Bootlin logo

Elixir Cross Referencer

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
/* 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 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/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 <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
/*
 * Default implementation of macro that returns current
 * instruction pointer ("program counter").
 */
static inline void *current_text_addr(void)
{
	void *pc;

	asm volatile("mov $1f, %0; 1:":"=r" (pc));

	return pc;
}

/*
 * 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.
 *  Members of this structure are referenced in head_32.S, so think twice
 *  before touching them. [mj]
 */

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
	__u8			x86_virt_bits;
	__u8			x86_phys_bits;
	/* CPUID returned core id bits: */
	__u8			x86_coreid_bits;
	__u8			cu_id;
	/* Max extended CPUID function supported: */
	__u32			extended_cpuid_level;
	/* Maximum supported CPUID level, -1=no CPUID: */
	int			cpuid_level;
	__u32			x86_capability[NCAPINTS + NBUGINTS];
	char			x86_vendor_id[16];
	char			x86_model_id[64];
	/* in KB - valid for CPUS which support this call: */
	unsigned int		x86_cache_size;
	int			x86_cache_alignment;	/* In bytes */
	/* Cache QoS architectural values: */
	int			x86_cache_max_rmid;	/* max index */
	int			x86_cache_occ_scale;	/* scale to bytes */
	int			x86_power;
	unsigned long		loops_per_jiffy;
	/* cpuid returned max cores value: */
	u16			 x86_max_cores;
	u16			apicid;
	u16			initial_apicid;
	u16			x86_clflush_size;
	/* number of cores as seen by the OS: */
	u16			booted_cores;
	/* Physical processor id: */
	u16			phys_proc_id;
	/* Logical processor id: */
	u16			logical_proc_id;
	/* Core id: */
	u16			cpu_core_id;
	/* Index into per_cpu list: */
	u16			cpu_index;
	u32			microcode;
	/* Address space bits used by the cache internally */
	u8			x86_cache_bits;
	unsigned		initialized : 1;
} __randomize_layout;

struct cpuid_regs {
	u32 eax, ebx, ecx, edx;
};

enum cpuid_regs_idx {
	CPUID_EAX = 0,
	CPUID_EBX,
	CPUID_ECX,
	CPUID_EDX,
};

#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_NUM		9

#define X86_VENDOR_UNKNOWN	0xff

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

extern struct x86_hw_tss	doublefault_tss;
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_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);

#ifdef CONFIG_X86_32
extern int have_cpuid_p(void);
#else
static inline int have_cpuid_p(void)
{
	return 1;
}
#endif
static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
				unsigned int *ecx, unsigned int *edx)
{
	/* ecx is often an input as well as an output. */
	asm volatile("cpuid"
	    : "=a" (*eax),
	      "=b" (*ebx),
	      "=c" (*ecx),
	      "=d" (*edx)
	    : "0" (*eax), "2" (*ecx)
	    : "memory");
}

#define native_cpuid_reg(reg)					\
static inline unsigned int native_cpuid_##reg(unsigned int op)	\
{								\
	unsigned int eax = op, ebx, ecx = 0, edx;		\
								\
	native_cpuid(&eax, &ebx, &ecx, &edx);			\
								\
	return reg;						\
}

/*
 * Native CPUID functions returning a single datum.
 */
native_cpuid_reg(eax)
native_cpuid_reg(ebx)
native_cpuid_reg(ecx)
native_cpuid_reg(edx)

/*
 * 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;

	/*
	 * We store cpu_current_top_of_stack in sp1 so it's always accessible.
	 * Linux does not use ring 1, so sp1 is not otherwise needed.
	 */
	u64			sp1;

	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/8)
#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
#define INVALID_IO_BITMAP_OFFSET	0x8000

struct entry_stack {
	unsigned long		words[64];
};

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

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;

	/*
	 * 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		io_bitmap[IO_BITMAP_LONGS + 1];
} __aligned(PAGE_SIZE);

DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);

/*
 * sizeof(unsigned long) coming from an extra "long" at the end
 * of the iobitmap.
 *
 * -1? seg base+limit should be pointing to the address of the
 * last valid byte
 */
#define __KERNEL_TSS_LIMIT	\
	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)

#ifdef CONFIG_X86_32
DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
#else
/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
#endif

/*
 * Save the original ist values for checking stack pointers during debugging
 */
struct orig_ist {
	unsigned long		ist[7];
};

#ifdef CONFIG_X86_64
DECLARE_PER_CPU(struct orig_ist, orig_ist);

union irq_stack_union {
	char irq_stack[IRQ_STACK_SIZE];
	/*
	 * 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.
	 */
	struct {
		char gs_base[40];
		unsigned long stack_canary;
	};
};

DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
DECLARE_INIT_PER_CPU(irq_stack_union);

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

DECLARE_PER_CPU(char *, irq_stack_ptr);
DECLARE_PER_CPU(unsigned int, irq_count);
extern asmlinkage void ignore_sysret(void);

