memblock.c 33.1 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>

23 24
#include <asm-generic/sections.h>

T
Tejun Heo 已提交
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,

37
	.bottom_up		= false,
T
Tejun Heo 已提交
38 39
	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
};
Y
Yinghai Lu 已提交
40

41
int memblock_debug __initdata_memblock;
42
static int memblock_can_resize __initdata_memblock;
43 44
static int memblock_memory_in_slab __initdata_memblock = 0;
static int memblock_reserved_in_slab __initdata_memblock = 0;
Y
Yinghai Lu 已提交
45

46
/* inline so we don't get a warning when pr_debug is compiled out */
47 48
static __init_memblock const char *
memblock_type_name(struct memblock_type *type)
49 50 51 52 53 54 55 56 57
{
	if (type == &memblock.memory)
		return "memory";
	else if (type == &memblock.reserved)
		return "reserved";
	else
		return "unknown";
}

58 59 60 61 62 63
/* 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);
}

64 65 66
/*
 * Address comparison utilities
 */
67
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
68
				       phys_addr_t base2, phys_addr_t size2)
Y
Yinghai Lu 已提交
69 70 71 72
{
	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}

73 74
static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
					phys_addr_t base, phys_addr_t size)
75 76 77 78 79 80 81 82 83 84 85 86 87
{
	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;
}

88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
/*
 * __memblock_find_range_bottom_up - find free area utility in bottom-up
 * @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
 *
 * Utility called from memblock_find_in_range_node(), find free area bottom-up.
 *
 * RETURNS:
 * Found address on success, 0 on failure.
 */
static phys_addr_t __init_memblock
__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
				phys_addr_t size, phys_addr_t align, int nid)
{
	phys_addr_t this_start, this_end, cand;
	u64 i;

	for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) {
		this_start = clamp(this_start, start, end);
		this_end = clamp(this_end, start, end);

		cand = round_up(this_start, align);
		if (cand < this_end && this_end - cand >= size)
			return cand;
	}

	return 0;
}

120
/**
121
 * __memblock_find_range_top_down - find free area utility, in top-down
122 123 124 125 126 127
 * @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
 *
128
 * Utility called from memblock_find_in_range_node(), find free area top-down.
129 130
 *
 * RETURNS:
131
 * Found address on success, 0 on failure.
132
 */
133 134 135
static phys_addr_t __init_memblock
__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
			       phys_addr_t size, phys_addr_t align, int nid)
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
{
	phys_addr_t this_start, this_end, cand;
	u64 i;

	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);

		if (this_end < size)
			continue;

		cand = round_down(this_end - size, align);
		if (cand >= this_start)
			return cand;
	}
151

152 153
	return 0;
}
154

155 156 157 158 159 160 161 162 163 164
/**
 * 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.
 *
165 166 167 168 169 170 171 172
 * When allocation direction is bottom-up, the @start should be greater
 * than the end of the kernel image. Otherwise, it will be trimmed. The
 * reason is that we want the bottom-up allocation just near the kernel
 * image so it is highly likely that the allocated memory and the kernel
 * will reside in the same node.
 *
 * If bottom-up allocation failed, will try to allocate memory top-down.
 *
173
 * RETURNS:
174
 * Found address on success, 0 on failure.
175 176 177 178 179
 */
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)
{
180 181 182
	int ret;
	phys_addr_t kernel_end;

183 184 185 186 187 188 189
	/* pump up @end */
	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
		end = memblock.current_limit;

	/* avoid allocating the first page */
	start = max_t(phys_addr_t, start, PAGE_SIZE);
	end = max(start, end);
190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
	kernel_end = __pa_symbol(_end);

	/*
	 * try bottom-up allocation only when bottom-up mode
	 * is set and @end is above the kernel image.
	 */
	if (memblock_bottom_up() && end > kernel_end) {
		phys_addr_t bottom_up_start;

		/* make sure we will allocate above the kernel */
		bottom_up_start = max(start, kernel_end);

		/* ok, try bottom-up allocation first */
		ret = __memblock_find_range_bottom_up(bottom_up_start, end,
						      size, align, nid);
		if (ret)
			return ret;

