dm-table.c 20.6 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) {
L
Linus Torvalds 已提交
253 254 255 256 257
		struct dm_dev *dd = list_entry(tmp, struct dm_dev, list);
		kfree(dd);
	}
}

258
static void table_destroy(struct dm_table *t)
L
Linus Torvalds 已提交
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
{
	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;

326
	inode = nd.path.dentry->d_inode;
L
Linus Torvalds 已提交
327 328 329 330 331 332 333 334 335 336 337 338 339
	if (!inode) {
		r = -ENOENT;
		goto out;
	}

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

	*dev = inode->i_rdev;

 out:
J
Jan Blunck 已提交
340
	path_put(&nd.path);
L
Linus Torvalds 已提交
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360
	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.
 */
361
static int open_dev(struct dm_dev *d, dev_t dev, struct mapped_device *md)
L
Linus Torvalds 已提交
362 363 364 365 366 367
{
	static char *_claim_ptr = "I belong to device-mapper";
	struct block_device *bdev;

	int r;

368
	BUG_ON(d->bdev);
L
Linus Torvalds 已提交
369 370 371 372

	bdev = open_by_devnum(dev, d->mode);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
373
	r = bd_claim_by_disk(bdev, _claim_ptr, dm_disk(md));
L
Linus Torvalds 已提交
374 375 376 377 378 379 380 381 382 383
	if (r)
		blkdev_put(bdev);
	else
		d->bdev = bdev;
	return r;
}

/*
 * Close a device that we've been using.
 */
384
static void close_dev(struct dm_dev *d, struct mapped_device *md)
L
Linus Torvalds 已提交
385 386 387 388
{
	if (!d->bdev)
		return;

389
	bd_release_from_disk(d->bdev, dm_disk(md));
L
Linus Torvalds 已提交
390 391 392 393 394
	blkdev_put(d->bdev);
	d->bdev = NULL;
}

/*
M
Mike Anderson 已提交
395
 * If possible, this checks an area of a destination device is valid.
L
Linus Torvalds 已提交
396 397 398
 */
static int check_device_area(struct dm_dev *dd, sector_t start, sector_t len)
{
M
Mike Anderson 已提交
399 400 401 402 403
	sector_t dev_size = dd->bdev->bd_inode->i_size >> SECTOR_SHIFT;

	if (!dev_size)
		return 1;

L
Linus Torvalds 已提交
404 405 406 407 408 409 410 411
	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.
 */
412
static int upgrade_mode(struct dm_dev *dd, int new_mode, struct mapped_device *md)
L
Linus Torvalds 已提交
413 414 415 416 417 418 419 420 421
{
	int r;
	struct dm_dev dd_copy;
	dev_t dev = dd->bdev->bd_dev;

	dd_copy = *dd;

	dd->mode |= new_mode;
	dd->bdev = NULL;
422
	r = open_dev(dd, dev, md);
L
Linus Torvalds 已提交
423
	if (!r)
424
		close_dev(&dd_copy, md);
L
Linus Torvalds 已提交
425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
	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
440
	dev_t uninitialized_var(dev);
L
Linus Torvalds 已提交
441 442 443
	struct dm_dev *dd;
	unsigned int major, minor;

444
	BUG_ON(!t);
L
Linus Torvalds 已提交
445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465

	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;

466
		if ((r = open_dev(dd, dev, t->md))) {
L
Linus Torvalds 已提交
467 468 469 470 471 472 473 474 475 476
			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)) {
477
		r = upgrade_mode(dd, mode, t->md);
L
Linus Torvalds 已提交
478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493
		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;
}

494
void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
L
Linus Torvalds 已提交
495
{
496
	struct request_queue *q = bdev_get_queue(bdev);
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516
	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)
L
Linus Torvalds 已提交
517
		rs->max_sectors =
518 519
			min_not_zero(rs->max_sectors,
				     (unsigned int) (PAGE_SIZE >> 9));
L
Linus Torvalds 已提交
520

521 522 523
	rs->max_phys_segments =
		min_not_zero(rs->max_phys_segments,
			     q->max_phys_segments);
L
Linus Torvalds 已提交
524

525 526
	rs->max_hw_segments =
		min_not_zero(rs->max_hw_segments, q->max_hw_segments);
L
Linus Torvalds 已提交
527

528
	rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
L
Linus Torvalds 已提交
529

530 531
	rs->max_segment_size =
		min_not_zero(rs->max_segment_size, q->max_segment_size);
L
Linus Torvalds 已提交
532

N
Neil Brown 已提交
533 534 535
	rs->max_hw_sectors =
		min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);

536 537 538
	rs->seg_boundary_mask =
		min_not_zero(rs->seg_boundary_mask,
			     q->seg_boundary_mask);
L
Linus Torvalds 已提交
539

V
Vasily Averin 已提交
540 541
	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);

542 543 544
	rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
}
EXPORT_SYMBOL_GPL(dm_set_device_limits);
545

546 547 548 549 550 551 552 553
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
554 555 556 557 558 559 560 561 562 563

	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)) {
564
		close_dev(dd, ti->table->md);
L
Linus Torvalds 已提交
565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611
		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;
612 613 614 615 616 617

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

L
Linus Torvalds 已提交
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
	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)
672
		rs->max_sectors = SAFE_MAX_SECTORS;
N
Neil Brown 已提交
673 674
	if (!rs->max_hw_sectors)
		rs->max_hw_sectors = SAFE_MAX_SECTORS;
L
Linus Torvalds 已提交
675 676 677 678 679 680 681 682 683 684
	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
685 686
	if (!rs->bounce_pfn)
		rs->bounce_pfn = -1;
L
Linus Torvalds 已提交
687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
}

