mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 03:20:53 +07:00
b6ffe9ba46
* Introduce the _flushcache() family of memory copy helpers and use them for persistent memory write operations on x86. The _flushcache() semantic indicates that the cache is either bypassed for the copy operation (movnt) or any lines dirtied by the copy operation are written back (clwb, clflushopt, or clflush). * Extend dax_operations with ->copy_from_iter() and ->flush() operations. These operations and other infrastructure updates allow all persistent memory specific dax functionality to be pushed into libnvdimm and the pmem driver directly. It also allows dax-specific sysfs attributes to be linked to a host device, for example: /sys/block/pmem0/dax/write_cache * Add support for the new NVDIMM platform/firmware mechanisms introduced in ACPI 6.2 and UEFI 2.7. This support includes the v1.2 namespace label format, extensions to the address-range-scrub command set, new error injection commands, and a new BTT (block-translation-table) layout. These updates support inter-OS and pre-OS compatibility. * Fix a longstanding memory corruption bug in nfit_test. * Make the pmem and nvdimm-region 'badblocks' sysfs files poll(2) capable. * Miscellaneous fixes and small updates across libnvdimm and the nfit driver. Acknowledgements that came after the branch was pushed: commit6aa734a2f3
"libnvdimm, region, pmem: fix 'badblocks' sysfs_get_dirent() reference lifetime" Reviewed-by: Toshi Kani <toshi.kani@hpe.com> -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJZXsUtAAoJEB7SkWpmfYgCOXcP/06bncqTEvtgrOF2b7O8w+8e mTySD51RUn6UpkFd37SMRch+rmbojuqj465TAE7XIXgyLgIOJixKaTlHYUoEnP3X rC4Q/g5mN0nittMDwL+vQaa1lQWd2kbjOlrqCgnLHVEEJpHmiQussunjvir4G1U7 5ROooP8W+qMK5y5XPLJAg/gyGhYkjpRSlDg3Eo5meZZ0IdURbI7+WCLKrPcQUERT WmDc9gLhJdSQVxBV/0m2gdAER4ADmFjcrlm8kjXRBhdlUmEFjM0zpvlHJutHTkks rNZWCmCJs0Sas+DmRKszFmvVFHRHqUVA3dWK4P6PJEX+tl7BwlPcxpbfacHTG2EZ btArFc584DZ+EIrim1cXXRvLFlxnKOFBtBeteFs7l2kZjEcN6S4I5OZgTyeDpe/i 2WDpHWLQWibkcIzH9y1EuMBkYnQjTJl1pecHzJoTaC+jAQ+opLiY7EecjLmCmQS6 MBYUeQZNufLGfT5b8KXfpKeiXhpFkYrAGp+ErfoH/6RKy2zqTdagN1yVhos2y+a7 JJu/Weetpn8qv+KTGUShO8TGyWv3wU46YkG2rKWl0FL1+C+6LMMw1/L0A97lwVlg BpypVVyaNu1D22ifZ8O5wbqPIYghoZ5akA0CiduhX19cpl5rTeTd8EvLjvcYhZEZ pMHuMAqIcIyLhIe2/sRF =xKQB -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm updates from Dan Williams: "libnvdimm updates for the latest ACPI and UEFI specifications. This pull request also includes new 'struct dax_operations' enabling to undo the abuse of copy_user_nocache() for copy operations to pmem. The dax work originally missed 4.12 to address concerns raised by Al. Summary: - Introduce the _flushcache() family of memory copy helpers and use them for persistent memory write operations on x86. The _flushcache() semantic indicates that the cache is either bypassed for the copy operation (movnt) or any lines dirtied by the copy operation are written back (clwb, clflushopt, or clflush). - Extend dax_operations with ->copy_from_iter() and ->flush() operations. These operations and other infrastructure updates allow all persistent memory specific dax functionality to be pushed into libnvdimm and the pmem driver directly. It also allows dax-specific sysfs attributes to be linked to a host device, for example: /sys/block/pmem0/dax/write_cache - Add support for the new NVDIMM platform/firmware mechanisms introduced in ACPI 6.2 and UEFI 2.7. This support includes the v1.2 namespace label format, extensions to the address-range-scrub command set, new error injection commands, and a new BTT (block-translation-table) layout. These updates support inter-OS and pre-OS compatibility. - Fix a longstanding memory corruption bug in nfit_test. - Make the pmem and nvdimm-region 'badblocks' sysfs files poll(2) capable. - Miscellaneous fixes and small updates across libnvdimm and the nfit driver. Acknowledgements that came after the branch was pushed: commit6aa734a2f3
