Free Electrons

Embedded Linux Experts

   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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
#ifndef _ASM_X86_PARAVIRT_H
#define _ASM_X86_PARAVIRT_H
/* Various instructions on x86 need to be replaced for
 * para-virtualization: those hooks are defined here. */

#ifdef CONFIG_PARAVIRT
#include <asm/pgtable_types.h>
#include <asm/asm.h>

#include <asm/paravirt_types.h>

#ifndef __ASSEMBLY__
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/cpumask.h>

static inline int paravirt_enabled(void)
{
	return pv_info.paravirt_enabled;
}

static inline void load_sp0(struct tss_struct *tss,
			     struct thread_struct *thread)
{
	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
}

/* The paravirtualized CPUID instruction. */
static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
			   unsigned int *ecx, unsigned int *edx)
{
	PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
}

/*
 * These special macros can be used to get or set a debugging register
 */
static inline unsigned long paravirt_get_debugreg(int reg)
{
	return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
}
#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
static inline void set_debugreg(unsigned long val, int reg)
{
	PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
}

static inline void clts(void)
{
	PVOP_VCALL0(pv_cpu_ops.clts);
}

static inline unsigned long read_cr0(void)
{
	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
}

static inline void write_cr0(unsigned long x)
{
	PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
}

static inline unsigned long read_cr2(void)
{
	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
}

static inline void write_cr2(unsigned long x)
{
	PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
}

static inline unsigned long read_cr3(void)
{
	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
}

static inline void write_cr3(unsigned long x)
{
	PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
}

static inline unsigned long read_cr4(void)
{
	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
}
static inline unsigned long read_cr4_safe(void)
{
	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
}

static inline void write_cr4(unsigned long x)
{
	PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
}

#ifdef CONFIG_X86_64
static inline unsigned long read_cr8(void)
{
	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr8);
}

static inline void write_cr8(unsigned long x)
{
	PVOP_VCALL1(pv_cpu_ops.write_cr8, x);
}
#endif

static inline void arch_safe_halt(void)
{
	PVOP_VCALL0(pv_irq_ops.safe_halt);
}

static inline void halt(void)
{
	PVOP_VCALL0(pv_irq_ops.halt);
}

static inline void wbinvd(void)
{
	PVOP_VCALL0(pv_cpu_ops.wbinvd);
}

#define get_kernel_rpl()  (pv_info.kernel_rpl)

static inline u64 paravirt_read_msr(unsigned msr, int *err)
{
	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
}

static inline int paravirt_rdmsr_regs(u32 *regs)
{
	return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs);
}

static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
{
	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
}

static inline int paravirt_wrmsr_regs(u32 *regs)
{
	return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs);
}

/* These should all do BUG_ON(_err), but our headers are too tangled. */
#define rdmsr(msr, val1, val2)			\
do {						\
	int _err;				\
	u64 _l = paravirt_read_msr(msr, &_err);	\
	val1 = (u32)_l;				\
	val2 = _l >> 32;			\
} while (0)

#define wrmsr(msr, val1, val2)			\
do {						\
	paravirt_write_msr(msr, val1, val2);	\
} while (0)

#define rdmsrl(msr, val)			\
do {						\
	int _err;				\
	val = paravirt_read_msr(msr, &_err);	\
} while (0)

#define wrmsrl(msr, val)	wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32)
#define wrmsr_safe(msr, a, b)	paravirt_write_msr(msr, a, b)

/* rdmsr with exception handling */
#define rdmsr_safe(msr, a, b)			\
({						\
	int _err;				\
	u64 _l = paravirt_read_msr(msr, &_err);	\
	(*a) = (u32)_l;				\
	(*b) = _l >> 32;			\
	_err;					\
})

#define rdmsr_safe_regs(regs)	paravirt_rdmsr_regs(regs)
#define wrmsr_safe_regs(regs)	paravirt_wrmsr_regs(regs)

static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
{
	int err;

