common.c 39.5 KB
Newer Older
1
2
3
4
#include <linux/bootmem.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
5
#include <linux/export.h>
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
#include <linux/percpu.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/kgdb.h>
#include <linux/smp.h>
#include <linux/io.h>
#include <linux/syscore_ops.h>

#include <asm/stackprotector.h>
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
#include <asm/archrandom.h>
#include <asm/hypervisor.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/debugreg.h>
#include <asm/sections.h>
#include <asm/vsyscall.h>
#include <linux/topology.h>
#include <linux/cpumask.h>
#include <asm/pgtable.h>
#include <linux/atomic.h>
#include <asm/proto.h>
#include <asm/setup.h>
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
#include <asm/mtrr.h>
#include <linux/numa.h>
#include <asm/asm.h>
#include <asm/bugs.h>
#include <asm/cpu.h>
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/pat.h>
#include <asm/microcode.h>
#include <asm/microcode_intel.h>

#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/uv/uv.h>
#endif

#include "cpu.h"

/* all of these masks are initialized in setup_cpu_local_masks() */
cpumask_var_t cpu_initialized_mask;
cpumask_var_t cpu_callout_mask;
cpumask_var_t cpu_callin_mask;

/* representing cpus for which sibling maps can be computed */
cpumask_var_t cpu_sibling_setup_mask;

/* correctly size the local cpu masks */
void __init setup_cpu_local_masks(void)
{
	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
	alloc_bootmem_cpumask_var(&cpu_callin_mask);
	alloc_bootmem_cpumask_var(&cpu_callout_mask);
	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
}

static void default_init(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_64
	cpu_detect_cache_sizes(c);
#else
	/* Not much we can do here... */
	/* Check if at least it has cpuid */
	if (c->cpuid_level == -1) {
		/* No cpuid. It must be an ancient CPU */
		if (c->x86 == 4)
			strcpy(c->x86_model_id, "486");
		else if (c->x86 == 3)
			strcpy(c->x86_model_id, "386");
	}
#endif
}

static const struct cpu_dev default_cpu = {
	.c_init		= default_init,
	.c_vendor	= "Unknown",
	.c_x86_vendor	= X86_VENDOR_UNKNOWN,
};

static const struct cpu_dev *this_cpu = &default_cpu;

DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
#ifdef CONFIG_X86_64
	/*
	 * We need valid kernel segments for data and code in long mode too
	 * IRET will check the segment types  kkeil 2000/10/28
	 * Also sysret mandates a special GDT layout
	 *
	 * TLS descriptors are currently at a different place compared to i386.
	 * Hopefully nobody expects them at a fixed place (Wine?)
	 */
	[GDT_ENTRY_KERNEL32_CS]		= GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
	[GDT_ENTRY_DEFAULT_USER32_CS]	= GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff),
	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff),
	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff),
#else
	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xc09a, 0, 0xfffff),
	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff),
	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff),
	/*
	 * Segments used for calling PnP BIOS have byte granularity.
	 * They code segments and data segments have fixed 64k limits,
	 * the transfer segment sizes are set at run time.
	 */
	/* 32-bit code */
	[GDT_ENTRY_PNPBIOS_CS32]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
	/* 16-bit code */
	[GDT_ENTRY_PNPBIOS_CS16]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
	/* 16-bit data */
	[GDT_ENTRY_PNPBIOS_DS]		= GDT_ENTRY_INIT(0x0092, 0, 0xffff),
	/* 16-bit data */
	[GDT_ENTRY_PNPBIOS_TS1]		= GDT_ENTRY_INIT(0x0092, 0, 0),
	/* 16-bit data */
	[GDT_ENTRY_PNPBIOS_TS2]		= GDT_ENTRY_INIT(0x0092, 0, 0),
	/*
	 * The APM segments have byte granularity and their bases
	 * are set at run time.  All have 64k limits.
	 */
	/* 32-bit code */
	[GDT_ENTRY_APMBIOS_BASE]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
	/* 16-bit code */
	[GDT_ENTRY_APMBIOS_BASE+1]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
	/* data */
	[GDT_ENTRY_APMBIOS_BASE+2]	= GDT_ENTRY_INIT(0x4092, 0, 0xffff),

	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
	GDT_STACK_CANARY_INIT
#endif
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);

static int __init x86_mpx_setup(char *s)
{
	/* require an exact match without trailing characters */
	if (strlen(s))
		return 0;

