aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/setup_64.c
blob: 3220c7b56eb3f1eb9029abb8871a299d5629b50b (plain) (blame)
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
/*
 *  Copyright (C) 1995  Linus Torvalds
 */

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

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/highmem.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <asm/processor.h>
#include <linux/console.h>
#include <linux/seq_file.h>
#include <linux/crash_dump.h>
#include <linux/root_dev.h>
#include <linux/pci.h>
#include <asm/pci-direct.h>
#include <linux/efi.h>
#include <linux/acpi.h>
#include <linux/kallsyms.h>
#include <linux/edd.h>
#include <linux/iscsi_ibft.h>
#include <linux/mmzone.h>
#include <linux/kexec.h>
#include <linux/cpufreq.h>
#include <linux/dmi.h>
#include <linux/dma-mapping.h>
#include <linux/ctype.h>
#include <linux/sort.h>
#include <linux/uaccess.h>
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>

#include <asm/mtrr.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/vsyscall.h>
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <video/edid.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/dma.h>
#include <asm/gart.h>
#include <asm/mpspec.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/setup.h>
#include <asm/numa.h>
#include <asm/sections.h>
#include <asm/dmi.h>
#include <asm/cacheflush.h>
#include <asm/mce.h>
#include <asm/ds.h>
#include <asm/topology.h>
#include <asm/trampoline.h>
#include <asm/pat.h>

#include <mach_apic.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define ARCH_SETUP
#endif

/*
 * Machine setup..
 */

struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);

__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;

unsigned long mmu_cr4_features;

/* Boot loader ID as an integer, for the benefit of proc_dointvec */
int bootloader_type;

unsigned long saved_video_mode;

int force_mwait __cpuinitdata;

/*
 * Early DMI memory
 */
int dmi_alloc_index;
char dmi_alloc_data[DMI_MAX_DATA];

/*
 * Setup options
 */
struct screen_info screen_info;
EXPORT_SYMBOL(screen_info);
struct sys_desc_table_struct {
	unsigned short length;
	unsigned char table[0];
};

struct edid_info edid_info;
EXPORT_SYMBOL_GPL(edid_info);

extern int root_mountflags;

char __initdata command_line[COMMAND_LINE_SIZE];

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 }
};

#define IORESOURCE_RAM (IORESOURCE_BUSY | IORESOURCE_MEM)

static struct resource data_resource = {
	.name = "Kernel data",
	.start = 0,
	.end = 0,
	.flags = IORESOURCE_RAM,
};
static struct resource code_resource = {
	.name = "Kernel code",
	.start = 0,
	.end = 0,
	.flags = IORESOURCE_RAM,
};
static struct resource bss_resource = {
	.name = "Kernel bss",
	.start = 0,
	.end = 0,
	.flags = IORESOURCE_RAM,
};

static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c);

#ifdef CONFIG_PROC_VMCORE
/* elfcorehdr= specifies the location of elf core header
 * stored by the crashed kernel. This option will be passed
 * by kexec loader to the capture kernel.
 */
static int __init setup_elfcorehdr(char *arg)
{
	char *end;
	if (!arg)
		return -EINVAL;
	elfcorehdr_addr = memparse(arg, &end);
	return end > arg ? 0 : -EINVAL;
}
early_param("elfcorehdr", setup_elfcorehdr);
#endif

#ifndef CONFIG_NUMA
static void __init
contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long bootmap_size, bootmap;

	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
				 PAGE_SIZE);
	if (bootmap == -1L)
		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
	e820_register_active_regions(0, start_pfn, end_pfn);
	free_bootmem_with_active_regions(0, end_pfn);
	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
}
#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 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 copy_edd(void)
{
}
#endif

