blob: 8c08660b4e5dd6c2411fb79fa62cbc557f751a70 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * linux/arch/i386/kernel/setup.c
3 *
4 * Copyright (C) 1995 Linus Torvalds
5 *
6 * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
7 *
8 * Memory region support
9 * David Parsons <orc@pell.chi.il.us>, July-August 1999
10 *
11 * Added E820 sanitization routine (removes overlapping memory regions);
12 * Brian Moyle <bmoyle@mvista.com>, February 2001
13 *
14 * Moved CPU detection code to cpu/${cpu}.c
15 * Patrick Mochel <mochel@osdl.org>, March 2002
16 *
17 * Provisions for empty E820 memory regions (reported by certain BIOSes).
18 * Alex Achenbach <xela@slit.de>, December 2002.
19 *
20 */
21
22/*
23 * This file handles the architecture-dependent parts of initialization
24 */
25
Alexey Dobriyan129f6942005-06-23 00:08:33 -070026#include <linux/config.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070027#include <linux/sched.h>
28#include <linux/mm.h>
Andy Whitcroft05b79bd2005-06-23 00:07:57 -070029#include <linux/mmzone.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070030#include <linux/tty.h>
31#include <linux/ioport.h>
32#include <linux/acpi.h>
33#include <linux/apm_bios.h>
34#include <linux/initrd.h>
35#include <linux/bootmem.h>
36#include <linux/seq_file.h>
37#include <linux/console.h>
38#include <linux/mca.h>
39#include <linux/root_dev.h>
40#include <linux/highmem.h>
41#include <linux/module.h>
42#include <linux/efi.h>
43#include <linux/init.h>
44#include <linux/edd.h>
45#include <linux/nodemask.h>
Eric W. Biederman1bc3b912005-06-25 14:58:01 -070046#include <linux/kexec.h>
Vivek Goyal2030eae2005-06-25 14:58:20 -070047#include <linux/crash_dump.h>
Andi Kleene9928672006-01-11 22:43:33 +010048#include <linux/dmi.h>
Dave Hansen22a98352006-03-27 01:16:04 -080049#include <linux/pfn.h>
Eric W. Biederman1bc3b912005-06-25 14:58:01 -070050
Linus Torvalds1da177e2005-04-16 15:20:36 -070051#include <video/edid.h>
Eric W. Biederman1bc3b912005-06-25 14:58:01 -070052
Eric W. Biederman9635b472005-06-25 14:57:41 -070053#include <asm/apic.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070054#include <asm/e820.h>
55#include <asm/mpspec.h>
56#include <asm/setup.h>
57#include <asm/arch_hooks.h>
58#include <asm/sections.h>
59#include <asm/io_apic.h>
60#include <asm/ist.h>
61#include <asm/io.h>
62#include "setup_arch_pre.h"
63#include <bios_ebda.h>
64
Vivek Goyal92aa63a2005-06-25 14:58:18 -070065/* Forward Declaration. */
66void __init find_max_pfn(void);
67
Linus Torvalds1da177e2005-04-16 15:20:36 -070068/* This value is set up by the early boot code to point to the value
69 immediately after the boot time page tables. It contains a *physical*
70 address, and must not be in the .bss segment! */
71unsigned long init_pg_tables_end __initdata = ~0UL;
72
Li Shaohua0bb31842005-06-25 14:54:55 -070073int disable_pse __devinitdata = 0;
Linus Torvalds1da177e2005-04-16 15:20:36 -070074
75/*
76 * Machine setup..
77 */
78
79#ifdef CONFIG_EFI
80int efi_enabled = 0;
81EXPORT_SYMBOL(efi_enabled);
82#endif
83
84/* cpu data as detected by the assembly code in head.S */
85struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
86/* common cpu data for all cpus */
Christoph Lameterc3d8c142005-09-06 15:16:33 -070087struct cpuinfo_x86 boot_cpu_data __read_mostly = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
Alexey Dobriyan129f6942005-06-23 00:08:33 -070088EXPORT_SYMBOL(boot_cpu_data);
Linus Torvalds1da177e2005-04-16 15:20:36 -070089
90unsigned long mmu_cr4_features;
91
Len Brown84663612005-08-24 12:09:07 -040092#ifdef CONFIG_ACPI
Linus Torvalds1da177e2005-04-16 15:20:36 -070093 int acpi_disabled = 0;
94#else
95 int acpi_disabled = 1;
96#endif
97EXPORT_SYMBOL(acpi_disabled);
98
Len Brown888ba6c2005-08-24 12:07:20 -040099#ifdef CONFIG_ACPI
Linus Torvalds1da177e2005-04-16 15:20:36 -0700100int __initdata acpi_force = 0;
101extern acpi_interrupt_flags acpi_sci_flags;
102#endif
103
104/* for MCA, but anyone else can use it if they want */
105unsigned int machine_id;
Alexey Dobriyan129f6942005-06-23 00:08:33 -0700106#ifdef CONFIG_MCA
107EXPORT_SYMBOL(machine_id);
108#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700109unsigned int machine_submodel_id;
110unsigned int BIOS_revision;
111unsigned int mca_pentium_flag;
112
113/* For PCI or other memory-mapped resources */
114unsigned long pci_mem_start = 0x10000000;
Alexey Dobriyan129f6942005-06-23 00:08:33 -0700115#ifdef CONFIG_PCI
116EXPORT_SYMBOL(pci_mem_start);
117#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700118
119/* Boot loader ID as an integer, for the benefit of proc_dointvec */
120int bootloader_type;
121
122/* user-defined highmem size */
123static unsigned int highmem_pages = -1;
124
125/*
126 * Setup options
127 */
128struct drive_info_struct { char dummy[32]; } drive_info;
Alexey Dobriyan129f6942005-06-23 00:08:33 -0700129#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || \
130 defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
131EXPORT_SYMBOL(drive_info);
132#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700133struct screen_info screen_info;
Alexey Dobriyan129f6942005-06-23 00:08:33 -0700134EXPORT_SYMBOL(screen_info);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700135struct apm_info apm_info;
Alexey Dobriyan129f6942005-06-23 00:08:33 -0700136EXPORT_SYMBOL(apm_info);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700137struct sys_desc_table_struct {
138 unsigned short length;
139 unsigned char table[0];
140};
141struct edid_info edid_info;
Antonino A. Daplas5e518d72005-09-09 13:04:34 -0700142EXPORT_SYMBOL_GPL(edid_info);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700143struct ist_info ist_info;
Alexey Dobriyan129f6942005-06-23 00:08:33 -0700144#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
145 defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
146EXPORT_SYMBOL(ist_info);
147#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700148struct e820map e820;
149
150extern void early_cpu_init(void);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700151extern void generic_apic_probe(char *);
152extern int root_mountflags;
153
154unsigned long saved_videomode;
155
156#define RAMDISK_IMAGE_START_MASK 0x07FF
157#define RAMDISK_PROMPT_FLAG 0x8000
158#define RAMDISK_LOAD_FLAG 0x4000
159
160static char command_line[COMMAND_LINE_SIZE];
161
162unsigned char __initdata boot_params[PARAM_SIZE];
163
164static struct resource data_resource = {
