scatterlist.c 12.8 KB
Newer Older
1 2 3 4 5 6 7 8 9
/*
 * Copyright (C) 2007 Jens Axboe <jens.axboe@oracle.com>
 *
 * Scatterlist handling helpers.
 *
 * This source code is licensed under the GNU General Public License,
 * Version 2. See the file COPYING for more details.
 */
#include <linux/module.h>
10
#include <linux/slab.h>
11
#include <linux/scatterlist.h>
12
#include <linux/highmem.h>
13
#include <linux/kmemleak.h>
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

/**
 * sg_next - return the next scatterlist entry in a list
 * @sg:		The current sg entry
 *
 * Description:
 *   Usually the next entry will be @sg@ + 1, but if this sg element is part
 *   of a chained scatterlist, it could jump to the start of a new
 *   scatterlist array.
 *
 **/
struct scatterlist *sg_next(struct scatterlist *sg)
{
#ifdef CONFIG_DEBUG_SG
	BUG_ON(sg->sg_magic != SG_MAGIC);
#endif
	if (sg_is_last(sg))
		return NULL;

	sg++;
	if (unlikely(sg_is_chain(sg)))
		sg = sg_chain_ptr(sg);

	return sg;
}
EXPORT_SYMBOL(sg_next);

/**
 * sg_last - return the last scatterlist entry in a list
 * @sgl:	First entry in the scatterlist
 * @nents:	Number of entries in the scatterlist
 *
 * Description:
 *   Should only be used casually, it (currently) scans the entire list
 *   to get the last entry.
 *
 *   Note that the @sgl@ pointer passed in need not be the first one,
 *   the important bit is that @nents@ denotes the number of entries that
 *   exist from @sgl@.
 *
 **/
struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
{
#ifndef ARCH_HAS_SG_CHAIN
	struct scatterlist *ret = &sgl[nents - 1];
#else
	struct scatterlist *sg, *ret = NULL;
	unsigned int i;

	for_each_sg(sgl, sg, nents, i)
		ret = sg;

#endif
#ifdef CONFIG_DEBUG_SG
	BUG_ON(sgl[0].sg_magic != SG_MAGIC);
	BUG_ON(!sg_is_last(ret));
#endif
	return ret;
}
EXPORT_SYMBOL(sg_last);

/**
 * sg_init_table - Initialize SG table
 * @sgl:	   The SG table
 * @nents:	   Number of entries in table
 *
 * Notes:
 *   If this is part of a chained sg table, sg_mark_end() should be
 *   used only on the last table part.
 *
 **/
void sg_init_table(struct scatterlist *sgl, unsigned int nents)
{
	memset(sgl, 0, sizeof(*sgl) * nents);
#ifdef CONFIG_DEBUG_SG
	{
		unsigned int i;
		for (i = 0; i < nents; i++)
			sgl[i].sg_magic = SG_MAGIC;
	}
#endif
	sg_mark_end(&sgl[nents - 1]);
}
EXPORT_SYMBOL(sg_init_table);

/**
 * sg_init_one - Initialize a single entry sg list
 * @sg:		 SG entry
 * @buf:	 Virtual address for IO
 * @buflen:	 IO length
 *
 **/
void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
{
	sg_init_table(sg, 1);
	sg_set_buf(sg, buf, buflen);
}
EXPORT_SYMBOL(sg_init_one);

/*
 * The default behaviour of sg_alloc_table() is to use these kmalloc/kfree
 * helpers.
 */
static struct scatterlist *sg_kmalloc(unsigned int nents, gfp_t gfp_mask)
{
119 120 121 122 123 124 125 126 127 128 129 130 131 132
	if (nents == SG_MAX_SINGLE_ALLOC) {
		/*
		 * Kmemleak doesn't track page allocations as they are not
		 * commonly used (in a raw form) for kernel data structures.
		 * As we chain together a list of pages and then a normal
		 * kmalloc (tracked by kmemleak), in order to for that last
		 * allocation not to become decoupled (and thus a
		 * false-positive) we need to inform kmemleak of all the
		 * intermediate allocations.
		 */
		void *ptr = (void *) __get_free_page(gfp_mask);
		kmemleak_alloc(ptr, PAGE_SIZE, 1, gfp_mask);
		return ptr;
	} else
133 134 135 136 137
		return kmalloc(nents * sizeof(struct scatterlist), gfp_mask);
}

static void sg_kfree(struct scatterlist *sg, unsigned int nents)
{
138 139
	if (nents == SG_MAX_SINGLE_ALLOC) {
		kmemleak_free(sg);
140
		free_page((unsigned long) sg);
141
	} else
142 143 144 145 146 147
		kfree(sg);
}

