efi.c 29.3 KB
Newer Older
H
Huang, Ying 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28
/*
 * Common EFI (Extensible Firmware Interface) support functions
 * Based on Extensible Firmware Interface Specification version 1.0
 *
 * Copyright (C) 1999 VA Linux Systems
 * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
 * Copyright (C) 1999-2002 Hewlett-Packard Co.
 *	David Mosberger-Tang <davidm@hpl.hp.com>
 *	Stephane Eranian <eranian@hpl.hp.com>
 * Copyright (C) 2005-2008 Intel Co.
 *	Fenghua Yu <fenghua.yu@intel.com>
 *	Bibo Mao <bibo.mao@intel.com>
 *	Chandramouli Narayanan <mouli@linux.intel.com>
 *	Huang Ying <ying.huang@intel.com>
 *
 * Copied from efi_32.c to eliminate the duplicated code between EFI
 * 32/64 support code. --ying 2007-10-26
 *
 * All EFI Runtime Services are not implemented yet as EFI only
 * supports physical mode addressing on SoftSDV. This is to be fixed
 * in a future version.  --drummond 1999-07-20
 *
 * Implemented EFI runtime services and virtual mode calls.  --davidm
 *
 * Goutham Rao: <goutham.rao@intel.com>
 *	Skip non-WB memory and ignore empty memory ranges.
 */

29 30
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

H
Huang, Ying 已提交
31 32 33
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/efi.h>
34
#include <linux/efi-bgrt.h>
35
#include <linux/export.h>
H
Huang, Ying 已提交
36
#include <linux/bootmem.h>
37
#include <linux/memblock.h>
H
Huang, Ying 已提交
38 39 40 41 42 43
#include <linux/spinlock.h>
#include <linux/uaccess.h>
#include <linux/time.h>
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/bcd.h>
44
#include <linux/ucs2_string.h>
H
Huang, Ying 已提交
45 46 47 48

#include <asm/setup.h>
#include <asm/efi.h>
#include <asm/time.h>
49 50
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
51
#include <asm/x86_init.h>
H
Huang, Ying 已提交
52 53 54

#define EFI_DEBUG	1

55 56 57 58 59 60 61
/*
 * There's some additional metadata associated with each
 * variable. Intel's reference implementation is 60 bytes - bump that
 * to account for potential alignment constraints
 */
#define VAR_METADATA_SIZE 64

62 63 64 65 66 67 68 69 70 71 72
struct efi __read_mostly efi = {
	.mps        = EFI_INVALID_TABLE_ADDR,
	.acpi       = EFI_INVALID_TABLE_ADDR,
	.acpi20     = EFI_INVALID_TABLE_ADDR,
	.smbios     = EFI_INVALID_TABLE_ADDR,
	.sal_systab = EFI_INVALID_TABLE_ADDR,
	.boot_info  = EFI_INVALID_TABLE_ADDR,
	.hcdp       = EFI_INVALID_TABLE_ADDR,
	.uga        = EFI_INVALID_TABLE_ADDR,
	.uv_systab  = EFI_INVALID_TABLE_ADDR,
};
H
Huang, Ying 已提交
73 74 75 76
EXPORT_SYMBOL(efi);

struct efi_memory_map memmap;

H
Harvey Harrison 已提交
77
static struct efi efi_phys __initdata;
H
Huang, Ying 已提交
78 79
static efi_system_table_t efi_systab __initdata;

80 81 82
static u64 efi_var_store_size;
static u64 efi_var_remaining_size;
static u64 efi_var_max_var_size;
83 84 85
static u64 boot_used_size;
static u64 boot_var_size;
static u64 active_size;
86

87 88 89 90 91 92 93 94
unsigned long x86_efi_facility;

/*
 * Returns 1 if 'facility' is enabled, 0 otherwise.
 */
int efi_enabled(int facility)
{
	return test_bit(facility, &x86_efi_facility) != 0;
95
}
96
EXPORT_SYMBOL(efi_enabled);
97

98
static bool __initdata disable_runtime = false;
99 100
static int __init setup_noefi(char *arg)
{
101
	disable_runtime = true;
102 103 104 105
	return 0;
}
early_param("noefi", setup_noefi);

106 107 108 109 110 111 112 113 114 115 116
int add_efi_memmap;
EXPORT_SYMBOL(add_efi_memmap);

static int __init setup_add_efi_memmap(char *arg)
{
	add_efi_memmap = 1;
	return 0;
}
early_param("add_efi_memmap", setup_add_efi_memmap);


