1/* SPDX-License-Identifier: GPL-2.0 */
2#ifndef _ASM_X86_PROCESSOR_H
3#define _ASM_X86_PROCESSOR_H
4
5#include <asm/processor-flags.h>
6
7/* Forward declaration, a strange C thing */
8struct task_struct;
9struct mm_struct;
10struct io_bitmap;
11struct vm86;
12
13#include <asm/math_emu.h>
14#include <asm/segment.h>
15#include <asm/types.h>
16#include <uapi/asm/sigcontext.h>
17#include <asm/current.h>
18#include <asm/cpufeatures.h>
19#include <asm/page.h>
20#include <asm/pgtable_types.h>
21#include <asm/percpu.h>
22#include <asm/msr.h>
23#include <asm/desc_defs.h>
24#include <asm/nops.h>
25#include <asm/special_insns.h>
26#include <asm/fpu/types.h>
27#include <asm/unwind_hints.h>
28#include <asm/vmxfeatures.h>
29#include <asm/vdso/processor.h>
30
31#include <linux/personality.h>
32#include <linux/cache.h>
33#include <linux/threads.h>
34#include <linux/math64.h>
35#include <linux/err.h>
36#include <linux/irqflags.h>
37#include <linux/mem_encrypt.h>
38
39/*
40 * We handle most unaligned accesses in hardware.  On the other hand
41 * unaligned DMA can be quite expensive on some Nehalem processors.
42 *
43 * Based on this we disable the IP header alignment in network drivers.
44 */
45#define NET_IP_ALIGN	0
46
47#define HBP_NUM 4
48
49/*
50 * These alignment constraints are for performance in the vSMP case,
51 * but in the task_struct case we must also meet hardware imposed
52 * alignment requirements of the FPU state:
53 */
54#ifdef CONFIG_X86_VSMP
55# define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
56# define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
57#else
58# define ARCH_MIN_TASKALIGN		__alignof__(union fpregs_state)
59# define ARCH_MIN_MMSTRUCT_ALIGN	0
60#endif
61
62enum tlb_infos {
63	ENTRIES,
64	NR_INFO
65};
66
67extern u16 __read_mostly tlb_lli_4k[NR_INFO];
68extern u16 __read_mostly tlb_lli_2m[NR_INFO];
69extern u16 __read_mostly tlb_lli_4m[NR_INFO];
70extern u16 __read_mostly tlb_lld_4k[NR_INFO];
71extern u16 __read_mostly tlb_lld_2m[NR_INFO];
72extern u16 __read_mostly tlb_lld_4m[NR_INFO];
73extern u16 __read_mostly tlb_lld_1g[NR_INFO];
74
75/*
76 *  CPU type and hardware bug flags. Kept separately for each CPU.
77 *  Members of this structure are referenced in head_32.S, so think twice
78 *  before touching them. [mj]
79 */
80
81struct cpuinfo_x86 {
82	__u8			x86;		/* CPU family */
83	__u8			x86_vendor;	/* CPU vendor */
84	__u8			x86_model;
85	__u8			x86_stepping;
86#ifdef CONFIG_X86_64
87	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
88	int			x86_tlbsize;
89#endif
90#ifdef CONFIG_X86_VMX_FEATURE_NAMES
91	__u32			vmx_capability[NVMXINTS];
92#endif
93	__u8			x86_virt_bits;
94	__u8			x86_phys_bits;
95	/* CPUID returned core id bits: */
96	__u8			x86_coreid_bits;
97	__u8			cu_id;
98	/* Max extended CPUID function supported: */
99	__u32			extended_cpuid_level;
100	/* Maximum supported CPUID level, -1=no CPUID: */
101	int			cpuid_level;
102	/*
103	 * Align to size of unsigned long because the x86_capability array
104	 * is passed to bitops which require the alignment. Use unnamed
105	 * union to enforce the array is aligned to size of unsigned long.
