summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/processor.h
blob: ae81a7191c1c0e837da8cd34ed7c1a488fd73cc9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_PROCESSOR_H
#define _ASM_X86_PROCESSOR_H

#include <asm/processor-flags.h>

/* Forward declaration, a strange C thing */
struct task_struct;
struct mm_struct;
struct io_bitmap;
struct vm86;

#include <asm/math_emu.h>
#include <asm/segment.h>
#include <asm/types.h>
#include <uapi/asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeatures.h>
#include <asm/cpuid.h>
#include <asm/page.h>
#include <asm/pgtable_types.h>
#include <asm/percpu.h>
#include <asm/msr.h>
#include <asm/desc_defs.h>
#include <asm/nops.h>
#include <asm/special_insns.h>
#include <asm/fpu/types.h>
#include <asm/unwind_hints.h>
#include <asm/vmxfeatures.h>
#include <asm/vdso/processor.h>
#include <asm/shstk.h>

#include <linux/personality.h>
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/math64.h>
#include <linux/err.h>
#include <linux/irqflags.h>
#include <linux/mem_encrypt.h>

/*
 * We handle most unaligned accesses in hardware.  On the other hand
 * unaligned DMA can be quite expensive on some Nehalem processors.
 *
 * Based on this we disable the IP header alignment in network drivers.
 */
#define NET_IP_ALIGN	0

#define HBP_NUM 4

/*
 * These alignment constraints are for performance in the vSMP case,
 * but in the task_struct case we must also meet hardware imposed
 * alignment requirements of the FPU state:
 */
#ifdef CONFIG_X86_VSMP
# define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
# define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
#else
# define ARCH_MIN_TASKALIGN		__alignof__(union fpregs_state)
# define ARCH_MIN_MMSTRUCT_ALIGN	0
#endif

enum tlb_infos {
	ENTRIES,
	NR_INFO
};

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

/*
 * CPU type and hardware bug flags. Kept separately for each CPU.
 */

struct cpuinfo_topology {
	// Real APIC ID read from the local APIC
	u32			apicid;
	// The initial APIC ID provided by CPUID
	u32			initial_apicid;

	// Physical package ID
	u32			pkg_id;

	// Physical die ID on AMD, Relative on Intel
	u32			die_id;

	// Compute unit ID - AMD specific
	u32			cu_id;

	// Core ID relative to the package
	u32			core_id;

	// Logical ID mappings
	u32			logical_pkg_id;
	u32			logical_die_id;

	// Cache level topology IDs
	u32			llc_id;
	u32			l2c_id;
};

struct cpuinfo_x86 {
	__u8			x86;		/* CPU family */
	__u8			x86_vendor;	/* CPU vendor */
	__u8			x86_model;
	__u8			x86_stepping;
#ifdef CONFIG_X86_64
	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
	int			x86_tlbsize;
#endif
#ifdef CONFIG_X86_VMX_FEATURE_NAMES
	__u32			vmx_capability[NVMXINTS];
#endif
	__u8			x86_virt_bits;
	__u8			x86_phys_bits;
	/* CPUID returned core id bits: */
	__u8			x86_coreid_bits;
	/* Max extended CPUID function supported: */
	__u32			extended_cpuid_level;
	/* Maximum supported CPUID level, -1=no CPUID: */
	int			cpuid_level;
	/*
	 * Align to size of unsigned long because the x86_capability array
	 * is passed to bitops which require the alignment. Use unnamed
	 * union to enforce the array is aligned to size of unsigned long.
	 */
	union {
		__u32		x86_capability[NCAPINTS + NBUGINTS];
		unsigned long	x86_capability_alignment;
	};
	char			x86_vendor_id[16];
	char			x86_model_id[64];
	struct cpuinfo_topology	topo;
	/* in KB - valid for CPUS which support this call: */
	unsigned int		x86_cache_size;
	int			x86_cache_alignment;	/* In bytes */
	/* Cache QoS architectural values, valid only on the BSP: */
	int			x86_cache_max_rmid;	/* max index */
	int			x86_cache_occ_scale;	/* scale to bytes */
	int			x86_cache_mbm_width_offset;
	int			x86_power;
	unsigned long		loops_per_jiffy;
	/* protected processor identification number */
	u64			ppin;
	/* cpuid returned max cores value: */
	u16			x86_max_cores;
	u16			x86_clflush_size;
	/* number of cores as seen by the OS: */
	u16			booted_cores;
	/* Index into per_cpu list: */
	u16			cpu_index;
	/*  Is SMT active on this core? */
	bool			smt_active;
	u32			microcode;
	/* Address space bits used by the cache internally */
	u8			x86_cache_bits;
	unsigned		initialized : 1;
} __randomize_layout;