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) {
703
		DMERR("%s: zero-length target", dm_device_name(t->md));
L
Linus Torvalds 已提交
704 705 706 707 708
		return -EINVAL;
	}

	tgt->type = dm_get_target_type(type);
	if (!tgt->type) {
709 710
		DMERR("%s: %s: unknown target type", dm_device_name(t->md),
		      type);
L
Linus Torvalds 已提交
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
		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:
747
	DMERR("%s: %s: %s", dm_device_name(t->md), type, tgt->error);
L
Linus Torvalds 已提交
748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768
	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
769
	for (i = t->depth - 2; i >= 0; i--) {
L
Linus Torvalds 已提交
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
		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
802
static DEFINE_MUTEX(_event_lock);
L
Linus Torvalds 已提交
803 804 805
void dm_table_event_callback(struct dm_table *t,
			     void (*fn)(void *), void *context)
{
A
Arjan van de Ven 已提交
806
	mutex_lock(&_event_lock);
L
Linus Torvalds 已提交
807 808
	t->event_fn = fn;
	t->event_context = context;
A
Arjan van de Ven 已提交
809
	mutex_unlock(&_event_lock);
L
Linus Torvalds 已提交
810 811 812 813 814 815 816 817 818 819
}

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
820
	mutex_lock(&_event_lock);
L
Linus Torvalds 已提交
821 822
	if (t->event_fn)
		t->event_fn(t->event_context);
A
Arjan van de Ven 已提交
823
	mutex_unlock(&_event_lock);
L
Linus Torvalds 已提交
824 825 826 827 828 829 830 831 832
}

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)
{
833
	if (index >= t->num_targets)
L
Linus Torvalds 已提交
834 835 836 837 838 839 840
		return NULL;

	return t->targets + index;
}

/*
 * Search the btree for the correct target.
841 842 843
 *
 * Caller should check returned pointer with dm_target_is_valid()
 * to trap I/O beyond end of device.
L
Linus Torvalds 已提交
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_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
873
	q->max_hw_sectors = t->limits.max_hw_sectors;
L
Linus Torvalds 已提交
874
	q->seg_boundary_mask = t->limits.seg_boundary_mask;
V
Vasily Averin 已提交
875
	q->bounce_pfn = t->limits.bounce_pfn;
N
Nick Piggin 已提交
876 877 878
	/* XXX: the below will probably go bug. must ensure there can be no
	 * concurrency on queue_flags, and use the unlocked versions...
	 */
879
	if (t->limits.no_cluster)
N
Nick Piggin 已提交
880
		queue_flag_clear(QUEUE_FLAG_CLUSTER, q);
881
	else
N
Nick Piggin 已提交
882
		queue_flag_set(QUEUE_FLAG_CLUSTER, q);
883

L
Linus Torvalds 已提交
884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918
}

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)
{
919 920 921
	if (!t)
		return;

922
	suspend_targets(t, 0);
L
Linus Torvalds 已提交
923 924 925 926
}

void dm_table_postsuspend_targets(struct dm_table *t)
{
927 928 929
	if (!t)
		return;

930
	suspend_targets(t, 1);
L
Linus Torvalds 已提交
931 932
}

933
int dm_table_resume_targets(struct dm_table *t)
L
Linus Torvalds 已提交
934
{
935 936 937 938 939 940 941 942 943 944 945 946
	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
947 948 949 950 951 952 953

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

		if (ti->type->resume)
			ti->type->resume(ti);
	}
954 955

	return 0;
L
Linus Torvalds 已提交
956 957 958 959
}

int dm_table_any_congested(struct dm_table *t, int bdi_bits)
{
P
Paul Jimenez 已提交
960 961
	struct dm_dev *dd;
	struct list_head *devices = dm_table_get_devices(t);
L
Linus Torvalds 已提交
962 963
	int r = 0;

P
Paul Jimenez 已提交
964
	list_for_each_entry(dd, devices, list) {
965
		struct request_queue *q = bdev_get_queue(dd->bdev);
L
Linus Torvalds 已提交
966 967 968 969 970 971 972 973
		r |= bdi_congested(&q->backing_dev_info, bdi_bits);
	}

	return r;
}

void dm_table_unplug_all(struct dm_table *t)
{
P
Paul Jimenez 已提交
974 975
	struct dm_dev *dd;
	struct list_head *devices = dm_table_get_devices(t);
L
Linus Torvalds 已提交
976

P
Paul Jimenez 已提交
977
	list_for_each_entry(dd, devices, list) {
978
		struct request_queue *q = bdev_get_queue(dd->bdev);
L
Linus Torvalds 已提交
979

980
		blk_unplug(q);
L
Linus Torvalds 已提交
981 982 983
	}
}

M
Mike Anderson 已提交
984 985 986 987 988 989 990
struct mapped_device *dm_table_get_md(struct dm_table *t)
{
	dm_get(t->md);

	return t->md;
}

L
Linus Torvalds 已提交
991 992 993 994
EXPORT_SYMBOL(dm_vcalloc);
EXPORT_SYMBOL(dm_get_device);
EXPORT_SYMBOL(dm_put_device);
EXPORT_SYMBOL(dm_table_event);
995
EXPORT_SYMBOL(dm_table_get_size);
L
Linus Torvalds 已提交
996
EXPORT_SYMBOL(dm_table_get_mode);
M
Mike Anderson 已提交
997
EXPORT_SYMBOL(dm_table_get_md);
L
Linus Torvalds 已提交
998 999 1000
EXPORT_SYMBOL(dm_table_put);
EXPORT_SYMBOL(dm_table_get);
EXPORT_SYMBOL(dm_table_unplug_all);