106	 */
107	union {
108		__u32		x86_capability[NCAPINTS + NBUGINTS];
109		unsigned long	x86_capability_alignment;
110	};
111	char			x86_vendor_id[16];
112	char			x86_model_id[64];
113	/* in KB - valid for CPUS which support this call: */
114	unsigned int		x86_cache_size;
115	int			x86_cache_alignment;	/* In bytes */
116	/* Cache QoS architectural values, valid only on the BSP: */
117	int			x86_cache_max_rmid;	/* max index */
118	int			x86_cache_occ_scale;	/* scale to bytes */
119	int			x86_cache_mbm_width_offset;
120	int			x86_power;
121	unsigned long		loops_per_jiffy;
122	/* cpuid returned max cores value: */
123	u16			x86_max_cores;
124	u16			apicid;
125	u16			initial_apicid;
126	u16			x86_clflush_size;
127	/* number of cores as seen by the OS: */
128	u16			booted_cores;
129	/* Physical processor id: */
130	u16			phys_proc_id;
131	/* Logical processor id: */
132	u16			logical_proc_id;
133	/* Core id: */
134	u16			cpu_core_id;
135	u16			cpu_die_id;
136	u16			logical_die_id;
137	/* Index into per_cpu list: */
138	u16			cpu_index;
139	u32			microcode;
140	/* Address space bits used by the cache internally */
141	u8			x86_cache_bits;
142	unsigned		initialized : 1;
143} __randomize_layout;
144
145struct cpuid_regs {
146	u32 eax, ebx, ecx, edx;
147};
148
149enum cpuid_regs_idx {
150	CPUID_EAX = 0,
151	CPUID_EBX,
152	CPUID_ECX,
153	CPUID_EDX,
154};
155
156#define X86_VENDOR_INTEL	0
157#define X86_VENDOR_CYRIX	1
158#define X86_VENDOR_AMD		2
159#define X86_VENDOR_UMC		3
160#define X86_VENDOR_CENTAUR	5
161#define X86_VENDOR_TRANSMETA	7
162#define X86_VENDOR_NSC		8
163#define X86_VENDOR_HYGON	9
164#define X86_VENDOR_ZHAOXIN	10
165#define X86_VENDOR_NUM		11
166
167#define X86_VENDOR_UNKNOWN	0xff
168
169/*
170 * capabilities of CPUs
171 */
172extern struct cpuinfo_x86	boot_cpu_data;
173extern struct cpuinfo_x86	new_cpu_data;
174
175extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
176extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];
177
178#ifdef CONFIG_SMP
179DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
180#define cpu_data(cpu)		per_cpu(cpu_info, cpu)
181#else
182#define cpu_info		boot_cpu_data
183#define cpu_data(cpu)		boot_cpu_data
184#endif
185
186extern const struct seq_operations cpuinfo_op;
187
188#define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
189
190extern void cpu_detect(struct cpuinfo_x86 *c);
191
192static inline unsigned long long l1tf_pfn_limit(void)
193{
194	return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT);
195}
196
197extern void early_cpu_init(void);
198extern void identify_boot_cpu(void);
199extern void identify_secondary_cpu(struct cpuinfo_x86 *);
200extern void print_cpu_info(struct cpuinfo_x86 *);
201void print_cpu_msr(struct cpuinfo_x86 *);
202
203#ifdef CONFIG_X86_32
204extern int have_cpuid_p(void);
205#else
206static inline int have_cpuid_p(void)
207{
208	return 1;
209}
210#endif
211static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
212				unsigned int *ecx, unsigned int *edx)
213{
214	/* ecx is often an input as well as an output. */
215	asm volatile("cpuid"
216	    : "=a" (*eax),
217	      "=b" (*ebx),
218	      "=c" (*ecx),
219	      "=d" (*edx)
220	    : "0" (*eax), "2" (*ecx)
221	    : "memory");
222}
223
224#define native_cpuid_reg(reg)					\
225static inline unsigned int native_cpuid_##reg(unsigned int op)	\
226{								\
227	unsigned int eax = op, ebx, ecx = 0, edx;		\
228								\
229	native_cpuid(&eax, &ebx, &ecx, &edx);			\
230								\
231	return reg;						\
232}
233
234/*
235 * Native CPUID functions returning a single datum.
