OpenCloudOS-Kernel/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 */

/*
 * 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

/* 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)

/* 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)

/* "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)
#define RAID6_INVALID_FLAGS	(CTR_FLAG_NOSYNC | RAID45_INVALID_FLAGS)
/* ...invalid options definitions per raid level */

struct raid_set {
	struct dm_target *ti;

	uint32_t bitmap_loaded;
	uint32_t ctr_flags;

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

	struct raid_dev dev[0];
};

/* 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",   "RAID10 (striped mirrors)",        0, 2, 10, UINT_MAX /* Varies */},
	{"raid4",    "RAID4 (dedicated parity disk)",	1, 2, 5, ALGORITHM_PARITY_0},
	{"raid5_la", "RAID5 (left asymmetric)",		1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
	{"raid5_ra", "RAID5 (right asymmetric)",	1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
	{"raid5_ls", "RAID5 (left symmetric)",		1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
	{"raid5_rs", "RAID5 (right symmetric)",		1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
	{"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}
};

/* 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"},
};

/* 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 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;
}

static char *raid10_md_layout_to_format(int layout)
{
	/*
	 * Bit 16 and 17 stand for "offset" and "use_far_sets"
	 * Refer to MD's raid10.c for details
	 */
	if ((layout & 0x10000) && (layout & 0x20000))
		return "offset";

	if ((layout & 0xFF) > 1)
		return "near";

	return "far";
}

static unsigned raid10_md_layout_to_copies(int layout)
{
	if ((layout & 0xFF) > 1)
		return layout & 0xFF;
	return (layout >> 8) & 0xFF;
}

static int raid10_format_to_md_layout(char *format, unsigned copies)
{
	unsigned n = 1, f = 1;

	if (!strcasecmp("near", format))
		n = copies;
	else
		f = copies;

	if (!strcasecmp("offset", format))
		return 0x30000 | (f << 8) | n;

	if (!strcasecmp("far", format))
		return 0x20000 | (f << 8) | n;

	return (f << 8) | n;
}

static struct raid_type *get_raid_type(const char *name)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(raid_types); i++)
		if (!strcmp(raid_types[i].name, name))
			return &raid_types[i];

	return NULL;
}

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->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)
{
	char *raid10_format = "near";
	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;

	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(rs->raid_type)) {
		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++) {
		arg = dm_shift_arg(as);
		if (!arg)
			return ti_error_einval(rs->ti, "Not enough raid parameters given");

		if (!strcasecmp(arg, "nosync")) {
			rs->md.recovery_cp = MaxSector;
			_set_flag(CTR_FLAG_NOSYNC, &rs->ctr_flags);
			continue;
		}
		if (!strcasecmp(arg, "sync")) {
			rs->md.recovery_cp = 0;
			_set_flag(CTR_FLAG_SYNC, &rs->ctr_flags);
			continue;
		}

		key = arg;
		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(rs->raid_type))
				return ti_error_einval(rs->ti, "'raid10_format' is an invalid parameter for this RAID type");
			if (strcmp("near", arg) &&
			    strcmp("far", arg) &&
			    strcmp("offset", arg))
				return ti_error_einval(rs->ti, "Invalid 'raid10_format' value given");

			raid10_format = (char *) arg;
			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(rs->raid_type))
				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(rs->raid_type))
				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_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(rs->raid_type))
				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(rs->raid_type)) {
		if (raid10_copies > rs->md.raid_disks)
			return ti_error_einval(rs->ti, "Not enough devices to satisfy specification");

		/*
		 * If the format is not "near", we only support
		 * two copies at the moment.
		 */
		if (strcmp("near", raid10_format) && (raid10_copies > 2))
			return ti_error_einval(rs->ti, "Too many copies for given RAID10 format.");

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

	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);
}

/*
 * 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 features;	/* Used to indicate possible future changes */

	__le32 num_devices;	/* Number of devices in this array. (Max 64) */
	__le32 array_position;	/* The position of this drive in the array */

	__le64 events;		/* Incremented by md when superblock updated */
	__le64 failed_devices;	/* Bit field of devices to indicate failures */