		/*
		 * we always limit bottom-up allocation above the kernel,
		 * but top-down allocation doesn't have the limit, so
		 * retrying top-down allocation may succeed when bottom-up
		 * allocation failed.
		 *
		 * bottom-up allocation is expected to be fail very rarely,
		 * so we use WARN_ONCE() here to see the stack trace if
		 * fail happens.
		 */
		WARN_ONCE(1, "memblock: bottom-up allocation failed, "
			     "memory hotunplug may be affected\n");
	}
221 222 223 224

	return __memblock_find_range_top_down(start, end, size, align, nid);
}

225 226 227 228 229 230 231 232 233 234
/**
 * 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:
235
 * Found address on success, 0 on failure.
236
 */
237 238 239
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)
240
{
241 242
	return memblock_find_in_range_node(start, end, size, align,
					   MAX_NUMNODES);
243 244
}

245
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
Y
Yinghai Lu 已提交
246
{
247
	type->total_size -= type->regions[r].size;
T
Tejun Heo 已提交
248 249
	memmove(&type->regions[r], &type->regions[r + 1],
		(type->cnt - (r + 1)) * sizeof(type->regions[r]));
250
	type->cnt--;
Y
Yinghai Lu 已提交
251

252 253
	/* Special case for empty arrays */
	if (type->cnt == 0) {
254
		WARN_ON(type->total_size != 0);
255 256 257
		type->cnt = 1;
		type->regions[0].base = 0;
		type->regions[0].size = 0;
T
Tejun Heo 已提交
258
		memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
259
	}
Y
Yinghai Lu 已提交
260 261
}

262 263 264 265 266 267 268 269 270 271 272 273
phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
					phys_addr_t *addr)
{
	if (memblock.reserved.regions == memblock_reserved_init_regions)
		return 0;

	*addr = __pa(memblock.reserved.regions);

	return PAGE_ALIGN(sizeof(struct memblock_region) *
			  memblock.reserved.max);
}

274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
/**
 * 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)
292 293
{
	struct memblock_region *new_array, *old_array;
294
	phys_addr_t old_alloc_size, new_alloc_size;
295 296
	phys_addr_t old_size, new_size, addr;
	int use_slab = slab_is_available();
297
	int *in_slab;
298 299 300 301 302 303 304 305 306 307

	/* 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;
308 309 310 311 312 313
	/*
	 * We need to allocated new one align to PAGE_SIZE,
	 *   so we can free them completely later.
	 */
	old_alloc_size = PAGE_ALIGN(old_size);
	new_alloc_size = PAGE_ALIGN(new_size);
314

315 316 317 318 319 320
	/* Retrieve the slab flag */
	if (type == &memblock.memory)
		in_slab = &memblock_memory_in_slab;
	else
		in_slab = &memblock_reserved_in_slab;

321 322 323
	/* Try to find some space for it.
	 *
	 * WARNING: We assume that either slab_is_available() and we use it or
324 325 326
	 * 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)
327 328
	 *
	 * This should however not be an issue for now, as we currently only
329 330
	 * call into MEMBLOCK while it's still active, or much later when slab
	 * is active for memory hotplug operations
331 332 333
	 */
	if (use_slab) {
		new_array = kmalloc(new_size, GFP_KERNEL);
T
Tejun Heo 已提交
334
		addr = new_array ? __pa(new_array) : 0;
335
	} else {
336 337 338 339 340 341
		/* 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,
342
						new_alloc_size, PAGE_SIZE);
343 344
		if (!addr && new_area_size)
			addr = memblock_find_in_range(0,
345 346
				min(new_area_start, memblock.current_limit),
				new_alloc_size, PAGE_SIZE);
347

348
		new_array = addr ? __va(addr) : NULL;
349
	}
T
Tejun Heo 已提交
350
	if (!addr) {
351 352 353 354 355
		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;
	}

356 357 358
	memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]",
			memblock_type_name(type), type->max * 2, (u64)addr,
			(u64)addr + new_size - 1);
359

360 361 362 363
	/*
	 * 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.
364 365 366 367 368 369 370
	 */
	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;

371
	/* Free old array. We needn't free it if the array is the static one */
372 373 374 375
	if (*in_slab)
		kfree(old_array);
	else if (old_array != memblock_memory_init_regions &&
		 old_array != memblock_reserved_init_regions)
376
		memblock_free(__pa(old_array), old_alloc_size);
377

378 379 380
	/*
	 * Reserve the new array if that comes from the memblock.  Otherwise, we
	 * needn't do it
381 382
	 */
	if (!use_slab)
383
		BUG_ON(memblock_reserve(addr, new_alloc_size));
384 385 386 387

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

388 389 390
	return 0;
}

391 392 393 394 395 396 397
/**
 * 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
398
{
399
	int i = 0;
Y
Yinghai Lu 已提交
400