#define X86_VENDOR_INTEL	0
#define X86_VENDOR_CYRIX	1
#define X86_VENDOR_AMD		2
#define X86_VENDOR_UMC		3
#define X86_VENDOR_CENTAUR	5
#define X86_VENDOR_TRANSMETA	7
#define X86_VENDOR_NSC		8
#define X86_VENDOR_HYGON	9
#define X86_VENDOR_ZHAOXIN	10
#define X86_VENDOR_VORTEX	11
#define X86_VENDOR_NUM		12

#define X86_VENDOR_UNKNOWN	0xff

/*
 * capabilities of CPUs
 */
extern struct cpuinfo_x86	boot_cpu_data;
extern struct cpuinfo_x86	new_cpu_data;

extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];

#ifdef CONFIG_SMP
DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
#define cpu_data(cpu)		per_cpu(cpu_info, cpu)
#else
#define cpu_info		boot_cpu_data
#define cpu_data(cpu)		boot_cpu_data
#endif

extern const struct seq_operations cpuinfo_op;

#define cache_line_size()	(boot_cpu_data.x86_cache_alignment)

extern void cpu_detect(struct cpuinfo_x86 *c);

static inline unsigned long long l1tf_pfn_limit(void)
{
	return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT);
}

extern void early_cpu_init(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);

/*
 * Friendlier CR3 helpers.
 */
static inline unsigned long read_cr3_pa(void)
{
	return __read_cr3() & CR3_ADDR_MASK;
}

static inline unsigned long native_read_cr3_pa(void)
{
	return __native_read_cr3() & CR3_ADDR_MASK;
}

static inline void load_cr3(pgd_t *pgdir)
{
	write_cr3(__sme_pa(pgdir));
}

/*
 * Note that while the legacy 'TSS' name comes from 'Task State Segment',
 * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
 * unrelated to the task-switch mechanism:
 */
#ifdef CONFIG_X86_32
/* This is the TSS defined by the hardware. */
struct x86_hw_tss {
	unsigned short		back_link, __blh;
	unsigned long		sp0;
	unsigned short		ss0, __ss0h;
	unsigned long		sp1;

	/*
	 * We don't use ring 1, so ss1 is a convenient scratch space in
	 * the same cacheline as sp0.  We use ss1 to cache the value in
	 * MSR_IA32_SYSENTER_CS.  When we context switch
	 * MSR_IA32_SYSENTER_CS, we first check if the new value being
	 * written matches ss1, and, if it's not, then we wrmsr the new
	 * value and update ss1.
	 *
	 * The only reason we context switch MSR_IA32_SYSENTER_CS is
	 * that we set it to zero in vm86 tasks to avoid corrupting the
	 * stack if we were to go through the sysenter path from vm86
	 * mode.
	 */
	unsigned short		ss1;	/* MSR_IA32_SYSENTER_CS */

	unsigned short		__ss1h;
	unsigned long		sp2;
	unsigned short		ss2, __ss2h;
	unsigned long		__cr3;
	unsigned long		ip;
	unsigned long		flags;
	unsigned long		ax;
	unsigned long		cx;
	unsigned long		dx;
	unsigned long		bx;
	unsigned long		sp;
	unsigned long		bp;
	unsigned long		si;
	unsigned long		di;
	unsigned short		es, __esh;
	unsigned short		cs, __csh;
	unsigned short		ss, __ssh;
	unsigned short		ds, __dsh;
	unsigned short		fs, __fsh;
	unsigned short		gs, __gsh;
	unsigned short		ldt, __ldth;
	unsigned short		trace;
	unsigned short		io_bitmap_base;

} __attribute__((packed));
#else
struct x86_hw_tss {
	u32			reserved1;
	u64			sp0;
	u64			sp1;

	/*
	 * Since Linux does not use ring 2, the 'sp2' slot is unused by
	 * hardware.  entry_SYSCALL_64 uses it as scratch space to stash
	 * the user RSP value.
	 */
	u64			sp2;

	u64			reserved2;
	u64			ist[7];
	u32			reserved3;
	u32			reserved4;
	u16			reserved5;
	u16			io_bitmap_base;