	/* do not emit a message if the feature is not present */
	if (!boot_cpu_has(X86_FEATURE_MPX))
		return 1;

	setup_clear_cpu_cap(X86_FEATURE_MPX);
	pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
	return 1;
}
__setup("nompx", x86_mpx_setup);

static int __init x86_noinvpcid_setup(char *s)
{
	/* noinvpcid doesn't accept parameters */
	if (s)
		return -EINVAL;

	/* do not emit a message if the feature is not present */
	if (!boot_cpu_has(X86_FEATURE_INVPCID))
		return 0;

	setup_clear_cpu_cap(X86_FEATURE_INVPCID);
	pr_info("noinvpcid: INVPCID feature disabled\n");
	return 0;
}
early_param("noinvpcid", x86_noinvpcid_setup);

#ifdef CONFIG_X86_32
static int cachesize_override = -1;
static int disable_x86_serial_nr = 1;

static int __init cachesize_setup(char *str)
{
	get_option(&str, &cachesize_override);
	return 1;
}
__setup("cachesize=", cachesize_setup);

static int __init x86_sep_setup(char *s)
{
	setup_clear_cpu_cap(X86_FEATURE_SEP);
	return 1;
}
__setup("nosep", x86_sep_setup);

/* Standard macro to see if a specific flag is changeable */
static inline int flag_is_changeable_p(u32 flag)
{
	u32 f1, f2;

	/*
	 * Cyrix and IDT cpus allow disabling of CPUID
	 * so the code below may return different results
	 * when it is executed before and after enabling
	 * the CPUID. Add "volatile" to not allow gcc to
	 * optimize the subsequent calls to this function.
	 */
	asm volatile ("pushfl		\n\t"
		      "pushfl		\n\t"
		      "popl %0		\n\t"
		      "movl %0, %1	\n\t"
		      "xorl %2, %0	\n\t"
		      "pushl %0		\n\t"
		      "popfl		\n\t"
		      "pushfl		\n\t"
		      "popl %0		\n\t"
		      "popfl		\n\t"

		      : "=&r" (f1), "=&r" (f2)
		      : "ir" (flag));

	return ((f1^f2) & flag) != 0;
}

/* Probe for the CPUID instruction */
int have_cpuid_p(void)
{
	return flag_is_changeable_p(X86_EFLAGS_ID);
}

static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
{
	unsigned long lo, hi;

	if (!cpu_has(c, X86_FEATURE_PN) || !disable_x86_serial_nr)
		return;

	/* Disable processor serial number: */

	rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
	lo |= 0x200000;
	wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);

	pr_notice("CPU serial number disabled.\n");
	clear_cpu_cap(c, X86_FEATURE_PN);

	/* Disabling the serial number may affect the cpuid level */
	c->cpuid_level = cpuid_eax(0);
}

static int __init x86_serial_nr_setup(char *s)
{
	disable_x86_serial_nr = 0;
	return 1;
}
__setup("serialnumber", x86_serial_nr_setup);
#else
static inline int flag_is_changeable_p(u32 flag)
{
	return 1;
}
static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
{
}
#endif

static __init int setup_disable_smep(char *arg)
{
	setup_clear_cpu_cap(X86_FEATURE_SMEP);
	/* Check for things that depend on SMEP being enabled: */
	check_mpx_erratum(&boot_cpu_data);
	return 1;
}
__setup("nosmep", setup_disable_smep);

static __always_inline void setup_smep(struct cpuinfo_x86 *c)
{
	if (cpu_has(c, X86_FEATURE_SMEP))
		cr4_set_bits(X86_CR4_SMEP);
}

static __init int setup_disable_smap(char *arg)
{
	setup_clear_cpu_cap(X86_FEATURE_SMAP);
	return 1;
}
__setup("nosmap", setup_disable_smap);

static __always_inline void setup_smap(struct cpuinfo_x86 *c)
{
	unsigned long eflags = native_save_fl();

	/* This should have been cleared long ago */
	BUG_ON(eflags & X86_EFLAGS_AC);

	if (cpu_has(c, X86_FEATURE_SMAP)) {
#ifdef CONFIG_X86_SMAP
		cr4_set_bits(X86_CR4_SMAP);
#else
		cr4_clear_bits(X86_CR4_SMAP);
#endif
	}
}

