summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/setup.c
blob: 145810b0edf6738b57a0e6560c53392ae54a82e7 (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
/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *
 *  Memory region support
 *	David Parsons <orc@pell.chi.il.us>, July-August 1999
 *
 *  Added E820 sanitization routine (removes overlapping memory regions);
 *  Brian Moyle <bmoyle@mvista.com>, February 2001
 *
 * Moved CPU detection code to cpu/${cpu}.c
 *    Patrick Mochel <mochel@osdl.org>, March 2002
 *
 *  Provisions for empty E820 memory regions (reported by certain BIOSes).
 *  Alex Achenbach <xela@slit.de>, December 2002.
 *
 */

/*
 * This file handles the architecture-dependent parts of initialization
 */

#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/acpi.h>
#include <linux/sfi.h>
#include <linux/apm_bios.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/seq_file.h>
#include <linux/console.h>
#include <linux/root_dev.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/edd.h>
#include <linux/iscsi_ibft.h>
#include <linux/nodemask.h>
#include <linux/kexec.h>
#include <linux/dmi.h>
#include <linux/pfn.h>
#include <linux/pci.h>
#include <asm/pci-direct.h>
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>
#include <linux/dma-contiguous.h>

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/delay.h>

#include <linux/kallsyms.h>
#include <linux/cpufreq.h>
#include <linux/dma-mapping.h>
#include <linux/ctype.h>
#include <linux/uaccess.h>

#include <linux/percpu.h>
#include <linux/crash_dump.h>
#include <linux/tboot.h>
#include <linux/jiffies.h>
#include <linux/mem_encrypt.h>

#include <linux/usb/xhci-dbgp.h>
#include <video/edid.h>

#include <asm/mtrr.h>
#include <asm/apic.h>
#include <asm/realmode.h>
#include <asm/e820/api.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/efi.h>
#include <asm/timer.h>
#include <asm/i8259.h>
#include <asm/sections.h>
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/setup_arch.h>
#include <asm/bios_ebda.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/bugs.h>
#include <asm/kasan.h>

#include <asm/vsyscall.h>
#include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/dma.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>

#include <asm/paravirt.h>
#include <asm/hypervisor.h>
#include <asm/olpc_ofw.h>

#include <asm/percpu.h>
#include <asm/topology.h>
#include <asm/apicdef.h>
#include <asm/amd_nb.h>
#include <asm/mce.h>
#include <asm/alternative.h>
#include <asm/prom.h>
#include <asm/microcode.h>
#include <asm/mmu_context.h>
#include <asm/kaslr.h>
#include <asm/unwind.h>

/*
 * max_low_pfn_mapped: highest direct mapped pfn under 4GB
 * max_pfn_mapped:     highest direct mapped pfn over 4GB
 *
 * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are
 * represented by pfn_mapped
 */
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;

#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
#endif


static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
unsigned long _brk_end = (unsigned long)__brk_base;

struct boot_params boot_params;

/*
 * Machine setup..
 */
static struct resource data_resource = {
	.name	= "Kernel data",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
};

static struct resource code_resource = {
	.name	= "Kernel code",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
};

static struct resource bss_resource = {
	.name	= "Kernel bss",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
};


#ifdef CONFIG_X86_32
/* cpu data as detected by the assembly code in head_32.S */
struct cpuinfo_x86 new_cpu_data;

/* common cpu data for all cpus */
struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);

unsigned int def_to_bigsmp;

/* for MCA, but anyone else can use it if they want */
unsigned int machine_id;
unsigned int machine_submodel_id;
unsigned int BIOS_revision;

struct apm_info apm_info;
EXPORT_SYMBOL(apm_info);

#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
	defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
struct ist_info ist_info;
EXPORT_SYMBOL(ist_info);
#else
struct ist_info ist_info;
#endif

#else
struct cpuinfo_x86 boot_cpu_data __read_mostly = {
	.x86_phys_bits = MAX_PHYSMEM_BITS,
};
EXPORT_SYMBOL(boot_cpu_data);
#endif


#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
__visible unsigned long mmu_cr4_features __ro_after_init;
#else
__visible unsigned long mmu_cr4_features __ro_after_init = X86_CR4_PAE;
#endif

/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
int bootloader_type, bootloader_version;

