2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* Internal header file for device mapper
|
|
|
|
*
|
|
|
|
* Copyright (C) 2001, 2002 Sistina Software
|
2006-06-26 09:27:32 +02:00
|
|
|
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
|
|
|
* This file is released under the LGPL.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef DM_INTERNAL_H
|
|
|
|
#define DM_INTERNAL_H
|
|
|
|
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/device-mapper.h>
|
|
|
|
#include <linux/list.h>
|
|
|
|
#include <linux/blkdev.h>
|
2006-03-27 11:17:54 +02:00
|
|
|
#include <linux/hdreg.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
#define DM_NAME "device-mapper"
|
2006-06-26 09:27:35 +02:00
|
|
|
|
2007-07-12 18:28:42 +02:00
|
|
|
#define DMERR(f, arg...) \
|
|
|
|
printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
|
|
|
|
#define DMERR_LIMIT(f, arg...) \
|
|
|
|
do { \
|
|
|
|
if (printk_ratelimit()) \
|
|
|
|
printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " \
|
|
|
|
f "\n", ## arg); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define DMWARN(f, arg...) \
|
|
|
|
printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
|
|
|
|
#define DMWARN_LIMIT(f, arg...) \
|
|
|
|
do { \
|
|
|
|
if (printk_ratelimit()) \
|
|
|
|
printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " \
|
|
|
|
f "\n", ## arg); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define DMINFO(f, arg...) \
|
|
|
|
printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
|
|
|
|
#define DMINFO_LIMIT(f, arg...) \
|
|
|
|
do { \
|
|
|
|
if (printk_ratelimit()) \
|
|
|
|
printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f \
|
|
|
|
"\n", ## arg); \
|
|
|
|
} while (0)
|
|
|
|
|
2006-10-03 10:15:35 +02:00
|
|
|
#ifdef CONFIG_DM_DEBUG
|
2007-07-12 18:28:42 +02:00
|
|
|
# define DMDEBUG(f, arg...) \
|
|
|
|
printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX " DEBUG: " f "\n", ## arg)
|
|
|
|
# define DMDEBUG_LIMIT(f, arg...) \
|
|
|
|
do { \
|
|
|
|
if (printk_ratelimit()) \
|
|
|
|
printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX ": " f \
|
|
|
|
"\n", ## arg); \
|
|
|
|
} while (0)
|
2006-10-03 10:15:35 +02:00
|
|
|
#else
|
|
|
|
# define DMDEBUG(f, arg...) do {} while (0)
|
2007-07-12 18:28:42 +02:00
|
|
|
# define DMDEBUG_LIMIT(f, arg...) do {} while (0)
|
2006-10-03 10:15:35 +02:00
|
|
|
#endif
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
#define DMEMIT(x...) sz += ((sz >= maxlen) ? \
|
|
|
|
0 : scnprintf(result + sz, maxlen - sz, x))
|
|
|
|
|
|
|
|
#define SECTOR_SHIFT 9
|
|
|
|
|
2006-12-08 11:41:05 +01:00
|
|
|
/*
|
|
|
|
* Definitions of return values from target end_io function.
|
|
|
|
*/
|
|
|
|
#define DM_ENDIO_INCOMPLETE 1
|
[PATCH] dm: suspend: add noflush pushback
In device-mapper I/O is sometimes queued within targets for later processing.
For example the multipath target can be configured to store I/O when no paths
are available instead of returning it -EIO.
This patch allows the device-mapper core to instruct a target to transfer the
contents of any such in-target queue back into the core. This frees up the
resources used by the target so the core can replace that target with an
alternative one and then resend the I/O to it. Without this patch the only
way to change the target in such circumstances involves returning the I/O with
an error back to the filesystem/application. In the multipath case, this
patch will let us add new paths for existing I/O to try after all the existing
paths have failed.
DMF_NOFLUSH_SUSPENDING
----------------------
If the DM_NOFLUSH_FLAG ioctl option is specified at suspend time, the
DMF_NOFLUSH_SUSPENDING flag is set in md->flags during dm_suspend(). It
is always cleared before dm_suspend() returns.
The flag must be visible while the target is flushing pending I/Os so it
is set before presuspend where the flush starts and unset after the wait
for md->pending where the flush ends.
Target drivers can check this flag by calling dm_noflush_suspending().
DM_MAPIO_REQUEUE / DM_ENDIO_REQUEUE
-----------------------------------
A target's map() function can now return DM_MAPIO_REQUEUE to request the
device mapper core queue the bio.
Similarly, a target's end_io() function can return DM_ENDIO_REQUEUE to request
the same. This has been labelled 'pushback'.
