blk-settings.c 25.5 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814
/*
 * Functions related to setting various queue properties from drivers
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
#include <linux/gcd.h>
#include <linux/lcm.h>
#include <linux/jiffies.h>
#include <linux/gfp.h>

#include "blk.h"

unsigned long blk_max_low_pfn;
EXPORT_SYMBOL(blk_max_low_pfn);

unsigned long blk_max_pfn;

/**
 * blk_queue_prep_rq - set a prepare_request function for queue
 * @q:		queue
 * @pfn:	prepare_request function
 *
 * It's possible for a queue to register a prepare_request callback which
 * is invoked before the request is handed to the request_fn. The goal of
 * the function is to prepare a request for I/O, it can be used to build a
 * cdb from the request data for instance.
 *
 */
void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
{
	q->prep_rq_fn = pfn;
}
EXPORT_SYMBOL(blk_queue_prep_rq);

/**
 * blk_queue_unprep_rq - set an unprepare_request function for queue
 * @q:		queue
 * @ufn:	unprepare_request function
 *
 * It's possible for a queue to register an unprepare_request callback
 * which is invoked before the request is finally completed. The goal
 * of the function is to deallocate any data that was allocated in the
 * prepare_request callback.
 *
 */
void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn)
{
	q->unprep_rq_fn = ufn;
}
EXPORT_SYMBOL(blk_queue_unprep_rq);

/**
 * blk_queue_merge_bvec - set a merge_bvec function for queue
 * @q:		queue
 * @mbfn:	merge_bvec_fn
 *
 * Usually queues have static limitations on the max sectors or segments that
 * we can put in a request. Stacking drivers may have some settings that
 * are dynamic, and thus we have to query the queue whether it is ok to
 * add a new bio_vec to a bio at a given offset or not. If the block device
 * has such limitations, it needs to register a merge_bvec_fn to control
 * the size of bio's sent to it. Note that a block device *must* allow a
 * single page to be added to an empty bio. The block device driver may want
 * to use the bio_split() function to deal with these bio's. By default
 * no merge_bvec_fn is defined for a queue, and only the fixed limits are
 * honored.
 */
void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
{
	q->merge_bvec_fn = mbfn;
}
EXPORT_SYMBOL(blk_queue_merge_bvec);

void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
{
	q->softirq_done_fn = fn;
}
EXPORT_SYMBOL(blk_queue_softirq_done);

void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
{
	q->rq_timeout = timeout;
}
EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);

void blk_queue_rq_timed_out(struct request_queue *q, rq_timed_out_fn *fn)
{
	q->rq_timed_out_fn = fn;
}
EXPORT_SYMBOL_GPL(blk_queue_rq_timed_out);

void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn)
{
	q->lld_busy_fn = fn;
}
EXPORT_SYMBOL_GPL(blk_queue_lld_busy);

/**
 * blk_set_default_limits - reset limits to default values
 * @lim:  the queue_limits structure to reset
 *
 * Description:
 *   Returns a queue_limit struct to its default state.  Can be used by
 *   stacking drivers like DM that stage table swaps and reuse an
 *   existing device queue.
 */
void blk_set_default_limits(struct queue_limits *lim)
{
	lim->max_segments = BLK_MAX_SEGMENTS;
	lim->max_integrity_segments = 0;
	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
	lim->max_sectors = BLK_DEF_MAX_SECTORS;
	lim->max_hw_sectors = INT_MAX;
	lim->max_discard_sectors = 0;
	lim->discard_granularity = 0;
	lim->discard_alignment = 0;
	lim->discard_misaligned = 0;
	lim->discard_zeroes_data = -1;
	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
	lim->alignment_offset = 0;
	lim->io_opt = 0;
	lim->misaligned = 0;
	lim->cluster = 1;
}
EXPORT_SYMBOL(blk_set_default_limits);

