1// SPDX-License-Identifier: GPL-2.0-only
2/* cpu_feature_enabled() cannot be used this early */
3#define USE_EARLY_PGTABLE_L5
4
5#include <linux/memblock.h>
6#include <linux/linkage.h>
7#include <linux/bitops.h>
8#include <linux/kernel.h>
9#include <linux/export.h>
10#include <linux/percpu.h>
11#include <linux/string.h>
12#include <linux/ctype.h>
13#include <linux/delay.h>
14#include <linux/sched/mm.h>
15#include <linux/sched/clock.h>
16#include <linux/sched/task.h>
17#include <linux/sched/smt.h>
18#include <linux/init.h>
19#include <linux/kprobes.h>
20#include <linux/kgdb.h>
21#include <linux/mem_encrypt.h>
22#include <linux/smp.h>
23#include <linux/cpu.h>
24#include <linux/io.h>
25#include <linux/syscore_ops.h>
26#include <linux/pgtable.h>
27#include <linux/utsname.h>
28
29#include <asm/alternative.h>
30#include <asm/cmdline.h>
31#include <asm/stackprotector.h>
32#include <asm/perf_event.h>
33#include <asm/mmu_context.h>
34#include <asm/doublefault.h>
35#include <asm/archrandom.h>
36#include <asm/hypervisor.h>
37#include <asm/processor.h>
38#include <asm/tlbflush.h>
39#include <asm/debugreg.h>
40#include <asm/sections.h>
41#include <asm/vsyscall.h>
42#include <linux/topology.h>
43#include <linux/cpumask.h>
44#include <linux/atomic.h>
45#include <asm/proto.h>
46#include <asm/setup.h>
47#include <asm/apic.h>
48#include <asm/desc.h>
49#include <asm/fpu/internal.h>
50#include <asm/mtrr.h>
51#include <asm/hwcap2.h>
52#include <linux/numa.h>
53#include <asm/numa.h>
54#include <asm/asm.h>
55#include <asm/bugs.h>
56#include <asm/cpu.h>
57#include <asm/mce.h>
58#include <asm/msr.h>
59#include <asm/memtype.h>
60#include <asm/microcode.h>
61#include <asm/microcode_intel.h>
62#include <asm/intel-family.h>
63#include <asm/cpu_device_id.h>
64#include <asm/uv/uv.h>
65#include <asm/set_memory.h>
66
67#include "cpu.h"
68
69u32 elf_hwcap2 __read_mostly;
70
71/* all of these masks are initialized in setup_cpu_local_masks() */
72cpumask_var_t cpu_initialized_mask;
73cpumask_var_t cpu_callout_mask;
74cpumask_var_t cpu_callin_mask;
75
76/* representing cpus for which sibling maps can be computed */
77cpumask_var_t cpu_sibling_setup_mask;
78
79/* Number of siblings per CPU package */
80int smp_num_siblings = 1;
81EXPORT_SYMBOL(smp_num_siblings);
82
83/* Last level cache ID of each logical CPU */
84DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
85
86/* correctly size the local cpu masks */
87void __init setup_cpu_local_masks(void)
88{
89	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
90	alloc_bootmem_cpumask_var(&cpu_callin_mask);
91	alloc_bootmem_cpumask_var(&cpu_callout_mask);
92	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
93}
94
95static void default_init(struct cpuinfo_x86 *c)
96{
97#ifdef CONFIG_X86_64
98	cpu_detect_cache_sizes(c);
99#else
100	/* Not much we can do here... */
101	/* Check if at least it has cpuid */
102	if (c->cpuid_level == -1) {
103		/* No cpuid. It must be an ancient CPU */
104		if (c->x86 == 4)
105			strcpy(c->x86_model_id, "486");
106		else if (c->x86 == 3)
107			strcpy(c->x86_model_id, "386");
108	}
109#endif
110}
111
112static const struct cpu_dev default_cpu = {
113	.c_init		= default_init,
114	.c_vendor	= "Unknown",
115	.c_x86_vendor	= X86_VENDOR_UNKNOWN,
116};
117
118static const struct cpu_dev *this_cpu = &default_cpu;
119
120DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
121#ifdef CONFIG_X86_64
122	/*
123	 * We need valid kernel segments for data and code in long mode too
124	 * IRET will check the segment types  kkeil 2000/10/28
125	 * Also sysret mandates a special GDT layout
126	 *
127	 * TLS descriptors are currently at a different place compared to i386.
128	 * Hopefully nobody expects them at a fixed place (Wine?)
129	 */
130	[GDT_ENTRY_KERNEL32_CS]		= GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
131	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
132	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
133	[GDT_ENTRY_DEFAULT_USER32_CS]	= GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff),
134	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff),
135	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff),
136#else
137	[GDT_ENTRY_KERNEL_CS]		= GDT_ENTRY_INIT(0xc09a, 0, 0xfffff),
138	[GDT_ENTRY_KERNEL_DS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
139	[GDT_ENTRY_DEFAULT_USER_CS]	= GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff),
140	[GDT_ENTRY_DEFAULT_USER_DS]	= GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff),
141	/*
142	 * Segments used for calling PnP BIOS have byte granularity.
143	 * They code segments and data segments have fixed 64k limits,
144	 * the transfer segment sizes are set at run time.
145	 */
146	/* 32-bit code */
147	[GDT_ENTRY_PNPBIOS_CS32]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
148	/* 16-bit code */
149	[GDT_ENTRY_PNPBIOS_CS16]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
150	/* 16-bit data */
151	[GDT_ENTRY_PNPBIOS_DS]		= GDT_ENTRY_INIT(0x0092, 0, 0xffff),
152	/* 16-bit data */
153	[GDT_ENTRY_PNPBIOS_TS1]		= GDT_ENTRY_INIT(0x0092, 0, 0),
154	/* 16-bit data */
155	[GDT_ENTRY_PNPBIOS_TS2]		= GDT_ENTRY_INIT(0x0092, 0, 0),
156	/*
157	 * The APM segments have byte granularity and their bases
158	 * are set at run time.  All have 64k limits.
159	 */
160	/* 32-bit code */
161	[GDT_ENTRY_APMBIOS_BASE]	= GDT_ENTRY_INIT(0x409a, 0, 0xffff),
162	/* 16-bit code */
163	[GDT_ENTRY_APMBIOS_BASE+1]	= GDT_ENTRY_INIT(0x009a, 0, 0xffff),
164	/* data */
165	[GDT_ENTRY_APMBIOS_BASE+2]	= GDT_ENTRY_INIT(0x4092, 0, 0xffff),
166
167	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
168	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
169	GDT_STACK_CANARY_INIT
170#endif
171} };
172EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
173
174#ifdef CONFIG_X86_64
175static int __init x86_nopcid_setup(char *s)
176{
177	/* nopcid doesn't accept parameters */
178	if (s)
179		return -EINVAL;
180
181	/* do not emit a message if the feature is not present */
182	if (!boot_cpu_has(X86_FEATURE_PCID))
183		return 0;
184
185	setup_clear_cpu_cap(X86_FEATURE_PCID);
186	pr_info("nopcid: PCID feature disabled\n");
187	return 0;
188}
189early_param("nopcid", x86_nopcid_setup);
190#endif
191
192static int __init x86_noinvpcid_setup(char *s)
193{
194	/* noinvpcid doesn't accept parameters */
195	if (s)
196		return -EINVAL;
197
198	/* do not emit a message if the feature is not present */
199	if (!boot_cpu_has(X86_FEATURE_INVPCID))
200		return 0;
201
202	setup_clear_cpu_cap(X86_FEATURE_INVPCID);
203	pr_info("noinvpcid: INVPCID feature disabled\n");
204	return 0;
205}
206early_param("noinvpcid", x86_noinvpcid_setup);
207
208#ifdef CONFIG_X86_32
209static int cachesize_override = -1;
210static int disable_x86_serial_nr = 1;
211
212static int __init cachesize_setup(char *str)
213{
214	get_option(&str, &cachesize_override);
215	return 1;
216}
217__setup("cachesize=", cachesize_setup);
218
219static int __init x86_sep_setup(char *s)
220{
221	setup_clear_cpu_cap(X86_FEATURE_SEP);
222	return 1;
223}
224__setup("nosep", x86_sep_setup);
225
226/* Standard macro to see if a specific flag is changeable */
227static inline int flag_is_changeable_p(u32 flag)
228{
229	u32 f1, f2;
230
231	/*
232	 * Cyrix and IDT cpus allow disabling of CPUID
233	 * so the code below may return different results
234	 * when it is executed before and after enabling
235	 * the CPUID. Add "volatile" to not allow gcc to
236	 * optimize the subsequent calls to this function.
