init.c 14.7 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

20 21
#include "mm_internal.h"

22 23 24
static unsigned long __initdata pgt_buf_start;
static unsigned long __initdata pgt_buf_end;
static unsigned long __initdata pgt_buf_top;
25

26 27
static unsigned long min_pfn_mapped;

28 29 30 31 32 33 34 35 36
/*
 * 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
37
__ref void *alloc_low_pages(unsigned int num)
38 39
{
	unsigned long pfn;
Y
Yinghai Lu 已提交
40
	int i;
41 42 43

#ifdef CONFIG_X86_64
	if (after_bootmem) {
Y
Yinghai Lu 已提交
44
		unsigned int order;
45

Y
Yinghai Lu 已提交
46 47 48
		order = get_order((unsigned long)num << PAGE_SHIFT);
		return (void *)__get_free_pages(GFP_ATOMIC | __GFP_NOTRACK |
						__GFP_ZERO, order);
49 50 51
	}
#endif

Y
Yinghai Lu 已提交
52
	if ((pgt_buf_end + num) >= pgt_buf_top) {
53 54 55 56 57
		unsigned long ret;
		if (min_pfn_mapped >= max_pfn_mapped)
			panic("alloc_low_page: ran out of memory");
		ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT,
					max_pfn_mapped << PAGE_SHIFT,
Y
Yinghai Lu 已提交
58
					PAGE_SIZE * num , PAGE_SIZE);
59 60
		if (!ret)
			panic("alloc_low_page: can not alloc memory");
Y
Yinghai Lu 已提交
61
		memblock_reserve(ret, PAGE_SIZE * num);
62
		pfn = ret >> PAGE_SHIFT;
Y
Yinghai Lu 已提交
63 64 65 66 67 68 69 70 71 72 73
	} else {
		pfn = pgt_buf_end;
		pgt_buf_end += num;
	}

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

		adr = __va((pfn + i) << PAGE_SHIFT);
		clear_page(adr);
	}
74

Y
Yinghai Lu 已提交
75
	return __va(pfn << PAGE_SHIFT);
76 77
}

Y
Yinghai Lu 已提交
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */
#define INIT_PGT_BUF_SIZE	(5 * PAGE_SIZE)
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);
}

93 94 95 96 97 98 99 100
int after_bootmem;

int direct_gbpages
#ifdef CONFIG_DIRECT_GBPAGES
				= 1
#endif
;

101 102 103 104 105 106 107 108 109 110
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
}

111 112 113 114 115 116
struct map_range {
	unsigned long start;
	unsigned long end;
	unsigned page_size_mask;
};

117
static int page_size_mask;
118

119
static void __init probe_page_size_mask(void)
120
{
121 122
	init_gbpages();

123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
#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;
	}
}
145

146 147 148 149 150 151
#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
#define NR_RANGE_MR 5
#endif

152 153 154
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)
155 156 157 158 159 160 161 162 163 164 165 166 167
{
	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;
}

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
/*
 * 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;
		}
	}
}

202 203 204
static int __meminit split_mem_range(struct map_range *mr, int nr_range,
				     unsigned long start,
				     unsigned long end)
205 206 207
{
	unsigned long start_pfn, end_pfn;
	unsigned long pos;
208
	int i;
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

	/* head if not big page alignment ? */
	start_pfn = start >> PAGE_SHIFT;
	pos = start_pfn << PAGE_SHIFT;
#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.
	 */
	if (pos == 0)
		end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT);
	else
		end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
				 << (PMD_SHIFT - PAGE_SHIFT);
#else /* CONFIG_X86_64 */
	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
			<< (PMD_SHIFT - PAGE_SHIFT);
#endif
	if (end_pfn > (end >> PAGE_SHIFT))
		end_pfn = end >> PAGE_SHIFT;
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
		pos = end_pfn << PAGE_SHIFT;
	}

	/* big page (2M) range */
	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
			 << (PMD_SHIFT - PAGE_SHIFT);
#ifdef CONFIG_X86_32
	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
#else /* CONFIG_X86_64 */
	end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
			 << (PUD_SHIFT - PAGE_SHIFT);
	if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
		end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
#endif

	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
		pos = end_pfn << PAGE_SHIFT;
	}

#ifdef CONFIG_X86_64
	/* big page (1G) range */
	start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
			 << (PUD_SHIFT - PAGE_SHIFT);
	end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
	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)));
		pos = end_pfn << PAGE_SHIFT;
	}

	/* tail is not big page (1G) alignment */
	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
			 << (PMD_SHIFT - PAGE_SHIFT);
	end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
		pos = end_pfn << PAGE_SHIFT;
	}
#endif

	/* tail is not big page (2M) alignment */
	start_pfn = pos>>PAGE_SHIFT;
	end_pfn = end>>PAGE_SHIFT;
	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);

	/* 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--;
	}

296 297 298
	if (!after_bootmem)
		adjust_range_page_size_mask(mr, nr_range);

