diff options
| author | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-05-06 01:55:20 +0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-05-06 01:55:20 +0400 |
| commit | ea62ccd00fd0b6720b033adfc9984f31130ce195 (patch) | |
| tree | 9837b797b2466fffcb0af96c388b06eae9c3df18 /include/asm-i386 | |
| parent | 886a0768affe9a32f18c45f8e1393bca9ece5392 (diff) | |
| parent | 35060b6a9a4e1c89bc6fbea61090e302dbc61847 (diff) | |
| download | linux-ea62ccd00fd0b6720b033adfc9984f31130ce195.tar.xz | |
Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6
* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (231 commits)
[PATCH] i386: Don't delete cpu_devs data to identify different x86 types in late_initcall
[PATCH] i386: type may be unused
[PATCH] i386: Some additional chipset register values validation.
[PATCH] i386: Add missing !X86_PAE dependincy to the 2G/2G split.
[PATCH] x86-64: Don't exclude asm-offsets.c in Documentation/dontdiff
[PATCH] i386: avoid redundant preempt_disable in __unlazy_fpu
[PATCH] i386: white space fixes in i387.h
[PATCH] i386: Drop noisy e820 debugging printks
[PATCH] x86-64: Fix allnoconfig error in genapic_flat.c
[PATCH] x86-64: Shut up warnings for vfat compat ioctls on other file systems
[PATCH] x86-64: Share identical video.S between i386 and x86-64
[PATCH] x86-64: Remove CONFIG_REORDER
[PATCH] x86-64: Print type and size correctly for unknown compat ioctls
[PATCH] i386: Remove copy_*_user BUG_ONs for (size < 0)
[PATCH] i386: Little cleanups in smpboot.c
[PATCH] x86-64: Don't enable NUMA for a single node in K8 NUMA scanning
[PATCH] x86: Use RDTSCP for synchronous get_cycles if possible
[PATCH] i386: Add X86_FEATURE_RDTSCP
[PATCH] i386: Implement X86_FEATURE_SYNC_RDTSC on i386
[PATCH] i386: Implement alternative_io for i386
...
Fix up trivial conflict in include/linux/highmem.h manually.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/asm-i386')
57 files changed, 2130 insertions, 1230 deletions
diff --git a/include/asm-i386/Kbuild b/include/asm-i386/Kbuild index 5ae93afc67e1..cbf6e8f1087b 100644 --- a/include/asm-i386/Kbuild +++ b/include/asm-i386/Kbuild @@ -3,8 +3,10 @@ include include/asm-generic/Kbuild.asm header-y += boot.h header-y += debugreg.h header-y += ldt.h +header-y += msr-index.h header-y += ptrace-abi.h header-y += ucontext.h +unifdef-y += msr.h unifdef-y += mtrr.h unifdef-y += vm86.h diff --git a/include/asm-i386/alternative.h b/include/asm-i386/alternative.h index b8fa9557c532..0f70b379b029 100644 --- a/include/asm-i386/alternative.h +++ b/include/asm-i386/alternative.h @@ -1,8 +1,6 @@ #ifndef _I386_ALTERNATIVE_H #define _I386_ALTERNATIVE_H -#ifdef __KERNEL__ - #include <asm/types.h> #include <linux/stddef.h> #include <linux/types.h> @@ -16,6 +14,7 @@ struct alt_instr { u8 pad; }; +extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); struct module; @@ -31,9 +30,7 @@ static inline void alternatives_smp_module_add(struct module *mod, char *name, void *text, void *text_end) {} static inline void alternatives_smp_module_del(struct module *mod) {} static inline void alternatives_smp_switch(int smp) {} -#endif - -#endif +#endif /* CONFIG_SMP */ /* * Alternative instructions for different CPU types or capabilities. @@ -85,6 +82,21 @@ static inline void alternatives_smp_switch(int smp) {} "663:\n\t" newinstr "\n664:\n" /* replacement */\ ".previous" :: "i" (feature), ##input) +/* Like alternative_input, but with a single output argument */ +#define alternative_io(oldinstr, newinstr, feature, output, input...) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 4\n" \ + " .long 661b\n" /* label */ \ + " .long 663f\n" /* new instruction */ \ + " .byte %c[feat]\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" : output : [feat] "i" (feature), ##input) + /* * Alternative inline assembly for SMP. * @@ -118,15 +130,17 @@ static inline void alternatives_smp_switch(int smp) {} #define LOCK_PREFIX "" #endif -struct paravirt_patch; +struct paravirt_patch_site; #ifdef CONFIG_PARAVIRT -void apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end); +void apply_paravirt(struct paravirt_patch_site *start, + struct paravirt_patch_site *end); #else static inline void -apply_paravirt(struct paravirt_patch *start, struct paravirt_patch *end) +apply_paravirt(struct paravirt_patch_site *start, + struct paravirt_patch_site *end) {} -#define __start_parainstructions NULL -#define __stop_parainstructions NULL +#define __parainstructions NULL +#define __parainstructions_end NULL #endif #endif /* _I386_ALTERNATIVE_H */ diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h index a19810a08ae9..1e8f6f252dd3 100644 --- a/include/asm-i386/apic.h +++ b/include/asm-i386/apic.h @@ -2,6 +2,7 @@ #define __ASM_APIC_H #include <linux/pm.h> +#include <linux/delay.h> #include <asm/fixmap.h> #include <asm/apicdef.h> #include <asm/processor.h> @@ -64,12 +65,8 @@ static __inline fastcall unsigned long native_apic_read(unsigned long reg) return *((volatile unsigned long *)(APIC_BASE+reg)); } -static __inline__ void apic_wait_icr_idle(void) -{ - while ( apic_read( APIC_ICR ) & APIC_ICR_BUSY ) - cpu_relax(); -} - +void apic_wait_icr_idle(void); +unsigned long safe_apic_wait_icr_idle(void); int get_physical_broadcast(void); #ifdef CONFIG_X86_GOOD_APIC diff --git a/include/asm-i386/bugs.h b/include/asm-i386/bugs.h index c90c7c499302..d28979ff73be 100644 --- a/include/asm-i386/bugs.h +++ b/include/asm-i386/bugs.h @@ -1,198 +1,12 @@ /* - * include/asm-i386/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - * - * Cyrix stuff, June 1998 by: - * - Rafael R. Reilova (moved everything from head.S), - * <rreilova@ececs.uc.edu> - * - Channing Corn (tests & fixes), - * - Andrew D. Balsa (code cleanup). - */ - -/* * This is included by init/main.c to check for architecture-dependent bugs. * * Needs: * void check_bugs(void); */ +#ifndef _ASM_I386_BUG_H +#define _ASM_I386_BUG_H -#include <linux/init.h> -#include <asm/processor.h> -#include <asm/i387.h> -#include <asm/msr.h> -#include <asm/paravirt.h> - -static int __init no_halt(char *s) -{ - boot_cpu_data.hlt_works_ok = 0; - return 1; -} - -__setup("no-hlt", no_halt); - -static int __init mca_pentium(char *s) -{ - mca_pentium_flag = 1; - return 1; -} - -__setup("mca-pentium", mca_pentium); - -static int __init no_387(char *s) -{ - boot_cpu_data.hard_math = 0; - write_cr0(0xE | read_cr0()); - return 1; -} - -__setup("no387", no_387); - -static double __initdata x = 4195835.0; -static double __initdata y = 3145727.0; - -/* - * This used to check for exceptions.. - * However, it turns out that to support that, - * the XMM trap handlers basically had to - * be buggy. So let's have a correct XMM trap - * handler, and forget about printing out - * some status at boot. - * - * We should really only care about bugs here - * anyway. Not features. - */ -static void __init check_fpu(void) -{ - if (!boot_cpu_data.hard_math) { -#ifndef CONFIG_MATH_EMULATION - printk(KERN_EMERG "No coprocessor found and no math emulation present.\n"); - printk(KERN_EMERG "Giving up.\n"); - for (;;) ; -#endif - return; - } - -/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */ - /* Test for the divl bug.. */ - __asm__("fninit\n\t" - "fldl %1\n\t" - "fdivl %2\n\t" - "fmull %2\n\t" - "fldl %1\n\t" - "fsubp %%st,%%st(1)\n\t" - "fistpl %0\n\t" - "fwait\n\t" - "fninit" - : "=m" (*&boot_cpu_data.fdiv_bug) - : "m" (*&x), "m" (*&y)); - if (boot_cpu_data.fdiv_bug) - printk("Hmm, FPU with FDIV bug.\n"); -} - -static void __init check_hlt(void) -{ - if (paravirt_enabled()) - return; - - printk(KERN_INFO "Checking 'hlt' instruction... "); - if (!boot_cpu_data.hlt_works_ok) { - printk("disabled\n"); - return; - } - halt(); - halt(); - halt(); - halt(); - printk("OK.\n"); -} - -/* - * Most 386 processors have a bug where a POPAD can lock the - * machine even from user space. - */ - -static void __init check_popad(void) -{ -#ifndef CONFIG_X86_POPAD_OK - int res, inp = (int) &res; - - printk(KERN_INFO "Checking for popad bug... "); - __asm__ __volatile__( - "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " - : "=&a" (res) - : "d" (inp) - : "ecx", "edi" ); - /* If this fails, it means that any user program may lock the CPU hard. Too bad. */ - if (res != 12345678) printk( "Buggy.\n" ); - else printk( "OK.\n" ); -#endif -} - -/* - * Check whether we are able to run this kernel safely on SMP. - * - * - In order to run on a i386, we need to be compiled for i386 - * (for due to lack of "invlpg" and working WP on a i386) - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - * - In order to support the local APIC on a buggy Pentium machine, - * we need to be compiled with CONFIG_X86_GOOD_APIC disabled, - * which happens implicitly if compiled for a Pentium or lower - * (unless an advanced selection of CPU features is used) as an - * otherwise config implies a properly working local APIC without - * the need to do extra reads from the APIC. -*/ - -static void __init check_config(void) -{ -/* - * We'd better not be a i386 if we're configured to use some - * i486+ only features! (WP works in supervisor mode and the - * new "invlpg" and "bswap" instructions) - */ -#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_BSWAP) - if (boot_cpu_data.x86 == 3) - panic("Kernel requires i486+ for 'invlpg' and other features"); -#endif - -/* - * If we configured ourselves for a TSC, we'd better have one! - */ -#ifdef CONFIG_X86_TSC - if (!cpu_has_tsc && !tsc_disable) - panic("Kernel compiled for Pentium+, requires TSC feature!"); -#endif - -/* - * If we were told we had a good local APIC, check for buggy Pentia, - * i.e. all B steppings and the C2 stepping of P54C when using their - * integrated APIC (see 11AP erratum in "Pentium Processor - * Specification Update"). - */ -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_GOOD_APIC) - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL - && cpu_has_apic - && boot_cpu_data.x86 == 5 - && boot_cpu_data.x86_model == 2 - && (boot_cpu_data.x86_mask < 6 || boot_cpu_data.x86_mask == 11)) - panic("Kernel compiled for PMMX+, assumes a local APIC without the read-before-write bug!"); -#endif -} - -extern void alternative_instructions(void); +void check_bugs(void); -static void __init check_bugs(void) -{ - identify_cpu(&boot_cpu_data); -#ifndef CONFIG_SMP - printk("CPU: "); - print_cpu_info(&boot_cpu_data); -#endif - check_config(); - check_fpu(); - check_hlt(); - check_popad(); - init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); -} +#endif /* _ASM_I386_BUG_H */ diff --git a/include/asm-i386/cpufeature.h b/include/asm-i386/cpufeature.h index d1b8e4ab6c1a..f514e906643a 100644 --- a/include/asm-i386/cpufeature.h +++ b/include/asm-i386/cpufeature.h @@ -7,7 +7,10 @@ #ifndef __ASM_I386_CPUFEATURE_H #define __ASM_I386_CPUFEATURE_H +#ifndef __ASSEMBLY__ #include <linux/bitops.h> +#endif +#include <asm/required-features.h> #define NCAPINTS 7 /* N 32-bit words worth of info */ @@ -49,6 +52,7 @@ #define X86_FEATURE_MP (1*32+19) /* MP Capable. */ #define X86_FEATURE_NX (1*32+20) /* Execute Disable */ #define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_RDTSCP (1*32+27) /* RDTSCP */ #define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */ #define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */ #define X86_FEATURE_3DNOW (1*32+31) /* 3DNow! */ @@ -76,6 +80,7 @@ #define X86_FEATURE_PEBS (3*32+12) /* Precise-Event Based Sampling */ #define X86_FEATURE_BTS (3*32+13) /* Branch Trace Store */ #define X86_FEATURE_LAPIC_TIMER_BROKEN (3*32+ 14) /* lapic timer broken in C1 */ +#define X86_FEATURE_SYNC_RDTSC (3*32+15) /* RDTSC synchronizes the CPU */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* Streaming SIMD Extensions-3 */ @@ -103,8 +108,12 @@ #define X86_FEATURE_LAHF_LM (6*32+ 0) /* LAHF/SAHF in long mode */ #define X86_FEATURE_CMP_LEGACY (6*32+ 1) /* If yes HyperThreading not valid */ -#define cpu_has(c, bit) test_bit(bit, (c)->x86_capability) -#define boot_cpu_has(bit) test_bit(bit, boot_cpu_data.x86_capability) +#define cpu_has(c, bit) \ + ((__builtin_constant_p(bit) && (bit) < 32 && \ + (1UL << (bit)) & REQUIRED_MASK1) ? \ + 1 : \ + test_bit(bit, (c)->x86_capability)) +#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) #define cpu_has_vme boot_cpu_has(X86_FEATURE_VME) diff --git a/include/asm-i386/current.h b/include/asm-i386/current.h index 5252ee0f6d7a..d35248539912 100644 --- a/include/asm-i386/current.h +++ b/include/asm-i386/current.h @@ -1,14 +1,15 @@ #ifndef _I386_CURRENT_H #define _I386_CURRENT_H -#include <asm/pda.h> #include <linux/compiler.h> +#include <asm/percpu.h> struct task_struct; +DECLARE_PER_CPU(struct task_struct *, current_task); static __always_inline struct task_struct *get_current(void) { - return read_pda(pcurrent); + return x86_read_percpu(current_task); } #define current get_current() diff --git a/include/asm-i386/desc.h b/include/asm-i386/desc.h index 050831f34f71..c547403f341d 100644 --- a/include/asm-i386/desc.h +++ b/include/asm-i386/desc.h @@ -12,23 +12,24 @@ #include <asm/mmu.h> -extern struct desc_struct cpu_gdt_table[GDT_ENTRIES]; - struct Xgt_desc_struct { unsigned short size; unsigned long address __attribute__((packed)); unsigned short pad; } __attribute__ ((packed)); -extern struct Xgt_desc_struct idt_descr; -DECLARE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr); -extern struct Xgt_desc_struct early_gdt_descr; +struct gdt_page +{ + struct desc_struct gdt[GDT_ENTRIES]; +} __attribute__((aligned(PAGE_SIZE))); +DECLARE_PER_CPU(struct gdt_page, gdt_page); static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) { - return (struct desc_struct *)per_cpu(cpu_gdt_descr, cpu).address; + return per_cpu(gdt_page, cpu).gdt; } +extern struct Xgt_desc_struct idt_descr; extern struct desc_struct idt_table[]; extern void set_intr_gate(unsigned int irq, void * addr); @@ -58,45 +59,33 @@ static inline void pack_gate(__u32 *a, __u32 *b, #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else -#define load_TR_desc() __asm__ __volatile__("ltr %w0"::"q" (GDT_ENTRY_TSS*8)) - -#define load_gdt(dtr) __asm__ __volatile("lgdt %0"::"m" (*dtr)) -#define load_idt(dtr) __asm__ __volatile("lidt %0"::"m" (*dtr)) +#define load_TR_desc() native_load_tr_desc() +#define load_gdt(dtr) native_load_gdt(dtr) +#define load_idt(dtr) native_load_idt(dtr) #define load_tr(tr) __asm__ __volatile("ltr %0"::"m" (tr)) #define load_ldt(ldt) __asm__ __volatile("lldt %0"::"m" (ldt)) -#define store_gdt(dtr) __asm__ ("sgdt %0":"=m" (*dtr)) -#define store_idt(dtr) __asm__ ("sidt %0":"=m" (*dtr)) -#define store_tr(tr) __asm__ ("str %0":"=m" (tr)) +#define store_gdt(dtr) native_store_gdt(dtr) +#define store_idt(dtr) native_store_idt(dtr) +#define store_tr(tr) (tr = native_store_tr()) #define store_ldt(ldt) __asm__ ("sldt %0":"=m" (ldt)) -#if TLS_SIZE != 24 -# error update this code. -#endif - -static inline void load_TLS(struct thread_struct *t, unsigned int cpu) -{ -#define C(i) get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i] - C(0); C(1); C(2); -#undef C -} +#define load_TLS(t, cpu) native_load_tls(t, cpu) +#define set_ldt native_set_ldt #define write_ldt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b) #define write_gdt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b) #define write_idt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b) +#endif -static inline void write_dt_entry(void *dt, int entry, __u32 entry_a, __u32 entry_b) +static inline void write_dt_entry(struct desc_struct *dt, + int entry, u32 entry_low, u32 entry_high) { - __u32 *lp = (__u32 *)((char *)dt + entry*8); - *lp = entry_a; - *(lp+1) = entry_b; + dt[entry].a = entry_low; + dt[entry].b = entry_high; } -#define set_ldt native_set_ldt -#endif /* CONFIG_PARAVIRT */ - -static inline fastcall void native_set_ldt(const void *addr, - unsigned int entries) +static inline void native_set_ldt(const void *addr, unsigned int entries) { if (likely(entries == 0)) __asm__ __volatile__("lldt %w0"::"q" (0)); @@ -112,6 +101,48 @@ static inline fastcall void native_set_ldt(const void *addr, } } + +static inline void native_load_tr_desc(void) +{ + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); +} + +static inline void native_load_gdt(const struct Xgt_desc_struct *dtr) +{ + asm volatile("lgdt %0"::"m" (*dtr)); +} + +static inline void native_load_idt(const struct Xgt_desc_struct *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +static inline void native_store_gdt(struct Xgt_desc_struct *dtr) +{ + asm ("sgdt %0":"=m" (*dtr)); +} + +static inline void native_store_idt(struct Xgt_desc_struct *dtr) +{ + asm ("sidt %0":"=m" (*dtr)); +} + +static inline unsigned long native_store_tr(void) +{ + unsigned long tr; + asm ("str %0":"=r" (tr)); + return tr; +} + +static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) +{ + unsigned int i; + struct desc_struct *gdt = get_cpu_gdt_table(cpu); + + for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) + gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; +} + static inline void _set_gate(int gate, unsigned int type, void *addr, unsigned short seg) { __u32 a, b; diff --git a/include/asm-i386/e820.h b/include/asm-i386/e820.h index c5b8fc6109d6..096a2a8eb1da 100644 --- a/include/asm-i386/e820.h +++ b/include/asm-i386/e820.h @@ -38,6 +38,7 @@ extern struct e820map e820; extern int e820_all_mapped(unsigned long start, unsigned long end, unsigned type); +extern int e820_any_mapped(u64 start, u64 end, unsigned type); extern void find_max_pfn(void); extern void register_bootmem_low_pages(unsigned long max_low_pfn); extern void e820_register_memory(void); diff --git a/include/asm-i386/elf.h b/include/asm-i386/elf.h index 952b3ee3c9bb..d304ab4161ff 100644 --- a/include/asm-i386/elf.h +++ b/include/asm-i386/elf.h @@ -133,39 +133,31 @@ extern int