aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/platform/efi/efi.c
blob: 59f7f6d60cf61a8410688514bd5fc9107ccd5d75 (plain)
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
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
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
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
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
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
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
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
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
989
990
991
992
993
994
995
996
997
998
999
1000
1001
// SPDX-License-Identifier: GPL-2.0
/*
 * 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>
 * Copyright (C) 2013 SuSE Labs
 *	Borislav Petkov <bp@suse.de> - runtime services VA mapping
 *
 * 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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/efi.h>
#include <linux/efi-bgrt.h>
#include <linux/export.h>
#include <linux/memblock.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>
#include <linux/time.h>
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/bcd.h>

#include <asm/setup.h>
#include <asm/efi.h>
#include <asm/e820/api.h>
#include <asm/time.h>
#include <asm/set_memory.h>
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/uv/uv.h>

static efi_system_table_t efi_systab __initdata;
static u64 efi_systab_phys __initdata;

static efi_config_table_type_t arch_tables[] __initdata = {
#ifdef CONFIG_X86_UV
	{UV_SYSTEM_TABLE_GUID, "UVsystab", &uv_systab_phys},
#endif
	{NULL_GUID, NULL, NULL},
};

static const unsigned long * const efi_tables[] = {
	&efi.mps,
	&efi.acpi,
	&efi.acpi20,
	&efi.smbios,
	&efi.smbios3,
	&efi.boot_info,
	&efi.hcdp,
	&efi.uga,
#ifdef CONFIG_X86_UV
	&uv_systab_phys,
#endif
	&efi.fw_vendor,
	&efi.runtime,
	&efi.config_table,
	&efi.esrt,
	&efi.properties_table,
	&efi.mem_attr_table,
#ifdef CONFIG_EFI_RCI2_TABLE
	&rci2_table_phys,
#endif
};

u64 efi_setup;		/* efi setup_data physical address */

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

void __init efi_find_mirror(void)
{
	efi_memory_desc_t *md;
	u64 mirror_size = 0, total_size = 0;

	if (!efi_enabled(EFI_MEMMAP))
		return;

	for_each_efi_memory_desc(md) {
		unsigned long long start = md->phys_addr;
		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;

		total_size += size;
		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
			memblock_mark_mirror(start, size);
			mirror_size += size;
		}
	}
	if (mirror_size)
		pr_info("Memory: %lldM/%lldM mirrored memory\n",
			mirror_size>>20, total_size>>20);
}

/*
 * Tell the kernel about the EFI memory map.  This might include
 * more than the max 128 entries that can fit in the passed in e820
 * legacy (zeropage) memory map, but the kernel's e820 table can hold
 * E820_MAX_ENTRIES.
 */

static void __init do_add_efi_memmap(void)
{
	efi_memory_desc_t *md;

	if (!efi_enabled(EFI_MEMMAP))
		return;

	for_each_efi_memory_desc(md) {
		unsigned long long start = md->phys_addr;
		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
		int e820_type;

		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 (efi_soft_reserve_enabled()
			    && (md->attribute & EFI_MEMORY_SP))
				e820_type = E820_TYPE_SOFT_RESERVED;
			else if (md->attribute & EFI_MEMORY_WB)
				e820_type = E820_TYPE_RAM;
			else
				e820_type = E820_TYPE_RESERVED;
			break;
		case EFI_ACPI_RECLAIM_MEMORY:
			e820_type = E820_TYPE_ACPI;
			break;
		case EFI_ACPI_MEMORY_NVS:
			e820_type = E820_TYPE_NVS;
			break;
		case EFI_UNUSABLE_MEMORY:
			e820_type = E820_TYPE_UNUSABLE;
			break;
		case EFI_PERSISTENT_MEMORY:
			e820_type = E820_TYPE_PMEM;
			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
			 */
			e820_type = E820_TYPE_RESERVED;
			break;
		}

		e820__range_add(start, size, e820_type);
	}
	e820__update_table(e820_table);
}

/*
 * Given add_efi_memmap defaults to 0 and there there is no alternative
 * e820 mechanism for soft-reserved memory, import the full EFI memory
 * map if soft reservations are present and enabled. Otherwise, the
 * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is
 * the efi=nosoftreserve option.
 */
static bool do_efi_soft_reserve(void)
{
	efi_memory_desc_t *md;