#ifdef CONFIG_KEXEC
static void __init reserve_crashkernel(void)
{
	unsigned long long total_mem;
	unsigned long long crash_size, crash_base;
	int ret;

	total_mem = ((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT;

	ret = parse_crashkernel(boot_command_line, total_mem,
			&crash_size, &crash_base);
	if (ret == 0 && crash_size) {
		if (crash_base <= 0) {
			printk(KERN_INFO "crashkernel reservation failed - "
					"you have to specify a base address\n");
			return;
		}

		if (reserve_bootmem_generic(crash_base, crash_size,
					BOOTMEM_EXCLUSIVE) < 0) {
			printk(KERN_INFO "crashkernel reservation failed - "
					"memory is in use\n");
			return;
		}

		printk(KERN_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 inline void __init reserve_crashkernel(void)
{}
#endif

#ifdef CONFIG_PCI_MMCONFIG
extern void __cpuinit fam10h_check_enable_mmcfg(void);
extern void __init check_enable_amd_mmconf_dmi(void);
#else
void __cpuinit fam10h_check_enable_mmcfg(void)
{
}
void __init check_enable_amd_mmconf_dmi(void)
{
}
#endif

/*
 * 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)
{
	unsigned i;

	printk(KERN_INFO "Command line: %s\n", boot_command_line);

	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
	screen_info = boot_params.screen_info;
	edid_info = boot_params.edid_info;
	saved_video_mode = boot_params.hdr.vid_mode;
	bootloader_type = boot_params.hdr.type_of_loader;

#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,
		     "EL64", 4)) {
		efi_enabled = 1;
		efi_reserve_early();
	}
#endif

	ARCH_SETUP

	setup_memory_map();
	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 = (unsigned long) &_end;

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

	early_identify_cpu(&boot_cpu_data);

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

	parse_setup_data();

	parse_early_param();

#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
	if (init_ohci1394_dma_early)
		init_ohci1394_dma_on_all_controllers();
#endif

	finish_e820_parsing();

	/* 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);

	early_gart_iommu_check();

	e820_register_active_regions(0, 0, -1UL);
	/*
	 * partially used pages are not usable - thus
	 * we are rounding upwards:
	 */
	end_pfn = e820_end_of_ram();

	/* pre allocte 4k for mptable mpc */
	early_reserve_e820_mpc_new();
	/* update e820 for memory not covered by WB MTRRs */
	mtrr_bp_init();
	if (mtrr_trim_uncached_memory(end_pfn)) {
		remove_all_active_ranges();
		e820_register_active_regions(0, 0, -1UL);
		end_pfn = e820_end_of_ram();
	}

	num_physpages = end_pfn;

	check_efer();

	max_pfn_mapped = init_memory_mapping(0, (end_pfn << PAGE_SHIFT));
	if (efi_enabled)
		efi_init();

	vsmp_init();

	dmi_scan_machine();

	io_delay_init();

#ifdef CONFIG_KVM_CLOCK
	kvmclock_init();
#endif

#ifdef CONFIG_SMP
	/* setup to use the early static init tables during kernel startup */
	x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init;
	x86_bios_cpu_apicid_early_ptr = (void *)x86_bios_cpu_apicid_init;
#ifdef CONFIG_NUMA
	x86_cpu_to_node_map_early_ptr = (void *)x86_cpu_to_node_map_init;
#endif
#endif

#ifdef CONFIG_ACPI
	/*
	 * Initialize the ACPI boot-time table parser (gets the RSDP and SDT).
	 * Call this early for SRAT node setup.
	 */
	acpi_boot_table_init();
#endif

	/* How many end-of-memory variables you have, grandma! */
	max_low_pfn = end_pfn;
	max_pfn = end_pfn;
	high_memory = (void *)__va(end_pfn * PAGE_SIZE - 1) + 1;

	/* Remove active ranges so rediscovery with NUMA-awareness happens */
	remove_all_active_ranges();

#ifdef CONFIG_ACPI_NUMA
	/*
	 * Parse SRAT to discover nodes.
	 */
	acpi_numa_init();
#endif

#ifdef CONFIG_NUMA
	numa_initmem_init(0, end_pfn);
#else
	contig_initmem_init(0, end_pfn);
#endif

	dma32_reserve_bootmem();