("libnvdimm, region, pmem: fix 'badblocks' sysfs_get_dirent() reference lifetime") was reviewed by Toshi Kani <toshi.kani@hpe.com>" * tag 'libnvdimm-for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (42 commits) libnvdimm, namespace: record 'lbasize' for pmem namespaces acpi/nfit: Issue Start ARS to retrieve existing records libnvdimm: New ACPI 6.2 DSM functions acpi, nfit: Show bus_dsm_mask in sysfs libnvdimm, acpi, nfit: Add bus level dsm mask for pass thru. acpi, nfit: Enable DSM pass thru for root functions. libnvdimm: passthru functions clear to send libnvdimm, btt: convert some info messages to warn/err libnvdimm, region, pmem: fix 'badblocks' sysfs_get_dirent() reference lifetime libnvdimm: fix the clear-error check in nsio_rw_bytes libnvdimm, btt: fix btt_rw_page not returning errors acpi, nfit: quiet invalid block-aperture-region warnings libnvdimm, btt: BTT updates for UEFI 2.7 format acpi, nfit: constify *_attribute_group libnvdimm, pmem: disable dax flushing when pmem is fronting a volatile region libnvdimm, pmem, dax: export a cache control attribute dax: convert to bitmask for flags dax: remove default copy_from_iter fallback libnvdimm, nfit: enable support for volatile ranges libnvdimm, pmem: fix persistence warning ...
664 lines
18 KiB
C
664 lines
18 KiB
C
/*
|
|
* Copyright (C) 2001 Sistina Software (UK) Limited.
|
|
* Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
|
|
*
|
|
* This file is released under the LGPL.
|
|
*/
|
|
|
|
#ifndef _LINUX_DEVICE_MAPPER_H
|
|
#define _LINUX_DEVICE_MAPPER_H
|
|
|
|
#include <linux/bio.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/math64.h>
|
|
#include <linux/ratelimit.h>
|
|
|
|
struct dm_dev;
|
|
struct dm_target;
|
|
struct dm_table;
|
|
struct mapped_device;
|
|
struct bio_vec;
|
|
|
|
/*
|
|
* Type of table, mapped_device's mempool and request_queue
|
|
*/
|
|
enum dm_queue_mode {
|
|
DM_TYPE_NONE = 0,
|
|
DM_TYPE_BIO_BASED = 1,
|
|
DM_TYPE_REQUEST_BASED = 2,
|
|
DM_TYPE_MQ_REQUEST_BASED = 3,
|
|
DM_TYPE_DAX_BIO_BASED = 4,
|
|
};
|
|
|
|
typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
|
|
|
|
union map_info {
|
|
void *ptr;
|
|
};
|
|
|
|
/*
|
|
* In the constructor the target parameter will already have the
|
|
* table, type, begin and len fields filled in.
|
|
*/
|
|
typedef int (*dm_ctr_fn) (struct dm_target *target,
|
|
unsigned int argc, char **argv);
|
|
|
|
/*
|
|
* The destructor doesn't need to free the dm_target, just
|
|
* anything hidden ti->private.
|
|
*/
|
|
typedef void (*dm_dtr_fn) (struct dm_target *ti);
|
|
|
|
/*
|
|
* The map function must return:
|
|
* < 0: error
|
|
* = 0: The target will handle the io by resubmitting it later
|
|
* = 1: simple remap complete
|
|
* = 2: The target wants to push back the io
|
|
*/
|
|
typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio);
|
|
typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti,
|
|
struct request *rq,
|
|
union map_info *map_context,
|
|
struct request **clone);
|
|
typedef void (*dm_release_clone_request_fn) (struct request *clone);
|
|
|
|
/*
|
|
* Returns:
|
|
* < 0 : error (currently ignored)
|
|
* 0 : ended successfully
|
|
* 1 : for some reason the io has still not completed (eg,
|
|
* multipath target might want to requeue a failed io).
