setup_32.c 20.2 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *
 *  Memory region support
 *	David Parsons <orc@pell.chi.il.us>, July-August 1999
 *
 *  Added E820 sanitization routine (removes overlapping memory regions);
 *  Brian Moyle <bmoyle@mvista.com>, February 2001
 *
 * Moved CPU detection code to cpu/${cpu}.c
 *    Patrick Mochel <mochel@osdl.org>, March 2002
 *
 *  Provisions for empty E820 memory regions (reported by certain BIOSes).
 *  Alex Achenbach <xela@slit.de>, December 2002.
 *
 */

/*
 * This file handles the architecture-dependent parts of initialization
 */

#include <linux/sched.h>
#include <linux/mm.h>
26
#include <linux/mmzone.h>
27
#include <linux/screen_info.h>
L
Linus Torvalds 已提交
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42
#include <linux/ioport.h>
#include <linux/acpi.h>
#include <linux/apm_bios.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
#include <linux/seq_file.h>
#include <linux/console.h>
#include <linux/mca.h>
#include <linux/root_dev.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/edd.h>
#include <linux/nodemask.h>
43
#include <linux/kexec.h>
44
#include <linux/crash_dump.h>
45
#include <linux/dmi.h>
D
Dave Hansen 已提交
46
#include <linux/pfn.h>
47
#include <linux/pci.h>
48

L
Linus Torvalds 已提交
49
#include <video/edid.h>
50

51
#include <asm/apic.h>
L
Linus Torvalds 已提交
52 53
#include <asm/e820.h>
#include <asm/mpspec.h>
54
#include <asm/mmzone.h>
L
Linus Torvalds 已提交
55 56 57 58 59 60
#include <asm/setup.h>
#include <asm/arch_hooks.h>
#include <asm/sections.h>
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/io.h>
61
#include <asm/vmi.h>
62
#include <setup_arch.h>
L
Linus Torvalds 已提交
63
#include <bios_ebda.h>
B
Bernhard Walle 已提交
64
#include <asm/cacheflush.h>
L
Linus Torvalds 已提交
65 66 67 68 69 70

/* This value is set up by the early boot code to point to the value
   immediately after the boot time page tables.  It contains a *physical*
   address, and must not be in the .bss segment! */
unsigned long init_pg_tables_end __initdata = ~0UL;

71
int disable_pse __cpuinitdata = 0;
L
Linus Torvalds 已提交
72 73 74 75

/*
 * Machine setup..
 */
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
static struct resource data_resource = {
	.name	= "Kernel data",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource code_resource = {
	.name	= "Kernel code",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource bss_resource = {
	.name	= "Kernel bss",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource video_ram_resource = {
	.name	= "Video RAM area",
	.start	= 0xa0000,
	.end	= 0xbffff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource standard_io_resources[] = { {
	.name	= "dma1",
	.start	= 0x0000,
	.end	= 0x001f,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "pic1",
	.start	= 0x0020,
	.end	= 0x0021,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name   = "timer0",
	.start	= 0x0040,
	.end    = 0x0043,
	.flags  = IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name   = "timer1",
	.start  = 0x0050,
	.end    = 0x0053,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "keyboard",
	.start	= 0x0060,
	.end	= 0x006f,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "dma page reg",
	.start	= 0x0080,
	.end	= 0x008f,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "pic2",
	.start	= 0x00a0,
	.end	= 0x00a1,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "dma2",
	.start	= 0x00c0,
	.end	= 0x00df,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "fpu",
	.start	= 0x00f0,
	.end	= 0x00ff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
} };
L
Linus Torvalds 已提交
150 151

/* cpu data as detected by the assembly code in head.S */
152
struct cpuinfo_x86 new_cpu_data __cpuinitdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
L
Linus Torvalds 已提交
153
/* common cpu data for all cpus */
154
struct cpuinfo_x86 boot_cpu_data __read_mostly = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
155
EXPORT_SYMBOL(boot_cpu_data);
L
Linus Torvalds 已提交
156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174

unsigned long mmu_cr4_features;

/* for MCA, but anyone else can use it if they want */
unsigned int machine_id;
unsigned int machine_submodel_id;
unsigned int BIOS_revision;
unsigned int mca_pentium_flag;

/* Boot loader ID as an integer, for the benefit of proc_dointvec */
int bootloader_type;