237	 */
238	asm volatile ("pushfl		\n\t"
239		      "pushfl		\n\t"
240		      "popl %0		\n\t"
241		      "movl %0, %1	\n\t"
242		      "xorl %2, %0	\n\t"
243		      "pushl %0		\n\t"
244		      "popfl		\n\t"
245		      "pushfl		\n\t"
246		      "popl %0		\n\t"
247		      "popfl		\n\t"
248
249		      : "=&r" (f1), "=&r" (f2)
250		      : "ir" (flag));
251
252	return ((f1^f2) & flag) != 0;
253}
254
255/* Probe for the CPUID instruction */
256int have_cpuid_p(void)
257{
258	return flag_is_changeable_p(X86_EFLAGS_ID);
259}
260
261static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
262{
263	unsigned long lo, hi;
264
265	if (!cpu_has(c, X86_FEATURE_PN) || !disable_x86_serial_nr)
266		return;
267
268	/* Disable processor serial number: */
269
270	rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
271	lo |= 0x200000;
272	wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
273
274	pr_notice("CPU serial number disabled.\n");
275	clear_cpu_cap(c, X86_FEATURE_PN);
276
277	/* Disabling the serial number may affect the cpuid level */
278	c->cpuid_level = cpuid_eax(0);
279}
280
281static int __init x86_serial_nr_setup(char *s)
282{
283	disable_x86_serial_nr = 0;
284	return 1;
285}
286__setup("serialnumber", x86_serial_nr_setup);
287#else
288static inline int flag_is_changeable_p(u32 flag)
289{
290	return 1;
291}
292static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
293{
294}
295#endif
296
297static __init int setup_disable_smep(char *arg)
298{
299	setup_clear_cpu_cap(X86_FEATURE_SMEP);
300	return 1;
301}
302__setup("nosmep", setup_disable_smep);
303
304static __always_inline void setup_smep(struct cpuinfo_x86 *c)
305{
306	if (cpu_has(c, X86_FEATURE_SMEP))
307		cr4_set_bits(X86_CR4_SMEP);
308}
309
310static __init int setup_disable_smap(char *arg)
311{
312	setup_clear_cpu_cap(X86_FEATURE_SMAP);
313	return 1;
314}
315__setup("nosmap", setup_disable_smap);
316
317static __always_inline void setup_smap(struct cpuinfo_x86 *c)
318{
319	unsigned long eflags = native_save_fl();
320
321	/* This should have been cleared long ago */
322	BUG_ON(eflags & X86_EFLAGS_AC);
323
324	if (cpu_has(c, X86_FEATURE_SMAP)) {
325#ifdef CONFIG_X86_SMAP
326		cr4_set_bits(X86_CR4_SMAP);
327#else
328		clear_cpu_cap(c, X86_FEATURE_SMAP);
329		cr4_clear_bits(X86_CR4_SMAP);
330#endif
331	}
332}
333
334static __always_inline void setup_umip(struct cpuinfo_x86 *c)
335{
336	/* Check the boot processor, plus build option for UMIP. */
337	if (!cpu_feature_enabled(X86_FEATURE_UMIP))
338		goto out;
339
340	/* Check the current processor's cpuid bits. */
341	if (!cpu_has(c, X86_FEATURE_UMIP))
342		goto out;
343
344	cr4_set_bits(X86_CR4_UMIP);
345
346	pr_info_once("x86/cpu: User Mode Instruction Prevention (UMIP) activated\n");
347
348	return;
349
350out:
351	/*
352	 * Make sure UMIP is disabled in case it was enabled in a
353	 * previous boot (e.g., via kexec).
354	 */
355	cr4_clear_bits(X86_CR4_UMIP);
356}
357
358/* These bits should not change their value after CPU init is finished. */
359static const unsigned long cr4_pinned_mask =
360	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
361static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
362static unsigned long cr4_pinned_bits __ro_after_init;
363
364void native_write_cr0(unsigned long val)
365{
366	unsigned long bits_missing = 0;
367
368set_register:
369	asm volatile("mov %0,%%cr0": "+r" (val) : : "memory");
370
371	if (static_branch_likely(&cr_pinning)) {
372		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
373			bits_missing = X86_CR0_WP;
374			val |= bits_missing;
375			goto set_register;
376		}
377		/* Warn after we've set the missing bits. */
378		WARN_ONCE(bits_missing, "CR0 WP bit went missing!?\n");
379	}
380}
381EXPORT_SYMBOL(native_write_cr0);
382
383void native_write_cr4(unsigned long val)
384{
385	unsigned long bits_changed = 0;
386
387set_register:
388	asm volatile("mov %0,%%cr4": "+r" (val) : : "memory");
389
390	if (static_branch_likely(&cr_pinning)) {
391		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
392			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
393			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
394			goto set_register;
395		}
396		/* Warn after we've corrected the changed bits. */
397		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
398			  bits_changed);
399	}
400}
401#if IS_MODULE(CONFIG_LKDTM)
402EXPORT_SYMBOL_GPL(native_write_cr4);
403#endif
404
405void cr4_update_irqsoff(unsigned long set, unsigned long clear)
406{
407	unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4);
408
409	lockdep_assert_irqs_disabled();
410
411	newval = (cr4 & ~clear) | set;
412	if (newval != cr4) {
413		this_cpu_write(cpu_tlbstate.cr4, newval);
414		__write_cr4(newval);
415	}
416}
417EXPORT_SYMBOL(cr4_update_irqsoff);
418
419/* Read the CR4 shadow. */
420unsigned long cr4_read_shadow(void)
421{
422	return this_cpu_read(cpu_tlbstate.cr4);
423}
424EXPORT_SYMBOL_GPL(cr4_read_shadow);
425
426void cr4_init(void)
427{
428	unsigned long cr4 = __read_cr4();
429
430	if (boot_cpu_has(X86_FEATURE_PCID))
431		cr4 |= X86_CR4_PCIDE;
432	if (static_branch_likely(&cr_pinning))
433		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
434
435	__write_cr4(cr4);
436
437	/* Initialize cr4 shadow for this CPU. */
438	this_cpu_write(cpu_tlbstate.cr4, cr4);
439}
440
441/*
442 * Once CPU feature detection is finished (and boot params have been
443 * parsed), record any of the sensitive CR bits that are set, and
444 * enable CR pinning.
445 */
446static void __init setup_cr_pinning(void)
447{
448	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
449	static_key_enable(&cr_pinning.key);
450}
451
452static __init int x86_nofsgsbase_setup(char *arg)
453{
454	/* Require an exact match without trailing characters. */
455	if (strlen(arg))
456		return 0;
457
458	/* Do not emit a message if the feature is not present. */
459	if (!boot_cpu_has(X86_FEATURE_FSGSBASE))
460		return 1;
461
462	setup_clear_cpu_cap(X86_FEATURE_FSGSBASE);
463	pr_info("FSGSBASE disabled via kernel command line\n");
464	return 1;
465}
466__setup("nofsgsbase", x86_nofsgsbase_setup);
467
468/*
469 * Protection Keys are not available in 32-bit mode.
470 */
471static bool pku_disabled;
472
473static __always_inline void setup_pku(struct cpuinfo_x86 *c)
474{
475	/* check the boot processor, plus compile options for PKU: */
476	if (!cpu_feature_enabled(X86_FEATURE_PKU))
477		return;
478	/* checks the actual processor's cpuid bits: */
479	if (!cpu_has(c, X86_FEATURE_PKU))
480		return;
481	if (pku_disabled)
482		return;
483
484	cr4_set_bits(X86_CR4_PKE);
485	/*
486	 * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
487	 * cpuid bit to be set.  We need to ensure that we
488	 * update that bit in this CPU's "cpu_info".
489	 */
490	set_cpu_cap(c, X86_FEATURE_OSPKE);
491}
492
493#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
494static __init int setup_disable_pku(char *arg)
495{
496	/*
497	 * Do not clear the X86_FEATURE_PKU bit.  All of the
498	 * runtime checks are against OSPKE so clearing the
499	 * bit does nothing.
500	 *
501	 * This way, we will see "pku" in cpuinfo, but not
502	 * "ospke", which is exactly what we want.  It shows
503	 * that the CPU has PKU, but the OS has not enabled it.
504	 * This happens to be exactly how a system would look
505	 * if we disabled the config option.
506	 */
507	pr_info("x86: 'nopku' specified, disabling Memory Protection Keys\n");
508	pku_disabled = true;
509	return 1;
510}
511__setup("nopku", setup_disable_pku);
512#endif /* CONFIG_X86_64 */
513
514/*
515 * Some CPU features depend on higher CPUID levels, which may not always
516 * be available due to CPUID level capping or broken virtualization
517 * software.  Add those features to this table to auto-disable them.
518 */
519struct cpuid_dependent_feature {
520	u32 feature;
521	u32 level;
522};
523
524static const struct cpuid_dependent_feature
525cpuid_dependent_features[] = {
526	{ X86_FEATURE_MWAIT,		0x00000005 },
527	{ X86_FEATURE_DCA,		0x00000009 },
528	{ X86_FEATURE_XSAVE,		0x0000000d },
529	{ 0, 0 }
530};
531
532static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
533{
534	const struct cpuid_dependent_feature *df;
535
536	for (df = cpuid_dependent_features; df->feature; df++) {
537
538		if (!cpu_has(c, df->feature))
539			continue;
540		/*
541		 * Note: cpuid_level is set to -1 if unavailable, but
542		 * extended_extended_level is set to 0 if unavailable
543		 * and the legitimate extended levels are all negative
544		 * when signed; hence the weird messing around with
545		 * signs here...
546		 */
547		if (!((s32)df->level < 0 ?