dump_task_extended_fpu (struct task_struct *, struct user_fxsr_struct #define ELF_CORE_COPY_XFPREGS(tsk, elf_xfpregs) dump_task_extended_fpu(tsk, elf_xfpregs) #define VDSO_HIGH_BASE (__fix_to_virt(FIX_VDSO)) -#define VDSO_BASE ((unsigned long)current->mm->context.vdso) - -#ifdef CONFIG_COMPAT_VDSO -# define VDSO_COMPAT_BASE VDSO_HIGH_BASE -# define VDSO_PRELINK VDSO_HIGH_BASE -#else -# define VDSO_COMPAT_BASE VDSO_BASE -# define VDSO_PRELINK 0 -#endif +#define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso) +#define VDSO_PRELINK 0 #define VDSO_SYM(x) \ - (VDSO_COMPAT_BASE + (unsigned long)(x) - VDSO_PRELINK) + (VDSO_CURRENT_BASE + (unsigned long)(x) - VDSO_PRELINK) #define VDSO_HIGH_EHDR ((const struct elfhdr *) VDSO_HIGH_BASE) -#define VDSO_EHDR ((const struct elfhdr *) VDSO_COMPAT_BASE) +#define VDSO_EHDR ((const struct elfhdr *) VDSO_CURRENT_BASE) extern void __kernel_vsyscall; #define VDSO_ENTRY VDSO_SYM(&__kernel_vsyscall) -#ifndef CONFIG_COMPAT_VDSO -#define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; + +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES extern int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack); -#endif extern unsigned int vdso_enabled; -#define ARCH_DLINFO \ -do if (vdso_enabled) { \ - NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ - NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_COMPAT_BASE); \ +#define ARCH_DLINFO \ +do if (vdso_enabled) { \ + NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } while (0) #endif diff --git a/include/asm-i386/fixmap.h b/include/asm-i386/fixmap.h index 3e9f610c35df..80ea052ee3a4 100644 --- a/include/asm-i386/fixmap.h +++ b/include/asm-i386/fixmap.h @@ -19,13 +19,9 @@ * Leave one empty page between vmalloc'ed areas and * the start of the fixmap. */ -#ifndef CONFIG_COMPAT_VDSO extern unsigned long __FIXADDR_TOP; -#else -#define __FIXADDR_TOP 0xfffff000 -#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) -#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) -#endif +#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) +#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) #ifndef __ASSEMBLY__ #include <linux/kernel.h> @@ -88,6 +84,9 @@ enum fixed_addresses { #ifdef CONFIG_PCI_MMCONFIG FIX_PCIE_MCFG, #endif +#ifdef CONFIG_PARAVIRT + FIX_PARAVIRT_BOOTMAP, +#endif __end_of_permanent_fixed_addresses, /* temporary boot-time mappings, used before ioremap() is functional */ #define NR_FIX_BTMAPS 16 diff --git a/include/asm-i386/genapic.h b/include/asm-i386/genapic.h index fd2be593b06e..33e3ffe1766c 100644 --- a/include/asm-i386/genapic.h +++ b/include/asm-i386/genapic.h @@ -36,7 +36,7 @@ struct genapic { void (*init_apic_ldr)(void); physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map); - void (*clustered_apic_check)(void); + void (*setup_apic_routing)(void); int (*multi_timer_check)(int apic, int irq); int (*apicid_to_node)(int logical_apicid); int (*cpu_to_logical_apicid)(int cpu); @@ -99,7 +99,7 @@ struct genapic { APICFUNC(check_apicid_present) \ APICFUNC(init_apic_ldr) \ APICFUNC(ioapic_phys_id_map) \ - APICFUNC(clustered_apic_check) \ + APICFUNC(setup_apic_routing) \ APICFUNC(multi_timer_check) \ APICFUNC(apicid_to_node) \ APICFUNC(cpu_to_logical_apicid) \ @@ -122,6 +122,6 @@ struct genapic { APICFUNC(phys_pkg_id) \ } -extern struct genapic *genapic, apic_default; +extern struct genapic *genapic; #endif diff --git a/include/asm-i386/highmem.h b/include/asm-i386/highmem.h index e9a34ebc25d5..13cdcd66fff2 100644 --- a/include/asm-i386/highmem.h +++ b/include/asm-i386/highmem.h @@ -24,6 +24,7 @@ #include <linux/threads.h> #include <asm/kmap_types.h> #include <asm/tlbflush.h> +#include <asm/paravirt.h> /* declarations for highmem.c */ extern unsigned long highstart_pfn, highend_pfn; @@ -67,11 +68,16 @@ extern void FASTCALL(kunmap_high(struct page *page)); void *kmap(struct page *page); void kunmap(struct page *page); +void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot); void *kmap_atomic(struct page *page, enum km_type type); void kunmap_atomic(void *kvaddr, enum km_type type); void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); struct page *kmap_atomic_to_page(void *ptr); +#ifndef CONFIG_PARAVIRT +#define kmap_atomic_pte(page, type) kmap_atomic(page, type) +#endif + #define flush_cache_kmaps() do { } while (0) #endif /* __KERNEL__ */ diff --git a/include/asm-i386/hpet.h b/include/asm-i386/hpet.h index fc03cf9de5c4..dddeedf504b7 100644 --- a/include/asm-i386/hpet.h +++ b/include/asm-i386/hpet.h @@ -28,8 +28,6 @@ #include <linux/timex.h> -#include <asm/fixmap.h> - /* * Documentation on HPET can be found at: * http://www.intel.com/ial/home/sp/pcmmspec.htm diff --git a/include/asm-i386/i387.h b/include/asm-i386/i387.h index 434936c732d6..cdd1e248e3b4 100644 --- a/include/asm-i386/i387.h +++ b/include/asm-i386/i387.h @@ -74,17 +74,18 @@ static inline void __save_init_fpu( struct task_struct *tsk ) task_thread_info(tsk)->status &= ~TS_USEDFPU; } -#define __unlazy_fpu( tsk ) do { \ - if (task_thread_info(tsk)->status & TS_USEDFPU) \ - save_init_fpu( tsk ); \ - else \ - tsk->fpu_counter = 0; \ +#define __unlazy_fpu( tsk ) do { \ + if (task_thread_info(tsk)->status & TS_USEDFPU) { \ + __save_init_fpu(tsk); \ + stts(); \ + } else \ + tsk->fpu_counter = 0; \ } while (0) #define __clear_fpu( tsk ) \ do { \ - if (task_thread_info(tsk)->status & TS_USEDFPU) { \ - asm volatile("fnclex ; fwait"); \ + if (task_thread_info(tsk)->status & TS_USEDFPU) { \ + asm volatile("fnclex ; fwait"); \ task_thread_info(tsk)->status &= ~TS_USEDFPU; \ stts(); \ } \ @@ -113,7 +114,7 @@ static inline void save_init_fpu( struct task_struct *tsk ) __clear_fpu( tsk ); \ preempt_enable(); \ } while (0) - \ + /* * FPU state interaction... */ diff --git a/include/asm-i386/io.h b/include/asm-i386/io.h index 59fe616933c4..e797586a5bfc 100644 --- a/include/asm-i386/io.h +++ b/include/asm-i386/io.h @@ -250,19 +250,22 @@ static inline void flush_write_buffers(void) #endif /* __KERNEL__ */ +static inline void native_io_delay(void) +{ + asm volatile("outb %%al,$0x80" : : : "memory"); +} + #if defined(CONFIG_PARAVIRT) #include <asm/paravirt.h> #else -#define __SLOW_DOWN_IO "outb %%al,$0x80;" - static inline void slow_down_io(void) { - __asm__ __volatile__( - __SLOW_DOWN_IO + native_io_delay(); #ifdef REALLY_SLOW_IO - __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO + native_io_delay(); + native_io_delay(); + native_io_delay(); #endif - : : ); } #endif diff --git a/include/asm-i386/irq.h b/include/asm-i386/irq.h index 11761cdaae19..9e15ce0006eb 100644 --- a/include/asm-i386/irq.h +++ b/include/asm-i386/irq.h @@ -37,8 +37,6 @@ static __inline__ int irq_canonicalize(int irq) extern int irqbalance_disable(char *str); #endif -extern void quirk_intel_irqbalance(void); - #ifdef CONFIG_HOTPLUG_CPU extern void fixup_irqs(cpumask_t map); #endif diff --git a/include/asm-i386/irq_regs.h b/include/asm-i386/irq_regs.h index a1b3f7f594a2..3368b20c0b48 100644 --- a/include/asm-i386/irq_regs.h +++ b/include/asm-i386/irq_regs.h @@ -1,25 +1,27 @@ /* * Per-cpu current frame pointer - the location of the last exception frame on - * the stack, stored in the PDA. + * the stack, stored in the per-cpu area. * * Jeremy Fitzhardinge <jeremy@goop.org> */ #ifndef _ASM_I386_IRQ_REGS_H #define _ASM_I386_IRQ_REGS_H -#include <asm/pda.h> +#include <asm/percpu.h> + +DECLARE_PER_CPU(struct pt_regs *, irq_regs); static inline struct pt_regs *get_irq_regs(void) { - return read_pda(irq_regs); + return x86_read_percpu(irq_regs); } static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs) { struct pt_regs *old_regs; - old_regs = read_pda(irq_regs); - write_pda(irq_regs, new_regs); + old_regs = get_irq_regs(); + x86_write_percpu(irq_regs, new_regs); return old_regs; } diff --git a/include/asm-i386/irqflags.h b/include/asm-i386/irqflags.h index 17b18cf4fe9d..eff8585cb741 100644 --- a/include/asm-i386/irqflags.h +++ b/include/asm-i386/irqflags.h @@ -9,6 +9,43 @@ */ #ifndef _ASM_IRQFLAGS_H #define _ASM_IRQFLAGS_H +#include <asm/processor-flags.h> + +#ifndef __ASSEMBLY__ +static inline unsigned long native_save_fl(void) +{ + unsigned long f; + asm volatile("pushfl ; popl %0":"=g" (f): /* no input */); + return f; +} + +static inline void native_restore_fl(unsigned long f) +{ + asm volatile("pushl %0 ; popfl": /* no output */ + :"g" (f) + :"memory", "cc"); +} + +static inline void native_irq_disable(void) +{ + asm volatile("cli": : :"memory"); +} + +static inline void native_irq_enable(void) +{ + asm volatile("sti": : :"memory"); +} + +static inline void native_safe_halt(void) +{ + asm volatile("sti; hlt": : :"memory"); +} + +static inline void native_halt(void) +{ + asm volatile("hlt": : :"memory"); +} +#endif /* __ASSEMBLY__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> @@ -17,35 +54,22 @@ static inline unsigned long __raw_local_save_flags(void) { - unsigned long flags; - - __asm__ __volatile__( - "pushfl ; popl %0" - : "=g" (flags) - : /* no input */ - ); - - return flags; + return native_save_fl(); } static inline void raw_local_irq_restore(unsigned long flags) { - __asm__ __volatile__( - "pushl %0 ; popfl" - : /* no output */ - :"g" (flags) - :"memory", "cc" - ); + native_restore_fl(flags); } static inline void raw_local_irq_disable(void) { - __asm__ __volatile__("cli" : : : "memory"); + native_irq_disable(); } static inline void raw_local_irq_enable(void) { - __asm__ __volatile__("sti" : : : "memory"); + native_irq_enable(); } /* @@ -54,7 +78,7 @@ static inline void raw_local_irq_enable(void) */ static inline void raw_safe_halt(void) { - __asm__ __volatile__("sti; hlt" : : : "memory"); + native_safe_halt(); } /* @@ -63,7 +87,7 @@ static inline void raw_safe_halt(void) */ static inline void halt(void) { - __asm__ __volatile__("hlt": : :"memory"); + native_halt(); } /* @@ -96,7 +120,7 @@ static inline unsigned long __raw_local_irq_save(void) static inline int raw_irqs_disabled_flags(unsigned long flags) { - return !(flags & (1 << 9)); + return !(flags & X86_EFLAGS_IF); } static inline int raw_irqs_disabled(void) diff --git a/include/asm-i386/kexec.h b/include/asm-i386/kexec.h index 4dfc9f5ed031..bcb5b21de2d2 100644 --- a/include/asm-i386/kexec.h +++ b/include/asm-i386/kexec.h @@ -21,7 +21,6 @@ #ifndef __ASSEMBLY__ -#include <asm/fixmap.h> #include <asm/ptrace.h> #include <asm/string.h> @@ -29,10 +28,6 @@ * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return. * I.e. Maximum page that is mapped directly into kernel memory, * and kmap is not required. - * - * Someone correct me if FIXADDR_START - PAGEOFFSET is not the correct - * calculation for the amount of memory directly mappable into the - * kernel memory space. */ /* Maximum physical address we can use pages from */ @@ -47,6 +42,9 @@ /* The native architecture */ #define KEXEC_ARCH KEXEC_ARCH_386 +/* We can also handle crash dumps from 64 bit kernel. */ +#define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64) + #define MAX_NOTE_BYTES 1024 /* CPU does not save ss and esp on stack if execution is already diff --git a/include/asm-i386/mach-bigsmp/mach_apic.h b/include/asm-i386/mach-bigsmp/mach_apic.h index 18b19a773440..ebd319f838ab 100644 --- a/include/asm-i386/mach-bigsmp/mach_apic.h +++ b/include/asm-i386/mach-bigsmp/mach_apic.h @@ -71,7 +71,7 @@ static inline void init_apic_ldr(void) apic_write_around(APIC_LDR, val); } -static inline void clustered_apic_check(void) +static inline void setup_apic_routing(void) { printk("Enabling APIC mode: %s. Using %d I/O APICs\n", "Physflat", nr_ioapics); diff --git a/include/asm-i386/mach-default/mach_apic.h b/include/asm-i386/mach-default/mach_apic.h index 3ef6292db780..6db1c3babe9a 100644 --- a/include/asm-i386/mach-default/mach_apic.h +++ b/include/asm-i386/mach-default/mach_apic.h @@ -54,7 +54,7 @@ static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map) return phys_map; } -static inline void clustered_apic_check(void) +static inline void setup_apic_routing(void) { printk("Enabling APIC mode: %s. Using %d I/O APICs\n", "Flat", nr_ioapics); diff --git a/include/asm-i386/mach-es7000/mach_apic.h b/include/asm-i386/mach-es7000/mach_apic.h index 26333685a7fb..2d978928a395 100644 --- a/include/asm-i386/mach-es7000/mach_apic.h +++ b/include/asm-i386/mach-es7000/mach_apic.h @@ -73,15 +73,8 @@ static inline void init_apic_ldr(void) apic_write_around(APIC_LDR, val); } -extern void es7000_sw_apic(void); -static inline void enable_apic_mode(void) -{ - es7000_sw_apic(); - return; -} - extern int apic_version [MAX_APICS]; -static inline void clustered_apic_check(void) +static inline void setup_apic_routing(void) { int apic = bios_cpu_apicid[smp_processor_id()]; printk("Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", diff --git a/include/asm-i386/mach-es7000/mach_mpparse.h b/include/asm-i386/mach-es7000/mach_mpparse.h index 24990e546da3..b9fb784e1fd5 100644 --- a/include/asm-i386/mach-es7000/mach_mpparse.h +++ b/include/asm-i386/mach-es7000/mach_mpparse.h @@ -18,18 +18,6 @@ extern int parse_unisys_oem (char *oemptr); extern int find_unisys_acpi_oem_table(unsigned long *oem_addr); extern void setup_unisys(void); -static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, - char *productid) -{ - if (mpc->mpc_oemptr) { - struct mp_config_oemtable *oem_table = - (struct mp_config_oemtable *)mpc->mpc_oemptr; - if (!strncmp(oem, "UNISYS", 6)) - return parse_unisys_oem((char *)oem_table); - } - return 0; -} - #ifdef CONFIG_ACPI static inline int es7000_check_dsdt(void) @@ -41,26 +29,6 @@ static inline int es7000_check_dsdt(void) return 1; return 0; } - -/* Hook from generic ACPI tables.c */ -static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - unsigned long oem_addr; - if (!find_unisys_acpi_oem_table(&oem_addr)) { - if (es7000_check_dsdt()) - return parse_unisys_oem((char *)oem_addr); - else { - setup_unisys(); - return 1; - } - } - return 0; -} -#else -static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - return 0; -} #endif #endif /* __ASM_MACH_MPPARSE_H */ diff --git a/include/asm-i386/mach-generic/mach_apic.h b/include/asm-i386/mach-generic/mach_apic.h index d9dc039da94a..a236e7021528 100644 --- a/include/asm-i386/mach-generic/mach_apic.h +++ b/include/asm-i386/mach-generic/mach_apic.h @@ -13,7 +13,7 @@ #define apic_id_registered (genapic->apic_id_registered) #define init_apic_ldr (genapic->init_apic_ldr) #define ioapic_phys_id_map (genapic->ioapic_phys_id_map) -#define clustered_apic_check (genapic->clustered_apic_check) +#define setup_apic_routing (genapic->setup_apic_routing) #define multi_timer_check (genapic->multi_timer_check) #define apicid_to_node (genapic->apicid_to_node) #define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) diff --git a/include/asm-i386/mach-numaq/mach_apic.h b/include/asm-i386/mach-numaq/mach_apic.h index 9d158095da82..5e5e7dd2692e 100644 --- a/include/asm-i386/mach-numaq/mach_apic.h +++ b/include/asm-i386/mach-numaq/mach_apic.h @@ -34,7 +34,7 @@ static inline void init_apic_ldr(void) /* Already done in NUMA-Q firmware */ } -static inline void clustered_apic_check(void) +static inline void setup_apic_routing(void) { printk("Enabling APIC mode: %s. Using %d I/O APICs\n", "NUMA-Q", nr_ioapics); diff --git a/include/asm-i386/mach-summit/mach_apic.h b/include/asm-i386/mach-summit/mach_apic.h index 43e5bd8f4a19..732f776aab8e 100644 --- a/include/asm-i386/mach-summit/mach_apic.h +++ b/include/asm-i386/mach-summit/mach_apic.h @@ -80,7 +80,7 @@ static inline int apic_id_registered(void) return 1; } -static inline void clustered_apic_check(void) +static inline void setup_apic_routing(void) { printk("Enabling APIC mode: Summit. Using %d I/O APICs\n", nr_ioapics); diff --git a/include/asm-i386/mach-summit/mach_mpparse.h b/include/asm-i386/mach-summit/mach_mpparse.h index 94268399170d..c2520539d934 100644 --- a/include/asm-i386/mach-summit/mach_mpparse.h +++ b/include/asm-i386/mach-summit/mach_mpparse.h @@ -30,7 +30,7 @@ static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, (!strncmp(productid, "VIGIL SMP", 9) || !strncmp(productid, "EXA", 3) || !strncmp(productid, "RUTHLESS SMP", 12))){ - mark_tsc_unstable(); + mark_tsc_unstable("Summit based system"); use_cyclone = 1; /*enable cyclone-timer*/ setup_summit(); return 1; @@ -44,7 +44,7 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (!strncmp(oem_id, "IBM", 3) && (!strncmp(oem_table_id, "SERVIGIL", 8) || !strncmp(oem_table_id, "EXA", 3))){ - mark_tsc_unstable(); + mark_tsc_unstable("Summit based system"); use_cyclone = 1; /*enable cyclone-timer*/ setup_summit(); return 1; diff --git a/include/asm-i386/mach-visws/mach_apic.h b/include/asm-i386/mach-visws/mach_apic.h index 18afe6b6fc4d..efac6f0d139f 100644 --- a/include/asm-i386/mach-visws/mach_apic.h +++ b/include/asm-i386/mach-visws/mach_apic.h @@ -47,7 +47,7 @@ static inline void summit_check(char *oem, char *productid) { } -static inline void clustered_apic_check(void) +static inline void setup_apic_routing(void) { } diff --git a/include/asm-i386/mmu_context.h b/include/asm-i386/mmu_context.h index e6aa30f8de5b..8198d1cca1f3 100644 --- a/include/asm-i386/mmu_context.h +++ b/include/asm-i386/mmu_context.h @@ -5,6 +5,16 @@ #include <asm/atomic.