The __map_bio() and clone_endio() functions in the core treat these return
values as errors and call dec_pending() to end the I/O.
dec_pending
-----------
dec_pending() saves the pushback request in struct dm_io->error. Once all
the split clones have ended, dec_pending() will put the original bio on
the md->pushback list. Note that this supercedes any I/O errors.
It is possible for the suspend with DM_NOFLUSH_FLAG to be aborted while
in progress (e.g. by user interrupt). dec_pending() checks for this and
returns -EIO if it happened.
pushdback list and pushback_lock
--------------------------------
The bio is queued on md->pushback temporarily in dec_pending(), and after
all pending I/Os return, md->pushback is merged into md->deferred in
dm_suspend() for re-issuing at resume time.
md->pushback_lock protects md->pushback.
The lock should be held with irq disabled because dec_pending() can be
called from interrupt context.
Queueing bios to md->pushback in dec_pending() must be done atomically
with the check for DMF_NOFLUSH_SUSPENDING flag. So md->pushback_lock is
held when checking the flag. Otherwise dec_pending() may queue a bio to
md->pushback after the interrupted dm_suspend() flushes md->pushback.
Then the bio would be left in md->pushback.
Flag setting in dm_suspend() can be done without md->pushback_lock because
the flag is checked only after presuspend and the set value is already
made visible via the target's presuspend function.
The flag can be checked without md->pushback_lock (e.g. the first part of
the dec_pending() or target drivers), because the flag is checked again
with md->pushback_lock held when the bio is really queued to md->pushback
as described above. So even if the flag is cleared after the lockless
checkings, the bio isn't left in md->pushback but returned to applications
with -EIO.
Other notes on the current patch
--------------------------------
- md->pushback is added to the struct mapped_device instead of using
md->deferred directly because md->io_lock which protects md->deferred is
rw_semaphore and can't be used in interrupt context like dec_pending(),
and md->io_lock protects the DMF_BLOCK_IO flag of md->flags too.
- Don't issue lock_fs() in dm_suspend() if the DM_NOFLUSH_FLAG
ioctl option is specified, because I/Os generated by lock_fs() would be
pushed back and never return if there were no valid devices.
- If an error occurs in dm_suspend() after the DMF_NOFLUSH_SUSPENDING
flag is set, md->pushback must be flushed because I/Os may be queued to
the list already. (flush_and_out label in dm_suspend())
Test results
------------
I have tested using multipath target with the next patch.
The following tests are for regression/compatibility:
- I/Os succeed when valid paths exist;
- I/Os fail when there are no valid paths and queue_if_no_path is not
set;
- I/Os are queued in the multipath target when there are no valid paths and
queue_if_no_path is set;
- The queued I/Os above fail when suspend is issued without the
DM_NOFLUSH_FLAG ioctl option. I/Os spanning 2 multipath targets also
fail.
The following tests are for the normal code path of new pushback feature:
- Queued I/Os in the multipath target are flushed from the target
but don't return when suspend is issued with the DM_NOFLUSH_FLAG
ioctl option;
- The I/Os above are queued in the multipath target again when
resume is issued without path recovery;
- The I/Os above succeed when resume is issued after path recovery
or table load;
- Queued I/Os in the multipath target succeed when resume is issued
with the DM_NOFLUSH_FLAG ioctl option after table load. I/Os
spanning 2 multipath targets also succeed.
The following tests are for the error paths of the new pushback feature:
- When the bdget_disk() fails in dm_suspend(), the
DMF_NOFLUSH_SUSPENDING flag is cleared and I/Os already queued to the
pushback list are flushed properly.
- When suspend with the DM_NOFLUSH_FLAG ioctl option is interrupted,
o I/Os which had already been queued to the pushback list
at the time don't return, and are re-issued at resume time;
o I/Os which hadn't been returned at the time return with EIO.
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Cc: dm-devel@redhat.com
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 11:41:09 +01:00
|
|
|
#define DM_ENDIO_REQUEUE 2
|
2006-12-08 11:41:05 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Definitions of return values from target map function.
|
|
|
|
*/
|
|
|
|
#define DM_MAPIO_SUBMITTED 0
|
|
|
|
#define DM_MAPIO_REMAPPED 1
|
[PATCH] dm: suspend: add noflush pushback
In device-mapper I/O is sometimes queued within targets for later processing.
For example the multipath target can be configured to store I/O when no paths
are available instead of returning it -EIO.
This patch allows the device-mapper core to instruct a target to transfer the
contents of any such in-target queue back into the core. This frees up the
resources used by the target so the core can replace that target with an
alternative one and then resend the I/O to it. Without this patch the only
way to change the target in such circumstances involves returning the I/O with
an error back to the filesystem/application. In the multipath case, this
patch will let us add new paths for existing I/O to try after all the existing
paths have failed.