165 .name = "Kernel data",
166 .start = 0,
167 .end = 0,
168 .flags = IORESOURCE_BUSY | IORESOURCE_MEM
169};
170
171static struct resource code_resource = {
172 .name = "Kernel code",
173 .start = 0,
174 .end = 0,
175 .flags = IORESOURCE_BUSY | IORESOURCE_MEM
176};
177
178static struct resource system_rom_resource = {
179 .name = "System ROM",
180 .start = 0xf0000,
181 .end = 0xfffff,
182 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
183};
184
185static struct resource extension_rom_resource = {
186 .name = "Extension ROM",
187 .start = 0xe0000,
188 .end = 0xeffff,
189 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
190};
191
192static struct resource adapter_rom_resources[] = { {
193 .name = "Adapter ROM",
194 .start = 0xc8000,
195 .end = 0,
196 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
197}, {
198 .name = "Adapter ROM",
199 .start = 0,
200 .end = 0,
201 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
202}, {
203 .name = "Adapter ROM",
204 .start = 0,
205 .end = 0,
206 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
207}, {
208 .name = "Adapter ROM",
209 .start = 0,
210 .end = 0,
211 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
212}, {
213 .name = "Adapter ROM",
214 .start = 0,
215 .end = 0,
216 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
217}, {
218 .name = "Adapter ROM",
219 .start = 0,
220 .end = 0,
221 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
222} };
223
224#define ADAPTER_ROM_RESOURCES \
225 (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0])
226
227static struct resource video_rom_resource = {
228 .name = "Video ROM",
229 .start = 0xc0000,
230 .end = 0xc7fff,
231 .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
232};
233
234static struct resource video_ram_resource = {
235 .name = "Video RAM area",
236 .start = 0xa0000,
237 .end = 0xbffff,
238 .flags = IORESOURCE_BUSY | IORESOURCE_MEM
239};
240
241static struct resource standard_io_resources[] = { {
242 .name = "dma1",
243 .start = 0x0000,
244 .end = 0x001f,
245 .flags = IORESOURCE_BUSY | IORESOURCE_IO
246}, {
247 .name = "pic1",
248 .start = 0x0020,
249 .end = 0x0021,
250 .flags = IORESOURCE_BUSY | IORESOURCE_IO
251}, {
252 .name = "timer0",
253 .start = 0x0040,
254 .end = 0x0043,
255 .flags = IORESOURCE_BUSY | IORESOURCE_IO
256}, {
257 .name = "timer1",
258 .start = 0x0050,
259 .end = 0x0053,
260 .flags = IORESOURCE_BUSY | IORESOURCE_IO
261}, {
262 .name = "keyboard",
263 .start = 0x0060,
264 .end = 0x006f,
265 .flags = IORESOURCE_BUSY | IORESOURCE_IO
266}, {
267 .name = "dma page reg",
268 .start = 0x0080,
269 .end = 0x008f,
270 .flags = IORESOURCE_BUSY | IORESOURCE_IO
271}, {
272 .name = "pic2",
273 .start = 0x00a0,
274 .end = 0x00a1,
275 .flags = IORESOURCE_BUSY | IORESOURCE_IO
276}, {
277 .name = "dma2",
278 .start = 0x00c0,
279 .end = 0x00df,
280 .flags = IORESOURCE_BUSY | IORESOURCE_IO
281}, {
282 .name = "fpu",
283 .start = 0x00f0,
284 .end = 0x00ff,
285 .flags = IORESOURCE_BUSY | IORESOURCE_IO
286} };
287
288#define STANDARD_IO_RESOURCES \
289 (sizeof standard_io_resources / sizeof standard_io_resources[0])
290
291#define romsignature(x) (*(unsigned short *)(x) == 0xaa55)
292
293static int __init romchecksum(unsigned char *rom, unsigned long length)
294{
295 unsigned char *p, sum = 0;
296
297 for (p = rom; p < rom + length; p++)
298 sum += *p;
299 return sum == 0;
300}
301
302static void __init probe_roms(void)
303{
304 unsigned long start, length, upper;
305 unsigned char *rom;
306 int i;
307
308 /* video rom */
309 upper = adapter_rom_resources[0].start;
310 for (start = video_rom_resource.start; start < upper; start += 2048) {
311 rom = isa_bus_to_virt(start);
312 if (!romsignature(rom))
313 continue;
314
315 video_rom_resource.start = start;
316
317 /* 0 < length <= 0x7f * 512, historically */
318 length = rom[2] * 512;
319
320 /* if checksum okay, trust length byte */
321 if (length && romchecksum(rom, length))
322 video_rom_resource.end = start + length - 1;
323
324 request_resource(&iomem_resource, &video_rom_resource);
325 break;
326 }
327
328 start = (video_rom_resource.end + 1 + 2047) & ~2047UL;
329 if (start < upper)
330 start = upper;
331
332 /* system rom */
333 request_resource(&iomem_resource, &system_rom_resource);
334 upper = system_rom_resource.start;
335
336 /* check for extension rom (ignore length byte!) */
337 rom = isa_bus_to_virt(extension_rom_resource.start);
338 if (romsignature(rom)) {
339 length = extension_rom_resource.end - extension_rom_resource.start + 1;
340 if (romchecksum(rom, length)) {
341 request_resource(&iomem_resource, &extension_rom_resource);
342 upper = extension_rom_resource.start;
343 }
344 }
345
346 /* check for adapter roms on 2k boundaries */
347 for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) {
348 rom = isa_bus_to_virt(start);
349 if (!romsignature(rom))
350 continue;
351
352 /* 0 < length <= 0x7f * 512, historically */
353 length = rom[2] * 512;
354
355 /* but accept any length that fits if checksum okay */
356 if (!length || start + length > upper || !romchecksum(rom, length))
357 continue;
358
359 adapter_rom_resources[i].start = start;
360 adapter_rom_resources[i].end = start + length - 1;
361 request_resource(&iomem_resource, &adapter_rom_resources[i]);
362
363 start = adapter_rom_resources[i++].end & ~2047UL;
364 }
365}
366
367static void __init limit_regions(unsigned long long size)
368{
369 unsigned long long current_addr = 0;
370 int i;
371
372 if (efi_enabled) {
Matt Tolentino7ae65fd2005-09-03 15:56:27 -0700373 efi_memory_desc_t *md;
374 void *p;
375
376 for (p = memmap.map, i = 0; p < memmap.map_end;
377 p += memmap.desc_size, i++) {
378 md = p;
379 current_addr = md->phys_addr + (md->num_pages << 12);
380 if (md->type == EFI_CONVENTIONAL_MEMORY) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700381 if (current_addr >= size) {
Matt Tolentino7ae65fd2005-09-03 15:56:27 -0700382 md->num_pages -=
Linus Torvalds1da177e2005-04-16 15:20:36 -0700383 (((current_addr-size) + PAGE_SIZE-1) >> PAGE_SHIFT);
384 memmap.nr_map = i + 1;
385 return;
386 }
387 }
388 }
389 }
390 for (i = 0; i < e820.nr_map; i++) {
Dave Hansenf014a552005-10-30 14:59:37 -0800391 current_addr = e820.map[i].addr + e820.map[i].size;
392 if (current_addr < size)
393 continue;
394
395 if (e820.map[i].type != E820_RAM)
396 continue;
397
398 if (e820.map[i].addr >= size) {
399 /*
400 * This region starts past the end of the
401 * requested size, skip it completely.
