blob: 81ec772b1cc91067d1dc7aa4f9b9774b04c5e380 [file] [log] [blame]
/*
* Copyright (C) 2010-2011 Neil Brown
* Copyright (C) 2010-2016 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#include <linux/slab.h>
#include <linux/module.h>
#include "md.h"
#include "raid1.h"
#include "raid5.h"
#include "raid10.h"
#include "bitmap.h"
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "raid"
#define MAX_RAID_DEVICES 253 /* md-raid kernel limit */
/*
* Minimum sectors of free reshape space per raid device
*/
#define MIN_FREE_RESHAPE_SPACE to_sector(4*4096)
static bool devices_handle_discard_safely = false;
/*
* The following flags are used by dm-raid.c to set up the array state.
* They must be cleared before md_run is called.
*/
#define FirstUse 10 /* rdev flag */
struct raid_dev {
/*
* Two DM devices, one to hold metadata and one to hold the
* actual data/parity. The reason for this is to not confuse
* ti->len and give more flexibility in altering size and
* characteristics.
*
* While it is possible for this device to be associated
* with a different physical device than the data_dev, it
* is intended for it to be the same.
* |--------- Physical Device ---------|
* |- meta_dev -|------ data_dev ------|
*/
struct dm_dev *meta_dev;
struct dm_dev *data_dev;
struct md_rdev rdev;
};
/*
* Bits for establishing rs->ctr_flags
*
* 1 = no flag value
* 2 = flag with value
*/
#define __CTR_FLAG_SYNC 0 /* 1 */ /* Not with raid0! */
#define __CTR_FLAG_NOSYNC 1 /* 1 */ /* Not with raid0! */
#define __CTR_FLAG_REBUILD 2 /* 2 */ /* Not with raid0! */
#define __CTR_FLAG_DAEMON_SLEEP 3 /* 2 */ /* Not with raid0! */
#define __CTR_FLAG_MIN_RECOVERY_RATE 4 /* 2 */ /* Not with raid0! */
#define __CTR_FLAG_MAX_RECOVERY_RATE 5 /* 2 */ /* Not with raid0! */
#define __CTR_FLAG_MAX_WRITE_BEHIND 6 /* 2 */ /* Only with raid1! */
#define __CTR_FLAG_WRITE_MOSTLY 7 /* 2 */ /* Only with raid1! */
#define __CTR_FLAG_STRIPE_CACHE 8 /* 2 */ /* Only with raid4/5/6! */
#define __CTR_FLAG_REGION_SIZE 9 /* 2 */ /* Not with raid0! */
#define __CTR_FLAG_RAID10_COPIES 10 /* 2 */ /* Only with raid10 */
#define __CTR_FLAG_RAID10_FORMAT 11 /* 2 */ /* Only with raid10 */
/* New for v1.9.0 */
#define __CTR_FLAG_DELTA_DISKS 12 /* 2 */ /* Only with reshapable raid1/4/5/6/10! */
#define __CTR_FLAG_DATA_OFFSET 13 /* 2 */ /* Only with reshapable raid4/5/6/10! */
#define __CTR_FLAG_RAID10_USE_NEAR_SETS 14 /* 2 */ /* Only with raid10! */
/*
* Flags for rs->ctr_flags field.
*/
#define CTR_FLAG_SYNC (1 << __CTR_FLAG_SYNC)
#define CTR_FLAG_NOSYNC (1 << __CTR_FLAG_NOSYNC)
#define CTR_FLAG_REBUILD (1 << __CTR_FLAG_REBUILD)
#define CTR_FLAG_DAEMON_SLEEP (1 << __CTR_FLAG_DAEMON_SLEEP)
#define CTR_FLAG_MIN_RECOVERY_RATE (1 << __CTR_FLAG_MIN_RECOVERY_RATE)
#define CTR_FLAG_MAX_RECOVERY_RATE (1 << __CTR_FLAG_MAX_RECOVERY_RATE)
#define CTR_FLAG_MAX_WRITE_BEHIND (1 << __CTR_FLAG_MAX_WRITE_BEHIND)
#define CTR_FLAG_WRITE_MOSTLY (1 << __CTR_FLAG_WRITE_MOSTLY)
#define CTR_FLAG_STRIPE_CACHE (1 << __CTR_FLAG_STRIPE_CACHE)
#define CTR_FLAG_REGION_SIZE (1 << __CTR_FLAG_REGION_SIZE)
#define CTR_FLAG_RAID10_COPIES (1 << __CTR_FLAG_RAID10_COPIES)
#define CTR_FLAG_RAID10_FORMAT (1 << __CTR_FLAG_RAID10_FORMAT)
#define CTR_FLAG_DELTA_DISKS (1 << __CTR_FLAG_DELTA_DISKS)
#define CTR_FLAG_DATA_OFFSET (1 << __CTR_FLAG_DATA_OFFSET)
#define CTR_FLAG_RAID10_USE_NEAR_SETS (1 << __CTR_FLAG_RAID10_USE_NEAR_SETS)
/*
* Definitions of various constructor flags to
* be used in checks of valid / invalid flags
* per raid level.
*/
/* Define all any sync flags */
#define CTR_FLAGS_ANY_SYNC (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC)
/* Define flags for options without argument (e.g. 'nosync') */
#define CTR_FLAG_OPTIONS_NO_ARGS (CTR_FLAGS_ANY_SYNC | \
CTR_FLAG_RAID10_USE_NEAR_SETS)
/* Define flags for options with one argument (e.g. 'delta_disks +2') */
#define CTR_FLAG_OPTIONS_ONE_ARG (CTR_FLAG_REBUILD | \
CTR_FLAG_WRITE_MOSTLY | \
CTR_FLAG_DAEMON_SLEEP | \
CTR_FLAG_MIN_RECOVERY_RATE | \
CTR_FLAG_MAX_RECOVERY_RATE | \
CTR_FLAG_MAX_WRITE_BEHIND | \
CTR_FLAG_STRIPE_CACHE | \
CTR_FLAG_REGION_SIZE | \
CTR_FLAG_RAID10_COPIES | \
CTR_FLAG_RAID10_FORMAT | \
CTR_FLAG_DELTA_DISKS | \
CTR_FLAG_DATA_OFFSET)
/* Valid options definitions per raid level... */
/* "raid0" does only accept data offset */
#define RAID0_VALID_FLAGS (CTR_FLAG_DATA_OFFSET)
/* "raid1" does not accept stripe cache, data offset, delta_disks or any raid10 options */
#define RAID1_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
CTR_FLAG_REBUILD | \
CTR_FLAG_WRITE_MOSTLY | \
CTR_FLAG_DAEMON_SLEEP | \
CTR_FLAG_MIN_RECOVERY_RATE | \
CTR_FLAG_MAX_RECOVERY_RATE | \
CTR_FLAG_MAX_WRITE_BEHIND | \
CTR_FLAG_REGION_SIZE | \
CTR_FLAG_DELTA_DISKS | \
CTR_FLAG_DATA_OFFSET)
/* "raid10" does not accept any raid1 or stripe cache options */
#define RAID10_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
CTR_FLAG_REBUILD | \
CTR_FLAG_DAEMON_SLEEP | \
CTR_FLAG_MIN_RECOVERY_RATE | \
CTR_FLAG_MAX_RECOVERY_RATE | \
CTR_FLAG_REGION_SIZE | \
CTR_FLAG_RAID10_COPIES | \
CTR_FLAG_RAID10_FORMAT | \
CTR_FLAG_DELTA_DISKS | \
CTR_FLAG_DATA_OFFSET | \
CTR_FLAG_RAID10_USE_NEAR_SETS)
/*
* "raid4/5/6" do not accept any raid1 or raid10 specific options
*
* "raid6" does not accept "nosync", because it is not guaranteed
* that both parity and q-syndrome are being written properly with
* any writes
*/
#define RAID45_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
CTR_FLAG_REBUILD | \
CTR_FLAG_DAEMON_SLEEP | \
CTR_FLAG_MIN_RECOVERY_RATE | \
CTR_FLAG_MAX_RECOVERY_RATE | \
CTR_FLAG_MAX_WRITE_BEHIND | \
CTR_FLAG_STRIPE_CACHE | \
CTR_FLAG_REGION_SIZE | \
CTR_FLAG_DELTA_DISKS | \
CTR_FLAG_DATA_OFFSET)
#define RAID6_VALID_FLAGS (CTR_FLAG_SYNC | \
CTR_FLAG_REBUILD | \
CTR_FLAG_DAEMON_SLEEP | \
CTR_FLAG_MIN_RECOVERY_RATE | \
CTR_FLAG_MAX_RECOVERY_RATE | \
CTR_FLAG_MAX_WRITE_BEHIND | \
CTR_FLAG_STRIPE_CACHE | \
CTR_FLAG_REGION_SIZE | \
CTR_FLAG_DELTA_DISKS | \
CTR_FLAG_DATA_OFFSET)
/* ...valid options definitions per raid level */
/*
* Flags for rs->runtime_flags field
* (RT_FLAG prefix meaning "runtime flag")
*
* These are all internal and used to define runtime state,
* e.g. to prevent another resume from preresume processing
* the raid set all over again.