401 402 403 404
	/* 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
405

T
Tejun Heo 已提交
406 407 408
		if (this->base + this->size != next->base ||
		    memblock_get_region_node(this) !=
		    memblock_get_region_node(next)) {
409 410 411
			BUG_ON(this->base + this->size > next->base);
			i++;
			continue;
412 413
		}

414
		this->size += next->size;
415 416
		/* move forward from next + 1, index of which is i + 2 */
		memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
417
		type->cnt--;
Y
Yinghai Lu 已提交
418
	}
419
}
Y
Yinghai Lu 已提交
420

421 422
/**
 * memblock_insert_region - insert new memblock region
423 424 425 426 427
 * @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
 * @nid:	node id of the new region
428 429 430 431 432 433
 *
 * 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
434
						   phys_addr_t size, int nid)
435 436 437 438 439 440 441
{
	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
442
	memblock_set_region_node(rgn, nid);
443
	type->cnt++;
444
	type->total_size += size;
445 446 447 448 449 450 451
}

/**
 * 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
452
 * @nid: nid of the new region
453 454 455 456 457 458 459 460 461
 *
 * 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.
 */
462
static int __init_memblock memblock_add_region(struct memblock_type *type,
463
				phys_addr_t base, phys_addr_t size, int nid)
464 465
{
	bool insert = false;
466 467
	phys_addr_t obase = base;
	phys_addr_t end = base + memblock_cap_size(base, &size);
468 469
	int i, nr_new;

470 471 472
	if (!size)
		return 0;

473 474
	/* special case for empty array */
	if (type->regions[0].size == 0) {
475
		WARN_ON(type->cnt != 1 || type->total_size);
476 477
		type->regions[0].base = base;
		type->regions[0].size = size;
478
		memblock_set_region_node(&type->regions[0], nid);
479
		type->total_size = size;
480
		return 0;
Y
Yinghai Lu 已提交
481
	}
482 483 484 485 486
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.
487
	 */
488 489
	base = obase;
	nr_new = 0;
Y
Yinghai Lu 已提交
490

491 492 493 494 495 496
	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
497
			break;
498 499 500 501 502 503 504 505 506 507
		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,
508
						       rbase - base, nid);
Y
Yinghai Lu 已提交
509
		}
510 511
		/* area below @rend is dealt with, forget about it */
		base = min(rend, end);
Y
Yinghai Lu 已提交
512
	}
513 514 515 516 517

	/* insert the remaining portion */
	if (base < end) {
		nr_new++;
		if (insert)
518
			memblock_insert_region(type, i, base, end - base, nid);
Y
Yinghai Lu 已提交
519 520
	}

521 522 523
	/*
	 * If this was the first round, resize array and repeat for actual
	 * insertions; otherwise, merge and return.
524
	 */
525 526
	if (!insert) {
		while (type->cnt + nr_new > type->max)
527
			if (memblock_double_array(type, obase, size) < 0)
528 529 530 531 532 533
				return -ENOMEM;
		insert = true;
		goto repeat;
	} else {
		memblock_merge_regions(type);
		return 0;
534
	}
Y
Yinghai Lu 已提交
535 536
}

537 538 539 540 541 542
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);
}

543
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
544
{
545
	return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES);
Y
Yinghai Lu 已提交
546 547
}

548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567
/**
 * 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)
{
568
	phys_addr_t end = base + memblock_cap_size(base, &size);
569 570 571 572
	int i;

	*start_rgn = *end_rgn = 0;

573 574 575
	if (!size)
		return 0;

576 577
	/* we'll create at most two more regions */
	while (type->cnt + 2 > type->max)
578
		if (memblock_double_array(type, base, size) < 0)
579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
			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;
597 598
			rgn->size -= base - rbase;
			type->total_size -= base - rbase;
599
			memblock_insert_region(type, i, rbase, base - rbase,
600
					       memblock_get_region_node(rgn));
601 602 603 604 605 606
		} else if (rend > end) {
			/*
			 * @rgn intersects from above.  Split and redo the
			 * current region - the new bottom half.
			 */
			rgn->base = end;
607 608
			rgn->size -= end - rbase;
			type->total_size -= end - rbase;
609
			memblock_insert_region(type, i--, rbase, end - rbase,
610
					       memblock_get_region_node(rgn));
611 612 613 614 615 616 617 618 619 620 621
		} else {
			/* @rgn is fully contained, record it */
			if (!*end_rgn)
				*start_rgn = i;
			*end_rgn = i + 1;
		}
	}

	return 0;
}

622 623
static int __init_memblock __memblock_remove(struct memblock_type *type,
					     phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
624
{
625 626
	int start_rgn, end_rgn;
	int i, ret;
Y
Yinghai Lu 已提交
627