402 */
403 e820.nr_map = i;
404 } else {
405 e820.nr_map = i + 1;
406 e820.map[i].size -= current_addr - size;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700407 }
Dave Hansenf014a552005-10-30 14:59:37 -0800408 return;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700409 }
410}
411
412static void __init add_memory_region(unsigned long long start,
413 unsigned long long size, int type)
414{
415 int x;
416
417 if (!efi_enabled) {
418 x = e820.nr_map;
419
420 if (x == E820MAX) {
421 printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
422 return;
423 }
424
425 e820.map[x].addr = start;
426 e820.map[x].size = size;
427 e820.map[x].type = type;
428 e820.nr_map++;
429 }
430} /* add_memory_region */
431
432#define E820_DEBUG 1
433
434static void __init print_memory_map(char *who)
435{
436 int i;
437
438 for (i = 0; i < e820.nr_map; i++) {
439 printk(" %s: %016Lx - %016Lx ", who,
440 e820.map[i].addr,
441 e820.map[i].addr + e820.map[i].size);
442 switch (e820.map[i].type) {
443 case E820_RAM: printk("(usable)\n");
444 break;
445 case E820_RESERVED:
446 printk("(reserved)\n");
447 break;
448 case E820_ACPI:
449 printk("(ACPI data)\n");
450 break;
451 case E820_NVS:
452 printk("(ACPI NVS)\n");
453 break;
454 default: printk("type %lu\n", e820.map[i].type);
455 break;
456 }
457 }
458}
459
460/*
461 * Sanitize the BIOS e820 map.
462 *
463 * Some e820 responses include overlapping entries. The following
464 * replaces the original e820 map with a new one, removing overlaps.
465 *
466 */
467struct change_member {
468 struct e820entry *pbios; /* pointer to original bios entry */
469 unsigned long long addr; /* address for this change point */
470};
471static struct change_member change_point_list[2*E820MAX] __initdata;
472static struct change_member *change_point[2*E820MAX] __initdata;
473static struct e820entry *overlap_list[E820MAX] __initdata;
474static struct e820entry new_bios[E820MAX] __initdata;
475
476static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
477{
478 struct change_member *change_tmp;
479 unsigned long current_type, last_type;
480 unsigned long long last_addr;
481 int chgidx, still_changing;
482 int overlap_entries;
483 int new_bios_entry;
484 int old_nr, new_nr, chg_nr;
485 int i;
486
487 /*
488 Visually we're performing the following (1,2,3,4 = memory types)...
489
490 Sample memory map (w/overlaps):
491 ____22__________________
492 ______________________4_
493 ____1111________________
494 _44_____________________
495 11111111________________
496 ____________________33__
497 ___________44___________
498 __________33333_________
499 ______________22________
500 ___________________2222_
501 _________111111111______
502 _____________________11_
503 _________________4______
504
505 Sanitized equivalent (no overlap):
506 1_______________________
507 _44_____________________
508 ___1____________________
509 ____22__________________
510 ______11________________
511 _________1______________
512 __________3_____________
513 ___________44___________
514 _____________33_________
515 _______________2________
516 ________________1_______
517 _________________4______
518 ___________________2____
519 ____________________33__
520 ______________________4_
521 */
522
523 /* if there's only one memory region, don't bother */
524 if (*pnr_map < 2)
525 return -1;
526
527 old_nr = *pnr_map;
528
529 /* bail out if we find any unreasonable addresses in bios map */
530 for (i=0; i<old_nr; i++)
531 if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
532 return -1;
533
534 /* create pointers for initial change-point information (for sorting) */
535 for (i=0; i < 2*old_nr; i++)
536 change_point[i] = &change_point_list[i];
537
538 /* record all known change-points (starting and ending addresses),
539 omitting those that are for empty memory regions */
540 chgidx = 0;
541 for (i=0; i < old_nr; i++) {
542 if (biosmap[i].size != 0) {
543 change_point[chgidx]->addr = biosmap[i].addr;
544 change_point[chgidx++]->pbios = &biosmap[i];
545 change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size;
546 change_point[chgidx++]->pbios = &biosmap[i];
547 }
548 }
549 chg_nr = chgidx; /* true number of change-points */
550
551 /* sort change-point list by memory addresses (low -> high) */
552 still_changing = 1;
553 while (still_changing) {
554 still_changing = 0;
555 for (i=1; i < chg_nr; i++) {
556 /* if <current_addr> > <last_addr>, swap */
557 /* or, if current=<start_addr> & last=<end_addr>, swap */
558 if ((change_point[i]->addr < change_point[i-1]->addr) ||
559 ((change_point[i]->addr == change_point[i-1]->addr) &&
560 (change_point[i]->addr == change_point[i]->pbios->addr) &&
561 (change_point[i-1]->addr != change_point[i-1]->pbios->addr))
562 )
563 {
564 change_tmp = change_point[i];
565 change_point[i] = change_point[i-1];
566 change_point[i-1] = change_tmp;
567 still_changing=1;
568 }
569 }
570 }
571
572 /* create a new bios memory map, removing overlaps */
573 overlap_entries=0; /* number of entries in the overlap table */
574 new_bios_entry=0; /* index for creating new bios map entries */
575 last_type = 0; /* start with undefined memory type */
576 last_addr = 0; /* start with 0 as last starting address */
577 /* loop through change-points, determining affect on the new bios map */
578 for (chgidx=0; chgidx < chg_nr; chgidx++)
579 {
580 /* keep track of all overlapping bios entries */
581 if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr)
582 {
583 /* add map entry to overlap list (> 1 entry implies an overlap) */
584 overlap_list[overlap_entries++]=change_point[chgidx]->pbios;
585 }
586 else
587 {
588 /* remove entry from list (order independent, so swap with last) */
589 for (i=0; i<overlap_entries; i++)
590 {
591 if (overlap_list[i] == change_point[chgidx]->pbios)
592 overlap_list[i] = overlap_list[overlap_entries-1];
593 }
594 overlap_entries--;
595 }
596 /* if there are overlapping entries, decide which "type" to use */
597 /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */
598 current_type = 0;
599 for (i=0; i<overlap_entries; i++)
600 if (overlap_list[i]->type > current_type)
601 current_type = overlap_list[i]->type;
602 /* continue building up new bios map based on this information */
603 if (current_type != last_type) {
604 if (last_type != 0) {
605 new_bios[new_bios_entry].size =
606 change_point[chgidx]->addr - last_addr;
607 /* move forward only if the new size was non-zero */
608 if (new_bios[new_bios_entry].size != 0)
609 if (++new_bios_entry >= E820MAX)
610 break; /* no more space left for new bios entries */
611 }
612 if (current_type != 0) {
613 new_bios[new_bios_entry].addr = change_point[chgidx]->addr;
614 new_bios[new_bios_entry].type = current_type;
615 last_addr=change_point[chgidx]->addr;
616 }
617 last_type = current_type;
618 }
619 }
620 new_nr = new_bios_entry; /* retain count for new bios entries */
621
622 /* copy new bios mapping into original location */
623 memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry));
624 *pnr_map = new_nr;
625
626 return 0;
627}
628
629/*
630 * Copy the BIOS e820 map into a safe place.
