dm-table.c 20.7 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 20 21 22 23 24 25
#include <asm/atomic.h>

#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
26
	struct mapped_device *md;
L
Linus Torvalds 已提交
27 28 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);

	lhs->seg_boundary_mask =
		min_not_zero(lhs->seg_boundary_mask, rhs->seg_boundary_mask);
102 103

	lhs->no_cluster |= rhs->no_cluster;
L
Linus Torvalds 已提交
104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
}

/*
 * 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.
	 */
	n_highs = (sector_t *) dm_vcalloc(num, sizeof(struct dm_target) +
					  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
211 212
int dm_table_create(struct dm_table **result, int mode,
		    unsigned num_targets, struct mapped_device *md)
L
Linus Torvalds 已提交
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234
{
	struct dm_table *t = kmalloc(sizeof(*t), GFP_KERNEL);

	if (!t)
		return -ENOMEM;

	memset(t, 0, sizeof(*t));
	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
235
	t->md = md;
L
Linus Torvalds 已提交
236 237 238 239
	*result = t;
	return 0;
}

D
David Teigland 已提交
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277
int dm_create_error_table(struct dm_table **result, struct mapped_device *md)
{
	struct dm_table *t;
	sector_t dev_size = 1;
	int r;

	/*
	 * Find current size of device.
	 * Default to 1 sector if inactive.
	 */
	t = dm_get_table(md);
	if (t) {
		dev_size = dm_table_get_size(t);
		dm_table_put(t);
	}

	r = dm_table_create(&t, FMODE_READ, 1, md);
	if (r)
		return r;

	r = dm_table_add_target(t, "error", 0, dev_size, NULL);
	if (r)
		goto out;

	r = dm_table_complete(t);
	if (r)
		goto out;

	*result = t;

out:
	if (r)
		dm_table_put(t);

	return r;
}
EXPORT_SYMBOL_GPL(dm_create_error_table);

L
Linus Torvalds 已提交
278 279 280 281 282 283 284 285 286 287 288
static void free_devices(struct list_head *devices)
{
	struct list_head *tmp, *next;

	for (tmp = devices->next; tmp != devices; tmp = next) {
		struct dm_dev *dd = list_entry(tmp, struct dm_dev, list);
		next = tmp->next;
		kfree(dd);
	}
}

289
static void table_destroy(struct dm_table *t)
L
Linus Torvalds 已提交
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391
{
	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)
{
	int r;
	struct nameidata nd;
	struct inode *inode;

	if ((r = path_lookup(path, LOOKUP_FOLLOW, &nd)))
		return r;

	inode = nd.dentry->d_inode;
	if (!inode) {
		r = -ENOENT;
		goto out;
	}

	if (!S_ISBLK(inode->i_mode)) {
		r = -ENOTBLK;
		goto out;
	}

	*dev = inode->i_rdev;

 out:
	path_release(&nd);
	return r;
}

/*
 * See if we've already got a device in the list.
 */
static struct dm_dev *find_device(struct list_head *l, dev_t dev)
{
	struct dm_dev *dd;

	list_for_each_entry (dd, l, list)
		if (dd->bdev->bd_dev == dev)
			return dd;

	return NULL;
}

/*
 * Open a device so we can use it as a map destination.
 */
392
static int open_dev(struct dm_dev *d, dev_t dev, struct mapped_device *md)
L
Linus Torvalds 已提交
393 394 395 396 397 398
{
	static char *_claim_ptr = "I belong to device-mapper";
	struct block_device *bdev;

	int r;

399
	BUG_ON(d->bdev);
L
Linus Torvalds 已提交
400 401 402 403

	bdev = open_by_devnum(dev, d->mode);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
404
	r = bd_claim_by_disk(bdev, _claim_ptr, dm_disk(md));
L
Linus Torvalds 已提交
405 406 407 408 409 410 411 412 413 414
	if (r)
		blkdev_put(bdev);
	else
		d->bdev = bdev;
	return r;
}

/*
 * Close a device that we've been using.
 */
415
static void close_dev(struct dm_dev *d, struct mapped_device *md)
L
Linus Torvalds 已提交
416 417 418 419
{
	if (!d->bdev)
		return;

420
	bd_release_from_disk(d->bdev, dm_disk(md));
L
Linus Torvalds 已提交
421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
	blkdev_put(d->bdev);
	d->bdev = NULL;
}