/* user-defined highmem size */
static unsigned int highmem_pages = -1;

/*
 * Setup options
 */
struct screen_info screen_info;
175
EXPORT_SYMBOL(screen_info);
L
Linus Torvalds 已提交
176
struct apm_info apm_info;
177
EXPORT_SYMBOL(apm_info);
L
Linus Torvalds 已提交
178
struct edid_info edid_info;
179
EXPORT_SYMBOL_GPL(edid_info);
L
Linus Torvalds 已提交
180
struct ist_info ist_info;
181 182 183 184
#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
	defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
EXPORT_SYMBOL(ist_info);
#endif
L
Linus Torvalds 已提交
185 186 187 188 189 190 191 192 193 194

extern void early_cpu_init(void);
extern int root_mountflags;

unsigned long saved_videomode;

#define RAMDISK_IMAGE_START_MASK  	0x07FF
#define RAMDISK_PROMPT_FLAG		0x8000
#define RAMDISK_LOAD_FLAG		0x4000	

195
static char __initdata command_line[COMMAND_LINE_SIZE];
L
Linus Torvalds 已提交
196

197
struct boot_params __initdata boot_params;
L
Linus Torvalds 已提交
198 199 200 201 202 203 204 205 206 207 208 209 210

#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
struct edd edd;
#ifdef CONFIG_EDD_MODULE
EXPORT_SYMBOL(edd);
#endif
/**
 * copy_edd() - Copy the BIOS EDD information
 *              from boot_params into a safe place.
 *
 */
static inline void copy_edd(void)
{
211 212 213 214 215
     memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer,
	    sizeof(edd.mbr_signature));
     memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info));
     edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries;
     edd.edd_info_nr = boot_params.eddbuf_entries;
L
Linus Torvalds 已提交
216 217 218 219 220 221 222
}
#else
static inline void copy_edd(void)
{
}
#endif

223
int __initdata user_defined_memmap = 0;
L
Linus Torvalds 已提交
224

225 226 227 228 229 230 231 232 233 234 235 236 237 238
/*
 * "mem=nopentium" disables the 4MB page tables.
 * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
 * to <mem>, overriding the bios size.
 * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from
 * <start> to <start>+<mem>, overriding the bios size.
 *
 * HPA tells me bootloaders need to parse mem=, so no new
 * option should be mem=  [also see Documentation/i386/boot.txt]
 */
static int __init parse_mem(char *arg)
{
	if (!arg)
		return -EINVAL;
L
Linus Torvalds 已提交
239

240
	if (strcmp(arg, "nopentium") == 0) {
241
		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PSE);
242 243 244 245 246 247 248
		disable_pse = 1;
	} else {
		/* If the user specifies memory size, we
		 * limit the BIOS-provided memory map to
		 * that size. exactmap can be used to specify
		 * the exact map. mem=number can be used to
		 * trim the existing memory map.
L
Linus Torvalds 已提交
249
		 */
250
		unsigned long long mem_size;
L
Linus Torvalds 已提交
251
 
252 253 254 255 256 257 258
		mem_size = memparse(arg, &arg);
		limit_regions(mem_size);
		user_defined_memmap = 1;
	}
	return 0;
}
early_param("mem", parse_mem);
L
Linus Torvalds 已提交
259

260 261 262 263 264 265 266 267
#ifdef CONFIG_PROC_VMCORE
/* elfcorehdr= specifies the location of elf core header
 * stored by the crashed kernel.
 */
static int __init parse_elfcorehdr(char *arg)
{
	if (!arg)
		return -EINVAL;
268

269 270 271 272 273
	elfcorehdr_addr = memparse(arg, &arg);
	return 0;
}
early_param("elfcorehdr", parse_elfcorehdr);
#endif /* CONFIG_PROC_VMCORE */
L
Linus Torvalds 已提交
274

275 276 277 278 279 280 281 282 283
/*
 * highmem=size forces highmem to be exactly 'size' bytes.
 * This works even on boxes that have no highmem otherwise.
 * This also works to reduce highmem size on bigger boxes.
 */
static int __init parse_highmem(char *arg)
{
	if (!arg)
		return -EINVAL;
284

285 286 287 288
	highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT;
	return 0;
}
early_param("highmem", parse_highmem);
289

