memblock.c 26.5 KB
Newer Older
Y
Yinghai Lu 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 * Procedures for maintaining information about logical memory blocks.
 *
 * Peter Bergner, IBM Corp.	June 2001.
 * Copyright (C) 2001 Peter Bergner.
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/kernel.h>
14
#include <linux/slab.h>
Y
Yinghai Lu 已提交
15 16
#include <linux/init.h>
#include <linux/bitops.h>
17
#include <linux/poison.h>
18
#include <linux/pfn.h>
19 20
#include <linux/debugfs.h>
#include <linux/seq_file.h>
Y
Yinghai Lu 已提交
21 22
#include <linux/memblock.h>

T
Tejun Heo 已提交
23 24 25 26 27 28 29 30 31 32 33 34 35 36
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;

struct memblock memblock __initdata_memblock = {
	.memory.regions		= memblock_memory_init_regions,
	.memory.cnt		= 1,	/* empty dummy entry */
	.memory.max		= INIT_MEMBLOCK_REGIONS,

	.reserved.regions	= memblock_reserved_init_regions,
	.reserved.cnt		= 1,	/* empty dummy entry */
	.reserved.max		= INIT_MEMBLOCK_REGIONS,

	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
};
Y
Yinghai Lu 已提交
37

38 39
int memblock_debug __initdata_memblock;
int memblock_can_resize __initdata_memblock;
Y
Yinghai Lu 已提交
40

41 42 43 44 45 46 47 48 49 50 51
/* inline so we don't get a warning when pr_debug is compiled out */
static inline const char *memblock_type_name(struct memblock_type *type)
{
	if (type == &memblock.memory)
		return "memory";
	else if (type == &memblock.reserved)
		return "reserved";
	else
		return "unknown";
}

52 53 54 55 56 57
/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */
static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
{
	return *size = min(*size, (phys_addr_t)ULLONG_MAX - base);
}

58 59 60
/*
 * Address comparison utilities
 */
61
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
62
				       phys_addr_t base2, phys_addr_t size2)
Y
Yinghai Lu 已提交
63 64 65 66
{
	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}

67 68
static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
					phys_addr_t base, phys_addr_t size)
69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
{
	unsigned long i;

	for (i = 0; i < type->cnt; i++) {
		phys_addr_t rgnbase = type->regions[i].base;
		phys_addr_t rgnsize = type->regions[i].size;
		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
			break;
	}

	return (i < type->cnt) ? i : -1;
}

/*
 * Find, allocate, deallocate or reserve unreserved regions. All allocations
 * are top-down.
 */

87
static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_addr_t end,
88 89 90 91 92
					  phys_addr_t size, phys_addr_t align)
{
	phys_addr_t base, res_base;
	long j;

93 94
	/* In case, huge size is requested */
	if (end < size)
T
Tejun Heo 已提交
95
		return 0;
96

97
	base = round_down(end - size, align);
98

99 100 101 102 103 104
	/* Prevent allocations returning 0 as it's also used to
	 * indicate an allocation failure
	 */
	if (start == 0)
		start = PAGE_SIZE;

105 106 107 108 109 110 111
	while (start <= base) {
		j = memblock_overlaps_region(&memblock.reserved, base, size);
		if (j < 0)
			return base;
		res_base = memblock.reserved.regions[j].base;
		if (res_base < size)
			break;
112
		base = round_down(res_base - size, align);
113 114
	}

T
Tejun Heo 已提交
115
	return 0;
116 117
}

118 119 120 121 122
/*
 * Find a free area with specified alignment in a specific range.
 */
phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end,
					phys_addr_t size, phys_addr_t align)
123 124 125 126 127 128
{
	long i;

	BUG_ON(0 == size);

	/* Pump up max_addr */
129 130
	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
		end = memblock.current_limit;
131 132 133 134 135 136 137 138