548		     (u32)df->level > (u32)c->extended_cpuid_level :
549		     (s32)df->level > (s32)c->cpuid_level))
550			continue;
551
552		clear_cpu_cap(c, df->feature);
553		if (!warn)
554			continue;
555
556		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
557			x86_cap_flag(df->feature), df->level);
558	}
559}
560
561/*
562 * Naming convention should be: <Name> [(<Codename>)]
563 * This table only is used unless init_<vendor>() below doesn't set it;
564 * in particular, if CPUID levels 0x80000002..4 are supported, this
565 * isn't used
566 */
567
568/* Look up CPU names by table lookup. */
569static const char *table_lookup_model(struct cpuinfo_x86 *c)
570{
571#ifdef CONFIG_X86_32
572	const struct legacy_cpu_model_info *info;
573
574	if (c->x86_model >= 16)
575		return NULL;	/* Range check */
576
577	if (!this_cpu)
578		return NULL;
579
580	info = this_cpu->legacy_models;
581
582	while (info->family) {
583		if (info->family == c->x86)
584			return info->model_names[c->x86_model];
585		info++;
586	}
587#endif
588	return NULL;		/* Not found */
589}
590
591/* Aligned to unsigned long to avoid split lock in atomic bitmap ops */
592__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
593__u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
594
595void load_percpu_segment(int cpu)
596{
597#ifdef CONFIG_X86_32
598	loadsegment(fs, __KERNEL_PERCPU);
599#else
600	__loadsegment_simple(gs, 0);
601	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
602#endif
603	load_stack_canary_segment();
604}
605
606#ifdef CONFIG_X86_32
607/* The 32-bit entry code needs to find cpu_entry_area. */
608DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
609#endif
610
611/* Load the original GDT from the per-cpu structure */
612void load_direct_gdt(int cpu)
613{
614	struct desc_ptr gdt_descr;
615
616	gdt_descr.address = (long)get_cpu_gdt_rw(cpu);
617	gdt_descr.size = GDT_SIZE - 1;
618	load_gdt(&gdt_descr);
619}
620EXPORT_SYMBOL_GPL(load_direct_gdt);
621
622/* Load a fixmap remapping of the per-cpu GDT */
623void load_fixmap_gdt(int cpu)
624{
625	struct desc_ptr gdt_descr;
626
627	gdt_descr.address = (long)get_cpu_gdt_ro(cpu);
628	gdt_descr.size = GDT_SIZE - 1;
629	load_gdt(&gdt_descr);
630}
631EXPORT_SYMBOL_GPL(load_fixmap_gdt);
632
633/*
634 * Current gdt points %fs at the "master" per-cpu area: after this,
635 * it's on the real one.
636 */
637void switch_to_new_gdt(int cpu)
638{
639	/* Load the original GDT */
640	load_direct_gdt(cpu);
641	/* Reload the per-cpu base */
642	load_percpu_segment(cpu);
643}
644
645static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
646
647static void get_model_name(struct cpuinfo_x86 *c)
648{
649	unsigned int *v;
650	char *p, *q, *s;
651
652	if (c->extended_cpuid_level < 0x80000004)
653		return;
654
655	v = (unsigned int *)c->x86_model_id;
656	cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
657	cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
658	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
659	c->x86_model_id[48] = 0;
660
661	/* Trim whitespace */
662	p = q = s = &c->x86_model_id[0];
663
664	while (*p == ' ')
665		p++;
666
667	while (*p) {
668		/* Note the last non-whitespace index */
669		if (!isspace(*p))
670			s = q;
671
672		*q++ = *p++;
673	}
674
675	*(s + 1) = '\0';
676}
677
678void detect_num_cpu_cores(struct cpuinfo_x86 *c)
679{
680	unsigned int eax, ebx, ecx, edx;
681
682	c->x86_max_cores = 1;
683	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
684		return;
685
686	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
687	if (eax & 0x1f)
688		c->x86_max_cores = (eax >> 26) + 1;
689}
690
691void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
692{
693	unsigned int n, dummy, ebx, ecx, edx, l2size;
694
695	n = c->extended_cpuid_level;
696
697	if (n >= 0x80000005) {
698		cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
699		c->x86_cache_size = (ecx>>24) + (edx>>24);
700#ifdef CONFIG_X86_64
701		/* On K8 L1 TLB is inclusive, so don't count it */
702		c->x86_tlbsize = 0;
703#endif
704	}
705
706	if (n < 0x80000006)	/* Some chips just has a large L1. */
707		return;
708
709	cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
710	l2size = ecx >> 16;
711
712#ifdef CONFIG_X86_64
713	c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
714#else
715	/* do processor-specific cache resizing */
716	if (this_cpu->legacy_cache_size)
717		l2size = this_cpu->legacy_cache_size(c, l2size);
718
719	/* Allow user to override all this if necessary. */
720	if (cachesize_override != -1)
721		l2size = cachesize_override;
722
723	if (l2size == 0)
724		return;		/* Again, no L2 cache is possible */
725#endif
726
727	c->x86_cache_size = l2size;
728}
729
730u16 __read_mostly tlb_lli_4k[NR_INFO];
731u16 __read_mostly tlb_lli_2m[NR_INFO];
732u16 __read_mostly tlb_lli_4m[NR_INFO];
733u16 __read_mostly tlb_lld_4k[NR_INFO];
734u16 __read_mostly tlb_lld_2m[NR_INFO];
735u16 __read_mostly tlb_lld_4m[NR_INFO];
736u16 __read_mostly tlb_lld_1g[NR_INFO];
737
738static void cpu_detect_tlb(struct cpuinfo_x86 *c)
739{
740	if (this_cpu->c_detect_tlb)
741		this_cpu->c_detect_tlb(c);
742
743	pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
744		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
745		tlb_lli_4m[ENTRIES]);
746
747	pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
748		tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
749		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
750}
751
752int detect_ht_early(struct cpuinfo_x86 *c)
753{
754#ifdef CONFIG_SMP
755	u32 eax, ebx, ecx, edx;
756
757	if (!cpu_has(c, X86_FEATURE_HT))
758		return -1;
759
760	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
761		return -1;
762
763	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
764		return -1;
765
766	cpuid(1, &eax, &ebx, &ecx, &edx);
767
768	smp_num_siblings = (ebx & 0xff0000) >> 16;
769	if (smp_num_siblings == 1)
770		pr_info_once("CPU0: Hyper-Threading is disabled\n");
771#endif
772	return 0;
773}
774
775void detect_ht(struct cpuinfo_x86 *c)
776{
777#ifdef CONFIG_SMP
778	int index_msb, core_bits;
779
780	if (detect_ht_early(c) < 0)
781		return;
782
783	index_msb = get_count_order(smp_num_siblings);
784	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
785
786	smp_num_siblings = smp_num_siblings / c->x86_max_cores;
787
788	index_msb = get_count_order(smp_num_siblings);
789
790	core_bits = get_count_order(c->x86_max_cores);
791
792	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
793				       ((1 << core_bits) - 1);
794#endif
795}
796
797static void get_cpu_vendor(struct cpuinfo_x86 *c)
798{
799	char *v = c->x86_vendor_id;
800	int i;
801
802	for (i = 0; i < X86_VENDOR_NUM; i++) {
803		if (!cpu_devs[i])
804			break;
805
806		if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
807		    (cpu_devs[i]->c_ident[1] &&
808		     !strcmp(v, cpu_devs[i]->c_ident[1]))) {
809
810			this_cpu = cpu_devs[i];
811			c->x86_vendor = this_cpu->c_x86_vendor;
812			return;
813		}
814	}
815
816	pr_err_once("CPU: vendor_id '%s' unknown, using generic init.\n" \
817		    "CPU: Your system may be unstable.\n", v);
818
819	c->x86_vendor = X86_VENDOR_UNKNOWN;
820	this_cpu = &default_cpu;
821}
822
823void cpu_detect(struct cpuinfo_x86 *c)
824{
825	/* Get vendor name */
826	cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
827	      (unsigned int *)&c->x86_vendor_id[0],
828	      (unsigned int *)&c->x86_vendor_id[8],
829	      (unsigned int *)&c->x86_vendor_id[4]);
830
831	c->x86 = 4;
832	/* Intel-defined flags: level 0x00000001 */
833	if (c->cpuid_level >= 0x00000001) {
834		u32 junk, tfms, cap0, misc;
835
836		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
837		c->x86		= x86_family(tfms);
838		c->x86_model	= x86_model(tfms);
839		c->x86_stepping	= x86_stepping(tfms);
840
841		if (cap0 & (1<<19)) {
842			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
843			c->x86_cache_alignment = c->x86_clflush_size;
844		}
845	}
846}
847
848static void apply_forced_caps(struct cpuinfo_x86 *c)
849{
850	int i;
851
852	for (i = 0; i < NCAPINTS + NBUGINTS; i++) {
853		c->x86_capability[i] &= ~cpu_caps_cleared[i];
854		c->x86_capability[i] |= cpu_caps_set[i];
855	}
856}
857
858static void init_speculation_control(struct cpuinfo_x86 *c)
859{
860	/*
861	 * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
862	 * and they also have a different bit for STIBP support. Also,
863	 * a hypervisor might have set the individual AMD bits even on
864	 * Intel CPUs, for finer-grained selection of what's available.
