Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /* |
| 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 Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 26 | #include <linux/config.h> |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 27 | #include <linux/sched.h> |
| 28 | #include <linux/mm.h> |
Andy Whitcroft | 05b79bd | 2005-06-23 00:07:57 -0700 | [diff] [blame] | 29 | #include <linux/mmzone.h> |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 30 | #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. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 46 | #include <linux/kexec.h> |
Vivek Goyal | 2030eae | 2005-06-25 14:58:20 -0700 | [diff] [blame] | 47 | #include <linux/crash_dump.h> |
Eric W. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 48 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 49 | #include <video/edid.h> |
Eric W. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 50 | |
Eric W. Biederman | 9635b47 | 2005-06-25 14:57:41 -0700 | [diff] [blame] | 51 | #include <asm/apic.h> |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 52 | #include <asm/e820.h> |
| 53 | #include <asm/mpspec.h> |
| 54 | #include <asm/setup.h> |
| 55 | #include <asm/arch_hooks.h> |
| 56 | #include <asm/sections.h> |
| 57 | #include <asm/io_apic.h> |
| 58 | #include <asm/ist.h> |
| 59 | #include <asm/io.h> |
| 60 | #include "setup_arch_pre.h" |
| 61 | #include <bios_ebda.h> |
| 62 | |
Vivek Goyal | 92aa63a | 2005-06-25 14:58:18 -0700 | [diff] [blame] | 63 | /* Forward Declaration. */ |
| 64 | void __init find_max_pfn(void); |
| 65 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 66 | /* This value is set up by the early boot code to point to the value |
| 67 | immediately after the boot time page tables. It contains a *physical* |
| 68 | address, and must not be in the .bss segment! */ |
| 69 | unsigned long init_pg_tables_end __initdata = ~0UL; |
| 70 | |
Li Shaohua | 0bb3184 | 2005-06-25 14:54:55 -0700 | [diff] [blame] | 71 | int disable_pse __devinitdata = 0; |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 72 | |
| 73 | /* |
| 74 | * Machine setup.. |
| 75 | */ |
| 76 | |
| 77 | #ifdef CONFIG_EFI |
| 78 | int efi_enabled = 0; |
| 79 | EXPORT_SYMBOL(efi_enabled); |
| 80 | #endif |
| 81 | |
| 82 | /* cpu data as detected by the assembly code in head.S */ |
| 83 | struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; |
| 84 | /* common cpu data for all cpus */ |
Christoph Lameter | c3d8c14 | 2005-09-06 15:16:33 -0700 | [diff] [blame] | 85 | struct cpuinfo_x86 boot_cpu_data __read_mostly = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 86 | EXPORT_SYMBOL(boot_cpu_data); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 87 | |
| 88 | unsigned long mmu_cr4_features; |
| 89 | |
Len Brown | 8466361 | 2005-08-24 12:09:07 -0400 | [diff] [blame] | 90 | #ifdef CONFIG_ACPI |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 91 | int acpi_disabled = 0; |
| 92 | #else |
| 93 | int acpi_disabled = 1; |
| 94 | #endif |
| 95 | EXPORT_SYMBOL(acpi_disabled); |
| 96 | |
Len Brown | 888ba6c | 2005-08-24 12:07:20 -0400 | [diff] [blame] | 97 | #ifdef CONFIG_ACPI |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 98 | int __initdata acpi_force = 0; |
| 99 | extern acpi_interrupt_flags acpi_sci_flags; |
| 100 | #endif |
| 101 | |
| 102 | /* for MCA, but anyone else can use it if they want */ |
| 103 | unsigned int machine_id; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 104 | #ifdef CONFIG_MCA |
| 105 | EXPORT_SYMBOL(machine_id); |
| 106 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 107 | unsigned int machine_submodel_id; |
| 108 | unsigned int BIOS_revision; |
| 109 | unsigned int mca_pentium_flag; |
| 110 | |
| 111 | /* For PCI or other memory-mapped resources */ |
| 112 | unsigned long pci_mem_start = 0x10000000; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 113 | #ifdef CONFIG_PCI |
| 114 | EXPORT_SYMBOL(pci_mem_start); |
| 115 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 116 | |
| 117 | /* Boot loader ID as an integer, for the benefit of proc_dointvec */ |
| 118 | int bootloader_type; |
| 119 | |
| 120 | /* user-defined highmem size */ |
| 121 | static unsigned int highmem_pages = -1; |
| 122 | |
| 123 | /* |
| 124 | * Setup options |
| 125 | */ |
| 126 | struct drive_info_struct { char dummy[32]; } drive_info; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 127 | #if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || \ |
| 128 | defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) |
| 129 | EXPORT_SYMBOL(drive_info); |
| 130 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 131 | struct screen_info screen_info; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 132 | #ifdef CONFIG_VT |
| 133 | EXPORT_SYMBOL(screen_info); |
| 134 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 135 | struct apm_info apm_info; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 136 | EXPORT_SYMBOL(apm_info); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 137 | struct sys_desc_table_struct { |
| 138 | unsigned short length; |
| 139 | unsigned char table[0]; |
| 140 | }; |
| 141 | struct edid_info edid_info; |
Antonino A. Daplas | 5e518d7 | 2005-09-09 13:04:34 -0700 | [diff] [blame^] | 142 | EXPORT_SYMBOL_GPL(edid_info); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 143 | struct ist_info ist_info; |
Alexey Dobriyan | 129f694 | 2005-06-23 00:08:33 -0700 | [diff] [blame] | 144 | #if defined(CONFIG_X86_SPEEDSTEP_SMI) || \ |
| 145 | defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) |
| 146 | EXPORT_SYMBOL(ist_info); |
| 147 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 148 | struct e820map e820; |
| 149 | |
| 150 | extern void early_cpu_init(void); |
| 151 | extern void dmi_scan_machine(void); |
| 152 | extern void generic_apic_probe(char *); |
| 153 | extern int root_mountflags; |
| 154 | |
| 155 | unsigned long saved_videomode; |
| 156 | |
| 157 | #define RAMDISK_IMAGE_START_MASK 0x07FF |
| 158 | #define RAMDISK_PROMPT_FLAG 0x8000 |
| 159 | #define RAMDISK_LOAD_FLAG 0x4000 |
| 160 | |
| 161 | static char command_line[COMMAND_LINE_SIZE]; |
| 162 | |
| 163 | unsigned char __initdata boot_params[PARAM_SIZE]; |
| 164 | |
| 165 | static struct resource data_resource = { |
| 166 | .name = "Kernel data", |
| 167 | .start = 0, |
| 168 | .end = 0, |
| 169 | .flags = IORESOURCE_BUSY | IORESOURCE_MEM |
| 170 | }; |
| 171 | |
| 172 | static struct resource code_resource = { |
| 173 | .name = "Kernel code", |
| 174 | .start = 0, |
| 175 | .end = 0, |
| 176 | .flags = IORESOURCE_BUSY | IORESOURCE_MEM |
| 177 | }; |
| 178 | |
| 179 | static struct resource system_rom_resource = { |
| 180 | .name = "System ROM", |
| 181 | .start = 0xf0000, |
| 182 | .end = 0xfffff, |
| 183 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 184 | }; |
| 185 | |
| 186 | static struct resource extension_rom_resource = { |
| 187 | .name = "Extension ROM", |
| 188 | .start = 0xe0000, |
| 189 | .end = 0xeffff, |
| 190 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 191 | }; |
| 192 | |
| 193 | static struct resource adapter_rom_resources[] = { { |
| 194 | .name = "Adapter ROM", |
| 195 | .start = 0xc8000, |
| 196 | .end = 0, |
| 197 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 198 | }, { |
| 199 | .name = "Adapter ROM", |
| 200 | .start = 0, |
| 201 | .end = 0, |
| 202 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 203 | }, { |