*/
#define RT_FLAG_RS_PRERESUMED 0
#define RT_FLAG_RS_RESUMED 1
#define RT_FLAG_RS_BITMAP_LOADED 2
#define RT_FLAG_UPDATE_SBS 3
#define RT_FLAG_RESHAPE_RS 4
/* Array elements of 64 bit needed for rebuild/failed disk bits */
#define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
/*
* raid set level, layout and chunk sectors backup/restore
*/
struct rs_layout {
int new_level;
int new_layout;
int new_chunk_sectors;
};
struct raid_set {
struct dm_target *ti;
uint32_t bitmap_loaded;
uint32_t stripe_cache_entries;
unsigned long ctr_flags;
unsigned long runtime_flags;
uint64_t rebuild_disks[DISKS_ARRAY_ELEMS];
int raid_disks;
int delta_disks;
int data_offset;
int raid10_copies;
int requested_bitmap_chunk_sectors;
struct mddev md;
struct raid_type *raid_type;
struct dm_target_callbacks callbacks;
struct raid_dev dev[0];
};
static void rs_config_backup(struct raid_set *rs, struct rs_layout *l)
{
struct mddev *mddev = &rs->md;
l->new_level = mddev->new_level;
l->new_layout = mddev->new_layout;
l->new_chunk_sectors = mddev->new_chunk_sectors;
}
static void rs_config_restore(struct raid_set *rs, struct rs_layout *l)
{
struct mddev *mddev = &rs->md;
mddev->new_level = l->new_level;
mddev->new_layout = l->new_layout;
mddev->new_chunk_sectors = l->new_chunk_sectors;
}
/* raid10 algorithms (i.e. formats) */
#define ALGORITHM_RAID10_DEFAULT 0
#define ALGORITHM_RAID10_NEAR 1
#define ALGORITHM_RAID10_OFFSET 2
#define ALGORITHM_RAID10_FAR 3
/* Supported raid types and properties. */
static struct raid_type {
const char *name; /* RAID algorithm. */
const char *descr; /* Descriptor text for logging. */
const unsigned int parity_devs; /* # of parity devices. */
const unsigned int minimal_devs;/* minimal # of devices in set. */
const unsigned int level; /* RAID level. */
const unsigned int algorithm; /* RAID algorithm. */
} raid_types[] = {
{"raid0", "raid0 (striping)", 0, 2, 0, 0 /* NONE */},
{"raid1", "raid1 (mirroring)", 0, 2, 1, 0 /* NONE */},
{"raid10_far", "raid10 far (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_FAR},
{"raid10_offset", "raid10 offset (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_OFFSET},
{"raid10_near", "raid10 near (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_NEAR},
{"raid10", "raid10 (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_DEFAULT},
{"raid4", "raid4 (dedicated last parity disk)", 1, 2, 4, ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */
{"raid5_n", "raid5 (dedicated last parity disk)", 1, 2, 5, ALGORITHM_PARITY_N},
{"raid5_ls", "raid5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
{"raid5_rs", "raid5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
{"raid5_la", "raid5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
{"raid5_ra", "raid5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
{"raid6_zr", "raid6 (zero restart)", 2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART},
{"raid6_nr", "raid6 (N restart)", 2, 4, 6, ALGORITHM_ROTATING_N_RESTART},
{"raid6_nc", "raid6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE},
{"raid6_n_6", "raid6 (dedicated parity/Q n/6)", 2, 4, 6, ALGORITHM_PARITY_N_6},
{"raid6_ls_6", "raid6 (left symmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_LEFT_SYMMETRIC_6},
{"raid6_rs_6", "raid6 (right symmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_RIGHT_SYMMETRIC_6},
{"raid6_la_6", "raid6 (left asymmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_LEFT_ASYMMETRIC_6},
{"raid6_ra_6", "raid6 (right asymmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_RIGHT_ASYMMETRIC_6}
};
/* True, if @v is in inclusive range [@min, @max] */
static bool __within_range(long v, long min, long max)
{
return v >= min && v <= max;
}
/* All table line arguments are defined here */
static struct arg_name_flag {
const unsigned long flag;
const char *name;
} __arg_name_flags[] = {
{ CTR_FLAG_SYNC, "sync"},
{ CTR_FLAG_NOSYNC, "nosync"},
{ CTR_FLAG_REBUILD, "rebuild"},
{ CTR_FLAG_DAEMON_SLEEP, "daemon_sleep"},
{ CTR_FLAG_MIN_RECOVERY_RATE, "min_recovery_rate"},
{ CTR_FLAG_MAX_RECOVERY_RATE, "max_recovery_rate"},
{ CTR_FLAG_MAX_WRITE_BEHIND, "max_write_behind"},
{ CTR_FLAG_WRITE_MOSTLY, "write_mostly"},
{ CTR_FLAG_STRIPE_CACHE, "stripe_cache"},
{ CTR_FLAG_REGION_SIZE, "region_size"},
{ CTR_FLAG_RAID10_COPIES, "raid10_copies"},
{ CTR_FLAG_RAID10_FORMAT, "raid10_format"},
{ CTR_FLAG_DATA_OFFSET, "data_offset"},
{ CTR_FLAG_DELTA_DISKS, "delta_disks"},
{ CTR_FLAG_RAID10_USE_NEAR_SETS, "raid10_use_near_sets"},
};
/* Return argument name string for given @flag */
static const char *dm_raid_arg_name_by_flag(const uint32_t flag)
{
if (hweight32(flag) == 1) {
struct arg_name_flag *anf = __arg_name_flags + ARRAY_SIZE(__arg_name_flags);
while (anf-- > __arg_name_flags)
if (flag & anf->flag)
return anf->name;
} else
DMERR("%s called with more than one flag!", __func__);
return NULL;
}
/*
* Bool helpers to test for various raid levels of a raid set.
* It's level as reported by the superblock rather than
* the requested raid_type passed to the constructor.
*/
/* Return true, if raid set in @rs is raid0 */
static bool rs_is_raid0(struct raid_set *rs)
{
return !rs->md.level;
}
/* Return true, if raid set in @rs is raid1 */
static bool rs_is_raid1(struct raid_set *rs)
{
return rs->md.level == 1;
}
/* Return true, if raid set in @rs is raid10 */
static bool rs_is_raid10(struct raid_set *rs)
{
return rs->md.level == 10;
}
/* Return true, if raid set in @rs is level 6 */
static bool rs_is_raid6(struct raid_set *rs)
{
return rs->md.level == 6;
}
/* Return true, if raid set in @rs is level 4, 5 or 6 */
static bool rs_is_raid456(struct raid_set *rs)
{
return __within_range(rs->md.level, 4, 6);
}
/* Return true, if raid set in @rs is reshapable */
static bool __is_raid10_far(int layout);
static bool rs_is_reshapable(struct raid_set *rs)
{
return rs_is_raid456(rs) ||
(rs_is_raid10(rs) && !__is_raid10_far(rs->md.new_layout));
}
/* Return true, if raid set in @rs is recovering */
static bool rs_is_recovering(struct raid_set *rs)
{
return rs->md.recovery_cp < rs->dev[0].rdev.sectors;
}
/* Return true, if raid set in @rs is reshaping */
static bool rs_is_reshaping(struct raid_set *rs)
{
return rs->md.reshape_position != MaxSector;
}
/*
* bool helpers to test for various raid levels of a raid type @rt
*/
/* Return true, if raid type in @rt is raid0 */
static bool rt_is_raid0(struct raid_type *rt)
{
return !rt->level;
}
/* Return true, if raid type in @rt is raid1 */
static bool rt_is_raid1(struct raid_type *rt)
{
return rt->level == 1;
}
/* Return true, if raid type in @rt is raid10 */
static bool rt_is_raid10(struct raid_type *rt)
{
return rt->level == 10;
}
/* Return true, if raid type in @rt is raid4/5 */
static bool rt_is_raid45(struct raid_type *rt)
{
return __within_range(rt->level, 4, 5);
}
/* Return true, if raid type in @rt is raid6 */
static bool rt_is_raid6(struct raid_type *rt)
{
return rt->level == 6;
}
/* Return true, if raid type in @rt is raid4/5/6 */
static bool rt_is_raid456(struct raid_type *rt)
{
return __within_range(rt->level, 4, 6);
}
/* END: raid level bools */
/* Return valid ctr flags for the raid level of @rs */
static unsigned long __valid_flags(struct raid_set *rs)
{
if (rt_is_raid0(rs->raid_type))
return RAID0_VALID_FLAGS;
else if (rt_is_raid1(rs->raid_type))
return RAID1_VALID_FLAGS;
else if (rt_is_raid10(rs->raid_type))
return RAID10_VALID_FLAGS;
else if (rt_is_raid45(rs->raid_type))
return RAID45_VALID_FLAGS;
else if (rt_is_raid6(rs->raid_type))
return RAID6_VALID_FLAGS;
return 0;
}
/*
* Check for valid flags set on @rs
*
* Has to be called after parsing of the ctr flags!
*/
static int rs_check_for_valid_flags(struct raid_set *rs)
{
if (rs->ctr_flags & ~__valid_flags(rs)) {
rs->ti->error = "Invalid flags combination";
return -EINVAL;
}
return 0;
}
/* MD raid10 bit definitions and helpers */
#define RAID10_OFFSET (1 << 16) /* stripes with data copies area adjacent on devices */
#define RAID10_BROCKEN_USE_FAR_SETS (1 << 17) /* Broken in raid10.c: use sets instead of whole stripe rotation */
#define RAID10_USE_FAR_SETS (1 << 18) /* Use sets instead of whole stripe rotation */
#define RAID10_FAR_COPIES_SHIFT 8 /* raid10 # far copies shift (2nd byte of layout) */
/* Return md raid10 near copies for @layout */
static unsigned int __raid10_near_copies(int layout)
{
return layout & 0xFF;
}
/* Return md raid10 far copies for @layout */
static unsigned int __raid10_far_copies(int layout)
{
return __raid10_near_copies(layout >> RAID10_FAR_COPIES_SHIFT);
}
/* Return true if md raid10 offset for @layout */
static bool __is_raid10_offset(int layout)
{
return !!(layout & RAID10_OFFSET);
}
/* Return true if md raid10 near for @layout */
static bool __is_raid10_near(int layout)
{
return !__is_raid10_offset(layout) && __raid10_near_copies(layout) > 1;
}
/* Return true if md raid10 far for @layout */
static bool __is_raid10_far(int layout)
{
return !__is_raid10_offset(layout) && __raid10_far_copies(layout) > 1;
}
/* Return md raid10 layout string for @layout */
static const char *raid10_md_layout_to_format(int layout)
{
/*
* Bit 16 stands for "offset"
* (i.e. adjacent stripes hold copies)
*
* Refer to MD's raid10.c for details
*/
if (__is_raid10_offset(layout))
return "offset";
if (__raid10_near_copies(layout) > 1)
return "near";
WARN_ON(__raid10_far_copies(layout) < 2);
return "far";
}
/* Return md raid10 algorithm for @name */
static int raid10_name_to_format(const char *name)
{
if (!strcasecmp(name, "near"))
return ALGORITHM_RAID10_NEAR;
else if (!strcasecmp(name, "offset"))
return ALGORITHM_RAID10_OFFSET;
else if (!strcasecmp(name, "far"))
return ALGORITHM_RAID10_FAR;
return -EINVAL;
}
/* Return md raid10 copies for @layout */
static unsigned int raid10_md_layout_to_copies(int layout)
{
return max(__raid10_near_copies(layout), __raid10_far_copies(layout));
}
/* Return md raid10 format id for @format string */
static int raid10_format_to_md_layout(struct raid_set *rs,
unsigned int algorithm,
unsigned int copies)
{
unsigned int n = 1, f = 1, r = 0;
/*
* MD resilienece flaw:
*
* enabling use_far_sets for far/offset formats causes copies
* to be colocated on the same devs together with their origins!
