init.c 20.0 KB
Newer Older
1
#include <linux/gfp.h>
2
#include <linux/initrd.h>
3
#include <linux/ioport.h>
4
#include <linux/swap.h>
5
#include <linux/memblock.h>
P
Pekka Enberg 已提交
6
#include <linux/bootmem.h>	/* for max_low_pfn */
7

8
#include <asm/cacheflush.h>
9
#include <asm/e820.h>
10
#include <asm/init.h>
11
#include <asm/page.h>
12
#include <asm/page_types.h>
13
#include <asm/sections.h>
14
#include <asm/setup.h>
15
#include <asm/tlbflush.h>
16
#include <asm/tlb.h>
17
#include <asm/proto.h>
P
Pekka Enberg 已提交
18
#include <asm/dma.h>		/* for MAX_DMA_PFN */
19
#include <asm/microcode.h>
20

21 22 23 24 25 26 27
/*
 * We need to define the tracepoints somewhere, and tlb.c
 * is only compied when SMP=y.
 */
#define CREATE_TRACE_POINTS
#include <trace/events/tlb.h>

28 29
#include "mm_internal.h"

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
/*
 * Tables translating between page_cache_type_t and pte encoding.
 * Minimal supported modes are defined statically, modified if more supported
 * cache modes are available.
 * Index into __cachemode2pte_tbl is the cachemode.
 * Index into __pte2cachemode_tbl are the caching attribute bits of the pte
 * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2.
 */
uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
	[_PAGE_CACHE_MODE_WB]		= 0,
	[_PAGE_CACHE_MODE_WC]		= _PAGE_PWT,
	[_PAGE_CACHE_MODE_UC_MINUS]	= _PAGE_PCD,
	[_PAGE_CACHE_MODE_UC]		= _PAGE_PCD | _PAGE_PWT,
	[_PAGE_CACHE_MODE_WT]		= _PAGE_PCD,
	[_PAGE_CACHE_MODE_WP]		= _PAGE_PCD,
};
EXPORT_SYMBOL_GPL(__cachemode2pte_tbl);
uint8_t __pte2cachemode_tbl[8] = {
	[__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB,
	[__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC,
	[__pte2cm_idx(_PAGE_PCD)] = _PAGE_CACHE_MODE_UC_MINUS,
	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD)] = _PAGE_CACHE_MODE_UC,
	[__pte2cm_idx(_PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
	[__pte2cm_idx(_PAGE_PWT | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
	[__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
};
EXPORT_SYMBOL_GPL(__pte2cachemode_tbl);

59 60 61
static unsigned long __initdata pgt_buf_start;
static unsigned long __initdata pgt_buf_end;
static unsigned long __initdata pgt_buf_top;
62

63 64
static unsigned long min_pfn_mapped;

65 66
static bool __initdata can_use_brk_pgt = true;

67 68 69 70 71 72 73 74 75
/*
 * Pages returned are already directly mapped.
 *
 * Changing that is likely to break Xen, see commit:
 *
 *    279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve
 *
 * for detailed information.
 */
Y
Yinghai Lu 已提交
76
__ref void *alloc_low_pages(unsigned int num)
77 78
{
	unsigned long pfn;
Y
Yinghai Lu 已提交
79
	int i;
80 81

	if (after_bootmem) {
Y
Yinghai Lu 已提交
82
		unsigned int order;
83

Y
Yinghai Lu 已提交
84 85 86
		order = get_order((unsigned long)num << PAGE_SHIFT);
		return (void *)__get_free_pages(GFP_ATOMIC | __GFP_NOTRACK |
						__GFP_ZERO, order);
87 88
	}