/*
 * Protection Keys are not available in 32-bit mode.
 */
static bool pku_disabled;

static __always_inline void setup_pku(struct cpuinfo_x86 *c)
{
	/* check the boot processor, plus compile options for PKU: */
	if (!cpu_feature_enabled(X86_FEATURE_PKU))
		return;
	/* checks the actual processor's cpuid bits: */
	if (!cpu_has(c, X86_FEATURE_PKU))
		return;
	if (pku_disabled)
		return;

	cr4_set_bits(X86_CR4_PKE);
	/*
	 * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
	 * cpuid bit to be set.  We need to ensure that we
	 * update that bit in this CPU's "cpu_info".
	 */
	get_cpu_cap(c);
}

#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
static __init int setup_disable_pku(char *arg)
{
	/*
	 * Do not clear the X86_FEATURE_PKU bit.  All of the
	 * runtime checks are against OSPKE so clearing the
	 * bit does nothing.
	 *
	 * This way, we will see "pku" in cpuinfo, but not
	 * "ospke", which is exactly what we want.  It shows
	 * that the CPU has PKU, but the OS has not enabled it.
	 * This happens to be exactly how a system would look
	 * if we disabled the config option.
	 */
	pr_info("x86: 'nopku' specified, disabling Memory Protection Keys\n");
	pku_disabled = true;
	return 1;
}
__setup("nopku", setup_disable_pku);
#endif /* CONFIG_X86_64 */

/*
 * Some CPU features depend on higher CPUID levels, which may not always
 * be available due to CPUID level capping or broken virtualization
 * software.  Add those features to this table to auto-disable them.
 */
struct cpuid_dependent_feature {
	u32 feature;
	u32 level;
};

static const struct cpuid_dependent_feature
cpuid_dependent_features[] = {
	{ X86_FEATURE_MWAIT,		0x00000005 },
	{ X86_FEATURE_DCA,		0x00000009 },
	{ X86_FEATURE_XSAVE,		0x0000000d },
	{ 0, 0 }
};

static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
{
	const struct cpuid_dependent_feature *df;

	for (df = cpuid_dependent_features; df->feature; df++) {

		if (!cpu_has(c, df->feature))
			continue;
		/*
		 * Note: cpuid_level is set to -1 if unavailable, but
		 * extended_extended_level is set to 0 if unavailable
		 * and the legitimate extended levels are all negative
		 * when signed; hence the weird messing around with
		 * signs here...
		 */
		if (!((s32)df->level < 0 ?
		     (u32)df->level > (u32)c->extended_cpuid_level :
		     (s32)df->level > (s32)c->cpuid_level))
			continue;

		clear_cpu_cap(c, df->feature);
		if (!warn)
			continue;

		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
			x86_cap_flag(df->feature), df->level);
	}
}

/*
 * Naming convention should be: <Name> [(<Codename>)]
 * This table only is used unless init_<vendor>() below doesn't set it;
 * in particular, if CPUID levels 0x80000002..4 are supported, this
 * isn't used
 */

/* Look up CPU names by table lookup. */
static const char *table_lookup_model(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
	const struct legacy_cpu_model_info *info;

	if (c->x86_model >= 16)
		return NULL;	/* Range check */

	if (!this_cpu)
		return NULL;

	info = this_cpu->legacy_models;

	while (info->family) {
		if (info->family == c->x86)
			return info->model_names[c->x86_model];
		info++;
	}
#endif
	return NULL;		/* Not found */
}

__u32 cpu_caps_cleared[NCAPINTS];
__u32 cpu_caps_set[NCAPINTS];

void load_percpu_segment(int cpu)
{
#ifdef CONFIG_X86_32
	loadsegment(fs, __KERNEL_PERCPU);
#else
	__loadsegment_simple(gs, 0);
	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
#endif
	load_stack_canary_segment();
}

/*
 * Current gdt points %fs at the "master" per-cpu area: after this,
 * it's on the real one.
 */
void switch_to_new_gdt(int cpu)
{
	struct desc_ptr gdt_descr;

	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
	gdt_descr.size = GDT_SIZE - 1;
	load_gdt(&gdt_descr);
	/* Reload the per-cpu base */

	load_percpu_segment(cpu);
}

static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};

static void get_model_name(struct cpuinfo_x86 *c)
{
	unsigned int *v;
	char *p, *q, *s;

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

	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;

	/* Trim whitespace */
	p = q = s = &c->x86_model_id[0];

	while (*p == ' ')
		p++;

	while (*p) {
		/* Note the last non-whitespace index */
		if (!isspace(*p))
			s = q;