865	 */
866	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
867		set_cpu_cap(c, X86_FEATURE_IBRS);
868		set_cpu_cap(c, X86_FEATURE_IBPB);
869		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
870	}
871
872	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
873		set_cpu_cap(c, X86_FEATURE_STIBP);
874
875	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
876	    cpu_has(c, X86_FEATURE_VIRT_SSBD))
877		set_cpu_cap(c, X86_FEATURE_SSBD);
878
879	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
880		set_cpu_cap(c, X86_FEATURE_IBRS);
881		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
882	}
883
884	if (cpu_has(c, X86_FEATURE_AMD_IBPB))
885		set_cpu_cap(c, X86_FEATURE_IBPB);
886
887	if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
888		set_cpu_cap(c, X86_FEATURE_STIBP);
889		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
890	}
891
892	if (cpu_has(c, X86_FEATURE_AMD_SSBD)) {
893		set_cpu_cap(c, X86_FEATURE_SSBD);
894		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
895		clear_cpu_cap(c, X86_FEATURE_VIRT_SSBD);
896	}
897}
898
899void get_cpu_cap(struct cpuinfo_x86 *c)
900{
901	u32 eax, ebx, ecx, edx;
902
903	/* Intel-defined flags: level 0x00000001 */
904	if (c->cpuid_level >= 0x00000001) {
905		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
906
907		c->x86_capability[CPUID_1_ECX] = ecx;
908		c->x86_capability[CPUID_1_EDX] = edx;
909	}
910
911	/* Thermal and Power Management Leaf: level 0x00000006 (eax) */
912	if (c->cpuid_level >= 0x00000006)
913		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
914
915	/* Additional Intel-defined flags: level 0x00000007 */
916	if (c->cpuid_level >= 0x00000007) {
917		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
918		c->x86_capability[CPUID_7_0_EBX] = ebx;
919		c->x86_capability[CPUID_7_ECX] = ecx;
920		c->x86_capability[CPUID_7_EDX] = edx;
921
922		/* Check valid sub-leaf index before accessing it */
923		if (eax >= 1) {
924			cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
925			c->x86_capability[CPUID_7_1_EAX] = eax;
926		}
927	}
928
929	/* Extended state features: level 0x0000000d */
930	if (c->cpuid_level >= 0x0000000d) {
931		cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);
932
933		c->x86_capability[CPUID_D_1_EAX] = eax;
934	}
935
936	/* AMD-defined flags: level 0x80000001 */
937	eax = cpuid_eax(0x80000000);
938	c->extended_cpuid_level = eax;
939
940	if ((eax & 0xffff0000) == 0x80000000) {
941		if (eax >= 0x80000001) {
942			cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
943
944			c->x86_capability[CPUID_8000_0001_ECX] = ecx;
945			c->x86_capability[CPUID_8000_0001_EDX] = edx;
946		}
947	}
948
949	if (c->extended_cpuid_level >= 0x80000007) {
950		cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
951
952		c->x86_capability[CPUID_8000_0007_EBX] = ebx;
953		c->x86_power = edx;
954	}
955
956	if (c->extended_cpuid_level >= 0x80000008) {
957		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
958		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
959	}
960
961	if (c->extended_cpuid_level >= 0x8000000a)
962		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
963
964	if (c->extended_cpuid_level >= 0x8000001f)
965		c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f);
966
967	if (c->extended_cpuid_level >= 0x80000021)
968		c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021);
969
970	init_scattered_cpuid_features(c);
971	init_speculation_control(c);
972
973	/*
974	 * Clear/Set all flags overridden by options, after probe.
975	 * This needs to happen each time we re-probe, which may happen
976	 * several times during CPU initialization.
977	 */
978	apply_forced_caps(c);
979}
980
981void get_cpu_address_sizes(struct cpuinfo_x86 *c)
982{
983	u32 eax, ebx, ecx, edx;
984
985	if (c->extended_cpuid_level >= 0x80000008) {
986		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
987
988		c->x86_virt_bits = (eax >> 8) & 0xff;
989		c->x86_phys_bits = eax & 0xff;
990	}
991#ifdef CONFIG_X86_32
992	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
993		c->x86_phys_bits = 36;
994#endif
995	c->x86_cache_bits = c->x86_phys_bits;
996}
997
998static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
999{
1000#ifdef CONFIG_X86_32
1001	int i;
1002
1003	/*
1004	 * First of all, decide if this is a 486 or higher
1005	 * It's a 486 if we can modify the AC flag
1006	 */
1007	if (flag_is_changeable_p(X86_EFLAGS_AC))
1008		c->x86 = 4;
1009	else
1010		c->x86 = 3;
1011
1012	for (i = 0; i < X86_VENDOR_NUM; i++)
1013		if (cpu_devs[i] && cpu_devs[i]->c_identify) {
1014			c->x86_vendor_id[0] = 0;
1015			cpu_devs[i]->c_identify(c);
1016			if (c->x86_vendor_id[0]) {
1017				get_cpu_vendor(c);
1018				break;
1019			}
1020		}
1021#endif
1022}
1023
1024#define NO_SPECULATION		BIT(0)
1025#define NO_MELTDOWN		BIT(1)
1026#define NO_SSB			BIT(2)
1027#define NO_L1TF			BIT(3)
1028#define NO_MDS			BIT(4)
1029#define MSBDS_ONLY		BIT(5)
1030#define NO_SWAPGS		BIT(6)
1031#define NO_ITLB_MULTIHIT	BIT(7)
1032#define NO_SPECTRE_V2		BIT(8)
1033#define NO_MMIO			BIT(9)
1034#define NO_EIBRS_PBRSB		BIT(10)
1035
1036#define VULNWL(vendor, family, model, whitelist)	\
1037	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
1038
1039#define VULNWL_INTEL(model, whitelist)		\
1040	VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
1041
1042#define VULNWL_AMD(family, whitelist)		\
1043	VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
1044
1045#define VULNWL_HYGON(family, whitelist)		\
1046	VULNWL(HYGON, family, X86_MODEL_ANY, whitelist)
1047
1048static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
1049	VULNWL(ANY,	4, X86_MODEL_ANY,	NO_SPECULATION),
1050	VULNWL(CENTAUR,	5, X86_MODEL_ANY,	NO_SPECULATION),
1051	VULNWL(INTEL,	5, X86_MODEL_ANY,	NO_SPECULATION),
1052	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
1053
1054	/* Intel Family 6 */
1055	VULNWL_INTEL(TIGERLAKE,			NO_MMIO),
1056	VULNWL_INTEL(TIGERLAKE_L,		NO_MMIO),
1057	VULNWL_INTEL(ALDERLAKE,			NO_MMIO),
1058	VULNWL_INTEL(ALDERLAKE_L,		NO_MMIO),
1059
1060	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
1061	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION | NO_ITLB_MULTIHIT),
1062	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
1063	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
1064	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
1065
1066	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1067	VULNWL_INTEL(ATOM_SILVERMONT_D,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1068	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1069	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1070	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1071	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1072
1073	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
1074
1075	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
1076	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
1077
1078	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
1079	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
1080	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
1081
1082	/*
1083	 * Technically, swapgs isn't serializing on AMD (despite it previously
1084	 * being documented as such in the APM).  But according to AMD, %gs is
1085	 * updated non-speculatively, and the issuing of %gs-relative memory
1086	 * operands will be blocked until the %gs update completes, which is
1087	 * good enough for our purposes.
1088	 */
1089
1090	VULNWL_INTEL(ATOM_TREMONT,		NO_EIBRS_PBRSB),
1091	VULNWL_INTEL(ATOM_TREMONT_L,		NO_EIBRS_PBRSB),
1092	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
1093
1094	/* AMD Family 0xf - 0x12 */
1095	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
1096	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
1097	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
1098	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
1099
1100	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
1101	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
1102	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
1103
1104	/* Zhaoxin Family 7 */
1105	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
1106	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
1107	{}
1108};
1109
1110#define VULNBL(vendor, family, model, blacklist)	\
1111	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist)
1112
1113#define VULNBL_INTEL_STEPPINGS(model, steppings, issues)		   \
1114	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6,		   \
1115					    INTEL_FAM6_##model, steppings, \
1116					    X86_FEATURE_ANY, issues)
1117
1118#define VULNBL_AMD(family, blacklist)		\
1119	VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
1120
1121#define VULNBL_HYGON(family, blacklist)		\
1122	VULNBL(HYGON, family, X86_MODEL_ANY, blacklist)
1123
1124#define SRBDS		BIT(0)
1125/* CPU is affected by X86_BUG_MMIO_STALE_DATA */
1126#define MMIO		BIT(1)
1127/* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */
1128#define MMIO_SBDS	BIT(2)
1129/* CPU is affected by RETbleed, speculating where you would not expect it */
1130#define RETBLEED	BIT(3)
1131/* CPU is affected by SMT (cross-thread) return predictions */
1132#define SMT_RSB		BIT(4)
1133/* CPU is affected by SRSO */
1134#define SRSO		BIT(5)
1135/* CPU is affected by GDS */
1136#define GDS		BIT(6)
1137/* CPU is affected by Register File Data Sampling */
1138#define RFDS		BIT(7)
1139
1140static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
1141	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
1142	VULNBL_INTEL_STEPPINGS(HASWELL,		X86_STEPPING_ANY,		SRBDS),
1143	VULNBL_INTEL_STEPPINGS(HASWELL_L,	X86_STEPPING_ANY,		SRBDS),
1144	VULNBL_INTEL_STEPPINGS(HASWELL_G,	X86_STEPPING_ANY,		SRBDS),
1145	VULNBL_INTEL_STEPPINGS(HASWELL_X,	X86_STEPPING_ANY,		MMIO),
1146	VULNBL_INTEL_STEPPINGS(BROADWELL_D,	X86_STEPPING_ANY,		MMIO),
1147	VULNBL_INTEL_STEPPINGS(BROADWELL_G,	X86_STEPPING_ANY,		SRBDS),
1148	VULNBL_INTEL_STEPPINGS(BROADWELL_X,	X86_STEPPING_ANY,		MMIO),
1149	VULNBL_INTEL_STEPPINGS(BROADWELL,	X86_STEPPING_ANY,		SRBDS),
1150	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
1151	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS | SRBDS),
1152	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		MMIO | RETBLEED | GDS | SRBDS),
1153	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS | SRBDS),
1154	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS | SRBDS),
