dm-raid.c 33.9 KB
Newer Older
N
NeilBrown 已提交
1 2 3 4 5 6 7 8
/*
 * Copyright (C) 2010-2011 Neil Brown
 * Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include <linux/slab.h>
9
#include <linux/module.h>
N
NeilBrown 已提交
10 11

#include "md.h"
J
Jonathan Brassow 已提交
12
#include "raid1.h"
N
NeilBrown 已提交
13 14 15
#include "raid5.h"
#include "bitmap.h"

A
Alasdair G Kergon 已提交
16 17
#include <linux/device-mapper.h>

N
NeilBrown 已提交
18 19 20
#define DM_MSG_PREFIX "raid"

/*
21 22
 * The following flags are used by dm-raid.c to set up the array state.
 * They must be cleared before md_run is called.
N
NeilBrown 已提交
23
 */
24
#define FirstUse 10             /* rdev flag */
N
NeilBrown 已提交
25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40

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;
41
	struct md_rdev rdev;
N
NeilBrown 已提交
42 43 44 45 46
};

/*
 * Flags for rs->print_flags field.
 */
47 48 49 50 51 52 53 54
#define DMPF_SYNC              0x1
#define DMPF_NOSYNC            0x2
#define DMPF_REBUILD           0x4
#define DMPF_DAEMON_SLEEP      0x8
#define DMPF_MIN_RECOVERY_RATE 0x10
#define DMPF_MAX_RECOVERY_RATE 0x20
#define DMPF_MAX_WRITE_BEHIND  0x40
#define DMPF_STRIPE_CACHE      0x80
55
#define DMPF_REGION_SIZE       0X100
N
NeilBrown 已提交
56 57 58
struct raid_set {
	struct dm_target *ti;

59 60
	uint32_t bitmap_loaded;
	uint32_t print_flags;
N
NeilBrown 已提交
61

62
	struct mddev md;
N
NeilBrown 已提交
63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
	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[] = {
J
Jonathan Brassow 已提交
78
	{"raid1",    "RAID1 (mirroring)",               0, 2, 1, 0 /* NONE */},
N
NeilBrown 已提交
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
	{"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}
};

static struct raid_type *get_raid_type(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) {
		ti->error = "Insufficient number of devices";
		return ERR_PTR(-EINVAL);
	}

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

	mddev_init(&rs->md);

	rs->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
137
	 *  rs->md.dev_sectors
N
NeilBrown 已提交
138 139 140 141 142 143 144 145 146
	 */

	return rs;
}

static void context_free(struct raid_set *rs)
{
	int i;

147 148 149
	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);
150
		md_rdev_clear(&rs->dev[i].rdev);
N
NeilBrown 已提交
151 152
		if (rs->dev[i].data_dev)
			dm_put_device(rs->ti, rs->dev[i].data_dev);
153
	}
N
NeilBrown 已提交
154 155 156 157 158 159 160 161 162

	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
 *
163 164 165 166 167 168 169 170 171 172
 * 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.
N
NeilBrown 已提交
173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
 */
static int dev_parms(struct raid_set *rs, char **argv)
{
	int i;
	int rebuild = 0;
	int metadata_available = 0;
	int ret = 0;

	for (i = 0; i < rs->md.raid_disks; i++, argv += 2) {
		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;

		if (strcmp(argv[0], "-")) {
195 196 197 198 199 200 201 202 203 204
			ret = dm_get_device(rs->ti, argv[0],
					    dm_table_get_mode(rs->ti->table),
					    &rs->dev[i].meta_dev);
			rs->ti->error = "RAID metadata device lookup failure";
			if (ret)
				return ret;

			rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL);
			if (!rs->dev[i].rdev.sb_page)
				return -ENOMEM;
N
NeilBrown 已提交
205 206 207 208 209 210 211 212 213
		}

		if (!strcmp(argv[1], "-")) {
			if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
			    (!rs->dev[i].rdev.recovery_offset)) {
				rs->ti->error = "Drive designated for rebuild not specified";
				return -EINVAL;
			}