| 204 | .name = "Adapter ROM", |
| 205 | .start = 0, |
| 206 | .end = 0, |
| 207 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 208 | }, { |
| 209 | .name = "Adapter ROM", |
| 210 | .start = 0, |
| 211 | .end = 0, |
| 212 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 213 | }, { |
| 214 | .name = "Adapter ROM", |
| 215 | .start = 0, |
| 216 | .end = 0, |
| 217 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 218 | }, { |
| 219 | .name = "Adapter ROM", |
| 220 | .start = 0, |
| 221 | .end = 0, |
| 222 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 223 | } }; |
| 224 | |
| 225 | #define ADAPTER_ROM_RESOURCES \ |
| 226 | (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0]) |
| 227 | |
| 228 | static struct resource video_rom_resource = { |
| 229 | .name = "Video ROM", |
| 230 | .start = 0xc0000, |
| 231 | .end = 0xc7fff, |
| 232 | .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM |
| 233 | }; |
| 234 | |
| 235 | static struct resource video_ram_resource = { |
| 236 | .name = "Video RAM area", |
| 237 | .start = 0xa0000, |
| 238 | .end = 0xbffff, |
| 239 | .flags = IORESOURCE_BUSY | IORESOURCE_MEM |
| 240 | }; |
| 241 | |
| 242 | static struct resource standard_io_resources[] = { { |
| 243 | .name = "dma1", |
| 244 | .start = 0x0000, |
| 245 | .end = 0x001f, |
| 246 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 247 | }, { |
| 248 | .name = "pic1", |
| 249 | .start = 0x0020, |
| 250 | .end = 0x0021, |
| 251 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 252 | }, { |
| 253 | .name = "timer0", |
| 254 | .start = 0x0040, |
| 255 | .end = 0x0043, |
| 256 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 257 | }, { |
| 258 | .name = "timer1", |
| 259 | .start = 0x0050, |
| 260 | .end = 0x0053, |
| 261 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 262 | }, { |
| 263 | .name = "keyboard", |
| 264 | .start = 0x0060, |
| 265 | .end = 0x006f, |
| 266 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 267 | }, { |
| 268 | .name = "dma page reg", |
| 269 | .start = 0x0080, |
| 270 | .end = 0x008f, |
| 271 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 272 | }, { |
| 273 | .name = "pic2", |
| 274 | .start = 0x00a0, |
| 275 | .end = 0x00a1, |
| 276 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 277 | }, { |
| 278 | .name = "dma2", |
| 279 | .start = 0x00c0, |
| 280 | .end = 0x00df, |
| 281 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 282 | }, { |
| 283 | .name = "fpu", |
| 284 | .start = 0x00f0, |
| 285 | .end = 0x00ff, |
| 286 | .flags = IORESOURCE_BUSY | IORESOURCE_IO |
| 287 | } }; |
| 288 | |
| 289 | #define STANDARD_IO_RESOURCES \ |
| 290 | (sizeof standard_io_resources / sizeof standard_io_resources[0]) |
| 291 | |
| 292 | #define romsignature(x) (*(unsigned short *)(x) == 0xaa55) |
| 293 | |
| 294 | static int __init romchecksum(unsigned char *rom, unsigned long length) |
| 295 | { |
| 296 | unsigned char *p, sum = 0; |
| 297 | |
| 298 | for (p = rom; p < rom + length; p++) |
| 299 | sum += *p; |
| 300 | return sum == 0; |
| 301 | } |
| 302 | |
| 303 | static void __init probe_roms(void) |
| 304 | { |
| 305 | unsigned long start, length, upper; |
| 306 | unsigned char *rom; |
| 307 | int i; |
| 308 | |
| 309 | /* video rom */ |
| 310 | upper = adapter_rom_resources[0].start; |
| 311 | for (start = video_rom_resource.start; start < upper; start += 2048) { |
| 312 | rom = isa_bus_to_virt(start); |
| 313 | if (!romsignature(rom)) |
| 314 | continue; |
| 315 | |
| 316 | video_rom_resource.start = start; |
| 317 | |
| 318 | /* 0 < length <= 0x7f * 512, historically */ |
| 319 | length = rom[2] * 512; |
| 320 | |
| 321 | /* if checksum okay, trust length byte */ |
| 322 | if (length && romchecksum(rom, length)) |
| 323 | video_rom_resource.end = start + length - 1; |
| 324 | |
| 325 | request_resource(&iomem_resource, &video_rom_resource); |
| 326 | break; |
| 327 | } |
| 328 | |
| 329 | start = (video_rom_resource.end + 1 + 2047) & ~2047UL; |
| 330 | if (start < upper) |
| 331 | start = upper; |
| 332 | |
| 333 | /* system rom */ |
| 334 | request_resource(&iomem_resource, &system_rom_resource); |
| 335 | upper = system_rom_resource.start; |
| 336 | |
| 337 | /* check for extension rom (ignore length byte!) */ |
| 338 | rom = isa_bus_to_virt(extension_rom_resource.start); |
| 339 | if (romsignature(rom)) { |
| 340 | length = extension_rom_resource.end - extension_rom_resource.start + 1; |
| 341 | if (romchecksum(rom, length)) { |
| 342 | request_resource(&iomem_resource, &extension_rom_resource); |
| 343 | upper = extension_rom_resource.start; |
| 344 | } |
| 345 | } |
| 346 | |
| 347 | /* check for adapter roms on 2k boundaries */ |
| 348 | for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) { |
| 349 | rom = isa_bus_to_virt(start); |
| 350 | if (!romsignature(rom)) |
| 351 | continue; |
| 352 | |
| 353 | /* 0 < length <= 0x7f * 512, historically */ |
| 354 | length = rom[2] * 512; |
| 355 | |
| 356 | /* but accept any length that fits if checksum okay */ |
| 357 | if (!length || start + length > upper || !romchecksum(rom, length)) |
| 358 | continue; |
| 359 | |
| 360 | adapter_rom_resources[i].start = start; |
| 361 | adapter_rom_resources[i].end = start + length - 1; |
| 362 | request_resource(&iomem_resource, &adapter_rom_resources[i]); |
| 363 | |
| 364 | start = adapter_rom_resources[i++].end & ~2047UL; |
| 365 | } |
| 366 | } |
| 367 | |
| 368 | static void __init limit_regions(unsigned long long size) |
| 369 | { |
| 370 | unsigned long long current_addr = 0; |
| 371 | int i; |
| 372 | |
| 373 | if (efi_enabled) { |
Matt Tolentino | 7ae65fd | 2005-09-03 15:56:27 -0700 | [diff] [blame] | 374 | efi_memory_desc_t *md; |
| 375 | void *p; |
| 376 | |
| 377 | for (p = memmap.map, i = 0; p < memmap.map_end; |
| 378 | p += memmap.desc_size, i++) { |
| 379 | md = p; |
| 380 | current_addr = md->phys_addr + (md->num_pages << 12); |
| 381 | if (md->type == EFI_CONVENTIONAL_MEMORY) { |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 382 | if (current_addr >= size) { |
Matt Tolentino | 7ae65fd | 2005-09-03 15:56:27 -0700 | [diff] [blame] | 383 | md->num_pages -= |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 384 | (((current_addr-size) + PAGE_SIZE-1) >> PAGE_SHIFT); |
| 385 | memmap.nr_map = i + 1; |
| 386 | return; |
| 387 | } |
| 388 | } |
| 389 | } |
| 390 | } |
| 391 | for (i = 0; i < e820.nr_map; i++) { |
| 392 | if (e820.map[i].type == E820_RAM) { |
| 393 | current_addr = e820.map[i].addr + e820.map[i].size; |
| 394 | if (current_addr >= size) { |
| 395 | e820.map[i].size -= current_addr-size; |
| 396 | e820.nr_map = i + 1; |
| 397 | return; |
| 398 | } |
| 399 | } |
| 400 | } |
| 401 | } |
| 402 | |
| 403 | static void __init add_memory_region(unsigned long long start, |
| 404 | unsigned long long size, int type) |
| 405 | { |
| 406 | int x; |
| 407 | |
| 408 | if (!efi_enabled) { |
| 409 | x = e820.nr_map; |
| 410 | |
| 411 | if (x == E820MAX) { |
| 412 | printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); |
| 413 | return; |
| 414 | } |
| 415 | |
| 416 | e820.map[x].addr = start; |
| 417 | e820.map[x].size = size; |
| 418 | e820.map[x].type = type; |
| 419 | e820.nr_map++; |
| 420 | } |
| 421 | } /* add_memory_region */ |
| 422 | |
| 423 | #define E820_DEBUG 1 |
| 424 | |
| 425 | static void __init print_memory_map(char *who) |
| 426 | { |
| 427 | int i; |
| 428 | |