*
* -> disable it for now in the definition above
*/
if (algorithm == ALGORITHM_RAID10_DEFAULT ||
algorithm == ALGORITHM_RAID10_NEAR)
n = copies;
else if (algorithm == ALGORITHM_RAID10_OFFSET) {
f = copies;
r = RAID10_OFFSET;
if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
r |= RAID10_USE_FAR_SETS;
} else if (algorithm == ALGORITHM_RAID10_FAR) {
f = copies;
r = !RAID10_OFFSET;
if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
r |= RAID10_USE_FAR_SETS;
} else
return -EINVAL;
return r | (f << RAID10_FAR_COPIES_SHIFT) | n;
}
/* END: MD raid10 bit definitions and helpers */
/* Check for any of the raid10 algorithms */
static bool __got_raid10(struct raid_type *rtp, const int layout)
{
if (rtp->level == 10) {
switch (rtp->algorithm) {
case ALGORITHM_RAID10_DEFAULT:
case ALGORITHM_RAID10_NEAR:
return __is_raid10_near(layout);
case ALGORITHM_RAID10_OFFSET:
return __is_raid10_offset(layout);
case ALGORITHM_RAID10_FAR:
return __is_raid10_far(layout);
default:
break;
}
}
return false;
}
/* Return raid_type for @name */
static struct raid_type *get_raid_type(const char *name)
{
struct raid_type *rtp = raid_types + ARRAY_SIZE(raid_types);
while (rtp-- > raid_types)
if (!strcasecmp(rtp->name, name))
return rtp;
return NULL;
}
/* Return raid_type for @name based derived from @level and @layout */
static struct raid_type *get_raid_type_by_ll(const int level, const int layout)
{
struct raid_type *rtp = raid_types + ARRAY_SIZE(raid_types);
while (rtp-- > raid_types) {
/* RAID10 special checks based on @layout flags/properties */
if (rtp->level == level &&
(__got_raid10(rtp, layout) || rtp->algorithm == layout))
return rtp;
}
return NULL;
}
/*
* Conditionally change bdev capacity of @rs
* in case of a disk add/remove reshape
*/
static void rs_set_capacity(struct raid_set *rs)
{
struct mddev *mddev = &rs->md;
struct md_rdev *rdev;
struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
/*
* raid10 sets rdev->sector to the device size, which
* is unintended in case of out-of-place reshaping
*/
rdev_for_each(rdev, mddev)
rdev->sectors = mddev->dev_sectors;
set_capacity(gendisk, mddev->array_sectors);
revalidate_disk(gendisk);
}
/*
* Set the mddev properties in @rs to the current
* ones retrieved from the freshest superblock
*/
static void rs_set_cur(struct raid_set *rs)
{
struct mddev *mddev = &rs->md;
mddev->new_level = mddev->level;
mddev->new_layout = mddev->layout;
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
/*
* Set the mddev properties in @rs to the new
* ones requested by the ctr
*/
static void rs_set_new(struct raid_set *rs)
{
struct mddev *mddev = &rs->md;
mddev->level = mddev->new_level;
mddev->layout = mddev->new_layout;
mddev->chunk_sectors = mddev->new_chunk_sectors;
mddev->raid_disks = rs->raid_disks;
mddev->delta_disks = 0;
}
static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *raid_type,
unsigned int raid_devs)
{
unsigned int i;
struct raid_set *rs;
if (raid_devs <= raid_type->parity_devs) {
ti->error = "Insufficient number of devices";
return ERR_PTR(-EINVAL);
}
rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL);
if (!rs) {
ti->error = "Cannot allocate raid context";
return ERR_PTR(-ENOMEM);
}
mddev_init(&rs->md);
rs->raid_disks = raid_devs;
rs->delta_disks = 0;
rs->ti = ti;
rs->raid_type = raid_type;
rs->stripe_cache_entries = 256;
rs->md.raid_disks = raid_devs;
rs->md.level = raid_type->level;
rs->md.new_level = rs->md.level;
rs->md.layout = raid_type->algorithm;
rs->md.new_layout = rs->md.layout;
rs->md.delta_disks = 0;
rs->md.recovery_cp = MaxSector;
for (i = 0; i < raid_devs; i++)
md_rdev_init(&rs->dev[i].rdev);
/*
* Remaining items to be initialized by further RAID params:
* rs->md.persistent
* rs->md.external
* rs->md.chunk_sectors
* rs->md.new_chunk_sectors
* rs->md.dev_sectors
*/
return rs;
}
static void raid_set_free(struct raid_set *rs)
{
int i;
for (i = 0; i < rs->raid_disks; i++) {
if (rs->dev[i].meta_dev)
dm_put_device(rs->ti, rs->dev[i].meta_dev);
md_rdev_clear(&rs->dev[i].rdev);
if (rs->dev[i].data_dev)
dm_put_device(rs->ti, rs->dev[i].data_dev);
}
kfree(rs);
}
/*
* For every device we have two words
* <meta_dev>: meta device name or '-' if missing
* <data_dev>: data device name or '-' if missing
*
* The following are permitted:
* - -
* - <data_dev>
* <meta_dev> <data_dev>
*
* The following is not allowed:
* <meta_dev> -
*
* This code parses those words. If there is a failure,
* the caller must use raid_set_free() to unwind the operations.
*/
static int parse_dev_params(struct raid_set *rs, struct dm_arg_set *as)
{
int i;
int rebuild = 0;
int metadata_available = 0;
int r = 0;
const char *arg;
/* Put off the number of raid devices argument to get to dev pairs */
arg = dm_shift_arg(as);
if (!arg)
return -EINVAL;
for (i = 0; i < rs->raid_disks; i++) {
rs->dev[i].rdev.raid_disk = i;
rs->dev[i].meta_dev = NULL;
rs->dev[i].data_dev = NULL;
/*
* There are no offsets, since there is a separate device
* for data and metadata.
*/
rs->dev[i].rdev.data_offset = 0;
rs->dev[i].rdev.mddev = &rs->md;
arg = dm_shift_arg(as);
if (!arg)
return -EINVAL;
if (strcmp(arg, "-")) {
r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
&rs->dev[i].meta_dev);
if (r) {
rs->ti->error = "RAID metadata device lookup failure";
return r;
}
rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL);
if (!rs->dev[i].rdev.sb_page) {
rs->ti->error = "Failed to allocate superblock page";
return -ENOMEM;
}
}
arg = dm_shift_arg(as);
if (!arg)
return -EINVAL;
if (!strcmp(arg, "-")) {
if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
(!rs->dev[i].rdev.recovery_offset)) {
rs->ti->error = "Drive designated for rebuild not specified";
return -EINVAL;
}
if (rs->dev[i].meta_dev) {
rs->ti->error = "No data device supplied with metadata device";
return -EINVAL;
}
continue;
}
r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
&rs->dev[i].data_dev);
if (r) {
rs->ti->error = "RAID device lookup failure";
return r;
}
if (rs->dev[i].meta_dev) {
metadata_available = 1;
rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev;
}
rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev;
list_add_tail(&rs->dev[i].rdev.same_set, &rs->md.disks);
if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
rebuild++;
}
if (metadata_available) {
rs->md.external = 0;
rs->md.persistent = 1;
rs->md.major_version = 2;
} else if (rebuild && !rs->md.recovery_cp) {
/*
* Without metadata, we will not be able to tell if the array
* is in-sync or not - we must assume it is not. Therefore,
* it is impossible to rebuild a drive.
*
* Even if there is metadata, the on-disk information may
* indicate that the array is not in-sync and it will then
* fail at that time.
*
* User could specify 'nosync' option if desperate.
*/
rs->ti->error = "Unable to rebuild drive while array is not in-sync";
return -EINVAL;
}
return 0;
}
/*
* validate_region_size
* @rs
* @region_size: region size in sectors. If 0, pick a size (4MiB default).
*
* Set rs->md.bitmap_info.chunksize (which really refers to 'region size').
* Ensure that (ti->len/region_size < 2^21) - required by MD bitmap.
*
* Returns: 0 on success, -EINVAL on failure.
*/
static int validate_region_size(struct raid_set *rs, unsigned long region_size)
{
unsigned long min_region_size = rs->ti->len / (1 << 21);
if (!region_size) {
/*
* Choose a reasonable default. All figures in sectors.
*/
if (min_region_size > (1 << 13)) {
/* If not a power of 2, make it the next power of 2 */
region_size = roundup_pow_of_two(min_region_size);
DMINFO("Choosing default region size of %lu sectors",
region_size);
} else {
DMINFO("Choosing default region size of 4MiB");
region_size = 1 << 13; /* sectors */
}
} else {
/*
* Validate user-supplied value.
*/
if (region_size > rs->ti->len) {
rs->ti->error = "Supplied region size is too large";
return -EINVAL;
}
if (region_size < min_region_size) {
DMERR("Supplied region_size (%lu sectors) below minimum (%lu)",
region_size, min_region_size);
rs->ti->error = "Supplied region size is too small";
return -EINVAL;
}
if (!is_power_of_2(region_size)) {
rs->ti->error = "Region size is not a power of 2";
return -EINVAL;
}
if (region_size < rs->md.chunk_sectors) {
rs->ti->error = "Region size is smaller than the chunk size";
return -EINVAL;
}
}
/*
* Convert sectors to bytes.
*/
rs->md.bitmap_info.chunksize = to_bytes(region_size);
return 0;
}
/*
* validate_raid_redundancy
* @rs
*
* Determine if there are enough devices in the array that haven't
* failed (or are being rebuilt) to form a usable array.
*
* Returns: 0 on success, -EINVAL on failure.
*/
static int validate_raid_redundancy(struct raid_set *rs)
{
unsigned int i, rebuild_cnt = 0;
unsigned int rebuilds_per_group = 0, copies;
unsigned int group_size, last_group_start;
for (i = 0; i < rs->md.raid_disks; i++)
if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
!rs->dev[i].rdev.sb_page)
rebuild_cnt++;
switch (rs->raid_type->level) {
case 1:
if (rebuild_cnt >= rs->md.raid_disks)
goto too_many;
break;
case 4:
case 5:
case 6:
if (rebuild_cnt > rs->raid_type->parity_devs)
goto too_many;
break;
case 10:
copies = raid10_md_layout_to_copies(rs->md.new_layout);
if (rebuild_cnt < copies)
break;
/*
* It is possible to have a higher rebuild count for RAID10,
* as long as the failed devices occur in different mirror
* groups (i.e. different stripes).