214 215 216 217
			rs->ti->error = "No data device supplied with metadata device";
			if (rs->dev[i].meta_dev)
				return -EINVAL;

N
NeilBrown 已提交
218 219 220 221 222 223 224 225 226 227 228
			continue;
		}

		ret = dm_get_device(rs->ti, argv[1],
				    dm_table_get_mode(rs->ti->table),
				    &rs->dev[i].data_dev);
		if (ret) {
			rs->ti->error = "RAID device lookup failure";
			return ret;
		}

229 230 231 232
		if (rs->dev[i].meta_dev) {
			metadata_available = 1;
			rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev;
		}
N
NeilBrown 已提交
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
		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");
		rs->ti->error = "RAID device lookup failure";
		return -EINVAL;
	}

	return 0;
}

263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
/*
 * 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)) {
			DMINFO("Choosing default region size of %lu sectors",
			       region_size);
			region_size = min_region_size;
		} else {
			DMINFO("Choosing default region size of 4MiB");
			region_size = 1 << 13; /* sectors */
		}
	} else {
		/*
		 * Validate user-supplied value.
		 */
		if (region_size > rs->ti->len) {
			rs->ti->error = "Supplied region size is too large";
			return -EINVAL;
		}

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

		if (!is_power_of_2(region_size)) {
			rs->ti->error = "Region size is not a power of 2";
			return -EINVAL;
		}

		if (region_size < rs->md.chunk_sectors) {
			rs->ti->error = "Region size is smaller than the chunk size";
			return -EINVAL;
		}
	}

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

	return 0;
}

N
NeilBrown 已提交
324 325 326 327
/*
 * Possible arguments are...
 *	<chunk_size> [optional_args]
 *
J
Jonathan Brassow 已提交
328 329 330 331 332
 * 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
N
NeilBrown 已提交
333
 *    [rebuild <idx>]			Rebuild the drive indicated by the index
J
Jonathan Brassow 已提交
334 335
 *    [daemon_sleep <ms>]		Time between bitmap daemon work to
 *                                      clear bits
N
NeilBrown 已提交
336 337
 *    [min_recovery_rate <kB/sec/disk>]	Throttle RAID initialization
 *    [max_recovery_rate <kB/sec/disk>]	Throttle RAID initialization
338
 *    [write_mostly <idx>]		Indicate a write mostly drive via index
N
NeilBrown 已提交
339 340
 *    [max_write_behind <sectors>]	See '-write-behind=' (man mdadm)
 *    [stripe_cache <sectors>]		Stripe cache size for higher RAIDs
341
 *    [region_size <sectors>]           Defines granularity of bitmap
N
NeilBrown 已提交
342 343 344 345 346
 */
static int parse_raid_params(struct raid_set *rs, char **argv,
			     unsigned num_raid_params)
{
	unsigned i, rebuild_cnt = 0;
347
	unsigned long value, region_size = 0;
348
	sector_t sectors_per_dev = rs->ti->len;
349
	sector_t max_io_len;
N
NeilBrown 已提交
350 351 352 353
	char *key;

	/*
	 * First, parse the in-order required arguments
J
Jonathan Brassow 已提交
354
	 * "chunk_size" is the only argument of this type.
N
NeilBrown 已提交
355
	 */
J
Jonathan Brassow 已提交
356
	if ((strict_strtoul(argv[0], 10, &value) < 0)) {
N
NeilBrown 已提交
357 358
		rs->ti->error = "Bad chunk size";
		return -EINVAL;
J
Jonathan Brassow 已提交
359 360 361 362 363 364 365 366 367 368
	} else if (rs->raid_type->level == 1) {
		if (value)
			DMERR("Ignoring chunk size parameter for RAID 1");
		value = 0;
	} else if (!is_power_of_2(value)) {
		rs->ti->error = "Chunk size must be a power of 2";
		return -EINVAL;
	} else if (value < 8) {
		rs->ti->error = "Chunk size value is too small";
		return -EINVAL;
N
NeilBrown 已提交
369 370 371 372 373 374 375
	}

	rs->md.new_chunk_sectors = rs->md.chunk_sectors = value;
	argv++;
	num_raid_params--;