H
Huang, Ying 已提交
117 118
static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
{
119 120 121 122 123 124 125
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt2(get_time, tm, tc);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
H
Huang, Ying 已提交
126 127 128 129
}

static efi_status_t virt_efi_set_time(efi_time_t *tm)
{
130 131 132 133 134 135 136
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt1(set_time, tm);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
H
Huang, Ying 已提交
137 138 139 140 141 142
}

static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
					     efi_bool_t *pending,
					     efi_time_t *tm)
{
143 144 145 146 147 148 149 150
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt3(get_wakeup_time,
				enabled, pending, tm);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
H
Huang, Ying 已提交
151 152 153 154
}

static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
{
155 156 157 158 159 160 161 162
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt2(set_wakeup_time,
				enabled, tm);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
H
Huang, Ying 已提交
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179
}

static efi_status_t virt_efi_get_variable(efi_char16_t *name,
					  efi_guid_t *vendor,
					  u32 *attr,
					  unsigned long *data_size,
					  void *data)
{
	return efi_call_virt5(get_variable,
			      name, vendor, attr,
			      data_size, data);
}

static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
					       efi_char16_t *name,
					       efi_guid_t *vendor)
{
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
	efi_status_t status;
	static bool finished = false;
	static u64 var_size;

	status = efi_call_virt3(get_next_variable,
				name_size, name, vendor);

	if (status == EFI_NOT_FOUND) {
		finished = true;
		if (var_size < boot_used_size) {
			boot_var_size = boot_used_size - var_size;
			active_size += boot_var_size;
		} else {
			printk(KERN_WARNING FW_BUG  "efi: Inconsistent initial sizes\n");
		}
	}

	if (boot_used_size && !finished) {
		unsigned long size;
		u32 attr;
		efi_status_t s;
		void *tmp;

		s = virt_efi_get_variable(name, vendor, &attr, &size, NULL);

		if (s != EFI_BUFFER_TOO_SMALL || !size)
			return status;

		tmp = kmalloc(size, GFP_ATOMIC);

		if (!tmp)
			return status;

		s = virt_efi_get_variable(name, vendor, &attr, &size, tmp);

		if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) {
			var_size += size;
			var_size += ucs2_strsize(name, 1024);
			active_size += size;
			active_size += VAR_METADATA_SIZE;
			active_size += ucs2_strsize(name, 1024);
		}

		kfree(tmp);
	}

	return status;
H
Huang, Ying 已提交
227 228 229 230
}

static efi_status_t virt_efi_set_variable(efi_char16_t *name,
					  efi_guid_t *vendor,
231
					  u32 attr,
H
Huang, Ying 已提交
232 233 234
					  unsigned long data_size,
					  void *data)
{
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
	efi_status_t status;
	u32 orig_attr = 0;
	unsigned long orig_size = 0;

	status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size,
				       NULL);

	if (status != EFI_BUFFER_TOO_SMALL)
		orig_size = 0;

	status = efi_call_virt5(set_variable,
				name, vendor, attr,
				data_size, data);

	if (status == EFI_SUCCESS) {
		if (orig_size) {
			active_size -= orig_size;
			active_size -= ucs2_strsize(name, 1024);
			active_size -= VAR_METADATA_SIZE;
		}
		if (data_size) {
			active_size += data_size;
			active_size += ucs2_strsize(name, 1024);
			active_size += VAR_METADATA_SIZE;
		}
	}

	return status;
H
Huang, Ying 已提交
263 264
}

265 266 267 268 269 270 271 272 273 274 275 276
static efi_status_t virt_efi_query_variable_info(u32 attr,
						 u64 *storage_space,
						 u64 *remaining_space,
						 u64 *max_variable_size)
{
	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
		return EFI_UNSUPPORTED;

	return efi_call_virt4(query_variable_info, attr, storage_space,
			      remaining_space, max_variable_size);
}

H
Huang, Ying 已提交
277 278 279 280 281 282 283 284 285 286 287 288 289 290
static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
{
	return efi_call_virt1(get_next_high_mono_count, count);
}

static void virt_efi_reset_system(int reset_type,
				  efi_status_t status,
				  unsigned long data_size,
				  efi_char16_t *data)
{
	efi_call_virt4(reset_system, reset_type, status,
		       data_size, data);
}

291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312
static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
					    unsigned long count,
					    unsigned long sg_list)
{
	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
		return EFI_UNSUPPORTED;

	return efi_call_virt3(update_capsule, capsules, count, sg_list);
}

static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
						unsigned long count,
						u64 *max_size,
						int *reset_type)
{
	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
		return EFI_UNSUPPORTED;

	return efi_call_virt4(query_capsule_caps, capsules, count, max_size,
			      reset_type);
}