| 429 | for (i = 0; i < e820.nr_map; i++) { |
| 430 | printk(" %s: %016Lx - %016Lx ", who, |
| 431 | e820.map[i].addr, |
| 432 | e820.map[i].addr + e820.map[i].size); |
| 433 | switch (e820.map[i].type) { |
| 434 | case E820_RAM: printk("(usable)\n"); |
| 435 | break; |
| 436 | case E820_RESERVED: |
| 437 | printk("(reserved)\n"); |
| 438 | break; |
| 439 | case E820_ACPI: |
| 440 | printk("(ACPI data)\n"); |
| 441 | break; |
| 442 | case E820_NVS: |
| 443 | printk("(ACPI NVS)\n"); |
| 444 | break; |
| 445 | default: printk("type %lu\n", e820.map[i].type); |
| 446 | break; |
| 447 | } |
| 448 | } |
| 449 | } |
| 450 | |
| 451 | /* |
| 452 | * Sanitize the BIOS e820 map. |
| 453 | * |
| 454 | * Some e820 responses include overlapping entries. The following |
| 455 | * replaces the original e820 map with a new one, removing overlaps. |
| 456 | * |
| 457 | */ |
| 458 | struct change_member { |
| 459 | struct e820entry *pbios; /* pointer to original bios entry */ |
| 460 | unsigned long long addr; /* address for this change point */ |
| 461 | }; |
| 462 | static struct change_member change_point_list[2*E820MAX] __initdata; |
| 463 | static struct change_member *change_point[2*E820MAX] __initdata; |
| 464 | static struct e820entry *overlap_list[E820MAX] __initdata; |
| 465 | static struct e820entry new_bios[E820MAX] __initdata; |
| 466 | |
| 467 | static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) |
| 468 | { |
| 469 | struct change_member *change_tmp; |
| 470 | unsigned long current_type, last_type; |
| 471 | unsigned long long last_addr; |
| 472 | int chgidx, still_changing; |
| 473 | int overlap_entries; |
| 474 | int new_bios_entry; |
| 475 | int old_nr, new_nr, chg_nr; |
| 476 | int i; |
| 477 | |
| 478 | /* |
| 479 | Visually we're performing the following (1,2,3,4 = memory types)... |
| 480 | |
| 481 | Sample memory map (w/overlaps): |
| 482 | ____22__________________ |
| 483 | ______________________4_ |
| 484 | ____1111________________ |
| 485 | _44_____________________ |
| 486 | 11111111________________ |
| 487 | ____________________33__ |
| 488 | ___________44___________ |
| 489 | __________33333_________ |
| 490 | ______________22________ |
| 491 | ___________________2222_ |
| 492 | _________111111111______ |
| 493 | _____________________11_ |
| 494 | _________________4______ |
| 495 | |
| 496 | Sanitized equivalent (no overlap): |
| 497 | 1_______________________ |
| 498 | _44_____________________ |
| 499 | ___1____________________ |
| 500 | ____22__________________ |
| 501 | ______11________________ |
| 502 | _________1______________ |
| 503 | __________3_____________ |
| 504 | ___________44___________ |
| 505 | _____________33_________ |
| 506 | _______________2________ |
| 507 | ________________1_______ |
| 508 | _________________4______ |
| 509 | ___________________2____ |
| 510 | ____________________33__ |
| 511 | ______________________4_ |
| 512 | */ |
| 513 | |
| 514 | /* if there's only one memory region, don't bother */ |
| 515 | if (*pnr_map < 2) |
| 516 | return -1; |
| 517 | |
| 518 | old_nr = *pnr_map; |
| 519 | |
| 520 | /* bail out if we find any unreasonable addresses in bios map */ |
| 521 | for (i=0; i<old_nr; i++) |
| 522 | if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) |
| 523 | return -1; |
| 524 | |
| 525 | /* create pointers for initial change-point information (for sorting) */ |
| 526 | for (i=0; i < 2*old_nr; i++) |
| 527 | change_point[i] = &change_point_list[i]; |
| 528 | |
| 529 | /* record all known change-points (starting and ending addresses), |
| 530 | omitting those that are for empty memory regions */ |
| 531 | chgidx = 0; |
| 532 | for (i=0; i < old_nr; i++) { |
| 533 | if (biosmap[i].size != 0) { |
| 534 | change_point[chgidx]->addr = biosmap[i].addr; |
| 535 | change_point[chgidx++]->pbios = &biosmap[i]; |
| 536 | change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size; |
| 537 | change_point[chgidx++]->pbios = &biosmap[i]; |
| 538 | } |
| 539 | } |
| 540 | chg_nr = chgidx; /* true number of change-points */ |
| 541 | |
| 542 | /* sort change-point list by memory addresses (low -> high) */ |
| 543 | still_changing = 1; |
| 544 | while (still_changing) { |
| 545 | still_changing = 0; |
| 546 | for (i=1; i < chg_nr; i++) { |
| 547 | /* if <current_addr> > <last_addr>, swap */ |
| 548 | /* or, if current=<start_addr> & last=<end_addr>, swap */ |
| 549 | if ((change_point[i]->addr < change_point[i-1]->addr) || |
| 550 | ((change_point[i]->addr == change_point[i-1]->addr) && |
| 551 | (change_point[i]->addr == change_point[i]->pbios->addr) && |
| 552 | (change_point[i-1]->addr != change_point[i-1]->pbios->addr)) |
| 553 | ) |
| 554 | { |
| 555 | change_tmp = change_point[i]; |
| 556 | change_point[i] = change_point[i-1]; |
| 557 | change_point[i-1] = change_tmp; |
| 558 | still_changing=1; |
| 559 | } |
| 560 | } |
| 561 | } |
| 562 | |
| 563 | /* create a new bios memory map, removing overlaps */ |
| 564 | overlap_entries=0; /* number of entries in the overlap table */ |
| 565 | new_bios_entry=0; /* index for creating new bios map entries */ |
| 566 | last_type = 0; /* start with undefined memory type */ |
| 567 | last_addr = 0; /* start with 0 as last starting address */ |
| 568 | /* loop through change-points, determining affect on the new bios map */ |
| 569 | for (chgidx=0; chgidx < chg_nr; chgidx++) |
| 570 | { |
| 571 | /* keep track of all overlapping bios entries */ |
| 572 | if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr) |
| 573 | { |
| 574 | /* add map entry to overlap list (> 1 entry implies an overlap) */ |
| 575 | overlap_list[overlap_entries++]=change_point[chgidx]->pbios; |
| 576 | } |
| 577 | else |
| 578 | { |
| 579 | /* remove entry from list (order independent, so swap with last) */ |
| 580 | for (i=0; i<overlap_entries; i++) |
| 581 | { |
| 582 | if (overlap_list[i] == change_point[chgidx]->pbios) |
| 583 | overlap_list[i] = overlap_list[overlap_entries-1]; |
| 584 | } |
| 585 | overlap_entries--; |
| 586 | } |
| 587 | /* if there are overlapping entries, decide which "type" to use */ |
| 588 | /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */ |
| 589 | current_type = 0; |
| 590 | for (i=0; i<overlap_entries; i++) |
| 591 | if (overlap_list[i]->type > current_type) |
| 592 | current_type = overlap_list[i]->type; |
| 593 | /* continue building up new bios map based on this information */ |
| 594 | if (current_type != last_type) { |
| 595 | if (last_type != 0) { |
| 596 | new_bios[new_bios_entry].size = |
| 597 | change_point[chgidx]->addr - last_addr; |
| 598 | /* move forward only if the new size was non-zero */ |
| 599 | if (new_bios[new_bios_entry].size != 0) |
| 600 | if (++new_bios_entry >= E820MAX) |
| 601 | break; /* no more space left for new bios entries */ |
| 602 | } |
| 603 | if (current_type != 0) { |
| 604 | new_bios[new_bios_entry].addr = change_point[chgidx]->addr; |
| 605 | new_bios[new_bios_entry].type = current_type; |
| 606 | last_addr=change_point[chgidx]->addr; |
| 607 | } |
| 608 | last_type = current_type; |
| 609 | } |
| 610 | } |
| 611 | new_nr = new_bios_entry; /* retain count for new bios entries */ |
| 612 | |
| 613 | /* copy new bios mapping into original location */ |
| 614 | memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry)); |
| 615 | *pnr_map = new_nr; |
| 616 | |
| 617 | return 0; |
| 618 | } |
| 619 | |
| 620 | /* |
| 621 | * Copy the BIOS e820 map into a safe place. |