	/*
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390
	 * 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.
N
NeilBrown 已提交
391
	 */
392
	for (i = 0; i < rs->md.raid_disks; i++) {
N
NeilBrown 已提交
393
		set_bit(In_sync, &rs->dev[i].rdev.flags);
394 395
		rs->dev[i].rdev.recovery_offset = MaxSector;
	}
N
NeilBrown 已提交
396

397 398 399
	/*
	 * Second, parse the unordered optional arguments
	 */
N
NeilBrown 已提交
400
	for (i = 0; i < num_raid_params; i++) {
401
		if (!strcasecmp(argv[i], "nosync")) {
N
NeilBrown 已提交
402 403 404 405
			rs->md.recovery_cp = MaxSector;
			rs->print_flags |= DMPF_NOSYNC;
			continue;
		}
406
		if (!strcasecmp(argv[i], "sync")) {
N
NeilBrown 已提交
407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
			rs->md.recovery_cp = 0;
			rs->print_flags |= DMPF_SYNC;
			continue;
		}

		/* The rest of the optional arguments come in key/value pairs */
		if ((i + 1) >= num_raid_params) {
			rs->ti->error = "Wrong number of raid parameters given";
			return -EINVAL;
		}

		key = argv[i++];
		if (strict_strtoul(argv[i], 10, &value) < 0) {
			rs->ti->error = "Bad numerical argument given in raid params";
			return -EINVAL;
		}

424
		if (!strcasecmp(key, "rebuild")) {
J
Jonathan Brassow 已提交
425
			rebuild_cnt++;
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444

			switch (rs->raid_type->level) {
			case 1:
				if (rebuild_cnt >= rs->md.raid_disks) {
					rs->ti->error = "Too many rebuild devices specified";
					return -EINVAL;
				}
				break;
			case 4:
			case 5:
			case 6:
				if (rebuild_cnt > rs->raid_type->parity_devs) {
					rs->ti->error = "Too many rebuild devices specified for given RAID type";
					return -EINVAL;
				}
				break;
			default:
				DMERR("The rebuild parameter is not supported for %s", rs->raid_type->name);
				rs->ti->error = "Rebuild not supported for this RAID type";
N
NeilBrown 已提交
445 446
				return -EINVAL;
			}
447

N
NeilBrown 已提交
448 449 450 451 452 453
			if (value > rs->md.raid_disks) {
				rs->ti->error = "Invalid rebuild index given";
				return -EINVAL;
			}
			clear_bit(In_sync, &rs->dev[value].rdev.flags);
			rs->dev[value].rdev.recovery_offset = 0;
454
			rs->print_flags |= DMPF_REBUILD;
455 456 457 458 459
		} else if (!strcasecmp(key, "write_mostly")) {
			if (rs->raid_type->level != 1) {
				rs->ti->error = "write_mostly option is only valid for RAID1";
				return -EINVAL;
			}
460
			if (value >= rs->md.raid_disks) {
461 462 463 464
				rs->ti->error = "Invalid write_mostly drive index given";
				return -EINVAL;
			}
			set_bit(WriteMostly, &rs->dev[value].rdev.flags);
465
		} else if (!strcasecmp(key, "max_write_behind")) {
466 467 468 469
			if (rs->raid_type->level != 1) {
				rs->ti->error = "max_write_behind option is only valid for RAID1";
				return -EINVAL;
			}
N
NeilBrown 已提交
470 471 472 473 474 475 476 477 478 479 480 481
			rs->print_flags |= DMPF_MAX_WRITE_BEHIND;

			/*
			 * In device-mapper, we specify things in sectors, but
			 * MD records this value in kB
			 */
			value /= 2;
			if (value > COUNTER_MAX) {
				rs->ti->error = "Max write-behind limit out of range";
				return -EINVAL;
			}
			rs->md.bitmap_info.max_write_behind = value;
482
		} else if (!strcasecmp(key, "daemon_sleep")) {
N
NeilBrown 已提交
483 484 485 486 487 488
			rs->print_flags |= DMPF_DAEMON_SLEEP;
			if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
				rs->ti->error = "daemon sleep period out of range";
				return -EINVAL;
			}
			rs->md.bitmap_info.daemon_sleep = value;
489
		} else if (!strcasecmp(key, "stripe_cache")) {
N
NeilBrown 已提交
490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505
			rs->print_flags |= DMPF_STRIPE_CACHE;