#if IS_ENABLED(CONFIG_KVM)
/* Save actual FS/GS selectors and bases to current->thread */
void save_fsgs_for_kvm(void);
#endif
#else	/* X86_64 */
#ifdef CONFIG_STACKPROTECTOR
/*
 * Make sure stack canary segment base is cached-aligned:
 *   "For Intel Atom processors, avoid non zero segment base address
 *    that is not aligned to cache line boundary at all cost."
 * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
 */
struct stack_canary {
	char __pad[20];		/* canary at %gs:20 */
	unsigned long canary;
};
DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
#endif
/*
 * per-CPU IRQ handling stacks
 */
struct irq_stack {
	u32                     stack[THREAD_SIZE/sizeof(u32)];
} __aligned(THREAD_SIZE);

DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
#endif	/* X86_64 */

extern unsigned int fpu_kernel_xstate_size;
extern unsigned int fpu_user_xstate_size;

struct perf_event;

typedef struct {
	unsigned long		seg;
} mm_segment_t;

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           debugreg6;
	/* 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: */
	unsigned long		*io_bitmap_ptr;
	unsigned long		iopl;
	/* Max allowed port in the bitmap, in bytes: */
	unsigned		io_bitmap_max;

	mm_segment_t		addr_limit;

	unsigned int		sig_on_uaccess_err:1;
	unsigned int		uaccess_err:1;	/* uaccess failed */

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

/* Whitelist the FPU state from the task_struct for hardened usercopy. */
static inline void arch_thread_struct_whitelist(unsigned long *offset,
						unsigned long *size)
{
	*offset = offsetof(struct thread_struct, fpu.state);
	*size = fpu_kernel_xstate_size;
}

/*
 * Thread-synchronous status.
 *
 * This is different from the flags in that nobody else
 * ever touches our thread-synchronous status, so we don't
 * have to worry about atomic accesses.
 */
#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/

/*
 * Set IOPL bits in EFLAGS from given mask
 */
static inline void native_set_iopl_mask(unsigned mask)
{
#ifdef CONFIG_X86_32
	unsigned int reg;

	asm volatile ("pushfl;"
		      "popl %0;"
		      "andl %1, %0;"
		      "orl %2, %0;"
		      "pushl %0;"
		      "popfl"
		      : "=&r" (reg)
		      : "i" (~X86_EFLAGS_IOPL), "r" (mask));
#endif
}

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

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

static 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(cpu_current_top_of_stack);
}

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

#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define __cpuid			native_cpuid

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

#define set_iopl_mask native_set_iopl_mask
#endif /* CONFIG_PARAVIRT */

/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);

unsigned long get_wchan(struct task_struct *p);

/*
 * Generic CPUID function
 * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
 * resulting in stale register contents being returned.
 */
static inline void cpuid(unsigned int op,
			 unsigned int *eax, unsigned int *ebx,
			 unsigned int *ecx, unsigned int *edx)
{
	*eax = op;
	*ecx = 0;
	__cpuid(eax, ebx, ecx, edx);
}

/* Some CPUID calls want 'count' to be placed in ecx */
static inline void cpuid_count(unsigned int op, int count,
			       unsigned int *eax, unsigned int *ebx,
			       unsigned int *ecx, unsigned int *edx)
{
	*eax = op;
	*ecx = count;
	__cpuid(eax, ebx, ecx, edx);
}

/*
 * CPUID functions returning a single datum
 */
static inline unsigned int cpuid_eax(unsigned int op)
{
	unsigned int eax, ebx, ecx, edx;

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

	return eax;
}

static inline unsigned int cpuid_ebx(unsigned int op)
{
	unsigned int eax, ebx, ecx, edx;

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

	return ebx;
}

static inline unsigned int cpuid_ecx(unsigned int op)
{
	unsigned int eax, ebx, ecx, edx;

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

	return ecx;
}

static inline unsigned int cpuid_edx(unsigned int op)
{
	unsigned int eax, ebx, ecx, edx;

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

	return edx;
}

/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
static __always_inline void rep_nop(void)
{
	asm volatile("rep; nop" ::: "memory");
}

static __always_inline void cpu_relax(void)
{
	rep_nop();
}

/*
 * This function forces the icache and prefetched instruction stream to
 * catch up with reality in two very specific cases:
 *
 *  a) Text was modified using one virtual address and is about to be executed
 *     from the same physical page at a different virtual address.
 *
 *  b) Text was modified on a different CPU, may subsequently be
 *     executed on this CPU, and you want to make sure the new version
 *     gets executed.  This generally means you're calling this in a IPI.
 *
 * If you're calling this for a different reason, you're probably doing
 * it wrong.
 */
static inline void sync_core(void)
{
	/*
	 * There are quite a few ways to do this.  IRET-to-self is nice
	 * because it works on every CPU, at any CPL (so it's compatible
	 * with paravirtualization), and it never exits to a hypervisor.
	 * The only down sides are that it's a bit slow (it seems to be
	 * a bit more than 2x slower than the fastest options) and that
	 * it unmasks NMIs.  The "push %cs" is needed because, in
	 * paravirtual environments, __KERNEL_CS may not be a valid CS
	 * value when we do IRET directly.
	 *
	 * In case NMI unmasking or performance ever becomes a problem,
	 * the next best option appears to be MOV-to-CR2 and an
	 * unconditional jump.  That sequence also works on all CPUs,
	 * but it will fault at CPL3 (i.e. Xen PV).
	 *
	 * CPUID is the conventional way, but it's nasty: it doesn't
	 * exist on some 486-like CPUs, and it usually exits to a
	 * hypervisor.
	 *
	 * Like all of Linux's memory ordering operations, this is a
	 * compiler barrier as well.
	 */
#ifdef CONFIG_X86_32
	asm volatile (
		"pushfl\n\t"
		"pushl %%cs\n\t"
		"pushl $1f\n\t"
		"iret\n\t"
		"1:"
		: ASM_CALL_CONSTRAINT : : "memory");
#else
	unsigned int tmp;