236 */
237native_cpuid_reg(eax)
238native_cpuid_reg(ebx)
239native_cpuid_reg(ecx)
240native_cpuid_reg(edx)
241
242/*
243 * Friendlier CR3 helpers.
244 */
245static inline unsigned long read_cr3_pa(void)
246{
247	return __read_cr3() & CR3_ADDR_MASK;
248}
249
250static inline unsigned long native_read_cr3_pa(void)
251{
252	return __native_read_cr3() & CR3_ADDR_MASK;
253}
254
255static inline void load_cr3(pgd_t *pgdir)
256{
257	write_cr3(__sme_pa(pgdir));
258}
259
260/*
261 * Note that while the legacy 'TSS' name comes from 'Task State Segment',
262 * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
263 * unrelated to the task-switch mechanism:
264 */
265#ifdef CONFIG_X86_32
266/* This is the TSS defined by the hardware. */
267struct x86_hw_tss {
268	unsigned short		back_link, __blh;
269	unsigned long		sp0;
270	unsigned short		ss0, __ss0h;
271	unsigned long		sp1;
272
273	/*
274	 * We don't use ring 1, so ss1 is a convenient scratch space in
275	 * the same cacheline as sp0.  We use ss1 to cache the value in
276	 * MSR_IA32_SYSENTER_CS.  When we context switch
277	 * MSR_IA32_SYSENTER_CS, we first check if the new value being
278	 * written matches ss1, and, if it's not, then we wrmsr the new
279	 * value and update ss1.
280	 *
281	 * The only reason we context switch MSR_IA32_SYSENTER_CS is
282	 * that we set it to zero in vm86 tasks to avoid corrupting the
283	 * stack if we were to go through the sysenter path from vm86
284	 * mode.
285	 */
286	unsigned short		ss1;	/* MSR_IA32_SYSENTER_CS */
287
288	unsigned short		__ss1h;
289	unsigned long		sp2;
290	unsigned short		ss2, __ss2h;
291	unsigned long		__cr3;
292	unsigned long		ip;
293	unsigned long		flags;
294	unsigned long		ax;
295	unsigned long		cx;
296	unsigned long		dx;
297	unsigned long		bx;
298	unsigned long		sp;
299	unsigned long		bp;
300	unsigned long		si;
301	unsigned long		di;
302	unsigned short		es, __esh;
303	unsigned short		cs, __csh;
304	unsigned short		ss, __ssh;
305	unsigned short		ds, __dsh;
306	unsigned short		fs, __fsh;
307	unsigned short		gs, __gsh;
308	unsigned short		ldt, __ldth;
309	unsigned short		trace;
310	unsigned short		io_bitmap_base;
311
312} __attribute__((packed));
313#else
314struct x86_hw_tss {
315	u32			reserved1;
316	u64			sp0;
317
318	/*
319	 * We store cpu_current_top_of_stack in sp1 so it's always accessible.
320	 * Linux does not use ring 1, so sp1 is not otherwise needed.
321	 */
322	u64			sp1;
323
324	/*
325	 * Since Linux does not use ring 2, the 'sp2' slot is unused by
326	 * hardware.  entry_SYSCALL_64 uses it as scratch space to stash
327	 * the user RSP value.
328	 */
329	u64			sp2;
330
331	u64			reserved2;
332	u64			ist[7];
333	u32			reserved3;
334	u32			reserved4;
335	u16			reserved5;
336	u16			io_bitmap_base;
337
338} __attribute__((packed));
339#endif
340
341/*
342 * IO-bitmap sizes:
343 */
344#define IO_BITMAP_BITS			65536
345#define IO_BITMAP_BYTES			(IO_BITMAP_BITS / BITS_PER_BYTE)
346#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES / sizeof(long))
347
348#define IO_BITMAP_OFFSET_VALID_MAP				\
349	(offsetof(struct tss_struct, io_bitmap.bitmap) -	\
350	 offsetof(struct tss_struct, x86_tss))
351
352#define IO_BITMAP_OFFSET_VALID_ALL				\
353	(offsetof(struct tss_struct, io_bitmap.mapall) -	\
354	 offsetof(struct tss_struct, x86_tss))
355
356#ifdef CONFIG_X86_IOPL_IOPERM
357/*
358 * sizeof(unsigned long) coming from an extra "long" at the end of the
359 * iobitmap. The limit is inclusive, i.e. the last valid byte.