|
|
* 2 : The target wants to push back the io
|
|
*/
|
|
typedef int (*dm_endio_fn) (struct dm_target *ti,
|
|
struct bio *bio, blk_status_t *error);
|
|
typedef int (*dm_request_endio_fn) (struct dm_target *ti,
|
|
struct request *clone, blk_status_t error,
|
|
union map_info *map_context);
|
|
|
|
typedef void (*dm_presuspend_fn) (struct dm_target *ti);
|
|
typedef void (*dm_presuspend_undo_fn) (struct dm_target *ti);
|
|
typedef void (*dm_postsuspend_fn) (struct dm_target *ti);
|
|
typedef int (*dm_preresume_fn) (struct dm_target *ti);
|
|
typedef void (*dm_resume_fn) (struct dm_target *ti);
|
|
|
|
typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
|
|
unsigned status_flags, char *result, unsigned maxlen);
|
|
|
|
typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
|
|
|
|
typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti,
|
|
struct block_device **bdev, fmode_t *mode);
|
|
|
|
/*
|
|
* These iteration functions are typically used to check (and combine)
|
|
* properties of underlying devices.
|
|
* E.g. Does at least one underlying device support flush?
|
|
* Does any underlying device not support WRITE_SAME?
|
|
*
|
|
* The callout function is called once for each contiguous section of
|
|
* an underlying device. State can be maintained in *data.
|
|
* Return non-zero to stop iterating through any further devices.
|
|
*/
|
|
typedef int (*iterate_devices_callout_fn) (struct dm_target *ti,
|
|
struct dm_dev *dev,
|
|
sector_t start, sector_t len,
|
|
void *data);
|
|
|
|
/*
|
|
* This function must iterate through each section of device used by the
|
|
* target until it encounters a non-zero return code, which it then returns.
|
|
* Returns zero if no callout returned non-zero.
|
|
*/
|
|
typedef int (*dm_iterate_devices_fn) (struct dm_target *ti,
|
|
iterate_devices_callout_fn fn,
|
|
void *data);
|
|
|
|
typedef void (*dm_io_hints_fn) (struct dm_target *ti,
|
|
struct queue_limits *limits);
|
|
|
|
/*
|
|
* Returns:
|
|
* 0: The target can handle the next I/O immediately.
|
|
* 1: The target can't handle the next I/O immediately.
|
|
*/
|
|
typedef int (*dm_busy_fn) (struct dm_target *ti);
|
|
|
|
/*
|
|
* Returns:
|
|
* < 0 : error
|
|
* >= 0 : the number of bytes accessible at the address
|
|
*/
|
|
typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
|
|
long nr_pages, void **kaddr, pfn_t *pfn);
|
|
typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
|
|
void *addr, size_t bytes, struct iov_iter *i);
|
|
typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr,
|
|
size_t size);
|
|
#define PAGE_SECTORS (PAGE_SIZE / 512)
|
|
|
|
void dm_error(const char *message);
|
|
|
|
struct dm_dev {
|
|
struct block_device *bdev;
|
|
struct dax_device *dax_dev;
|
|
fmode_t mode;
|
|
char name[16];
|
|
};
|
|
|
|
dev_t dm_get_dev_t(const char *path);
|
|
|
|
/*
|
|
* Constructors should call these functions to ensure destination devices
|
|
* are opened/closed correctly.
|
|
*/
|
|
int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
|
|
struct dm_dev **result);
|
|
void dm_put_device(struct dm_target *ti, struct dm_dev *d);
|
|
|
|
/*
|
|
* Information about a target type
|
|
*/
|
|
|
|
struct target_type {
|
|
uint64_t features;
|
|
const char *name;
|
|
struct module *module;
|
|
unsigned version[3];
|
|
dm_ctr_fn ctr;
|
|
dm_dtr_fn dtr;
|
|
dm_map_fn map;
|
|
dm_clone_and_map_request_fn clone_and_map_rq;
|
|
dm_release_clone_request_fn release_clone_rq;
|
|
dm_endio_fn end_io;
|
|
dm_request_endio_fn rq_end_io;
|
|
dm_presuspend_fn presuspend;
|
|
dm_presuspend_undo_fn presuspend_undo;
|
|
dm_postsuspend_fn postsuspend;
|
|
dm_preresume_fn preresume;
|
|
dm_resume_fn resume;
|
|
dm_status_fn status;
|
|
dm_message_fn message;
|
|
dm_prepare_ioctl_fn prepare_ioctl;
|
|
dm_busy_fn busy;
|
|
dm_iterate_devices_fn iterate_devices;
|
|
dm_io_hints_fn io_hints;
|
|
dm_dax_direct_access_fn direct_access;
|
|
dm_dax_copy_from_iter_fn dax_copy_from_iter;
|
|
dm_dax_flush_fn dax_flush;
|
|
|
|
/* For internal device-mapper use. */
|
|
struct list_head list;
|
|
};
|
|
|
|
/*
|
|
* Target features
|
|
*/
|
|
|
|
/*
|
|
* Any table that contains an instance of this target must have only one.
