diff options
Diffstat (limited to 'include')
46 files changed, 830 insertions, 261 deletions
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 9d774d07d95b..00c23433b39f 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -183,6 +183,19 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres #endif /* + * A facility to provide batching of the reload of page tables with the + * actual context switch code for paravirtualized guests. By convention, + * only one of the lazy modes (CPU, MMU) should be active at any given + * time, entry should never be nested, and entry and exits should always + * be paired. This is for sanity of maintaining and reasoning about the + * kernel code. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE +#define arch_enter_lazy_cpu_mode() do {} while (0) +#define arch_leave_lazy_cpu_mode() do {} while (0) +#endif + +/* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h index 41a44319905f..3a61206fd108 100644 --- a/include/asm-i386/apic.h +++ b/include/asm-i386/apic.h @@ -43,6 +43,8 @@ extern void generic_apic_probe(void); #define apic_write native_apic_write #define apic_write_atomic native_apic_write_atomic #define apic_read native_apic_read +#define setup_boot_clock setup_boot_APIC_clock +#define setup_secondary_clock setup_secondary_APIC_clock #endif static __inline fastcall void native_apic_write(unsigned long reg, diff --git a/include/asm-i386/bugs.h b/include/asm-i386/bugs.h index 38f1aebbbdb5..c90c7c499302 100644 --- a/include/asm-i386/bugs.h +++ b/include/asm-i386/bugs.h @@ -160,7 +160,7 @@ static void __init check_config(void) * If we configured ourselves for a TSC, we'd better have one! */ #ifdef CONFIG_X86_TSC - if (!cpu_has_tsc) + if (!cpu_has_tsc && !tsc_disable) panic("Kernel compiled for Pentium+, requires TSC feature!"); #endif diff --git a/include/asm-i386/desc.h b/include/asm-i386/desc.h index f398cc456448..050831f34f71 100644 --- a/include/asm-i386/desc.h +++ b/include/asm-i386/desc.h @@ -22,7 +22,7 @@ struct Xgt_desc_struct { 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; static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) { diff --git a/include/asm-i386/elf.h b/include/asm-i386/elf.h index 369035dfe4b6..8d33c9bb7c1c 100644 --- a/include/asm-i386/elf.h +++ b/include/asm-i386/elf.h @@ -90,8 +90,8 @@ typedef struct user_fxsr_struct elf_fpxregset_t; pr_reg[6] = regs->eax; \ pr_reg[7] = regs->xds; \ pr_reg[8] = regs->xes; \ - savesegment(fs,pr_reg[9]); \ - pr_reg[10] = regs->xgs; \ + pr_reg[9] = regs->xfs; \ + savesegment(gs,pr_reg[10]); \ pr_reg[11] = regs->orig_eax; \ pr_reg[12] = regs->eip; \ pr_reg[13] = regs->xcs; \ diff --git a/include/asm-i386/idle.h b/include/asm-i386/idle.h new file mode 100644 index 000000000000..87ab93911199 --- /dev/null +++ b/include/asm-i386/idle.h @@ -0,0 +1,14 @@ +#ifndef _ASM_I386_IDLE_H +#define _ASM_I386_IDLE_H 1 + +#define IDLE_START 1 +#define IDLE_END 2 + +struct notifier_block; +void idle_notifier_register(struct notifier_block *n); +void idle_notifier_unregister(struct notifier_block *n); + +void exit_idle(void); +void enter_idle(void); + +#endif diff --git a/include/asm-i386/mce.h b/include/asm-i386/mce.h index 7cc1a973bf00..b0a02ee34ffd 100644 --- a/include/asm-i386/mce.h +++ b/include/asm-i386/mce.h @@ -3,3 +3,5 @@ extern void mcheck_init(struct cpuinfo_x86 *c); #else #define mcheck_init(c) do {} while(0) #endif + +extern int mce_disabled; diff --git a/include/asm-i386/mmu_context.h b/include/asm-i386/mmu_context.h index 68ff102d6f5e..e6aa30f8de5b 100644 --- a/include/asm-i386/mmu_context.h +++ b/include/asm-i386/mmu_context.h @@ -63,7 +63,7 @@ static inline void switch_mm(struct mm_struct *prev, } #define deactivate_mm(tsk, mm) \ - asm("movl %0,%%fs": :"r" (0)); + asm("movl %0,%%gs": :"r" (0)); #define activate_mm(prev, next) \ switch_mm((prev),(next),NULL) diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h index 9f06265065f4..6317e0a4d735 100644 --- a/include/asm-i386/paravirt.h +++ b/include/asm-i386/paravirt.h @@ -59,90 +59,102 @@ struct paravirt_ops convention. This makes it easier to implement inline assembler replacements. */ - void (fastcall *cpuid)(unsigned int *eax, unsigned int *ebx, + void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); - unsigned long (fastcall *get_debugreg)(int regno); - void (fastcall *set_debugreg)(int regno, unsigned long value); + unsigned long (*get_debugreg)(int regno); + void (*set_debugreg)(int regno, unsigned long value); - void (fastcall *clts)(void); + void (*clts)(void); - unsigned long (fastcall *read_cr0)(void); - void (fastcall *write_cr0)(unsigned long); + unsigned long (*read_cr0)(void); + void (*write_cr0)(unsigned long); - unsigned long (fastcall *read_cr2)(void); - void (fastcall *write_cr2)(unsigned long); + unsigned long (*read_cr2)(void); + void (*write_cr2)(unsigned long); - unsigned long (fastcall *read_cr3)(void); - void (fastcall *write_cr3)(unsigned long); + unsigned long (*read_cr3)(void); + void (*write_cr3)(unsigned long); - unsigned long (fastcall *read_cr4_safe)(void); - unsigned long (fastcall *read_cr4)(void); - void (fastcall *write_cr4)(unsigned long); + unsigned long (*read_cr4_safe)(void); + unsigned long (*read_cr4)(void); + void (*write_cr4)(unsigned long); - unsigned long (fastcall *save_fl)(void); - void (fastcall *restore_fl)(unsigned long); - void (fastcall *irq_disable)(void); - void (fastcall *irq_enable)(void); - void (fastcall *safe_halt)(void); - void (fastcall *halt)(void); - void (fastcall *wbinvd)(void); + 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. */ - u64 (fastcall *read_msr)(unsigned int msr, int *err); - int (fastcall *write_msr)(unsigned int msr, u64 