processor.h 20.9 KB
Newer Older
1 2 3
#ifndef __ASM_X86_PROCESSOR_H
#define __ASM_X86_PROCESSOR_H

4 5
#include <asm/processor-flags.h>

I
Ingo Molnar 已提交
6 7 8 9
/* migration helpers, for KVM - will be removed in 2.6.25: */
#include <asm/vm86.h>
#define Xgt_desc_struct	desc_ptr

10 11 12 13
/* Forward declaration, a strange C thing */
struct task_struct;
struct mm_struct;

14 15 16 17 18 19 20
#include <asm/vm86.h>
#include <asm/math_emu.h>
#include <asm/segment.h>
#include <asm/types.h>
#include <asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeature.h>
21
#include <asm/system.h>
22
#include <asm/page.h>
23
#include <asm/percpu.h>
24 25
#include <asm/msr.h>
#include <asm/desc_defs.h>
26
#include <asm/nops.h>
27
#include <linux/personality.h>
28 29
#include <linux/cpumask.h>
#include <linux/cache.h>
30 31
#include <linux/threads.h>
#include <linux/init.h>
32

33 34 35 36 37 38 39 40 41 42 43
/*
 * 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\n1:":"=r" (pc));
	return pc;
}

44 45 46 47 48 49 50 51
#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	16
#define ARCH_MIN_MMSTRUCT_ALIGN	0
#endif

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
/*
 *  CPU type and hardware bug flags. Kept separately for each CPU.
 *  Members of this structure are referenced in head.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_mask;
#ifdef CONFIG_X86_32
	char	wp_works_ok;	/* It doesn't on 386's */
	char	hlt_works_ok;	/* Problems on some 486Dx4's and old 386's */
	char	hard_math;
	char	rfu;
	char	fdiv_bug;
	char	f00f_bug;
	char	coma_bug;
	char	pad0;
#else
	/* number of 4K pages in DTLB/ITLB combined(in pages)*/
	int     x86_tlbsize;
	__u8    x86_virt_bits, x86_phys_bits;
	/* cpuid returned core id bits */
	__u8    x86_coreid_bits;
	/* Max extended CPUID function supported */
	__u32   extended_cpuid_level;
#endif
	int	cpuid_level;	/* Maximum supported CPUID level, -1=no CPUID */
	__u32	x86_capability[NCAPINTS];
	char	x86_vendor_id[16];
	char	x86_model_id[64];
	int 	x86_cache_size;  /* in KB - valid for CPUS which support this
				    call  */
	int 	x86_cache_alignment;	/* In bytes */
	int	x86_power;
	unsigned long loops_per_jiffy;
#ifdef CONFIG_SMP
	cpumask_t llc_shared_map;	/* cpus sharing the last level cache */
#endif
	unsigned char x86_max_cores;	/* cpuid returned max cores value */
	unsigned char apicid;
	unsigned short x86_clflush_size;
#ifdef CONFIG_SMP
	unsigned char booted_cores;	/* number of cores as seen by OS */
	__u8 phys_proc_id; 		/* Physical processor id. */
	__u8 cpu_core_id;  		/* Core id */
	__u8 cpu_index;			/* index into per_cpu list */
#endif
} __attribute__((__aligned__(SMP_CACHE_BYTES)));

#define X86_VENDOR_INTEL 0
#define X86_VENDOR_CYRIX 1
#define X86_VENDOR_AMD 2
#define X86_VENDOR_UMC 3
#define X86_VENDOR_NEXGEN 4
#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

115 116 117
/*
 * capabilities of CPUs
 */
118
extern struct cpuinfo_x86 boot_cpu_data;
119 120
extern struct cpuinfo_x86 new_cpu_data;
extern struct tss_struct doublefault_tss;
121 122 123 124 125 126 127 128 129 130

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

131 132 133 134 135
void cpu_detect(struct cpuinfo_x86 *c);

extern void identify_cpu(struct cpuinfo_x86 *);
extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
136 137 138 139 140
extern void print_cpu_info(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern unsigned short num_cache_leaves;

141 142 143 144 145 146
#if defined(CONFIG_X86_HT) || defined(CONFIG_X86_64)
extern void detect_ht(struct cpuinfo_x86 *c);
#else
static inline void detect_ht(struct cpuinfo_x86 *c) {}
#endif

