dm-table.c 20.4 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * Copyright (C) 2001 Sistina Software (UK) Limited.
 * Copyright (C) 2004 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm.h"

#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
A
Arjan van de Ven 已提交
17
#include <linux/mutex.h>
L
Linus Torvalds 已提交
18 19
#include <asm/atomic.h>

20 21
#define DM_MSG_PREFIX "table"

L
Linus Torvalds 已提交
22 23 24 25 26 27
#define MAX_DEPTH 16
#define NODE_SIZE L1_CACHE_BYTES
#define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
#define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)

struct dm_table {
M
Mike Anderson 已提交
28
	struct mapped_device *md;
L
Linus Torvalds 已提交
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
	atomic_t holders;

	/* btree table */
	unsigned int depth;
	unsigned int counts[MAX_DEPTH];	/* in nodes */
	sector_t *index[MAX_DEPTH];

	unsigned int num_targets;
	unsigned int num_allocated;
	sector_t *highs;
	struct dm_target *targets;

	/*
	 * Indicates the rw permissions for the new logical
	 * device.  This should be a combination of FMODE_READ
	 * and FMODE_WRITE.
	 */
	int mode;

	/* a list of devices used by this table */
	struct list_head devices;

	/*
	 * These are optimistic limits taken from all the
	 * targets, some targets will need smaller limits.
	 */
	struct io_restrictions limits;

	/* events get handed up using this callback */
	void (*event_fn)(void *);
	void *event_context;
};

/*
 * Similar to ceiling(log_size(n))
 */
static unsigned int int_log(unsigned int n, unsigned int base)
{
	int result = 0;

	while (n > 1) {
		n = dm_div_up(n, base);
		result++;
	}

	return result;
}

/*
 * Returns the minimum that is _not_ zero, unless both are zero.
 */
#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))

/*
 * Combine two io_restrictions, always taking the lower value.
 */
static void combine_restrictions_low(struct io_restrictions *lhs,
				     struct io_restrictions *rhs)
{
	lhs->max_sectors =
		min_not_zero(lhs->max_sectors, rhs->max_sectors);

	lhs->max_phys_segments =
		min_not_zero(lhs->max_phys_segments, rhs->max_phys_segments);

	lhs->max_hw_segments =
		min_not_zero(lhs->max_hw_segments, rhs->max_hw_segments);

	lhs->hardsect_size = max(lhs->hardsect_size, rhs->hardsect_size);

	lhs->max_segment_size =
		min_not_zero(lhs->max_segment_size, rhs->max_segment_size);

N
Neil Brown 已提交
102 103 104
	lhs->max_hw_sectors =
		min_not_zero(lhs->max_hw_sectors, rhs->max_hw_sectors);

L
Linus Torvalds 已提交
105 106
	lhs->seg_boundary_mask =
		min_not_zero(lhs->seg_boundary_mask, rhs->seg_boundary_mask);
107

V
Vasily Averin 已提交
108 109
	lhs->bounce_pfn = min_not_zero(lhs->bounce_pfn, rhs->bounce_pfn);

110
	lhs->no_cluster |= rhs->no_cluster;
L
Linus Torvalds 已提交
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
}

/*
 * Calculate the index of the child node of the n'th node k'th key.
 */
static inline unsigned int get_child(unsigned int n, unsigned int k)
{
	return (n * CHILDREN_PER_NODE) + k;
}

/*
 * Return the n'th node of level l from table t.
 */
static inline sector_t *get_node(struct dm_table *t,
				 unsigned int l, unsigned int n)
{
	return t->index[l] + (n * KEYS_PER_NODE);
}