DMF_NOFLUSH_SUSPENDING
----------------------
If the DM_NOFLUSH_FLAG ioctl option is specified at suspend time, the
DMF_NOFLUSH_SUSPENDING flag is set in md->flags during dm_suspend(). It
is always cleared before dm_suspend() returns.
The flag must be visible while the target is flushing pending I/Os so it
is set before presuspend where the flush starts and unset after the wait
for md->pending where the flush ends.
Target drivers can check this flag by calling dm_noflush_suspending().
DM_MAPIO_REQUEUE / DM_ENDIO_REQUEUE
-----------------------------------
A target's map() function can now return DM_MAPIO_REQUEUE to request the
device mapper core queue the bio.
Similarly, a target's end_io() function can return DM_ENDIO_REQUEUE to request
the same. This has been labelled 'pushback'.
The __map_bio() and clone_endio() functions in the core treat these return
values as errors and call dec_pending() to end the I/O.
dec_pending
-----------
dec_pending() saves the pushback request in struct dm_io->error. Once all
the split clones have ended, dec_pending() will put the original bio on
the md->pushback list. Note that this supercedes any I/O errors.
It is possible for the suspend with DM_NOFLUSH_FLAG to be aborted while
in progress (e.g. by user interrupt). dec_pending() checks for this and
returns -EIO if it happened.
pushdback list and pushback_lock
--------------------------------
The bio is queued on md->pushback temporarily in dec_pending(), and after
all pending I/Os return, md->pushback is merged into md->deferred in
dm_suspend() for re-issuing at resume time.
md->pushback_lock protects md->pushback.
The lock should be held with irq disabled because dec_pending() can be
called from interrupt context.
Queueing bios to md->pushback in dec_pending() must be done atomically
with the check for DMF_NOFLUSH_SUSPENDING flag. So md->pushback_lock is
held when checking the flag. Otherwise dec_pending() may queue a bio to
md->pushback after the interrupted dm_suspend() flushes md->pushback.
Then the bio would be left in md->pushback.
Flag setting in dm_suspend() can be done without md->pushback_lock because
the flag is checked only after presuspend and the set value is already
made visible via the target's presuspend function.
The flag can be checked without md->pushback_lock (e.g. the first part of
the dec_pending() or target drivers), because the flag is checked again
with md->pushback_lock held when the bio is really queued to md->pushback
as described above. So even if the flag is cleared after the lockless
checkings, the bio isn't left in md->pushback but returned to applications
with -EIO.
Other notes on the current patch
--------------------------------
- md->pushback is added to the struct mapped_device instead of using
md->deferred directly because md->io_lock which protects md->deferred is
rw_semaphore and can't be used in interrupt context like dec_pending(),
and md->io_lock protects the DMF_BLOCK_IO flag of md->flags too.
- Don't issue lock_fs() in dm_suspend() if the DM_NOFLUSH_FLAG
ioctl option is specified, because I/Os generated by lock_fs() would be
pushed back and never return if there were no valid devices.
- If an error occurs in dm_suspend() after the DMF_NOFLUSH_SUSPENDING
flag is set, md->pushback must be flushed because I/Os may be queued to
the list already. (flush_and_out label in dm_suspend())
Test results
------------
I have tested using multipath target with the next patch.
The following tests are for regression/compatibility:
- I/Os succeed when valid paths exist;
- I/Os fail when there are no valid paths and queue_if_no_path is not
set;
- I/Os are queued in the multipath target when there are no valid paths and
queue_if_no_path is set;
- The queued I/Os above fail when suspend is issued without the
DM_NOFLUSH_FLAG ioctl option. I/Os spanning 2 multipath targets also
fail.
The following tests are for the normal code path of new pushback feature:
- Queued I/Os in the multipath target are flushed from the target
but don't return when suspend is issued with the DM_NOFLUSH_FLAG
ioctl option;
- The I/Os above are queued in the multipath target again when
resume is issued without path recovery;
- The I/Os above succeed when resume is issued after path recovery
or table load;
- Queued I/Os in the multipath target succeed when resume is issued
with the DM_NOFLUSH_FLAG ioctl option after table load. I/Os
spanning 2 multipath targets also succeed.
The following tests are for the error paths of the new pushback feature:
- When the bdget_disk() fails in dm_suspend(), the
DMF_NOFLUSH_SUSPENDING flag is cleared and I/Os already queued to the
pushback list are flushed properly.
- When suspend with the DM_NOFLUSH_FLAG ioctl option is interrupted,
o I/Os which had already been queued to the pushback list
at the time don't return, and are re-issued at resume time;
o I/Os which hadn't been returned at the time return with EIO.