/**
 * blk_queue_make_request - define an alternate make_request function for a device
 * @q:  the request queue for the device to be affected
 * @mfn: the alternate make_request function
 *
 * Description:
 *    The normal way for &struct bios to be passed to a device
 *    driver is for them to be collected into requests on a request
 *    queue, and then to allow the device driver to select requests
 *    off that queue when it is ready.  This works well for many block
 *    devices. However some block devices (typically virtual devices
 *    such as md or lvm) do not benefit from the processing on the
 *    request queue, and are served best by having the requests passed
 *    directly to them.  This can be achieved by providing a function
 *    to blk_queue_make_request().
 *
 * Caveat:
 *    The driver that does this *must* be able to deal appropriately
 *    with buffers in "highmemory". This can be accomplished by either calling
 *    __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
 *    blk_queue_bounce() to create a buffer in normal memory.
 **/
void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
{
	/*
	 * set defaults
	 */
	q->nr_requests = BLKDEV_MAX_RQ;

	q->make_request_fn = mfn;
	blk_queue_dma_alignment(q, 511);
	blk_queue_congestion_threshold(q);
	q->nr_batching = BLK_BATCH_REQ;

	q->unplug_thresh = 4;		/* hmm */
	q->unplug_delay = msecs_to_jiffies(3);	/* 3 milliseconds */
	if (q->unplug_delay == 0)
		q->unplug_delay = 1;

	q->unplug_timer.function = blk_unplug_timeout;
	q->unplug_timer.data = (unsigned long)q;

	blk_set_default_limits(&q->limits);
	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);

	/*
	 * If the caller didn't supply a lock, fall back to our embedded
	 * per-queue locks
	 */
	if (!q->queue_lock)
		q->queue_lock = &q->__queue_lock;

	/*
	 * by default assume old behaviour and bounce for any highmem page
	 */
	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
}
EXPORT_SYMBOL(blk_queue_make_request);

/**
 * blk_queue_bounce_limit - set bounce buffer limit for queue
 * @q: the request queue for the device
 * @dma_mask: the maximum address the device can handle
 *
 * Description:
 *    Different hardware can have different requirements as to what pages
 *    it can do I/O directly to. A low level driver can call
 *    blk_queue_bounce_limit to have lower memory pages allocated as bounce
 *    buffers for doing I/O to pages residing above @dma_mask.
 **/
void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
{
	unsigned long b_pfn = dma_mask >> PAGE_SHIFT;
	int dma = 0;

	q->bounce_gfp = GFP_NOIO;
#if BITS_PER_LONG == 64
	/*
	 * Assume anything <= 4GB can be handled by IOMMU.  Actually
	 * some IOMMUs can handle everything, but I don't know of a
	 * way to test this here.
	 */
	if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
		dma = 1;
	q->limits.bounce_pfn = max(max_low_pfn, b_pfn);
#else
	if (b_pfn < blk_max_low_pfn)
		dma = 1;
	q->limits.bounce_pfn = b_pfn;
#endif
	if (dma) {
		init_emergency_isa_pool();
		q->bounce_gfp = GFP_NOIO | GFP_DMA;
		q->limits.bounce_pfn = b_pfn;
	}
}
EXPORT_SYMBOL(blk_queue_bounce_limit);

/**
 * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
 * @limits: the queue limits
 * @max_hw_sectors:  max hardware sectors in the usual 512b unit
 *
 * Description:
 *    Enables a low level driver to set a hard upper limit,
 *    max_hw_sectors, on the size of requests.  max_hw_sectors is set by
 *    the device driver based upon the combined capabilities of I/O
 *    controller and storage device.
 *
 *    max_sectors is a soft limit imposed by the block layer for
 *    filesystem type requests.  This value can be overridden on a
 *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
 *    The soft limit can not exceed max_hw_sectors.
 **/
void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
{
	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_hw_sectors);
	}

	limits->max_hw_sectors = max_hw_sectors;
	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
				    BLK_DEF_MAX_SECTORS);
}
EXPORT_SYMBOL(blk_limits_max_hw_sectors);