	*p = paravirt_read_msr(msr, &err);
	return err;
}
static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
{
	u32 gprs[8] = { 0 };
	int err;

	gprs[1] = msr;
	gprs[7] = 0x9c5a203a;

	err = paravirt_rdmsr_regs(gprs);

	*p = gprs[0] | ((u64)gprs[2] << 32);

	return err;
}

static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
{
	u32 gprs[8] = { 0 };

	gprs[0] = (u32)val;
	gprs[1] = msr;
	gprs[2] = val >> 32;
	gprs[7] = 0x9c5a203a;

	return paravirt_wrmsr_regs(gprs);
}

static inline u64 paravirt_read_tsc(void)
{
	return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
}

#define rdtscl(low)				\
do {						\
	u64 _l = paravirt_read_tsc();		\
	low = (int)_l;				\
} while (0)

#define rdtscll(val) (val = paravirt_read_tsc())

static inline unsigned long long paravirt_sched_clock(void)
{
	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
}

struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;

static inline u64 paravirt_steal_clock(int cpu)
{
	return PVOP_CALL1(u64, pv_time_ops.steal_clock, cpu);
}

static inline unsigned long long paravirt_read_pmc(int counter)
{
	return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
}

#define rdpmc(counter, low, high)		\
do {						\
	u64 _l = paravirt_read_pmc(counter);	\
	low = (u32)_l;				\
	high = _l >> 32;			\
} while (0)

static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
{
	return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
}

#define rdtscp(low, high, aux)				\
do {							\
	int __aux;					\
	unsigned long __val = paravirt_rdtscp(&__aux);	\
	(low) = (u32)__val;				\
	(high) = (u32)(__val >> 32);			\
	(aux) = __aux;					\
} while (0)

#define rdtscpll(val, aux)				\
do {							\
	unsigned long __aux; 				\
	val = paravirt_rdtscp(&__aux);			\
	(aux) = __aux;					\
} while (0)

static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
}

static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
{
	PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
}

static inline void load_TR_desc(void)
{
	PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
}
static inline void load_gdt(const struct desc_ptr *dtr)
{
	PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
}
static inline void load_idt(const struct desc_ptr *dtr)
{
	PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
}
static inline void set_ldt(const void *addr, unsigned entries)
{
	PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
}
static inline void store_gdt(struct desc_ptr *dtr)
{
	PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
}
static inline void store_idt(struct desc_ptr *dtr)
{
	PVOP_VCALL1(pv_cpu_ops.store_idt, dtr);
}
static inline unsigned long paravirt_store_tr(void)
{
	return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
}
#define store_tr(tr)	((tr) = paravirt_store_tr())
static inline void load_TLS(struct thread_struct *t, unsigned cpu)
{
	PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
}

#ifdef CONFIG_X86_64
static inline void load_gs_index(unsigned int gs)
{
	PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
}
#endif

static inline void write_ldt_entry(struct desc_struct *dt, int entry,
				   const void *desc)
{
	PVOP_VCALL3(pv_cpu_ops.write_ldt_entry, dt, entry, desc);
}

static inline void write_gdt_entry(struct desc_struct *dt, int entry,
				   void *desc, int type)
{
	PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, desc, type);
}

static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
{
	PVOP_VCALL3(pv_cpu_ops.write_idt_entry, dt, entry, g);
}
static inline void set_iopl_mask(unsigned mask)
{
	PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
}

/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
{
	pv_cpu_ops.io_delay();
#ifdef REALLY_SLOW_IO
	pv_cpu_ops.io_delay();
	pv_cpu_ops.io_delay();
	pv_cpu_ops.io_delay();
#endif
}

