blk-settings.c 26.9 KB
Newer Older
1 2 3 4 5 6 7 8 9
/*
 * 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 */
10
#include <linux/gcd.h>
11
#include <linux/lcm.h>
Randy Dunlap's avatar
Randy Dunlap committed
12
#include <linux/jiffies.h>
13
#include <linux/gfp.h>
14 15 16

#include "blk.h"

17
unsigned long blk_max_low_pfn;
18
EXPORT_SYMBOL(blk_max_low_pfn);
19 20

unsigned long blk_max_pfn;
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38

/**
 * 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);

39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55
/**
 * 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);

56 57 58 59 60 61
void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
{
	q->softirq_done_fn = fn;
}
EXPORT_SYMBOL(blk_queue_softirq_done);

62 63 64 65 66 67 68 69 70 71 72 73
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);

74 75 76 77 78 79
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);

80 81
/**
 * blk_set_default_limits - reset limits to default values
82
 * @lim:  the queue_limits structure to reset
83 84
 *
 * Description:
85
 *   Returns a queue_limit struct to its default state.
86 87 88
 */
void blk_set_default_limits(struct queue_limits *lim)
{
89
	lim->max_segments = BLK_MAX_SEGMENTS;
90
	lim->max_integrity_segments = 0;
91
	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
92
	lim->virt_boundary_mask = 0;
93
	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
94
	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
95
	lim->chunk_sectors = 0;
96
	lim->max_write_same_sectors = 0;
97
	lim->max_discard_sectors = 0;
98
	lim->max_hw_discard_sectors = 0;
99 100 101
	lim->discard_granularity = 0;
	lim->discard_alignment = 0;
	lim->discard_misaligned = 0;
102
	lim->discard_zeroes_data = 0;
103
	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
104
	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
105 106 107
	lim->alignment_offset = 0;
	lim->io_opt = 0;
	lim->misaligned = 0;
108
	lim->cluster = 1;
109 110 111
}
EXPORT_SYMBOL(blk_set_default_limits);

112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
/**
 * blk_set_stacking_limits - set default limits for stacking devices
 * @lim:  the queue_limits structure to reset
 *
 * Description:
 *   Returns a queue_limit struct to its default state. Should be used
 *   by stacking drivers like DM that have no internal limits.
 */
void blk_set_stacking_limits(struct queue_limits *lim)
{
	blk_set_default_limits(lim);

	/* Inherit limits from component devices */
	lim->discard_zeroes_data = 1;
	lim->max_segments = USHRT_MAX;
	lim->max_hw_sectors = UINT_MAX;
128
	lim->max_segment_size = UINT_MAX;
129
	lim->max_sectors = UINT_MAX;
130
	lim->max_write_same_sectors = UINT_MAX;
131 132 133
}
EXPORT_SYMBOL(blk_set_stacking_limits);

134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
/**
 * 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.
 **/
156
void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
157 158 159 160 161
{
	/*
	 * set defaults
	 */
	q->nr_requests = BLKDEV_MAX_RQ;
162

163 164 165 166 167
	q->make_request_fn = mfn;
	blk_queue_dma_alignment(q, 511);
	blk_queue_congestion_threshold(q);
	q->nr_batching = BLK_BATCH_REQ;

168 169
	blk_set_default_limits(&q->limits);

170 171 172 173 174 175 176 177 178
	/*
	 * 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
179
 * @q: the request queue for the device
180
 * @max_addr: the maximum address the device can handle
181 182 183 184 185
 *
 * 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
186
 *    buffers for doing I/O to pages residing above @max_addr.
187
 **/
188
void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
189
{
190
	unsigned long b_pfn = max_addr >> PAGE_SHIFT;
191 192 193 194
	int dma = 0;

	q->bounce_gfp = GFP_NOIO;
#if BITS_PER_LONG == 64
195 196 197 198 199 200
	/*
	 * 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))
201
		dma = 1;
202
	q->limits.bounce_pfn = max(max_low_pfn, b_pfn);
203
#else
204
	if (b_pfn < blk_max_low_pfn)
205
		dma = 1;
206
	q->limits.bounce_pfn = b_pfn;
207
#endif
208 209 210
	if (dma) {
		init_emergency_isa_pool();
		q->bounce_gfp = GFP_NOIO | GFP_DMA;
211
		q->limits.bounce_pfn = b_pfn;
212 213 214 215 216
	}
}
EXPORT_SYMBOL(blk_queue_bounce_limit);