#ifdef CONFIG_ACPI_SLEEP
	/*
	 * Reserve low memory region for sleep support.
	 */
       acpi_reserve_bootmem();
#endif

#ifdef CONFIG_X86_MPPARSE
       /*
	* Find and reserve possible boot-time SMP configuration:
	*/
	find_smp_config();
#endif
#ifdef CONFIG_BLK_DEV_INITRD
	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
		unsigned long end_of_mem    = end_pfn << PAGE_SHIFT;

		if (ramdisk_end <= end_of_mem) {
			/*
			 * don't need to reserve again, already reserved early
			 * in x86_64_start_kernel, and early_res_to_bootmem
			 * convert that to reserved in bootmem
			 */
			initrd_start = ramdisk_image + PAGE_OFFSET;
			initrd_end = initrd_start+ramdisk_size;
		} else {
			free_bootmem(ramdisk_image, ramdisk_size);
			printk(KERN_ERR "initrd extends beyond end of memory "
			       "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
			       ramdisk_end, end_of_mem);
			initrd_start = 0;
		}
	}
#endif
	reserve_crashkernel();

	reserve_ibft_region();

	paging_init();
	map_vsyscall();

	early_quirks();

#ifdef CONFIG_ACPI
	/*
	 * Read APIC and some other early information from ACPI tables.
	 */
	acpi_boot_init();
#endif

	init_cpu_to_node();

#ifdef CONFIG_X86_MPPARSE
	/*
	 * get boot-time SMP configuration:
	 */
	if (smp_found_config)
		get_smp_config();
#endif
	init_apic_mappings();
	ioapic_init_mappings();

	kvm_guest_init();

	/*
	 * We trust e820 completely. No explicit ROM probing in memory.
	 */
	e820_reserve_resources();
	e820_mark_nosave_regions(end_pfn);

	/* 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]);

	e820_setup_gap();

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

	/* do this before identify_cpu for boot cpu */
	check_enable_amd_mmconf_dmi();
}

static int __cpuinit get_model_name(struct cpuinfo_x86 *c)
{
	unsigned int *v;

	if (c->extended_cpuid_level < 0x80000004)
		return 0;

	v = (unsigned int *) c->x86_model_id;
	cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
	cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
	c->x86_model_id[48] = 0;
	return 1;
}


static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
{
	unsigned int n, dummy, eax, ebx, ecx, edx;

	n = c->extended_cpuid_level;

	if (n >= 0x80000005) {
		cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
		printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), "
		       "D cache %dK (%d bytes/line)\n",
		       edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
		c->x86_cache_size = (ecx>>24) + (edx>>24);
		/* On K8 L1 TLB is inclusive, so don't count it */
		c->x86_tlbsize = 0;
	}

	if (n >= 0x80000006) {
		cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
		ecx = cpuid_ecx(0x80000006);
		c->x86_cache_size = ecx >> 16;
		c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);

		printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
		c->x86_cache_size, ecx & 0xFF);
	}
	if (n >= 0x80000008) {
		cpuid(0x80000008, &eax, &dummy, &dummy, &dummy);
		c->x86_virt_bits = (eax >> 8) & 0xff;
		c->x86_phys_bits = eax & 0xff;
	}
}

#ifdef CONFIG_NUMA
static int __cpuinit nearby_node(int apicid)
{
	int i, node;

	for (i = apicid - 1; i >= 0; i--) {
		node = apicid_to_node[i];
		if (node != NUMA_NO_NODE && node_online(node))
			return node;
	}
	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
		node = apicid_to_node[i];
		if (node != NUMA_NO_NODE && node_online(node))
			return node;
	}
	return first_node(node_online_map); /* Shouldn't happen */
}
#endif

/*
 * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
 * Assumes number of cores is a power of two.
 */
static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
	unsigned bits;
#ifdef CONFIG_NUMA
	int cpu = smp_processor_id();
	int node = 0;
	unsigned apicid = hard_smp_processor_id();
#endif
	bits = c->x86_coreid_bits;