/*
 * Setup options
 */
struct screen_info screen_info;
EXPORT_SYMBOL(screen_info);
struct edid_info edid_info;
EXPORT_SYMBOL_GPL(edid_info);

extern int root_mountflags;

unsigned long saved_video_mode;

#define RAMDISK_IMAGE_START_MASK	0x07FF
#define RAMDISK_PROMPT_FLAG		0x8000
#define RAMDISK_LOAD_FLAG		0x4000

static char __initdata command_line[COMMAND_LINE_SIZE];
#ifdef CONFIG_CMDLINE_BOOL
static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
#endif

#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
struct edd edd;
#ifdef CONFIG_EDD_MODULE
EXPORT_SYMBOL(edd);
#endif
/**
 * copy_edd() - Copy the BIOS EDD information
 *              from boot_params into a safe place.
 *
 */
static inline void __init copy_edd(void)
{
     memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer,
	    sizeof(edd.mbr_signature));
     memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info));
     edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries;
     edd.edd_info_nr = boot_params.eddbuf_entries;
}
#else
static inline void __init copy_edd(void)
{
}
#endif

void * __init extend_brk(size_t size, size_t align)
{
	size_t mask = align - 1;
	void *ret;

	BUG_ON(_brk_start == 0);
	BUG_ON(align & mask);

	_brk_end = (_brk_end + mask) & ~mask;
	BUG_ON((char *)(_brk_end + size) > __brk_limit);

	ret = (void *)_brk_end;
	_brk_end += size;

	memset(ret, 0, size);

	return ret;
}

#ifdef CONFIG_X86_32
static void __init cleanup_highmap(void)
{
}
#endif

static void __init reserve_brk(void)
{
	if (_brk_end > _brk_start)
		memblock_reserve(__pa_symbol(_brk_start),
				 _brk_end - _brk_start);

	/* Mark brk area as locked down and no longer taking any
	   new allocations */
	_brk_start = 0;
}

u64 relocated_ramdisk;

#ifdef CONFIG_BLK_DEV_INITRD

static u64 __init get_ramdisk_image(void)
{
	u64 ramdisk_image = boot_params.hdr.ramdisk_image;

	ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;

	return ramdisk_image;
}
static u64 __init get_ramdisk_size(void)
{
	u64 ramdisk_size = boot_params.hdr.ramdisk_size;

	ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;

	return ramdisk_size;
}

static void __init relocate_initrd(void)
{
	/* Assume only end is not page aligned */
	u64 ramdisk_image = get_ramdisk_image();
	u64 ramdisk_size  = get_ramdisk_size();
	u64 area_size     = PAGE_ALIGN(ramdisk_size);

	/* We need to move the initrd down into directly mapped mem */
	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
						   area_size, PAGE_SIZE);

	if (!relocated_ramdisk)
		panic("Cannot find place for new RAMDISK of size %lld\n",
		      ramdisk_size);

	/* Note: this includes all the mem currently occupied by
	   the initrd, we rely on that fact to keep the data intact. */
	memblock_reserve(relocated_ramdisk, area_size);
	initrd_start = relocated_ramdisk + PAGE_OFFSET;
	initrd_end   = initrd_start + ramdisk_size;
	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);

	copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);

	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
		" [mem %#010llx-%#010llx]\n",
		ramdisk_image, ramdisk_image + ramdisk_size - 1,
		relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
}

static void __init early_reserve_initrd(void)
{
	/* Assume only end is not page aligned */
	u64 ramdisk_image = get_ramdisk_image();
	u64 ramdisk_size  = get_ramdisk_size();
	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);

	if (!boot_params.hdr.type_of_loader ||
	    !ramdisk_image || !ramdisk_size)
		return;		/* No initrd provided by bootloader */

	memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
}
static void __init reserve_initrd(void)
{
	/* Assume only end is not page aligned */
	u64 ramdisk_image = get_ramdisk_image();
	u64 ramdisk_size  = get_ramdisk_size();
	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
	u64 mapped_size;

	if (!boot_params.hdr.type_of_loader ||
	    !ramdisk_image || !ramdisk_size)
		return;		/* No initrd provided by bootloader */

