nobootmem.c 11.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 *  bootmem - A boot-time physical memory allocator and configurator
 *
 *  Copyright (C) 1999 Ingo Molnar
 *                1999 Kanoj Sarcar, SGI
 *                2008 Johannes Weiner
 *
 * Access to this subsystem has to be serialized externally (which is true
 * for the boot process anyway).
 */
#include <linux/init.h>
#include <linux/pfn.h>
#include <linux/slab.h>
14
#include <linux/export.h>
15 16 17
#include <linux/kmemleak.h>
#include <linux/range.h>
#include <linux/memblock.h>
18
#include <linux/bootmem.h>
19 20 21 22 23 24

#include <asm/bug.h>
#include <asm/io.h>

#include "internal.h"

25 26 27 28
#ifndef CONFIG_HAVE_MEMBLOCK
#error CONFIG_HAVE_MEMBLOCK not defined
#endif

29 30 31 32 33
#ifndef CONFIG_NEED_MULTIPLE_NODES
struct pglist_data __refdata contig_page_data;
EXPORT_SYMBOL(contig_page_data);
#endif

34 35 36
unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;
I
Igor Mammedov 已提交
37
unsigned long long max_possible_pfn;
38

39 40 41 42 43
static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
					u64 goal, u64 limit)
{
	void *ptr;
	u64 addr;
44
	ulong flags = choose_memblock_flags();
45 46 47 48

	if (limit > memblock.current_limit)
		limit = memblock.current_limit;

49
again:
50
	addr = memblock_find_in_range_node(size, align, goal, limit, nid,
51 52 53 54 55 56 57
					   flags);
	if (!addr && (flags & MEMBLOCK_MIRROR)) {
		flags &= ~MEMBLOCK_MIRROR;
		pr_warn("Could not allocate %pap bytes of mirrored memory\n",
			&size);
		goto again;
	}
T
Tejun Heo 已提交
58
	if (!addr)
59 60
		return NULL;

61 62 63
	if (memblock_reserve(addr, size))
		return NULL;

64 65 66 67 68 69 70 71 72 73
	ptr = phys_to_virt(addr);
	memset(ptr, 0, size);
	/*
	 * The min_count is set to 0 so that bootmem allocated blocks
	 * are never reported as leaks.
	 */
	kmemleak_alloc(ptr, size, 0, 0);
	return ptr;
}

74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
/*
 * free_bootmem_late - free bootmem pages directly to page allocator
 * @addr: starting address of the range
 * @size: size of the range in bytes
 *
 * This is only useful when the bootmem allocator has already been torn
 * down, but we are still initializing the system.  Pages are given directly
 * to the page allocator, no bootmem metadata is updated because it is gone.
 */
void __init free_bootmem_late(unsigned long addr, unsigned long size)
{
	unsigned long cursor, end;

	kmemleak_free_part(__va(addr), size);

	cursor = PFN_UP(addr);
	end = PFN_DOWN(addr + size);

	for (; cursor < end; cursor++) {
93
		__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
94 95 96 97 98 99
		totalram_pages++;
	}
}

static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
100
	int order;
101

102 103
	while (start < end) {
		order = min(MAX_ORDER - 1UL, __ffs(start));
104

105 106
		while (start + (1UL << order) > end)
			order--;
107

108
		__free_pages_bootmem(pfn_to_page(start), start, order);
109

110 111
		start += (1UL << order);
	}
112 113
}

114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
static unsigned long __init __free_memory_core(phys_addr_t start,
				 phys_addr_t end)
{
	unsigned long start_pfn = PFN_UP(start);
	unsigned long end_pfn = min_t(unsigned long,
				      PFN_DOWN(end), max_low_pfn);

	if (start_pfn > end_pfn)
		return 0;

	__free_pages_memory(start_pfn, end_pfn);

	return end_pfn - start_pfn;
}

129
static unsigned long __init free_low_memory_core_early(void)
130 131
{
	unsigned long count = 0;
132
	phys_addr_t start, end;
133 134
	u64 i;

135 136
	memblock_clear_hotplug(0, -1);

137 138 139
	for_each_reserved_mem_region(i, &start, &end)
		reserve_bootmem_region(start, end);

140 141
	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
				NULL)
142 143
		count += __free_memory_core(start, end);

144
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
145 146 147 148 149 150 151 152 153 154 155 156 157
	{
		phys_addr_t size;

		/* Free memblock.reserved array if it was allocated */
		size = get_allocated_memblock_reserved_regions_info(&start);
		if (size)
			count += __free_memory_core(start, start + size);

		/* Free memblock.memory array if it was allocated */
		size = get_allocated_memblock_memory_regions_info(&start);
		if (size)
			count += __free_memory_core(start, start + size);
	}
158 159
#endif

160 161 162
	return count;
}

163 164
static int reset_managed_pages_done __initdata;

165
void reset_node_managed_pages(pg_data_t *pgdat)
166 167 168 169
{
	struct zone *z;