*
* When checking "near" format, make sure no adjacent devices
* have failed beyond what can be handled. In addition to the
* simple case where the number of devices is a multiple of the
* number of copies, we must also handle cases where the number
* of devices is not a multiple of the number of copies.
* E.g. dev1 dev2 dev3 dev4 dev5
* A A B B C
* C D D E E
*/
if (__is_raid10_near(rs->md.new_layout)) {
for (i = 0; i < rs->md.raid_disks; i++) {
if (!(i % copies))
rebuilds_per_group = 0;
if ((!rs->dev[i].rdev.sb_page ||
!test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
(++rebuilds_per_group >= copies))
goto too_many;
}
break;
}
/*
* When checking "far" and "offset" formats, we need to ensure
* that the device that holds its copy is not also dead or
* being rebuilt. (Note that "far" and "offset" formats only
* support two copies right now. These formats also only ever
* use the 'use_far_sets' variant.)
*
* This check is somewhat complicated by the need to account
* for arrays that are not a multiple of (far) copies. This
* results in the need to treat the last (potentially larger)
* set differently.
*/
group_size = (rs->md.raid_disks / copies);
last_group_start = (rs->md.raid_disks / group_size) - 1;
last_group_start *= group_size;
for (i = 0; i < rs->md.raid_disks; i++) {
if (!(i % copies) && !(i > last_group_start))
rebuilds_per_group = 0;
if ((!rs->dev[i].rdev.sb_page ||
!test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
(++rebuilds_per_group >= copies))
goto too_many;
}
break;
default:
if (rebuild_cnt)
return -EINVAL;
}
return 0;
too_many:
return -EINVAL;
}
/*
* Possible arguments are...
* <chunk_size> [optional_args]
*
* Argument definitions
* <chunk_size> The number of sectors per disk that
* will form the "stripe"
* [[no]sync] Force or prevent recovery of the
* entire array
* [rebuild <idx>] Rebuild the drive indicated by the index
* [daemon_sleep <ms>] Time between bitmap daemon work to
* clear bits
* [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization
* [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization
* [write_mostly <idx>] Indicate a write mostly drive via index
* [max_write_behind <sectors>] See '-write-behind=' (man mdadm)
* [stripe_cache <sectors>] Stripe cache size for higher RAIDs
* [region_size <sectors>] Defines granularity of bitmap
*
* RAID10-only options:
* [raid10_copies <# copies>] Number of copies. (Default: 2)
* [raid10_format <near|far|offset>] Layout algorithm. (Default: near)
*/
static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
unsigned int num_raid_params)
{
int value, raid10_format = ALGORITHM_RAID10_DEFAULT;
unsigned int raid10_copies = 2;
unsigned int i, write_mostly = 0;
unsigned int region_size = 0;
sector_t max_io_len;
const char *arg, *key;
struct raid_dev *rd;
struct raid_type *rt = rs->raid_type;
arg = dm_shift_arg(as);
num_raid_params--; /* Account for chunk_size argument */
if (kstrtoint(arg, 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given for chunk_size";
return -EINVAL;
}
/*
* First, parse the in-order required arguments
* "chunk_size" is the only argument of this type.
*/
if (rt_is_raid1(rt)) {
if (value)
DMERR("Ignoring chunk size parameter for RAID 1");
value = 0;
} else if (!is_power_of_2(value)) {
rs->ti->error = "Chunk size must be a power of 2";
return -EINVAL;
} else if (value < 8) {
rs->ti->error = "Chunk size value is too small";
return -EINVAL;
}
rs->md.new_chunk_sectors = rs->md.chunk_sectors = value;
/*
* We set each individual device as In_sync with a completed
* 'recovery_offset'. If there has been a device failure or
* replacement then one of the following cases applies:
*
* 1) User specifies 'rebuild'.
* - Device is reset when param is read.
* 2) A new device is supplied.
* - No matching superblock found, resets device.
* 3) Device failure was transient and returns on reload.
* - Failure noticed, resets device for bitmap replay.
* 4) Device hadn't completed recovery after previous failure.
* - Superblock is read and overrides recovery_offset.
*
* What is found in the superblocks of the devices is always
* authoritative, unless 'rebuild' or '[no]sync' was specified.
*/
for (i = 0; i < rs->raid_disks; i++) {
set_bit(In_sync, &rs->dev[i].rdev.flags);
rs->dev[i].rdev.recovery_offset = MaxSector;
}
/*
* Second, parse the unordered optional arguments
*/
for (i = 0; i < num_raid_params; i++) {
key = dm_shift_arg(as);
if (!key) {
rs->ti->error = "Not enough raid parameters given";
return -EINVAL;
}
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC))) {
if (test_and_set_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
rs->ti->error = "Only one 'nosync' argument allowed";
return -EINVAL;
}
continue;
}
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_SYNC))) {
if (test_and_set_bit(__CTR_FLAG_SYNC, &rs->ctr_flags)) {
rs->ti->error = "Only one 'sync' argument allowed";
return -EINVAL;
}
continue;
}
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_USE_NEAR_SETS))) {
if (test_and_set_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
rs->ti->error = "Only one 'raid10_use_new_sets' argument allowed";
return -EINVAL;
}
continue;
}
arg = dm_shift_arg(as);
i++; /* Account for the argument pairs */
if (!arg) {
rs->ti->error = "Wrong number of raid parameters given";
return -EINVAL;
}
/*
* Parameters that take a string value are checked here.
*/
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_FORMAT))) {
if (test_and_set_bit(__CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags)) {
rs->ti->error = "Only one 'raid10_format' argument pair allowed";
return -EINVAL;
}
if (!rt_is_raid10(rt)) {
rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
return -EINVAL;
}
raid10_format = raid10_name_to_format(arg);
if (raid10_format < 0) {
rs->ti->error = "Invalid 'raid10_format' value given";
return raid10_format;
}
continue;
}
if (kstrtoint(arg, 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given in raid params";
return -EINVAL;
}
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD))) {
/*
* "rebuild" is being passed in by userspace to provide
* indexes of replaced devices and to set up additional
* devices on raid level takeover.
*/
if (!__within_range(value, 0, rs->raid_disks - 1)) {
rs->ti->error = "Invalid rebuild index given";
return -EINVAL;
}
if (test_and_set_bit(value, (void *) rs->rebuild_disks)) {
rs->ti->error = "rebuild for this index already given";
return -EINVAL;
}
rd = rs->dev + value;
clear_bit(In_sync, &rd->rdev.flags);
clear_bit(Faulty, &rd->rdev.flags);
rd->rdev.recovery_offset = 0;
set_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags);
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY))) {
if (!rt_is_raid1(rt)) {
rs->ti->error = "write_mostly option is only valid for RAID1";
return -EINVAL;
}
if (!__within_range(value, 0, rs->md.raid_disks - 1)) {
rs->ti->error = "Invalid write_mostly index given";
return -EINVAL;
}
write_mostly++;
set_bit(WriteMostly, &rs->dev[value].rdev.flags);
set_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags);
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_WRITE_BEHIND))) {
if (!rt_is_raid1(rt)) {
rs->ti->error = "max_write_behind option is only valid for RAID1";
return -EINVAL;
}
if (test_and_set_bit(__CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags)) {
rs->ti->error = "Only one max_write_behind argument pair allowed";
return -EINVAL;
}
/*
* In device-mapper, we specify things in sectors, but
* MD records this value in kB
*/
value /= 2;
if (value > COUNTER_MAX) {
rs->ti->error = "Max write-behind limit out of range";
return -EINVAL;
}
rs->md.bitmap_info.max_write_behind = value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP))) {
if (test_and_set_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags)) {
rs->ti->error = "Only one daemon_sleep argument pair allowed";
return -EINVAL;
}
if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
rs->ti->error = "daemon sleep period out of range";
return -EINVAL;
}
rs->md.bitmap_info.daemon_sleep = value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DATA_OFFSET))) {
/* Userspace passes new data_offset after having extended the the data image LV */
if (test_and_set_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
rs->ti->error = "Only one data_offset argument pair allowed";
return -EINVAL;
}
/* Ensure sensible data offset */
if (value < 0 ||
(value && (value < MIN_FREE_RESHAPE_SPACE || value % to_sector(PAGE_SIZE)))) {
rs->ti->error = "Bogus data_offset value";
return -EINVAL;
}
rs->data_offset = value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DELTA_DISKS))) {
/* Define the +/-# of disks to add to/remove from the given raid set */
if (test_and_set_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
rs->ti->error = "Only one delta_disks argument pair allowed";
return -EINVAL;
}
/* Ensure MAX_RAID_DEVICES and raid type minimal_devs! */
if (!__within_range(abs(value), 1, MAX_RAID_DEVICES - rt->minimal_devs)) {
rs->ti->error = "Too many delta_disk requested";
return -EINVAL;
}
rs->delta_disks = value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_STRIPE_CACHE))) {
if (test_and_set_bit(__CTR_FLAG_STRIPE_CACHE, &rs->ctr_flags)) {
rs->ti->error = "Only one stripe_cache argument pair allowed";
return -EINVAL;
}
if (!rt_is_raid456(rt)) {
rs->ti->error = "Inappropriate argument: stripe_cache";
return -EINVAL;
}
rs->stripe_cache_entries = value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MIN_RECOVERY_RATE))) {
if (test_and_set_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags)) {
rs->ti->error = "Only one min_recovery_rate argument pair allowed";
return -EINVAL;
}
if (value > INT_MAX) {
rs->ti->error = "min_recovery_rate out of range";
return -EINVAL;
}
rs->md.sync_speed_min = (int)value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE))) {
if (test_and_set_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags)) {
rs->ti->error = "Only one max_recovery_rate argument pair allowed";
return -EINVAL;
}
if (value > INT_MAX) {
rs->ti->error = "max_recovery_rate out of range";
return -EINVAL;
}
rs->md.sync_speed_max = (int)value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REGION_SIZE))) {
if (test_and_set_bit(__CTR_FLAG_REGION_SIZE, &rs->ctr_flags)) {
rs->ti->error = "Only one region_size argument pair allowed";
return -EINVAL;
}
region_size = value;
rs->requested_bitmap_chunk_sectors = value;
} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_COPIES))) {
if (test_and_set_bit(__CTR_FLAG_RAID10_COPIES, &rs->ctr_flags)) {
rs->ti->error = "Only one raid10_copies argument pair allowed";
return -EINVAL;
}
if (!__within_range(value, 2, rs->md.raid_disks)) {
rs->ti->error = "Bad value for 'raid10_copies'";
return -EINVAL;
}