	if (!efi_enabled(EFI_MEMMAP))
		return false;

	if (!efi_soft_reserve_enabled())
		return false;

	for_each_efi_memory_desc(md)
		if (md->type == EFI_CONVENTIONAL_MEMORY &&
		    (md->attribute & EFI_MEMORY_SP))
			return true;
	return false;
}

int __init efi_memblock_x86_reserve_range(void)
{
	struct efi_info *e = &boot_params.efi_info;
	struct efi_memory_map_data data;
	phys_addr_t pmap;
	int rv;

	if (efi_enabled(EFI_PARAVIRT))
		return 0;

#ifdef CONFIG_X86_32
	/* Can't handle data above 4GB at this time */
	if (e->efi_memmap_hi) {
		pr_err("Memory map is above 4GB, disabling EFI.\n");
		return -EINVAL;
	}
	pmap =  e->efi_memmap;
#else
	pmap = (e->efi_memmap |	((__u64)e->efi_memmap_hi << 32));
#endif
	data.phys_map		= pmap;
	data.size 		= e->efi_memmap_size;
	data.desc_size		= e->efi_memdesc_size;
	data.desc_version	= e->efi_memdesc_version;

	rv = efi_memmap_init_early(&data);
	if (rv)
		return rv;

	if (add_efi_memmap || do_efi_soft_reserve())
		do_add_efi_memmap();

	efi_fake_memmap_early();

	WARN(efi.memmap.desc_version != 1,
	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
	     efi.memmap.desc_version);

	memblock_reserve(pmap, efi.memmap.nr_map * efi.memmap.desc_size);

	return 0;
}

#define OVERFLOW_ADDR_SHIFT	(64 - EFI_PAGE_SHIFT)
#define OVERFLOW_ADDR_MASK	(U64_MAX << OVERFLOW_ADDR_SHIFT)
#define U64_HIGH_BIT		(~(U64_MAX >> 1))

static bool __init efi_memmap_entry_valid(const efi_memory_desc_t *md, int i)
{
	u64 end = (md->num_pages << EFI_PAGE_SHIFT) + md->phys_addr - 1;
	u64 end_hi = 0;
	char buf[64];

	if (md->num_pages == 0) {
		end = 0;
	} else if (md->num_pages > EFI_PAGES_MAX ||
		   EFI_PAGES_MAX - md->num_pages <
		   (md->phys_addr >> EFI_PAGE_SHIFT)) {
		end_hi = (md->num_pages & OVERFLOW_ADDR_MASK)
			>> OVERFLOW_ADDR_SHIFT;

		if ((md->phys_addr & U64_HIGH_BIT) && !(end & U64_HIGH_BIT))
			end_hi += 1;
	} else {
		return true;
	}

	pr_warn_once(FW_BUG "Invalid EFI memory map entries:\n");

	if (end_hi) {
		pr_warn("mem%02u: %s range=[0x%016llx-0x%llx%016llx] (invalid)\n",
			i, efi_md_typeattr_format(buf, sizeof(buf), md),
			md->phys_addr, end_hi, end);
	} else {
		pr_warn("mem%02u: %s range=[0x%016llx-0x%016llx] (invalid)\n",
			i, efi_md_typeattr_format(buf, sizeof(buf), md),
			md->phys_addr, end);
	}
	return false;
}

static void __init efi_clean_memmap(void)
{
	efi_memory_desc_t *out = efi.memmap.map;
	const efi_memory_desc_t *in = out;
	const efi_memory_desc_t *end = efi.memmap.map_end;
	int i, n_removal;

	for (i = n_removal = 0; in < end; i++) {
		if (efi_memmap_entry_valid(in, i)) {
			if (out != in)
				memcpy(out, in, efi.memmap.desc_size);
			out = (void *)out + efi.memmap.desc_size;
		} else {
			n_removal++;
		}
		in = (void *)in + efi.memmap.desc_size;
	}