/**
 * __sg_free_table - Free a previously mapped sg table
 * @table:	The sg table header to use
148
 * @max_ents:	The maximum number of entries per single scatterlist
149 150 151
 * @free_fn:	Free function
 *
 *  Description:
152 153 154
 *    Free an sg table previously allocated and setup with
 *    __sg_alloc_table().  The @max_ents value must be identical to
 *    that previously used with __sg_alloc_table().
155 156
 *
 **/
157 158
void __sg_free_table(struct sg_table *table, unsigned int max_ents,
		     sg_free_fn *free_fn)
159 160 161 162 163 164 165 166 167 168 169 170
{
	struct scatterlist *sgl, *next;

	if (unlikely(!table->sgl))
		return;

	sgl = table->sgl;
	while (table->orig_nents) {
		unsigned int alloc_size = table->orig_nents;
		unsigned int sg_size;

		/*
171
		 * If we have more than max_ents segments left,
172 173 174 175
		 * then assign 'next' to the sg table after the current one.
		 * sg_size is then one less than alloc size, since the last
		 * element is the chain pointer.
		 */
176 177 178
		if (alloc_size > max_ents) {
			next = sg_chain_ptr(&sgl[max_ents - 1]);
			alloc_size = max_ents;
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
			sg_size = alloc_size - 1;
		} else {
			sg_size = alloc_size;
			next = NULL;
		}

		table->orig_nents -= sg_size;
		free_fn(sgl, alloc_size);
		sgl = next;
	}

	table->sgl = NULL;
}
EXPORT_SYMBOL(__sg_free_table);

/**
 * sg_free_table - Free a previously allocated sg table
 * @table:	The mapped sg table header
 *
 **/
void sg_free_table(struct sg_table *table)
{
201
	__sg_free_table(table, SG_MAX_SINGLE_ALLOC, sg_kfree);
202 203 204 205 206 207 208
}
EXPORT_SYMBOL(sg_free_table);

/**
 * __sg_alloc_table - Allocate and initialize an sg table with given allocator
 * @table:	The sg table header to use
 * @nents:	Number of entries in sg list
209
 * @max_ents:	The maximum number of entries the allocator returns per call
210 211 212
 * @gfp_mask:	GFP allocation mask
 * @alloc_fn:	Allocator to use
 *
213 214 215 216 217 218
 * Description:
 *   This function returns a @table @nents long. The allocator is
 *   defined to return scatterlist chunks of maximum size @max_ents.
 *   Thus if @nents is bigger than @max_ents, the scatterlists will be
 *   chained in units of @max_ents.
 *
219 220 221 222 223
 * Notes:
 *   If this function returns non-0 (eg failure), the caller must call
 *   __sg_free_table() to cleanup any leftover allocations.
 *
 **/
224 225
int __sg_alloc_table(struct sg_table *table, unsigned int nents,
		     unsigned int max_ents, gfp_t gfp_mask,
226 227 228 229 230 231
		     sg_alloc_fn *alloc_fn)
{
	struct scatterlist *sg, *prv;
	unsigned int left;

#ifndef ARCH_HAS_SG_CHAIN
232
	BUG_ON(nents > max_ents);
233 234 235 236 237 238 239 240 241
#endif

	memset(table, 0, sizeof(*table));

	left = nents;
	prv = NULL;
	do {
		unsigned int sg_size, alloc_size = left;

242 243
		if (alloc_size > max_ents) {
			alloc_size = max_ents;
244 245 246 247 248 249 250
			sg_size = alloc_size - 1;
		} else
			sg_size = alloc_size;

		left -= sg_size;

		sg = alloc_fn(alloc_size, gfp_mask);
251 252 253 254 255 256 257 258 259 260 261 262
		if (unlikely(!sg)) {
			/*
			 * Adjust entry count to reflect that the last
			 * entry of the previous table won't be used for
			 * linkage.  Without this, sg_kfree() may get
			 * confused.
			 */
			if (prv)
				table->nents = ++table->orig_nents;

 			return -ENOMEM;
		}
263 264 265 266 267 268 269 270 271

		sg_init_table(sg, alloc_size);
		table->nents = table->orig_nents += sg_size;

