memblock.c 28.5 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
int memblock_debug __initdata_memblock;
39
static int memblock_can_resize __initdata_memblock;
40 41
static int memblock_memory_in_slab __initdata_memblock = 0;
static int memblock_reserved_in_slab __initdata_memblock = 0;
Y
Yinghai Lu 已提交
42

43 44 45 46 47 48 49 50 51 52 53
/* 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";
}

54 55 56 57 58 59
/* 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);
}

60 61 62
/*
 * Address comparison utilities
 */
63
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
64
				       phys_addr_t base2, phys_addr_t size2)
Y
Yinghai Lu 已提交
65 66 67 68
{
	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}

69 70
static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
					phys_addr_t base, phys_addr_t size)
71 72 73 74 75 76 77 78 79 80 81 82 83
{
	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;
}

84 85 86 87 88 89 90 91 92 93 94 95
/**
 * memblock_find_in_range_node - find free area in given range and node
 * @start: start of candidate range
 * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
 * @size: size of free area to find
 * @align: alignment of free area to find
 * @nid: nid of the free area to find, %MAX_NUMNODES for any node
 *
 * Find @size free area aligned to @align in the specified range and node.
 *
 * RETURNS:
 * Found address on success, %0 on failure.
96
 */
97 98 99
phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
					phys_addr_t end, phys_addr_t size,
					phys_addr_t align, int nid)
100
{
101 102
	phys_addr_t this_start, this_end, cand;
	u64 i;
103

104 105 106
	/* pump up @end */
	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
		end = memblock.current_limit;
107

108 109
	/* avoid allocating the first page */
	start = max_t(phys_addr_t, start, PAGE_SIZE);
110
	end = max(start, end);
111

112 113 114
	for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
		this_start = clamp(this_start, start, end);
		this_end = clamp(this_end, start, end);
115

116 117 118
		if (this_end < size)
			continue;

119 120 121 122
		cand = round_down(this_end - size, align);
		if (cand >= this_start)
			return cand;
	}
T
Tejun Heo 已提交
123
	return 0;
124 125
}

126 127 128 129 130 131 132 133 134 135 136
/**
 * memblock_find_in_range - find free area in given range
 * @start: start of candidate range
 * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
 * @size: size of free area to find
 * @align: alignment of free area to find
 *
 * Find @size free area aligned to @align in the specified range.
 *
 * RETURNS:
 * Found address on success, %0 on failure.
137
 */
138 139 140
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)
141
{
142 143
	return memblock_find_in_range_node(start, end, size, align,
					   MAX_NUMNODES);
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
/*
 * 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);
}

170
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
Y
Yinghai Lu 已提交
171
{
172
	type->total_size -= type->regions[r].size;
T
Tejun Heo 已提交
173 174
	memmove(&type->regions[r], &type->regions[r + 1],
		(type->cnt - (r + 1)) * sizeof(type->regions[r]));
175
	type->cnt--;
Y
Yinghai Lu 已提交
176

177 178
	/* Special case for empty arrays */
	if (type->cnt == 0) {
179
		WARN_ON(type->total_size != 0);
180 181 182
		type->cnt = 1;
		type->regions[0].base = 0;
		type->regions[0].size = 0;
T
Tejun Heo 已提交
183
		memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
184
	}
Y
Yinghai Lu 已提交
185 186
}

187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204
/**
 * memblock_double_array - double the size of the memblock regions array
 * @type: memblock type of the regions array being doubled
 * @new_area_start: starting address of memory range to avoid overlap with
 * @new_area_size: size of memory range to avoid overlap with
 *
 * Double the size of the @type regions array. If memblock is being used to
 * allocate memory for a new reserved regions array and there is a previously
 * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
 * waiting to be reserved, ensure the memory used by the new array does
 * not overlap.
 *
 * RETURNS:
 * 0 on success, -1 on failure.
 */
static int __init_memblock memblock_double_array(struct memblock_type *type,
						phys_addr_t new_area_start,
						phys_addr_t new_area_size)
205 206 207 208
{
	struct memblock_region *new_array, *old_array;
	phys_addr_t old_size, new_size, addr;
	int use_slab = slab_is_available();
209
	int *in_slab;
210 211 212 213 214 215 216 217 218 219 220

	/* 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;

221 222 223 224 225 226
	/* Retrieve the slab flag */
	if (type == &memblock.memory)
		in_slab = &memblock_memory_in_slab;
	else
		in_slab = &memblock_reserved_in_slab;

