linux/drivers/md/dm.h

218 lines
6.6 KiB
C
Raw Normal View History

/*
* 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/moduleparam.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/hdreg.h>
#include <linux/completion.h>
#include <linux/kobject.h>
#include <linux/refcount.h>
#include "dm-stats.h"
/*
* Suspend feature flags
*/
#define DM_SUSPEND_LOCKFS_FLAG (1 << 0)
#define DM_SUSPEND_NOFLUSH_FLAG (1 << 1)
/*
* Status feature flags
*/
#define DM_STATUS_NOFLUSH_FLAG (1 << 0)
/*
* List of devices that a metadevice uses and should open/close.
*/
struct dm_dev_internal {
struct list_head list;
refcount_t count;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
struct dm_dev *dm_dev;
};
struct dm_table;
struct dm_md_mempools;
/*-----------------------------------------------------------------
* Internal table functions.
*---------------------------------------------------------------*/
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);
bool dm_table_has_no_data_devices(struct dm_table *table);
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_presuspend_undo_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);
enum dm_queue_mode dm_table_get_type(struct dm_table *t);
struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
bool dm_table_bio_based(struct dm_table *t);
bool dm_table_request_based(struct dm_table *t);
bool dm_table_all_blk_mq_devices(struct dm_table *t);
void dm_table_free_md_mempools(struct dm_table *t);
struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
void dm_lock_md_type(struct mapped_device *md);
void dm_unlock_md_type(struct mapped_device *md);
void dm_set_md_type(struct mapped_device *md, enum dm_queue_mode type);
enum dm_queue_mode dm_get_md_type(struct mapped_device *md);
struct target_type *dm_get_immutable_target_type(struct mapped_device *md);
int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
dm: do not initialise full request queue when bio based Change bio-based mapped devices no longer to have a fully initialized request_queue (request_fn, elevator, etc). This means bio-based DM devices no longer register elevator sysfs attributes ('iosched/' tree or 'scheduler' other than "none"). In contrast, a request-based DM device will continue to have a full request_queue and will register elevator sysfs attributes. Therefore a user can determine a DM device's type by checking if elevator sysfs attributes exist. First allocate a minimalist request_queue structure for a DM device (needed for both bio and request-based DM). Initialization of a full request_queue is deferred until it is known that the DM device is request-based, at the end of the table load sequence. Factor DM device's request_queue initialization: - common to both request-based and bio-based into dm_init_md_queue(). - specific to request-based into dm_init_request_based_queue(). The md->type_lock mutex is used to protect md->queue, in addition to md->type, during table_load(). A DM device's first table_load will establish the immutable md->type. But md->queue initialization, based on md->type, may fail at that time (because blk_init_allocated_queue cannot allocate memory). Therefore any subsequent table_load must (re)try dm_setup_md_queue independently of establishing md->type. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2010-08-12 03:14:02 +00:00
/*
* To check the return value from dm_table_find_target().
*/
#define dm_target_is_valid(t) ((t)->table)
/*
* To check whether the target type is bio-based or not (request-based).
*/
#define dm_target_bio_based(t) ((t)->type->map != NULL)
/*
* To check whether the target type is request-based or not (bio-based).
*/
#define dm_target_request_based(t) ((t)->type->clone_and_map_rq != NULL)
/*
* To check whether the target type is a hybrid (capable of being
* either request-based or bio-based).
*/
#define dm_target_hybrid(t) (dm_target_bio_based(t) && dm_target_request_based(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 *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);
/*
* Is this mapped_device being deleted?
*/
int dm_deleting_md(struct mapped_device *md);
/*
* Is this mapped_device suspended?