	/*
	 * If SME is active, this memory will be marked encrypted by the
	 * kernel when it is accessed (including relocation). However, the
	 * ramdisk image was loaded decrypted by the bootloader, so make
	 * sure that it is encrypted before accessing it. For SEV the
	 * ramdisk will already be encrypted, so only do this for SME.
	 */
	if (sme_active())
		sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);

	initrd_start = 0;

	mapped_size = memblock_mem_size(max_pfn_mapped);
	if (ramdisk_size >= (mapped_size>>1))
		panic("initrd too large to handle, "
		       "disabling initrd (%lld needed, %lld available)\n",
		       ramdisk_size, mapped_size>>1);

	printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
			ramdisk_end - 1);

	if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image),
				PFN_DOWN(ramdisk_end))) {
		/* All are mapped, easy case */
		initrd_start = ramdisk_image + PAGE_OFFSET;
		initrd_end = initrd_start + ramdisk_size;
		return;
	}

	relocate_initrd();

	memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
}

#else
static void __init early_reserve_initrd(void)
{
}
static void __init reserve_initrd(void)
{
}
#endif /* CONFIG_BLK_DEV_INITRD */

static void __init parse_setup_data(void)
{
	struct setup_data *data;
	u64 pa_data, pa_next;

	pa_data = boot_params.hdr.setup_data;
	while (pa_data) {
		u32 data_len, data_type;

		data = early_memremap(pa_data, sizeof(*data));
		data_len = data->len + sizeof(struct setup_data);
		data_type = data->type;
		pa_next = data->next;
		early_memunmap(data, sizeof(*data));

		switch (data_type) {
		case SETUP_E820_EXT:
			e820__memory_setup_extended(pa_data, data_len);
			break;
		case SETUP_DTB:
			add_dtb(pa_data);
			break;
		case SETUP_EFI:
			parse_efi_setup(pa_data, data_len);
			break;
		default:
			break;
		}
		pa_data = pa_next;
	}
}

static void __init memblock_x86_reserve_range_setup_data(void)
{
	struct setup_data *data;
	u64 pa_data;

	pa_data = boot_params.hdr.setup_data;
	while (pa_data) {
		data = early_memremap(pa_data, sizeof(*data));
		memblock_reserve(pa_data, sizeof(*data) + data->len);
		pa_data = data->next;
		early_memunmap(data, sizeof(*data));
	}
}

/*
 * --------- Crashkernel reservation ------------------------------
 */

#ifdef CONFIG_KEXEC_CORE

/* 16M alignment for crash kernel regions */
#define CRASH_ALIGN		(16 << 20)

/*
 * Keep the crash kernel below this limit.  On 32 bits earlier kernels
 * would limit the kernel to the low 512 MiB due to mapping restrictions.
 * On 64bit, old kexec-tools need to under 896MiB.
 */
#ifdef CONFIG_X86_32
# define CRASH_ADDR_LOW_MAX	(512 << 20)
# define CRASH_ADDR_HIGH_MAX	(512 << 20)
#else
# define CRASH_ADDR_LOW_MAX	(896UL << 20)
# define CRASH_ADDR_HIGH_MAX	MAXMEM
#endif

static int __init reserve_crashkernel_low(void)
{
#ifdef CONFIG_X86_64
	unsigned long long base, low_base = 0, low_size = 0;
	unsigned long total_low_mem;
	int ret;

	total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT));

	/* crashkernel=Y,low */
	ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base);
	if (ret) {
		/*
		 * two parts from lib/swiotlb.c:
		 * -swiotlb size: user-specified with swiotlb= or default.
		 *
		 * -swiotlb overflow buffer: now hardcoded to 32k. We round it
		 * to 8M for other buffers that may need to stay low too. Also
		 * make sure we allocate enough extra low memory so that we
		 * don't run out of DMA buffers for 32-bit devices.
		 */
		low_size = max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20);
	} else {
		/* passed with crashkernel=0,low ? */
		if (!low_size)
			return 0;
	}

	low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN);
	if (!low_base) {
		pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n",
		       (unsigned long)(low_size >> 20));
		return -ENOMEM;
	}

	ret = memblock_reserve(low_base, low_size);
	if (ret) {
		pr_err("%s: Error reserving crashkernel low memblock.\n", __func__);
		return ret;
	}