1155	VULNBL_INTEL_STEPPINGS(CANNONLAKE_L,	X86_STEPPING_ANY,		RETBLEED),
1156	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
1157	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPING_ANY,		MMIO | GDS),
1158	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPING_ANY,		MMIO | GDS),
1159	VULNBL_INTEL_STEPPINGS(COMETLAKE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
1160	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x0, 0x0),	MMIO | RETBLEED),
1161	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
1162	VULNBL_INTEL_STEPPINGS(TIGERLAKE_L,	X86_STEPPING_ANY,		GDS),
1163	VULNBL_INTEL_STEPPINGS(TIGERLAKE,	X86_STEPPING_ANY,		GDS),
1164	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
1165	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
1166	VULNBL_INTEL_STEPPINGS(ALDERLAKE,	X86_STEPPING_ANY,		RFDS),
1167	VULNBL_INTEL_STEPPINGS(ALDERLAKE_L,	X86_STEPPING_ANY,		RFDS),
1168	VULNBL_INTEL_STEPPINGS(RAPTORLAKE,	X86_STEPPING_ANY,		RFDS),
1169	VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P,	X86_STEPPING_ANY,		RFDS),
1170	VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S,	X86_STEPPING_ANY,		RFDS),
1171	VULNBL_INTEL_STEPPINGS(ALDERLAKE_N,	X86_STEPPING_ANY,		RFDS),
1172	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RFDS),
1173	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO | RFDS),
1174	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RFDS),
1175	VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT,	X86_STEPPING_ANY,		RFDS),
1176	VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D,	X86_STEPPING_ANY,		RFDS),
1177	VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY,		RFDS),
1178
1179	VULNBL_AMD(0x15, RETBLEED),
1180	VULNBL_AMD(0x16, RETBLEED),
1181	VULNBL_AMD(0x17, RETBLEED | SRSO),
1182	VULNBL_HYGON(0x18, RETBLEED),
1183	VULNBL_AMD(0x19, SRSO),
1184	{}
1185};
1186
1187static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which)
1188{
1189	const struct x86_cpu_id *m = x86_match_cpu(table);
1190
1191	return m && !!(m->driver_data & which);
1192}
1193
1194u64 x86_read_arch_cap_msr(void)
1195{
1196	u64 ia32_cap = 0;
1197
1198	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
1199		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
1200
1201	return ia32_cap;
1202}
1203
1204static bool arch_cap_mmio_immune(u64 ia32_cap)
1205{
1206	return (ia32_cap & ARCH_CAP_FBSDP_NO &&
1207		ia32_cap & ARCH_CAP_PSDP_NO &&
1208		ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
1209}
1210
1211static bool __init vulnerable_to_rfds(u64 ia32_cap)
1212{
1213	/* The "immunity" bit trumps everything else: */
1214	if (ia32_cap & ARCH_CAP_RFDS_NO)
1215		return false;
1216
1217	/*
1218	 * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to
1219	 * indicate that mitigation is needed because guest is running on a
1220	 * vulnerable hardware or may migrate to such hardware:
1221	 */
1222	if (ia32_cap & ARCH_CAP_RFDS_CLEAR)
1223		return true;
1224
1225	/* Only consult the blacklist when there is no enumeration: */
1226	return cpu_matches(cpu_vuln_blacklist, RFDS);
1227}
1228
1229static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
1230{
1231	u64 ia32_cap = x86_read_arch_cap_msr();
1232
1233	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
1234	if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
1235	    !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
1236		setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
1237
1238	if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION))
1239		return;
1240
1241	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
1242
1243	if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2))
1244		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
1245
1246	if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
1247	    !(ia32_cap & ARCH_CAP_SSB_NO) &&
1248	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
1249		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
1250
1251	/*
1252	 * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature
1253	 * flag and protect from vendor-specific bugs via the whitelist.
1254	 */
1255	if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) {
1256		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
1257		if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
1258		    !(ia32_cap & ARCH_CAP_PBRSB_NO))
1259			setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
1260	}
1261
1262	if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
1263	    !(ia32_cap & ARCH_CAP_MDS_NO)) {
1264		setup_force_cpu_bug(X86_BUG_MDS);
1265		if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY))
1266			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
1267	}
1268
1269	if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS))
1270		setup_force_cpu_bug(X86_BUG_SWAPGS);
1271
1272	/*
1273	 * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when:
1274	 *	- TSX is supported or
1275	 *	- TSX_CTRL is present
1276	 *
1277	 * TSX_CTRL check is needed for cases when TSX could be disabled before
1278	 * the kernel boot e.g. kexec.
1279	 * TSX_CTRL check alone is not sufficient for cases when the microcode
1280	 * update is not present or running as guest that don't get TSX_CTRL.
1281	 */
1282	if (!(ia32_cap & ARCH_CAP_TAA_NO) &&
1283	    (cpu_has(c, X86_FEATURE_RTM) ||
1284	     (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
1285		setup_force_cpu_bug(X86_BUG_TAA);
1286
1287	/*
1288	 * SRBDS affects CPUs which support RDRAND or RDSEED and are listed
1289	 * in the vulnerability blacklist.
1290	 *
1291	 * Some of the implications and mitigation of Shared Buffers Data
1292	 * Sampling (SBDS) are similar to SRBDS. Give SBDS same treatment as
1293	 * SRBDS.
1294	 */
1295	if ((cpu_has(c, X86_FEATURE_RDRAND) ||
1296	     cpu_has(c, X86_FEATURE_RDSEED)) &&
1297	    cpu_matches(cpu_vuln_blacklist, SRBDS | MMIO_SBDS))
1298		    setup_force_cpu_bug(X86_BUG_SRBDS);
1299
1300	/*
1301	 * Processor MMIO Stale Data bug enumeration
1302	 *
1303	 * Affected CPU list is generally enough to enumerate the vulnerability,
1304	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
1305	 * not want the guest to enumerate the bug.
1306	 *
1307	 * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
1308	 * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
1309	 */
1310	if (!arch_cap_mmio_immune(ia32_cap)) {
1311		if (cpu_matches(cpu_vuln_blacklist, MMIO))
1312			setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
1313		else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
1314			setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
1315	}
1316
1317	if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
1318		if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))
1319			setup_force_cpu_bug(X86_BUG_RETBLEED);
1320	}
1321
1322	/*
1323	 * Check if CPU is vulnerable to GDS. If running in a virtual machine on
1324	 * an affected processor, the VMM may have disabled the use of GATHER by
1325	 * disabling AVX2. The only way to do this in HW is to clear XCR0[2],
1326	 * which means that AVX will be disabled.
1327	 */
1328	if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) &&
1329	    boot_cpu_has(X86_FEATURE_AVX))
1330		setup_force_cpu_bug(X86_BUG_GDS);
1331
1332	if (!cpu_has(c, X86_FEATURE_SRSO_NO)) {
1333		if (cpu_matches(cpu_vuln_blacklist, SRSO))
1334			setup_force_cpu_bug(X86_BUG_SRSO);
1335	}
1336
1337	if (vulnerable_to_rfds(ia32_cap))
1338		setup_force_cpu_bug(X86_BUG_RFDS);
1339
1340	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
1341		return;
1342
1343	/* Rogue Data Cache Load? No! */
1344	if (ia32_cap & ARCH_CAP_RDCL_NO)
1345		return;
1346
1347	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
1348
1349	if (cpu_matches(cpu_vuln_whitelist, NO_L1TF))
1350		return;
1351
1352	setup_force_cpu_bug(X86_BUG_L1TF);
1353}
1354
1355/*
1356 * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
1357 * unfortunately, that's not true in practice because of early VIA
1358 * chips and (more importantly) broken virtualizers that are not easy
1359 * to detect. In the latter case it doesn't even *fail* reliably, so
1360 * probing for it doesn't even work. Disable it completely on 32-bit
1361 * unless we can find a reliable way to detect all the broken cases.
1362 * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
1363 */
1364static void detect_nopl(void)
1365{
1366#ifdef CONFIG_X86_32
1367	setup_clear_cpu_cap(X86_FEATURE_NOPL);
1368#else
1369	setup_force_cpu_cap(X86_FEATURE_NOPL);
1370#endif
1371}
1372
1373/*
1374 * We parse cpu parameters early because fpu__init_system() is executed
1375 * before parse_early_param().
1376 */
1377static void __init cpu_parse_early_param(void)
1378{
1379	char arg[128];
1380	char *argptr = arg;
1381	int arglen, res, bit;
1382
1383#ifdef CONFIG_X86_32
1384	if (cmdline_find_option_bool(boot_command_line, "no387"))
1385#ifdef CONFIG_MATH_EMULATION
1386		setup_clear_cpu_cap(X86_FEATURE_FPU);
1387#else
1388		pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
1389#endif
1390
1391	if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
1392		setup_clear_cpu_cap(X86_FEATURE_FXSR);
1393#endif
1394
1395	if (cmdline_find_option_bool(boot_command_line, "noxsave"))
1396		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
1397
1398	if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
1399		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
1400
1401	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
1402		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
1403
1404	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
1405	if (arglen <= 0)
1406		return;
1407
1408	pr_info("Clearing CPUID bits:");
1409	do {
1410		res = get_option(&argptr, &bit);
1411		if (res == 0 || res == 3)
1412			break;
1413
1414		/* If the argument was too long, the last bit may be cut off */
1415		if (res == 1 && arglen >= sizeof(arg))
1416			break;
1417
1418		if (bit >= 0 && bit < NCAPINTS * 32) {
1419			pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
1420			setup_clear_cpu_cap(bit);
1421		}
1422	} while (res == 2);
1423	pr_cont("\n");
1424}
1425
1426/*
1427 * Do minimum CPU detection early.
1428 * Fields really needed: vendor, cpuid_level, family, model, mask,
1429 * cache alignment.
1430 * The others are not touched to avoid unwanted side effects.
1431 *
1432 * WARNING: this function is only called on the boot CPU.  Don't add code
1433 * here that is supposed to run on all CPUs.