/*
 * If possible (ie. blk_size[major] is set), this checks an area
 * of a destination device is valid.
 */
static int check_device_area(struct dm_dev *dd, sector_t start, sector_t len)
{
	sector_t dev_size;
	dev_size = dd->bdev->bd_inode->i_size >> SECTOR_SHIFT;
	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.
 */
441
static int upgrade_mode(struct dm_dev *dd, int new_mode, struct mapped_device *md)
L
Linus Torvalds 已提交
442 443 444 445 446 447 448 449 450
{
	int r;
	struct dm_dev dd_copy;
	dev_t dev = dd->bdev->bd_dev;

	dd_copy = *dd;

	dd->mode |= new_mode;
	dd->bdev = NULL;
451
	r = open_dev(dd, dev, md);
L
Linus Torvalds 已提交
452
	if (!r)
453
		close_dev(&dd_copy, md);
L
Linus Torvalds 已提交
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
	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;
	dev_t dev;
	struct dm_dev *dd;
	unsigned int major, minor;

473
	BUG_ON(!t);
L
Linus Torvalds 已提交
474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494

	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;

		dd->mode = mode;
		dd->bdev = NULL;

495
		if ((r = open_dev(dd, dev, t->md))) {
L
Linus Torvalds 已提交
496 497 498 499 500 501 502 503 504 505
			kfree(dd);
			return r;
		}

		format_dev_t(dd->name, dev);

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

	} else if (dd->mode != (mode | dd->mode)) {
506
		r = upgrade_mode(dd, mode, t->md);
L
Linus Torvalds 已提交
507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552
		if (r)
			return r;
	}
	atomic_inc(&dd->count);

	if (!check_device_area(dd, start, len)) {
		DMWARN("device %s too small for target", path);
		dm_put_device(ti, dd);
		return -EINVAL;
	}

	*result = dd;

	return 0;
}


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) {
		request_queue_t *q = bdev_get_queue((*result)->bdev);
		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);

		/* FIXME: Device-Mapper on top of RAID-0 breaks because DM
		 *        currently doesn't honor MD's merge_bvec_fn routine.
		 *        In this case, we'll force DM to use PAGE_SIZE or
		 *        smaller I/O, just to be safe. A better fix is in the
		 *        works, but add this for the time being so it will at
		 *        least operate correctly.
		 */
		if (q->merge_bvec_fn)
			rs->max_sectors =
				min_not_zero(rs->max_sectors,
553
					     (unsigned int) (PAGE_SIZE >> 9));
L
Linus Torvalds 已提交
554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569

		rs->max_phys_segments =
			min_not_zero(rs->max_phys_segments,
				     q->max_phys_segments);

		rs->max_hw_segments =
			min_not_zero(rs->max_hw_segments, q->max_hw_segments);

		rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);

		rs->max_segment_size =
			min_not_zero(rs->max_segment_size, q->max_segment_size);

		rs->seg_boundary_mask =
			min_not_zero(rs->seg_boundary_mask,
				     q->seg_boundary_mask);
570 571

		rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
L
Linus Torvalds 已提交
572 573 574 575 576 577 578 579 580 581 582
	}

	return r;
}

/*
 * Decrement a devices use count and remove it if necessary.
 */
void dm_put_device(struct dm_target *ti, struct dm_dev *dd)
{
	if (atomic_dec_and_test(&dd->count)) {
583
		close_dev(dd, ti->table->md);
L
Linus Torvalds 已提交
584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
		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;
631 632 633 634 635 636

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

L
Linus Torvalds 已提交
637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
	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)
691
		rs->max_sectors = SAFE_MAX_SECTORS;
L
Linus Torvalds 已提交
692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
	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;
}

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) {
		tgt->error = "zero-length target";
		DMERR("%s", tgt->error);
		return -EINVAL;
	}

	tgt->type = dm_get_target_type(type);
	if (!tgt->type) {
		tgt->error = "unknown target type";
		DMERR("%s", tgt->error);
		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:
	DMERR("%s", tgt->error);
	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 */
	for (i = t->depth - 2, total = 0; i >= 0; i--) {
		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
818
static DEFINE_MUTEX(_event_lock);
L
Linus Torvalds 已提交
819 820 821
void dm_table_event_callback(struct dm_table *t,
			     void (*fn)(void *), void *context)
{
A
Arjan van de Ven 已提交
822
	mutex_lock(&_event_lock);
L
Linus Torvalds 已提交
823 824
	t->event_fn = fn;
	t->event_context = context;
A
Arjan van de Ven 已提交
825
	mutex_unlock(&_event_lock);
L
Linus Torvalds 已提交
826 827 828 829 830 831 832 833 834 835
}