val); - - u64 (fastcall *read_tsc)(void); - u64 (fastcall *read_pmc)(void); - - void (fastcall *load_tr_desc)(void); - void (fastcall *load_gdt)(const struct Xgt_desc_struct *); - void (fastcall *load_idt)(const struct Xgt_desc_struct *); - void (fastcall *store_gdt)(struct Xgt_desc_struct *); - void (fastcall *store_idt)(struct Xgt_desc_struct *); - void (fastcall *set_ldt)(const void *desc, unsigned entries); - unsigned long (fastcall *store_tr)(void); - void (fastcall *load_tls)(struct thread_struct *t, unsigned int cpu); - void (fastcall *write_ldt_entry)(void *dt, int entrynum, + u64 (*read_msr)(unsigned int msr, int *err); + int (*write_msr)(unsigned int msr, u64 val); + + u64 (*read_tsc)(void); + u64 (*read_pmc)(void); + + void (*load_tr_desc)(void); + void (*load_gdt)(const struct Xgt_desc_struct *); + void (*load_idt)(const struct Xgt_desc_struct *); + void (*store_gdt)(struct Xgt_desc_struct *); + void (*store_idt)(struct Xgt_desc_struct *); + 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 (fastcall *write_gdt_entry)(void *dt, int entrynum, + void (*write_gdt_entry)(void *dt, int entrynum, u32 low, u32 high); - void (fastcall *write_idt_entry)(void *dt, int entrynum, + void (*write_idt_entry)(void *dt, int entrynum, u32 low, u32 high); - void (fastcall *load_esp0)(struct tss_struct *tss, + void (*load_esp0)(struct tss_struct *tss, struct thread_struct *thread); - void (fastcall *set_iopl_mask)(unsigned mask); + void (*set_iopl_mask)(unsigned mask); - void (fastcall *io_delay)(void); + void (*io_delay)(void); void (*const_udelay)(unsigned long loops); #ifdef CONFIG_X86_LOCAL_APIC - void (fastcall *apic_write)(unsigned long reg, unsigned long v); - void (fastcall *apic_write_atomic)(unsigned long reg, unsigned long v); - unsigned long (fastcall *apic_read)(unsigned long reg); + 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); #endif - void (fastcall *flush_tlb_user)(void); - void (fastcall *flush_tlb_kernel)(void); - void (fastcall *flush_tlb_single)(u32 addr); - - void (fastcall *set_pte)(pte_t *ptep, pte_t pteval); - void (fastcall *set_pte_at)(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval); - void (fastcall *set_pmd)(pmd_t *pmdp, pmd_t pmdval); - void (fastcall *pte_update)(struct mm_struct *mm, u32 addr, pte_t *ptep); - void (fastcall *pte_update_defer)(struct mm_struct *mm, u32 addr, pte_t *ptep); + void (*flush_tlb_user)(void); + void (*flush_tlb_kernel)(void); + void (*flush_tlb_single)(u32 addr); + + 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); + + 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_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); #ifdef CONFIG_X86_PAE - void (fastcall *set_pte_atomic)(pte_t *ptep, pte_t pteval); - void (fastcall *set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); - void (fastcall *set_pud)(pud_t *pudp, pud_t pudval); - void (fastcall *pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); - void (fastcall *pmd_clear)(pmd_t *pmdp); + 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_pud)(pud_t *pudp, pud_t pudval); + void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + void (*pmd_clear)(pmd_t *pmdp); #endif + void (*set_lazy_mode)(int mode); + /* These two are jmp to, not actually called. */ - void (fastcall *irq_enable_sysexit)(void); - void (fastcall *iret)(void); + 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. */ @@ -313,13 +325,38 @@ static inline unsigned long apic_read(unsigned long reg) { return paravirt_ops.apic_read(reg); } + +static inline void setup_boot_clock(void) +{ + paravirt_ops.setup_boot_clock(); +} + +static inline void setup_secondary_clock(void) +{ + paravirt_ops.setup_secondary_clock(); +} #endif +#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); +} +#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) +#define paravirt_alloc_pt(pfn) paravirt_ops.alloc_pt(pfn) +#define paravirt_release_pt(pfn) paravirt_ops.release_pt(pfn) + +#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 set_pte(pte_t *ptep, pte_t pteval) { paravirt_ops.set_pte(ptep, pteval); @@ -372,6 +409,19 @@ static inline void pmd_clear(pmd_t *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 __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 __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) + /* These all sit in the .parainstructions section to tell us what to patch. */ struct paravirt_patch { u8 *instr; /* original instructions */ diff --git a/include/asm-i386/pda.h b/include/asm-i386/pda.h index 2ba2736aa109..b12d59a318b7 100644 --- a/include/asm-i386/pda.h +++ b/include/asm-i386/pda.h @@ -39,19 +39,19 @@ extern struct i386_pda _proxy_pda; if (0) { T__ tmp__; tmp__ = (val); } \ switch (sizeof(_proxy_pda.field)) { \ case 1: \ - asm(op "b %1,%%gs:%c2" \ + asm(op "b %1,%%fs:%c2" \ : "+m" (_proxy_pda.field) \ :"ri" ((T__)val), \ "i"(pda_offset(field))); \ break; \ case 2: \ - asm(op "w %1,%%gs:%c2" \ + asm(op "w %1,%%fs:%c2" \ : "+m" (_proxy_pda.field) \ :"ri" ((T__)val), \ "i"(pda_offset(field))); \ break; \ case 4: \ - asm(op "l %1,%%gs:%c2" \ + asm(op "l %1,%%fs:%c2" \ : "+m" (_proxy_pda.field) \ :"ri" ((T__)val), \ "i"(pda_offset(field))); \ @@ -65,19 +65,19 @@ extern struct i386_pda _proxy_pda; typeof(_proxy_pda.field) ret__; \ switch (sizeof(_proxy_pda.field)) { \ case 1: \ - asm(op "b %%gs:%c1,%0" \ + asm(op "b %%fs:%c1,%0" \ : "=r" (ret__) \ : "i" (pda_offset(field)), \ "m" (_proxy_pda.field)); \ break; \ case 2: \ - asm(op "w %%gs:%c1,%0" \ + asm(op "w %%fs:%c1,%0" \ : "=r" (ret__) \ : "i" (pda_offset(field)), \ "m" (_proxy_pda.field)); \ break; \ case 4: \ - asm(op "l %%gs:%c1,%0" \ + asm(op "l %%fs:%c1,%0" \ : "=r" (ret__) \ : "i" (pda_offset(field)), \ "m" (_proxy_pda.field)); \ diff --git a/include/asm-i386/pgalloc.h b/include/asm-i386/pgalloc.h index 4b1e61359f89..c8dc2d0141a7 100644 --- a/include/asm-i386/pgalloc.h +++ b/include/asm-i386/pgalloc.h @@ -5,13 +5,31 @@ #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ -#define pmd_populate_kernel(mm, pmd, pte) \ - set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))) +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#else +#define paravirt_alloc_pt(pfn) do { } while (0) +#define paravirt_alloc_pd(pfn) do { } while (0) +#define paravirt_alloc_pd(pfn) do { } while (0) +#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0) +#define paravirt_release_pt(pfn) do { } while (0) +#define paravirt_release_pd(pfn) do { } while (0) +#endif + +#define pmd_populate_kernel(mm, pmd, pte) \ +do { \ + paravirt_alloc_pt(__pa(pte) >> PAGE_SHIFT); \ + set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \ +} while (0) #define pmd_populate(mm, pmd, pte) \ +do { \ + paravirt_alloc_pt(page_to_pfn(pte)); \ set_pmd(pmd, __pmd(_PAGE_TABLE + \ ((unsigned long long)page_to_pfn(pte) << \ - (unsigned long long) PAGE_SHIFT))) + (unsigned long long) PAGE_SHIFT))); \ +} while (0) + /* * Allocate and free page tables. */ @@ -32,7 +50,11 @@ static inline void pte_free(struct page *pte) } -#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) +#define __pte_free_tlb(tlb,pte) \ +do { \ + paravirt_release_pt(page_to_pfn(pte)); \ + tlb_remove_page((tlb),(pte)); \ +} while (0) #ifdef CONFIG_X86_PAE /* diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 359f10b54f59..edfbe46a5e13 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -257,6 +257,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) : :"a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + /* "mwait %eax,%ecx;" */ + asm volatile( + "sti; .byte 0x0f,0x01,0xc9;" + : :"a" (eax), "c" (ecx)); +} + extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); /* from system description table in BIOS. Mostly for MCA use, but @@ -424,7 +432,7 @@ struct thread_struct { .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ - .gs = __KERNEL_PDA, \ + .fs = __KERNEL_PDA, \ } /* @@ -442,8 +450,8 @@ struct thread_struct { } #define start_thread(regs, new_eip, new_esp) do { \ - __asm__("movl %0,%%fs": :"r" (0)); \ - regs->xgs = 0; \ + __asm__("movl %0,%%gs": :"r" (0)); \ + regs->xfs = 0; \ set_fs(USER_DS); \ regs->xds = __USER_DS; \ regs->xes = __USER_DS; \ diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h index bdbc894339b4..6002597b9e12 100644 --- a/include/asm-i386/ptrace.h +++ b/include/asm-i386/ptrace.h @@ -16,8 +16,8 @@ struct pt_regs { long eax; int xds; int xes; - /* int xfs; */ - int xgs; + int xfs; + /* int xgs; */ long orig_eax; long eip; int xcs; @@ -49,6 +49,10 @@ static inline int user_mode_vm(struct pt_regs *regs) { return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL; } +static inline int v8086_mode(struct pt_regs *regs) +{ + return (regs->eflags & VM_MASK); +} #define instruction_pointer(regs) ((regs)->eip) #define regs_return_value(regs) ((regs)->eax) diff --git a/include/asm-i386/segment.h b/include/asm-i386/segment.h index 3c796af33776..065f10bfa487 100644 --- a/include/asm-i386/segment.h +++ b/include/asm-i386/segment.h @@ -83,14 +83,8 @@ * The GDT has 32 entries */ #define GDT_ENTRIES 32 - #define GDT_SIZE (GDT_ENTRIES * 8) -/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */ -#define SEGMENT_IS_FLAT_CODE(x) (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8) -/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */ -#define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8) - /* Simple and small GDT entries for booting only */ #define GDT_ENTRY_BOOT_CS 2 @@ -134,4 +128,17 @@ #ifndef CONFIG_PARAVIRT #define get_kernel_rpl() 0 #endif +/* + * Matching rules for certain types of segments. + */ + +/* Matches only __KERNEL_CS, ignoring PnP / USER / APM segments */ +#define SEGMENT_IS_KERNEL_CODE(x) (((x) & 0xfc) == GDT_ENTRY_KERNEL_CS * 8) + +/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */ +#define SEGMENT_IS_FLAT_CODE(x) (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8) + +/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */ +#define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8) + #endif diff --git a/include/asm-i386/setup.h b/include/asm-i386/setup.h index 76316275d6f9..0e8077cbfdac 100644 --- a/include/asm-i386/setup.h +++ b/include/asm-i386/setup.h @@ -77,6 +77,8 @@ int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map); void __init add_memory_region(unsigned long long start, unsigned long long size, int type); +extern unsigned long init_pg_tables_end; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h index 64fe624c02ca..6bf0033a301c 100644 --- a/include/asm-i386/smp.h +++ b/include/asm-i386/smp.h @@ -52,6 +52,11 @@ extern void cpu_exit_clear(void); extern void cpu_uninit(void); #endif +#ifndef CONFIG_PARAVIRT +#define startup_ipi_hook(phys_apicid, start_eip, start_esp) \ +do { } while (0) +#endif + /* * This function is needed by all SMP systems. It must _always_ be valid * from the initial startup. We map APIC_BASE very early in page_setup(), diff --git a/include/asm-i386/time.h b/include/asm-i386/time.h index ea8065af825a..571b4294dc2e 100644 --- a/include/asm-i386/time.h +++ b/include/asm-i386/time.h @@ -30,6 +30,7 @@ static inline int native_set_wallclock(unsigned long nowtime) #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> +extern unsigned long long native_sched_clock(void); #else /* !CONFIG_PARAVIRT */ #define get_wallclock() native_get_wallclock() diff --git a/include/asm-i386/timer.h b/include/asm-i386/timer.h index d0ebd05f8516..4752c3a6a708 