631 *
632 * Sanity-check it while we're at it..
633 *
634 * If we're lucky and live on a modern system, the setup code
635 * will have given us a memory map that we can use to properly
636 * set up memory. If we aren't, we'll fake a memory map.
637 *
638 * We check to see that the memory map contains at least 2 elements
639 * before we'll use it, because the detection code in setup.S may
640 * not be perfect and most every PC known to man has two memory
641 * regions: one from 0 to 640k, and one from 1mb up. (The IBM
642 * thinkpad 560x, for example, does not cooperate with the memory
643 * detection code.)
644 */
645static int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
646{
647 /* Only one memory region (or negative)? Ignore it */
648 if (nr_map < 2)
649 return -1;
650
651 do {
652 unsigned long long start = biosmap->addr;
653 unsigned long long size = biosmap->size;
654 unsigned long long end = start + size;
655 unsigned long type = biosmap->type;
656
657 /* Overflow in 64 bits? Ignore the memory map. */
658 if (start > end)
659 return -1;
660
661 /*
662 * Some BIOSes claim RAM in the 640k - 1M region.
663 * Not right. Fix it up.
664 */
665 if (type == E820_RAM) {
666 if (start < 0x100000ULL && end > 0xA0000ULL) {
667 if (start < 0xA0000ULL)
668 add_memory_region(start, 0xA0000ULL-start, type);
669 if (end <= 0x100000ULL)
670 continue;
671 start = 0x100000ULL;
672 size = end - start;
673 }
674 }
675 add_memory_region(start, size, type);
676 } while (biosmap++,--nr_map);
677 return 0;
678}
679
680#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
681struct edd edd;
682#ifdef CONFIG_EDD_MODULE
683EXPORT_SYMBOL(edd);
684#endif
685/**
686 * copy_edd() - Copy the BIOS EDD information
687 * from boot_params into a safe place.
688 *
689 */
690static inline void copy_edd(void)
691{
692 memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature));
693 memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info));
694 edd.mbr_signature_nr = EDD_MBR_SIG_NR;
695 edd.edd_info_nr = EDD_NR;
696}
697#else
698static inline void copy_edd(void)
699{
700}
701#endif
702
703/*
704 * Do NOT EVER look at the BIOS memory size location.
705 * It does not work on many machines.
706 */
707#define LOWMEMSIZE() (0x9f000)
708
709static void __init parse_cmdline_early (char ** cmdline_p)
710{
711 char c = ' ', *to = command_line, *from = saved_command_line;
712 int len = 0;
713 int userdef = 0;
714
715 /* Save unparsed command line copy for /proc/cmdline */
716 saved_command_line[COMMAND_LINE_SIZE-1] = '\0';
717
718 for (;;) {
719 if (c != ' ')
720 goto next_char;
721 /*
722 * "mem=nopentium" disables the 4MB page tables.
723 * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
724 * to <mem>, overriding the bios size.
725 * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from
726 * <start> to <start>+<mem>, overriding the bios size.
727 *
728 * HPA tells me bootloaders need to parse mem=, so no new
729 * option should be mem= [also see Documentation/i386/boot.txt]
730 */
731 if (!memcmp(from, "mem=", 4)) {
732 if (to != command_line)
733 to--;
734 if (!memcmp(from+4, "nopentium", 9)) {
735 from += 9+4;
736 clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
737 disable_pse = 1;
738 } else {
739 /* If the user specifies memory size, we
740 * limit the BIOS-provided memory map to
741 * that size. exactmap can be used to specify
742 * the exact map. mem=number can be used to
743 * trim the existing memory map.
744 */
745 unsigned long long mem_size;
746
747 mem_size = memparse(from+4, &from);
748 limit_regions(mem_size);
749 userdef=1;
750 }
751 }
752
753 else if (!memcmp(from, "memmap=", 7)) {
754 if (to != command_line)
755 to--;
756 if (!memcmp(from+7, "exactmap", 8)) {
Vivek Goyal92aa63a2005-06-25 14:58:18 -0700757#ifdef CONFIG_CRASH_DUMP
758 /* If we are doing a crash dump, we
759 * still need to know the real mem
760 * size before original memory map is
761 * reset.
762 */
763 find_max_pfn();
764 saved_max_pfn = max_pfn;
765#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700766 from += 8+7;
767 e820.nr_map = 0;
768 userdef = 1;
769 } else {
770 /* If the user specifies memory size, we
771 * limit the BIOS-provided memory map to
772 * that size. exactmap can be used to specify
773 * the exact map. mem=number can be used to
774 * trim the existing memory map.
775 */
776 unsigned long long start_at, mem_size;
777
778 mem_size = memparse(from+7, &from);
779 if (*from == '@') {
780 start_at = memparse(from+1, &from);
781 add_memory_region(start_at, mem_size, E820_RAM);
782 } else if (*from == '#') {
783 start_at = memparse(from+1, &from);
784 add_memory_region(start_at, mem_size, E820_ACPI);
785 } else if (*from == '$') {
786 start_at = memparse(from+1, &from);
787 add_memory_region(start_at, mem_size, E820_RESERVED);
788 } else {
789 limit_regions(mem_size);
790 userdef=1;
791 }
792 }
793 }
794
795 else if (!memcmp(from, "noexec=", 7))
796 noexec_setup(from + 7);
797
798
799#ifdef CONFIG_X86_SMP
800 /*
801 * If the BIOS enumerates physical processors before logical,
802 * maxcpus=N at enumeration-time can be used to disable HT.