/**
 * blk_queue_max_hw_sectors - set max sectors for a request for this queue
 * @q:  the request queue for the device
 * @max_hw_sectors:  max hardware sectors in the usual 512b unit
 *
 * Description:
 *    See description for blk_limits_max_hw_sectors().
 **/
void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
{
	blk_limits_max_hw_sectors(&q->limits, max_hw_sectors);
}
EXPORT_SYMBOL(blk_queue_max_hw_sectors);

/**
 * blk_queue_max_discard_sectors - set max sectors for a single discard
 * @q:  the request queue for the device
 * @max_discard_sectors: maximum number of sectors to discard
 **/
void blk_queue_max_discard_sectors(struct request_queue *q,
		unsigned int max_discard_sectors)
{
	q->limits.max_discard_sectors = max_discard_sectors;
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);

/**
 * blk_queue_max_segments - set max hw segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    hw data segments in a request.
 **/
void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
{
	if (!max_segments) {
		max_segments = 1;
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_segments);
	}

	q->limits.max_segments = max_segments;
}
EXPORT_SYMBOL(blk_queue_max_segments);

/**
 * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
 * @q:  the request queue for the device
 * @max_size:  max size of segment in bytes
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of a
 *    coalesced segment
 **/
void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
{
	if (max_size < PAGE_CACHE_SIZE) {
		max_size = PAGE_CACHE_SIZE;
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_size);
	}

	q->limits.max_segment_size = max_size;
}
EXPORT_SYMBOL(blk_queue_max_segment_size);

/**
 * blk_queue_logical_block_size - set logical block size for the queue
 * @q:  the request queue for the device
 * @size:  the logical block size, in bytes
 *
 * Description:
 *   This should be set to the lowest possible block size that the
 *   storage device can address.  The default of 512 covers most
 *   hardware.
 **/
void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
{
	q->limits.logical_block_size = size;

	if (q->limits.physical_block_size < size)
		q->limits.physical_block_size = size;

	if (q->limits.io_min < q->limits.physical_block_size)
		q->limits.io_min = q->limits.physical_block_size;
}
EXPORT_SYMBOL(blk_queue_logical_block_size);

/**
 * blk_queue_physical_block_size - set physical block size for the queue
 * @q:  the request queue for the device
 * @size:  the physical block size, in bytes
 *
 * Description:
 *   This should be set to the lowest possible sector size that the
 *   hardware can operate on without reverting to read-modify-write
 *   operations.
 */
void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
{
	q->limits.physical_block_size = size;

	if (q->limits.physical_block_size < q->limits.logical_block_size)
		q->limits.physical_block_size = q->limits.logical_block_size;

	if (q->limits.io_min < q->limits.physical_block_size)
		q->limits.io_min = q->limits.physical_block_size;
}
EXPORT_SYMBOL(blk_queue_physical_block_size);

/**
 * blk_queue_alignment_offset - set physical block alignment offset
 * @q:	the request queue for the device
 * @offset: alignment offset in bytes
 *
 * Description:
 *   Some devices are naturally misaligned to compensate for things like
 *   the legacy DOS partition table 63-sector offset.  Low-level drivers
 *   should call this function for devices whose first sector is not
 *   naturally aligned.
 */
void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
{
	q->limits.alignment_offset =
		offset & (q->limits.physical_block_size - 1);
	q->limits.misaligned = 0;
}
EXPORT_SYMBOL(blk_queue_alignment_offset);

/**
 * blk_limits_io_min - set minimum request size for a device
 * @limits: the queue limits
 * @min:  smallest I/O size in bytes
 *
 * Description:
 *   Some devices have an internal block size bigger than the reported
 *   hardware sector size.  This function can be used to signal the
 *   smallest I/O the device can perform without incurring a performance
 *   penalty.
 */
void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
{
	limits->io_min = min;

	if (limits->io_min < limits->logical_block_size)
		limits->io_min = limits->logical_block_size;

	if (limits->io_min < limits->physical_block_size)
		limits->io_min = limits->physical_block_size;
}
EXPORT_SYMBOL(blk_limits_io_min);

