_node,
-
- .encode_layoutcommit = objlayout_encode_layoutcommit,
- .encode_layoutreturn = objlayout_encode_layoutreturn,
-};
-
-MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");
-MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>");
-MODULE_LICENSE("GPL");
-
-static int __init
-objlayout_init(void)
-{
- int ret = pnfs_register_layoutdriver(&objlayout_type);
-
- if (ret)
- printk(KERN_INFO
- "NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n",
- __func__, ret);
- else
- printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n",
- __func__);
- return ret;
-}
-
-static void __exit
-objlayout_exit(void)
-{
- pnfs_unregister_layoutdriver(&objlayout_type);
- printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n",
- __func__);
-}
-
-MODULE_ALIAS("nfs-layouttype4-2");
-
-module_init(objlayout_init);
-module_exit(objlayout_exit);
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
deleted file mode 100644
index 8f3d2acb81c3..000000000000
--- a/fs/nfs/objlayout/objlayout.c
+++ /dev/null
@@ -1,706 +0,0 @@
-/*
- * pNFS Objects layout driver high level definitions
- *
- * Copyright (C) 2007 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.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
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/kmod.h>
-#include <linux/moduleparam.h>
-#include <linux/ratelimit.h>
-#include <scsi/osd_initiator.h>
-#include "objlayout.h"
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-/*
- * Create a objlayout layout structure for the given inode and return it.
- */
-struct pnfs_layout_hdr *
-objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
-{
- struct objlayout *objlay;
-
- objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
- if (!objlay)
- return NULL;
- spin_lock_init(&objlay->lock);
- INIT_LIST_HEAD(&objlay->err_list);
- dprintk("%s: Return %p\n", __func__, objlay);
- return &objlay->pnfs_layout;
-}
-
-/*
- * Free an objlayout layout structure
- */
-void
-objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
-{
- struct objlayout *objlay = OBJLAYOUT(lo);
-
- dprintk("%s: objlay %p\n", __func__, objlay);
-
- WARN_ON(!list_empty(&objlay->err_list));
- kfree(objlay);
-}
-
-/*
- * Unmarshall layout and store it in pnfslay.
- */
-struct pnfs_layout_segment *
-objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay,
- struct nfs4_layoutget_res *lgr,
- gfp_t gfp_flags)
-{
- int status = -ENOMEM;
- struct xdr_stream stream;
- struct xdr_buf buf = {
- .pages = lgr->layoutp->pages,
- .page_len = lgr->layoutp->len,
- .buflen = lgr->layoutp->len,
- .len = lgr->layoutp->len,
- };
- struct page *scratch;
- struct pnfs_layout_segment *lseg;
-
- dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay);
-
- scratch = alloc_page(gfp_flags);
- if (!scratch)
- goto err_nofree;
-
- xdr_init_decode(&stream, &buf, NULL);
- xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
-
- status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags);
- if (unlikely(status)) {
- dprintk("%s: objio_alloc_lseg Return err %d\n", __func__,
- status);
- goto err;
- }
-
- __free_page(scratch);
-
- dprintk("%s: Return %p\n", __func__, lseg);
- return lseg;
-
-err:
- __free_page(scratch);
-err_nofree:
- dprintk("%s: Err Return=>%d\n", __func__, status);
- return ERR_PTR(status);
-}
-
-/*
- * Free a layout segement
- */
-void
-objlayout_free_lseg(struct pnfs_layout_segment *lseg)
-{
- dprintk("%s: freeing layout segment %p\n", __func__, lseg);
-
- if (unlikely(!lseg))
- return;
-
- objio_free_lseg(lseg);
-}
-
-/*
- * I/O Operations
- */
-static inline u64
-end_offset(u64 start, u64 len)
-{
- u64 end;
-
- end = start + len;
- return end >= start ? end : NFS4_MAX_UINT64;
-}
-
-static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
- struct page ***p_pages, unsigned *p_pgbase,
- u64 offset, unsigned long count)
-{
- u64 lseg_end_offset;
-
- BUG_ON(offset < lseg->pls_range.offset);
- lseg_end_offset = end_offset(lseg->pls_range.offset,
- lseg->pls_range.length);
- BUG_ON(offset >= lseg_end_offset);
- WARN_ON(offset + count > lseg_end_offset);
-
- if (*p_pgbase > PAGE_SIZE) {
- dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase);
- *p_pages += *p_pgbase >> PAGE_SHIFT;
- *p_pgbase &= ~PAGE_MASK;
- }
-}
-
-/*
- * I/O done common code
- */
-static void
-objlayout_iodone(struct objlayout_io_res *oir)
-{
- if (likely(oir->status >= 0)) {
- objio_free_result(oir);
- } else {
- struct objlayout *objlay = oir->objlay;
-
- spin_lock(&objlay->lock);
- objlay->delta_space_valid = OBJ_DSU_INVALID;
- list_add(&objlay->err_list, &oir->err_list);
- spin_unlock(&objlay->lock);
- }
-}
-
-/*
- * objlayout_io_set_result - Set an osd_error code on a specific osd comp.
- *
- * The @index component IO failed (error returned from target). Register
- * the error for later reporting at layout-return.
- */
-void
-objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
- struct pnfs_osd_objid *pooid, int osd_error,
- u64 offset, u64 length, bool is_write)
-{
- struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index];
-
- BUG_ON(index >= oir->num_comps);
- if (osd_error) {
- ioerr->oer_component = *pooid;
- ioerr->oer_comp_offset = offset;
- ioerr->oer_comp_length = length;
- ioerr->oer_iswrite = is_write;
- ioerr->oer_errno = osd_error;
-
- dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) "
- "par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n",
- __func__, index, ioerr->oer_errno,
- ioerr->oer_iswrite,
- _DEVID_LO(&ioerr->oer_component.oid_device_id),
- _DEVID_HI(&ioerr->oer_component.oid_device_id),
- ioerr->oer_component.oid_partition_id,
- ioerr->oer_component.oid_object_id,
- ioerr->oer_comp_offset,
- ioerr->oer_comp_length);
- } else {
- /* User need not call if no error is reported */
- ioerr->oer_errno = 0;
- }
-}
-
-/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete().
- * This is because the osd completion is called with ints-off from
- * the block layer
- */
-static void _rpc_read_complete(struct work_struct *work)
-{
- struct rpc_task *task;
- struct nfs_pgio_header *hdr;
-
- dprintk("%s enter\n", __func__);
- task = container_of(work, struct rpc_task, u.tk_work);
- hdr = container_of(task, struct nfs_pgio_header, task);
-
- pnfs_ld_read_done(hdr);
-}
-
-void
-objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
-{
- struct nfs_pgio_header *hdr = oir->rpcdata;
-
- oir->status = hdr->task.tk_status = status;
- if (status >= 0)
- hdr->res.count = status;
- else
- hdr->pnfs_error = status;
- objlayout_iodone(oir);
- /* must not use oir after this point */
-
- dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__,
- status, hdr->res.eof, sync);
-
- if (sync)
- pnfs_ld_read_done(hdr);
- else {
- INIT_WORK(&hdr->task.u.tk_work, _rpc_read_complete);
- schedule_work(&hdr->task.u.tk_work);
- }
-}
-
-/*
- * Perform sync or async reads.
- */
-enum pnfs_try_status
-objlayout_read_pagelist(struct nfs_pgio_header *hdr)
-{
- struct inode *inode = hdr->inode;
- loff_t offset = hdr->args.offset;
- size_t count = hdr->args.count;
- int err;
- loff_t eof;
-
- eof = i_size_read(inode);
- if (unlikely(offset + count > eof)) {
- if (offset >= eof) {
- err = 0;
- hdr->res.count = 0;
- hdr->res.eof = 1;
- /*FIXME: do we need to call pnfs_ld_read_done() */
- goto out;
- }
- count = eof - offset;
- }
-
- hdr->res.eof = (offset + count) >= eof;
- _fix_verify_io_params(hdr->lseg, &hdr->args.pages,
- &hdr->args.pgbase,
- hdr->args.offset, hdr->args.count);
-
- dprintk("%s: inode(%lx) offset 0x%llx count 0x%zx eof=%d\n",
- __func__, inode->i_ino, offset, count, hdr->res.eof);
-
- err = objio_read_pagelist(hdr);
- out:
- if (unlikely(err)) {
- hdr->pnfs_error = err;
- dprintk("%s: Returned Error %d\n", __func__, err);
- return PNFS_NOT_ATTEMPTED;
- }
- return PNFS_ATTEMPTED;
-}
-
-/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete().
- * This is because the osd completion is called with ints-off from
- * the block layer
- */
-static void _rpc_write_complete(struct work_struct *work)
-{
- struct rpc_task *task;
- struct nfs_pgio_header *hdr;
-
- dprintk("%s enter\n", __func__);
- task = container_of(work, struct rpc_task, u.tk_work);
- hdr = container_of(task, struct nfs_pgio_header, task);
-
- pnfs_ld_write_done(hdr);
-}
-
-void
-objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
-{
- struct nfs_pgio_header *hdr = oir->rpcdata;
-
- oir->status = hdr->task.tk_status = status;
- if (status >= 0) {
- hdr->res.count = status;
- hdr->verf.committed = oir->committed;
- } else {
- hdr->pnfs_error = status;
- }
- objlayout_iodone(oir);
- /* must not use oir after this point */
-
- dprintk("%s: Return status %zd committed %d sync=%d\n", __func__,
- status, hdr->verf.committed, sync);
-
- if (sync)
- pnfs_ld_write_done(hdr);
- else {
- INIT_WORK(&hdr->task.u.tk_work, _rpc_write_complete);
- schedule_work(&hdr->task.u.tk_work);
- }
-}
-
-/*
- * Perform sync or async writes.
- */
-enum pnfs_try_status
-objlayout_write_pagelist(struct nfs_pgio_header *hdr, int how)
-{
- int err;
-
- _fix_verify_io_params(hdr->lseg, &hdr->args.pages,
- &hdr->args.pgbase,
- hdr->args.offset, hdr->args.count);
-
- err = objio_write_pagelist(hdr, how);
- if (unlikely(err)) {
- hdr->pnfs_error = err;
- dprintk("%s: Returned Error %d\n", __func__, err);
- return PNFS_NOT_ATTEMPTED;
- }
- return PNFS_ATTEMPTED;
-}
-
-void
-objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay,
- struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *args)
-{
- struct objlayout *objlay = OBJLAYOUT(pnfslay);
- struct pnfs_osd_layoutupdate lou;
- __be32 *start;
-
- dprintk("%s: Begin\n", __func__);
-
- spin_lock(&objlay->lock);
- lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID);
- lou.dsu_delta = objlay->delta_space_used;
- objlay->delta_space_used = 0;
- objlay->delta_space_valid = OBJ_DSU_INIT;
- lou.olu_ioerr_flag = !list_empty(&objlay->err_list);
- spin_unlock(&objlay->lock);
-
- start = xdr_reserve_space(xdr, 4);
-
- BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou));
-
- *start = cpu_to_be32((xdr->p - start - 1) * 4);
-
- dprintk("%s: Return delta_space_used %lld err %d\n", __func__,
- lou.dsu_delta, lou.olu_ioerr_flag);
-}
-
-static int
-err_prio(u32 oer_errno)
-{
- switch (oer_errno) {
- case 0:
- return 0;
-
- case PNFS_OSD_ERR_RESOURCE:
- return OSD_ERR_PRI_RESOURCE;
- case PNFS_OSD_ERR_BAD_CRED:
- return OSD_ERR_PRI_BAD_CRED;
- case PNFS_OSD_ERR_NO_ACCESS:
- return OSD_ERR_PRI_NO_ACCESS;
- case PNFS_OSD_ERR_UNREACHABLE:
- return OSD_ERR_PRI_UNREACHABLE;
- case PNFS_OSD_ERR_NOT_FOUND:
- return OSD_ERR_PRI_NOT_FOUND;
- case PNFS_OSD_ERR_NO_SPACE:
- return OSD_ERR_PRI_NO_SPACE;
- default:
- WARN_ON(1);
- /* fallthrough */
- case PNFS_OSD_ERR_EIO:
- return OSD_ERR_PRI_EIO;
- }
-}
-
-static void
-merge_ioerr(struct pnfs_osd_ioerr *dest_err,
- const struct pnfs_osd_ioerr *src_err)
-{
- u64 dest_end, src_end;
-
- if (!dest_err->oer_errno) {
- *dest_err = *src_err;
- /* accumulated device must be blank */
- memset(&dest_err->oer_component.oid_device_id, 0,
- sizeof(dest_err->oer_component.oid_device_id));
-
- return;
- }
-
- if (dest_err->oer_component.oid_partition_id !=
- src_err->oer_component.oid_partition_id)
- dest_err->oer_component.oid_partition_id = 0;
-
- if (dest_err->oer_component.oid_object_id !=
- src_err->oer_component.oid_object_id)
- dest_err->oer_component.oid_object_id = 0;
-
- if (dest_err->oer_comp_offset > src_err->oer_comp_offset)
- dest_err->oer_comp_offset = src_err->oer_comp_offset;
-
- dest_end = end_offset(dest_err->oer_comp_offset,
- dest_err->oer_comp_length);
- src_end = end_offset(src_err->oer_comp_offset,
- src_err->oer_comp_length);
- if (dest_end < src_end)
- dest_end = src_end;
-
- dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset;
-
- if ((src_err->oer_iswrite == dest_err->oer_iswrite) &&
- (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) {
- dest_err->oer_errno = src_err->oer_errno;
- } else if (src_err->oer_iswrite) {
- dest_err->oer_iswrite = true;
- dest_err->oer_errno = src_err->oer_errno;
- }
-}
-
-static void
-encode_accumulated_error(struct objlayout *objlay, __be32 *p)
-{
- struct objlayout_io_res *oir, *tmp;
- struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
-
- list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
- unsigned i;
-
- for (i = 0; i < oir->num_comps; i++) {
- struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
-
- if (!ioerr->oer_errno)
- continue;
-
- printk(KERN_ERR "NFS: %s: err[%d]: errno=%d "
- "is_write=%d dev(%llx:%llx) par=0x%llx "
- "obj=0x%llx offset=0x%llx length=0x%llx\n",
- __func__, i, ioerr->oer_errno,
- ioerr->oer_iswrite,
- _DEVID_LO(&ioerr->oer_component.oid_device_id),
- _DEVID_HI(&ioerr->oer_component.oid_device_id),
- ioerr->oer_component.oid_partition_id,
- ioerr->oer_component.oid_object_id,
- ioerr->oer_comp_offset,
- ioerr->oer_comp_length);
-
- merge_ioerr(&accumulated_err, ioerr);
- }
- list_del(&oir->err_list);
- objio_free_result(oir);
- }
-
- pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
-}
-
-void
-objlayout_encode_layoutreturn(struct xdr_stream *xdr,
- const struct nfs4_layoutreturn_args *args)
-{
- struct pnfs_layout_hdr *pnfslay = args->layout;
- struct objlayout *objlay = OBJLAYOUT(pnfslay);
- struct objlayout_io_res *oir, *tmp;
- __be32 *start;
-
- dprintk("%s: Begin\n", __func__);
- start = xdr_reserve_space(xdr, 4);
- BUG_ON(!start);
-
- spin_lock(&objlay->lock);
-
- list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
- __be32 *last_xdr = NULL, *p;
- unsigned i;
- int res = 0;
-
- for (i = 0; i < oir->num_comps; i++) {
- struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
-
- if (!ioerr->oer_errno)
- continue;
-
- dprintk("%s: err[%d]: errno=%d is_write=%d "
- "dev(%llx:%llx) par=0x%llx obj=0x%llx "
- "offset=0x%llx length=0x%llx\n",
- __func__, i, ioerr->oer_errno,
- ioerr->oer_iswrite,
- _DEVID_LO(&ioerr->oer_component.oid_device_id),
- _DEVID_HI(&ioerr->oer_component.oid_device_id),
- ioerr->oer_component.oid_partition_id,
- ioerr->oer_component.oid_object_id,
- ioerr->oer_comp_offset,
- ioerr->oer_comp_length);
-
- p = pnfs_osd_xdr_ioerr_reserve_space(xdr);
- if (unlikely(!p)) {
- res = -E2BIG;
- break; /* accumulated_error */
- }
-
- last_xdr = p;
- pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]);
- }
-
- /* TODO: use xdr_write_pages */
- if (unlikely(res)) {
- /* no space for even one error descriptor */
- BUG_ON(!last_xdr);
-
- /* we've encountered a situation with lots and lots of
- * errors and no space to encode them all. Use the last
- * available slot to report the union of all the
- * remaining errors.
- */
- encode_accumulated_error(objlay, last_xdr);
- goto loop_done;
- }
- list_del(&oir->err_list);
- objio_free_result(oir);
- }
-loop_done:
- spin_unlock(&objlay->lock);
-
- *start = cpu_to_be32((xdr->p - start - 1) * 4);
- dprintk("%s: Return\n", __func__);
-}
-
-enum {
- OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
- OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
- OSD_LOGIN_UPCALL_PATHLEN = 256
-};
-
-static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login";
-
-module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog),
- 0600);
-MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program");
-
-struct __auto_login {
- char uri[OBJLAYOUT_MAX_URI_LEN];
- char osdname[OBJLAYOUT_MAX_OSDNAME_LEN];
- char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN];
-};
-
-static int __objlayout_upcall(struct __auto_login *login)
-{
- static char *envp[] = { "HOME=/",
- "TERM=linux",
- "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
- NULL
- };
- char *argv[8];
- int ret;
-
- if (unlikely(!osd_login_prog[0])) {
- dprintk("%s: osd_login_prog is disabled\n", __func__);
- return -EACCES;
- }
-
- dprintk("%s uri: %s\n", __func__, login->uri);
- dprintk("%s osdname %s\n", __func__, login->osdname);
- dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex);
-
- argv[0] = (char *)osd_login_prog;
- argv[1] = "-u";
- argv[2] = login->uri;
- argv[3] = "-o";
- argv[4] = login->osdname;
- argv[5] = "-s";
- argv[6] = login->systemid_hex;
- argv[7] = NULL;
-
- ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
- /*
- * Disable the upcall mechanism if we're getting an ENOENT or
- * EACCES error. The admin can re-enable it on the fly by using
- * sysfs to set the objlayoutdriver.osd_login_prog module parameter once
- * the problem has been fixed.
- */
- if (ret == -ENOENT || ret == -EACCES) {
- printk(KERN_ERR "PNFS-OBJ: %s was not found please set "
- "objlayoutdriver.osd_login_prog kernel parameter!\n",
- osd_login_prog);
- osd_login_prog[0] = '\0';
- }
- dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret);
-
- return ret;
-}
-
-/* Assume dest is all zeros */
-static void __copy_nfsS_and_zero_terminate(struct nfs4_string s,
- char *dest, int max_len,
- const char *var_name)
-{
- if (!s.len)
- return;
-
- if (s.len >= max_len) {
- pr_warn_ratelimited(
- "objlayout_autologin: %s: s.len(%d) >= max_len(%d)",
- var_name, s.len, max_len);
- s.len = max_len - 1; /* space for null terminator */
- }
-
- memcpy(dest, s.data, s.len);
-}
-
-/* Assume sysid is all zeros */
-static void _sysid_2_hex(struct nfs4_string s,
- char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN])
-{
- int i;
- char *cur;
-
- if (!s.len)
- return;
-
- if (s.len != OSD_SYSTEMID_LEN) {
- pr_warn_ratelimited(
- "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN",
- s.len);
- if (s.len > OSD_SYSTEMID_LEN)
- s.len = OSD_SYSTEMID_LEN;
- }
-
- cur = sysid;
- for (i = 0; i < s.len; i++)
- cur = hex_byte_pack(cur, s.data[i]);
-}
-
-int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr)
-{
- int rc;
- struct __auto_login login;
-
- if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len)
- return -ENODEV;
-
- memset(&login, 0, sizeof(login));
- __copy_nfsS_and_zero_terminate(
- deviceaddr->oda_targetaddr.ota_netaddr.r_addr,
- login.uri, sizeof(login.uri), "URI");
-
- __copy_nfsS_and_zero_terminate(
- deviceaddr->oda_osdname,
- login.osdname, sizeof(login.osdname), "OSDNAME");
-
- _sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex);
-
- rc = __objlayout_upcall(&login);
- if (rc > 0) /* script returns positive values */
- rc = -ENODEV;
-
- return rc;
-}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
deleted file mode 100644
index fc94a5872ed4..000000000000
--- a/fs/nfs/objlayout/objlayout.h
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Data types and function declerations for interfacing with the
- * pNFS standard object layout driver.
- *
- * Copyright (C) 2007 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.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
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _OBJLAYOUT_H
-#define _OBJLAYOUT_H
-
-#include <linux/nfs_fs.h>
-#include <linux/pnfs_osd_xdr.h>
-#include "../pnfs.h"
-
-/*
- * per-inode layout
- */
-struct objlayout {
- struct pnfs_layout_hdr pnfs_layout;
-
- /* for layout_commit */
- enum osd_delta_space_valid_enum {
- OBJ_DSU_INIT = 0,
- OBJ_DSU_VALID,
- OBJ_DSU_INVALID,
- } delta_space_valid;
- s64 delta_space_used; /* consumed by write ops */
-
- /* for layout_return */
- spinlock_t lock;
- struct list_head err_list;
-};
-
-static inline struct objlayout *
-OBJLAYOUT(struct pnfs_layout_hdr *lo)
-{
- return container_of(lo, struct objlayout, pnfs_layout);
-}
-
-/*
- * per-I/O operation state
- * embedded in objects provider io_state data structure
- */
-struct objlayout_io_res {
- struct objlayout *objlay;
-
- void *rpcdata;
- int status; /* res */
- int committed; /* res */
-
- /* Error reporting (layout_return) */
- struct list_head err_list;
- unsigned num_comps;
- /* Pointer to array of error descriptors of size num_comps.
- * It should contain as many entries as devices in the osd_layout
- * that participate in the I/O. It is up to the io_engine to allocate
- * needed space and set num_comps.
- */
- struct pnfs_osd_ioerr *ioerrs;
-};
-
-static inline
-void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
- struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
- struct pnfs_layout_hdr *pnfs_layout_type)
-{
- oir->objlay = OBJLAYOUT(pnfs_layout_type);
- oir->rpcdata = rpcdata;
- INIT_LIST_HEAD(&oir->err_list);
- oir->num_comps = num_comps;
- oir->ioerrs = ioerrs;
-}
-
-/*
- * Raid engine I/O API
- */
-extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
- struct pnfs_layout_hdr *pnfslay,
- struct pnfs_layout_range *range,
- struct xdr_stream *xdr,
- gfp_t gfp_flags);
-extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
-
-/* objio_free_result will free these @oir structs received from
- * objlayout_{read,write}_done
- */
-extern void objio_free_result(struct objlayout_io_res *oir);
-
-extern int objio_read_pagelist(struct nfs_pgio_header *rdata);
-extern int objio_write_pagelist(struct nfs_pgio_header *wdata, int how);
-
-/*
- * callback API
- */
-extern void objlayout_io_set_result(struct objlayout_io_res *oir,
- unsigned index, struct pnfs_osd_objid *pooid,
- int osd_error, u64 offset, u64 length, bool is_write);
-
-static inline void
-objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
-{
- /* If one of the I/Os errored out and the delta_space_used was
- * invalid we render the complete report as invalid. Protocol mandate
- * the DSU be accurate or not reported.
- */
- spin_lock(&objlay->lock);
- if (objlay->delta_space_valid != OBJ_DSU_INVALID) {
- objlay->delta_space_valid = OBJ_DSU_VALID;
- objlay->delta_space_used += space_used;
- }
- spin_unlock(&objlay->lock);
-}
-
-extern void objlayout_read_done(struct objlayout_io_res *oir,
- ssize_t status, bool sync);
-extern void objlayout_write_done(struct objlayout_io_res *oir,
- ssize_t status, bool sync);
-
-/*
- * exported generic objects function vectors
- */
-
-extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags);
-extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *);
-
-extern struct pnfs_layout_segment *objlayout_alloc_lseg(
- struct pnfs_layout_hdr *,
- struct nfs4_layoutget_res *,
- gfp_t gfp_flags);
-extern void objlayout_free_lseg(struct pnfs_layout_segment *);
-
-extern enum pnfs_try_status objlayout_read_pagelist(
- struct nfs_pgio_header *);
-
-extern enum pnfs_try_status objlayout_write_pagelist(
- struct nfs_pgio_header *,
- int how);
-
-extern void objlayout_encode_layoutcommit(
- struct pnfs_layout_hdr *,
- struct xdr_stream *,
- const struct nfs4_layoutcommit_args *);
-
-extern void objlayout_encode_layoutreturn(
- struct xdr_stream *,
- const struct nfs4_layoutreturn_args *);
-
-extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr);
-
-#endif /* _OBJLAYOUT_H */
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
deleted file mode 100644
index f093c7ec983b..000000000000
--- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
+++ /dev/null
@@ -1,415 +0,0 @@
-/*
- * Object-Based pNFS Layout XDR layer
- *
- * Copyright (C) 2007 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.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
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/pnfs_osd_xdr.h>
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-/*
- * The following implementation is based on RFC5664
- */
-
-/*
- * struct pnfs_osd_objid {
- * struct nfs4_deviceid oid_device_id;
- * u64 oid_partition_id;
- * u64 oid_object_id;
- * }; // xdr size 32 bytes
- */
-static __be32 *
-_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid)
-{
- p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data,
- sizeof(objid->oid_device_id.data));
-
- p = xdr_decode_hyper(p, &objid->oid_partition_id);
- p = xdr_decode_hyper(p, &objid->oid_object_id);
- return p;
-}
-/*
- * struct pnfs_osd_opaque_cred {
- * u32 cred_len;
- * void *cred;
- * }; // xdr size [variable]
- * The return pointers are from the xdr buffer
- */
-static int
-_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred,
- struct xdr_stream *xdr)
-{
- __be32 *p = xdr_inline_decode(xdr, 1);
-
- if (!p)
- return -EINVAL;
-
- opaque_cred->cred_len = be32_to_cpu(*p++);
-
- p = xdr_inline_decode(xdr, opaque_cred->cred_len);
- if (!p)
- return -EINVAL;
-
- opaque_cred->cred = p;
- return 0;
-}
-
-/*
- * struct pnfs_osd_object_cred {
- * struct pnfs_osd_objid oc_object_id;
- * u32 oc_osd_version;
- * u32 oc_cap_key_sec;
- * struct pnfs_osd_opaque_cred oc_cap_key
- * struct pnfs_osd_opaque_cred oc_cap;
- * }; // xdr size 32 + 4 + 4 + [variable] + [variable]
- */
-static int
-_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp,
- struct xdr_stream *xdr)
-{
- __be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4);
- int ret;
-
- if (!p)
- return -EIO;
-
- p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
- comp->oc_osd_version = be32_to_cpup(p++);
- comp->oc_cap_key_sec = be32_to_cpup(p);
-
- ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr);
- if (unlikely(ret))
- return ret;
-
- ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr);
- return ret;
-}
-
-/*
- * struct pnfs_osd_data_map {
- * u32 odm_num_comps;
- * u64 odm_stripe_unit;
- * u32 odm_group_width;
- * u32 odm_group_depth;
- * u32 odm_mirror_cnt;
- * u32 odm_raid_algorithm;
- * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4
- */
-static inline int
-_osd_data_map_xdr_sz(void)
-{
- return 4 + 8 + 4 + 4 + 4 + 4;
-}
-
-static __be32 *
-_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map)
-{
- data_map->odm_num_comps = be32_to_cpup(p++);
- p = xdr_decode_hyper(p, &data_map->odm_stripe_unit);
- data_map->odm_group_width = be32_to_cpup(p++);
- data_map->odm_group_depth = be32_to_cpup(p++);
- data_map->odm_mirror_cnt = be32_to_cpup(p++);
- data_map->odm_raid_algorithm = be32_to_cpup(p++);
- dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u "
- "odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n",
- __func__,
- data_map->odm_num_comps,
- (unsigned long long)data_map->odm_stripe_unit,
- data_map->odm_group_width,
- data_map->odm_group_depth,
- data_map->odm_mirror_cnt,
- data_map->odm_raid_algorithm);
- return p;
-}
-
-int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
- struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr)
-{
- __be32 *p;
-
- memset(iter, 0, sizeof(*iter));
-
- p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4);
- if (unlikely(!p))
- return -EINVAL;
-
- p = _osd_xdr_decode_data_map(p, &layout->olo_map);
- layout->olo_comps_index = be32_to_cpup(p++);
- layout->olo_num_comps = be32_to_cpup(p++);
- dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
- layout->olo_comps_index, layout->olo_num_comps);
-
- iter->total_comps = layout->olo_num_comps;
- return 0;
-}
-
-bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
- struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
- int *err)
-{
- BUG_ON(iter->decoded_comps > iter->total_comps);
- if (iter->decoded_comps == iter->total_comps)
- return false;
-
- *err = _osd_xdr_decode_object_cred(comp, xdr);
- if (unlikely(*err)) {
- dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d "
- "total_comps=%d\n", __func__, *err,
- iter->decoded_comps, iter->total_comps);
- return false; /* stop the loop */
- }
- dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx "
- "key_len=%u cap_len=%u\n",
- __func__,
- _DEVID_LO(&comp->oc_object_id.oid_device_id),
- _DEVID_HI(&comp->oc_object_id.oid_device_id),
- comp->oc_object_id.oid_partition_id,
- comp->oc_object_id.oid_object_id,
- comp->oc_cap_key.cred_len, comp->oc_cap.cred_len);
-
- iter->decoded_comps++;
- return true;
-}
-
-/*
- * Get Device Information Decoding
- *
- * Note: since Device Information is currently done synchronously, all
- * variable strings fields are left inside the rpc buffer and are only
- * pointed to by the pnfs_osd_deviceaddr members. So the read buffer
- * should not be freed while the returned information is in use.