			/*
			 * In device-mapper, we specify things in sectors, but
			 * MD records this value in kB
			 */
			value /= 2;

			if (rs->raid_type->level < 5) {
				rs->ti->error = "Inappropriate argument: stripe_cache";
				return -EINVAL;
			}
			if (raid5_set_cache_size(&rs->md, (int)value)) {
				rs->ti->error = "Bad stripe_cache size";
				return -EINVAL;
			}
506
		} else if (!strcasecmp(key, "min_recovery_rate")) {
N
NeilBrown 已提交
507 508 509 510 511 512
			rs->print_flags |= DMPF_MIN_RECOVERY_RATE;
			if (value > INT_MAX) {
				rs->ti->error = "min_recovery_rate out of range";
				return -EINVAL;
			}
			rs->md.sync_speed_min = (int)value;
513
		} else if (!strcasecmp(key, "max_recovery_rate")) {
N
NeilBrown 已提交
514 515 516 517 518 519
			rs->print_flags |= DMPF_MAX_RECOVERY_RATE;
			if (value > INT_MAX) {
				rs->ti->error = "max_recovery_rate out of range";
				return -EINVAL;
			}
			rs->md.sync_speed_max = (int)value;
520 521 522
		} else if (!strcasecmp(key, "region_size")) {
			rs->print_flags |= DMPF_REGION_SIZE;
			region_size = value;
N
NeilBrown 已提交
523 524 525 526 527 528 529
		} else {
			DMERR("Unable to parse RAID parameter: %s", key);
			rs->ti->error = "Unable to parse RAID parameters";
			return -EINVAL;
		}
	}

530 531 532 533
	if (validate_region_size(rs, region_size))
		return -EINVAL;

	if (rs->md.chunk_sectors)
534
		max_io_len = rs->md.chunk_sectors;
535
	else
536
		max_io_len = region_size;
537

538 539
	if (dm_set_target_max_io_len(rs->ti, max_io_len))
		return -EINVAL;
J
Jonathan Brassow 已提交
540

541 542 543 544 545 546 547
	if ((rs->raid_type->level > 1) &&
	    sector_div(sectors_per_dev, (rs->md.raid_disks - rs->raid_type->parity_devs))) {
		rs->ti->error = "Target length not divisible by number of data devices";
		return -EINVAL;
	}
	rs->md.dev_sectors = sectors_per_dev;

N
NeilBrown 已提交
548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
	/* Assume there are no metadata devices until the drives are parsed */
	rs->md.persistent = 0;
	rs->md.external = 1;

	return 0;
}

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);

J
Jonathan Brassow 已提交
566 567 568
	if (rs->raid_type->level == 1)
		return md_raid1_congested(&rs->md, bits);

N
NeilBrown 已提交
569 570 571
	return md_raid5_congested(&rs->md, bits);
}

572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609
/*
 * 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;

	__u8 pad[452];		/* Round struct to 512 bytes. */
				/* Always set to 0 when writing. */
} __packed;

610
static int read_disk_sb(struct md_rdev *rdev, int size)
611 612 613 614 615 616 617
{
	BUG_ON(!rdev->sb_page);

	if (rdev->sb_loaded)
		return 0;

	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
618 619
		DMERR("Failed to read superblock of device at position %d",
		      rdev->raid_disk);
620
		md_error(rdev->mddev, rdev);
621 622 623 624 625 626 627 628
		return -EINVAL;
	}

	rdev->sb_loaded = 1;

	return 0;
}

629
static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
630
{
631
	int i;
632 633
	uint64_t failed_devices;
	struct dm_raid_superblock *sb;
634
	struct raid_set *rs = container_of(mddev, struct raid_set, md);
635 636 637 638