89
	if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) {
90 91
		unsigned long ret;
		if (min_pfn_mapped >= max_pfn_mapped)
92
			panic("alloc_low_pages: ran out of memory");
93 94
		ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT,
					max_pfn_mapped << PAGE_SHIFT,
Y
Yinghai Lu 已提交
95
					PAGE_SIZE * num , PAGE_SIZE);
96
		if (!ret)
97
			panic("alloc_low_pages: can not alloc memory");
Y
Yinghai Lu 已提交
98
		memblock_reserve(ret, PAGE_SIZE * num);
99
		pfn = ret >> PAGE_SHIFT;
Y
Yinghai Lu 已提交
100 101 102
	} else {
		pfn = pgt_buf_end;
		pgt_buf_end += num;
103 104
		printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
			pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
Y
Yinghai Lu 已提交
105 106 107 108 109 110 111 112
	}

	for (i = 0; i < num; i++) {
		void *adr;

		adr = __va((pfn + i) << PAGE_SHIFT);
		clear_page(adr);
	}
113

Y
Yinghai Lu 已提交
114
	return __va(pfn << PAGE_SHIFT);
115 116
}

117 118
/* need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS */
#define INIT_PGT_BUF_SIZE	(6 * PAGE_SIZE)
Y
Yinghai Lu 已提交
119 120 121 122 123 124 125 126 127 128 129 130 131
RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
void  __init early_alloc_pgt_buf(void)
{
	unsigned long tables = INIT_PGT_BUF_SIZE;
	phys_addr_t base;

	base = __pa(extend_brk(tables, PAGE_SIZE));

	pgt_buf_start = base >> PAGE_SHIFT;
	pgt_buf_end = pgt_buf_start;
	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
}

132 133 134 135 136 137 138 139
int after_bootmem;

int direct_gbpages
#ifdef CONFIG_DIRECT_GBPAGES
				= 1
#endif
;

140 141 142 143 144 145 146 147 148 149
static void __init init_gbpages(void)
{
#ifdef CONFIG_X86_64
	if (direct_gbpages && cpu_has_gbpages)
		printk(KERN_INFO "Using GB pages for direct mapping\n");
	else
		direct_gbpages = 0;
#endif
}

150 151 152 153 154 155
struct map_range {
	unsigned long start;
	unsigned long end;
	unsigned page_size_mask;
};

156
static int page_size_mask;
157

158
static void __init probe_page_size_mask(void)
159
{
160 161
	init_gbpages();

162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183
#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK)
	/*
	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
	 * This will simplify cpa(), which otherwise needs to support splitting
	 * large pages into small in interrupt context, etc.
	 */
	if (direct_gbpages)
		page_size_mask |= 1 << PG_LEVEL_1G;
	if (cpu_has_pse)
		page_size_mask |= 1 << PG_LEVEL_2M;
#endif

	/* Enable PSE if available */
	if (cpu_has_pse)
		set_in_cr4(X86_CR4_PSE);

	/* Enable PGE if available */
	if (cpu_has_pge) {
		set_in_cr4(X86_CR4_PGE);
		__supported_pte_mask |= _PAGE_GLOBAL;
	}
}
184

185 186 187 188 189 190
#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
#define NR_RANGE_MR 5
#endif

191 192 193
static int __meminit save_mr(struct map_range *mr, int nr_range,
			     unsigned long start_pfn, unsigned long end_pfn,
			     unsigned long page_size_mask)
194 195 196 197 198 199 200 201 202 203 204 205 206
{
	if (start_pfn < end_pfn) {
		if (nr_range >= NR_RANGE_MR)
			panic("run out of range for init_memory_mapping\n");
		mr[nr_range].start = start_pfn<<PAGE_SHIFT;
		mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
		mr[nr_range].page_size_mask = page_size_mask;
		nr_range++;
	}

	return nr_range;
}

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
/*
 * adjust the page_size_mask for small range to go with
 *	big page size instead small one if nearby are ram too.
 */
static void __init_refok adjust_range_page_size_mask(struct map_range *mr,
							 int nr_range)
{
	int i;

	for (i = 0; i < nr_range; i++) {
		if ((page_size_mask & (1<<PG_LEVEL_2M)) &&
		    !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) {
			unsigned long start = round_down(mr[i].start, PMD_SIZE);
			unsigned long end = round_up(mr[i].end, PMD_SIZE);