100644 --- a/include/asm-i386/timer.h +++ b/include/asm-i386/timer.h @@ -8,6 +8,9 @@ void setup_pit_timer(void); /* Modifiers for buggy PIT handling */ extern int pit_latch_buggy; extern int timer_ack; +extern int no_timer_check; +extern unsigned long long (*custom_sched_clock)(void); +extern int no_sync_cmos_clock; extern int recalibrate_cpu_khz(void); #endif diff --git a/include/asm-i386/vmi.h b/include/asm-i386/vmi.h new file mode 100644 index 000000000000..43c89333037e --- /dev/null +++ b/include/asm-i386/vmi.h @@ -0,0 +1,262 @@ +/* + * VMI interface definition + * + * Copyright (C) 2005, VMware, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Maintained by: Zachary Amsden zach@vmware.com + * + */ +#include <linux/types.h> + +/* + *--------------------------------------------------------------------- + * + * VMI Option ROM API + * + *--------------------------------------------------------------------- + */ +#define VMI_SIGNATURE 0x696d5663 /* "cVmi" */ + +#define PCI_VENDOR_ID_VMWARE 0x15AD +#define PCI_DEVICE_ID_VMWARE_VMI 0x0801 + +/* + * We use two version numbers for compatibility, with the major + * number signifying interface breakages, and the minor number + * interface extensions. + */ +#define VMI_API_REV_MAJOR 3 +#define VMI_API_REV_MINOR 0 + +#define VMI_CALL_CPUID 0 +#define VMI_CALL_WRMSR 1 +#define VMI_CALL_RDMSR 2 +#define VMI_CALL_SetGDT 3 +#define VMI_CALL_SetLDT 4 +#define VMI_CALL_SetIDT 5 +#define VMI_CALL_SetTR 6 +#define VMI_CALL_GetGDT 7 +#define VMI_CALL_GetLDT 8 +#define VMI_CALL_GetIDT 9 +#define VMI_CALL_GetTR 10 +#define VMI_CALL_WriteGDTEntry 11 +#define VMI_CALL_WriteLDTEntry 12 +#define VMI_CALL_WriteIDTEntry 13 +#define VMI_CALL_UpdateKernelStack 14 +#define VMI_CALL_SetCR0 15 +#define VMI_CALL_SetCR2 16 +#define VMI_CALL_SetCR3 17 +#define VMI_CALL_SetCR4 18 +#define VMI_CALL_GetCR0 19 +#define VMI_CALL_GetCR2 20 +#define VMI_CALL_GetCR3 21 +#define VMI_CALL_GetCR4 22 +#define VMI_CALL_WBINVD 23 +#define VMI_CALL_SetDR 24 +#define VMI_CALL_GetDR 25 +#define VMI_CALL_RDPMC 26 +#define VMI_CALL_RDTSC 27 +#define VMI_CALL_CLTS 28 +#define VMI_CALL_EnableInterrupts 29 +#define VMI_CALL_DisableInterrupts 30 +#define VMI_CALL_GetInterruptMask 31 +#define VMI_CALL_SetInterruptMask 32 +#define VMI_CALL_IRET 33 +#define VMI_CALL_SYSEXIT 34 +#define VMI_CALL_Halt 35 +#define VMI_CALL_Reboot 36 +#define VMI_CALL_Shutdown 37 +#define VMI_CALL_SetPxE 38 +#define VMI_CALL_SetPxELong 39 +#define VMI_CALL_UpdatePxE 40 +#define VMI_CALL_UpdatePxELong 41 +#define VMI_CALL_MachineToPhysical 42 +#define VMI_CALL_PhysicalToMachine 43 +#define VMI_CALL_AllocatePage 44 +#define VMI_CALL_ReleasePage 45 +#define VMI_CALL_InvalPage 46 +#define VMI_CALL_FlushTLB 47 +#define VMI_CALL_SetLinearMapping 48 + +#define VMI_CALL_SetIOPLMask 61 +#define VMI_CALL_SetInitialAPState 62 +#define VMI_CALL_APICWrite 63 +#define VMI_CALL_APICRead 64 +#define VMI_CALL_SetLazyMode 73 + +/* + *--------------------------------------------------------------------- + * + * MMU operation flags + * + *--------------------------------------------------------------------- + */ + +/* Flags used by VMI_{Allocate|Release}Page call */ +#define VMI_PAGE_PAE 0x10 /* Allocate PAE shadow */ +#define VMI_PAGE_CLONE 0x20 /* Clone from another shadow */ +#define VMI_PAGE_ZEROED 0x40 /* Page is pre-zeroed */ + + +/* Flags shared by Allocate|Release Page and PTE updates */ +#define VMI_PAGE_PT 0x01 +#define VMI_PAGE_PD 0x02 +#define VMI_PAGE_PDP 0x04 +#define VMI_PAGE_PML4 0x08 + +#define VMI_PAGE_NORMAL 0x00 /* for debugging */ + +/* Flags used by PTE updates */ +#define VMI_PAGE_CURRENT_AS 0x10 /* implies VMI_PAGE_VA_MASK is valid */ +#define VMI_PAGE_DEFER 0x20 /* may queue update until TLB inval */ +#define VMI_PAGE_VA_MASK 0xfffff000 + +#ifdef CONFIG_X86_PAE +#define VMI_PAGE_L1 (VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED) +#define VMI_PAGE_L2 (VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED) +#else +#define VMI_PAGE_L1 (VMI_PAGE_PT | VMI_PAGE_ZEROED) +#define VMI_PAGE_L2 (VMI_PAGE_PD | VMI_PAGE_ZEROED) +#endif + +/* Flags used by VMI_FlushTLB call */ +#define VMI_FLUSH_TLB 0x01 +#define VMI_FLUSH_GLOBAL 0x02 + +/* + *--------------------------------------------------------------------- + * + * VMI relocation definitions for ROM call get_reloc + * + *--------------------------------------------------------------------- + */ + +/* VMI Relocation types */ +#define VMI_RELOCATION_NONE 0 +#define VMI_RELOCATION_CALL_REL 1 +#define VMI_RELOCATION_JUMP_REL 2 +#define VMI_RELOCATION_NOP 3 + +#ifndef __ASSEMBLY__ +struct vmi_relocation_info { + unsigned char *eip; + unsigned char type; + unsigned char reserved[3]; +}; +#endif + + +/* + *--------------------------------------------------------------------- + * + * Generic ROM structures and definitions + * + *--------------------------------------------------------------------- + */ + +#ifndef __ASSEMBLY__ + +struct vrom_header { + u16 rom_signature; // option ROM signature + u8 rom_length; // ROM length in 512 byte chunks + u8 rom_entry[4]; // 16-bit code entry point + u8 rom_pad0; // 4-byte align pad + u32 vrom_signature; // VROM identification signature + u8 api_version_min;// Minor version of API + u8 api_version_maj;// Major version of API + u8 jump_slots; // Number of jump slots + u8 reserved1; // Reserved for expansion + u32 virtual_top; // Hypervisor virtual address start + u16 reserved2; // Reserved for expansion + u16 license_offs; // Offset to License string + u16 pci_header_offs;// Offset to PCI OPROM header + u16 pnp_header_offs;// Offset to PnP OPROM header + u32 rom_pad3; // PnP reserverd / VMI reserved + u8 