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

639 640 641 642
	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);
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670

	memset(sb, 0, 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
 */
671
static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
672 673 674 675 676 677 678 679 680 681 682 683 684 685
{
	int ret;
	struct dm_raid_superblock *sb;
	struct dm_raid_superblock *refsb;
	uint64_t events_sb, events_refsb;

	rdev->sb_start = 0;
	rdev->sb_size = sizeof(*sb);

	ret = read_disk_sb(rdev, rdev->sb_size);
	if (ret)
		return ret;

	sb = page_address(rdev->sb_page);
686 687 688 689 690 691 692 693

	/*
	 * 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)) {
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
		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;
}

716
static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
717 718 719 720 721 722 723 724
{
	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;
N
NeilBrown 已提交
725
	struct md_rdev *r;
726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767
	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) ||
	    (le32_to_cpu(sb->layout) != mddev->layout) ||
	    (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors)) {
		DMERR("Reshaping arrays not yet supported.");
		return -EINVAL;
	}

	/* We can only change the number of devices in RAID1 right now */
	if ((rs->raid_type->level != 1) &&
	    (le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
		DMERR("Reshaping arrays not yet supported.");
		return -EINVAL;
	}

	if (!(rs->print_flags & (DMPF_SYNC | DMPF_NOSYNC)))
		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.
	 */
N
NeilBrown 已提交
768
	rdev_for_each(r, mddev) {
769
		if (!test_bit(In_sync, &r->flags)) {
770 771
			DMINFO("Device %d specified for rebuild: "
			       "Clearing superblock", r->raid_disk);
772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799
			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.
	 */
N
NeilBrown 已提交
800
	rdev_for_each(r, mddev) {
801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832
		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 (rs->raid_type->level != 1) {
					rs->ti->error = "Cannot change device "
						"positions in RAID array";
					return -EINVAL;
				}
				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;
}

833
static int super_validate(struct mddev *mddev, struct md_rdev *rdev)
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
{
	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;

	mddev->bitmap_info.offset = 4096 >> 9; /* Enable bitmap creation */
	rdev->mddev->bitmap_info.default_offset = 4096 >> 9;
	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 ret;
873 874
	unsigned redundancy = 0;
	struct raid_dev *dev;
875
	struct md_rdev *rdev, *tmp, *freshest;
876
	struct mddev *mddev = &rs->md;
877

878 879 880 881 882 883 884 885 886 887 888 889 890 891
	switch (rs->raid_type->level) {
	case 1:
		redundancy = rs->md.raid_disks - 1;
		break;
	case 4:
	case 5:
	case 6:
		redundancy = rs->raid_type->parity_devs;
		break;
	default:
		ti->error = "Unknown RAID type";
		return -EINVAL;
	}

892
	freshest = NULL;
893
	rdev_for_each_safe(rdev, tmp, mddev) {
894 895 896 897 898 899 900 901 902 903 904 905
		if (!rdev->meta_bdev)
			continue;

		ret = super_load(rdev, freshest);

		switch (ret) {
		case 1:
			freshest = rdev;
			break;
		case 0:
			break;
		default:
906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936
			dev = container_of(rdev, struct raid_dev, rdev);
			if (redundancy--) {
				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);

				continue;
			}
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952
			ti->error = "Failed to load superblock";
			return ret;
		}
	}

	if (!freshest)
		return 0;

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

N
NeilBrown 已提交
953
	rdev_for_each(rdev, mddev)
954 955 956 957 958 959
		if ((rdev != freshest) && super_validate(mddev, rdev))
			return -EINVAL;

	return 0;
}

N
NeilBrown 已提交
960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032
/*
 * Construct a RAID4/5/6 mapping:
 * Args:
 *	<raid_type> <#raid_params> <raid_params>		\
 *	<#raid_devs> { <meta_dev1> <dev1> .. <meta_devN> <devN> }
 *
 * <raid_params> varies by <raid_type>.  See 'parse_raid_params' for
 * details on possible <raid_params>.
 */
static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
	int ret;
	struct raid_type *rt;
	unsigned long num_raid_params, num_raid_devs;
	struct raid_set *rs = NULL;