} __attribute__((packed));
#endif

/*
 * IO-bitmap sizes:
 */
#define IO_BITMAP_BITS			65536
#define IO_BITMAP_BYTES			(IO_BITMAP_BITS / BITS_PER_BYTE)
#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES / sizeof(long))

#define IO_BITMAP_OFFSET_VALID_MAP				\
	(offsetof(struct tss_struct, io_bitmap.bitmap) -	\
	 offsetof(struct tss_struct, x86_tss))

#define IO_BITMAP_OFFSET_VALID_ALL				\
	(offsetof(struct tss_struct, io_bitmap.mapall) -	\
	 offsetof(struct tss_struct, x86_tss))

#ifdef CONFIG_X86_IOPL_IOPERM
/*
 * sizeof(unsigned long) coming from an extra "long" at the end of the
 * iobitmap. The limit is inclusive, i.e. the last valid byte.
 */
# define __KERNEL_TSS_LIMIT	\
	(IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \
	 sizeof(unsigned long) - 1)
#else
# define __KERNEL_TSS_LIMIT	\
	(offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1)
#endif

/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */
#define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)

struct entry_stack {
	char	stack[PAGE_SIZE];
};

struct entry_stack_page {
	struct entry_stack stack;
} __aligned(PAGE_SIZE);

/*
 * All IO bitmap related data stored in the TSS:
 */
struct x86_io_bitmap {
	/* The sequence number of the last active bitmap. */
	u64			prev_sequence;

	/*
	 * Store the dirty size of the last io bitmap offender. The next
	 * one will have to do the cleanup as the switch out to a non io
	 * bitmap user will just set x86_tss.io_bitmap_base to a value
	 * outside of the TSS limit. So for sane tasks there is no need to
	 * actually touch the io_bitmap at all.
	 */
	unsigned int		prev_max;

	/*
	 * The extra 1 is there because the CPU will access an
	 * additional byte beyond the end of the IO permission
	 * bitmap. The extra byte must be all 1 bits, and must
	 * be within the limit.
	 */
	unsigned long		bitmap[IO_BITMAP_LONGS + 1];

	/*
	 * Special I/O bitmap to emulate IOPL(3). All bytes zero,
	 * except the additional byte at the end.
	 */
	unsigned long		mapall[IO_BITMAP_LONGS + 1];
};

struct tss_struct {
	/*
	 * The fixed hardware portion.  This must not cross a page boundary
	 * at risk of violating the SDM's advice and potentially triggering
	 * errata.
	 */
	struct x86_hw_tss	x86_tss;

	struct x86_io_bitmap	io_bitmap;
} __aligned(PAGE_SIZE);

DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);

/* Per CPU interrupt stacks */
struct irq_stack {
	char		stack[IRQ_STACK_SIZE];
} __aligned(IRQ_STACK_SIZE);

#ifdef CONFIG_X86_64
struct fixed_percpu_data {
	/*
	 * GCC hardcodes the stack canary as %gs:40.  Since the
	 * irq_stack is the object at %gs:0, we reserve the bottom
	 * 48 bytes of the irq stack for the canary.
	 *
	 * Once we are willing to require -mstack-protector-guard-symbol=
	 * support for x86_64 stackprotector, we can get rid of this.
	 */
	char		gs_base[40];
	unsigned long	stack_canary;
};

DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
DECLARE_INIT_PER_CPU(fixed_percpu_data);

static inline unsigned long cpu_kernelmode_gs_base(int cpu)
{
	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
}

extern asmlinkage void entry_SYSCALL32_ignore(void);

/* Save actual FS/GS selectors and bases to current->thread */
void current_save_fsgs(void);
#else	/* X86_64 */
#ifdef CONFIG_STACKPROTECTOR
DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
#endif
#endif	/* !X86_64 */

struct perf_event;

struct thread_struct {
	/* Cached TLS descriptors: */
	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
#ifdef CONFIG_X86_32
	unsigned long		sp0;
#endif
	unsigned long		sp;
#ifdef CONFIG_X86_32
	unsigned long		sysenter_cs;
#else
	unsigned short		es;
	unsigned short		ds;
	unsigned short		fsindex;
	unsigned short		gsindex;
#endif