/**
217 218
 * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
 * @limits: the queue limits
219
 * @max_hw_sectors:  max hardware sectors in the usual 512b unit
220 221
 *
 * Description:
222 223
 *    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
224 225
 *    the device driver based upon the capabilities of the I/O
 *    controller.
226 227 228 229 230
 *
 *    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.
231
 **/
232
void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
233
{
234 235
	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
236
		printk(KERN_INFO "%s: set to minimum %d\n",
237
		       __func__, max_hw_sectors);
238 239
	}

240 241 242
	limits->max_hw_sectors = max_hw_sectors;
	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
				    BLK_DEF_MAX_SECTORS);
243 244 245 246 247 248 249 250 251 252 253 254 255 256
}
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);
257
}
258
EXPORT_SYMBOL(blk_queue_max_hw_sectors);
259

260 261 262 263 264 265 266 267
/**
 * blk_queue_chunk_sectors - set size of the chunk for this queue
 * @q:  the request queue for the device
 * @chunk_sectors:  chunk sectors in the usual 512b unit
 *
 * Description:
 *    If a driver doesn't want IOs to cross a given chunk size, it can set
 *    this limit and prevent merging across chunks. Note that the chunk size
268 269 270 271
 *    must currently be a power-of-2 in sectors. Also note that the block
 *    layer must accept a page worth of data at any offset. So if the
 *    crossing of chunks is a hard limitation in the driver, it must still be
 *    prepared to split single page bios.
272 273 274 275 276 277 278 279
 **/
void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
{
	BUG_ON(!is_power_of_2(chunk_sectors));
	q->limits.chunk_sectors = chunk_sectors;
}
EXPORT_SYMBOL(blk_queue_chunk_sectors);

280 281 282
/**
 * blk_queue_max_discard_sectors - set max sectors for a single discard
 * @q:  the request queue for the device
283
 * @max_discard_sectors: maximum number of sectors to discard
284 285 286 287
 **/
void blk_queue_max_discard_sectors(struct request_queue *q,
		unsigned int max_discard_sectors)
{
288
	q->limits.max_hw_discard_sectors = max_discard_sectors;
289 290 291 292
	q->limits.max_discard_sectors = max_discard_sectors;
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);

293 294 295 296 297 298 299 300 301 302 303 304
/**
 * blk_queue_max_write_same_sectors - set max sectors for a single write same
 * @q:  the request queue for the device
 * @max_write_same_sectors: maximum number of sectors to write per command
 **/
void blk_queue_max_write_same_sectors(struct request_queue *q,
				      unsigned int max_write_same_sectors)
{
	q->limits.max_write_same_sectors = max_write_same_sectors;
}
EXPORT_SYMBOL(blk_queue_max_write_same_sectors);

305
/**
306
 * blk_queue_max_segments - set max hw segments for a request for this queue
307 308 309 310 311
 * @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
312
 *    hw data segments in a request.
313
 **/
314
void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
315 316 317
{
	if (!max_segments) {
		max_segments = 1;
318 319
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_segments);
320 321
	}

322
	q->limits.max_segments = max_segments;
323
}
324
EXPORT_SYMBOL(blk_queue_max_segments);
325 326 327 328 329 330 331 332 333 334 335 336 337 338

/**
 * 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;
339 340
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_size);
341 342
	}

343
	q->limits.max_segment_size = max_size;
344 345 346 347
}
EXPORT_SYMBOL(blk_queue_max_segment_size);

/**
348
 * blk_queue_logical_block_size - set logical block size for the queue
349
 * @q:  the request queue for the device
350
 * @size:  the logical block size, in bytes
351 352
 *
 * Description:
353 354 355
 *   This should be set to the lowest possible block size that the
 *   storage device can address.  The default of 512 covers most
 *   hardware.
356
 **/
357
void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
358
{
359
	q->limits.logical_block_size = size;
360 361 362 363 364 365

	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;
366
}
367
EXPORT_SYMBOL(blk_queue_logical_block_size);
368