H
Huang, Ying 已提交
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328
static efi_status_t __init phys_efi_set_virtual_address_map(
	unsigned long memory_map_size,
	unsigned long descriptor_size,
	u32 descriptor_version,
	efi_memory_desc_t *virtual_map)
{
	efi_status_t status;

	efi_call_phys_prelog();
	status = efi_call_phys4(efi_phys.set_virtual_address_map,
				memory_map_size, descriptor_size,
				descriptor_version, virtual_map);
	efi_call_phys_epilog();
	return status;
}

329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
					     efi_time_cap_t *tc)
{
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	efi_call_phys_prelog();
	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
				virt_to_phys(tc));
	efi_call_phys_epilog();
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
}

int efi_set_rtc_mmss(unsigned long nowtime)
H
Huang, Ying 已提交
345 346 347 348 349 350 351 352
{
	int real_seconds, real_minutes;
	efi_status_t 	status;
	efi_time_t 	eft;
	efi_time_cap_t 	cap;

	status = efi.get_time(&eft, &cap);
	if (status != EFI_SUCCESS) {
353
		pr_err("Oops: efitime: can't read time!\n");
H
Huang, Ying 已提交
354 355 356 357 358 359 360 361 362 363 364 365 366
		return -1;
	}

	real_seconds = nowtime % 60;
	real_minutes = nowtime / 60;
	if (((abs(real_minutes - eft.minute) + 15)/30) & 1)
		real_minutes += 30;
	real_minutes %= 60;
	eft.minute = real_minutes;
	eft.second = real_seconds;

	status = efi.set_time(&eft);
	if (status != EFI_SUCCESS) {
367
		pr_err("Oops: efitime: can't write time!\n");
H
Huang, Ying 已提交
368 369 370 371 372
		return -1;
	}
	return 0;
}

373
unsigned long efi_get_time(void)
H
Huang, Ying 已提交
374 375 376 377 378 379 380
{
	efi_status_t status;
	efi_time_t eft;
	efi_time_cap_t cap;

	status = efi.get_time(&eft, &cap);
	if (status != EFI_SUCCESS)
381
		pr_err("Oops: efitime: can't read time!\n");
H
Huang, Ying 已提交
382 383 384 385 386

	return mktime(eft.year, eft.month, eft.day, eft.hour,
		      eft.minute, eft.second);
}

387 388 389 390 391 392
/*
 * Tell the kernel about the EFI memory map.  This might include
 * more than the max 128 entries that can fit in the e820 legacy
 * (zeropage) memory map.
 */

393
static void __init do_add_efi_memmap(void)
394 395 396 397 398 399 400 401 402
{
	void *p;

	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		efi_memory_desc_t *md = p;
		unsigned long long start = md->phys_addr;
		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
		int e820_type;

403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428
		switch (md->type) {
		case EFI_LOADER_CODE:
		case EFI_LOADER_DATA:
		case EFI_BOOT_SERVICES_CODE:
		case EFI_BOOT_SERVICES_DATA:
		case EFI_CONVENTIONAL_MEMORY:
			if (md->attribute & EFI_MEMORY_WB)
				e820_type = E820_RAM;
			else
				e820_type = E820_RESERVED;
			break;
		case EFI_ACPI_RECLAIM_MEMORY:
			e820_type = E820_ACPI;
			break;
		case EFI_ACPI_MEMORY_NVS:
			e820_type = E820_NVS;
			break;
		case EFI_UNUSABLE_MEMORY:
			e820_type = E820_UNUSABLE;
			break;
		default:
			/*
			 * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE
			 * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
			 * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
			 */
429
			e820_type = E820_RESERVED;
430 431
			break;
		}
432
		e820_add_region(start, size, e820_type);
433 434 435 436
	}
	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
}

437
int __init efi_memblock_x86_reserve_range(void)
438 439 440
{
	unsigned long pmap;

441
#ifdef CONFIG_X86_32
442 443 444 445 446
	/* Can't handle data above 4GB at this time */
	if (boot_params.efi_info.efi_memmap_hi) {
		pr_err("Memory map is above 4GB, disabling EFI.\n");
		return -EINVAL;
	}
447
	pmap = boot_params.efi_info.efi_memmap;
448 449 450
#else
	pmap = (boot_params.efi_info.efi_memmap |
		((__u64)boot_params.efi_info.efi_memmap_hi<<32));
451 452 453 454 455 456
#endif
	memmap.phys_map = (void *)pmap;
	memmap.nr_map = boot_params.efi_info.efi_memmap_size /
		boot_params.efi_info.efi_memdesc_size;
	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
457
	memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
458 459

	return 0;
460 461
}

H
Huang, Ying 已提交
462 463 464 465 466 467 468 469 470 471 472
#if EFI_DEBUG
static void __init print_efi_memmap(void)
{
	efi_memory_desc_t *md;
	void *p;
	int i;

	for (p = memmap.map, i = 0;
	     p < memmap.map_end;
	     p += memmap.desc_size, i++) {
		md = p;
473
		pr_info("mem%02u: type=%u, attr=0x%llx, "
H
Huang, Ying 已提交
474 475 476 477 478 479 480 481
			"range=[0x%016llx-0x%016llx) (%lluMB)\n",
			i, md->type, md->attribute, md->phys_addr,
			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
	}
}
#endif  /*  EFI_DEBUG  */