	/* We do a top-down search, this tends to limit memory
	 * fragmentation by keeping early boot allocs near the
	 * top of memory
	 */
	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
		phys_addr_t memblockbase = memblock.memory.regions[i].base;
		phys_addr_t memblocksize = memblock.memory.regions[i].size;
139
		phys_addr_t bottom, top, found;
140 141 142

		if (memblocksize < size)
			continue;
143 144 145 146 147 148 149
		if ((memblockbase + memblocksize) <= start)
			break;
		bottom = max(memblockbase, start);
		top = min(memblockbase + memblocksize, end);
		if (bottom >= top)
			continue;
		found = memblock_find_region(bottom, top, size, align);
T
Tejun Heo 已提交
150
		if (found)
151
			return found;
152
	}
T
Tejun Heo 已提交
153
	return 0;
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
/*
 * Free memblock.reserved.regions
 */
int __init_memblock memblock_free_reserved_regions(void)
{
	if (memblock.reserved.regions == memblock_reserved_init_regions)
		return 0;

	return memblock_free(__pa(memblock.reserved.regions),
		 sizeof(struct memblock_region) * memblock.reserved.max);
}

/*
 * Reserve memblock.reserved.regions
 */
int __init_memblock memblock_reserve_reserved_regions(void)
{
	if (memblock.reserved.regions == memblock_reserved_init_regions)
		return 0;

	return memblock_reserve(__pa(memblock.reserved.regions),
		 sizeof(struct memblock_region) * memblock.reserved.max);
}

180
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
Y
Yinghai Lu 已提交
181
{
T
Tejun Heo 已提交
182 183
	memmove(&type->regions[r], &type->regions[r + 1],
		(type->cnt - (r + 1)) * sizeof(type->regions[r]));
184
	type->cnt--;
Y
Yinghai Lu 已提交
185

186 187 188 189 190
	/* Special case for empty arrays */
	if (type->cnt == 0) {
		type->cnt = 1;
		type->regions[0].base = 0;
		type->regions[0].size = 0;
T
Tejun Heo 已提交
191
		memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
192
	}
Y
Yinghai Lu 已提交
193 194
}

195
static int __init_memblock memblock_double_array(struct memblock_type *type)
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
{
	struct memblock_region *new_array, *old_array;
	phys_addr_t old_size, new_size, addr;
	int use_slab = slab_is_available();

	/* We don't allow resizing until we know about the reserved regions
	 * of memory that aren't suitable for allocation
	 */
	if (!memblock_can_resize)
		return -1;

	/* Calculate new doubled size */
	old_size = type->max * sizeof(struct memblock_region);
	new_size = old_size << 1;

	/* Try to find some space for it.
	 *
	 * WARNING: We assume that either slab_is_available() and we use it or
	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
	 * when bootmem is currently active (unless bootmem itself is implemented
	 * on top of MEMBLOCK which isn't the case yet)
	 *
	 * This should however not be an issue for now, as we currently only
	 * call into MEMBLOCK while it's still active, or much later when slab is
	 * active for memory hotplug operations
	 */
	if (use_slab) {
		new_array = kmalloc(new_size, GFP_KERNEL);
T
Tejun Heo 已提交
224
		addr = new_array ? __pa(new_array) : 0;
225
	} else
226
		addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
T
Tejun Heo 已提交
227
	if (!addr) {
228 229 230 231 232 233
		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
		       memblock_type_name(type), type->max, type->max * 2);
		return -1;
	}
	new_array = __va(addr);

234 235 236
	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);

237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
	/* Found space, we now need to move the array over before
	 * we add the reserved region since it may be our reserved
	 * array itself that is full.
	 */
	memcpy(new_array, type->regions, old_size);
	memset(new_array + type->max, 0, old_size);
	old_array = type->regions;
	type->regions = new_array;
	type->max <<= 1;

	/* If we use SLAB that's it, we are done */
	if (use_slab)
		return 0;

	/* Add the new reserved region now. Should not fail ! */
252
	BUG_ON(memblock_reserve(addr, new_size));
253 254 255 256 257 258 259 260 261 262 263 264 265