	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
		(unsigned long)(low_size >> 20),
		(unsigned long)(low_base >> 20),
		(unsigned long)(total_low_mem >> 20));

	crashk_low_res.start = low_base;
	crashk_low_res.end   = low_base + low_size - 1;
	insert_resource(&iomem_resource, &crashk_low_res);
#endif
	return 0;
}

static void __init reserve_crashkernel(void)
{
	unsigned long long crash_size, crash_base, total_mem;
	bool high = false;
	int ret;

	total_mem = memblock_phys_mem_size();

	/* crashkernel=XM */
	ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base);
	if (ret != 0 || crash_size <= 0) {
		/* crashkernel=X,high */
		ret = parse_crashkernel_high(boot_command_line, total_mem,
					     &crash_size, &crash_base);
		if (ret != 0 || crash_size <= 0)
			return;
		high = true;
	}

	/* 0 means: find the address automatically */
	if (crash_base <= 0) {
		/*
		 * Set CRASH_ADDR_LOW_MAX upper bound for crash memory,
		 * as old kexec-tools loads bzImage below that, unless
		 * "crashkernel=size[KMG],high" is specified.
		 */
		crash_base = memblock_find_in_range(CRASH_ALIGN,
						    high ? CRASH_ADDR_HIGH_MAX
							 : CRASH_ADDR_LOW_MAX,
						    crash_size, CRASH_ALIGN);
		if (!crash_base) {
			pr_info("crashkernel reservation failed - No suitable area found.\n");
			return;
		}

	} else {
		unsigned long long start;

		start = memblock_find_in_range(crash_base,
					       crash_base + crash_size,
					       crash_size, 1 << 20);
		if (start != crash_base) {
			pr_info("crashkernel reservation failed - memory is in use.\n");
			return;
		}
	}
	ret = memblock_reserve(crash_base, crash_size);
	if (ret) {
		pr_err("%s: Error reserving crashkernel memblock.\n", __func__);
		return;
	}

	if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) {
		memblock_free(crash_base, crash_size);
		return;
	}

	pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n",
		(unsigned long)(crash_size >> 20),
		(unsigned long)(crash_base >> 20),
		(unsigned long)(total_mem >> 20));

	crashk_res.start = crash_base;
	crashk_res.end   = crash_base + crash_size - 1;
	insert_resource(&iomem_resource, &crashk_res);
}
#else
static void __init reserve_crashkernel(void)
{
}
#endif

static struct resource standard_io_resources[] = {
	{ .name = "dma1", .start = 0x00, .end = 0x1f,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "pic1", .start = 0x20, .end = 0x21,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "timer0", .start = 0x40, .end = 0x43,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "timer1", .start = 0x50, .end = 0x53,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "keyboard", .start = 0x60, .end = 0x60,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "keyboard", .start = 0x64, .end = 0x64,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "dma page reg", .start = 0x80, .end = 0x8f,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "pic2", .start = 0xa0, .end = 0xa1,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "dma2", .start = 0xc0, .end = 0xdf,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
	{ .name = "fpu", .start = 0xf0, .end = 0xff,
		.flags = IORESOURCE_BUSY | IORESOURCE_IO }
};

void __init reserve_standard_io_resources(void)
{
	int i;

	/* request I/O space for devices used on all i[345]86 PCs */
	for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++)
		request_resource(&ioport_resource, &standard_io_resources[i]);

}

static __init void reserve_ibft_region(void)
{
	unsigned long addr, size = 0;

	addr = find_ibft_region(&size);

	if (size)
		memblock_reserve(addr, size);
}

static bool __init snb_gfx_workaround_needed(void)
{
#ifdef CONFIG_PCI
	int i;
	u16 vendor, devid;
	static const __initconst u16 snb_ids[] = {
		0x0102,
		0x0112,
		0x0122,
		0x0106,
		0x0116,
		0x0126,
		0x010a,
	};

	/* Assume no if something weird is going on with PCI */
	if (!early_pci_allowed())
		return false;

	vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
	if (vendor != 0x8086)
		return false;

	devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
	for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
		if (devid == snb_ids[i])
			return true;
#endif

	return false;
}

/*
 * Sandy Bridge graphics has trouble with certain ranges, exclude
 * them from allocation.
 */
static void __init trim_snb_memory(void)
{
	static const __initconst unsigned long bad_pages[] = {
		0x20050000,
		0x20110000,
		0x20130000,
		0x20138000,
		0x40004000,
	};
	int i;

	if (!snb_gfx_workaround_needed())
		return;

	printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");

