dm raid: add new reshaping/raid10 format table line options to parameter parser

[cascardo/linux.git] / drivers / md / dm-raid.c

/*
 * 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 */

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;
};

/*
 * Flags for rs->ctr_flags field.
 *
 * 1 = no flag value
 * 2 = flag with value
 */
#define CTR_FLAG_SYNC              0x1   /* 1 */ /* Not with raid0! */
#define CTR_FLAG_NOSYNC            0x2   /* 1 */ /* Not with raid0! */
#define CTR_FLAG_REBUILD           0x4   /* 2 */ /* Not with raid0! */
#define CTR_FLAG_DAEMON_SLEEP      0x8   /* 2 */ /* Not with raid0! */
#define CTR_FLAG_MIN_RECOVERY_RATE 0x10  /* 2 */ /* Not with raid0! */
#define CTR_FLAG_MAX_RECOVERY_RATE 0x20  /* 2 */ /* Not with raid0! */
#define CTR_FLAG_MAX_WRITE_BEHIND  0x40  /* 2 */ /* Only with raid1! */
#define CTR_FLAG_WRITE_MOSTLY      0x80  /* 2 */ /* Only with raid1! */
#define CTR_FLAG_STRIPE_CACHE      0x100 /* 2 */ /* Only with raid4/5/6! */
#define CTR_FLAG_REGION_SIZE       0x200 /* 2 */ /* Not with raid0! */
#define CTR_FLAG_RAID10_COPIES     0x400 /* 2 */ /* Only with raid10 */
#define CTR_FLAG_RAID10_FORMAT     0x800 /* 2 */ /* Only with raid10 */
/* New for v1.8.0 */
#define CTR_FLAG_DELTA_DISKS          0x1000 /* 2 */ /* Only with reshapable raid4/5/6/10! */
#define CTR_FLAG_DATA_OFFSET          0x2000 /* 2 */ /* Only with reshapable raid4/5/6/10! */
#define CTR_FLAG_RAID10_USE_NEAR_SETS 0x4000 /* 2 */ /* Only with raid10! */

/*
 * 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)

/* All ctr optional arguments */
#define ALL_CTR_FLAGS           (CTR_FLAG_OPTIONS_NO_ARGS | \
                                 CTR_FLAG_OPTIONS_ONE_ARG)

/* Invalid options definitions per raid level... */

/* "raid0" does not accept any options */
#define RAID0_INVALID_FLAGS ALL_CTR_FLAGS

/* "raid1" does not accept stripe cache or any raid10 options */
#define RAID1_INVALID_FLAGS     (CTR_FLAG_STRIPE_CACHE | \
                                 CTR_FLAG_RAID10_COPIES | \
                                 CTR_FLAG_RAID10_FORMAT | \
                                 CTR_FLAG_DELTA_DISKS | \
                                 CTR_FLAG_DATA_OFFSET)

/* "raid10" does not accept any raid1 or stripe cache options */
#define RAID10_INVALID_FLAGS    (CTR_FLAG_WRITE_MOSTLY | \
                                 CTR_FLAG_MAX_WRITE_BEHIND | \
                                 CTR_FLAG_STRIPE_CACHE)
/*
 * "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_INVALID_FLAGS    (CTR_FLAG_WRITE_MOSTLY | \
                                 CTR_FLAG_MAX_WRITE_BEHIND | \
                                 CTR_FLAG_RAID10_FORMAT | \
                                 CTR_FLAG_RAID10_COPIES | \
                                 CTR_FLAG_RAID10_USE_NEAR_SETS)
#define RAID6_INVALID_FLAGS     (CTR_FLAG_NOSYNC | RAID45_INVALID_FLAGS)
/* ...invalid options definitions per raid level */

/* Array elements of 64 bit needed for rebuild/write_mostly bits */
#define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)

struct raid_set {
        struct dm_target *ti;

        uint32_t bitmap_loaded;
        uint32_t ctr_flags;

        int raid_disks;
        int delta_disks;
        int data_offset;
        int raid10_copies;

        struct mddev md;
        struct raid_type *raid_type;
        struct dm_target_callbacks callbacks;

        struct raid_dev dev[0];
};

/* 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 parity_devs;     /* # of parity devices. */
        const unsigned minimal_devs;    /* minimal # of devices in set. */
        const unsigned level;           /* RAID level. */
        const unsigned 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 _in_range(long v, long min, long max)
{
        return v >= min && v <= max;
}

/* ctr flag bit manipulation... */
/* Set single @flag in @flags */
static void _set_flag(uint32_t flag, uint32_t *flags)
{
        WARN_ON_ONCE(hweight32(flag) != 1);
        *flags |= flag;
}

/* Test single @flag in @flags */
static bool _test_flag(uint32_t flag, uint32_t flags)
{
        WARN_ON_ONCE(hweight32(flag) != 1);
        return (flag & flags) ? true : false;
}

/* Test multiple @flags in @all_flags */
static bool _test_flags(uint32_t flags, uint32_t all_flags)
{
        return (flags & all_flags) ? true : false;
}