	if (n_removal > 0) {
		struct efi_memory_map_data data = {
			.phys_map = efi.memmap.phys_map,
			.desc_version = efi.memmap.desc_version,
			.desc_size = efi.memmap.desc_size,
			.size = data.desc_size * (efi.memmap.nr_map - n_removal),
			.flags = 0,
		};

		pr_warn("Removing %d invalid memory map entries.\n", n_removal);
		efi_memmap_install(&data);
	}
}

void __init efi_print_memmap(void)
{
	efi_memory_desc_t *md;
	int i = 0;

	for_each_efi_memory_desc(md) {
		char buf[64];

		pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n",
			i++, efi_md_typeattr_format(buf, sizeof(buf), md),
			md->phys_addr,
			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1,
			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
	}
}

static int __init efi_systab_init(u64 phys)
{
	int size = efi_enabled(EFI_64BIT) ? sizeof(efi_system_table_64_t)
					  : sizeof(efi_system_table_32_t);
	bool over4g = false;
	void *p;

	p = early_memremap_ro(phys, size);
	if (p == NULL) {
		pr_err("Couldn't map the system table!\n");
		return -ENOMEM;
	}

	if (efi_enabled(EFI_64BIT)) {
		const efi_system_table_64_t *systab64 = p;

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

		over4g = systab64->con_in_handle	> U32_MAX ||
			 systab64->con_in		> U32_MAX ||
			 systab64->con_out_handle	> U32_MAX ||
			 systab64->con_out		> U32_MAX ||
			 systab64->stderr_handle	> U32_MAX ||
			 systab64->stderr		> U32_MAX ||
			 systab64->boottime		> U32_MAX;

		if (efi_setup) {
			struct efi_setup_data *data;

			data = early_memremap_ro(efi_setup, sizeof(*data));
			if (!data) {
				early_memunmap(p, size);
				return -ENOMEM;
			}

			efi_systab.fw_vendor	= (unsigned long)data->fw_vendor;
			efi_systab.runtime	= (void *)(unsigned long)data->runtime;
			efi_systab.tables	= (unsigned long)data->tables;

			over4g |= data->fw_vendor	> U32_MAX ||
				  data->runtime		> U32_MAX ||
				  data->tables		> U32_MAX;

			early_memunmap(data, sizeof(*data));
		} else {
			over4g |= systab64->fw_vendor	> U32_MAX ||
				  systab64->runtime	> U32_MAX ||
				  systab64->tables	> U32_MAX;
		}
	} else {
		const efi_system_table_32_t *systab32 = p;

		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		= (void *)(unsigned long)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_memunmap(p, size);

	if (IS_ENABLED(CONFIG_X86_32) && over4g) {
		pr_err("EFI data located above 4GB, disabling EFI.\n");
		return -EINVAL;
	}

	efi.systab = &efi_systab;

	/*
	 * Verify the EFI Table
	 */
	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
		pr_err("System table signature incorrect!\n");
		return -EINVAL;
	}
	if ((efi.systab->hdr.revision >> 16) == 0)
		pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n",
		       efi.systab->hdr.revision >> 16,
		       efi.systab->hdr.revision & 0xffff);

	return 0;
}

void __init efi_init(void)
{
	efi_char16_t *c16;
	char vendor[100] = "unknown";
	int i = 0;

	if (IS_ENABLED(CONFIG_X86_32) &&
	    (boot_params.efi_info.efi_systab_hi ||
	     boot_params.efi_info.efi_memmap_hi)) {
		pr_info("Table located above 4GB, disabling EFI.\n");
		return;
	}

	efi_systab_phys = boot_params.efi_info.efi_systab |
			  ((__u64)boot_params.efi_info.efi_systab_hi << 32);

	if (efi_systab_init(efi_systab_phys))
		return;

	efi.config_table = (unsigned long)efi.systab->tables;
	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
	efi.runtime	 = (unsigned long)efi.systab->runtime;

	/*
	 * Show what we know for posterity
	 */
	c16 = early_memremap_ro(efi.systab->fw_vendor,
				sizeof(vendor) * sizeof(efi_char16_t));
	if (c16) {
		for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i)
			vendor[i] = c16[i];
		vendor[i] = '\0';
		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
	} else {
		pr_err("Could not map the firmware vendor!\n");
	}