290 291 292 293 294 295 296 297 298
/*
 * vmalloc=size forces the vmalloc area to be exactly 'size'
 * bytes. This can be used to increase (or decrease) the
 * vmalloc area - the default is 128m.
 */
static int __init parse_vmalloc(char *arg)
{
	if (!arg)
		return -EINVAL;
299

300 301
	__VMALLOC_RESERVE = memparse(arg, &arg);
	return 0;
L
Linus Torvalds 已提交
302
}
303
early_param("vmalloc", parse_vmalloc);
L
Linus Torvalds 已提交
304

305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
/*
 * reservetop=size reserves a hole at the top of the kernel address space which
 * a hypervisor can load into later.  Needed for dynamically loaded hypervisors,
 * so relocating the fixmap can be done before paging initialization.
 */
static int __init parse_reservetop(char *arg)
{
	unsigned long address;

	if (!arg)
		return -EINVAL;

	address = memparse(arg, &arg);
	reserve_top_address(address);
	return 0;
}
early_param("reservetop", parse_reservetop);

L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
/*
 * Determine low and high memory ranges:
 */
unsigned long __init find_max_low_pfn(void)
{
	unsigned long max_low_pfn;

	max_low_pfn = max_pfn;
	if (max_low_pfn > MAXMEM_PFN) {
		if (highmem_pages == -1)
			highmem_pages = max_pfn - MAXMEM_PFN;
		if (highmem_pages + MAXMEM_PFN < max_pfn)
			max_pfn = MAXMEM_PFN + highmem_pages;
		if (highmem_pages + MAXMEM_PFN > max_pfn) {
			printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages));
			highmem_pages = 0;
		}
		max_low_pfn = MAXMEM_PFN;
#ifndef CONFIG_HIGHMEM
		/* Maximum memory usable is what is directly addressable */
		printk(KERN_WARNING "Warning only %ldMB will be used.\n",
					MAXMEM>>20);
		if (max_pfn > MAX_NONPAE_PFN)
346
			printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
L
Linus Torvalds 已提交
347 348 349 350
		else
			printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
		max_pfn = MAXMEM_PFN;
#else /* !CONFIG_HIGHMEM */
351
#ifndef CONFIG_HIGHMEM64G
L
Linus Torvalds 已提交
352 353 354
		if (max_pfn > MAX_NONPAE_PFN) {
			max_pfn = MAX_NONPAE_PFN;
			printk(KERN_WARNING "Warning only 4GB will be used.\n");
355
			printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
L
Linus Torvalds 已提交
356
		}
357
#endif /* !CONFIG_HIGHMEM64G */
L
Linus Torvalds 已提交
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
#endif /* !CONFIG_HIGHMEM */
	} else {
		if (highmem_pages == -1)
			highmem_pages = 0;
#ifdef CONFIG_HIGHMEM
		if (highmem_pages >= max_pfn) {
			printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
			highmem_pages = 0;
		}
		if (highmem_pages) {
			if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){
				printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages));
				highmem_pages = 0;
			}
			max_low_pfn -= highmem_pages;
		}
#else
		if (highmem_pages)
			printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
#endif
	}
	return max_low_pfn;
}

/*
 * workaround for Dell systems that neglect to reserve EBDA
 */
static void __init reserve_ebda_region(void)
{
	unsigned int addr;
	addr = get_bios_ebda();
	if (addr)
		reserve_bootmem(addr, PAGE_SIZE);	
}

393
#ifndef CONFIG_NEED_MULTIPLE_NODES
L
Linus Torvalds 已提交
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
void __init setup_bootmem_allocator(void);
static unsigned long __init setup_memory(void)
{
	/*
	 * partially used pages are not usable - thus
	 * we are rounding upwards:
	 */
	min_low_pfn = PFN_UP(init_pg_tables_end);

	find_max_pfn();

	max_low_pfn = find_max_low_pfn();