/* Return true if single @flag is set in @*flags, else set it and return false */
static bool _test_and_set_flag(uint32_t flag, uint32_t *flags)
{
        if (_test_flag(flag, *flags))
                return true;

        _set_flag(flag, flags);
        return false;
}
/* ...ctr and runtime flag bit manipulation */

/* All table line arguments are defined here */
static struct arg_name_flag {
        const uint32_t 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, "writemostly"},
        { 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 *_argname_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 (_test_flag(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,
 * is. 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 raid10 */
static bool rs_is_raid10(struct raid_set *rs)
{
        return rs->md.level == 10;
}

/*
 * bool helpers to test for various raid levels of a raid type
 */

/* 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 _in_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 _in_range(rt->level, 4, 6);
}
/* END: raid level bools */

/*
 * Convenience functions to set ti->error to @errmsg and
 * return @r in order to shorten code in a lot of places
 */
static int ti_error_ret(struct dm_target *ti, const char *errmsg, int r)
{
        ti->error = (char *) errmsg;
        return r;
}

static int ti_error_einval(struct dm_target *ti, const char *errmsg)
{
        return ti_error_ret(ti, errmsg, -EINVAL);
}
/* END: convenience functions to set ti->error to @errmsg... */

/* Return invalid ctr flags for the raid level of @rs */
static uint32_t _invalid_flags(struct raid_set *rs)
{
        if (rt_is_raid0(rs->raid_type))
                return RAID0_INVALID_FLAGS;
        else if (rt_is_raid1(rs->raid_type))
                return RAID1_INVALID_FLAGS;
        else if (rt_is_raid10(rs->raid_type))
                return RAID10_INVALID_FLAGS;
        else if (rt_is_raid45(rs->raid_type))
                return RAID45_INVALID_FLAGS;
        else if (rt_is_raid6(rs->raid_type))
                return RAID6_INVALID_FLAGS;

        return ~0;
}

/*
 * Check for any invalid flags set on @rs defined by bitset @invalid_flags
 *
 * Has to be called after parsing of the ctr flags!
 */
static int rs_check_for_invalid_flags(struct raid_set *rs)
{
        if (_test_flags(rs->ctr_flags, _invalid_flags(rs)))
                return ti_error_einval(rs->ti, "Invalid flag combined");

        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 unsigned int _is_raid10_offset(int layout)
{
        return layout & RAID10_OFFSET;
}

/* Return true if md raid10 near for @layout */
static unsigned int _is_raid10_near(int layout)
{
        return !_is_raid10_offset(layout) && _raid10_near_copies(layout) > 1;
}

/* Return true if md raid10 far for @layout */
static unsigned int _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 const 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 _raid10_near_copies(layout) > 1 ?
               _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_flag(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_flag(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 int _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 0;
}

/* 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;
}

/*
 * 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->delta_disks = 0;
}


static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs)
{
        unsigned i;
        struct raid_set *rs;

        if (raid_devs <= raid_type->parity_devs)
                return ERR_PTR(ti_error_einval(ti, "Insufficient number of devices"));

        rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL);
        if (!rs)
                return ERR_PTR(ti_error_ret(ti, "Cannot allocate raid context", -ENOMEM));

        mddev_init(&rs->md);

        rs->raid_disks = raid_devs;
        rs->delta_disks = 0;

        rs->ti = ti;
        rs->raid_type = raid_type;
        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 = 0;

        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 context_free(struct raid_set *rs)
{
        int i;

        for (i = 0; i < rs->md.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 context_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->md.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)
                                return ti_error_ret(rs->ti, "RAID metadata device lookup failure", r);

                        rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL);
                        if (!rs->dev[i].rdev.sb_page)
                                return ti_error_ret(rs->ti, "Failed to allocate superblock page", -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))
                                return ti_error_einval(rs->ti, "Drive designated for rebuild not specified");

                        if (rs->dev[i].meta_dev)
                                return ti_error_einval(rs->ti, "No data device supplied with metadata device");

                        continue;
                }

                r = dm_get_device(rs->ti, arg,
                                    dm_table_get_mode(rs->ti->table),
                                    &rs->dev[i].data_dev);
                if (r)
                        return ti_error_ret(rs->ti, "RAID device lookup failure", 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(&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.
                 */
                DMERR("Unable to rebuild drive while array is not in-sync");
                return ti_error_einval(rs->ti, "Unable to rebuild drive while array is not in-sync");
        }

        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)
                        return ti_error_einval(rs->ti, "Supplied region size is too large");

                if (region_size < min_region_size) {
                        DMERR("Supplied region_size (%lu sectors) below minimum (%lu)",
                              region_size, min_region_size);
                        return ti_error_einval(rs->ti, "Supplied region size is too small");
                }

                if (!is_power_of_2(region_size))
                        return ti_error_einval(rs->ti, "Region size is not a power of 2");

                if (region_size < rs->md.chunk_sectors)
                        return ti_error_einval(rs->ti, "Region size is smaller than the chunk size");
        }

        /*
         * Convert sectors to bytes.
         */
        rs->md.bitmap_info.chunksize = (region_size << 9);