360 */
361# define __KERNEL_TSS_LIMIT	\
362	(IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \
363	 sizeof(unsigned long) - 1)
364#else
365# define __KERNEL_TSS_LIMIT	\
366	(offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1)
367#endif
368
369/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */
370#define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
371
372struct entry_stack {
373	char	stack[PAGE_SIZE];
374};
375
376struct entry_stack_page {
377	struct entry_stack stack;
378} __aligned(PAGE_SIZE);
379
380/*
381 * All IO bitmap related data stored in the TSS:
382 */
383struct x86_io_bitmap {
384	/* The sequence number of the last active bitmap. */
385	u64			prev_sequence;
386
387	/*
388	 * Store the dirty size of the last io bitmap offender. The next
389	 * one will have to do the cleanup as the switch out to a non io
390	 * bitmap user will just set x86_tss.io_bitmap_base to a value
391	 * outside of the TSS limit. So for sane tasks there is no need to
392	 * actually touch the io_bitmap at all.
393	 */
394	unsigned int		prev_max;
395
396	/*
397	 * The extra 1 is there because the CPU will access an
398	 * additional byte beyond the end of the IO permission
399	 * bitmap. The extra byte must be all 1 bits, and must
400	 * be within the limit.
401	 */
402	unsigned long		bitmap[IO_BITMAP_LONGS + 1];
403
404	/*
405	 * Special I/O bitmap to emulate IOPL(3). All bytes zero,
406	 * except the additional byte at the end.
407	 */
408	unsigned long		mapall[IO_BITMAP_LONGS + 1];
409};
410
411struct tss_struct {
412	/*
413	 * The fixed hardware portion.  This must not cross a page boundary
414	 * at risk of violating the SDM's advice and potentially triggering
415	 * errata.
416	 */
417	struct x86_hw_tss	x86_tss;
418
419	struct x86_io_bitmap	io_bitmap;
420} __aligned(PAGE_SIZE);
421
422DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
423
424/* Per CPU interrupt stacks */
425struct irq_stack {
426	char		stack[IRQ_STACK_SIZE];
427} __aligned(IRQ_STACK_SIZE);
428
429DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
430
431#ifdef CONFIG_X86_32
432DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
433#else
434/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
435#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
436#endif
437
438#ifdef CONFIG_X86_64
439struct fixed_percpu_data {
440	/*
441	 * GCC hardcodes the stack canary as %gs:40.  Since the
442	 * irq_stack is the object at %gs:0, we reserve the bottom
443	 * 48 bytes of the irq stack for the canary.
444	 */
445	char		gs_base[40];
446	unsigned long	stack_canary;
447};
448
449DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
450DECLARE_INIT_PER_CPU(fixed_percpu_data);
451
452static inline unsigned long cpu_kernelmode_gs_base(int cpu)
453{
454	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
455}
456
457DECLARE_PER_CPU(unsigned int, irq_count);
458extern asmlinkage void ignore_sysret(void);
459
460/* Save actual FS/GS selectors and bases to current->thread */
461void current_save_fsgs(void);
462#else	/* X86_64 */
463#ifdef CONFIG_STACKPROTECTOR
464/*
465 * Make sure stack canary segment base is cached-aligned:
466 *   "For Intel Atom processors, avoid non zero segment base address
467 *    that is not aligned to cache line boundary at all cost."