| 622 | * |
| 623 | * Sanity-check it while we're at it.. |
| 624 | * |
| 625 | * If we're lucky and live on a modern system, the setup code |
| 626 | * will have given us a memory map that we can use to properly |
| 627 | * set up memory. If we aren't, we'll fake a memory map. |
| 628 | * |
| 629 | * We check to see that the memory map contains at least 2 elements |
| 630 | * before we'll use it, because the detection code in setup.S may |
| 631 | * not be perfect and most every PC known to man has two memory |
| 632 | * regions: one from 0 to 640k, and one from 1mb up. (The IBM |
| 633 | * thinkpad 560x, for example, does not cooperate with the memory |
| 634 | * detection code.) |
| 635 | */ |
| 636 | static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) |
| 637 | { |
| 638 | /* Only one memory region (or negative)? Ignore it */ |
| 639 | if (nr_map < 2) |
| 640 | return -1; |
| 641 | |
| 642 | do { |
| 643 | unsigned long long start = biosmap->addr; |
| 644 | unsigned long long size = biosmap->size; |
| 645 | unsigned long long end = start + size; |
| 646 | unsigned long type = biosmap->type; |
| 647 | |
| 648 | /* Overflow in 64 bits? Ignore the memory map. */ |
| 649 | if (start > end) |
| 650 | return -1; |
| 651 | |
| 652 | /* |
| 653 | * Some BIOSes claim RAM in the 640k - 1M region. |
| 654 | * Not right. Fix it up. |
| 655 | */ |
| 656 | if (type == E820_RAM) { |
| 657 | if (start < 0x100000ULL && end > 0xA0000ULL) { |
| 658 | if (start < 0xA0000ULL) |
| 659 | add_memory_region(start, 0xA0000ULL-start, type); |
| 660 | if (end <= 0x100000ULL) |
| 661 | continue; |
| 662 | start = 0x100000ULL; |
| 663 | size = end - start; |
| 664 | } |
| 665 | } |
| 666 | add_memory_region(start, size, type); |
| 667 | } while (biosmap++,--nr_map); |
| 668 | return 0; |
| 669 | } |
| 670 | |
| 671 | #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) |
| 672 | struct edd edd; |
| 673 | #ifdef CONFIG_EDD_MODULE |
| 674 | EXPORT_SYMBOL(edd); |
| 675 | #endif |
| 676 | /** |
| 677 | * copy_edd() - Copy the BIOS EDD information |
| 678 | * from boot_params into a safe place. |
| 679 | * |
| 680 | */ |
| 681 | static inline void copy_edd(void) |
| 682 | { |
| 683 | memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); |
| 684 | memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); |
| 685 | edd.mbr_signature_nr = EDD_MBR_SIG_NR; |
| 686 | edd.edd_info_nr = EDD_NR; |
| 687 | } |
| 688 | #else |
| 689 | static inline void copy_edd(void) |
| 690 | { |
| 691 | } |
| 692 | #endif |
| 693 | |
| 694 | /* |
| 695 | * Do NOT EVER look at the BIOS memory size location. |
| 696 | * It does not work on many machines. |
| 697 | */ |
| 698 | #define LOWMEMSIZE() (0x9f000) |
| 699 | |
| 700 | static void __init parse_cmdline_early (char ** cmdline_p) |
| 701 | { |
| 702 | char c = ' ', *to = command_line, *from = saved_command_line; |
| 703 | int len = 0; |
| 704 | int userdef = 0; |
| 705 | |
| 706 | /* Save unparsed command line copy for /proc/cmdline */ |
| 707 | saved_command_line[COMMAND_LINE_SIZE-1] = '\0'; |
| 708 | |
| 709 | for (;;) { |
| 710 | if (c != ' ') |
| 711 | goto next_char; |
| 712 | /* |
| 713 | * "mem=nopentium" disables the 4MB page tables. |
| 714 | * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM |
| 715 | * to <mem>, overriding the bios size. |
| 716 | * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from |
| 717 | * <start> to <start>+<mem>, overriding the bios size. |
| 718 | * |
| 719 | * HPA tells me bootloaders need to parse mem=, so no new |
| 720 | * option should be mem= [also see Documentation/i386/boot.txt] |
| 721 | */ |
| 722 | if (!memcmp(from, "mem=", 4)) { |
| 723 | if (to != command_line) |
| 724 | to--; |
| 725 | if (!memcmp(from+4, "nopentium", 9)) { |
| 726 | from += 9+4; |
| 727 | clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); |
| 728 | disable_pse = 1; |
| 729 | } else { |
| 730 | /* If the user specifies memory size, we |
| 731 | * limit the BIOS-provided memory map to |
| 732 | * that size. exactmap can be used to specify |
| 733 | * the exact map. mem=number can be used to |
| 734 | * trim the existing memory map. |
| 735 | */ |
| 736 | unsigned long long mem_size; |
| 737 | |
| 738 | mem_size = memparse(from+4, &from); |
| 739 | limit_regions(mem_size); |
| 740 | userdef=1; |
| 741 | } |
| 742 | } |
| 743 | |
| 744 | else if (!memcmp(from, "memmap=", 7)) { |
| 745 | if (to != command_line) |
| 746 | to--; |
| 747 | if (!memcmp(from+7, "exactmap", 8)) { |
Vivek Goyal | 92aa63a | 2005-06-25 14:58:18 -0700 | [diff] [blame] | 748 | #ifdef CONFIG_CRASH_DUMP |
| 749 | /* If we are doing a crash dump, we |
| 750 | * still need to know the real mem |
| 751 | * size before original memory map is |
| 752 | * reset. |
| 753 | */ |
| 754 | find_max_pfn(); |
| 755 | saved_max_pfn = max_pfn; |
| 756 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 757 | from += 8+7; |
| 758 | e820.nr_map = 0; |
| 759 | userdef = 1; |
| 760 | } else { |
| 761 | /* If the user specifies memory size, we |
| 762 | * limit the BIOS-provided memory map to |
| 763 | * that size. exactmap can be used to specify |
| 764 | * the exact map. mem=number can be used to |
| 765 | * trim the existing memory map. |
| 766 | */ |
| 767 | unsigned long long start_at, mem_size; |
| 768 | |
| 769 | mem_size = memparse(from+7, &from); |
| 770 | if (*from == '@') { |
| 771 | start_at = memparse(from+1, &from); |
| 772 | add_memory_region(start_at, mem_size, E820_RAM); |
| 773 | } else if (*from == '#') { |
| 774 | start_at = memparse(from+1, &from); |
| 775 | add_memory_region(start_at, mem_size, E820_ACPI); |
| 776 | } else if (*from == '$') { |
| 777 | start_at = memparse(from+1, &from); |
| 778 | add_memory_region(start_at, mem_size, E820_RESERVED); |
| 779 | } else { |
| 780 | limit_regions(mem_size); |
| 781 | userdef=1; |
| 782 | } |
| 783 | } |
| 784 | } |
| 785 | |
| 786 | else if (!memcmp(from, "noexec=", 7)) |
| 787 | noexec_setup(from + 7); |
| 788 | |
| 789 | |
| 790 | #ifdef CONFIG_X86_SMP |
| 791 | /* |
| 792 | * If the BIOS enumerates physical processors before logical, |
| 793 | * maxcpus=N at enumeration-time can be used to disable HT. |
| 794 | */ |
| 795 | else if (!memcmp(from, "maxcpus=", 8)) { |
| 796 | extern unsigned int maxcpus; |
| 797 | |
| 798 | maxcpus = simple_strtoul(from + 8, NULL, 0); |
| 799 | } |
| 800 | #endif |
| 801 | |
Len Brown | 888ba6c | 2005-08-24 12:07:20 -0400 | [diff] [blame] | 802 | #ifdef CONFIG_ACPI |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 803 | /* "acpi=off" disables both ACPI table parsing and interpreter */ |
| 804 | else if (!memcmp(from, "acpi=off", 8)) { |
| 805 | disable_acpi(); |
| 806 | } |
| 807 | |
| 808 | /* acpi=force to over-ride black-list */ |
| 809 | else if (!memcmp(from, "acpi=force", 10)) { |
| 810 | acpi_force = 1; |
| 811 | acpi_ht = 1; |
| 812 | acpi_disabled = 0; |
| 813 | } |
| 814 | |
| 815 | /* acpi=strict disables out-of-spec workarounds */ |
| 816 | else if (!memcmp(from, "acpi=strict", 11)) { |
| 817 | acpi_strict = 1; |
| 818 | } |
| 819 | |
| 820 | /* Limit ACPI just to boot-time to enable HT */ |
| 821 | else if (!memcmp(from, "acpi=ht", 7)) { |
| 822 | if (!acpi_force) |
| 823 | disable_acpi(); |
| 824 | acpi_ht = 1; |
| 825 | } |
| 826 | |
| 827 | /* "pci=noacpi" disable ACPI IRQ routing and PCI scan */ |
| 828 | else if (!memcmp(from, "pci=noacpi", 10)) { |
| 829 | acpi_disable_pci(); |