482 483 484 485 486 487
void __init efi_reserve_boot_services(void)
{
	void *p;

	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		efi_memory_desc_t *md = p;
488 489
		u64 start = md->phys_addr;
		u64 size = md->num_pages << EFI_PAGE_SHIFT;
490 491 492 493

		if (md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA)
			continue;
494 495 496 497 498 499
		/* Only reserve where possible:
		 * - Not within any already allocated areas
		 * - Not over any memory area (really needed, if above?)
		 * - Not within any part of the kernel
		 * - Not the bios reserved area
		*/
500 501
		if ((start+size >= __pa_symbol(_text)
				&& start <= __pa_symbol(_end)) ||
502
			!e820_all_mapped(start, start+size, E820_RAM) ||
503
			memblock_is_region_reserved(start, size)) {
504 505
			/* Could not reserve, skip it */
			md->num_pages = 0;
506
			memblock_dbg("Could not reserve boot range "
507 508 509
					"[0x%010llx-0x%010llx]\n",
						start, start+size-1);
		} else
510
			memblock_reserve(start, size);
511 512 513
	}
}

514
void __init efi_unmap_memmap(void)
515
{
516
	clear_bit(EFI_MEMMAP, &x86_efi_facility);
517 518 519 520 521 522 523
	if (memmap.map) {
		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
		memmap.map = NULL;
	}
}

void __init efi_free_boot_services(void)
524 525 526
{
	void *p;

527
	if (!efi_is_native())
528 529
		return;

530 531 532 533 534 535 536 537 538
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		efi_memory_desc_t *md = p;
		unsigned long long start = md->phys_addr;
		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;

		if (md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA)
			continue;

539 540 541 542
		/* Could not reserve boot area */
		if (!size)
			continue;

543 544
		free_bootmem_late(start, size);
	}
545 546

	efi_unmap_memmap();
547 548
}

549
static int __init efi_systab_init(void *phys)
H
Huang, Ying 已提交
550
{
551
	if (efi_enabled(EFI_64BIT)) {
552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
		efi_system_table_64_t *systab64;
		u64 tmp = 0;

		systab64 = early_ioremap((unsigned long)phys,
					 sizeof(*systab64));
		if (systab64 == NULL) {
			pr_err("Couldn't map the system table!\n");
			return -ENOMEM;
		}

		efi_systab.hdr = systab64->hdr;
		efi_systab.fw_vendor = systab64->fw_vendor;
		tmp |= systab64->fw_vendor;
		efi_systab.fw_revision = systab64->fw_revision;
		efi_systab.con_in_handle = systab64->con_in_handle;
		tmp |= systab64->con_in_handle;
		efi_systab.con_in = systab64->con_in;
		tmp |= systab64->con_in;
		efi_systab.con_out_handle = systab64->con_out_handle;
		tmp |= systab64->con_out_handle;
		efi_systab.con_out = systab64->con_out;
		tmp |= systab64->con_out;
		efi_systab.stderr_handle = systab64->stderr_handle;
		tmp |= systab64->stderr_handle;
		efi_systab.stderr = systab64->stderr;
		tmp |= systab64->stderr;
		efi_systab.runtime = (void *)(unsigned long)systab64->runtime;
		tmp |= systab64->runtime;
		efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
		tmp |= systab64->boottime;
		efi_systab.nr_tables = systab64->nr_tables;
		efi_systab.tables = systab64->tables;
		tmp |= systab64->tables;

		early_iounmap(systab64, sizeof(*systab64));
#ifdef CONFIG_X86_32
		if (tmp >> 32) {
			pr_err("EFI data located above 4GB, disabling EFI.\n");
			return -EINVAL;
		}
#endif
	} else {
		efi_system_table_32_t *systab32;

		systab32 = early_ioremap((unsigned long)phys,
					 sizeof(*systab32));
		if (systab32 == NULL) {
			pr_err("Couldn't map the system table!\n");
			return -ENOMEM;
		}

		efi_systab.hdr = systab32->hdr;
		efi_systab.fw_vendor = systab32->fw_vendor;
		efi_systab.fw_revision = systab32->fw_revision;
		efi_systab.con_in_handle = systab32->con_in_handle;
		efi_systab.con_in = systab32->con_in;
		efi_systab.con_out_handle = systab32->con_out_handle;
		efi_systab.con_out = systab32->con_out;
		efi_systab.stderr_handle = systab32->stderr_handle;
		efi_systab.stderr = systab32->stderr;
		efi_systab.runtime = (void *)(unsigned long)systab32->runtime;
		efi_systab.boottime = (void *)(unsigned long)systab32->boottime;
		efi_systab.nr_tables = systab32->nr_tables;
		efi_systab.tables = systab32->tables;

		early_iounmap(systab32, sizeof(*systab32));
618
	}
619

H
Huang, Ying 已提交
620 621 622 623 624
	efi.systab = &efi_systab;