	/*
	 * Reserve all memory below the 1 MB mark that has not
	 * already been reserved.
	 */
	memblock_reserve(0, 1<<20);
	
	for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
		if (memblock_reserve(bad_pages[i], PAGE_SIZE))
			printk(KERN_WARNING "failed to reserve 0x%08lx\n",
			       bad_pages[i]);
	}
}

/*
 * Here we put platform-specific memory range workarounds, i.e.
 * memory known to be corrupt or otherwise in need to be reserved on
 * specific platforms.
 *
 * If this gets used more widely it could use a real dispatch mechanism.
 */
static void __init trim_platform_memory_ranges(void)
{
	trim_snb_memory();
}

static void __init trim_bios_range(void)
{
	/*
	 * A special case is the first 4Kb of memory;
	 * This is a BIOS owned area, not kernel ram, but generally
	 * not listed as such in the E820 table.
	 *
	 * This typically reserves additional memory (64KiB by default)
	 * since some BIOSes are known to corrupt low memory.  See the
	 * Kconfig help text for X86_RESERVE_LOW.
	 */
	e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);

	/*
	 * special case: Some BIOSen report the PC BIOS
	 * area (640->1Mb) as ram even though it is not.
	 * take them out.
	 */
	e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1);

	e820__update_table(e820_table);
}

/* called before trim_bios_range() to spare extra sanitize */
static void __init e820_add_kernel_range(void)
{
	u64 start = __pa_symbol(_text);
	u64 size = __pa_symbol(_end) - start;

	/*
	 * Complain if .text .data and .bss are not marked as E820_TYPE_RAM and
	 * attempt to fix it by adding the range. We may have a confused BIOS,
	 * or the user may have used memmap=exactmap or memmap=xxM$yyM to
	 * exclude kernel range. If we really are running on top non-RAM,
	 * we will crash later anyways.
	 */
	if (e820__mapped_all(start, start + size, E820_TYPE_RAM))
		return;

	pr_warn(".text .data .bss are not marked as E820_TYPE_RAM!\n");
	e820__range_remove(start, size, E820_TYPE_RAM, 0);
	e820__range_add(start, size, E820_TYPE_RAM);
}

static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;

static int __init parse_reservelow(char *p)
{
	unsigned long long size;

	if (!p)
		return -EINVAL;

	size = memparse(p, &p);

	if (size < 4096)
		size = 4096;

	if (size > 640*1024)
		size = 640*1024;

	reserve_low = size;

	return 0;
}

early_param("reservelow", parse_reservelow);

static void __init trim_low_memory_range(void)
{
	memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
}
	
/*
 * Dump out kernel offset information on panic.
 */
static int
dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
{
	if (kaslr_enabled()) {
		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
			 kaslr_offset(),
			 __START_KERNEL,
			 __START_KERNEL_map,
			 MODULES_VADDR-1);
	} else {
		pr_emerg("Kernel Offset: disabled\n");
	}

	return 0;
}

/*
 * Determine if we were loaded by an EFI loader.  If so, then we have also been
 * passed the efi memmap, systab, etc., so we should use these data structures
 * for initialization.  Note, the efi init code path is determined by the
 * global efi_enabled. This allows the same kernel image to be used on existing
 * systems (with a traditional BIOS) as well as on EFI systems.
 */
/*
 * setup_arch - architecture-specific boot-time initializations
 *
 * Note: On x86_64, fixmaps are ready for use even before this is called.
 */

void __init setup_arch(char **cmdline_p)
{
	memblock_reserve(__pa_symbol(_text),
			 (unsigned long)__bss_stop - (unsigned long)_text);

	early_reserve_initrd();

	/*
	 * At this point everything still needed from the boot loader
	 * or BIOS or kernel text should be early reserved or marked not
	 * RAM in e820. All other memory is free game.
	 */

#ifdef CONFIG_X86_32
	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));