        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 i, rebuild_cnt = 0;
        unsigned rebuilds_per_group = 0, copies, d;
        unsigned 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.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 (!strcmp("near", raid10_md_layout_to_format(rs->md.layout))) {
                        for (i = 0; i < rs->md.raid_disks * copies; i++) {
                                if (!(i % copies))
                                        rebuilds_per_group = 0;
                                d = i % rs->md.raid_disks;
                                if ((!rs->dev[d].rdev.sb_page ||
                                     !test_bit(In_sync, &rs->dev[d].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 num_raid_params)
{
        int raid10_format = ALGORITHM_RAID10_DEFAULT;
        unsigned raid10_copies = 2;
        unsigned i;
        unsigned value, region_size = 0;
        sector_t sectors_per_dev = rs->ti->len;
        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 (kstrtouint(arg, 10, &value) < 0)
                return ti_error_einval(rs->ti, "Bad numerical argument given for chunk_size");

        /*
         * 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))
                return ti_error_einval(rs->ti, "Chunk size must be a power of 2");
        else if (value < 8)
                return ti_error_einval(rs->ti, "Chunk size value is too small");

        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->md.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)
                        return ti_error_einval(rs->ti, "Not enough raid parameters given");

                if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_NOSYNC))) {
                        if (_test_and_set_flag(CTR_FLAG_NOSYNC, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one 'nosync' argument allowed");
                        rs->md.recovery_cp = MaxSector;
                        continue;
                }
                if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_SYNC))) {
                        if (_test_and_set_flag(CTR_FLAG_SYNC, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one 'sync' argument allowed");
                        rs->md.recovery_cp = 0;
                        continue;
                }
                if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_RAID10_USE_NEAR_SETS))) {
                        if (_test_and_set_flag(CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one 'raid10_use_new_sets' argument allowed");
                        continue;
                }

                arg = dm_shift_arg(as);
                i++; /* Account for the argument pairs */
                if (!arg)
                        return ti_error_einval(rs->ti, "Wrong number of raid parameters given");

                /*
                 * Parameters that take a string value are checked here.
                 */

                if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_RAID10_FORMAT))) {
                        if (_test_and_set_flag(CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one 'raid10_format' argument pair allowed");
                        if (!rt_is_raid10(rt))
                                return ti_error_einval(rs->ti, "'raid10_format' is an invalid parameter for this RAID type");
                        raid10_format = raid10_name_to_format(arg);
                        if (raid10_format < 0)
                                return ti_error_ret(rs->ti, "Invalid 'raid10_format' value given", raid10_format);
                        continue;
                }

                if (kstrtouint(arg, 10, &value) < 0)
                        return ti_error_einval(rs->ti, "Bad numerical argument given in raid params");

                if (!strcasecmp(key, _argname_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 (!_in_range(value, 0, rs->md.raid_disks - 1))
                                return ti_error_einval(rs->ti, "Invalid rebuild index given");

                        rd = rs->dev + value;
                        clear_bit(In_sync, &rd->rdev.flags);
                        clear_bit(Faulty, &rd->rdev.flags);
                        rd->rdev.recovery_offset = 0;
                        _set_flag(CTR_FLAG_REBUILD, &rs->ctr_flags);
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_WRITE_MOSTLY))) {
                        if (!rt_is_raid1(rt))
                                return ti_error_einval(rs->ti, "write_mostly option is only valid for RAID1");

                        if (!_in_range(value, 0, rs->md.raid_disks - 1))
                                return ti_error_einval(rs->ti, "Invalid write_mostly index given");

                        set_bit(WriteMostly, &rs->dev[value].rdev.flags);
                        _set_flag(CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags);
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_MAX_WRITE_BEHIND))) {
                        if (!rt_is_raid1(rt))
                                return ti_error_einval(rs->ti, "max_write_behind option is only valid for RAID1");

                        if (_test_and_set_flag(CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one max_write_behind argument pair allowed");

                        /*
                         * In device-mapper, we specify things in sectors, but
                         * MD records this value in kB
                         */
                        value /= 2;
                        if (value > COUNTER_MAX)
                                return ti_error_einval(rs->ti, "Max write-behind limit out of range");

                        rs->md.bitmap_info.max_write_behind = value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_DAEMON_SLEEP))) {
                        if (_test_and_set_flag(CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one daemon_sleep argument pair allowed");
                        if (!value || (value > MAX_SCHEDULE_TIMEOUT))
                                return ti_error_einval(rs->ti, "daemon sleep period out of range");
                        rs->md.bitmap_info.daemon_sleep = value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_DATA_OFFSET))) {
                        /* Userspace passes new data_offset after having extended the the data image LV */
                        if (_test_and_set_flag(CTR_FLAG_DATA_OFFSET, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one data_offset argument pair allowed");

                        /* Ensure sensible data offset */
                        if (value < 0)
                                return ti_error_einval(rs->ti, "Bogus data_offset value");

                        rs->data_offset = value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_DELTA_DISKS))) {
                        /* Define the +/-# of disks to add to/remove from the given raid set */
                        if (_test_and_set_flag(CTR_FLAG_DELTA_DISKS, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one delta_disks argument pair allowed");