	/*
	 * Verify the EFI Table
	 */
625
	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
626
		pr_err("System table signature incorrect!\n");
627 628
		return -EINVAL;
	}
H
Huang, Ying 已提交
629
	if ((efi.systab->hdr.revision >> 16) == 0)
630
		pr_err("Warning: System table version "
H
Huang, Ying 已提交
631 632 633
		       "%d.%02d, expected 1.00 or greater!\n",
		       efi.systab->hdr.revision >> 16,
		       efi.systab->hdr.revision & 0xffff);
634 635

	return 0;
636
}
H
Huang, Ying 已提交
637

638
static int __init efi_config_init(u64 tables, int nr_tables)
639
{
640 641 642
	void *config_tables, *tablep;
	int i, sz;

643
	if (efi_enabled(EFI_64BIT))
644 645 646
		sz = sizeof(efi_config_table_64_t);
	else
		sz = sizeof(efi_config_table_32_t);
H
Huang, Ying 已提交
647 648 649 650

	/*
	 * Let's see what config tables the firmware passed to us.
	 */
651
	config_tables = early_ioremap(tables, nr_tables * sz);
652
	if (config_tables == NULL) {
653
		pr_err("Could not map Configuration table!\n");
654 655
		return -ENOMEM;
	}
H
Huang, Ying 已提交
656

657
	tablep = config_tables;
658
	pr_info("");
H
Huang, Ying 已提交
659
	for (i = 0; i < efi.systab->nr_tables; i++) {
660 661 662
		efi_guid_t guid;
		unsigned long table;

663
		if (efi_enabled(EFI_64BIT)) {
664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680
			u64 table64;
			guid = ((efi_config_table_64_t *)tablep)->guid;
			table64 = ((efi_config_table_64_t *)tablep)->table;
			table = table64;
#ifdef CONFIG_X86_32
			if (table64 >> 32) {
				pr_cont("\n");
				pr_err("Table located above 4GB, disabling EFI.\n");
				early_iounmap(config_tables,
					      efi.systab->nr_tables * sz);
				return -EINVAL;
			}
#endif
		} else {
			guid = ((efi_config_table_32_t *)tablep)->guid;
			table = ((efi_config_table_32_t *)tablep)->table;
		}
681 682 683 684 685 686 687 688 689 690 691 692
		if (!efi_guidcmp(guid, MPS_TABLE_GUID)) {
			efi.mps = table;
			pr_cont(" MPS=0x%lx ", table);
		} else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) {
			efi.acpi20 = table;
			pr_cont(" ACPI 2.0=0x%lx ", table);
		} else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) {
			efi.acpi = table;
			pr_cont(" ACPI=0x%lx ", table);
		} else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) {
			efi.smbios = table;
			pr_cont(" SMBIOS=0x%lx ", table);
N
Nick Piggin 已提交
693
#ifdef CONFIG_X86_UV
694 695 696
		} else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) {
			efi.uv_systab = table;
			pr_cont(" UVsystab=0x%lx ", table);
N
Nick Piggin 已提交
697
#endif
698 699 700 701 702 703
		} else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) {
			efi.hcdp = table;
			pr_cont(" HCDP=0x%lx ", table);
		} else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) {
			efi.uga = table;
			pr_cont(" UGA=0x%lx ", table);
H
Huang, Ying 已提交
704
		}
705
		tablep += sz;
H
Huang, Ying 已提交
706
	}
707
	pr_cont("\n");
708
	early_iounmap(config_tables, efi.systab->nr_tables * sz);
709
	return 0;
710 711
}

712
static int __init efi_runtime_init(void)
713 714
{
	efi_runtime_services_t *runtime;
H
Huang, Ying 已提交
715 716 717 718 719 720 721