	/* If the array wasn't our static init one, then free it. We only do
	 * that before SLAB is available as later on, we don't know whether
	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
	 * anyways
	 */
	if (old_array != memblock_memory_init_regions &&
	    old_array != memblock_reserved_init_regions)
		memblock_free(__pa(old_array), old_size);

	return 0;
}

266 267 268 269 270 271 272
/**
 * memblock_merge_regions - merge neighboring compatible regions
 * @type: memblock type to scan
 *
 * Scan @type and merge neighboring compatible regions.
 */
static void __init_memblock memblock_merge_regions(struct memblock_type *type)
Y
Yinghai Lu 已提交
273
{
274
	int i = 0;
Y
Yinghai Lu 已提交
275

276 277 278 279
	/* cnt never goes below 1 */
	while (i < type->cnt - 1) {
		struct memblock_region *this = &type->regions[i];
		struct memblock_region *next = &type->regions[i + 1];
Y
Yinghai Lu 已提交
280

T
Tejun Heo 已提交
281 282 283
		if (this->base + this->size != next->base ||
		    memblock_get_region_node(this) !=
		    memblock_get_region_node(next)) {
284 285 286
			BUG_ON(this->base + this->size > next->base);
			i++;
			continue;
287 288
		}

289 290 291
		this->size += next->size;
		memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next));
		type->cnt--;
Y
Yinghai Lu 已提交
292
	}
293
}
Y
Yinghai Lu 已提交
294

295 296 297 298 299 300 301 302 303 304 305 306
/**
 * memblock_insert_region - insert new memblock region
 * @type: memblock type to insert into
 * @idx: index for the insertion point
 * @base: base address of the new region
 * @size: size of the new region
 *
 * Insert new memblock region [@base,@base+@size) into @type at @idx.
 * @type must already have extra room to accomodate the new region.
 */
static void __init_memblock memblock_insert_region(struct memblock_type *type,
						   int idx, phys_addr_t base,
T
Tejun Heo 已提交
307
						   phys_addr_t size, int nid)
308 309 310 311 312 313 314
{
	struct memblock_region *rgn = &type->regions[idx];

	BUG_ON(type->cnt >= type->max);
	memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
	rgn->base = base;
	rgn->size = size;
T
Tejun Heo 已提交
315
	memblock_set_region_node(rgn, nid);
316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332
	type->cnt++;
}

/**
 * memblock_add_region - add new memblock region
 * @type: memblock type to add new region into
 * @base: base address of the new region
 * @size: size of the new region
 *
 * Add new memblock region [@base,@base+@size) into @type.  The new region
 * is allowed to overlap with existing ones - overlaps don't affect already
 * existing regions.  @type is guaranteed to be minimal (all neighbouring
 * compatible regions are merged) after the addition.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
333 334
static int __init_memblock memblock_add_region(struct memblock_type *type,
					       phys_addr_t base, phys_addr_t size)
335 336
{
	bool insert = false;
337 338
	phys_addr_t obase = base;
	phys_addr_t end = base + memblock_cap_size(base, &size);
339 340 341 342 343
	int i, nr_new;

	/* special case for empty array */
	if (type->regions[0].size == 0) {
		WARN_ON(type->cnt != 1);
344 345
		type->regions[0].base = base;
		type->regions[0].size = size;
T
Tejun Heo 已提交
346
		memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
347
		return 0;
Y
Yinghai Lu 已提交
348
	}
349 350 351 352 353
repeat:
	/*
	 * The following is executed twice.  Once with %false @insert and
	 * then with %true.  The first counts the number of regions needed
	 * to accomodate the new area.  The second actually inserts them.
354
	 */
355 356
	base = obase;
	nr_new = 0;
Y
Yinghai Lu 已提交
357