reserved[96]; // Reserved for headers + char vmi_init[8]; // VMI_Init jump point + char get_reloc[8]; // VMI_GetRelocationInfo jump point +} __attribute__((packed)); + +struct pnp_header { + char sig[4]; + char rev; + char size; + short next; + short res; + long devID; + unsigned short manufacturer_offset; + unsigned short product_offset; +} __attribute__((packed)); + +struct pci_header { + char sig[4]; + short vendorID; + short deviceID; + short vpdData; + short size; + char rev; + char class; + char subclass; + char interface; + short chunks; + char rom_version_min; + char rom_version_maj; + char codetype; + char lastRom; + short reserved; +} __attribute__((packed)); + +/* Function prototypes for bootstrapping */ +extern void vmi_init(void); +extern void vmi_bringup(void); +extern void vmi_apply_boot_page_allocations(void); + +/* State needed to start an application processor in an SMP system. */ +struct vmi_ap_state { + u32 cr0; + u32 cr2; + u32 cr3; + u32 cr4; + + u64 efer; + + u32 eip; + u32 eflags; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u32 esp; + u32 ebp; + u32 esi; + u32 edi; + u16 cs; + u16 ss; + u16 ds; + u16 es; + u16 fs; + u16 gs; + u16 ldtr; + + u16 gdtr_limit; + u32 gdtr_base; + u32 idtr_base; + u16 idtr_limit; +}; + +#endif diff --git a/include/asm-i386/vmi_time.h b/include/asm-i386/vmi_time.h new file mode 100644 index 000000000000..c12931211007 --- /dev/null +++ b/include/asm-i386/vmi_time.h @@ -0,0 +1,103 @@ +/* + * VMI Time wrappers + * + * Copyright (C) 2006, VMware, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Send feedback to dhecht@vmware.com + * + */ + +#ifndef __VMI_TIME_H +#define __VMI_TIME_H + +/* + * Raw VMI call indices for timer functions + */ +#define VMI_CALL_GetCycleFrequency 66 +#define VMI_CALL_GetCycleCounter 67 +#define VMI_CALL_SetAlarm 68 +#define VMI_CALL_CancelAlarm 69 +#define VMI_CALL_GetWallclockTime 70 +#define VMI_CALL_WallclockUpdated 71 + +/* Cached VMI timer operations */ +extern struct vmi_timer_ops { + u64 (*get_cycle_frequency)(void); + u64 (*get_cycle_counter)(int); + u64 (*get_wallclock)(void); + int (*wallclock_updated)(void); + void (*set_alarm)(u32 flags, u64 expiry, u64 period); + void (*cancel_alarm)(u32 flags); +} vmi_timer_ops; + +/* Prototypes */ +extern void __init vmi_time_init(void); +extern unsigned long vmi_get_wallclock(void); +extern int vmi_set_wallclock(unsigned long now); +extern unsigned long long vmi_sched_clock(void); + +#ifdef CONFIG_X86_LOCAL_APIC +extern void __init vmi_timer_setup_boot_alarm(void); +extern void __init 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); +#endif + +/* + * When run under a hypervisor, a vcpu is always in one of three states: + * running, halted, or ready. The vcpu is in the 'running' state if it + * is executing. When the vcpu executes the halt interface, the vcpu + * enters the 'halted' state and remains halted until there is some work + * pending for the vcpu (e.g. an alarm expires, host I/O completes on + * behalf of virtual I/O). At this point, the vcpu enters the 'ready' + * state (waiting for the hypervisor to reschedule it). Finally, at any + * time when the vcpu is not in the 'running' state nor the 'halted' + * state, it is in the 'ready' state. + * + * Real time is advances while the vcpu is 'running', 'ready', or + * 'halted'. Stolen time is the time in which the vcpu is in the + * 'ready' state. Available time is the remaining time -- the vcpu is + * either 'running' or 'halted'. + * + * All three views of time are accessible through the VMI cycle + * counters. + */ + +/* The cycle counters. */ +#define VMI_CYCLES_REAL 0 +#define VMI_CYCLES_AVAILABLE 1 +#define VMI_CYCLES_STOLEN 2 + +/* The alarm interface 'flags' bits */ +#define VMI_ALARM_COUNTERS 2 + +#define VMI_ALARM_COUNTER_MASK 0x000000ff + +#define VMI_ALARM_WIRED_IRQ0 0x00000000 +#define VMI_ALARM_WIRED_LVTT 0x00010000 + +#define VMI_ALARM_IS_ONESHOT 0x00000000 +#define VMI_ALARM_IS_PERIODIC 0x00000100 + +#define CONFIG_VMI_ALARM_HZ 100 + +#endif diff --git a/include/asm-ia64/dma-mapping.h b/include/asm-ia64/dma-mapping.h index ebd5887f4b1a..6299b51575bb 100644 --- a/include/asm-ia64/dma-mapping.h +++ b/include/asm-ia64/dma-mapping.h @@ -8,9 +8,20 @@ #include <asm/machvec.h> #define dma_alloc_coherent platform_dma_alloc_coherent -#define dma_alloc_noncoherent platform_dma_alloc_coherent /* coherent mem. is cheap */ +/* coherent mem. is cheap */ +static inline void * +dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flag) +{ + return dma_alloc_coherent(dev, size, dma_handle, flag); +} #define dma_free_coherent platform_dma_free_coherent -#define dma_free_noncoherent platform_dma_free_coherent +static inline void +dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle) +{ + dma_free_coherent(dev, size, cpu_addr, dma_handle); +} #define dma_map_single platform_dma_map_single #define dma_map_sg platform_dma_map_sg #define dma_unmap_single platform_dma_unmap_single diff --git a/include/asm-x86_64/bitops.h b/include/asm-x86_64/bitops.h index 8da9609070f4..d4dbbe5f7bd9 100644 --- a/include/asm-x86_64/bitops.h +++ b/include/asm-x86_64/bitops.h @@ -7,7 +7,7 @@ #include <asm/alternative.h> -#if __GNUC__ < 4 || __GNUC_MINOR__ < 1 +#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1) /* Technically wrong, but this avoids compilation errors on some gcc versions. */ #define ADDR "=m" (*(volatile long *) addr) diff --git a/include/asm-x86_64/dma-mapping.h b/include/asm-x86_64/dma-mapping.h index 49dbab09ef2b..d2af227f06d0 100644 --- a/include/asm-x86_64/dma-mapping.h +++ b/include/asm-x86_64/dma-mapping.h @@ -66,6 +66,9 @@ static inline int dma_mapping_error(dma_addr_t