raid10_copies = value;
} else {
DMERR("Unable to parse RAID parameter: %s", key);
rs->ti->error = "Unable to parse RAID parameter";
return -EINVAL;
}
}
if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) &&
test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
rs->ti->error = "sync and nosync are mutually exclusive";
return -EINVAL;
}
if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags) &&
(test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ||
test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))) {
rs->ti->error = "sync/nosync and rebuild are mutually exclusive";
return -EINVAL;
}
if (write_mostly >= rs->md.raid_disks) {
rs->ti->error = "Can't set all raid1 devices to write_mostly";
return -EINVAL;
}
if (validate_region_size(rs, region_size))
return -EINVAL;
if (rs->md.chunk_sectors)
max_io_len = rs->md.chunk_sectors;
else
max_io_len = region_size;
if (dm_set_target_max_io_len(rs->ti, max_io_len))
return -EINVAL;
if (rt_is_raid10(rt)) {
if (raid10_copies > rs->md.raid_disks) {
rs->ti->error = "Not enough devices to satisfy specification";
return -EINVAL;
}
rs->md.new_layout = raid10_format_to_md_layout(rs, raid10_format, raid10_copies);
if (rs->md.new_layout < 0) {
rs->ti->error = "Error getting raid10 format";
return rs->md.new_layout;
}
rt = get_raid_type_by_ll(10, rs->md.new_layout);
if (!rt) {
rs->ti->error = "Failed to recognize new raid10 layout";
return -EINVAL;
}
if ((rt->algorithm == ALGORITHM_RAID10_DEFAULT ||
rt->algorithm == ALGORITHM_RAID10_NEAR) &&
test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
rs->ti->error = "RAID10 format 'near' and 'raid10_use_near_sets' are incompatible";
return -EINVAL;
}
}
rs->raid10_copies = raid10_copies;
/* Assume there are no metadata devices until the drives are parsed */
rs->md.persistent = 0;
rs->md.external = 1;
/* Check, if any invalid ctr arguments have been passed in for the raid level */
return rs_check_for_valid_flags(rs);
}
/* Set raid4/5/6 cache size */
static int rs_set_raid456_stripe_cache(struct raid_set *rs)
{
int r;
struct r5conf *conf;
struct mddev *mddev = &rs->md;
uint32_t min_stripes = max(mddev->chunk_sectors, mddev->new_chunk_sectors) / 2;
uint32_t nr_stripes = rs->stripe_cache_entries;
if (!rt_is_raid456(rs->raid_type)) {
rs->ti->error = "Inappropriate raid level; cannot change stripe_cache size";
return -EINVAL;
}
if (nr_stripes < min_stripes) {
DMINFO("Adjusting requested %u stripe cache entries to %u to suit stripe size",
nr_stripes, min_stripes);
nr_stripes = min_stripes;
}
conf = mddev->private;
if (!conf) {
rs->ti->error = "Cannot change stripe_cache size on inactive RAID set";
return -EINVAL;
}
/* Try setting number of stripes in raid456 stripe cache */
if (conf->min_nr_stripes != nr_stripes) {
r = raid5_set_cache_size(mddev, nr_stripes);
if (r) {
rs->ti->error = "Failed to set raid4/5/6 stripe cache size";
return r;
}
DMINFO("%u stripe cache entries", nr_stripes);
}
return 0;
}
/* Return # of data stripes as kept in mddev as of @rs (i.e. as of superblock) */
static unsigned int mddev_data_stripes(struct raid_set *rs)
{
return rs->md.raid_disks - rs->raid_type->parity_devs;
}
/* Return # of data stripes of @rs (i.e. as of ctr) */
static unsigned int rs_data_stripes(struct raid_set *rs)
{
return rs->raid_disks - rs->raid_type->parity_devs;
}
/* Calculate the sectors per device and per array used for @rs */
static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
{
int delta_disks;
unsigned int data_stripes;
struct mddev *mddev = &rs->md;
struct md_rdev *rdev;
sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len;
if (use_mddev) {
delta_disks = mddev->delta_disks;
data_stripes = mddev_data_stripes(rs);
} else {
delta_disks = rs->delta_disks;
data_stripes = rs_data_stripes(rs);
}
/* Special raid1 case w/o delta_disks support (yet) */
if (rt_is_raid1(rs->raid_type))
;
else if (rt_is_raid10(rs->raid_type)) {
if (rs->raid10_copies < 2 ||
delta_disks < 0) {
rs->ti->error = "Bogus raid10 data copies or delta disks";
return -EINVAL;
}
dev_sectors *= rs->raid10_copies;
if (sector_div(dev_sectors, data_stripes))
goto bad;
array_sectors = (data_stripes + delta_disks) * dev_sectors;
if (sector_div(array_sectors, rs->raid10_copies))
goto bad;
} else if (sector_div(dev_sectors, data_stripes))
goto bad;
else
/* Striped layouts */
array_sectors = (data_stripes + delta_disks) * dev_sectors;
rdev_for_each(rdev, mddev)
rdev->sectors = dev_sectors;
mddev->array_sectors = array_sectors;
mddev->dev_sectors = dev_sectors;
return 0;
bad:
rs->ti->error = "Target length not divisible by number of data devices";
return -EINVAL;
}
/* Setup recovery on @rs */
static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
{
/* raid0 does not recover */
if (rs_is_raid0(rs))
rs->md.recovery_cp = MaxSector;
/*
* A raid6 set has to be recovered either
* completely or for the grown part to
* ensure proper parity and Q-Syndrome
*/
else if (rs_is_raid6(rs))
rs->md.recovery_cp = dev_sectors;
/*
* Other raid set types may skip recovery
* depending on the 'nosync' flag.
*/
else
rs->md.recovery_cp = test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)
? MaxSector : dev_sectors;
}
/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */
static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
{
if (!dev_sectors)
/* New raid set or 'sync' flag provided */
__rs_setup_recovery(rs, 0);
else if (dev_sectors == MaxSector)
/* Prevent recovery */
__rs_setup_recovery(rs, MaxSector);
else if (rs->dev[0].rdev.sectors < dev_sectors)
/* Grown raid set */
__rs_setup_recovery(rs, rs->dev[0].rdev.sectors);
else
__rs_setup_recovery(rs, MaxSector);
}
static void do_table_event(struct work_struct *ws)
{
struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
smp_rmb(); /* Make sure we access most actual mddev properties */
if (!rs_is_reshaping(rs))
rs_set_capacity(rs);
dm_table_event(rs->ti->table);
}
static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
{
struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
return mddev_congested(&rs->md, bits);
}
/*
* Make sure a valid takover (level switch) is being requested on @rs
*
* Conversions of raid sets from one MD personality to another
* have to conform to restrictions which are enforced here.
*/
static int rs_check_takeover(struct raid_set *rs)
{
struct mddev *mddev = &rs->md;
unsigned int near_copies;
if (rs->md.degraded) {
rs->ti->error = "Can't takeover degraded raid set";
return -EPERM;
}
if (rs_is_reshaping(rs)) {
rs->ti->error = "Can't takeover reshaping raid set";
return -EPERM;
}
switch (mddev->level) {
case 0:
/* raid0 -> raid1/5 with one disk */
if ((mddev->new_level == 1 || mddev->new_level == 5) &&
mddev->raid_disks == 1)
return 0;
/* raid0 -> raid10 */
if (mddev->new_level == 10 &&
!(rs->raid_disks % mddev->raid_disks))
return 0;
/* raid0 with multiple disks -> raid4/5/6 */
if (__within_range(mddev->new_level, 4, 6) &&
mddev->new_layout == ALGORITHM_PARITY_N &&
mddev->raid_disks > 1)
return 0;
break;
case 10:
/* Can't takeover raid10_offset! */
if (__is_raid10_offset(mddev->layout))
break;
near_copies = __raid10_near_copies(mddev->layout);
/* raid10* -> raid0 */
if (mddev->new_level == 0) {
/* Can takeover raid10_near with raid disks divisable by data copies! */
if (near_copies > 1 &&
!(mddev->raid_disks % near_copies)) {
mddev->raid_disks /= near_copies;
mddev->delta_disks = mddev->raid_disks;
return 0;
}
/* Can takeover raid10_far */
if (near_copies == 1 &&
__raid10_far_copies(mddev->layout) > 1)
return 0;
break;
}
/* raid10_{near,far} -> raid1 */
if (mddev->new_level == 1 &&
max(near_copies, __raid10_far_copies(mddev->layout)) == mddev->raid_disks)
return 0;
/* raid10_{near,far} with 2 disks -> raid4/5 */
if (__within_range(mddev->new_level, 4, 5) &&
mddev->raid_disks == 2)
return 0;
break;
case 1:
/* raid1 with 2 disks -> raid4/5 */
if (__within_range(mddev->new_level, 4, 5) &&
mddev->raid_disks == 2) {
mddev->degraded = 1;
return 0;
}
/* raid1 -> raid0 */
if (mddev->new_level == 0 &&
mddev->raid_disks == 1)
return 0;
/* raid1 -> raid10 */
if (mddev->new_level == 10)
return 0;
break;
case 4:
/* raid4 -> raid0 */
if (mddev->new_level == 0)
return 0;
/* raid4 -> raid1/5 with 2 disks */
if ((mddev->new_level == 1 || mddev->new_level == 5) &&
mddev->raid_disks == 2)
return 0;
/* raid4 -> raid5/6 with parity N */
if (__within_range(mddev->new_level, 5, 6) &&
mddev->layout == ALGORITHM_PARITY_N)
return 0;
break;
case 5:
/* raid5 with parity N -> raid0 */
if (mddev->new_level == 0 &&
mddev->layout == ALGORITHM_PARITY_N)
return 0;
/* raid5 with parity N -> raid4 */
if (mddev->new_level == 4 &&
mddev->layout == ALGORITHM_PARITY_N)
return 0;
/* raid5 with 2 disks -> raid1/4/10 */
if ((mddev->new_level == 1 || mddev->new_level == 4 || mddev->new_level == 10) &&
mddev->raid_disks == 2)
return 0;
/* raid5_* -> raid6_*_6 with Q-Syndrome N (e.g. raid5_ra -> raid6_ra_6 */
if (mddev->new_level == 6 &&
((mddev->layout == ALGORITHM_PARITY_N && mddev->new_layout == ALGORITHM_PARITY_N) ||
__within_range(mddev->new_layout, ALGORITHM_LEFT_ASYMMETRIC_6, ALGORITHM_RIGHT_SYMMETRIC_6)))
return 0;
break;
case 6:
/* raid6 with parity N -> raid0 */
if (mddev->new_level == 0 &&
mddev->layout == ALGORITHM_PARITY_N)
return 0;
/* raid6 with parity N -> raid4 */
if (mddev->new_level == 4 &&
mddev->layout == ALGORITHM_PARITY_N)
return 0;
/* raid6_*_n with Q-Syndrome N -> raid5_* */
if (mddev->new_level == 5 &&
((mddev->layout == ALGORITHM_PARITY_N && mddev->new_layout == ALGORITHM_PARITY_N) ||
__within_range(mddev->new_layout, ALGORITHM_LEFT_ASYMMETRIC, ALGORITHM_RIGHT_SYMMETRIC)))
return 0;
default:
break;
}
rs->ti->error = "takeover not possible";
return -EINVAL;
}
/* True if @rs requested to be taken over */
static bool rs_takeover_requested(struct raid_set *rs)
{
return rs->md.new_level != rs->md.level;
}
/* True if @rs is requested to reshape by ctr */
static bool rs_reshape_requested(struct raid_set *rs)
{
bool change;
struct mddev *mddev = &rs->md;
if (rs_takeover_requested(rs))
return false;
if (!mddev->level)
return false;
change = mddev->new_layout != mddev->layout ||
mddev->new_chunk_sectors != mddev->chunk_sectors ||
rs->delta_disks;
/* Historical case to support raid1 reshape without delta disks */
if (mddev->level == 1) {
if (rs->delta_disks)
return !!rs->delta_disks;
return !change &&
mddev->raid_disks != rs->raid_disks;
}
if (mddev->level == 10)
return change &&
!__is_raid10_far(mddev->new_layout) &&
rs->delta_disks >= 0;
return change;
}
/* Features */
#define FEATURE_FLAG_SUPPORTS_V190 0x1 /* Supports extended superblock */
/* State flags for sb->flags */
#define SB_FLAG_RESHAPE_ACTIVE 0x1
#define SB_FLAG_RESHAPE_BACKWARDS 0x2
/*
* This structure is never routinely used by userspace, unlike md superblocks.