| 830 | } |
| 831 | /* "acpi=noirq" disables ACPI interrupt routing */ |
| 832 | else if (!memcmp(from, "acpi=noirq", 10)) { |
| 833 | acpi_noirq_set(); |
| 834 | } |
| 835 | |
| 836 | else if (!memcmp(from, "acpi_sci=edge", 13)) |
| 837 | acpi_sci_flags.trigger = 1; |
| 838 | |
| 839 | else if (!memcmp(from, "acpi_sci=level", 14)) |
| 840 | acpi_sci_flags.trigger = 3; |
| 841 | |
| 842 | else if (!memcmp(from, "acpi_sci=high", 13)) |
| 843 | acpi_sci_flags.polarity = 1; |
| 844 | |
| 845 | else if (!memcmp(from, "acpi_sci=low", 12)) |
| 846 | acpi_sci_flags.polarity = 3; |
| 847 | |
| 848 | #ifdef CONFIG_X86_IO_APIC |
| 849 | else if (!memcmp(from, "acpi_skip_timer_override", 24)) |
| 850 | acpi_skip_timer_override = 1; |
| 851 | #endif |
| 852 | |
| 853 | #ifdef CONFIG_X86_LOCAL_APIC |
| 854 | /* disable IO-APIC */ |
| 855 | else if (!memcmp(from, "noapic", 6)) |
| 856 | disable_ioapic_setup(); |
| 857 | #endif /* CONFIG_X86_LOCAL_APIC */ |
Len Brown | 888ba6c | 2005-08-24 12:07:20 -0400 | [diff] [blame] | 858 | #endif /* CONFIG_ACPI */ |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 859 | |
Eric W. Biederman | 9635b47 | 2005-06-25 14:57:41 -0700 | [diff] [blame] | 860 | #ifdef CONFIG_X86_LOCAL_APIC |
| 861 | /* enable local APIC */ |
| 862 | else if (!memcmp(from, "lapic", 5)) |
| 863 | lapic_enable(); |
| 864 | |
| 865 | /* disable local APIC */ |
| 866 | else if (!memcmp(from, "nolapic", 6)) |
| 867 | lapic_disable(); |
| 868 | #endif /* CONFIG_X86_LOCAL_APIC */ |
| 869 | |
Eric W. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 870 | #ifdef CONFIG_KEXEC |
| 871 | /* crashkernel=size@addr specifies the location to reserve for |
| 872 | * a crash kernel. By reserving this memory we guarantee |
| 873 | * that linux never set's it up as a DMA target. |
| 874 | * Useful for holding code to do something appropriate |
| 875 | * after a kernel panic. |
| 876 | */ |
| 877 | else if (!memcmp(from, "crashkernel=", 12)) { |
| 878 | unsigned long size, base; |
| 879 | size = memparse(from+12, &from); |
| 880 | if (*from == '@') { |
| 881 | base = memparse(from+1, &from); |
| 882 | /* FIXME: Do I want a sanity check |
| 883 | * to validate the memory range? |
| 884 | */ |
| 885 | crashk_res.start = base; |
| 886 | crashk_res.end = base + size - 1; |
| 887 | } |
| 888 | } |
| 889 | #endif |
Vivek Goyal | 2030eae | 2005-06-25 14:58:20 -0700 | [diff] [blame] | 890 | #ifdef CONFIG_CRASH_DUMP |
| 891 | /* elfcorehdr= specifies the location of elf core header |
| 892 | * stored by the crashed kernel. |
| 893 | */ |
| 894 | else if (!memcmp(from, "elfcorehdr=", 11)) |
| 895 | elfcorehdr_addr = memparse(from+11, &from); |
| 896 | #endif |
Eric W. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 897 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 898 | /* |
| 899 | * highmem=size forces highmem to be exactly 'size' bytes. |
| 900 | * This works even on boxes that have no highmem otherwise. |
| 901 | * This also works to reduce highmem size on bigger boxes. |
| 902 | */ |
| 903 | else if (!memcmp(from, "highmem=", 8)) |
| 904 | highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT; |
| 905 | |
| 906 | /* |
| 907 | * vmalloc=size forces the vmalloc area to be exactly 'size' |
| 908 | * bytes. This can be used to increase (or decrease) the |
| 909 | * vmalloc area - the default is 128m. |
| 910 | */ |
| 911 | else if (!memcmp(from, "vmalloc=", 8)) |
| 912 | __VMALLOC_RESERVE = memparse(from+8, &from); |
| 913 | |
| 914 | next_char: |
| 915 | c = *(from++); |
| 916 | if (!c) |
| 917 | break; |
| 918 | if (COMMAND_LINE_SIZE <= ++len) |
| 919 | break; |
| 920 | *(to++) = c; |
| 921 | } |
| 922 | *to = '\0'; |
| 923 | *cmdline_p = command_line; |
| 924 | if (userdef) { |
| 925 | printk(KERN_INFO "user-defined physical RAM map:\n"); |
| 926 | print_memory_map("user"); |
| 927 | } |
| 928 | } |
| 929 | |
| 930 | /* |
| 931 | * Callback for efi_memory_walk. |
| 932 | */ |
| 933 | static int __init |
| 934 | efi_find_max_pfn(unsigned long start, unsigned long end, void *arg) |
| 935 | { |
| 936 | unsigned long *max_pfn = arg, pfn; |
| 937 | |
| 938 | if (start < end) { |
| 939 | pfn = PFN_UP(end -1); |
| 940 | if (pfn > *max_pfn) |
| 941 | *max_pfn = pfn; |
| 942 | } |
| 943 | return 0; |
| 944 | } |
| 945 | |
| 946 | |
| 947 | /* |
| 948 | * Find the highest page frame number we have available |
| 949 | */ |
| 950 | void __init find_max_pfn(void) |
| 951 | { |
| 952 | int i; |
| 953 | |
| 954 | max_pfn = 0; |
| 955 | if (efi_enabled) { |
| 956 | efi_memmap_walk(efi_find_max_pfn, &max_pfn); |
| 957 | return; |
| 958 | } |
| 959 | |
| 960 | for (i = 0; i < e820.nr_map; i++) { |
| 961 | unsigned long start, end; |
| 962 | /* RAM? */ |
| 963 | if (e820.map[i].type != E820_RAM) |
| 964 | continue; |
| 965 | start = PFN_UP(e820.map[i].addr); |
| 966 | end = PFN_DOWN(e820.map[i].addr + e820.map[i].size); |
| 967 | if (start >= end) |
| 968 | continue; |
| 969 | if (end > max_pfn) |
| 970 | max_pfn = end; |
| 971 | } |
| 972 | } |
| 973 | |
| 974 | /* |
| 975 | * Determine low and high memory ranges: |
| 976 | */ |
| 977 | unsigned long __init find_max_low_pfn(void) |
| 978 | { |
| 979 | unsigned long max_low_pfn; |
| 980 | |
| 981 | max_low_pfn = max_pfn; |
| 982 | if (max_low_pfn > MAXMEM_PFN) { |
| 983 | if (highmem_pages == -1) |
| 984 | highmem_pages = max_pfn - MAXMEM_PFN; |
| 985 | if (highmem_pages + MAXMEM_PFN < max_pfn) |
| 986 | max_pfn = MAXMEM_PFN + highmem_pages; |
| 987 | if (highmem_pages + MAXMEM_PFN > max_pfn) { |
| 988 | printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages)); |
| 989 | highmem_pages = 0; |
| 990 | } |
| 991 | max_low_pfn = MAXMEM_PFN; |
| 992 | #ifndef CONFIG_HIGHMEM |
| 993 | /* Maximum memory usable is what is directly addressable */ |
| 994 | printk(KERN_WARNING "Warning only %ldMB will be used.\n", |
| 995 | MAXMEM>>20); |
| 996 | if (max_pfn > MAX_NONPAE_PFN) |
| 997 | printk(KERN_WARNING "Use a PAE enabled kernel.\n"); |
| 998 | else |
| 999 | printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); |
| 1000 | max_pfn = MAXMEM_PFN; |
| 1001 | #else /* !CONFIG_HIGHMEM */ |
| 1002 | #ifndef CONFIG_X86_PAE |
| 1003 | if (max_pfn > MAX_NONPAE_PFN) { |
| 1004 | max_pfn = MAX_NONPAE_PFN; |
| 1005 | printk(KERN_WARNING "Warning only 4GB will be used.\n"); |
| 1006 | printk(KERN_WARNING "Use a PAE enabled kernel.\n"); |
| 1007 | } |
| 1008 | #endif /* !CONFIG_X86_PAE */ |
| 1009 | #endif /* !CONFIG_HIGHMEM */ |
| 1010 | } else { |
| 1011 | if (highmem_pages == -1) |
| 1012 | highmem_pages = 0; |
| 1013 | #ifdef CONFIG_HIGHMEM |
| 1014 | if (highmem_pages >= max_pfn) { |
| 1015 | printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn)); |
| 1016 | highmem_pages = 0; |
| 1017 | } |
| 1018 | if (highmem_pages) { |
| 1019 | if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){ |
| 1020 | printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages)); |
| 1021 | highmem_pages = 0; |
| 1022 | } |
| 1023 | max_low_pfn -= highmem_pages; |
| 1024 | } |
| 1025 | #else |
| 1026 | if (highmem_pages) |
| 1027 | printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); |
| 1028 | #endif |
| 1029 | } |
| 1030 | return max_low_pfn; |
| 1031 | } |
| 1032 | |
| 1033 | /* |
| 1034 | * Free all available memory for boot time allocation. Used |
| 1035 | * as a callback function by efi_memory_walk() |
| 1036 | */ |
| 1037 | |
| 1038 | static int __init |