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> +#include <asm/paravirt.h> +#ifndef CONFIG_PARAVIRT +#include <asm-generic/mm_hooks.h> + +static inline void paravirt_activate_mm(struct mm_struct *prev, + struct mm_struct *next) +{ +} +#endif /* !CONFIG_PARAVIRT */ + /* * Used for LDT copy/destruction. @@ -65,7 +75,10 @@ static inline void switch_mm(struct mm_struct *prev, #define deactivate_mm(tsk, mm) \ asm("movl %0,%%gs": :"r" (0)); -#define activate_mm(prev, next) \ - switch_mm((prev),(next),NULL) +#define activate_mm(prev, next) \ + do { \ + paravirt_activate_mm(prev, next); \ + switch_mm((prev),(next),NULL); \ + } while(0); #endif diff --git a/include/asm-i386/module.h b/include/asm-i386/module.h index 02f8f541cbe0..7e5fda6c3976 100644 --- a/include/asm-i386/module.h +++ b/include/asm-i386/module.h @@ -54,6 +54,8 @@ struct mod_arch_specific #define MODULE_PROC_FAMILY "CYRIXIII " #elif defined CONFIG_MVIAC3_2 #define MODULE_PROC_FAMILY "VIAC3-2 " +#elif defined CONFIG_MVIAC7 +#define MODULE_PROC_FAMILY "VIAC7 " #elif defined CONFIG_MGEODEGX1 #define MODULE_PROC_FAMILY "GEODEGX1 " #elif defined CONFIG_MGEODE_LX diff --git a/include/asm-i386/msr-index.h b/include/asm-i386/msr-index.h new file mode 100644 index 000000000000..a02eb2991349 --- /dev/null +++ b/include/asm-i386/msr-index.h @@ -0,0 +1,278 @@ +#ifndef __ASM_MSR_INDEX_H +#define __ASM_MSR_INDEX_H + +/* CPU model specific register (MSR) numbers */ + +/* x86-64 specific MSRs */ +#define MSR_EFER 0xc0000080 /* extended feature register */ +#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */ +#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */ +#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */ +#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */ +#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */ +#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */ +#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */ + +/* EFER bits: */ +#define _EFER_SCE 0 /* SYSCALL/SYSRET */ +#define _EFER_LME 8 /* Long mode enable */ +#define _EFER_LMA 10 /* Long mode active (read-only) */ +#define _EFER_NX 11 /* No execute enable */ + +#define EFER_SCE (1<<_EFER_SCE) +#define EFER_LME (1<<_EFER_LME) +#define EFER_LMA (1<<_EFER_LMA) +#define EFER_NX (1<<_EFER_NX) + +/* Intel MSRs. Some also available on other CPUs */ +#define MSR_IA32_PERFCTR0 0x000000c1 +#define MSR_IA32_PERFCTR1 0x000000c2 +#define MSR_FSB_FREQ 0x000000cd + +#define MSR_MTRRcap 0x000000fe +#define MSR_IA32_BBL_CR_CTL 0x00000119 + +#define MSR_IA32_SYSENTER_CS 0x00000174 +#define MSR_IA32_SYSENTER_ESP 0x00000175 +#define MSR_IA32_SYSENTER_EIP 0x00000176 + +#define MSR_IA32_MCG_CAP 0x00000179 +#define MSR_IA32_MCG_STATUS 0x0000017a +#define MSR_IA32_MCG_CTL 0x0000017b + +#define MSR_IA32_PEBS_ENABLE 0x000003f1 +#define MSR_IA32_DS_AREA 0x00000600 +#define MSR_IA32_PERF_CAPABILITIES 0x00000345 + +#define MSR_MTRRfix64K_00000 0x00000250 +#define MSR_MTRRfix16K_80000 0x00000258 +#define MSR_MTRRfix16K_A0000 0x00000259 +#define MSR_MTRRfix4K_C0000 0x00000268 +#define MSR_MTRRfix4K_C8000 0x00000269 +#define MSR_MTRRfix4K_D0000 0x0000026a +#define MSR_MTRRfix4K_D8000 0x0000026b +#define MSR_MTRRfix4K_E0000 0x0000026c +#define MSR_MTRRfix4K_E8000 0x0000026d +#define MSR_MTRRfix4K_F0000 0x0000026e +#define MSR_MTRRfix4K_F8000 0x0000026f +#define MSR_MTRRdefType 0x000002ff + +#define MSR_IA32_DEBUGCTLMSR 0x000001d9 +#define MSR_IA32_LASTBRANCHFROMIP 0x000001db +#define MSR_IA32_LASTBRANCHTOIP 0x000001dc +#define MSR_IA32_LASTINTFROMIP 0x000001dd +#define MSR_IA32_LASTINTTOIP 0x000001de + +#define MSR_IA32_MC0_CTL 0x00000400 +#define MSR_IA32_MC0_STATUS 0x00000401 +#define MSR_IA32_MC0_ADDR 0x00000402 +#define MSR_IA32_MC0_MISC 0x00000403 + +#define MSR_P6_PERFCTR0 0x000000c1 +#define MSR_P6_PERFCTR1 0x000000c2 +#define MSR_P6_EVNTSEL0 0x00000186 +#define MSR_P6_EVNTSEL1 0x00000187 + +/* K7/K8 MSRs. Not complete. See the architecture manual for a more + complete list. */ +#define MSR_K7_EVNTSEL0 0xc0010000 +#define MSR_K7_PERFCTR0 0xc0010004 +#define MSR_K7_EVNTSEL1 0xc0010001 +#define MSR_K7_PERFCTR1 0xc0010005 +#define MSR_K7_EVNTSEL2 0xc0010002 +#define MSR_K7_PERFCTR2 0xc0010006 +#define MSR_K7_EVNTSEL3 0xc0010003 +#define MSR_K7_PERFCTR3 0xc0010007 +#define MSR_K8_TOP_MEM1 0xc001001a +#define MSR_K7_CLK_CTL 0xc001001b +#define MSR_K8_TOP_MEM2 0xc001001d +#define MSR_K8_SYSCFG 0xc0010010 + +#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */ +#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */ +#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */ + +#define MSR_K7_HWCR 0xc0010015 +#define MSR_K8_HWCR 0xc0010015 +#define MSR_K7_FID_VID_CTL 0xc0010041 +#define MSR_K7_FID_VID_STATUS 0xc0010042 +#define MSR_K8_ENABLE_C1E 0xc0010055 + +/* K6 MSRs */ +#define MSR_K6_EFER 0xc0000080 +#define MSR_K6_STAR 0xc0000081 +#define MSR_K6_WHCR 0xc0000082 +#define MSR_K6_UWCCR 0xc0000085 +#define MSR_K6_EPMR 0xc0000086 +#define MSR_K6_PSOR 0xc0000087 +#define MSR_K6_PFIR 0xc0000088 + +/* Centaur-Hauls/IDT defined MSRs. */ +#define MSR_IDT_FCR1 0x00000107 +#define MSR_IDT_FCR2 0x00000108 +#define MSR_IDT_FCR3 0x00000109 +#define MSR_IDT_FCR4 0x0000010a + +#define MSR_IDT_MCR0 0x00000110 +#define MSR_IDT_MCR1 0x00000111 +#define MSR_IDT_MCR2 0x00000112 +#define MSR_IDT_MCR3 0x00000113 +#define MSR_IDT_MCR4 0x00000114 +#define MSR_IDT_MCR5 0x00000115 +#define MSR_IDT_MCR6 0x00000116 +#define MSR_IDT_MCR7 0x00000117 +#define MSR_IDT_MCR_CTRL 0x00000120 + +/* VIA Cyrix defined MSRs*/ +#define MSR_VIA_FCR 0x00001107 +#define MSR_VIA_LONGHAUL 0x0000110a +#define MSR_VIA_RNG 0x0000110b +#define MSR_VIA_BCR2 0x00001147 + +/* Transmeta defined MSRs */ +#define MSR_TMTA_LONGRUN_CTRL 0x80868010 +#define MSR_TMTA_LONGRUN_FLAGS 0x80868011 +#define MSR_TMTA_LRTI_READOUT 0x80868018 +#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a + +/* Intel defined MSRs. */ +#define MSR_IA32_P5_MC_ADDR 0x00000000 +#define MSR_IA32_P5_MC_TYPE 0x00000001 +#define MSR_IA32_TSC 0x00000010 +#define MSR_IA32_PLATFORM_ID 0x00000017 +#define MSR_IA32_EBL_CR_POWERON 0x0000002a + +#define MSR_IA32_APICBASE 0x0000001b +#define MSR_IA32_APICBASE_BSP (1<<8) +#define MSR_IA32_APICBASE_ENABLE (1<<11) +#define MSR_IA32_APICBASE_BASE (0xfffff<<12) + +#define MSR_IA32_UCODE_WRITE 0x00000079 +#define MSR_IA32_UCODE_REV 0x0000008b + +#define MSR_IA32_PERF_STATUS 0x00000198 +#define MSR_IA32_PERF_CTL 0x00000199 + +#define MSR_IA32_MPERF 0x000000e7 +#define MSR_IA32_APERF 0x000000e8 + +#define MSR_IA32_THERM_CONTROL 0x0000019a +#define MSR_IA32_THERM_INTERRUPT 0x0000019b +#define MSR_IA32_THERM_STATUS 0x0000019c +#define MSR_IA32_MISC_ENABLE 0x000001a0 + +/* Intel Model 6 */ +#define MSR_P6_EVNTSEL0 0x00000186 +#define MSR_P6_EVNTSEL1 0x00000187 + +/* P4/Xeon+ specific */ +#define MSR_IA32_MCG_EAX 0x00000180 +#define MSR_IA32_MCG_EBX 0x00000181 +#define MSR_IA32_MCG_ECX 0x00000182 +#define MSR_IA32_MCG_EDX 0x00000183 +#define MSR_IA32_MCG_ESI 0x00000184 +#define MSR_IA32_MCG_EDI 0x00000185 +#define MSR_IA32_MCG_EBP 0x00000186 +#define MSR_IA32_MCG_ESP 0x00000187 +#define MSR_IA32_MCG_EFLAGS 0x00000188 +#define MSR_IA32_MCG_EIP 0x00000189 +#define MSR_IA32_MCG_RESERVED 0x0000018a + +/* Pentium IV performance counter MSRs */ +#define MSR_P4_BPU_PERFCTR0 0x00000300 +#define MSR_P4_BPU_PERFCTR1 0x00000301 +#define MSR_P4_BPU_PERFCTR2 0x00000302 +#define MSR_P4_BPU_PERFCTR3 0x00000303 +#define MSR_P4_MS_PERFCTR0 0x00000304 +#define MSR_P4_MS_PERFCTR1 0x00000305 +#define MSR_P4_MS_PERFCTR2 0x00000306 +#define MSR_P4_MS_PERFCTR3 0x00000307 +#define MSR_P4_FLAME_PERFCTR0 0x00000308 +#define MSR_P4_FLAME_PERFCTR1 0x00000309 +#define MSR_P4_FLAME_PERFCTR2 0x0000030a +#define MSR_P4_FLAME_PERFCTR3 0x0000030b +#define MSR_P4_IQ_PERFCTR0 0x0000030c +#define MSR_P4_IQ_PERFCTR1 0x0000030d +#define MSR_P4_IQ_PERFCTR2 0x0000030e +#define MSR_P4_IQ_PERFCTR3 0x0000030f +#define MSR_P4_IQ_PERFCTR4 0x00000310 +#define MSR_P4_IQ_PERFCTR5 0x00000311 +#define MSR_P4_BPU_CCCR0 0x00000360 +#define MSR_P4_BPU_CCCR1 0x00000361 +#define MSR_P4_BPU_CCCR2 0x00000362 +#define MSR_P4_BPU_CCCR3 0x00000363 +#define MSR_P4_MS_CCCR0 0x00000364 +#define MSR_P4_MS_CCCR1 0x00000365 +#define MSR_P4_MS_CCCR2 0x00000366 +#define MSR_P4_MS_CCCR3 0x00000367 +#define MSR_P4_FLAME_CCCR0 0x00000368 +#define MSR_P4_FLAME_CCCR1 0x00000369 +#define MSR_P4_FLAME_CCCR2 0x0000036a +#define MSR_P4_FLAME_CCCR3 0x0000036b +#define MSR_P4_IQ_CCCR0 0x0000036c +#define MSR_P4_IQ_CCCR1 0x0000036d +#define MSR_P4_IQ_CCCR2 0x0000036e +#define MSR_P4_IQ_CCCR3 0x0000036f +#define MSR_P4_IQ_CCCR4 0x00000370 +#define MSR_P4_IQ_CCCR5 0x00000371 +#define MSR_P4_ALF_ESCR0 0x000003ca +#define MSR_P4_ALF_ESCR1 0x000003cb +#define MSR_P4_BPU_ESCR0 0x000003b2 +#define MSR_P4_BPU_ESCR1 0x000003b3 +#define MSR_P4_BSU_ESCR0 0x000003a0 +#define MSR_P4_BSU_ESCR1 0x000003a1 +#define MSR_P4_CRU_ESCR0 0x000003b8 +#define MSR_P4_CRU_ESCR1 0x000003b9 +#define MSR_P4_CRU_ESCR2 0x000003cc +#define MSR_P4_CRU_ESCR3 0x000003cd +#define MSR_P4_CRU_ESCR4 0x000003e0 +#define MSR_P4_CRU_ESCR5 0x000003e1 +#define MSR_P4_DAC_ESCR0 0x000003a8 +#define MSR_P4_DAC_ESCR1 0x000003a9 +#define MSR_P4_FIRM_ESCR0 0x000003a4 +#define MSR_P4_FIRM_ESCR1 0x000003a5 +#define MSR_P4_FLAME_ESCR0 0x000003a6 +#define MSR_P4_FLAME_ESCR1 0x000003a7 +#define MSR_P4_FSB_ESCR0 0x000003a2 +#define MSR_P4_FSB_ESCR1 0x000003a3 +#define MSR_P4_IQ_ESCR0 0x000003ba +#define MSR_P4_IQ_ESCR1 0x000003bb +#define MSR_P4_IS_ESCR0 0x000003b4 +#define MSR_P4_IS_ESCR1 0x000003b5 +#define MSR_P4_ITLB_ESCR0 0x000003b6 +#define MSR_P4_ITLB_ESCR1 0x000003b7 +#define MSR_P4_IX_ESCR0 0x000003c8 +#define MSR_P4_IX_ESCR1 0x000003c9 +#define MSR_P4_MOB_ESCR0 0x000003aa +#define MSR_P4_MOB_ESCR1 0x000003ab +#define MSR_P4_MS_ESCR0 0x000003c0 +#define MSR_P4_MS_ESCR1 0x000003c1 +#define MSR_P4_PMH_ESCR0 0x000003ac +#define MSR_P4_PMH_ESCR1 0x000003ad +#define MSR_P4_RAT_ESCR0 0x000003bc +#define MSR_P4_RAT_ESCR1 0x000003bd +#define MSR_P4_SAAT_ESCR0 0x000003ae +#define MSR_P4_SAAT_ESCR1 0x000003af +#define MSR_P4_SSU_ESCR0 0x000003be +#define MSR_P4_SSU_ESCR1 0x000003bf /* guess: not in manual */ + +#define MSR_P4_TBPU_ESCR0 0x000003c2 +#define MSR_P4_TBPU_ESCR1 0x000003c3 +#define MSR_P4_TC_ESCR0 0x000003c4 +#define MSR_P4_TC_ESCR1 0x000003c5 +#define MSR_P4_U2L_ESCR0 0x000003b0 +#define MSR_P4_U2L_ESCR1 0x000003b1 + +/* Intel Core-based CPU performance counters */ +#define MSR_CORE_PERF_FIXED_CTR0 0x00000309 +#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a +#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b +#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d +#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e +#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 + +/* Geode defined MSRs */ +#define MSR_GEODE_BUSCONT_CONF0 0x00001900 + +#endif /* __ASM_MSR_INDEX_H */ diff --git a/include/asm-i386/msr.h b/include/asm-i386/msr.h index 2ad3f30b1a68..9559894c7658 100644 --- a/include/asm-i386/msr.h +++ b/include/asm-i386/msr.h @@ -1,6 +1,79 @@ #ifndef __ASM_MSR_H #define __ASM_MSR_H +#include <asm/msr-index.h> + +#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ + +#include <asm/errno.h> + +static inline unsigned long long native_read_msr(unsigned int msr) +{ + unsigned long long val; + + asm volatile("rdmsr" : "=A" (val) : "c" (msr)); + return val; +} + +static inline unsigned long long native_read_msr_safe(unsigned int msr, + int *err) +{ + unsigned long long val; + + asm volatile("2: rdmsr ; xorl %0,%0\n" + "1:\n\t" + ".section .fixup,\"ax\"\n\t" + "3: movl %3,%0 ; jmp 1b\n\t" + ".previous\n\t" + ".section __ex_table,\"a\"\n" + " .align 4\n\t" + " .long 2b,3b\n\t" + ".previous" + : "=r" (*err), "=A" (val) + : "c" (msr), "i" (-EFAULT)); + + return val; +} + +static inline void native_write_msr(unsigned int msr, unsigned long long val) +{ + asm volatile("wrmsr" : : "c" (msr), "A"(val)); +} + +static inline int native_write_msr_safe(unsigned int msr, + unsigned long long val) +{ + int err; + asm volatile("2: wrmsr ; xorl %0,%0\n" + "1:\n\t" + ".section .fixup,\"ax\"\n\t" + "3: movl %4,%0 ; jmp 1b\n\t" + ".previous\n\t" + ".section __ex_table,\"a\"\n" + " .align 4\n\t" + " .long 2b,3b\n\t" + ".previous" + : "=a" (err) + : "c" (msr), "0" ((u32)val), "d" ((u32)(val>>32)), + "i" (-EFAULT)); + return err; +} + +static inline unsigned long long native_read_tsc(void) +{ + unsigned long long val; + asm volatile("rdtsc" : "=A" (val)); + return val; +} + +static inline unsigned long long native_read_pmc(void) +{ + unsigned long long val; + asm volatile("rdpmc" : "=A" (val)); + return val; +} + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else @@ -11,22 +84,20 @@ * pointer indirection), this allows gcc to optimize better */ -#define rdmsr(msr,val1,val2) \ - __asm__ __volatile__("rdmsr" \ - : "=a" (val1), "=d" (val2) \ - : "c" (msr)) +#define rdmsr(msr,val1,val2) \ + do { \ + unsigned long long __val = native_read_msr(msr); \ + val1 = __val; \ + val2 = __val >> 32; \ + } while(0) -#define wrmsr(msr,val1,val2) \ - __asm__ __volatile__("wrmsr" \ - : /* no outputs */ \ - : "c" (msr), "a" (val1), "d" (val2)) +#define wrmsr(msr,val1,val2) \ + native_write_msr(msr, ((unsigned long long)val2 << 32) | val1) -#define rdmsrl(msr,val) do { \ - unsigned long l__,h__; \ - rdmsr (msr, l__, h__); \ - val = l__; \ - val |= ((u64)h__<<32); \ -} while(0) +#define rdmsrl(msr,val) \ + do { \ + (val) = native_read_msr(msr); \ + } while(0) static inline void wrmsrl (unsigned long msr, unsigned long long val) { @@ -37,50 +108,41 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val) } /* wrmsr with exception handling */ -#define wrmsr_safe(msr,a,b) ({ int ret__; \ - asm volatile("2: wrmsr ; xorl %0,%0\n" \ - "1:\n\t" \ - ".section .fixup,\"ax\"\n\t" \ - "3: movl %4,%0 ; jmp 1b\n\t" \ - ".previous\n\t" \ - ".section __ex_table,\"a\"\n" \ - " .align 4\n\t" \ - " .long 2b,3b\n\t" \ - ".previous" \ - : "=a" (ret__) \ - : "c" (msr), "0" (a), "d" (b), "i" (-EFAULT));\ - ret__; }) +#define wrmsr_safe(msr,val1,val2) \ + (native_write_msr_safe(msr, ((unsigned long long)val2 << 32) | val1)) /* rdmsr with exception handling */ -#define rdmsr_safe(msr,a,b) ({ int ret__; \ - asm volatile("2: rdmsr ; xorl %0,%0\n" \ - "1:\n\t" \ - ".section .fixup,\"ax\"\n\t" \ - "3: movl %4,%0 ; jmp 1b\n\t" \ - ".previous\n\t" \ - ".section __ex_table,\"a\"\n" \ - " .align 4\n\t" \ - " .long 2b,3b\n\t" \ - ".previous" \ - : "=r" (ret__), "=a" (*(a)), "=d" (*(b)) \ - : "c" (msr), "i" (-EFAULT));\ - ret__; }) - -#define rdtsc(low,high) \ - __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high)) - -#define rdtscl(low) \ - __asm__ __volatile__("rdtsc" : "=a" (low) : : "edx") - -#define rdtscll(val) \ - __asm__ __volatile__("rdtsc" : "=A" (val)) +#define rdmsr_safe(msr,p1,p2) \ + ({ \ + int __err; \ + unsigned long long __val = native_read_msr_safe(msr, &__err);\ + (*p1) = __val; \ + (*p2) = __val >> 32; \ + __err; \ + }) + +#define rdtsc(low,high) \ + do { \ + u64 _l = native_read_tsc(); \ + (low) = (u32)_l; \ + (high) = _l >> 32; \ + } while(0) + +#define rdtscl(low) \ + do { \ + (low) = native_read_tsc(); \ + } while(0) + +#define rdtscll(val) ((val) = native_read_tsc()) #define write_tsc(val1,val2) wrmsr(0x10, val1, val2) -#define rdpmc(counter,low,high) \ - __asm__ __volatile__("rdpmc" \ - : "=a" (low), "=d" (high) \ - : "c" (counter)) +#define rdpmc(counter,low,high) \ + do { \ + u64 _l = native_read_pmc(); \ + low = (u32)_l; \ + high = _l >> 32; \ + } while(0) #endif /* !CONFIG_PARAVIRT */ #ifdef CONFIG_SMP @@ -96,234 +158,6 @@ static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) wrmsr(msr_no, l, h); } #endif /* CONFIG_SMP */ - -/* symbolic names for some interesting MSRs */ -/* Intel defined MSRs. */ -#define MSR_IA32_P5_MC_ADDR 0 -#define MSR_IA32_P5_MC_TYPE 1 -#define MSR_IA32_PLATFORM_ID 0x17 -#define MSR_IA32_EBL_CR_POWERON 0x2a - -#define MSR_IA32_APICBASE 0x1b -#define MSR_IA32_APICBASE_BSP (1<<8) -#define MSR_IA32_APICBASE_ENABLE (1<<11) -#define MSR_IA32_APICBASE_BASE (0xfffff<<12) - -#define MSR_IA32_UCODE_WRITE 0x79 -#define MSR_IA32_UCODE_REV 0x8b - -#define MSR_P6_PERFCTR0 0xc1 -#define MSR_P6_PERFCTR1 0xc2 -#define MSR_FSB_FREQ 0xcd - - -#define MSR_IA32_BBL_CR_CTL 0x119 - -#define MSR_IA32_SYSENTER_CS 0x174 -#define MSR_IA32_SYSENTER_ESP 0x175 -#define MSR_IA32_SYSENTER_EIP 0x176 - -#define MSR_IA32_MCG_CAP 0x179 -#define MSR_IA32_MCG_STATUS 0x17a -#define MSR_IA32_MCG_CTL 0x17b - -/* P4/Xeon+ specific */ -#define MSR_IA32_MCG_EAX 0x180 -#define MSR_IA32_MCG_EBX 0x181 -#define MSR_IA32_MCG_ECX 0x182 -#define MSR_IA32_MCG_EDX 0x183 -#define MSR_IA32_MCG_ESI 0x184 -#define MSR_IA32_MCG_EDI 0x185 -#define MSR_IA32_MCG_EBP 0x186 -#define MSR_IA32_MCG_ESP 0x187 -#define MSR_IA32_MCG_EFLAGS 0x188 -#define MSR_IA32_MCG_EIP 0x189 -#define MSR_IA32_MCG_RESERVED 0x18A - -#define MSR_P6_EVNTSEL0 0x186 -#define MSR_P6_EVNTSEL1 0x187 - -#define MSR_IA32_PERF_STATUS 0x198 -#define MSR_IA32_PERF_CTL 0x199 - -#define MSR_IA32_MPERF 0xE7 -#define MSR_IA32_APERF 0xE8 - -#define MSR_IA32_THERM_CONTROL 0x19a -#define MSR_IA32_THERM_INTERRUPT 0x19b -#define MSR_IA32_THERM_STATUS 0x19c -#define MSR_IA32_MISC_ENABLE 0x1a0 - -#define MSR_IA32_DEBUGCTLMSR 0x1d9 -#define MSR_IA32_LASTBRANCHFROMIP 0x1db -#define MSR_IA32_LASTBRANCHTOIP 0x1dc -#define MSR_IA32_LASTINTFROMIP 0x1dd -#define MSR_IA32_LASTINTTOIP 0x1de - -#define MSR_IA32_MC0_CTL 0x400 -#define MSR_IA32_MC0_STATUS 0x401 -#define MSR_IA32_MC0_ADDR 0x402 -#define MSR_IA32_MC0_MISC 0x403 - -#define MSR_IA32_PEBS_ENABLE 0x3f1 -#define MSR_IA32_DS_AREA 0x600 -#define MSR_IA32_PERF_CAPABILITIES 0x345 - -/* Pentium IV performance counter MSRs */ -#define MSR_P4_BPU_PERFCTR0 0x300 -#define MSR_P4_BPU_PERFCTR1 0x301 -#define MSR_P4_BPU_PERFCTR2 0x302 -#define MSR_P4_BPU_PERFCTR3 0x303 -#define MSR_P4_MS_PERFCTR0 0x304 -#define MSR_P4_MS_PERFCTR1 0x305 -#define MSR_P4_MS_PERFCTR2 0x306 -#define MSR_P4_MS_PERFCTR3 0x307 -#define MSR_P4_FLAME_PERFCTR0 0x308 -#define MSR_P4_FLAME_PERFCTR1 0x309 -#define MSR_P4_FLAME_PERFCTR2 0x30a -#define MSR_P4_FLAME_PERFCTR3 0x30b -#define MSR_P4_IQ_PERFCTR0 0x30c -#define MSR_P4_IQ_PERFCTR1 0x30d -#define MSR_P4_IQ_PERFCTR2 0x30e -#define MSR_P4_IQ_PERFCTR3 0x30f -#define MSR_P4_IQ_PERFCTR4 0x310 -#define MSR_P4_IQ_PERFCTR5 0x311 -#define MSR_P4_BPU_CCCR0 0x360 -#define MSR_P4_BPU_CCCR1 0x361 -#define MSR_P4_BPU_CCCR2 0x362 -#define