	asm volatile (
		UNWIND_HINT_SAVE
		"mov %%ss, %0\n\t"
		"pushq %q0\n\t"
		"pushq %%rsp\n\t"
		"addq $8, (%%rsp)\n\t"
		"pushfq\n\t"
		"mov %%cs, %0\n\t"
		"pushq %q0\n\t"
		"pushq $1f\n\t"
		"iretq\n\t"
		UNWIND_HINT_RESTORE
		"1:"
		: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
#endif
}

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);
extern int sysenter_setup(void);

void early_trap_pf_init(void);

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

extern void switch_to_new_gdt(int);
extern void load_direct_gdt(int);
extern void load_fixmap_gdt(int);
extern void load_percpu_segment(int);
extern void cpu_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
#define ARCH_HAS_SPINLOCK_PREFETCH

#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 inline void prefetchw(const void *x)
{
	alternative_input(BASE_PREFETCH, "prefetchw %P1",
			  X86_FEATURE_3DNOWPREFETCH,
			  "m" (*(const char *)x));
}

static inline void spin_lock_prefetch(const void *x)
{
	prefetchw(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
/*
 * User space process size: 3GB (default).
 */
#define IA32_PAGE_OFFSET	PAGE_OFFSET
#define TASK_SIZE		PAGE_OFFSET
#define TASK_SIZE_LOW		TASK_SIZE
#define TASK_SIZE_MAX		TASK_SIZE
#define DEFAULT_MAP_WINDOW	TASK_SIZE
#define STACK_TOP		TASK_SIZE
#define STACK_TOP_MAX		STACK_TOP

#define INIT_THREAD  {							  \
	.sp0			= TOP_OF_INIT_STACK,			  \
	.sysenter_cs		= __KERNEL_CS,				  \
	.io_bitmap_ptr		= NULL,					  \
	.addr_limit		= KERNEL_DS,				  \
}

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

#else
/*
 * User space process size.  This is the first address outside the user range.
 * There are a few constraints that determine this:
 *
 * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
 * address, then that syscall will enter the kernel with a
 * non-canonical return address, and SYSRET will explode dangerously.
 * We avoid this particular problem by preventing anything executable
 * from being mapped at the maximum canonical address.
 *
 * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
 * CPUs malfunction if they execute code from the highest canonical page.
 * They'll speculate right off the end of the canonical space, and
 * bad things happen.  This is worked around in the same way as the
 * Intel problem.
 *
 * With page table isolation enabled, we map the LDT in ... [stay tuned]
 */
#define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)

#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)

/* This decides where the kernel will search for a free chunk of vm
 * space during mmap's.
 */
#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
					0xc0000000 : 0xFFFFe000)

#define TASK_SIZE_LOW		(test_thread_flag(TIF_ADDR32) ? \
					IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW)
#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
					IA32_PAGE_OFFSET : TASK_SIZE_MAX)

#define STACK_TOP		TASK_SIZE_LOW
#define STACK_TOP_MAX		TASK_SIZE_MAX

#define INIT_THREAD  {						\
	.addr_limit		= KERNEL_DS,			\
}

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);

/* Register/unregister a process' MPX related resource */
#define MPX_ENABLE_MANAGEMENT()	mpx_enable_management()
#define MPX_DISABLE_MANAGEMENT()	mpx_disable_management()

#ifdef CONFIG_X86_INTEL_MPX
extern int mpx_enable_management(void);
extern int mpx_disable_management(void);
#else
static inline int mpx_enable_management(void)
{
	return -EINVAL;
}
static inline int mpx_disable_management(void)
{
	return -EINVAL;
}
#endif /* CONFIG_X86_INTEL_MPX */

#ifdef CONFIG_CPU_SUP_AMD
extern u16 amd_get_nb_id(int cpu);
extern u32 amd_get_nodes_per_socket(void);
#else
static inline u16 amd_get_nb_id(int cpu)		{ return 0; }
static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
#endif

static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
{
	uint32_t base, eax, signature[3];

	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);

		if (!memcmp(sig, signature, 12) &&
		    (leaves == 0 || ((eax - base) >= leaves)))
			return base;
	}

	return 0;
}

extern unsigned long arch_align_stack(unsigned long sp);
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
extern void free_kernel_image_pages(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 stop_this_cpu(void *dummy);
void df_debug(struct pt_regs *regs, long error_code);
void microcode_check(void);

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;

#endif /* _ASM_X86_PROCESSOR_H */