/*
 * Return the highest key that you could lookup from the n'th
 * node on level l of the btree.
 */
static sector_t high(struct dm_table *t, unsigned int l, unsigned int n)
{
	for (; l < t->depth - 1; l++)
		n = get_child(n, CHILDREN_PER_NODE - 1);

	if (n >= t->counts[l])
		return (sector_t) - 1;

	return get_node(t, l, n)[KEYS_PER_NODE - 1];
}

/*
 * Fills in a level of the btree based on the highs of the level
 * below it.
 */
static int setup_btree_index(unsigned int l, struct dm_table *t)
{
	unsigned int n, k;
	sector_t *node;

	for (n = 0U; n < t->counts[l]; n++) {
		node = get_node(t, l, n);

		for (k = 0U; k < KEYS_PER_NODE; k++)
			node[k] = high(t, l + 1, get_child(n, k));
	}

	return 0;
}

void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size)
{
	unsigned long size;
	void *addr;

	/*
	 * Check that we're not going to overflow.
	 */
	if (nmemb > (ULONG_MAX / elem_size))
		return NULL;

	size = nmemb * elem_size;
	addr = vmalloc(size);
	if (addr)
		memset(addr, 0, size);

	return addr;
}

/*
 * highs, and targets are managed as dynamic arrays during a
 * table load.
 */
static int alloc_targets(struct dm_table *t, unsigned int num)
{
	sector_t *n_highs;
	struct dm_target *n_targets;
	int n = t->num_targets;

	/*
	 * Allocate both the target array and offset array at once.
195 196
	 * Append an empty entry to catch sectors beyond the end of
	 * the device.
L
Linus Torvalds 已提交
197
	 */
198
	n_highs = (sector_t *) dm_vcalloc(num + 1, sizeof(struct dm_target) +
L
Linus Torvalds 已提交
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
					  sizeof(sector_t));
	if (!n_highs)
		return -ENOMEM;

	n_targets = (struct dm_target *) (n_highs + num);

	if (n) {
		memcpy(n_highs, t->highs, sizeof(*n_highs) * n);
		memcpy(n_targets, t->targets, sizeof(*n_targets) * n);
	}

	memset(n_highs + n, -1, sizeof(*n_highs) * (num - n));
	vfree(t->highs);

	t->num_allocated = num;
	t->highs = n_highs;
	t->targets = n_targets;

	return 0;
}

M
Mike Anderson 已提交
220 221
int dm_table_create(struct dm_table **result, int mode,
		    unsigned num_targets, struct mapped_device *md)
L
Linus Torvalds 已提交
222
{
D
Dmitry Monakhov 已提交
223
	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
L
Linus Torvalds 已提交
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242

	if (!t)
		return -ENOMEM;

	INIT_LIST_HEAD(&t->devices);
	atomic_set(&t->holders, 1);

	if (!num_targets)
		num_targets = KEYS_PER_NODE;

	num_targets = dm_round_up(num_targets, KEYS_PER_NODE);

	if (alloc_targets(t, num_targets)) {
		kfree(t);
		t = NULL;
		return -ENOMEM;
	}

	t->mode = mode;
M
Mike Anderson 已提交
243
	t->md = md;
L
Linus Torvalds 已提交
244 245 246 247 248 249 250 251
	*result = t;
	return 0;
}

static void free_devices(struct list_head *devices)
{
	struct list_head *tmp, *next;

P
Paul Jimenez 已提交
252
	list_for_each_safe(tmp, next, devices) {
M
Mikulas Patocka 已提交
253 254
		struct dm_dev_internal *dd =
		    list_entry(tmp, struct dm_dev_internal, list);
L
Linus Torvalds 已提交
255 256 257 258
		kfree(dd);
	}
}

259
static void table_destroy(struct dm_table *t)
L
Linus Torvalds 已提交
260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319
{
	unsigned int i;

	/* free the indexes (see dm_table_complete) */
	if (t->depth >= 2)
		vfree(t->index[t->depth - 2]);

	/* free the targets */
	for (i = 0; i < t->num_targets; i++) {
		struct dm_target *tgt = t->targets + i;

		if (tgt->type->dtr)
			tgt->type->dtr(tgt);

		dm_put_target_type(tgt->type);
	}

	vfree(t->highs);