- */
-/*
- *struct nfs4_string {
- * unsigned int len;
- * char *data;
- *}; // size [variable]
- * NOTE: Returned string points to inside the XDR buffer
- */
-static __be32 *
-__read_u8_opaque(__be32 *p, struct nfs4_string *str)
-{
- str->len = be32_to_cpup(p++);
- str->data = (char *)p;
-
- p += XDR_QUADLEN(str->len);
- return p;
-}
-
-/*
- * struct pnfs_osd_targetid {
- * u32 oti_type;
- * struct nfs4_string oti_scsi_device_id;
- * };// size 4 + [variable]
- */
-static __be32 *
-__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid)
-{
- u32 oti_type;
-
- oti_type = be32_to_cpup(p++);
- targetid->oti_type = oti_type;
-
- switch (oti_type) {
- case OBJ_TARGET_SCSI_NAME:
- case OBJ_TARGET_SCSI_DEVICE_ID:
- p = __read_u8_opaque(p, &targetid->oti_scsi_device_id);
- }
-
- return p;
-}
-
-/*
- * struct pnfs_osd_net_addr {
- * struct nfs4_string r_netid;
- * struct nfs4_string r_addr;
- * };
- */
-static __be32 *
-__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr)
-{
- p = __read_u8_opaque(p, &netaddr->r_netid);
- p = __read_u8_opaque(p, &netaddr->r_addr);
-
- return p;
-}
-
-/*
- * struct pnfs_osd_targetaddr {
- * u32 ota_available;
- * struct pnfs_osd_net_addr ota_netaddr;
- * };
- */
-static __be32 *
-__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr)
-{
- u32 ota_available;
-
- ota_available = be32_to_cpup(p++);
- targetaddr->ota_available = ota_available;
-
- if (ota_available)
- p = __read_net_addr(p, &targetaddr->ota_netaddr);
-
-
- return p;
-}
-
-/*
- * struct pnfs_osd_deviceaddr {
- * struct pnfs_osd_targetid oda_targetid;
- * struct pnfs_osd_targetaddr oda_targetaddr;
- * u8 oda_lun[8];
- * struct nfs4_string oda_systemid;
- * struct pnfs_osd_object_cred oda_root_obj_cred;
- * struct nfs4_string oda_osdname;
- * };
- */
-
-/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does
- * not have an xdr_stream
- */
-static __be32 *
-__read_opaque_cred(__be32 *p,
- struct pnfs_osd_opaque_cred *opaque_cred)
-{
- opaque_cred->cred_len = be32_to_cpu(*p++);
- opaque_cred->cred = p;
- return p + XDR_QUADLEN(opaque_cred->cred_len);
-}
-
-static __be32 *
-__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp)
-{
- p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
- comp->oc_osd_version = be32_to_cpup(p++);
- comp->oc_cap_key_sec = be32_to_cpup(p++);
-
- p = __read_opaque_cred(p, &comp->oc_cap_key);
- p = __read_opaque_cred(p, &comp->oc_cap);
- return p;
-}
-
-void pnfs_osd_xdr_decode_deviceaddr(
- struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p)
-{
- p = __read_targetid(p, &deviceaddr->oda_targetid);
-
- p = __read_targetaddr(p, &deviceaddr->oda_targetaddr);
-
- p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun,
- sizeof(deviceaddr->oda_lun));
-
- p = __read_u8_opaque(p, &deviceaddr->oda_systemid);
-
- p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred);
-
- p = __read_u8_opaque(p, &deviceaddr->oda_osdname);
-
- /* libosd likes this terminated in dbg. It's last, so no problems */
- deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0;
-}
-
-/*
- * struct pnfs_osd_layoutupdate {
- * u32 dsu_valid;
- * s64 dsu_delta;
- * u32 olu_ioerr_flag;
- * }; xdr size 4 + 8 + 4
- */
-int
-pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
- struct pnfs_osd_layoutupdate *lou)
-{
- __be32 *p = xdr_reserve_space(xdr, 4 + 8 + 4);
-
- if (!p)
- return -E2BIG;
-
- *p++ = cpu_to_be32(lou->dsu_valid);
- if (lou->dsu_valid)
- p = xdr_encode_hyper(p, lou->dsu_delta);
- *p++ = cpu_to_be32(lou->olu_ioerr_flag);
- return 0;
-}
-
-/*
- * struct pnfs_osd_objid {
- * struct nfs4_deviceid oid_device_id;
- * u64 oid_partition_id;
- * u64 oid_object_id;
- * }; // xdr size 32 bytes
- */
-static inline __be32 *
-pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id)
-{
- p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data,
- sizeof(object_id->oid_device_id.data));
- p = xdr_encode_hyper(p, object_id->oid_partition_id);
- p = xdr_encode_hyper(p, object_id->oid_object_id);
-
- return p;
-}
-
-/*
- * struct pnfs_osd_ioerr {
- * struct pnfs_osd_objid oer_component;
- * u64 oer_comp_offset;
- * u64 oer_comp_length;
- * u32 oer_iswrite;
- * u32 oer_errno;
- * }; // xdr size 32 + 24 bytes
- */
-void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr)
-{
- p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component);
- p = xdr_encode_hyper(p, ioerr->oer_comp_offset);
- p = xdr_encode_hyper(p, ioerr->oer_comp_length);
- *p++ = cpu_to_be32(ioerr->oer_iswrite);
- *p = cpu_to_be32(ioerr->oer_errno);
-}
-
-__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr)
-{
- __be32 *p;
-
- p = xdr_reserve_space(xdr, 32 + 24);
- if (unlikely(!p))
- dprintk("%s: out of xdr space\n", __func__);
-
- return p;
-}
--
2.11.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 4/4] scsi: remove the SCSI OSD library
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
` (2 preceding siblings ...)
2017-04-12 16:01 ` [PATCH 3/4] nfs: remove the objlayout driver Christoph Hellwig
@ 2017-04-12 16:01 ` Christoph Hellwig
2017-04-14 2:27 ` RFC: drop the T10 OSD code and its users Martin K. Petersen
` (2 subsequent siblings)
6 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-12 16:01 UTC (permalink / raw)
To: ooo, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
Now that all the users are gone the SCSI OSD library can be removed
as well.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/scsi/osd.txt | 192 ----
drivers/scsi/Makefile | 1 -
drivers/scsi/osd/Kbuild | 20 -
drivers/scsi/osd/Kconfig | 49 -
drivers/scsi/osd/osd_debug.h | 30 -
drivers/scsi/osd/osd_initiator.c | 2076 --------------------------------------
drivers/scsi/osd/osd_uld.c | 595 -----------
include/scsi/osd_initiator.h | 515 ----------
include/scsi/osd_ore.h | 201 ----
9 files changed, 3679 deletions(-)
delete mode 100644 Documentation/scsi/osd.txt
delete mode 100644 drivers/scsi/osd/Kbuild
delete mode 100644 drivers/scsi/osd/Kconfig
delete mode 100644 drivers/scsi/osd/osd_debug.h
delete mode 100644 drivers/scsi/osd/osd_initiator.c
delete mode 100644 drivers/scsi/osd/osd_uld.c
delete mode 100644 include/scsi/osd_initiator.h
delete mode 100644 include/scsi/osd_ore.h
diff --git a/Documentation/scsi/osd.txt b/Documentation/scsi/osd.txt
deleted file mode 100644
index 2bc2ab06b0c0..000000000000
--- a/Documentation/scsi/osd.txt
+++ /dev/null
@@ -1,192 +0,0 @@
-The OSD Standard
-================
-OSD (Object-Based Storage Device) is a T10 SCSI command set that is designed
-to provide efficient operation of input/output logical units that manage the
-allocation, placement, and accessing of variable-size data-storage containers,
-called objects. Objects are intended to contain operating system and application
-constructs. 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.
-
-See: http://www.t10.org/ftp/t10/drafts/osd2/ for the latest draft for OSD 2
-or search the web for "OSD SCSI"
-
-OSD in the Linux Kernel
-=======================
-osd-initiator:
- The main component of OSD in Kernel is the osd-initiator library. Its main
-user is intended to be the pNFS-over-objects layout driver, which uses objects
-as its back-end data storage. Other clients are the other osd parts listed below.
-
-osd-uld:
- This is a SCSI ULD that registers for OSD type devices and provides a testing
-platform, both for the in-kernel initiator as well as connected targets. It
-currently has no useful user-mode API, though it could have if need be.
-
-osd target:
- There are no current plans for an OSD target implementation in kernel. For all
-needs, a user-mode target that is based on the scsi tgt target framework is
-available from Ohio Supercomputer Center (OSC) at:
-http://www.open-osd.org/bin/view/Main/OscOsdProject
-There are several other target implementations. See http://open-osd.org for more
-links.
-
-Files and Folders
-=================
-This is the complete list of files included in this work:
-include/scsi/
- osd_initiator.h Main API for the initiator library
- osd_types.h Common OSD types
- osd_sec.h Security Manager API
- osd_protocol.h Wire definitions of the OSD standard protocol
- osd_attributes.h Wire definitions of OSD attributes
-
-drivers/scsi/osd/
- osd_initiator.c OSD-Initiator library implementation
- osd_uld.c The OSD scsi ULD
- osd_ktest.{h,c} In-kernel test suite (called by osd_uld)
- osd_debug.h Some printk macros
- Makefile For both in-tree and out-of-tree compilation
- Kconfig Enables inclusion of the different pieces
- osd_test.c User-mode application to call the kernel tests
-
-The OSD-Initiator Library
-=========================
-osd_initiator is a low level implementation of an osd initiator encoder.
-But even though, it should be intuitive and easy to use. Perhaps over time an
-higher lever will form that automates some of the more common recipes.
-
-init/fini:
-- osd_dev_init() associates a scsi_device with an osd_dev structure
- and initializes some global pools. This should be done once per scsi_device
- (OSD LUN). The osd_dev structure is needed for calling osd_start_request().
-
-- osd_dev_fini() cleans up before a osd_dev/scsi_device destruction.
-
-OSD commands encoding, execution, and decoding of results:
-
-struct osd_request's is used to iteratively encode an OSD command and carry
-its state throughout execution. Each request goes through these stages:
-
-a. osd_start_request() allocates the request.
-
-b. Any of the osd_req_* methods is used to encode a request of the specified
- type.
-
-c. osd_req_add_{get,set}_attr_* may be called to add get/set attributes to the
- CDB. "List" or "Page" mode can be used exclusively. The attribute-list API
- can be called multiple times on the same request. However, only one
- attribute-page can be read, as mandated by the OSD standard.
-
-d. osd_finalize_request() computes offsets into the data-in and data-out buffers
- and signs the request using the provided capability key and integrity-
- check parameters.
-
-e. osd_execute_request() may be called to execute the request via the block
- layer and wait for its completion. The request can be executed
- asynchronously by calling the block layer API directly.
-
-f. After execution, osd_req_decode_sense() can be called to decode the request's
- sense information.
-
-g. osd_req_decode_get_attr() may be called to retrieve osd_add_get_attr_list()
- values.
-
-h. osd_end_request() must be called to deallocate the request and any resource
- associated with it. Note that osd_end_request cleans up the request at any
- stage and it must always be called after a successful osd_start_request().
-
-osd_request's structure:
-
-The OSD standard defines a complex structure of IO segments pointed to by
-members in the CDB. Up to 3 segments can be deployed in the IN-Buffer and up to
-4 in the OUT-Buffer. The ASCII illustration below depicts a secure-read with
-associated get+set of attributes-lists. Other combinations very on the same
-basic theme. From no-segments-used up to all-segments-used.
-
-|________OSD-CDB__________|
-| |
-|read_len (offset=0) -|---------\
-| | |
-|get_attrs_list_length | |
-|get_attrs_list_offset -|----\ |
-| | | |
-|retrieved_attrs_alloc_len| | |
-|retrieved_attrs_offset -|----|----|-\
-| | | | |
-|set_attrs_list_length | | | |
-|set_attrs_list_offset -|-\ | | |
-| | | | | |
-|in_data_integ_offset -|-|--|----|-|-\
-|out_data_integ_offset -|-|--|--\ | | |
-\_________________________/ | | | | | |
- | | | | | |
-|_______OUT-BUFFER________| | | | | | |
-| Set attr list |</ | | | | |
-| | | | | | |
-|-------------------------| | | | | |
-| Get attr descriptors |<---/ | | | |
-| | | | | |
-|-------------------------| | | | |
-| Out-data integrity |<------/ | | |
-| | | | |
-\_________________________/ | | |
- | | |
-|________IN-BUFFER________| | | |
-| In-Data read |<--------/ | |
-| | | |
-|-------------------------| | |
-| Get attr list |<----------/ |
-| | |
-|-------------------------| |
-| In-data integrity |<------------/
-| |
-\_________________________/
-
-A block device request can carry bidirectional payload by means of associating
-a bidi_read request with a main write-request. Each in/out request is described
-by a chain of BIOs associated with each request.
-The CDB is of a SCSI VARLEN CDB format, as described by OSD standard.
-The OSD standard also mandates alignment restrictions at start of each segment.
-
-In the code, in struct osd_request, there are two _osd_io_info structures to
-describe the IN/OUT buffers above, two BIOs for the data payload and up to five
-_osd_req_data_segment structures to hold the different segments allocation and
-information.
-
-Important: We have chosen to disregard the assumption that a BIO-chain (and
-the resulting sg-list) describes a linear memory buffer. Meaning only first and
-last scatter chain can be incomplete and all the middle chains are of PAGE_SIZE.
-For us, a scatter-gather-list, as its name implies and as used by the Networking
-layer, is to describe a vector of buffers that will be transferred to/from the
-wire. It works very well with current iSCSI transport. iSCSI is currently the
-only deployed OSD transport. In the future we anticipate SAS and FC attached OSD
-devices as well.
-
-The OSD Testing ULD
-===================
-TODO: More user-mode control on tests.
-
-Authors, Mailing list
-=====================
-Please communicate with us on any deployment of osd, whether using this code
-or not.
-
-Any problems, questions, bug reports, lonely OSD nights, please email:
- OSD Dev List <osd-dev@open-osd.org>
-
-More up-to-date information can be found on:
-http://open-osd.org
-
-Boaz Harrosh <ooo@electrozaur.com>
-
-References
-==========
-Weber, R., "SCSI Object-Based Storage Device Commands",
-T10/1355-D ANSI/INCITS 400-2004,
-http://www.t10.org/ftp/t10/drafts/osd/osd-r10.pdf
-
-Weber, R., "SCSI Object-Based Storage Device Commands -2 (OSD-2)"
-T10/1729-D, Working Draft, rev. 3
-http://www.t10.org/ftp/t10/drafts/osd2/osd2r03.pdf
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index fc2855565a51..f5e75a3dac9e 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -152,7 +152,6 @@ obj-$(CONFIG_CHR_DEV_SG) += sg.o
obj-$(CONFIG_CHR_DEV_SCH) += ch.o
obj-$(CONFIG_SCSI_ENCLOSURE) += ses.o
-obj-$(CONFIG_SCSI_OSD_INITIATOR) += osd/
obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/
# This goes last, so that "real" scsi devices probe earlier
diff --git a/drivers/scsi/osd/Kbuild b/drivers/scsi/osd/Kbuild
deleted file mode 100644
index 58cecd45b0f5..000000000000
--- a/drivers/scsi/osd/Kbuild
+++ /dev/null
@@ -1,20 +0,0 @@
-#
-# Kbuild for the OSD modules
-#
-# Copyright (C) 2008 Panasas Inc. All rights reserved.
-#
-# Authors:
-# Boaz Harrosh <ooo@electrozaur.com>
-# Benny Halevy <bhalevy@panasas.com>
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License version 2
-#
-
-# libosd.ko - osd-initiator library
-libosd-y := osd_initiator.o
-obj-$(CONFIG_SCSI_OSD_INITIATOR) += libosd.o
-
-# osd.ko - SCSI ULD and char-device
-osd-y := osd_uld.o
-obj-$(CONFIG_SCSI_OSD_ULD) += osd.o
diff --git a/drivers/scsi/osd/Kconfig b/drivers/scsi/osd/Kconfig
deleted file mode 100644
index 347cc5e33749..000000000000
--- a/drivers/scsi/osd/Kconfig
+++ /dev/null
@@ -1,49 +0,0 @@
-#
-# Kernel configuration file for the OSD scsi protocol
-#
-# Copyright (C) 2008 Panasas Inc. All rights reserved.
-#
-# Authors:
-# Boaz Harrosh <ooo@electrozaur.com>
-# Benny Halevy <bhalevy@panasas.com>
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public version 2 License as
-# published by the Free Software Foundation
-#
-config SCSI_OSD_INITIATOR
- tristate "OSD-Initiator library"
- depends on SCSI
- help
- Enable the OSD-Initiator library (libosd.ko).
- NOTE: You must also select CRYPTO_SHA1 + CRYPTO_HMAC and their
- dependencies
-
-config SCSI_OSD_ULD
- tristate "OSD Upper Level driver"
- depends on SCSI_OSD_INITIATOR
- help
- Build a SCSI upper layer driver that exports /dev/osdX devices
- to user-mode for testing and controlling OSD devices. It is also
- needed by exofs, for mounting an OSD based file system.
-
-config SCSI_OSD_DPRINT_SENSE
- int "(0-2) When sense is returned, DEBUG print all sense descriptors"
- default 1
- depends on SCSI_OSD_INITIATOR
- help
- When a CHECK_CONDITION status is returned from a target, and a
- sense-buffer is retrieved, turning this on will dump a full
- sense-decoding message. Setting to 2 will also print recoverable
- errors that might be regularly returned for some filesystem
- operations.
-
-config SCSI_OSD_DEBUG
- bool "Compile All OSD modules with lots of DEBUG prints"
- default n
- depends on SCSI_OSD_INITIATOR
- help
- OSD Code is populated with lots of OSD_DEBUG(..) printouts to
- dmesg. Enable this if you found a bug and you want to help us
- track the problem (see also MAINTAINERS). Setting this will also
- force SCSI_OSD_DPRINT_SENSE=2.
diff --git a/drivers/scsi/osd/osd_debug.h b/drivers/scsi/osd/osd_debug.h
deleted file mode 100644
index 26341261bb5c..000000000000
--- a/drivers/scsi/osd/osd_debug.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * osd_debug.h - Some kprintf macros
- *
- * Copyright (C) 2008 Panasas Inc. All rights reserved.
- *
- * Authors:
- * Boaz Harrosh <ooo@electrozaur.com>
- * Benny Halevy <bhalevy@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
- *
- */
-#ifndef __OSD_DEBUG_H__
-#define __OSD_DEBUG_H__
-
-#define OSD_ERR(fmt, a...) printk(KERN_ERR "osd: " fmt, ##a)
-#define OSD_INFO(fmt, a...) printk(KERN_NOTICE "osd: " fmt, ##a)
-
-#ifdef CONFIG_SCSI_OSD_DEBUG
-#define OSD_DEBUG(fmt, a...) \
- printk(KERN_NOTICE "osd @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define OSD_DEBUG(fmt, a...) do {} while (0)
-#endif
-
-/* u64 has problems with printk this will cast it to unsigned long long */
-#define _LLU(x) (unsigned long long)(x)
-
-#endif /* ndef __OSD_DEBUG_H__ */
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
deleted file mode 100644
index 9d0727b2bdec..000000000000
--- a/drivers/scsi/osd/osd_initiator.c
+++ /dev/null
@@ -1,2076 +0,0 @@
-/*
- * osd_initiator - Main body of the osd initiator library.
- *
- * Note: The file does not contain the advanced security functionality which
- * is only needed by the security_manager's initiators.
- *
- * Copyright (C) 2008 Panasas Inc. All rights reserved.
- *
- * Authors:
- * Boaz Harrosh <ooo@electrozaur.com>
- * Benny Halevy <bhalevy@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
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/slab.h>
-#include <linux/module.h>
-
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_sec.h>
-#include <scsi/osd_attributes.h>
-#include <scsi/osd_sense.h>
-
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_request.h>
-
-#include "osd_debug.h"
-
-#ifndef __unused
-# define __unused __attribute__((unused))
-#endif
-
-enum { OSD_REQ_RETRIES = 1 };
-
-MODULE_AUTHOR("Boaz Harrosh <ooo@electrozaur.com>");
-MODULE_DESCRIPTION("open-osd initiator library libosd.ko");
-MODULE_LICENSE("GPL");
-
-static inline void build_test(void)
-{
- /* structures were not packed */
- BUILD_BUG_ON(sizeof(struct osd_capability) != OSD_CAP_LEN);
- BUILD_BUG_ON(sizeof(struct osdv2_cdb) != OSD_TOTAL_CDB_LEN);
- BUILD_BUG_ON(sizeof(struct osdv1_cdb) != OSDv1_TOTAL_CDB_LEN);
-}
-
-static const char *_osd_ver_desc(struct osd_request *or)
-{
- return osd_req_is_ver1(or) ? "OSD1" : "OSD2";
-}
-
-#define ATTR_DEF_RI(id, len) ATTR_DEF(OSD_APAGE_ROOT_INFORMATION, id, len)
-
-static int _osd_get_print_system_info(struct osd_dev *od,
- void *caps, struct osd_dev_info *odi)
-{
- struct osd_request *or;
- struct osd_attr get_attrs[] = {
- ATTR_DEF_RI(OSD_ATTR_RI_VENDOR_IDENTIFICATION, 8),
- ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_IDENTIFICATION, 16),
- ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_MODEL, 32),
- ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_REVISION_LEVEL, 4),
- ATTR_DEF_RI(OSD_ATTR_RI_PRODUCT_SERIAL_NUMBER, 64 /*variable*/),
- ATTR_DEF_RI(OSD_ATTR_RI_OSD_NAME, 64 /*variable*/),
- ATTR_DEF_RI(OSD_ATTR_RI_TOTAL_CAPACITY, 8),
- ATTR_DEF_RI(OSD_ATTR_RI_USED_CAPACITY, 8),
- ATTR_DEF_RI(OSD_ATTR_RI_NUMBER_OF_PARTITIONS, 8),
- ATTR_DEF_RI(OSD_ATTR_RI_CLOCK, 6),
- /* IBM-OSD-SIM Has a bug with this one put it last */
- ATTR_DEF_RI(OSD_ATTR_RI_OSD_SYSTEM_ID, 20),
- };
- void *iter = NULL, *pFirst;
- int nelem = ARRAY_SIZE(get_attrs), a = 0;
- int ret;
-
- or = osd_start_request(od, GFP_KERNEL);
- if (!or)
- return -ENOMEM;
-
- /* get attrs */
- osd_req_get_attributes(or, &osd_root_object);
- osd_req_add_get_attr_list(or, get_attrs, ARRAY_SIZE(get_attrs));
-
- ret = osd_finalize_request(or, 0, caps, NULL);
- if (ret)
- goto out;
-
- ret = osd_execute_request(or);
- if (ret) {
- OSD_ERR("Failed to detect %s => %d\n", _osd_ver_desc(or), ret);
- goto out;
- }
-
- osd_req_decode_get_attr_list(or, get_attrs, &nelem, &iter);
-
- OSD_INFO("Detected %s device\n",
- _osd_ver_desc(or));
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("VENDOR_IDENTIFICATION [%s]\n",
- (char *)pFirst);
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("PRODUCT_IDENTIFICATION [%s]\n",
- (char *)pFirst);
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("PRODUCT_MODEL [%s]\n",
- (char *)pFirst);
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("PRODUCT_REVISION_LEVEL [%u]\n",
- pFirst ? get_unaligned_be32(pFirst) : ~0U);
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("PRODUCT_SERIAL_NUMBER [%s]\n",
- (char *)pFirst);
-
- odi->osdname_len = get_attrs[a].len;
- /* Avoid NULL for memcmp optimization 0-length is good enough */
- odi->osdname = kzalloc(odi->osdname_len + 1, GFP_KERNEL);
- if (!odi->osdname) {
- ret = -ENOMEM;
- goto out;
- }
- if (odi->osdname_len)
- memcpy(odi->osdname, get_attrs[a].val_ptr, odi->osdname_len);
- OSD_INFO("OSD_NAME [%s]\n", odi->osdname);
- a++;
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("TOTAL_CAPACITY [0x%llx]\n",
- pFirst ? _LLU(get_unaligned_be64(pFirst)) : ~0ULL);
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("USED_CAPACITY [0x%llx]\n",
- pFirst ? _LLU(get_unaligned_be64(pFirst)) : ~0ULL);
-
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("NUMBER_OF_PARTITIONS [%llu]\n",
- pFirst ? _LLU(get_unaligned_be64(pFirst)) : ~0ULL);
-
- if (a >= nelem)
- goto out;
-
- /* FIXME: Where are the time utilities */
- pFirst = get_attrs[a++].val_ptr;
- OSD_INFO("CLOCK [0x%6phN]\n", pFirst);
-
- if (a < nelem) { /* IBM-OSD-SIM bug, Might not have it */
- unsigned len = get_attrs[a].len;
- char sid_dump[32*4 + 2]; /* 2nibbles+space+ASCII */
-
- hex_dump_to_buffer(get_attrs[a].val_ptr, len, 32, 1,
- sid_dump, sizeof(sid_dump), true);
- OSD_INFO("OSD_SYSTEM_ID(%d)\n"
- " [%s]\n", len, sid_dump);
-
- if (unlikely(len > sizeof(odi->systemid))) {
- OSD_ERR("OSD Target error: OSD_SYSTEM_ID too long(%d). "
- "device identification might not work\n", len);
- len = sizeof(odi->systemid);
- }
- odi->systemid_len = len;
- memcpy(odi->systemid, get_attrs[a].val_ptr, len);
- a++;
- }
-out:
- osd_end_request(or);
- return ret;
-}
-
-int osd_auto_detect_ver(struct osd_dev *od,
- void *caps, struct osd_dev_info *odi)
-{
- int ret;
-
- /* Auto-detect the osd version */
- ret = _osd_get_print_system_info(od, caps, odi);
- if (ret) {
- osd_dev_set_ver(od, OSD_VER1);
- OSD_DEBUG("converting to OSD1\n");
- ret = _osd_get_print_system_info(od, caps, odi);
- }
-
- return ret;
-}
-EXPORT_SYMBOL(osd_auto_detect_ver);
-
-static unsigned _osd_req_cdb_len(struct osd_request *or)
-{
- return osd_req_is_ver1(or) ? OSDv1_TOTAL_CDB_LEN : OSD_TOTAL_CDB_LEN;
-}
-
-static unsigned _osd_req_alist_elem_size(struct osd_request *or, unsigned len)
-{
- return osd_req_is_ver1(or) ?
- osdv1_attr_list_elem_size(len) :
- osdv2_attr_list_elem_size(len);
-}
-
-static void _osd_req_alist_elem_encode(struct osd_request *or,
- void *attr_last, const struct osd_attr *oa)
-{
- if (osd_req_is_ver1(or)) {
- struct osdv1_attributes_list_element *attr = attr_last;
-
- attr->attr_page = cpu_to_be32(oa->attr_page);
- attr->attr_id = cpu_to_be32(oa->attr_id);
- attr->attr_bytes = cpu_to_be16(oa->len);
- memcpy(attr->attr_val, oa->val_ptr, oa->len);
- } else {
- struct osdv2_attributes_list_element *attr = attr_last;
-
- attr->attr_page = cpu_to_be32(oa->attr_page);
- attr->attr_id = cpu_to_be32(oa->attr_id);
- attr->attr_bytes = cpu_to_be16(oa->len);
- memcpy(attr->attr_val, oa->val_ptr, oa->len);
- }
-}
-
-static int _osd_req_alist_elem_decode(struct osd_request *or,
- void *cur_p, struct osd_attr *oa, unsigned max_bytes)
-{
- unsigned inc;
- if (osd_req_is_ver1(or)) {
- struct osdv1_attributes_list_element *attr = cur_p;
-
- if (max_bytes < sizeof(*attr))
- return -1;
-
- oa->len = be16_to_cpu(attr->attr_bytes);
- inc = _osd_req_alist_elem_size(or, oa->len);
- if (inc > max_bytes)
- return -1;
-
- oa->attr_page = be32_to_cpu(attr->attr_page);
- oa->attr_id = be32_to_cpu(attr->attr_id);
-
- /* OSD1: On empty attributes we return a pointer to 2 bytes
- * of zeros. This keeps similar behaviour with OSD2.
- * (See below)
- */
- oa->val_ptr = likely(oa->len) ? attr->attr_val :
- (u8 *)&attr->attr_bytes;
- } else {
- struct osdv2_attributes_list_element *attr = cur_p;
-
- if (max_bytes < sizeof(*attr))
- return -1;
-
- oa->len = be16_to_cpu(attr->attr_bytes);
- inc = _osd_req_alist_elem_size(or, oa->len);
- if (inc > max_bytes)
- return -1;
-
- oa->attr_page = be32_to_cpu(attr->attr_page);
- oa->attr_id = be32_to_cpu(attr->attr_id);
-
- /* OSD2: For convenience, on empty attributes, we return 8 bytes
- * of zeros here. This keeps the same behaviour with OSD2r04,
- * and is nice with null terminating ASCII fields.
- * oa->val_ptr == NULL marks the end-of-list, or error.
- */
- oa->val_ptr = likely(oa->len) ? attr->attr_val : attr->reserved;
- }
- return inc;
-}
-
-static unsigned _osd_req_alist_size(struct osd_request *or, void *list_head)
-{
- return osd_req_is_ver1(or) ?
- osdv1_list_size(list_head) :
- osdv2_list_size(list_head);
-}
-
-static unsigned _osd_req_sizeof_alist_header(struct osd_request *or)
-{
- return osd_req_is_ver1(or) ?
- sizeof(struct osdv1_attributes_list_header) :
- sizeof(struct osdv2_attributes_list_header);
-}
-
-static void _osd_req_set_alist_type(struct osd_request *or,
- void *list, int list_type)
-{
- if (osd_req_is_ver1(or)) {
- struct osdv1_attributes_list_header *attr_list = list;
-
- memset(attr_list, 0, sizeof(*attr_list));
- attr_list->type = list_type;
- } else {
- struct osdv2_attributes_list_header *attr_list = list;
-
- memset(attr_list, 0, sizeof(*attr_list));
- attr_list->type = list_type;
- }
-}
-
-static bool _osd_req_is_alist_type(struct osd_request *or,
- void *list, int list_type)
-{
- if (!list)
- return false;
-
- if (osd_req_is_ver1(or)) {
- struct osdv1_attributes_list_header *attr_list = list;
-
- return attr_list->type == list_type;
- } else {
- struct osdv2_attributes_list_header *attr_list = list;
-
- return attr_list->type == list_type;
- }
-}
-
-/* This is for List-objects not Attributes-Lists */
-static void _osd_req_encode_olist(struct osd_request *or,
- struct osd_obj_id_list *list)
-{
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
-
- if (osd_req_is_ver1(or)) {
- cdbh->v1.list_identifier = list->list_identifier;
- cdbh->v1.start_address = list->continuation_id;
- } else {
- cdbh->v2.list_identifier = list->list_identifier;
- cdbh->v2.start_address = list->continuation_id;
- }
-}
-
-static osd_cdb_offset osd_req_encode_offset(struct osd_request *or,
- u64 offset, unsigned *padding)
-{
- return __osd_encode_offset(offset, padding,
- osd_req_is_ver1(or) ?