#ifdef CONFIG_HIGHMEM
	highstart_pfn = highend_pfn = max_pfn;
	if (max_pfn > max_low_pfn) {
		highstart_pfn = max_low_pfn;
	}
	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
		pages_to_mb(highend_pfn - highstart_pfn));
414 415 416 417 418 419 420 421
	num_physpages = highend_pfn;
	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
	num_physpages = max_low_pfn;
	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
#ifdef CONFIG_FLATMEM
	max_mapnr = num_physpages;
L
Linus Torvalds 已提交
422 423 424 425 426 427 428 429 430 431 432
#endif
	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
			pages_to_mb(max_low_pfn));

	setup_bootmem_allocator();

	return max_low_pfn;
}

void __init zone_sizes_init(void)
{
433 434 435 436 437
	unsigned long max_zone_pfns[MAX_NR_ZONES];
	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] =
		virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
L
Linus Torvalds 已提交
438
#ifdef CONFIG_HIGHMEM
439
	max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
440 441 442
	add_active_range(0, 0, highend_pfn);
#else
	add_active_range(0, 0, max_low_pfn);
L
Linus Torvalds 已提交
443
#endif
444 445

	free_area_init_nodes(max_zone_pfns);
L
Linus Torvalds 已提交
446 447
}
#else
448
extern unsigned long __init setup_memory(void);
L
Linus Torvalds 已提交
449
extern void zone_sizes_init(void);
450
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
L
Linus Torvalds 已提交
451

452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
static inline unsigned long long get_total_mem(void)
{
	unsigned long long total;

	total = max_low_pfn - min_low_pfn;
#ifdef CONFIG_HIGHMEM
	total += highend_pfn - highstart_pfn;
#endif

	return total << PAGE_SHIFT;
}

#ifdef CONFIG_KEXEC
static void __init reserve_crashkernel(void)
{
	unsigned long long total_mem;
	unsigned long long crash_size, crash_base;
	int ret;

	total_mem = get_total_mem();

	ret = parse_crashkernel(boot_command_line, total_mem,
			&crash_size, &crash_base);
	if (ret == 0 && crash_size > 0) {
		if (crash_base > 0) {
			printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
					"for crashkernel (System RAM: %ldMB)\n",
					(unsigned long)(crash_size >> 20),
					(unsigned long)(crash_base >> 20),
					(unsigned long)(total_mem >> 20));
			crashk_res.start = crash_base;
			crashk_res.end   = crash_base + crash_size - 1;
			reserve_bootmem(crash_base, crash_size);
		} else
			printk(KERN_INFO "crashkernel reservation failed - "
					"you have to specify a base address\n");
	}
}
#else
static inline void __init reserve_crashkernel(void)
{}
#endif

L
Linus Torvalds 已提交
495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510
void __init setup_bootmem_allocator(void)
{
	unsigned long bootmap_size;
	/*
	 * Initialize the boot-time allocator (with low memory only):
	 */
	bootmap_size = init_bootmem(min_low_pfn, max_low_pfn);

	register_bootmem_low_pages(max_low_pfn);

	/*
	 * Reserve the bootmem bitmap itself as well. We do this in two
	 * steps (first step was init_bootmem()) because this catches
	 * the (very unlikely) case of us accidentally initializing the
	 * bootmem allocator with an invalid RAM area.
	 */
511 512
	reserve_bootmem(__pa_symbol(_text), (PFN_PHYS(min_low_pfn) +
			 bootmap_size + PAGE_SIZE-1) - __pa_symbol(_text));
L
Linus Torvalds 已提交
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

	/*
	 * reserve physical page 0 - it's a special BIOS page on many boxes,
	 * enabling clean reboots, SMP operation, laptop functions.
	 */
	reserve_bootmem(0, PAGE_SIZE);

	/* reserve EBDA region, it's a 4K region */
	reserve_ebda_region();

    /* could be an AMD 768MPX chipset. Reserve a page  before VGA to prevent
       PCI prefetch into it (errata #56). Usually the page is reserved anyways,
       unless you have no PS/2 mouse plugged in. */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
	    boot_cpu_data.x86 == 6)
	     reserve_bootmem(0xa0000 - 4096, 4096);