	/* free the device list */
	if (t->devices.next != &t->devices) {
		DMWARN("devices still present during destroy: "
		       "dm_table_remove_device calls missing");

		free_devices(&t->devices);
	}

	kfree(t);
}

void dm_table_get(struct dm_table *t)
{
	atomic_inc(&t->holders);
}

void dm_table_put(struct dm_table *t)
{
	if (!t)
		return;

	if (atomic_dec_and_test(&t->holders))
		table_destroy(t);
}

/*
 * Checks to see if we need to extend highs or targets.
 */
static inline int check_space(struct dm_table *t)
{
	if (t->num_targets >= t->num_allocated)
		return alloc_targets(t, t->num_allocated * 2);

	return 0;
}

/*
 * Convert a device path to a dev_t.
 */
static int lookup_device(const char *path, dev_t *dev)
{
320 321 322 323 324 325
	struct block_device *bdev = lookup_bdev(path);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
	*dev = bdev->bd_dev;
	bdput(bdev);
	return 0;
L
Linus Torvalds 已提交
326 327 328 329 330
}

/*
 * See if we've already got a device in the list.
 */
M
Mikulas Patocka 已提交
331
static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev)
L
Linus Torvalds 已提交
332
{
M
Mikulas Patocka 已提交
333
	struct dm_dev_internal *dd;
L
Linus Torvalds 已提交
334 335

	list_for_each_entry (dd, l, list)
M
Mikulas Patocka 已提交
336
		if (dd->dm_dev.bdev->bd_dev == dev)
L
Linus Torvalds 已提交
337 338 339 340 341 342 343 344
			return dd;

	return NULL;
}

/*
 * Open a device so we can use it as a map destination.
 */
M
Mikulas Patocka 已提交
345 346
static int open_dev(struct dm_dev_internal *d, dev_t dev,
		    struct mapped_device *md)
L
Linus Torvalds 已提交
347 348 349 350 351 352
{
	static char *_claim_ptr = "I belong to device-mapper";
	struct block_device *bdev;

	int r;

M
Mikulas Patocka 已提交
353
	BUG_ON(d->dm_dev.bdev);
L
Linus Torvalds 已提交
354

M
Mikulas Patocka 已提交
355
	bdev = open_by_devnum(dev, d->dm_dev.mode);
L
Linus Torvalds 已提交
356 357
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
358
	r = bd_claim_by_disk(bdev, _claim_ptr, dm_disk(md));
L
Linus Torvalds 已提交
359 360 361
	if (r)
		blkdev_put(bdev);
	else
M
Mikulas Patocka 已提交
362
		d->dm_dev.bdev = bdev;
L
Linus Torvalds 已提交
363 364 365 366 367 368
	return r;
}

/*
 * Close a device that we've been using.
 */
M
Mikulas Patocka 已提交
369
static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
L
Linus Torvalds 已提交
370
{
M
Mikulas Patocka 已提交
371
	if (!d->dm_dev.bdev)
L
Linus Torvalds 已提交
372 373
		return;

M
Mikulas Patocka 已提交
374 375 376
	bd_release_from_disk(d->dm_dev.bdev, dm_disk(md));
	blkdev_put(d->dm_dev.bdev);
	d->dm_dev.bdev = NULL;
L
Linus Torvalds 已提交
377 378 379
}

/*
M
Mike Anderson 已提交
380
 * If possible, this checks an area of a destination device is valid.
L
Linus Torvalds 已提交
381
 */
M
Mikulas Patocka 已提交
382 383
static int check_device_area(struct dm_dev_internal *dd, sector_t start,
			     sector_t len)
L
Linus Torvalds 已提交
384
{
M
Mikulas Patocka 已提交
385
	sector_t dev_size = dd->dm_dev.bdev->bd_inode->i_size >> SECTOR_SHIFT;
M
Mike Anderson 已提交
386 387 388 389

	if (!dev_size)
		return 1;

L
Linus Torvalds 已提交
390 391 392 393 394 395 396 397
	return ((start < dev_size) && (len <= (dev_size - start)));
}