	/* Must have at least <raid_type> <#raid_params> */
	if (argc < 2) {
		ti->error = "Too few arguments";
		return -EINVAL;
	}

	/* raid type */
	rt = get_raid_type(argv[0]);
	if (!rt) {
		ti->error = "Unrecognised raid_type";
		return -EINVAL;
	}
	argc--;
	argv++;

	/* number of RAID parameters */
	if (strict_strtoul(argv[0], 10, &num_raid_params) < 0) {
		ti->error = "Cannot understand number of RAID parameters";
		return -EINVAL;
	}
	argc--;
	argv++;

	/* Skip over RAID params for now and find out # of devices */
	if (num_raid_params + 1 > argc) {
		ti->error = "Arguments do not agree with counts given";
		return -EINVAL;
	}

	if ((strict_strtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
	    (num_raid_devs >= INT_MAX)) {
		ti->error = "Cannot understand number of raid devices";
		return -EINVAL;
	}

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

	ret = parse_raid_params(rs, argv, (unsigned)num_raid_params);
	if (ret)
		goto bad;

	ret = -EINVAL;

	argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
	argv += num_raid_params + 1;

	if (argc != (num_raid_devs * 2)) {
		ti->error = "Supplied RAID devices does not match the count given";
		goto bad;
	}

	ret = dev_parms(rs, argv);
	if (ret)
		goto bad;

1033 1034 1035 1036 1037
	rs->md.sync_super = super_sync;
	ret = analyse_superblocks(ti, rs);
	if (ret)
		goto bad;

N
NeilBrown 已提交
1038 1039
	INIT_WORK(&rs->md.event_work, do_table_event);
	ti->private = rs;
J
Jonathan E Brassow 已提交
1040
	ti->num_flush_requests = 1;
N
NeilBrown 已提交
1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054

	mutex_lock(&rs->md.reconfig_mutex);
	ret = md_run(&rs->md);
	rs->md.in_sync = 0; /* Assume already marked dirty */
	mutex_unlock(&rs->md.reconfig_mutex);

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

	rs->callbacks.congested_fn = raid_is_congested;
	dm_table_add_target_callbacks(ti->table, &rs->callbacks);

J
Jonathan Brassow 已提交
1055
	mddev_suspend(&rs->md);
N
NeilBrown 已提交
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075
	return 0;

bad:
	context_free(rs);

	return ret;
}

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, union map_info *map_context)
{
	struct raid_set *rs = ti->private;
1076
	struct mddev *mddev = &rs->md;
N
NeilBrown 已提交
1077 1078 1079 1080 1081 1082 1083

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

	return DM_MAPIO_SUBMITTED;
}

static int raid_status(struct dm_target *ti, status_type_t type,
1084
		       unsigned status_flags, char *result, unsigned maxlen)
N
NeilBrown 已提交
1085 1086 1087 1088
{
	struct raid_set *rs = ti->private;
	unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
	unsigned sz = 0;
1089
	int i, array_in_sync = 0;
N
NeilBrown 已提交
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
	sector_t sync;

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

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

1101 1102
		if (sync >= rs->md.resync_max_sectors) {
			array_in_sync = 1;
N
NeilBrown 已提交
1103
			sync = rs->md.resync_max_sectors;
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129
		} 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;
		}
		/*
		 * 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");
		}
N
NeilBrown 已提交
1130

1131 1132 1133 1134 1135 1136 1137 1138
		/*
		 * 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.
		 */
N
NeilBrown 已提交
1139 1140 1141 1142 1143 1144 1145
		DMEMIT(" %llu/%llu",
		       (unsigned long long) sync,
		       (unsigned long long) rs->md.resync_max_sectors);

		break;
	case STATUSTYPE_TABLE:
		/* The string you would use to construct this array */
1146
		for (i = 0; i < rs->md.raid_disks; i++) {
1147 1148
			if ((rs->print_flags & DMPF_REBUILD) &&
			    rs->dev[i].data_dev &&
N
NeilBrown 已提交
1149
			    !test_bit(In_sync, &rs->dev[i].rdev.flags))
1150
				raid_param_cnt += 2; /* for rebuilds */
1151 1152 1153 1154
			if (rs->dev[i].data_dev &&
			    test_bit(WriteMostly, &rs->dev[i].rdev.flags))
				raid_param_cnt += 2;
		}
N
NeilBrown 已提交
1155