#ifdef CONFIG_SMP
	/*
	 * But first pinch a few for the stack/trampoline stuff
	 * FIXME: Don't need the extra page at 4K, but need to fix
	 * trampoline before removing it. (see the GDT stuff)
	 */
	reserve_bootmem(PAGE_SIZE, PAGE_SIZE);
#endif
L
Len Brown 已提交
538
#ifdef CONFIG_ACPI_SLEEP
L
Linus Torvalds 已提交
539 540 541 542 543 544 545 546 547 548 549
	/*
	 * Reserve low memory region for sleep support.
	 */
	acpi_reserve_bootmem();
#endif
#ifdef CONFIG_X86_FIND_SMP_CONFIG
	/*
	 * Find and reserve possible boot-time SMP configuration:
	 */
	find_smp_config();
#endif
550
	numa_kva_reserve();
L
Linus Torvalds 已提交
551
#ifdef CONFIG_BLK_DEV_INITRD
552 553 554 555 556 557 558 559 560 561 562
	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
		unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT;

		if (ramdisk_end <= end_of_lowmem) {
			reserve_bootmem(ramdisk_image, ramdisk_size);
			initrd_start = ramdisk_image + PAGE_OFFSET;
			initrd_end = initrd_start+ramdisk_size;
		} else {
L
Linus Torvalds 已提交
563
			printk(KERN_ERR "initrd extends beyond end of memory "
564 565
			       "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
			       ramdisk_end, end_of_lowmem);
L
Linus Torvalds 已提交
566 567 568 569
			initrd_start = 0;
		}
	}
#endif
570
	reserve_crashkernel();
L
Linus Torvalds 已提交
571 572 573 574 575 576 577 578 579 580
}

/*
 * The node 0 pgdat is initialized before all of these because
 * it's needed for bootmem.  node>0 pgdats have their virtual
 * space allocated before the pagetables are in place to access
 * them, so they can't be cleared then.
 *
 * This should all compile down to nothing when NUMA is off.
 */
A
Adrian Bunk 已提交
581
static void __init remapped_pgdat_init(void)
L
Linus Torvalds 已提交
582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599
{
	int nid;

	for_each_online_node(nid) {
		if (nid != 0)
			memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
	}
}

#ifdef CONFIG_MCA
static void set_mca_bus(int x)
{
	MCA_bus = x;
}
#else
static void set_mca_bus(int x) { }
#endif

600
/* Overridden in paravirt.c if CONFIG_PARAVIRT */
601
char * __init __attribute__((weak)) memory_setup(void)
602 603 604 605
{
	return machine_specific_memory_setup();
}

L
Linus Torvalds 已提交
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621
/*
 * Determine if we were loaded by an EFI loader.  If so, then we have also been
 * passed the efi memmap, systab, etc., so we should use these data structures
 * for initialization.  Note, the efi init code path is determined by the
 * global efi_enabled. This allows the same kernel image to be used on existing
 * systems (with a traditional BIOS) as well as on EFI systems.
 */
void __init setup_arch(char **cmdline_p)
{
	unsigned long max_low_pfn;

	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
	pre_setup_arch_hook();
	early_cpu_init();

#ifdef CONFIG_EFI
622 623
	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
		     "EL32", 4))
L
Linus Torvalds 已提交
624 625 626
		efi_enabled = 1;
#endif

627 628 629 630 631 632 633 634 635 636 637
	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
	screen_info = boot_params.screen_info;
	edid_info = boot_params.edid_info;
	apm_info.bios = boot_params.apm_bios_info;
	ist_info = boot_params.ist_info;
	saved_videomode = boot_params.hdr.vid_mode;
	if( boot_params.sys_desc_table.length != 0 ) {
		set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2);
		machine_id = boot_params.sys_desc_table.table[0];
		machine_submodel_id = boot_params.sys_desc_table.table[1];
		BIOS_revision = boot_params.sys_desc_table.table[2];
L
Linus Torvalds 已提交
638
	}
639
	bootloader_type = boot_params.hdr.type_of_loader;
L
Linus Torvalds 已提交
640 641

#ifdef CONFIG_BLK_DEV_RAM
642 643 644
	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
L
Linus Torvalds 已提交
645 646
#endif
	ARCH_SETUP
647 648 649 650

	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
	print_memory_map(memory_setup());

L
Linus Torvalds 已提交
651 652
	copy_edd();

653
	if (!boot_params.hdr.root_flags)
L
Linus Torvalds 已提交
654 655 656 657 658 659 660 661 662 663
		root_mountflags &= ~MS_RDONLY;
	init_mm.start_code = (unsigned long) _text;
	init_mm.end_code = (unsigned long) _etext;
	init_mm.end_data = (unsigned long) _edata;
	init_mm.brk = init_pg_tables_end + PAGE_OFFSET;

	code_resource.start = virt_to_phys(_text);
	code_resource.end = virt_to_phys(_etext)-1;
	data_resource.start = virt_to_phys(_etext);
	data_resource.end = virt_to_phys(_edata)-1;
B
Bernhard Walle 已提交
664 665
	bss_resource.start = virt_to_phys(&__bss_start);
	bss_resource.end = virt_to_phys(&__bss_stop)-1;
L
Linus Torvalds 已提交
666