/*
 * This upgrades the mode on an already open dm_dev.  Being
 * careful to leave things as they were if we fail to reopen the
 * device.
 */
M
Mikulas Patocka 已提交
398 399
static int upgrade_mode(struct dm_dev_internal *dd, int new_mode,
			struct mapped_device *md)
L
Linus Torvalds 已提交
400 401
{
	int r;
M
Mikulas Patocka 已提交
402 403
	struct dm_dev_internal dd_copy;
	dev_t dev = dd->dm_dev.bdev->bd_dev;
L
Linus Torvalds 已提交
404 405 406

	dd_copy = *dd;

M
Mikulas Patocka 已提交
407 408
	dd->dm_dev.mode |= new_mode;
	dd->dm_dev.bdev = NULL;
409
	r = open_dev(dd, dev, md);
L
Linus Torvalds 已提交
410
	if (!r)
411
		close_dev(&dd_copy, md);
L
Linus Torvalds 已提交
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
	else
		*dd = dd_copy;

	return r;
}

/*
 * Add a device to the list, or just increment the usage count if
 * it's already present.
 */
static int __table_get_device(struct dm_table *t, struct dm_target *ti,
			      const char *path, sector_t start, sector_t len,
			      int mode, struct dm_dev **result)
{
	int r;
A
Andrew Morton 已提交
427
	dev_t uninitialized_var(dev);
M
Mikulas Patocka 已提交
428
	struct dm_dev_internal *dd;
L
Linus Torvalds 已提交
429 430
	unsigned int major, minor;

431
	BUG_ON(!t);
L
Linus Torvalds 已提交
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449

	if (sscanf(path, "%u:%u", &major, &minor) == 2) {
		/* Extract the major/minor numbers */
		dev = MKDEV(major, minor);
		if (MAJOR(dev) != major || MINOR(dev) != minor)
			return -EOVERFLOW;
	} else {
		/* convert the path to a device */
		if ((r = lookup_device(path, &dev)))
			return r;
	}

	dd = find_device(&t->devices, dev);
	if (!dd) {
		dd = kmalloc(sizeof(*dd), GFP_KERNEL);
		if (!dd)
			return -ENOMEM;

M
Mikulas Patocka 已提交
450 451
		dd->dm_dev.mode = mode;
		dd->dm_dev.bdev = NULL;
L
Linus Torvalds 已提交
452

453
		if ((r = open_dev(dd, dev, t->md))) {
L
Linus Torvalds 已提交
454 455 456 457
			kfree(dd);
			return r;
		}

M
Mikulas Patocka 已提交
458
		format_dev_t(dd->dm_dev.name, dev);
L
Linus Torvalds 已提交
459 460 461 462

		atomic_set(&dd->count, 0);
		list_add(&dd->list, &t->devices);

M
Mikulas Patocka 已提交
463
	} else if (dd->dm_dev.mode != (mode | dd->dm_dev.mode)) {
464
		r = upgrade_mode(dd, mode, t->md);
L
Linus Torvalds 已提交
465 466 467 468 469 470 471
		if (r)
			return r;
	}
	atomic_inc(&dd->count);

	if (!check_device_area(dd, start, len)) {
		DMWARN("device %s too small for target", path);
M
Mikulas Patocka 已提交
472
		dm_put_device(ti, &dd->dm_dev);
L
Linus Torvalds 已提交
473 474 475
		return -EINVAL;
	}

M
Mikulas Patocka 已提交
476
	*result = &dd->dm_dev;
L
Linus Torvalds 已提交
477 478 479 480

	return 0;
}

481
void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
L
Linus Torvalds 已提交
482
{
483
	struct request_queue *q = bdev_get_queue(bdev);
484 485 486 487 488 489 490 491 492 493 494 495
	struct io_restrictions *rs = &ti->limits;

	/*
	 * Combine the device limits low.
	 *
	 * FIXME: if we move an io_restriction struct
	 *        into q this would just be a call to
	 *        combine_restrictions_low()
	 */
	rs->max_sectors =
		min_not_zero(rs->max_sectors, q->max_sectors);