- OSDv1_OFFSET_MIN_SHIFT : OSD_OFFSET_MIN_SHIFT,
- OSD_OFFSET_MAX_SHIFT);
-}
-
-static struct osd_security_parameters *
-_osd_req_sec_params(struct osd_request *or)
-{
- struct osd_cdb *ocdb = &or->cdb;
-
- if (osd_req_is_ver1(or))
- return (struct osd_security_parameters *)&ocdb->v1.sec_params;
- else
- return (struct osd_security_parameters *)&ocdb->v2.sec_params;
-}
-
-void osd_dev_init(struct osd_dev *osdd, struct scsi_device *scsi_device)
-{
- memset(osdd, 0, sizeof(*osdd));
- osdd->scsi_device = scsi_device;
- osdd->def_timeout = BLK_DEFAULT_SG_TIMEOUT;
-#ifdef OSD_VER1_SUPPORT
- osdd->version = OSD_VER2;
-#endif
- /* TODO: Allocate pools for osd_request attributes ... */
-}
-EXPORT_SYMBOL(osd_dev_init);
-
-void osd_dev_fini(struct osd_dev *osdd)
-{
- /* TODO: De-allocate pools */
-
- osdd->scsi_device = NULL;
-}
-EXPORT_SYMBOL(osd_dev_fini);
-
-static struct osd_request *_osd_request_alloc(gfp_t gfp)
-{
- struct osd_request *or;
-
- /* TODO: Use mempool with one saved request */
- or = kzalloc(sizeof(*or), gfp);
- return or;
-}
-
-static void _osd_request_free(struct osd_request *or)
-{
- kfree(or);
-}
-
-struct osd_request *osd_start_request(struct osd_dev *dev, gfp_t gfp)
-{
- struct osd_request *or;
-
- or = _osd_request_alloc(gfp);
- if (!or)
- return NULL;
-
- or->osd_dev = dev;
- or->alloc_flags = gfp;
- or->timeout = dev->def_timeout;
- or->retries = OSD_REQ_RETRIES;
-
- return or;
-}
-EXPORT_SYMBOL(osd_start_request);
-
-static void _osd_free_seg(struct osd_request *or __unused,
- struct _osd_req_data_segment *seg)
-{
- if (!seg->buff || !seg->alloc_size)
- return;
-
- kfree(seg->buff);
- seg->buff = NULL;
- seg->alloc_size = 0;
-}
-
-static void _put_request(struct request *rq)
-{
- /*
- * If osd_finalize_request() was called but the request was not
- * executed through the block layer, then we must release BIOs.
- * TODO: Keep error code in or->async_error. Need to audit all
- * code paths.
- */
- if (unlikely(rq->bio))
- blk_end_request(rq, -ENOMEM, blk_rq_bytes(rq));
- else
- blk_put_request(rq);
-}
-
-void osd_end_request(struct osd_request *or)
-{
- struct request *rq = or->request;
-
- if (rq) {
- if (rq->next_rq) {
- _put_request(rq->next_rq);
- rq->next_rq = NULL;
- }
-
- _put_request(rq);
- }
-
- _osd_free_seg(or, &or->get_attr);
- _osd_free_seg(or, &or->enc_get_attr);
- _osd_free_seg(or, &or->set_attr);
- _osd_free_seg(or, &or->cdb_cont);
-
- _osd_request_free(or);
-}
-EXPORT_SYMBOL(osd_end_request);
-
-static void _set_error_resid(struct osd_request *or, struct request *req,
- int error)
-{
- or->async_error = error;
- or->req_errors = req->errors ? : error;
- or->sense_len = scsi_req(req)->sense_len;
- if (or->sense_len)
- memcpy(or->sense, scsi_req(req)->sense, or->sense_len);
- if (or->out.req)
- or->out.residual = scsi_req(or->out.req)->resid_len;
- if (or->in.req)
- or->in.residual = scsi_req(or->in.req)->resid_len;
-}
-
-int osd_execute_request(struct osd_request *or)
-{
- int error = blk_execute_rq(or->request->q, NULL, or->request, 0);
-
- _set_error_resid(or, or->request, error);
- return error;
-}
-EXPORT_SYMBOL(osd_execute_request);
-
-static void osd_request_async_done(struct request *req, int error)
-{
- struct osd_request *or = req->end_io_data;
-
- _set_error_resid(or, req, error);
- if (req->next_rq) {
- __blk_put_request(req->q, req->next_rq);
- req->next_rq = NULL;
- }
-
- __blk_put_request(req->q, req);
- or->request = NULL;
- or->in.req = NULL;
- or->out.req = NULL;
-
- if (or->async_done)
- or->async_done(or, or->async_private);
- else
- osd_end_request(or);
-}
-
-int osd_execute_request_async(struct osd_request *or,
- osd_req_done_fn *done, void *private)
-{
- or->request->end_io_data = or;
- or->async_private = private;
- or->async_done = done;
-
- blk_execute_rq_nowait(or->request->q, NULL, or->request, 0,
- osd_request_async_done);
- return 0;
-}
-EXPORT_SYMBOL(osd_execute_request_async);
-
-u8 sg_out_pad_buffer[1 << OSDv1_OFFSET_MIN_SHIFT];
-u8 sg_in_pad_buffer[1 << OSDv1_OFFSET_MIN_SHIFT];
-
-static int _osd_realloc_seg(struct osd_request *or,
- struct _osd_req_data_segment *seg, unsigned max_bytes)
-{
- void *buff;
-
- if (seg->alloc_size >= max_bytes)
- return 0;
-
- buff = krealloc(seg->buff, max_bytes, or->alloc_flags);
- if (!buff) {
- OSD_ERR("Failed to Realloc %d-bytes was-%d\n", max_bytes,
- seg->alloc_size);
- return -ENOMEM;
- }
-
- memset(buff + seg->alloc_size, 0, max_bytes - seg->alloc_size);
- seg->buff = buff;
- seg->alloc_size = max_bytes;
- return 0;
-}
-
-static int _alloc_cdb_cont(struct osd_request *or, unsigned total_bytes)
-{
- OSD_DEBUG("total_bytes=%d\n", total_bytes);
- return _osd_realloc_seg(or, &or->cdb_cont, total_bytes);
-}
-
-static int _alloc_set_attr_list(struct osd_request *or,
- const struct osd_attr *oa, unsigned nelem, unsigned add_bytes)
-{
- unsigned total_bytes = add_bytes;
-
- for (; nelem; --nelem, ++oa)
- total_bytes += _osd_req_alist_elem_size(or, oa->len);
-
- OSD_DEBUG("total_bytes=%d\n", total_bytes);
- return _osd_realloc_seg(or, &or->set_attr, total_bytes);
-}
-
-static int _alloc_get_attr_desc(struct osd_request *or, unsigned max_bytes)
-{
- OSD_DEBUG("total_bytes=%d\n", max_bytes);
- return _osd_realloc_seg(or, &or->enc_get_attr, max_bytes);
-}
-
-static int _alloc_get_attr_list(struct osd_request *or)
-{
- OSD_DEBUG("total_bytes=%d\n", or->get_attr.total_bytes);
- return _osd_realloc_seg(or, &or->get_attr, or->get_attr.total_bytes);
-}
-
-/*
- * Common to all OSD commands
- */
-
-static void _osdv1_req_encode_common(struct osd_request *or,
- __be16 act, const struct osd_obj_id *obj, u64 offset, u64 len)
-{
- struct osdv1_cdb *ocdb = &or->cdb.v1;
-
- /*
- * For speed, the commands
- * OSD_ACT_PERFORM_SCSI_COMMAND , V1 0x8F7E, V2 0x8F7C
- * OSD_ACT_SCSI_TASK_MANAGEMENT , V1 0x8F7F, V2 0x8F7D
- * are not supported here. Should pass zero and set after the call
- */
- act &= cpu_to_be16(~0x0080); /* V1 action code */
-
- OSD_DEBUG("OSDv1 execute opcode 0x%x\n", be16_to_cpu(act));
-
- ocdb->h.varlen_cdb.opcode = VARIABLE_LENGTH_CMD;
- ocdb->h.varlen_cdb.additional_cdb_length = OSD_ADDITIONAL_CDB_LENGTH;
- ocdb->h.varlen_cdb.service_action = act;
-
- ocdb->h.partition = cpu_to_be64(obj->partition);
- ocdb->h.object = cpu_to_be64(obj->id);
- ocdb->h.v1.length = cpu_to_be64(len);
- ocdb->h.v1.start_address = cpu_to_be64(offset);
-}
-
-static void _osdv2_req_encode_common(struct osd_request *or,
- __be16 act, const struct osd_obj_id *obj, u64 offset, u64 len)
-{
- struct osdv2_cdb *ocdb = &or->cdb.v2;
-
- OSD_DEBUG("OSDv2 execute opcode 0x%x\n", be16_to_cpu(act));
-
- ocdb->h.varlen_cdb.opcode = VARIABLE_LENGTH_CMD;
- ocdb->h.varlen_cdb.additional_cdb_length = OSD_ADDITIONAL_CDB_LENGTH;
- ocdb->h.varlen_cdb.service_action = act;
-
- ocdb->h.partition = cpu_to_be64(obj->partition);
- ocdb->h.object = cpu_to_be64(obj->id);
- ocdb->h.v2.length = cpu_to_be64(len);
- ocdb->h.v2.start_address = cpu_to_be64(offset);
-}
-
-static void _osd_req_encode_common(struct osd_request *or,
- __be16 act, const struct osd_obj_id *obj, u64 offset, u64 len)
-{
- if (osd_req_is_ver1(or))
- _osdv1_req_encode_common(or, act, obj, offset, len);
- else
- _osdv2_req_encode_common(or, act, obj, offset, len);
-}
-
-/*
- * Device commands
- */
-/*TODO: void osd_req_set_master_seed_xchg(struct osd_request *, ...); */
-/*TODO: void osd_req_set_master_key(struct osd_request *, ...); */
-
-void osd_req_format(struct osd_request *or, u64 tot_capacity)
-{
- _osd_req_encode_common(or, OSD_ACT_FORMAT_OSD, &osd_root_object, 0,
- tot_capacity);
-}
-EXPORT_SYMBOL(osd_req_format);
-
-int osd_req_list_dev_partitions(struct osd_request *or,
- osd_id initial_id, struct osd_obj_id_list *list, unsigned nelem)
-{
- return osd_req_list_partition_objects(or, 0, initial_id, list, nelem);
-}
-EXPORT_SYMBOL(osd_req_list_dev_partitions);
-
-static void _osd_req_encode_flush(struct osd_request *or,
- enum osd_options_flush_scope_values op)
-{
- struct osd_cdb_head *ocdb = osd_cdb_head(&or->cdb);
-
- ocdb->command_specific_options = op;
-}
-
-void osd_req_flush_obsd(struct osd_request *or,
- enum osd_options_flush_scope_values op)
-{
- _osd_req_encode_common(or, OSD_ACT_FLUSH_OSD, &osd_root_object, 0, 0);
- _osd_req_encode_flush(or, op);
-}
-EXPORT_SYMBOL(osd_req_flush_obsd);
-
-/*TODO: void osd_req_perform_scsi_command(struct osd_request *,
- const u8 *cdb, ...); */
-/*TODO: void osd_req_task_management(struct osd_request *, ...); */
-
-/*
- * Partition commands
- */
-static void _osd_req_encode_partition(struct osd_request *or,
- __be16 act, osd_id partition)
-{
- struct osd_obj_id par = {
- .partition = partition,
- .id = 0,
- };
-
- _osd_req_encode_common(or, act, &par, 0, 0);
-}
-
-void osd_req_create_partition(struct osd_request *or, osd_id partition)
-{
- _osd_req_encode_partition(or, OSD_ACT_CREATE_PARTITION, partition);
-}
-EXPORT_SYMBOL(osd_req_create_partition);
-
-void osd_req_remove_partition(struct osd_request *or, osd_id partition)
-{
- _osd_req_encode_partition(or, OSD_ACT_REMOVE_PARTITION, partition);
-}
-EXPORT_SYMBOL(osd_req_remove_partition);
-
-/*TODO: void osd_req_set_partition_key(struct osd_request *,
- osd_id partition, u8 new_key_id[OSD_CRYPTO_KEYID_SIZE],
- u8 seed[OSD_CRYPTO_SEED_SIZE]); */
-
-static int _osd_req_list_objects(struct osd_request *or,
- __be16 action, const struct osd_obj_id *obj, osd_id initial_id,
- struct osd_obj_id_list *list, unsigned nelem)
-{
- struct request_queue *q = osd_request_queue(or->osd_dev);
- u64 len = nelem * sizeof(osd_id) + sizeof(*list);
- struct bio *bio;
-
- _osd_req_encode_common(or, action, obj, (u64)initial_id, len);
-
- if (list->list_identifier)
- _osd_req_encode_olist(or, list);
-
- WARN_ON(or->in.bio);
- bio = bio_map_kern(q, list, len, or->alloc_flags);
- if (IS_ERR(bio)) {
- OSD_ERR("!!! Failed to allocate list_objects BIO\n");
- return PTR_ERR(bio);
- }
-
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
- or->in.bio = bio;
- or->in.total_bytes = bio->bi_iter.bi_size;
- return 0;
-}
-
-int osd_req_list_partition_collections(struct osd_request *or,
- osd_id partition, osd_id initial_id, struct osd_obj_id_list *list,
- unsigned nelem)
-{
- struct osd_obj_id par = {
- .partition = partition,
- .id = 0,
- };
-
- return osd_req_list_collection_objects(or, &par, initial_id, list,
- nelem);
-}
-EXPORT_SYMBOL(osd_req_list_partition_collections);
-
-int osd_req_list_partition_objects(struct osd_request *or,
- osd_id partition, osd_id initial_id, struct osd_obj_id_list *list,
- unsigned nelem)
-{
- struct osd_obj_id par = {
- .partition = partition,
- .id = 0,
- };
-
- return _osd_req_list_objects(or, OSD_ACT_LIST, &par, initial_id, list,
- nelem);
-}
-EXPORT_SYMBOL(osd_req_list_partition_objects);
-
-void osd_req_flush_partition(struct osd_request *or,
- osd_id partition, enum osd_options_flush_scope_values op)
-{
- _osd_req_encode_partition(or, OSD_ACT_FLUSH_PARTITION, partition);
- _osd_req_encode_flush(or, op);
-}
-EXPORT_SYMBOL(osd_req_flush_partition);
-
-/*
- * Collection commands
- */
-/*TODO: void osd_req_create_collection(struct osd_request *,
- const struct osd_obj_id *); */
-/*TODO: void osd_req_remove_collection(struct osd_request *,
- const struct osd_obj_id *); */
-
-int osd_req_list_collection_objects(struct osd_request *or,
- const struct osd_obj_id *obj, osd_id initial_id,
- struct osd_obj_id_list *list, unsigned nelem)
-{
- return _osd_req_list_objects(or, OSD_ACT_LIST_COLLECTION, obj,
- initial_id, list, nelem);
-}
-EXPORT_SYMBOL(osd_req_list_collection_objects);
-
-/*TODO: void query(struct osd_request *, ...); V2 */
-
-void osd_req_flush_collection(struct osd_request *or,
- const struct osd_obj_id *obj, enum osd_options_flush_scope_values op)
-{
- _osd_req_encode_common(or, OSD_ACT_FLUSH_PARTITION, obj, 0, 0);
- _osd_req_encode_flush(or, op);
-}
-EXPORT_SYMBOL(osd_req_flush_collection);
-
-/*TODO: void get_member_attrs(struct osd_request *, ...); V2 */
-/*TODO: void set_member_attrs(struct osd_request *, ...); V2 */
-
-/*
- * Object commands
- */
-void osd_req_create_object(struct osd_request *or, struct osd_obj_id *obj)
-{
- _osd_req_encode_common(or, OSD_ACT_CREATE, obj, 0, 0);
-}
-EXPORT_SYMBOL(osd_req_create_object);
-
-void osd_req_remove_object(struct osd_request *or, struct osd_obj_id *obj)
-{
- _osd_req_encode_common(or, OSD_ACT_REMOVE, obj, 0, 0);
-}
-EXPORT_SYMBOL(osd_req_remove_object);
-
-
-/*TODO: void osd_req_create_multi(struct osd_request *or,
- struct osd_obj_id *first, struct osd_obj_id_list *list, unsigned nelem);
-*/
-
-void osd_req_write(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset,
- struct bio *bio, u64 len)
-{
- _osd_req_encode_common(or, OSD_ACT_WRITE, obj, offset, len);
- WARN_ON(or->out.bio || or->out.total_bytes);
- WARN_ON(!op_is_write(bio_op(bio)));
- or->out.bio = bio;
- or->out.total_bytes = len;
-}
-EXPORT_SYMBOL(osd_req_write);
-
-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 = osd_request_queue(or->osd_dev);
- struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
-
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- osd_req_write(or, obj, offset, bio, len);
- return 0;
-}
-EXPORT_SYMBOL(osd_req_write_kern);
-
-/*TODO: void osd_req_append(struct osd_request *,
- const struct osd_obj_id *, struct bio *data_out); */
-/*TODO: void osd_req_create_write(struct osd_request *,
- const struct osd_obj_id *, struct bio *data_out, u64 offset); */
-/*TODO: void osd_req_clear(struct osd_request *,
- const struct osd_obj_id *, u64 offset, u64 len); */
-/*TODO: void osd_req_punch(struct osd_request *,
- const struct osd_obj_id *, u64 offset, u64 len); V2 */
-
-void osd_req_flush_object(struct osd_request *or,
- const struct osd_obj_id *obj, enum osd_options_flush_scope_values op,
- /*V2*/ u64 offset, /*V2*/ u64 len)
-{
- if (unlikely(osd_req_is_ver1(or) && (offset || len))) {
- OSD_DEBUG("OSD Ver1 flush on specific range ignored\n");
- offset = 0;
- len = 0;
- }
-
- _osd_req_encode_common(or, OSD_ACT_FLUSH, obj, offset, len);
- _osd_req_encode_flush(or, op);
-}
-EXPORT_SYMBOL(osd_req_flush_object);
-
-void osd_req_read(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset,
- struct bio *bio, u64 len)
-{
- _osd_req_encode_common(or, OSD_ACT_READ, obj, offset, len);
- WARN_ON(or->in.bio || or->in.total_bytes);
- WARN_ON(op_is_write(bio_op(bio)));
- or->in.bio = bio;
- or->in.total_bytes = len;
-}
-EXPORT_SYMBOL(osd_req_read);
-
-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 = osd_request_queue(or->osd_dev);
- struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
-
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- osd_req_read(or, obj, offset, bio, len);
- return 0;
-}
-EXPORT_SYMBOL(osd_req_read_kern);
-
-static int _add_sg_continuation_descriptor(struct osd_request *or,
- const struct osd_sg_entry *sglist, unsigned numentries, u64 *len)
-{
- struct osd_sg_continuation_descriptor *oscd;
- u32 oscd_size;
- unsigned i;
- int ret;
-
- oscd_size = sizeof(*oscd) + numentries * sizeof(oscd->entries[0]);
-
- if (!or->cdb_cont.total_bytes) {
- /* First time, jump over the header, we will write to:
- * cdb_cont.buff + cdb_cont.total_bytes
- */
- or->cdb_cont.total_bytes =
- sizeof(struct osd_continuation_segment_header);
- }
-
- ret = _alloc_cdb_cont(or, or->cdb_cont.total_bytes + oscd_size);
- if (unlikely(ret))
- return ret;
-
- oscd = or->cdb_cont.buff + or->cdb_cont.total_bytes;
- oscd->hdr.type = cpu_to_be16(SCATTER_GATHER_LIST);
- oscd->hdr.pad_length = 0;
- oscd->hdr.length = cpu_to_be32(oscd_size - sizeof(*oscd));
-
- *len = 0;
- /* copy the sg entries and convert to network byte order */
- for (i = 0; i < numentries; i++) {
- oscd->entries[i].offset = cpu_to_be64(sglist[i].offset);
- oscd->entries[i].len = cpu_to_be64(sglist[i].len);
- *len += sglist[i].len;
- }
-
- or->cdb_cont.total_bytes += oscd_size;
- OSD_DEBUG("total_bytes=%d oscd_size=%d numentries=%d\n",
- or->cdb_cont.total_bytes, oscd_size, numentries);
- return 0;
-}
-
-static int _osd_req_finalize_cdb_cont(struct osd_request *or, const u8 *cap_key)
-{
- struct request_queue *req_q = osd_request_queue(or->osd_dev);
- struct bio *bio;
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
- struct osd_continuation_segment_header *cont_seg_hdr;
-
- if (!or->cdb_cont.total_bytes)
- return 0;
-
- cont_seg_hdr = or->cdb_cont.buff;
- cont_seg_hdr->format = CDB_CONTINUATION_FORMAT_V2;
- cont_seg_hdr->service_action = cdbh->varlen_cdb.service_action;
-
- /* create a bio for continuation segment */
- bio = bio_map_kern(req_q, or->cdb_cont.buff, or->cdb_cont.total_bytes,
- GFP_KERNEL);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
- /* integrity check the continuation before the bio is linked
- * with the other data segments since the continuation
- * integrity is separate from the other data segments.
- */
- osd_sec_sign_data(cont_seg_hdr->integrity_check, bio, cap_key);
-
- cdbh->v2.cdb_continuation_length = cpu_to_be32(or->cdb_cont.total_bytes);
-
- /* we can't use _req_append_segment, because we need to link in the
- * continuation bio to the head of the bio list - the
- * continuation segment (if it exists) is always the first segment in
- * the out data buffer.
- */
- bio->bi_next = or->out.bio;
- or->out.bio = bio;
- or->out.total_bytes += or->cdb_cont.total_bytes;
-
- return 0;
-}
-
-/* osd_req_write_sg: Takes a @bio that points to the data out buffer and an
- * @sglist that has the scatter gather entries. Scatter-gather enables a write
- * of multiple none-contiguous areas of an object, in a single call. The extents
- * may overlap and/or be in any order. The only constrain is that:
- * total_bytes(sglist) >= total_bytes(bio)
- */
-int osd_req_write_sg(struct osd_request *or,
- const struct osd_obj_id *obj, struct bio *bio,
- const struct osd_sg_entry *sglist, unsigned numentries)
-{
- u64 len;
- int ret = _add_sg_continuation_descriptor(or, sglist, numentries, &len);
-
- if (ret)
- return ret;
- osd_req_write(or, obj, 0, bio, len);
-
- return 0;
-}
-EXPORT_SYMBOL(osd_req_write_sg);
-
-/* osd_req_read_sg: Read multiple extents of an object into @bio
- * See osd_req_write_sg
- */
-int osd_req_read_sg(struct osd_request *or,
- const struct osd_obj_id *obj, struct bio *bio,
- const struct osd_sg_entry *sglist, unsigned numentries)
-{
- u64 len;
- u64 off;
- int ret;
-
- if (numentries > 1) {
- off = 0;
- ret = _add_sg_continuation_descriptor(or, sglist, numentries,
- &len);
- if (ret)
- return ret;
- } else {
- /* Optimize the case of single segment, read_sg is a
- * bidi operation.
- */
- len = sglist->len;
- off = sglist->offset;
- }
- osd_req_read(or, obj, off, bio, len);
-
- return 0;
-}
-EXPORT_SYMBOL(osd_req_read_sg);
-
-/* SG-list write/read Kern API
- *
- * osd_req_{write,read}_sg_kern takes an array of @buff pointers and an array
- * of sg_entries. @numentries indicates how many pointers and sg_entries there
- * are. By requiring an array of buff pointers. This allows a caller to do a
- * single write/read and scatter into multiple buffers.
- * NOTE: Each buffer + len should not cross a page boundary.
- */
-static struct bio *_create_sg_bios(struct osd_request *or,
- void **buff, const struct osd_sg_entry *sglist, unsigned numentries)
-{
- struct request_queue *q = osd_request_queue(or->osd_dev);
- struct bio *bio;
- unsigned i;
-
- bio = bio_kmalloc(GFP_KERNEL, numentries);
- if (unlikely(!bio)) {
- OSD_DEBUG("Failed to allocate BIO size=%u\n", numentries);
- return ERR_PTR(-ENOMEM);
- }
-
- for (i = 0; i < numentries; i++) {
- unsigned offset = offset_in_page(buff[i]);
- struct page *page = virt_to_page(buff[i]);
- unsigned len = sglist[i].len;
- unsigned added_len;
-
- BUG_ON(offset + len > PAGE_SIZE);
- added_len = bio_add_pc_page(q, bio, page, len, offset);
- if (unlikely(len != added_len)) {
- OSD_DEBUG("bio_add_pc_page len(%d) != added_len(%d)\n",
- len, added_len);
- bio_put(bio);
- return ERR_PTR(-ENOMEM);
- }
- }
-
- return bio;
-}
-
-int osd_req_write_sg_kern(struct osd_request *or,
- const struct osd_obj_id *obj, void **buff,
- const struct osd_sg_entry *sglist, unsigned numentries)
-{
- struct bio *bio = _create_sg_bios(or, buff, sglist, numentries);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- osd_req_write_sg(or, obj, bio, sglist, numentries);
-
- return 0;
-}
-EXPORT_SYMBOL(osd_req_write_sg_kern);
-
-int osd_req_read_sg_kern(struct osd_request *or,
- const struct osd_obj_id *obj, void **buff,
- const struct osd_sg_entry *sglist, unsigned numentries)
-{
- struct bio *bio = _create_sg_bios(or, buff, sglist, numentries);
- if (IS_ERR(bio))
- return PTR_ERR(bio);
-
- osd_req_read_sg(or, obj, bio, sglist, numentries);
-
- return 0;
-}
-EXPORT_SYMBOL(osd_req_read_sg_kern);
-
-
-
-void osd_req_get_attributes(struct osd_request *or,
- const struct osd_obj_id *obj)
-{
- _osd_req_encode_common(or, OSD_ACT_GET_ATTRIBUTES, obj, 0, 0);
-}
-EXPORT_SYMBOL(osd_req_get_attributes);
-
-void osd_req_set_attributes(struct osd_request *or,
- const struct osd_obj_id *obj)
-{
- _osd_req_encode_common(or, OSD_ACT_SET_ATTRIBUTES, obj, 0, 0);
-}
-EXPORT_SYMBOL(osd_req_set_attributes);
-
-/*
- * Attributes List-mode
- */
-
-int osd_req_add_set_attr_list(struct osd_request *or,
- const struct osd_attr *oa, unsigned nelem)
-{
- unsigned total_bytes = or->set_attr.total_bytes;
- void *attr_last;
- int ret;
-
- if (or->attributes_mode &&
- or->attributes_mode != OSD_CDB_GET_SET_ATTR_LISTS) {
- WARN_ON(1);
- return -EINVAL;
- }
- or->attributes_mode = OSD_CDB_GET_SET_ATTR_LISTS;
-
- if (!total_bytes) { /* first-time: allocate and put list header */
- total_bytes = _osd_req_sizeof_alist_header(or);
- ret = _alloc_set_attr_list(or, oa, nelem, total_bytes);
- if (ret)
- return ret;
- _osd_req_set_alist_type(or, or->set_attr.buff,
- OSD_ATTR_LIST_SET_RETRIEVE);
- }
- attr_last = or->set_attr.buff + total_bytes;
-
- for (; nelem; --nelem) {
- unsigned elem_size = _osd_req_alist_elem_size(or, oa->len);
-
- total_bytes += elem_size;
- if (unlikely(or->set_attr.alloc_size < total_bytes)) {
- or->set_attr.total_bytes = total_bytes - elem_size;
- ret = _alloc_set_attr_list(or, oa, nelem, total_bytes);
- if (ret)
- return ret;
- attr_last =
- or->set_attr.buff + or->set_attr.total_bytes;
- }
-
- _osd_req_alist_elem_encode(or, attr_last, oa);
-
- attr_last += elem_size;
- ++oa;
- }
-
- or->set_attr.total_bytes = total_bytes;
- return 0;
-}
-EXPORT_SYMBOL(osd_req_add_set_attr_list);
-
-static int _req_append_segment(struct osd_request *or,
- unsigned padding, struct _osd_req_data_segment *seg,
- struct _osd_req_data_segment *last_seg, struct _osd_io_info *io)
-{
- void *pad_buff;
- int ret;
-
- if (padding) {
- /* check if we can just add it to last buffer */
- if (last_seg &&
- (padding <= last_seg->alloc_size - last_seg->total_bytes))
- pad_buff = last_seg->buff + last_seg->total_bytes;
- else
- pad_buff = io->pad_buff;
-
- ret = blk_rq_map_kern(io->req->q, io->req, pad_buff, padding,
- or->alloc_flags);
- if (ret)
- return ret;
- io->total_bytes += padding;
- }
-
- ret = blk_rq_map_kern(io->req->q, io->req, seg->buff, seg->total_bytes,
- or->alloc_flags);
- if (ret)
- return ret;
-
- io->total_bytes += seg->total_bytes;
- OSD_DEBUG("padding=%d buff=%p total_bytes=%d\n", padding, seg->buff,
- seg->total_bytes);
- return 0;
-}
-
-static int _osd_req_finalize_set_attr_list(struct osd_request *or)
-{
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
- unsigned padding;
- int ret;
-
- if (!or->set_attr.total_bytes) {
- cdbh->attrs_list.set_attr_offset = OSD_OFFSET_UNUSED;
- return 0;
- }
-
- cdbh->attrs_list.set_attr_bytes = cpu_to_be32(or->set_attr.total_bytes);
- cdbh->attrs_list.set_attr_offset =
- osd_req_encode_offset(or, or->out.total_bytes, &padding);
-
- ret = _req_append_segment(or, padding, &or->set_attr,
- or->out.last_seg, &or->out);
- if (ret)
- return ret;
-
- or->out.last_seg = &or->set_attr;
- return 0;
-}
-
-int osd_req_add_get_attr_list(struct osd_request *or,
- const struct osd_attr *oa, unsigned nelem)
-{
- unsigned total_bytes = or->enc_get_attr.total_bytes;
- void *attr_last;
- int ret;
-
- if (or->attributes_mode &&
- or->attributes_mode != OSD_CDB_GET_SET_ATTR_LISTS) {
- WARN_ON(1);
- return -EINVAL;
- }
- or->attributes_mode = OSD_CDB_GET_SET_ATTR_LISTS;
-
- /* first time calc data-in list header size */
- if (!or->get_attr.total_bytes)
- or->get_attr.total_bytes = _osd_req_sizeof_alist_header(or);
-
- /* calc data-out info */
- if (!total_bytes) { /* first-time: allocate and put list header */
- unsigned max_bytes;
-
- total_bytes = _osd_req_sizeof_alist_header(or);
- max_bytes = total_bytes +
- nelem * sizeof(struct osd_attributes_list_attrid);
- ret = _alloc_get_attr_desc(or, max_bytes);
- if (ret)
- return ret;
-
- _osd_req_set_alist_type(or, or->enc_get_attr.buff,
- OSD_ATTR_LIST_GET);
- }
- attr_last = or->enc_get_attr.buff + total_bytes;
-
- for (; nelem; --nelem) {
- struct osd_attributes_list_attrid *attrid;
- const unsigned cur_size = sizeof(*attrid);
-
- total_bytes += cur_size;
- if (unlikely(or->enc_get_attr.alloc_size < total_bytes)) {
- or->enc_get_attr.total_bytes = total_bytes - cur_size;
- ret = _alloc_get_attr_desc(or,
- total_bytes + nelem * sizeof(*attrid));
- if (ret)
- return ret;
- attr_last = or->enc_get_attr.buff +
- or->enc_get_attr.total_bytes;
- }
-
- attrid = attr_last;
- attrid->attr_page = cpu_to_be32(oa->attr_page);
- attrid->attr_id = cpu_to_be32(oa->attr_id);
-
- attr_last += cur_size;
-
- /* calc data-in size */
- or->get_attr.total_bytes +=
- _osd_req_alist_elem_size(or, oa->len);
- ++oa;
- }
-
- or->enc_get_attr.total_bytes = total_bytes;
-
- OSD_DEBUG(
- "get_attr.total_bytes=%u(%u) enc_get_attr.total_bytes=%u(%zu)\n",
- or->get_attr.total_bytes,
- or->get_attr.total_bytes - _osd_req_sizeof_alist_header(or),
- or->enc_get_attr.total_bytes,
- (or->enc_get_attr.total_bytes - _osd_req_sizeof_alist_header(or))
- / sizeof(struct osd_attributes_list_attrid));
-
- return 0;
-}
-EXPORT_SYMBOL(osd_req_add_get_attr_list);
-
-static int _osd_req_finalize_get_attr_list(struct osd_request *or)
-{
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
- unsigned out_padding;
- unsigned in_padding;
- int ret;
-
- if (!or->enc_get_attr.total_bytes) {
- cdbh->attrs_list.get_attr_desc_offset = OSD_OFFSET_UNUSED;
- cdbh->attrs_list.get_attr_offset = OSD_OFFSET_UNUSED;
- return 0;
- }
-
- ret = _alloc_get_attr_list(or);
- if (ret)
- return ret;
-
- /* The out-going buffer info update */
- OSD_DEBUG("out-going\n");
- cdbh->attrs_list.get_attr_desc_bytes =
- cpu_to_be32(or->enc_get_attr.total_bytes);
-
- cdbh->attrs_list.get_attr_desc_offset =
- osd_req_encode_offset(or, or->out.total_bytes, &out_padding);
-
- ret = _req_append_segment(or, out_padding, &or->enc_get_attr,
- or->out.last_seg, &or->out);
- if (ret)
- return ret;
- or->out.last_seg = &or->enc_get_attr;
-
- /* The incoming buffer info update */
- OSD_DEBUG("in-coming\n");
- cdbh->attrs_list.get_attr_alloc_length =
- cpu_to_be32(or->get_attr.total_bytes);
-
- cdbh->attrs_list.get_attr_offset =
- osd_req_encode_offset(or, or->in.total_bytes, &in_padding);
-
- ret = _req_append_segment(or, in_padding, &or->get_attr, NULL,
- &or->in);
- if (ret)
- return ret;
- or->in.last_seg = &or->get_attr;
-
- return 0;
-}
-
-int osd_req_decode_get_attr_list(struct osd_request *or,
- struct osd_attr *oa, int *nelem, void **iterator)
-{
- unsigned cur_bytes, returned_bytes;
- int n;
- const unsigned sizeof_attr_list = _osd_req_sizeof_alist_header(or);
- void *cur_p;
-
- if (!_osd_req_is_alist_type(or, or->get_attr.buff,
- OSD_ATTR_LIST_SET_RETRIEVE)) {
- oa->attr_page = 0;
- oa->attr_id = 0;
- oa->val_ptr = NULL;
- oa->len = 0;
- *iterator = NULL;
- return 0;
- }
-
- if (*iterator) {
- BUG_ON((*iterator < or->get_attr.buff) ||
- (or->get_attr.buff + or->get_attr.alloc_size < *iterator));
- cur_p = *iterator;
- cur_bytes = (*iterator - or->get_attr.buff) - sizeof_attr_list;
- returned_bytes = or->get_attr.total_bytes;
- } else { /* first time decode the list header */
- cur_bytes = sizeof_attr_list;
- returned_bytes = _osd_req_alist_size(or, or->get_attr.buff) +
- sizeof_attr_list;
-
- cur_p = or->get_attr.buff + sizeof_attr_list;
-
- if (returned_bytes > or->get_attr.alloc_size) {
- OSD_DEBUG("target report: space was not big enough! "
- "Allocate=%u Needed=%u\n",
- or->get_attr.alloc_size,
- returned_bytes + sizeof_attr_list);
-
- returned_bytes =
- or->get_attr.alloc_size - sizeof_attr_list;
- }
- or->get_attr.total_bytes = returned_bytes;
- }
-
- for (n = 0; (n < *nelem) && (cur_bytes < returned_bytes); ++n) {
- int inc = _osd_req_alist_elem_decode(or, cur_p, oa,
- returned_bytes - cur_bytes);
-
- if (inc < 0) {
- OSD_ERR("BAD FOOD from target. list not valid!"