/**
 * blk_queue_io_min - set minimum request size for the queue
 * @q:	the request queue for the device
 * @min:  smallest I/O size in bytes
 *
 * Description:
 *   Storage devices may report a granularity or preferred minimum I/O
 *   size which is the smallest request the device can perform without
 *   incurring a performance penalty.  For disk drives this is often the
 *   physical block size.  For RAID arrays it is often the stripe chunk
 *   size.  A properly aligned multiple of minimum_io_size is the
 *   preferred request size for workloads where a high number of I/O
 *   operations is desired.
 */
void blk_queue_io_min(struct request_queue *q, unsigned int min)
{
	blk_limits_io_min(&q->limits, min);
}
EXPORT_SYMBOL(blk_queue_io_min);

/**
 * blk_limits_io_opt - set optimal request size for a device
 * @limits: the queue limits
 * @opt:  smallest I/O size in bytes
 *
 * Description:
 *   Storage devices may report an optimal I/O size, which is the
 *   device's preferred unit for sustained I/O.  This is rarely reported
 *   for disk drives.  For RAID arrays it is usually the stripe width or
 *   the internal track size.  A properly aligned multiple of
 *   optimal_io_size is the preferred request size for workloads where
 *   sustained throughput is desired.
 */
void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
{
	limits->io_opt = opt;
}
EXPORT_SYMBOL(blk_limits_io_opt);

/**
 * blk_queue_io_opt - set optimal request size for the queue
 * @q:	the request queue for the device
 * @opt:  optimal request size in bytes
 *
 * Description:
 *   Storage devices may report an optimal I/O size, which is the
 *   device's preferred unit for sustained I/O.  This is rarely reported
 *   for disk drives.  For RAID arrays it is usually the stripe width or
 *   the internal track size.  A properly aligned multiple of
 *   optimal_io_size is the preferred request size for workloads where
 *   sustained throughput is desired.
 */
void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
{
	blk_limits_io_opt(&q->limits, opt);
}
EXPORT_SYMBOL(blk_queue_io_opt);

/**
 * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
 * @t:	the stacking driver (top)
 * @b:  the underlying device (bottom)
 **/
void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
{
	blk_stack_limits(&t->limits, &b->limits, 0);
}
EXPORT_SYMBOL(blk_queue_stack_limits);

/**
 * blk_stack_limits - adjust queue_limits for stacked devices
 * @t:	the stacking driver limits (top device)
 * @b:  the underlying queue limits (bottom, component device)
 * @start:  first data sector within component device
 *
 * Description:
 *    This function is used by stacking drivers like MD and DM to ensure
 *    that all component devices have compatible block sizes and
 *    alignments.  The stacking driver must provide a queue_limits
 *    struct (top) and then iteratively call the stacking function for
 *    all component (bottom) devices.  The stacking function will
 *    attempt to combine the values and ensure proper alignment.
 *
 *    Returns 0 if the top and bottom queue_limits are compatible.  The
 *    top device's block sizes and alignment offsets may be adjusted to
 *    ensure alignment with the bottom device. If no compatible sizes
 *    and alignments exist, -1 is returned and the resulting top
 *    queue_limits will have the misaligned flag set to indicate that
 *    the alignment_offset is undefined.
 */
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
		     sector_t start)
{
	unsigned int top, bottom, alignment, ret = 0;

	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);

	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
					    b->seg_boundary_mask);

	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
						 b->max_integrity_segments);

	t->max_segment_size = min_not_zero(t->max_segment_size,
					   b->max_segment_size);

	t->misaligned |= b->misaligned;

	alignment = queue_limit_alignment_offset(b, start);

	/* Bottom device has different alignment.  Check that it is
	 * compatible with the current top alignment.
	 */
	if (t->alignment_offset != alignment) {

		top = max(t->physical_block_size, t->io_min)
			+ t->alignment_offset;
		bottom = max(b->physical_block_size, b->io_min) + alignment;