| 1039 | free_available_memory(unsigned long start, unsigned long end, void *arg) |
| 1040 | { |
| 1041 | /* check max_low_pfn */ |
| 1042 | if (start >= ((max_low_pfn + 1) << PAGE_SHIFT)) |
| 1043 | return 0; |
| 1044 | if (end >= ((max_low_pfn + 1) << PAGE_SHIFT)) |
| 1045 | end = (max_low_pfn + 1) << PAGE_SHIFT; |
| 1046 | if (start < end) |
| 1047 | free_bootmem(start, end - start); |
| 1048 | |
| 1049 | return 0; |
| 1050 | } |
| 1051 | /* |
| 1052 | * Register fully available low RAM pages with the bootmem allocator. |
| 1053 | */ |
| 1054 | static void __init register_bootmem_low_pages(unsigned long max_low_pfn) |
| 1055 | { |
| 1056 | int i; |
| 1057 | |
| 1058 | if (efi_enabled) { |
| 1059 | efi_memmap_walk(free_available_memory, NULL); |
| 1060 | return; |
| 1061 | } |
| 1062 | for (i = 0; i < e820.nr_map; i++) { |
| 1063 | unsigned long curr_pfn, last_pfn, size; |
| 1064 | /* |
| 1065 | * Reserve usable low memory |
| 1066 | */ |
| 1067 | if (e820.map[i].type != E820_RAM) |
| 1068 | continue; |
| 1069 | /* |
| 1070 | * We are rounding up the start address of usable memory: |
| 1071 | */ |
| 1072 | curr_pfn = PFN_UP(e820.map[i].addr); |
| 1073 | if (curr_pfn >= max_low_pfn) |
| 1074 | continue; |
| 1075 | /* |
| 1076 | * ... and at the end of the usable range downwards: |
| 1077 | */ |
| 1078 | last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size); |
| 1079 | |
| 1080 | if (last_pfn > max_low_pfn) |
| 1081 | last_pfn = max_low_pfn; |
| 1082 | |
| 1083 | /* |
| 1084 | * .. finally, did all the rounding and playing |
| 1085 | * around just make the area go away? |
| 1086 | */ |
| 1087 | if (last_pfn <= curr_pfn) |
| 1088 | continue; |
| 1089 | |
| 1090 | size = last_pfn - curr_pfn; |
| 1091 | free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size)); |
| 1092 | } |
| 1093 | } |
| 1094 | |
| 1095 | /* |
| 1096 | * workaround for Dell systems that neglect to reserve EBDA |
| 1097 | */ |
| 1098 | static void __init reserve_ebda_region(void) |
| 1099 | { |
| 1100 | unsigned int addr; |
| 1101 | addr = get_bios_ebda(); |
| 1102 | if (addr) |
| 1103 | reserve_bootmem(addr, PAGE_SIZE); |
| 1104 | } |
| 1105 | |
Andy Whitcroft | 05b79bd | 2005-06-23 00:07:57 -0700 | [diff] [blame] | 1106 | #ifndef CONFIG_NEED_MULTIPLE_NODES |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1107 | void __init setup_bootmem_allocator(void); |
| 1108 | static unsigned long __init setup_memory(void) |
| 1109 | { |
| 1110 | /* |
| 1111 | * partially used pages are not usable - thus |
| 1112 | * we are rounding upwards: |
| 1113 | */ |
| 1114 | min_low_pfn = PFN_UP(init_pg_tables_end); |
| 1115 | |
| 1116 | find_max_pfn(); |
| 1117 | |
| 1118 | max_low_pfn = find_max_low_pfn(); |
| 1119 | |
| 1120 | #ifdef CONFIG_HIGHMEM |
| 1121 | highstart_pfn = highend_pfn = max_pfn; |
| 1122 | if (max_pfn > max_low_pfn) { |
| 1123 | highstart_pfn = max_low_pfn; |
| 1124 | } |
| 1125 | printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", |
| 1126 | pages_to_mb(highend_pfn - highstart_pfn)); |
| 1127 | #endif |
| 1128 | printk(KERN_NOTICE "%ldMB LOWMEM available.\n", |
| 1129 | pages_to_mb(max_low_pfn)); |
| 1130 | |
| 1131 | setup_bootmem_allocator(); |
| 1132 | |
| 1133 | return max_low_pfn; |
| 1134 | } |
| 1135 | |
| 1136 | void __init zone_sizes_init(void) |
| 1137 | { |
| 1138 | unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; |
| 1139 | unsigned int max_dma, low; |
| 1140 | |
| 1141 | max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; |
| 1142 | low = max_low_pfn; |
| 1143 | |
| 1144 | if (low < max_dma) |
| 1145 | zones_size[ZONE_DMA] = low; |
| 1146 | else { |
| 1147 | zones_size[ZONE_DMA] = max_dma; |
| 1148 | zones_size[ZONE_NORMAL] = low - max_dma; |
| 1149 | #ifdef CONFIG_HIGHMEM |
| 1150 | zones_size[ZONE_HIGHMEM] = highend_pfn - low; |
| 1151 | #endif |
| 1152 | } |
| 1153 | free_area_init(zones_size); |
| 1154 | } |
| 1155 | #else |
Andy Whitcroft | 05b79bd | 2005-06-23 00:07:57 -0700 | [diff] [blame] | 1156 | extern unsigned long __init setup_memory(void); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1157 | extern void zone_sizes_init(void); |
Andy Whitcroft | 05b79bd | 2005-06-23 00:07:57 -0700 | [diff] [blame] | 1158 | #endif /* !CONFIG_NEED_MULTIPLE_NODES */ |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1159 | |
| 1160 | void __init setup_bootmem_allocator(void) |
| 1161 | { |
| 1162 | unsigned long bootmap_size; |
| 1163 | /* |
| 1164 | * Initialize the boot-time allocator (with low memory only): |
| 1165 | */ |
| 1166 | bootmap_size = init_bootmem(min_low_pfn, max_low_pfn); |
| 1167 | |
| 1168 | register_bootmem_low_pages(max_low_pfn); |
| 1169 | |
| 1170 | /* |
| 1171 | * Reserve the bootmem bitmap itself as well. We do this in two |
| 1172 | * steps (first step was init_bootmem()) because this catches |
| 1173 | * the (very unlikely) case of us accidentally initializing the |
| 1174 | * bootmem allocator with an invalid RAM area. |
| 1175 | */ |
Vivek Goyal | 8a91908 | 2005-06-25 14:57:51 -0700 | [diff] [blame] | 1176 | reserve_bootmem(__PHYSICAL_START, (PFN_PHYS(min_low_pfn) + |
| 1177 | bootmap_size + PAGE_SIZE-1) - (__PHYSICAL_START)); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1178 | |
| 1179 | /* |
| 1180 | * reserve physical page 0 - it's a special BIOS page on many boxes, |
| 1181 | * enabling clean reboots, SMP operation, laptop functions. |
| 1182 | */ |
| 1183 | reserve_bootmem(0, PAGE_SIZE); |
| 1184 | |
| 1185 | /* reserve EBDA region, it's a 4K region */ |
| 1186 | reserve_ebda_region(); |
| 1187 | |
| 1188 | /* could be an AMD 768MPX chipset. Reserve a page before VGA to prevent |
| 1189 | PCI prefetch into it (errata #56). Usually the page is reserved anyways, |
| 1190 | unless you have no PS/2 mouse plugged in. */ |
| 1191 | if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && |
| 1192 | boot_cpu_data.x86 == 6) |
| 1193 | reserve_bootmem(0xa0000 - 4096, 4096); |
| 1194 | |
| 1195 | #ifdef CONFIG_SMP |
| 1196 | /* |
| 1197 | * But first pinch a few for the stack/trampoline stuff |
| 1198 | * FIXME: Don't need the extra page at 4K, but need to fix |
| 1199 | * trampoline before removing it. (see the GDT stuff) |
| 1200 | */ |
| 1201 | reserve_bootmem(PAGE_SIZE, PAGE_SIZE); |
| 1202 | #endif |
| 1203 | #ifdef CONFIG_ACPI_SLEEP |
| 1204 | /* |
| 1205 | * Reserve low memory region for sleep support. |
| 1206 | */ |
| 1207 | acpi_reserve_bootmem(); |
| 1208 | #endif |
| 1209 | #ifdef CONFIG_X86_FIND_SMP_CONFIG |
| 1210 | /* |
| 1211 | * Find and reserve possible boot-time SMP configuration: |
| 1212 | */ |
| 1213 | find_smp_config(); |
| 1214 | #endif |
| 1215 | |
| 1216 | #ifdef CONFIG_BLK_DEV_INITRD |
| 1217 | if (LOADER_TYPE && INITRD_START) { |
| 1218 | if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) { |
| 1219 | reserve_bootmem(INITRD_START, INITRD_SIZE); |
| 1220 | initrd_start = |
| 1221 | INITRD_START ? INITRD_START + PAGE_OFFSET : 0; |
| 1222 | initrd_end = initrd_start+INITRD_SIZE; |
| 1223 | } |
| 1224 | else { |
| 1225 | printk(KERN_ERR "initrd extends beyond end of memory " |
| 1226 | "(0x%08lx > 0x%08lx)\ndisabling initrd\n", |
| 1227 | INITRD_START + INITRD_SIZE, |
| 1228 | max_low_pfn << PAGE_SHIFT); |
| 1229 | initrd_start = 0; |
| 1230 | } |
| 1231 | } |
| 1232 | #endif |
Eric W. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 1233 | #ifdef CONFIG_KEXEC |
| 1234 | if (crashk_res.start != crashk_res.end) |