468 * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
469 */
470struct stack_canary {
471	char __pad[20];		/* canary at %gs:20 */
472	unsigned long canary;
473};
474DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
475#endif
476/* Per CPU softirq stack pointer */
477DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
478#endif	/* X86_64 */
479
480extern unsigned int fpu_kernel_xstate_size;
481extern unsigned int fpu_user_xstate_size;
482
483struct perf_event;
484
485struct thread_struct {
486	/* Cached TLS descriptors: */
487	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
488#ifdef CONFIG_X86_32
489	unsigned long		sp0;
490#endif
491	unsigned long		sp;
492#ifdef CONFIG_X86_32
493	unsigned long		sysenter_cs;
494#else
495	unsigned short		es;
496	unsigned short		ds;
497	unsigned short		fsindex;
498	unsigned short		gsindex;
499#endif
500
501#ifdef CONFIG_X86_64
502	unsigned long		fsbase;
503	unsigned long		gsbase;
504#else
505	/*
506	 * XXX: this could presumably be unsigned short.  Alternatively,
507	 * 32-bit kernels could be taught to use fsindex instead.
508	 */
509	unsigned long fs;
510	unsigned long gs;
511#endif
512
513	/* Save middle states of ptrace breakpoints */
514	struct perf_event	*ptrace_bps[HBP_NUM];
515	/* Debug status used for traps, single steps, etc... */
516	unsigned long           virtual_dr6;
517	/* Keep track of the exact dr7 value set by the user */
518	unsigned long           ptrace_dr7;
519	/* Fault info: */
520	unsigned long		cr2;
521	unsigned long		trap_nr;
522	unsigned long		error_code;
523#ifdef CONFIG_VM86
524	/* Virtual 86 mode info */
525	struct vm86		*vm86;
526#endif
527	/* IO permissions: */
528	struct io_bitmap	*io_bitmap;
529
530	/*
531	 * IOPL. Priviledge level dependent I/O permission which is
532	 * emulated via the I/O bitmap to prevent user space from disabling
533	 * interrupts.
534	 */
535	unsigned long		iopl_emul;
536
537	unsigned int		iopl_warn:1;
538	unsigned int		sig_on_uaccess_err:1;
539
540	/* Floating point and extended processor state */
541	struct fpu		fpu;
542	/*
543	 * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
544	 * the end.
545	 */
546};
547
548/* Whitelist the FPU state from the task_struct for hardened usercopy. */
549static inline void arch_thread_struct_whitelist(unsigned long *offset,
550						unsigned long *size)
551{
552	*offset = offsetof(struct thread_struct, fpu.state);
553	*size = fpu_kernel_xstate_size;
554}
555
556static inline void
557native_load_sp0(unsigned long sp0)
558{
559	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
560}
561
562static __always_inline void native_swapgs(void)
563{
564#ifdef CONFIG_X86_64
565	asm volatile("swapgs" ::: "memory");
566#endif
567}
568
569static inline unsigned long current_top_of_stack(void)
570{
571	/*
572	 *  We can't read directly from tss.sp0: sp0 on x86_32 is special in
573	 *  and around vm86 mode and sp0 on x86_64 is special because of the
574	 *  entry trampoline.
575	 */
576	return this_cpu_read_stable(cpu_current_top_of_stack);
577}
578
579static inline bool on_thread_stack(void)
580{
581	return (unsigned long)(current_top_of_stack() -
582			       current_stack_pointer) < THREAD_SIZE;
583}
584
585#ifdef CONFIG_PARAVIRT_XXL
586#include <asm/paravirt.h>
587#else
588#define __cpuid			native_cpuid
589
590static inline void load_sp0(unsigned long sp0)
591{
592	native_load_sp0(sp0);
593}
594
595#endif /* CONFIG_PARAVIRT_XXL */
596
597/* Free all resources held by a thread. */
598extern void release_thread(struct task_struct *);
599
600unsigned long get_wchan(struct task_struct *p);
601
602/*
603 * Generic CPUID function
604 * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
605 * resulting in stale register contents being returned.