628 629 630
	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;
Y
Yinghai Lu 已提交
631

632 633
	for (i = end_rgn - 1; i >= start_rgn; i--)
		memblock_remove_region(type, i);
634
	return 0;
Y
Yinghai Lu 已提交
635 636
}

637
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
638 639 640 641
{
	return __memblock_remove(&memblock.memory, base, size);
}

642
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
643
{
644
	memblock_dbg("   memblock_free: [%#016llx-%#016llx] %pF\n",
645 646 647
		     (unsigned long long)base,
		     (unsigned long long)base + size,
		     (void *)_RET_IP_);
648

Y
Yinghai Lu 已提交
649 650 651
	return __memblock_remove(&memblock.reserved, base, size);
}

652
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
653
{
654
	struct memblock_type *_rgn = &memblock.reserved;
Y
Yinghai Lu 已提交
655

656
	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n",
657 658 659
		     (unsigned long long)base,
		     (unsigned long long)base + size,
		     (void *)_RET_IP_);
Y
Yinghai Lu 已提交
660

661
	return memblock_add_region(_rgn, base, size, MAX_NUMNODES);
Y
Yinghai Lu 已提交
662 663
}

664 665 666
/**
 * __next_free_mem_range - next function for for_each_free_mem_range()
 * @idx: pointer to u64 loop variable
667
 * @nid: node selector, %MAX_NUMNODES for all nodes
W
Wanpeng Li 已提交
668 669 670
 * @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
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739
 *
 * 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;
}

740 741 742 743
/**
 * __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
744 745 746
 * @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
747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
 *
 * 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
804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
#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;
852 853
	int start_rgn, end_rgn;
	int i, ret;
T
Tejun Heo 已提交
854

855 856 857
	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;
T
Tejun Heo 已提交
858

859
	for (i = start_rgn; i < end_rgn; i++)
860
		memblock_set_region_node(&type->regions[i], nid);
T
Tejun Heo 已提交
861 862 863 864 865 866

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

867 868 869
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
870
{
871
	phys_addr_t found;
Y
Yinghai Lu 已提交
872

873 874 875
	if (WARN_ON(!align))
		align = __alignof__(long long);

876 877 878
	/* align @size to avoid excessive fragmentation on reserved array */
	size = round_up(size, align);

879
	found = memblock_find_in_range_node(0, max_addr, size, align, nid);
880
	if (found && !memblock_reserve(found, size))
881
		return found;
Y
Yinghai Lu 已提交
882

883
	return 0;
Y
Yinghai Lu 已提交
884 885
}

886 887 888 889 890 891 892 893 894 895
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);
}

896
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
897
{
898 899 900 901 902 903 904 905 906
	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
907 908
}

909
phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
Y
Yinghai Lu 已提交
910
{
911 912
	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
Y
Yinghai Lu 已提交
913

914 915 916 917 918 919
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;
920
	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
Y
Yinghai Lu 已提交
921 922
}

923 924 925 926 927

/*
 * Remaining API functions
 */

928
phys_addr_t __init memblock_phys_mem_size(void)
Y
Yinghai Lu 已提交
929
{
930
	return memblock.memory.total_size;
Y
Yinghai Lu 已提交
931 932
}

Y
Yinghai Lu 已提交
933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949
phys_addr_t __init memblock_mem_size(unsigned long limit_pfn)
{
	unsigned long pages = 0;
	struct memblock_region *r;
	unsigned long start_pfn, end_pfn;

	for_each_memblock(memory, r) {
		start_pfn = memblock_region_memory_base_pfn(r);
		end_pfn = memblock_region_memory_end_pfn(r);
		start_pfn = min_t(unsigned long, start_pfn, limit_pfn);
		end_pfn = min_t(unsigned long, end_pfn, limit_pfn);
		pages += end_pfn - start_pfn;
	}

	return (phys_addr_t)pages << PAGE_SHIFT;
}

950 951 952 953 954 955
/* lowest address */
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
{
	return memblock.memory.regions[0].base;
}

956
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
Y
Yinghai Lu 已提交
957 958 959
{
	int idx = memblock.memory.cnt - 1;