		*q++ = *p++;
	}

	*(s + 1) = '\0';
}

void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
{
	unsigned int n, dummy, ebx, ecx, edx, l2size;

	n = c->extended_cpuid_level;

	if (n >= 0x80000005) {
		cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
		c->x86_cache_size = (ecx>>24) + (edx>>24);
#ifdef CONFIG_X86_64
		/* On K8 L1 TLB is inclusive, so don't count it */
		c->x86_tlbsize = 0;
#endif
	}

	if (n < 0x80000006)	/* Some chips just has a large L1. */
		return;

	cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
	l2size = ecx >> 16;

#ifdef CONFIG_X86_64
	c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
#else
	/* do processor-specific cache resizing */
	if (this_cpu->legacy_cache_size)
		l2size = this_cpu->legacy_cache_size(c, l2size);

	/* Allow user to override all this if necessary. */
	if (cachesize_override != -1)
		l2size = cachesize_override;

	if (l2size == 0)
		return;		/* Again, no L2 cache is possible */
#endif

	c->x86_cache_size = l2size;
}

u16 __read_mostly tlb_lli_4k[NR_INFO];
u16 __read_mostly tlb_lli_2m[NR_INFO];
u16 __read_mostly tlb_lli_4m[NR_INFO];
u16 __read_mostly tlb_lld_4k[NR_INFO];
u16 __read_mostly tlb_lld_2m[NR_INFO];
u16 __read_mostly tlb_lld_4m[NR_INFO];
u16 __read_mostly tlb_lld_1g[NR_INFO];

static void cpu_detect_tlb(struct cpuinfo_x86 *c)
{
	if (this_cpu->c_detect_tlb)
		this_cpu->c_detect_tlb(c);

	pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
		tlb_lli_4m[ENTRIES]);

	pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
		tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
}

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

	if (!cpu_has(c, X86_FEATURE_HT))
		return;

	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
		goto out;

	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
		return;

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

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

	if (smp_num_siblings == 1) {
		pr_info_once("CPU0: Hyper-Threading is disabled\n");
		goto out;
	}

	if (smp_num_siblings <= 1)
		goto out;

	index_msb = get_count_order(smp_num_siblings);
	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, 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 = apic->phys_pkg_id(c->initial_apicid, index_msb) &
				       ((1 << core_bits) - 1);

out:
	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
		pr_info("CPU: Physical Processor ID: %d\n",
			c->phys_proc_id);
		pr_info("CPU: Processor Core ID: %d\n",
			c->cpu_core_id);
		printed = 1;
	}
#endif
}

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

	for (i = 0; i < X86_VENDOR_NUM; i++) {
		if (!cpu_devs[i])
			break;

		if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
		    (cpu_devs[i]->c_ident[1] &&
		     !strcmp(v, cpu_devs[i]->c_ident[1]))) {

			this_cpu = cpu_devs[i];
			c->x86_vendor = this_cpu->c_x86_vendor;
			return;
		}
	}

	pr_err_once("CPU: vendor_id '%s' unknown, using generic init.\n" \
		    "CPU: Your system may be unstable.\n", v);

	c->x86_vendor = X86_VENDOR_UNKNOWN;
	this_cpu = &default_cpu;
}

void cpu_detect(struct cpuinfo_x86 *c)
{
	/* 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]);

	c->x86 = 4;
	/* Intel-defined flags: level 0x00000001 */
	if (c->cpuid_level >= 0x00000001) {
		u32 junk, tfms, cap0, misc;

		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
		c->x86		= x86_family(tfms);
		c->x86_model	= x86_model(tfms);
		c->x86_mask	= x86_stepping(tfms);

		if (cap0 & (1<<19)) {
			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
			c->x86_cache_alignment = c->x86_clflush_size;
		}
	}
}

void get_cpu_cap(struct cpuinfo_x86 *c)
{
	u32 eax, ebx, ecx, edx;

	/* Intel-defined flags: level 0x00000001 */
	if (c->cpuid_level >= 0x00000001) {
		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);

		c->x86_capability[CPUID_1_ECX] = ecx;
		c->x86_capability[CPUID_1_EDX] = edx;
	}

670
671
672
673
	/* Thermal and Power Management Leaf: level 0x00000006 (eax) */
	if (c->cpuid_level >= 0x00000006)
		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);

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
	/* Additional Intel-defined flags: level 0x00000007 */
	if (c->cpuid_level >= 0x00000007) {
		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
		c->x86_capability[CPUID_7_0_EBX] = ebx;
		c->x86_capability[CPUID_7_ECX] = ecx;
	}