	/* Low order bits define the core id (index of core in socket) */
	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
	/* Convert the initial APIC ID into the socket ID */
	c->phys_proc_id = c->initial_apicid >> bits;

#ifdef CONFIG_NUMA
	node = c->phys_proc_id;
	if (apicid_to_node[apicid] != NUMA_NO_NODE)
		node = apicid_to_node[apicid];
	if (!node_online(node)) {
		/* Two possibilities here:
		   - The CPU is missing memory and no node was created.
		   In that case try picking one from a nearby CPU
		   - The APIC IDs differ from the HyperTransport node IDs
		   which the K8 northbridge parsing fills in.
		   Assume they are all increased by a constant offset,
		   but in the same order as the HT nodeids.
		   If that doesn't result in a usable node fall back to the
		   path for the previous case.  */

		int ht_nodeid = c->initial_apicid;

		if (ht_nodeid >= 0 &&
		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
			node = apicid_to_node[ht_nodeid];
		/* Pick a nearby node */
		if (!node_online(node))
			node = nearby_node(apicid);
	}
	numa_set_node(cpu, node);

	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
#endif
#endif
}

static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
	unsigned bits, ecx;

	/* Multi core CPU? */
	if (c->extended_cpuid_level < 0x80000008)
		return;

	ecx = cpuid_ecx(0x80000008);

	c->x86_max_cores = (ecx & 0xff) + 1;

	/* CPU telling us the core id bits shift? */
	bits = (ecx >> 12) & 0xF;

	/* Otherwise recompute */
	if (bits == 0) {
		while ((1 << bits) < c->x86_max_cores)
			bits++;
	}

	c->x86_coreid_bits = bits;

#endif
}

#define ENABLE_C1E_MASK		0x18000000
#define CPUID_PROCESSOR_SIGNATURE	1
#define CPUID_XFAM		0x0ff00000
#define CPUID_XFAM_K8		0x00000000
#define CPUID_XFAM_10H		0x00100000
#define CPUID_XFAM_11H		0x00200000
#define CPUID_XMOD		0x000f0000
#define CPUID_XMOD_REV_F	0x00040000

/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
static __cpuinit int amd_apic_timer_broken(void)
{
	u32 lo, hi, eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);

	switch (eax & CPUID_XFAM) {
	case CPUID_XFAM_K8:
		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
			break;
	case CPUID_XFAM_10H:
	case CPUID_XFAM_11H:
		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
		if (lo & ENABLE_C1E_MASK)
			return 1;
		break;
	default:
		/* err on the side of caution */
		return 1;
	}
	return 0;
}

static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
{
	early_init_amd_mc(c);

 	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
	if (c->x86_power & (1<<8))
		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
}

static void __cpuinit init_amd(struct cpuinfo_x86 *c)
{
	unsigned level;

#ifdef CONFIG_SMP
	unsigned long value;

	/*
	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
	 * bit 6 of msr C001_0015
	 *
	 * Errata 63 for SH-B3 steppings
	 * Errata 122 for all steppings (F+ have it disabled by default)
	 */
	if (c->x86 == 15) {
		rdmsrl(MSR_K8_HWCR, value);
		value |= 1 << 6;
		wrmsrl(MSR_K8_HWCR, value);
	}
#endif

	/* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
	   3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
	clear_cpu_cap(c, 0*32+31);

	/* On C+ stepping K8 rep microcode works well for copy/memset */
	level = cpuid_eax(1);
	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
			     level >= 0x0f58))
		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
	if (c->x86 == 0x10 || c->x86 == 0x11)
		set_cpu_cap(c, X86_FEATURE_REP_GOOD);

	/* Enable workaround for FXSAVE leak */
	if (c->x86 >= 6)
		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);

	level = get_model_name(c);
	if (!level) {
		switch (c->x86) {
		case 15:
			/* Should distinguish Models here, but this is only
			   a fallback anyways. */
			strcpy(c->x86_model_id, "Hammer");
			break;
		}
	}
	display_cacheinfo(c);