|
|
*/
|
|
#define DM_TARGET_SINGLETON 0x00000001
|
|
#define dm_target_needs_singleton(type) ((type)->features & DM_TARGET_SINGLETON)
|
|
|
|
/*
|
|
* Indicates that a target does not support read-only devices.
|
|
*/
|
|
#define DM_TARGET_ALWAYS_WRITEABLE 0x00000002
|
|
#define dm_target_always_writeable(type) \
|
|
((type)->features & DM_TARGET_ALWAYS_WRITEABLE)
|
|
|
|
/*
|
|
* Any device that contains a table with an instance of this target may never
|
|
* have tables containing any different target type.
|
|
*/
|
|
#define DM_TARGET_IMMUTABLE 0x00000004
|
|
#define dm_target_is_immutable(type) ((type)->features & DM_TARGET_IMMUTABLE)
|
|
|
|
/*
|
|
* Indicates that a target may replace any target; even immutable targets.
|
|
* .map, .map_rq, .clone_and_map_rq and .release_clone_rq are all defined.
|
|
*/
|
|
#define DM_TARGET_WILDCARD 0x00000008
|
|
#define dm_target_is_wildcard(type) ((type)->features & DM_TARGET_WILDCARD)
|
|
|
|
/*
|
|
* Some targets need to be sent the same WRITE bio severals times so
|
|
* that they can send copies of it to different devices. This function
|
|
* examines any supplied bio and returns the number of copies of it the
|
|
* target requires.
|
|
*/
|
|
typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio);
|
|
|
|
/*
|
|
* A target implements own bio data integrity.
|
|
*/
|
|
#define DM_TARGET_INTEGRITY 0x00000010
|
|
#define dm_target_has_integrity(type) ((type)->features & DM_TARGET_INTEGRITY)
|
|
|
|
/*
|
|
* A target passes integrity data to the lower device.
|
|
*/
|
|
#define DM_TARGET_PASSES_INTEGRITY 0x00000020
|
|
#define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY)
|
|
|
|
/*
|
|
* Indicates that a target supports host-managed zoned block devices.
|
|
*/
|
|
#define DM_TARGET_ZONED_HM 0x00000040
|
|
#define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM)
|
|
|
|
struct dm_target {
|
|
struct dm_table *table;
|
|
struct target_type *type;
|
|
|
|
/* target limits */
|
|
sector_t begin;
|
|
sector_t len;
|
|
|
|
/* If non-zero, maximum size of I/O submitted to a target. */
|
|
uint32_t max_io_len;
|
|
|
|
/*
|
|
* A number of zero-length barrier bios that will be submitted
|
|
* to the target for the purpose of flushing cache.
|
|
*
|
|
* The bio number can be accessed with dm_bio_get_target_bio_nr.
|
|
* It is a responsibility of the target driver to remap these bios
|
|
* to the real underlying devices.
|
|
*/
|
|
unsigned num_flush_bios;
|
|
|
|
/*
|
|
* The number of discard bios that will be submitted to the target.
|
|
* The bio number can be accessed with dm_bio_get_target_bio_nr.
|
|
*/
|
|
unsigned num_discard_bios;
|
|
|
|
/*
|
|
* The number of WRITE SAME bios that will be submitted to the target.
|
|
* The bio number can be accessed with dm_bio_get_target_bio_nr.
|
|
*/
|
|
unsigned num_write_same_bios;
|
|
|
|
/*
|
|
* The number of WRITE ZEROES bios that will be submitted to the target.
|
|
* The bio number can be accessed with dm_bio_get_target_bio_nr.
