init.c 11.7 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 22
unsigned long __initdata pgt_buf_start;
unsigned long __meminitdata pgt_buf_end;
unsigned long __meminitdata pgt_buf_top;
23 24 25 26 27 28 29 30 31

int after_bootmem;

int direct_gbpages
#ifdef CONFIG_DIRECT_GBPAGES
				= 1
#endif
;

32 33 34 35 36 37
struct map_range {
	unsigned long start;
	unsigned long end;
	unsigned page_size_mask;
};

38
static int page_size_mask;
39 40 41 42 43 44
/*
 * First calculate space needed for kernel direct mapping page tables to cover
 * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB
 * pages. Then find enough contiguous space for those page tables.
 */
static void __init find_early_table_space(struct map_range *mr, int nr_range)
45
{
46 47 48
	int i;
	unsigned long puds = 0, pmds = 0, ptes = 0, tables;
	unsigned long start = 0, good_end;
49
	phys_addr_t base;
50

51 52
	for (i = 0; i < nr_range; i++) {
		unsigned long range, extra;
53

54 55
		range = mr[i].end - mr[i].start;
		puds += (range + PUD_SIZE - 1) >> PUD_SHIFT;
56

57 58 59 60 61 62
		if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) {
			extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT);
			pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT;
		} else {
			pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT;
		}
63

64 65
		if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) {
			extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT);
66
#ifdef CONFIG_X86_32
67
			extra += PMD_SIZE;
68
#endif
69 70 71 72 73
			ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
		} else {
			ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT;
		}
	}
74

75 76
	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
77 78 79 80 81 82
	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
T
Takashi Iwai 已提交
83
	good_end = max_pfn_mapped << PAGE_SHIFT;
84

Y
Yinghai Lu 已提交
85
	base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
T
Tejun Heo 已提交
86
	if (!base)
87 88
		panic("Cannot find space for the kernel page tables");

89 90 91
	pgt_buf_start = base >> PAGE_SHIFT;
	pgt_buf_end = pgt_buf_start;
	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
92

93
	printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
94
		mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT,
95
		(pgt_buf_top << PAGE_SHIFT) - 1);
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
void probe_page_size_mask(void)
{
#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;
	}
}
122
void __init native_pagetable_reserve(u64 start, u64 end)
123
{
124
	memblock_reserve(start, end - start);
125 126
}

127 128 129 130 131 132
#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
#define NR_RANGE_MR 5
#endif

133 134 135
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)
136 137 138 139 140 141 142 143 144 145 146 147 148
{
	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;
}

149 150 151
static int __meminit split_mem_range(struct map_range *mr, int nr_range,
				     unsigned long start,
				     unsigned long end)
152 153 154
{
	unsigned long start_pfn, end_pfn;
	unsigned long pos;
155
	int i;
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

	/* 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++)
244 245
		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
				mr[i].start, mr[i].end - 1,
246 247 248
			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));

249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
	return nr_range;
}

/*
 * 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);

270 271 272 273 274 275 276 277
	/*
	 * 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)
278
		find_early_table_space(mr, nr_range);
279 280 281 282 283 284 285 286 287 288 289 290 291

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

#ifdef CONFIG_X86_32
	early_ioremap_page_table_range_init();

	load_cr3(swapper_pg_dir);
#endif

	__flush_tlb_all();

292 293 294 295 296
	/*
	 * Reserve the kernel pagetable pages we used (pgt_buf_start -
	 * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
	 * so that they can be reused for other purposes.
	 *
297 298
	 * On native it just means calling memblock_reserve, on Xen it also
	 * means marking RW the pagetable pages that we allocated before
299 300 301 302 303 304 305 306
	 * but that haven't been used.
	 *
	 * In fact on xen we mark RO the whole range pgt_buf_start -
	 * pgt_buf_top, because we have to make sure that when
	 * init_memory_mapping reaches the pagetable pages area, it maps
	 * RO all the pagetable pages, including the ones that are beyond
	 * pgt_buf_end at that time.
	 */
307
	if (!after_bootmem && pgt_buf_end > pgt_buf_start)
308 309
		x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
				PFN_PHYS(pgt_buf_end));
310 311 312 313 314 315 316

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

	return ret >> PAGE_SHIFT;
}

317

318 319 320 321 322 323 324 325 326 327 328 329
/*
 * 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)
{
330
	if (pagenr < 256)
331 332 333 334 335 336 337 338
		return 1;
	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
		return 0;
	if (!page_is_ram(pagenr))
		return 1;
	return 0;
}

339 340
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
341 342
	unsigned long addr;
	unsigned long begin_aligned, end_aligned;
343

344 345 346 347 348 349 350 351 352 353
	/* 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)
354 355
		return;

356 357
	addr = begin;

358 359 360 361 362 363
	/*
	 * 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
364 365
	printk(KERN_INFO "debug: unmapping init [mem %#010lx-%#010lx]\n",
		begin, end - 1);
366 367 368 369 370
	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
371
	 * writeable and non-executable first.
372
	 */
373
	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
374 375 376 377 378 379 380
	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));
381
		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
382 383 384 385 386 387 388 389 390 391 392 393
		free_page(addr);
		totalram_pages++;
	}
#endif
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}
394 395

#ifdef CONFIG_BLK_DEV_INITRD
396
void __init free_initrd_mem(unsigned long start, unsigned long end)
397
{
398 399 400 401 402 403 404 405 406 407
	/*
	 * 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));
408 409
}
#endif
P
Pekka Enberg 已提交
410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430

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);
}