667
	parse_early_param();
L
Linus Torvalds 已提交
668

669 670 671
	if (user_defined_memmap) {
		printk(KERN_INFO "user-defined physical RAM map:\n");
		print_memory_map("user");
672
	}
673

674
	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
675
	*cmdline_p = command_line;
676

677 678 679
	if (efi_enabled)
		efi_init();

L
Linus Torvalds 已提交
680 681
	max_low_pfn = setup_memory();

682 683 684 685 686 687 688 689
#ifdef CONFIG_VMI
	/*
	 * Must be after max_low_pfn is determined, and before kernel
	 * pagetables are setup.
	 */
	vmi_init();
#endif

L
Linus Torvalds 已提交
690 691 692
	/*
	 * NOTE: before this point _nobody_ is allowed to allocate
	 * any memory using the bootmem allocator.  Although the
S
Simon Arlott 已提交
693
	 * allocator is now initialised only the first 8Mb of the kernel
L
Linus Torvalds 已提交
694 695 696 697 698 699 700 701 702 703 704
	 * virtual address space has been mapped.  All allocations before
	 * paging_init() has completed must use the alloc_bootmem_low_pages()
	 * variant (which allocates DMA'able memory) and care must be taken
	 * not to exceed the 8Mb limit.
	 */

#ifdef CONFIG_SMP
	smp_alloc_memory(); /* AP processor realmode stacks in low memory*/
#endif
	paging_init();
	remapped_pgdat_init();
705
	sparse_init();
L
Linus Torvalds 已提交
706 707 708 709 710 711
	zone_sizes_init();

	/*
	 * NOTE: at this point the bootmem allocator is fully available.
	 */

712 713
	paravirt_post_allocator_init();

L
Linus Torvalds 已提交
714 715
	dmi_scan_machine();

716 717
	io_delay_init();;

L
Linus Torvalds 已提交
718
#ifdef CONFIG_X86_GENERICARCH
719
	generic_apic_probe();
L
Linus Torvalds 已提交
720 721 722 723
#endif	
	if (efi_enabled)
		efi_map_memmap();

L
Len Brown 已提交
724
#ifdef CONFIG_ACPI
L
Linus Torvalds 已提交
725 726 727 728
	/*
	 * Parse the ACPI tables for possible boot-time SMP configuration.
	 */
	acpi_boot_table_init();
729 730
#endif

731
	early_quirks();
732 733

#ifdef CONFIG_ACPI
L
Linus Torvalds 已提交
734 735
	acpi_boot_init();

736 737 738 739 740 741 742
#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC)
	if (def_to_bigsmp)
		printk(KERN_WARNING "More than 8 CPUs detected and "
			"CONFIG_X86_PC cannot handle it.\nUse "
			"CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
#endif
#endif
L
Linus Torvalds 已提交
743 744 745 746 747
#ifdef CONFIG_X86_LOCAL_APIC
	if (smp_found_config)
		get_smp_config();
#endif

748
	e820_register_memory();
749
	e820_mark_nosave_regions();
L
Linus Torvalds 已提交
750 751 752 753 754 755 756 757 758 759

#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
		conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
	conswitchp = &dummy_con;
#endif
#endif
}
760 761 762 763 764 765 766 767 768 769 770 771

/*
 * Request address space for all standard resources
 *
 * This is called just before pcibios_init(), which is also a
 * subsys_initcall, but is linked in later (in arch/i386/pci/common.c).
 */
static int __init request_standard_resources(void)
{
	int i;

	printk(KERN_INFO "Setting up standard PCI resources\n");
772
	init_iomem_resources(&code_resource, &data_resource, &bss_resource);
773 774 775 776 777 778 779 780 781 782

	request_resource(&iomem_resource, &video_ram_resource);

	/* request I/O space for devices used on all i[345]86 PCs */
	for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++)
		request_resource(&ioport_resource, &standard_io_resources[i]);
	return 0;
}

subsys_initcall(request_standard_resources);