358 359 360 361 362 363
	for (i = 0; i < type->cnt; i++) {
		struct memblock_region *rgn = &type->regions[i];
		phys_addr_t rbase = rgn->base;
		phys_addr_t rend = rbase + rgn->size;

		if (rbase >= end)
Y
Yinghai Lu 已提交
364
			break;
365 366 367 368 369 370 371 372 373 374
		if (rend <= base)
			continue;
		/*
		 * @rgn overlaps.  If it separates the lower part of new
		 * area, insert that portion.
		 */
		if (rbase > base) {
			nr_new++;
			if (insert)
				memblock_insert_region(type, i++, base,
T
Tejun Heo 已提交
375
						rbase - base, MAX_NUMNODES);
Y
Yinghai Lu 已提交
376
		}
377 378
		/* area below @rend is dealt with, forget about it */
		base = min(rend, end);
Y
Yinghai Lu 已提交
379
	}
380 381 382 383 384

	/* insert the remaining portion */
	if (base < end) {
		nr_new++;
		if (insert)
T
Tejun Heo 已提交
385 386
			memblock_insert_region(type, i, base, end - base,
					       MAX_NUMNODES);
Y
Yinghai Lu 已提交
387 388
	}

389 390 391
	/*
	 * If this was the first round, resize array and repeat for actual
	 * insertions; otherwise, merge and return.
392
	 */
393 394 395 396 397 398 399 400 401
	if (!insert) {
		while (type->cnt + nr_new > type->max)
			if (memblock_double_array(type) < 0)
				return -ENOMEM;
		insert = true;
		goto repeat;
	} else {
		memblock_merge_regions(type);
		return 0;
402
	}
Y
Yinghai Lu 已提交
403 404
}

405
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
406
{
407
	return memblock_add_region(&memblock.memory, base, size);
Y
Yinghai Lu 已提交
408 409
}

410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429
/**
 * memblock_isolate_range - isolate given range into disjoint memblocks
 * @type: memblock type to isolate range for
 * @base: base of range to isolate
 * @size: size of range to isolate
 * @start_rgn: out parameter for the start of isolated region
 * @end_rgn: out parameter for the end of isolated region
 *
 * Walk @type and ensure that regions don't cross the boundaries defined by
 * [@base,@base+@size).  Crossing regions are split at the boundaries,
 * which may create at most two more regions.  The index of the first
 * region inside the range is returned in *@start_rgn and end in *@end_rgn.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
static int __init_memblock memblock_isolate_range(struct memblock_type *type,
					phys_addr_t base, phys_addr_t size,
					int *start_rgn, int *end_rgn)
{
430
	phys_addr_t end = base + memblock_cap_size(base, &size);
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
	int i;

	*start_rgn = *end_rgn = 0;

	/* we'll create at most two more regions */
	while (type->cnt + 2 > type->max)
		if (memblock_double_array(type) < 0)
			return -ENOMEM;

	for (i = 0; i < type->cnt; i++) {
		struct memblock_region *rgn = &type->regions[i];
		phys_addr_t rbase = rgn->base;
		phys_addr_t rend = rbase + rgn->size;

		if (rbase >= end)
			break;
		if (rend <= base)
			continue;

		if (rbase < base) {
			/*
			 * @rgn intersects from below.  Split and continue
			 * to process the next region - the new top half.
			 */
			rgn->base = base;
			rgn->size = rend - rgn->base;
			memblock_insert_region(type, i, rbase, base - rbase,
458
					       memblock_get_region_node(rgn));
459 460 461 462 463 464 465 466
		} else if (rend > end) {
			/*
			 * @rgn intersects from above.  Split and redo the
			 * current region - the new bottom half.
			 */
			rgn->base = end;
			rgn->size = rend - rgn->base;
			memblock_insert_region(type, i--, rbase, end - rbase,
467
					       memblock_get_region_node(rgn));
468 469 470 471 472 473 474 475 476 477 478
		} else {
			/* @rgn is fully contained, record it */
			if (!*end_rgn)
				*start_rgn = i;
			*end_rgn = i + 1;
		}
	}

	return 0;
}

479 480
static int __init_memblock __memblock_remove(struct memblock_type *type,
					     phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
481
{
482 483
	int start_rgn, end_rgn;
	int i, ret;
Y
Yinghai Lu 已提交
484