	/* Multi core CPU? */
	if (c->extended_cpuid_level >= 0x80000008)
		amd_detect_cmp(c);

	if (c->extended_cpuid_level >= 0x80000006 &&
		(cpuid_edx(0x80000006) & 0xf000))
		num_cache_leaves = 4;
	else
		num_cache_leaves = 3;

	if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
		set_cpu_cap(c, X86_FEATURE_K8);

	/* MFENCE stops RDTSC speculation */
	set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);

	if (c->x86 == 0x10)
		fam10h_check_enable_mmcfg();

	if (amd_apic_timer_broken())
		disable_apic_timer = 1;

	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
		unsigned long long tseg;

		/*
		 * Split up direct mapping around the TSEG SMM area.
		 * Don't do it for gbpages because there seems very little
		 * benefit in doing so.
		 */
		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
		(tseg >> PMD_SHIFT) < (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
			set_memory_4k((unsigned long)__va(tseg), 1);
	}
}

void __cpuinit detect_ht(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
	u32 eax, ebx, ecx, edx;
	int index_msb, core_bits;

	cpuid(1, &eax, &ebx, &ecx, &edx);


	if (!cpu_has(c, X86_FEATURE_HT))
		return;
	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
		goto out;

	smp_num_siblings = (ebx & 0xff0000) >> 16;

	if (smp_num_siblings == 1) {
		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
	} else if (smp_num_siblings > 1) {

		if (smp_num_siblings > NR_CPUS) {
			printk(KERN_WARNING "CPU: Unsupported number of "
			       "siblings %d", smp_num_siblings);
			smp_num_siblings = 1;
			return;
		}

		index_msb = get_count_order(smp_num_siblings);
		c->phys_proc_id = phys_pkg_id(index_msb);

		smp_num_siblings = smp_num_siblings / c->x86_max_cores;

		index_msb = get_count_order(smp_num_siblings);

		core_bits = get_count_order(c->x86_max_cores);

		c->cpu_core_id = phys_pkg_id(index_msb) &
					       ((1 << core_bits) - 1);
	}
out:
	if ((c->x86_max_cores * smp_num_siblings) > 1) {
		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
		       c->phys_proc_id);
		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
		       c->cpu_core_id);
	}

#endif
}

/*
 * find out the number of processor cores on the die
 */
static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
{
	unsigned int eax, t;

	if (c->cpuid_level < 4)
		return 1;

	cpuid_count(4, 0, &eax, &t, &t, &t);

	if (eax & 0x1f)
		return ((eax >> 26) + 1);
	else
		return 1;
}

static void __cpuinit srat_detect_node(void)
{
#ifdef CONFIG_NUMA
	unsigned node;
	int cpu = smp_processor_id();
	int apicid = hard_smp_processor_id();

	/* Don't do the funky fallback heuristics the AMD version employs
	   for now. */
	node = apicid_to_node[apicid];
	if (node == NUMA_NO_NODE || !node_online(node))
		node = first_node(node_online_map);
	numa_set_node(cpu, node);

	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
#endif
}

static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
{
	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
}

static void __cpuinit init_intel(struct cpuinfo_x86 *c)
{
	/* Cache sizes */
	unsigned n;

	init_intel_cacheinfo(c);
	if (c->cpuid_level > 9) {
		unsigned eax = cpuid_eax(10);
		/* Check for version and the number of counters */
		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
	}

	if (cpu_has_ds) {
		unsigned int l1, l2;
		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
		if (!(l1 & (1<<11)))
			set_cpu_cap(c, X86_FEATURE_BTS);
		if (!(l1 & (1<<12)))
			set_cpu_cap(c, X86_FEATURE_PEBS);
	}


	if (cpu_has_bts)
		ds_init_intel(c);