|
|
*/
|
|
unsigned num_write_zeroes_bios;
|
|
|
|
/*
|
|
* The minimum number of extra bytes allocated in each io for the
|
|
* target to use.
|
|
*/
|
|
unsigned per_io_data_size;
|
|
|
|
/*
|
|
* If defined, this function is called to find out how many
|
|
* duplicate bios should be sent to the target when writing
|
|
* data.
|
|
*/
|
|
dm_num_write_bios_fn num_write_bios;
|
|
|
|
/* target specific data */
|
|
void *private;
|
|
|
|
/* Used to provide an error string from the ctr */
|
|
char *error;
|
|
|
|
/*
|
|
* Set if this target needs to receive flushes regardless of
|
|
* whether or not its underlying devices have support.
|
|
*/
|
|
bool flush_supported:1;
|
|
|
|
/*
|
|
* Set if this target needs to receive discards regardless of
|
|
* whether or not its underlying devices have support.
|
|
*/
|
|
bool discards_supported:1;
|
|
|
|
/*
|
|
* Set if the target required discard bios to be split
|
|
* on max_io_len boundary.
|
|
*/
|
|
bool split_discard_bios:1;
|
|
};
|
|
|
|
/* Each target can link one of these into the table */
|
|
struct dm_target_callbacks {
|
|
struct list_head list;
|
|
int (*congested_fn) (struct dm_target_callbacks *, int);
|
|
};
|
|
|
|
/*
|
|
* For bio-based dm.
|
|
* One of these is allocated for each bio.
|
|
* This structure shouldn't be touched directly by target drivers.
|
|
* It is here so that we can inline dm_per_bio_data and
|
|
* dm_bio_from_per_bio_data
|
|
*/
|
|
struct dm_target_io {
|
|
struct dm_io *io;
|
|
struct dm_target *ti;
|
|
unsigned target_bio_nr;
|
|
unsigned *len_ptr;
|
|
struct bio clone;
|
|
};
|
|
|
|
static inline void *dm_per_bio_data(struct bio *bio, size_t data_size)
|
|
{
|
|
return (char *)bio - offsetof(struct dm_target_io, clone) - data_size;
|
|
}
|
|
|
|
static inline struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size)
|
|
{
|
|
return (struct bio *)((char *)data + data_size + offsetof(struct dm_target_io, clone));
|
|
}
|
|
|
|
static inline unsigned dm_bio_get_target_bio_nr(const struct bio *bio)
|
|
{
|
|
return container_of(bio, struct dm_target_io, clone)->target_bio_nr;
|
|
}
|
|
|
|
int dm_register_target(struct target_type *t);
|
|
void dm_unregister_target(struct target_type *t);
|
|
|
|
/*
|
|
* Target argument parsing.
|
|
*/
|
|
struct dm_arg_set {
|
|
unsigned argc;
|
|
char **argv;
|
|
};
|
|
|
|
/*
|
|
* The minimum and maximum value of a numeric argument, together with
|
|
* the error message to use if the number is found to be outside that range.
|
|
*/
|
|
struct dm_arg {
|
|
unsigned min;
|
|
unsigned max;
|
|
char *error;
|
|
};
|
|
|
|
/*
|
|
* Validate the next argument, either returning it as *value or, if invalid,
|
|
* returning -EINVAL and setting *error.
|
|
*/
|
|
int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set,
|
|
unsigned *value, char **error);
|
|
|
|
/*
|
|
* Process the next argument as the start of a group containing between
|
|
* arg->min and arg->max further arguments. Either return the size as
|
|
* *num_args or, if invalid, return -EINVAL and set *error.
|
|
*/
|
|
int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set,
|
|
unsigned *num_args, char **error);
|
|
|
|
/*
|
|
* Return the current argument and shift to the next.
|
|
*/
|
|
const char *dm_shift_arg(struct dm_arg_set *as);
|
|
|
|
/*
|
|
* Move through num_args arguments.
|
|
*/
|
|
void dm_consume_args(struct dm_arg_set *as, unsigned num_args);
|
|
|
|
/*-----------------------------------------------------------------
|
|
* Functions for creating and manipulating mapped devices.
|
|
* Drop the reference with dm_put when you finish with the object.
|
|
*---------------------------------------------------------------*/
|
|
|
|
/*
|
|
* DM_ANY_MINOR chooses the next available minor number.