485 486 487
	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;
Y
Yinghai Lu 已提交
488

489 490
	for (i = end_rgn - 1; i >= start_rgn; i--)
		memblock_remove_region(type, i);
491
	return 0;
Y
Yinghai Lu 已提交
492 493
}

494
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
495 496 497 498
{
	return __memblock_remove(&memblock.memory, base, size);
}

499
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
500
{
501
	memblock_dbg("   memblock_free: [%#016llx-%#016llx] %pF\n",
502 503 504
		     (unsigned long long)base,
		     (unsigned long long)base + size,
		     (void *)_RET_IP_);
505

Y
Yinghai Lu 已提交
506 507 508
	return __memblock_remove(&memblock.reserved, base, size);
}

509
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
510
{
511
	struct memblock_type *_rgn = &memblock.reserved;
Y
Yinghai Lu 已提交
512

513
	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n",
514 515 516
		     (unsigned long long)base,
		     (unsigned long long)base + size,
		     (void *)_RET_IP_);
Y
Yinghai Lu 已提交
517 518 519 520 521
	BUG_ON(0 == size);

	return memblock_add_region(_rgn, base, size);
}

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
/**
 * __next_free_mem_range - next function for for_each_free_mem_range()
 * @idx: pointer to u64 loop variable
 * @nid: nid: node selector, %MAX_NUMNODES for all nodes
 * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
 * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
 * @p_nid: ptr to int for nid of the range, can be %NULL
 *
 * Find the first free area from *@idx which matches @nid, fill the out
 * parameters, and update *@idx for the next iteration.  The lower 32bit of
 * *@idx contains index into memory region and the upper 32bit indexes the
 * areas before each reserved region.  For example, if reserved regions
 * look like the following,
 *
 *	0:[0-16), 1:[32-48), 2:[128-130)
 *
 * The upper 32bit indexes the following regions.
 *
 *	0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX)
 *
 * As both region arrays are sorted, the function advances the two indices
 * in lockstep and returns each intersection.
 */
void __init_memblock __next_free_mem_range(u64 *idx, int nid,
					   phys_addr_t *out_start,
					   phys_addr_t *out_end, int *out_nid)
{
	struct memblock_type *mem = &memblock.memory;
	struct memblock_type *rsv = &memblock.reserved;
	int mi = *idx & 0xffffffff;
	int ri = *idx >> 32;

	for ( ; mi < mem->cnt; mi++) {
		struct memblock_region *m = &mem->regions[mi];
		phys_addr_t m_start = m->base;
		phys_addr_t m_end = m->base + m->size;

		/* only memory regions are associated with nodes, check it */
		if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m))
			continue;

		/* scan areas before each reservation for intersection */
		for ( ; ri < rsv->cnt + 1; ri++) {
			struct memblock_region *r = &rsv->regions[ri];
			phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0;
			phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX;

			/* if ri advanced past mi, break out to advance mi */
			if (r_start >= m_end)
				break;
			/* if the two regions intersect, we're done */
			if (m_start < r_end) {
				if (out_start)
					*out_start = max(m_start, r_start);
				if (out_end)
					*out_end = min(m_end, r_end);
				if (out_nid)
					*out_nid = memblock_get_region_node(m);
				/*
				 * The region which ends first is advanced
				 * for the next iteration.
				 */
				if (m_end <= r_end)
					mi++;
				else
					ri++;
				*idx = (u32)mi | (u64)ri << 32;
				return;
			}
		}
	}