803 */
804 else if (!memcmp(from, "maxcpus=", 8)) {
805 extern unsigned int maxcpus;
806
807 maxcpus = simple_strtoul(from + 8, NULL, 0);
808 }
809#endif
810
Len Brown888ba6c2005-08-24 12:07:20 -0400811#ifdef CONFIG_ACPI
Linus Torvalds1da177e2005-04-16 15:20:36 -0700812 /* "acpi=off" disables both ACPI table parsing and interpreter */
813 else if (!memcmp(from, "acpi=off", 8)) {
814 disable_acpi();
815 }
816
817 /* acpi=force to over-ride black-list */
818 else if (!memcmp(from, "acpi=force", 10)) {
819 acpi_force = 1;
820 acpi_ht = 1;
821 acpi_disabled = 0;
822 }
823
824 /* acpi=strict disables out-of-spec workarounds */
825 else if (!memcmp(from, "acpi=strict", 11)) {
826 acpi_strict = 1;
827 }
828
829 /* Limit ACPI just to boot-time to enable HT */
830 else if (!memcmp(from, "acpi=ht", 7)) {
831 if (!acpi_force)
832 disable_acpi();
833 acpi_ht = 1;
834 }
835
836 /* "pci=noacpi" disable ACPI IRQ routing and PCI scan */
837 else if (!memcmp(from, "pci=noacpi", 10)) {
838 acpi_disable_pci();
839 }
840 /* "acpi=noirq" disables ACPI interrupt routing */
841 else if (!memcmp(from, "acpi=noirq", 10)) {
842 acpi_noirq_set();
843 }
844
845 else if (!memcmp(from, "acpi_sci=edge", 13))
846 acpi_sci_flags.trigger = 1;
847
848 else if (!memcmp(from, "acpi_sci=level", 14))
849 acpi_sci_flags.trigger = 3;
850
851 else if (!memcmp(from, "acpi_sci=high", 13))
852 acpi_sci_flags.polarity = 1;
853
854 else if (!memcmp(from, "acpi_sci=low", 12))
855 acpi_sci_flags.polarity = 3;
856
857#ifdef CONFIG_X86_IO_APIC
858 else if (!memcmp(from, "acpi_skip_timer_override", 24))
859 acpi_skip_timer_override = 1;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700860
Chuck Ebbert66759a02005-09-12 18:49:25 +0200861 if (!memcmp(from, "disable_timer_pin_1", 19))
862 disable_timer_pin_1 = 1;
863 if (!memcmp(from, "enable_timer_pin_1", 18))
864 disable_timer_pin_1 = -1;
865
Linus Torvalds1da177e2005-04-16 15:20:36 -0700866 /* disable IO-APIC */
867 else if (!memcmp(from, "noapic", 6))
868 disable_ioapic_setup();
Cal Peake0a305d22005-09-13 02:28:07 -0400869#endif /* CONFIG_X86_IO_APIC */
Len Brown888ba6c2005-08-24 12:07:20 -0400870#endif /* CONFIG_ACPI */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700871
Eric W. Biederman9635b472005-06-25 14:57:41 -0700872#ifdef CONFIG_X86_LOCAL_APIC
873 /* enable local APIC */
874 else if (!memcmp(from, "lapic", 5))
875 lapic_enable();
876
877 /* disable local APIC */
878 else if (!memcmp(from, "nolapic", 6))
879 lapic_disable();
880#endif /* CONFIG_X86_LOCAL_APIC */
881
Eric W. Biederman1bc3b912005-06-25 14:58:01 -0700882#ifdef CONFIG_KEXEC
883 /* crashkernel=size@addr specifies the location to reserve for
884 * a crash kernel. By reserving this memory we guarantee
885 * that linux never set's it up as a DMA target.
886 * Useful for holding code to do something appropriate
887 * after a kernel panic.
888 */
889 else if (!memcmp(from, "crashkernel=", 12)) {
890 unsigned long size, base;
891 size = memparse(from+12, &from);
892 if (*from == '@') {
893 base = memparse(from+1, &from);
894 /* FIXME: Do I want a sanity check
895 * to validate the memory range?
896 */
897 crashk_res.start = base;
898 crashk_res.end = base + size - 1;
899 }
900 }
901#endif
Vivek Goyalaac04b32006-01-09 20:51:47 -0800902#ifdef CONFIG_PROC_VMCORE
Vivek Goyal2030eae2005-06-25 14:58:20 -0700903 /* elfcorehdr= specifies the location of elf core header
904 * stored by the crashed kernel.
905 */
906 else if (!memcmp(from, "elfcorehdr=", 11))
907 elfcorehdr_addr = memparse(from+11, &from);
908#endif
Eric W. Biederman1bc3b912005-06-25 14:58:01 -0700909
Linus Torvalds1da177e2005-04-16 15:20:36 -0700910 /*
911 * highmem=size forces highmem to be exactly 'size' bytes.
912 * This works even on boxes that have no highmem otherwise.
913 * This also works to reduce highmem size on bigger boxes.
914 */
915 else if (!memcmp(from, "highmem=", 8))
916 highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT;
917
918 /*
919 * vmalloc=size forces the vmalloc area to be exactly 'size'
920 * bytes. This can be used to increase (or decrease) the
921 * vmalloc area - the default is 128m.
922 */
923 else if (!memcmp(from, "vmalloc=", 8))
924 __VMALLOC_RESERVE = memparse(from+8, &from);
925
926 next_char:
927 c = *(from++);
928 if (!c)
929 break;
930 if (COMMAND_LINE_SIZE <= ++len)
931 break;
932 *(to++) = c;
933 }
934 *to = '\0';
935 *cmdline_p = command_line;
936 if (userdef) {
937 printk(KERN_INFO "user-defined physical RAM map:\n");
938 print_memory_map("user");
939 }
940}
941
942/*
943 * Callback for efi_memory_walk.
944 */
945static int __init
946efi_find_max_pfn(unsigned long start, unsigned long end, void *arg)
947{
948 unsigned long *max_pfn = arg, pfn;
949
950 if (start < end) {
951 pfn = PFN_UP(end -1);
952 if (pfn > *max_pfn)
953 *max_pfn = pfn;
954 }
955 return 0;
956}
957
Andy Whitcroft215c3402006-01-06 00:12:06 -0800958static int __init
959efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
960{
961 memory_present(0, start, end);
962 return 0;
963}
Linus Torvalds1da177e2005-04-16 15:20:36 -0700964
965/*
966 * Find the highest page frame number we have available
967 */
968void __init find_max_pfn(void)
969{
970 int i;
971
972 max_pfn = 0;
973 if (efi_enabled) {
974 efi_memmap_walk(efi_find_max_pfn, &max_pfn);
Andy Whitcroft215c3402006-01-06 00:12:06 -0800975 efi_memmap_walk(efi_memory_present_wrapper, NULL);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700976 return;
977 }
978
979 for (i = 0; i < e820.nr_map; i++) {
980 unsigned long start, end;
981 /* RAM? */
982 if (e820.map[i].type != E820_RAM)
983 continue;
984 start = PFN_UP(e820.map[i].addr);
985 end = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
986 if (start >= end)
987 continue;
988 if (end > max_pfn)
989 max_pfn = end;
Andy Whitcroft215c3402006-01-06 00:12:06 -0800990 memory_present(0, start, end);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700991 }
992}
993
994/*
995 * Determine low and high memory ranges:
996 */
997unsigned long __init find_max_low_pfn(void)
998{
999 unsigned long max_low_pfn;
1000
1001 max_low_pfn = max_pfn;
1002 if (max_low_pfn > MAXMEM_PFN) {
1003 if (highmem_pages == -1)
1004 highmem_pages = max_pfn - MAXMEM_PFN;
1005 if (highmem_pages + MAXMEM_PFN < max_pfn)