MSR_P4_BPU_CCCR3 0x363 -#define MSR_P4_MS_CCCR0 0x364 -#define MSR_P4_MS_CCCR1 0x365 -#define MSR_P4_MS_CCCR2 0x366 -#define MSR_P4_MS_CCCR3 0x367 -#define MSR_P4_FLAME_CCCR0 0x368 -#define MSR_P4_FLAME_CCCR1 0x369 -#define MSR_P4_FLAME_CCCR2 0x36a -#define MSR_P4_FLAME_CCCR3 0x36b -#define MSR_P4_IQ_CCCR0 0x36c -#define MSR_P4_IQ_CCCR1 0x36d -#define MSR_P4_IQ_CCCR2 0x36e -#define MSR_P4_IQ_CCCR3 0x36f -#define MSR_P4_IQ_CCCR4 0x370 -#define MSR_P4_IQ_CCCR5 0x371 -#define MSR_P4_ALF_ESCR0 0x3ca -#define MSR_P4_ALF_ESCR1 0x3cb -#define MSR_P4_BPU_ESCR0 0x3b2 -#define MSR_P4_BPU_ESCR1 0x3b3 -#define MSR_P4_BSU_ESCR0 0x3a0 -#define MSR_P4_BSU_ESCR1 0x3a1 -#define MSR_P4_CRU_ESCR0 0x3b8 -#define MSR_P4_CRU_ESCR1 0x3b9 -#define MSR_P4_CRU_ESCR2 0x3cc -#define MSR_P4_CRU_ESCR3 0x3cd -#define MSR_P4_CRU_ESCR4 0x3e0 -#define MSR_P4_CRU_ESCR5 0x3e1 -#define MSR_P4_DAC_ESCR0 0x3a8 -#define MSR_P4_DAC_ESCR1 0x3a9 -#define MSR_P4_FIRM_ESCR0 0x3a4 -#define MSR_P4_FIRM_ESCR1 0x3a5 -#define MSR_P4_FLAME_ESCR0 0x3a6 -#define MSR_P4_FLAME_ESCR1 0x3a7 -#define MSR_P4_FSB_ESCR0 0x3a2 -#define MSR_P4_FSB_ESCR1 0x3a3 -#define MSR_P4_IQ_ESCR0 0x3ba -#define MSR_P4_IQ_ESCR1 0x3bb -#define MSR_P4_IS_ESCR0 0x3b4 -#define MSR_P4_IS_ESCR1 0x3b5 -#define MSR_P4_ITLB_ESCR0 0x3b6 -#define MSR_P4_ITLB_ESCR1 0x3b7 -#define MSR_P4_IX_ESCR0 0x3c8 -#define MSR_P4_IX_ESCR1 0x3c9 -#define MSR_P4_MOB_ESCR0 0x3aa -#define MSR_P4_MOB_ESCR1 0x3ab -#define MSR_P4_MS_ESCR0 0x3c0 -#define MSR_P4_MS_ESCR1 0x3c1 -#define MSR_P4_PMH_ESCR0 0x3ac -#define MSR_P4_PMH_ESCR1 0x3ad -#define MSR_P4_RAT_ESCR0 0x3bc -#define MSR_P4_RAT_ESCR1 0x3bd -#define MSR_P4_SAAT_ESCR0 0x3ae -#define MSR_P4_SAAT_ESCR1 0x3af -#define MSR_P4_SSU_ESCR0 0x3be -#define MSR_P4_SSU_ESCR1 0x3bf /* guess: not defined in manual */ -#define MSR_P4_TBPU_ESCR0 0x3c2 -#define MSR_P4_TBPU_ESCR1 0x3c3 -#define MSR_P4_TC_ESCR0 0x3c4 -#define MSR_P4_TC_ESCR1 0x3c5 -#define MSR_P4_U2L_ESCR0 0x3b0 -#define MSR_P4_U2L_ESCR1 0x3b1 - -/* AMD Defined MSRs */ -#define MSR_K6_EFER 0xC0000080 -#define MSR_K6_STAR 0xC0000081 -#define MSR_K6_WHCR 0xC0000082 -#define MSR_K6_UWCCR 0xC0000085 -#define MSR_K6_EPMR 0xC0000086 -#define MSR_K6_PSOR 0xC0000087 -#define MSR_K6_PFIR 0xC0000088 - -#define MSR_K7_EVNTSEL0 0xC0010000 -#define MSR_K7_EVNTSEL1 0xC0010001 -#define MSR_K7_EVNTSEL2 0xC0010002 -#define MSR_K7_EVNTSEL3 0xC0010003 -#define MSR_K7_PERFCTR0 0xC0010004 -#define MSR_K7_PERFCTR1 0xC0010005 -#define MSR_K7_PERFCTR2 0xC0010006 -#define MSR_K7_PERFCTR3 0xC0010007 -#define MSR_K7_HWCR 0xC0010015 -#define MSR_K7_CLK_CTL 0xC001001b -#define MSR_K7_FID_VID_CTL 0xC0010041 -#define MSR_K7_FID_VID_STATUS 0xC0010042 - -#define MSR_K8_ENABLE_C1E 0xC0010055 - -/* extended feature register */ -#define MSR_EFER 0xc0000080 - -/* EFER bits: */ - -/* Execute Disable enable */ -#define _EFER_NX 11 -#define EFER_NX (1<<_EFER_NX) - -/* Centaur-Hauls/IDT defined MSRs. */ -#define MSR_IDT_FCR1 0x107 -#define MSR_IDT_FCR2 0x108 -#define MSR_IDT_FCR3 0x109 -#define MSR_IDT_FCR4 0x10a - -#define MSR_IDT_MCR0 0x110 -#define MSR_IDT_MCR1 0x111 -#define MSR_IDT_MCR2 0x112 -#define MSR_IDT_MCR3 0x113 -#define MSR_IDT_MCR4 0x114 -#define MSR_IDT_MCR5 0x115 -#define MSR_IDT_MCR6 0x116 -#define MSR_IDT_MCR7 0x117 -#define MSR_IDT_MCR_CTRL 0x120 - -/* VIA Cyrix defined MSRs*/ -#define MSR_VIA_FCR 0x1107 -#define MSR_VIA_LONGHAUL 0x110a -#define MSR_VIA_RNG 0x110b -#define MSR_VIA_BCR2 0x1147 - -/* Transmeta defined MSRs */ -#define MSR_TMTA_LONGRUN_CTRL 0x80868010 -#define MSR_TMTA_LONGRUN_FLAGS 0x80868011 -#define MSR_TMTA_LRTI_READOUT 0x80868018 -#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a - -/* Intel Core-based CPU performance counters */ -#define MSR_CORE_PERF_FIXED_CTR0 0x309 -#define MSR_CORE_PERF_FIXED_CTR1 0x30a -#define MSR_CORE_PERF_FIXED_CTR2 0x30b -#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x38d -#define MSR_CORE_PERF_GLOBAL_STATUS 0x38e -#define MSR_CORE_PERF_GLOBAL_CTRL 0x38f -#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x390 - -/* Geode defined MSRs */ -#define MSR_GEODE_BUSCONT_CONF0 0x1900 - +#endif +#endif #endif /* __ASM_MSR_H */ diff --git a/include/asm-i386/mtrr.h b/include/asm-i386/mtrr.h index 07f063ae26ea..7e9c7ccbdcfe 100644 --- a/include/asm-i386/mtrr.h +++ b/include/asm-i386/mtrr.h @@ -69,6 +69,8 @@ struct mtrr_gentry /* The following functions are for use by other drivers */ # ifdef CONFIG_MTRR +extern void mtrr_save_fixed_ranges(void *); +extern void mtrr_save_state(void); extern int mtrr_add (unsigned long base, unsigned long size, unsigned int type, char increment); extern int mtrr_add_page (unsigned long base, unsigned long size, @@ -79,6 +81,8 @@ extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi); extern void mtrr_ap_init(void); extern void mtrr_bp_init(void); # else +#define mtrr_save_fixed_ranges(arg) do {} while (0) +#define mtrr_save_state() do {} while (0) static __inline__ int mtrr_add (unsigned long base, unsigned long size, unsigned int type, char increment) { diff --git a/include/asm-i386/nmi.h b/include/asm-i386/nmi.h index b04333ea6f31..fb1e133efd9f 100644 --- a/include/asm-i386/nmi.h +++ b/include/asm-i386/nmi.h @@ -50,4 +50,12 @@ void __trigger_all_cpu_backtrace(void); #endif +void lapic_watchdog_stop(void); +int lapic_watchdog_init(unsigned nmi_hz); +int lapic_wd_event(unsigned nmi_hz); +unsigned lapic_adjust_nmi_hz(unsigned hz); +int lapic_watchdog_ok(void); +void disable_lapic_nmi_watchdog(void); +void enable_lapic_nmi_watchdog(void); + #endif /* ASM_NMI_H */ diff --git a/include/asm-i386/page.h b/include/asm-i386/page.h index 7b19f454761d..818ac8bf01e2 100644 --- a/include/asm-i386/page.h +++ b/include/asm-i386/page.h @@ -12,7 +12,6 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ - #ifdef CONFIG_X86_USE_3DNOW #include <asm/mmx.h> @@ -42,26 +41,81 @@ * These are used to make use of C type-checking.. */ extern int nx_enabled; + #ifdef CONFIG_X86_PAE extern unsigned long long __supported_pte_mask; typedef struct { unsigned long pte_low, pte_high; } pte_t; typedef struct { unsigned long long pmd; } pmd_t; typedef struct { unsigned long long pgd; } pgd_t; typedef struct { unsigned long long pgprot; } pgprot_t; -#define pmd_val(x) ((x).pmd) -#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32)) -#define __pmd(x) ((pmd_t) { (x) } ) + +static inline unsigned long long native_pgd_val(pgd_t pgd) +{ + return pgd.pgd; +} + +static inline unsigned long long native_pmd_val(pmd_t pmd) +{ + return pmd.pmd; +} + +static inline unsigned long long native_pte_val(pte_t pte) +{ + return pte.pte_low | ((unsigned long long)pte.pte_high << 32); +} + +static inline pgd_t native_make_pgd(unsigned long long val) +{ + return (pgd_t) { val }; +} + +static inline pmd_t native_make_pmd(unsigned long long val) +{ + return (pmd_t) { val }; +} + +static inline pte_t native_make_pte(unsigned long long val) +{ + return (pte_t) { .pte_low = val, .pte_high = (val >> 32) } ; +} + +#ifndef CONFIG_PARAVIRT +#define pmd_val(x) native_pmd_val(x) +#define __pmd(x) native_make_pmd(x) +#endif + #define HPAGE_SHIFT 21 #include <asm-generic/pgtable-nopud.h> -#else +#else /* !CONFIG_X86_PAE */ typedef struct { unsigned long pte_low; } pte_t; typedef struct { unsigned long pgd; } pgd_t; typedef struct { unsigned long pgprot; } pgprot_t; #define boot_pte_t pte_t /* or would you rather have a typedef */ -#define pte_val(x) ((x).pte_low) + +static inline unsigned long native_pgd_val(pgd_t pgd) +{ + return pgd.pgd; +} + +static inline unsigned long native_pte_val(pte_t pte) +{ + return pte.pte_low; +} + +static inline pgd_t native_make_pgd(unsigned long val) +{ + return (pgd_t) { val }; +} + +static inline pte_t native_make_pte(unsigned long val) +{ + return (pte_t) { .pte_low = val }; +} + #define HPAGE_SHIFT 22 #include <asm-generic/pgtable-nopmd.h> -#endif +#endif /* CONFIG_X86_PAE */ + #define PTE_MASK PAGE_MASK #ifdef CONFIG_HUGETLB_PAGE @@ -71,13 +125,16 @@ typedef struct { unsigned long pgprot; } pgprot_t; #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #endif -#define pgd_val(x) ((x).pgd) #define pgprot_val(x) ((x).pgprot) - -#define __pte(x) ((pte_t) { (x) } ) -#define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) +#ifndef CONFIG_PARAVIRT +#define pgd_val(x) native_pgd_val(x) +#define __pgd(x) native_make_pgd(x) +#define pte_val(x) native_pte_val(x) +#define __pte(x) native_make_pte(x) +#endif + #endif /* !__ASSEMBLY__ */ /* to align the pointer to the (next) page boundary */ @@ -143,9 +200,7 @@ extern int page_is_ram(unsigned long pagenr); #include <asm-generic/memory_model.h> #include <asm-generic/page.h> -#ifndef CONFIG_COMPAT_VDSO #define __HAVE_ARCH_GATE_AREA 1 -#endif #endif /* __KERNEL__ */ #endif /* _I386_PAGE_H */ diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h index e63f1e444fcf..e2e7f98723c5 100644 --- a/include/asm-i386/paravirt.h +++ b/include/asm-i386/paravirt.h @@ -2,20 +2,9 @@ #define __ASM_PARAVIRT_H /* Various instructions on x86 need to be replaced for * para-virtualization: those hooks are defined here. */ -#include <linux/linkage.h> -#include <linux/stringify.h> -#include <asm/page.h> #ifdef CONFIG_PARAVIRT -/* These are the most performance critical ops, so we want to be able to patch - * callers */ -#define PARAVIRT_IRQ_DISABLE 0 -#define PARAVIRT_IRQ_ENABLE 1 -#define PARAVIRT_RESTORE_FLAGS 2 -#define PARAVIRT_SAVE_FLAGS 3 -#define PARAVIRT_SAVE_FLAGS_IRQ_DISABLE 4 -#define PARAVIRT_INTERRUPT_RETURN 5 -#define PARAVIRT_STI_SYSEXIT 6 +#include <asm/page.h> /* Bitmask of what can be clobbered: usually at least eax. */ #define CLBR_NONE 0x0 @@ -25,13 +14,29 @@ #define CLBR_ANY 0x7 #ifndef __ASSEMBLY__ +#include <linux/types.h> +#include <linux/cpumask.h> +#include <asm/kmap_types.h> + +struct page; struct thread_struct; struct Xgt_desc_struct; struct tss_struct; struct mm_struct; +struct desc_struct; + +/* Lazy mode for batching updates / context switch */ +enum paravirt_lazy_mode { + PARAVIRT_LAZY_NONE = 0, + PARAVIRT_LAZY_MMU = 1, + PARAVIRT_LAZY_CPU = 2, + PARAVIRT_LAZY_FLUSH = 3, +}; + struct paravirt_ops { unsigned int kernel_rpl; + int shared_kernel_pmd; int paravirt_enabled; const char *name; @@ -44,24 +49,33 @@ struct paravirt_ops */ unsigned (*patch)(u8 type, u16 clobber, void *firstinsn, unsigned len); + /* Basic arch-specific setup */ void (*arch_setup)(void); char *(*memory_setup)(void); void (*init_IRQ)(void); + void (*time_init)(void); + /* + * Called before/after init_mm pagetable setup. setup_start + * may reset %cr3, and may pre-install parts of the pagetable; + * pagetable setup is expected to preserve any existing + * mapping. + */ + void (*pagetable_setup_start)(pgd_t *pgd_base); + void (*pagetable_setup_done)(pgd_t *pgd_base); + + /* Print a banner to identify the environment */ void (*banner)(void); + /* Set and set time of day */ unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long); - void (*time_init)(void); - - /* All the function pointers here are declared as "fastcall" - so that we get a specific register-based calling - convention. This makes it easier to implement inline - assembler replacements. */ + /* cpuid emulation, mostly so that caps bits can be disabled */ void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); + /* hooks for various privileged instructions */ unsigned long (*get_debugreg)(int regno); void (*set_debugreg)(int regno, unsigned long value); @@ -80,15 +94,23 @@ struct paravirt_ops unsigned long (*read_cr4)(void); void (*write_cr4)(unsigned long); + /* + * Get/set interrupt state. save_fl and restore_fl are only + * expected to use X86_EFLAGS_IF; all other bits + * returned from save_fl are undefined, and may be ignored by + * restore_fl. + */ unsigned long (*save_fl)(void); void (*restore_fl)(unsigned long); void (*irq_disable)(void); void (*irq_enable)(void); void (*safe_halt)(void); void (*halt)(void); + void (*wbinvd)(void); - /* err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ + /* MSR, PMC and TSR operations. + err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ u64 (*read_msr)(unsigned int msr, int *err); int (*write_msr)(unsigned int msr, u64 val); @@ -97,6 +119,7 @@ struct paravirt_ops u64 (*get_scheduled_cycles)(void); unsigned long (*get_cpu_khz)(void); + /* Segment descriptor handling */ void (*load_tr_desc)(void); void (*load_gdt)(const struct Xgt_desc_struct *); void (*load_idt)(const struct Xgt_desc_struct *); @@ -105,59 +128,98 @@ struct paravirt_ops void (*set_ldt)(const void *desc, unsigned entries); unsigned long (*store_tr)(void); void (*load_tls)(struct thread_struct *t, unsigned int cpu); - void (*write_ldt_entry)(void *dt, int entrynum, - u32 low, u32 high); - void (*write_gdt_entry)(void *dt, int entrynum, - u32 low, u32 high); - void (*write_idt_entry)(void *dt, int entrynum, - u32 low, u32 high); - void (*load_esp0)(struct tss_struct *tss, - struct thread_struct *thread); + void (*write_ldt_entry)(struct desc_struct *, + int entrynum, u32 low, u32 high); + void (*write_gdt_entry)(struct desc_struct *, + int entrynum, u32 low, u32 high); + void (*write_idt_entry)(struct desc_struct *, + int entrynum, u32 low, u32 high); + void (*load_esp0)(struct tss_struct *tss, struct thread_struct *t); void (*set_iopl_mask)(unsigned mask); - void (*io_delay)(void); + /* + * Hooks for intercepting the creation/use/destruction of an + * mm_struct. + */ + void (*activate_mm)(struct mm_struct *prev, + struct mm_struct *next); + void (*dup_mmap)(struct mm_struct *oldmm, + struct mm_struct *mm); + void (*exit_mmap)(struct mm_struct *mm); + #ifdef CONFIG_X86_LOCAL_APIC + /* + * Direct APIC operations, principally for VMI. Ideally + * these shouldn't be in this interface. + */ void (*apic_write)(unsigned long reg, unsigned long v); void (*apic_write_atomic)(unsigned long reg, unsigned long v); unsigned long (*apic_read)(unsigned long reg); void (*setup_boot_clock)(void); void (*setup_secondary_clock)(void); + + void (*startup_ipi_hook)(int phys_apicid, + unsigned long start_eip, + unsigned long start_esp); #endif + /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(u32 addr); - - void (*map_pt_hook)(int type, pte_t *va, u32 pfn); + void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm, + unsigned long va); + /* Hooks for allocating/releasing pagetable pages */ void (*alloc_pt)(u32 pfn); void (*alloc_pd)(u32 pfn); void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count); void (*release_pt)(u32 pfn); void (*release_pd)(u32 pfn); + /* Pagetable manipulation functions */ void (*set_pte)(pte_t *ptep, pte_t pteval); - void (*set_pte_at)(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval); + void (*set_pte_at)(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval); void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); - void (*pte_update)(struct mm_struct *mm, u32 addr, pte_t *ptep); - void (*pte_update_defer)(struct mm_struct *mm, u32 addr, pte_t *ptep); + void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + void (*pte_update_defer)(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); + +#ifdef CONFIG_HIGHPTE + void *(*kmap_atomic_pte)(struct page *page, enum km_type type); +#endif + #ifdef CONFIG_X86_PAE void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); - void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); + void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); void (*set_pud)(pud_t *pudp, pud_t pudval); - void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void (*pmd_clear)(pmd_t *pmdp); + + unsigned long long (*pte_val)(pte_t); + unsigned long long (*pmd_val)(pmd_t); + unsigned long long (*pgd_val)(pgd_t); + + pte_t (*make_pte)(unsigned long long pte); + pmd_t (*make_pmd)(unsigned long long pmd); + pgd_t (*make_pgd)(unsigned long long pgd); +#else + unsigned long (*pte_val)(pte_t); + unsigned long (*pgd_val)(pgd_t); + + pte_t (*make_pte)(unsigned long pte); + pgd_t (*make_pgd)(unsigned long pgd); #endif - void (*set_lazy_mode)(int mode); + /* Set deferred update mode, used for batching operations. */ + void (*set_lazy_mode)(enum paravirt_lazy_mode mode); /* These two are jmp to, not actually called. */ void (*irq_enable_sysexit)(void); void (*iret)(void); - - void (*startup_ipi_hook)(int phys_apicid, unsigned long start_eip, unsigned long start_esp); }; /* Mark a paravirt probe function. */ @@ -167,23 +229,202 @@ struct paravirt_ops extern struct paravirt_ops paravirt_ops; -#define paravirt_enabled() (paravirt_ops.paravirt_enabled) +#define PARAVIRT_PATCH(x) \ + (offsetof(struct paravirt_ops, x) / sizeof(void *)) + +#define paravirt_type(type) \ + [paravirt_typenum] "i" (PARAVIRT_PATCH(type)) +#define paravirt_clobber(clobber) \ + [paravirt_clobber] "i" (clobber) + +/* + * Generate some code, and mark it as patchable by the + * apply_paravirt() alternate instruction patcher. + */ +#define _paravirt_alt(insn_string, type, clobber) \ + "771:\n\t" insn_string "\n" "772:\n" \ + ".pushsection .parainstructions,\"a\"\n" \ + " .long 771b\n" \ + " .byte " type "\n" \ + " .byte 772b-771b\n" \ + " .short " clobber "\n" \ + ".popsection\n" + +/* Generate patchable code, with the default asm parameters. */ +#define paravirt_alt(insn_string) \ + _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") + +unsigned paravirt_patch_nop(void); +unsigned paravirt_patch_ignore(unsigned len); +unsigned paravirt_patch_call(void *target, u16 tgt_clobbers, + void *site, u16 site_clobbers, + unsigned len); +unsigned paravirt_patch_jmp(void *target, void *site, unsigned len); +unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len); + +unsigned paravirt_patch_insns(void *site, unsigned len, + const char *start, const char *end); + + +/* + * This generates an indirect call based on the operation type number. + * The type number, computed in PARAVIRT_PATCH, is