147 148 149 150 151 152 153 154 155 156 157 158
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__("cpuid"
		: "=a" (*eax),
		  "=b" (*ebx),
		  "=c" (*ecx),
		  "=d" (*edx)
		: "0" (*eax), "2" (*ecx));
}

159 160 161 162
static inline void load_cr3(pgd_t *pgdir)
{
	write_cr3(__pa(pgdir));
}
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
#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;
	unsigned short	ss1, __ss1h;	/* ss1 caches MSR_IA32_SYSENTER_CS */
	unsigned long	sp2;
	unsigned short	ss2, __ss2h;
	unsigned long	__cr3;
	unsigned long	ip;
	unsigned long	flags;
	unsigned long	ax, cx, dx, bx;
	unsigned long	sp, bp, si, 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, io_bitmap_base;
} __attribute__((packed));
#else
struct x86_hw_tss {
	u32 reserved1;
	u64 sp0;
	u64 sp1;
	u64 sp2;
	u64 reserved2;
	u64 ist[7];
	u32 reserved3;
	u32 reserved4;
	u16 reserved5;
	u16 io_bitmap_base;
} __attribute__((packed)) ____cacheline_aligned;
#endif

/*
 * Size of io_bitmap.
 */
#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)
#define INVALID_IO_BITMAP_OFFSET 0x8000
#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000

struct tss_struct {
	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];
	/*
	 * Cache the current maximum and the last task that used the bitmap:
	 */
	unsigned long io_bitmap_max;
	struct thread_struct *io_bitmap_owner;
	/*
	 * pads the TSS to be cacheline-aligned (size is 0x100)
	 */
	unsigned long __cacheline_filler[35];
	/*
	 * .. and then another 0x100 bytes for emergency kernel stack
	 */
	unsigned long stack[64];
} __attribute__((packed));

DECLARE_PER_CPU(struct tss_struct, init_tss);

240 241 242 243 244
/* Save the original ist values for checking stack pointers during debugging */
struct orig_ist {
	unsigned long ist[7];
};

R
Roland McGrath 已提交
245
#define	MXCSR_DEFAULT		0x1f80
246

R
Roland McGrath 已提交
247 248 249 250 251 252 253 254 255 256
struct i387_fsave_struct {
	u32	cwd;
	u32	swd;
	u32	twd;
	u32	fip;
	u32	fcs;
	u32	foo;
	u32	fos;
	u32	st_space[20];	/* 8*10 bytes for each FP-reg = 80 bytes */
	u32	status;		/* software status information */
257 258 259 260 261 262 263
};

struct i387_fxsave_struct {
	u16	cwd;
	u16	swd;
	u16	twd;
	u16	fop;
R
Roland McGrath 已提交
264 265 266 267 268 269 270 271 272 273 274 275
	union {
		struct {
			u64	rip;
			u64	rdp;
		};
		struct {
			u32	fip;
			u32	fcs;
			u32	foo;
			u32	fos;
		};
	};
276 277 278 279 280 281 282
	u32	mxcsr;
	u32	mxcsr_mask;
	u32	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
	u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg = 256 bytes */
	u32	padding[24];
} __attribute__((aligned(16)));

R
Roland McGrath 已提交
283 284 285 286 287 288 289 290 291 292 293 294 295 296
struct i387_soft_struct {
	u32	cwd;
	u32	swd;
	u32	twd;
	u32	fip;
	u32	fcs;
	u32	foo;
	u32	fos;
	u32	st_space[20];	/* 8*10 bytes for each FP-reg = 80 bytes */
	u8	ftop, changed, lookahead, no_update, rm, alimit;
	struct info	*info;
	u32	entry_eip;
};

297
union i387_union {
R
Roland McGrath 已提交
298
	struct i387_fsave_struct	fsave;
299
	struct i387_fxsave_struct	fxsave;
R
Roland McGrath 已提交
300
	struct i387_soft_struct 	soft;
301 302
};

R
Roland McGrath 已提交
303
#ifdef CONFIG_X86_32
304 305 306 307 308
/*
 * the following now lives in the per cpu area:
 * extern	int cpu_llc_id[NR_CPUS];
 */
DECLARE_PER_CPU(u8, cpu_llc_id);
R
Roland McGrath 已提交
309
#else
310
DECLARE_PER_CPU(struct orig_ist, orig_ist);
311
#endif
312