                        /* Ensure MAX_RAID_DEVICES and raid type minimal_devs! */
                        if (!_in_range(abs(value), 1, MAX_RAID_DEVICES - rt->minimal_devs))
                                return ti_error_einval(rs->ti, "Too many delta_disk requested");

                        rs->delta_disks = value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_STRIPE_CACHE))) {
                        if (_test_and_set_flag(CTR_FLAG_STRIPE_CACHE, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one stripe_cache argument pair allowed");
                        /*
                         * In device-mapper, we specify things in sectors, but
                         * MD records this value in kB
                         */
                        value /= 2;

                        if (!rt_is_raid456(rt))
                                return ti_error_einval(rs->ti, "Inappropriate argument: stripe_cache");
                        if (raid5_set_cache_size(&rs->md, (int)value))
                                return ti_error_einval(rs->ti, "Bad stripe_cache size");

                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_MIN_RECOVERY_RATE))) {
                        if (_test_and_set_flag(CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one min_recovery_rate argument pair allowed");
                        if (value > INT_MAX)
                                return ti_error_einval(rs->ti, "min_recovery_rate out of range");
                        rs->md.sync_speed_min = (int)value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_MAX_RECOVERY_RATE))) {
                        if (_test_and_set_flag(CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one max_recovery_rate argument pair allowed");
                        if (value > INT_MAX)
                                return ti_error_einval(rs->ti, "max_recovery_rate out of range");
                        rs->md.sync_speed_max = (int)value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_REGION_SIZE))) {
                        if (_test_and_set_flag(CTR_FLAG_REGION_SIZE, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one region_size argument pair allowed");

                        region_size = value;
                } else if (!strcasecmp(key, _argname_by_flag(CTR_FLAG_RAID10_COPIES))) {
                        if (_test_and_set_flag(CTR_FLAG_RAID10_COPIES, &rs->ctr_flags))
                                return ti_error_einval(rs->ti, "Only one raid10_copies argument pair allowed");

                        if (!_in_range(value, 2, rs->md.raid_disks))
                                return ti_error_einval(rs->ti, "Bad value for 'raid10_copies'");

                        raid10_copies = value;
                } else {
                        DMERR("Unable to parse RAID parameter: %s", key);
                        return ti_error_einval(rs->ti, "Unable to parse RAID parameters");
                }
        }

        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)
                        return ti_error_einval(rs->ti, "Not enough devices to satisfy specification");

                rs->md.new_layout = raid10_format_to_md_layout(rs, raid10_format, raid10_copies);
                if (rs->md.new_layout < 0)
                        return ti_error_ret(rs->ti, "Error getting raid10 format", rs->md.new_layout);

                rt = get_raid_type_by_ll(10, rs->md.new_layout);
                if (!rt)
                        return ti_error_einval(rs->ti, "Failed to recognize new raid10 layout");

                if ((rt->algorithm == ALGORITHM_RAID10_DEFAULT ||
                     rt->algorithm == ALGORITHM_RAID10_NEAR) &&
                    _test_flag(CTR_FLAG_RAID10_USE_NEAR_SETS, rs->ctr_flags))
                        return ti_error_einval(rs->ti, "RAID10 format 'near' and 'raid10_use_near_sets' are incompatible");

                /* (Len * #mirrors) / #devices */
                sectors_per_dev = rs->ti->len * raid10_copies;
                sector_div(sectors_per_dev, rs->md.raid_disks);

                rs->md.layout = raid10_format_to_md_layout(rs, raid10_format, raid10_copies);
                rs->md.new_layout = rs->md.layout;
        } else if (!rt_is_raid1(rt) &&
                   sector_div(sectors_per_dev,
                              (rs->md.raid_disks - rt->parity_devs)))
                return ti_error_einval(rs->ti, "Target length not divisible by number of data devices");

        rs->raid10_copies = raid10_copies;
        rs->md.dev_sectors = sectors_per_dev;

        /* 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_invalid_flags(rs);
}

static void do_table_event(struct work_struct *ws)
{
        struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);

        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);
}

/*  Features */
#define FEATURE_FLAG_SUPPORTS_RESHAPE   0x1

/* 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 1.8.0 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 1.8.0 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 V1.8.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!!
         *
         * FEATURE_FLAG_SUPPORTS_RESHAPE 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 1.8.0 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;

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, 1)) {
                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 (_test_flag(FEATURE_FLAG_SUPPORTS_RESHAPE, le32_to_cpu(sb->compat_features))) {
                int i = ARRAY_SIZE(sb->extended_failed_devices);

                while (i--)
                        failed_devices[i+1] = le64_to_cpu(sb->extended_failed_devices[i]);
        }
}

static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
{
        int i;
        uint64_t failed_devices;
        struct dm_raid_superblock *sb;
        struct raid_set *rs = container_of(mddev, struct raid_set, md);

        sb = page_address(rdev->sb_page);
        failed_devices = le64_to_cpu(sb->failed_devices);

        for (i = 0; i < mddev->raid_disks; i++)
                if (!rs->dev[i].data_dev ||
                    test_bit(Faulty, &(rs->dev[i].rdev.flags)))
                        failed_devices |= (1ULL << i);

        memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));

        sb->magic = cpu_to_le32(DM_RAID_MAGIC);
        sb->compat_features = cpu_to_le32(0);   /* No features yet */