227 228 229 230 231 232 233 234 235 236 237 238 239
	/* 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
240
		addr = new_array ? __pa(new_array) : 0;
241
	} else {
242 243 244 245 246 247 248 249 250 251 252 253
		/* only exclude range when trying to double reserved.regions */
		if (type != &memblock.reserved)
			new_area_start = new_area_size = 0;

		addr = memblock_find_in_range(new_area_start + new_area_size,
						memblock.current_limit,
						new_size, sizeof(phys_addr_t));
		if (!addr && new_area_size)
			addr = memblock_find_in_range(0,
					min(new_area_start, memblock.current_limit),
					new_size, sizeof(phys_addr_t));

254 255
		new_array = addr ? __va(addr) : 0;
	}
T
Tejun Heo 已提交
256
	if (!addr) {
257 258 259 260 261
		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;
	}

262 263 264
	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);

265 266 267 268 269 270 271 272 273 274
	/* 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;

275 276
	/* Free old array. We needn't free it if the array is the
	 * static one
277
	 */
278 279 280 281
	if (*in_slab)
		kfree(old_array);
	else if (old_array != memblock_memory_init_regions &&
		 old_array != memblock_reserved_init_regions)
282 283
		memblock_free(__pa(old_array), old_size);

284 285 286 287 288 289 290 291 292
	/* Reserve the new array if that comes from the memblock.
	 * Otherwise, we needn't do it
	 */
	if (!use_slab)
		BUG_ON(memblock_reserve(addr, new_size));

	/* Update slab flag */
	*in_slab = use_slab;

293 294 295
	return 0;
}

296 297 298 299 300 301 302
/**
 * 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
303
{
304
	int i = 0;
Y
Yinghai Lu 已提交
305

306 307 308 309
	/* 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
310

T
Tejun Heo 已提交
311 312 313
		if (this->base + this->size != next->base ||
		    memblock_get_region_node(this) !=
		    memblock_get_region_node(next)) {
314 315 316
			BUG_ON(this->base + this->size > next->base);
			i++;
			continue;
317 318
		}

319 320 321
		this->size += next->size;
		memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next));
		type->cnt--;
Y
Yinghai Lu 已提交
322
	}
323
}
Y
Yinghai Lu 已提交
324

325 326 327 328 329 330 331 332 333 334 335 336
/**
 * 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
337
						   phys_addr_t size, int nid)
338 339 340 341 342 343 344
{
	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
345
	memblock_set_region_node(rgn, nid);
346
	type->cnt++;
347
	type->total_size += size;
348 349 350 351 352 353 354
}

/**
 * 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
355
 * @nid: nid of the new region
356 357 358 359 360 361 362 363 364
 *
 * 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.
 */
365
static int __init_memblock memblock_add_region(struct memblock_type *type,
366
				phys_addr_t base, phys_addr_t size, int nid)
367 368
{
	bool insert = false;
369 370
	phys_addr_t obase = base;
	phys_addr_t end = base + memblock_cap_size(base, &size);
371 372
	int i, nr_new;

373 374 375
	if (!size)
		return 0;

376 377
	/* special case for empty array */
	if (type->regions[0].size == 0) {
378
		WARN_ON(type->cnt != 1 || type->total_size);
379 380
		type->regions[0].base = base;
		type->regions[0].size = size;
381
		memblock_set_region_node(&type->regions[0], nid);
382
		type->total_size = size;
383
		return 0;
Y
Yinghai Lu 已提交
384
	}
385 386 387 388 389
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.
390
	 */
391 392
	base = obase;
	nr_new = 0;
Y
Yinghai Lu 已提交
393

394 395 396 397 398 399
	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
400
			break;
401 402 403 404 405 406 407 408 409 410
		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,
411
						       rbase - base, nid);
Y
Yinghai Lu 已提交
412
		}
413 414
		/* area below @rend is dealt with, forget about it */
		base = min(rend, end);
Y
Yinghai Lu 已提交
415
	}
416 417 418 419 420

	/* insert the remaining portion */
	if (base < end) {
		nr_new++;
		if (insert)
421
			memblock_insert_region(type, i, base, end - base, nid);
Y
Yinghai Lu 已提交
422 423
	}

424 425 426
	/*
	 * If this was the first round, resize array and repeat for actual
	 * insertions; otherwise, merge and return.
427
	 */
428 429
	if (!insert) {
		while (type->cnt + nr_new > type->max)
430
			if (memblock_double_array(type, obase, size) < 0)
431 432 433 434 435 436
				return -ENOMEM;
		insert = true;
		goto repeat;
	} else {
		memblock_merge_regions(type);
		return 0;
437
	}
Y
Yinghai Lu 已提交
438 439
}

440 441 442 443 444 445
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
				       int nid)
{
	return memblock_add_region(&memblock.memory, base, size, nid);
}

446
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
447
{
448
	return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES);
Y
Yinghai Lu 已提交
449 450
}

451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470
/**
 * 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)
{
471
	phys_addr_t end = base + memblock_cap_size(base, &size);
472 473 474 475
	int i;