*/
int dm_suspended_md(struct mapped_device *md);
dm: enhance internal suspend and resume interface Rename dm_internal_{suspend,resume} to dm_internal_{suspend,resume}_fast -- dm-stats will continue using these methods to avoid all the extra suspend/resume logic that is not needed in order to quickly flush IO. Introduce dm_internal_suspend_noflush() variant that actually calls the mapped_device's target callbacks -- otherwise target-specific hooks are avoided (e.g. dm-thin's thin_presuspend and thin_postsuspend). Common code between dm_internal_{suspend_noflush,resume} and dm_{suspend,resume} was factored out as __dm_{suspend,resume}. Update dm_internal_{suspend_noflush,resume} to always take and release the mapped_device's suspend_lock. Also update dm_{suspend,resume} to be aware of potential for DM_INTERNAL_SUSPEND_FLAG to be set and respond accordingly by interruptibly waiting for the DM_INTERNAL_SUSPEND_FLAG to be cleared. Add lockdep annotation to dm_suspend() and dm_resume(). The existing DM_SUSPEND_FLAG remains unchanged. DM_INTERNAL_SUSPEND_FLAG is set by dm_internal_suspend_noflush() and cleared by dm_internal_resume(). Both DM_SUSPEND_FLAG and DM_INTERNAL_SUSPEND_FLAG may be set if a device was already suspended when dm_internal_suspend_noflush() was called -- this can be thought of as a "nested suspend". A "nested suspend" can occur with legacy userspace dm-thin code that might suspend all active thin volumes before suspending the pool for resize. But otherwise, in the normal dm-thin-pool suspend case moving forward: the thin-pool will have DM_SUSPEND_FLAG set and all active thins from that thin-pool will have DM_INTERNAL_SUSPEND_FLAG set. Also add DM_INTERNAL_SUSPEND_FLAG to status report. This new DM_INTERNAL_SUSPEND_FLAG state is being reported to assist with debugging (e.g. 'dmsetup info' will report an internally suspended device accordingly). Signed-off-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Joe Thornber <ejt@redhat.com>
2014-10-28 22:34:52 +00:00
/*
* Internal suspend and resume methods.
*/
int dm_suspended_internally_md(struct mapped_device *md);
void dm_internal_suspend_fast(struct mapped_device *md);
void dm_internal_resume_fast(struct mapped_device *md);
void dm_internal_suspend_noflush(struct mapped_device *md);
void dm_internal_resume(struct mapped_device *md);
/*
* Test if the device is scheduled for deferred remove.
*/
int dm_test_deferred_remove_flag(struct mapped_device *md);
/*
* Try to remove devices marked for deferred removal.
*/
void dm_deferred_remove(void);
/*
* 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);
/*
* The kobject helper
*/
void dm_kobject_release(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);
dm: separate device deletion from dm_put This patch separates the device deletion code from dm_put() to make sure the deletion happens in the process context. By this patch, device deletion always occurs in an ioctl (process) context and dm_put() can be called in interrupt context. As a result, the request-based dm's bad dm_put() usage pointed out by Mikulas below disappears. http://marc.info/?l=dm-devel&m=126699981019735&w=2 Without this patch, I confirmed there is a case to crash the system: dm_put() => dm_table_destroy() => vfree() => BUG_ON(in_interrupt()) Some more backgrounds and details: In request-based dm, a device opener can remove a mapped_device while the last request is still completing, because bios in the last request complete first and then the device opener can close and remove the mapped_device before the last request completes: CPU0 CPU1 ================================================================= <<INTERRUPT>> blk_end_request_all(clone_rq) blk_update_request(clone_rq) bio_endio(clone_bio) == end_clone_bio blk_update_request(orig_rq) bio_endio(orig_bio) <<I/O completed>> dm_blk_close() dev_remove() dm_put(md) <<Free md>> blk_finish_request(clone_rq) .... dm_end_request(clone_rq) free_rq_clone(clone_rq) blk_end_request_all(orig_rq) rq_completed(md) So request-based dm used dm_get()/dm_put() to hold md for each I/O until its request completion handling is fully done. However, the final dm_put() can call the device deletion code which must not be run in interrupt context and may cause kernel panic. To solve the problem, this patch moves the device deletion code, dm_destroy(), to predetermined places that is actually deleting the mapped_device in ioctl (process) context, and changes dm_put() just to decrement the reference count of the mapped_device. By this change, dm_put() can be used in any context and the symmetric model below is introduced: dm_create(): create a mapped_device