derived from the + * offset into the paravirt_ops structure, and can therefore be freely + * converted back into a structure offset. + */ +#define PARAVIRT_CALL "call *(paravirt_ops+%c[paravirt_typenum]*4);" + +/* + * These macros are intended to wrap calls into a paravirt_ops + * operation, so that they can be later identified and patched at + * runtime. + * + * Normally, a call to a pv_op function is a simple indirect call: + * (paravirt_ops.operations)(args...). + * + * Unfortunately, this is a relatively slow operation for modern CPUs, + * because it cannot necessarily determine what the destination + * address is. In this case, the address is a runtime constant, so at + * the very least we can patch the call to e a simple direct call, or + * ideally, patch an inline implementation into the callsite. (Direct + * calls are essentially free, because the call and return addresses + * are completely predictable.) + * + * These macros rely on the standard gcc "regparm(3)" calling + * convention, in which the first three arguments are placed in %eax, + * %edx, %ecx (in that order), and the remaining arguments are placed + * on the stack. All caller-save registers (eax,edx,ecx) are expected + * to be modified (either clobbered or used for return values). + * + * The call instruction itself is marked by placing its start address + * and size into the .parainstructions section, so that + * apply_paravirt() in arch/i386/kernel/alternative.c can do the + * appropriate patching under the control of the backend paravirt_ops + * implementation. + * + * Unfortunately there's no way to get gcc to generate the args setup + * for the call, and then allow the call itself to be generated by an + * inline asm. Because of this, we must do the complete arg setup and + * return value handling from within these macros. This is fairly + * cumbersome. + * + * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments. + * It could be extended to more arguments, but there would be little + * to be gained from that. For each number of arguments, there are + * the two VCALL and CALL variants for void and non-void functions. + * + * When there is a return value, the invoker of the macro must specify + * the return type. The macro then uses sizeof() on that type to + * determine whether its a 32 or 64 bit value, and places the return + * in the right register(s) (just %eax for 32-bit, and %edx:%eax for + * 64-bit). + * + * 64-bit arguments are passed as a pair of adjacent 32-bit arguments + * in low,high order. + * + * Small structures are passed and returned in registers. The macro + * calling convention can't directly deal with this, so the wrapper + * functions must do this. + * + * These PVOP_* macros are only defined within this header. This + * means that all uses must be wrapped in inline functions. This also + * makes sure the incoming and outgoing types are always correct. + */ +#define __PVOP_CALL(rettype, op, pre, post, ...) \ + ({ \ + rettype __ret; \ + unsigned long __eax, __edx, __ecx; \ + if (sizeof(rettype) > sizeof(unsigned long)) { \ + asm volatile(pre \ + paravirt_alt(PARAVIRT_CALL) \ + post \ + : "=a" (__eax), "=d" (__edx), \ + "=c" (__ecx) \ + : paravirt_type(op), \ + paravirt_clobber(CLBR_ANY), \ + ##__VA_ARGS__ \ + : "memory", "cc"); \ + __ret = (rettype)((((u64)__edx) << 32) | __eax); \ + } else { \ + asm volatile(pre \ + paravirt_alt(PARAVIRT_CALL) \ + post \ + : "=a" (__eax), "=d" (__edx), \ + "=c" (__ecx) \ + : paravirt_type(op), \ + paravirt_clobber(CLBR_ANY), \ + ##__VA_ARGS__ \ + : "memory", "cc"); \ + __ret = (rettype)__eax; \ + } \ + __ret; \ + }) +#define __PVOP_VCALL(op, pre, post, ...) \ + ({ \ + unsigned long __eax, __edx, __ecx; \ + asm volatile(pre \ + paravirt_alt(PARAVIRT_CALL) \ + post \ + : "=a" (__eax), "=d" (__edx), "=c" (__ecx) \ + : paravirt_type(op), \ + paravirt_clobber(CLBR_ANY), \ + ##__VA_ARGS__ \ + : "memory", "cc"); \ + }) + +#define PVOP_CALL0(rettype, op) \ + __PVOP_CALL(rettype, op, "", "") +#define PVOP_VCALL0(op) \ + __PVOP_VCALL(op, "", "") + +#define PVOP_CALL1(rettype, op, arg1) \ + __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1))) +#define PVOP_VCALL1(op, arg1) \ + __PVOP_VCALL(op, "", "", "0" ((u32)(arg1))) + +#define PVOP_CALL2(rettype, op, arg1, arg2) \ + __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)), "1" ((u32)(arg2))) +#define PVOP_VCALL2(op, arg1, arg2) \ + __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)), "1" ((u32)(arg2))) + +#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \ + __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)), \ + "1"((u32)(arg2)), "2"((u32)(arg3))) +#define PVOP_VCALL3(op, arg1, arg2, arg3) \ + __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)), "1"((u32)(arg2)), \ + "2"((u32)(arg3))) + +#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ + __PVOP_CALL(rettype, op, \ + "push %[_arg4];", "lea 4(%%esp),%%esp;", \ + "0" ((u32)(arg1)), "1" ((u32)(arg2)), \ + "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) +#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ + __PVOP_VCALL(op, \ + "push %[_arg4];", "lea 4(%%esp),%%esp;", \ + "0" ((u32)(arg1)), "1" ((u32)(arg2)), \ + "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) + +static inline int paravirt_enabled(void) +{ + return paravirt_ops.paravirt_enabled; +} static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) { - paravirt_ops.load_esp0(tss, thread); + PVOP_VCALL2(load_esp0, tss, thread); } #define ARCH_SETUP paravirt_ops.arch_setup(); static inline unsigned long get_wallclock(void) { - return paravirt_ops.get_wallclock(); + return PVOP_CALL0(unsigned long, get_wallclock); } static inline int set_wallclock(unsigned long nowtime) { - return paravirt_ops.set_wallclock(nowtime); + return PVOP_CALL1(int, set_wallclock, nowtime); } static inline void (*choose_time_init(void))(void) @@ -195,113 +436,208 @@ static inline void (*choose_time_init(void))(void) static inline void __cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { - paravirt_ops.cpuid(eax, ebx, ecx, edx); + PVOP_VCALL4(cpuid, eax, ebx, ecx, edx); } /* * These special macros can be used to get or set a debugging register */ -#define get_debugreg(var, reg) var = paravirt_ops.get_debugreg(reg) -#define set_debugreg(val, reg) paravirt_ops.set_debugreg(reg, val) +static inline unsigned long paravirt_get_debugreg(int reg) +{ + return PVOP_CALL1(unsigned long, 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(set_debugreg, reg, val); +} + +static inline void clts(void) +{ + PVOP_VCALL0(clts); +} -#define clts() paravirt_ops.clts() +static inline unsigned long read_cr0(void) +{ + return PVOP_CALL0(unsigned long, read_cr0); +} -#define read_cr0() paravirt_ops.read_cr0() -#define write_cr0(x) paravirt_ops.write_cr0(x) +static inline void write_cr0(unsigned long x) +{ + PVOP_VCALL1(write_cr0, x); +} -#define read_cr2() paravirt_ops.read_cr2() -#define write_cr2(x) paravirt_ops.write_cr2(x) +static inline unsigned long read_cr2(void) +{ + return PVOP_CALL0(unsigned long, read_cr2); +} -#define read_cr3() paravirt_ops.read_cr3() -#define write_cr3(x) paravirt_ops.write_cr3(x) +static inline void write_cr2(unsigned long x) +{ + PVOP_VCALL1(write_cr2, x); +} -#define read_cr4() paravirt_ops.read_cr4() -#define read_cr4_safe(x) paravirt_ops.read_cr4_safe() -#define write_cr4(x) paravirt_ops.write_cr4(x) +static inline unsigned long read_cr3(void) +{ + return PVOP_CALL0(unsigned long, read_cr3); +} + +static inline void write_cr3(unsigned long x) +{ + PVOP_VCALL1(write_cr3, x); +} + +static inline unsigned long read_cr4(void) +{ + return PVOP_CALL0(unsigned long, read_cr4); +} +static inline unsigned long read_cr4_safe(void) +{ + return PVOP_CALL0(unsigned long, read_cr4_safe); +} + +static inline void write_cr4(unsigned long x) +{ + PVOP_VCALL1(write_cr4, x); +} static inline void raw_safe_halt(void) { - paravirt_ops.safe_halt(); + PVOP_VCALL0(safe_halt); } static inline void halt(void) { - paravirt_ops.safe_halt(); + PVOP_VCALL0(safe_halt); +} + +static inline void wbinvd(void) +{ + PVOP_VCALL0(wbinvd); } -#define wbinvd() paravirt_ops.wbinvd() #define get_kernel_rpl() (paravirt_ops.kernel_rpl) -#define rdmsr(msr,val1,val2) do { \ - int _err; \ - u64 _l = paravirt_ops.read_msr(msr,&_err); \ - val1 = (u32)_l; \ - val2 = _l >> 32; \ +static inline u64 paravirt_read_msr(unsigned msr, int *err) +{ + return PVOP_CALL2(u64, read_msr, msr, err); +} +static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high) +{ + return PVOP_CALL3(int, write_msr, msr, low, high); +} + +/* 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 { \ - u64 _l = ((u64)(val2) << 32) | (val1); \ - paravirt_ops.write_msr((msr), _l); \ +#define wrmsr(msr,val1,val2) do { \ + paravirt_write_msr(msr, val1, val2); \ } while(0) -#define rdmsrl(msr,val) do { \ - int _err; \ - val = paravirt_ops.read_msr((msr),&_err); \ +#define rdmsrl(msr,val) do { \ + int _err; \ + val = paravirt_read_msr(msr, &_err); \ } while(0) -#define wrmsrl(msr,val) (paravirt_ops.write_msr((msr),(val))) -#define wrmsr_safe(msr,a,b) ({ \ - u64 _l = ((u64)(b) << 32) | (a); \ - paravirt_ops.write_msr((msr),_l); \ -}) +#define wrmsrl(msr,val) ((void)paravirt_write_msr(msr, val, 0)) +#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_ops.read_msr(msr,&_err); \ - (*a) = (u32)_l; \ - (*b) = _l >> 32; \ +#define rdmsr_safe(msr,a,b) ({ \ + int _err; \ + u64 _l = paravirt_read_msr(msr, &_err); \ + (*a) = (u32)_l; \ + (*b) = _l >> 32; \ _err; }) -#define rdtsc(low,high) do { \ - u64 _l = paravirt_ops.read_tsc(); \ - low = (u32)_l; \ - high = _l >> 32; \ + +static inline u64 paravirt_read_tsc(void) +{ + return PVOP_CALL0(u64, read_tsc); +} +#define rdtsc(low,high) do { \ + u64 _l = paravirt_read_tsc(); \ + low = (u32)_l; \ + high = _l >> 32; \ } while(0) -#define rdtscl(low) do { \ - u64 _l = paravirt_ops.read_tsc(); \ - low = (int)_l; \ +#define rdtscl(low) do { \ + u64 _l = paravirt_read_tsc(); \ + low = (int)_l; \ } while(0) -#define rdtscll(val) (val = paravirt_ops.read_tsc()) +#define rdtscll(val) (val = paravirt_read_tsc()) #define get_scheduled_cycles(val) (val = paravirt_ops.get_scheduled_cycles()) #define calculate_cpu_khz() (paravirt_ops.get_cpu_khz()) #define write_tsc(val1,val2) wrmsr(0x10, val1, val2) -#define rdpmc(counter,low,high) do { \ - u64 _l = paravirt_ops.read_pmc(); \ - low = (u32)_l; \ - high = _l >> 32; \ +static inline unsigned long long paravirt_read_pmc(int counter) +{ + return PVOP_CALL1(u64, read_pmc, counter); +} + +#define rdpmc(counter,low,high) do { \ + u64 _l = paravirt_read_pmc(counter); \ + low = (u32)_l; \ + high = _l >> 32; \ } while(0) -#define load_TR_desc() (paravirt_ops.load_tr_desc()) -#define load_gdt(dtr) (paravirt_ops.load_gdt(dtr)) -#define load_idt(dtr) (paravirt_ops.load_idt(dtr)) -#define set_ldt(addr, entries) (paravirt_ops.set_ldt((addr), (entries))) -#define store_gdt(dtr) (paravirt_ops.store_gdt(dtr)) -#define store_idt(dtr) (paravirt_ops.store_idt(dtr)) -#define store_tr(tr) ((tr) = paravirt_ops.store_tr()) -#define load_TLS(t,cpu) (paravirt_ops.load_tls((t),(cpu))) -#define write_ldt_entry(dt, entry, low, high) \ - (paravirt_ops.write_ldt_entry((dt), (entry), (low), (high))) -#define write_gdt_entry(dt, entry, low, high) \ - (paravirt_ops.write_gdt_entry((dt), (entry), (low), (high))) -#define write_idt_entry(dt, entry, low, high) \ - (paravirt_ops.write_idt_entry((dt), (entry), (low), (high))) -#define set_iopl_mask(mask) (paravirt_ops.set_iopl_mask(mask)) +static inline void load_TR_desc(void) +{ + PVOP_VCALL0(load_tr_desc); +} +static inline void load_gdt(const struct Xgt_desc_struct *dtr) +{ + PVOP_VCALL1(load_gdt, dtr); +} +static inline void load_idt(const struct Xgt_desc_struct *dtr) +{ + PVOP_VCALL1(load_idt, dtr); +} +static inline void set_ldt(const void *addr, unsigned entries) +{ + PVOP_VCALL2(set_ldt, addr, entries); +} +static inline void store_gdt(struct Xgt_desc_struct *dtr) +{ + PVOP_VCALL1(store_gdt, dtr); +} +static inline void store_idt(struct Xgt_desc_struct *dtr) +{ + PVOP_VCALL1(store_idt, dtr); +} +static inline unsigned long paravirt_store_tr(void) +{ + return PVOP_CALL0(unsigned long, store_tr); +} +#define store_tr(tr) ((tr) = paravirt_store_tr()) +static inline void load_TLS(struct thread_struct *t, unsigned cpu) +{ + PVOP_VCALL2(load_tls, t, cpu); +} +static inline void write_ldt_entry(void *dt, int entry, u32 low, u32 high) +{ + PVOP_VCALL4(write_ldt_entry, dt, entry, low, high); +} +static inline void write_gdt_entry(void *dt, int entry, u32 low, u32 high) +{ + PVOP_VCALL4(write_gdt_entry, dt, entry, low, high); +} +static inline void write_idt_entry(void *dt, int entry, u32 low, u32 high) +{ + PVOP_VCALL4(write_idt_entry, dt, entry, low, high); +} +static inline void set_iopl_mask(unsigned mask) +{ + PVOP_VCALL1(set_iopl_mask, mask); +} /* The paravirtualized I/O functions */ static inline void slow_down_io(void) { @@ -319,215 +655,390 @@ static inline void slow_down_io(void) { */ static inline void apic_write(unsigned long reg, unsigned long v) { - paravirt_ops.apic_write(reg,v); + PVOP_VCALL2(apic_write, reg, v); } static inline void apic_write_atomic(unsigned long reg, unsigned long v) { - paravirt_ops.apic_write_atomic(reg,v); + PVOP_VCALL2(apic_write_atomic, reg, v); } static inline unsigned long apic_read(unsigned long reg) { - return paravirt_ops.apic_read(reg); + return PVOP_CALL1(unsigned long, apic_read, reg); } static inline void setup_boot_clock(void) { - paravirt_ops.setup_boot_clock(); + PVOP_VCALL0(setup_boot_clock); } static inline void setup_secondary_clock(void) { - paravirt_ops.setup_secondary_clock(); + PVOP_VCALL0(setup_secondary_clock); } #endif +static inline void paravirt_pagetable_setup_start(pgd_t *base) +{ + if (paravirt_ops.pagetable_setup_start) + (*paravirt_ops.pagetable_setup_start)(base); +} + +static inline void paravirt_pagetable_setup_done(pgd_t *base) +{ + if (paravirt_ops.pagetable_setup_done) + (*paravirt_ops.pagetable_setup_done)(base); +} + #ifdef CONFIG_SMP static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, unsigned long start_esp) { - return paravirt_ops.startup_ipi_hook(phys_apicid, start_eip, start_esp); + PVOP_VCALL3(startup_ipi_hook, phys_apicid, start_eip, start_esp); } #endif -#define __flush_tlb() paravirt_ops.flush_tlb_user() -#define __flush_tlb_global() paravirt_ops.flush_tlb_kernel() -#define __flush_tlb_single(addr) paravirt_ops.flush_tlb_single(addr) +static inline void paravirt_activate_mm(struct mm_struct *prev, + struct mm_struct *next) +{ + PVOP_VCALL2(activate_mm, prev, next); +} -#define paravirt_map_pt_hook(type, va, pfn) paravirt_ops.map_pt_hook(type, va, pfn) +static inline void arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) +{ + PVOP_VCALL2(dup_mmap, oldmm, mm); +} -#define paravirt_alloc_pt(pfn) paravirt_ops.alloc_pt(pfn) -#define paravirt_release_pt(pfn) paravirt_ops.release_pt(pfn) +static inline void arch_exit_mmap(struct mm_struct *mm) +{ + PVOP_VCALL1(exit_mmap, mm); +} -#define paravirt_alloc_pd(pfn) paravirt_ops.alloc_pd(pfn) -#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) \ - paravirt_ops.alloc_pd_clone(pfn, clonepfn, start, count) -#define paravirt_release_pd(pfn) paravirt_ops.release_pd(pfn) +static inline void __flush_tlb(void) +{ + PVOP_VCALL0(flush_tlb_user); +} +static inline void __flush_tlb_global(void) +{ + PVOP_VCALL0(flush_tlb_kernel); +} +static inline void __flush_tlb_single(unsigned long addr) +{ + PVOP_VCALL1(flush_tlb_single, addr); +} -static inline void set_pte(pte_t *ptep, pte_t pteval) +static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, + unsigned long va) { - paravirt_ops.set_pte(ptep, pteval); + PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va); } -static inline void set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval) +static inline void paravirt_alloc_pt(unsigned pfn) { - paravirt_ops.set_pte_at(mm, addr, ptep, pteval); + PVOP_VCALL1(alloc_pt, pfn); +} +static inline void paravirt_release_pt(unsigned pfn) +{ + PVOP_VCALL1(release_pt, pfn); } -static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval) +static inline void paravirt_alloc_pd(unsigned pfn) { - paravirt_ops.set_pmd(pmdp, pmdval); + PVOP_VCALL1(alloc_pd, pfn); } -static inline void pte_update(struct mm_struct *mm, u32 addr, pte_t *ptep) +static inline void paravirt_alloc_pd_clone(unsigned pfn, unsigned clonepfn, + unsigned start, unsigned count) { - paravirt_ops.pte_update(mm, addr, ptep); + PVOP_VCALL4(alloc_pd_clone, pfn, clonepfn, start, count); +} +static inline void paravirt_release_pd(unsigned pfn) +{ + PVOP_VCALL1(release_pd, pfn); } -static inline void pte_update_defer(struct mm_struct *mm, u32 addr, pte_t *ptep) +#ifdef CONFIG_HIGHPTE +static inline void *kmap_atomic_pte(struct page *page, enum km_type type) { - paravirt_ops.pte_update_defer(mm, addr, ptep); + unsigned long ret; + ret = PVOP_CALL2(unsigned long, kmap_atomic_pte, page, type); + return (void *)ret; +} +#endif + +static inline void pte_update(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + PVOP_VCALL3(pte_update, mm, addr, ptep); +} + +static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + PVOP_VCALL3(pte_update_defer, mm, addr, ptep); } #ifdef CONFIG_X86_PAE +static inline pte_t __pte(unsigned long long val) +{ + unsigned long long ret = PVOP_CALL2(unsigned long long, make_pte, + val, val >> 32); + return (pte_t) { ret, ret >> 32 }; +} + +static inline pmd_t __pmd(unsigned long long val) +{ + return (pmd_t) { PVOP_CALL2(unsigned long long, make_pmd, val, val >> 32) }; +} + +static inline pgd_t __pgd(unsigned long long val) +{ + return (pgd_t) { PVOP_CALL2(unsigned long long, make_pgd, val, val >> 32) }; +} + +static inline unsigned long long pte_val(pte_t x) +{ + return PVOP_CALL2(unsigned long