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
836
	mutex_lock(&_event_lock);
L
Linus Torvalds 已提交
837 838
	if (t->event_fn)
		t->event_fn(t->event_context);
A
Arjan van de Ven 已提交
839
	mutex_unlock(&_event_lock);
L
Linus Torvalds 已提交
840 841 842 843 844 845 846 847 848
}

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)
{
849
	if (index >= t->num_targets)
L
Linus Torvalds 已提交
850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
		return NULL;

	return t->targets + index;
}

/*
 * Search the btree for the correct target.
 */
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;
	q->seg_boundary_mask = t->limits.seg_boundary_mask;
887 888 889 890 891
	if (t->limits.no_cluster)
		q->queue_flags &= ~(1 << QUEUE_FLAG_CLUSTER);
	else
		q->queue_flags |= (1 << QUEUE_FLAG_CLUSTER);

L
Linus Torvalds 已提交
892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926
}

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)
{
927 928 929
	if (!t)
		return;

L
Linus Torvalds 已提交
930 931 932 933 934
	return suspend_targets(t, 0);
}

void dm_table_postsuspend_targets(struct dm_table *t)
{
935 936 937
	if (!t)
		return;

L
Linus Torvalds 已提交
938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
	return suspend_targets(t, 1);
}

void dm_table_resume_targets(struct dm_table *t)
{
	int i;

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

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

int dm_table_any_congested(struct dm_table *t, int bdi_bits)
{
	struct list_head *d, *devices;
	int r = 0;

	devices = dm_table_get_devices(t);
	for (d = devices->next; d != devices; d = d->next) {
		struct dm_dev *dd = list_entry(d, struct dm_dev, list);
		request_queue_t *q = bdev_get_queue(dd->bdev);
		r |= bdi_congested(&q->backing_dev_info, bdi_bits);
	}

	return r;
}

void dm_table_unplug_all(struct dm_table *t)
{
	struct list_head *d, *devices = dm_table_get_devices(t);

	for (d = devices->next; d != devices; d = d->next) {
		struct dm_dev *dd = list_entry(d, struct dm_dev, list);
		request_queue_t *q = bdev_get_queue(dd->bdev);

		if (q->unplug_fn)
			q->unplug_fn(q);
	}
}

int dm_table_flush_all(struct dm_table *t)
{
	struct list_head *d, *devices = dm_table_get_devices(t);
	int ret = 0;

	for (d = devices->next; d != devices; d = d->next) {
		struct dm_dev *dd = list_entry(d, struct dm_dev, list);
		request_queue_t *q = bdev_get_queue(dd->bdev);
		int err;

		if (!q->issue_flush_fn)
			err = -EOPNOTSUPP;
		else
			err = q->issue_flush_fn(q, dd->bdev->bd_disk, NULL);

		if (!ret)
			ret = err;
	}

	return ret;
}

M
Mike Anderson 已提交
1003 1004 1005 1006 1007 1008 1009
struct mapped_device *dm_table_get_md(struct dm_table *t)
{
	dm_get(t->md);

	return t->md;
}

L
Linus Torvalds 已提交
1010 1011 1012 1013
EXPORT_SYMBOL(dm_vcalloc);
EXPORT_SYMBOL(dm_get_device);
EXPORT_SYMBOL(dm_put_device);
EXPORT_SYMBOL(dm_table_event);
1014
EXPORT_SYMBOL(dm_table_get_size);
L
Linus Torvalds 已提交
1015
EXPORT_SYMBOL(dm_table_get_mode);
M
Mike Anderson 已提交
1016
EXPORT_SYMBOL(dm_table_get_md);
L
Linus Torvalds 已提交
1017 1018 1019 1020
EXPORT_SYMBOL(dm_table_put);
EXPORT_SYMBOL(dm_table_get);
EXPORT_SYMBOL(dm_table_unplug_all);
EXPORT_SYMBOL(dm_table_flush_all);