369 370 371 372 373 374 375 376 377 378
/**
 * 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.
 */
379
void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
380 381 382 383 384 385 386 387 388 389 390 391 392 393
{
	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
394
 * @offset: alignment offset in bytes
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
 *
 * 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);

410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
/**
 * 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);

433 434 435
/**
 * blk_queue_io_min - set minimum request size for the queue
 * @q:	the request queue for the device
436
 * @min:  smallest I/O size in bytes
437 438
 *
 * Description:
439 440 441 442 443 444 445
 *   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.
446 447 448
 */
void blk_queue_io_min(struct request_queue *q, unsigned int min)
{
449
	blk_limits_io_min(&q->limits, min);
450 451 452
}
EXPORT_SYMBOL(blk_queue_io_min);

453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
/**
 * 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);

472 473 474
/**
 * blk_queue_io_opt - set optimal request size for the queue
 * @q:	the request queue for the device
475
 * @opt:  optimal request size in bytes
476 477
 *
 * Description:
478 479 480 481 482 483
 *   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.
484 485 486
 */
void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
{
487
	blk_limits_io_opt(&q->limits, opt);
488 489 490
}
EXPORT_SYMBOL(blk_queue_io_opt);

491 492 493 494 495 496 497
/**
 * 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)
{
498
	blk_stack_limits(&t->limits, &b->limits, 0);
499 500 501
}
EXPORT_SYMBOL(blk_queue_stack_limits);

502 503
/**
 * blk_stack_limits - adjust queue_limits for stacked devices
504 505
 * @t:	the stacking driver limits (top device)
 * @b:  the underlying queue limits (bottom, component device)
506
 * @start:  first data sector within component device
507 508
 *
 * Description:
509 510 511 512 513 514 515 516 517 518 519 520 521
 *    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.
522 523
 */
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
524
		     sector_t start)
525
{
526
	unsigned int top, bottom, alignment, ret = 0;
527

528 529
	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);
530 531
	t->max_write_same_sectors = min(t->max_write_same_sectors,
					b->max_write_same_sectors);
532
	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
533 534 535

	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
					    b->seg_boundary_mask);
536 537
	t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
					    b->virt_boundary_mask);
538

539
	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
540 541
	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
						 b->max_integrity_segments);
542 543 544 545

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

546 547
	t->misaligned |= b->misaligned;

548
	alignment = queue_limit_alignment_offset(b, start);
549

550 551 552
	/* Bottom device has different alignment.  Check that it is
	 * compatible with the current top alignment.
	 */
553 554 555 556
	if (t->alignment_offset != alignment) {

		top = max(t->physical_block_size, t->io_min)
			+ t->alignment_offset;
557
		bottom = max(b->physical_block_size, b->io_min) + alignment;
558

559
		/* Verify that top and bottom intervals line up */
560
		if (max(top, bottom) % min(top, bottom)) {
561
			t->misaligned = 1;
562 563
			ret = -1;
		}
564 565
	}

566 567 568 569 570 571 572
	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);
573
	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
574

575
	t->cluster &= b->cluster;
576
	t->discard_zeroes_data &= b->discard_zeroes_data;
577

578
	/* Physical block size a multiple of the logical block size? */
579 580
	if (t->physical_block_size & (t->logical_block_size - 1)) {
		t->physical_block_size = t->logical_block_size;
581
		t->misaligned = 1;
582
		ret = -1;
583 584
	}

585
	/* Minimum I/O a multiple of the physical block size? */
586 587 588
	if (t->io_min & (t->physical_block_size - 1)) {
		t->io_min = t->physical_block_size;
		t->misaligned = 1;
589
		ret = -1;
590 591
	}

592
	/* Optimal I/O a multiple of the physical block size? */
593 594 595
	if (t->io_opt & (t->physical_block_size - 1)) {
		t->io_opt = 0;
		t->misaligned = 1;
596
		ret = -1;
597
	}
598

599 600 601 602
	t->raid_partial_stripes_expensive =
		max(t->raid_partial_stripes_expensive,
		    b->raid_partial_stripes_expensive);

603
	/* Find lowest common alignment_offset */
604
	t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
605
		% max(t->physical_block_size, t->io_min);
606

607
	/* Verify that new alignment_offset is on a logical block boundary */
608
	if (t->alignment_offset & (t->logical_block_size - 1)) {
609
		t->misaligned = 1;
610 611
		ret = -1;
	}
612