long, pte_val, x.pte_low, x.pte_high); +} + +static inline unsigned long long pmd_val(pmd_t x) +{ + return PVOP_CALL2(unsigned long long, pmd_val, x.pmd, x.pmd >> 32); +} + +static inline unsigned long long pgd_val(pgd_t x) +{ + return PVOP_CALL2(unsigned long long, pgd_val, x.pgd, x.pgd >> 32); +} + +static inline void set_pte(pte_t *ptep, pte_t pteval) +{ + PVOP_VCALL3(set_pte, ptep, pteval.pte_low, pteval.pte_high); +} + +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval) +{ + /* 5 arg words */ + paravirt_ops.set_pte_at(mm, addr, ptep, pteval); +} + static inline void set_pte_atomic(pte_t *ptep, pte_t pteval) { - paravirt_ops.set_pte_atomic(ptep, pteval); + PVOP_VCALL3(set_pte_atomic, ptep, pteval.pte_low, pteval.pte_high); } -static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) +static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) { + /* 5 arg words */ paravirt_ops.set_pte_present(mm, addr, ptep, pte); } +static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval) +{ + PVOP_VCALL3(set_pmd, pmdp, pmdval.pmd, pmdval.pmd >> 32); +} + static inline void set_pud(pud_t *pudp, pud_t pudval) { - paravirt_ops.set_pud(pudp, pudval); + PVOP_VCALL3(set_pud, pudp, pudval.pgd.pgd, pudval.pgd.pgd >> 32); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - paravirt_ops.pte_clear(mm, addr, ptep); + PVOP_VCALL3(pte_clear, mm, addr, ptep); } static inline void pmd_clear(pmd_t *pmdp) { - paravirt_ops.pmd_clear(pmdp); + PVOP_VCALL1(pmd_clear, pmdp); } -#endif -/* Lazy mode for batching updates / context switch */ -#define PARAVIRT_LAZY_NONE 0 -#define PARAVIRT_LAZY_MMU 1 -#define PARAVIRT_LAZY_CPU 2 -#define PARAVIRT_LAZY_FLUSH 3 +#else /* !CONFIG_X86_PAE */ + +static inline pte_t __pte(unsigned long val) +{ + return (pte_t) { PVOP_CALL1(unsigned long, make_pte, val) }; +} + +static inline pgd_t __pgd(unsigned long val) +{ + return (pgd_t) { PVOP_CALL1(unsigned long, make_pgd, val) }; +} + +static inline unsigned long pte_val(pte_t x) +{ + return PVOP_CALL1(unsigned long, pte_val, x.pte_low); +} + +static inline unsigned long pgd_val(pgd_t x) +{ + return PVOP_CALL1(unsigned long, pgd_val, x.pgd); +} + +static inline void set_pte(pte_t *ptep, pte_t pteval) +{ + PVOP_VCALL2(set_pte, ptep, pteval.pte_low); +} + +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval) +{ + PVOP_VCALL4(set_pte_at, mm, addr, ptep, pteval.pte_low); +} + +static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval) +{ + PVOP_VCALL2(set_pmd, pmdp, pmdval.pud.pgd.pgd); +} +#endif /* CONFIG_X86_PAE */ #define __HAVE_ARCH_ENTER_LAZY_CPU_MODE -#define arch_enter_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_CPU) -#define arch_leave_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) -#define arch_flush_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_FLUSH) +static inline void arch_enter_lazy_cpu_mode(void) +{ + PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_CPU); +} + +static inline void arch_leave_lazy_cpu_mode(void) +{ + PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE); +} + +static inline void arch_flush_lazy_cpu_mode(void) +{ + PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH); +} + #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define arch_enter_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_MMU) -#define arch_leave_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) -#define arch_flush_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_FLUSH) +static inline void arch_enter_lazy_mmu_mode(void) +{ + PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_MMU); +} + +static inline void arch_leave_lazy_mmu_mode(void) +{ + PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE); +} + +static inline void arch_flush_lazy_mmu_mode(void) +{ + PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH); +} + +void _paravirt_nop(void); +#define paravirt_nop ((void *)_paravirt_nop) /* These all sit in the .parainstructions section to tell us what to patch. */ -struct paravirt_patch { +struct paravirt_patch_site { u8 *instr; /* original instructions */ u8 instrtype; /* type of this instruction */ u8 len; /* length of original instruction */ u16 clobbers; /* what registers you may clobber */ }; -#define paravirt_alt(insn_string, typenum, clobber) \ - "771:\n\t" insn_string "\n" "772:\n" \ - ".pushsection .parainstructions,\"a\"\n" \ - " .long 771b\n" \ - " .byte " __stringify(typenum) "\n" \ - " .byte 772b-771b\n" \ - " .short " __stringify(clobber) "\n" \ - ".popsection" +extern struct paravirt_patch_site __parainstructions[], + __parainstructions_end[]; static inline unsigned long __raw_local_save_flags(void) { unsigned long f; - __asm__ __volatile__(paravirt_alt( "pushl %%ecx; pushl %%edx;" - "call *%1;" - "popl %%edx; popl %%ecx", - PARAVIRT_SAVE_FLAGS, CLBR_NONE) - : "=a"(f): "m"(paravirt_ops.save_fl) - : "memory", "cc"); + asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;" + PARAVIRT_CALL + "popl %%edx; popl %%ecx") + : "=a"(f) + : paravirt_type(save_fl), + paravirt_clobber(CLBR_EAX) + : "memory", "cc"); return f; } static inline void raw_local_irq_restore(unsigned long f) { - __asm__ __volatile__(paravirt_alt( "pushl %%ecx; pushl %%edx;" - "call *%1;" - "popl %%edx; popl %%ecx", - PARAVIRT_RESTORE_FLAGS, CLBR_EAX) - : "=a"(f) : "m" (paravirt_ops.restore_fl), "0"(f) - : "memory", "cc"); + asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;" + PARAVIRT_CALL + "popl %%edx; popl %%ecx") + : "=a"(f) + : "0"(f), + paravirt_type(restore_fl), + paravirt_clobber(CLBR_EAX) + : "memory", "cc"); } static inline void raw_local_irq_disable(void) { - __asm__ __volatile__(paravirt_alt( "pushl %%ecx; pushl %%edx;" - "call *%0;" - "popl %%edx; popl %%ecx", - PARAVIRT_IRQ_DISABLE, CLBR_EAX) - : : "m" (paravirt_ops.irq_disable) - : "memory", "eax", "cc"); + asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;" + PARAVIRT_CALL + "popl %%edx; popl %%ecx") + : + : paravirt_type(irq_disable), + paravirt_clobber(CLBR_EAX) + : "memory", "eax", "cc"); } static inline void raw_local_irq_enable(void) { - __asm__ __volatile__(paravirt_alt( "pushl %%ecx; pushl %%edx;" - "call *%0;" - "popl %%edx; popl %%ecx", - PARAVIRT_IRQ_ENABLE, CLBR_EAX) - : : "m" (paravirt_ops.irq_enable) - : "memory", "eax", "cc"); + asm volatile(paravirt_alt("pushl %%ecx; pushl %%edx;" + PARAVIRT_CALL + "popl %%edx; popl %%ecx") + : + : paravirt_type(irq_enable), + paravirt_clobber(CLBR_EAX) + : "memory", "eax", "cc"); } static inline unsigned long __raw_local_irq_save(void) { unsigned long f; - __asm__ __volatile__(paravirt_alt( "pushl %%ecx; pushl %%edx;" - "call *%1; pushl %%eax;" - "call *%2; popl %%eax;" - "popl %%edx; popl %%ecx", - PARAVIRT_SAVE_FLAGS_IRQ_DISABLE, - CLBR_NONE) - : "=a"(f) - : "m" (paravirt_ops.save_fl), - "m" (paravirt_ops.irq_disable) - : "memory", "cc"); + f = __raw_local_save_flags(); + raw_local_irq_disable(); return f; } -#define CLI_STRING paravirt_alt("pushl %%ecx; pushl %%edx;" \ - "call *paravirt_ops+%c[irq_disable];" \ - "popl %%edx; popl %%ecx", \ - PARAVIRT_IRQ_DISABLE, CLBR_EAX) +#define CLI_STRING \ + _paravirt_alt("pushl %%ecx; pushl %%edx;" \ + "call *paravirt_ops+%c[paravirt_cli_type]*4;" \ + "popl %%edx; popl %%ecx", \ + "%c[paravirt_cli_type]", "%c[paravirt_clobber]") + +#define STI_STRING \ + _paravirt_alt("pushl %%ecx; pushl %%edx;" \ + "call *paravirt_ops+%c[paravirt_sti_type]*4;" \ + "popl %%edx; popl %%ecx", \ + "%c[paravirt_sti_type]", "%c[paravirt_clobber]") -#define STI_STRING paravirt_alt("pushl %%ecx; pushl %%edx;" \ - "call *paravirt_ops+%c[irq_enable];" \ - "popl %%edx; popl %%ecx", \ - PARAVIRT_IRQ_ENABLE, CLBR_EAX) #define CLI_STI_CLOBBERS , "%eax" -#define CLI_STI_INPUT_ARGS \ +#define CLI_STI_INPUT_ARGS \ , \ - [irq_disable] "i" (offsetof(struct paravirt_ops, irq_disable)), \ - [irq_enable] "i" (offsetof(struct paravirt_ops, irq_enable)) + [paravirt_cli_type] "i" (PARAVIRT_PATCH(irq_disable)), \ + [paravirt_sti_type] "i" (PARAVIRT_PATCH(irq_enable)), \ + paravirt_clobber(CLBR_EAX) + +/* 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 #else /* __ASSEMBLY__ */ -#define PARA_PATCH(ptype, clobbers, ops) \ +#define PARA_PATCH(off) ((off) / 4) + +#define PARA_SITE(ptype, clobbers, ops) \ 771:; \ ops; \ 772:; \ @@ -538,28 +1049,30 @@ static inline unsigned long __raw_local_irq_save(void) .short clobbers; \ .popsection -#define INTERRUPT_RETURN \ - PARA_PATCH(PARAVIRT_INTERRUPT_RETURN, CLBR_ANY, \ - jmp *%cs:paravirt_ops+PARAVIRT_iret) +#define INTERRUPT_RETURN \ + PARA_SITE(PARA_PATCH(PARAVIRT_iret), CLBR_NONE, \ + jmp *%cs:paravirt_ops+PARAVIRT_iret) -#define DISABLE_INTERRUPTS(clobbers) \ - PARA_PATCH(PARAVIRT_IRQ_DISABLE, clobbers, \ - pushl %ecx; pushl %edx; \ - call *paravirt_ops+PARAVIRT_irq_disable; \ - popl %edx; popl %ecx) \ +#define DISABLE_INTERRUPTS(clobbers) \ + PARA_SITE(PARA_PATCH(PARAVIRT_irq_disable), clobbers, \ + pushl %eax; pushl %ecx; pushl %edx; \ + call *%cs:paravirt_ops+PARAVIRT_irq_disable; \ + popl %edx; popl %ecx; popl %eax) \ -#define ENABLE_INTERRUPTS(clobbers) \ - PARA_PATCH(PARAVIRT_IRQ_ENABLE, clobbers, \ - pushl %ecx; pushl %edx; \ - call *%cs:paravirt_ops+PARAVIRT_irq_enable; \ - popl %edx; popl %ecx) +#define ENABLE_INTERRUPTS(clobbers) \ + PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable), clobbers, \ + pushl %eax; pushl %ecx; pushl %edx; \ + call *%cs:paravirt_ops+PARAVIRT_irq_enable; \ + popl %edx; popl %ecx; popl %eax) -#define ENABLE_INTERRUPTS_SYSEXIT \ - PARA_PATCH(PARAVIRT_STI_SYSEXIT, CLBR_ANY, \ - jmp *%cs:paravirt_ops+PARAVIRT_irq_enable_sysexit) +#define ENABLE_INTERRUPTS_SYSEXIT \ + PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable_sysexit), CLBR_NONE, \ + jmp *%cs:paravirt_ops+PARAVIRT_irq_enable_sysexit) #define GET_CR0_INTO_EAX \ - call *paravirt_ops+PARAVIRT_read_cr0 + push %ecx; push %edx; \ + call *paravirt_ops+PARAVIRT_read_cr0; \ + pop %edx; pop %ecx #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT */ diff --git a/include/asm-i386/pda.h b/include/asm-i386/pda.h deleted file mode 100644 index b12d59a318b7..000000000000 --- a/include/asm-i386/pda.h +++ /dev/null @@ -1,100 +0,0 @@ -/* - Per-processor Data Areas - Jeremy Fitzhardinge <jeremy@goop.org> 2006 - Based on asm-x86_64/pda.h by Andi Kleen. - */ -#ifndef _I386_PDA_H -#define _I386_PDA_H - -#include <linux/stddef.h> -#include <linux/types.h> - -struct i386_pda -{ - struct i386_pda *_pda; /* pointer to self */ - - int cpu_number; - struct task_struct *pcurrent; /* current process */ - struct pt_regs *irq_regs; -}; - -extern struct i386_pda *_cpu_pda[]; - -#define cpu_pda(i) (_cpu_pda[i]) - -#define pda_offset(field) offsetof(struct i386_pda, field) - -extern void __bad_pda_field(void); - -/* This variable is never instantiated. It is only used as a stand-in - for the real per-cpu PDA memory, so that gcc can understand what - memory operations the inline asms() below are performing. This - eliminates the need to make the asms volatile or have memory - clobbers, so gcc can readily analyse them. */ -extern struct i386_pda _proxy_pda; - -#define pda_to_op(op,field,val) \ - do { \ - typedef typeof(_proxy_pda.field) T__; \ - if (0) { T__ tmp__; tmp__ = (val); } \ - switch (sizeof(_proxy_pda.field)) { \ - case 1: \ - asm(op "b %1,%%fs:%c2" \ - : "+m" (_proxy_pda.field) \ - :"ri" ((T__)val), \ - "i"(pda_offset(field))); \ - break; \ - case 2: \ - asm(op "w %1,%%fs:%c2" \ - : "+m" (_proxy_pda.field) \ - :"ri" ((T__)val), \ - "i"(pda_offset(field))); \ - break; \ - case 4: \ - asm(op "l %1,%%fs:%c2" \ - : "+m" (_proxy_pda.field) \ - :"ri" ((T__)val), \ - "i"(pda_offset(field))); \ - break; \ - default: __bad_pda_field(); \ - } \ - } while (0) - -#define pda_from_op(op,field) \ - ({ \ - typeof(_proxy_pda.field) ret__; \ - switch (sizeof(_proxy_pda.field)) { \ - case 1: \ - asm(op "b %%fs:%c1,%0" \ - : "=r" (ret__) \ - : "i" (pda_offset(field)), \ - "m" (_proxy_pda.field)); \ - break; \ - case 2: \ - asm(op "w %%fs:%c1,%0" \ - : "=r" (ret__) \ - : "i" (pda_offset(field)), \ - "m" (_proxy_pda.field)); \ - break; \ - case 4: \ - asm(op "l %%fs:%c1,%0" \ - : "=r" (ret__) \ - : "i" (pda_offset(field)), \ - "m" (_proxy_pda.field)); \ - break; \ - default: __bad_pda_field(); \ - } \ - ret__; }) - -/* Return a pointer to a pda field */ -#define pda_addr(field) \ - ((typeof(_proxy_pda.field) *)((unsigned char *)read_pda(_pda) + \ - pda_offset(field))) - -#define read_pda(field) pda_from_op("mov",field) -#define write_pda(field,val) pda_to_op("mov",field,val) -#define add_pda(field,val) pda_to_op("add",field,val) -#define sub_pda(field,val) pda_to_op("sub",field,val) -#define or_pda(field,val) pda_to_op("or",field,val) - -#endif /* _I386_PDA_H */ diff --git a/include/asm-i386/percpu.h b/include/asm-i386/percpu.h index 510ae1d3486c..f54830b5d5ac 100644 --- a/include/asm-i386/percpu.h +++ b/include/asm-i386/percpu.h @@ -1,9 +1,32 @@ #ifndef __ARCH_I386_PERCPU__ #define __ARCH_I386_PERCPU__ -#ifndef __ASSEMBLY__ -#include <asm-generic/percpu.h> -#else +#ifdef __ASSEMBLY__ + +/* + * PER_CPU finds an address of a per-cpu variable. + * + * Args: + * var - variable name + * reg - 32bit register + * + * The resulting address is stored in the "reg" argument. + * + * Example: + * PER_CPU(cpu_gdt_descr, %ebx) + */ +#ifdef CONFIG_SMP +#define PER_CPU(var, reg) \ + movl %fs:per_cpu__##this_cpu_off, reg; \ + lea per_cpu__##var(reg), reg +#define PER_CPU_VAR(var) %fs:per_cpu__##var +#else /* ! SMP */ +#define PER_CPU(var, reg) \ + movl $per_cpu__##var, reg +#define PER_CPU_VAR(var) per_cpu__##var +#endif /* SMP */ + +#else /* ...!ASSEMBLY */ /* * PER_CPU finds an address of a per-cpu variable. @@ -18,14 +41,109 @@ * PER_CPU(cpu_gdt_descr, %ebx) */ #ifdef CONFIG_SMP -#define PER_CPU(var, cpu) \ - movl __per_cpu_offset(,cpu,4), cpu; \ - addl $per_cpu__/**/var, cpu; -#else /* ! SMP */ -#define PER_CPU(var, cpu) \ - movl $per_cpu__/**/var, cpu; +/* Same as generic implementation except for optimized local access. */ +#define __GENERIC_PER_CPU + +/* This is used for other cpus to find our section. */ +extern unsigned long __per_cpu_offset[]; + +#define per_cpu_offset(x) (__per_cpu_offset[x]) + +/* Separate out the type, so (int[3], foo) works. */ +#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name +#define DEFINE_PER_CPU(type, name) \ + __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name + +/* We can use this directly for local CPU (faster). */ +DECLARE_PER_CPU(unsigned long, this_cpu_off); + +/* var is in discarded region: offset to particular copy we want */ +#define per_cpu(var, cpu) (*({ \ + extern int simple_indentifier_##var(void); \ + RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]); })) + +#define __raw_get_cpu_var(var) (*({ \ + extern int simple_indentifier_##var(void); \ + RELOC_HIDE(&per_cpu__##var, x86_read_percpu(this_cpu_off)); \ +})) + +#define __get_cpu_var(var) __raw_get_cpu_var(var) + +/* A macro to avoid #include hell... */ +#define percpu_modcopy(pcpudst, src, size) \ +do { \ + unsigned int __i; \ + for_each_possible_cpu(__i) \ + memcpy((pcpudst)+__per_cpu_offset[__i], \ + (src), (size)); \ +} while (0) + +#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) +#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) + +/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */ +#define __percpu_seg "%%fs:" +#else /* !SMP */ +#include <asm-generic/percpu.h> +#define __percpu_seg "" #endif /* SMP */ +/* For arch-specific code, we can use direct single-insn ops (they + * don't give an lvalue though). */ +extern void __bad_percpu_size(void); + +#define percpu_to_op(op,var,val) \ + do { \ + typedef typeof(var) T__; \ + if (0) { T__ tmp__; tmp__ = (val); } \ + switch (sizeof(var)) { \ + case 1: \ + asm(op "b %1,"__percpu_seg"%0" \ + : "+m" (var) \ + :"ri" ((T__)val)); \ + break; \ + case 2: \ + asm(op "w %1,"__percpu_seg"%0" \ + : "+m" (var) \ + :"ri" ((T__)val)); \ + break; \ + case 4: \ + asm(op "l %1,"__percpu_seg"%0" \ + : "+m" (var) \ + :"ri" ((T__)val)); \ + break; \ + default: __bad_percpu_size(); \ + } \ + } while (0) + +#define percpu_from_op(op,var) \ + ({ \ + typeof(var) ret__; \ + switch (sizeof(var)) { \ + case 1: \ + asm(op "b "__percpu_seg"%1,%0" \ + : "=r" (ret__) \ + : "m" (var)); \ + break; \ + case 2: \ + asm(op "w "__percpu_seg"%1,%0" \ + : "=r" (ret__) \ + : "m" (var)); \ + break; \ + case 4: \ + asm(op "l "__percpu_seg"%1,%0" \ + : "=r" (ret__) \ + : "m" (var)); \ + break; \ + default: __bad_percpu_size(); \ + } \ + ret__; }) + +#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var) +#define x86_write_percpu(var,val) percpu_to_op("mov", per_cpu__##var, val) +#define x86_add_percpu(var,val) percpu_to_op("add", per_cpu__##var, val) +#define x86_sub_percpu(var,val) percpu_to_op("sub", per_cpu__##var, val) +#define x86_or_percpu(var,val) percpu_to_op("or", per_cpu__##var, val) #endif /* !