#ifdef CONFIG_SMP
static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
				    unsigned long start_esp)
{
	PVOP_VCALL3(pv_apic_ops.startup_ipi_hook,
		    phys_apicid, start_eip, start_esp);
}
#endif

static inline void paravirt_activate_mm(struct mm_struct *prev,
					struct mm_struct *next)
{
	PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
}

static inline void arch_dup_mmap(struct mm_struct *oldmm,
				 struct mm_struct *mm)
{
	PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
}

static inline void arch_exit_mmap(struct mm_struct *mm)
{
	PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
}

static inline void __flush_tlb(void)
{
	PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
}
static inline void __flush_tlb_global(void)
{
	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
}
static inline void __flush_tlb_single(unsigned long addr)
{
	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
}

static inline void flush_tlb_others(const struct cpumask *cpumask,
				    struct mm_struct *mm,
				    unsigned long va)
{
	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
}

static inline int paravirt_pgd_alloc(struct mm_struct *mm)
{
	return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
}

static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
	PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
}

static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
{
	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
}
static inline void paravirt_release_pte(unsigned long pfn)
{
	PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
}

static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
{
	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
}

static inline void paravirt_release_pmd(unsigned long pfn)
{
	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
}

static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
{
	PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
}
static inline void paravirt_release_pud(unsigned long pfn)
{
	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
}

static inline void pte_update(struct mm_struct *mm, unsigned long addr,
			      pte_t *ptep)
{
	PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
}
static inline void pmd_update(struct mm_struct *mm, unsigned long addr,
			      pmd_t *pmdp)
{
	PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp);
}

static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
				    pte_t *ptep)
{
	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
}

static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr,
				    pmd_t *pmdp)
{
	PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp);
}

static inline pte_t __pte(pteval_t val)
{
	pteval_t ret;

	if (sizeof(pteval_t) > sizeof(long))
		ret = PVOP_CALLEE2(pteval_t,
				   pv_mmu_ops.make_pte,
				   val, (u64)val >> 32);
	else
		ret = PVOP_CALLEE1(pteval_t,
				   pv_mmu_ops.make_pte,
				   val);

	return (pte_t) { .pte = ret };
}

static inline pteval_t pte_val(pte_t pte)
{
	pteval_t ret;

	if (sizeof(pteval_t) > sizeof(long))
		ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val,
				   pte.pte, (u64)pte.pte >> 32);
	else
		ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val,
				   pte.pte);

	return ret;
}

static inline pgd_t __pgd(pgdval_t val)
{
	pgdval_t ret;

	if (sizeof(pgdval_t) > sizeof(long))
		ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd,
				   val, (u64)val >> 32);
	else
		ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd,
				   val);

	return (pgd_t) { ret };
}

static inline pgdval_t pgd_val(pgd_t pgd)
{
	pgdval_t ret;

	if (sizeof(pgdval_t) > sizeof(long))
		ret =  PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val,
				    pgd.pgd, (u64)pgd.pgd >> 32);
	else
		ret =  PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val,
				    pgd.pgd);

	return ret;
}

#define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
					   pte_t *ptep)
{
	pteval_t ret;

	ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
			 mm, addr, ptep);

	return (pte_t) { .pte = ret };
}

static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
					   pte_t *ptep, pte_t pte)
{
	if (sizeof(pteval_t) > sizeof(long))
		/* 5 arg words */
		pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
	else
		PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
			    mm, addr, ptep, pte.pte);
}

static inline void set_pte(pte_t *ptep, pte_t pte)
{
	if (sizeof(pteval_t) > sizeof(long))
		PVOP_VCALL3(pv_mmu_ops.set_pte, ptep,
			    pte.pte, (u64)pte.pte >> 32);
	else
		PVOP_VCALL2(pv_mmu_ops.set_pte, ptep,
			    pte.pte);
}

static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
			      pte_t *ptep, pte_t pte)
{
	if (sizeof(pteval_t) > sizeof(long))
		/* 5 arg words */
		pv_mmu_ops.set_pte_at(mm, addr, ptep, pte);
	else
		PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
			      pmd_t *pmdp, pmd_t pmd)
{
	if (sizeof(pmdval_t) > sizeof(long))
		/* 5 arg words */
		pv_mmu_ops.set_pmd_at(mm, addr, pmdp, pmd);
	else
		PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp,
			    native_pmd_val(pmd));
}
#endif

static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
	pmdval_t val = native_pmd_val(pmd);

	if (sizeof(pmdval_t) > sizeof(long))
		PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp, val, (u64)val >> 32);
	else
		PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val);
}

