init.c 11.6 KB
Newer Older
1
#include <linux/initrd.h>
2
#include <linux/ioport.h>
3
#include <linux/swap.h>
4

5
#include <asm/cacheflush.h>
6
#include <asm/e820.h>
7
#include <asm/init.h>
8
#include <asm/page.h>
9
#include <asm/page_types.h>
10
#include <asm/sections.h>
11
#include <asm/setup.h>
12
#include <asm/system.h>
13
#include <asm/tlbflush.h>
14 15 16
#include <asm/tlb.h>

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
17

18 19 20
unsigned long __initdata e820_table_start;
unsigned long __meminitdata e820_table_end;
unsigned long __meminitdata e820_table_top;
21 22 23 24 25 26 27 28 29

int after_bootmem;

int direct_gbpages
#ifdef CONFIG_DIRECT_GBPAGES
				= 1
#endif
;

P
Pekka Enberg 已提交
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
int nx_enabled;

#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
static int disable_nx __cpuinitdata;

/*
 * noexec = on|off
 *
 * Control non-executable mappings for processes.
 *
 * on      Enable
 * off     Disable
 */
static int __init noexec_setup(char *str)
{
	if (!str)
		return -EINVAL;
	if (!strncmp(str, "on", 2)) {
		__supported_pte_mask |= _PAGE_NX;
		disable_nx = 0;
	} else if (!strncmp(str, "off", 3)) {
		disable_nx = 1;
		__supported_pte_mask &= ~_PAGE_NX;
	}
	return 0;
}
early_param("noexec", noexec_setup);
#endif

#ifdef CONFIG_X86_PAE
static void __init set_nx(void)
{
	unsigned int v[4], l, h;

	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);

		if ((v[3] & (1 << 20)) && !disable_nx) {
			rdmsr(MSR_EFER, l, h);
			l |= EFER_NX;
			wrmsr(MSR_EFER, l, h);
			nx_enabled = 1;
			__supported_pte_mask |= _PAGE_NX;
		}
	}
}
#else
static inline void set_nx(void)
{
}
#endif

#ifdef CONFIG_X86_64
void __cpuinit check_efer(void)
{
	unsigned long efer;

	rdmsrl(MSR_EFER, efer);
	if (!(efer & EFER_NX) || disable_nx)
		__supported_pte_mask &= ~_PAGE_NX;
}
#endif

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
static void __init find_early_table_space(unsigned long end, int use_pse,
					  int use_gbpages)
{
	unsigned long puds, pmds, ptes, tables, start;

	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);

	if (use_gbpages) {
		unsigned long extra;

		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
	} else
		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;

	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);

	if (use_pse) {
		unsigned long extra;

		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
#ifdef CONFIG_X86_32
		extra += PMD_SIZE;
#endif
		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
	} else
		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;

	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);

#ifdef CONFIG_X86_32
	/* for fixmap */
	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
#endif

	/*
	 * RED-PEN putting page tables only on node 0 could
	 * cause a hotspot and fill up ZONE_DMA. The page tables
	 * need roughly 0.5KB per GB.
	 */
#ifdef CONFIG_X86_32
	start = 0x7000;
136
#else
137 138
	start = 0x8000;
#endif
139 140
	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
					tables, PAGE_SIZE);
141
	if (e820_table_start == -1UL)
142 143
		panic("Cannot find space for the kernel page tables");

144 145 146
	e820_table_start >>= PAGE_SHIFT;
	e820_table_end = e820_table_start;
	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
147 148

	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
149
		end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT);
150 151 152 153 154 155 156 157 158 159 160 161 162 163
}

struct map_range {
	unsigned long start;
	unsigned long end;
	unsigned page_size_mask;
};

#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
#define NR_RANGE_MR 5
#endif

164 165 166
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)
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
{
	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;
}