	/*
	 * copy kernel address range established so far and switch
	 * to the proper swapper page table
	 */
	clone_pgd_range(swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
			initial_page_table + KERNEL_PGD_BOUNDARY,
			KERNEL_PGD_PTRS);

	load_cr3(swapper_pg_dir);
	/*
	 * Note: Quark X1000 CPUs advertise PGE incorrectly and require
	 * a cr3 based tlb flush, so the following __flush_tlb_all()
	 * will not flush anything because the cpu quirk which clears
	 * X86_FEATURE_PGE has not been invoked yet. Though due to the
	 * load_cr3() above the TLB has been flushed already. The
	 * quirk is invoked before subsequent calls to __flush_tlb_all()
	 * so proper operation is guaranteed.
	 */
	__flush_tlb_all();
#else
	printk(KERN_INFO "Command line: %s\n", boot_command_line);
#endif

	/*
	 * If we have OLPC OFW, we might end up relocating the fixmap due to
	 * reserve_top(), so do this before touching the ioremap area.
	 */
	olpc_ofw_detect();

	idt_setup_early_traps();
	early_cpu_init();
	early_ioremap_init();

	setup_olpc_ofw_pgd();

	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
	screen_info = boot_params.screen_info;
	edid_info = boot_params.edid_info;
#ifdef CONFIG_X86_32
	apm_info.bios = boot_params.apm_bios_info;
	ist_info = boot_params.ist_info;
#endif
	saved_video_mode = boot_params.hdr.vid_mode;
	bootloader_type = boot_params.hdr.type_of_loader;
	if ((bootloader_type >> 4) == 0xe) {
		bootloader_type &= 0xf;
		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
	}
	bootloader_version  = bootloader_type & 0xf;
	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;

#ifdef CONFIG_BLK_DEV_RAM
	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
#endif
#ifdef CONFIG_EFI
	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
		     EFI32_LOADER_SIGNATURE, 4)) {
		set_bit(EFI_BOOT, &efi.flags);
	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
		     EFI64_LOADER_SIGNATURE, 4)) {
		set_bit(EFI_BOOT, &efi.flags);
		set_bit(EFI_64BIT, &efi.flags);
	}
#endif

	x86_init.oem.arch_setup();

	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
	e820__memory_setup();
	parse_setup_data();

	copy_edd();

	if (!boot_params.hdr.root_flags)
		root_mountflags &= ~MS_RDONLY;
	init_mm.start_code = (unsigned long) _text;
	init_mm.end_code = (unsigned long) _etext;
	init_mm.end_data = (unsigned long) _edata;
	init_mm.brk = _brk_end;

	mpx_mm_init(&init_mm);

	code_resource.start = __pa_symbol(_text);
	code_resource.end = __pa_symbol(_etext)-1;
	data_resource.start = __pa_symbol(_etext);
	data_resource.end = __pa_symbol(_edata)-1;
	bss_resource.start = __pa_symbol(__bss_start);
	bss_resource.end = __pa_symbol(__bss_stop)-1;

#ifdef CONFIG_CMDLINE_BOOL
#ifdef CONFIG_CMDLINE_OVERRIDE
	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
#else
	if (builtin_cmdline[0]) {
		/* append boot loader cmdline to builtin */
		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
	}
#endif
#endif

	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
	*cmdline_p = command_line;

	/*
	 * x86_configure_nx() is called before parse_early_param() to detect
	 * whether hardware doesn't support NX (so that the early EHCI debug
	 * console setup can safely call set_fixmap()). It may then be called
	 * again from within noexec_setup() during parsing early parameters
	 * to honor the respective command line option.
	 */
	x86_configure_nx();

	parse_early_param();

	if (efi_enabled(EFI_BOOT))
		efi_memblock_x86_reserve_range();
#ifdef CONFIG_MEMORY_HOTPLUG
	/*
	 * Memory used by the kernel cannot be hot-removed because Linux
	 * cannot migrate the kernel pages. When memory hotplug is
	 * enabled, we should prevent memblock from allocating memory
	 * for the kernel.
	 *
	 * ACPI SRAT records all hotpluggable memory ranges. But before
	 * SRAT is parsed, we don't know about it.
	 *
	 * The kernel image is loaded into memory at very early time. We
	 * cannot prevent this anyway. So on NUMA system, we set any
	 * node the kernel resides in as un-hotpluggable.
	 *
	 * Since on modern servers, one node could have double-digit
	 * gigabytes memory, we can assume the memory around the kernel
	 * image is also un-hotpluggable. So before SRAT is parsed, just
	 * allocate memory near the kernel image to try the best to keep
	 * the kernel away from hotpluggable memory.
	 */
	if (movable_node_is_enabled())
		memblock_set_bottom_up(true);
#endif

	x86_report_nx();