| 1235 | reserve_bootmem(crashk_res.start, |
| 1236 | crashk_res.end - crashk_res.start + 1); |
| 1237 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1238 | } |
| 1239 | |
| 1240 | /* |
| 1241 | * The node 0 pgdat is initialized before all of these because |
| 1242 | * it's needed for bootmem. node>0 pgdats have their virtual |
| 1243 | * space allocated before the pagetables are in place to access |
| 1244 | * them, so they can't be cleared then. |
| 1245 | * |
| 1246 | * This should all compile down to nothing when NUMA is off. |
| 1247 | */ |
| 1248 | void __init remapped_pgdat_init(void) |
| 1249 | { |
| 1250 | int nid; |
| 1251 | |
| 1252 | for_each_online_node(nid) { |
| 1253 | if (nid != 0) |
| 1254 | memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); |
| 1255 | } |
| 1256 | } |
| 1257 | |
| 1258 | /* |
| 1259 | * Request address space for all standard RAM and ROM resources |
| 1260 | * and also for regions reported as reserved by the e820. |
| 1261 | */ |
| 1262 | static void __init |
| 1263 | legacy_init_iomem_resources(struct resource *code_resource, struct resource *data_resource) |
| 1264 | { |
| 1265 | int i; |
| 1266 | |
| 1267 | probe_roms(); |
| 1268 | for (i = 0; i < e820.nr_map; i++) { |
| 1269 | struct resource *res; |
| 1270 | if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) |
| 1271 | continue; |
| 1272 | res = alloc_bootmem_low(sizeof(struct resource)); |
| 1273 | switch (e820.map[i].type) { |
| 1274 | case E820_RAM: res->name = "System RAM"; break; |
| 1275 | case E820_ACPI: res->name = "ACPI Tables"; break; |
| 1276 | case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; |
| 1277 | default: res->name = "reserved"; |
| 1278 | } |
| 1279 | res->start = e820.map[i].addr; |
| 1280 | res->end = res->start + e820.map[i].size - 1; |
| 1281 | res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; |
| 1282 | request_resource(&iomem_resource, res); |
| 1283 | if (e820.map[i].type == E820_RAM) { |
| 1284 | /* |
| 1285 | * We don't know which RAM region contains kernel data, |
| 1286 | * so we try it repeatedly and let the resource manager |
| 1287 | * test it. |
| 1288 | */ |
| 1289 | request_resource(res, code_resource); |
| 1290 | request_resource(res, data_resource); |
Eric W. Biederman | 1bc3b91 | 2005-06-25 14:58:01 -0700 | [diff] [blame] | 1291 | #ifdef CONFIG_KEXEC |
| 1292 | request_resource(res, &crashk_res); |
| 1293 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1294 | } |
| 1295 | } |
| 1296 | } |
| 1297 | |
| 1298 | /* |
| 1299 | * Request address space for all standard resources |
| 1300 | */ |
| 1301 | static void __init register_memory(void) |
| 1302 | { |
| 1303 | unsigned long gapstart, gapsize; |
| 1304 | unsigned long long last; |
| 1305 | int i; |
| 1306 | |
| 1307 | if (efi_enabled) |
| 1308 | efi_initialize_iomem_resources(&code_resource, &data_resource); |
| 1309 | else |
| 1310 | legacy_init_iomem_resources(&code_resource, &data_resource); |
| 1311 | |
| 1312 | /* EFI systems may still have VGA */ |
| 1313 | request_resource(&iomem_resource, &video_ram_resource); |
| 1314 | |
| 1315 | /* request I/O space for devices used on all i[345]86 PCs */ |
| 1316 | for (i = 0; i < STANDARD_IO_RESOURCES; i++) |
| 1317 | request_resource(&ioport_resource, &standard_io_resources[i]); |
| 1318 | |
| 1319 | /* |
| 1320 | * Search for the bigest gap in the low 32 bits of the e820 |
| 1321 | * memory space. |
| 1322 | */ |
| 1323 | last = 0x100000000ull; |
| 1324 | gapstart = 0x10000000; |
| 1325 | gapsize = 0x400000; |
| 1326 | i = e820.nr_map; |
| 1327 | while (--i >= 0) { |
| 1328 | unsigned long long start = e820.map[i].addr; |
| 1329 | unsigned long long end = start + e820.map[i].size; |
| 1330 | |
| 1331 | /* |
| 1332 | * Since "last" is at most 4GB, we know we'll |
| 1333 | * fit in 32 bits if this condition is true |
| 1334 | */ |
| 1335 | if (last > end) { |
| 1336 | unsigned long gap = last - end; |
| 1337 | |
| 1338 | if (gap > gapsize) { |
| 1339 | gapsize = gap; |
| 1340 | gapstart = end; |
| 1341 | } |
| 1342 | } |
| 1343 | if (start < last) |
| 1344 | last = start; |
| 1345 | } |
| 1346 | |
| 1347 | /* |
| 1348 | * Start allocating dynamic PCI memory a bit into the gap, |
| 1349 | * aligned up to the nearest megabyte. |
| 1350 | * |
| 1351 | * Question: should we try to pad it up a bit (do something |
| 1352 | * like " + (gapsize >> 3)" in there too?). We now have the |
| 1353 | * technology. |
| 1354 | */ |
| 1355 | pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; |
| 1356 | |
| 1357 | printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n", |
| 1358 | pci_mem_start, gapstart, gapsize); |
| 1359 | } |
| 1360 | |
| 1361 | /* Use inline assembly to define this because the nops are defined |
| 1362 | as inline assembly strings in the include files and we cannot |
| 1363 | get them easily into strings. */ |
| 1364 | asm("\t.data\nintelnops: " |
| 1365 | GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 |
| 1366 | GENERIC_NOP7 GENERIC_NOP8); |
| 1367 | asm("\t.data\nk8nops: " |
| 1368 | K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 |
| 1369 | K8_NOP7 K8_NOP8); |
| 1370 | asm("\t.data\nk7nops: " |
| 1371 | K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 |
| 1372 | K7_NOP7 K7_NOP8); |
| 1373 | |
| 1374 | extern unsigned char intelnops[], k8nops[], k7nops[]; |
| 1375 | static unsigned char *intel_nops[ASM_NOP_MAX+1] = { |
| 1376 | NULL, |
| 1377 | intelnops, |
| 1378 | intelnops + 1, |
| 1379 | intelnops + 1 + 2, |
| 1380 | intelnops + 1 + 2 + 3, |
| 1381 | intelnops + 1 + 2 + 3 + 4, |
| 1382 | intelnops + 1 + 2 + 3 + 4 + 5, |
| 1383 | intelnops + 1 + 2 + 3 + 4 + 5 + 6, |
| 1384 | intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7, |
| 1385 | }; |
| 1386 | static unsigned char *k8_nops[ASM_NOP_MAX+1] = { |
| 1387 | NULL, |
| 1388 | k8nops, |
| 1389 | k8nops + 1, |
| 1390 | k8nops + 1 + 2, |
| 1391 | k8nops + 1 + 2 + 3, |
| 1392 | k8nops + 1 + 2 + 3 + 4, |
| 1393 | k8nops + 1 + 2 + 3 + 4 + 5, |
| 1394 | k8nops + 1 + 2 + 3 + 4 + 5 + 6, |
| 1395 | k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, |
| 1396 | }; |
| 1397 | static unsigned char *k7_nops[ASM_NOP_MAX+1] = { |
| 1398 | NULL, |
| 1399 | k7nops, |
| 1400 | k7nops + 1, |
| 1401 | k7nops + 1 + 2, |
| 1402 | k7nops + 1 + 2 + 3, |
| 1403 | k7nops + 1 + 2 + 3 + 4, |
| 1404 | k7nops + 1 + 2 + 3 + 4 + 5, |
| 1405 | k7nops + 1 + 2 + 3 + 4 + 5 + 6, |
| 1406 | k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, |
| 1407 | }; |
| 1408 | static struct nop { |
| 1409 | int cpuid; |
| 1410 | unsigned char **noptable; |
| 1411 | } noptypes[] = { |
| 1412 | { X86_FEATURE_K8, k8_nops }, |
| 1413 | { X86_FEATURE_K7, k7_nops }, |
| 1414 | { -1, NULL } |
| 1415 | }; |
| 1416 | |
| 1417 | /* Replace instructions with better alternatives for this CPU type. |
| 1418 | |
| 1419 | This runs before SMP is initialized to avoid SMP problems with |
| 1420 | self modifying code. This implies that assymetric systems where |
| 1421 | APs have less capabilities than the boot processor are not handled. |
Linus Torvalds | 72538d8 | 2005-07-22 18:29:40 -0400 | [diff] [blame] | 1422 | Tough. Make sure you disable such features by hand. */ |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1423 | void apply_alternatives(void *start, void *end) |
| 1424 | { |
| 1425 | struct alt_instr *a; |
| 1426 | int diff, i, k; |
| 1427 | unsigned char **noptable = intel_nops; |