- "c=%d r=%d n=%d\n",
- cur_bytes, returned_bytes, n);
- oa->val_ptr = NULL;
- cur_bytes = returned_bytes; /* break the caller loop */
- break;
- }
-
- cur_bytes += inc;
- cur_p += inc;
- ++oa;
- }
-
- *iterator = (returned_bytes - cur_bytes) ? cur_p : NULL;
- *nelem = n;
- return returned_bytes - cur_bytes;
-}
-EXPORT_SYMBOL(osd_req_decode_get_attr_list);
-
-/*
- * Attributes Page-mode
- */
-
-int osd_req_add_get_attr_page(struct osd_request *or,
- u32 page_id, void *attar_page, unsigned max_page_len,
- const struct osd_attr *set_one_attr)
-{
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
-
- if (or->attributes_mode &&
- or->attributes_mode != OSD_CDB_GET_ATTR_PAGE_SET_ONE) {
- WARN_ON(1);
- return -EINVAL;
- }
- or->attributes_mode = OSD_CDB_GET_ATTR_PAGE_SET_ONE;
-
- or->get_attr.buff = attar_page;
- or->get_attr.total_bytes = max_page_len;
-
- cdbh->attrs_page.get_attr_page = cpu_to_be32(page_id);
- cdbh->attrs_page.get_attr_alloc_length = cpu_to_be32(max_page_len);
-
- if (!set_one_attr || !set_one_attr->attr_page)
- return 0; /* The set is optional */
-
- or->set_attr.buff = set_one_attr->val_ptr;
- or->set_attr.total_bytes = set_one_attr->len;
-
- cdbh->attrs_page.set_attr_page = cpu_to_be32(set_one_attr->attr_page);
- cdbh->attrs_page.set_attr_id = cpu_to_be32(set_one_attr->attr_id);
- cdbh->attrs_page.set_attr_length = cpu_to_be32(set_one_attr->len);
- return 0;
-}
-EXPORT_SYMBOL(osd_req_add_get_attr_page);
-
-static int _osd_req_finalize_attr_page(struct osd_request *or)
-{
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
- unsigned in_padding, out_padding;
- int ret;
-
- /* returned page */
- cdbh->attrs_page.get_attr_offset =
- osd_req_encode_offset(or, or->in.total_bytes, &in_padding);
-
- ret = _req_append_segment(or, in_padding, &or->get_attr, NULL,
- &or->in);
- if (ret)
- return ret;
-
- if (or->set_attr.total_bytes == 0)
- return 0;
-
- /* set one value */
- cdbh->attrs_page.set_attr_offset =
- osd_req_encode_offset(or, or->out.total_bytes, &out_padding);
-
- ret = _req_append_segment(or, out_padding, &or->set_attr, NULL,
- &or->out);
- return ret;
-}
-
-static inline void osd_sec_parms_set_out_offset(bool is_v1,
- struct osd_security_parameters *sec_parms, osd_cdb_offset offset)
-{
- if (is_v1)
- sec_parms->v1.data_out_integrity_check_offset = offset;
- else
- sec_parms->v2.data_out_integrity_check_offset = offset;
-}
-
-static inline void osd_sec_parms_set_in_offset(bool is_v1,
- struct osd_security_parameters *sec_parms, osd_cdb_offset offset)
-{
- if (is_v1)
- sec_parms->v1.data_in_integrity_check_offset = offset;
- else
- sec_parms->v2.data_in_integrity_check_offset = offset;
-}
-
-static int _osd_req_finalize_data_integrity(struct osd_request *or,
- bool has_in, bool has_out, struct bio *out_data_bio, u64 out_data_bytes,
- const u8 *cap_key)
-{
- struct osd_security_parameters *sec_parms = _osd_req_sec_params(or);
- int ret;
-
- if (!osd_is_sec_alldata(sec_parms))
- return 0;
-
- if (has_out) {
- struct _osd_req_data_segment seg = {
- .buff = &or->out_data_integ,
- .total_bytes = sizeof(or->out_data_integ),
- };
- unsigned pad;
-
- or->out_data_integ.data_bytes = cpu_to_be64(out_data_bytes);
- or->out_data_integ.set_attributes_bytes = cpu_to_be64(
- or->set_attr.total_bytes);
- or->out_data_integ.get_attributes_bytes = cpu_to_be64(
- or->enc_get_attr.total_bytes);
-
- osd_sec_parms_set_out_offset(osd_req_is_ver1(or), sec_parms,
- osd_req_encode_offset(or, or->out.total_bytes, &pad));
-
- ret = _req_append_segment(or, pad, &seg, or->out.last_seg,
- &or->out);
- if (ret)
- return ret;
- or->out.last_seg = NULL;
-
- /* they are now all chained to request sign them all together */
- osd_sec_sign_data(&or->out_data_integ, out_data_bio,
- cap_key);
- }
-
- if (has_in) {
- struct _osd_req_data_segment seg = {
- .buff = &or->in_data_integ,
- .total_bytes = sizeof(or->in_data_integ),
- };
- unsigned pad;
-
- osd_sec_parms_set_in_offset(osd_req_is_ver1(or), sec_parms,
- osd_req_encode_offset(or, or->in.total_bytes, &pad));
-
- ret = _req_append_segment(or, pad, &seg, or->in.last_seg,
- &or->in);
- if (ret)
- return ret;
-
- or->in.last_seg = NULL;
- }
-
- return 0;
-}
-
-/*
- * osd_finalize_request and helpers
- */
-static struct request *_make_request(struct request_queue *q, bool has_write,
- struct _osd_io_info *oii, gfp_t flags)
-{
- struct request *req;
- struct bio *bio = oii->bio;
- int ret;
-
- req = blk_get_request(q, has_write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
- flags);
- if (IS_ERR(req))
- return req;
- scsi_req_init(req);
-
- for_each_bio(bio) {
- struct bio *bounce_bio = bio;
-
- blk_queue_bounce(req->q, &bounce_bio);
- ret = blk_rq_append_bio(req, bounce_bio);
- if (ret)
- return ERR_PTR(ret);
- }
-
- return req;
-}
-
-static int _init_blk_request(struct osd_request *or,
- bool has_in, bool has_out)
-{
- gfp_t flags = or->alloc_flags;
- struct scsi_device *scsi_device = or->osd_dev->scsi_device;
- struct request_queue *q = scsi_device->request_queue;
- struct request *req;
- int ret;
-
- req = _make_request(q, has_out, has_out ? &or->out : &or->in, flags);
- if (IS_ERR(req)) {
- ret = PTR_ERR(req);
- goto out;
- }
-
- or->request = req;
- req->rq_flags |= RQF_QUIET;
-
- req->timeout = or->timeout;
- scsi_req(req)->retries = or->retries;
-
- if (has_out) {
- or->out.req = req;
- if (has_in) {
- /* allocate bidi request */
- req = _make_request(q, false, &or->in, flags);
- if (IS_ERR(req)) {
- OSD_DEBUG("blk_get_request for bidi failed\n");
- ret = PTR_ERR(req);
- goto out;
- }
- scsi_req_init(req);
- or->in.req = or->request->next_rq = req;
- }
- } else if (has_in)
- or->in.req = req;
-
- ret = 0;
-out:
- OSD_DEBUG("or=%p has_in=%d has_out=%d => %d, %p\n",
- or, has_in, has_out, ret, or->request);
- return ret;
-}
-
-int osd_finalize_request(struct osd_request *or,
- u8 options, const void *cap, const u8 *cap_key)
-{
- struct osd_cdb_head *cdbh = osd_cdb_head(&or->cdb);
- bool has_in, has_out;
- /* Save for data_integrity without the cdb_continuation */
- struct bio *out_data_bio = or->out.bio;
- u64 out_data_bytes = or->out.total_bytes;
- int ret;
-
- if (options & OSD_REQ_FUA)
- cdbh->options |= OSD_CDB_FUA;
-
- if (options & OSD_REQ_DPO)
- cdbh->options |= OSD_CDB_DPO;
-
- if (options & OSD_REQ_BYPASS_TIMESTAMPS)
- cdbh->timestamp_control = OSD_CDB_BYPASS_TIMESTAMPS;
-
- osd_set_caps(&or->cdb, cap);
-
- has_in = or->in.bio || or->get_attr.total_bytes;
- has_out = or->out.bio || or->cdb_cont.total_bytes ||
- or->set_attr.total_bytes || or->enc_get_attr.total_bytes;
-
- ret = _osd_req_finalize_cdb_cont(or, cap_key);
- if (ret) {
- OSD_DEBUG("_osd_req_finalize_cdb_cont failed\n");
- return ret;
- }
- ret = _init_blk_request(or, has_in, has_out);
- if (ret) {
- OSD_DEBUG("_init_blk_request failed\n");
- return ret;
- }
-
- or->out.pad_buff = sg_out_pad_buffer;
- or->in.pad_buff = sg_in_pad_buffer;
-
- if (!or->attributes_mode)
- or->attributes_mode = OSD_CDB_GET_SET_ATTR_LISTS;
- cdbh->command_specific_options |= or->attributes_mode;
- if (or->attributes_mode == OSD_CDB_GET_ATTR_PAGE_SET_ONE) {
- ret = _osd_req_finalize_attr_page(or);
- if (ret) {
- OSD_DEBUG("_osd_req_finalize_attr_page failed\n");
- return ret;
- }
- } else {
- /* TODO: I think that for the GET_ATTR command these 2 should
- * be reversed to keep them in execution order (for embedded
- * targets with low memory footprint)
- */
- ret = _osd_req_finalize_set_attr_list(or);
- if (ret) {
- OSD_DEBUG("_osd_req_finalize_set_attr_list failed\n");
- return ret;
- }
-
- ret = _osd_req_finalize_get_attr_list(or);
- if (ret) {
- OSD_DEBUG("_osd_req_finalize_get_attr_list failed\n");
- return ret;
- }
- }
-
- ret = _osd_req_finalize_data_integrity(or, has_in, has_out,
- out_data_bio, out_data_bytes,
- cap_key);
- if (ret)
- return ret;
-
- osd_sec_sign_cdb(&or->cdb, cap_key);
-
- scsi_req(or->request)->cmd = or->cdb.buff;
- scsi_req(or->request)->cmd_len = _osd_req_cdb_len(or);
-
- return 0;
-}
-EXPORT_SYMBOL(osd_finalize_request);
-
-static bool _is_osd_security_code(int code)
-{
- return (code == osd_security_audit_value_frozen) ||
- (code == osd_security_working_key_frozen) ||
- (code == osd_nonce_not_unique) ||
- (code == osd_nonce_timestamp_out_of_range) ||
- (code == osd_invalid_dataout_buffer_integrity_check_value);
-}
-
-#define OSD_SENSE_PRINT1(fmt, a...) \
- do { \
- if (__cur_sense_need_output) \
- OSD_ERR(fmt, ##a); \
- } while (0)
-
-#define OSD_SENSE_PRINT2(fmt, a...) OSD_SENSE_PRINT1(" " fmt, ##a)
-
-int osd_req_decode_sense_full(struct osd_request *or,
- struct osd_sense_info *osi, bool silent,
- struct osd_obj_id *bad_obj_list __unused, int max_obj __unused,
- struct osd_attr *bad_attr_list, int max_attr)
-{
- int sense_len, original_sense_len;
- struct osd_sense_info local_osi;
- struct scsi_sense_descriptor_based *ssdb;
- void *cur_descriptor;
-#if (CONFIG_SCSI_OSD_DPRINT_SENSE == 0)
- const bool __cur_sense_need_output = false;
-#else
- bool __cur_sense_need_output = !silent;
-#endif
- int ret;
-
- if (likely(!or->req_errors))
- return 0;
-
- osi = osi ? : &local_osi;
- memset(osi, 0, sizeof(*osi));
-
- ssdb = (typeof(ssdb))or->sense;
- sense_len = or->sense_len;
- if ((sense_len < (int)sizeof(*ssdb) || !ssdb->sense_key)) {
- OSD_ERR("Block-layer returned error(0x%x) but "
- "sense_len(%u) || key(%d) is empty\n",
- or->req_errors, sense_len, ssdb->sense_key);
- goto analyze;
- }
-
- if ((ssdb->response_code != 0x72) && (ssdb->response_code != 0x73)) {
- OSD_ERR("Unrecognized scsi sense: rcode=%x length=%d\n",
- ssdb->response_code, sense_len);
- goto analyze;
- }
-
- osi->key = ssdb->sense_key;
- osi->additional_code = be16_to_cpu(ssdb->additional_sense_code);
- original_sense_len = ssdb->additional_sense_length + 8;
-
-#if (CONFIG_SCSI_OSD_DPRINT_SENSE == 1)
- if (__cur_sense_need_output)
- __cur_sense_need_output = (osi->key > scsi_sk_recovered_error);
-#endif
- OSD_SENSE_PRINT1("Main Sense information key=0x%x length(%d, %d) "
- "additional_code=0x%x async_error=%d errors=0x%x\n",
- osi->key, original_sense_len, sense_len,
- osi->additional_code, or->async_error,
- or->req_errors);
-
- if (original_sense_len < sense_len)
- sense_len = original_sense_len;
-
- cur_descriptor = ssdb->ssd;
- sense_len -= sizeof(*ssdb);
- while (sense_len > 0) {
- struct scsi_sense_descriptor *ssd = cur_descriptor;
- int cur_len = ssd->additional_length + 2;
-
- sense_len -= cur_len;
-
- if (sense_len < 0)
- break; /* sense was truncated */
-
- switch (ssd->descriptor_type) {
- case scsi_sense_information:
- case scsi_sense_command_specific_information:
- {
- struct scsi_sense_command_specific_data_descriptor
- *sscd = cur_descriptor;
-
- osi->command_info =
- get_unaligned_be64(&sscd->information) ;
- OSD_SENSE_PRINT2(
- "command_specific_information 0x%llx \n",
- _LLU(osi->command_info));
- break;
- }
- case scsi_sense_key_specific:
- {
- struct scsi_sense_key_specific_data_descriptor
- *ssks = cur_descriptor;
-
- osi->sense_info = get_unaligned_be16(&ssks->value);
- OSD_SENSE_PRINT2(
- "sense_key_specific_information %u"
- "sksv_cd_bpv_bp (0x%x)\n",
- osi->sense_info, ssks->sksv_cd_bpv_bp);
- break;
- }
- case osd_sense_object_identification:
- { /*FIXME: Keep first not last, Store in array*/
- struct osd_sense_identification_data_descriptor
- *osidd = cur_descriptor;
-
- osi->not_initiated_command_functions =
- le32_to_cpu(osidd->not_initiated_functions);
- osi->completed_command_functions =
- le32_to_cpu(osidd->completed_functions);
- osi->obj.partition = be64_to_cpu(osidd->partition_id);
- osi->obj.id = be64_to_cpu(osidd->object_id);
- OSD_SENSE_PRINT2(
- "object_identification pid=0x%llx oid=0x%llx\n",
- _LLU(osi->obj.partition), _LLU(osi->obj.id));
- OSD_SENSE_PRINT2(
- "not_initiated_bits(%x) "
- "completed_command_bits(%x)\n",
- osi->not_initiated_command_functions,
- osi->completed_command_functions);
- break;
- }
- case osd_sense_response_integrity_check:
- {
- struct osd_sense_response_integrity_check_descriptor
- *osricd = cur_descriptor;
- const unsigned len =
- sizeof(osricd->integrity_check_value);
- char key_dump[len*4 + 2]; /* 2nibbles+space+ASCII */
-
- hex_dump_to_buffer(osricd->integrity_check_value, len,
- 32, 1, key_dump, sizeof(key_dump), true);
- OSD_SENSE_PRINT2("response_integrity [%s]\n", key_dump);
- }
- case osd_sense_attribute_identification:
- {
- struct osd_sense_attributes_data_descriptor
- *osadd = cur_descriptor;
- unsigned len = min(cur_len, sense_len);
- struct osd_sense_attr *pattr = osadd->sense_attrs;
-
- while (len >= sizeof(*pattr)) {
- u32 attr_page = be32_to_cpu(pattr->attr_page);
- u32 attr_id = be32_to_cpu(pattr->attr_id);
-
- if (!osi->attr.attr_page) {
- osi->attr.attr_page = attr_page;
- osi->attr.attr_id = attr_id;
- }
-
- if (bad_attr_list && max_attr) {
- bad_attr_list->attr_page = attr_page;
- bad_attr_list->attr_id = attr_id;
- bad_attr_list++;
- max_attr--;
- }
-
- len -= sizeof(*pattr);
- OSD_SENSE_PRINT2(
- "osd_sense_attribute_identification"
- "attr_page=0x%x attr_id=0x%x\n",
- attr_page, attr_id);
- }
- }
- /*These are not legal for OSD*/
- case scsi_sense_field_replaceable_unit:
- OSD_SENSE_PRINT2("scsi_sense_field_replaceable_unit\n");
- break;
- case scsi_sense_stream_commands:
- OSD_SENSE_PRINT2("scsi_sense_stream_commands\n");
- break;
- case scsi_sense_block_commands:
- OSD_SENSE_PRINT2("scsi_sense_block_commands\n");
- break;
- case scsi_sense_ata_return:
- OSD_SENSE_PRINT2("scsi_sense_ata_return\n");
- break;
- default:
- if (ssd->descriptor_type <= scsi_sense_Reserved_last)
- OSD_SENSE_PRINT2(
- "scsi_sense Reserved descriptor (0x%x)",
- ssd->descriptor_type);
- else
- OSD_SENSE_PRINT2(
- "scsi_sense Vendor descriptor (0x%x)",
- ssd->descriptor_type);
- }
-
- cur_descriptor += cur_len;
- }
-
-analyze:
- if (!osi->key) {
- /* scsi sense is Empty, the request was never issued to target
- * linux return code might tell us what happened.
- */
- if (or->async_error == -ENOMEM)
- osi->osd_err_pri = OSD_ERR_PRI_RESOURCE;
- else
- osi->osd_err_pri = OSD_ERR_PRI_UNREACHABLE;
- ret = or->async_error;
- } else if (osi->key <= scsi_sk_recovered_error) {
- osi->osd_err_pri = 0;
- ret = 0;
- } else if (osi->additional_code == scsi_invalid_field_in_cdb) {
- if (osi->cdb_field_offset == OSD_CFO_STARTING_BYTE) {
- osi->osd_err_pri = OSD_ERR_PRI_CLEAR_PAGES;
- ret = -EFAULT; /* caller should recover from this */
- } else if (osi->cdb_field_offset == OSD_CFO_OBJECT_ID) {
- osi->osd_err_pri = OSD_ERR_PRI_NOT_FOUND;
- ret = -ENOENT;
- } else if (osi->cdb_field_offset == OSD_CFO_PERMISSIONS) {
- osi->osd_err_pri = OSD_ERR_PRI_NO_ACCESS;
- ret = -EACCES;
- } else {
- osi->osd_err_pri = OSD_ERR_PRI_BAD_CRED;
- ret = -EINVAL;
- }
- } else if (osi->additional_code == osd_quota_error) {
- osi->osd_err_pri = OSD_ERR_PRI_NO_SPACE;
- ret = -ENOSPC;
- } else if (_is_osd_security_code(osi->additional_code)) {
- osi->osd_err_pri = OSD_ERR_PRI_BAD_CRED;
- ret = -EINVAL;
- } else {
- osi->osd_err_pri = OSD_ERR_PRI_EIO;
- ret = -EIO;
- }
-
- if (!or->out.residual)
- or->out.residual = or->out.total_bytes;
- if (!or->in.residual)
- or->in.residual = or->in.total_bytes;
-
- return ret;
-}
-EXPORT_SYMBOL(osd_req_decode_sense_full);
-
-/*
- * Implementation of osd_sec.h API
- * TODO: Move to a separate osd_sec.c file at a later stage.
- */
-
-enum { OSD_SEC_CAP_V1_ALL_CAPS =
- OSD_SEC_CAP_APPEND | OSD_SEC_CAP_OBJ_MGMT | OSD_SEC_CAP_REMOVE |
- OSD_SEC_CAP_CREATE | OSD_SEC_CAP_SET_ATTR | OSD_SEC_CAP_GET_ATTR |
- OSD_SEC_CAP_WRITE | OSD_SEC_CAP_READ | OSD_SEC_CAP_POL_SEC |
- OSD_SEC_CAP_GLOBAL | OSD_SEC_CAP_DEV_MGMT
-};
-
-enum { OSD_SEC_CAP_V2_ALL_CAPS =
- OSD_SEC_CAP_V1_ALL_CAPS | OSD_SEC_CAP_QUERY | OSD_SEC_CAP_M_OBJECT
-};
-
-void osd_sec_init_nosec_doall_caps(void *caps,
- const struct osd_obj_id *obj, bool is_collection, const bool is_v1)
-{
- struct osd_capability *cap = caps;
- u8 type;
- u8 descriptor_type;
-
- if (likely(obj->id)) {
- if (unlikely(is_collection)) {
- type = OSD_SEC_OBJ_COLLECTION;
- descriptor_type = is_v1 ? OSD_SEC_OBJ_DESC_OBJ :
- OSD_SEC_OBJ_DESC_COL;
- } else {
- type = OSD_SEC_OBJ_USER;
- descriptor_type = OSD_SEC_OBJ_DESC_OBJ;
- }
- WARN_ON(!obj->partition);
- } else {
- type = obj->partition ? OSD_SEC_OBJ_PARTITION :
- OSD_SEC_OBJ_ROOT;
- descriptor_type = OSD_SEC_OBJ_DESC_PAR;
- }
-
- memset(cap, 0, sizeof(*cap));
-
- cap->h.format = OSD_SEC_CAP_FORMAT_VER1;
- cap->h.integrity_algorithm__key_version = 0; /* MAKE_BYTE(0, 0); */
- cap->h.security_method = OSD_SEC_NOSEC;
-/* cap->expiration_time;
- cap->AUDIT[30-10];
- cap->discriminator[42-30];
- cap->object_created_time; */
- cap->h.object_type = type;
- osd_sec_set_caps(&cap->h, OSD_SEC_CAP_V1_ALL_CAPS);
- cap->h.object_descriptor_type = descriptor_type;
- cap->od.obj_desc.policy_access_tag = 0;
- cap->od.obj_desc.allowed_partition_id = cpu_to_be64(obj->partition);
- cap->od.obj_desc.allowed_object_id = cpu_to_be64(obj->id);
-}
-EXPORT_SYMBOL(osd_sec_init_nosec_doall_caps);
-
-/* FIXME: Extract version from caps pointer.
- * Also Pete's target only supports caps from OSDv1 for now
- */
-void osd_set_caps(struct osd_cdb *cdb, const void *caps)
-{
- /* NOTE: They start at same address */
- memcpy(&cdb->v1.caps, caps, OSDv1_CAP_LEN);
-}
-
-bool osd_is_sec_alldata(struct osd_security_parameters *sec_parms __unused)
-{
- return false;
-}
-
-void osd_sec_sign_cdb(struct osd_cdb *ocdb __unused, const u8 *cap_key __unused)
-{
-}
-
-void osd_sec_sign_data(void *data_integ __unused,
- struct bio *bio __unused, const u8 *cap_key __unused)
-{
-}
-
-/*
- * Declared in osd_protocol.h
- * 4.12.5 Data-In and Data-Out buffer offsets
- * byte offset = mantissa * (2^(exponent+8))
- * Returns the smallest allowed encoded offset that contains given @offset
- * The actual encoded offset returned is @offset + *@padding.
- */
-osd_cdb_offset __osd_encode_offset(
- u64 offset, unsigned *padding, int min_shift, int max_shift)
-{
- u64 try_offset = -1, mod, align;
- osd_cdb_offset be32_offset;
- int shift;
-
- *padding = 0;
- if (!offset)
- return 0;
-
- for (shift = min_shift; shift < max_shift; ++shift) {
- try_offset = offset >> shift;
- if (try_offset < (1 << OSD_OFFSET_MAX_BITS))
- break;
- }
-
- BUG_ON(shift == max_shift);
-
- align = 1 << shift;
- mod = offset & (align - 1);
- if (mod) {
- *padding = align - mod;
- try_offset += 1;
- }
-
- try_offset |= ((shift - 8) & 0xf) << 28;
- be32_offset = cpu_to_be32((u32)try_offset);
-
- OSD_DEBUG("offset=%llu mantissa=%llu exp=%d encoded=%x pad=%d\n",
- _LLU(offset), _LLU(try_offset & 0x0FFFFFFF), shift,
- be32_offset, *padding);
- return be32_offset;
-}
diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c
deleted file mode 100644
index e0ce5d2fd14d..000000000000
--- a/drivers/scsi/osd/osd_uld.c
+++ /dev/null
@@ -1,595 +0,0 @@
-/*
- * osd_uld.c - OSD Upper Layer Driver
- *
- * A Linux driver module that registers as a SCSI ULD and probes
- * for OSD type SCSI devices.
- * It's main function is to export osd devices to in-kernel users like
- * osdfs and pNFS-objects-LD. It also provides one ioctl for running
- * in Kernel tests.
- *
- * Copyright (C) 2008 Panasas Inc. All rights reserved.