1006 max_pfn = MAXMEM_PFN + highmem_pages;
1007 if (highmem_pages + MAXMEM_PFN > max_pfn) {
1008 printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages));
1009 highmem_pages = 0;
1010 }
1011 max_low_pfn = MAXMEM_PFN;
1012#ifndef CONFIG_HIGHMEM
1013 /* Maximum memory usable is what is directly addressable */
1014 printk(KERN_WARNING "Warning only %ldMB will be used.\n",
1015 MAXMEM>>20);
1016 if (max_pfn > MAX_NONPAE_PFN)
1017 printk(KERN_WARNING "Use a PAE enabled kernel.\n");
1018 else
1019 printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
1020 max_pfn = MAXMEM_PFN;
1021#else /* !CONFIG_HIGHMEM */
1022#ifndef CONFIG_X86_PAE
1023 if (max_pfn > MAX_NONPAE_PFN) {
1024 max_pfn = MAX_NONPAE_PFN;
1025 printk(KERN_WARNING "Warning only 4GB will be used.\n");
1026 printk(KERN_WARNING "Use a PAE enabled kernel.\n");
1027 }
1028#endif /* !CONFIG_X86_PAE */
1029#endif /* !CONFIG_HIGHMEM */
1030 } else {
1031 if (highmem_pages == -1)
1032 highmem_pages = 0;
1033#ifdef CONFIG_HIGHMEM
1034 if (highmem_pages >= max_pfn) {
1035 printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
1036 highmem_pages = 0;
1037 }
1038 if (highmem_pages) {
1039 if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){
1040 printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages));
1041 highmem_pages = 0;
1042 }
1043 max_low_pfn -= highmem_pages;
1044 }
1045#else
1046 if (highmem_pages)
1047 printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
1048#endif
1049 }
1050 return max_low_pfn;
1051}
1052
1053/*
1054 * Free all available memory for boot time allocation. Used
1055 * as a callback function by efi_memory_walk()
1056 */
1057
1058static int __init
1059free_available_memory(unsigned long start, unsigned long end, void *arg)
1060{
1061 /* check max_low_pfn */
Tolentino, Matthew E23dd8422006-03-26 01:37:09 -08001062 if (start >= (max_low_pfn << PAGE_SHIFT))
Linus Torvalds1da177e2005-04-16 15:20:36 -07001063 return 0;
Tolentino, Matthew E23dd8422006-03-26 01:37:09 -08001064 if (end >= (max_low_pfn << PAGE_SHIFT))
1065 end = max_low_pfn << PAGE_SHIFT;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001066 if (start < end)
1067 free_bootmem(start, end - start);
1068
1069 return 0;
1070}
1071/*
1072 * Register fully available low RAM pages with the bootmem allocator.
1073 */
1074static void __init register_bootmem_low_pages(unsigned long max_low_pfn)
1075{
1076 int i;
1077
1078 if (efi_enabled) {
1079 efi_memmap_walk(free_available_memory, NULL);
1080 return;
1081 }
1082 for (i = 0; i < e820.nr_map; i++) {
1083 unsigned long curr_pfn, last_pfn, size;
1084 /*
1085 * Reserve usable low memory
1086 */
1087 if (e820.map[i].type != E820_RAM)
1088 continue;
1089 /*
1090 * We are rounding up the start address of usable memory:
1091 */
1092 curr_pfn = PFN_UP(e820.map[i].addr);
1093 if (curr_pfn >= max_low_pfn)
1094 continue;
1095 /*
1096 * ... and at the end of the usable range downwards:
1097 */
1098 last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
1099
1100 if (last_pfn > max_low_pfn)
1101 last_pfn = max_low_pfn;
1102
1103 /*
1104 * .. finally, did all the rounding and playing
1105 * around just make the area go away?
1106 */
1107 if (last_pfn <= curr_pfn)
1108 continue;
1109
1110 size = last_pfn - curr_pfn;
1111 free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size));
1112 }
1113}
1114
1115/*
1116 * workaround for Dell systems that neglect to reserve EBDA
1117 */
1118static void __init reserve_ebda_region(void)
1119{
1120 unsigned int addr;
1121 addr = get_bios_ebda();
1122 if (addr)
1123 reserve_bootmem(addr, PAGE_SIZE);
1124}
1125
Andy Whitcroft05b79bd2005-06-23 00:07:57 -07001126#ifndef CONFIG_NEED_MULTIPLE_NODES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001127void __init setup_bootmem_allocator(void);
1128static unsigned long __init setup_memory(void)
1129{
1130 /*
1131 * partially used pages are not usable - thus
1132 * we are rounding upwards:
1133 */
1134 min_low_pfn = PFN_UP(init_pg_tables_end);
1135
1136 find_max_pfn();
1137
1138 max_low_pfn = find_max_low_pfn();
1139
1140#ifdef CONFIG_HIGHMEM
1141 highstart_pfn = highend_pfn = max_pfn;
1142 if (max_pfn > max_low_pfn) {
1143 highstart_pfn = max_low_pfn;
1144 }
1145 printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
1146 pages_to_mb(highend_pfn - highstart_pfn));
1147#endif
1148 printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
1149 pages_to_mb(max_low_pfn));
1150
1151 setup_bootmem_allocator();
1152
1153 return max_low_pfn;
1154}
1155
1156void __init zone_sizes_init(void)
1157{
1158 unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
1159 unsigned int max_dma, low;
1160
1161 max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
1162 low = max_low_pfn;
1163
1164 if (low < max_dma)
1165 zones_size[ZONE_DMA] = low;
1166 else {
1167 zones_size[ZONE_DMA] = max_dma;
1168 zones_size[ZONE_NORMAL] = low - max_dma;
1169#ifdef CONFIG_HIGHMEM
1170 zones_size[ZONE_HIGHMEM] = highend_pfn - low;
1171#endif
1172 }
1173 free_area_init(zones_size);
1174}
1175#else
Andy Whitcroft05b79bd2005-06-23 00:07:57 -07001176extern unsigned long __init setup_memory(void);
Linus Torvalds1da177e2005-04-16 15:20:36 -07001177extern void zone_sizes_init(void);
Andy Whitcroft05b79bd2005-06-23 00:07:57 -07001178#endif /* !CONFIG_NEED_MULTIPLE_NODES */
Linus Torvalds1da177e2005-04-16 15:20:36 -07001179
1180void __init setup_bootmem_allocator(void)
1181{
1182 unsigned long bootmap_size;
1183 /*
1184 * Initialize the boot-time allocator (with low memory only):
1185 */
1186 bootmap_size = init_bootmem(min_low_pfn, max_low_pfn);
1187
1188 register_bootmem_low_pages(max_low_pfn);
1189
1190 /*
1191 * Reserve the bootmem bitmap itself as well. We do this in two
1192 * steps (first step was init_bootmem()) because this catches
1193 * the (very unlikely) case of us accidentally initializing the
1194 * bootmem allocator with an invalid RAM area.
1195 */
Vivek Goyal8a919082005-06-25 14:57:51 -07001196 reserve_bootmem(__PHYSICAL_START, (PFN_PHYS(min_low_pfn) +
1197 bootmap_size + PAGE_SIZE-1) - (__PHYSICAL_START));
Linus Torvalds1da177e2005-04-16 15:20:36 -07001198
1199 /*
1200 * reserve physical page 0 - it's a special BIOS page on many boxes,
1201 * enabling clean reboots, SMP operation, laptop functions.