#ifdef CONFIG_X86_64
	unsigned long		fsbase;
	unsigned long		gsbase;
#else
	/*
	 * XXX: this could presumably be unsigned short.  Alternatively,
	 * 32-bit kernels could be taught to use fsindex instead.
	 */
	unsigned long fs;
	unsigned long gs;
#endif

	/* Save middle states of ptrace breakpoints */
	struct perf_event	*ptrace_bps[HBP_NUM];
	/* Debug status used for traps, single steps, etc... */
	unsigned long           virtual_dr6;
	/* Keep track of the exact dr7 value set by the user */
	unsigned long           ptrace_dr7;
	/* Fault info: */
	unsigned long		cr2;
	unsigned long		trap_nr;
	unsigned long		error_code;
#ifdef CONFIG_VM86
	/* Virtual 86 mode info */
	struct vm86		*vm86;
#endif
	/* IO permissions: */
	struct io_bitmap	*io_bitmap;

	/*
	 * IOPL. Privilege level dependent I/O permission which is
	 * emulated via the I/O bitmap to prevent user space from disabling
	 * interrupts.
	 */
	unsigned long		iopl_emul;

	unsigned int		iopl_warn:1;
	unsigned int		sig_on_uaccess_err:1;

	/*
	 * Protection Keys Register for Userspace.  Loaded immediately on
	 * context switch. Store it in thread_struct to avoid a lookup in
	 * the tasks's FPU xstate buffer. This value is only valid when a
	 * task is scheduled out. For 'current' the authoritative source of
	 * PKRU is the hardware itself.
	 */
	u32			pkru;

#ifdef CONFIG_X86_USER_SHADOW_STACK
	unsigned long		features;
	unsigned long		features_locked;

	struct thread_shstk	shstk;
#endif

	/* Floating point and extended processor state */
	struct fpu		fpu;
	/*
	 * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
	 * the end.
	 */
};

extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size);

static inline void arch_thread_struct_whitelist(unsigned long *offset,
						unsigned long *size)
{
	fpu_thread_struct_whitelist(offset, size);
}

static inline void
native_load_sp0(unsigned long sp0)
{
	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}

static __always_inline void native_swapgs(void)
{
#ifdef CONFIG_X86_64
	asm volatile("swapgs" ::: "memory");
#endif
}

static __always_inline unsigned long current_top_of_stack(void)
{
	/*
	 *  We can't read directly from tss.sp0: sp0 on x86_32 is special in
	 *  and around vm86 mode and sp0 on x86_64 is special because of the
	 *  entry trampoline.
	 */
	return this_cpu_read_stable(pcpu_hot.top_of_stack);
}

static __always_inline bool on_thread_stack(void)
{
	return (unsigned long)(current_top_of_stack() -
			       current_stack_pointer) < THREAD_SIZE;
}

#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else

static inline void load_sp0(unsigned long sp0)
{
	native_load_sp0(sp0);
}

#endif /* CONFIG_PARAVIRT_XXL */

unsigned long __get_wchan(struct task_struct *p);

extern void select_idle_routine(const struct cpuinfo_x86 *c);
extern void amd_e400_c1e_apic_setup(void);

extern unsigned long		boot_option_idle_override;

enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
			 IDLE_POLL};

extern void enable_sep_cpu(void);


/* Defined in head.S */
extern struct desc_ptr		early_gdt_descr;

extern void switch_gdt_and_percpu_base(int);
extern void load_direct_gdt(int);
extern void load_fixmap_gdt(int);
extern void cpu_init(void);
extern void cpu_init_exception_handling(void);
extern void cr4_init(void);

static inline unsigned long get_debugctlmsr(void)
{
	unsigned long debugctlmsr = 0;

#ifndef CONFIG_X86_DEBUGCTLMSR
	if (boot_cpu_data.x86 < 6)
		return 0;
#endif
	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);

	return debugctlmsr;
}

static inline void update_debugctlmsr(unsigned long debugctlmsr)
{
#ifndef CONFIG_X86_DEBUGCTLMSR
	if (boot_cpu_data.x86 < 6)
		return;
#endif
	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
}

extern void set_task_blockstep(struct task_struct *task, bool on);

/* Boot loader type from the setup header: */
extern int			bootloader_type;
extern int			bootloader_version;

extern char			ignore_fpu_irq;