	/*
	 * Check out the runtime services table. We need to map
	 * the runtime services table so that we can grab the physical
	 * address of several of the EFI runtime functions, needed to
	 * set the firmware into virtual mode.
	 */
722 723
	runtime = early_ioremap((unsigned long)efi.systab->runtime,
				sizeof(efi_runtime_services_t));
724
	if (!runtime) {
725
		pr_err("Could not map the runtime service table!\n");
726 727 728 729
		return -ENOMEM;
	}
	/*
	 * We will only need *early* access to the following
730
	 * two EFI runtime services before set_virtual_address_map
731 732
	 * is invoked.
	 */
733
	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
734 735 736
	efi_phys.set_virtual_address_map =
		(efi_set_virtual_address_map_t *)
		runtime->set_virtual_address_map;
737 738 739 740 741
	/*
	 * Make efi_get_time can be called before entering
	 * virtual mode.
	 */
	efi.get_time = phys_efi_get_time;
742
	early_iounmap(runtime, sizeof(efi_runtime_services_t));
743 744

	return 0;
745
}
H
Huang, Ying 已提交
746

747
static int __init efi_memmap_init(void)
748
{
H
Huang, Ying 已提交
749
	/* Map the EFI memory map */
750 751
	memmap.map = early_ioremap((unsigned long)memmap.phys_map,
				   memmap.nr_map * memmap.desc_size);
752
	if (memmap.map == NULL) {
753
		pr_err("Could not map the memory map!\n");
754 755
		return -ENOMEM;
	}
H
Huang, Ying 已提交
756
	memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
R
Russ Anderson 已提交
757

758 759
	if (add_efi_memmap)
		do_add_efi_memmap();
760 761

	return 0;
762 763 764 765 766 767 768 769
}

void __init efi_init(void)
{
	efi_char16_t *c16;
	char vendor[100] = "unknown";
	int i = 0;
	void *tmp;
770 771 772
	struct setup_data *data;
	struct efi_var_bootdata *efi_var_data;
	u64 pa_data;
773 774

#ifdef CONFIG_X86_32
775 776 777 778 779
	if (boot_params.efi_info.efi_systab_hi ||
	    boot_params.efi_info.efi_memmap_hi) {
		pr_info("Table located above 4GB, disabling EFI.\n");
		return;
	}
780 781 782
	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
#else
	efi_phys.systab = (efi_system_table_t *)
783 784
			  (boot_params.efi_info.efi_systab |
			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
785 786
#endif

787
	if (efi_systab_init(efi_phys.systab))
788
		return;
789

790 791 792 793 794 795 796 797 798 799 800 801 802 803
	pa_data = boot_params.hdr.setup_data;
	while (pa_data) {
		data = early_ioremap(pa_data, sizeof(*efi_var_data));
		if (data->type == SETUP_EFI_VARS) {
			efi_var_data = (struct efi_var_bootdata *)data;

			efi_var_store_size = efi_var_data->store_size;
			efi_var_remaining_size = efi_var_data->remaining_size;
			efi_var_max_var_size = efi_var_data->max_var_size;
		}
		pa_data = data->next;
		early_iounmap(data, sizeof(*efi_var_data));
	}

804 805
	boot_used_size = efi_var_store_size - efi_var_remaining_size;

806
	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
807 808 809 810 811 812 813 814 815 816

	/*
	 * Show what we know for posterity
	 */
	c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2);
	if (c16) {
		for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i)
			vendor[i] = *c16++;
		vendor[i] = '\0';
	} else
817
		pr_err("Could not map the firmware vendor!\n");
818 819
	early_iounmap(tmp, 2);

820 821 822
	pr_info("EFI v%u.%.02u by %s\n",
		efi.systab->hdr.revision >> 16,
		efi.systab->hdr.revision & 0xffff, vendor);
823

824
	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
825
		return;
826 827

	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
828

829 830 831 832 833
	/*
	 * Note: We currently don't support runtime services on an EFI
	 * that doesn't match the kernel 32/64-bit mode.
	 */

834
	if (!efi_is_native())
835
		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
836
	else {
837
		if (disable_runtime || efi_runtime_init())
838 839
			return;
		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
840
	}
841

842
	if (efi_memmap_init())
843
		return;
844 845 846

	set_bit(EFI_MEMMAP, &x86_efi_facility);

847
#ifdef CONFIG_X86_32
848
	if (efi_is_native()) {
849 850 851
		x86_platform.get_wallclock = efi_get_time;
		x86_platform.set_wallclock = efi_set_rtc_mmss;
	}
852
#endif
853

H
Huang, Ying 已提交
854 855 856 857 858
#if EFI_DEBUG
	print_efi_memmap();
#endif
}

859 860 861 862 863
void __init efi_late_init(void)
{
	efi_bgrt_init();
}

864 865 866 867 868 869 870 871 872 873 874 875 876 877 878
void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
{
	u64 addr, npages;

	addr = md->virt_addr;
	npages = md->num_pages;

	memrange_efi_to_native(&addr, &npages);

	if (executable)
		set_memory_x(addr, npages);
	else
		set_memory_nx(addr, npages);
}

879 880 881 882 883 884 885 886
static void __init runtime_code_page_mkexec(void)
{
	efi_memory_desc_t *md;
	void *p;