        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->failed_devices = cpu_to_le64(failed_devices);

        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);
}

/*
 * 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);

                /* 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 (_test_flag(FEATURE_FLAG_SUPPORTS_RESHAPE, le32_to_cpu(sb->compat_features))) {
                /* 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 (_test_flag(SB_FLAG_RESHAPE_ACTIVE, le32_to_cpu(sb->flags))) {
                        if (_test_flag(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 && _test_flag(SB_FLAG_RESHAPE_BACKWARDS, le32_to_cpu(sb->flags))))
                                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 {
                /*
                 * Reshaping is not allowed, because we don't have the appropriate 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_flag(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.
         */
        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);
                        mddev->recovery_cp = 0;
                } else if (new_devs && new_devs != rs->raid_disks && !rebuilds) {
                        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 (mddev->recovery_cp != MaxSector) {
                        DMERR("'rebuild' specified while raid set is not in-sync (recovery_cp=%llu)",
                              (unsigned long long) mddev->recovery_cp);
                        return -EINVAL;
                } else if (mddev->reshape_position != MaxSector) {
                        DMERR("'rebuild' specified while raid set is being reshaped");
                        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)
                                                return ti_error_einval(rs->ti, "Cannot change raid10 near "
                                                                               "set to odd # of devices!");

                                        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))
                                        return ti_error_einval(rs->ti, "Cannot change device positions in raid set");

                                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 (!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 (sb->compat_features || sb->incompat_features) {
                rs->ti->error = "Unable to assemble array: No 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->md.reshape_position == MaxSector)
                        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.
                 */
                rdev->sectors = to_sector(i_size_read(rdev->bdev->bd_inode));

                if (_test_flag(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))
                return ti_error_einval(rs->ti, "Insufficient redundancy to activate array");

        /*
         * Validation of the freshest device provides the source of
         * validation for the remaining devices.
         */
        if (super_validate(rs, freshest))
                return ti_error_einval(rs->ti, "Unable to assemble array: Invalid superblocks");

        rdev_for_each(rdev, mddev)
                if ((rdev != freshest) && super_validate(rs, rdev))
                        return -EINVAL;

        return 0;
}

/*
 * Enable/disable discard support on RAID set depending on
 * RAID level and discard properties of underlying RAID members.
 */
static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
{
        int i;
        bool raid456;

        /* 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->md.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.
         */
        ti->split_discard_bios = !!(rs->md.level == 1 || rs->md.level == 10);
        ti->num_discard_bios = 1;
}

/*
 * Construct a RAID0/1/10/4/5/6 mapping:
 * Args:
 *      <raid_type> <#raid_params> <raid_params>{0,}    \
 *      <#raid_devs> [<meta_dev1> <dev1>]{1,}
 *
 * <raid_params> varies by <raid_type>.  See 'parse_raid_params' for
 * details on possible <raid_params>.
 *
 * Userspace is free to initialize the metadata devices, hence the superblocks to
 * enforce recreation based on the passed in table parameters.
 *
 */
static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
        int r;
        struct raid_type *rt;
        unsigned num_raid_params, num_raid_devs;
        struct raid_set *rs = NULL;
        const char *arg;
        struct dm_arg_set as = { argc, argv }, as_nrd;
        struct dm_arg _args[] = {
                { 0, as.argc, "Cannot understand number of raid parameters" },
                { 1, 254, "Cannot understand number of raid devices parameters" }
        };

        /* Must have <raid_type> */
        arg = dm_shift_arg(&as);
        if (!arg)
                return ti_error_einval(rs->ti, "No arguments");

        rt = get_raid_type(arg);
        if (!rt)
                return ti_error_einval(rs->ti, "Unrecognised raid_type");

        /* Must have <#raid_params> */
        if (dm_read_arg_group(_args, &as, &num_raid_params, &ti->error))
                return -EINVAL;

        /* number of raid device tupples <meta_dev data_dev> */
        as_nrd = as;
        dm_consume_args(&as_nrd, num_raid_params);
        _args[1].max = (as_nrd.argc - 1) / 2;
        if (dm_read_arg(_args + 1, &as_nrd, &num_raid_devs, &ti->error))
                return -EINVAL;

        if (!_in_range(num_raid_devs, 1, MAX_RAID_DEVICES))
                return ti_error_einval(rs->ti, "Invalid number of supplied raid devices");

        rs = context_alloc(ti, rt, num_raid_devs);
        if (IS_ERR(rs))
                return PTR_ERR(rs);

        r = parse_raid_params(rs, &as, num_raid_params);
        if (r)
                goto bad;

        r = parse_dev_params(rs, &as);
        if (r)
                goto bad;

        rs->md.sync_super = super_sync;
        r = analyse_superblocks(ti, rs);
        if (r)
                goto bad;