960
	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
Y
Yinghai Lu 已提交
961 962
}

963
void __init memblock_enforce_memory_limit(phys_addr_t limit)
Y
Yinghai Lu 已提交
964 965
{
	unsigned long i;
966
	phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
Y
Yinghai Lu 已提交
967

968
	if (!limit)
Y
Yinghai Lu 已提交
969 970
		return;

971
	/* find out max address */
Y
Yinghai Lu 已提交
972
	for (i = 0; i < memblock.memory.cnt; i++) {
973
		struct memblock_region *r = &memblock.memory.regions[i];
Y
Yinghai Lu 已提交
974

975 976 977
		if (limit <= r->size) {
			max_addr = r->base + limit;
			break;
Y
Yinghai Lu 已提交
978
		}
979
		limit -= r->size;
Y
Yinghai Lu 已提交
980
	}
981 982 983 984

	/* 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
985 986
}

987
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004
{
	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;
}

1005
int __init memblock_is_reserved(phys_addr_t addr)
Y
Yinghai Lu 已提交
1006
{
1007 1008
	return memblock_search(&memblock.reserved, addr) != -1;
}
Y
Yinghai Lu 已提交
1009

1010
int __init_memblock memblock_is_memory(phys_addr_t addr)
1011 1012 1013 1014
{
	return memblock_search(&memblock.memory, addr) != -1;
}

1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
			 unsigned long *start_pfn, unsigned long *end_pfn)
{
	struct memblock_type *type = &memblock.memory;
	int mid = memblock_search(type, (phys_addr_t)pfn << PAGE_SHIFT);

	if (mid == -1)
		return -1;

	*start_pfn = type->regions[mid].base >> PAGE_SHIFT;
	*end_pfn = (type->regions[mid].base + type->regions[mid].size)
			>> PAGE_SHIFT;

	return type->regions[mid].nid;
}
#endif

1033 1034 1035 1036 1037 1038 1039 1040 1041 1042
/**
 * 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
 */
1043
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
1044
{
1045
	int idx = memblock_search(&memblock.memory, base);
1046
	phys_addr_t end = base + memblock_cap_size(base, &size);
1047 1048 1049

	if (idx == -1)
		return 0;
1050 1051
	return memblock.memory.regions[idx].base <= base &&
		(memblock.memory.regions[idx].base +
1052
		 memblock.memory.regions[idx].size) >= end;
Y
Yinghai Lu 已提交
1053 1054
}

1055 1056 1057 1058 1059 1060 1061 1062 1063 1064
/**
 * 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
 */
1065
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
Y
Yinghai Lu 已提交
1066
{
1067
	memblock_cap_size(base, &size);
1068
	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
Y
Yinghai Lu 已提交
1069 1070
}

1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
void __init_memblock memblock_trim_memory(phys_addr_t align)
{
	int i;
	phys_addr_t start, end, orig_start, orig_end;
	struct memblock_type *mem = &memblock.memory;

	for (i = 0; i < mem->cnt; i++) {
		orig_start = mem->regions[i].base;
		orig_end = mem->regions[i].base + mem->regions[i].size;
		start = round_up(orig_start, align);
		end = round_down(orig_end, align);

		if (start == orig_start && end == orig_end)
			continue;

		if (start < end) {
			mem->regions[i].base = start;
			mem->regions[i].size = end - start;
		} else {
			memblock_remove_region(mem, i);
			i--;
		}
	}
}
1095

1096
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
1097 1098 1099 1100
{
	memblock.current_limit = limit;
}

T
Tejun Heo 已提交
1101
static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
1102 1103 1104 1105
{
	unsigned long long base, size;
	int i;

T
Tejun Heo 已提交
1106
	pr_info(" %s.cnt  = 0x%lx\n", name, type->cnt);
1107

T
Tejun Heo 已提交
1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
	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);
1121 1122 1123
	}
}

T
Tejun Heo 已提交
1124
void __init_memblock __memblock_dump_all(void)
1125 1126
{
	pr_info("MEMBLOCK configuration:\n");
1127 1128 1129
	pr_info(" memory size = %#llx reserved size = %#llx\n",
		(unsigned long long)memblock.memory.total_size,
		(unsigned long long)memblock.reserved.total_size);
1130 1131 1132 1133 1134

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

1135
void __init memblock_allow_resize(void)
1136
{
1137
	memblock_can_resize = 1;
1138 1139 1140 1141 1142 1143 1144 1145 1146 1147
}

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

1148
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK)
1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196

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 */