1434 */
1435static void __init early_identify_cpu(struct cpuinfo_x86 *c)
1436{
1437#ifdef CONFIG_X86_64
1438	c->x86_clflush_size = 64;
1439	c->x86_phys_bits = 36;
1440	c->x86_virt_bits = 48;
1441#else
1442	c->x86_clflush_size = 32;
1443	c->x86_phys_bits = 32;
1444	c->x86_virt_bits = 32;
1445#endif
1446	c->x86_cache_alignment = c->x86_clflush_size;
1447
1448	memset(&c->x86_capability, 0, sizeof(c->x86_capability));
1449	c->extended_cpuid_level = 0;
1450
1451	if (!have_cpuid_p())
1452		identify_cpu_without_cpuid(c);
1453
1454	/* cyrix could have cpuid enabled via c_identify()*/
1455	if (have_cpuid_p()) {
1456		cpu_detect(c);
1457		get_cpu_vendor(c);
1458		get_cpu_cap(c);
1459		get_cpu_address_sizes(c);
1460		setup_force_cpu_cap(X86_FEATURE_CPUID);
1461		cpu_parse_early_param();
1462
1463		if (this_cpu->c_early_init)
1464			this_cpu->c_early_init(c);
1465
1466		c->cpu_index = 0;
1467		filter_cpuid_features(c, false);
1468
1469		if (this_cpu->c_bsp_init)
1470			this_cpu->c_bsp_init(c);
1471	} else {
1472		setup_clear_cpu_cap(X86_FEATURE_CPUID);
1473	}
1474
1475	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
1476
1477	cpu_set_bug_bits(c);
1478
1479	cpu_set_core_cap_bits(c);
1480
1481#ifdef CONFIG_X86_32
1482	/*
1483	 * Regardless of whether PCID is enumerated, the SDM says
1484	 * that it can't be enabled in 32-bit mode.
1485	 */
1486	setup_clear_cpu_cap(X86_FEATURE_PCID);
1487#endif
1488
1489	/*
1490	 * Later in the boot process pgtable_l5_enabled() relies on
1491	 * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
1492	 * enabled by this point we need to clear the feature bit to avoid
1493	 * false-positives at the later stage.
1494	 *
1495	 * pgtable_l5_enabled() can be false here for several reasons:
1496	 *  - 5-level paging is disabled compile-time;
1497	 *  - it's 32-bit kernel;
1498	 *  - machine doesn't support 5-level paging;
1499	 *  - user specified 'no5lvl' in kernel command line.
1500	 */
1501	if (!pgtable_l5_enabled())
1502		setup_clear_cpu_cap(X86_FEATURE_LA57);
1503
1504	detect_nopl();
1505}
1506
1507void __init early_cpu_init(void)
1508{
1509	const struct cpu_dev *const *cdev;
1510	int count = 0;
1511
1512#ifdef CONFIG_PROCESSOR_SELECT
1513	pr_info("KERNEL supported cpus:\n");
1514#endif
1515
1516	for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
1517		const struct cpu_dev *cpudev = *cdev;
1518
1519		if (count >= X86_VENDOR_NUM)
1520			break;
1521		cpu_devs[count] = cpudev;
1522		count++;
1523
1524#ifdef CONFIG_PROCESSOR_SELECT
1525		{
1526			unsigned int j;
1527
1528			for (j = 0; j < 2; j++) {
1529				if (!cpudev->c_ident[j])
1530					continue;
1531				pr_info("  %s %s\n", cpudev->c_vendor,
1532					cpudev->c_ident[j]);
1533			}
1534		}
1535#endif
1536	}
1537	early_identify_cpu(&boot_cpu_data);
1538}
1539
1540static bool detect_null_seg_behavior(void)
1541{
1542	/*
1543	 * Empirically, writing zero to a segment selector on AMD does
1544	 * not clear the base, whereas writing zero to a segment
1545	 * selector on Intel does clear the base.  Intel's behavior
1546	 * allows slightly faster context switches in the common case
1547	 * where GS is unused by the prev and next threads.
1548	 *
1549	 * Since neither vendor documents this anywhere that I can see,
1550	 * detect it directly instead of hardcoding the choice by
1551	 * vendor.
1552	 *
1553	 * I've designated AMD's behavior as the "bug" because it's
1554	 * counterintuitive and less friendly.
1555	 */
1556
1557	unsigned long old_base, tmp;
1558	rdmsrl(MSR_FS_BASE, old_base);
1559	wrmsrl(MSR_FS_BASE, 1);
1560	loadsegment(fs, 0);
1561	rdmsrl(MSR_FS_BASE, tmp);
1562	wrmsrl(MSR_FS_BASE, old_base);
1563	return tmp == 0;
1564}
1565
1566void check_null_seg_clears_base(struct cpuinfo_x86 *c)
1567{
1568	/* BUG_NULL_SEG is only relevant with 64bit userspace */
1569	if (!IS_ENABLED(CONFIG_X86_64))
1570		return;
1571
1572	/* Zen3 CPUs advertise Null Selector Clears Base in CPUID. */
1573	if (c->extended_cpuid_level >= 0x80000021 &&
1574	    cpuid_eax(0x80000021) & BIT(6))
1575		return;
1576
1577	/*
1578	 * CPUID bit above wasn't set. If this kernel is still running
1579	 * as a HV guest, then the HV has decided not to advertize
1580	 * that CPUID bit for whatever reason.	For example, one
1581	 * member of the migration pool might be vulnerable.  Which
1582	 * means, the bug is present: set the BUG flag and return.
1583	 */
1584	if (cpu_has(c, X86_FEATURE_HYPERVISOR)) {
1585		set_cpu_bug(c, X86_BUG_NULL_SEG);
1586		return;
1587	}
1588
1589	/*
1590	 * Zen2 CPUs also have this behaviour, but no CPUID bit.
1591	 * 0x18 is the respective family for Hygon.
1592	 */
1593	if ((c->x86 == 0x17 || c->x86 == 0x18) &&
1594	    detect_null_seg_behavior())
1595		return;
1596
1597	/* All the remaining ones are affected */
1598	set_cpu_bug(c, X86_BUG_NULL_SEG);
1599}
1600
1601static void generic_identify(struct cpuinfo_x86 *c)
1602{
1603	c->extended_cpuid_level = 0;
1604
1605	if (!have_cpuid_p())
1606		identify_cpu_without_cpuid(c);
1607
1608	/* cyrix could have cpuid enabled via c_identify()*/
1609	if (!have_cpuid_p())
1610		return;
1611
1612	cpu_detect(c);
1613
1614	get_cpu_vendor(c);
1615
1616	get_cpu_cap(c);
1617
1618	get_cpu_address_sizes(c);
1619
1620	if (c->cpuid_level >= 0x00000001) {
1621		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
1622#ifdef CONFIG_X86_32
1623# ifdef CONFIG_SMP
1624		c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
1625# else
1626		c->apicid = c->initial_apicid;
1627# endif
1628#endif
1629		c->phys_proc_id = c->initial_apicid;
1630	}
1631
1632	get_model_name(c); /* Default name */
1633
1634	/*
1635	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
1636	 * systems that run Linux at CPL > 0 may or may not have the
1637	 * issue, but, even if they have the issue, there's absolutely
1638	 * nothing we can do about it because we can't use the real IRET
1639	 * instruction.
1640	 *
1641	 * NB: For the time being, only 32-bit kernels support
1642	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
1643	 * whether to apply espfix using paravirt hooks.  If any
1644	 * non-paravirt system ever shows up that does *not* have the
1645	 * ESPFIX issue, we can change this.
1646	 */
1647#ifdef CONFIG_X86_32
1648	set_cpu_bug(c, X86_BUG_ESPFIX);
1649#endif
1650}
1651
1652/*
1653 * Validate that ACPI/mptables have the same information about the
1654 * effective APIC id and update the package map.
1655 */
1656static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
1657{
1658#ifdef CONFIG_SMP
1659	unsigned int apicid, cpu = smp_processor_id();
1660
1661	apicid = apic->cpu_present_to_apicid(cpu);
1662
1663	if (apicid != c->apicid) {
1664		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
1665		       cpu, apicid, c->initial_apicid);
1666	}
1667	BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
1668	BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
1669#else
1670	c->logical_proc_id = 0;
1671#endif
1672}
1673
1674/*
1675 * This does the hard work of actually picking apart the CPU stuff...
1676 */
1677static void identify_cpu(struct cpuinfo_x86 *c)
1678{
1679	int i;
1680
1681	c->loops_per_jiffy = loops_per_jiffy;
1682	c->x86_cache_size = 0;
1683	c->x86_vendor = X86_VENDOR_UNKNOWN;
1684	c->x86_model = c->x86_stepping = 0;	/* So far unknown... */
1685	c->x86_vendor_id[0] = '\0'; /* Unset */
1686	c->x86_model_id[0] = '\0';  /* Unset */
1687	c->x86_max_cores = 1;
1688	c->x86_coreid_bits = 0;
1689	c->cu_id = 0xff;
1690#ifdef CONFIG_X86_64
1691	c->x86_clflush_size = 64;
1692	c->x86_phys_bits = 36;
1693	c->x86_virt_bits = 48;
1694#else
1695	c->cpuid_level = -1;	/* CPUID not detected */
1696	c->x86_clflush_size = 32;
1697	c->x86_phys_bits = 32;
1698	c->x86_virt_bits = 32;
1699#endif
1700	c->x86_cache_alignment = c->x86_clflush_size;
1701	memset(&c->x86_capability, 0, sizeof(c->x86_capability));
1702#ifdef CONFIG_X86_VMX_FEATURE_NAMES
1703	memset(&c->vmx_capability, 0, sizeof(c->vmx_capability));
1704#endif
1705
1706	generic_identify(c);
1707
1708	if (this_cpu->c_identify)
1709		this_cpu->c_identify(c);
1710
1711	/* Clear/Set all flags overridden by options, after probe */
1712	apply_forced_caps(c);
1713
1714#ifdef CONFIG_X86_64
1715	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
1716#endif
1717
1718	/*
1719	 * Vendor-specific initialization.  In this section we
1720	 * canonicalize the feature flags, meaning if there are
1721	 * features a certain CPU supports which CPUID doesn't
1722	 * tell us, CPUID claiming incorrect flags, or other bugs,
1723	 * we handle them here.