	/* Extended state features: level 0x0000000d */
	if (c->cpuid_level >= 0x0000000d) {
		cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);

		c->x86_capability[CPUID_D_1_EAX] = eax;
	}

	/* Additional Intel-defined flags: level 0x0000000F */
	if (c->cpuid_level >= 0x0000000F) {

		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
		c->x86_capability[CPUID_F_0_EDX] = edx;

		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
			/* will be overridden if occupancy monitoring exists */
			c->x86_cache_max_rmid = ebx;

			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
			c->x86_capability[CPUID_F_1_EDX] = edx;

			if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
			      ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
			       (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
				c->x86_cache_max_rmid = ecx;
				c->x86_cache_occ_scale = ebx;
			}
		} else {
			c->x86_cache_max_rmid = -1;
			c->x86_cache_occ_scale = -1;
		}
	}

	/* AMD-defined flags: level 0x80000001 */
	eax = cpuid_eax(0x80000000);
	c->extended_cpuid_level = eax;

	if ((eax & 0xffff0000) == 0x80000000) {
		if (eax >= 0x80000001) {
			cpuid(0x80000001, &eax, &ebx, &ecx, &edx);

			c->x86_capability[CPUID_8000_0001_ECX] = ecx;
			c->x86_capability[CPUID_8000_0001_EDX] = edx;
		}
	}

	if (c->extended_cpuid_level >= 0x80000007) {
		cpuid(0x80000007, &eax, &ebx, &ecx, &edx);

		c->x86_capability[CPUID_8000_0007_EBX] = ebx;
		c->x86_power = edx;
	}

	if (c->extended_cpuid_level >= 0x80000008) {
		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);

		c->x86_virt_bits = (eax >> 8) & 0xff;
		c->x86_phys_bits = eax & 0xff;
		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
	}
#ifdef CONFIG_X86_32
	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
		c->x86_phys_bits = 36;
#endif

	if (c->extended_cpuid_level >= 0x8000000a)
		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);

	init_scattered_cpuid_features(c);
}

static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
	int i;

	/*
	 * First of all, decide if this is a 486 or higher
	 * It's a 486 if we can modify the AC flag
	 */
	if (flag_is_changeable_p(X86_EFLAGS_AC))
		c->x86 = 4;
	else
		c->x86 = 3;

	for (i = 0; i < X86_VENDOR_NUM; i++)
		if (cpu_devs[i] && cpu_devs[i]->c_identify) {
			c->x86_vendor_id[0] = 0;
			cpu_devs[i]->c_identify(c);
			if (c->x86_vendor_id[0]) {
				get_cpu_vendor(c);
				break;
			}
		}
#endif
}

/*
 * Do minimum CPU detection early.
 * Fields really needed: vendor, cpuid_level, family, model, mask,
 * cache alignment.
 * The others are not touched to avoid unwanted side effects.
 *
 * WARNING: this function is only called on the BP.  Don't add code here
 * that is supposed to run on all CPUs.
 */
static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_64
	c->x86_clflush_size = 64;
	c->x86_phys_bits = 36;
	c->x86_virt_bits = 48;
#else
	c->x86_clflush_size = 32;
	c->x86_phys_bits = 32;
	c->x86_virt_bits = 32;
#endif
	c->x86_cache_alignment = c->x86_clflush_size;

	memset(&c->x86_capability, 0, sizeof c->x86_capability);
	c->extended_cpuid_level = 0;

	if (!have_cpuid_p())
		identify_cpu_without_cpuid(c);

	/* cyrix could have cpuid enabled via c_identify()*/
808
809
810
811
	if (have_cpuid_p()) {
		cpu_detect(c);
		get_cpu_vendor(c);
		get_cpu_cap(c);
812

813
814
		if (this_cpu->c_early_init)
			this_cpu->c_early_init(c);
815

816
817
		c->cpu_index = 0;
		filter_cpuid_features(c, false);
818

819
820
821
		if (this_cpu->c_bsp_init)
			this_cpu->c_bsp_init(c);
	}
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

	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
	fpu__init_system(c);
}

void __init early_cpu_init(void)
{
	const struct cpu_dev *const *cdev;
	int count = 0;

#ifdef CONFIG_PROCESSOR_SELECT
	pr_info("KERNEL supported cpus:\n");
#endif

	for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
		const struct cpu_dev *cpudev = *cdev;

		if (count >= X86_VENDOR_NUM)
			break;
		cpu_devs[count] = cpudev;
		count++;