		/*
		 * If this is the first mapping, assign the sg table header.
		 * If this is not the first mapping, chain previous part.
		 */
		if (prv)
272
			sg_chain(prv, max_ents, sg);
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
		else
			table->sgl = sg;

		/*
		 * If no more entries after this one, mark the end
		 */
		if (!left)
			sg_mark_end(&sg[sg_size - 1]);

		/*
		 * only really needed for mempool backed sg allocations (like
		 * SCSI), a possible improvement here would be to pass the
		 * table pointer into the allocator and let that clear these
		 * flags
		 */
		gfp_mask &= ~__GFP_WAIT;
		gfp_mask |= __GFP_HIGH;
		prv = sg;
	} while (left);

	return 0;
}
EXPORT_SYMBOL(__sg_alloc_table);

/**
 * sg_alloc_table - Allocate and initialize an sg table
 * @table:	The sg table header to use
 * @nents:	Number of entries in sg list
 * @gfp_mask:	GFP allocation mask
 *
 *  Description:
 *    Allocate and initialize an sg table. If @nents@ is larger than
 *    SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
 *
 **/
int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
{
	int ret;

312 313
	ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC,
			       gfp_mask, sg_kmalloc);
314
	if (unlikely(ret))
315
		__sg_free_table(table, SG_MAX_SINGLE_ALLOC, sg_kfree);
316 317 318 319

	return ret;
}
EXPORT_SYMBOL(sg_alloc_table);
320

T
Tejun Heo 已提交
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
/**
 * sg_miter_start - start mapping iteration over a sg list
 * @miter: sg mapping iter to be started
 * @sgl: sg list to iterate over
 * @nents: number of sg entries
 *
 * Description:
 *   Starts mapping iterator @miter.
 *
 * Context:
 *   Don't care.
 */
void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl,
		    unsigned int nents, unsigned int flags)
{
	memset(miter, 0, sizeof(struct sg_mapping_iter));

	miter->__sg = sgl;
	miter->__nents = nents;
	miter->__offset = 0;
341
	WARN_ON(!(flags & (SG_MITER_TO_SG | SG_MITER_FROM_SG)));
T
Tejun Heo 已提交
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
	miter->__flags = flags;
}
EXPORT_SYMBOL(sg_miter_start);

/**
 * sg_miter_next - proceed mapping iterator to the next mapping
 * @miter: sg mapping iter to proceed
 *
 * Description:
 *   Proceeds @miter@ to the next mapping.  @miter@ should have been
 *   started using sg_miter_start().  On successful return,
 *   @miter@->page, @miter@->addr and @miter@->length point to the
 *   current mapping.
 *
 * Context:
 *   IRQ disabled if SG_MITER_ATOMIC.  IRQ must stay disabled till
 *   @miter@ is stopped.  May sleep if !SG_MITER_ATOMIC.
 *
 * Returns:
 *   true if @miter contains the next mapping.  false if end of sg
 *   list is reached.
 */
bool sg_miter_next(struct sg_mapping_iter *miter)
{
	unsigned int off, len;

	/* check for end and drop resources from the last iteration */
	if (!miter->__nents)
		return false;

	sg_miter_stop(miter);

	/* get to the next sg if necessary.  __offset is adjusted by stop */
375 376 377 378 379 380
	while (miter->__offset == miter->__sg->length) {
		if (--miter->__nents) {
			miter->__sg = sg_next(miter->__sg);
			miter->__offset = 0;
		} else
			return false;
T
Tejun Heo 已提交
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
	}

	/* map the next page */
	off = miter->__sg->offset + miter->__offset;
	len = miter->__sg->length - miter->__offset;

	miter->page = nth_page(sg_page(miter->__sg), off >> PAGE_SHIFT);
	off &= ~PAGE_MASK;
	miter->length = min_t(unsigned int, len, PAGE_SIZE - off);
	miter->consumed = miter->length;

	if (miter->__flags & SG_MITER_ATOMIC)
		miter->addr = kmap_atomic(miter->page, KM_BIO_SRC_IRQ) + off;
	else
		miter->addr = kmap(miter->page) + off;

	return true;
}
EXPORT_SYMBOL(sg_miter_next);

