2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2004 Red Hat UK Ltd.
|
|
|
|
*
|
|
|
|
* This file is released under the GPL.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef DM_BIO_LIST_H
|
|
|
|
#define DM_BIO_LIST_H
|
|
|
|
|
|
|
|
#include <linux/bio.h>
|
|
|
|
|
|
|
|
struct bio_list {
|
|
|
|
struct bio *head;
|
|
|
|
struct bio *tail;
|
|
|
|
};
|
|
|
|
|
2007-05-09 17:33:05 +08:00
|
|
|
static inline int bio_list_empty(const struct bio_list *bl)
|
|
|
|
{
|
|
|
|
return bl->head == NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define BIO_LIST_INIT { .head = NULL, .tail = NULL }
|
|
|
|
|
|
|
|
#define BIO_LIST(bl) \
|
|
|
|
struct bio_list bl = BIO_LIST_INIT
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void bio_list_init(struct bio_list *bl)
|
|
|
|
{
|
|
|
|
bl->head = bl->tail = NULL;
|
|
|
|
}
|
|
|
|
|
2007-05-09 17:33:05 +08:00
|
|
|
#define bio_list_for_each(bio, bl) \
|
2007-07-13 00:26:19 +08:00
|
|
|
for (bio = (bl)->head; bio; bio = bio->bi_next)
|
2007-05-09 17:33:05 +08:00
|
|
|
|
|
|
|
static inline unsigned bio_list_size(const struct bio_list *bl)
|
|
|
|
{
|
|
|
|
unsigned sz = 0;
|
|
|
|
struct bio *bio;
|
|
|
|
|
|
|
|
bio_list_for_each(bio, bl)
|
|
|
|
sz++;
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
|
|
|
|
{
|
|
|
|
bio->bi_next = NULL;
|
|
|
|
|
|
|
|
if (bl->tail)
|
|
|
|
bl->tail->bi_next = bio;
|
|
|
|
else
|
|
|
|
bl->head = bio;
|
|
|
|
|
|
|
|
bl->tail = bio;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
|
|
|
|
{
|
2005-11-22 13:32:36 +08:00
|
|
|
if (!bl2->head)
|
|
|
|
return;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (bl->tail)
|
|
|
|
bl->tail->bi_next = bl2->head;
|
|
|
|
else
|
|
|
|
bl->head = bl2->head;
|
|
|
|
|
|
|
|
bl->tail = bl2->tail;
|
|
|
|
}
|
|
|
|
|
[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 18:41:09 +08:00
|
|
|
static inline void bio_list_merge_head(struct bio_list *bl,
|
|
|
|
struct bio_list *bl2)
|
|
|
|
{
|
|
|
|
if (!bl2->head)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (bl->head)
|
|
|
|
bl2->tail->bi_next = bl->head;
|
|
|
|
else
|
|
|
|
bl->tail = bl2->tail;
|
|
|
|
|
|
|
|
bl->head = bl2->head;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline struct bio *bio_list_pop(struct bio_list *bl)
|
|
|
|
{
|
|
|
|
struct bio *bio = bl->head;
|
|
|
|
|
|
|
|
if (bio) {
|
|
|
|
bl->head = bl->head->bi_next;
|
|
|
|
if (!bl->head)
|
|
|
|
bl->tail = NULL;
|
|
|
|
|
|
|
|
bio->bi_next = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return bio;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct bio *bio_list_get(struct bio_list *bl)
|
|
|
|
{
|
|
|
|
struct bio *bio = bl->head;
|
|
|
|
|
|
|
|
bl->head = bl->tail = NULL;
|
|
|
|
|
|
|
|
return bio;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|