613 614
	/* Discard alignment and granularity */
	if (b->discard_granularity) {
615
		alignment = queue_limit_discard_alignment(b, start);
616 617 618 619 620

		if (t->discard_granularity != 0 &&
		    t->discard_alignment != alignment) {
			top = t->discard_granularity + t->discard_alignment;
			bottom = b->discard_granularity + alignment;
621

622
			/* Verify that top and bottom intervals line up */
623
			if ((max(top, bottom) % min(top, bottom)) != 0)
624 625 626
				t->discard_misaligned = 1;
		}

627 628
		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
						      b->max_discard_sectors);
629 630
		t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
							 b->max_hw_discard_sectors);
631 632
		t->discard_granularity = max(t->discard_granularity,
					     b->discard_granularity);
633
		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
634
			t->discard_granularity;
635
	}
636

637
	return ret;
638
}
639
EXPORT_SYMBOL(blk_stack_limits);
640

641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658
/**
 * 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);

659
	return blk_stack_limits(t, &bq->limits, start);
660 661 662
}
EXPORT_SYMBOL(bdev_stack_limits);

663 664
/**
 * disk_stack_limits - adjust queue limits for stacked drivers
665
 * @disk:  MD/DM gendisk (top)
666 667 668 669
 * @bdev:  the underlying block device (bottom)
 * @offset:  offset to beginning of data within component device
 *
 * Description:
670 671
 *    Merges the limits for a top level gendisk and a bottom level
 *    block_device.
672 673 674 675 676 677
 */
void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
		       sector_t offset)
{
	struct request_queue *t = disk->queue;

678
	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
679 680 681 682 683 684 685 686 687 688 689
		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);

690 691 692 693 694
/**
 * blk_queue_dma_pad - set pad mask
 * @q:     the request queue for the device
 * @mask:  pad mask
 *
695
 * Set dma pad mask.
696
 *
697 698
 * Appending pad buffer to a request modifies the last entry of a
 * scatter list such that it includes the pad buffer.
699 700 701 702 703 704 705
 **/
void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
{
	q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_dma_pad);

706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
/**
 * 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);

723 724 725
/**
 * blk_queue_dma_drain - Set up a drain buffer for excess dma.
 * @q:  the request queue for the device
726
 * @dma_drain_needed: fn which returns non-zero if drain is necessary
727 728 729 730 731 732 733 734 735 736 737 738
 * @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.
 *
739 740 741 742
 * 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.
743
 */
744
int blk_queue_dma_drain(struct request_queue *q,
745 746
			       dma_drain_needed_fn *dma_drain_needed,
			       void *buf, unsigned int size)
747
{
748
	if (queue_max_segments(q) < 2)
749 750
		return -EINVAL;
	/* make room for appending the drain */
751
	blk_queue_max_segments(q, queue_max_segments(q) - 1);
752
	q->dma_drain_needed = dma_drain_needed;
753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768
	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;
769 770
		printk(KERN_INFO "%s: set to minimum %lx\n",
		       __func__, mask);
771 772
	}

773
	q->limits.seg_boundary_mask = mask;
774 775 776
}
EXPORT_SYMBOL(blk_queue_segment_boundary);

777 778 779 780 781 782 783 784 785 786 787
/**
 * blk_queue_virt_boundary - set boundary rules for bio merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
{
	q->limits.virt_boundary_mask = mask;
}
EXPORT_SYMBOL(blk_queue_virt_boundary);

788 789 790 791 792 793
/**
 * blk_queue_dma_alignment - set dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
794
 *    set required memory and length alignment for direct dma transactions.
Alan Cox's avatar
Alan Cox committed
795
 *    this is used when building direct io requests for the queue.
796 797 798 799 800 801 802 803 804 805 806 807 808 809
 *
 **/
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:
810
 *    update required memory and length alignment for direct dma transactions.
811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826
 *    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);

827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846
/**
 * 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);

847 848 849 850 851 852
void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
{
	q->flush_not_queueable = !queueable;
}
EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);

853
static int __init blk_settings_init(void)
854 855 856 857 858 859
{
	blk_max_low_pfn = max_low_pfn - 1;
	blk_max_pfn = max_pfn - 1;
	return 0;
}
subsys_initcall(blk_settings_init);