#ifdef CONFIG_PROCESSOR_SELECT
		{
			unsigned int j;

			for (j = 0; j < 2; j++) {
				if (!cpudev->c_ident[j])
					continue;
				pr_info("  %s %s\n", cpudev->c_vendor,
					cpudev->c_ident[j]);
			}
		}
#endif
	}
	early_identify_cpu(&boot_cpu_data);
}

/*
 * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
 * unfortunately, that's not true in practice because of early VIA
 * chips and (more importantly) broken virtualizers that are not easy
 * to detect. In the latter case it doesn't even *fail* reliably, so
 * probing for it doesn't even work. Disable it completely on 32-bit
 * unless we can find a reliable way to detect all the broken cases.
 * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
 */
static void detect_nopl(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
	clear_cpu_cap(c, X86_FEATURE_NOPL);
#else
	set_cpu_cap(c, X86_FEATURE_NOPL);
#endif
}

static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_64
	/*
	 * Empirically, writing zero to a segment selector on AMD does
	 * not clear the base, whereas writing zero to a segment
	 * selector on Intel does clear the base.  Intel's behavior
	 * allows slightly faster context switches in the common case
	 * where GS is unused by the prev and next threads.
	 *
	 * Since neither vendor documents this anywhere that I can see,
	 * detect it directly instead of hardcoding the choice by
	 * vendor.
	 *
	 * I've designated AMD's behavior as the "bug" because it's
	 * counterintuitive and less friendly.
	 */

	unsigned long old_base, tmp;
	rdmsrl(MSR_FS_BASE, old_base);
	wrmsrl(MSR_FS_BASE, 1);
	loadsegment(fs, 0);
	rdmsrl(MSR_FS_BASE, tmp);
	if (tmp != 0)
		set_cpu_bug(c, X86_BUG_NULL_SEG);
	wrmsrl(MSR_FS_BASE, old_base);
#endif
}

static void generic_identify(struct cpuinfo_x86 *c)
{
	c->extended_cpuid_level = 0;

	if (!have_cpuid_p())
		identify_cpu_without_cpuid(c);

	/* cyrix could have cpuid enabled via c_identify()*/
	if (!have_cpuid_p())
		return;

	cpu_detect(c);

	get_cpu_vendor(c);

	get_cpu_cap(c);

	if (c->cpuid_level >= 0x00000001) {
		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
# ifdef CONFIG_SMP
		c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
# else
		c->apicid = c->initial_apicid;
# endif
#endif
		c->phys_proc_id = c->initial_apicid;
	}

	get_model_name(c); /* Default name */

	detect_nopl(c);

	detect_null_seg_behavior(c);

	/*
	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
	 * systems that run Linux at CPL > 0 may or may not have the
	 * issue, but, even if they have the issue, there's absolutely
	 * nothing we can do about it because we can't use the real IRET
	 * instruction.
	 *
	 * NB: For the time being, only 32-bit kernels support
	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
	 * whether to apply espfix using paravirt hooks.  If any
	 * non-paravirt system ever shows up that does *not* have the
	 * ESPFIX issue, we can change this.
	 */
#ifdef CONFIG_X86_32
# ifdef CONFIG_PARAVIRT
	do {
		extern void native_iret(void);
		if (pv_cpu_ops.iret == native_iret)
			set_cpu_bug(c, X86_BUG_ESPFIX);
	} while (0);
# else
	set_cpu_bug(c, X86_BUG_ESPFIX);
# endif
#endif
}

static void x86_init_cache_qos(struct cpuinfo_x86 *c)
{
	/*
	 * The heavy lifting of max_rmid and cache_occ_scale are handled
	 * in get_cpu_cap().  Here we just set the max_rmid for the boot_cpu
	 * in case CQM bits really aren't there in this CPU.
	 */
	if (c != &boot_cpu_data) {
		boot_cpu_data.x86_cache_max_rmid =
			min(boot_cpu_data.x86_cache_max_rmid,
			    c->x86_cache_max_rmid);
	}
}

982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
 * Validate that ACPI/mptables have the same information about the
 * effective APIC id and update the package map.
 */
static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
	unsigned int apicid, cpu = smp_processor_id();

	apicid = apic->cpu_present_to_apicid(cpu);

	if (apicid != c->apicid) {
		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
		       cpu, apicid, c->initial_apicid);
	}
	BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
#else
	c->logical_proc_id = 0;
#endif