#ifdef CONFIG_X86_32
			if ((end >> PAGE_SHIFT) > max_low_pfn)
				continue;
#endif

			if (memblock_is_region_memory(start, end - start))
				mr[i].page_size_mask |= 1<<PG_LEVEL_2M;
		}
		if ((page_size_mask & (1<<PG_LEVEL_1G)) &&
		    !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) {
			unsigned long start = round_down(mr[i].start, PUD_SIZE);
			unsigned long end = round_up(mr[i].end, PUD_SIZE);

			if (memblock_is_region_memory(start, end - start))
				mr[i].page_size_mask |= 1<<PG_LEVEL_1G;
		}
	}
}

241 242 243
static int __meminit split_mem_range(struct map_range *mr, int nr_range,
				     unsigned long start,
				     unsigned long end)
244
{
Y
Yinghai Lu 已提交
245
	unsigned long start_pfn, end_pfn, limit_pfn;
246
	unsigned long pfn;
247
	int i;
248

Y
Yinghai Lu 已提交
249 250
	limit_pfn = PFN_DOWN(end);

251
	/* head if not big page alignment ? */
252
	pfn = start_pfn = PFN_DOWN(start);
253 254 255 256 257 258 259
#ifdef CONFIG_X86_32
	/*
	 * Don't use a large page for the first 2/4MB of memory
	 * because there are often fixed size MTRRs in there
	 * and overlapping MTRRs into large pages can cause
	 * slowdowns.
	 */
260
	if (pfn == 0)
261
		end_pfn = PFN_DOWN(PMD_SIZE);
262
	else
263
		end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
264
#else /* CONFIG_X86_64 */
265
	end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
266
#endif
Y
Yinghai Lu 已提交
267 268
	if (end_pfn > limit_pfn)
		end_pfn = limit_pfn;
269 270
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
271
		pfn = end_pfn;
272 273 274
	}

	/* big page (2M) range */
275
	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
276
#ifdef CONFIG_X86_32
Y
Yinghai Lu 已提交
277
	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
278
#else /* CONFIG_X86_64 */
279
	end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
Y
Yinghai Lu 已提交
280 281
	if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE)))
		end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
282 283 284 285 286
#endif

	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
287
		pfn = end_pfn;
288 289 290 291
	}

#ifdef CONFIG_X86_64
	/* big page (1G) range */
292
	start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
Y
Yinghai Lu 已提交
293
	end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE));
294 295 296 297
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask &
				 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
298
		pfn = end_pfn;
299 300 301
	}

	/* tail is not big page (1G) alignment */
302
	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
Y
Yinghai Lu 已提交
303
	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
304 305 306
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
307
		pfn = end_pfn;
308 309 310 311
	}
#endif

	/* tail is not big page (2M) alignment */
312
	start_pfn = pfn;
Y
Yinghai Lu 已提交
313
	end_pfn = limit_pfn;
314 315
	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);

316 317 318
	if (!after_bootmem)
		adjust_range_page_size_mask(mr, nr_range);

319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
	/* try to merge same page size and continuous */
	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
		unsigned long old_start;
		if (mr[i].end != mr[i+1].start ||
		    mr[i].page_size_mask != mr[i+1].page_size_mask)
			continue;
		/* move it */
		old_start = mr[i].start;
		memmove(&mr[i], &mr[i+1],
			(nr_range - 1 - i) * sizeof(struct map_range));
		mr[i--].start = old_start;
		nr_range--;
	}

	for (i = 0; i < nr_range; i++)
334 335
		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
				mr[i].start, mr[i].end - 1,
336 337 338
			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));

339 340 341
	return nr_range;
}

342 343
struct range pfn_mapped[E820_X_MAX];
int nr_pfn_mapped;
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

static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
{
	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX,
					     nr_pfn_mapped, start_pfn, end_pfn);
	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX);

	max_pfn_mapped = max(max_pfn_mapped, end_pfn);

	if (start_pfn < (1UL<<(32-PAGE_SHIFT)))
		max_low_pfn_mapped = max(max_low_pfn_mapped,
					 min(end_pfn, 1UL<<(32-PAGE_SHIFT)));
}

bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
{
	int i;

	for (i = 0; i < nr_pfn_mapped; i++)
		if ((start_pfn >= pfn_mapped[i].start) &&
		    (end_pfn <= pfn_mapped[i].end))
			return true;