606 */
607static inline void cpuid(unsigned int op,
608			 unsigned int *eax, unsigned int *ebx,
609			 unsigned int *ecx, unsigned int *edx)
610{
611	*eax = op;
612	*ecx = 0;
613	__cpuid(eax, ebx, ecx, edx);
614}
615
616/* Some CPUID calls want 'count' to be placed in ecx */
617static inline void cpuid_count(unsigned int op, int count,
618			       unsigned int *eax, unsigned int *ebx,
619			       unsigned int *ecx, unsigned int *edx)
620{
621	*eax = op;
622	*ecx = count;
623	__cpuid(eax, ebx, ecx, edx);
624}
625
626/*
627 * CPUID functions returning a single datum
628 */
629static inline unsigned int cpuid_eax(unsigned int op)
630{
631	unsigned int eax, ebx, ecx, edx;
632
633	cpuid(op, &eax, &ebx, &ecx, &edx);
634
635	return eax;
636}
637
638static inline unsigned int cpuid_ebx(unsigned int op)
639{
640	unsigned int eax, ebx, ecx, edx;
641
642	cpuid(op, &eax, &ebx, &ecx, &edx);
643
644	return ebx;
645}
646
647static inline unsigned int cpuid_ecx(unsigned int op)
648{
649	unsigned int eax, ebx, ecx, edx;
650
651	cpuid(op, &eax, &ebx, &ecx, &edx);
652
653	return ecx;
654}
655
656static inline unsigned int cpuid_edx(unsigned int op)
657{
658	unsigned int eax, ebx, ecx, edx;
659
660	cpuid(op, &eax, &ebx, &ecx, &edx);
661
662	return edx;
663}
664
665extern void select_idle_routine(const struct cpuinfo_x86 *c);
666extern void amd_e400_c1e_apic_setup(void);
667
668extern unsigned long		boot_option_idle_override;
669
670enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
671			 IDLE_POLL};
672
673extern void enable_sep_cpu(void);
674extern int sysenter_setup(void);
675
676
677/* Defined in head.S */
678extern struct desc_ptr		early_gdt_descr;
679
680extern void switch_to_new_gdt(int);
681extern void load_direct_gdt(int);
682extern void load_fixmap_gdt(int);
683extern void load_percpu_segment(int);
684extern void cpu_init(void);
685extern void cpu_init_secondary(void);
686extern void cpu_init_exception_handling(void);
687extern void cr4_init(void);
688
689static inline unsigned long get_debugctlmsr(void)
690{
691	unsigned long debugctlmsr = 0;
692
693#ifndef CONFIG_X86_DEBUGCTLMSR
694	if (boot_cpu_data.x86 < 6)
695		return 0;
696#endif
697	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
698
699	return debugctlmsr;
700}
701
702static inline void update_debugctlmsr(unsigned long debugctlmsr)
703{
704#ifndef CONFIG_X86_DEBUGCTLMSR
705	if (boot_cpu_data.x86 < 6)
706		return;
707#endif
708	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
709}
710
711extern void set_task_blockstep(struct task_struct *task, bool on);
712
713/* Boot loader type from the setup header: */
714extern int			bootloader_type;
715extern int			bootloader_version;
716
717extern char			ignore_fpu_irq;
718
719#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
720#define ARCH_HAS_PREFETCHW
721#define ARCH_HAS_SPINLOCK_PREFETCH
722
723#ifdef CONFIG_X86_32
724# define BASE_PREFETCH		""
725# define ARCH_HAS_PREFETCH
726#else
727# define BASE_PREFETCH		"prefetcht0 %P1"
728#endif
729
730/*
731 * Prefetch instructions for Pentium III (+) and AMD Athlon (+)
732 *
733 * It's not worth to care about 3dnow prefetches for the K6
734 * because they are microcoded there and very slow.
735 */
736static inline void prefetch(const void *x)
737{
738	alternative_input(BASE_PREFETCH, "prefetchnta %P1",
739			  X86_FEATURE_XMM,
740			  "m" (*(const char *)x));
741}
742
743/*
744 * 3dnow prefetch to get an exclusive cache line.