	/* Make EFI runtime service code area executable */
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;
H
Huang, Ying 已提交
887 888 889 890

		if (md->type != EFI_RUNTIME_SERVICES_CODE)
			continue;

891
		efi_set_executable(md, true);
892 893 894
	}
}

895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922
/*
 * We can't ioremap data in EFI boot services RAM, because we've already mapped
 * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
 * callable after efi_enter_virtual_mode and before efi_free_boot_services.
 */
void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
{
	void *p;
	if (WARN_ON(!memmap.map))
		return NULL;
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		efi_memory_desc_t *md = p;
		u64 size = md->num_pages << EFI_PAGE_SHIFT;
		u64 end = md->phys_addr + size;
		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
		    md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA)
			continue;
		if (!md->virt_addr)
			continue;
		if (phys_addr >= md->phys_addr && phys_addr < end) {
			phys_addr += md->virt_addr - md->phys_addr;
			return (__force void __iomem *)(unsigned long)phys_addr;
		}
	}
	return NULL;
}

923 924 925 926 927 928 929 930 931 932
void efi_memory_uc(u64 addr, unsigned long size)
{
	unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
	u64 npages;

	npages = round_up(size, page_shift) / page_shift;
	memrange_efi_to_native(&addr, &npages);
	set_memory_uc(addr, npages);
}

H
Huang, Ying 已提交
933 934 935 936 937 938 939 940 941 942
/*
 * This function will switch the EFI runtime services to virtual mode.
 * Essentially, look through the EFI memmap and map every region that
 * has the runtime attribute bit set in its memory descriptor and update
 * that memory descriptor with the virtual address obtained from ioremap().
 * This enables the runtime services to be called without having to
 * thunk back into physical mode for every invocation.
 */
void __init efi_enter_virtual_mode(void)
{
943
	efi_memory_desc_t *md, *prev_md = NULL;
H
Huang, Ying 已提交
944
	efi_status_t status;
H
Huang, Ying 已提交
945
	unsigned long size;
946
	u64 end, systab, start_pfn, end_pfn;
947 948
	void *p, *va, *new_memmap = NULL;
	int count = 0;
H
Huang, Ying 已提交
949 950

	efi.systab = NULL;
951

952 953 954 955 956
	/*
	 * We don't do virtual mode, since we don't do runtime services, on
	 * non-native EFI
	 */

957
	if (!efi_is_native()) {
958 959 960
		efi_unmap_memmap();
		return;
	}
961

962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988
	/* Merge contiguous regions of the same type and attribute */
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		u64 prev_size;
		md = p;

		if (!prev_md) {
			prev_md = md;
			continue;
		}

		if (prev_md->type != md->type ||
		    prev_md->attribute != md->attribute) {
			prev_md = md;
			continue;
		}

		prev_size = prev_md->num_pages << EFI_PAGE_SHIFT;

		if (md->phys_addr == (prev_md->phys_addr + prev_size)) {
			prev_md->num_pages += md->num_pages;
			md->type = EFI_RESERVED_TYPE;
			md->attribute = 0;
			continue;
		}
		prev_md = md;
	}

H
Huang, Ying 已提交
989 990
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;
991 992 993
		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
		    md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA)
H
Huang, Ying 已提交
994
			continue;
H
Huang, Ying 已提交
995 996 997 998

		size = md->num_pages << EFI_PAGE_SHIFT;
		end = md->phys_addr + size;

999
		start_pfn = PFN_DOWN(md->phys_addr);
1000
		end_pfn = PFN_UP(end);
1001
		if (pfn_range_is_mapped(start_pfn, end_pfn)) {
H
Huang, Ying 已提交
1002
			va = __va(md->phys_addr);
1003 1004 1005 1006 1007 1008

			if (!(md->attribute & EFI_MEMORY_WB))
				efi_memory_uc((u64)(unsigned long)va, size);
		} else
			va = efi_ioremap(md->phys_addr, size,
					 md->type, md->attribute);
H
Huang, Ying 已提交
1009 1010 1011 1012

		md->virt_addr = (u64) (unsigned long) va;

		if (!va) {
1013
			pr_err("ioremap of 0x%llX failed!\n",
H
Huang, Ying 已提交
1014
			       (unsigned long long)md->phys_addr);
H
Huang, Ying 已提交
1015 1016 1017 1018 1019 1020 1021 1022
			continue;
		}

		systab = (u64) (unsigned long) efi_phys.systab;
		if (md->phys_addr <= systab && systab < end) {
			systab += md->virt_addr - md->phys_addr;
			efi.systab = (efi_system_table_t *) (unsigned long) systab;
		}
1023 1024 1025 1026 1027 1028
		new_memmap = krealloc(new_memmap,
				      (count + 1) * memmap.desc_size,
				      GFP_KERNEL);
		memcpy(new_memmap + (count * memmap.desc_size), md,
		       memmap.desc_size);
		count++;
H
Huang, Ying 已提交
1029 1030 1031 1032 1033
	}