|
|
*/
|
|
#define DM_ANY_MINOR (-1)
|
|
int dm_create(int minor, struct mapped_device **md);
|
|
|
|
/*
|
|
* Reference counting for md.
|
|
*/
|
|
struct mapped_device *dm_get_md(dev_t dev);
|
|
void dm_get(struct mapped_device *md);
|
|
int dm_hold(struct mapped_device *md);
|
|
void dm_put(struct mapped_device *md);
|
|
|
|
/*
|
|
* An arbitrary pointer may be stored alongside a mapped device.
|
|
*/
|
|
void dm_set_mdptr(struct mapped_device *md, void *ptr);
|
|
void *dm_get_mdptr(struct mapped_device *md);
|
|
|
|
/*
|
|
* A device can still be used while suspended, but I/O is deferred.
|
|
*/
|
|
int dm_suspend(struct mapped_device *md, unsigned suspend_flags);
|
|
int dm_resume(struct mapped_device *md);
|
|
|
|
/*
|
|
* Event functions.
|
|
*/
|
|
uint32_t dm_get_event_nr(struct mapped_device *md);
|
|
int dm_wait_event(struct mapped_device *md, int event_nr);
|
|
uint32_t dm_next_uevent_seq(struct mapped_device *md);
|
|
void dm_uevent_add(struct mapped_device *md, struct list_head *elist);
|
|
|
|
/*
|
|
* Info functions.
|
|
*/
|
|
const char *dm_device_name(struct mapped_device *md);
|
|
int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
|
|
struct gendisk *dm_disk(struct mapped_device *md);
|
|
int dm_suspended(struct dm_target *ti);
|
|
int dm_noflush_suspending(struct dm_target *ti);
|
|
void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
|
|
void dm_remap_zone_report(struct dm_target *ti, struct bio *bio,
|
|
sector_t start);
|
|
union map_info *dm_get_rq_mapinfo(struct request *rq);
|
|
|
|
struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
|
|
|
|
/*
|
|
* Geometry functions.
|
|
*/
|
|
int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo);
|
|
int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
|
|
|
|
/*-----------------------------------------------------------------
|
|
* Functions for manipulating device-mapper tables.
|
|
*---------------------------------------------------------------*/
|
|
|
|
/*
|
|
* First create an empty table.
|
|
*/
|
|
int dm_table_create(struct dm_table **result, fmode_t mode,
|
|
unsigned num_targets, struct mapped_device *md);
|
|
|
|
/*
|
|
* Then call this once for each target.
|
|
*/
|
|
int dm_table_add_target(struct dm_table *t, const char *type,
|
|
sector_t start, sector_t len, char *params);
|
|
|
|
/*
|
|
* Target_ctr should call this if it needs to add any callbacks.
|
|
*/
|
|
void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb);
|
|
|
|
/*
|
|
* Target can use this to set the table's type.
|
|
* Can only ever be called from a target's ctr.
|
|
* Useful for "hybrid" target (supports both bio-based
|
|
* and request-based).
|
|
*/
|
|
void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type);
|
|
|
|
/*
|
|
* Finally call this to make the table ready for use.
|
|
*/
|
|
int dm_table_complete(struct dm_table *t);
|
|
|
|
/*
|
|
* Target may require that it is never sent I/O larger than len.
|
|
*/
|
|
int __must_check dm_set_target_max_io_len(struct dm_target *ti, sector_t len);
|
|
|
|
/*
|
|
* Table reference counting.
|
|
*/
|
|
struct dm_table *dm_get_live_table(struct mapped_device *md, int *srcu_idx);
|
|
void dm_put_live_table(struct mapped_device *md, int srcu_idx);
|
|
void dm_sync_table(struct mapped_device *md);
|
|
|
|
/*
|
|
* Queries
|
|
*/
|
|
sector_t dm_table_get_size(struct dm_table *t);
|
|
unsigned int dm_table_get_num_targets(struct dm_table *t);
|
|
fmode_t dm_table_get_mode(struct dm_table *t);
|
|
struct mapped_device *dm_table_get_md(struct dm_table *t);
|
|
|
|
/*
|
|
* Trigger an event.
|
|
*/
|
|
void dm_table_event(struct dm_table *t);
|
|
|
|
/*
|
|
* Run the queue for request-based targets.