#if PAGETABLE_LEVELS >= 3
static inline pmd_t __pmd(pmdval_t val)
{
	pmdval_t ret;

	if (sizeof(pmdval_t) > sizeof(long))
		ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd,
				   val, (u64)val >> 32);
	else
		ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd,
				   val);

	return (pmd_t) { ret };
}

static inline pmdval_t pmd_val(pmd_t pmd)
{
	pmdval_t ret;

	if (sizeof(pmdval_t) > sizeof(long))
		ret =  PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val,
				    pmd.pmd, (u64)pmd.pmd >> 32);
	else
		ret =  PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val,
				    pmd.pmd);

	return ret;
}

static inline void set_pud(pud_t *pudp, pud_t pud)
{
	pudval_t val = native_pud_val(pud);

	if (sizeof(pudval_t) > sizeof(long))
		PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
			    val, (u64)val >> 32);
	else
		PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
			    val);
}
#if PAGETABLE_LEVELS == 4
static inline pud_t __pud(pudval_t val)
{
	pudval_t ret;

	if (sizeof(pudval_t) > sizeof(long))
		ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud,
				   val, (u64)val >> 32);
	else
		ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud,
				   val);

	return (pud_t) { ret };
}

static inline pudval_t pud_val(pud_t pud)
{
	pudval_t ret;

	if (sizeof(pudval_t) > sizeof(long))
		ret =  PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val,
				    pud.pud, (u64)pud.pud >> 32);
	else
		ret =  PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val,
				    pud.pud);

	return ret;
}

static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
{
	pgdval_t val = native_pgd_val(pgd);

	if (sizeof(pgdval_t) > sizeof(long))
		PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp,
			    val, (u64)val >> 32);
	else
		PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp,
			    val);
}

static inline void pgd_clear(pgd_t *pgdp)
{
	set_pgd(pgdp, __pgd(0));
}

static inline void pud_clear(pud_t *pudp)
{
	set_pud(pudp, __pud(0));
}

#endif	/* PAGETABLE_LEVELS == 4 */

#endif	/* PAGETABLE_LEVELS >= 3 */

#ifdef CONFIG_X86_PAE
/* Special-case pte-setting operations for PAE, which can't update a
   64-bit pte atomically */
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
{
	PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
		    pte.pte, pte.pte >> 32);
}

static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
			     pte_t *ptep)
{
	PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
}

static inline void pmd_clear(pmd_t *pmdp)
{
	PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
}
#else  /* !CONFIG_X86_PAE */
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
{
	set_pte(ptep, pte);
}

static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
			     pte_t *ptep)
{
	set_pte_at(mm, addr, ptep, __pte(0));
}

static inline void pmd_clear(pmd_t *pmdp)
{
	set_pmd(pmdp, __pmd(0));
}
#endif	/* CONFIG_X86_PAE */

#define  __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(struct task_struct *prev)
{
	PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
}

static inline void arch_end_context_switch(struct task_struct *next)
{
	PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
}

#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
	PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter);
}

static inline void arch_leave_lazy_mmu_mode(void)
{
	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
}

static inline void arch_flush_lazy_mmu_mode(void)
{
	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
}

static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
				phys_addr_t phys, pgprot_t flags)
{
	pv_mmu_ops.set_fixmap(idx, phys, flags);
}

#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)

static inline int arch_spin_is_locked(struct arch_spinlock *lock)
{
	return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
}

static inline int arch_spin_is_contended(struct arch_spinlock *lock)
{
	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
}
#define arch_spin_is_contended	arch_spin_is_contended

static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
{
	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
}

static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock,
						  unsigned long flags)
{
	PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
}

static __always_inline int arch_spin_trylock(struct arch_spinlock *lock)
{
	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
}

static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
{
	PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
}

#endif

#ifdef CONFIG_X86_32
#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
#define PV_RESTORE_REGS "popl %edx; popl %ecx;"

/* save and restore all caller-save registers, except return value */
#define PV_SAVE_ALL_CALLER_REGS		"pushl %ecx;"
#define PV_RESTORE_ALL_CALLER_REGS	"popl  %ecx;"