496 497 498 499
	/*
	 * Check if merge fn is supported.
	 * If not we'll force DM to use PAGE_SIZE or
	 * smaller I/O, just to be safe.
500
	 */
501 502

	if (q->merge_bvec_fn && !ti->type->merge)
L
Linus Torvalds 已提交
503
		rs->max_sectors =
504 505
			min_not_zero(rs->max_sectors,
				     (unsigned int) (PAGE_SIZE >> 9));
L
Linus Torvalds 已提交
506

507 508 509
	rs->max_phys_segments =
		min_not_zero(rs->max_phys_segments,
			     q->max_phys_segments);
L
Linus Torvalds 已提交
510

511 512
	rs->max_hw_segments =
		min_not_zero(rs->max_hw_segments, q->max_hw_segments);
L
Linus Torvalds 已提交
513

514
	rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
L
Linus Torvalds 已提交
515

516 517
	rs->max_segment_size =
		min_not_zero(rs->max_segment_size, q->max_segment_size);
L
Linus Torvalds 已提交
518

N
Neil Brown 已提交
519 520 521
	rs->max_hw_sectors =
		min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);

522 523 524
	rs->seg_boundary_mask =
		min_not_zero(rs->seg_boundary_mask,
			     q->seg_boundary_mask);
L
Linus Torvalds 已提交
525

V
Vasily Averin 已提交
526 527
	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);

528 529 530
	rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
}
EXPORT_SYMBOL_GPL(dm_set_device_limits);
531

532 533 534 535 536 537 538 539
int dm_get_device(struct dm_target *ti, const char *path, sector_t start,
		  sector_t len, int mode, struct dm_dev **result)
{
	int r = __table_get_device(ti->table, ti, path,
				   start, len, mode, result);

	if (!r)
		dm_set_device_limits(ti, (*result)->bdev);
L
Linus Torvalds 已提交
540 541 542 543 544 545 546

	return r;
}

/*
 * Decrement a devices use count and remove it if necessary.
 */
M
Mikulas Patocka 已提交
547
void dm_put_device(struct dm_target *ti, struct dm_dev *d)
L
Linus Torvalds 已提交
548
{
M
Mikulas Patocka 已提交
549 550 551
	struct dm_dev_internal *dd = container_of(d, struct dm_dev_internal,
						  dm_dev);

L
Linus Torvalds 已提交
552
	if (atomic_dec_and_test(&dd->count)) {
553
		close_dev(dd, ti->table->md);
L
Linus Torvalds 已提交
554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
		list_del(&dd->list);
		kfree(dd);
	}
}

/*
 * Checks to see if the target joins onto the end of the table.
 */
static int adjoin(struct dm_table *table, struct dm_target *ti)
{
	struct dm_target *prev;

	if (!table->num_targets)
		return !ti->begin;

	prev = &table->targets[table->num_targets - 1];
	return (ti->begin == (prev->begin + prev->len));
}

/*
 * Used to dynamically allocate the arg array.
 */
static char **realloc_argv(unsigned *array_size, char **old_argv)
{
	char **argv;
	unsigned new_size;

	new_size = *array_size ? *array_size * 2 : 64;
	argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL);
	if (argv) {
		memcpy(argv, old_argv, *array_size * sizeof(*argv));
		*array_size = new_size;
	}

	kfree(old_argv);
	return argv;
}

/*
 * Destructively splits up the argument list to pass to ctr.
 */
int dm_split_args(int *argc, char ***argvp, char *input)
{
	char *start, *end = input, *out, **argv = NULL;
	unsigned array_size = 0;

	*argc = 0;
601 602 603 604 605 606

	if (!input) {
		*argvp = NULL;
		return 0;
	}

L
Linus Torvalds 已提交
607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660
	argv = realloc_argv(&array_size, argv);
	if (!argv)
		return -ENOMEM;

	while (1) {
		start = end;