313 314 315 316 317
extern void print_cpu_info(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern unsigned short num_cache_leaves;

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
struct thread_struct {
/* cached TLS descriptors. */
	struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
	unsigned long	sp0;
	unsigned long	sp;
#ifdef CONFIG_X86_32
	unsigned long	sysenter_cs;
#else
	unsigned long 	usersp;	/* Copy from PDA */
	unsigned short	es, ds, fsindex, gsindex;
#endif
	unsigned long	ip;
	unsigned long	fs;
	unsigned long	gs;
/* Hardware debugging registers */
	unsigned long	debugreg0;
	unsigned long	debugreg1;
	unsigned long	debugreg2;
	unsigned long	debugreg3;
	unsigned long	debugreg6;
	unsigned long	debugreg7;
/* fault info */
	unsigned long	cr2, trap_no, error_code;
/* floating point info */
	union i387_union	i387 __attribute__((aligned(16)));;
#ifdef CONFIG_X86_32
/* virtual 86 mode info */
	struct vm86_struct __user *vm86_info;
	unsigned long		screen_bitmap;
	unsigned long		v86flags, v86mask, saved_sp0;
	unsigned int		saved_fs, saved_gs;
#endif
/* IO permissions */
	unsigned long	*io_bitmap_ptr;
	unsigned long	iopl;
/* max allowed port in the bitmap, in bytes: */
	unsigned io_bitmap_max;
/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
	unsigned long	debugctlmsr;
/* Debug Store - if not 0 points to a DS Save Area configuration;
 *               goes into MSR_IA32_DS_AREA */
	unsigned long	ds_area_msr;
};

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
static inline unsigned long native_get_debugreg(int regno)
{
	unsigned long val = 0; 	/* Damn you, gcc! */

	switch (regno) {
	case 0:
		asm("mov %%db0, %0" :"=r" (val)); break;
	case 1:
		asm("mov %%db1, %0" :"=r" (val)); break;
	case 2:
		asm("mov %%db2, %0" :"=r" (val)); break;
	case 3:
		asm("mov %%db3, %0" :"=r" (val)); break;
	case 6:
		asm("mov %%db6, %0" :"=r" (val)); break;
	case 7:
		asm("mov %%db7, %0" :"=r" (val)); break;
	default:
		BUG();
	}
	return val;
}

static inline void native_set_debugreg(int regno, unsigned long value)
{
	switch (regno) {
	case 0:
		asm("mov %0,%%db0"	: /* no output */ :"r" (value));
		break;
	case 1:
		asm("mov %0,%%db1"	: /* no output */ :"r" (value));
		break;
	case 2:
		asm("mov %0,%%db2"	: /* no output */ :"r" (value));
		break;
	case 3:
		asm("mov %0,%%db3"	: /* no output */ :"r" (value));
		break;
	case 6:
		asm("mov %0,%%db6"	: /* no output */ :"r" (value));
		break;
	case 7:
		asm("mov %0,%%db7"	: /* no output */ :"r" (value));
		break;
	default:
		BUG();
	}
}

411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428
/*
 * 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
}

429 430 431 432 433 434 435 436 437 438 439 440
static inline void native_load_sp0(struct tss_struct *tss,
				   struct thread_struct *thread)
{
	tss->x86_tss.sp0 = thread->sp0;
#ifdef CONFIG_X86_32
	/* Only happens when SEP is enabled, no need to test "SEP"arately */
	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
		tss->x86_tss.ss1 = thread->sysenter_cs;
		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
	}
#endif
}
441

442 443 444 445 446 447 448
static inline void native_swapgs(void)
{
#ifdef CONFIG_X86_64
	asm volatile("swapgs" ::: "memory");
#endif
}

449 450 451
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
452
#define __cpuid native_cpuid
453 454 455 456 457 458 459 460 461 462
#define paravirt_enabled() 0

/*
 * These special macros can be used to get or set a debugging register
 */
#define get_debugreg(var, register)				\
	(var) = native_get_debugreg(register)
#define set_debugreg(value, register)				\
	native_set_debugreg(register, value)

463 464 465 466 467 468
static inline void load_sp0(struct tss_struct *tss,
			    struct thread_struct *thread)
{
	native_load_sp0(tss, thread);
}