	return false;
}

370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387
/*
 * Setup the direct mapping of the physical memory at PAGE_OFFSET.
 * This runs before bootmem is initialized and gets pages directly from
 * the physical memory. To access them they are temporarily mapped.
 */
unsigned long __init_refok init_memory_mapping(unsigned long start,
					       unsigned long end)
{
	struct map_range mr[NR_RANGE_MR];
	unsigned long ret = 0;
	int nr_range, i;

	pr_info("init_memory_mapping: [mem %#010lx-%#010lx]\n",
	       start, end - 1);

	memset(mr, 0, sizeof(mr));
	nr_range = split_mem_range(mr, 0, start, end);

388 389 390 391
	for (i = 0; i < nr_range; i++)
		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
						   mr[i].page_size_mask);

392 393
	add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT);

394 395 396
	return ret >> PAGE_SHIFT;
}

397
/*
398 399 400 401 402 403 404 405 406 407 408
 * We need to iterate through the E820 memory map and create direct mappings
 * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
 * create direct mappings for all pfns from [0 to max_low_pfn) and
 * [4GB to max_pfn) because of possible memory holes in high addresses
 * that cannot be marked as UC by fixed/variable range MTRRs.
 * Depending on the alignment of E820 ranges, this may possibly result
 * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
 *
 * init_mem_mapping() calls init_range_memory_mapping() with big range.
 * That range would have hole in the middle or ends, and only ram parts
 * will be mapped in init_range_memory_mapping().
409
 */
Y
Yinghai Lu 已提交
410
static unsigned long __init init_range_memory_mapping(
411 412
					   unsigned long r_start,
					   unsigned long r_end)
413 414
{
	unsigned long start_pfn, end_pfn;
Y
Yinghai Lu 已提交
415
	unsigned long mapped_ram_size = 0;
416 417 418
	int i;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
419 420 421
		u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end);
		u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end);
		if (start >= end)
422 423
			continue;

424 425 426 427 428 429
		/*
		 * if it is overlapping with brk pgt, we need to
		 * alloc pgt buf from memblock instead.
		 */
		can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >=
				    min(end, (u64)pgt_buf_top<<PAGE_SHIFT);
430
		init_memory_mapping(start, end);
Y
Yinghai Lu 已提交
431
		mapped_ram_size += end - start;
432
		can_use_brk_pgt = true;
433
	}
Y
Yinghai Lu 已提交
434 435

	return mapped_ram_size;
436 437
}

438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456
static unsigned long __init get_new_step_size(unsigned long step_size)
{
	/*
	 * Explain why we shift by 5 and why we don't have to worry about
	 * 'step_size << 5' overflowing:
	 *
	 * initial mapped size is PMD_SIZE (2M).
	 * We can not set step_size to be PUD_SIZE (1G) yet.
	 * In worse case, when we cross the 1G boundary, and
	 * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
	 * to map 1G range with PTE. Use 5 as shift for now.
	 *
	 * Don't need to worry about overflow, on 32bit, when step_size
	 * is 0, round_down() returns 0 for start, and that turns it
	 * into 0x100000000ULL.
	 */
	return step_size << 5;
}

457 458 459 460 461 462 463 464 465 466 467 468
/**
 * memory_map_top_down - Map [map_start, map_end) top down
 * @map_start: start address of the target memory range
 * @map_end: end address of the target memory range
 *
 * This function will setup direct mapping for memory range
 * [map_start, map_end) in top-down. That said, the page tables
 * will be allocated at the end of the memory, and we map the
 * memory in top-down.
 */
static void __init memory_map_top_down(unsigned long map_start,
				       unsigned long map_end)
469
{
470
	unsigned long real_end, start, last_start;
Y
Yinghai Lu 已提交
471 472 473 474
	unsigned long step_size;
	unsigned long addr;
	unsigned long mapped_ram_size = 0;
	unsigned long new_mapped_ram_size;
475