1724	 *
1725	 * At the end of this section, c->x86_capability better
1726	 * indicate the features this CPU genuinely supports!
1727	 */
1728	if (this_cpu->c_init)
1729		this_cpu->c_init(c);
1730
1731	/* Disable the PN if appropriate */
1732	squash_the_stupid_serial_number(c);
1733
1734	/* Set up SMEP/SMAP/UMIP */
1735	setup_smep(c);
1736	setup_smap(c);
1737	setup_umip(c);
1738
1739	/* Enable FSGSBASE instructions if available. */
1740	if (cpu_has(c, X86_FEATURE_FSGSBASE)) {
1741		cr4_set_bits(X86_CR4_FSGSBASE);
1742		elf_hwcap2 |= HWCAP2_FSGSBASE;
1743	}
1744
1745	/*
1746	 * The vendor-specific functions might have changed features.
1747	 * Now we do "generic changes."
1748	 */
1749
1750	/* Filter out anything that depends on CPUID levels we don't have */
1751	filter_cpuid_features(c, true);
1752
1753	/* If the model name is still unset, do table lookup. */
1754	if (!c->x86_model_id[0]) {
1755		const char *p;
1756		p = table_lookup_model(c);
1757		if (p)
1758			strcpy(c->x86_model_id, p);
1759		else
1760			/* Last resort... */
1761			sprintf(c->x86_model_id, "%02x/%02x",
1762				c->x86, c->x86_model);
1763	}
1764
1765#ifdef CONFIG_X86_64
1766	detect_ht(c);
1767#endif
1768
1769	x86_init_rdrand(c);
1770	setup_pku(c);
1771
1772	/*
1773	 * Clear/Set all flags overridden by options, need do it
1774	 * before following smp all cpus cap AND.
1775	 */
1776	apply_forced_caps(c);
1777
1778	/*
1779	 * On SMP, boot_cpu_data holds the common feature set between
1780	 * all CPUs; so make sure that we indicate which features are
1781	 * common between the CPUs.  The first time this routine gets
1782	 * executed, c == &boot_cpu_data.
1783	 */
1784	if (c != &boot_cpu_data) {
1785		/* AND the already accumulated flags with these */
1786		for (i = 0; i < NCAPINTS; i++)
1787			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
1788
1789		/* OR, i.e. replicate the bug flags */
1790		for (i = NCAPINTS; i < NCAPINTS + NBUGINTS; i++)
1791			c->x86_capability[i] |= boot_cpu_data.x86_capability[i];
1792	}
1793
1794	/* Init Machine Check Exception if available. */
1795	mcheck_cpu_init(c);
1796
1797	select_idle_routine(c);
1798
1799#ifdef CONFIG_NUMA
1800	numa_add_cpu(smp_processor_id());
1801#endif
1802}
1803
1804/*
1805 * Set up the CPU state needed to execute SYSENTER/SYSEXIT instructions
1806 * on 32-bit kernels:
1807 */
1808#ifdef CONFIG_X86_32
1809void enable_sep_cpu(void)
1810{
1811	struct tss_struct *tss;
1812	int cpu;
1813
1814	if (!boot_cpu_has(X86_FEATURE_SEP))
1815		return;
1816
1817	cpu = get_cpu();
1818	tss = &per_cpu(cpu_tss_rw, cpu);
1819
1820	/*
1821	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
1822	 * see the big comment in struct x86_hw_tss's definition.
1823	 */
1824
1825	tss->x86_tss.ss1 = __KERNEL_CS;
1826	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
1827	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
1828	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
1829
1830	put_cpu();
1831}
1832#endif
1833
1834void __init identify_boot_cpu(void)
1835{
1836	identify_cpu(&boot_cpu_data);
1837#ifdef CONFIG_X86_32
1838	sysenter_setup();
1839	enable_sep_cpu();
1840#endif
1841	cpu_detect_tlb(&boot_cpu_data);
1842	setup_cr_pinning();
1843
1844	tsx_init();
1845}
1846
1847void identify_secondary_cpu(struct cpuinfo_x86 *c)
1848{
1849	BUG_ON(c == &boot_cpu_data);
1850	identify_cpu(c);
1851#ifdef CONFIG_X86_32
1852	enable_sep_cpu();
1853#endif
1854	mtrr_ap_init();
1855	validate_apic_and_package_id(c);
1856	x86_spec_ctrl_setup_ap();
1857	update_srbds_msr();
1858	if (boot_cpu_has_bug(X86_BUG_GDS))
1859		update_gds_msr();
1860}
1861
1862static __init int setup_noclflush(char *arg)
1863{
1864	setup_clear_cpu_cap(X86_FEATURE_CLFLUSH);
1865	setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT);
1866	return 1;
1867}
1868__setup("noclflush", setup_noclflush);
1869
1870void print_cpu_info(struct cpuinfo_x86 *c)
1871{
1872	const char *vendor = NULL;
1873
1874	if (c->x86_vendor < X86_VENDOR_NUM) {
1875		vendor = this_cpu->c_vendor;
1876	} else {
1877		if (c->cpuid_level >= 0)
1878			vendor = c->x86_vendor_id;
1879	}
1880
1881	if (vendor && !strstr(c->x86_model_id, vendor))
1882		pr_cont("%s ", vendor);
1883
1884	if (c->x86_model_id[0])
1885		pr_cont("%s", c->x86_model_id);
1886	else
1887		pr_cont("%d86", c->x86);
1888
1889	pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model);
1890
1891	if (c->x86_stepping || c->cpuid_level >= 0)
1892		pr_cont(", stepping: 0x%x)\n", c->x86_stepping);
1893	else
1894		pr_cont(")\n");
1895}
1896
1897/*
1898 * clearcpuid= was already parsed in fpu__init_parse_early_param.
1899 * But we need to keep a dummy __setup around otherwise it would
1900 * show up as an environment variable for init.
1901 */
1902static __init int setup_clearcpuid(char *arg)
1903{
1904	return 1;
1905}
1906__setup("clearcpuid=", setup_clearcpuid);
1907
1908#ifdef CONFIG_X86_64
1909DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
1910		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
1911EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
1912
1913/*
1914 * The following percpu variables are hot.  Align current_task to
1915 * cacheline size such that they fall in the same cacheline.
1916 */
1917DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
1918	&init_task;
1919EXPORT_PER_CPU_SYMBOL(current_task);
1920
1921DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
1922DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
1923
1924DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
1925EXPORT_PER_CPU_SYMBOL(__preempt_count);
1926
1927/* May not be marked __init: used by software suspend */
1928void syscall_init(void)
1929{
1930	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
1931	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
1932
1933#ifdef CONFIG_IA32_EMULATION
1934	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
1935	/*
1936	 * This only works on Intel CPUs.
1937	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
1938	 * This does not cause SYSENTER to jump to the wrong location, because
1939	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
1940	 */
1941	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
1942	wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
1943		    (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
1944	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
1945#else
1946	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
1947	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
1948	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
1949	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
1950#endif
1951
1952	/* Flags to clear on syscall */
1953	wrmsrl(MSR_SYSCALL_MASK,
1954	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
1955	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
1956}
1957
1958#else	/* CONFIG_X86_64 */
1959
1960DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
1961EXPORT_PER_CPU_SYMBOL(current_task);
1962DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
1963EXPORT_PER_CPU_SYMBOL(__preempt_count);
1964
1965/*
1966 * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
1967 * the top of the kernel stack.  Use an extra percpu variable to track the
1968 * top of the kernel stack directly.
1969 */
1970DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
1971	(unsigned long)&init_thread_union + THREAD_SIZE;
1972EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
1973
1974#ifdef CONFIG_STACKPROTECTOR
1975DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
1976#endif
1977
1978#endif	/* CONFIG_X86_64 */
1979
1980/*
1981 * Clear all 6 debug registers:
1982 */
1983static void clear_all_debug_regs(void)
1984{
1985	int i;
1986
1987	for (i = 0; i < 8; i++) {
1988		/* Ignore db4, db5 */
1989		if ((i == 4) || (i == 5))
1990			continue;
1991
1992		set_debugreg(0, i);
1993	}
1994}
1995
1996#ifdef CONFIG_KGDB
1997/*
1998 * Restore debug regs if using kgdbwait and you have a kernel debugger
1999 * connection established.