* Devices with this superblock should only ever be accessed via device-mapper.
*/
#define DM_RAID_MAGIC 0x64526D44
struct dm_raid_superblock {
__le32 magic; /* "DmRd" */
__le32 compat_features; /* Used to indicate compatible features (like 1.9.0 ondisk metadata extension) */
__le32 num_devices; /* Number of devices in this raid set. (Max 64) */
__le32 array_position; /* The position of this drive in the raid set */
__le64 events; /* Incremented by md when superblock updated */
__le64 failed_devices; /* Pre 1.9.0 part of bit field of devices to */
/* indicate failures (see extension below) */
/*
* This offset tracks the progress of the repair or replacement of
* an individual drive.
*/
__le64 disk_recovery_offset;
/*
* This offset tracks the progress of the initial raid set
* synchronisation/parity calculation.
*/
__le64 array_resync_offset;
/*
* raid characteristics
*/
__le32 level;
__le32 layout;
__le32 stripe_sectors;
/********************************************************************
* BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!!
*
* FEATURE_FLAG_SUPPORTS_V190 in the features member indicates that those exist
*/
__le32 flags; /* Flags defining array states for reshaping */
/*
* This offset tracks the progress of a raid
* set reshape in order to be able to restart it
*/
__le64 reshape_position;
/*
* These define the properties of the array in case of an interrupted reshape
*/
__le32 new_level;
__le32 new_layout;
__le32 new_stripe_sectors;
__le32 delta_disks;
__le64 array_sectors; /* Array size in sectors */
/*
* Sector offsets to data on devices (reshaping).
* Needed to support out of place reshaping, thus
* not writing over any stripes whilst converting
* them from old to new layout
*/
__le64 data_offset;
__le64 new_data_offset;
__le64 sectors; /* Used device size in sectors */
/*
* Additonal Bit field of devices indicating failures to support
* up to 256 devices with the 1.9.0 on-disk metadata format
*/
__le64 extended_failed_devices[DISKS_ARRAY_ELEMS - 1];
__le32 incompat_features; /* Used to indicate any incompatible features */
/* Always set rest up to logical block size to 0 when writing (see get_metadata_device() below). */
} __packed;
/*
* Check for reshape constraints on raid set @rs:
*
* - reshape function non-existent
* - degraded set
* - ongoing recovery
* - ongoing reshape
*
* Returns 0 if none or -EPERM if given constraint
* and error message reference in @errmsg
*/
static int rs_check_reshape(struct raid_set *rs)
{
struct mddev *mddev = &rs->md;
if (!mddev->pers || !mddev->pers->check_reshape)
rs->ti->error = "Reshape not supported";
else if (mddev->degraded)
rs->ti->error = "Can't reshape degraded raid set";
else if (rs_is_recovering(rs))
rs->ti->error = "Convert request on recovering raid set prohibited";
else if (rs_is_reshaping(rs))
rs->ti->error = "raid set already reshaping!";
else if (!(rs_is_raid1(rs) || rs_is_raid10(rs) || rs_is_raid456(rs)))
rs->ti->error = "Reshaping only supported for raid1/4/5/6/10";
else
return 0;
return -EPERM;
}
static int read_disk_sb(struct md_rdev *rdev, int size)
{
BUG_ON(!rdev->sb_page);
if (rdev->sb_loaded)
return 0;
if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true)) {
DMERR("Failed to read superblock of device at position %d",
rdev->raid_disk);
md_error(rdev->mddev, rdev);
return -EINVAL;
}
rdev->sb_loaded = 1;
return 0;
}
static void sb_retrieve_failed_devices(struct dm_raid_superblock *sb, uint64_t *failed_devices)
{
failed_devices[0] = le64_to_cpu(sb->failed_devices);
memset(failed_devices + 1, 0, sizeof(sb->extended_failed_devices));
if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
int i = ARRAY_SIZE(sb->extended_failed_devices);
while (i--)
failed_devices[i+1] = le64_to_cpu(sb->extended_failed_devices[i]);
}
}
static void sb_update_failed_devices(struct dm_raid_superblock *sb, uint64_t *failed_devices)
{
int i = ARRAY_SIZE(sb->extended_failed_devices);
sb->failed_devices = cpu_to_le64(failed_devices[0]);
while (i--)
sb->extended_failed_devices[i] = cpu_to_le64(failed_devices[i+1]);
}
/*
* Synchronize the superblock members with the raid set properties
*
* All superblock data is little endian.
*/
static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
{
bool update_failed_devices = false;
unsigned int i;
uint64_t failed_devices[DISKS_ARRAY_ELEMS];
struct dm_raid_superblock *sb;
struct raid_set *rs = container_of(mddev, struct raid_set, md);
/* No metadata device, no superblock */
if (!rdev->meta_bdev)
return;
BUG_ON(!rdev->sb_page);
sb = page_address(rdev->sb_page);
sb_retrieve_failed_devices(sb, failed_devices);
for (i = 0; i < rs->raid_disks; i++)
if (!rs->dev[i].data_dev || test_bit(Faulty, &rs->dev[i].rdev.flags)) {
update_failed_devices = true;
set_bit(i, (void *) failed_devices);
}
if (update_failed_devices)
sb_update_failed_devices(sb, failed_devices);
sb->magic = cpu_to_le32(DM_RAID_MAGIC);
sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
sb->num_devices = cpu_to_le32(mddev->raid_disks);
sb->array_position = cpu_to_le32(rdev->raid_disk);
sb->events = cpu_to_le64(mddev->events);
sb->disk_recovery_offset = cpu_to_le64(rdev->recovery_offset);
sb->array_resync_offset = cpu_to_le64(mddev->recovery_cp);
sb->level = cpu_to_le32(mddev->level);
sb->layout = cpu_to_le32(mddev->layout);
sb->stripe_sectors = cpu_to_le32(mddev->chunk_sectors);
sb->new_level = cpu_to_le32(mddev->new_level);
sb->new_layout = cpu_to_le32(mddev->new_layout);
sb->new_stripe_sectors = cpu_to_le32(mddev->new_chunk_sectors);
sb->delta_disks = cpu_to_le32(mddev->delta_disks);
smp_rmb(); /* Make sure we access most recent reshape position */
sb->reshape_position = cpu_to_le64(mddev->reshape_position);
if (le64_to_cpu(sb->reshape_position) != MaxSector) {
/* Flag ongoing reshape */
sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE);
if (mddev->delta_disks < 0 || mddev->reshape_backwards)
sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_BACKWARDS);
} else {
/* Clear reshape flags */
sb->flags &= ~(cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE|SB_FLAG_RESHAPE_BACKWARDS));
}
sb->array_sectors = cpu_to_le64(mddev->array_sectors);
sb->data_offset = cpu_to_le64(rdev->data_offset);
sb->new_data_offset = cpu_to_le64(rdev->new_data_offset);
sb->sectors = cpu_to_le64(rdev->sectors);
sb->incompat_features = cpu_to_le32(0);
/* Zero out the rest of the payload after the size of the superblock */
memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
}
/*
* super_load
*
* This function creates a superblock if one is not found on the device
* and will decide which superblock to use if there's a choice.
*
* Return: 1 if use rdev, 0 if use refdev, -Exxx otherwise
*/
static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
{
int r;
struct dm_raid_superblock *sb;
struct dm_raid_superblock *refsb;
uint64_t events_sb, events_refsb;
rdev->sb_start = 0;
rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev);
if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) {
DMERR("superblock size of a logical block is no longer valid");
return -EINVAL;
}
r = read_disk_sb(rdev, rdev->sb_size);
if (r)
return r;
sb = page_address(rdev->sb_page);
/*
* Two cases that we want to write new superblocks and rebuild:
* 1) New device (no matching magic number)
* 2) Device specified for rebuild (!In_sync w/ offset == 0)
*/
if ((sb->magic != cpu_to_le32(DM_RAID_MAGIC)) ||
(!test_bit(In_sync, &rdev->flags) && !rdev->recovery_offset)) {
super_sync(rdev->mddev, rdev);
set_bit(FirstUse, &rdev->flags);
sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
/* Force writing of superblocks to disk */
set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);
/* Any superblock is better than none, choose that if given */
return refdev ? 0 : 1;
}
if (!refdev)
return 1;
events_sb = le64_to_cpu(sb->events);
refsb = page_address(refdev->sb_page);
events_refsb = le64_to_cpu(refsb->events);
return (events_sb > events_refsb) ? 1 : 0;
}
static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
{
int role;
unsigned int d;
struct mddev *mddev = &rs->md;
uint64_t events_sb;
uint64_t failed_devices[DISKS_ARRAY_ELEMS];
struct dm_raid_superblock *sb;
uint32_t new_devs = 0, rebuild_and_new = 0, rebuilds = 0;
struct md_rdev *r;
struct dm_raid_superblock *sb2;
sb = page_address(rdev->sb_page);
events_sb = le64_to_cpu(sb->events);
/*
* Initialise to 1 if this is a new superblock.