#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
#define ARCH_HAS_PREFETCHW

#ifdef CONFIG_X86_32
# define BASE_PREFETCH		""
# define ARCH_HAS_PREFETCH
#else
# define BASE_PREFETCH		"prefetcht0 %P1"
#endif

/*
 * Prefetch instructions for Pentium III (+) and AMD Athlon (+)
 *
 * It's not worth to care about 3dnow prefetches for the K6
 * because they are microcoded there and very slow.
 */
static inline void prefetch(const void *x)
{
	alternative_input(BASE_PREFETCH, "prefetchnta %P1",
			  X86_FEATURE_XMM,
			  "m" (*(const char *)x));
}

/*
 * 3dnow prefetch to get an exclusive cache line.
 * Useful for spinlocks to avoid one state transition in the
 * cache coherency protocol:
 */
static __always_inline void prefetchw(const void *x)
{
	alternative_input(BASE_PREFETCH, "prefetchw %P1",
			  X86_FEATURE_3DNOWPREFETCH,
			  "m" (*(const char *)x));
}

#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
			   TOP_OF_KERNEL_STACK_PADDING)

#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))

#define task_pt_regs(task) \
({									\
	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
	((struct pt_regs *)__ptr) - 1;					\
})

#ifdef CONFIG_X86_32
#define INIT_THREAD  {							  \
	.sp0			= TOP_OF_INIT_STACK,			  \
	.sysenter_cs		= __KERNEL_CS,				  \
}

#define KSTK_ESP(task)		(task_pt_regs(task)->sp)

#else
extern unsigned long __end_init_task[];

#define INIT_THREAD {							    \
	.sp	= (unsigned long)&__end_init_task - sizeof(struct pt_regs), \
}

extern unsigned long KSTK_ESP(struct task_struct *task);

#endif /* CONFIG_X86_64 */

extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
					       unsigned long new_sp);

/*
 * This decides where the kernel will search for a free chunk of vm
 * space during mmap's.
 */
#define __TASK_UNMAPPED_BASE(task_size)	(PAGE_ALIGN(task_size / 3))
#define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE_LOW)

#define KSTK_EIP(task)		(task_pt_regs(task)->ip)

/* Get/set a process' ability to use the timestamp counter instruction */
#define GET_TSC_CTL(adr)	get_tsc_mode((adr))
#define SET_TSC_CTL(val)	set_tsc_mode((val))

extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);

DECLARE_PER_CPU(u64, msr_misc_features_shadow);

static inline u32 per_cpu_llc_id(unsigned int cpu)
{
	return per_cpu(cpu_info.topo.llc_id, cpu);
}

static inline u32 per_cpu_l2c_id(unsigned int cpu)
{
	return per_cpu(cpu_info.topo.l2c_id, cpu);
}

#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
extern void amd_clear_divider(void);
extern void amd_check_microcode(void);
#else
static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
static inline u32 amd_get_highest_perf(void)		{ return 0; }
static inline void amd_clear_divider(void)		{ }
static inline void amd_check_microcode(void)		{ }
#endif

extern unsigned long arch_align_stack(unsigned long sp);
void free_init_pages(const char *what, unsigned long begin, unsigned long end);
extern void free_kernel_image_pages(const char *what, void *begin, void *end);

void default_idle(void);
#ifdef	CONFIG_XEN
bool xen_set_default_idle(void);
#else
#define xen_set_default_idle 0
#endif

void __noreturn stop_this_cpu(void *dummy);
void microcode_check(struct cpuinfo_x86 *prev_info);
void store_cpu_caps(struct cpuinfo_x86 *info);

enum l1tf_mitigations {
	L1TF_MITIGATION_OFF,
	L1TF_MITIGATION_FLUSH_NOWARN,
	L1TF_MITIGATION_FLUSH,
	L1TF_MITIGATION_FLUSH_NOSMT,
	L1TF_MITIGATION_FULL,
	L1TF_MITIGATION_FULL_FORCE
};

extern enum l1tf_mitigations l1tf_mitigation;

enum mds_mitigations {
	MDS_MITIGATION_OFF,
	MDS_MITIGATION_FULL,
	MDS_MITIGATION_VMWERV,
};

extern bool gds_ucode_mitigated(void);

#endif /* _ASM_X86_PROCESSOR_H */