	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
170 171 172 173 174 175 176
		z->managed_pages = 0;
}

void __init reset_all_zones_managed_pages(void)
{
	struct pglist_data *pgdat;

177 178 179
	if (reset_managed_pages_done)
		return;

180 181
	for_each_online_pgdat(pgdat)
		reset_node_managed_pages(pgdat);
182

183
	reset_managed_pages_done = 1;
184 185
}

186 187 188 189 190 191 192
/**
 * free_all_bootmem - release free pages to the buddy allocator
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem(void)
{
193 194
	unsigned long pages;

195
	reset_all_zones_managed_pages();
196

197
	/*
198
	 * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
L
Lucas De Marchi 已提交
199
	 *  because in some case like Node0 doesn't have RAM installed
200 201
	 *  low ram will be on Node1
	 */
202 203 204 205
	pages = free_low_memory_core_early();
	totalram_pages += pages;

	return pages;
206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
}

/**
 * free_bootmem_node - mark a page range as usable
 * @pgdat: node the range resides on
 * @physaddr: starting address of the range
 * @size: size of the range in bytes
 *
 * Partial pages will be considered reserved and left as they are.
 *
 * The range must reside completely on the specified node.
 */
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
			      unsigned long size)
{
221
	memblock_free(physaddr, size);
222 223 224 225 226 227 228 229 230 231 232 233 234
}

/**
 * free_bootmem - mark a page range as usable
 * @addr: starting address of the range
 * @size: size of the range in bytes
 *
 * Partial pages will be considered reserved and left as they are.
 *
 * The range must be contiguous but may span node boundaries.
 */
void __init free_bootmem(unsigned long addr, unsigned long size)
{
235
	memblock_free(addr, size);
236 237 238 239 240 241 242 243 244 245 246 247 248 249
}

static void * __init ___alloc_bootmem_nopanic(unsigned long size,
					unsigned long align,
					unsigned long goal,
					unsigned long limit)
{
	void *ptr;

	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc(size, GFP_NOWAIT);

restart:

250
	ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit);
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293

	if (ptr)
		return ptr;

	if (goal != 0) {
		goal = 0;
		goto restart;
	}

	return NULL;
}

/**
 * __alloc_bootmem_nopanic - allocate boot memory without panicking
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may happen on any node in the system.
 *
 * Returns NULL on failure.
 */
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
					unsigned long goal)
{
	unsigned long limit = -1UL;

	return ___alloc_bootmem_nopanic(size, align, goal, limit);
}

static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
					unsigned long goal, unsigned long limit)
{
	void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);

	if (mem)
		return mem;
	/*
	 * Whoops, we cannot satisfy the allocation request.
	 */
294
	pr_alert("bootmem alloc of %lu bytes failed!\n", size);
295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319
	panic("Out of memory");
	return NULL;
}

/**
 * __alloc_bootmem - allocate boot memory
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may happen on any node in the system.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
			      unsigned long goal)
{
	unsigned long limit = -1UL;

	return ___alloc_bootmem(size, align, goal, limit);
}

320
void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
321 322 323 324 325 326 327 328 329 330 331 332 333
						   unsigned long size,
						   unsigned long align,
						   unsigned long goal,
						   unsigned long limit)
{
	void *ptr;

again:
	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
					goal, limit);
	if (ptr)
		return ptr;

334
	ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align,
335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
					goal, limit);
	if (ptr)
		return ptr;

	if (goal) {
		goal = 0;
		goto again;
	}

	return NULL;
}

void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
}

356
static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
357 358 359 360 361 362 363 364 365
				    unsigned long align, unsigned long goal,
				    unsigned long limit)
{
	void *ptr;

	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, limit);
	if (ptr)
		return ptr;

366
	pr_alert("bootmem alloc of %lu bytes failed!\n", size);
367 368 369 370
	panic("Out of memory");
	return NULL;
}

371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391
/**
 * __alloc_bootmem_node - allocate boot memory from a specific node
 * @pgdat: node to allocate from
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may fall back to any node in the system if the specified node
 * can not hold the requested memory.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

392
	return ___alloc_bootmem_node(pgdat, size, align, goal, 0);
393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420
}

void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
	return __alloc_bootmem_node(pgdat, size, align, goal);
}


/**
 * __alloc_bootmem_low - allocate low boot memory
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may happen on any node in the system.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
				  unsigned long goal)
{
	return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
}

421 422 423 424 425 426 427 428
void * __init __alloc_bootmem_low_nopanic(unsigned long size,
					  unsigned long align,
					  unsigned long goal)
{
	return ___alloc_bootmem_nopanic(size, align, goal,
					ARCH_LOW_ADDRESS_LIMIT);
}

429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
/**
 * __alloc_bootmem_low_node - allocate low boot memory from a specific node
 * @pgdat: node to allocate from
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may fall back to any node in the system if the specified node
 * can not hold the requested memory.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
				       unsigned long align, unsigned long goal)
{
	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

450 451
	return ___alloc_bootmem_node(pgdat, size, align, goal,
				     ARCH_LOW_ADDRESS_LIMIT);
452
}