dm_destroy(): destroy a mapped_device dm_get(): increment the reference count of a mapped_device dm_put(): decrement the reference count of a mapped_device dm_destroy() waits for all references of the mapped_device to disappear, then deletes the mapped_device. dm_destroy() uses active waiting with msleep(1), since deleting the mapped_device isn't performance-critical task. And since at this point, nobody opens the mapped_device and no new reference will be taken, the pending counts are just for racing completing activity and will eventually decrease to zero. For the unlikely case of the forced module unload, dm_destroy_immediate(), which doesn't wait and forcibly deletes the mapped_device, is also introduced and used in dm_hash_remove_all(). Otherwise, "rmmod -f" may be stuck and never return. And now, because the mapped_device is deleted at this point, subsequent accesses to the mapped_device may cause NULL pointer references. Cc: stable@kernel.org 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>
2010-08-12 03:13:56 +00:00
/*
* mapped_device operations
*/
void dm_destroy(struct mapped_device *md);
void dm_destroy_immediate(struct mapped_device *md);
int dm_open_count(struct mapped_device *md);
int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred);
int dm_cancel_deferred_remove(struct mapped_device *md);
int dm_request_based(struct mapped_device *md);
sector_t dm_get_size(struct mapped_device *md);
struct request_queue *dm_get_md_queue(struct mapped_device *md);
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
struct dm_dev **result);
void dm_put_table_device(struct mapped_device *md, struct dm_dev *d);
struct dm_stats *dm_get_stats(struct mapped_device *md);
int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
unsigned cookie);
void dm_internal_suspend(struct mapped_device *md);
void dm_internal_resume(struct mapped_device *md);
int dm_io_init(void);
void dm_io_exit(void);
int dm_kcopyd_init(void);
void dm_kcopyd_exit(void);
/*
* Mempool operations
*/
struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_queue_mode type,
unsigned integrity, unsigned per_bio_data_size,
unsigned min_pool_size);
void dm_free_md_mempools(struct dm_md_mempools *pools);
/*
* Various helpers
*/
unsigned dm_get_reserved_bio_based_ios(void);
dm: impose configurable deadline for dm_request_fn's merge heuristic Otherwise, for sequential workloads, the dm_request_fn can allow excessive request merging at the expense of increased service time. Add a per-device sysfs attribute to allow the user to control how long a request, that is a reasonable merge candidate, can be queued on the request queue. The resolution of this request dispatch deadline is in microseconds (ranging from 1 to 100000 usecs), to set a 20us deadline: echo 20 > /sys/block/dm-7/dm/rq_based_seq_io_merge_deadline The dm_request_fn's merge heuristic and associated extra accounting is disabled by default (rq_based_seq_io_merge_deadline is 0). This sysfs attribute is not applicable to bio-based DM devices so it will only ever report 0 for them. By allowing a request to remain on the queue it will block others requests on the queue. But introducing a short dequeue delay has proven very effective at enabling certain sequential IO workloads on really fast, yet IOPS constrained, devices to build up slightly larger IOs -- yielding 90+% throughput improvements. Having precise control over the time taken to wait for larger requests to build affords control beyond that of waiting for certain IO sizes to accumulate (which would require a deadline anyway). This knob will only ever make sense with sequential IO workloads and the particular value used is storage configuration specific. Given the expected niche use-case for when this knob is useful it has been deemed acceptable to expose this relatively crude method for crafting optimal IO on specific storage -- especially given the solution is simple yet effective. In the context of DM multipath, it is advisable to tune this sysfs attribute to a value that offers the best performance for the common case (e.g. if 4 paths are expected active, tune for that; if paths fail then performance may be slightly reduced). Alternatives were explored to have request-based DM autotune this value (e.g. if/when paths fail) but they were quickly deemed too fragile and complex to warrant further design and development time. If this problem proves more common as faster storage emerges we'll have to look at elevating a generic solution into the block core. Tested-by: Shiva Krishna Merla <shivakrishna.merla@netapp.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-02-26 05:50:28 +00:00
#endif