aboutsummaryrefslogtreecommitdiff
path: root/mm/nobootmem.c
blob: e2bdb07079cee8d67b7e1eb771fec6d509045145 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
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
294
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
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
/*
 *  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>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/kmemleak.h>
#include <linux/range.h>
#include <linux/memblock.h>

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

#include "internal.h"

#ifndef CONFIG_NEED_MULTIPLE_NODES
struct pglist_data __refdata contig_page_data;
EXPORT_SYMBOL(contig_page_data);
#endif

unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;

#ifdef CONFIG_CRASH_DUMP
/*
 * If we have booted due to a crash, max_pfn will be a very low value. We need
 * to know the amount of memory that the previous kernel used.
 */
unsigned long saved_max_pfn;
#endif

static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
					u64 goal, u64 limit)
{
	void *ptr;
	u64 addr;

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

	addr = find_memory_core_early(nid, size, align, goal, limit);

	if (addr == MEMBLOCK_ERROR)
		return NULL;

	ptr = phys_to_virt(addr);
	memset(ptr, 0, size);
	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
	/*
	 * 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;
}

/*
 * 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++) {
		__free_pages_bootmem(pfn_to_page(cursor), 0);
		totalram_pages++;
	}
}

static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
	int i;
	unsigned long start_aligned, end_aligned;
	int order = ilog2(BITS_PER_LONG);

	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
	end_aligned = end & ~(BITS_PER_LONG - 1);

	if (end_aligned <= start_aligned) {
		for (i = start; i < end; i++)
			__free_pages_bootmem(pfn_to_page(i), 0);

		return;
	}

	for (i = start; i < start_aligned; i++)
		__free_pages_bootmem(pfn_to_page(i), 0);

	for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
		__free_pages_bootmem(pfn_to_page(i), order);

	for (i = end_aligned; i < end; i++)
		__free_pages_bootmem(pfn_to_page(i), 0);
}

unsigned long __init free_all_memory_core_early(int nodeid)
{
	int i;
	u64 start, end;
	unsigned long count = 0;
	struct range *range = NULL;
	int nr_range;

	nr_range = get_free_all_memory_range(&range, nodeid);

	for (i = 0; i < nr_range; i++) {
		start = range[i].start;
		end = range[i].end;
		count += end - start;
		__free_pages_memory(start, end);
	}

	return count;
}

/**
 * free_all_bootmem_node - release a node's free pages to the buddy allocator
 * @pgdat: node to be released
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
{
	register_page_bootmem_info_node(pgdat);

	/* free_all_memory_core_early(MAX_NUMNODES) will be called later */
	return 0;
}

/**
 * free_all_bootmem - release free pages to the buddy allocator
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem(void)
{
	/*
	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
	 *  because in some case like Node0 doesnt have RAM installed
	 *  low ram will be on Node1
	 * Use MAX_NUMNODES will make sure all ranges in early_node_map[]
	 *  will be used instead of only Node0 related
	 */
	return free_all_memory_core_early(MAX_NUMNODES);
}

/**
 * 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)
{
	kmemleak_free_part(__va(physaddr), size);
	memblock_x86_free_range(physaddr, physaddr + size);
}

/**
 * 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)
{
	kmemleak_free_part(__va(addr), size);
	memblock_x86_free_range(addr, addr + size);
}

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:

	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit);

	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.
	 */
	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
	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);
}

/**
 * __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)
{
	void *ptr;

	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
					 goal, -1ULL);
	if (ptr)
		return ptr;

	return __alloc_memory_core_early(MAX_NUMNODES, size, align,
					 goal, -1ULL);
}

void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
#ifdef MAX_DMA32_PFN
	unsigned long end_pfn;

	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

	/* update goal according ...MAX_DMA32_PFN */
	end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages;

	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
		void *ptr;
		unsigned long new_goal;

		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
		ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
						 new_goal, -1ULL);
		if (ptr)
			return ptr;
	}
#endif

	return __alloc_bootmem_node(pgdat, size, align, goal);

}

#ifdef CONFIG_SPARSEMEM
/**
 * alloc_bootmem_section - allocate boot memory from a specific section
 * @size: size of the request in bytes
 * @section_nr: sparse map section to allocate from
 *
 * Return NULL on failure.
 */
void * __init alloc_bootmem_section(unsigned long size,
				    unsigned long section_nr)
{
	unsigned long pfn, goal, limit;

	pfn = section_nr_to_pfn(section_nr);
	goal = pfn << PAGE_SHIFT;
	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;

	return __alloc_memory_core_early(early_pfn_to_nid(pfn), size,
					 SMP_CACHE_BYTES, goal, limit);
}
#endif

void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
	void *ptr;

	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

	ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
						 goal, -1ULL);
	if (ptr)
		return ptr;

	return __alloc_bootmem_nopanic(size, align, goal);
}

#ifndef ARCH_LOW_ADDRESS_LIMIT
#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
#endif

/**
 * __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);
}

/**
 * __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)
{
	void *ptr;

	if (WARN_ON_ONCE(slab_is_available()))
		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);

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

	return  __alloc_memory_core_early(MAX_NUMNODES, size, align,
				goal, ARCH_LOW_ADDRESS_LIMIT);
}