2000 */
2001static void dbg_restore_debug_regs(void)
2002{
2003	if (unlikely(kgdb_connected && arch_kgdb_ops.correct_hw_break))
2004		arch_kgdb_ops.correct_hw_break();
2005}
2006#else /* ! CONFIG_KGDB */
2007#define dbg_restore_debug_regs()
2008#endif /* ! CONFIG_KGDB */
2009
2010static void wait_for_master_cpu(int cpu)
2011{
2012#ifdef CONFIG_SMP
2013	/*
2014	 * wait for ACK from master CPU before continuing
2015	 * with AP initialization
2016	 */
2017	WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask));
2018	while (!cpumask_test_cpu(cpu, cpu_callout_mask))
2019		cpu_relax();
2020#endif
2021}
2022
2023#ifdef CONFIG_X86_64
2024static inline void setup_getcpu(int cpu)
2025{
2026	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
2027	struct desc_struct d = { };
2028
2029	if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID))
2030		write_rdtscp_aux(cpudata);
2031
2032	/* Store CPU and node number in limit. */
2033	d.limit0 = cpudata;
2034	d.limit1 = cpudata >> 16;
2035
2036	d.type = 5;		/* RO data, expand down, accessed */
2037	d.dpl = 3;		/* Visible to user code */
2038	d.s = 1;		/* Not a system segment */
2039	d.p = 1;		/* Present */
2040	d.d = 1;		/* 32-bit */
2041
2042	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S);
2043}
2044
2045static inline void ucode_cpu_init(int cpu)
2046{
2047	if (cpu)
2048		load_ucode_ap();
2049}
2050
2051static inline void tss_setup_ist(struct tss_struct *tss)
2052{
2053	/* Set up the per-CPU TSS IST stacks */
2054	tss->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
2055	tss->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
2056	tss->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
2057	tss->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
2058	/* Only mapped when SEV-ES is active */
2059	tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC);
2060}
2061
2062#else /* CONFIG_X86_64 */
2063
2064static inline void setup_getcpu(int cpu) { }
2065
2066static inline void ucode_cpu_init(int cpu)
2067{
2068	show_ucode_info_early();
2069}
2070
2071static inline void tss_setup_ist(struct tss_struct *tss) { }
2072
2073#endif /* !CONFIG_X86_64 */
2074
2075static inline void tss_setup_io_bitmap(struct tss_struct *tss)
2076{
2077	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
2078
2079#ifdef CONFIG_X86_IOPL_IOPERM
2080	tss->io_bitmap.prev_max = 0;
2081	tss->io_bitmap.prev_sequence = 0;
2082	memset(tss->io_bitmap.bitmap, 0xff, sizeof(tss->io_bitmap.bitmap));
2083	/*
2084	 * Invalidate the extra array entry past the end of the all
2085	 * permission bitmap as required by the hardware.
2086	 */
2087	tss->io_bitmap.mapall[IO_BITMAP_LONGS] = ~0UL;
2088#endif
2089}
2090
2091/*
2092 * Setup everything needed to handle exceptions from the IDT, including the IST
2093 * exceptions which use paranoid_entry().
2094 */
2095void cpu_init_exception_handling(void)
2096{
2097	struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
2098	int cpu = raw_smp_processor_id();
2099
2100	/* paranoid_entry() gets the CPU number from the GDT */
2101	setup_getcpu(cpu);
2102
2103	/* IST vectors need TSS to be set up. */
2104	tss_setup_ist(tss);
2105	tss_setup_io_bitmap(tss);
2106	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
2107
2108	load_TR_desc();
2109
2110	/* Finally load the IDT */
2111	load_current_idt();
2112}
2113
2114/*
2115 * cpu_init() initializes state that is per-CPU. Some data is already
2116 * initialized (naturally) in the bootstrap process, such as the GDT.  We
2117 * reload it nevertheless, this function acts as a 'CPU state barrier',
2118 * nothing should get across.
2119 */
2120void cpu_init(void)
2121{
2122	struct task_struct *cur = current;
2123	int cpu = raw_smp_processor_id();
2124
2125	wait_for_master_cpu(cpu);
2126
2127	ucode_cpu_init(cpu);
2128
2129#ifdef CONFIG_NUMA
2130	if (this_cpu_read(numa_node) == 0 &&
2131	    early_cpu_to_node(cpu) != NUMA_NO_NODE)
2132		set_numa_node(early_cpu_to_node(cpu));
2133#endif
2134	pr_debug("Initializing CPU#%d\n", cpu);
2135
2136	if (IS_ENABLED(CONFIG_X86_64) || cpu_feature_enabled(X86_FEATURE_VME) ||
2137	    boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE))
2138		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
2139
2140	/*
2141	 * Initialize the per-CPU GDT with the boot GDT,
2142	 * and set up the GDT descriptor:
2143	 */
2144	switch_to_new_gdt(cpu);
2145
2146	if (IS_ENABLED(CONFIG_X86_64)) {
2147		loadsegment(fs, 0);
2148		memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
2149		syscall_init();
2150
2151		wrmsrl(MSR_FS_BASE, 0);
2152		wrmsrl(MSR_KERNEL_GS_BASE, 0);
2153		barrier();
2154
2155		x2apic_setup();
2156	}
2157
2158	mmgrab(&init_mm);
2159	cur->active_mm = &init_mm;
2160	BUG_ON(cur->mm);
2161	initialize_tlbstate_and_flush();
2162	enter_lazy_tlb(&init_mm, cur);
2163
2164	/*
2165	 * sp0 points to the entry trampoline stack regardless of what task
2166	 * is running.
2167	 */
2168	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
2169
2170	load_mm_ldt(&init_mm);
2171
2172	clear_all_debug_regs();
2173	dbg_restore_debug_regs();
2174
2175	doublefault_init_cpu_tss();
2176
2177	if (is_uv_system())
2178		uv_cpu_init();
2179
2180	load_fixmap_gdt(cpu);
2181}
2182
2183#ifdef CONFIG_SMP
2184void cpu_init_secondary(void)
2185{
2186	/*
2187	 * Relies on the BP having set-up the IDT tables, which are loaded
2188	 * on this CPU in cpu_init_exception_handling().
2189	 */
2190	cpu_init_exception_handling();
2191	cpu_init();
2192	fpu__init_cpu();
2193}
2194#endif
2195
2196#ifdef CONFIG_MICROCODE_LATE_LOADING
2197/**
2198 * store_cpu_caps() - Store a snapshot of CPU capabilities
2199 * @curr_info: Pointer where to store it
2200 *
2201 * Returns: None
2202 */
2203void store_cpu_caps(struct cpuinfo_x86 *curr_info)
2204{
2205	/* Reload CPUID max function as it might've changed. */
2206	curr_info->cpuid_level = cpuid_eax(0);
2207
2208	/* Copy all capability leafs and pick up the synthetic ones. */
2209	memcpy(&curr_info->x86_capability, &boot_cpu_data.x86_capability,
2210	       sizeof(curr_info->x86_capability));
2211
2212	/* Get the hardware CPUID leafs */
2213	get_cpu_cap(curr_info);
2214}
2215
2216/**
2217 * microcode_check() - Check if any CPU capabilities changed after an update.
2218 * @prev_info:	CPU capabilities stored before an update.
2219 *
2220 * The microcode loader calls this upon late microcode load to recheck features,
2221 * only when microcode has been updated. Caller holds microcode_mutex and CPU
2222 * hotplug lock.
2223 *
2224 * Return: None
2225 */
2226void microcode_check(struct cpuinfo_x86 *prev_info)
2227{
2228	struct cpuinfo_x86 curr_info;
2229
2230	perf_check_microcode();
2231
2232	amd_check_microcode();
2233
2234	store_cpu_caps(&curr_info);
2235
2236	if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability,
2237		    sizeof(prev_info->x86_capability)))
2238		return;
2239
2240	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
2241	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
2242}
2243#endif
2244
2245/*
2246 * Invoked from core CPU hotplug code after hotplug operations
2247 */
2248void arch_smt_update(void)
2249{
2250	/* Handle the speculative execution misfeatures */
2251	cpu_bugs_smt_update();
2252	/* Check whether IPI broadcasting can be enabled */
2253	apic_smt_update();
2254}
2255
2256void __init arch_cpu_finalize_init(void)
2257{
2258	identify_boot_cpu();
2259
2260	/*
2261	 * identify_boot_cpu() initialized SMT support information, let the
2262	 * core code know.
2263	 */
2264	cpu_smt_check_topology();
2265
2266	if (!IS_ENABLED(CONFIG_SMP)) {
2267		pr_info("CPU: ");
2268		print_cpu_info(&boot_cpu_data);
2269	}
2270
2271	cpu_select_mitigations();
2272
2273	arch_smt_update();
2274
2275	if (IS_ENABLED(CONFIG_X86_32)) {
2276		/*
2277		 * Check whether this is a real i386 which is not longer
2278		 * supported and fixup the utsname.
2279		 */
2280		if (boot_cpu_data.x86 < 4)
2281			panic("Kernel requires i486+ for 'invlpg' and other features");
2282
2283		init_utsname()->machine[1] =
2284			'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
2285	}
2286
2287	/*
2288	 * Must be before alternatives because it might set or clear
2289	 * feature bits.
2290	 */
2291	fpu__init_system();
2292	fpu__init_cpu();
2293
2294	alternative_instructions();
2295
2296	if (IS_ENABLED(CONFIG_X86_64)) {
2297		/*
2298		 * Make sure the first 2MB area is not mapped by huge pages
2299		 * There are typically fixed size MTRRs in there and overlapping
2300		 * MTRRs into large pages causes slow downs.
2301		 *
2302		 * Right now we don't do that with gbpages because there seems
2303		 * very little benefit for that case.
2304		 */
2305		if (!direct_gbpages)
2306			set_memory_4k((unsigned long)__va(0), 1);
2307	} else {
2308		fpu__init_check_bugs();
2309	}
2310
2311	/*
2312	 * This needs to be called before any devices perform DMA
2313	 * operations that might use the SWIOTLB bounce buffers. It will
2314	 * mark the bounce buffers as decrypted so that their usage will
2315	 * not cause "plain-text" data to be decrypted when accessed. It
2316	 * must be called after late_time_init() so that Hyper-V x86/x64
2317	 * hypercalls work when the SWIOTLB bounce buffers are decrypted.
2318	 */
2319	mem_encrypt_init();
2320}
2321