#define PV_FLAGS_ARG "0"
#define PV_EXTRA_CLOBBERS
#define PV_VEXTRA_CLOBBERS
#else
/* save and restore all caller-save registers, except return value */
#define PV_SAVE_ALL_CALLER_REGS						\
	"push %rcx;"							\
	"push %rdx;"							\
	"push %rsi;"							\
	"push %rdi;"							\
	"push %r8;"							\
	"push %r9;"							\
	"push %r10;"							\
	"push %r11;"
#define PV_RESTORE_ALL_CALLER_REGS					\
	"pop %r11;"							\
	"pop %r10;"							\
	"pop %r9;"							\
	"pop %r8;"							\
	"pop %rdi;"							\
	"pop %rsi;"							\
	"pop %rdx;"							\
	"pop %rcx;"

/* We save some registers, but all of them, that's too much. We clobber all
 * caller saved registers but the argument parameter */
#define PV_SAVE_REGS "pushq %%rdi;"
#define PV_RESTORE_REGS "popq %%rdi;"
#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
#define PV_FLAGS_ARG "D"
#endif

/*
 * Generate a thunk around a function which saves all caller-save
 * registers except for the return value.  This allows C functions to
 * be called from assembler code where fewer than normal registers are
 * available.  It may also help code generation around calls from C
 * code if the common case doesn't use many registers.
 *
 * When a callee is wrapped in a thunk, the caller can assume that all
 * arg regs and all scratch registers are preserved across the
 * call. The return value in rax/eax will not be saved, even for void
 * functions.
 */
#define PV_CALLEE_SAVE_REGS_THUNK(func)					\
	extern typeof(func) __raw_callee_save_##func;			\
	static void *__##func##__ __used = func;			\
									\
	asm(".pushsection .text;"					\
	    "__raw_callee_save_" #func ": "				\
	    PV_SAVE_ALL_CALLER_REGS					\
	    "call " #func ";"						\
	    PV_RESTORE_ALL_CALLER_REGS					\
	    "ret;"							\
	    ".popsection")

/* Get a reference to a callee-save function */
#define PV_CALLEE_SAVE(func)						\
	((struct paravirt_callee_save) { __raw_callee_save_##func })

/* Promise that "func" already uses the right calling convention */
#define __PV_IS_CALLEE_SAVE(func)			\
	((struct paravirt_callee_save) { func })

static inline notrace unsigned long arch_local_save_flags(void)
{
	return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
}

static inline notrace void arch_local_irq_restore(unsigned long f)
{
	PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
}

static inline notrace void arch_local_irq_disable(void)
{
	PVOP_VCALLEE0(pv_irq_ops.irq_disable);
}

static inline notrace void arch_local_irq_enable(void)
{
	PVOP_VCALLEE0(pv_irq_ops.irq_enable);
}

static inline notrace unsigned long arch_local_irq_save(void)
{
	unsigned long f;

	f = arch_local_save_flags();
	arch_local_irq_disable();
	return f;
}


/* Make sure as little as possible of this mess escapes. */
#undef PARAVIRT_CALL
#undef __PVOP_CALL
#undef __PVOP_VCALL
#undef PVOP_VCALL0
#undef PVOP_CALL0
#undef PVOP_VCALL1
#undef PVOP_CALL1
#undef PVOP_VCALL2
#undef PVOP_CALL2
#undef PVOP_VCALL3
#undef PVOP_CALL3
#undef PVOP_VCALL4
#undef PVOP_CALL4

extern void default_banner(void);

#else  /* __ASSEMBLY__ */

#define _PVSITE(ptype, clobbers, ops, word, algn)	\
771:;						\
	ops;					\
772:;						\
	.pushsection .parainstructions,"a";	\
	 .align	algn;				\
	 word 771b;				\
	 .byte ptype;				\
	 .byte 772b-771b;			\
	 .short clobbers;			\
	.popsection