        INIT_WORK(&rs->md.event_work, do_table_event);
        ti->private = rs;
        ti->num_flush_bios = 1;

        /*
         * Disable/enable discard support on RAID set.
         */
        configure_discard_support(ti, rs);

        /* Has to be held on running the array */
        mddev_lock_nointr(&rs->md);
        r = md_run(&rs->md);
        rs->md.in_sync = 0; /* Assume already marked dirty */
        mddev_unlock(&rs->md);

        if (r) {
                ti->error = "Fail to run raid array";
                goto bad;
        }

        if (ti->len != rs->md.array_sectors) {
                r = ti_error_einval(ti, "Array size does not match requested target length");
                goto size_mismatch;
        }
        rs->callbacks.congested_fn = raid_is_congested;
        dm_table_add_target_callbacks(ti->table, &rs->callbacks);

        mddev_suspend(&rs->md);
        return 0;

size_mismatch:
        md_stop(&rs->md);
bad:
        context_free(rs);

        return r;
}

static void raid_dtr(struct dm_target *ti)
{
        struct raid_set *rs = ti->private;

        list_del_init(&rs->callbacks.list);
        md_stop(&rs->md);
        context_free(rs);
}

static int raid_map(struct dm_target *ti, struct bio *bio)
{
        struct raid_set *rs = ti->private;
        struct mddev *mddev = &rs->md;

        mddev->pers->make_request(mddev, bio);

        return DM_MAPIO_SUBMITTED;
}

static const char *decipher_sync_action(struct mddev *mddev)
{
        if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
                return "frozen";

        if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
            (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
                if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
                        return "reshape";

                if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
                        if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
                                return "resync";
                        else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
                                return "check";
                        return "repair";
                }

                if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
                        return "recover";
        }

        return "idle";
}

static void raid_status(struct dm_target *ti, status_type_t type,
                        unsigned status_flags, char *result, unsigned maxlen)
{
        struct raid_set *rs = ti->private;
        unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
        unsigned sz = 0;
        int i, array_in_sync = 0;
        sector_t sync;

        switch (type) {
        case STATUSTYPE_INFO:
                DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks);

                if (!rt_is_raid0(rs->raid_type)) {
                        if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
                                sync = rs->md.curr_resync_completed;
                        else
                                sync = rs->md.recovery_cp;

                        if (sync >= rs->md.resync_max_sectors) {
                                /*
                                 * Sync complete.
                                 */
                                array_in_sync = 1;
                                sync = rs->md.resync_max_sectors;
                        } else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
                                /*
                                 * If "check" or "repair" is occurring, the array has
                                 * undergone and initial sync and the health characters
                                 * should not be 'a' anymore.
                                 */
                                array_in_sync = 1;
                        } else {
                                /*
                                 * The array may be doing an initial sync, or it may
                                 * be rebuilding individual components.  If all the
                                 * devices are In_sync, then it is the array that is
                                 * being initialized.
                                 */
                                for (i = 0; i < rs->md.raid_disks; i++)
                                        if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
                                                array_in_sync = 1;
                        }
                } else {
                        /* RAID0 */
                        array_in_sync = 1;
                        sync = rs->md.resync_max_sectors;
                }

                /*
                 * Status characters:
                 *  'D' = Dead/Failed device
                 *  'a' = Alive but not in-sync
                 *  'A' = Alive and in-sync
                 */
                for (i = 0; i < rs->md.raid_disks; i++) {
                        if (test_bit(Faulty, &rs->dev[i].rdev.flags))
                                DMEMIT("D");
                        else if (!array_in_sync ||
                                 !test_bit(In_sync, &rs->dev[i].rdev.flags))
                                DMEMIT("a");
                        else
                                DMEMIT("A");
                }

                /*
                 * In-sync ratio:
                 *  The in-sync ratio shows the progress of:
                 *   - Initializing the array
                 *   - Rebuilding a subset of devices of the array
                 *  The user can distinguish between the two by referring
                 *  to the status characters.
                 */
                DMEMIT(" %llu/%llu",
                       (unsigned long long) sync,
                       (unsigned long long) rs->md.resync_max_sectors);

                /*
                 * Sync action:
                 *   See Documentation/device-mapper/dm-raid.c for
                 *   information on each of these states.
                 */
                DMEMIT(" %s", decipher_sync_action(&rs->md));

                /*
                 * resync_mismatches/mismatch_cnt
                 *   This field shows the number of discrepancies found when
                 *   performing a "check" of the array.
                 */
                DMEMIT(" %llu",
                       (strcmp(rs->md.last_sync_action, "check")) ? 0 :
                       (unsigned long long)
                       atomic64_read(&rs->md.resync_mismatches));
                break;
        case STATUSTYPE_TABLE:
                /* The string you would use to construct this array */
                for (i = 0; i < rs->md.raid_disks; i++) {
                        if (_test_flag(CTR_FLAG_REBUILD, rs->ctr_flags) &&
                            rs->dev[i].data_dev &&
                            !test_bit(In_sync, &rs->dev[i].rdev.flags))
                                raid_param_cnt += 2; /* for rebuilds */
                        if (rs->dev[i].data_dev &&
                            test_bit(WriteMostly, &rs->dev[i].rdev.flags))
                                raid_param_cnt += 2;
                }

                raid_param_cnt += (hweight32(rs->ctr_flags & ~CTR_FLAG_REBUILD) * 2);
                if (rs->ctr_flags & (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC))
                        raid_param_cnt--;