*/
mddev->events = events_sb ? : 1;
mddev->reshape_position = MaxSector;
/*
* Reshaping is supported, e.g. reshape_position is valid
* in superblock and superblock content is authoritative.
*/
if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
/* Superblock is authoritative wrt given raid set layout! */
mddev->raid_disks = le32_to_cpu(sb->num_devices);
mddev->level = le32_to_cpu(sb->level);
mddev->layout = le32_to_cpu(sb->layout);
mddev->chunk_sectors = le32_to_cpu(sb->stripe_sectors);
mddev->new_level = le32_to_cpu(sb->new_level);
mddev->new_layout = le32_to_cpu(sb->new_layout);
mddev->new_chunk_sectors = le32_to_cpu(sb->new_stripe_sectors);
mddev->delta_disks = le32_to_cpu(sb->delta_disks);
mddev->array_sectors = le64_to_cpu(sb->array_sectors);
/* raid was reshaping and got interrupted */
if (le32_to_cpu(sb->flags) & SB_FLAG_RESHAPE_ACTIVE) {
if (test_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
DMERR("Reshape requested but raid set is still reshaping");
return -EINVAL;
}
if (mddev->delta_disks < 0 ||
(!mddev->delta_disks && (le32_to_cpu(sb->flags) & SB_FLAG_RESHAPE_BACKWARDS)))
mddev->reshape_backwards = 1;
else
mddev->reshape_backwards = 0;
mddev->reshape_position = le64_to_cpu(sb->reshape_position);
rs->raid_type = get_raid_type_by_ll(mddev->level, mddev->layout);
}
} else {
/*
* No takeover/reshaping, because we don't have the extended v1.9.0 metadata
*/
if (le32_to_cpu(sb->level) != mddev->level) {
DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)");
return -EINVAL;
}
if (le32_to_cpu(sb->layout) != mddev->layout) {
DMERR("Reshaping raid sets not yet supported. (raid layout change)");
DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
DMERR(" Old layout: %s w/ %d copies",
raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
DMERR(" New layout: %s w/ %d copies",
raid10_md_layout_to_format(mddev->layout),
raid10_md_layout_to_copies(mddev->layout));
return -EINVAL;
}
if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
DMERR("Reshaping raid sets not yet supported. (stripe sectors change)");
return -EINVAL;
}
/* We can only change the number of devices in raid1 with old (i.e. pre 1.0.7) metadata */
if (!rt_is_raid1(rs->raid_type) &&
(le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
DMERR("Reshaping raid sets not yet supported. (device count change from %u to %u)",
sb->num_devices, mddev->raid_disks);
return -EINVAL;
}
/* Table line is checked vs. authoritative superblock */
rs_set_new(rs);
}
if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
mddev->recovery_cp = le64_to_cpu(sb->array_resync_offset);
/*
* During load, we set FirstUse if a new superblock was written.
* There are two reasons we might not have a superblock:
* 1) The raid set is brand new - in which case, all of the
* devices must have their In_sync bit set. Also,
* recovery_cp must be 0, unless forced.
* 2) This is a new device being added to an old raid set
* and the new device needs to be rebuilt - in which
* case the In_sync bit will /not/ be set and
* recovery_cp must be MaxSector.
* 3) This is/are a new device(s) being added to an old
* raid set during takeover to a higher raid level
* to provide capacity for redundancy or during reshape
* to add capacity to grow the raid set.
*/
d = 0;
rdev_for_each(r, mddev) {
if (test_bit(FirstUse, &r->flags))
new_devs++;
if (!test_bit(In_sync, &r->flags)) {
DMINFO("Device %d specified for rebuild; clearing superblock",
r->raid_disk);
rebuilds++;
if (test_bit(FirstUse, &r->flags))
rebuild_and_new++;
}
d++;
}
if (new_devs == rs->raid_disks || !rebuilds) {
/* Replace a broken device */
if (new_devs == 1 && !rs->delta_disks)
;
if (new_devs == rs->raid_disks) {
DMINFO("Superblocks created for new raid set");
set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
} else if (new_devs != rebuilds &&
new_devs != rs->delta_disks) {
DMERR("New device injected into existing raid set without "
"'delta_disks' or 'rebuild' parameter specified");
return -EINVAL;
}
} else if (new_devs && new_devs != rebuilds) {
DMERR("%u 'rebuild' devices cannot be injected into"
" a raid set with %u other first-time devices",
rebuilds, new_devs);
return -EINVAL;
} else if (rebuilds) {
if (rebuild_and_new && rebuilds != rebuild_and_new) {
DMERR("new device%s provided without 'rebuild'",
new_devs > 1 ? "s" : "");
return -EINVAL;
} else if (rs_is_recovering(rs)) {
DMERR("'rebuild' specified while raid set is not in-sync (recovery_cp=%llu)",
(unsigned long long) mddev->recovery_cp);
return -EINVAL;
} else if (rs_is_reshaping(rs)) {
DMERR("'rebuild' specified while raid set is being reshaped (reshape_position=%llu)",
(unsigned long long) mddev->reshape_position);
return -EINVAL;
}
}
/*
* Now we set the Faulty bit for those devices that are
* recorded in the superblock as failed.
*/
sb_retrieve_failed_devices(sb, failed_devices);
rdev_for_each(r, mddev) {
if (!r->sb_page)
continue;
sb2 = page_address(r->sb_page);
sb2->failed_devices = 0;
memset(sb2->extended_failed_devices, 0, sizeof(sb2->extended_failed_devices));
/*
* Check for any device re-ordering.
*/
if (!test_bit(FirstUse, &r->flags) && (r->raid_disk >= 0)) {
role = le32_to_cpu(sb2->array_position);
if (role < 0)
continue;
if (role != r->raid_disk) {
if (__is_raid10_near(mddev->layout)) {
if (mddev->raid_disks % __raid10_near_copies(mddev->layout) ||
rs->raid_disks % rs->raid10_copies) {
rs->ti->error =
"Cannot change raid10 near set to odd # of devices!";
return -EINVAL;
}
sb2->array_position = cpu_to_le32(r->raid_disk);
} else if (!(rs_is_raid10(rs) && rt_is_raid0(rs->raid_type)) &&
!(rs_is_raid0(rs) && rt_is_raid10(rs->raid_type)) &&
!rt_is_raid1(rs->raid_type)) {
rs->ti->error = "Cannot change device positions in raid set";
return -EINVAL;
}
DMINFO("raid device #%d now at position #%d", role, r->raid_disk);
}
/*
* Partial recovery is performed on
* returning failed devices.
*/
if (test_bit(role, (void *) failed_devices))
set_bit(Faulty, &r->flags);
}
}
return 0;
}
static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
{
struct mddev *mddev = &rs->md;
struct dm_raid_superblock *sb;
if (rs_is_raid0(rs) || !rdev->sb_page)
return 0;
sb = page_address(rdev->sb_page);
/*
* If mddev->events is not set, we know we have not yet initialized
* the array.
*/
if (!mddev->events && super_init_validation(rs, rdev))
return -EINVAL;
if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags";
return -EINVAL;
}
if (sb->incompat_features) {
rs->ti->error = "Unable to assemble array: No incompatible feature flags supported yet";
return -EINVAL;
}
/* Enable bitmap creation for RAID levels != 0 */
mddev->bitmap_info.offset = rt_is_raid0(rs->raid_type) ? 0 : to_sector(4096);
rdev->mddev->bitmap_info.default_offset = mddev->bitmap_info.offset;
if (!test_and_clear_bit(FirstUse, &rdev->flags)) {
/* Retrieve device size stored in superblock to be prepared for shrink */
rdev->sectors = le64_to_cpu(sb->sectors);
rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset);
if (rdev->recovery_offset == MaxSector)
set_bit(In_sync, &rdev->flags);
/*
* If no reshape in progress -> we're recovering single
* disk(s) and have to set the device(s) to out-of-sync
*/
else if (!rs_is_reshaping(rs))
clear_bit(In_sync, &rdev->flags); /* Mandatory for recovery */
}
/*
* If a device comes back, set it as not In_sync and no longer faulty.
*/
if (test_and_clear_bit(Faulty, &rdev->flags)) {
rdev->recovery_offset = 0;
clear_bit(In_sync, &rdev->flags);
rdev->saved_raid_disk = rdev->raid_disk;
}
/* Reshape support -> restore repective data offsets */
rdev->data_offset = le64_to_cpu(sb->data_offset);
rdev->new_data_offset = le64_to_cpu(sb->new_data_offset);
return 0;
}
/*
* Analyse superblocks and select the freshest.
*/
static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
{
int r;
struct raid_dev *dev;
struct md_rdev *rdev, *tmp, *freshest;
struct mddev *mddev = &rs->md;
freshest = NULL;
rdev_for_each_safe(rdev, tmp, mddev) {
/*
* Skipping super_load due to CTR_FLAG_SYNC will cause
* the array to undergo initialization again as
* though it were new. This is the intended effect
* of the "sync" directive.
*
* When reshaping capability is added, we must ensure
* that the "sync" directive is disallowed during the
* reshape.
*/
if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags))
continue;
if (!rdev->meta_bdev)
continue;
r = super_load(rdev, freshest);
switch (r) {
case 1:
freshest = rdev;
break;
case 0:
break;
default:
dev = container_of(rdev, struct raid_dev, rdev);
if (dev->meta_dev)
dm_put_device(ti, dev->meta_dev);
dev->meta_dev = NULL;
rdev->meta_bdev = NULL;
if (rdev->sb_page)
put_page(rdev->sb_page);
rdev->sb_page = NULL;
rdev->sb_loaded = 0;
/*
* We might be able to salvage the data device
* even though the meta device has failed. For
* now, we behave as though '- -' had been
* set for this device in the table.