	n = c->extended_cpuid_level;
	if (n >= 0x80000008) {
		unsigned eax = cpuid_eax(0x80000008);
		c->x86_virt_bits = (eax >> 8) & 0xff;
		c->x86_phys_bits = eax & 0xff;
		/* CPUID workaround for Intel 0F34 CPU */
		if (c->x86_vendor == X86_VENDOR_INTEL &&
		    c->x86 == 0xF && c->x86_model == 0x3 &&
		    c->x86_mask == 0x4)
			c->x86_phys_bits = 36;
	}

	if (c->x86 == 15)
		c->x86_cache_alignment = c->x86_clflush_size * 2;
	if (c->x86 == 6)
		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
	c->x86_max_cores = intel_num_cpu_cores(c);

	srat_detect_node();
}

static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
{
	if (c->x86 == 0x6 && c->x86_model >= 0xf)
		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
}

static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
{
	/* Cache sizes */
	unsigned n;

	n = c->extended_cpuid_level;
	if (n >= 0x80000008) {
		unsigned eax = cpuid_eax(0x80000008);
		c->x86_virt_bits = (eax >> 8) & 0xff;
		c->x86_phys_bits = eax & 0xff;
	}

	if (c->x86 == 0x6 && c->x86_model >= 0xf) {
		c->x86_cache_alignment = c->x86_clflush_size * 2;
		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
	}
	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}

static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
{
	char *v = c->x86_vendor_id;

	if (!strcmp(v, "AuthenticAMD"))
		c->x86_vendor = X86_VENDOR_AMD;
	else if (!strcmp(v, "GenuineIntel"))
		c->x86_vendor = X86_VENDOR_INTEL;
	else if (!strcmp(v, "CentaurHauls"))
		c->x86_vendor = X86_VENDOR_CENTAUR;
	else
		c->x86_vendor = X86_VENDOR_UNKNOWN;
}

/* Do some early cpuid on the boot CPU to get some parameter that are
   needed before check_bugs. Everything advanced is in identify_cpu
   below. */
static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
{
	u32 tfms, xlvl;

	c->loops_per_jiffy = loops_per_jiffy;
	c->x86_cache_size = -1;
	c->x86_vendor = X86_VENDOR_UNKNOWN;
	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
	c->x86_vendor_id[0] = '\0'; /* Unset */
	c->x86_model_id[0] = '\0';  /* Unset */
	c->x86_clflush_size = 64;
	c->x86_cache_alignment = c->x86_clflush_size;
	c->x86_max_cores = 1;
	c->x86_coreid_bits = 0;
	c->extended_cpuid_level = 0;
	memset(&c->x86_capability, 0, sizeof c->x86_capability);

	/* Get vendor name */
	cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
	      (unsigned int *)&c->x86_vendor_id[0],
	      (unsigned int *)&c->x86_vendor_id[8],
	      (unsigned int *)&c->x86_vendor_id[4]);

	get_cpu_vendor(c);

	/* Initialize the standard set of capabilities */
	/* Note that the vendor-specific code below might override */

	/* Intel-defined flags: level 0x00000001 */
	if (c->cpuid_level >= 0x00000001) {
		__u32 misc;
		cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4],
		      &c->x86_capability[0]);
		c->x86 = (tfms >> 8) & 0xf;
		c->x86_model = (tfms >> 4) & 0xf;
		c->x86_mask = tfms & 0xf;
		if (c->x86 == 0xf)
			c->x86 += (tfms >> 20) & 0xff;
		if (c->x86 >= 0x6)
			c->x86_model += ((tfms >> 16) & 0xF) << 4;
		if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
	} else {
		/* Have CPUID level 0 only - unheard of */
		c->x86 = 4;
	}

	c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xff;
#ifdef CONFIG_SMP
	c->phys_proc_id = c->initial_apicid;
#endif
	/* AMD-defined flags: level 0x80000001 */
	xlvl = cpuid_eax(0x80000000);
	c->extended_cpuid_level = xlvl;
	if ((xlvl & 0xffff0000) == 0x80000000) {
		if (xlvl >= 0x80000001) {
			c->x86_capability[1] = cpuid_edx(0x80000001);
			c->x86_capability[6] = cpuid_ecx(0x80000001);
		}
		if (xlvl >= 0x80000004)
			get_model_name(c); /* Default name */
	}