                DMEMIT("%s %u %u", rs->raid_type->name,
                       raid_param_cnt, rs->md.chunk_sectors);

                if (_test_flag(CTR_FLAG_SYNC, rs->ctr_flags) &&
                    rs->md.recovery_cp == MaxSector)
                        DMEMIT(" sync");
                if (_test_flag(CTR_FLAG_NOSYNC, rs->ctr_flags))
                        DMEMIT(" nosync");

                for (i = 0; i < rs->md.raid_disks; i++)
                        if (_test_flag(CTR_FLAG_REBUILD, rs->ctr_flags) &&
                            rs->dev[i].data_dev &&
                            !test_bit(In_sync, &rs->dev[i].rdev.flags))
                                DMEMIT(" rebuild %u", i);

                if (_test_flag(CTR_FLAG_DAEMON_SLEEP, rs->ctr_flags))
                        DMEMIT(" daemon_sleep %lu",
                               rs->md.bitmap_info.daemon_sleep);

                if (_test_flag(CTR_FLAG_MIN_RECOVERY_RATE, rs->ctr_flags))
                        DMEMIT(" min_recovery_rate %d", rs->md.sync_speed_min);

                if (_test_flag(CTR_FLAG_MAX_RECOVERY_RATE, rs->ctr_flags))
                        DMEMIT(" max_recovery_rate %d", rs->md.sync_speed_max);

                for (i = 0; i < rs->md.raid_disks; i++)
                        if (rs->dev[i].data_dev &&
                            test_bit(WriteMostly, &rs->dev[i].rdev.flags))
                                DMEMIT(" write_mostly %u", i);

                if (_test_flag(CTR_FLAG_MAX_WRITE_BEHIND, rs->ctr_flags))
                        DMEMIT(" max_write_behind %lu",
                               rs->md.bitmap_info.max_write_behind);

                if (_test_flag(CTR_FLAG_STRIPE_CACHE, rs->ctr_flags)) {
                        struct r5conf *conf = rs->md.private;

                        /* convert from kiB to sectors */
                        DMEMIT(" stripe_cache %d",
                               conf ? conf->max_nr_stripes * 2 : 0);
                }

                if (_test_flag(CTR_FLAG_REGION_SIZE, rs->ctr_flags))
                        DMEMIT(" region_size %lu",
                               rs->md.bitmap_info.chunksize >> 9);

                if (_test_flag(CTR_FLAG_RAID10_COPIES, rs->ctr_flags))
                        DMEMIT(" raid10_copies %u",
                               raid10_md_layout_to_copies(rs->md.layout));

                if (_test_flag(CTR_FLAG_RAID10_FORMAT, rs->ctr_flags))
                        DMEMIT(" raid10_format %s",
                               raid10_md_layout_to_format(rs->md.layout));

                DMEMIT(" %d", rs->md.raid_disks);
                for (i = 0; i < rs->md.raid_disks; i++) {
                        if (rs->dev[i].meta_dev)
                                DMEMIT(" %s", rs->dev[i].meta_dev->name);
                        else
                                DMEMIT(" -");

                        if (rs->dev[i].data_dev)
                                DMEMIT(" %s", rs->dev[i].data_dev->name);
                        else
                                DMEMIT(" -");
                }
        }
}

static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
{
        struct raid_set *rs = ti->private;
        struct mddev *mddev = &rs->md;

        if (!strcasecmp(argv[0], "reshape")) {
                DMERR("Reshape not supported.");
                return -EINVAL;
        }

        if (!mddev->pers || !mddev->pers->sync_request)
                return -EINVAL;

        if (!strcasecmp(argv[0], "frozen"))
                set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
        else
                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);

        if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
                if (mddev->sync_thread) {
                        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
                        md_reap_sync_thread(mddev);
                }
        } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
                   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
                return -EBUSY;
        else if (!strcasecmp(argv[0], "resync"))
                set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
        else if (!strcasecmp(argv[0], "recover")) {
                set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
                set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
        } else {
                if (!strcasecmp(argv[0], "check"))
                        set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
                else if (!!strcasecmp(argv[0], "repair"))
                        return -EINVAL;
                set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
                set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
        }
        if (mddev->ro == 2) {
                /* A write to sync_action is enough to justify
                 * canceling read-auto mode
                 */
                mddev->ro = 0;
                if (!mddev->suspended)
                        md_wakeup_thread(mddev->sync_thread);
        }
        set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
        if (!mddev->suspended)
                md_wakeup_thread(mddev->thread);

        return 0;
}

static int raid_iterate_devices(struct dm_target *ti,
                                iterate_devices_callout_fn fn, void *data)
{
        struct raid_set *rs = ti->private;
        unsigned i;
        int r = 0;