	/* signal end of iteration */
	*idx = ULLONG_MAX;
}

T
Tejun Heo 已提交
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
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/*
 * Common iterator interface used to define for_each_mem_range().
 */
void __init_memblock __next_mem_pfn_range(int *idx, int nid,
				unsigned long *out_start_pfn,
				unsigned long *out_end_pfn, int *out_nid)
{
	struct memblock_type *type = &memblock.memory;
	struct memblock_region *r;

	while (++*idx < type->cnt) {
		r = &type->regions[*idx];

		if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size))
			continue;
		if (nid == MAX_NUMNODES || nid == r->nid)
			break;
	}
	if (*idx >= type->cnt) {
		*idx = -1;
		return;
	}

	if (out_start_pfn)
		*out_start_pfn = PFN_UP(r->base);
	if (out_end_pfn)
		*out_end_pfn = PFN_DOWN(r->base + r->size);
	if (out_nid)
		*out_nid = r->nid;
}

/**
 * memblock_set_node - set node ID on memblock regions
 * @base: base of area to set node ID for
 * @size: size of area to set node ID for
 * @nid: node ID to set
 *
 * Set the nid of memblock memory regions in [@base,@base+@size) to @nid.
 * Regions which cross the area boundaries are split as necessary.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
				      int nid)
{
	struct memblock_type *type = &memblock.memory;
646 647
	int start_rgn, end_rgn;
	int i, ret;
T
Tejun Heo 已提交
648

649 650 651
	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;
T
Tejun Heo 已提交
652

653 654
	for (i = start_rgn; i < end_rgn; i++)
		type->regions[i].nid = nid;
T
Tejun Heo 已提交
655 656 657 658 659 660

	memblock_merge_regions(type);
	return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */

661
phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
Y
Yinghai Lu 已提交
662
{
663
	phys_addr_t found;
Y
Yinghai Lu 已提交
664

665 666 667
	/* We align the size to limit fragmentation. Without this, a lot of
	 * small allocs quickly eat up the whole reserve array on sparc
	 */
668
	size = round_up(size, align);
Y
Yinghai Lu 已提交
669

670
	found = memblock_find_in_range(0, max_addr, size, align);
671
	if (found && !memblock_reserve(found, size))
672
		return found;
Y
Yinghai Lu 已提交
673

674
	return 0;
Y
Yinghai Lu 已提交
675 676
}

677
phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
Y
Yinghai Lu 已提交
678
{
679 680 681 682 683 684 685 686 687
	phys_addr_t alloc;

	alloc = __memblock_alloc_base(size, align, max_addr);

	if (alloc == 0)
		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
		      (unsigned long long) size, (unsigned long long) max_addr);

	return alloc;
Y
Yinghai Lu 已提交
688 689
}

690
phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
Y
Yinghai Lu 已提交
691
{
692 693
	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
Y
Yinghai Lu 已提交
694 695


696
/*
697
 * Additional node-local top-down allocators.
698 699 700 701
 *
 * WARNING: Only available after early_node_map[] has been populated,
 * on some architectures, that is after all the calls to add_active_range()
 * have been done to populate it.
702
 */
Y
Yinghai Lu 已提交
703

704 705
static phys_addr_t __init memblock_nid_range_rev(phys_addr_t start,
						 phys_addr_t end, int *nid)
706
{
707 708 709 710
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
	unsigned long start_pfn, end_pfn;
	int i;

711
	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, nid)
712 713
		if (end > PFN_PHYS(start_pfn) && end <= PFN_PHYS(end_pfn))
			return max(start, PFN_PHYS(start_pfn));
714
#endif
715
	*nid = 0;
716
	return start;
717 718
}

719 720
phys_addr_t __init memblock_find_in_range_node(phys_addr_t start,
					       phys_addr_t end,
721 722
					       phys_addr_t size,
					       phys_addr_t align, int nid)
Y
Yinghai Lu 已提交
723
{
724 725
	struct memblock_type *mem = &memblock.memory;
	int i;
Y
Yinghai Lu 已提交
726

727
	BUG_ON(0 == size);
Y
Yinghai Lu 已提交
728

729 730 731
	/* Pump up max_addr */
	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
		end = memblock.current_limit;
Y
Yinghai Lu 已提交
732