- *
- * Authors:
- * Boaz Harrosh <ooo@electrozaur.com>
- * Benny Halevy <bhalevy@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
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/namei.h>
-#include <linux/cdev.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/idr.h>
-#include <linux/major.h>
-#include <linux/file.h>
-#include <linux/slab.h>
-
-#include <scsi/scsi.h>
-#include <scsi/scsi_driver.h>
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_ioctl.h>
-
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_sec.h>
-
-#include "osd_debug.h"
-
-#ifndef TYPE_OSD
-# define TYPE_OSD 0x11
-#endif
-
-#ifndef SCSI_OSD_MAJOR
-# define SCSI_OSD_MAJOR 260
-#endif
-#define SCSI_OSD_MAX_MINOR MINORMASK
-
-static const char osd_name[] = "osd";
-static const char *osd_version_string = "open-osd 0.2.1";
-
-MODULE_AUTHOR("Boaz Harrosh <ooo@electrozaur.com>");
-MODULE_DESCRIPTION("open-osd Upper-Layer-Driver osd.ko");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CHARDEV_MAJOR(SCSI_OSD_MAJOR);
-MODULE_ALIAS_SCSI_DEVICE(TYPE_OSD);
-
-struct osd_uld_device {
- int minor;
- struct device class_dev;
- struct cdev cdev;
- struct osd_dev od;
- struct osd_dev_info odi;
- struct gendisk *disk;
-};
-
-struct osd_dev_handle {
- struct osd_dev od;
- struct file *file;
- struct osd_uld_device *oud;
-} ;
-
-static DEFINE_IDA(osd_minor_ida);
-
-/*
- * scsi sysfs attribute operations
- */
-static ssize_t osdname_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct osd_uld_device *ould = container_of(dev, struct osd_uld_device,
- class_dev);
- return sprintf(buf, "%s\n", ould->odi.osdname);
-}
-static DEVICE_ATTR_RO(osdname);
-
-static ssize_t systemid_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct osd_uld_device *ould = container_of(dev, struct osd_uld_device,
- class_dev);
-
- memcpy(buf, ould->odi.systemid, ould->odi.systemid_len);
- return ould->odi.systemid_len;
-}
-static DEVICE_ATTR_RO(systemid);
-
-static struct attribute *osd_uld_attrs[] = {
- &dev_attr_osdname.attr,
- &dev_attr_systemid.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(osd_uld);
-
-static struct class osd_uld_class = {
- .owner = THIS_MODULE,
- .name = "scsi_osd",
- .dev_groups = osd_uld_groups,
-};
-
-/*
- * Char Device operations
- */
-
-static int osd_uld_open(struct inode *inode, struct file *file)
-{
- struct osd_uld_device *oud = container_of(inode->i_cdev,
- struct osd_uld_device, cdev);
-
- get_device(&oud->class_dev);
- /* cache osd_uld_device on file handle */
- file->private_data = oud;
- OSD_DEBUG("osd_uld_open %p\n", oud);
- return 0;
-}
-
-static int osd_uld_release(struct inode *inode, struct file *file)
-{
- struct osd_uld_device *oud = file->private_data;
-
- OSD_DEBUG("osd_uld_release %p\n", file->private_data);
- file->private_data = NULL;
- put_device(&oud->class_dev);
- return 0;
-}
-
-/* FIXME: Only one vector for now */
-unsigned g_test_ioctl;
-do_test_fn *g_do_test;
-
-int osduld_register_test(unsigned ioctl, do_test_fn *do_test)
-{
- if (g_test_ioctl)
- return -EINVAL;
-
- g_test_ioctl = ioctl;
- g_do_test = do_test;
- return 0;
-}
-EXPORT_SYMBOL(osduld_register_test);
-
-void osduld_unregister_test(unsigned ioctl)
-{
- if (ioctl == g_test_ioctl) {
- g_test_ioctl = 0;
- g_do_test = NULL;
- }
-}
-EXPORT_SYMBOL(osduld_unregister_test);
-
-static do_test_fn *_find_ioctl(unsigned cmd)
-{
- if (g_test_ioctl == cmd)
- return g_do_test;
- else
- return NULL;
-}
-
-static long osd_uld_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- struct osd_uld_device *oud = file->private_data;
- int ret;
- do_test_fn *do_test;
-
- do_test = _find_ioctl(cmd);
- if (do_test)
- ret = do_test(&oud->od, cmd, arg);
- else {
- OSD_ERR("Unknown ioctl %d: osd_uld_device=%p\n", cmd, oud);
- ret = -ENOIOCTLCMD;
- }
- return ret;
-}
-
-static const struct file_operations osd_fops = {
- .owner = THIS_MODULE,
- .open = osd_uld_open,
- .release = osd_uld_release,
- .unlocked_ioctl = osd_uld_ioctl,
- .llseek = noop_llseek,
-};
-
-struct osd_dev *osduld_path_lookup(const char *name)
-{
- struct osd_uld_device *oud;
- struct osd_dev_handle *odh;
- struct file *file;
- int error;
-
- if (!name || !*name) {
- OSD_ERR("Mount with !path || !*path\n");
- return ERR_PTR(-EINVAL);
- }
-
- odh = kzalloc(sizeof(*odh), GFP_KERNEL);
- if (unlikely(!odh))
- return ERR_PTR(-ENOMEM);
-
- file = filp_open(name, O_RDWR, 0);
- if (IS_ERR(file)) {
- error = PTR_ERR(file);
- goto free_od;
- }
-
- if (file->f_op != &osd_fops){
- error = -EINVAL;
- goto close_file;
- }
-
- oud = file->private_data;
-
- odh->od = oud->od;
- odh->file = file;
- odh->oud = oud;
-
- return &odh->od;
-
-close_file:
- fput(file);
-free_od:
- kfree(odh);
- return ERR_PTR(error);
-}
-EXPORT_SYMBOL(osduld_path_lookup);
-
-static inline bool _the_same_or_null(const u8 *a1, unsigned a1_len,
- const u8 *a2, unsigned a2_len)
-{
- if (!a2_len) /* User string is Empty means don't care */
- return true;
-
- if (a1_len != a2_len)
- return false;
-
- return 0 == memcmp(a1, a2, a1_len);
-}
-
-static int _match_odi(struct device *dev, const void *find_data)
-{
- struct osd_uld_device *oud = container_of(dev, struct osd_uld_device,
- class_dev);
- const struct osd_dev_info *odi = find_data;
-
- if (_the_same_or_null(oud->odi.systemid, oud->odi.systemid_len,
- odi->systemid, odi->systemid_len) &&
- _the_same_or_null(oud->odi.osdname, oud->odi.osdname_len,
- odi->osdname, odi->osdname_len)) {
- OSD_DEBUG("found device sysid_len=%d osdname=%d\n",
- odi->systemid_len, odi->osdname_len);
- return 1;
- } else {
- return 0;
- }
-}
-
-/* osduld_info_lookup - Loop through all devices, return the requested osd_dev.
- *
- * if @odi->systemid_len and/or @odi->osdname_len are zero, they act as a don't
- * care. .e.g if they're both zero /dev/osd0 is returned.
- */
-struct osd_dev *osduld_info_lookup(const struct osd_dev_info *odi)
-{
- struct device *dev = class_find_device(&osd_uld_class, NULL, odi, _match_odi);
- if (likely(dev)) {
- struct osd_dev_handle *odh = kzalloc(sizeof(*odh), GFP_KERNEL);
- struct osd_uld_device *oud = container_of(dev,
- struct osd_uld_device, class_dev);
-
- if (unlikely(!odh)) {
- put_device(dev);
- return ERR_PTR(-ENOMEM);
- }
-
- odh->od = oud->od;
- odh->oud = oud;
-
- return &odh->od;
- }
-
- return ERR_PTR(-ENODEV);
-}
-EXPORT_SYMBOL(osduld_info_lookup);
-
-void osduld_put_device(struct osd_dev *od)
-{
- if (od && !IS_ERR(od)) {
- struct osd_dev_handle *odh =
- container_of(od, struct osd_dev_handle, od);
- struct osd_uld_device *oud = odh->oud;
-
- BUG_ON(od->scsi_device != oud->od.scsi_device);
-
- /* If scsi has released the device (logout), and exofs has last
- * reference on oud it will be freed by above osd_uld_release
- * within fput below. But this will oops in cdev_release which
- * is called after the fops->release. A get_/put_ pair makes
- * sure we have a cdev for the duration of fput
- */
- if (odh->file) {
- get_device(&oud->class_dev);
- fput(odh->file);
- }
- put_device(&oud->class_dev);
- kfree(odh);
- }
-}
-EXPORT_SYMBOL(osduld_put_device);
-
-const struct osd_dev_info *osduld_device_info(struct osd_dev *od)
-{
- struct osd_dev_handle *odh =
- container_of(od, struct osd_dev_handle, od);
- return &odh->oud->odi;
-}
-EXPORT_SYMBOL(osduld_device_info);
-
-bool osduld_device_same(struct osd_dev *od, const struct osd_dev_info *odi)
-{
- struct osd_dev_handle *odh =
- container_of(od, struct osd_dev_handle, od);
- struct osd_uld_device *oud = odh->oud;
-
- return (oud->odi.systemid_len == odi->systemid_len) &&
- _the_same_or_null(oud->odi.systemid, oud->odi.systemid_len,
- odi->systemid, odi->systemid_len) &&
- (oud->odi.osdname_len == odi->osdname_len) &&
- _the_same_or_null(oud->odi.osdname, oud->odi.osdname_len,
- odi->osdname, odi->osdname_len);
-}
-EXPORT_SYMBOL(osduld_device_same);
-
-/*
- * Scsi Device operations
- */
-
-static int __detect_osd(struct osd_uld_device *oud)
-{
- struct scsi_device *scsi_device = oud->od.scsi_device;
- struct scsi_sense_hdr sense_hdr;
- char caps[OSD_CAP_LEN];
- int error;
-
- /* sending a test_unit_ready as first command seems to be needed
- * by some targets
- */
- OSD_DEBUG("start scsi_test_unit_ready %p %p %p\n",
- oud, scsi_device, scsi_device->request_queue);
- error = scsi_test_unit_ready(scsi_device, 10*HZ, 5, &sense_hdr);
- if (error)
- OSD_ERR("warning: scsi_test_unit_ready failed\n");
-
- osd_sec_init_nosec_doall_caps(caps, &osd_root_object, false, true);
- if (osd_auto_detect_ver(&oud->od, caps, &oud->odi))
- return -ENODEV;
-
- return 0;
-}
-
-static void __remove(struct device *dev)
-{
- struct osd_uld_device *oud = container_of(dev, struct osd_uld_device,
- class_dev);
- struct scsi_device *scsi_device = oud->od.scsi_device;
-
- kfree(oud->odi.osdname);
-
- if (oud->cdev.owner)
- cdev_del(&oud->cdev);
-
- osd_dev_fini(&oud->od);
- scsi_device_put(scsi_device);
-
- OSD_INFO("osd_remove %s\n",
- oud->disk ? oud->disk->disk_name : NULL);
-
- if (oud->disk)
- put_disk(oud->disk);
- ida_remove(&osd_minor_ida, oud->minor);
-
- kfree(oud);
-}
-
-static int osd_probe(struct device *dev)
-{
- struct scsi_device *scsi_device = to_scsi_device(dev);
- struct gendisk *disk;
- struct osd_uld_device *oud;
- int minor;
- int error;
-
- if (scsi_device->type != TYPE_OSD)
- return -ENODEV;
-
- do {
- if (!ida_pre_get(&osd_minor_ida, GFP_KERNEL))
- return -ENODEV;
-
- error = ida_get_new(&osd_minor_ida, &minor);
- } while (error == -EAGAIN);
-
- if (error)
- return error;
- if (minor >= SCSI_OSD_MAX_MINOR) {
- error = -EBUSY;
- goto err_retract_minor;
- }
-
- error = -ENOMEM;
- oud = kzalloc(sizeof(*oud), GFP_KERNEL);
- if (NULL == oud)
- goto err_retract_minor;
-
- dev_set_drvdata(dev, oud);
- oud->minor = minor;
-
- /* allocate a disk and set it up */
- /* FIXME: do we need this since sg has already done that */
- disk = alloc_disk(1);
- if (!disk) {
- OSD_ERR("alloc_disk failed\n");
- goto err_free_osd;
- }
- disk->major = SCSI_OSD_MAJOR;
- disk->first_minor = oud->minor;
- sprintf(disk->disk_name, "osd%d", oud->minor);
- oud->disk = disk;
-
- /* hold one more reference to the scsi_device that will get released
- * in __release, in case a logout is happening while fs is mounted
- */
- scsi_device_get(scsi_device);
- osd_dev_init(&oud->od, scsi_device);
-
- /* Detect the OSD Version */
- error = __detect_osd(oud);
- if (error) {
- OSD_ERR("osd detection failed, non-compatible OSD device\n");
- goto err_put_disk;
- }
-
- /* init the char-device for communication with user-mode */
- cdev_init(&oud->cdev, &osd_fops);
- oud->cdev.owner = THIS_MODULE;
- error = cdev_add(&oud->cdev,
- MKDEV(SCSI_OSD_MAJOR, oud->minor), 1);
- if (error) {
- OSD_ERR("cdev_add failed\n");
- goto err_put_disk;
- }
-
- /* class device member */
- oud->class_dev.devt = oud->cdev.dev;
- oud->class_dev.class = &osd_uld_class;
- oud->class_dev.parent = dev;
- oud->class_dev.release = __remove;
- error = dev_set_name(&oud->class_dev, "%s", disk->disk_name);
- if (error) {
- OSD_ERR("dev_set_name failed => %d\n", error);
- goto err_put_cdev;
- }
-
- error = device_register(&oud->class_dev);
- if (error) {
- OSD_ERR("device_register failed => %d\n", error);
- goto err_put_cdev;
- }
-
- get_device(&oud->class_dev);
-
- OSD_INFO("osd_probe %s\n", disk->disk_name);
- return 0;
-
-err_put_cdev:
- cdev_del(&oud->cdev);
-err_put_disk:
- scsi_device_put(scsi_device);
- put_disk(disk);
-err_free_osd:
- dev_set_drvdata(dev, NULL);
- kfree(oud);
-err_retract_minor:
- ida_remove(&osd_minor_ida, minor);
- return error;
-}
-
-static int osd_remove(struct device *dev)
-{
- struct scsi_device *scsi_device = to_scsi_device(dev);
- struct osd_uld_device *oud = dev_get_drvdata(dev);
-
- if (!oud || (oud->od.scsi_device != scsi_device)) {
- OSD_ERR("Half cooked osd-device %p,%p || %p!=%p",
- dev, oud, oud ? oud->od.scsi_device : NULL,
- scsi_device);
- }
-
- device_unregister(&oud->class_dev);
-
- put_device(&oud->class_dev);
- return 0;
-}
-
-/*
- * Global driver and scsi registration
- */
-
-static struct scsi_driver osd_driver = {
- .gendrv = {
- .name = osd_name,
- .owner = THIS_MODULE,
- .probe = osd_probe,
- .remove = osd_remove,
- }
-};
-
-static int __init osd_uld_init(void)
-{
- int err;
-
- err = class_register(&osd_uld_class);
- if (err) {
- OSD_ERR("Unable to register sysfs class => %d\n", err);
- return err;
- }
-
- err = register_chrdev_region(MKDEV(SCSI_OSD_MAJOR, 0),
- SCSI_OSD_MAX_MINOR, osd_name);
- if (err) {
- OSD_ERR("Unable to register major %d for osd ULD => %d\n",
- SCSI_OSD_MAJOR, err);
- goto err_out;
- }
-
- err = scsi_register_driver(&osd_driver.gendrv);
- if (err) {
- OSD_ERR("scsi_register_driver failed => %d\n", err);
- goto err_out_chrdev;
- }
-
- OSD_INFO("LOADED %s\n", osd_version_string);
- return 0;
-
-err_out_chrdev:
- unregister_chrdev_region(MKDEV(SCSI_OSD_MAJOR, 0), SCSI_OSD_MAX_MINOR);
-err_out:
- class_unregister(&osd_uld_class);
- return err;
-}
-
-static void __exit osd_uld_exit(void)
-{
- scsi_unregister_driver(&osd_driver.gendrv);
- unregister_chrdev_region(MKDEV(SCSI_OSD_MAJOR, 0), SCSI_OSD_MAX_MINOR);
- class_unregister(&osd_uld_class);
- OSD_INFO("UNLOADED %s\n", osd_version_string);
-}
-
-module_init(osd_uld_init);
-module_exit(osd_uld_exit);
diff --git a/include/scsi/osd_initiator.h b/include/scsi/osd_initiator.h
deleted file mode 100644
index a09cca829082..000000000000
--- a/include/scsi/osd_initiator.h
+++ /dev/null
@@ -1,515 +0,0 @@
-/*
- * osd_initiator.h - OSD initiator API definition
- *
- * Copyright (C) 2008 Panasas Inc. All rights reserved.
- *
- * Authors:
- * Boaz Harrosh <ooo@electrozaur.com>
- * Benny Halevy <bhalevy@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
- *
- */
-#ifndef __OSD_INITIATOR_H__
-#define __OSD_INITIATOR_H__
-
-#include <scsi/osd_protocol.h>
-#include <scsi/osd_types.h>
-
-#include <linux/blkdev.h>
-#include <scsi/scsi_device.h>
-
-/* Note: "NI" in comments below means "Not Implemented yet" */
-
-/* Configure of code:
- * #undef if you *don't* want OSD v1 support in runtime.
- * If #defined the initiator will dynamically configure to encode OSD v1
- * CDB's if the target is detected to be OSD v1 only.
- * OSD v2 only commands, options, and attributes will be ignored if target
- * is v1 only.
- * If #defined will result in bigger/slower code (OK Slower maybe not)
- * Q: Should this be CONFIG_SCSI_OSD_VER1_SUPPORT and set from Kconfig?
- */
-#define OSD_VER1_SUPPORT y
-
-enum osd_std_version {
- OSD_VER_NONE = 0,
- OSD_VER1 = 1,
- OSD_VER2 = 2,
-};
-
-/*
- * Object-based Storage Device.
- * This object represents an OSD device.
- * It is not a full linux device in any way. It is only
- * a place to hang resources associated with a Linux
- * request Q and some default properties.
- */
-struct osd_dev {
- struct scsi_device *scsi_device;
- unsigned def_timeout;
-
-#ifdef OSD_VER1_SUPPORT
- enum osd_std_version version;
-#endif
-};
-
-/* Unique Identification of an OSD device */
-struct osd_dev_info {
- unsigned systemid_len;
- u8 systemid[OSD_SYSTEMID_LEN];
- unsigned osdname_len;
- u8 *osdname;
-};
-
-/* Retrieve/return osd_dev(s) for use by Kernel clients
- * Use IS_ERR/ERR_PTR on returned "osd_dev *".
- */
-struct osd_dev *osduld_path_lookup(const char *dev_name);
-struct osd_dev *osduld_info_lookup(const struct osd_dev_info *odi);
-void osduld_put_device(struct osd_dev *od);
-
-const struct osd_dev_info *osduld_device_info(struct osd_dev *od);
-bool osduld_device_same(struct osd_dev *od, const struct osd_dev_info *odi);
-
-/* Add/remove test ioctls from external modules */
-typedef int (do_test_fn)(struct osd_dev *od, unsigned cmd, unsigned long arg);
-int osduld_register_test(unsigned ioctl, do_test_fn *do_test);
-void osduld_unregister_test(unsigned ioctl);
-
-/* These are called by uld at probe time */
-void osd_dev_init(struct osd_dev *od, struct scsi_device *scsi_device);
-void osd_dev_fini(struct osd_dev *od);
-
-/**
- * osd_auto_detect_ver - Detect the OSD version, return Unique Identification
- *
- * @od: OSD target lun handle
- * @caps: Capabilities authorizing OSD root read attributes access
- * @odi: Retrieved information uniquely identifying the osd target lun
- * Note: odi->osdname must be kfreed by caller.
- *
- * Auto detects the OSD version of the OSD target and sets the @od
- * accordingly. Meanwhile also returns the "system id" and "osd name" root
- * attributes which uniquely identify the OSD target. This member is usually
- * called by the ULD. ULD users should call osduld_device_info().
- * This rutine allocates osd requests and memory at GFP_KERNEL level and might
- * sleep.
- */
-int osd_auto_detect_ver(struct osd_dev *od,
- void *caps, struct osd_dev_info *odi);
-
-static inline struct request_queue *osd_request_queue(struct osd_dev *od)
-{
- return od->scsi_device->request_queue;
-}
-
-/* we might want to use function vector in the future */
-static inline void osd_dev_set_ver(struct osd_dev *od, enum osd_std_version v)
-{
-#ifdef OSD_VER1_SUPPORT
- od->version = v;
-#endif
-}
-
-static inline bool osd_dev_is_ver1(struct osd_dev *od)
-{
-#ifdef OSD_VER1_SUPPORT
- return od->version == OSD_VER1;
-#else
- return false;
-#endif
-}
-
-struct osd_request;
-typedef void (osd_req_done_fn)(struct osd_request *or, void *private);
-
-struct osd_request {
- struct osd_cdb cdb;
- struct osd_data_out_integrity_info out_data_integ;
- struct osd_data_in_integrity_info in_data_integ;
-
- struct osd_dev *osd_dev;
- struct request *request;
-
- struct _osd_req_data_segment {
- void *buff;
- unsigned alloc_size; /* 0 here means: don't call kfree */
- unsigned total_bytes;
- } cdb_cont, set_attr, enc_get_attr, get_attr;
-
- struct _osd_io_info {
- struct bio *bio;
- u64 total_bytes;
- u64 residual;
- struct request *req;
- struct _osd_req_data_segment *last_seg;
- u8 *pad_buff;
- } out, in;
-
- gfp_t alloc_flags;
- unsigned timeout;
- unsigned retries;
- unsigned sense_len;
- u8 sense[OSD_MAX_SENSE_LEN];
- enum osd_attributes_mode attributes_mode;
-
- osd_req_done_fn *async_done;
- void *async_private;
- int async_error;
- int req_errors;
-};
-
-static inline bool osd_req_is_ver1(struct osd_request *or)
-{
- return osd_dev_is_ver1(or->osd_dev);
-}
-
-/*
- * How to use the osd library:
- *
- * osd_start_request
- * Allocates a request.
- *
- * osd_req_*
- * Call one of, to encode the desired operation.
- *
- * osd_add_{get,set}_attr
- * Optionally add attributes to the CDB, list or page mode.
- *
- * osd_finalize_request
- * Computes final data out/in offsets and signs the request,
- * making it ready for execution.
- *
- * osd_execute_request
- * May be called to execute it through the block layer. Other wise submit
- * the associated block request in some other way.
- *
- * After execution:
- * osd_req_decode_sense
- * Decodes sense information to verify execution results.
- *
- * osd_req_decode_get_attr
- * Retrieve osd_add_get_attr_list() values if used.
- *
- * osd_end_request
- * Must be called to deallocate the request.
- */
-
-/**
- * osd_start_request - Allocate and initialize an osd_request
- *
- * @osd_dev: OSD device that holds the scsi-device and default values
- * that the request is associated with.
- * @gfp: The allocation flags to use for request allocation, and all
- * subsequent allocations. This will be stored at
- * osd_request->alloc_flags, can be changed by user later
- *
- * Allocate osd_request and initialize all members to the
- * default/initial state.
- */
-struct osd_request *osd_start_request(struct osd_dev *od, gfp_t gfp);
-
-enum osd_req_options {
- OSD_REQ_FUA = 0x08, /* Force Unit Access */
- OSD_REQ_DPO = 0x10, /* Disable Page Out */
-
- OSD_REQ_BYPASS_TIMESTAMPS = 0x80,
-};
-
-/**
- * osd_finalize_request - Sign request and prepare request for execution
- *
- * @or: osd_request to prepare
- * @options: combination of osd_req_options bit flags or 0.
- * @cap: A Pointer to an OSD_CAP_LEN bytes buffer that is received from
- * The security manager as capabilities for this cdb.
- * @cap_key: The cryptographic key used to sign the cdb/data. Can be null
- * if NOSEC is used.
- *
- * The actual request and bios are only allocated here, so are the get_attr
- * buffers that will receive the returned attributes. Copy's @cap to cdb.
- * Sign the cdb/data with @cap_key.
- */
-int osd_finalize_request(struct osd_request *or,
- u8 options, const void *cap, const u8 *cap_key);
-
-/**
- * osd_execute_request - Execute the request synchronously through block-layer
- *
- * @or: osd_request to Executed
- *
- * Calls blk_execute_rq to q the command and waits for completion.
- */
-int osd_execute_request(struct osd_request *or);
-
-/**
- * osd_execute_request_async - Execute the request without waitting.
- *
- * @or: - osd_request to Executed
- * @done: (Optional) - Called at end of execution
- * @private: - Will be passed to @done function
- *
- * Calls blk_execute_rq_nowait to queue the command. When execution is done
- * optionally calls @done with @private as parameter. @or->async_error will
- * have the return code
- */
-int osd_execute_request_async(struct osd_request *or,
- osd_req_done_fn *done, void *private);
-
-/**
- * osd_req_decode_sense_full - Decode sense information after execution.
- *
- * @or: - osd_request to examine
- * @osi - Receives a more detailed error report information (optional).
- * @silent - Do not print to dmsg (Even if enabled)
- * @bad_obj_list - Some commands act on multiple objects. Failed objects will
- * be received here (optional)
- * @max_obj - Size of @bad_obj_list.
- * @bad_attr_list - List of failing attributes (optional)
- * @max_attr - Size of @bad_attr_list.
- *
- * After execution, osd_request results are analyzed using this function. The
- * return code is the final disposition on the error. So it is possible that a
- * CHECK_CONDITION was returned from target but this will return NO_ERROR, for
- * example on recovered errors. All parameters are optional if caller does
- * not need any returned information.
- * Note: This function will also dump the error to dmsg according to settings
- * of the SCSI_OSD_DPRINT_SENSE Kconfig value. Set @silent if you know the
- * command would routinely fail, to not spam the dmsg file.
- */
-
-/**
- * osd_err_priority - osd categorized return codes in ascending severity.
- *
- * The categories are borrowed from the pnfs_osd_errno enum.
- * See comments for translated Linux codes returned by osd_req_decode_sense.
- */
-enum osd_err_priority {
- OSD_ERR_PRI_NO_ERROR = 0,
- /* Recoverable, caller should clear_highpage() all pages */
- OSD_ERR_PRI_CLEAR_PAGES = 1, /* -EFAULT */
- OSD_ERR_PRI_RESOURCE = 2, /* -ENOMEM */
- OSD_ERR_PRI_BAD_CRED = 3, /* -EINVAL */
- OSD_ERR_PRI_NO_ACCESS = 4, /* -EACCES */
- OSD_ERR_PRI_UNREACHABLE = 5, /* any other */
- OSD_ERR_PRI_NOT_FOUND = 6, /* -ENOENT */
- OSD_ERR_PRI_NO_SPACE = 7, /* -ENOSPC */
- OSD_ERR_PRI_EIO = 8, /* -EIO */
-};
-
-struct osd_sense_info {
- enum osd_err_priority osd_err_pri;
-
- int key; /* one of enum scsi_sense_keys */
- int additional_code ; /* enum osd_additional_sense_codes */
- union { /* Sense specific information */
- u16 sense_info;
- u16 cdb_field_offset; /* scsi_invalid_field_in_cdb */
- };
- union { /* Command specific information */
- u64 command_info;
- };
-
- u32 not_initiated_command_functions; /* osd_command_functions_bits */
- u32 completed_command_functions; /* osd_command_functions_bits */
- struct osd_obj_id obj;
- struct osd_attr attr;
-};
-
-int osd_req_decode_sense_full(struct osd_request *or,
- struct osd_sense_info *osi, bool silent,
- struct osd_obj_id *bad_obj_list, int max_obj,
- struct osd_attr *bad_attr_list, int max_attr);
-
-static inline int osd_req_decode_sense(struct osd_request *or,
- struct osd_sense_info *osi)
-{
- return osd_req_decode_sense_full(or, osi, false, NULL, 0, NULL, 0);
-}
-
-/**
- * osd_end_request - return osd_request to free store
- *
- * @or: osd_request to free
- *
- * Deallocate all osd_request resources (struct req's, BIOs, buffers, etc.)
- */
-void osd_end_request(struct osd_request *or);
-
-/*
- * CDB Encoding
- *
- * Note: call only one of the following methods.
- */
-
-/*
- * Device commands
- */
-void osd_req_set_master_seed_xchg(struct osd_request *or, ...);/* NI */
-void osd_req_set_master_key(struct osd_request *or, ...);/* NI */
-
-void osd_req_format(struct osd_request *or, u64 tot_capacity);
-
-/* list all partitions
- * @list header must be initialized to zero on first run.
- *
- * Call osd_is_obj_list_done() to find if we got the complete list.
- */
-int osd_req_list_dev_partitions(struct osd_request *or,
- osd_id initial_id, struct osd_obj_id_list *list, unsigned nelem);
-
-void osd_req_flush_obsd(struct osd_request *or,
- enum osd_options_flush_scope_values);
-
-void osd_req_perform_scsi_command(struct osd_request *or,
- const u8 *cdb, ...);/* NI */
-void osd_req_task_management(struct osd_request *or, ...);/* NI */
-
-/*
- * Partition commands
- */
-void osd_req_create_partition(struct osd_request *or, osd_id partition);
-void osd_req_remove_partition(struct osd_request *or, osd_id partition);
-
-void osd_req_set_partition_key(struct osd_request *or,
- osd_id partition, u8 new_key_id[OSD_CRYPTO_KEYID_SIZE],
- u8 seed[OSD_CRYPTO_SEED_SIZE]);/* NI */
-
-/* list all collections in the partition
- * @list header must be init to zero on first run.
- *
- * Call osd_is_obj_list_done() to find if we got the complete list.
- */
-int osd_req_list_partition_collections(struct osd_request *or,
- osd_id partition, osd_id initial_id, struct osd_obj_id_list *list,
- unsigned nelem);
-
-/* list all objects in the partition
- * @list header must be init to zero on first run.
- *
- * Call osd_is_obj_list_done() to find if we got the complete list.
- */
-int osd_req_list_partition_objects(struct osd_request *or,
- osd_id partition, osd_id initial_id, struct osd_obj_id_list *list,
- unsigned nelem);
-
-void osd_req_flush_partition(struct osd_request *or,
- osd_id partition, enum osd_options_flush_scope_values);
-
-/*
- * Collection commands
- */
-void osd_req_create_collection(struct osd_request *or,
- const struct osd_obj_id *);/* NI */
-void osd_req_remove_collection(struct osd_request *or,
- const struct osd_obj_id *);/* NI */
-
-/* list all objects in the collection */
-int osd_req_list_collection_objects(struct osd_request *or,
- const struct osd_obj_id *, osd_id initial_id,
- struct osd_obj_id_list *list, unsigned nelem);
-
-/* V2 only filtered list of objects in the collection */
-void osd_req_query(struct osd_request *or, ...);/* NI */
-
-void osd_req_flush_collection(struct osd_request *or,
- const struct osd_obj_id *, enum osd_options_flush_scope_values);
-
-void osd_req_get_member_attrs(struct osd_request *or, ...);/* V2-only NI */
-void osd_req_set_member_attrs(struct osd_request *or, ...);/* V2-only NI */
-
-/*
- * Object commands
- */
-void osd_req_create_object(struct osd_request *or, struct osd_obj_id *);
-void osd_req_remove_object(struct osd_request *or, struct osd_obj_id *);
-
-void osd_req_write(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, struct bio *bio, u64 len);
-int osd_req_write_kern(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
-void osd_req_append(struct osd_request *or,
- const struct osd_obj_id *, struct bio *data_out);/* NI */
-void osd_req_create_write(struct osd_request *or,
- const struct osd_obj_id *, struct bio *data_out, u64 offset);/* NI */
-void osd_req_clear(struct osd_request *or,
- const struct osd_obj_id *, u64 offset, u64 len);/* NI */
-void osd_req_punch(struct osd_request *or,
- const struct osd_obj_id *, u64 offset, u64 len);/* V2-only NI */
-
-void osd_req_flush_object(struct osd_request *or,
- const struct osd_obj_id *, enum osd_options_flush_scope_values,
- /*V2*/ u64 offset, /*V2*/ u64 len);
-
-void osd_req_read(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, struct bio *bio, u64 len);
-int osd_req_read_kern(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
-
-/* Scatter/Gather write/read commands */
-int osd_req_write_sg(struct osd_request *or,
- const struct osd_obj_id *obj, struct bio *bio,
- const struct osd_sg_entry *sglist, unsigned numentries);
-int osd_req_read_sg(struct osd_request *or,
- const struct osd_obj_id *obj, struct bio *bio,
- const struct osd_sg_entry *sglist, unsigned numentries);
-int osd_req_write_sg_kern(struct osd_request *or,
- const struct osd_obj_id *obj, void **buff,
- const struct osd_sg_entry *sglist, unsigned numentries);
-int osd_req_read_sg_kern(struct osd_request *or,
- const struct osd_obj_id *obj, void **buff,
- const struct osd_sg_entry *sglist, unsigned numentries);
-
-/*
- * Root/Partition/Collection/Object Attributes commands
- */
-
-/* get before set */
-void osd_req_get_attributes(struct osd_request *or, const struct osd_obj_id *);
-
-/* set before get */
-void osd_req_set_attributes(struct osd_request *or, const struct osd_obj_id *);
-
-/*
- * Attributes appended to most commands
- */
-
-/* Attributes List mode (or V2 CDB) */
- /*
- * TODO: In ver2 if at finalize time only one attr was set and no gets,
- * then the Attributes CDB mode is used automatically to save IO.