		/* Skip whitespace */
		while (*start && isspace(*start))
			start++;

		if (!*start)
			break;	/* success, we hit the end */

		/* 'out' is used to remove any back-quotes */
		end = out = start;
		while (*end) {
			/* Everything apart from '\0' can be quoted */
			if (*end == '\\' && *(end + 1)) {
				*out++ = *(end + 1);
				end += 2;
				continue;
			}

			if (isspace(*end))
				break;	/* end of token */

			*out++ = *end++;
		}

		/* have we already filled the array ? */
		if ((*argc + 1) > array_size) {
			argv = realloc_argv(&array_size, argv);
			if (!argv)
				return -ENOMEM;
		}

		/* we know this is whitespace */
		if (*end)
			end++;

		/* terminate the string and put it in the array */
		*out = '\0';
		argv[*argc] = start;
		(*argc)++;
	}

	*argvp = argv;
	return 0;
}

static void check_for_valid_limits(struct io_restrictions *rs)
{
	if (!rs->max_sectors)
661
		rs->max_sectors = SAFE_MAX_SECTORS;
N
Neil Brown 已提交
662 663
	if (!rs->max_hw_sectors)
		rs->max_hw_sectors = SAFE_MAX_SECTORS;
L
Linus Torvalds 已提交
664 665 666 667 668 669 670 671 672 673
	if (!rs->max_phys_segments)
		rs->max_phys_segments = MAX_PHYS_SEGMENTS;
	if (!rs->max_hw_segments)
		rs->max_hw_segments = MAX_HW_SEGMENTS;
	if (!rs->hardsect_size)
		rs->hardsect_size = 1 << SECTOR_SHIFT;
	if (!rs->max_segment_size)
		rs->max_segment_size = MAX_SEGMENT_SIZE;
	if (!rs->seg_boundary_mask)
		rs->seg_boundary_mask = -1;
V
Vasily Averin 已提交
674 675
	if (!rs->bounce_pfn)
		rs->bounce_pfn = -1;
L
Linus Torvalds 已提交
676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691
}

int dm_table_add_target(struct dm_table *t, const char *type,
			sector_t start, sector_t len, char *params)
{
	int r = -EINVAL, argc;
	char **argv;
	struct dm_target *tgt;

	if ((r = check_space(t)))
		return r;

	tgt = t->targets + t->num_targets;
	memset(tgt, 0, sizeof(*tgt));

	if (!len) {
692
		DMERR("%s: zero-length target", dm_device_name(t->md));
L
Linus Torvalds 已提交
693 694 695 696 697
		return -EINVAL;
	}

	tgt->type = dm_get_target_type(type);
	if (!tgt->type) {
698 699
		DMERR("%s: %s: unknown target type", dm_device_name(t->md),
		      type);
L
Linus Torvalds 已提交
700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735
		return -EINVAL;
	}

	tgt->table = t;
	tgt->begin = start;
	tgt->len = len;
	tgt->error = "Unknown error";

	/*
	 * Does this target adjoin the previous one ?
	 */
	if (!adjoin(t, tgt)) {
		tgt->error = "Gap in table";
		r = -EINVAL;
		goto bad;
	}

	r = dm_split_args(&argc, &argv, params);
	if (r) {
		tgt->error = "couldn't split parameters (insufficient memory)";
		goto bad;
	}

	r = tgt->type->ctr(tgt, argc, argv);
	kfree(argv);
	if (r)
		goto bad;

	t->highs[t->num_targets++] = tgt->begin + tgt->len - 1;

	/* FIXME: the plan is to combine high here and then have
	 * the merge fn apply the target level restrictions. */
	combine_restrictions_low(&t->limits, &tgt->limits);
	return 0;

 bad:
736
	DMERR("%s: %s: %s", dm_device_name(t->md), type, tgt->error);
L
Linus Torvalds 已提交
737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757
	dm_put_target_type(tgt->type);
	return r;
}

static int setup_indexes(struct dm_table *t)
{
	int i;
	unsigned int total = 0;
	sector_t *indexes;

	/* allocate the space for *all* the indexes */
	for (i = t->depth - 2; i >= 0; i--) {
		t->counts[i] = dm_div_up(t->counts[i + 1], CHILDREN_PER_NODE);
		total += t->counts[i];
	}

	indexes = (sector_t *) dm_vcalloc(total, (unsigned long) NODE_SIZE);
	if (!indexes)
		return -ENOMEM;