733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
	for (i = mem->cnt - 1; i >= 0; i--) {
		struct memblock_region *r = &mem->regions[i];
		phys_addr_t base = max(start, r->base);
		phys_addr_t top = min(end, r->base + r->size);

		while (base < top) {
			phys_addr_t tbase, ret;
			int tnid;

			tbase = memblock_nid_range_rev(base, top, &tnid);
			if (nid == MAX_NUMNODES || tnid == nid) {
				ret = memblock_find_region(tbase, top, size, align);
				if (ret)
					return ret;
			}
			top = tbase;
Y
Yinghai Lu 已提交
749 750
		}
	}
751

T
Tejun Heo 已提交
752
	return 0;
Y
Yinghai Lu 已提交
753 754
}

755
phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
Y
Yinghai Lu 已提交
756
{
757
	phys_addr_t found;
Y
Yinghai Lu 已提交
758

759 760
	/*
	 * We align the size to limit fragmentation. Without this, a lot of
761 762
	 * small allocs quickly eat up the whole reserve array on sparc
	 */
763
	size = round_up(size, align);
764

765 766
	found = memblock_find_in_range_node(0, MEMBLOCK_ALLOC_ACCESSIBLE,
					    size, align, nid);
767
	if (found && !memblock_reserve(found, size))
768
		return found;
Y
Yinghai Lu 已提交
769

770 771 772 773 774 775 776 777 778
	return 0;
}

phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
{
	phys_addr_t res = memblock_alloc_nid(size, align, nid);

	if (res)
		return res;
779
	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
Y
Yinghai Lu 已提交
780 781
}

782 783 784 785 786

/*
 * Remaining API functions
 */

Y
Yinghai Lu 已提交
787
/* You must call memblock_analyze() before this. */
788
phys_addr_t __init memblock_phys_mem_size(void)
Y
Yinghai Lu 已提交
789
{
790
	return memblock.memory_size;
Y
Yinghai Lu 已提交
791 792
}

793 794 795 796 797 798
/* lowest address */
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
{
	return memblock.memory.regions[0].base;
}

799
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
Y
Yinghai Lu 已提交
800 801 802
{
	int idx = memblock.memory.cnt - 1;

803
	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
Y
Yinghai Lu 已提交
804 805 806
}

/* You must call memblock_analyze() after this. */
807
void __init memblock_enforce_memory_limit(phys_addr_t memory_limit)
Y
Yinghai Lu 已提交
808 809
{
	unsigned long i;
810
	phys_addr_t limit;
811
	struct memblock_region *p;
Y
Yinghai Lu 已提交
812 813 814 815 816 817 818

	if (!memory_limit)
		return;

	/* Truncate the memblock regions to satisfy the memory limit. */
	limit = memory_limit;
	for (i = 0; i < memblock.memory.cnt; i++) {
819 820
		if (limit > memblock.memory.regions[i].size) {
			limit -= memblock.memory.regions[i].size;
Y
Yinghai Lu 已提交
821 822 823
			continue;
		}

824
		memblock.memory.regions[i].size = limit;
Y
Yinghai Lu 已提交
825 826 827 828 829 830 831 832
		memblock.memory.cnt = i + 1;
		break;
	}

	memory_limit = memblock_end_of_DRAM();

	/* And truncate any reserves above the limit also. */
	for (i = 0; i < memblock.reserved.cnt; i++) {
833
		p = &memblock.reserved.regions[i];
Y
Yinghai Lu 已提交
834 835 836 837 838 839 840 841 842 843 844 845 846

		if (p->base > memory_limit)
			p->size = 0;
		else if ((p->base + p->size) > memory_limit)
			p->size = memory_limit - p->base;

		if (p->size == 0) {
			memblock_remove_region(&memblock.reserved, i);
			i--;
		}
	}
}

847
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864
{
	unsigned int left = 0, right = type->cnt;

	do {
		unsigned int mid = (right + left) / 2;

		if (addr < type->regions[mid].base)
			right = mid;
		else if (addr >= (type->regions[mid].base +
				  type->regions[mid].size))
			left = mid + 1;
		else
			return mid;
	} while (left < right);
	return -1;
}