	BUG_ON(!efi.systab);

	status = phys_efi_set_virtual_address_map(
1034
		memmap.desc_size * count,
H
Huang, Ying 已提交
1035 1036
		memmap.desc_size,
		memmap.desc_version,
1037
		(efi_memory_desc_t *)__pa(new_memmap));
H
Huang, Ying 已提交
1038 1039

	if (status != EFI_SUCCESS) {
1040 1041
		pr_alert("Unable to switch EFI into virtual mode "
			 "(status=%lx)!\n", status);
H
Huang, Ying 已提交
1042 1043 1044 1045 1046 1047 1048 1049 1050
		panic("EFI call to SetVirtualAddressMap() failed!");
	}

	/*
	 * Now that EFI is in virtual mode, update the function
	 * pointers in the runtime service table to the new virtual addresses.
	 *
	 * Call EFI services through wrapper functions.
	 */
1051
	efi.runtime_version = efi_systab.hdr.revision;
H
Huang, Ying 已提交
1052 1053 1054 1055 1056 1057 1058 1059 1060
	efi.get_time = virt_efi_get_time;
	efi.set_time = virt_efi_set_time;
	efi.get_wakeup_time = virt_efi_get_wakeup_time;
	efi.set_wakeup_time = virt_efi_set_wakeup_time;
	efi.get_variable = virt_efi_get_variable;
	efi.get_next_variable = virt_efi_get_next_variable;
	efi.set_variable = virt_efi_set_variable;
	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
	efi.reset_system = virt_efi_reset_system;
1061
	efi.set_virtual_address_map = NULL;
1062 1063 1064
	efi.query_variable_info = virt_efi_query_variable_info;
	efi.update_capsule = virt_efi_update_capsule;
	efi.query_capsule_caps = virt_efi_query_capsule_caps;
1065 1066
	if (__supported_pte_mask & _PAGE_NX)
		runtime_code_page_mkexec();
1067

1068
	kfree(new_memmap);
H
Huang, Ying 已提交
1069 1070 1071 1072 1073 1074 1075 1076 1077 1078
}

/*
 * Convenience functions to obtain memory types and attributes
 */
u32 efi_mem_type(unsigned long phys_addr)
{
	efi_memory_desc_t *md;
	void *p;

1079 1080 1081
	if (!efi_enabled(EFI_MEMMAP))
		return 0;

H
Huang, Ying 已提交
1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;
		if ((md->phys_addr <= phys_addr) &&
		    (phys_addr < (md->phys_addr +
				  (md->num_pages << EFI_PAGE_SHIFT))))
			return md->type;
	}
	return 0;
}

u64 efi_mem_attributes(unsigned long phys_addr)
{
	efi_memory_desc_t *md;
	void *p;

	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;
		if ((md->phys_addr <= phys_addr) &&
		    (phys_addr < (md->phys_addr +
				  (md->num_pages << EFI_PAGE_SHIFT))))
			return md->attribute;
	}
	return 0;
}
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124

/*
 * Some firmware has serious problems when using more than 50% of the EFI
 * variable store, i.e. it triggers bugs that can brick machines. Ensure that
 * we never use more than this safe limit.
 *
 * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
 * store.
 */
efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
{
	efi_status_t status;
	u64 storage_size, remaining_size, max_size;

	status = efi.query_variable_info(attributes, &storage_size,
					 &remaining_size, &max_size);
	if (status != EFI_SUCCESS)
		return status;

1125 1126 1127
	if (!max_size && remaining_size > size)
		printk_once(KERN_ERR FW_BUG "Broken EFI implementation"
			    " is returning MaxVariableSize=0\n");
1128 1129 1130 1131 1132 1133 1134 1135 1136 1137
	/*
	 * Some firmware implementations refuse to boot if there's insufficient
	 * space in the variable store. We account for that by refusing the
	 * write if permitting it would reduce the available space to under
	 * 50%. However, some firmware won't reclaim variable space until
	 * after the used (not merely the actively used) space drops below
	 * a threshold. We can approximate that case with the value calculated
	 * above. If both the firmware and our calculations indicate that the
	 * available space would drop below 50%, refuse the write.
	 */
1138 1139 1140

	if (!storage_size || size > remaining_size ||
	    (max_size && size > max_size) ||
1141 1142
	    ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) &&
	     (remaining_size - size < storage_size / 2)))
1143 1144 1145 1146
		return EFI_OUT_OF_RESOURCES;

	return EFI_SUCCESS;
}