	/* set up internal nodes, bottom-up */
J
Jun'ichi Nomura 已提交
758
	for (i = t->depth - 2; i >= 0; i--) {
L
Linus Torvalds 已提交
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790
		t->index[i] = indexes;
		indexes += (KEYS_PER_NODE * t->counts[i]);
		setup_btree_index(i, t);
	}

	return 0;
}

/*
 * Builds the btree to index the map.
 */
int dm_table_complete(struct dm_table *t)
{
	int r = 0;
	unsigned int leaf_nodes;

	check_for_valid_limits(&t->limits);

	/* how many indexes will the btree have ? */
	leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE);
	t->depth = 1 + int_log(leaf_nodes, CHILDREN_PER_NODE);

	/* leaf layer has already been set up */
	t->counts[t->depth - 1] = leaf_nodes;
	t->index[t->depth - 1] = t->highs;

	if (t->depth >= 2)
		r = setup_indexes(t);

	return r;
}

A
Arjan van de Ven 已提交
791
static DEFINE_MUTEX(_event_lock);
L
Linus Torvalds 已提交
792 793 794
void dm_table_event_callback(struct dm_table *t,
			     void (*fn)(void *), void *context)
{
A
Arjan van de Ven 已提交
795
	mutex_lock(&_event_lock);
L
Linus Torvalds 已提交
796 797
	t->event_fn = fn;
	t->event_context = context;
A
Arjan van de Ven 已提交
798
	mutex_unlock(&_event_lock);
L
Linus Torvalds 已提交
799 800 801 802 803 804 805 806 807 808
}

void dm_table_event(struct dm_table *t)
{
	/*
	 * You can no longer call dm_table_event() from interrupt
	 * context, use a bottom half instead.
	 */
	BUG_ON(in_interrupt());

A
Arjan van de Ven 已提交
809
	mutex_lock(&_event_lock);
L
Linus Torvalds 已提交
810 811
	if (t->event_fn)
		t->event_fn(t->event_context);
A
Arjan van de Ven 已提交
812
	mutex_unlock(&_event_lock);
L
Linus Torvalds 已提交
813 814 815 816 817 818 819 820 821
}

sector_t dm_table_get_size(struct dm_table *t)
{
	return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0;
}

struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index)
{
822
	if (index >= t->num_targets)
L
Linus Torvalds 已提交
823 824 825 826 827 828 829
		return NULL;

	return t->targets + index;
}

/*
 * Search the btree for the correct target.
830 831 832
 *
 * Caller should check returned pointer with dm_target_is_valid()
 * to trap I/O beyond end of device.
L
Linus Torvalds 已提交
833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861
 */
struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
{
	unsigned int l, n = 0, k = 0;
	sector_t *node;

	for (l = 0; l < t->depth; l++) {
		n = get_child(n, k);
		node = get_node(t, l, n);

		for (k = 0; k < KEYS_PER_NODE; k++)
			if (node[k] >= sector)
				break;
	}

	return &t->targets[(KEYS_PER_NODE * n) + k];
}

void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q)
{
	/*
	 * Make sure we obey the optimistic sub devices
	 * restrictions.
	 */
	blk_queue_max_sectors(q, t->limits.max_sectors);
	q->max_phys_segments = t->limits.max_phys_segments;
	q->max_hw_segments = t->limits.max_hw_segments;
	q->hardsect_size = t->limits.hardsect_size;
	q->max_segment_size = t->limits.max_segment_size;
N
Neil Brown 已提交
862
	q->max_hw_sectors = t->limits.max_hw_sectors;
L
Linus Torvalds 已提交
863
	q->seg_boundary_mask = t->limits.seg_boundary_mask;
V
Vasily Averin 已提交
864
	q->bounce_pfn = t->limits.bounce_pfn;
865

866
	if (t->limits.no_cluster)
867
		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
868
	else
869
		queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q);
870