	/*
	 * 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 array
	 * synchronisation/parity calculation.
	 */
	__le64 array_resync_offset;

	/*
	 * RAID characteristics
	 */
	__le32 level;
	__le32 layout;
	__le32 stripe_sectors;

	/* Remainder of a logical block is zero-filled when writing (see super_sync()). */
} __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 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->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 mddev *mddev, struct md_rdev *rdev)
{
	int role;
	struct raid_set *rs = container_of(mddev, struct raid_set, md);
	uint64_t events_sb;
	uint64_t failed_devices;
	struct dm_raid_superblock *sb;
	uint32_t new_devs = 0;
	uint32_t rebuilds = 0;
	struct md_rdev *r;
	struct dm_raid_superblock *sb2;

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

	/*
	 * Initialise to 1 if this is a new superblock.
	 */
	mddev->events = events_sb ? : 1;

	/*
	 * Reshaping is not currently allowed
	 */
	if (le32_to_cpu(sb->level) != mddev->level) {
		DMERR("Reshaping arrays not yet supported. (RAID level change)");
		return -EINVAL;
	}
	if (le32_to_cpu(sb->layout) != mddev->layout) {
		DMERR("Reshaping arrays 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 arrays not yet supported. (stripe sectors change)");
		return -EINVAL;
	}

	/* We can only change the number of devices in RAID1 right now */
	if (!rt_is_raid1(rs->raid_type) &&
	    (le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
		DMERR("Reshaping arrays not yet supported. (device count change)");
		return -EINVAL;
	}

	if (!(_test_flags(CTR_FLAGS_ANY_SYNC, 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 array 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 array
	 *    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.
	 */
	rdev_for_each(r, mddev) {
		if (!test_bit(In_sync, &r->flags)) {
			DMINFO("Device %d specified for rebuild: "
			       "Clearing superblock", r->raid_disk);
			rebuilds++;
		} else if (test_bit(FirstUse, &r->flags))
			new_devs++;
	}

	if (!rebuilds) {
		if (new_devs == mddev->raid_disks) {
			DMINFO("Superblocks created for new array");
			set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
		} else if (new_devs) {
			DMERR("New device injected "
			      "into existing array without 'rebuild' "
			      "parameter specified");
			return -EINVAL;
		}
	} else if (new_devs) {
		DMERR("'rebuild' devices cannot be "
		      "injected into an array with other first-time devices");
		return -EINVAL;
	} else if (mddev->recovery_cp != MaxSector) {
		DMERR("'rebuild' specified while array is not in-sync");
		return -EINVAL;
	}

	/*
	 * Now we set the Faulty bit for those devices that are
	 * recorded in the superblock as failed.
	 */
	rdev_for_each(r, mddev) {
		if (!r->sb_page)
			continue;
		sb2 = page_address(r->sb_page);
		sb2->failed_devices = 0;

		/*
		 * 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 != r->raid_disk) {
				if (!rt_is_raid1(rs->raid_type))
					return ti_error_einval(rs->ti, "Cannot change device "
								       "positions in RAID array");
				DMINFO("RAID1 device #%d now at position #%d",
				       role, r->raid_disk);
			}

			/*
			 * Partial recovery is performed on
			 * returning failed devices.
			 */
			if (failed_devices & (1 << role))
				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 = 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(mddev, rdev))
		return -EINVAL;

	if (le32_to_cpu(sb->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_bit(FirstUse, &rdev->flags)) {
		rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset);
		if (rdev->recovery_offset != MaxSector)
			clear_bit(In_sync, &rdev->flags);
	}

	/*
	 * If a device comes back, set it as not In_sync and no longer faulty.
	 */
	if (test_bit(Faulty, &rdev->flags)) {
		clear_bit(Faulty, &rdev->flags);
		clear_bit(In_sync, &rdev->flags);
		rdev->saved_raid_disk = rdev->raid_disk;
		rdev->recovery_offset = 0;
	}

	clear_bit(FirstUse, &rdev->flags);

	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");