	/* after early param, so could get panic from serial */
	memblock_x86_reserve_range_setup_data();

	if (acpi_mps_check()) {
#ifdef CONFIG_X86_LOCAL_APIC
		disable_apic = 1;
#endif
		setup_clear_cpu_cap(X86_FEATURE_APIC);
	}

#ifdef CONFIG_PCI
	if (pci_early_dump_regs)
		early_dump_pci_devices();
#endif

	e820__reserve_setup_data();
	e820__finish_early_params();

	if (efi_enabled(EFI_BOOT))
		efi_init();

	dmi_scan_machine();
	dmi_memdev_walk();
	dmi_set_dump_stack_arch_desc();

	/*
	 * VMware detection requires dmi to be available, so this
	 * needs to be done after dmi_scan_machine(), for the boot CPU.
	 */
	init_hypervisor_platform();

	x86_init.resources.probe_roms();

	/* after parse_early_param, so could debug it */
	insert_resource(&iomem_resource, &code_resource);
	insert_resource(&iomem_resource, &data_resource);
	insert_resource(&iomem_resource, &bss_resource);

	e820_add_kernel_range();
	trim_bios_range();
#ifdef CONFIG_X86_32
	if (ppro_with_ram_bug()) {
		e820__range_update(0x70000000ULL, 0x40000ULL, E820_TYPE_RAM,
				  E820_TYPE_RESERVED);
		e820__update_table(e820_table);
		printk(KERN_INFO "fixed physical RAM map:\n");
		e820__print_table("bad_ppro");
	}
#else
	early_gart_iommu_check();
#endif

	/*
	 * partially used pages are not usable - thus
	 * we are rounding upwards:
	 */
	max_pfn = e820__end_of_ram_pfn();

	/* update e820 for memory not covered by WB MTRRs */
	mtrr_bp_init();
	if (mtrr_trim_uncached_memory(max_pfn))
		max_pfn = e820__end_of_ram_pfn();

	max_possible_pfn = max_pfn;

	/*
	 * This call is required when the CPU does not support PAT. If
	 * mtrr_bp_init() invoked it already via pat_init() the call has no
	 * effect.
	 */
	init_cache_modes();

	/*
	 * Define random base addresses for memory sections after max_pfn is
	 * defined and before each memory section base is used.
	 */
	kernel_randomize_memory();

#ifdef CONFIG_X86_32
	/* max_low_pfn get updated here */
	find_low_pfn_range();
#else
	check_x2apic();

	/* How many end-of-memory variables you have, grandma! */
	/* need this before calling reserve_initrd */
	if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
		max_low_pfn = e820__end_of_low_ram_pfn();
	else
		max_low_pfn = max_pfn;

	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
#endif

	/*
	 * Find and reserve possible boot-time SMP configuration:
	 */
	find_smp_config();

	reserve_ibft_region();

	early_alloc_pgt_buf();

	/*
	 * Need to conclude brk, before e820__memblock_setup()
	 *  it could use memblock_find_in_range, could overlap with
	 *  brk area.
	 */
	reserve_brk();

	cleanup_highmap();

	memblock_set_current_limit(ISA_END_ADDRESS);
	e820__memblock_setup();

	reserve_bios_regions();

	if (efi_enabled(EFI_MEMMAP)) {
		efi_fake_memmap();
		efi_find_mirror();
		efi_esrt_init();

		/*
		 * The EFI specification says that boot service code won't be
		 * called after ExitBootServices(). This is, in fact, a lie.
		 */
		efi_reserve_boot_services();
	}

	/* preallocate 4k for mptable mpc */
	e820__memblock_alloc_reserved_mpc_new();

#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
	setup_bios_corruption_check();
#endif

#ifdef CONFIG_X86_32
	printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
			(max_pfn_mapped<<PAGE_SHIFT) - 1);
#endif

	reserve_real_mode();

	trim_platform_memory_ranges();
	trim_low_memory_range();

	init_mem_mapping();

	idt_setup_early_pf();