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

	if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables))
		return;

	if (efi_config_init(arch_tables))
		return;

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

	if (!efi_runtime_supported())
		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");

	if (!efi_runtime_supported() || efi_runtime_disabled()) {
		efi_memmap_unmap();
		return;
	}

	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
	efi_clean_memmap();

	if (efi_enabled(EFI_DBG))
		efi_print_memmap();
}

#if defined(CONFIG_X86_32) || defined(CONFIG_X86_UV)

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);
}

void __init runtime_code_page_mkexec(void)
{
	efi_memory_desc_t *md;

	/* Make EFI runtime service code area executable */
	for_each_efi_memory_desc(md) {
		if (md->type != EFI_RUNTIME_SERVICES_CODE)
			continue;

		efi_set_executable(md, true);
	}
}

void __init 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);
}

void __init old_map_region(efi_memory_desc_t *md)
{
	u64 start_pfn, end_pfn, end;
	unsigned long size;
	void *va;

	start_pfn = PFN_DOWN(md->phys_addr);
	size	  = md->num_pages << PAGE_SHIFT;
	end	  = md->phys_addr + size;
	end_pfn   = PFN_UP(end);

	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
		va = __va(md->phys_addr);

		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);

	md->virt_addr = (u64) (unsigned long) va;
	if (!va)
		pr_err("ioremap of 0x%llX failed!\n",
		       (unsigned long long)md->phys_addr);
}

#endif

/* Merge contiguous regions of the same type and attribute */
static void __init efi_merge_regions(void)
{
	efi_memory_desc_t *md, *prev_md = NULL;

	for_each_efi_memory_desc(md) {
		u64 prev_size;

		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;
	}
}

static void __init get_systab_virt_addr(efi_memory_desc_t *md)
{
	unsigned long size;
	u64 end, systab;

	size = md->num_pages << EFI_PAGE_SHIFT;
	end = md->phys_addr + size;
	systab = efi_systab_phys;
	if (md->phys_addr <= systab && systab < end) {
		systab += md->virt_addr - md->phys_addr;
		efi.systab = (efi_system_table_t *)(unsigned long)systab;
	}
}

static void *realloc_pages(void *old_memmap, int old_shift)
{
	void *ret;

	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
	if (!ret)
		goto out;

	/*
	 * A first-time allocation doesn't have anything to copy.
	 */
	if (!old_memmap)
		return ret;

	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);

out:
	free_pages((unsigned long)old_memmap, old_shift);
	return ret;
}

/*
 * Iterate the EFI memory map in reverse order because the regions
 * will be mapped top-down. The end result is the same as if we had
 * mapped things forward, but doesn't require us to change the
 * existing implementation of efi_map_region().
 */
static inline void *efi_map_next_entry_reverse(void *entry)
{
	/* Initial call */
	if (!entry)
		return efi.memmap.map_end - efi.memmap.desc_size;

	entry -= efi.memmap.desc_size;
	if (entry < efi.memmap.map)
		return NULL;

	return entry;
}

/*
 * efi_map_next_entry - Return the next EFI memory map descriptor
 * @entry: Previous EFI memory map descriptor
 *
 * This is a helper function to iterate over the EFI memory map, which
 * we do in different orders depending on the current configuration.
 *
 * To begin traversing the memory map @entry must be %NULL.
 *
 * Returns %NULL when we reach the end of the memory map.
 */
static void *efi_map_next_entry(void *entry)
{
	if (!efi_have_uv1_memmap() && efi_enabled(EFI_64BIT)) {
		/*
		 * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE
		 * config table feature requires us to map all entries
		 * in the same order as they appear in the EFI memory
		 * map. That is to say, entry N must have a lower
		 * virtual address than entry N+1. This is because the
		 * firmware toolchain leaves relative references in
		 * the code/data sections, which are split and become
		 * separate EFI memory regions. Mapping things
		 * out-of-order leads to the firmware accessing
		 * unmapped addresses.
		 *
		 * Since we need to map things this way whether or not
		 * the kernel actually makes use of
		 * EFI_PROPERTIES_TABLE, let's just switch to this
		 * scheme by default for 64-bit.
		 */
		return efi_map_next_entry_reverse(entry);
	}