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Cc: dm-devel@redhat.com
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 11:41:09 +01:00
|
|
|
#define DM_MAPIO_REQUEUE DM_ENDIO_REQUEUE
|
2006-12-08 11:41:05 +01:00
|
|
|
|
2006-12-08 11:41:04 +01:00
|
|
|
/*
|
|
|
|
* Suspend feature flags
|
|
|
|
*/
|
|
|
|
#define DM_SUSPEND_LOCKFS_FLAG (1 << 0)
|
2006-12-08 11:41:07 +01:00
|
|
|
#define DM_SUSPEND_NOFLUSH_FLAG (1 << 1)
|
2006-12-08 11:41:04 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* List of devices that a metadevice uses and should open/close.
|
|
|
|
*/
|
|
|
|
struct dm_dev {
|
|
|
|
struct list_head list;
|
|
|
|
|
|
|
|
atomic_t count;
|
|
|
|
int mode;
|
|
|
|
struct block_device *bdev;
|
|
|
|
char name[16];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct dm_table;
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
2006-06-26 09:27:33 +02:00
|
|
|
* Internal table functions.
|
2005-04-17 00:20:36 +02:00
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
void dm_table_event_callback(struct dm_table *t,
|
|
|
|
void (*fn)(void *), void *context);
|
|
|
|
struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index);
|
|
|
|
struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector);
|
|
|
|
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q);
|
|
|
|
struct list_head *dm_table_get_devices(struct dm_table *t);
|
|
|
|
void dm_table_presuspend_targets(struct dm_table *t);
|
|
|
|
void dm_table_postsuspend_targets(struct dm_table *t);
|
2006-10-03 10:15:36 +02:00
|
|
|
int dm_table_resume_targets(struct dm_table *t);
|
2005-04-17 00:20:36 +02:00
|
|
|
int dm_table_any_congested(struct dm_table *t, int bdi_bits);
|
|
|
|
void dm_table_unplug_all(struct dm_table *t);
|
|
|
|
int dm_table_flush_all(struct dm_table *t);
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* A registry of target types.
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
int dm_target_init(void);
|
|
|
|
void dm_target_exit(void);
|
|
|
|
struct target_type *dm_get_target_type(const char *name);
|
|
|
|
void dm_put_target_type(struct target_type *t);
|
|
|
|
int dm_target_iterate(void (*iter_func)(struct target_type *tt,
|
|
|
|
void *param), void *param);
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* Useful inlines.
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
static inline int array_too_big(unsigned long fixed, unsigned long obj,
|
|
|
|
unsigned long num)
|
|
|
|
{
|
|
|
|
return (num > (ULONG_MAX - fixed) / obj);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ceiling(n / sz)
|
|
|
|
*/
|
|
|
|
#define dm_div_up(n, sz) (((n) + (sz) - 1) / (sz))
|
|
|
|
|
|
|
|
#define dm_sector_div_up(n, sz) ( \
|
|
|
|
{ \
|
|
|
|
sector_t _r = ((n) + (sz) - 1); \
|
|
|
|
sector_div(_r, (sz)); \
|
|
|
|
_r; \
|
|
|
|
} \
|
|
|
|
)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ceiling(n / size) * size
|
|
|
|
*/
|
|
|
|
#define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz))
|
|
|
|
|
|
|
|
static inline sector_t to_sector(unsigned long n)
|
|
|
|
{
|
|
|
|
return (n >> 9);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline unsigned long to_bytes(sector_t n)
|
|
|
|
{
|
|
|
|
return (n << 9);
|
|
|
|
}
|
|
|
|
|
|
|
|
int dm_split_args(int *argc, char ***argvp, char *input);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The device-mapper can be driven through one of two interfaces;
|
|
|
|
* ioctl or filesystem, depending which patch you have applied.
|
|
|
|
*/
|
|
|
|
int dm_interface_init(void);
|
|
|
|
void dm_interface_exit(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Targets for linear and striped mappings
|
|
|
|
*/
|
|
|
|
int dm_linear_init(void);
|
|
|
|
void dm_linear_exit(void);
|
|
|
|
|
|
|
|
int dm_stripe_init(void);
|
|
|
|
void dm_stripe_exit(void);
|
|
|
|
|
|
|
|
void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
|
|
|
|
union map_info *dm_get_mapinfo(struct bio *bio);
|
2006-06-26 09:27:34 +02:00
|
|
|
int dm_open_count(struct mapped_device *md);
|
|
|
|
int dm_lock_for_deletion(struct mapped_device *md);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
#endif
|