- */
-
-/* set a list of attributes. */
-int osd_req_add_set_attr_list(struct osd_request *or,
- const struct osd_attr *, unsigned nelem);
-
-/* get a list of attributes */
-int osd_req_add_get_attr_list(struct osd_request *or,
- const struct osd_attr *, unsigned nelem);
-
-/*
- * Attributes list decoding
- * Must be called after osd_request.request was executed
- * It is called in a loop to decode the returned get_attr
- * (see osd_add_get_attr)
- */
-int osd_req_decode_get_attr_list(struct osd_request *or,
- struct osd_attr *, int *nelem, void **iterator);
-
-/* Attributes Page mode */
-
-/*
- * Read an attribute page and optionally set one attribute
- *
- * Retrieves the attribute page directly to a user buffer.
- * @attr_page_data shall stay valid until end of execution.
- * See osd_attributes.h for common page structures
- */
-int osd_req_add_get_attr_page(struct osd_request *or,
- u32 page_id, void *attr_page_data, unsigned max_page_len,
- const struct osd_attr *set_one);
-
-#endif /* __OSD_LIB_H__ */
diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h
deleted file mode 100644
index 7a8d2cd30328..000000000000
--- a/include/scsi/osd_ore.h
+++ /dev/null
@@ -1,201 +0,0 @@
-/*
- * Copyright (C) 2011
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * Public Declarations of the ORE API
- *
- * This file is part of the ORE (Object Raid Engine) library.
- *
- * ORE is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation. (GPL v2)
- *
- * ORE 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 the ORE; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-#ifndef __ORE_H__
-#define __ORE_H__
-
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_attributes.h>
-#include <scsi/osd_sec.h>
-#include <linux/pnfs_osd_xdr.h>
-#include <linux/bug.h>
-
-struct ore_comp {
- struct osd_obj_id obj;
- u8 cred[OSD_CAP_LEN];
-};
-
-struct ore_layout {
- /* Our way of looking at the data_map */
- enum pnfs_osd_raid_algorithm4
- raid_algorithm;
- unsigned stripe_unit;
- unsigned mirrors_p1;
-
- unsigned group_width;
- unsigned parity;
- u64 group_depth;
- unsigned group_count;
-
- /* Cached often needed calculations filled in by
- * ore_verify_layout
- */
- unsigned long max_io_length; /* Max length that should be passed to
- * ore_get_rw_state
- */
-};
-
-struct ore_dev {
- struct osd_dev *od;
-};
-
-struct ore_components {
- unsigned first_dev; /* First logical device no */
- unsigned numdevs; /* Num of devices in array */
- /* If @single_comp == EC_SINGLE_COMP, @comps points to a single
- * component. else there are @numdevs components
- */
- enum EC_COMP_USAGE {
- EC_SINGLE_COMP = 0, EC_MULTPLE_COMPS = 0xffffffff
- } single_comp;
- struct ore_comp *comps;
-
- /* Array of pointers to ore_dev-* . User will usually have these pointed
- * too a bigger struct which contain an "ore_dev ored" member and use
- * container_of(oc->ods[i], struct foo_dev, ored) to access the bigger
- * structure.
- */
- struct ore_dev **ods;
-};
-
-/* ore_comp_dev Recievies a logical device index */
-static inline struct osd_dev *ore_comp_dev(
- const struct ore_components *oc, unsigned i)
-{
- BUG_ON((i < oc->first_dev) || (oc->first_dev + oc->numdevs <= i));
- return oc->ods[i - oc->first_dev]->od;
-}
-
-static inline void ore_comp_set_dev(
- struct ore_components *oc, unsigned i, struct osd_dev *od)
-{
- oc->ods[i - oc->first_dev]->od = od;
-}
-
-struct ore_striping_info {
- u64 offset;
- u64 obj_offset;
- u64 length;
- u64 first_stripe_start; /* only used in raid writes */
- u64 M; /* for truncate */
- unsigned bytes_in_stripe;
- unsigned dev;
- unsigned par_dev;
- unsigned unit_off;
- unsigned cur_pg;
- unsigned cur_comp;
- unsigned maxdevUnits;
-};
-
-struct ore_io_state;
-typedef void (*ore_io_done_fn)(struct ore_io_state *ios, void *private);
-struct _ore_r4w_op {
- /* @Priv given here is passed ios->private */
- struct page * (*get_page)(void *priv, u64 page_index, bool *uptodate);
- void (*put_page)(void *priv, struct page *page);
-};
-
-struct ore_io_state {
- struct kref kref;
- struct ore_striping_info si;
-
- void *private;
- ore_io_done_fn done;
-
- struct ore_layout *layout;
- struct ore_components *oc;
-
- /* Global read/write IO*/
- loff_t offset;
- unsigned long length;
- void *kern_buff;
-
- struct page **pages;
- unsigned nr_pages;
- unsigned pgbase;
- unsigned pages_consumed;
-
- /* Attributes */
- unsigned in_attr_len;
- struct osd_attr *in_attr;
- unsigned out_attr_len;
- struct osd_attr *out_attr;
-
- bool reading;
-
- /* House keeping of Parity pages */
- bool extra_part_alloc;
- struct page **parity_pages;
- unsigned max_par_pages;
- unsigned cur_par_page;
- unsigned sgs_per_dev;
- struct __stripe_pages_2d *sp2d;
- struct ore_io_state *ios_read_4_write;
- const struct _ore_r4w_op *r4w;
-
- /* Variable array of size numdevs */
- unsigned numdevs;
- struct ore_per_dev_state {
- struct osd_request *or;
- struct bio *bio;
- loff_t offset;
- unsigned length;
- unsigned last_sgs_total;
- unsigned dev;
- struct osd_sg_entry *sglist;
- unsigned cur_sg;
- } per_dev[];
-};
-
-static inline unsigned ore_io_state_size(unsigned numdevs)
-{
- return sizeof(struct ore_io_state) +
- sizeof(struct ore_per_dev_state) * numdevs;
-}
-
-/* ore.c */
-int ore_verify_layout(unsigned total_comps, struct ore_layout *layout);
-void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
- u64 length, struct ore_striping_info *si);
-int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps,
- bool is_reading, u64 offset, u64 length,
- struct ore_io_state **ios);
-int ore_get_io_state(struct ore_layout *layout, struct ore_components *comps,
- struct ore_io_state **ios);
-void ore_put_io_state(struct ore_io_state *ios);
-
-typedef void (*ore_on_dev_error)(struct ore_io_state *ios, struct ore_dev *od,
- unsigned dev_index, enum osd_err_priority oep,
- u64 dev_offset, u64 dev_len);
-int ore_check_io(struct ore_io_state *ios, ore_on_dev_error rep);
-
-int ore_create(struct ore_io_state *ios);
-int ore_remove(struct ore_io_state *ios);
-int ore_write(struct ore_io_state *ios);
-int ore_read(struct ore_io_state *ios);
-int ore_truncate(struct ore_layout *layout, struct ore_components *comps,
- u64 size);
-
-int extract_attr_from_ios(struct ore_io_state *ios, struct osd_attr *attr);
-
-extern const struct osd_attr g_attr_logical_length;
-
-#endif
--
2.11.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: RFC: drop the T10 OSD code and its users
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
` (3 preceding siblings ...)
2017-04-12 16:01 ` [PATCH 4/4] scsi: remove the SCSI OSD library Christoph Hellwig
@ 2017-04-14 2:27 ` Martin K. Petersen
2017-04-18 16:24 ` Boaz Harrosh
2017-04-19 15:11 ` Jens Axboe
6 siblings, 0 replies; 16+ messages in thread
From: Martin K. Petersen @ 2017-04-14 2:27 UTC (permalink / raw)
To: Christoph Hellwig
Cc: ooo, martin.petersen, trond.myklebust, axboe, osd-dev, linux-nfs,
linux-scsi, linux-block, linux-kernel
Christoph,
> The only real user of the T10 OSD protocol, the pNFS object layout
> driver never went to the point of having shipping products, and the
> other two users (osdblk and exofs) were simple example of it's usage.
>
> The code has been mostly unmaintained for years and is getting in the
> way of block / SCSI changes, so I think it's finally time to drop it.
No particular objections from me.
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: RFC: drop the T10 OSD code and its users
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
` (4 preceding siblings ...)
2017-04-14 2:27 ` RFC: drop the T10 OSD code and its users Martin K. Petersen
@ 2017-04-18 16:24 ` Boaz Harrosh
2017-04-18 17:06 ` Chandy, John
2017-04-19 15:11 ` Jens Axboe
6 siblings, 1 reply; 16+ messages in thread
From: Boaz Harrosh @ 2017-04-18 16:24 UTC (permalink / raw)
To: Christoph Hellwig, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
On 04/12/2017 07:01 PM, Christoph Hellwig wrote:
Hi Sir Christoph
> The only real user of the T10 OSD protocol, the pNFS object layout
> driver never went to the point of having shipping products, and the
> other two users (osdblk and exofs) were simple example of it's usage.
>
I understand why osdblk might be a pain, and was broken from day one, and
should by all means go away ASAP.
But exofs should not be bothering anyone, and as far as I know does
not use any special API's except the osd_uld code of course.
> The code has been mostly unmaintained for years and is getting in the
> way of block / SCSI changes, so I think it's finally time to drop it.
>
Please tell me what are those changes you are talking about? I might be
able to help in conversion. I guess you mean osd_uld and the Upper SCSI API.
Just point me at a tree where osd_uld is broken, and perhaps with a little
guidance from you I can do a satisfactory conversion.
Is true that no new code went in for a long while, but I still from time
to time run a setup and test that the all stack, like iscsi-bidi and so on still
works.
That said, yes only a stand alone exofs was tested for a long time, a full
pnfs setup is missing any supporting server. So Yes I admit that pnfs-obj is
getting very rotten. And is most probably broken, on the pnfs side of things.
[Which I admit makes my little plea kind of mute ;-) ]
Every once in a while I get emails from Students basing all kind of interesting
experiments on top of the exofs and object base storage. So for the sake of academics
and for the sake of a true bidi-stack testing, might we want to evaluate what is the
up coming cost, and what is a minimum set we are willing to keep?
Please advise?
thanks
Boaz
> These patches are against Jens' block for-next tree as that already
> has various modifications of the SCSI code.
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: RFC: drop the T10 OSD code and its users
2017-04-18 16:24 ` Boaz Harrosh
@ 2017-04-18 17:06 ` Chandy, John
0 siblings, 0 replies; 16+ messages in thread
From: Chandy, John @ 2017-04-18 17:06 UTC (permalink / raw)
To: Boaz Harrosh
Cc: Christoph Hellwig, martin.petersen, trond.myklebust, axboe,
osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
As one of those academics that Boaz was talking about, we do use the OSD driver for various research projects including support for OSD in parallel file systems like OrangeFS and Lustre.
John.
> On Apr 18, 2017, at 12:24 PM, Boaz Harrosh <ooo@electrozaur.com> wrote:
>
> On 04/12/2017 07:01 PM, Christoph Hellwig wrote:
>
> Hi Sir Christoph
>
>> The only real user of the T10 OSD protocol, the pNFS object layout
>> driver never went to the point of having shipping products, and the
>> other two users (osdblk and exofs) were simple example of it's usage.
>>
>
> I understand why osdblk might be a pain, and was broken from day one, and
> should by all means go away ASAP.
>
> But exofs should not be bothering anyone, and as far as I know does
> not use any special API's except the osd_uld code of course.
>
>> The code has been mostly unmaintained for years and is getting in the
>> way of block / SCSI changes, so I think it's finally time to drop it.
>>
>
> Please tell me what are those changes you are talking about? I might be
> able to help in conversion. I guess you mean osd_uld and the Upper SCSI API.
> Just point me at a tree where osd_uld is broken, and perhaps with a little
> guidance from you I can do a satisfactory conversion.
>
> Is true that no new code went in for a long while, but I still from time
> to time run a setup and test that the all stack, like iscsi-bidi and so on still
> works.
>
> That said, yes only a stand alone exofs was tested for a long time, a full
> pnfs setup is missing any supporting server. So Yes I admit that pnfs-obj is
> getting very rotten. And is most probably broken, on the pnfs side of things.
> [Which I admit makes my little plea kind of mute ;-) ]
>
> Every once in a while I get emails from Students basing all kind of interesting
> experiments on top of the exofs and object base storage. So for the sake of academics
> and for the sake of a true bidi-stack testing, might we want to evaluate what is the
> up coming cost, and what is a minimum set we are willing to keep?
>
> Please advise?
>
> thanks
> Boaz
>
>> These patches are against Jens' block for-next tree as that already
>> has various modifications of the SCSI code.
>>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 1/4] block: remove the osdblk driver
2017-04-12 16:01 ` [PATCH 1/4] block: remove the osdblk driver Christoph Hellwig
@ 2017-04-19 7:21 ` Boaz Harrosh
0 siblings, 0 replies; 16+ messages in thread
From: Boaz Harrosh @ 2017-04-19 7:21 UTC (permalink / raw)
To: Christoph Hellwig, martin.petersen, trond.myklebust, axboe
Cc: osd-dev, linux-nfs, linux-scsi, linux-block, linux-kernel
On 04/12/2017 07:01 PM, Christoph Hellwig wrote:
> This was just a proof of concept user for the SCSI OSD library, and
> never had any real users.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Yes please remove this driver
ACK-by Boaz Harrosh <ooo@electrozaur.com>
> ---
> drivers/block/Kconfig | 16 --
> drivers/block/Makefile | 1 -
> drivers/block/osdblk.c | 693 -------------------------------------------------
> 3 files changed, 710 deletions(-)
> delete mode 100644 drivers/block/osdblk.c
>
> diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
> index a1c2e816128f..58e24c354933 100644
> --- a/drivers/block/Kconfig
> +++ b/drivers/block/Kconfig
> @@ -312,22 +312,6 @@ config BLK_DEV_SKD
>
> Use device /dev/skd$N amd /dev/skd$Np$M.
>
> -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 b12c772bbeb3..42e8cee1cbc7 100644
> --- a/drivers/block/Makefile
> +++ b/drivers/block/Makefile
> @@ -22,7 +22,6 @@ obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
> obj-$(CONFIG_MG_DISK) += mg_disk.o
> obj-$(CONFIG_SUNVDC) += sunvdc.o
> obj-$(CONFIG_BLK_DEV_SKD) += skd.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
> deleted file mode 100644
> index 8127b8201a01..000000000000
> --- a/drivers/block/osdblk.c
> +++ /dev/null
> @@ -1,693 +0,0 @@
> -
> -/*
> - 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 <linux/slab.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 const 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_clone_kmalloc(old_chain, gfpmask);
> - if (!tmp)
> - goto err_out;
> -
> - tmp->bi_bdev = NULL;
> - gfpmask &= ~__GFP_DIRECT_RECLAIM;
> - 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;
> -
> - /* 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 = (req_op(rq) == REQ_OP_FLUSH);
> - 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_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, BLK_TAG_ALLOC_FIFO);
> - 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_write_cache(q, true, false);
> -
> - 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,
> - struct class_attribute *attr,
> - 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,
> - struct class_attribute *attr,
> - 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,
> - struct class_attribute *attr,
> - const char *buf,
> - size_t count)
> -{
> - struct osdblk_device *osdev = NULL;
> - int target_id, rc;
> - unsigned long ul;
> - struct list_head *tmp;
> -
> - rc = kstrtoul(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);
> -
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: RFC: drop the T10 OSD code and its users
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
` (5 preceding siblings ...)
2017-04-18 16:24 ` Boaz Harrosh
@ 2017-04-19 15:11 ` Jens Axboe
6 siblings, 0 replies; 16+ messages in thread
From: Jens Axboe @ 2017-04-19 15:11 UTC (permalink / raw)
To: Christoph Hellwig
Cc: ooo, martin.petersen, trond.myklebust, osd-dev, linux-nfs,
linux-scsi, linux-block, linux-kernel
On Wed, Apr 12 2017, Christoph Hellwig wrote:
> The only real user of the T10 OSD protocol, the pNFS object layout
> driver never went to the point of having shipping products, and the
> other two users (osdblk and exofs) were simple example of it's usage.
>
> The code has been mostly unmaintained for years and is getting in the
> way of block / SCSI changes, so I think it's finally time to drop it.
>
> These patches are against Jens' block for-next tree as that already
I've added 1/4 for now, as that one should obviously go. If we have
consensus to kill the rest, I'm all for it.
--
Jens Axboe
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/4] nfs: remove the objlayout driver
2017-04-12 16:01 ` [PATCH 3/4] nfs: remove the objlayout driver Christoph Hellwig
@ 2017-04-20 20:18 ` Trond Myklebust
2017-04-21 10:51 ` Christoph Hellwig
2017-04-21 13:17 ` Boaz Harrosh
2017-04-21 7:27 ` Valentin Rothberg
1 sibling, 2 replies; 16+ messages in thread
From: Trond Myklebust @ 2017-04-20 20:18 UTC (permalink / raw)
To: hch, ooo, Trond Myklebust, martin.petersen, axboe
Cc: linux-scsi, linux-kernel, osd-dev, linux-block, linux-nfs
On Wed, 2017-04-12 at 18:01 +0200, Christoph Hellwig wrote:
> The objlayout code has been in the tree, but it's been unmaintained
> and
> no server product for it actually ever shipped.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 6 -
> Documentation/filesystems/nfs/pnfs.txt | 37 --
> fs/nfs/Kconfig | 5 -
> fs/nfs/Makefile | 1 -
> fs/nfs/objlayout/Kbuild | 5 -
> fs/nfs/objlayout/objio_osd.c | 675 --------------
> --------
> fs/nfs/objlayout/objlayout.c | 706 --------------
> ----------
> fs/nfs/objlayout/objlayout.h | 183 ------
> fs/nfs/objlayout/pnfs_osd_xdr_cli.c | 415 --------------
> 9 files changed, 2033 deletions(-)
> delete mode 100644 fs/nfs/objlayout/Kbuild
> delete mode 100644 fs/nfs/objlayout/objio_osd.c
> delete mode 100644 fs/nfs/objlayout/objlayout.c
> delete mode 100644 fs/nfs/objlayout/objlayout.h
> delete mode 100644 fs/nfs/objlayout/pnfs_osd_xdr_cli.c
>
OK. I'm applying this patch for the 4.12 merge window. If, as Boaz
suggests, there is still an interest in exofs, then I suggest we put
that to the test by moving it into the STAGING area, to see if someone
will step up to maintain it.
Cheers
Trond
--
Trond Myklebust
Linux NFS client maintainer, PrimaryData
trond.myklebust@primarydata.com
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/4] nfs: remove the objlayout driver
2017-04-12 16:01 ` [PATCH 3/4] nfs: remove the objlayout driver Christoph Hellwig
2017-04-20 20:18 ` Trond Myklebust
@ 2017-04-21 7:27 ` Valentin Rothberg
2017-04-21 10:50 ` Christoph Hellwig
1 sibling, 1 reply; 16+ messages in thread
From: Valentin Rothberg @ 2017-04-21 7:27 UTC (permalink / raw)
To: Christoph Hellwig
Cc: ooo, martin.petersen, trond.myklebust, axboe, osd-dev, linux-nfs,
linux-scsi, linux-block, LKML
Hi Christoph,
I just came across this patch in linux-next commit 6d22323b2e9f.
scripts/checkkconfigsymbols.py reports that there is a leftover
reference on PNFS_OBJLAYOUT in fs/exofs/Kconfig.ore line 10 (depends
on EXOFS_FS || PNFS_OBJLAYOUT). I assume that this reference can
safely be removed now? If you want to I can send a trivial patch
removing it.
Kind regards,
Valentin
On Wed, Apr 12, 2017 at 6:01 PM, Christoph Hellwig <hch@lst.de> wrote:
> The objlayout code has been in the tree, but it's been unmaintained and
> no server product for it actually ever shipped.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 6 -
> Documentation/filesystems/nfs/pnfs.txt | 37 --
> fs/nfs/Kconfig | 5 -
> fs/nfs/Makefile | 1 -
> fs/nfs/objlayout/Kbuild | 5 -
> fs/nfs/objlayout/objio_osd.c | 675 ----------------------
> fs/nfs/objlayout/objlayout.c | 706 ------------------------
> fs/nfs/objlayout/objlayout.h | 183 ------
> fs/nfs/objlayout/pnfs_osd_xdr_cli.c | 415 --------------
> 9 files changed, 2033 deletions(-)
> delete mode 100644 fs/nfs/objlayout/Kbuild
> delete mode 100644 fs/nfs/objlayout/objio_osd.c
> delete mode 100644 fs/nfs/objlayout/objlayout.c
> delete mode 100644 fs/nfs/objlayout/objlayout.h
> delete mode 100644 fs/nfs/objlayout/pnfs_osd_xdr_cli.c
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index facc20a3f962..17156d66b124 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -2419,12 +2419,6 @@
> and gids from such clients. This is intended to ease
> migration from NFSv2/v3.
>
> - objlayoutdriver.osd_login_prog=
> - [NFS] [OBJLAYOUT] sets the pathname to the program which
> - is used to automatically discover and login into new
> - osd-targets. Please see:
> - Documentation/filesystems/pnfs.txt for more explanations
> -
> nmi_debug= [KNL,AVR32,SH] Specify one or more actions to take
> when a NMI is triggered.
> Format: [state][,regs][,debounce][,die]
> diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
> index 8de578a98222..80dc0bdc302a 100644
> --- a/Documentation/filesystems/nfs/pnfs.txt
> +++ b/Documentation/filesystems/nfs/pnfs.txt
> @@ -64,46 +64,9 @@ table which are called by the nfs-client pnfs-core to implement the
> different layout types.
>
> Files-layout-driver code is in: fs/nfs/filelayout/.. directory
> -Objects-layout-driver code is in: fs/nfs/objlayout/.. directory
> Blocks-layout-driver code is in: fs/nfs/blocklayout/.. directory
> Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
>
> -objects-layout setup
> ---------------------
> -
> -As part of the full STD implementation the objlayoutdriver.ko needs, at times,
> -to automatically login to yet undiscovered iscsi/osd devices. For this the
> -driver makes up-calles to a user-mode script called *osd_login*
> -
> -The path_name of the script to use is by default:
> - /sbin/osd_login.
> -This name can be overridden by the Kernel module parameter:
> - objlayoutdriver.osd_login_prog
> -
> -If Kernel does not find the osd_login_prog path it will zero it out
> -and will not attempt farther logins. An admin can then write new value
> -to the objlayoutdriver.osd_login_prog Kernel parameter to re-enable it.
> -
> -The /sbin/osd_login is part of the nfs-utils package, and should usually
> -be installed on distributions that support this Kernel version.
> -
> -The API to the login script is as follows:
> - Usage: $0 -u <URI> -o <OSDNAME> -s <SYSTEMID>
> - Options:
> - -u target uri e.g. iscsi://<ip>:<port>
> - (always exists)
> - (More protocols can be defined in the future.
> - The client does not interpret this string it is
> - passed unchanged as received from the Server)
> - -o osdname of the requested target OSD
> - (Might be empty)
> - (A string which denotes the OSD name, there is a
> - limit of 64 chars on this string)
> - -s systemid of the requested target OSD
> - (Might be empty)
> - (This string, if not empty is always an hex
> - representation of the 20 bytes osd_system_id)
> -
> blocks-layout setup
> -------------------
>
> diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
> index f31fd0dd92c6..69d02cf8cf37 100644
> --- a/fs/nfs/Kconfig
> +++ b/fs/nfs/Kconfig
> @@ -123,11 +123,6 @@ config PNFS_BLOCK
> depends on NFS_V4_1 && BLK_DEV_DM
> default NFS_V4
>
> -config PNFS_OBJLAYOUT
> - tristate
> - depends on NFS_V4_1 && SCSI_OSD_ULD
> - default NFS_V4
> -
> config PNFS_FLEXFILE_LAYOUT
> tristate
> depends on NFS_V4_1 && NFS_V3
> diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
> index 6abdda209642..98f4e5728a67 100644
> --- a/fs/nfs/Makefile
> +++ b/fs/nfs/Makefile
> @@ -31,6 +31,5 @@ nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o pnfs_nfs.o
> nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o
>
> obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
> -obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
> obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
> obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/
> diff --git a/fs/nfs/objlayout/Kbuild b/fs/nfs/objlayout/Kbuild
> deleted file mode 100644
> index ed30ea072bb8..000000000000
> --- a/fs/nfs/objlayout/Kbuild
> +++ /dev/null
> @@ -1,5 +0,0 @@
> -#
> -# Makefile for the pNFS Objects Layout Driver kernel module
> -#
> -objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o
> -obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o
> diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
> deleted file mode 100644
> index 049c1b1f2932..000000000000
> --- a/fs/nfs/objlayout/objio_osd.c
> +++ /dev/null
> @@ -1,675 +0,0 @@
> -/*
> - * pNFS Objects layout implementation over open-osd initiator library
> - *
> - * Copyright (C) 2009 Panasas Inc. [year of first publication]
> - * All rights reserved.
> - *
> - * Benny Halevy <bhalevy@panasas.com>
> - * Boaz Harrosh <ooo@electrozaur.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
> - * See the file COPYING included with this distribution for more details.
> - *
> - * Redistribution and use in source and binary forms, with or without
> - * modification, are permitted provided that the following conditions
> - * are met:
> - *
> - * 1. Redistributions of source code must retain the above copyright
> - * notice, this list of conditions and the following disclaimer.
> - * 2. Redistributions in binary form must reproduce the above copyright
> - * notice, this list of conditions and the following disclaimer in the
> - * documentation and/or other materials provided with the distribution.
> - * 3. Neither the name of the Panasas company nor the names of its
> - * contributors may be used to endorse or promote products derived
> - * from this software without specific prior written permission.
> - *
> - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
> - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
> - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
> - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
> - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
> - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
> - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
> - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
> - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
> - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
> - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
> - */
> -
> -#include <linux/module.h>
> -#include <scsi/osd_ore.h>
> -
> -#include "objlayout.h"
> -#include "../internal.h"
> -
> -#define NFSDBG_FACILITY NFSDBG_PNFS_LD
> -
> -struct objio_dev_ent {
> - struct nfs4_deviceid_node id_node;
> - struct ore_dev od;
> -};
> -
> -static void
> -objio_free_deviceid_node(struct nfs4_deviceid_node *d)
> -{
> - struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
> -
> - dprintk("%s: free od=%p\n", __func__, de->od.od);
> - osduld_put_device(de->od.od);
> - kfree_rcu(d, rcu);
> -}
> -
> -struct objio_segment {
> - struct pnfs_layout_segment lseg;
> -
> - struct ore_layout layout;
> - struct ore_components oc;
> -};
> -
> -static inline struct objio_segment *
> -OBJIO_LSEG(struct pnfs_layout_segment *lseg)
> -{
> - return container_of(lseg, struct objio_segment, lseg);
> -}
> -
> -struct objio_state {
> - /* Generic layer */
> - struct objlayout_io_res oir;
> -
> - bool sync;
> - /*FIXME: Support for extra_bytes at ore_get_rw_state() */
> - struct ore_io_state *ios;
> -};
> -
> -/* Send and wait for a get_device_info of devices in the layout,
> - then look them up with the osd_initiator library */
> -struct nfs4_deviceid_node *
> -objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
> - gfp_t gfp_flags)
> -{
> - struct pnfs_osd_deviceaddr *deviceaddr;
> - struct objio_dev_ent *ode = NULL;
> - struct osd_dev *od;
> - struct osd_dev_info odi;
> - bool retry_flag = true;
> - __be32 *p;
> - int err;
> -
> - deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags);
> - if (!deviceaddr)
> - return NULL;
> -
> - p = page_address(pdev->pages[0]);
> - pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p);
> -
> - odi.systemid_len = deviceaddr->oda_systemid.len;
> - if (odi.systemid_len > sizeof(odi.systemid)) {
> - dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n",
> - __func__, sizeof(odi.systemid));
> - err = -EINVAL;
> - goto out;
> - } else if (odi.systemid_len)
> - memcpy(odi.systemid, deviceaddr->oda_systemid.data,
> - odi.systemid_len);
> - odi.osdname_len = deviceaddr->oda_osdname.len;
> - odi.osdname = (u8 *)deviceaddr->oda_osdname.data;
> -
> - if (!odi.osdname_len && !odi.systemid_len) {
> - dprintk("%s: !odi.osdname_len && !odi.systemid_len\n",
> - __func__);
> - err = -ENODEV;
> - goto out;
> - }
> -
> -retry_lookup:
> - od = osduld_info_lookup(&odi);
> - if (IS_ERR(od)) {
> - err = PTR_ERR(od);
> - dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
> - if (err == -ENODEV && retry_flag) {
> - err = objlayout_autologin(deviceaddr);
> - if (likely(!err)) {
> - retry_flag = false;
> - goto retry_lookup;
> - }
> - }
> - goto out;
> - }
> -
> - dprintk("Adding new dev_id(%llx:%llx)\n",
> - _DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id));
> -
> - ode = kzalloc(sizeof(*ode), gfp_flags);
> - if (!ode) {
> - dprintk("%s: -ENOMEM od=%p\n", __func__, od);
> - goto out;
> - }
> -
> - nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id);
> - kfree(deviceaddr);
> -
> - ode->od.od = od;
> - return &ode->id_node;
> -
> -out:
> - kfree(deviceaddr);
> - return NULL;
> -}
> -
> -static void copy_single_comp(struct ore_components *oc, unsigned c,
> - struct pnfs_osd_object_cred *src_comp)
> -{
> - struct ore_comp *ocomp = &oc->comps[c];
> -
> - WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */
> - WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred));
> -
> - ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id;
> - ocomp->obj.id = src_comp->oc_object_id.oid_object_id;
> -
> - memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
> -}
> -
> -static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
> - struct objio_segment **pseg)
> -{
> -/* This is the in memory structure of the objio_segment
> - *
> - * struct __alloc_objio_segment {
> - * struct objio_segment olseg;
> - * struct ore_dev *ods[numdevs];
> - * struct ore_comp comps[numdevs];
> - * } *aolseg;
> - * NOTE: The code as above compiles and runs perfectly. It is elegant,
> - * type safe and compact. At some Past time Linus has decided he does not
> - * like variable length arrays, For the sake of this principal we uglify
> - * the code as below.