/**
 * sg_miter_stop - stop mapping iteration
 * @miter: sg mapping iter to be stopped
 *
 * Description:
 *   Stops mapping iterator @miter.  @miter should have been started
 *   started using sg_miter_start().  A stopped iteration can be
 *   resumed by calling sg_miter_next() on it.  This is useful when
 *   resources (kmap) need to be released during iteration.
 *
 * Context:
 *   IRQ disabled if the SG_MITER_ATOMIC is set.  Don't care otherwise.
 */
void sg_miter_stop(struct sg_mapping_iter *miter)
{
	WARN_ON(miter->consumed > miter->length);

	/* drop resources from the last iteration */
	if (miter->addr) {
		miter->__offset += miter->consumed;

422 423 424
		if (miter->__flags & SG_MITER_TO_SG)
			flush_kernel_dcache_page(miter->page);

T
Tejun Heo 已提交
425 426 427 428
		if (miter->__flags & SG_MITER_ATOMIC) {
			WARN_ON(!irqs_disabled());
			kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
		} else
429
			kunmap(miter->page);
T
Tejun Heo 已提交
430 431 432 433 434 435 436 437 438

		miter->page = NULL;
		miter->addr = NULL;
		miter->length = 0;
		miter->consumed = 0;
	}
}
EXPORT_SYMBOL(sg_miter_stop);

439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
/**
 * sg_copy_buffer - Copy data between a linear buffer and an SG list
 * @sgl:		 The SG list
 * @nents:		 Number of SG entries
 * @buf:		 Where to copy from
 * @buflen:		 The number of bytes to copy
 * @to_buffer: 		 transfer direction (non zero == from an sg list to a
 * 			 buffer, 0 == from a buffer to an sg list
 *
 * Returns the number of copied bytes.
 *
 **/
static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
			     void *buf, size_t buflen, int to_buffer)
{
T
Tejun Heo 已提交
454 455
	unsigned int offset = 0;
	struct sg_mapping_iter miter;
456
	unsigned long flags;
457 458 459 460 461 462
	unsigned int sg_flags = SG_MITER_ATOMIC;

	if (to_buffer)
		sg_flags |= SG_MITER_FROM_SG;
	else
		sg_flags |= SG_MITER_TO_SG;
T
Tejun Heo 已提交
463

464
	sg_miter_start(&miter, sgl, nents, sg_flags);
T
Tejun Heo 已提交
465

466 467
	local_irq_save(flags);

T
Tejun Heo 已提交
468 469 470 471 472 473 474
	while (sg_miter_next(&miter) && offset < buflen) {
		unsigned int len;

		len = min(miter.length, buflen - offset);

		if (to_buffer)
			memcpy(buf + offset, miter.addr, len);
475
		else
T
Tejun Heo 已提交
476
			memcpy(miter.addr, buf + offset, len);
477

T
Tejun Heo 已提交
478
		offset += len;
479 480
	}

T
Tejun Heo 已提交
481 482
	sg_miter_stop(&miter);

483
	local_irq_restore(flags);
T
Tejun Heo 已提交
484
	return offset;
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
}

/**
 * sg_copy_from_buffer - Copy from a linear buffer to an SG list
 * @sgl:		 The SG list
 * @nents:		 Number of SG entries
 * @buf:		 Where to copy from
 * @buflen:		 The number of bytes to copy
 *
 * Returns the number of copied bytes.
 *
 **/
size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents,
			   void *buf, size_t buflen)
{
	return sg_copy_buffer(sgl, nents, buf, buflen, 0);
}
EXPORT_SYMBOL(sg_copy_from_buffer);

/**
 * sg_copy_to_buffer - Copy from an SG list to a linear buffer
 * @sgl:		 The SG list
 * @nents:		 Number of SG entries
 * @buf:		 Where to copy to
 * @buflen:		 The number of bytes to copy
 *
 * Returns the number of copied bytes.
 *
 **/
size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
			 void *buf, size_t buflen)
{
	return sg_copy_buffer(sgl, nents, buf, buflen, 1);
}
EXPORT_SYMBOL(sg_copy_to_buffer);