469
#define set_iopl_mask native_set_iopl_mask
470
#define SWAPGS	swapgs
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
#endif /* CONFIG_PARAVIRT */

/*
 * Save the cr4 feature set we're using (ie
 * Pentium 4MB enable and PPro Global page
 * enable), so that any CPU's that boot up
 * after us can get the correct flags.
 */
extern unsigned long mmu_cr4_features;

static inline void set_in_cr4(unsigned long mask)
{
	unsigned cr4;
	mmu_cr4_features |= mask;
	cr4 = read_cr4();
	cr4 |= mask;
	write_cr4(cr4);
}

static inline void clear_in_cr4(unsigned long mask)
{
	unsigned cr4;
	mmu_cr4_features &= ~mask;
	cr4 = read_cr4();
	cr4 &= ~mask;
	write_cr4(cr4);
}

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
struct microcode_header {
	unsigned int hdrver;
	unsigned int rev;
	unsigned int date;
	unsigned int sig;
	unsigned int cksum;
	unsigned int ldrver;
	unsigned int pf;
	unsigned int datasize;
	unsigned int totalsize;
	unsigned int reserved[3];
};

struct microcode {
	struct microcode_header hdr;
	unsigned int bits[0];
};

typedef struct microcode microcode_t;
typedef struct microcode_header microcode_header_t;

/* microcode format is extended from prescott processors */
struct extended_signature {
	unsigned int sig;
	unsigned int pf;
	unsigned int cksum;
};

struct extended_sigtable {
	unsigned int count;
	unsigned int cksum;
	unsigned int reserved[3];
	struct extended_signature sigs[0];
};

534 535 536 537 538
typedef struct {
	unsigned long seg;
} mm_segment_t;


539 540 541 542 543 544 545 546 547 548
/*
 * create a kernel thread without removing it from tasklists
 */
extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);

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

/* Prepare to copy thread state - unlazy all lazy status */
extern void prepare_to_copy(struct task_struct *tsk);
549

550
unsigned long get_wchan(struct task_struct *p);
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

/*
 * 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;
}

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

/* Stop speculative execution */
static inline void sync_core(void)
{
	int tmp;
	asm volatile("cpuid" : "=a" (tmp) : "0" (1)
					  : "ebx", "ecx", "edx", "memory");
}

#define cpu_relax()   rep_nop()

static inline void __monitor(const void *eax, unsigned long ecx,
		unsigned long edx)
{
	/* "monitor %eax,%ecx,%edx;" */
	asm volatile(
		".byte 0x0f,0x01,0xc8;"
		: :"a" (eax), "c" (ecx), "d"(edx));
}

static inline void __mwait(unsigned long eax, unsigned long ecx)
{
	/* "mwait %eax,%ecx;" */
	asm volatile(
		".byte 0x0f,0x01,0xc9;"
		: :"a" (eax), "c" (ecx));
}

static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
{
	/* "mwait %eax,%ecx;" */
	asm volatile(
		"sti; .byte 0x0f,0x01,0xc9;"
		: :"a" (eax), "c" (ecx));
}

extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);

extern int force_mwait;

extern void select_idle_routine(const struct cpuinfo_x86 *c);

extern unsigned long boot_option_idle_override;

657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
extern void enable_sep_cpu(void);
extern int sysenter_setup(void);

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

extern void cpu_set_gdt(int);
extern void switch_to_new_gdt(void);
extern void cpu_init(void);
extern void init_gdt(int cpu);

/* from system description table in BIOS.  Mostly for MCA use, but
 * others may find it useful. */
extern unsigned int machine_id;
extern unsigned int machine_submodel_id;
extern unsigned int BIOS_revision;
extern unsigned int mca_pentium_flag;

675 676
/* Boot loader type from the setup header */
extern int bootloader_type;
677 678

extern char ignore_fpu_irq;
679 680 681 682 683 684
#define cache_line_size() (boot_cpu_data.x86_cache_alignment)

#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
#define ARCH_HAS_PREFETCHW
#define ARCH_HAS_SPINLOCK_PREFETCH

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
#ifdef CONFIG_X86_32
#define BASE_PREFETCH	ASM_NOP4
#define ARCH_HAS_PREFETCH
#else
#define BASE_PREFETCH	"prefetcht0 (%1)"
#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.
   However we don't do prefetches for pre XP Athlons currently
   That should be fixed. */
static inline void prefetch(const void *x)
{
	alternative_input(BASE_PREFETCH,
			  "prefetchnta (%1)",
			  X86_FEATURE_XMM,
			  "r" (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 (%1)",
			  X86_FEATURE_3DNOW,
			  "r" (x));
}