299
	for (i = 0; i < nr_range; i++)
300 301
		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
				mr[i].start, mr[i].end - 1,
302 303 304
			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));

305 306 307
	return nr_range;
}

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
static struct range pfn_mapped[E820_X_MAX];
static int nr_pfn_mapped;

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;
}

336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
/*
 * 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);

354 355 356 357
	for (i = 0; i < nr_range; i++)
		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
						   mr[i].page_size_mask);

358 359
	add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT);

360 361 362
	return ret >> PAGE_SHIFT;
}

363
/*
Y
Yinghai Lu 已提交
364
 * would have hole in the middle or ends, and only ram parts will be mapped.
365
 */
Y
Yinghai Lu 已提交
366 367
static unsigned long __init init_range_memory_mapping(
					   unsigned long range_start,
368
					   unsigned long range_end)
369 370
{
	unsigned long start_pfn, end_pfn;
Y
Yinghai Lu 已提交
371
	unsigned long mapped_ram_size = 0;
372 373 374 375 376 377
	int i;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
		u64 start = (u64)start_pfn << PAGE_SHIFT;
		u64 end = (u64)end_pfn << PAGE_SHIFT;

378
		if (end <= range_start)
379 380
			continue;

381 382 383 384
		if (start < range_start)
			start = range_start;

		if (start >= range_end)
385 386
			continue;

387 388
		if (end > range_end)
			end = range_end;
389

390
		init_memory_mapping(start, end);
Y
Yinghai Lu 已提交
391 392

		mapped_ram_size += end - start;
393
	}
Y
Yinghai Lu 已提交
394 395

	return mapped_ram_size;
396 397
}

Y
Yinghai Lu 已提交
398 399
/* (PUD_SHIFT-PMD_SHIFT)/2 */
#define STEP_SIZE_SHIFT 5
400 401
void __init init_mem_mapping(void)
{
Y
Yinghai Lu 已提交
402 403 404 405 406
	unsigned long end, real_end, start, last_start;
	unsigned long step_size;
	unsigned long addr;
	unsigned long mapped_ram_size = 0;
	unsigned long new_mapped_ram_size;
407

408 409 410
	probe_page_size_mask();

#ifdef CONFIG_X86_64
411
	end = max_pfn << PAGE_SHIFT;
412
#else
413
	end = max_low_pfn << PAGE_SHIFT;
414
#endif
415

416 417
	/* the ISA range is always mapped regardless of memory holes */
	init_memory_mapping(0, ISA_END_ADDRESS);
Y
Yinghai Lu 已提交
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448

	/* xen has big range in reserved near end of ram, skip it at first */
	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE,
			 PAGE_SIZE);
	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;
	while (last_start > ISA_END_ADDRESS) {
		if (last_start > step_size) {
			start = round_down(last_start - 1, step_size);
			if (start < ISA_END_ADDRESS)
				start = ISA_END_ADDRESS;
		} else
			start = ISA_END_ADDRESS;
		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)
			step_size <<= STEP_SIZE_SHIFT;
		mapped_ram_size += new_mapped_ram_size;
	}

	if (real_end < end)
		init_range_memory_mapping(real_end, end);

449 450 451 452 453
#ifdef CONFIG_X86_64
	if (max_pfn > max_low_pfn) {
		/* can we preseve max_low_pfn ?*/
		max_low_pfn = max_pfn;
	}
454 455 456 457
#else
	early_ioremap_page_table_range_init();
	load_cr3(swapper_pg_dir);
	__flush_tlb_all();
458
#endif
459

460
	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
461
}
462

463 464 465 466 467 468 469 470 471 472 473 474
/*
 * 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)
{
475
	if (pagenr < 256)
476 477 478 479 480 481 482 483
		return 1;
	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
		return 0;
	if (!page_is_ram(pagenr))
		return 1;
	return 0;
}

484 485
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
486 487
	unsigned long addr;
	unsigned long begin_aligned, end_aligned;
488

489 490 491 492 493 494 495 496 497 498
	/* 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)
499 500
		return;

501 502
	addr = begin;

503 504 505 506 507 508
	/*
	 * 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
509 510
	printk(KERN_INFO "debug: unmapping init [mem %#010lx-%#010lx]\n",
		begin, end - 1);
511 512 513 514 515
	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
516
	 * writeable and non-executable first.
517
	 */
518
	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
519 520 521 522 523 524 525
	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);

	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);

	for (; addr < end; addr += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(addr));
		init_page_count(virt_to_page(addr));
526
		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
527 528 529 530 531 532 533 534 535 536 537 538
		free_page(addr);
		totalram_pages++;
	}
#endif
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}
539 540

#ifdef CONFIG_BLK_DEV_INITRD
541
void __init free_initrd_mem(unsigned long start, unsigned long end)
542
{
543 544 545 546 547 548 549 550 551 552
	/*
	 * 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
	 */
	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
553 554
}
#endif
P
Pekka Enberg 已提交
555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575

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);
}