	*start_rgn = *end_rgn = 0;

476 477 478
	if (!size)
		return 0;

479 480
	/* we'll create at most two more regions */
	while (type->cnt + 2 > type->max)
481
		if (memblock_double_array(type, base, size) < 0)
482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
			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;
500 501
			rgn->size -= base - rbase;
			type->total_size -= base - rbase;
502
			memblock_insert_region(type, i, rbase, base - rbase,
503
					       memblock_get_region_node(rgn));
504 505 506 507 508 509
		} else if (rend > end) {
			/*
			 * @rgn intersects from above.  Split and redo the
			 * current region - the new bottom half.
			 */
			rgn->base = end;
510 511
			rgn->size -= end - rbase;
			type->total_size -= end - rbase;
512
			memblock_insert_region(type, i--, rbase, end - rbase,
513
					       memblock_get_region_node(rgn));
514 515 516 517 518 519 520 521 522 523 524
		} else {
			/* @rgn is fully contained, record it */
			if (!*end_rgn)
				*start_rgn = i;
			*end_rgn = i + 1;
		}
	}

	return 0;
}

525 526
static int __init_memblock __memblock_remove(struct memblock_type *type,
					     phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
527
{
528 529
	int start_rgn, end_rgn;
	int i, ret;
Y
Yinghai Lu 已提交
530

531 532 533
	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;
Y
Yinghai Lu 已提交
534

535 536
	for (i = end_rgn - 1; i >= start_rgn; i--)
		memblock_remove_region(type, i);
537
	return 0;
Y
Yinghai Lu 已提交
538 539
}

540
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
541 542 543 544
{
	return __memblock_remove(&memblock.memory, base, size);
}

545
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
546
{
547
	memblock_dbg("   memblock_free: [%#016llx-%#016llx] %pF\n",
548 549 550
		     (unsigned long long)base,
		     (unsigned long long)base + size,
		     (void *)_RET_IP_);
551

Y
Yinghai Lu 已提交
552 553 554
	return __memblock_remove(&memblock.reserved, base, size);
}

555
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
556
{
557
	struct memblock_type *_rgn = &memblock.reserved;
Y
Yinghai Lu 已提交
558

559
	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n",
560 561 562
		     (unsigned long long)base,
		     (unsigned long long)base + size,
		     (void *)_RET_IP_);
Y
Yinghai Lu 已提交
563

564
	return memblock_add_region(_rgn, base, size, MAX_NUMNODES);
Y
Yinghai Lu 已提交
565 566
}

567 568 569 570
/**
 * __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
W
Wanpeng Li 已提交
571 572 573
 * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
 * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
 * @out_nid: ptr to int for nid of the range, can be %NULL
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
 *
 * 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;
}

643 644 645 646
/**
 * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse()
 * @idx: pointer to u64 loop variable
 * @nid: nid: node selector, %MAX_NUMNODES for all nodes
W
Wanpeng Li 已提交
647 648 649
 * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
 * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
 * @out_nid: ptr to int for nid of the range, can be %NULL
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
 *
 * Reverse of __next_free_mem_range().
 */
void __init_memblock __next_free_mem_range_rev(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;

	if (*idx == (u64)ULLONG_MAX) {
		mi = mem->cnt - 1;
		ri = rsv->cnt;
	}

	for ( ; mi >= 0; 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 >= 0; 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_end <= m_start)
				break;
			/* if the two regions intersect, we're done */
			if (m_end > r_start) {
				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);

				if (m_start >= r_start)
					mi--;
				else
					ri--;
				*idx = (u32)mi | (u64)ri << 32;
				return;
			}
		}
	}

	*idx = ULLONG_MAX;
}

T
Tejun Heo 已提交
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
#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;
755 756
	int start_rgn, end_rgn;
	int i, ret;
T
Tejun Heo 已提交
757

758 759 760
	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;
T
Tejun Heo 已提交
761

762 763
	for (i = start_rgn; i < end_rgn; i++)
		type->regions[i].nid = nid;
T
Tejun Heo 已提交
764 765 766 767 768 769

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

770 771 772
static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
					phys_addr_t align, phys_addr_t max_addr,
					int nid)
Y
Yinghai Lu 已提交
773
{
774
	phys_addr_t found;
Y
Yinghai Lu 已提交
775

776 777 778
	/* align @size to avoid excessive fragmentation on reserved array */
	size = round_up(size, align);

779
	found = memblock_find_in_range_node(0, max_addr, size, align, nid);
780
	if (found && !memblock_reserve(found, size))
781
		return found;
Y
Yinghai Lu 已提交
782

783
	return 0;
Y
Yinghai Lu 已提交
784 785
}

786 787 788 789 790 791 792 793 794 795
phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
{
	return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
}

phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
	return memblock_alloc_base_nid(size, align, max_addr, MAX_NUMNODES);
}

