summaryrefslogtreecommitdiffstats
path: root/arch/x86/platform/efi/efi.c
blob: 87fc96bcc13ceb1b4d90895e35528dda85641954 (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
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
/*
 * 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/bootmem.h>
#include <linux/slab.h>
#include <linux/memblock.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/time.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/rtc.h>
#include <asm/uv/uv.h>

#define EFI_DEBUG

#define EFI_MIN_RESERVE 5120

#define EFI_DUMMY_GUID \
	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)

static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };

struct efi_memory_map memmap;

static struct efi efi_phys __initdata;
static efi_system_table_t efi_systab __initdata;

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

u64 efi_setup;		/* efi setup_data physical address */

static bool disable_runtime __initdata = false;
static int __init setup_noefi(char *arg)
{
	disable_runtime = true;
	return 0;
}
early_param("noefi", setup_noefi);

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);

static bool efi_no_storage_paranoia;

static int __init setup_storage_paranoia(char *arg)
{
	efi_no_storage_paranoia = true;
	return 0;
}
early_param("efi_no_storage_paranoia", setup_storage_paranoia);

static efi_status_t virt_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);
	status = efi_call_virt(get_time, tm, tc);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
}

static efi_status_t virt_efi_set_time(efi_time_t *tm)
{
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt(set_time, tm);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
}

static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
					     efi_bool_t *pending,
					     efi_time_t *tm)
{
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
}

static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
{
	unsigned long flags;
	efi_status_t status;

	spin_lock_irqsave(&rtc_lock, flags);
	status = efi_call_virt(set_wakeup_time, enabled, tm);
	spin_unlock_irqrestore(&rtc_lock, flags);
	return status;
}

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_virt(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)
{
	return efi_call_virt(get_next_variable,
			     name_size, name, vendor);
}

static efi_status_t virt_efi_set_variable(efi_char16_t *name,
					  efi_guid_t *vendor,
					  u32 attr,
					  unsigned long data_size,
					  void *data)
{
	return efi_call_virt(set_variable,
			     name, vendor, attr,
			     data_size, data);
}

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_virt(query_variable_info, attr, storage_space,
			     remaining_space, max_variable_size);
}

static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
{
	return efi_call_virt(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_virt(reset_system, reset_type, status,
			data_size, data);
}

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_virt(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_virt(query_capsule_caps, capsules, count, max_size,
			     reset_type);
}

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_phys(efi_phys.set_virtual_address_map,
			       memory_map_size, descriptor_size,
			       descriptor_version, virtual_map);
	efi_call_phys_epilog();
	return status;
}

int efi_set_rtc_mmss(const struct timespec *now)
{
	unsigned long nowtime = now->tv_sec;
	efi_status_t	status;
	efi_time_t	eft;
	efi_time_cap_t	cap;
	struct rtc_time	tm;

	status = efi.get_time(&eft, &cap);
	if (status != EFI_SUCCESS) {
		pr_err("Oops: efitime: can't read time!\n");
		return -1;
	}

	rtc_time_to_tm(nowtime, &tm);
	if (!rtc_valid_tm(&tm)) {
		eft.year = tm.tm_year + 1900;
		eft.month = tm.tm_mon + 1;
		eft.day = tm.tm_mday;
		eft.minute = tm.tm_min;
		eft.second = tm.tm_sec;
		eft.nanosecond = 0;
	} else {
		pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
		       __func__, nowtime);
		return -1;
	}

	status = efi.set_time(&eft);
	if (status != EFI_SUCCESS) {
		pr_err("Oops: efitime: can't write time!\n");
		return -1;
	}
	return 0;
}

void efi_get_time(struct timespec *now)
{
	efi_status_t status;
	efi_time_t eft;
	efi_time_cap_t cap;

	status = efi.get_time(&eft, &cap);
	if (status != EFI_SUCCESS)
		pr_err("Oops: efitime: can't read time!\n");

	now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour,
			     eft.minute, eft.second);
	now->tv_nsec = 0;
}

/*
 * 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.
 */

static void __init do_add_efi_memmap(void)
{
	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;

		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
			 */
			e820_type = E820_RESERVED;
			break;
		}
		e820_add_region(start, size, e820_type);
	}
	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
}

int __init efi_memblock_x86_reserve_range(void)
{
	struct efi_info *e = &boot_params.efi_info;
	unsigned long pmap;

#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
	memmap.phys_map		= (void *)pmap;
	memmap.nr_map		= e->efi_memmap_size /
				  e->efi_memdesc_size;
	memmap.desc_size	= e->efi_memdesc_size;
	memmap.desc_version	= e->efi_memdesc_version;

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

	efi.memmap = &memmap;

	return 0;
}

static void __init print_efi_memmap(void)
{
#ifdef EFI_DEBUG
	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;
		pr_info("mem%02u: type=%u, attr=0x%llx, 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  */
}