L
Linus Torvalds 已提交
871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905
}

unsigned int dm_table_get_num_targets(struct dm_table *t)
{
	return t->num_targets;
}

struct list_head *dm_table_get_devices(struct dm_table *t)
{
	return &t->devices;
}

int dm_table_get_mode(struct dm_table *t)
{
	return t->mode;
}

static void suspend_targets(struct dm_table *t, unsigned postsuspend)
{
	int i = t->num_targets;
	struct dm_target *ti = t->targets;

	while (i--) {
		if (postsuspend) {
			if (ti->type->postsuspend)
				ti->type->postsuspend(ti);
		} else if (ti->type->presuspend)
			ti->type->presuspend(ti);

		ti++;
	}
}

void dm_table_presuspend_targets(struct dm_table *t)
{
906 907 908
	if (!t)
		return;

909
	suspend_targets(t, 0);
L
Linus Torvalds 已提交
910 911 912 913
}

void dm_table_postsuspend_targets(struct dm_table *t)
{
914 915 916
	if (!t)
		return;

917
	suspend_targets(t, 1);
L
Linus Torvalds 已提交
918 919
}

920
int dm_table_resume_targets(struct dm_table *t)
L
Linus Torvalds 已提交
921
{
922 923 924 925 926 927 928 929 930 931 932 933
	int i, r = 0;

	for (i = 0; i < t->num_targets; i++) {
		struct dm_target *ti = t->targets + i;

		if (!ti->type->preresume)
			continue;

		r = ti->type->preresume(ti);
		if (r)
			return r;
	}
L
Linus Torvalds 已提交
934 935 936 937 938 939 940

	for (i = 0; i < t->num_targets; i++) {
		struct dm_target *ti = t->targets + i;

		if (ti->type->resume)
			ti->type->resume(ti);
	}
941 942

	return 0;
L
Linus Torvalds 已提交
943 944 945 946
}

int dm_table_any_congested(struct dm_table *t, int bdi_bits)
{
M
Mikulas Patocka 已提交
947
	struct dm_dev_internal *dd;
P
Paul Jimenez 已提交
948
	struct list_head *devices = dm_table_get_devices(t);
L
Linus Torvalds 已提交
949 950
	int r = 0;

P
Paul Jimenez 已提交
951
	list_for_each_entry(dd, devices, list) {
M
Mikulas Patocka 已提交
952
		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
L
Linus Torvalds 已提交
953 954 955 956 957 958 959 960
		r |= bdi_congested(&q->backing_dev_info, bdi_bits);
	}

	return r;
}

void dm_table_unplug_all(struct dm_table *t)
{
M
Mikulas Patocka 已提交
961
	struct dm_dev_internal *dd;
P
Paul Jimenez 已提交
962
	struct list_head *devices = dm_table_get_devices(t);
L
Linus Torvalds 已提交
963

P
Paul Jimenez 已提交
964
	list_for_each_entry(dd, devices, list) {
M
Mikulas Patocka 已提交
965
		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
L
Linus Torvalds 已提交
966

967
		blk_unplug(q);
L
Linus Torvalds 已提交
968 969 970
	}
}

M
Mike Anderson 已提交
971 972 973 974 975 976 977
struct mapped_device *dm_table_get_md(struct dm_table *t)
{
	dm_get(t->md);

	return t->md;
}

L
Linus Torvalds 已提交
978 979 980 981
EXPORT_SYMBOL(dm_vcalloc);
EXPORT_SYMBOL(dm_get_device);
EXPORT_SYMBOL(dm_put_device);
EXPORT_SYMBOL(dm_table_event);
982
EXPORT_SYMBOL(dm_table_get_size);
L
Linus Torvalds 已提交
983
EXPORT_SYMBOL(dm_table_get_mode);
M
Mike Anderson 已提交
984
EXPORT_SYMBOL(dm_table_get_md);
L
Linus Torvalds 已提交
985 986 987
EXPORT_SYMBOL(dm_table_put);
EXPORT_SYMBOL(dm_table_get);
EXPORT_SYMBOL(dm_table_unplug_all);