dma_addr) #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) +#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) +#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) + extern void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); extern void dma_free_coherent(struct device *dev, size_t size, void *vaddr, diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h index fa2086774105..6216fa3f2802 100644 --- a/include/asm-x86_64/e820.h +++ b/include/asm-x86_64/e820.h @@ -46,6 +46,7 @@ extern void e820_mark_nosave_regions(void); extern void e820_print_map(char *who); extern int e820_any_mapped(unsigned long start, unsigned long end, unsigned type); extern int e820_all_mapped(unsigned long start, unsigned long end, unsigned type); +extern unsigned long e820_hole_size(unsigned long start, unsigned long end); extern void e820_setup_gap(void); extern void e820_register_active_regions(int nid, @@ -56,6 +57,7 @@ extern void finish_e820_parsing(void); extern struct e820map e820; extern unsigned ebda_addr, ebda_size; +extern unsigned long nodemap_addr, nodemap_size; #endif/*!__ASSEMBLY__*/ #endif/*__E820_HEADER*/ diff --git a/include/asm-x86_64/hw_irq.h b/include/asm-x86_64/hw_irq.h index 179cce755aa7..552df5f10a6d 100644 --- a/include/asm-x86_64/hw_irq.h +++ b/include/asm-x86_64/hw_irq.h @@ -91,7 +91,7 @@ extern void enable_8259A_irq(unsigned int irq); extern int i8259A_irq_pending(unsigned int irq); extern void make_8259A_irq(unsigned int irq); extern void init_8259A(int aeoi); -extern void FASTCALL(send_IPI_self(int vector)); +extern void send_IPI_self(int vector); extern void init_VISWS_APIC_irqs(void); extern void setup_IO_APIC(void); extern void disable_IO_APIC(void); diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h index f5d84bb7c948..de2cd9a2303a 100644 --- a/include/asm-x86_64/io.h +++ b/include/asm-x86_64/io.h @@ -100,7 +100,7 @@ __OUTS(l) #define IO_SPACE_LIMIT 0xffff -#if defined(__KERNEL__) && __x86_64__ +#if defined(__KERNEL__) && defined(__x86_64__) #include <linux/vmalloc.h> diff --git a/include/asm-x86_64/io_apic.h b/include/asm-x86_64/io_apic.h index 561ecbfd4cb5..f4fb238c89f1 100644 --- a/include/asm-x86_64/io_apic.h +++ b/include/asm-x86_64/io_apic.h @@ -85,18 +85,8 @@ struct IO_APIC_route_entry { mask : 1, /* 0: enabled, 1: disabled */ __reserved_2 : 15; - union { struct { __u32 - __reserved_1 : 24, - physical_dest : 4, - __reserved_2 : 4; - } physical; - - struct { __u32 - __reserved_1 : 24, - logical_dest : 8; - } logical; - } dest; - + __u32 __reserved_3 : 24, + dest : 8; } __attribute__ ((packed)); /* diff --git a/include/asm-x86_64/mce.h b/include/asm-x86_64/mce.h index 5a11146d6d9c..177e92b4019b 100644 --- a/include/asm-x86_64/mce.h +++ b/include/asm-x86_64/mce.h @@ -103,6 +103,8 @@ void mce_log_therm_throt_event(unsigned int cpu, __u64 status); extern atomic_t mce_entry; +extern void do_machine_check(struct pt_regs *, long); + #endif #endif diff --git a/include/asm-x86_64/mmzone.h b/include/asm-x86_64/mmzone.h index c38ebdf6f426..fb558fb1d211 100644 --- a/include/asm-x86_64/mmzone.h +++ b/include/asm-x86_64/mmzone.h @@ -11,24 +11,25 @@ #include <asm/smp.h> -/* Should really switch to dynamic allocation at some point */ -#define NODEMAPSIZE 0x4fff - /* Simple perfect hash to map physical addresses to node numbers */ struct memnode { int shift; - u8 map[NODEMAPSIZE]; -} ____cacheline_aligned; + unsigned int mapsize; + u8 *map; + u8 embedded_map[64-16]; +} ____cacheline_aligned; /* total size = 64 bytes */ extern struct memnode memnode; #define memnode_shift memnode.shift #define memnodemap memnode.map +#define memnodemapsize memnode.mapsize extern struct pglist_data *node_data[]; static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) { unsigned nid; - VIRTUAL_BUG_ON((addr >> memnode_shift) >= NODEMAPSIZE); + VIRTUAL_BUG_ON(!memnodemap); + VIRTUAL_BUG_ON((addr >> memnode_shift) >= memnodemapsize); nid = memnodemap[addr >> memnode_shift]; VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]); return nid; @@ -46,5 +47,10 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) extern int pfn_valid(unsigned long pfn); #endif +#ifdef CONFIG_NUMA_EMU +#define FAKE_NODE_MIN_SIZE (64*1024*1024) +#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1ul)) +#endif + #endif #endif diff --git a/include/asm-x86_64/mutex.h b/include/asm-x86_64/mutex.h index 16396b1de3e4..6c2949a3c677 100644 --- a/include/asm-x86_64/mutex.h +++ b/include/asm-x86_64/mutex.h @@ -21,7 +21,7 @@ do { \ unsigned long dummy; \ \ typecheck(atomic_t *, v); \ - typecheck_fn(fastcall void (*)(atomic_t *), fail_fn); \ + typecheck_fn(void (*)(atomic_t *), fail_fn); \ \ __asm__ __volatile__( \ LOCK_PREFIX " decl (%%rdi) \n" \ @@ -47,7 +47,7 @@ do { \ */ static inline int __mutex_fastpath_lock_retval(atomic_t *count, - int fastcall (*fail_fn)(atomic_t *)) + int (*fail_fn)(atomic_t *)) { if (unlikely(atomic_dec_return(count) < 0)) return fail_fn(count); @@ -67,7 +67,7 @@ do { \ unsigned long dummy; \ \ typecheck(atomic_t *, v); \ - typecheck_fn(fastcall void (*)(atomic_t *), fail_fn); \ + typecheck_fn(void (*)(atomic_t *), fail_fn); \ \ __asm__ __volatile__( \ LOCK_PREFIX " incl (%%rdi) \n" \ diff --git a/include/asm-x86_64/pgalloc.h b/include/asm-x86_64/pgalloc.h index 43d4c333a8b1..4e28b6060a5e 100644 --- a/include/asm-x86_64/pgalloc.h +++ b/include/asm-x86_64/pgalloc.h @@ -18,11 +18,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *p set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT))); } -static inline pmd_t *get_pmd(void) -{ - return (pmd_t *)get_zeroed_page(GFP_KERNEL); -} - static inline void pmd_free(pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h index 