715
#define spin_lock_prefetch(x)	prefetchw(x)
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
#ifdef CONFIG_X86_32
/*
 * User space process size: 3GB (default).
 */
#define TASK_SIZE	(PAGE_OFFSET)

#define INIT_THREAD  {							\
	.sp0 = sizeof(init_stack) + (long)&init_stack,			\
	.vm86_info = NULL,						\
	.sysenter_cs = __KERNEL_CS,					\
	.io_bitmap_ptr = NULL,						\
	.fs = __KERNEL_PERCPU,						\
}

/*
 * Note that the .io_bitmap member must be extra-big. This is 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.
 */
#define INIT_TSS  {							\
	.x86_tss = {							\
		.sp0		= sizeof(init_stack) + (long)&init_stack, \
		.ss0		= __KERNEL_DS,				\
		.ss1		= __KERNEL_CS,				\
		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,		\
	 },								\
	.io_bitmap	= { [0 ... IO_BITMAP_LONGS] = ~0 },		\
}

#define start_thread(regs, new_eip, new_esp) do {		\
	__asm__("movl %0,%%gs": :"r" (0));			\
	regs->fs = 0;						\
	set_fs(USER_DS);					\
	regs->ds = __USER_DS;					\
	regs->es = __USER_DS;					\
	regs->ss = __USER_DS;					\
	regs->cs = __USER_CS;					\
	regs->ip = new_eip;					\
	regs->sp = new_esp;					\
} while (0)


extern unsigned long thread_saved_pc(struct task_struct *tsk);

#define THREAD_SIZE_LONGS      (THREAD_SIZE/sizeof(unsigned long))
#define KSTK_TOP(info)                                                 \
({                                                                     \
       unsigned long *__ptr = (unsigned long *)(info);                 \
       (unsigned long)(&__ptr[THREAD_SIZE_LONGS]);                     \
})

/*
 * The below -8 is to reserve 8 bytes on top of the ring0 stack.
 * This is necessary to guarantee that the entire "struct pt_regs"
 * is accessable even if the CPU haven't stored the SS/ESP registers
 * on the stack (interrupt gate does not save these registers
 * when switching to the same priv ring).
 * Therefore beware: accessing the ss/esp fields of the
 * "struct pt_regs" is possible, but they may contain the
 * completely wrong values.
 */
#define task_pt_regs(task)                                             \
({                                                                     \
       struct pt_regs *__regs__;                                       \
       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
       __regs__ - 1;                                                   \
})

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

#else
/*
 * User space process size. 47bits minus one guard page.
 */
#define TASK_SIZE64	(0x800000000000UL - 4096)

/* 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 		(test_thread_flag(TIF_IA32) ? \
				 IA32_PAGE_OFFSET : TASK_SIZE64)
#define TASK_SIZE_OF(child) 	((test_tsk_thread_flag(child, TIF_IA32)) ? \
				  IA32_PAGE_OFFSET : TASK_SIZE64)

#define INIT_THREAD  { \
	.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
}

#define INIT_TSS  { \
	.x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
}

#define start_thread(regs, new_rip, new_rsp) do { 			     \
	asm volatile("movl %0,%%fs; movl %0,%%es; movl %0,%%ds": :"r" (0));  \
	load_gs_index(0);						     \
	(regs)->ip = (new_rip);						     \
	(regs)->sp = (new_rsp);						     \
	write_pda(oldrsp, (new_rsp));					     \
	(regs)->cs = __USER_CS;						     \
	(regs)->ss = __USER_DS;						     \
	(regs)->flags = 0x200;						     \
	set_fs(USER_DS);						     \
} while (0)

/*
 * Return saved PC of a blocked thread.
 * What is this good for? it will be always the scheduler or ret_from_fork.
 */
#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.sp - 8))

#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
#define KSTK_ESP(tsk) -1 /* sorry. doesn't work for syscall. */
#endif /* CONFIG_X86_64 */

834 835 836 837 838 839 840
/* This decides where the kernel will search for a free chunk of vm
 * space during mmap's.
 */
#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))

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

841
#endif