| 1428 | for (i = 0; noptypes[i].cpuid >= 0; i++) { |
| 1429 | if (boot_cpu_has(noptypes[i].cpuid)) { |
| 1430 | noptable = noptypes[i].noptable; |
| 1431 | break; |
| 1432 | } |
| 1433 | } |
| 1434 | for (a = start; (void *)a < end; a++) { |
| 1435 | if (!boot_cpu_has(a->cpuid)) |
| 1436 | continue; |
| 1437 | BUG_ON(a->replacementlen > a->instrlen); |
| 1438 | memcpy(a->instr, a->replacement, a->replacementlen); |
| 1439 | diff = a->instrlen - a->replacementlen; |
| 1440 | /* Pad the rest with nops */ |
| 1441 | for (i = a->replacementlen; diff > 0; diff -= k, i += k) { |
| 1442 | k = diff; |
| 1443 | if (k > ASM_NOP_MAX) |
| 1444 | k = ASM_NOP_MAX; |
| 1445 | memcpy(a->instr + i, noptable[k], k); |
| 1446 | } |
| 1447 | } |
| 1448 | } |
| 1449 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1450 | void __init alternative_instructions(void) |
| 1451 | { |
| 1452 | extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1453 | apply_alternatives(__alt_instructions, __alt_instructions_end); |
| 1454 | } |
| 1455 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1456 | static char * __init machine_specific_memory_setup(void); |
| 1457 | |
| 1458 | #ifdef CONFIG_MCA |
| 1459 | static void set_mca_bus(int x) |
| 1460 | { |
| 1461 | MCA_bus = x; |
| 1462 | } |
| 1463 | #else |
| 1464 | static void set_mca_bus(int x) { } |
| 1465 | #endif |
| 1466 | |
| 1467 | /* |
| 1468 | * Determine if we were loaded by an EFI loader. If so, then we have also been |
| 1469 | * passed the efi memmap, systab, etc., so we should use these data structures |
| 1470 | * for initialization. Note, the efi init code path is determined by the |
| 1471 | * global efi_enabled. This allows the same kernel image to be used on existing |
| 1472 | * systems (with a traditional BIOS) as well as on EFI systems. |
| 1473 | */ |
| 1474 | void __init setup_arch(char **cmdline_p) |
| 1475 | { |
| 1476 | unsigned long max_low_pfn; |
| 1477 | |
| 1478 | memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); |
| 1479 | pre_setup_arch_hook(); |
| 1480 | early_cpu_init(); |
| 1481 | |
| 1482 | /* |
| 1483 | * FIXME: This isn't an official loader_type right |
| 1484 | * now but does currently work with elilo. |
| 1485 | * If we were configured as an EFI kernel, check to make |
| 1486 | * sure that we were loaded correctly from elilo and that |
| 1487 | * the system table is valid. If not, then initialize normally. |
| 1488 | */ |
| 1489 | #ifdef CONFIG_EFI |
| 1490 | if ((LOADER_TYPE == 0x50) && EFI_SYSTAB) |
| 1491 | efi_enabled = 1; |
| 1492 | #endif |
| 1493 | |
| 1494 | ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); |
| 1495 | drive_info = DRIVE_INFO; |
| 1496 | screen_info = SCREEN_INFO; |
| 1497 | edid_info = EDID_INFO; |
| 1498 | apm_info.bios = APM_BIOS_INFO; |
| 1499 | ist_info = IST_INFO; |
| 1500 | saved_videomode = VIDEO_MODE; |
| 1501 | if( SYS_DESC_TABLE.length != 0 ) { |
| 1502 | set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2); |
| 1503 | machine_id = SYS_DESC_TABLE.table[0]; |
| 1504 | machine_submodel_id = SYS_DESC_TABLE.table[1]; |
| 1505 | BIOS_revision = SYS_DESC_TABLE.table[2]; |
| 1506 | } |
| 1507 | bootloader_type = LOADER_TYPE; |
| 1508 | |
| 1509 | #ifdef CONFIG_BLK_DEV_RAM |
| 1510 | rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; |
| 1511 | rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); |
| 1512 | rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); |
| 1513 | #endif |
| 1514 | ARCH_SETUP |
| 1515 | if (efi_enabled) |
| 1516 | efi_init(); |
| 1517 | else { |
| 1518 | printk(KERN_INFO "BIOS-provided physical RAM map:\n"); |
| 1519 | print_memory_map(machine_specific_memory_setup()); |
| 1520 | } |
| 1521 | |
| 1522 | copy_edd(); |
| 1523 | |
| 1524 | if (!MOUNT_ROOT_RDONLY) |
| 1525 | root_mountflags &= ~MS_RDONLY; |
| 1526 | init_mm.start_code = (unsigned long) _text; |
| 1527 | init_mm.end_code = (unsigned long) _etext; |
| 1528 | init_mm.end_data = (unsigned long) _edata; |
| 1529 | init_mm.brk = init_pg_tables_end + PAGE_OFFSET; |
| 1530 | |
| 1531 | code_resource.start = virt_to_phys(_text); |
| 1532 | code_resource.end = virt_to_phys(_etext)-1; |
| 1533 | data_resource.start = virt_to_phys(_etext); |
| 1534 | data_resource.end = virt_to_phys(_edata)-1; |
| 1535 | |
| 1536 | parse_cmdline_early(cmdline_p); |
| 1537 | |
| 1538 | max_low_pfn = setup_memory(); |
| 1539 | |
| 1540 | /* |
| 1541 | * NOTE: before this point _nobody_ is allowed to allocate |
| 1542 | * any memory using the bootmem allocator. Although the |
| 1543 | * alloctor is now initialised only the first 8Mb of the kernel |
| 1544 | * virtual address space has been mapped. All allocations before |
| 1545 | * paging_init() has completed must use the alloc_bootmem_low_pages() |
| 1546 | * variant (which allocates DMA'able memory) and care must be taken |
| 1547 | * not to exceed the 8Mb limit. |
| 1548 | */ |
| 1549 | |
| 1550 | #ifdef CONFIG_SMP |
| 1551 | smp_alloc_memory(); /* AP processor realmode stacks in low memory*/ |
| 1552 | #endif |
| 1553 | paging_init(); |
| 1554 | remapped_pgdat_init(); |
Andy Whitcroft | 05b79bd | 2005-06-23 00:07:57 -0700 | [diff] [blame] | 1555 | sparse_init(); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1556 | zone_sizes_init(); |
| 1557 | |
| 1558 | /* |
| 1559 | * NOTE: at this point the bootmem allocator is fully available. |
| 1560 | */ |
| 1561 | |
| 1562 | #ifdef CONFIG_EARLY_PRINTK |
| 1563 | { |
| 1564 | char *s = strstr(*cmdline_p, "earlyprintk="); |
| 1565 | if (s) { |
| 1566 | extern void setup_early_printk(char *); |
| 1567 | |
| 1568 | setup_early_printk(s); |
| 1569 | printk("early console enabled\n"); |
| 1570 | } |
| 1571 | } |
| 1572 | #endif |
| 1573 | |
| 1574 | |
| 1575 | dmi_scan_machine(); |
| 1576 | |
| 1577 | #ifdef CONFIG_X86_GENERICARCH |
| 1578 | generic_apic_probe(*cmdline_p); |
| 1579 | #endif |
| 1580 | if (efi_enabled) |
| 1581 | efi_map_memmap(); |
| 1582 | |
Len Brown | 888ba6c | 2005-08-24 12:07:20 -0400 | [diff] [blame] | 1583 | #ifdef CONFIG_ACPI |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1584 | /* |
| 1585 | * Parse the ACPI tables for possible boot-time SMP configuration. |
| 1586 | */ |
| 1587 | acpi_boot_table_init(); |
| 1588 | acpi_boot_init(); |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1589 | |
Venkatesh Pallipadi | 911a62d | 2005-09-03 15:56:31 -0700 | [diff] [blame] | 1590 | #if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) |
| 1591 | if (def_to_bigsmp) |
| 1592 | printk(KERN_WARNING "More than 8 CPUs detected and " |
| 1593 | "CONFIG_X86_PC cannot handle it.\nUse " |
| 1594 | "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n"); |
| 1595 | #endif |
| 1596 | #endif |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1597 | #ifdef CONFIG_X86_LOCAL_APIC |
| 1598 | if (smp_found_config) |
| 1599 | get_smp_config(); |
| 1600 | #endif |
| 1601 | |
| 1602 | register_memory(); |
| 1603 | |
| 1604 | #ifdef CONFIG_VT |
| 1605 | #if defined(CONFIG_VGA_CONSOLE) |
| 1606 | if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) |
| 1607 | conswitchp = &vga_con; |
| 1608 | #elif defined(CONFIG_DUMMY_CONSOLE) |
| 1609 | conswitchp = &dummy_con; |
| 1610 | #endif |
| 1611 | #endif |
| 1612 | } |
| 1613 | |
| 1614 | #include "setup_arch_post.h" |
| 1615 | /* |
| 1616 | * Local Variables: |
| 1617 | * mode:c |
| 1618 | * c-file-style:"k&r" |
| 1619 | * c-basic-offset:8 |
| 1620 | * End: |
| 1621 | */ |