__ASSEMBLY__ */ #endif /* __ARCH_I386_PERCPU__ */ diff --git a/include/asm-i386/pgalloc.h b/include/asm-i386/pgalloc.h index c8dc2d0141a7..47430175b75f 100644 --- a/include/asm-i386/pgalloc.h +++ b/include/asm-i386/pgalloc.h @@ -1,7 +1,6 @@ #ifndef _I386_PGALLOC_H #define _I386_PGALLOC_H -#include <asm/fixmap.h> #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ diff --git a/include/asm-i386/pgtable-2level-defs.h b/include/asm-i386/pgtable-2level-defs.h index 02518079f816..0f71c9f13da4 100644 --- a/include/asm-i386/pgtable-2level-defs.h +++ b/include/asm-i386/pgtable-2level-defs.h @@ -1,6 +1,8 @@ #ifndef _I386_PGTABLE_2LEVEL_DEFS_H #define _I386_PGTABLE_2LEVEL_DEFS_H +#define SHARED_KERNEL_PMD 0 + /* * traditional i386 two-level paging structure: */ diff --git a/include/asm-i386/pgtable-2level.h b/include/asm-i386/pgtable-2level.h index 38c3fcc0676d..a50fd1773de8 100644 --- a/include/asm-i386/pgtable-2level.h +++ b/include/asm-i386/pgtable-2level.h @@ -11,10 +11,23 @@ * within a page table are directly modified. Thus, the following * hook is made available. */ +static inline void native_set_pte(pte_t *ptep , pte_t pte) +{ + *ptep = pte; +} +static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep , pte_t pte) +{ + native_set_pte(ptep, pte); +} +static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + *pmdp = pmd; +} #ifndef CONFIG_PARAVIRT -#define set_pte(pteptr, pteval) (*(pteptr) = pteval) -#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) -#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) +#define set_pte(pteptr, pteval) native_set_pte(pteptr, pteval) +#define set_pte_at(mm,addr,ptep,pteval) native_set_pte_at(mm, addr, ptep, pteval) +#define set_pmd(pmdptr, pmdval) native_set_pmd(pmdptr, pmdval) #endif #define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval) @@ -23,11 +36,23 @@ #define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) #define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0) -#define raw_ptep_get_and_clear(xp) __pte(xchg(&(xp)->pte_low, 0)) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp) +{ + *xp = __pte(0); +} + +#ifdef CONFIG_SMP +static inline pte_t native_ptep_get_and_clear(pte_t *xp) +{ + return __pte(xchg(&xp->pte_low, 0)); +} +#else +#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) +#endif #define pte_page(x) pfn_to_page(pte_pfn(x)) #define pte_none(x) (!(x).pte_low) -#define pte_pfn(x) ((unsigned long)(((x).pte_low >> PAGE_SHIFT))) +#define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT) #define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) @@ -66,6 +91,4 @@ static inline int pte_exec_kernel(pte_t pte) #define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -void vmalloc_sync_all(void); - #endif /* _I386_PGTABLE_2LEVEL_H */ diff --git a/include/asm-i386/pgtable-3level-defs.h b/include/asm-i386/pgtable-3level-defs.h index eb3a1ea88671..c0df89f66e8b 100644 --- a/include/asm-i386/pgtable-3level-defs.h +++ b/include/asm-i386/pgtable-3level-defs.h @@ -1,6 +1,12 @@ #ifndef _I386_PGTABLE_3LEVEL_DEFS_H #define _I386_PGTABLE_3LEVEL_DEFS_H +#ifdef CONFIG_PARAVIRT +#define SHARED_KERNEL_PMD (paravirt_ops.shared_kernel_pmd) +#else +#define SHARED_KERNEL_PMD 1 +#endif + /* * PGDIR_SHIFT determines what a top-level page table entry can map */ diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h index 7a2318f38303..eb0f1d7e96a1 100644 --- a/include/asm-i386/pgtable-3level.h +++ b/include/asm-i386/pgtable-3level.h @@ -42,20 +42,23 @@ static inline int pte_exec_kernel(pte_t pte) return pte_x(pte); } -#ifndef CONFIG_PARAVIRT /* Rules for using set_pte: the pte being assigned *must* be * either not present or in a state where the hardware will * not attempt to update the pte. In places where this is * not possible, use pte_get_and_clear to obtain the old pte * value and then use set_pte to update it. -ben */ -static inline void set_pte(pte_t *ptep, pte_t pte) +static inline void native_set_pte(pte_t *ptep, pte_t pte) { ptep->pte_high = pte.pte_high; smp_wmb(); ptep->pte_low = pte.pte_low; } -#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) +static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep , pte_t pte) +{ + native_set_pte(ptep, pte); +} /* * Since this is only called on user PTEs, and the page fault handler @@ -63,7 +66,8 @@ static inline void set_pte(pte_t *ptep, pte_t pte) * we are justified in merely clearing the PTE present bit, followed * by a set. The ordering here is important. */ -static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) +static inline void native_set_pte_present(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) { ptep->pte_low = 0; smp_wmb(); @@ -72,32 +76,48 @@ static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte ptep->pte_low = pte.pte_low; } -#define set_pte_atomic(pteptr,pteval) \ - set_64bit((unsigned long long *)(pteptr),pte_val(pteval)) -#define set_pmd(pmdptr,pmdval) \ - set_64bit((unsigned long long *)(pmdptr),pmd_val(pmdval)) -#define set_pud(pudptr,pudval) \ - (*(pudptr) = (pudval)) +static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) +{ + set_64bit((unsigned long long *)(ptep),native_pte_val(pte)); +} +static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + set_64bit((unsigned long long *)(pmdp),native_pmd_val(pmd)); +} +static inline void native_set_pud(pud_t *pudp, pud_t pud) +{ + *pudp = pud; +} /* * For PTEs and PDEs, we must clear the P-bit first when clearing a page table * entry, so clear the bottom half first and enforce ordering with a compiler * barrier. */ -static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { ptep->pte_low = 0; smp_wmb(); ptep->pte_high = 0; } -static inline void pmd_clear(pmd_t *pmd) +static inline void native_pmd_clear(pmd_t *pmd) { u32 *tmp = (u32 *)pmd; *tmp = 0; smp_wmb(); *(tmp + 1) = 0; } + +#ifndef CONFIG_PARAVIRT +#define set_pte(ptep, pte) native_set_pte(ptep, pte) +#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) +#define set_pte_present(mm, addr, ptep, pte) native_set_pte_present(mm, addr, ptep, pte) +#define set_pte_atomic(ptep, pte) native_set_pte_atomic(ptep, pte) +#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) +#define set_pud(pudp, pud) native_set_pud(pudp, pud) +#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) +#define pmd_clear(pmd) native_pmd_clear(pmd) #endif /* @@ -119,7 +139,8 @@ static inline void pud_clear (pud_t * pud) { } #define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \ pmd_index(address)) -static inline pte_t raw_ptep_get_and_clear(pte_t *ptep) +#ifdef CONFIG_SMP +static inline pte_t native_ptep_get_and_clear(pte_t *ptep) { pte_t res; @@ -130,6 +151,9 @@ static inline pte_t raw_ptep_get_and_clear(pte_t *ptep) return res; } +#else +#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) +#endif #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) @@ -146,28 +170,21 @@ static inline int pte_none(pte_t pte) static inline unsigned long pte_pfn(pte_t pte) { - return (pte.pte_low >> PAGE_SHIFT) | - (pte.pte_high << (32 - PAGE_SHIFT)); + return pte_val(pte) >> PAGE_SHIFT; } extern unsigned long long __supported_pte_mask; static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - pte_t pte; - - pte.pte_high = (page_nr >> (32 - PAGE_SHIFT)) | \ - (pgprot_val(pgprot) >> 32); - pte.pte_high &= (__supported_pte_mask >> 32); - pte.pte_low = ((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)) & \ - __supported_pte_mask; - return pte; + return __pte((((unsigned long long)page_nr << PAGE_SHIFT) | + pgprot_val(pgprot)) & __supported_pte_mask); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) | \ - pgprot_val(pgprot)) & __supported_pte_mask); + return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) | + pgprot_val(pgprot)) & __supported_pte_mask); } /* @@ -187,6 +204,4 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) #define __pmd_free_tlb(tlb, x) do { } while (0) -#define vmalloc_sync_all() ((void)0) - #endif /* _I386_PGTABLE_3LEVEL_H */ diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h index c3b58d473a55..c6b8b944120c 100644 --- a/include/asm-i386/pgtable.h +++ b/include/asm-i386/pgtable.h @@ -159,6 +159,7 @@ void paging_init(void); extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC; #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) +#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) #define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) @@ -166,6 +167,7 @@ extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC; #define PAGE_KERNEL __pgprot(__PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) #define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) +#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX) #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) @@ -241,6 +243,8 @@ static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; re static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; } static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return pte; } +extern void vmalloc_sync_all(void); + #ifdef CONFIG_X86_PAE # include <asm/pgtable-3level.h> #else @@ -263,9 +267,18 @@ static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return p */ #define pte_update(mm, addr, ptep) do { } while (0) #define pte_update_defer(mm, addr, ptep) do { } while (0) -#define paravirt_map_pt_hook(slot, va, pfn) do { } while (0) #endif +/* local pte updates need not use xchg for locking */ +static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) +{ + pte_t res = *ptep; + + /* Pure native function needs no input for mm, addr */ + native_pte_clear(NULL, 0, ptep); + return res; +} + /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware @@ -330,7 +343,7 @@ do { \ #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_t pte = raw_ptep_get_and_clear(ptep); + pte_t pte = native_ptep_get_and_clear(ptep); pte_update(mm, addr, ptep); return pte; } @@ -340,8 +353,11 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long { pte_t pte; if (full) { - pte = *ptep; - pte_clear(mm, addr, ptep); + /* + * Full address destruction in progress; paravirt does not + * care about updates and native needs no locking + */ + pte = native_local_ptep_get_and_clear(ptep); } else { pte = ptep_get_and_clear(mm, addr, ptep); } @@ -470,24 +486,10 @@ extern pte_t *lookup_address(unsigned long address); #endif #if defined(CONFIG_HIGHPTE) -#define pte_offset_map(dir, address) \ -({ \ - pte_t *__ptep; \ - unsigned pfn = pmd_val(*(dir)) >> PAGE_SHIFT; \ - __ptep = (pte_t *)kmap_atomic(pfn_to_page(pfn),KM_PTE0);\ - paravirt_map_pt_hook(KM_PTE0,__ptep, pfn); \ - __ptep = __ptep + pte_index(address); \ - __ptep; \ -}) -#define pte_offset_map_nested(dir, address) \ -({ \ - pte_t *__ptep; \ - unsigned pfn = pmd_val(*(dir)) >> PAGE_SHIFT; \ - __ptep = (pte_t *)kmap_atomic(pfn_to_page(pfn),KM_PTE1);\ - paravirt_map_pt_hook(KM_PTE1,__ptep, pfn); \ - __ptep = __ptep + pte_index(address); \ - __ptep; \ -}) +#define pte_offset_map(dir, address) \ + ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + pte_index(address)) +#define pte_offset_map_nested(dir, address) \ + ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + pte_index(address)) #define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) #define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1) #else @@ -510,6 +512,22 @@ do { \ * tables contain all the necessary information. */ #define update_mmu_cache(vma,address,pte) do { } while (0) + +void native_pagetable_setup_start(pgd_t *base); +void native_pagetable_setup_done(pgd_t *base); + +#ifndef CONFIG_PARAVIRT +static inline void paravirt_pagetable_setup_start(pgd_t *base) +{ + native_pagetable_setup_start(base); +} + +static inline void paravirt_pagetable_setup_done(pgd_t *base) +{ + native_pagetable_setup_done(base); +} +#endif /* !CONFIG_PARAVIRT */ + #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_FLATMEM diff --git a/include/asm-i386/processor-flags.h b/include/asm-i386/processor-flags.h new file mode 100644 index 000000000000..5404e90edd57 --- /dev/null +++ b/include/asm-i386/processor-flags.h @@ -0,0 +1,91 @@ +#ifndef __ASM_I386_PROCESSOR_FLAGS_H +#define __ASM_I386_PROCESSOR_FLAGS_H +/* Various flags defined: can be included from assembler. */ + +/* + * EFLAGS bits + */ +#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ +#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ +#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ +#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ +#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ +#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ +#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ +#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ +#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ +#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ +#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ +#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ +#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ +#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ +#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ +#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ +#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ + +/* + * Basic CPU control in CR0 + */ +#define X86_CR0_PE 0x00000001 /* Protection Enable */ +#define X86_CR0_MP 0x00000002 /* Monitor Coprocessor */ +#define X86_CR0_EM 0x00000004 /* Emulation */ +#define X86_CR0_TS 0x00000008 /* Task Switched */ +#define X86_CR0_ET 0x00000010 /* Extension Type */ +#define X86_CR0_NE 0x00000020 /* Numeric Error */ +#define X86_CR0_WP 0x00010000 /* Write Protect */ +#define X86_CR0_AM 0x00040000 /* Alignment Mask */ +#define X86_CR0_NW 0x20000000 /* Not Write-through */ +#define X86_CR0_CD 0x40000000 /* Cache Disable */ +#define X86_CR0_PG 0x80000000 /* Paging */ + +/* + * Paging options in CR3 + */ +#define X86_CR3_PWT 0x00000008 /* Page Write Through */ +#define X86_CR3_PCD 0x00000010 /* Page Cache Disable */ + +/* + * Intel CPU features in CR4 + */ +#define X86_CR4_VME 0x00000001 /* enable vm86 extensions */ +#define X86_CR4_PVI 0x00000002 /* virtual interrupts flag enable */ +#define X86_CR4_TSD 0x00000004 /* disable time stamp at ipl 3 */ +#define X86_CR4_DE 0x00000008 /* enable debugging extensions */ +#define X86_CR4_PSE 0x00000010 /* enable page size extensions */ +#define X86_CR4_PAE 0x00000020 /* enable physical address extensions */ +#define X86_CR4_MCE 0x00000040 /* Machine check enable */ +#define X86_CR4_PGE 0x00000080 /* enable global pages */ +#define X86_CR4_PCE 0x00000100 /* enable performance counters at ipl 3 */ +#define X86_CR4_OSFXSR 0x00000200 /* enable fast FPU save and restore */ +#define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */ +#define X86_CR4_VMXE 0x00002000 /* enable VMX virtualization */ + +/* + * x86-64 Task Priority Register, CR8 + */ +#define X86_CR8_TPR 0x00000007 /* task priority register */ + +/* + * AMD and Transmeta use MSRs for configuration; see <asm/msr-index.h> + */ + +/* + * NSC/Cyrix CPU configuration register indexes + */ +#define CX86_PCR0 0x20 +#define CX86_GCR 0xb8 +#define CX86_CCR0 0xc0 +#define CX86_CCR1 0xc1 +#define CX86_CCR2 0xc2 +#define CX86_CCR3 0xc3 +#define CX86_CCR4 0xe8 +#define CX86_CCR5 0xe9 +#define CX86_CCR6 0xea +#define CX86_CCR7 0xeb +#define CX86_PCR1 0xf0 +#define CX86_DIR0 0xfe +#define CX86_DIR1 0xff +#define CX86_ARR_BASE 0xc4 +#define CX86_RCR_BASE 0xdc + +#endif /* __ASM_I386_PROCESSOR_FLAGS_H */ diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 11bf899de8aa..70f3515c3db0 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -21,6 +21,7 @@ #include <asm/percpu.h> #include <linux/cpumask.h> #include <linux/init.h> +#include <asm/processor-flags.h> /* flag for disabling the tsc */ extern int tsc_disable; @@ -115,7 +116,8 @@ extern char ignore_fpu_irq; void __init 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 *); extern void print_cpu_info(struct cpuinfo_x86 *); extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); extern unsigned short num_cache_leaves; @@ -126,28 +128,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); static inline void detect_ht(struct cpuinfo_x86 *c) {} #endif -/* - * EFLAGS bits - */ -#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ -#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ -#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ -#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ -#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ -#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ -#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ -#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ -#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ -#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ -#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ -#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ -#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ -#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ -#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ -#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ -#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ - -static inline fastcall void native_cpuid(unsigned int *eax, unsigned int *ebx, +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. */ @@ -162,21 +143,6 @@ static inline fastcall void native_cpuid(unsigned int *eax, unsigned int *ebx, #define load_cr3(pgdir) write_cr3(__pa(pgdir)) /* - * Intel CPU features in CR4 - */ -#define X86_CR4_VME 0x0001 /* enable vm86 extensions */ -#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */ -#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */ -#define X86_CR4_DE 0x0008 /* enable debugging extensions */ -#define X86_CR4_PSE 0x0010 /* enable page size extensions */ -#define X86_CR4_PAE 0x0020 /* enable physical address extensions */ -#define X86_CR4_MCE 0x0040 /* Machine check enable */ -#define X86_CR4_PGE 0x0080 /* enable global pages */ -#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */ -#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */ -#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */ - -/* * 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 @@ -203,26 +169,6 @@ static inline void clear_in_cr4 (unsigned long mask) } /* - * NSC/Cyrix CPU configuration register indexes - */ - -#define CX86_PCR0 0x20 -#define CX86_GCR 0xb8 -#define CX86_CCR0 0xc0 -#define CX86_CCR1 0xc1 -#define CX86_CCR2 0xc2 -#define CX86_CCR3 0xc3 -#define CX86_CCR4 0xe8 -#define CX86_CCR5 0xe9 -#define CX86_CCR6 0xea -#define CX86_CCR7 0xeb -#define CX86_PCR1 0xf0 -#define CX86_DIR0 0xfe -#define CX86_DIR1 0xff -#define CX86_ARR_BASE 0xc4 -#define CX86_RCR_BASE 0xdc - -/* * NSC/Cyrix CPU indexed register access macros */ @@ -345,7 +291,8 @@ typedef struct { struct thread_struct; -struct tss_struct { +/* This is the TSS defined by the hardware. */ +struct i386_hw_tss { unsigned short back_link,__blh; unsigned long esp0; unsigned short ss0,__ss0h; @@ -369,6 +316,11 @@ struct tss_struct { unsigned short gs, __gsh; unsigned short ldt, __ldth; unsigned short trace, io_bitmap_base; +} __attribute__((packed)); + +struct tss_struct { + struct i386_hw_tss x86_tss; + /* * The extra 1 is there because the CPU will access an * additional byte beyond the end of the IO permission @@ -421,10 +373,11 @@ struct thread_struct { }; #define INIT_THREAD { \ + .esp0 = sizeof(init_stack) + (long)&init_stack, \ .