	/* Initial call */
	if (!entry)
		return efi.memmap.map;

	entry += efi.memmap.desc_size;
	if (entry >= efi.memmap.map_end)
		return NULL;

	return entry;
}

static bool should_map_region(efi_memory_desc_t *md)
{
	/*
	 * Runtime regions always require runtime mappings (obviously).
	 */
	if (md->attribute & EFI_MEMORY_RUNTIME)
		return true;

	/*
	 * 32-bit EFI doesn't suffer from the bug that requires us to
	 * reserve boot services regions, and mixed mode support
	 * doesn't exist for 32-bit kernels.
	 */
	if (IS_ENABLED(CONFIG_X86_32))
		return false;

	/*
	 * EFI specific purpose memory may be reserved by default
	 * depending on kernel config and boot options.
	 */
	if (md->type == EFI_CONVENTIONAL_MEMORY &&
	    efi_soft_reserve_enabled() &&
	    (md->attribute & EFI_MEMORY_SP))
		return false;

	/*
	 * Map all of RAM so that we can access arguments in the 1:1
	 * mapping when making EFI runtime calls.
	 */
	if (efi_is_mixed()) {
		if (md->type == EFI_CONVENTIONAL_MEMORY ||
		    md->type == EFI_LOADER_DATA ||
		    md->type == EFI_LOADER_CODE)
			return true;
	}

	/*
	 * Map boot services regions as a workaround for buggy
	 * firmware that accesses them even when they shouldn't.
	 *
	 * See efi_{reserve,free}_boot_services().
	 */
	if (md->type == EFI_BOOT_SERVICES_CODE ||
	    md->type == EFI_BOOT_SERVICES_DATA)
		return true;

	return false;
}

/*
 * Map the efi memory ranges of the runtime services and update new_mmap with
 * virtual addresses.
 */
static void * __init efi_map_regions(int *count, int *pg_shift)
{
	void *p, *new_memmap = NULL;
	unsigned long left = 0;
	unsigned long desc_size;
	efi_memory_desc_t *md;

	desc_size = efi.memmap.desc_size;

	p = NULL;
	while ((p = efi_map_next_entry(p))) {
		md = p;

		if (!should_map_region(md))
			continue;

		efi_map_region(md);
		get_systab_virt_addr(md);

		if (left < desc_size) {
			new_memmap = realloc_pages(new_memmap, *pg_shift);
			if (!new_memmap)
				return NULL;

			left += PAGE_SIZE << *pg_shift;
			(*pg_shift)++;
		}

		memcpy(new_memmap + (*count * desc_size), md, desc_size);

		left -= desc_size;
		(*count)++;
	}

	return new_memmap;
}

static void __init kexec_enter_virtual_mode(void)
{
#ifdef CONFIG_KEXEC_CORE
	efi_memory_desc_t *md;
	unsigned int num_pages;

	efi.systab = NULL;

	/*
	 * We don't do virtual mode, since we don't do runtime services, on
	 * non-native EFI. With the UV1 memmap, we don't do runtime services in
	 * kexec kernel because in the initial boot something else might
	 * have been mapped at these virtual addresses.
	 */
	if (efi_is_mixed() || efi_have_uv1_memmap()) {
		efi_memmap_unmap();
		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
		return;
	}

	if (efi_alloc_page_tables()) {
		pr_err("Failed to allocate EFI page tables\n");
		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
		return;
	}

	/*
	* Map efi regions which were passed via setup_data. The virt_addr is a
	* fixed addr which was used in first kernel of a kexec boot.
	*/
	for_each_efi_memory_desc(md) {
		efi_map_region_fixed(md); /* FIXME: add error handling */
		get_systab_virt_addr(md);
	}

	/*
	 * Unregister the early EFI memmap from efi_init() and install
	 * the new EFI memory map.
	 */
	efi_memmap_unmap();

	if (efi_memmap_init_late(efi.memmap.phys_map,
				 efi.memmap.desc_size * efi.memmap.nr_map)) {
		pr_err("Failed to remap late EFI memory map\n");
		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
		return;
	}