		/* Verify that top and bottom intervals line up */
		if (max(top, bottom) & (min(top, bottom) - 1)) {
			t->misaligned = 1;
			ret = -1;
		}
	}

	t->logical_block_size = max(t->logical_block_size,
				    b->logical_block_size);

	t->physical_block_size = max(t->physical_block_size,
				     b->physical_block_size);

	t->io_min = max(t->io_min, b->io_min);
	t->io_opt = lcm(t->io_opt, b->io_opt);

	t->cluster &= b->cluster;
	t->discard_zeroes_data &= b->discard_zeroes_data;

	/* Physical block size a multiple of the logical block size? */
	if (t->physical_block_size & (t->logical_block_size - 1)) {
		t->physical_block_size = t->logical_block_size;
		t->misaligned = 1;
		ret = -1;
	}

	/* Minimum I/O a multiple of the physical block size? */
	if (t->io_min & (t->physical_block_size - 1)) {
		t->io_min = t->physical_block_size;
		t->misaligned = 1;
		ret = -1;
	}

	/* Optimal I/O a multiple of the physical block size? */
	if (t->io_opt & (t->physical_block_size - 1)) {
		t->io_opt = 0;
		t->misaligned = 1;
		ret = -1;
	}

	/* Find lowest common alignment_offset */
	t->alignment_offset = lcm(t->alignment_offset, alignment)
		& (max(t->physical_block_size, t->io_min) - 1);

	/* Verify that new alignment_offset is on a logical block boundary */
	if (t->alignment_offset & (t->logical_block_size - 1)) {
		t->misaligned = 1;
		ret = -1;
	}

	/* Discard alignment and granularity */
	if (b->discard_granularity) {
		alignment = queue_limit_discard_alignment(b, start);

		if (t->discard_granularity != 0 &&
		    t->discard_alignment != alignment) {
			top = t->discard_granularity + t->discard_alignment;
			bottom = b->discard_granularity + alignment;

			/* Verify that top and bottom intervals line up */
			if (max(top, bottom) & (min(top, bottom) - 1))
				t->discard_misaligned = 1;
		}

		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
						      b->max_discard_sectors);
		t->discard_granularity = max(t->discard_granularity,
					     b->discard_granularity);
		t->discard_alignment = lcm(t->discard_alignment, alignment) &
			(t->discard_granularity - 1);
	}

	return ret;
}
EXPORT_SYMBOL(blk_stack_limits);

/**
 * bdev_stack_limits - adjust queue limits for stacked drivers
 * @t:	the stacking driver limits (top device)
 * @bdev:  the component block_device (bottom)
 * @start:  first data sector within component device
 *
 * Description:
 *    Merges queue limits for a top device and a block_device.  Returns
 *    0 if alignment didn't change.  Returns -1 if adding the bottom
 *    device caused misalignment.
 */
int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
		      sector_t start)
{
	struct request_queue *bq = bdev_get_queue(bdev);

	start += get_start_sect(bdev);

	return blk_stack_limits(t, &bq->limits, start);
}
EXPORT_SYMBOL(bdev_stack_limits);

/**
 * disk_stack_limits - adjust queue limits for stacked drivers
 * @disk:  MD/DM gendisk (top)
 * @bdev:  the underlying block device (bottom)
 * @offset:  offset to beginning of data within component device
 *
 * Description:
 *    Merges the limits for a top level gendisk and a bottom level
 *    block_device.
 */
void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
		       sector_t offset)
{
	struct request_queue *t = disk->queue;

	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];

		disk_name(disk, 0, top);
		bdevname(bdev, bottom);

		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
		       top, bottom);
	}
}
EXPORT_SYMBOL(disk_stack_limits);

/**
 * blk_queue_dma_pad - set pad mask
 * @q:     the request queue for the device
 * @mask:  pad mask
 *
 * Set dma pad mask.
 *
 * Appending pad buffer to a request modifies the last entry of a
 * scatter list such that it includes the pad buffer.
 **/
void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
{
	q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_dma_pad);