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ - .fs = __KERNEL_PDA, \ + .fs = __KERNEL_PERCPU, \ } /* @@ -434,10 +387,12 @@ struct thread_struct { * be within the limit. */ #define INIT_TSS { \ - .esp0 = sizeof(init_stack) + (long)&init_stack, \ - .ss0 = __KERNEL_DS, \ - .ss1 = __KERNEL_CS, \ - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \ + .x86_tss = { \ + .esp0 = 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 }, \ } @@ -544,40 +499,70 @@ static inline void rep_nop(void) #define cpu_relax() rep_nop() -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#else -#define paravirt_enabled() 0 -#define __cpuid native_cpuid - -static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) +static inline void native_load_esp0(struct tss_struct *tss, struct thread_struct *thread) { - tss->esp0 = thread->esp0; + tss->x86_tss.esp0 = thread->esp0; /* This can only happen when SEP is enabled, no need to test "SEP"arately */ - if (unlikely(tss->ss1 != thread->sysenter_cs)) { - tss->ss1 = thread->sysenter_cs; + 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); } } -/* - * These special macros can be used to get or set a debugging register - */ -#define get_debugreg(var, register) \ - __asm__("movl %%db" #register ", %0" \ - :"=r" (var)) -#define set_debugreg(value, register) \ - __asm__("movl %0,%%db" #register \ - : /* no output */ \ - :"r" (value)) -#define set_iopl_mask native_set_iopl_mask -#endif /* CONFIG_PARAVIRT */ +static inline unsigned long native_get_debugreg(int regno) +{ + unsigned long val = 0; /* Damn you, gcc! */ + + switch (regno) { + case 0: + asm("movl %%db0, %0" :"=r" (val)); break; + case 1: + asm("movl %%db1, %0" :"=r" (val)); break; + case 2: + asm("movl %%db2, %0" :"=r" (val)); break; + case 3: + asm("movl %%db3, %0" :"=r" (val)); break; + case 6: + asm("movl %%db6, %0" :"=r" (val)); break; + case 7: + asm("movl %%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("movl %0,%%db0" : /* no output */ :"r" (value)); + break; + case 1: + asm("movl %0,%%db1" : /* no output */ :"r" (value)); + break; + case 2: + asm("movl %0,%%db2" : /* no output */ :"r" (value)); + break; + case 3: + asm("movl %0,%%db3" : /* no output */ :"r" (value)); + break; + case 6: + asm("movl %0,%%db6" : /* no output */ :"r" (value)); + break; + case 7: + asm("movl %0,%%db7" : /* no output */ :"r" (value)); + break; + default: + BUG(); + } +} /* * Set IOPL bits in EFLAGS from given mask */ -static fastcall inline void native_set_iopl_mask(unsigned mask) +static inline void native_set_iopl_mask(unsigned mask) { unsigned int reg; __asm__ __volatile__ ("pushfl;" @@ -590,6 +575,28 @@ static fastcall inline void native_set_iopl_mask(unsigned mask) : "i" (~X86_EFLAGS_IOPL), "r" (mask)); } +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#else +#define paravirt_enabled() 0 +#define __cpuid native_cpuid + +static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) +{ + native_load_esp0(tss, thread); +} + +/* + * 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) + +#define set_iopl_mask native_set_iopl_mask +#endif /* CONFIG_PARAVIRT */ + /* * Generic CPUID function * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx @@ -742,8 +749,10 @@ extern unsigned long boot_option_idle_override; extern void enable_sep_cpu(void); extern int sysenter_setup(void); -extern int init_gdt(int cpu, struct task_struct *idle); extern void cpu_set_gdt(int); -extern void secondary_cpu_init(void); +extern void switch_to_new_gdt(void); +extern void cpu_init(void); + +extern int force_mwait; #endif /* __ASM_I386_PROCESSOR_H */ diff --git a/include/asm-i386/reboot.h b/include/asm-i386/reboot.h new file mode 100644 index 000000000000..e9e3ffc22c07 --- /dev/null +++ b/include/asm-i386/reboot.h @@ -0,0 +1,20 @@ +#ifndef _ASM_REBOOT_H +#define _ASM_REBOOT_H + +struct pt_regs; + +struct machine_ops +{ + void (*restart)(char *cmd); + void (*halt)(void); + void (*power_off)(void); + void (*shutdown)(void); + void (*crash_shutdown)(struct pt_regs *); + void (*emergency_restart)(void); +}; + +extern struct machine_ops machine_ops; + +void machine_real_restart(unsigned char *code, int length); + +#endif /* _ASM_REBOOT_H */ diff --git a/include/asm-i386/reboot_fixups.h b/include/asm-i386/reboot_fixups.h new file mode 100644 index 000000000000..0cb7d87c2b68 --- /dev/null +++ b/include/asm-i386/reboot_fixups.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_REBOOT_FIXUPS_H +#define _LINUX_REBOOT_FIXUPS_H + +extern void mach_reboot_fixups(void); + +#endif /* _LINUX_REBOOT_FIXUPS_H */ diff --git a/include/asm-i386/required-features.h b/include/asm-i386/required-features.h new file mode 100644 index 000000000000..9db866c1e64c --- /dev/null +++ b/include/asm-i386/required-features.h @@ -0,0 +1,34 @@ +#ifndef _ASM_REQUIRED_FEATURES_H +#define _ASM_REQUIRED_FEATURES_H 1 + +/* Define minimum CPUID feature set for kernel These bits are checked + really early to actually display a visible error message before the + kernel dies. Only add word 0 bits here + + Some requirements that are not in CPUID yet are also in the + CONFIG_X86_MINIMUM_CPU mode which is checked too. + + The real information is in arch/i386/Kconfig.cpu, this just converts + the CONFIGs into a bitmask */ + +#ifdef CONFIG_X86_PAE +#define NEED_PAE (1<<X86_FEATURE_PAE) +#else +#define NEED_PAE 0 +#endif + +#ifdef CONFIG_X86_CMOV +#define NEED_CMOV (1<<X86_FEATURE_CMOV) +#else +#define NEED_CMOV 0 +#endif + +#ifdef CONFIG_X86_CMPXCHG64 +#define NEED_CMPXCHG64 (1<<X86_FEATURE_CX8) +#else +#define NEED_CMPXCHG64 0 +#endif + +#define REQUIRED_MASK1 (NEED_PAE|NEED_CMOV|NEED_CMPXCHG64) + +#endif diff --git a/include/asm-i386/segment.h b/include/asm-i386/segment.h index 065f10bfa487..597a47c2515f 100644 --- a/include/asm-i386/segment.h +++ b/include/asm-i386/segment.h @@ -39,7 +39,7 @@ * 25 - APM BIOS support * * 26 - ESPFIX small SS - * 27 - PDA [ per-cpu private data area ] + * 27 - per-cpu [ offset to per-cpu data area ] * 28 - unused * 29 - unused * 30 - unused @@ -74,8 +74,12 @@ #define GDT_ENTRY_ESPFIX_SS (GDT_ENTRY_KERNEL_BASE + 14) #define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8) -#define GDT_ENTRY_PDA (GDT_ENTRY_KERNEL_BASE + 15) -#define __KERNEL_PDA (GDT_ENTRY_PDA * 8) +#define GDT_ENTRY_PERCPU (GDT_ENTRY_KERNEL_BASE + 15) +#ifdef CONFIG_SMP +#define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8) +#else +#define __KERNEL_PERCPU 0 +#endif #define GDT_ENTRY_DOUBLEFAULT_TSS 31 diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h index 6bf0033a301c..090abc1da32a 100644 --- a/include/asm-i386/smp.h +++ b/include/asm-i386/smp.h @@ -8,19 +8,15 @@ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/cpumask.h> -#include <asm/pda.h> #endif -#ifdef CONFIG_X86_LOCAL_APIC -#ifndef __ASSEMBLY__ -#include <asm/fixmap.h> +#if defined(CONFIG_X86_LOCAL_APIC) && !defined(__ASSEMBLY__) #include <asm/bitops.h> #include <asm/mpspec.h> +#include <asm/apic.h> #ifdef CONFIG_X86_IO_APIC #include <asm/io_apic.h> #endif -#include <asm/apic.h> -#endif #endif #define BAD_APICID 0xFFu @@ -52,6 +48,59 @@ extern void cpu_exit_clear(void); extern void cpu_uninit(void); #endif +struct smp_ops +{ + void (*smp_prepare_boot_cpu)(void); + void (*smp_prepare_cpus)(unsigned max_cpus); + int (*cpu_up)(unsigned cpu); + void (*smp_cpus_done)(unsigned max_cpus); + + void (*smp_send_stop)(void); + void (*smp_send_reschedule)(int cpu); + int (*smp_call_function_mask)(cpumask_t mask, + void (*func)(void *info), void *info, + int wait); +}; + +extern struct smp_ops smp_ops; + +static inline void smp_prepare_boot_cpu(void) +{ + smp_ops.smp_prepare_boot_cpu(); +} +static inline void smp_prepare_cpus(unsigned int max_cpus) +{ + smp_ops.smp_prepare_cpus(max_cpus); +} +static inline int __cpu_up(unsigned int cpu) +{ + return smp_ops.cpu_up(cpu); +} +static inline void smp_cpus_done(unsigned int max_cpus) +{ + smp_ops.smp_cpus_done(max_cpus); +} + +static inline void smp_send_stop(void) +{ + smp_ops.smp_send_stop(); +} +static inline void smp_send_reschedule(int cpu) +{ + smp_ops.smp_send_reschedule(cpu); +} +static inline int smp_call_function_mask(cpumask_t mask, + void (*func) (void *info), void *info, + int wait) +{ + return smp_ops.smp_call_function_mask(mask, func, info, wait); +} + +void native_smp_prepare_boot_cpu(void); +void native_smp_prepare_cpus(unsigned int max_cpus); +int native_cpu_up(unsigned int cpunum); +void native_smp_cpus_done(unsigned int max_cpus); + #ifndef CONFIG_PARAVIRT #define startup_ipi_hook(phys_apicid, start_eip, start_esp) \ do { } while (0) @@ -62,7 +111,8 @@ do { } while (0) * from the initial startup. We map APIC_BASE very early in page_setup(), * so this is correct in the x86 case. */ -#define raw_smp_processor_id() (read_pda(cpu_number)) +DECLARE_PER_CPU(int, cpu_number); +#define raw_smp_processor_id() (x86_read_percpu(cpu_number)) extern cpumask_t cpu_callout_map; extern cpumask_t cpu_callin_map; diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h index a6d20d9a1a30..c3a58c08c495 100644 --- a/include/asm-i386/system.h +++ b/include/asm-i386/system.h @@ -88,65 +88,96 @@ __asm__ __volatile__ ("movw %%dx,%1\n\t" \ #define savesegment(seg, value) \ asm volatile("mov %%" #seg ",%0":"=rm" (value)) + +static inline void native_clts(void) +{ + asm volatile ("clts"); +} + +static inline unsigned long native_read_cr0(void) +{ + unsigned long val; + asm volatile("movl %%cr0,%0\n\t" :"=r" (val)); + return val; +} + +static inline void native_write_cr0(unsigned long val) +{ + asm volatile("movl %0,%%cr0": :"r" (val)); +} + +static inline unsigned long native_read_cr2(void) +{ + unsigned long val; + asm volatile("movl %%cr2,%0\n\t" :"=r" (val)); + return val; +} + +static inline void native_write_cr2(unsigned long val) +{ + asm volatile("movl %0,%%cr2": :"r" (val)); +} + +static inline unsigned long native_read_cr3(void) +{ + unsigned long val; + asm volatile("movl %%cr3,%0\n\t" :"=r" (val)); + return val; +} + +static inline void native_write_cr3(unsigned long val) +{ + asm volatile("movl %0,%%cr3": :"r" (val)); +} + +static inline unsigned long native_read_cr4(void) +{ + unsigned long val; + asm volatile("movl %%cr4,%0\n\t" :"=r" (val)); + return val; +} + +static inline unsigned long native_read_cr4_safe(void) +{ + unsigned long val; + /* This could fault if %cr4 does not exist */ + asm("1: movl %%cr4, %0 \n" + "2: \n" + ".section __ex_table,\"a\" \n" + ".long 1b,2b \n" + ".previous \n" + : "=r" (val): "0" (0)); + return val; +} + +static inline void native_write_cr4(unsigned long val) +{ + asm volatile("movl %0,%%cr4": :"r" (val)); +} + +static inline void native_wbinvd(void) +{ + asm volatile("wbinvd": : :"memory"); +} + + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else -#define read_cr0() ({ \ - unsigned int __dummy; \ - __asm__ __volatile__( \ - "movl %%cr0,%0\n\t" \ - :"=r" (__dummy)); \ - __dummy; \ -}) -#define write_cr0(x) \ - __asm__ __volatile__("movl %0,%%cr0": :"r" (x)) - -#define read_cr2() ({ \ - unsigned int __dummy; \ - __asm__ __volatile__( \ - "movl %%cr2,%0\n\t" \ - :"=r" (__dummy)); \ - __dummy; \ -}) -#define write_cr2(x) \ - __asm__ __volatile__("movl %0,%%cr2": :"r" (x)) - -#define read_cr3() ({ \ - unsigned int __dummy; \ - __asm__ ( \ - "movl %%cr3,%0\n\t" \ - :"=r" (__dummy)); \ - __dummy; \ -}) -#define write_cr3(x) \ - __asm__ __volatile__("movl %0,%%cr3": :"r" (x)) - -#define read_cr4() ({ \ - unsigned int __dummy; \ - __asm__( \ - "movl %%cr4,%0\n\t" \ - :"=r" (__dummy)); \ - __dummy; \ -}) -#define read_cr4_safe() ({ \ - unsigned int __dummy; \ - /* This could fault if %cr4 does not exist */ \ - __asm__("1: movl %%cr4, %0 \n" \ - "2: \n" \ - ".section __ex_table,\"a\" \n" \ - ".long 1b,2b \n" \ - ".previous \n" \ - : "=r" (__dummy): "0" (0)); \ - __dummy; \ -}) -#define write_cr4(x) \ - __asm__ __volatile__("movl %0,%%cr4": :"r" (x)) - -#define wbinvd() \ - __asm__ __volatile__ ("wbinvd": : :"memory") +#define read_cr0() (native_read_cr0()) +#define write_cr0(x) (native_write_cr0(x)) +#define read_cr2() (native_read_cr2()) +#define write_cr2(x) (native_write_cr2(x)) +#define read_cr3() (native_read_cr3()) +#define write_cr3(x) (native_write_cr3(x)) +#define read_cr4() (native_read_cr4()) +#define read_cr4_safe() (native_read_cr4_safe()) +#define write_cr4(x) (native_write_cr4(x)) +#define wbinvd() (native_wbinvd()) /* Clear the 'TS' bit */ -#define clts() __asm__ __volatile__ ("clts") +#define clts() (native_clts()) + #endif/* CONFIG_PARAVIRT */ /* Set the 'TS' bit */ diff --git a/include/asm-i386/timer.h b/include/asm-i386/timer.h index 12dd67bf760f..153770e25faa 100644 --- a/include/asm-i386/timer.h +++ b/include/asm-i386/timer.h @@ -9,8 +9,6 @@ void setup_pit_timer(void); unsigned long long native_sched_clock(void); unsigned long native_calculate_cpu_khz(void); -/* Modifiers for buggy PIT handling */ -extern int pit_latch_buggy; extern int timer_ack; extern int no_timer_check; extern int no_sync_cmos_clock; diff --git a/include/asm-i386/tlbflush.h b/include/asm-i386/tlbflush.h index 4dd82840d53b..db7f77eacfa0 100644 --- a/include/asm-i386/tlbflush.h +++ b/include/asm-i386/tlbflush.h @@ -79,11 +79,15 @@ * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables + * - flush_tlb_others(cpumask, mm, va) flushes a TLBs on other cpus * * ..but the i386 has somewhat limited tlb flushing capabilities, * and page-granular flushes are available only on i486 and up. */ +#define TLB_FLUSH_ALL 0xffffffff + + #ifndef CONFIG_SMP #define flush_tlb() __flush_tlb() @@ -110,7 +114,12 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, __flush_tlb(); } -#else +static inline void native_flush_tlb_others(const cpumask_t *cpumask, + struct mm_struct *mm, unsigned long va) +{ +} + +#else /* SMP */ #include <asm/smp.h> @@ -129,6 +138,9 @@ static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long st flush_tlb_mm(vma->vm_mm); } +void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm, + unsigned long va); + #define TLBSTATE_OK 1 #define TLBSTATE_LAZY 2 @@ -139,8 +151,11 @@ struct tlb_state char __cacheline_padding[L1_CACHE_BYTES-8]; }; DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate); +#endif /* SMP */ - +#ifndef CONFIG_PARAVIRT +#define flush_tlb_others(mask, mm, va) \ + native_flush_tlb_others(&mask, mm, va) #endif #define flush_tlb_kernel_range(start, end) flush_tlb_all() diff --git a/include/asm-i386/tsc.h b/include/asm-i386/tsc.h index 84016ff481b9..3f3c1fa000b4 100644 --- a/include/asm-i386/tsc.h +++ b/include/asm-i386/tsc.h @@ -35,25 +35,30 @@ static inline cycles_t get_cycles(void) static __always_inline cycles_t get_cycles_sync(void) { unsigned long long ret; -#ifdef X86_FEATURE_SYNC_RDTSC unsigned eax; /* + * Use RDTSCP if possible; it is guaranteed to be synchronous + * and doesn't cause a VMEXIT on Hypervisors + */ + alternative_io(ASM_NOP3, ".byte 0x0f,0x01,0xf9", X86_FEATURE_RDTSCP, + "=A" (ret), "0" (0ULL) : "ecx", "memory"); + if (ret) + return ret; + + /* * Don't do an additional sync on CPUs where we know * RDTSC is already synchronous: */ alternative_io("cpuid", ASM_NOP2, X86_FEATURE_SYNC_RDTSC, "=a" (eax), "0" (1) : "ebx","ecx","edx","memory"); -#else - sync_core(); -#endif rdtscll(ret); return ret; } extern void tsc_init(void); -extern void mark_tsc_unstable(void); +extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern void init_tsc_clocksource(void); diff --git a/include/asm-i386/uaccess.h b/include/asm-i386/uaccess.h index 70829ae3ad52..e2aa5e0d0cc7 100644 --- a/include/asm-i386/uaccess.h +++ b/include/asm-i386/uaccess.h @@ -397,7 +397,19 @@ unsigned long __must_check __copy_from_user_ll_nocache(void *to, unsigned long __must_check __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n); -/* +/** + * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. + * @to: Destination address, in user space. + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * + * Context: User context only. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. + * The caller should also make sure he pins the user space address + * so that the we don't result in page fault and sleep. + * * Here we special-case 1, 2 and 4-byte copy_*_user invocations. On a fault * we return the initial request size (1, 2 or 4), as copy_*_user should do. * If a store crosses a page boundary and gets a fault, the x86 will not write diff --git a/include/asm-i386/vmi_time.h b/include/asm-i386/vmi_time.h index c3a1fcf66c96..213930b995cb 100644 --- a/include/asm-i386/vmi_time.h +++ b/include/asm-i386/vmi_time.h @@ -53,22 +53,8 @@ extern unsigned long long vmi_get_sched_cycles(void); extern unsigned long vmi_cpu_khz(void); #ifdef CONFIG_X86_LOCAL_APIC -extern void __init vmi_timer_setup_boot_alarm(void); -extern void __devinit vmi_timer_setup_secondary_alarm(void); -extern void apic_vmi_timer_interrupt(void); -#endif - -#ifdef CONFIG_NO_IDLE_HZ -extern int vmi_stop_hz_timer(void); -extern void vmi_account_time_restart_hz_timer(void); -#else -static inline int vmi_stop_hz_timer(void) -{ - return 0; -} -static inline void vmi_account_time_restart_hz_timer(void) -{ -} +extern void __devinit vmi_time_bsp_init(void); +extern void __devinit vmi_time_ap_init(void); #endif /* |