#ifdef CONFIG_X86_64
static void __init init_gbpages(void)
{
	if (direct_gbpages && cpu_has_gbpages)
		printk(KERN_INFO "Using GB pages for direct mapping\n");
	else
		direct_gbpages = 0;
}
#else
static inline void init_gbpages(void)
{
}
#endif

/*
 * 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)
{
	unsigned long page_size_mask = 0;
	unsigned long start_pfn, end_pfn;
204
	unsigned long ret = 0;
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
	unsigned long pos;

	struct map_range mr[NR_RANGE_MR];
	int nr_range, i;
	int use_pse, use_gbpages;

	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);

	if (!after_bootmem)
		init_gbpages();

#ifdef CONFIG_DEBUG_PAGEALLOC
	/*
	 * 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.
	 */
	use_pse = use_gbpages = 0;
#else
	use_pse = cpu_has_pse;
	use_gbpages = direct_gbpages;
#endif

	set_nx();
	if (nx_enabled)
		printk(KERN_INFO "NX (Execute Disable) protection: active\n");

	/* 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;
	}

	if (use_gbpages)
		page_size_mask |= 1 << PG_LEVEL_1G;
	if (use_pse)
		page_size_mask |= 1 << PG_LEVEL_2M;

	memset(mr, 0, sizeof(mr));
	nr_range = 0;

	/* 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--;
	}

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

	/*
	 * Find space for the kernel direct mapping tables.
	 *
	 * Later we should allocate these tables in the local node of the
	 * memory mapped. Unfortunately this is done currently before the
	 * nodes are discovered.
	 */
	if (!after_bootmem)
		find_early_table_space(end, use_pse, use_gbpages);

#ifdef CONFIG_X86_32
	for (i = 0; i < nr_range; i++)
354 355
		kernel_physical_mapping_init(mr[i].start, mr[i].end,
					     mr[i].page_size_mask);
356 357 358 359 360 361 362 363 364 365 366 367 368 369
	ret = end;
#else /* CONFIG_X86_64 */
	for (i = 0; i < nr_range; i++)
		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
						   mr[i].page_size_mask);
#endif

#ifdef CONFIG_X86_32
	early_ioremap_page_table_range_init();

	load_cr3(swapper_pg_dir);
#endif

#ifdef CONFIG_X86_64
370 371 372 373
	if (!after_bootmem && !start) {
		pud_t *pud;
		pmd_t *pmd;

374
		mmu_cr4_features = read_cr4();
375 376 377 378 379 380 381 382 383 384 385 386

		/*
		 * _brk_end cannot change anymore, but it and _end may be
		 * located on different 2M pages. cleanup_highmap(), however,
		 * can only consider _end when it runs, so destroy any
		 * mappings beyond _brk_end here.
		 */
		pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
		pmd = pmd_offset(pud, _brk_end - 1);
		while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
			pmd_clear(pmd);
	}
387 388 389
#endif
	__flush_tlb_all();

390 391 392
	if (!after_bootmem && e820_table_end > e820_table_start)
		reserve_early(e820_table_start << PAGE_SHIFT,
				 e820_table_end << PAGE_SHIFT, "PGTABLE");
393 394 395 396 397 398 399

	if (!after_bootmem)
		early_memtest(start, end);

	return ret >> PAGE_SHIFT;
}

400

401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421
/*
 * 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)
{
	if (pagenr <= 256)
		return 1;
	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
		return 0;
	if (!page_is_ram(pagenr))
		return 1;
	return 0;
}

422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
	unsigned long addr = begin;

	if (addr >= end)
		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
	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
		begin, PAGE_ALIGN(end));
	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
	 * writeable first.
	 */
	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));
		memset((void *)(addr & ~(PAGE_SIZE-1)),
			POISON_FREE_INITMEM, PAGE_SIZE);
		free_page(addr);
		totalram_pages++;
	}
#endif
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}
465 466 467 468 469 470 471

#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
	free_init_pages("initrd memory", start, end);
}
#endif