#define COND_PUSH(set, mask, reg)			\
	.if ((~(set)) & mask); push %reg; .endif
#define COND_POP(set, mask, reg)			\
	.if ((~(set)) & mask); pop %reg; .endif

#ifdef CONFIG_X86_64

#define PV_SAVE_REGS(set)			\
	COND_PUSH(set, CLBR_RAX, rax);		\
	COND_PUSH(set, CLBR_RCX, rcx);		\
	COND_PUSH(set, CLBR_RDX, rdx);		\
	COND_PUSH(set, CLBR_RSI, rsi);		\
	COND_PUSH(set, CLBR_RDI, rdi);		\
	COND_PUSH(set, CLBR_R8, r8);		\
	COND_PUSH(set, CLBR_R9, r9);		\
	COND_PUSH(set, CLBR_R10, r10);		\
	COND_PUSH(set, CLBR_R11, r11)
#define PV_RESTORE_REGS(set)			\
	COND_POP(set, CLBR_R11, r11);		\
	COND_POP(set, CLBR_R10, r10);		\
	COND_POP(set, CLBR_R9, r9);		\
	COND_POP(set, CLBR_R8, r8);		\
	COND_POP(set, CLBR_RDI, rdi);		\
	COND_POP(set, CLBR_RSI, rsi);		\
	COND_POP(set, CLBR_RDX, rdx);		\
	COND_POP(set, CLBR_RCX, rcx);		\
	COND_POP(set, CLBR_RAX, rax)

#define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
#define PARA_INDIRECT(addr)	*addr(%rip)
#else
#define PV_SAVE_REGS(set)			\
	COND_PUSH(set, CLBR_EAX, eax);		\
	COND_PUSH(set, CLBR_EDI, edi);		\
	COND_PUSH(set, CLBR_ECX, ecx);		\
	COND_PUSH(set, CLBR_EDX, edx)
#define PV_RESTORE_REGS(set)			\
	COND_POP(set, CLBR_EDX, edx);		\
	COND_POP(set, CLBR_ECX, ecx);		\
	COND_POP(set, CLBR_EDI, edi);		\
	COND_POP(set, CLBR_EAX, eax)

#define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
#define PARA_INDIRECT(addr)	*%cs:addr
#endif

#define INTERRUPT_RETURN						\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))

#define DISABLE_INTERRUPTS(clobbers)					\
	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)

#define ENABLE_INTERRUPTS(clobbers)					\
	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)

#define USERGS_SYSRET32							\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
		  CLBR_NONE,						\
		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))

#ifdef CONFIG_X86_32
#define GET_CR0_INTO_EAX				\
	push %ecx; push %edx;				\
	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
	pop %edx; pop %ecx

#define ENABLE_INTERRUPTS_SYSEXIT					\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
		  CLBR_NONE,						\
		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))


#else	/* !CONFIG_X86_32 */

/*
 * If swapgs is used while the userspace stack is still current,
 * there's no way to call a pvop.  The PV replacement *must* be
 * inlined, or the swapgs instruction must be trapped and emulated.
 */
#define SWAPGS_UNSAFE_STACK						\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
		  swapgs)

/*
 * Note: swapgs is very special, and in practise is either going to be
 * implemented with a single "swapgs" instruction or something very
 * special.  Either way, we don't need to save any registers for
 * it.
 */
#define SWAPGS								\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)		\
		 )

#define GET_CR2_INTO_RCX				\
	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);	\
	movq %rax, %rcx;				\
	xorq %rax, %rax;

#define PARAVIRT_ADJUST_EXCEPTION_FRAME					\
	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \
		  CLBR_NONE,						\
		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame))

#define USERGS_SYSRET64							\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
		  CLBR_NONE,						\
		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))

#define ENABLE_INTERRUPTS_SYSEXIT32					\
	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
		  CLBR_NONE,						\
		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
#endif	/* CONFIG_X86_32 */

#endif /* __ASSEMBLY__ */
#else  /* CONFIG_PARAVIRT */
# define default_banner x86_init_noop
#endif /* !CONFIG_PARAVIRT */
#endif /* _ASM_X86_PARAVIRT_H */