        for (i = 0; !r && i < rs->md.raid_disks; i++)
                if (rs->dev[i].data_dev)
                        r = fn(ti,
                                 rs->dev[i].data_dev,
                                 0, /* No offset on data devs */
                                 rs->md.dev_sectors,
                                 data);

        return r;
}

static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
        struct raid_set *rs = ti->private;
        unsigned chunk_size = rs->md.chunk_sectors << 9;
        struct r5conf *conf = rs->md.private;

        blk_limits_io_min(limits, chunk_size);
        blk_limits_io_opt(limits, chunk_size * (conf->raid_disks - conf->max_degraded));
}

static void raid_presuspend(struct dm_target *ti)
{
        struct raid_set *rs = ti->private;

        md_stop_writes(&rs->md);
}

static void raid_postsuspend(struct dm_target *ti)
{
        struct raid_set *rs = ti->private;

        mddev_suspend(&rs->md);
}

static void attempt_restore_of_faulty_devices(struct raid_set *rs)
{
        int i;
        uint64_t failed_devices, cleared_failed_devices = 0;
        unsigned long flags;
        struct dm_raid_superblock *sb;
        struct md_rdev *r;

        for (i = 0; i < rs->md.raid_disks; i++) {
                r = &rs->dev[i].rdev;
                if (test_bit(Faulty, &r->flags) && r->sb_page &&
                    sync_page_io(r, 0, r->sb_size, r->sb_page, REQ_OP_READ, 0,
                                 1)) {
                        DMINFO("Faulty %s device #%d has readable super block."
                               "  Attempting to revive it.",
                               rs->raid_type->name, i);

                        /*
                         * Faulty bit may be set, but sometimes the array can
                         * be suspended before the personalities can respond
                         * by removing the device from the array (i.e. calling
                         * 'hot_remove_disk').  If they haven't yet removed
                         * the failed device, its 'raid_disk' number will be
                         * '>= 0' - meaning we must call this function
                         * ourselves.
                         */
                        if ((r->raid_disk >= 0) &&
                            (r->mddev->pers->hot_remove_disk(r->mddev, r) != 0))
                                /* Failed to revive this device, try next */
                                continue;

                        r->raid_disk = i;
                        r->saved_raid_disk = i;
                        flags = r->flags;
                        clear_bit(Faulty, &r->flags);
                        clear_bit(WriteErrorSeen, &r->flags);
                        clear_bit(In_sync, &r->flags);
                        if (r->mddev->pers->hot_add_disk(r->mddev, r)) {
                                r->raid_disk = -1;
                                r->saved_raid_disk = -1;
                                r->flags = flags;
                        } else {
                                r->recovery_offset = 0;
                                cleared_failed_devices |= 1 << i;
                        }
                }
        }
        if (cleared_failed_devices) {
                rdev_for_each(r, &rs->md) {
                        sb = page_address(r->sb_page);
                        failed_devices = le64_to_cpu(sb->failed_devices);
                        failed_devices &= ~cleared_failed_devices;
                        sb->failed_devices = cpu_to_le64(failed_devices);
                }
        }
}

static void raid_resume(struct dm_target *ti)
{
        struct raid_set *rs = ti->private;

        if (!rt_is_raid0(rs->raid_type)) {
                set_bit(MD_CHANGE_DEVS, &rs->md.flags);

                if (!rs->bitmap_loaded) {
                        bitmap_load(&rs->md);
                        rs->bitmap_loaded = 1;
                } else {
                        /*
                         * A secondary resume while the device is active.
                         * Take this opportunity to check whether any failed
                         * devices are reachable again.
                         */
                        attempt_restore_of_faulty_devices(rs);
                }

                clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
        }

        mddev_resume(&rs->md);
}

static struct target_type raid_target = {
        .name = "raid",
        .version = {1, 8, 1},
        .module = THIS_MODULE,
        .ctr = raid_ctr,
        .dtr = raid_dtr,
        .map = raid_map,
        .status = raid_status,
        .message = raid_message,
        .iterate_devices = raid_iterate_devices,
        .io_hints = raid_io_hints,
        .presuspend = raid_presuspend,
        .postsuspend = raid_postsuspend,
        .resume = raid_resume,
};

static int __init dm_raid_init(void)
{
        DMINFO("Loading target version %u.%u.%u",
               raid_target.version[0],
               raid_target.version[1],
               raid_target.version[2]);
        return dm_register_target(&raid_target);
}

static void __exit dm_raid_exit(void)
{
        dm_unregister_target(&raid_target);
}

module_init(dm_raid_init);
module_exit(dm_raid_exit);

module_param(devices_handle_discard_safely, bool, 0644);
MODULE_PARM_DESC(devices_handle_discard_safely,
                 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");

MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
MODULE_ALIAS("dm-raid1");
MODULE_ALIAS("dm-raid10");
MODULE_ALIAS("dm-raid4");
MODULE_ALIAS("dm-raid5");
MODULE_ALIAS("dm-raid6");
MODULE_AUTHOR("Neil Brown <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");