> - */
> - struct objio_segment *lseg;
> - size_t lseg_size = sizeof(*lseg) +
> - numdevs * sizeof(lseg->oc.ods[0]) +
> - numdevs * sizeof(*lseg->oc.comps);
> -
> - lseg = kzalloc(lseg_size, gfp_flags);
> - if (unlikely(!lseg)) {
> - dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__,
> - numdevs, lseg_size);
> - return -ENOMEM;
> - }
> -
> - lseg->oc.numdevs = numdevs;
> - lseg->oc.single_comp = EC_MULTPLE_COMPS;
> - lseg->oc.ods = (void *)(lseg + 1);
> - lseg->oc.comps = (void *)(lseg->oc.ods + numdevs);
> -
> - *pseg = lseg;
> - return 0;
> -}
> -
> -int objio_alloc_lseg(struct pnfs_layout_segment **outp,
> - struct pnfs_layout_hdr *pnfslay,
> - struct pnfs_layout_range *range,
> - struct xdr_stream *xdr,
> - gfp_t gfp_flags)
> -{
> - struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode);
> - struct objio_segment *objio_seg;
> - struct pnfs_osd_xdr_decode_layout_iter iter;
> - struct pnfs_osd_layout layout;
> - struct pnfs_osd_object_cred src_comp;
> - unsigned cur_comp;
> - int err;
> -
> - err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
> - if (unlikely(err))
> - return err;
> -
> - err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg);
> - if (unlikely(err))
> - return err;
> -
> - objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit;
> - objio_seg->layout.group_width = layout.olo_map.odm_group_width;
> - objio_seg->layout.group_depth = layout.olo_map.odm_group_depth;
> - objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
> - objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm;
> -
> - err = ore_verify_layout(layout.olo_map.odm_num_comps,
> - &objio_seg->layout);
> - if (unlikely(err))
> - goto err;
> -
> - objio_seg->oc.first_dev = layout.olo_comps_index;
> - cur_comp = 0;
> - while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
> - struct nfs4_deviceid_node *d;
> - struct objio_dev_ent *ode;
> -
> - copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
> -
> - d = nfs4_find_get_deviceid(server,
> - &src_comp.oc_object_id.oid_device_id,
> - pnfslay->plh_lc_cred, gfp_flags);
> - if (!d) {
> - err = -ENXIO;
> - goto err;
> - }
> -
> - ode = container_of(d, struct objio_dev_ent, id_node);
> - objio_seg->oc.ods[cur_comp++] = &ode->od;
> - }
> - /* pnfs_osd_xdr_decode_layout_comp returns false on error */
> - if (unlikely(err))
> - goto err;
> -
> - *outp = &objio_seg->lseg;
> - return 0;
> -
> -err:
> - kfree(objio_seg);
> - dprintk("%s: Error: return %d\n", __func__, err);
> - *outp = NULL;
> - return err;
> -}
> -
> -void objio_free_lseg(struct pnfs_layout_segment *lseg)
> -{
> - int i;
> - struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
> -
> - for (i = 0; i < objio_seg->oc.numdevs; i++) {
> - struct ore_dev *od = objio_seg->oc.ods[i];
> - struct objio_dev_ent *ode;
> -
> - if (!od)
> - break;
> - ode = container_of(od, typeof(*ode), od);
> - nfs4_put_deviceid_node(&ode->id_node);
> - }
> - kfree(objio_seg);
> -}
> -
> -static int
> -objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading,
> - struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase,
> - loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags,
> - struct objio_state **outp)
> -{
> - struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
> - struct ore_io_state *ios;
> - int ret;
> - struct __alloc_objio_state {
> - struct objio_state objios;
> - struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs];
> - } *aos;
> -
> - aos = kzalloc(sizeof(*aos), gfp_flags);
> - if (unlikely(!aos))
> - return -ENOMEM;
> -
> - objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs,
> - aos->ioerrs, rpcdata, pnfs_layout_type);
> -
> - ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading,
> - offset, count, &ios);
> - if (unlikely(ret)) {
> - kfree(aos);
> - return ret;
> - }
> -
> - ios->pages = pages;
> - ios->pgbase = pgbase;
> - ios->private = aos;
> - BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT);
> -
> - aos->objios.sync = 0;
> - aos->objios.ios = ios;
> - *outp = &aos->objios;
> - return 0;
> -}
> -
> -void objio_free_result(struct objlayout_io_res *oir)
> -{
> - struct objio_state *objios = container_of(oir, struct objio_state, oir);
> -
> - ore_put_io_state(objios->ios);
> - kfree(objios);
> -}
> -
> -static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
> -{
> - switch (oep) {
> - case OSD_ERR_PRI_NO_ERROR:
> - return (enum pnfs_osd_errno)0;
> -
> - case OSD_ERR_PRI_CLEAR_PAGES:
> - BUG_ON(1);
> - return 0;
> -
> - case OSD_ERR_PRI_RESOURCE:
> - return PNFS_OSD_ERR_RESOURCE;
> - case OSD_ERR_PRI_BAD_CRED:
> - return PNFS_OSD_ERR_BAD_CRED;
> - case OSD_ERR_PRI_NO_ACCESS:
> - return PNFS_OSD_ERR_NO_ACCESS;
> - case OSD_ERR_PRI_UNREACHABLE:
> - return PNFS_OSD_ERR_UNREACHABLE;
> - case OSD_ERR_PRI_NOT_FOUND:
> - return PNFS_OSD_ERR_NOT_FOUND;
> - case OSD_ERR_PRI_NO_SPACE:
> - return PNFS_OSD_ERR_NO_SPACE;
> - default:
> - WARN_ON(1);
> - /* fallthrough */
> - case OSD_ERR_PRI_EIO:
> - return PNFS_OSD_ERR_EIO;
> - }
> -}
> -
> -static void __on_dev_error(struct ore_io_state *ios,
> - struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep,
> - u64 dev_offset, u64 dev_len)
> -{
> - struct objio_state *objios = ios->private;
> - struct pnfs_osd_objid pooid;
> - struct objio_dev_ent *ode = container_of(od, typeof(*ode), od);
> - /* FIXME: what to do with more-then-one-group layouts. We need to
> - * translate from ore_io_state index to oc->comps index
> - */
> - unsigned comp = dev_index;
> -
> - pooid.oid_device_id = ode->id_node.deviceid;
> - pooid.oid_partition_id = ios->oc->comps[comp].obj.partition;
> - pooid.oid_object_id = ios->oc->comps[comp].obj.id;
> -
> - objlayout_io_set_result(&objios->oir, comp,
> - &pooid, osd_pri_2_pnfs_err(oep),
> - dev_offset, dev_len, !ios->reading);
> -}
> -
> -/*
> - * read
> - */
> -static void _read_done(struct ore_io_state *ios, void *private)
> -{
> - struct objio_state *objios = private;
> - ssize_t status;
> - int ret = ore_check_io(ios, &__on_dev_error);
> -
> - /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
> -
> - if (likely(!ret))
> - status = ios->length;
> - else
> - status = ret;
> -
> - objlayout_read_done(&objios->oir, status, objios->sync);
> -}
> -
> -int objio_read_pagelist(struct nfs_pgio_header *hdr)
> -{
> - struct objio_state *objios;
> - int ret;
> -
> - ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
> - hdr->lseg, hdr->args.pages, hdr->args.pgbase,
> - hdr->args.offset, hdr->args.count, hdr,
> - GFP_KERNEL, &objios);
> - if (unlikely(ret))
> - return ret;
> -
> - objios->ios->done = _read_done;
> - dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
> - hdr->args.offset, hdr->args.count);
> - ret = ore_read(objios->ios);
> - if (unlikely(ret))
> - objio_free_result(&objios->oir);
> - return ret;
> -}
> -
> -/*
> - * write
> - */
> -static void _write_done(struct ore_io_state *ios, void *private)
> -{
> - struct objio_state *objios = private;
> - ssize_t status;
> - int ret = ore_check_io(ios, &__on_dev_error);
> -
> - /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
> -
> - if (likely(!ret)) {
> - /* FIXME: should be based on the OSD's persistence model
> - * See OSD2r05 Section 4.13 Data persistence model */
> - objios->oir.committed = NFS_FILE_SYNC;
> - status = ios->length;
> - } else {
> - status = ret;
> - }
> -
> - objlayout_write_done(&objios->oir, status, objios->sync);
> -}
> -
> -static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
> -{
> - struct objio_state *objios = priv;
> - struct nfs_pgio_header *hdr = objios->oir.rpcdata;
> - struct address_space *mapping = hdr->inode->i_mapping;
> - pgoff_t index = offset / PAGE_SIZE;
> - struct page *page;
> - loff_t i_size = i_size_read(hdr->inode);
> -
> - if (offset >= i_size) {
> - *uptodate = true;
> - dprintk("%s: g_zero_page index=0x%lx\n", __func__, index);
> - return ZERO_PAGE(0);
> - }
> -
> - page = find_get_page(mapping, index);
> - if (!page) {
> - page = find_or_create_page(mapping, index, GFP_NOFS);
> - if (unlikely(!page)) {
> - dprintk("%s: grab_cache_page Failed index=0x%lx\n",
> - __func__, index);
> - return NULL;
> - }
> - unlock_page(page);
> - }
> - *uptodate = PageUptodate(page);
> - dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
> - return page;
> -}
> -
> -static void __r4w_put_page(void *priv, struct page *page)
> -{
> - dprintk("%s: index=0x%lx\n", __func__,
> - (page == ZERO_PAGE(0)) ? -1UL : page->index);
> - if (ZERO_PAGE(0) != page)
> - put_page(page);
> - return;
> -}
> -
> -static const struct _ore_r4w_op _r4w_op = {
> - .get_page = &__r4w_get_page,
> - .put_page = &__r4w_put_page,
> -};
> -
> -int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
> -{
> - struct objio_state *objios;
> - int ret;
> -
> - ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
> - hdr->lseg, hdr->args.pages, hdr->args.pgbase,
> - hdr->args.offset, hdr->args.count, hdr, GFP_NOFS,
> - &objios);
> - if (unlikely(ret))
> - return ret;
> -
> - objios->sync = 0 != (how & FLUSH_SYNC);
> - objios->ios->r4w = &_r4w_op;
> -
> - if (!objios->sync)
> - objios->ios->done = _write_done;
> -
> - dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
> - hdr->args.offset, hdr->args.count);
> - ret = ore_write(objios->ios);
> - if (unlikely(ret)) {
> - objio_free_result(&objios->oir);
> - return ret;
> - }
> -
> - if (objios->sync)
> - _write_done(objios->ios, objios);
> -
> - return 0;
> -}
> -
> -/*
> - * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
> - * of bytes (maximum @req->wb_bytes) that can be coalesced.
> - */
> -static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
> - struct nfs_page *prev, struct nfs_page *req)
> -{
> - struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
> - unsigned int size;
> -
> - size = pnfs_generic_pg_test(pgio, prev, req);
> -
> - if (!size || mirror->pg_count + req->wb_bytes >
> - (unsigned long)pgio->pg_layout_private)
> - return 0;
> -
> - return min(size, req->wb_bytes);
> -}
> -
> -static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
> -{
> - pnfs_generic_pg_init_read(pgio, req);
> - if (unlikely(pgio->pg_lseg == NULL))
> - return; /* Not pNFS */
> -
> - pgio->pg_layout_private = (void *)
> - OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
> -}
> -
> -static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
> - unsigned long *stripe_end)
> -{
> - u32 stripe_off;
> - unsigned stripe_size;
> -
> - if (layout->raid_algorithm == PNFS_OSD_RAID_0)
> - return true;
> -
> - stripe_size = layout->stripe_unit *
> - (layout->group_width - layout->parity);
> -
> - div_u64_rem(offset, stripe_size, &stripe_off);
> - if (!stripe_off)
> - return true;
> -
> - *stripe_end = stripe_size - stripe_off;
> - return false;
> -}
> -
> -static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
> -{
> - unsigned long stripe_end = 0;
> - u64 wb_size;
> -
> - if (pgio->pg_dreq == NULL)
> - wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
> - else
> - wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
> -
> - pnfs_generic_pg_init_write(pgio, req, wb_size);
> - if (unlikely(pgio->pg_lseg == NULL))
> - return; /* Not pNFS */
> -
> - if (req->wb_offset ||
> - !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE,
> - &OBJIO_LSEG(pgio->pg_lseg)->layout,
> - &stripe_end)) {
> - pgio->pg_layout_private = (void *)stripe_end;
> - } else {
> - pgio->pg_layout_private = (void *)
> - OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
> - }
> -}
> -
> -static const struct nfs_pageio_ops objio_pg_read_ops = {
> - .pg_init = objio_init_read,
> - .pg_test = objio_pg_test,
> - .pg_doio = pnfs_generic_pg_readpages,
> - .pg_cleanup = pnfs_generic_pg_cleanup,
> -};
> -
> -static const struct nfs_pageio_ops objio_pg_write_ops = {
> - .pg_init = objio_init_write,
> - .pg_test = objio_pg_test,
> - .pg_doio = pnfs_generic_pg_writepages,
> - .pg_cleanup = pnfs_generic_pg_cleanup,
> -};
> -
> -static struct pnfs_layoutdriver_type objlayout_type = {
> - .id = LAYOUT_OSD2_OBJECTS,
> - .name = "LAYOUT_OSD2_OBJECTS",
> - .flags = PNFS_LAYOUTRET_ON_SETATTR |
> - PNFS_LAYOUTRET_ON_ERROR,
> -
> - .max_deviceinfo_size = PAGE_SIZE,
> - .owner = THIS_MODULE,
> - .alloc_layout_hdr = objlayout_alloc_layout_hdr,
> - .free_layout_hdr = objlayout_free_layout_hdr,
> -
> - .alloc_lseg = objlayout_alloc_lseg,
> - .free_lseg = objlayout_free_lseg,
> -
> - .read_pagelist = objlayout_read_pagelist,
> - .write_pagelist = objlayout_write_pagelist,
> - .pg_read_ops = &objio_pg_read_ops,
> - .pg_write_ops = &objio_pg_write_ops,
> -
> - .sync = pnfs_generic_sync,
> -
> - .free_deviceid_node = objio_free_deviceid_node,
> -
> - .encode_layoutcommit = objlayout_encode_layoutcommit,
> - .encode_layoutreturn = objlayout_encode_layoutreturn,
> -};
> -
> -MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");
> -MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>");
> -MODULE_LICENSE("GPL");
> -
> -static int __init
> -objlayout_init(void)
> -{
> - int ret = pnfs_register_layoutdriver(&objlayout_type);
> -
> - if (ret)
> - printk(KERN_INFO
> - "NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n",
> - __func__, ret);
> - else
> - printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n",
> - __func__);
> - return ret;
> -}
> -
> -static void __exit
> -objlayout_exit(void)
> -{
> - pnfs_unregister_layoutdriver(&objlayout_type);
> - printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n",
> - __func__);
> -}
> -
> -MODULE_ALIAS("nfs-layouttype4-2");
> -
> -module_init(objlayout_init);
> -module_exit(objlayout_exit);
> diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
> deleted file mode 100644
> index 8f3d2acb81c3..000000000000
> --- a/fs/nfs/objlayout/objlayout.c
> +++ /dev/null
> @@ -1,706 +0,0 @@
> -/*
> - * pNFS Objects layout driver high level definitions
> - *
> - * Copyright (C) 2007 Panasas Inc. [year of first publication]
> - * All rights reserved.
> - *
> - * Benny Halevy <bhalevy@panasas.com>
> - * Boaz Harrosh <ooo@electrozaur.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
> - * See the file COPYING included with this distribution for more details.
> - *
> - * Redistribution and use in source and binary forms, with or without
> - * modification, are permitted provided that the following conditions
> - * are met:
> - *
> - * 1. Redistributions of source code must retain the above copyright
> - * notice, this list of conditions and the following disclaimer.
> - * 2. Redistributions in binary form must reproduce the above copyright
> - * notice, this list of conditions and the following disclaimer in the
> - * documentation and/or other materials provided with the distribution.
> - * 3. Neither the name of the Panasas company nor the names of its
> - * contributors may be used to endorse or promote products derived
> - * from this software without specific prior written permission.
> - *
> - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
> - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
> - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
> - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
> - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
> - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
> - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
> - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
> - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
> - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
> - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
> - */
> -
> -#include <linux/kmod.h>
> -#include <linux/moduleparam.h>
> -#include <linux/ratelimit.h>
> -#include <scsi/osd_initiator.h>
> -#include "objlayout.h"
> -
> -#define NFSDBG_FACILITY NFSDBG_PNFS_LD
> -/*
> - * Create a objlayout layout structure for the given inode and return it.
> - */
> -struct pnfs_layout_hdr *
> -objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
> -{
> - struct objlayout *objlay;
> -
> - objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
> - if (!objlay)
> - return NULL;
> - spin_lock_init(&objlay->lock);
> - INIT_LIST_HEAD(&objlay->err_list);
> - dprintk("%s: Return %p\n", __func__, objlay);
> - return &objlay->pnfs_layout;
> -}
> -
> -/*
> - * Free an objlayout layout structure
> - */
> -void
> -objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
> -{
> - struct objlayout *objlay = OBJLAYOUT(lo);
> -
> - dprintk("%s: objlay %p\n", __func__, objlay);
> -
> - WARN_ON(!list_empty(&objlay->err_list));
> - kfree(objlay);
> -}
> -
> -/*
> - * Unmarshall layout and store it in pnfslay.
> - */
> -struct pnfs_layout_segment *
> -objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay,
> - struct nfs4_layoutget_res *lgr,
> - gfp_t gfp_flags)
> -{
> - int status = -ENOMEM;
> - struct xdr_stream stream;
> - struct xdr_buf buf = {
> - .pages = lgr->layoutp->pages,
> - .page_len = lgr->layoutp->len,
> - .buflen = lgr->layoutp->len,
> - .len = lgr->layoutp->len,
> - };
> - struct page *scratch;
> - struct pnfs_layout_segment *lseg;
> -
> - dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay);
> -
> - scratch = alloc_page(gfp_flags);
> - if (!scratch)
> - goto err_nofree;
> -
> - xdr_init_decode(&stream, &buf, NULL);
> - xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
> -
> - status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags);
> - if (unlikely(status)) {
> - dprintk("%s: objio_alloc_lseg Return err %d\n", __func__,
> - status);
> - goto err;
> - }
> -
> - __free_page(scratch);
> -
> - dprintk("%s: Return %p\n", __func__, lseg);
> - return lseg;
> -
> -err:
> - __free_page(scratch);
> -err_nofree:
> - dprintk("%s: Err Return=>%d\n", __func__, status);
> - return ERR_PTR(status);
> -}
> -
> -/*
> - * Free a layout segement
> - */
> -void
> -objlayout_free_lseg(struct pnfs_layout_segment *lseg)
> -{
> - dprintk("%s: freeing layout segment %p\n", __func__, lseg);
> -
> - if (unlikely(!lseg))
> - return;
> -
> - objio_free_lseg(lseg);
> -}
> -
> -/*
> - * I/O Operations
> - */
> -static inline u64
> -end_offset(u64 start, u64 len)
> -{
> - u64 end;
> -
> - end = start + len;
> - return end >= start ? end : NFS4_MAX_UINT64;
> -}
> -
> -static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
> - struct page ***p_pages, unsigned *p_pgbase,
> - u64 offset, unsigned long count)
> -{
> - u64 lseg_end_offset;
> -
> - BUG_ON(offset < lseg->pls_range.offset);
> - lseg_end_offset = end_offset(lseg->pls_range.offset,
> - lseg->pls_range.length);
> - BUG_ON(offset >= lseg_end_offset);
> - WARN_ON(offset + count > lseg_end_offset);
> -
> - if (*p_pgbase > PAGE_SIZE) {
> - dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase);
> - *p_pages += *p_pgbase >> PAGE_SHIFT;
> - *p_pgbase &= ~PAGE_MASK;
> - }
> -}
> -
> -/*
> - * I/O done common code
> - */
> -static void
> -objlayout_iodone(struct objlayout_io_res *oir)
> -{
> - if (likely(oir->status >= 0)) {
> - objio_free_result(oir);
> - } else {
> - struct objlayout *objlay = oir->objlay;
> -
> - spin_lock(&objlay->lock);
> - objlay->delta_space_valid = OBJ_DSU_INVALID;
> - list_add(&objlay->err_list, &oir->err_list);
> - spin_unlock(&objlay->lock);
> - }
> -}
> -
> -/*
> - * objlayout_io_set_result - Set an osd_error code on a specific osd comp.
> - *
> - * The @index component IO failed (error returned from target). Register
> - * the error for later reporting at layout-return.
> - */
> -void
> -objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
> - struct pnfs_osd_objid *pooid, int osd_error,
> - u64 offset, u64 length, bool is_write)
> -{
> - struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index];
> -
> - BUG_ON(index >= oir->num_comps);
> - if (osd_error) {
> - ioerr->oer_component = *pooid;
> - ioerr->oer_comp_offset = offset;
> - ioerr->oer_comp_length = length;
> - ioerr->oer_iswrite = is_write;
> - ioerr->oer_errno = osd_error;
> -
> - dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) "
> - "par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n",
> - __func__, index, ioerr->oer_errno,
> - ioerr->oer_iswrite,
> - _DEVID_LO(&ioerr->oer_component.oid_device_id),
> - _DEVID_HI(&ioerr->oer_component.oid_device_id),
> - ioerr->oer_component.oid_partition_id,
> - ioerr->oer_component.oid_object_id,
> - ioerr->oer_comp_offset,
> - ioerr->oer_comp_length);
> - } else {
> - /* User need not call if no error is reported */
> - ioerr->oer_errno = 0;
> - }
> -}
> -
> -/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete().
> - * This is because the osd completion is called with ints-off from
> - * the block layer
> - */
> -static void _rpc_read_complete(struct work_struct *work)
> -{
> - struct rpc_task *task;
> - struct nfs_pgio_header *hdr;
> -
> - dprintk("%s enter\n", __func__);
> - task = container_of(work, struct rpc_task, u.tk_work);
> - hdr = container_of(task, struct nfs_pgio_header, task);
> -
> - pnfs_ld_read_done(hdr);
> -}
> -
> -void
> -objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
> -{
> - struct nfs_pgio_header *hdr = oir->rpcdata;
> -
> - oir->status = hdr->task.tk_status = status;
> - if (status >= 0)
> - hdr->res.count = status;
> - else
> - hdr->pnfs_error = status;
> - objlayout_iodone(oir);
> - /* must not use oir after this point */
> -
> - dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__,
> - status, hdr->res.eof, sync);
> -
> - if (sync)
> - pnfs_ld_read_done(hdr);
> - else {
> - INIT_WORK(&hdr->task.u.tk_work, _rpc_read_complete);
> - schedule_work(&hdr->task.u.tk_work);
> - }
> -}
> -
> -/*
> - * Perform sync or async reads.
> - */
> -enum pnfs_try_status
> -objlayout_read_pagelist(struct nfs_pgio_header *hdr)
> -{
> - struct inode *inode = hdr->inode;
> - loff_t offset = hdr->args.offset;
> - size_t count = hdr->args.count;
> - int err;
> - loff_t eof;
> -
> - eof = i_size_read(inode);
> - if (unlikely(offset + count > eof)) {
> - if (offset >= eof) {
> - err = 0;
> - hdr->res.count = 0;
> - hdr->res.eof = 1;
> - /*FIXME: do we need to call pnfs_ld_read_done() */
> - goto out;
> - }
> - count = eof - offset;
> - }
> -
> - hdr->res.eof = (offset + count) >= eof;
> - _fix_verify_io_params(hdr->lseg, &hdr->args.pages,
> - &hdr->args.pgbase,
> - hdr->args.offset, hdr->args.count);
> -
> - dprintk("%s: inode(%lx) offset 0x%llx count 0x%zx eof=%d\n",
> - __func__, inode->i_ino, offset, count, hdr->res.eof);
> -
> - err = objio_read_pagelist(hdr);
> - out:
> - if (unlikely(err)) {
> - hdr->pnfs_error = err;
> - dprintk("%s: Returned Error %d\n", __func__, err);
> - return PNFS_NOT_ATTEMPTED;
> - }
> - return PNFS_ATTEMPTED;
> -}
> -
> -/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete().
> - * This is because the osd completion is called with ints-off from
> - * the block layer
> - */
> -static void _rpc_write_complete(struct work_struct *work)
> -{
> - struct rpc_task *task;
> - struct nfs_pgio_header *hdr;
> -
> - dprintk("%s enter\n", __func__);
> - task = container_of(work, struct rpc_task, u.tk_work);
> - hdr = container_of(task, struct nfs_pgio_header, task);
> -
> - pnfs_ld_write_done(hdr);
> -}
> -
> -void
> -objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
> -{
> - struct nfs_pgio_header *hdr = oir->rpcdata;
> -
> - oir->status = hdr->task.tk_status = status;
> - if (status >= 0) {
> - hdr->res.count = status;
> - hdr->verf.committed = oir->committed;
> - } else {
> - hdr->pnfs_error = status;
> - }
> - objlayout_iodone(oir);
> - /* must not use oir after this point */
> -
> - dprintk("%s: Return status %zd committed %d sync=%d\n", __func__,
> - status, hdr->verf.committed, sync);
> -
> - if (sync)
> - pnfs_ld_write_done(hdr);
> - else {
> - INIT_WORK(&hdr->task.u.tk_work, _rpc_write_complete);
> - schedule_work(&hdr->task.u.tk_work);
> - }
> -}
> -
> -/*
> - * Perform sync or async writes.
> - */
> -enum pnfs_try_status
> -objlayout_write_pagelist(struct nfs_pgio_header *hdr, int how)
> -{
> - int err;
> -
> - _fix_verify_io_params(hdr->lseg, &hdr->args.pages,
> - &hdr->args.pgbase,
> - hdr->args.offset, hdr->args.count);
> -
> - err = objio_write_pagelist(hdr, how);
> - if (unlikely(err)) {
> - hdr->pnfs_error = err;
> - dprintk("%s: Returned Error %d\n", __func__, err);
> - return PNFS_NOT_ATTEMPTED;
> - }
> - return PNFS_ATTEMPTED;
> -}
> -
> -void
> -objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay,
> - struct xdr_stream *xdr,
> - const struct nfs4_layoutcommit_args *args)
> -{
> - struct objlayout *objlay = OBJLAYOUT(pnfslay);
> - struct pnfs_osd_layoutupdate lou;
> - __be32 *start;
> -
> - dprintk("%s: Begin\n", __func__);
> -
> - spin_lock(&objlay->lock);
> - lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID);
> - lou.dsu_delta = objlay->delta_space_used;
> - objlay->delta_space_used = 0;
> - objlay->delta_space_valid = OBJ_DSU_INIT;
> - lou.olu_ioerr_flag = !list_empty(&objlay->err_list);
> - spin_unlock(&objlay->lock);
> -
> - start = xdr_reserve_space(xdr, 4);
> -
> - BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou));
> -
> - *start = cpu_to_be32((xdr->p - start - 1) * 4);
> -
> - dprintk("%s: Return delta_space_used %lld err %d\n", __func__,
> - lou.dsu_delta, lou.olu_ioerr_flag);
> -}
> -
> -static int
> -err_prio(u32 oer_errno)
> -{
> - switch (oer_errno) {
> - case 0:
> - return 0;
> -
> - case PNFS_OSD_ERR_RESOURCE:
> - return OSD_ERR_PRI_RESOURCE;
> - case PNFS_OSD_ERR_BAD_CRED:
> - return OSD_ERR_PRI_BAD_CRED;
> - case PNFS_OSD_ERR_NO_ACCESS:
> - return OSD_ERR_PRI_NO_ACCESS;
> - case PNFS_OSD_ERR_UNREACHABLE:
> - return OSD_ERR_PRI_UNREACHABLE;
> - case PNFS_OSD_ERR_NOT_FOUND:
> - return OSD_ERR_PRI_NOT_FOUND;
> - case PNFS_OSD_ERR_NO_SPACE:
> - return OSD_ERR_PRI_NO_SPACE;
> - default:
> - WARN_ON(1);
> - /* fallthrough */
> - case PNFS_OSD_ERR_EIO:
> - return OSD_ERR_PRI_EIO;
> - }
> -}
> -
> -static void
> -merge_ioerr(struct pnfs_osd_ioerr *dest_err,
> - const struct pnfs_osd_ioerr *src_err)
> -{
> - u64 dest_end, src_end;
> -
> - if (!dest_err->oer_errno) {
> - *dest_err = *src_err;
> - /* accumulated device must be blank */
> - memset(&dest_err->oer_component.oid_device_id, 0,
> - sizeof(dest_err->oer_component.oid_device_id));
> -
> - return;
> - }
> -
> - if (dest_err->oer_component.oid_partition_id !=
> - src_err->oer_component.oid_partition_id)
> - dest_err->oer_component.oid_partition_id = 0;
> -
> - if (dest_err->oer_component.oid_object_id !=
> - src_err->oer_component.oid_object_id)
> - dest_err->oer_component.oid_object_id = 0;
> -
> - if (dest_err->oer_comp_offset > src_err->oer_comp_offset)
> - dest_err->oer_comp_offset = src_err->oer_comp_offset;
> -
> - dest_end = end_offset(dest_err->oer_comp_offset,
> - dest_err->oer_comp_length);
> - src_end = end_offset(src_err->oer_comp_offset,
> - src_err->oer_comp_length);
> - if (dest_end < src_end)
> - dest_end = src_end;
> -
> - dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset;
> -
> - if ((src_err->oer_iswrite == dest_err->oer_iswrite) &&
> - (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) {
> - dest_err->oer_errno = src_err->oer_errno;
> - } else if (src_err->oer_iswrite) {
> - dest_err->oer_iswrite = true;
> - dest_err->oer_errno = src_err->oer_errno;
> - }
> -}
> -
> -static void
> -encode_accumulated_error(struct objlayout *objlay, __be32 *p)
> -{
> - struct objlayout_io_res *oir, *tmp;
> - struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
> -
> - list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
> - unsigned i;
> -
> - for (i = 0; i < oir->num_comps; i++) {
> - struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
> -
> - if (!ioerr->oer_errno)
> - continue;
> -
> - printk(KERN_ERR "NFS: %s: err[%d]: errno=%d "
> - "is_write=%d dev(%llx:%llx) par=0x%llx "
> - "obj=0x%llx offset=0x%llx length=0x%llx\n",
> - __func__, i, ioerr->oer_errno,
> - ioerr->oer_iswrite,
> - _DEVID_LO(&ioerr->oer_component.oid_device_id),
> - _DEVID_HI(&ioerr->oer_component.oid_device_id),
> - ioerr->oer_component.oid_partition_id,
> - ioerr->oer_component.oid_object_id,
> - ioerr->oer_comp_offset,
> - ioerr->oer_comp_length);
> -
> - merge_ioerr(&accumulated_err, ioerr);
> - }
> - list_del(&oir->err_list);
> - objio_free_result(oir);
> - }
> -
> - pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
> -}
> -
> -void
> -objlayout_encode_layoutreturn(struct xdr_stream *xdr,
> - const struct nfs4_layoutreturn_args *args)
> -{
> - struct pnfs_layout_hdr *pnfslay = args->layout;
> - struct objlayout *objlay = OBJLAYOUT(pnfslay);
> - struct objlayout_io_res *oir, *tmp;
> - __be32 *start;
> -
> - dprintk("%s: Begin\n", __func__);
> - start = xdr_reserve_space(xdr, 4);
> - BUG_ON(!start);
> -
> - spin_lock(&objlay->lock);
> -
> - list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
> - __be32 *last_xdr = NULL, *p;
> - unsigned i;
> - int res = 0;
> -
> - for (i = 0; i < oir->num_comps; i++) {
> - struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
> -
> - if (!ioerr->oer_errno)
> - continue;
> -
> - dprintk("%s: err[%d]: errno=%d is_write=%d "
> - "dev(%llx:%llx) par=0x%llx obj=0x%llx "
> - "offset=0x%llx length=0x%llx\n",
> - __func__, i, ioerr->oer_errno,
> - ioerr->oer_iswrite,
> - _DEVID_LO(&ioerr->oer_component.oid_device_id),
> - _DEVID_HI(&ioerr->oer_component.oid_device_id),
> - ioerr->oer_component.oid_partition_id,
> - ioerr->oer_component.oid_object_id,
> - ioerr->oer_comp_offset,
> - ioerr->oer_comp_length);
> -
> - p = pnfs_osd_xdr_ioerr_reserve_space(xdr);
> - if (unlikely(!p)) {
> - res = -E2BIG;
> - break; /* accumulated_error */
> - }
> -
> - last_xdr = p;
> - pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]);
> - }
> -
> - /* TODO: use xdr_write_pages */
> - if (unlikely(res)) {
> - /* no space for even one error descriptor */
> - BUG_ON(!last_xdr);
> -
> - /* we've encountered a situation with lots and lots of
> - * errors and no space to encode them all. Use the last
> - * available slot to report the union of all the
> - * remaining errors.