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;
		u64 start = md->phys_addr;
		u64 size = md->num_pages << EFI_PAGE_SHIFT;

		if (md->type != EFI_BOOT_SERVICES_CODE &&
		    md->type != EFI_BOOT_SERVICES_DATA)
			continue;
		/* 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
		*/
		if ((start + size > __pa_symbol(_text)
				&& start <= __pa_symbol(_end)) ||
			!e820_all_mapped(start, start+size, E820_RAM) ||
			memblock_is_region_reserved(start, size)) {
			/* Could not reserve, skip it */
			md->num_pages = 0;
			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
				     start, start+size-1);
		} else
			memblock_reserve(start, size);
	}
}

void __init efi_unmap_memmap(void)
{
	clear_bit(EFI_MEMMAP, &efi.flags);
	if (memmap.map) {
		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
		memmap.map = NULL;
	}
}

void __init efi_free_boot_services(void)
{
	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;

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

		/* Could not reserve boot area */
		if (!size)
			continue;

		free_bootmem_late(start, size);
	}

	efi_unmap_memmap();
}

static int __init efi_systab_init(void *phys)
{
	if (efi_enabled(EFI_64BIT)) {
		efi_system_table_64_t *systab64;
		struct efi_setup_data *data = NULL;
		u64 tmp = 0;

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

		efi_systab.hdr = systab64->hdr;
		efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor :
					      systab64->fw_vendor;
		tmp |= data ? data->fw_vendor : 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 = data ?
				     (void *)(unsigned long)data->runtime :
				     (void *)(unsigned long)systab64->runtime;
		tmp |= data ? data->runtime : systab64->runtime;
		efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
		tmp |= systab64->boottime;
		efi_systab.nr_tables = systab64->nr_tables;
		efi_systab.tables = data ? (unsigned long)data->tables :
					   systab64->tables;
		tmp |= data ? data->tables : systab64->tables;

		early_iounmap(systab64, sizeof(*systab64));
		if (data)
			early_iounmap(data, sizeof(*data));
#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));
	}

	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);

	set_bit(EFI_SYSTEM_TABLES, &efi.flags);

	return 0;
}

static int __init efi_runtime_init32(void)
{
	efi_runtime_services_32_t *runtime;

	runtime = early_ioremap((unsigned long)efi.systab->runtime,
			sizeof(efi_runtime_services_32_t));
	if (!runtime) {
		pr_err("Could not map the runtime service table!\n");
		return -ENOMEM;
	}

	/*
	 * We will only need *early* access to the following two
	 * EFI runtime services before set_virtual_address_map
	 * is invoked.
	 */
	efi_phys.set_virtual_address_map =
			(efi_set_virtual_address_map_t *)
			(unsigned long)runtime->set_virtual_address_map;
	early_iounmap(runtime, sizeof(efi_runtime_services_32_t));

	return 0;
}

static int __init efi_runtime_init64(void)
{
	efi_runtime_services_64_t *runtime;

	runtime = early_ioremap((unsigned long)efi.systab->runtime,
			sizeof(efi_runtime_services_64_t));
	if (!runtime) {
		pr_err("Could not map the runtime service table!\n");
		return -ENOMEM;
	}

	/*
	 * We will only need *early* access to the following two
	 * EFI runtime services before set_virtual_address_map
	 * is invoked.
	 */
	efi_phys.set_virtual_address_map =
			(efi_set_virtual_address_map_t *)
			(unsigned long)runtime->set_virtual_address_map;
	early_iounmap(runtime, sizeof(efi_runtime_services_64_t));

	return 0;
}

static int __init efi_runtime_init(void)
{
	int rv;

	/*
	 * 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.
	 */
	if (efi_enabled(EFI_64BIT))
		rv = efi_runtime_init64();
	else
		rv = efi_runtime_init32();

	if (rv)
		return rv;

	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);

	return 0;
}

static int __init efi_memmap_init(void)
{
	/* Map the EFI memory map */
	memmap.map = early_ioremap((unsigned long)memmap.phys_map,
				   memmap.nr_map * memmap.desc_size);
	if (memmap.map == NULL) {
		pr_err("Could not map the memory map!\n");
		return -ENOMEM;
	}
	memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);

	if (add_efi_memmap)
		do_add_efi_memmap();

	set_bit(EFI_MEMMAP, &efi.flags);

	return 0;
}

/*
 * A number of config table entries get remapped to virtual addresses
 * after entering EFI virtual mode. However, the kexec kernel requires
 * their physical addresses therefore we pass them via setup_data and
 * correct those entries to their respective physical addresses here.
 *
 * Currently only handles smbios which is necessary for some firmware
 * implementation.
 */
static int __init efi_reuse_config(u64 tables, int nr_tables)
{
	int i, sz, ret = 0;
	void *p, *tablep;
	struct efi_setup_data *data;