745 * Useful for spinlocks to avoid one state transition in the
746 * cache coherency protocol:
747 */
748static __always_inline void prefetchw(const void *x)
749{
750	alternative_input(BASE_PREFETCH, "prefetchw %P1",
751			  X86_FEATURE_3DNOWPREFETCH,
752			  "m" (*(const char *)x));
753}
754
755static inline void spin_lock_prefetch(const void *x)
756{
757	prefetchw(x);
758}
759
760#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
761			   TOP_OF_KERNEL_STACK_PADDING)
762
763#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))
764
765#define task_pt_regs(task) \
766({									\
767	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
768	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
769	((struct pt_regs *)__ptr) - 1;					\
770})
771
772#ifdef CONFIG_X86_32
773#define INIT_THREAD  {							  \
774	.sp0			= TOP_OF_INIT_STACK,			  \
775	.sysenter_cs		= __KERNEL_CS,				  \
776}
777
778#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
779
780#else
781#define INIT_THREAD { }
782
783extern unsigned long KSTK_ESP(struct task_struct *task);
784
785#endif /* CONFIG_X86_64 */
786
787extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
788					       unsigned long new_sp);
789
790/*
791 * This decides where the kernel will search for a free chunk of vm
792 * space during mmap's.
793 */
794#define __TASK_UNMAPPED_BASE(task_size)	(PAGE_ALIGN(task_size / 3))
795#define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE_LOW)
796
797#define KSTK_EIP(task)		(task_pt_regs(task)->ip)
798
799/* Get/set a process' ability to use the timestamp counter instruction */
800#define GET_TSC_CTL(adr)	get_tsc_mode((adr))
801#define SET_TSC_CTL(val)	set_tsc_mode((val))
802
803extern int get_tsc_mode(unsigned long adr);
804extern int set_tsc_mode(unsigned int val);
805
806DECLARE_PER_CPU(u64, msr_misc_features_shadow);
807
808#ifdef CONFIG_CPU_SUP_AMD
809extern u16 amd_get_nb_id(int cpu);
810extern u32 amd_get_nodes_per_socket(void);
811extern bool cpu_has_ibpb_brtype_microcode(void);
812extern void amd_clear_divider(void);
813#else
814static inline u16 amd_get_nb_id(int cpu)		{ return 0; }
815static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
816static inline bool cpu_has_ibpb_brtype_microcode(void)	{ return false; }
817static inline void amd_clear_divider(void)		{ }
818#endif
819
820static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
821{
822	uint32_t base, eax, signature[3];
823
824	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
825		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
826
827		if (!memcmp(sig, signature, 12) &&
828		    (leaves == 0 || ((eax - base) >= leaves)))
829			return base;
830	}
831
832	return 0;
833}
834
835extern unsigned long arch_align_stack(unsigned long sp);
836void free_init_pages(const char *what, unsigned long begin, unsigned long end);
837extern void free_kernel_image_pages(const char *what, void *begin, void *end);
838
839void default_idle(void);
840#ifdef	CONFIG_XEN
841bool xen_set_default_idle(void);
842#else
843#define xen_set_default_idle 0
844#endif
845
846void __noreturn stop_this_cpu(void *dummy);
847void microcode_check(struct cpuinfo_x86 *prev_info);
848void store_cpu_caps(struct cpuinfo_x86 *info);
849
850enum l1tf_mitigations {
851	L1TF_MITIGATION_OFF,
852	L1TF_MITIGATION_FLUSH_NOWARN,
853	L1TF_MITIGATION_FLUSH,
854	L1TF_MITIGATION_FLUSH_NOSMT,
855	L1TF_MITIGATION_FULL,
856	L1TF_MITIGATION_FULL_FORCE
857};
858
859extern enum l1tf_mitigations l1tf_mitigation;
860
861enum mds_mitigations {
862	MDS_MITIGATION_OFF,
863	MDS_MITIGATION_FULL,
864	MDS_MITIGATION_VMWERV,
865};
866
867extern bool gds_ucode_mitigated(void);
868
869#endif /* _ASM_X86_PROCESSOR_H */
870