1202 */
1203 reserve_bootmem(0, PAGE_SIZE);
1204
1205 /* reserve EBDA region, it's a 4K region */
1206 reserve_ebda_region();
1207
1208 /* could be an AMD 768MPX chipset. Reserve a page before VGA to prevent
1209 PCI prefetch into it (errata #56). Usually the page is reserved anyways,
1210 unless you have no PS/2 mouse plugged in. */
1211 if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
1212 boot_cpu_data.x86 == 6)
1213 reserve_bootmem(0xa0000 - 4096, 4096);
1214
1215#ifdef CONFIG_SMP
1216 /*
1217 * But first pinch a few for the stack/trampoline stuff
1218 * FIXME: Don't need the extra page at 4K, but need to fix
1219 * trampoline before removing it. (see the GDT stuff)
1220 */
1221 reserve_bootmem(PAGE_SIZE, PAGE_SIZE);
1222#endif
1223#ifdef CONFIG_ACPI_SLEEP
1224 /*
1225 * Reserve low memory region for sleep support.
1226 */
1227 acpi_reserve_bootmem();
1228#endif
1229#ifdef CONFIG_X86_FIND_SMP_CONFIG
1230 /*
1231 * Find and reserve possible boot-time SMP configuration:
1232 */
1233 find_smp_config();
1234#endif
1235
1236#ifdef CONFIG_BLK_DEV_INITRD
1237 if (LOADER_TYPE && INITRD_START) {
1238 if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
1239 reserve_bootmem(INITRD_START, INITRD_SIZE);
1240 initrd_start =
1241 INITRD_START ? INITRD_START + PAGE_OFFSET : 0;
1242 initrd_end = initrd_start+INITRD_SIZE;
1243 }
1244 else {
1245 printk(KERN_ERR "initrd extends beyond end of memory "
1246 "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
1247 INITRD_START + INITRD_SIZE,
1248 max_low_pfn << PAGE_SHIFT);
1249 initrd_start = 0;
1250 }
1251 }
1252#endif
Eric W. Biederman1bc3b912005-06-25 14:58:01 -07001253#ifdef CONFIG_KEXEC
1254 if (crashk_res.start != crashk_res.end)
1255 reserve_bootmem(crashk_res.start,
1256 crashk_res.end - crashk_res.start + 1);
1257#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -07001258}
1259
1260/*
1261 * The node 0 pgdat is initialized before all of these because
1262 * it's needed for bootmem. node>0 pgdats have their virtual
1263 * space allocated before the pagetables are in place to access
1264 * them, so they can't be cleared then.
1265 *
1266 * This should all compile down to nothing when NUMA is off.
1267 */
1268void __init remapped_pgdat_init(void)
1269{
1270 int nid;
1271
1272 for_each_online_node(nid) {
1273 if (nid != 0)
1274 memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
1275 }
1276}
1277
1278/*
1279 * Request address space for all standard RAM and ROM resources
1280 * and also for regions reported as reserved by the e820.
1281 */
1282static void __init
1283legacy_init_iomem_resources(struct resource *code_resource, struct resource *data_resource)
1284{
1285 int i;
1286
1287 probe_roms();
1288 for (i = 0; i < e820.nr_map; i++) {
1289 struct resource *res;
Linus Torvaldsb408cbc2006-02-22 15:50:30 -08001290 res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
Linus Torvalds1da177e2005-04-16 15:20:36 -07001291 switch (e820.map[i].type) {
1292 case E820_RAM: res->name = "System RAM"; break;
1293 case E820_ACPI: res->name = "ACPI Tables"; break;
1294 case E820_NVS: res->name = "ACPI Non-volatile Storage"; break;
1295 default: res->name = "reserved";
1296 }
1297 res->start = e820.map[i].addr;
1298 res->end = res->start + e820.map[i].size - 1;
1299 res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
1300 request_resource(&iomem_resource, res);
1301 if (e820.map[i].type == E820_RAM) {
1302 /*
1303 * We don't know which RAM region contains kernel data,
1304 * so we try it repeatedly and let the resource manager
1305 * test it.
1306 */
1307 request_resource(res, code_resource);
1308 request_resource(res, data_resource);
Eric W. Biederman1bc3b912005-06-25 14:58:01 -07001309#ifdef CONFIG_KEXEC
1310 request_resource(res, &crashk_res);
1311#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -07001312 }
1313 }
1314}
1315
1316/*
1317 * Request address space for all standard resources
Linus Torvaldsb408cbc2006-02-22 15:50:30 -08001318 *
1319 * This is called just before pcibios_assign_resources(), which is also
1320 * an fs_initcall, but is linked in later (in arch/i386/pci/i386.c).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001321 */
Linus Torvaldsb408cbc2006-02-22 15:50:30 -08001322static int __init request_standard_resources(void)
Linus Torvalds1da177e2005-04-16 15:20:36 -07001323{
Linus Torvaldsb408cbc2006-02-22 15:50:30 -08001324 int i;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001325
Linus Torvaldsb408cbc2006-02-22 15:50:30 -08001326 printk("Setting up standard PCI resources\n");
Linus Torvalds1da177e2005-04-16 15:20:36 -07001327 if (efi_enabled)
1328 efi_initialize_iomem_resources(&code_resource, &data_resource);
1329 else
1330 legacy_init_iomem_resources(&code_resource, &data_resource);
1331
1332 /* EFI systems may still have VGA */
1333 request_resource(&iomem_resource, &video_ram_resource);
1334
1335 /* request I/O space for devices used on all i[345]86 PCs */
1336 for (i = 0; i < STANDARD_IO_RESOURCES; i++)
1337 request_resource(&ioport_resource, &standard_io_resources[i]);
Linus Torvaldsb408cbc2006-02-22 15:50:30 -08001338 return 0;
1339}
1340
1341fs_initcall(request_standard_resources);
1342
1343static void __init register_memory(void)
1344{
1345 unsigned long gapstart, gapsize, round;
1346 unsigned long long last;
1347 int i;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001348
1349 /*
1350 * Search for the bigest gap in the low 32 bits of the e820
1351 * memory space.