1156
		raid_param_cnt += (hweight32(rs->print_flags & ~DMPF_REBUILD) * 2);
N
NeilBrown 已提交
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169
		if (rs->print_flags & (DMPF_SYNC | DMPF_NOSYNC))
			raid_param_cnt--;

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

		if ((rs->print_flags & DMPF_SYNC) &&
		    (rs->md.recovery_cp == MaxSector))
			DMEMIT(" sync");
		if (rs->print_flags & DMPF_NOSYNC)
			DMEMIT(" nosync");

		for (i = 0; i < rs->md.raid_disks; i++)
1170 1171
			if ((rs->print_flags & DMPF_REBUILD) &&
			    rs->dev[i].data_dev &&
N
NeilBrown 已提交
1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184
			    !test_bit(In_sync, &rs->dev[i].rdev.flags))
				DMEMIT(" rebuild %u", i);

		if (rs->print_flags & DMPF_DAEMON_SLEEP)
			DMEMIT(" daemon_sleep %lu",
			       rs->md.bitmap_info.daemon_sleep);

		if (rs->print_flags & DMPF_MIN_RECOVERY_RATE)
			DMEMIT(" min_recovery_rate %d", rs->md.sync_speed_min);

		if (rs->print_flags & DMPF_MAX_RECOVERY_RATE)
			DMEMIT(" max_recovery_rate %d", rs->md.sync_speed_max);

1185 1186 1187 1188 1189
		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);

N
NeilBrown 已提交
1190 1191 1192 1193 1194
		if (rs->print_flags & DMPF_MAX_WRITE_BEHIND)
			DMEMIT(" max_write_behind %lu",
			       rs->md.bitmap_info.max_write_behind);

		if (rs->print_flags & DMPF_STRIPE_CACHE) {
1195
			struct r5conf *conf = rs->md.private;
N
NeilBrown 已提交
1196 1197 1198 1199 1200 1201

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

1202 1203 1204 1205
		if (rs->print_flags & DMPF_REGION_SIZE)
			DMEMIT(" region_size %lu",
			       rs->md.bitmap_info.chunksize >> 9);

N
NeilBrown 已提交
1206 1207
		DMEMIT(" %d", rs->md.raid_disks);
		for (i = 0; i < rs->md.raid_disks; i++) {
1208 1209 1210 1211
			if (rs->dev[i].meta_dev)
				DMEMIT(" %s", rs->dev[i].meta_dev->name);
			else
				DMEMIT(" -");
N
NeilBrown 已提交
1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243

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

	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 ret = 0;

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

	return ret;
}

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;
1244
	struct r5conf *conf = rs->md.private;
N
NeilBrown 已提交
1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267

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

1268
	set_bit(MD_CHANGE_DEVS, &rs->md.flags);
1269 1270 1271
	if (!rs->bitmap_loaded) {
		bitmap_load(&rs->md);
		rs->bitmap_loaded = 1;
1272
	}
1273

1274
	clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
N
NeilBrown 已提交
1275 1276 1277 1278 1279
	mddev_resume(&rs->md);
}

static struct target_type raid_target = {
	.name = "raid",
1280
	.version = {1, 2, 0},
N
NeilBrown 已提交
1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
	.module = THIS_MODULE,
	.ctr = raid_ctr,
	.dtr = raid_dtr,
	.map = raid_map,
	.status = raid_status,
	.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)
{
	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_DESCRIPTION(DM_NAME " raid4/5/6 target");
MODULE_ALIAS("dm-raid4");
MODULE_ALIAS("dm-raid5");
MODULE_ALIAS("dm-raid6");
MODULE_AUTHOR("Neil Brown <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");