865
int __init memblock_is_reserved(phys_addr_t addr)
Y
Yinghai Lu 已提交
866
{
867 868
	return memblock_search(&memblock.reserved, addr) != -1;
}
Y
Yinghai Lu 已提交
869

870
int __init_memblock memblock_is_memory(phys_addr_t addr)
871 872 873 874
{
	return memblock_search(&memblock.memory, addr) != -1;
}

875
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
876
{
877
	int idx = memblock_search(&memblock.memory, base);
878
	phys_addr_t end = base + memblock_cap_size(base, &size);
879 880 881

	if (idx == -1)
		return 0;
882 883
	return memblock.memory.regions[idx].base <= base &&
		(memblock.memory.regions[idx].base +
884
		 memblock.memory.regions[idx].size) >= end;
Y
Yinghai Lu 已提交
885 886
}

887
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
888
{
889
	memblock_cap_size(base, &size);
890
	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
Y
Yinghai Lu 已提交
891 892
}

893

894
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
895 896 897 898
{
	memblock.current_limit = limit;
}

T
Tejun Heo 已提交
899
static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
900 901 902 903
{
	unsigned long long base, size;
	int i;

T
Tejun Heo 已提交
904
	pr_info(" %s.cnt  = 0x%lx\n", name, type->cnt);
905

T
Tejun Heo 已提交
906 907 908 909 910 911 912 913 914 915 916 917 918
	for (i = 0; i < type->cnt; i++) {
		struct memblock_region *rgn = &type->regions[i];
		char nid_buf[32] = "";

		base = rgn->base;
		size = rgn->size;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
		if (memblock_get_region_node(rgn) != MAX_NUMNODES)
			snprintf(nid_buf, sizeof(nid_buf), " on node %d",
				 memblock_get_region_node(rgn));
#endif
		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n",
			name, i, base, base + size - 1, size, nid_buf);
919 920 921
	}
}

T
Tejun Heo 已提交
922
void __init_memblock __memblock_dump_all(void)
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938
{
	pr_info("MEMBLOCK configuration:\n");
	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);

	memblock_dump(&memblock.memory, "memory");
	memblock_dump(&memblock.reserved, "reserved");
}

void __init memblock_analyze(void)
{
	int i;

	memblock.memory_size = 0;

	for (i = 0; i < memblock.memory.cnt; i++)
		memblock.memory_size += memblock.memory.regions[i].size;
939 940 941

	/* We allow resizing from there */
	memblock_can_resize = 1;
942 943 944 945 946 947 948 949 950 951
}

static int __init early_memblock(char *p)
{
	if (p && strstr(p, "debug"))
		memblock_debug = 1;
	return 0;
}
early_param("memblock", early_memblock);

952
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK)
953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000

static int memblock_debug_show(struct seq_file *m, void *private)
{
	struct memblock_type *type = m->private;
	struct memblock_region *reg;
	int i;

	for (i = 0; i < type->cnt; i++) {
		reg = &type->regions[i];
		seq_printf(m, "%4d: ", i);
		if (sizeof(phys_addr_t) == 4)
			seq_printf(m, "0x%08lx..0x%08lx\n",
				   (unsigned long)reg->base,
				   (unsigned long)(reg->base + reg->size - 1));
		else
			seq_printf(m, "0x%016llx..0x%016llx\n",
				   (unsigned long long)reg->base,
				   (unsigned long long)(reg->base + reg->size - 1));

	}
	return 0;
}

static int memblock_debug_open(struct inode *inode, struct file *file)
{
	return single_open(file, memblock_debug_show, inode->i_private);
}

static const struct file_operations memblock_debug_fops = {
	.open = memblock_debug_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

static int __init memblock_init_debugfs(void)
{
	struct dentry *root = debugfs_create_dir("memblock", NULL);
	if (!root)
		return -ENXIO;
	debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
	debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);

	return 0;
}
__initcall(memblock_init_debugfs);

#endif /* CONFIG_DEBUG_FS */