476
	/* xen has big range in reserved near end of ram, skip it at first.*/
477
	addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
Y
Yinghai Lu 已提交
478 479 480 481 482 483 484
	real_end = addr + PMD_SIZE;

	/* step_size need to be small so pgt_buf from BRK could cover it */
	step_size = PMD_SIZE;
	max_pfn_mapped = 0; /* will get exact value next */
	min_pfn_mapped = real_end >> PAGE_SHIFT;
	last_start = start = real_end;
485 486 487 488 489 490 491

	/*
	 * We start from the top (end of memory) and go to the bottom.
	 * The memblock_find_in_range() gets us a block of RAM from the
	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
	 * for page table.
	 */
492
	while (last_start > map_start) {
Y
Yinghai Lu 已提交
493 494
		if (last_start > step_size) {
			start = round_down(last_start - 1, step_size);
495 496
			if (start < map_start)
				start = map_start;
Y
Yinghai Lu 已提交
497
		} else
498
			start = map_start;
Y
Yinghai Lu 已提交
499 500 501 502 503 504
		new_mapped_ram_size = init_range_memory_mapping(start,
							last_start);
		last_start = start;
		min_pfn_mapped = last_start >> PAGE_SHIFT;
		/* only increase step_size after big range get mapped */
		if (new_mapped_ram_size > mapped_ram_size)
505
			step_size = get_new_step_size(step_size);
Y
Yinghai Lu 已提交
506 507 508
		mapped_ram_size += new_mapped_ram_size;
	}

509 510 511 512
	if (real_end < map_end)
		init_range_memory_mapping(real_end, map_end);
}

513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
/**
 * memory_map_bottom_up - Map [map_start, map_end) bottom up
 * @map_start: start address of the target memory range
 * @map_end: end address of the target memory range
 *
 * This function will setup direct mapping for memory range
 * [map_start, map_end) in bottom-up. Since we have limited the
 * bottom-up allocation above the kernel, the page tables will
 * be allocated just above the kernel and we map the memory
 * in [map_start, map_end) in bottom-up.
 */
static void __init memory_map_bottom_up(unsigned long map_start,
					unsigned long map_end)
{
	unsigned long next, new_mapped_ram_size, start;
	unsigned long mapped_ram_size = 0;
	/* step_size need to be small so pgt_buf from BRK could cover it */
	unsigned long step_size = PMD_SIZE;

	start = map_start;
	min_pfn_mapped = start >> PAGE_SHIFT;

	/*
	 * We start from the bottom (@map_start) and go to the top (@map_end).
	 * The memblock_find_in_range() gets us a block of RAM from the
	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
	 * for page table.
	 */
	while (start < map_end) {
		if (map_end - start > step_size) {
			next = round_up(start + 1, step_size);
			if (next > map_end)
				next = map_end;
		} else
			next = map_end;

		new_mapped_ram_size = init_range_memory_mapping(start, next);
		start = next;

		if (new_mapped_ram_size > mapped_ram_size)
			step_size = get_new_step_size(step_size);
		mapped_ram_size += new_mapped_ram_size;
	}
}

558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
void __init init_mem_mapping(void)
{
	unsigned long end;

	probe_page_size_mask();

#ifdef CONFIG_X86_64
	end = max_pfn << PAGE_SHIFT;
#else
	end = max_low_pfn << PAGE_SHIFT;
#endif

	/* the ISA range is always mapped regardless of memory holes */
	init_memory_mapping(0, ISA_END_ADDRESS);

573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591
	/*
	 * If the allocation is in bottom-up direction, we setup direct mapping
	 * in bottom-up, otherwise we setup direct mapping in top-down.
	 */
	if (memblock_bottom_up()) {
		unsigned long kernel_end = __pa_symbol(_end);

		/*
		 * we need two separate calls here. This is because we want to
		 * allocate page tables above the kernel. So we first map
		 * [kernel_end, end) to make memory above the kernel be mapped
		 * as soon as possible. And then use page tables allocated above
		 * the kernel to map [ISA_END_ADDRESS, kernel_end).
		 */
		memory_map_bottom_up(kernel_end, end);
		memory_map_bottom_up(ISA_END_ADDRESS, kernel_end);
	} else {
		memory_map_top_down(ISA_END_ADDRESS, end);
	}
Y
Yinghai Lu 已提交
592