|
|
*/
|
|
void dm_table_run_md_queue_async(struct dm_table *t);
|
|
|
|
/*
|
|
* The device must be suspended before calling this method.
|
|
* Returns the previous table, which the caller must destroy.
|
|
*/
|
|
struct dm_table *dm_swap_table(struct mapped_device *md,
|
|
struct dm_table *t);
|
|
|
|
/*
|
|
* A wrapper around vmalloc.
|
|
*/
|
|
void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
|
|
|
|
/*-----------------------------------------------------------------
|
|
* Macros.
|
|
*---------------------------------------------------------------*/
|
|
#define DM_NAME "device-mapper"
|
|
|
|
#ifdef CONFIG_PRINTK
|
|
extern struct ratelimit_state dm_ratelimit_state;
|
|
|
|
#define dm_ratelimit() __ratelimit(&dm_ratelimit_state)
|
|
#else
|
|
#define dm_ratelimit() 0
|
|
#endif
|
|
|
|
#define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n"
|
|
|
|
#define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__)
|
|
|
|
#define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__)
|
|
#define DMERR_LIMIT(fmt, ...) \
|
|
do { \
|
|
if (dm_ratelimit()) \
|
|
DMERR(fmt, ##__VA_ARGS__); \
|
|
} while (0)
|
|
|
|
#define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__)
|
|
#define DMWARN_LIMIT(fmt, ...) \
|
|
do { \
|
|
if (dm_ratelimit()) \
|
|
DMWARN(fmt, ##__VA_ARGS__); \
|
|
} while (0)
|
|
|
|
#define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__)
|
|
#define DMINFO_LIMIT(fmt, ...) \
|
|
do { \
|
|
if (dm_ratelimit()) \
|
|
DMINFO(fmt, ##__VA_ARGS__); \
|
|
} while (0)
|
|
|
|
#ifdef CONFIG_DM_DEBUG
|
|
#define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__)
|
|
#define DMDEBUG_LIMIT(fmt, ...) \
|
|
do { \
|
|
if (dm_ratelimit()) \
|
|
DMDEBUG(fmt, ##__VA_ARGS__); \
|
|
} while (0)
|
|
#else
|
|
#define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
|
|
#define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
|
|
#endif
|
|
|
|
#define DMEMIT(x...) sz += ((sz >= maxlen) ? \
|
|
0 : scnprintf(result + sz, maxlen - sz, x))
|
|
|
|
#define SECTOR_SHIFT 9
|
|
|
|
/*
|
|
* Definitions of return values from target end_io function.
|
|
*/
|
|
#define DM_ENDIO_DONE 0
|
|
#define DM_ENDIO_INCOMPLETE 1
|
|
#define DM_ENDIO_REQUEUE 2
|
|
|
|
/*
|
|
* Definitions of return values from target map function.
|
|
*/
|
|
#define DM_MAPIO_SUBMITTED 0
|
|
#define DM_MAPIO_REMAPPED 1
|
|
#define DM_MAPIO_REQUEUE DM_ENDIO_REQUEUE
|
|
#define DM_MAPIO_DELAY_REQUEUE 3
|
|
#define DM_MAPIO_KILL 4
|
|
|
|
#define dm_sector_div64(x, y)( \
|
|
{ \
|
|
u64 _res; \
|
|
(x) = div64_u64_rem(x, y, &_res); \
|
|
_res; \
|
|
} \
|
|
)
|
|
|
|
/*
|
|
* 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))
|
|
|
|
#define dm_array_too_big(fixed, obj, num) \
|
|
((num) > (UINT_MAX - (fixed)) / (obj))
|
|
|
|
/*
|
|
* Sector offset taken relative to the start of the target instead of
|
|
* relative to the start of the device.
|
|
*/
|
|
#define dm_target_offset(ti, sector) ((sector) - (ti)->begin)
|
|
|
|
static inline sector_t to_sector(unsigned long n)
|
|
{
|
|
return (n >> SECTOR_SHIFT);
|
|
}
|
|
|
|
static inline unsigned long to_bytes(sector_t n)
|
|
{
|
|
return (n << SECTOR_SHIFT);
|
|
}
|
|
|
|
#endif /* _LINUX_DEVICE_MAPPER_H */
|