796
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
797
{
798 799 800 801 802 803 804 805 806
	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
807 808
}

809
phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
Y
Yinghai Lu 已提交
810
{
811 812
	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
Y
Yinghai Lu 已提交
813

814 815 816 817 818 819
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;
820
	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
Y
Yinghai Lu 已提交
821 822
}

823 824 825 826 827

/*
 * Remaining API functions
 */

828
phys_addr_t __init memblock_phys_mem_size(void)
Y
Yinghai Lu 已提交
829
{
830
	return memblock.memory.total_size;
Y
Yinghai Lu 已提交
831 832
}

833 834 835 836 837 838
/* lowest address */
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
{
	return memblock.memory.regions[0].base;
}

839
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
Y
Yinghai Lu 已提交
840 841 842
{
	int idx = memblock.memory.cnt - 1;

843
	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
Y
Yinghai Lu 已提交
844 845
}

846
void __init memblock_enforce_memory_limit(phys_addr_t limit)
Y
Yinghai Lu 已提交
847 848
{
	unsigned long i;
849
	phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
Y
Yinghai Lu 已提交
850

851
	if (!limit)
Y
Yinghai Lu 已提交
852 853
		return;

854
	/* find out max address */
Y
Yinghai Lu 已提交
855
	for (i = 0; i < memblock.memory.cnt; i++) {
856
		struct memblock_region *r = &memblock.memory.regions[i];
Y
Yinghai Lu 已提交
857

858 859 860
		if (limit <= r->size) {
			max_addr = r->base + limit;
			break;
Y
Yinghai Lu 已提交
861
		}
862
		limit -= r->size;
Y
Yinghai Lu 已提交
863
	}
864 865 866 867

	/* truncate both memory and reserved regions */
	__memblock_remove(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX);
	__memblock_remove(&memblock.reserved, max_addr, (phys_addr_t)ULLONG_MAX);
Y
Yinghai Lu 已提交
868 869
}

870
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887
{
	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;
}

888
int __init memblock_is_reserved(phys_addr_t addr)
Y
Yinghai Lu 已提交
889
{
890 891
	return memblock_search(&memblock.reserved, addr) != -1;
}
Y
Yinghai Lu 已提交
892

893
int __init_memblock memblock_is_memory(phys_addr_t addr)
894 895 896 897
{
	return memblock_search(&memblock.memory, addr) != -1;
}

898 899 900 901 902 903 904 905 906 907
/**
 * memblock_is_region_memory - check if a region is a subset of memory
 * @base: base of region to check
 * @size: size of region to check
 *
 * Check if the region [@base, @base+@size) is a subset of a memory block.
 *
 * RETURNS:
 * 0 if false, non-zero if true
 */
908
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
909
{
910
	int idx = memblock_search(&memblock.memory, base);
911
	phys_addr_t end = base + memblock_cap_size(base, &size);
912 913 914

	if (idx == -1)
		return 0;
915 916
	return memblock.memory.regions[idx].base <= base &&
		(memblock.memory.regions[idx].base +
917
		 memblock.memory.regions[idx].size) >= end;
Y
Yinghai Lu 已提交
918 919
}

920 921 922 923 924 925 926 927 928 929
/**
 * memblock_is_region_reserved - check if a region intersects reserved memory
 * @base: base of region to check
 * @size: size of region to check
 *
 * Check if the region [@base, @base+@size) intersects a reserved memory block.
 *
 * RETURNS:
 * 0 if false, non-zero if true
 */
930
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
931
{
932
	memblock_cap_size(base, &size);
933
	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
Y
Yinghai Lu 已提交
934 935
}

936

937
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
938 939 940 941
{
	memblock.current_limit = limit;
}

T
Tejun Heo 已提交
942
static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
943 944 945 946
{
	unsigned long long base, size;
	int i;

T
Tejun Heo 已提交
947
	pr_info(" %s.cnt  = 0x%lx\n", name, type->cnt);
948

T
Tejun Heo 已提交
949 950 951 952 953 954 955 956 957 958 959 960 961
	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);
962 963 964
	}
}

T
Tejun Heo 已提交
965
void __init_memblock __memblock_dump_all(void)
966 967
{
	pr_info("MEMBLOCK configuration:\n");
968 969 970
	pr_info(" memory size = %#llx reserved size = %#llx\n",
		(unsigned long long)memblock.memory.total_size,
		(unsigned long long)memblock.reserved.total_size);
971 972 973 974 975

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

976
void __init memblock_allow_resize(void)
977
{
978
	memblock_can_resize = 1;
979 980 981 982 983 984 985 986 987 988
}

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

989
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK)
990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037

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 */