	if (!efi_setup)
		return 0;

	if (!efi_enabled(EFI_64BIT))
		return 0;

	data = early_memremap(efi_setup, sizeof(*data));
	if (!data) {
		ret = -ENOMEM;
		goto out;
	}

	if (!data->smbios)
		goto out_memremap;

	sz = sizeof(efi_config_table_64_t);

	p = tablep = early_memremap(tables, nr_tables * sz);
	if (!p) {
		pr_err("Could not map Configuration table!\n");
		ret = -ENOMEM;
		goto out_memremap;
	}

	for (i = 0; i < efi.systab->nr_tables; i++) {
		efi_guid_t guid;

		guid = ((efi_config_table_64_t *)p)->guid;

		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
			((efi_config_table_64_t *)p)->table = data->smbios;
		p += sz;
	}
	early_iounmap(tablep, nr_tables * sz);

out_memremap:
	early_iounmap(data, sizeof(*data));
out:
	return ret;
}

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

#ifdef CONFIG_X86_32
	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;
	}
	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
#else
	efi_phys.systab = (efi_system_table_t *)
			  (boot_params.efi_info.efi_systab |
			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
#endif

	if (efi_systab_init(efi_phys.systab))
		return;

	set_bit(EFI_SYSTEM_TABLES, &efi.flags);

	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 = 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
		pr_err("Could not map the firmware vendor!\n");
	early_iounmap(tmp, 2);

	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");
	else {
		if (disable_runtime || efi_runtime_init())
			return;
	}
	if (efi_memmap_init())
		return;

	set_bit(EFI_MEMMAP, &efi.flags);

	print_efi_memmap();
}

void __init efi_late_init(void)
{
	efi_bgrt_init();
}

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;
	void *p;

	/* Make EFI runtime service code area executable */
	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;

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

		efi_set_executable(md, true);
	}
}

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);
}

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);
}

static void native_runtime_setup(void)
{
	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;
	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;
}

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

	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;
	}
}

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 = (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;
	}
}

static void __init save_runtime_map(void)
{
#ifdef CONFIG_KEXEC
	efi_memory_desc_t *md;
	void *tmp, *p, *q = NULL;
	int count = 0;

	if (efi_enabled(EFI_OLD_MEMMAP))
		return;

	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;

		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
		    (md->type == EFI_BOOT_SERVICES_CODE) ||
		    (md->type == EFI_BOOT_SERVICES_DATA))
			continue;
		tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL);
		if (!tmp)
			goto out;
		q = tmp;

		memcpy(q + count * memmap.desc_size, md, memmap.desc_size);
		count++;
	}

	efi_runtime_map_setup(q, count, memmap.desc_size);
	return;

out:
	kfree(q);
	pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
#endif
}

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;
}

/*
 * 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;
	efi_memory_desc_t *md;

	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;
		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
#ifdef CONFIG_X86_64
			if (md->type != EFI_BOOT_SERVICES_CODE &&
			    md->type != EFI_BOOT_SERVICES_DATA)
#endif
				continue;
		}

		efi_map_region(md);
		get_systab_virt_addr(md);

		if (left < memmap.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 * memmap.desc_size), md,
		       memmap.desc_size);

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

	return new_memmap;
}

static void __init kexec_enter_virtual_mode(void)
{
#ifdef CONFIG_KEXEC
	efi_memory_desc_t *md;
	void *p;

	efi.systab = NULL;

	/*
	 * We don't do virtual mode, since we don't do runtime services, on
	 * non-native EFI
	 */
	if (!efi_is_native()) {
		efi_unmap_memmap();
		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 (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
		md = p;
		efi_map_region_fixed(md); /* FIXME: add error handling */
		get_systab_virt_addr(md);
	}

	save_runtime_map();

	BUG_ON(!efi.systab);

	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;

	native_runtime_setup();

	efi.set_virtual_address_map = NULL;

	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
		runtime_code_page_mkexec();

	/* clean DUMMY object */
	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
			 EFI_VARIABLE_NON_VOLATILE |
			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
			 EFI_VARIABLE_RUNTIME_ACCESS,
			 0, NULL);
#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
 * ->trampoline_pgd page table using a top-down VA allocation scheme.
 *
 * 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 with efi=old_map on its command line. 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 PGDs of the
 * kernel page table into ->trampoline_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;

	efi.systab = NULL;

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

	save_runtime_map();