*/
if (dev->data_dev)
dm_put_device(ti, dev->data_dev);
dev->data_dev = NULL;
rdev->bdev = NULL;
list_del(&rdev->same_set);
}
}
if (!freshest)
return 0;
if (validate_raid_redundancy(rs)) {
rs->ti->error = "Insufficient redundancy to activate array";
return -EINVAL;
}
/*
* Validation of the freshest device provides the source of
* validation for the remaining devices.
*/
rs->ti->error = "Unable to assemble array: Invalid superblocks";
if (super_validate(rs, freshest))
return -EINVAL;
rdev_for_each(rdev, mddev)
if ((rdev != freshest) && super_validate(rs, rdev))
return -EINVAL;
return 0;
}
/*
* Adjust data_offset and new_data_offset on all disk members of @rs
* for out of place reshaping if requested by contructor
*
* We need free space at the beginning of each raid disk for forward
* and at the end for backward reshapes which userspace has to provide
* via remapping/reordering of space.
*/
static int rs_adjust_data_offsets(struct raid_set *rs)
{
sector_t data_offset = 0, new_data_offset = 0;
struct md_rdev *rdev;
/* Constructor did not request data offset change */
if (!test_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
if (!rs_is_reshapable(rs))
goto out;
return 0;
}
/* HM FIXME: get InSync raid_dev? */
rdev = &rs->dev[0].rdev;
if (rs->delta_disks < 0) {
/*
* Removing disks (reshaping backwards):
*
* - before reshape: data is at offset 0 and free space
* is at end of each component LV
*
* - after reshape: data is at offset rs->data_offset != 0 on each component LV
*/
data_offset = 0;
new_data_offset = rs->data_offset;
} else if (rs->delta_disks > 0) {
/*
* Adding disks (reshaping forwards):
*
* - before reshape: data is at offset rs->data_offset != 0 and
* free space is at begin of each component LV
*
* - after reshape: data is at offset 0 on each component LV
*/
data_offset = rs->data_offset;
new_data_offset = 0;
} else {
/*
* User space passes in 0 for data offset after having removed reshape space
*
* - or - (data offset != 0)
*
* Changing RAID layout or chunk size -> toggle offsets
*
* - before reshape: data is at offset rs->data_offset 0 and
* free space is at end of each component LV
* -or-
* data is at offset rs->data_offset != 0 and
* free space is at begin of each component LV
*
* - after reshape: data is at offset 0 if it was at offset != 0
* or at offset != 0 if it was at offset 0
* on each component LV
*
*/
data_offset = rs->data_offset ? rdev->data_offset : 0;
new_data_offset = data_offset ? 0 : rs->data_offset;
set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
}
/*
* Make sure we got a minimum amount of free sectors per device
*/
if (rs->data_offset &&
to_sector(i_size_read(rdev->bdev->bd_inode)) - rdev->sectors < MIN_FREE_RESHAPE_SPACE) {
rs->ti->error = data_offset ? "No space for forward reshape" :
"No space for backward reshape";
return -ENOSPC;
}
out:
/* Adjust data offsets on all rdevs */
rdev_for_each(rdev, &rs->md) {
rdev->data_offset = data_offset;
rdev->new_data_offset = new_data_offset;
}
return 0;
}
/* Userpace reordered disks -> adjust raid_disk indexes in @rs */
static void __reorder_raid_disk_indexes(struct raid_set *rs)
{
int i = 0;
struct md_rdev *rdev;
rdev_for_each(rdev, &rs->md) {
rdev->raid_disk = i++;
rdev->saved_raid_disk = rdev->new_raid_disk = -1;
}
}
/*
* Setup @rs for takeover by a different raid level
*/
static int rs_setup_takeover(struct raid_set *rs)
{
struct mddev *mddev = &rs->md;
struct md_rdev *rdev;
unsigned int d = mddev->raid_disks = rs->raid_disks;
sector_t new_data_offset = rs->dev[0].rdev.data_offset ? 0 : rs->data_offset;
if (rt_is_raid10(rs->raid_type)) {
if (mddev->level == 0) {
/* Userpace reordered disks -> adjust raid_disk indexes */
__reorder_raid_disk_indexes(rs);
/* raid0 -> raid10_far layout */
mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_FAR,
rs->raid10_copies);
} else if (mddev->level == 1)
/* raid1 -> raid10_near layout */
mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_NEAR,
rs->raid_disks);
else
return -EINVAL;
}
clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
mddev->recovery_cp = MaxSector;
while (d--) {
rdev = &rs->dev[d].rdev;
if (test_bit(d, (void *) rs->rebuild_disks)) {
clear_bit(In_sync, &rdev->flags);
clear_bit(Faulty, &rdev->flags);
mddev->recovery_cp = rdev->recovery_offset = 0;
/* Bitmap has to be created when we do an "up" takeover */
set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
}
rdev->new_data_offset = new_data_offset;
}
return 0;
}
/* Prepare @rs for reshape */
static int rs_prepare_reshape(struct raid_set *rs)
{
bool reshape;
struct mddev *mddev = &rs->md;
if (rs_is_raid10(rs)) {
if (rs->raid_disks != mddev->raid_disks &&
__is_raid10_near(mddev->layout) &&
rs->raid10_copies &&
rs->raid10_copies != __raid10_near_copies(mddev->layout)) {
/*
* raid disk have to be multiple of data copies to allow this conversion,
*
* This is actually not a reshape it is a
* rebuild of any additional mirrors per group
*/
if (rs->raid_disks % rs->raid10_copies) {
rs->ti->error = "Can't reshape raid10 mirror groups";
return -EINVAL;
}
/* Userpace reordered disks to add/remove mirrors -> adjust raid_disk indexes */
__reorder_raid_disk_indexes(rs);
mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_NEAR,
rs->raid10_copies);
mddev->new_layout = mddev->layout;
reshape = false;
} else
reshape = true;
} else if (rs_is_raid456(rs))
reshape = true;
else if (rs_is_raid1(rs)) {
if (rs->delta_disks) {
/* Process raid1 via delta_disks */
mddev->degraded = rs->delta_disks < 0 ? -rs->delta_disks : rs->delta_disks;
reshape = true;
} else {
/* Process raid1 without delta_disks */
mddev->raid_disks = rs->raid_disks;
reshape = false;
}
} else {
rs->ti->error = "Called with bogus raid type";
return -EINVAL;
}
if (reshape) {
set_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags);
set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
} else if (mddev->raid_disks < rs->raid_disks)
/* Create new superblocks and bitmaps, if any new disks */
set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
return 0;
}
/*
*
* - change raid layout
* - change chunk size
* - add disks
* - remove disks
*/
static int rs_setup_reshape(struct raid_set *rs)
{
int r = 0;
unsigned int cur_raid_devs, d;
struct mddev *mddev = &rs->md;
struct md_rdev *rdev;
mddev->delta_disks = rs->delta_disks;
cur_raid_devs = mddev->raid_disks;
/* Ignore impossible layout change whilst adding/removing disks */
if (mddev->delta_disks &&
mddev->layout != mddev->new_layout) {
DMINFO("Ignoring invalid layout change with delta_disks=%d", rs->delta_disks);
mddev->new_layout = mddev->layout;
}
/*
* Adjust array size:
*
* - in case of adding disks, array size has
* to grow after the disk adding reshape,
* which'll hapen in the event handler;
* reshape will happen forward, so space has to
* be available at the beginning of each disk
*
* - in case of removing disks, array size
* has to shrink before starting the reshape,
* which'll happen here;
* reshape will happen backward, so space has to
* be available at the end of each disk
*
* - data_offset and new_data_offset are
* adjusted for aforementioned out of place
* reshaping based on userspace passing in
* the "data_offset <sectors>" key/value
* pair via the constructor
*/
/* Add disk(s) */
if (rs->delta_disks > 0) {
/* Prepare disks for check in raid4/5/6/10 {check|start}_reshape */
for (d = cur_raid_devs; d < rs->raid_disks; d++) {
rdev = &rs->dev[d].rdev;
clear_bit(In_sync, &rdev->flags);
/*
* save_raid_disk needs to be -1, or recovery_offset will be set to 0
* by md, which'll store that erroneously in the superblock on reshape
*/
rdev->saved_raid_disk = -1;
rdev->raid_disk = d;
rdev->sectors = mddev->dev_sectors;
rdev->recovery_offset = rs_is_raid1(rs) ? 0 : MaxSector;
}
mddev->reshape_backwards = 0; /* adding disks -> forward reshape */
/* Remove disk(s) */
} else if (rs->delta_disks < 0) {
r = rs_set_dev_and_array_sectors(rs, true);
mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */
/* Change layout and/or chunk size */
} else {
/*
* Reshape layout (e.g. raid5_ls -> raid5_n) and/or chunk size:
*
* keeping number of disks and do layout change ->
*
* toggle reshape_backward depending on data_offset:
*
* - free space upfront -> reshape forward
*
* - free space at the end -> reshape backward
*
*
* This utilizes free reshape space avoiding the need
* for userspace to move (parts of) LV segments in
* case of layout/chunksize change (for disk
* adding/removing reshape space has to be at
* the proper address (see above with delta_disks):
*
* add disk(s) -> begin
* remove disk(s)-> end
*/
mddev->reshape_backwards = rs->dev[0].rdev.data_offset ? 0 : 1;
}
return r;
}
/*
* Enable/disable discard support on RAID set depending on
* RAID level and discard properties of underlying RAID members.
*/
static void configure_discard_support(struct raid_set *rs)
{
int i;
bool raid456;
struct dm_target *ti = rs->ti;
/* Assume discards not supported until after checks below. */
ti->discards_supported = false;
/* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
for (i = 0; i < rs->raid_disks; i++) {
struct request_queue *q;
if (!rs->dev[i].rdev.bdev)
continue;
q = bdev_get_queue(rs->dev[i].rdev.bdev);
if (!q || !blk_queue_discard(q))
return;
if (raid456) {
if (!q->limits.discard_zeroes_data)
return;
if (!devices_handle_discard_safely) {
DMERR("raid456 discard support disabled due to discard_zeroes_data uncertainty.");
DMERR("Set dm-raid.devices_handle_discard_safely=Y to override.");
return;
}
}
}
/* All RAID members properly support discards */
ti->discards_supported = true;
/*
* RAID1 and RAID10 personalities require bio splitting,
* RAID0/4/5/6 don't and process large discard bios properly.
*/