1352 */
1353 last = 0x100000000ull;
1354 gapstart = 0x10000000;
1355 gapsize = 0x400000;
1356 i = e820.nr_map;
1357 while (--i >= 0) {
1358 unsigned long long start = e820.map[i].addr;
1359 unsigned long long end = start + e820.map[i].size;
1360
1361 /*
1362 * Since "last" is at most 4GB, we know we'll
1363 * fit in 32 bits if this condition is true
1364 */
1365 if (last > end) {
1366 unsigned long gap = last - end;
1367
1368 if (gap > gapsize) {
1369 gapsize = gap;
1370 gapstart = end;
1371 }
1372 }
1373 if (start < last)
1374 last = start;
1375 }
1376
1377 /*
Daniel Ritzf0eca962005-09-09 00:57:14 +02001378 * See how much we want to round up: start off with
1379 * rounding to the next 1MB area.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001380 */
Daniel Ritzf0eca962005-09-09 00:57:14 +02001381 round = 0x100000;
1382 while ((gapsize >> 4) > round)
1383 round += round;
1384 /* Fun with two's complement */
1385 pci_mem_start = (gapstart + round) & -round;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001386
1387 printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n",
1388 pci_mem_start, gapstart, gapsize);
1389}
1390
Linus Torvalds1da177e2005-04-16 15:20:36 -07001391static char * __init machine_specific_memory_setup(void);
1392
1393#ifdef CONFIG_MCA
1394static void set_mca_bus(int x)
1395{
1396 MCA_bus = x;
1397}
1398#else
1399static void set_mca_bus(int x) { }
1400#endif
1401
1402/*
1403 * Determine if we were loaded by an EFI loader. If so, then we have also been
1404 * passed the efi memmap, systab, etc., so we should use these data structures
1405 * for initialization. Note, the efi init code path is determined by the
1406 * global efi_enabled. This allows the same kernel image to be used on existing
1407 * systems (with a traditional BIOS) as well as on EFI systems.
1408 */
1409void __init setup_arch(char **cmdline_p)
1410{
1411 unsigned long max_low_pfn;
1412
1413 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
1414 pre_setup_arch_hook();
1415 early_cpu_init();
1416
1417 /*
1418 * FIXME: This isn't an official loader_type right
1419 * now but does currently work with elilo.
1420 * If we were configured as an EFI kernel, check to make
1421 * sure that we were loaded correctly from elilo and that
1422 * the system table is valid. If not, then initialize normally.
1423 */
1424#ifdef CONFIG_EFI
1425 if ((LOADER_TYPE == 0x50) && EFI_SYSTAB)
1426 efi_enabled = 1;
1427#endif
1428
1429 ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV);
1430 drive_info = DRIVE_INFO;
1431 screen_info = SCREEN_INFO;
1432 edid_info = EDID_INFO;
1433 apm_info.bios = APM_BIOS_INFO;
1434 ist_info = IST_INFO;
1435 saved_videomode = VIDEO_MODE;
1436 if( SYS_DESC_TABLE.length != 0 ) {
1437 set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2);
1438 machine_id = SYS_DESC_TABLE.table[0];
1439 machine_submodel_id = SYS_DESC_TABLE.table[1];
1440 BIOS_revision = SYS_DESC_TABLE.table[2];
1441 }
1442 bootloader_type = LOADER_TYPE;
1443
1444#ifdef CONFIG_BLK_DEV_RAM
1445 rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
1446 rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
1447 rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
1448#endif
1449 ARCH_SETUP
1450 if (efi_enabled)
1451 efi_init();
1452 else {
1453 printk(KERN_INFO "BIOS-provided physical RAM map:\n");
1454 print_memory_map(machine_specific_memory_setup());
1455 }
1456
1457 copy_edd();
1458
1459 if (!MOUNT_ROOT_RDONLY)
1460 root_mountflags &= ~MS_RDONLY;
1461 init_mm.start_code = (unsigned long) _text;
1462 init_mm.end_code = (unsigned long) _etext;
1463 init_mm.end_data = (unsigned long) _edata;
1464 init_mm.brk = init_pg_tables_end + PAGE_OFFSET;
1465
1466 code_resource.start = virt_to_phys(_text);
1467 code_resource.end = virt_to_phys(_etext)-1;
1468 data_resource.start = virt_to_phys(_etext);
1469 data_resource.end = virt_to_phys(_edata)-1;
1470
1471 parse_cmdline_early(cmdline_p);
1472
Stas Sergeev99b7de32006-03-23 02:59:41 -08001473#ifdef CONFIG_EARLY_PRINTK
1474 {
1475 char *s = strstr(*cmdline_p, "earlyprintk=");
1476 if (s) {
1477 setup_early_printk(strchr(s, '=') + 1);
1478 printk("early console enabled\n");
1479 }
1480 }
1481#endif
1482
Linus Torvalds1da177e2005-04-16 15:20:36 -07001483 max_low_pfn = setup_memory();
1484
1485 /*
1486 * NOTE: before this point _nobody_ is allowed to allocate
1487 * any memory using the bootmem allocator. Although the
1488 * alloctor is now initialised only the first 8Mb of the kernel
1489 * virtual address space has been mapped. All allocations before
1490 * paging_init() has completed must use the alloc_bootmem_low_pages()
1491 * variant (which allocates DMA'able memory) and care must be taken
1492 * not to exceed the 8Mb limit.
1493 */
1494
1495#ifdef CONFIG_SMP
1496 smp_alloc_memory(); /* AP processor realmode stacks in low memory*/
1497#endif
1498 paging_init();
1499 remapped_pgdat_init();
Andy Whitcroft05b79bd2005-06-23 00:07:57 -07001500 sparse_init();
Linus Torvalds1da177e2005-04-16 15:20:36 -07001501 zone_sizes_init();
1502
1503 /*
1504 * NOTE: at this point the bootmem allocator is fully available.
1505 */
1506
Linus Torvalds1da177e2005-04-16 15:20:36 -07001507 dmi_scan_machine();
1508
1509#ifdef CONFIG_X86_GENERICARCH
1510 generic_apic_probe(*cmdline_p);
1511#endif
1512 if (efi_enabled)
1513 efi_map_memmap();
1514
Andi Kleenf9262c12006-03-08 17:57:25 -08001515#ifdef CONFIG_X86_IO_APIC
1516 check_acpi_pci(); /* Checks more than just ACPI actually */
1517#endif
1518
Len Brown888ba6c2005-08-24 12:07:20 -04001519#ifdef CONFIG_ACPI
Linus Torvalds1da177e2005-04-16 15:20:36 -07001520 /*
1521 * Parse the ACPI tables for possible boot-time SMP configuration.
1522 */
1523 acpi_boot_table_init();
1524 acpi_boot_init();
Linus Torvalds1da177e2005-04-16 15:20:36 -07001525
Venkatesh Pallipadi911a62d2005-09-03 15:56:31 -07001526#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC)
1527 if (def_to_bigsmp)
1528 printk(KERN_WARNING "More than 8 CPUs detected and "
1529 "CONFIG_X86_PC cannot handle it.\nUse "
1530 "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
1531#endif
1532#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -07001533#ifdef CONFIG_X86_LOCAL_APIC
1534 if (smp_found_config)
1535 get_smp_config();
1536#endif
1537
1538 register_memory();
1539
1540#ifdef CONFIG_VT
1541#if defined(CONFIG_VGA_CONSOLE)
1542 if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
1543 conswitchp = &vga_con;
1544#elif defined(CONFIG_DUMMY_CONSOLE)
1545 conswitchp = &dummy_con;
1546#endif
1547#endif
1548}
1549
1550#include "setup_arch_post.h"
1551/*
1552 * Local Variables:
1553 * mode:c
1554 * c-file-style:"k&r"
1555 * c-basic-offset:8
1556 * End:
1557 */