	BUG_ON(!efi.systab);

	num_pages = ALIGN(efi.memmap.nr_map * efi.memmap.desc_size, PAGE_SIZE);
	num_pages >>= PAGE_SHIFT;

	if (efi_setup_page_tables(efi.memmap.phys_map, num_pages)) {
		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
		return;
	}

	efi_sync_low_kernel_mappings();

	/*
	 * 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.
	 */
	efi.runtime_version = efi_systab.hdr.revision;

	efi_native_runtime_setup();
#endif
}

/*
 * This function will switch the EFI runtime services to virtual mode.
 * Essentially, we look through the EFI memmap and map every region that
 * has the runtime attribute bit set in its memory descriptor into the
 * efi_pgd page table.
 *
 * The old method which used to update that memory descriptor with the
 * virtual address obtained from ioremap() is still supported when the
 * kernel is booted on SG1 UV1 hardware. Same old method enabled the
 * runtime services to be called without having to thunk back into
 * physical mode for every invocation.
 *
 * The new method does a pagetable switch in a preemption-safe manner
 * so that we're in a different address space when calling a runtime
 * function. For function arguments passing we do copy the PUDs of the
 * kernel page table into efi_pgd prior to each call.
 *
 * Specially for kexec boot, efi runtime maps in previous kernel should
 * be passed in via setup_data. In that case runtime ranges will be mapped
 * to the same virtual addresses as the first kernel, see
 * kexec_enter_virtual_mode().
 */
static void __init __efi_enter_virtual_mode(void)
{
	int count = 0, pg_shift = 0;
	void *new_memmap = NULL;
	efi_status_t status;
	unsigned long pa;

	efi.systab = NULL;

	if (efi_alloc_page_tables()) {
		pr_err("Failed to allocate EFI page tables\n");
		goto err;
	}

	efi_merge_regions();
	new_memmap = efi_map_regions(&count, &pg_shift);
	if (!new_memmap) {
		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
		goto err;
	}

	pa = __pa(new_memmap);

	/*
	 * Unregister the early EFI memmap from efi_init() and install
	 * the new EFI memory map that we are about to pass to the
	 * firmware via SetVirtualAddressMap().
	 */
	efi_memmap_unmap();

	if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) {
		pr_err("Failed to remap late EFI memory map\n");
		goto err;
	}

	if (efi_enabled(EFI_DBG)) {
		pr_info("EFI runtime memory map:\n");
		efi_print_memmap();
	}

	if (WARN_ON(!efi.systab))
		goto err;

	if (efi_setup_page_tables(pa, 1 << pg_shift))
		goto err;

	efi_sync_low_kernel_mappings();

	status = efi_set_virtual_address_map(efi.memmap.desc_size * count,
					     efi.memmap.desc_size,
					     efi.memmap.desc_version,
					     (efi_memory_desc_t *)pa);
	if (status != EFI_SUCCESS) {
		pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n",
		       status);
		goto err;
	}

	efi_free_boot_services();

	/*
	 * 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.
	 */
	efi.runtime_version = efi_systab.hdr.revision;

	if (!efi_is_mixed())
		efi_native_runtime_setup();
	else
		efi_thunk_runtime_setup();

	/*
	 * Apply more restrictive page table mapping attributes now that
	 * SVAM() has been called and the firmware has performed all
	 * necessary relocation fixups for the new virtual addresses.
	 */
	efi_runtime_update_mappings();

	/* clean DUMMY object */
	efi_delete_dummy_variable();
	return;

err:
	clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
}

void __init efi_enter_virtual_mode(void)
{
	if (efi_enabled(EFI_PARAVIRT))
		return;

	if (efi_setup)
		kexec_enter_virtual_mode();
	else
		__efi_enter_virtual_mode();

	efi_dump_pagetable();
}

bool efi_is_table_address(unsigned long phys_addr)
{
	unsigned int i;

	if (phys_addr == EFI_INVALID_TABLE_ADDR)
		return false;

	for (i = 0; i < ARRAY_SIZE(efi_tables); i++)
		if (*(efi_tables[i]) == phys_addr)
			return true;

	return false;
}

Privacy Policy