	/*
	 * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
	 * with the current CR4 value.  This may not be necessary, but
	 * auditing all the early-boot CR4 manipulation would be needed to
	 * rule it out.
	 *
	 * Mask off features that don't work outside long mode (just
	 * PCIDE for now).
	 */
	mmu_cr4_features = __read_cr4() & ~X86_CR4_PCIDE;

	memblock_set_current_limit(get_max_mapped());

	/*
	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
	 */

#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
	if (init_ohci1394_dma_early)
		init_ohci1394_dma_on_all_controllers();
#endif
	/* Allocate bigger log buffer */
	setup_log_buf(1);

	if (efi_enabled(EFI_BOOT)) {
		switch (boot_params.secure_boot) {
		case efi_secureboot_mode_disabled:
			pr_info("Secure boot disabled\n");
			break;
		case efi_secureboot_mode_enabled:
			pr_info("Secure boot enabled\n");
			break;
		default:
			pr_info("Secure boot could not be determined\n");
			break;
		}
	}

	reserve_initrd();

	acpi_table_upgrade();

	vsmp_init();

	io_delay_init();

	early_platform_quirks();

	/*
	 * Parse the ACPI tables for possible boot-time SMP configuration.
	 */
	acpi_boot_table_init();

	early_acpi_boot_init();

	initmem_init();
	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);

	/*
	 * Reserve memory for crash kernel after SRAT is parsed so that it
	 * won't consume hotpluggable memory.
	 */
	reserve_crashkernel();

	memblock_find_dma_reserve();

#ifdef CONFIG_KVM_GUEST
	kvmclock_init();
#endif

	tsc_early_delay_calibrate();
	if (!early_xdbc_setup_hardware())
		early_xdbc_register_console();

	x86_init.paging.pagetable_init();

	kasan_init();

#ifdef CONFIG_X86_32
	/* sync back kernel address range */
	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
			KERNEL_PGD_PTRS);

	/*
	 * sync back low identity map too.  It is used for example
	 * in the 32-bit EFI stub.
	 */
	clone_pgd_range(initial_page_table,
			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
#endif

	tboot_probe();

	map_vsyscall();

	generic_apic_probe();

	early_quirks();

	/*
	 * Read APIC and some other early information from ACPI tables.
	 */
	acpi_boot_init();
	sfi_init();
	x86_dtb_init();

	/*
	 * get boot-time SMP configuration:
	 */
	get_smp_config();

	/*
	 * Systems w/o ACPI and mptables might not have it mapped the local
	 * APIC yet, but prefill_possible_map() might need to access it.
	 */
	init_apic_mappings();

	prefill_possible_map();

	init_cpu_to_node();

	io_apic_init_mappings();

	x86_init.hyper.guest_late_init();

	e820__reserve_resources();
	e820__register_nosave_regions(max_low_pfn);

	x86_init.resources.reserve_resources();

	e820__setup_pci_gap();

#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
		conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
	conswitchp = &dummy_con;
#endif
#endif
	x86_init.oem.banner();

	x86_init.timers.wallclock_init();

	mcheck_init();

	arch_init_ideal_nops();

	register_refined_jiffies(CLOCK_TICK_RATE);

#ifdef CONFIG_EFI
	if (efi_enabled(EFI_BOOT))
		efi_apply_memmap_quirks();
#endif

	unwind_init();
}

#ifdef CONFIG_X86_32

static struct resource video_ram_resource = {
	.name	= "Video RAM area",
	.start	= 0xa0000,
	.end	= 0xbffff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

void __init i386_reserve_resources(void)
{
	request_resource(&iomem_resource, &video_ram_resource);
	reserve_standard_io_resources();
}

#endif /* CONFIG_X86_32 */

static struct notifier_block kernel_offset_notifier = {
	.notifier_call = dump_kernel_offset
};

static int __init register_kernel_offset_dumper(void)
{
	atomic_notifier_chain_register(&panic_notifier_list,
					&kernel_offset_notifier);
	return 0;
}
__initcall(register_kernel_offset_dumper);

void arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
{
	if (!boot_cpu_has(X86_FEATURE_OSPKE))
		return;

	seq_printf(m, "ProtectionKey:  %8u\n", vma_pkey(vma));
}
OpenPOWER on IntegriCloud