> - */
> - encode_accumulated_error(objlay, last_xdr);
> - goto loop_done;
> - }
> - list_del(&oir->err_list);
> - objio_free_result(oir);
> - }
> -loop_done:
> - spin_unlock(&objlay->lock);
> -
> - *start = cpu_to_be32((xdr->p - start - 1) * 4);
> - dprintk("%s: Return\n", __func__);
> -}
> -
> -enum {
> - OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
> - OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
> - OSD_LOGIN_UPCALL_PATHLEN = 256
> -};
> -
> -static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login";
> -
> -module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog),
> - 0600);
> -MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program");
> -
> -struct __auto_login {
> - char uri[OBJLAYOUT_MAX_URI_LEN];
> - char osdname[OBJLAYOUT_MAX_OSDNAME_LEN];
> - char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN];
> -};
> -
> -static int __objlayout_upcall(struct __auto_login *login)
> -{
> - static char *envp[] = { "HOME=/",
> - "TERM=linux",
> - "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
> - NULL
> - };
> - char *argv[8];
> - int ret;
> -
> - if (unlikely(!osd_login_prog[0])) {
> - dprintk("%s: osd_login_prog is disabled\n", __func__);
> - return -EACCES;
> - }
> -
> - dprintk("%s uri: %s\n", __func__, login->uri);
> - dprintk("%s osdname %s\n", __func__, login->osdname);
> - dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex);
> -
> - argv[0] = (char *)osd_login_prog;
> - argv[1] = "-u";
> - argv[2] = login->uri;
> - argv[3] = "-o";
> - argv[4] = login->osdname;
> - argv[5] = "-s";
> - argv[6] = login->systemid_hex;
> - argv[7] = NULL;
> -
> - ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
> - /*
> - * Disable the upcall mechanism if we're getting an ENOENT or
> - * EACCES error. The admin can re-enable it on the fly by using
> - * sysfs to set the objlayoutdriver.osd_login_prog module parameter once
> - * the problem has been fixed.
> - */
> - if (ret == -ENOENT || ret == -EACCES) {
> - printk(KERN_ERR "PNFS-OBJ: %s was not found please set "
> - "objlayoutdriver.osd_login_prog kernel parameter!\n",
> - osd_login_prog);
> - osd_login_prog[0] = '\0';
> - }
> - dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret);
> -
> - return ret;
> -}
> -
> -/* Assume dest is all zeros */
> -static void __copy_nfsS_and_zero_terminate(struct nfs4_string s,
> - char *dest, int max_len,
> - const char *var_name)
> -{
> - if (!s.len)
> - return;
> -
> - if (s.len >= max_len) {
> - pr_warn_ratelimited(
> - "objlayout_autologin: %s: s.len(%d) >= max_len(%d)",
> - var_name, s.len, max_len);
> - s.len = max_len - 1; /* space for null terminator */
> - }
> -
> - memcpy(dest, s.data, s.len);
> -}
> -
> -/* Assume sysid is all zeros */
> -static void _sysid_2_hex(struct nfs4_string s,
> - char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN])
> -{
> - int i;
> - char *cur;
> -
> - if (!s.len)
> - return;
> -
> - if (s.len != OSD_SYSTEMID_LEN) {
> - pr_warn_ratelimited(
> - "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN",
> - s.len);
> - if (s.len > OSD_SYSTEMID_LEN)
> - s.len = OSD_SYSTEMID_LEN;
> - }
> -
> - cur = sysid;
> - for (i = 0; i < s.len; i++)
> - cur = hex_byte_pack(cur, s.data[i]);
> -}
> -
> -int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr)
> -{
> - int rc;
> - struct __auto_login login;
> -
> - if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len)
> - return -ENODEV;
> -
> - memset(&login, 0, sizeof(login));
> - __copy_nfsS_and_zero_terminate(
> - deviceaddr->oda_targetaddr.ota_netaddr.r_addr,
> - login.uri, sizeof(login.uri), "URI");
> -
> - __copy_nfsS_and_zero_terminate(
> - deviceaddr->oda_osdname,
> - login.osdname, sizeof(login.osdname), "OSDNAME");
> -
> - _sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex);
> -
> - rc = __objlayout_upcall(&login);
> - if (rc > 0) /* script returns positive values */
> - rc = -ENODEV;
> -
> - return rc;
> -}
> diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
> deleted file mode 100644
> index fc94a5872ed4..000000000000
> --- a/fs/nfs/objlayout/objlayout.h
> +++ /dev/null
> @@ -1,183 +0,0 @@
> -/*
> - * Data types and function declerations for interfacing with the
> - * pNFS standard object layout driver.
> - *
> - * Copyright (C) 2007 Panasas Inc. [year of first publication]
> - * All rights reserved.
> - *
> - * Benny Halevy <bhalevy@panasas.com>
> - * Boaz Harrosh <ooo@electrozaur.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
> - * See the file COPYING included with this distribution for more details.
> - *
> - * Redistribution and use in source and binary forms, with or without
> - * modification, are permitted provided that the following conditions
> - * are met:
> - *
> - * 1. Redistributions of source code must retain the above copyright
> - * notice, this list of conditions and the following disclaimer.
> - * 2. Redistributions in binary form must reproduce the above copyright
> - * notice, this list of conditions and the following disclaimer in the
> - * documentation and/or other materials provided with the distribution.
> - * 3. Neither the name of the Panasas company nor the names of its
> - * contributors may be used to endorse or promote products derived
> - * from this software without specific prior written permission.
> - *
> - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
> - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
> - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
> - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
> - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
> - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
> - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
> - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
> - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
> - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
> - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
> - */
> -
> -#ifndef _OBJLAYOUT_H
> -#define _OBJLAYOUT_H
> -
> -#include <linux/nfs_fs.h>
> -#include <linux/pnfs_osd_xdr.h>
> -#include "../pnfs.h"
> -
> -/*
> - * per-inode layout
> - */
> -struct objlayout {
> - struct pnfs_layout_hdr pnfs_layout;
> -
> - /* for layout_commit */
> - enum osd_delta_space_valid_enum {
> - OBJ_DSU_INIT = 0,
> - OBJ_DSU_VALID,
> - OBJ_DSU_INVALID,
> - } delta_space_valid;
> - s64 delta_space_used; /* consumed by write ops */
> -
> - /* for layout_return */
> - spinlock_t lock;
> - struct list_head err_list;
> -};
> -
> -static inline struct objlayout *
> -OBJLAYOUT(struct pnfs_layout_hdr *lo)
> -{
> - return container_of(lo, struct objlayout, pnfs_layout);
> -}
> -
> -/*
> - * per-I/O operation state
> - * embedded in objects provider io_state data structure
> - */
> -struct objlayout_io_res {
> - struct objlayout *objlay;
> -
> - void *rpcdata;
> - int status; /* res */
> - int committed; /* res */
> -
> - /* Error reporting (layout_return) */
> - struct list_head err_list;
> - unsigned num_comps;
> - /* Pointer to array of error descriptors of size num_comps.
> - * It should contain as many entries as devices in the osd_layout
> - * that participate in the I/O. It is up to the io_engine to allocate
> - * needed space and set num_comps.
> - */
> - struct pnfs_osd_ioerr *ioerrs;
> -};
> -
> -static inline
> -void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
> - struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
> - struct pnfs_layout_hdr *pnfs_layout_type)
> -{
> - oir->objlay = OBJLAYOUT(pnfs_layout_type);
> - oir->rpcdata = rpcdata;
> - INIT_LIST_HEAD(&oir->err_list);
> - oir->num_comps = num_comps;
> - oir->ioerrs = ioerrs;
> -}
> -
> -/*
> - * Raid engine I/O API
> - */
> -extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
> - struct pnfs_layout_hdr *pnfslay,
> - struct pnfs_layout_range *range,
> - struct xdr_stream *xdr,
> - gfp_t gfp_flags);
> -extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
> -
> -/* objio_free_result will free these @oir structs received from
> - * objlayout_{read,write}_done
> - */
> -extern void objio_free_result(struct objlayout_io_res *oir);
> -
> -extern int objio_read_pagelist(struct nfs_pgio_header *rdata);
> -extern int objio_write_pagelist(struct nfs_pgio_header *wdata, int how);
> -
> -/*
> - * callback API
> - */
> -extern void objlayout_io_set_result(struct objlayout_io_res *oir,
> - unsigned index, struct pnfs_osd_objid *pooid,
> - int osd_error, u64 offset, u64 length, bool is_write);
> -
> -static inline void
> -objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
> -{
> - /* If one of the I/Os errored out and the delta_space_used was
> - * invalid we render the complete report as invalid. Protocol mandate
> - * the DSU be accurate or not reported.
> - */
> - spin_lock(&objlay->lock);
> - if (objlay->delta_space_valid != OBJ_DSU_INVALID) {
> - objlay->delta_space_valid = OBJ_DSU_VALID;
> - objlay->delta_space_used += space_used;
> - }
> - spin_unlock(&objlay->lock);
> -}
> -
> -extern void objlayout_read_done(struct objlayout_io_res *oir,
> - ssize_t status, bool sync);
> -extern void objlayout_write_done(struct objlayout_io_res *oir,
> - ssize_t status, bool sync);
> -
> -/*
> - * exported generic objects function vectors
> - */
> -
> -extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags);
> -extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *);
> -
> -extern struct pnfs_layout_segment *objlayout_alloc_lseg(
> - struct pnfs_layout_hdr *,
> - struct nfs4_layoutget_res *,
> - gfp_t gfp_flags);
> -extern void objlayout_free_lseg(struct pnfs_layout_segment *);
> -
> -extern enum pnfs_try_status objlayout_read_pagelist(
> - struct nfs_pgio_header *);
> -
> -extern enum pnfs_try_status objlayout_write_pagelist(
> - struct nfs_pgio_header *,
> - int how);
> -
> -extern void objlayout_encode_layoutcommit(
> - struct pnfs_layout_hdr *,
> - struct xdr_stream *,
> - const struct nfs4_layoutcommit_args *);
> -
> -extern void objlayout_encode_layoutreturn(
> - struct xdr_stream *,
> - const struct nfs4_layoutreturn_args *);
> -
> -extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr);
> -
> -#endif /* _OBJLAYOUT_H */
> diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
> deleted file mode 100644
> index f093c7ec983b..000000000000
> --- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
> +++ /dev/null
> @@ -1,415 +0,0 @@
> -/*
> - * Object-Based pNFS Layout XDR layer
> - *
> - * Copyright (C) 2007 Panasas Inc. [year of first publication]
> - * All rights reserved.
> - *
> - * Benny Halevy <bhalevy@panasas.com>
> - * Boaz Harrosh <ooo@electrozaur.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
> - * See the file COPYING included with this distribution for more details.
> - *
> - * Redistribution and use in source and binary forms, with or without
> - * modification, are permitted provided that the following conditions
> - * are met:
> - *
> - * 1. Redistributions of source code must retain the above copyright
> - * notice, this list of conditions and the following disclaimer.
> - * 2. Redistributions in binary form must reproduce the above copyright
> - * notice, this list of conditions and the following disclaimer in the
> - * documentation and/or other materials provided with the distribution.
> - * 3. Neither the name of the Panasas company nor the names of its
> - * contributors may be used to endorse or promote products derived
> - * from this software without specific prior written permission.
> - *
> - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
> - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
> - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
> - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
> - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
> - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
> - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
> - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
> - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
> - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
> - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
> - */
> -
> -#include <linux/pnfs_osd_xdr.h>
> -
> -#define NFSDBG_FACILITY NFSDBG_PNFS_LD
> -
> -/*
> - * The following implementation is based on RFC5664
> - */
> -
> -/*
> - * struct pnfs_osd_objid {
> - * struct nfs4_deviceid oid_device_id;
> - * u64 oid_partition_id;
> - * u64 oid_object_id;
> - * }; // xdr size 32 bytes
> - */
> -static __be32 *
> -_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid)
> -{
> - p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data,
> - sizeof(objid->oid_device_id.data));
> -
> - p = xdr_decode_hyper(p, &objid->oid_partition_id);
> - p = xdr_decode_hyper(p, &objid->oid_object_id);
> - return p;
> -}
> -/*
> - * struct pnfs_osd_opaque_cred {
> - * u32 cred_len;
> - * void *cred;
> - * }; // xdr size [variable]
> - * The return pointers are from the xdr buffer
> - */
> -static int
> -_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred,
> - struct xdr_stream *xdr)
> -{
> - __be32 *p = xdr_inline_decode(xdr, 1);
> -
> - if (!p)
> - return -EINVAL;
> -
> - opaque_cred->cred_len = be32_to_cpu(*p++);
> -
> - p = xdr_inline_decode(xdr, opaque_cred->cred_len);
> - if (!p)
> - return -EINVAL;
> -
> - opaque_cred->cred = p;
> - return 0;
> -}
> -
> -/*
> - * struct pnfs_osd_object_cred {
> - * struct pnfs_osd_objid oc_object_id;
> - * u32 oc_osd_version;
> - * u32 oc_cap_key_sec;
> - * struct pnfs_osd_opaque_cred oc_cap_key
> - * struct pnfs_osd_opaque_cred oc_cap;
> - * }; // xdr size 32 + 4 + 4 + [variable] + [variable]
> - */
> -static int
> -_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp,
> - struct xdr_stream *xdr)
> -{
> - __be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4);
> - int ret;
> -
> - if (!p)
> - return -EIO;
> -
> - p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
> - comp->oc_osd_version = be32_to_cpup(p++);
> - comp->oc_cap_key_sec = be32_to_cpup(p);
> -
> - ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr);
> - if (unlikely(ret))
> - return ret;
> -
> - ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr);
> - return ret;
> -}
> -
> -/*
> - * struct pnfs_osd_data_map {
> - * u32 odm_num_comps;
> - * u64 odm_stripe_unit;
> - * u32 odm_group_width;
> - * u32 odm_group_depth;
> - * u32 odm_mirror_cnt;
> - * u32 odm_raid_algorithm;
> - * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4
> - */
> -static inline int
> -_osd_data_map_xdr_sz(void)
> -{
> - return 4 + 8 + 4 + 4 + 4 + 4;
> -}
> -
> -static __be32 *
> -_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map)
> -{
> - data_map->odm_num_comps = be32_to_cpup(p++);
> - p = xdr_decode_hyper(p, &data_map->odm_stripe_unit);
> - data_map->odm_group_width = be32_to_cpup(p++);
> - data_map->odm_group_depth = be32_to_cpup(p++);
> - data_map->odm_mirror_cnt = be32_to_cpup(p++);
> - data_map->odm_raid_algorithm = be32_to_cpup(p++);
> - dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u "
> - "odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n",
> - __func__,
> - data_map->odm_num_comps,
> - (unsigned long long)data_map->odm_stripe_unit,
> - data_map->odm_group_width,
> - data_map->odm_group_depth,
> - data_map->odm_mirror_cnt,
> - data_map->odm_raid_algorithm);
> - return p;
> -}
> -
> -int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
> - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr)
> -{
> - __be32 *p;
> -
> - memset(iter, 0, sizeof(*iter));
> -
> - p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4);
> - if (unlikely(!p))
> - return -EINVAL;
> -
> - p = _osd_xdr_decode_data_map(p, &layout->olo_map);
> - layout->olo_comps_index = be32_to_cpup(p++);
> - layout->olo_num_comps = be32_to_cpup(p++);
> - dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
> - layout->olo_comps_index, layout->olo_num_comps);
> -
> - iter->total_comps = layout->olo_num_comps;
> - return 0;
> -}
> -
> -bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
> - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
> - int *err)
> -{
> - BUG_ON(iter->decoded_comps > iter->total_comps);
> - if (iter->decoded_comps == iter->total_comps)
> - return false;
> -
> - *err = _osd_xdr_decode_object_cred(comp, xdr);
> - if (unlikely(*err)) {
> - dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d "
> - "total_comps=%d\n", __func__, *err,
> - iter->decoded_comps, iter->total_comps);
> - return false; /* stop the loop */
> - }
> - dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx "
> - "key_len=%u cap_len=%u\n",
> - __func__,
> - _DEVID_LO(&comp->oc_object_id.oid_device_id),
> - _DEVID_HI(&comp->oc_object_id.oid_device_id),
> - comp->oc_object_id.oid_partition_id,
> - comp->oc_object_id.oid_object_id,
> - comp->oc_cap_key.cred_len, comp->oc_cap.cred_len);
> -
> - iter->decoded_comps++;
> - return true;
> -}
> -
> -/*
> - * Get Device Information Decoding
> - *
> - * Note: since Device Information is currently done synchronously, all
> - * variable strings fields are left inside the rpc buffer and are only
> - * pointed to by the pnfs_osd_deviceaddr members. So the read buffer
> - * should not be freed while the returned information is in use.
> - */
> -/*
> - *struct nfs4_string {
> - * unsigned int len;
> - * char *data;
> - *}; // size [variable]
> - * NOTE: Returned string points to inside the XDR buffer
> - */
> -static __be32 *
> -__read_u8_opaque(__be32 *p, struct nfs4_string *str)
> -{
> - str->len = be32_to_cpup(p++);
> - str->data = (char *)p;
> -
> - p += XDR_QUADLEN(str->len);
> - return p;
> -}
> -
> -/*
> - * struct pnfs_osd_targetid {
> - * u32 oti_type;
> - * struct nfs4_string oti_scsi_device_id;
> - * };// size 4 + [variable]
> - */
> -static __be32 *
> -__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid)
> -{
> - u32 oti_type;
> -
> - oti_type = be32_to_cpup(p++);
> - targetid->oti_type = oti_type;
> -
> - switch (oti_type) {
> - case OBJ_TARGET_SCSI_NAME:
> - case OBJ_TARGET_SCSI_DEVICE_ID:
> - p = __read_u8_opaque(p, &targetid->oti_scsi_device_id);
> - }
> -
> - return p;
> -}
> -
> -/*
> - * struct pnfs_osd_net_addr {
> - * struct nfs4_string r_netid;
> - * struct nfs4_string r_addr;
> - * };
> - */
> -static __be32 *
> -__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr)
> -{
> - p = __read_u8_opaque(p, &netaddr->r_netid);
> - p = __read_u8_opaque(p, &netaddr->r_addr);
> -
> - return p;
> -}
> -
> -/*
> - * struct pnfs_osd_targetaddr {
> - * u32 ota_available;
> - * struct pnfs_osd_net_addr ota_netaddr;
> - * };
> - */
> -static __be32 *
> -__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr)
> -{
> - u32 ota_available;
> -
> - ota_available = be32_to_cpup(p++);
> - targetaddr->ota_available = ota_available;
> -
> - if (ota_available)
> - p = __read_net_addr(p, &targetaddr->ota_netaddr);
> -
> -
> - return p;
> -}
> -
> -/*
> - * struct pnfs_osd_deviceaddr {
> - * struct pnfs_osd_targetid oda_targetid;
> - * struct pnfs_osd_targetaddr oda_targetaddr;
> - * u8 oda_lun[8];
> - * struct nfs4_string oda_systemid;
> - * struct pnfs_osd_object_cred oda_root_obj_cred;
> - * struct nfs4_string oda_osdname;
> - * };
> - */
> -
> -/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does
> - * not have an xdr_stream
> - */
> -static __be32 *
> -__read_opaque_cred(__be32 *p,
> - struct pnfs_osd_opaque_cred *opaque_cred)
> -{
> - opaque_cred->cred_len = be32_to_cpu(*p++);
> - opaque_cred->cred = p;
> - return p + XDR_QUADLEN(opaque_cred->cred_len);
> -}
> -
> -static __be32 *
> -__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp)
> -{
> - p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
> - comp->oc_osd_version = be32_to_cpup(p++);
> - comp->oc_cap_key_sec = be32_to_cpup(p++);
> -
> - p = __read_opaque_cred(p, &comp->oc_cap_key);
> - p = __read_opaque_cred(p, &comp->oc_cap);
> - return p;
> -}
> -
> -void pnfs_osd_xdr_decode_deviceaddr(
> - struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p)
> -{
> - p = __read_targetid(p, &deviceaddr->oda_targetid);
> -
> - p = __read_targetaddr(p, &deviceaddr->oda_targetaddr);
> -
> - p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun,
> - sizeof(deviceaddr->oda_lun));
> -
> - p = __read_u8_opaque(p, &deviceaddr->oda_systemid);
> -
> - p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred);
> -
> - p = __read_u8_opaque(p, &deviceaddr->oda_osdname);
> -
> - /* libosd likes this terminated in dbg. It's last, so no problems */
> - deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0;
> -}
> -
> -/*
> - * struct pnfs_osd_layoutupdate {
> - * u32 dsu_valid;
> - * s64 dsu_delta;
> - * u32 olu_ioerr_flag;
> - * }; xdr size 4 + 8 + 4
> - */
> -int
> -pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
> - struct pnfs_osd_layoutupdate *lou)
> -{
> - __be32 *p = xdr_reserve_space(xdr, 4 + 8 + 4);
> -
> - if (!p)
> - return -E2BIG;
> -
> - *p++ = cpu_to_be32(lou->dsu_valid);
> - if (lou->dsu_valid)
> - p = xdr_encode_hyper(p, lou->dsu_delta);
> - *p++ = cpu_to_be32(lou->olu_ioerr_flag);
> - return 0;
> -}
> -
> -/*
> - * struct pnfs_osd_objid {
> - * struct nfs4_deviceid oid_device_id;
> - * u64 oid_partition_id;
> - * u64 oid_object_id;
> - * }; // xdr size 32 bytes
> - */
> -static inline __be32 *
> -pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id)
> -{
> - p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data,
> - sizeof(object_id->oid_device_id.data));
> - p = xdr_encode_hyper(p, object_id->oid_partition_id);
> - p = xdr_encode_hyper(p, object_id->oid_object_id);
> -
> - return p;
> -}
> -
> -/*
> - * struct pnfs_osd_ioerr {
> - * struct pnfs_osd_objid oer_component;
> - * u64 oer_comp_offset;
> - * u64 oer_comp_length;
> - * u32 oer_iswrite;
> - * u32 oer_errno;
> - * }; // xdr size 32 + 24 bytes
> - */
> -void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr)
> -{
> - p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component);
> - p = xdr_encode_hyper(p, ioerr->oer_comp_offset);
> - p = xdr_encode_hyper(p, ioerr->oer_comp_length);
> - *p++ = cpu_to_be32(ioerr->oer_iswrite);
> - *p = cpu_to_be32(ioerr->oer_errno);
> -}
> -
> -__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr)
> -{
> - __be32 *p;
> -
> - p = xdr_reserve_space(xdr, 32 + 24);
> - if (unlikely(!p))
> - dprintk("%s: out of xdr space\n", __func__);
> -
> - return p;
> -}
> --
> 2.11.0
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/4] nfs: remove the objlayout driver
2017-04-21 7:27 ` Valentin Rothberg
@ 2017-04-21 10:50 ` Christoph Hellwig
0 siblings, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-21 10:50 UTC (permalink / raw)
To: Valentin Rothberg
Cc: Christoph Hellwig, ooo, martin.petersen, trond.myklebust, axboe,
osd-dev, linux-nfs, linux-scsi, linux-block, LKML
On Fri, Apr 21, 2017 at 09:27:11AM +0200, Valentin Rothberg wrote:
> Hi Christoph,
>
> I just came across this patch in linux-next commit 6d22323b2e9f.
> scripts/checkkconfigsymbols.py reports that there is a leftover
> reference on PNFS_OBJLAYOUT in fs/exofs/Kconfig.ore line 10 (depends
> on EXOFS_FS || PNFS_OBJLAYOUT). I assume that this reference can
> safely be removed now? If you want to I can send a trivial patch
> removing it.
Yes, please do.
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/4] nfs: remove the objlayout driver
2017-04-20 20:18 ` Trond Myklebust
@ 2017-04-21 10:51 ` Christoph Hellwig
2017-04-21 13:17 ` Boaz Harrosh
1 sibling, 0 replies; 16+ messages in thread
From: Christoph Hellwig @ 2017-04-21 10:51 UTC (permalink / raw)
To: Trond Myklebust
Cc: hch, ooo, martin.petersen, axboe, linux-scsi, linux-kernel,
osd-dev, linux-block, linux-nfs
On Thu, Apr 20, 2017 at 08:18:28PM +0000, Trond Myklebust wrote:
> OK. I'm applying this patch for the 4.12 merge window. If, as Boaz
> suggests, there is still an interest in exofs, then I suggest we put
> that to the test by moving it into the STAGING area, to see if someone
> will step up to maintain it.
I think that would be a good idea, I'll can prepare a patch for the
net merge window.
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/4] nfs: remove the objlayout driver
2017-04-20 20:18 ` Trond Myklebust
2017-04-21 10:51 ` Christoph Hellwig
@ 2017-04-21 13:17 ` Boaz Harrosh
[not found] ` <B6CCD2A9-4691-45DC-AD60-E9A2ECDE22D3@primarydata.com>
1 sibling, 1 reply; 16+ messages in thread
From: Boaz Harrosh @ 2017-04-21 13:17 UTC (permalink / raw)
To: Trond Myklebust, hch, martin.petersen, axboe
Cc: linux-scsi, linux-kernel, osd-dev, linux-block, linux-nfs
On 04/20/2017 11:18 PM, Trond Myklebust wrote:
<>
>
> OK. I'm applying this patch for the 4.12 merge window.
That is understandable this code was not tested for a long while
> If, as Boaz
> suggests, there is still an interest in exofs, then I suggest we put
> that to the test by moving it into the STAGING area, to see if someone
> will step up to maintain it.
>
I do not understand what you mean by "someone will maintain it"
What is it that is missing in exofs that you see needs development?
As I said I regularly run and test this FS and update as things advance
there where no new fixtures for a while, but no regressions either.
Please explain what it means "will maintain it"
> Cheers
> Trond
>
Thanks
Boaz
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH 3/4] nfs: remove the objlayout driver
[not found] ` <B6CCD2A9-4691-45DC-AD60-E9A2ECDE22D3@primarydata.com>
@ 2017-04-23 9:36 ` Boaz Harrosh
0 siblings, 0 replies; 16+ messages in thread
From: Boaz Harrosh @ 2017-04-23 9:36 UTC (permalink / raw)
To: Trond Myklebust
Cc: hch, Martin Petersen, Jens Axboe, linux-scsi,
Linux Kernel Mailing List, linux-block, Linux NFS Mailing List
On 04/21/2017 05:00 PM, Trond Myklebust wrote:
> Maintenance is not development. It’s about doing all the followup
> _after_ the feature is declared to be developed. That’s been missing
> for quite some time in the case of the OSD pNFS code, which is why
> I’m not even bothering to consider staging. If you are saying you are
> still maintaining exofs, and want to continue doing so, then great,
> but note that there is a file called BUGS in that directory that has
> been untouched since 2008, and that’s why I thing staging is a good
> idea.
>
No, the BUGS file is just stale. As you said was not ever updated. All
the bugs (1) in there do no longer exist for a long long time.
I will send a patch to remove the file.
Yes I maintain this fs. It has the complete fixture list, of what was
first intended. I keep running it every major kernel release to make
sure it actually runs, and there are no regressions.
If this FS stands in the way of any new development please anyone
contact me and I will help in the conversion. Of exofs and the
osd-uld.
Thanks
Boaz
^ permalink raw reply [flat|nested] 16+ messages in thread
end of thread, other threads:[~2017-04-23 9:36 UTC | newest]
Thread overview: 16+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-04-12 16:01 RFC: drop the T10 OSD code and its users Christoph Hellwig
2017-04-12 16:01 ` [PATCH 1/4] block: remove the osdblk driver Christoph Hellwig
2017-04-19 7:21 ` Boaz Harrosh
2017-04-12 16:01 ` [PATCH 2/4] fs: remove exofs Christoph Hellwig
2017-04-12 16:01 ` [PATCH 3/4] nfs: remove the objlayout driver Christoph Hellwig
2017-04-20 20:18 ` Trond Myklebust
2017-04-21 10:51 ` Christoph Hellwig
2017-04-21 13:17 ` Boaz Harrosh
[not found] ` <B6CCD2A9-4691-45DC-AD60-E9A2ECDE22D3@primarydata.com>
2017-04-23 9:36 ` Boaz Harrosh
2017-04-21 7:27 ` Valentin Rothberg
2017-04-21 10:50 ` Christoph Hellwig
2017-04-12 16:01 ` [PATCH 4/4] scsi: remove the SCSI OSD library Christoph Hellwig
2017-04-14 2:27 ` RFC: drop the T10 OSD code and its users Martin K. Petersen
2017-04-18 16:24 ` Boaz Harrosh
2017-04-18 17:06 ` Chandy, John
2017-04-19 15:11 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).