cec47e3d4a
This patch adds core functions for request-based dm.
When struct mapped device (md) is initialized, md->queue has
an I/O scheduler and the following functions are used for
request-based dm as the queue functions:
make_request_fn: dm_make_request()
pref_fn: dm_prep_fn()
request_fn: dm_request_fn()
softirq_done_fn: dm_softirq_done()
lld_busy_fn: dm_lld_busy()
Actual initializations are done in another patch (PATCH 2).
Below is a brief summary of how request-based dm behaves, including:
- making request from bio
- cloning, mapping and dispatching request
- completing request and bio
- suspending md
- resuming md
bio to request
==============
md->queue->make_request_fn() (dm_make_request()) calls __make_request()
for a bio submitted to the md.
Then, the bio is kept in the queue as a new request or merged into
another request in the queue if possible.
Cloning and Mapping
===================
Cloning and mapping are done in md->queue->request_fn() (dm_request_fn()),
when requests are dispatched after they are sorted by the I/O scheduler.
dm_request_fn() checks busy state of underlying devices using
target's busy() function and stops dispatching requests to keep them
on the dm device's queue if busy.
It helps better I/O merging, since no merge is done for a request
once it is dispatched to underlying devices.
Actual cloning and mapping are done in dm_prep_fn() and map_request()
called from dm_request_fn().
dm_prep_fn() clones not only request but also bios of the request
so that dm can hold bio completion in error cases and prevent
the bio submitter from noticing the error.
(See the "Completion" section below for details.)
After the cloning, the clone is mapped by target's map_rq() function
and inserted to underlying device's queue using
blk_insert_cloned_request().
Completion
==========
Request completion can be hooked by rq->end_io(), but then, all bios
in the request will have been completed even error cases, and the bio
submitter will have noticed the error.
To prevent the bio completion in error cases, request-based dm clones
both bio and request and hooks both bio->bi_end_io() and rq->end_io():
bio->bi_end_io(): end_clone_bio()
rq->end_io(): end_clone_request()
Summary of the request completion flow is below:
blk_end_request() for a clone request
=> blk_update_request()
=> bio->bi_end_io() == end_clone_bio() for each clone bio
=> Free the clone bio
=> Success: Complete the original bio (blk_update_request())
Error: Don't complete the original bio
=> blk_finish_request()
=> rq->end_io() == end_clone_request()
=> blk_complete_request()
=> dm_softirq_done()
=> Free the clone request
=> Success: Complete the original request (blk_end_request())
Error: Requeue the original request
end_clone_bio() completes the original request on the size of
the original bio in successful cases.
Even if all bios in the original request are completed by that
completion, the original request must not be completed yet to keep
the ordering of request completion for the stacking.
So end_clone_bio() uses blk_update_request() instead of
blk_end_request().
In error cases, end_clone_bio() doesn't complete the original bio.
It just frees the cloned bio and gives over the error handling to
end_clone_request().
end_clone_request(), which is called with queue lock held, completes
the clone request and the original request in a softirq context
(dm_softirq_done()), which has no queue lock, to avoid a deadlock
issue on submission of another request during the completion:
- The submitted request may be mapped to the same device
- Request submission requires queue lock, but the queue lock
has been held by itself and it doesn't know that
The clone request has no clone bio when dm_softirq_done() is called.
So target drivers can't resubmit it again even error cases.
Instead, they can ask dm core for requeueing and remapping
the original request in that cases.
suspend
=======
Request-based dm uses stopping md->queue as suspend of the md.
For noflush suspend, just stops md->queue.
For flush suspend, inserts a marker request to the tail of md->queue.
And dispatches all requests in md->queue until the marker comes to
the front of md->queue. Then, stops dispatching request and waits
for the all dispatched requests to complete.
After that, completes the marker request, stops md->queue and
wake up the waiter on the suspend queue, md->wait.
resume
======
Starts md->queue.
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>
106 lines
3.1 KiB
C
106 lines
3.1 KiB
C
/*
|
|
* Internal header file for device mapper
|
|
*
|
|
* Copyright (C) 2001, 2002 Sistina Software
|
|
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
|
|
*
|
|
* 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>
|
|
#include <linux/hdreg.h>
|
|
|
|
/*
|
|
* Suspend feature flags
|
|
*/
|
|
#define DM_SUSPEND_LOCKFS_FLAG (1 << 0)
|
|
#define DM_SUSPEND_NOFLUSH_FLAG (1 << 1)
|
|
|
|
/*
|
|
* List of devices that a metadevice uses and should open/close.
|
|
*/
|
|
struct dm_dev_internal {
|
|
struct list_head list;
|
|
atomic_t count;
|
|
struct dm_dev dm_dev;
|
|
};
|
|
|
|
struct dm_table;
|
|
|
|
/*-----------------------------------------------------------------
|
|
* Internal table functions.
|
|
*---------------------------------------------------------------*/
|
|
void dm_table_destroy(struct dm_table *t);
|
|
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);
|
|
int dm_calculate_queue_limits(struct dm_table *table,
|
|
struct queue_limits *limits);
|
|
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
|
|
struct queue_limits *limits);
|
|
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);
|
|
int dm_table_resume_targets(struct dm_table *t);
|
|
int dm_table_any_congested(struct dm_table *t, int bdi_bits);
|
|
int dm_table_any_busy_target(struct dm_table *t);
|
|
|
|
/*
|
|
* To check the return value from dm_table_find_target().
|
|
*/
|
|
#define dm_target_is_valid(t) ((t)->table)
|
|
|
|
/*-----------------------------------------------------------------
|
|
* 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 *tt);
|
|
int dm_target_iterate(void (*iter_func)(struct target_type *tt,
|
|
void *param), void *param);
|
|
|
|
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);
|
|
|
|
/*
|
|
* sysfs interface
|
|
*/
|
|
int dm_sysfs_init(struct mapped_device *md);
|
|
void dm_sysfs_exit(struct mapped_device *md);
|
|
struct kobject *dm_kobject(struct mapped_device *md);
|
|
struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
|
|
|
|
/*
|
|
* 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);
|
|
|
|
int dm_open_count(struct mapped_device *md);
|
|
int dm_lock_for_deletion(struct mapped_device *md);
|
|
|
|
void dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
|
|
unsigned cookie);
|
|
|
|
int dm_kcopyd_init(void);
|
|
void dm_kcopyd_exit(void);
|
|
|
|
#endif
|