	/* Transmeta-defined flags: level 0x80860001 */
	xlvl = cpuid_eax(0x80860000);
	if ((xlvl & 0xffff0000) == 0x80860000) {
		/* Don't set x86_cpuid_level here for now to not confuse. */
		if (xlvl >= 0x80860001)
			c->x86_capability[2] = cpuid_edx(0x80860001);
	}

	c->extended_cpuid_level = cpuid_eax(0x80000000);
	if (c->extended_cpuid_level >= 0x80000007)
		c->x86_power = cpuid_edx(0x80000007);

	switch (c->x86_vendor) {
	case X86_VENDOR_AMD:
		early_init_amd(c);
		break;
	case X86_VENDOR_INTEL:
		early_init_intel(c);
		break;
	case X86_VENDOR_CENTAUR:
		early_init_centaur(c);
		break;
	}

	validate_pat_support(c);
}

/*
 * This does the hard work of actually picking apart the CPU stuff...
 */
void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
{
	int i;

	early_identify_cpu(c);

	init_scattered_cpuid_features(c);

	c->apicid = phys_pkg_id(0);

	/*
	 * Vendor-specific initialization.  In this section we
	 * canonicalize the feature flags, meaning if there are
	 * features a certain CPU supports which CPUID doesn't
	 * tell us, CPUID claiming incorrect flags, or other bugs,
	 * we handle them here.
	 *
	 * At the end of this section, c->x86_capability better
	 * indicate the features this CPU genuinely supports!
	 */
	switch (c->x86_vendor) {
	case X86_VENDOR_AMD:
		init_amd(c);
		break;

	case X86_VENDOR_INTEL:
		init_intel(c);
		break;

	case X86_VENDOR_CENTAUR:
		init_centaur(c);
		break;

	case X86_VENDOR_UNKNOWN:
	default:
		display_cacheinfo(c);
		break;
	}

	detect_ht(c);

	/*
	 * On SMP, boot_cpu_data holds the common feature set between
	 * all CPUs; so make sure that we indicate which features are
	 * common between the CPUs.  The first time this routine gets
	 * executed, c == &boot_cpu_data.
	 */
	if (c != &boot_cpu_data) {
		/* AND the already accumulated flags with these */
		for (i = 0; i < NCAPINTS; i++)
			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
	}

	/* Clear all flags overriden by options */
	for (i = 0; i < NCAPINTS; i++)
		c->x86_capability[i] &= ~cleared_cpu_caps[i];

#ifdef CONFIG_X86_MCE
	mcheck_init(c);
#endif
	select_idle_routine(c);

#ifdef CONFIG_NUMA
	numa_add_cpu(smp_processor_id());
#endif

}

void __cpuinit identify_boot_cpu(void)
{
	identify_cpu(&boot_cpu_data);
}

void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
{
	BUG_ON(c == &boot_cpu_data);
	identify_cpu(c);
	mtrr_ap_init();
}

static __init int setup_noclflush(char *arg)
{
	setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
	return 1;
}
__setup("noclflush", setup_noclflush);

void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
{
	if (c->x86_model_id[0])
		printk(KERN_CONT "%s", c->x86_model_id);

	if (c->x86_mask || c->cpuid_level >= 0)
		printk(KERN_CONT " stepping %02x\n", c->x86_mask);
	else
		printk(KERN_CONT "\n");
}

static __init int setup_disablecpuid(char *arg)
{
	int bit;
	if (get_option(&arg, &bit) && bit < NCAPINTS*32)
		setup_clear_cpu_cap(bit);
	else
		return 0;
	return 1;
}
__setup("clearcpuid=", setup_disablecpuid);