	BUG_ON(!efi.systab);

	if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
		return;

	efi_sync_low_kernel_mappings();
	efi_dump_pagetable();

	if (efi_is_native()) {
		status = phys_efi_set_virtual_address_map(
				memmap.desc_size * count,
				memmap.desc_size,
				memmap.desc_version,
				(efi_memory_desc_t *)__pa(new_memmap));
	} else {
		status = efi_thunk_set_virtual_address_map(
				efi_phys.set_virtual_address_map,
				memmap.desc_size * count,
				memmap.desc_size,
				memmap.desc_version,
				(efi_memory_desc_t *)__pa(new_memmap));
	}

	if (status != EFI_SUCCESS) {
		pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
			 status);
		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.
	 */
	efi.runtime_version = efi_systab.hdr.revision;

	if (efi_is_native())
		native_runtime_setup();
	else
		efi_thunk_runtime_setup();

	efi.set_virtual_address_map = NULL;

	efi_runtime_mkexec();

	/*
	 * We mapped the descriptor array into the EFI pagetable above but we're
	 * not unmapping it here. Here's why:
	 *
	 * We're copying select PGDs from the kernel page table to the EFI page
	 * table and when we do so and make changes to those PGDs like unmapping
	 * stuff from them, those changes appear in the kernel page table and we
	 * go boom.
	 *
	 * From setup_real_mode():
	 *
	 * ...
	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
	 *
	 * In this particular case, our allocation is in PGD 0 of the EFI page
	 * table but we've copied that PGD from PGD[272] of the EFI page table:
	 *
	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
	 *
	 * where the direct memory mapping in kernel space is.
	 *
	 * new_memmap's VA comes from that direct mapping and thus clearing it,
	 * it would get cleared in the kernel page table too.
	 *
	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
	 */
	free_pages((unsigned long)new_memmap, pg_shift);

	/* clean DUMMY object */
	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
			 EFI_VARIABLE_NON_VOLATILE |
			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
			 EFI_VARIABLE_RUNTIME_ACCESS,
			 0, NULL);
}

void __init efi_enter_virtual_mode(void)
{
	if (efi_setup)
		kexec_enter_virtual_mode();
	else
		__efi_enter_virtual_mode();
}

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

	if (!efi_enabled(EFI_MEMMAP))
		return 0;

	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;
}

/*
 * Some firmware implementations refuse to boot if there's insufficient space
 * in the variable store. Ensure that we never use more than a 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;

	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
		return 0;

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

	/*
	 * We account for that by refusing the write if permitting it would
	 * reduce the available space to under 5KB. This figure was provided by
	 * Samsung, so should be safe.
	 */
	if ((remaining_size - size < EFI_MIN_RESERVE) &&
		!efi_no_storage_paranoia) {

		/*
		 * Triggering garbage collection may require that the firmware
		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
		 * that by attempting to use more space than is available.
		 */
		unsigned long dummy_size = remaining_size + 1024;
		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);

		if (!dummy)
			return EFI_OUT_OF_RESOURCES;

		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
					  EFI_VARIABLE_NON_VOLATILE |
					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
					  EFI_VARIABLE_RUNTIME_ACCESS,
					  dummy_size, dummy);

		if (status == EFI_SUCCESS) {
			/*
			 * This should have failed, so if it didn't make sure
			 * that we delete it...
			 */
			efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
					 EFI_VARIABLE_NON_VOLATILE |
					 EFI_VARIABLE_BOOTSERVICE_ACCESS |
					 EFI_VARIABLE_RUNTIME_ACCESS,
					 0, dummy);
		}

		kfree(dummy);

		/*
		 * The runtime code may now have triggered a garbage collection
		 * run, so check the variable info again
		 */
		status = efi.query_variable_info(attributes, &storage_size,
						 &remaining_size, &max_size);

		if (status != EFI_SUCCESS)
			return status;

		/*
		 * There still isn't enough room, so return an error
		 */
		if (remaining_size - size < EFI_MIN_RESERVE)
			return EFI_OUT_OF_RESOURCES;
	}

	return EFI_SUCCESS;
}
EXPORT_SYMBOL_GPL(efi_query_variable_store);

static int __init parse_efi_cmdline(char *str)
{
	if (*str == '=')
		str++;

	if (!strncmp(str, "old_map", 7))
		set_bit(EFI_OLD_MEMMAP, &efi.flags);

	return 0;
}
early_param("efi", parse_efi_cmdline);

void __init efi_apply_memmap_quirks(void)
{
	/*
	 * Once setup is done earlier, unmap the EFI memory map on mismatched
	 * firmware/kernel architectures since there is no support for runtime
	 * services.
	 */
	if (!efi_runtime_supported()) {
		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
		efi_unmap_memmap();
	}

	/*
	 * UV doesn't support the new EFI pagetable mapping yet.
	 */
	if (is_uv_system())
		set_bit(EFI_OLD_MEMMAP, &efi.flags);
}