593 594 595 596 597
#ifdef CONFIG_X86_64
	if (max_pfn > max_low_pfn) {
		/* can we preseve max_low_pfn ?*/
		max_low_pfn = max_pfn;
	}
598 599
#else
	early_ioremap_page_table_range_init();
600 601
#endif

602 603 604
	load_cr3(swapper_pg_dir);
	__flush_tlb_all();

605
	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
606
}
607

608 609 610 611 612 613 614 615 616 617 618 619
/*
 * devmem_is_allowed() checks to see if /dev/mem access to a certain address
 * is valid. The argument is a physical page number.
 *
 *
 * On x86, access has to be given to the first megabyte of ram because that area
 * contains bios code and data regions used by X and dosemu and similar apps.
 * Access has to be given to non-kernel-ram areas as well, these contain the PCI
 * mmio resources as well as potential bios/acpi data regions.
 */
int devmem_is_allowed(unsigned long pagenr)
{
620
	if (pagenr < 256)
621 622 623 624 625 626 627 628
		return 1;
	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
		return 0;
	if (!page_is_ram(pagenr))
		return 1;
	return 0;
}

629 630
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
631
	unsigned long begin_aligned, end_aligned;
632

633 634 635 636 637 638 639 640 641 642
	/* Make sure boundaries are page aligned */
	begin_aligned = PAGE_ALIGN(begin);
	end_aligned   = end & PAGE_MASK;

	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
		begin = begin_aligned;
		end   = end_aligned;
	}

	if (begin >= end)
643 644 645 646 647 648 649 650
		return;

	/*
	 * If debugging page accesses then do not free this memory but
	 * mark them not present - any buggy init-section access will
	 * create a kernel page fault:
	 */
#ifdef CONFIG_DEBUG_PAGEALLOC
651 652
	printk(KERN_INFO "debug: unmapping init [mem %#010lx-%#010lx]\n",
		begin, end - 1);
653 654 655 656 657
	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
	/*
	 * We just marked the kernel text read only above, now that
	 * we are going to free part of that, we need to make that
658
	 * writeable and non-executable first.
659
	 */
660
	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
661 662
	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);

663
	free_reserved_area((void *)begin, (void *)end, POISON_FREE_INITMEM, what);
664 665 666 667 668
#endif
}

void free_initmem(void)
{
669
	free_init_pages("unused kernel",
670 671 672
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}
673 674

#ifdef CONFIG_BLK_DEV_INITRD
675
void __init free_initrd_mem(unsigned long start, unsigned long end)
676
{
677 678 679 680 681 682 683 684 685
#ifdef CONFIG_MICROCODE_EARLY
	/*
	 * Remember, initrd memory may contain microcode or other useful things.
	 * Before we lose initrd mem, we need to find a place to hold them
	 * now that normal virtual memory is enabled.
	 */
	save_microcode_in_initrd();
#endif

686 687 688 689 690 691 692 693 694
	/*
	 * end could be not aligned, and We can not align that,
	 * decompresser could be confused by aligned initrd_end
	 * We already reserve the end partial page before in
	 *   - i386_start_kernel()
	 *   - x86_64_start_kernel()
	 *   - relocate_initrd()
	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
	 */
695
	free_init_pages("initrd", start, PAGE_ALIGN(end));
696 697
}
#endif
P
Pekka Enberg 已提交
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718

void __init zone_sizes_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];

	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));

#ifdef CONFIG_ZONE_DMA
	max_zone_pfns[ZONE_DMA]		= MAX_DMA_PFN;
#endif
#ifdef CONFIG_ZONE_DMA32
	max_zone_pfns[ZONE_DMA32]	= MAX_DMA32_PFN;
#endif
	max_zone_pfns[ZONE_NORMAL]	= max_low_pfn;
#ifdef CONFIG_HIGHMEM
	max_zone_pfns[ZONE_HIGHMEM]	= max_pfn;
#endif

	free_area_init_nodes(max_zone_pfns);
}