/**
 * blk_queue_update_dma_pad - update pad mask
 * @q:     the request queue for the device
 * @mask:  pad mask
 *
 * Update dma pad mask.
 *
 * Appending pad buffer to a request modifies the last entry of a
 * scatter list such that it includes the pad buffer.
 **/
void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
{
	if (mask > q->dma_pad_mask)
		q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_pad);

/**
 * blk_queue_dma_drain - Set up a drain buffer for excess dma.
 * @q:  the request queue for the device
 * @dma_drain_needed: fn which returns non-zero if drain is necessary
 * @buf:	physically contiguous buffer
 * @size:	size of the buffer in bytes
 *
 * Some devices have excess DMA problems and can't simply discard (or
 * zero fill) the unwanted piece of the transfer.  They have to have a
 * real area of memory to transfer it into.  The use case for this is
 * ATAPI devices in DMA mode.  If the packet command causes a transfer
 * bigger than the transfer size some HBAs will lock up if there
 * aren't DMA elements to contain the excess transfer.  What this API
 * does is adjust the queue so that the buf is always appended
 * silently to the scatterlist.
 *
 * Note: This routine adjusts max_hw_segments to make room for appending
 * the drain buffer.  If you call blk_queue_max_segments() after calling
 * this routine, you must set the limit to one fewer than your device
 * can support otherwise there won't be room for the drain buffer.
 */
int blk_queue_dma_drain(struct request_queue *q,
			       dma_drain_needed_fn *dma_drain_needed,
			       void *buf, unsigned int size)
{
	if (queue_max_segments(q) < 2)
		return -EINVAL;
	/* make room for appending the drain */
	blk_queue_max_segments(q, queue_max_segments(q) - 1);
	q->dma_drain_needed = dma_drain_needed;
	q->dma_drain_buffer = buf;
	q->dma_drain_size = size;

	return 0;
}
EXPORT_SYMBOL_GPL(blk_queue_dma_drain);

/**
 * blk_queue_segment_boundary - set boundary rules for segment merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
{
	if (mask < PAGE_CACHE_SIZE - 1) {
		mask = PAGE_CACHE_SIZE - 1;
		printk(KERN_INFO "%s: set to minimum %lx\n",
		       __func__, mask);
	}

	q->limits.seg_boundary_mask = mask;
}
EXPORT_SYMBOL(blk_queue_segment_boundary);

/**
 * blk_queue_dma_alignment - set dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    set required memory and length alignment for direct dma transactions.
 *    this is used when building direct io requests for the queue.
 *
 **/
void blk_queue_dma_alignment(struct request_queue *q, int mask)
{
	q->dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_dma_alignment);

/**
 * blk_queue_update_dma_alignment - update dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    update required memory and length alignment for direct dma transactions.
 *    If the requested alignment is larger than the current alignment, then
 *    the current queue alignment is updated to the new value, otherwise it
 *    is left alone.  The design of this is to allow multiple objects
 *    (driver, device, transport etc) to set their respective
 *    alignments without having them interfere.
 *
 **/
void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
{
	BUG_ON(mask > PAGE_SIZE);

	if (mask > q->dma_alignment)
		q->dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_alignment);

/**
 * blk_queue_flush - configure queue's cache flush capability
 * @q:		the request queue for the device
 * @flush:	0, REQ_FLUSH or REQ_FLUSH | REQ_FUA
 *
 * Tell block layer cache flush capability of @q.  If it supports
 * flushing, REQ_FLUSH should be set.  If it supports bypassing
 * write cache for individual writes, REQ_FUA should be set.
 */
void blk_queue_flush(struct request_queue *q, unsigned int flush)
{
	WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA));

	if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA)))
		flush &= ~REQ_FUA;

	q->flush_flags = flush & (REQ_FLUSH | REQ_FUA);
}
EXPORT_SYMBOL_GPL(blk_queue_flush);

static int __init blk_settings_init(void)
{
	blk_max_low_pfn = max_low_pfn - 1;
	blk_max_pfn = max_pfn - 1;
	return 0;
}
subsys_initcall(blk_settings_init);