59901c690a0d..730bd6028416 100644 --- a/include/asm-x86_64/pgtable.h +++ b/include/asm-x86_64/pgtable.h @@ -359,15 +359,6 @@ static inline int pmd_large(pmd_t pte) { #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) #define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE) -/* physical address -> PTE */ -static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) -{ - pte_t pte; - pte_val(pte) = physpage | pgprot_val(pgprot); - pte_val(pte) &= __supported_pte_mask; - return pte; -} - /* Change flags of a PTE */ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { diff --git a/include/asm-x86_64/uaccess.h b/include/asm-x86_64/uaccess.h index 8079e29c14fd..1981f70fcad1 100644 --- a/include/asm-x86_64/uaccess.h +++ b/include/asm-x86_64/uaccess.h @@ -367,4 +367,18 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) return copy_user_generic((__force void *)dst, src, size); } +#define ARCH_HAS_NOCACHE_UACCESS 1 +extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); + +static inline int __copy_from_user_nocache(void *dst, const void __user *src, unsigned size) +{ + might_sleep(); + return __copy_user_nocache(dst, (__force void *)src, size, 1); +} + +static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size) +{ + return __copy_user_nocache(dst, (__force void *)src, size, 0); +} + #endif /* __X86_64_UACCESS_H */ diff --git a/include/asm-x86_64/vsyscall.h b/include/asm-x86_64/vsyscall.h index 05cb8dd200de..0c7847165eae 100644 --- a/include/asm-x86_64/vsyscall.h +++ b/include/asm-x86_64/vsyscall.h @@ -56,11 +56,6 @@ extern struct vxtime_data vxtime; extern int vgetcpu_mode; extern struct timezone sys_tz; extern int sysctl_vsyscall; -extern seqlock_t xtime_lock; - -extern int sysctl_vsyscall; - -#define ARCH_HAVE_XTIME_LOCK 1 #endif /* __KERNEL__ */ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c1e82c514443..2d956cd566ae 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -59,6 +59,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(long signr, struct pt_regs * regs, struct file * file); unsigned long min_coredump; /* minimal dump size */ + int hasvdso; }; extern int register_binfmt(struct linux_binfmt *); diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 045e38cdbe64..9f62d6182d32 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -74,19 +74,20 @@ struct svc_export { uid_t ex_anon_uid; gid_t ex_anon_gid; int ex_fsid; + unsigned char * ex_uuid; /* 16 byte fsid */ struct nfsd4_fs_locations ex_fslocs; }; /* an "export key" (expkey) maps a filehandlefragement to an - * svc_export for a given client. There can be two per export, one - * for type 0 (dev/ino), one for type 1 (fsid) + * svc_export for a given client. There can be several per export, + * for the different fsid types. */ struct svc_expkey { struct cache_head h; struct auth_domain * ek_client; int ek_fsidtype; - u32 ek_fsid[3]; + u32 ek_fsid[6]; struct vfsmount * ek_mnt; struct dentry * ek_dentry; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 4b7c4b568f6d..72feac581aa3 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -254,18 +254,6 @@ void nfsd_lockd_shutdown(void); */ extern struct timeval nfssvc_boot; -static inline int is_fsid(struct svc_fh *fh, struct knfsd_fh *reffh) -{ - if (fh->fh_export->ex_flags & NFSEXP_FSID) { - struct vfsmount *mnt = fh->fh_export->ex_mnt; - if (!old_valid_dev(mnt->mnt_sb->s_dev) || - (reffh->fh_version == 1 && reffh->fh_fsid_type == 1)) - return 1; - } - return 0; -} - - #ifdef CONFIG_NFSD_V4 /* before processing a COMPOUND operation, we have to check that there diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index d9c6c382165d..11e568ee0eeb 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -165,38 +165,91 @@ typedef struct svc_fh { } svc_fh; -static inline void mk_fsid_v0(u32 *fsidv, dev_t dev, ino_t ino) -{ - fsidv[0] = htonl((MAJOR(dev)<<16) | - MINOR(dev)); - fsidv[1] = ino_t_to_u32(ino); -} +enum nfsd_fsid { + FSID_DEV = 0, + FSID_NUM, + FSID_MAJOR_MINOR, + FSID_ENCODE_DEV, + FSID_UUID4_INUM, + FSID_UUID8, + FSID_UUID16, + FSID_UUID16_INUM, +}; -static inline void mk_fsid_v1(u32 *fsidv, u32 fsid) -{ - fsidv[0] = fsid; -} +enum fsid_source { + FSIDSOURCE_DEV, + FSIDSOURCE_FSID, + FSIDSOURCE_UUID, +}; +extern enum fsid_source fsid_source(struct svc_fh *fhp); -static inline void mk_fsid_v2(u32 *fsidv, dev_t dev, ino_t ino) -{ - fsidv[0] = htonl(MAJOR(dev)); - fsidv[1] = htonl(MINOR(dev)); - fsidv[2] = ino_t_to_u32(ino); -} -static inline void mk_fsid_v3(u32 *fsidv, dev_t dev, ino_t ino) +/* This might look a little large to "inline" but in all calls except + * one, 'vers' is constant so moste of the function disappears. + */ +static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino, + u32 fsid, unsigned char *uuid) { - fsidv[0] = new_encode_dev(dev); - fsidv[1] = ino_t_to_u32(ino); + u32 *up; + switch(vers) { + case FSID_DEV: + fsidv[0] = htonl((MAJOR(dev)<<16) | + MINOR(dev)); + fsidv[1] = ino_t_to_u32(ino); + break; + case FSID_NUM: + fsidv[0] = fsid; + break; + case FSID_MAJOR_MINOR: + fsidv[0] = htonl(MAJOR(dev)); + fsidv[1] = htonl(MINOR(dev)); + fsidv[2] = ino_t_to_u32(ino); + break; + + case FSID_ENCODE_DEV: + fsidv[0] = new_encode_dev(dev); + fsidv[1] = ino_t_to_u32(ino); + break; + + case FSID_UUID4_INUM: + /* 4 byte fsid and inode number */ + up = (u32*)uuid; + fsidv[0] = ino_t_to_u32(ino); + fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3]; + break; + + case FSID_UUID8: + /* 8 byte fsid */ + up = (u32*)uuid; + fsidv[0] = up[0] ^ up[2]; + fsidv[1] = up[1] ^ up[3]; + break; + + case FSID_UUID16: + /* 16 byte fsid - NFSv3+ only */ + memcpy(fsidv, uuid, 16); + break; + + case FSID_UUID16_INUM: + /* 8 byte inode and 16 byte fsid */ + *(u64*)fsidv = (u64)ino; + memcpy(fsidv+2, uuid, 16); + break; + default: BUG(); + } } static inline int key_len(int type) { switch(type) { - case 0: return 8; - case 1: return 4; - case 2: return 12; - case 3: return 8; + case FSID_DEV: return 8; + case FSID_NUM: return 4; + case FSID_MAJOR_MINOR: return 12; + case FSID_ENCODE_DEV: return 8; + case FSID_UUID4_INUM: return 8; + case FSID_UUID8: return 8; + case FSID_UUID16: return 16; + case FSID_UUID16_INUM: return 24; default: return 0; } } diff --git a/include/linux/nmi.h b/include/linux/nmi.h index acb4ed130247..29af2d5df097 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -17,8 +17,15 @@ #ifdef ARCH_HAS_NMI_WATCHDOG #include <asm/nmi.h> extern void touch_nmi_watchdog(void); +extern void acpi_nmi_disable(void); +extern void acpi_nmi_enable(void); #else -# define touch_nmi_watchdog() touch_softlockup_watchdog() +static inline void touch_nmi_watchdog(void) +{ + touch_softlockup_watchdog(); +} +static inline void acpi_nmi_disable(void) { } +static inline void acpi_nmi_enable(void) { } #endif #ifndef trigger_all_cpu_backtrace diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2e132473cbe5..be4652a0545a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -113,8 +113,6 @@ extern struct vfsmount *proc_mnt; extern int proc_fill_super(struct super_block *,void *,int); extern struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *); -extern int proc_match(int, const char *,struct proc_dir_entry *); - /* * These are generic /proc routines that use the internal * "struct proc_dir_entry" tree to traverse the filesystem. diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index cf23813cbec2..586aaba91720 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -122,7 +122,7 @@ /*Digi jsm */ #define PORT_JSM 69 -#define PORT_IP3106 70 +#define PORT_PNX8XXX 70 /* Hilscher netx */ #define PORT_NETX 71 diff --git a/include/linux/serial_ip3106.h b/include/linux/serial_ip3106.h deleted file mode 100644 index f500ac602c5c..000000000000 --- a/include/linux/serial_ip3106.h +++ /dev/null @@ -1,81 +0,0 @@ -/* - * Embedded Alley Solutions, source@embeddedalley.com. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _LINUX_SERIAL_IP3106_H -#define _LINUX_SERIAL_IP3106_H - -#include <linux/serial_core.h> -#include <linux/device.h> - -#define IP3106_NR_PORTS 2 - -struct ip3106_port { - struct uart_port port; - struct timer_list timer; - unsigned int old_status; -}; - -/* register offsets */ -#define IP3106_LCR 0 -#define IP3106_MCR 0x004 -#define IP3106_BAUD 0x008 -#define IP3106_CFG 0x00c -#define IP3106_FIFO 0x028 -#define IP3106_ISTAT 0xfe0 -#define IP3106_IEN 0xfe4 -#define IP3106_ICLR 0xfe8 -#define IP3106_ISET 0xfec -#define IP3106_PD 0xff4 -#define IP3106_MID 0xffc - -#define IP3106_UART_LCR_TXBREAK (1<<30) -#define IP3106_UART_LCR_PAREVN 0x10000000 -#define IP3106_UART_LCR_PAREN 0x08000000 -#define IP3106_UART_LCR_2STOPB 0x04000000 -#define IP3106_UART_LCR_8BIT 0x01000000 -#define IP3106_UART_LCR_TX_RST 0x00040000 -#define IP3106_UART_LCR_RX_RST 0x00020000 -#define IP3106_UART_LCR_RX_NEXT 0x00010000 - -#define IP3106_UART_MCR_SCR 0xFF000000 -#define IP3106_UART_MCR_DCD 0x00800000 -#define IP3106_UART_MCR_CTS 0x00100000 -#define IP3106_UART_MCR_LOOP 0x00000010 -#define IP3106_UART_MCR_RTS 0x00000002 -#define IP3106_UART_MCR_DTR 0x00000001 - -#define IP3106_UART_INT_TX 0x00000080 -#define IP3106_UART_INT_EMPTY 0x00000040 -#define IP3106_UART_INT_RCVTO 0x00000020 -#define IP3106_UART_INT_RX 0x00000010 -#define IP3106_UART_INT_RXOVRN 0x00000008 -#define IP3106_UART_INT_FRERR 0x00000004 -#define IP3106_UART_INT_BREAK 0x00000002 -#define IP3106_UART_INT_PARITY 0x00000001 -#define IP3106_UART_INT_ALLRX 0x0000003F -#define IP3106_UART_INT_ALLTX 0x000000C0 - -#define IP3106_UART_FIFO_TXFIFO 0x001F0000 -#define IP3106_UART_FIFO_TXFIFO_STA (0x1f<<16) -#define IP3106_UART_FIFO_RXBRK 0x00008000 -#define IP3106_UART_FIFO_RXFE 0x00004000 -#define IP3106_UART_FIFO_RXPAR 0x00002000 -#define IP3106_UART_FIFO_RXFIFO 0x00001F00 -#define IP3106_UART_FIFO_RBRTHR 0x000000FF - -#endif diff --git a/include/linux/serial_pnx8xxx.h b/include/linux/serial_pnx8xxx.h new file mode 100644 index 000000000000..de6c19c7f340 --- /dev/null +++ b/include/linux/serial_pnx8xxx.h @@ -0,0 +1,81 @@ +/* + * Embedded Alley Solutions, source@embeddedalley.com. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _LINUX_SERIAL_PNX8XXX_H +#define _LINUX_SERIAL_PNX8XXX_H + +#include <linux/serial_core.h> +#include <linux/device.h> + +#define PNX8XXX_NR_PORTS 2 + +struct pnx8xxx_port { + struct uart_port port; + struct timer_list timer; + unsigned int old_status; +}; + +/* register offsets */ +#define PNX8XXX_LCR 0 +#define PNX8XXX_MCR 0x004 +#define PNX8XXX_BAUD 0x008 +#define PNX8XXX_CFG 0x00c +#define PNX8XXX_FIFO 0x028 +#define PNX8XXX_ISTAT 0xfe0 +#define PNX8XXX_IEN 0xfe4 +#define PNX8XXX_ICLR 0xfe8 +#define PNX8XXX_ISET 0xfec +#define PNX8XXX_PD 0xff4 +#define PNX8XXX_MID 0xffc + +#define PNX8XXX_UART_LCR_TXBREAK (1<<30) +#define PNX8XXX_UART_LCR_PAREVN 0x10000000 +#define PNX8XXX_UART_LCR_PAREN 0x08000000 +#define PNX8XXX_UART_LCR_2STOPB 0x04000000 +#define PNX8XXX_UART_LCR_8BIT 0x01000000 +#define PNX8XXX_UART_LCR_TX_RST 0x00040000 +#define PNX8XXX_UART_LCR_RX_RST 0x00020000 +#define PNX8XXX_UART_LCR_RX_NEXT 0x00010000 + +#define PNX8XXX_UART_MCR_SCR 0xFF000000 +#define PNX8XXX_UART_MCR_DCD 0x00800000 +#define PNX8XXX_UART_MCR_CTS 0x00100000 +#define PNX8XXX_UART_MCR_LOOP 0x00000010 +#define PNX8XXX_UART_MCR_RTS 0x00000002 +#define PNX8XXX_UART_MCR_DTR 0x00000001 + +#define PNX8XXX_UART_INT_TX 0x00000080 +#define PNX8XXX_UART_INT_EMPTY 0x00000040 +#define PNX8XXX_UART_INT_RCVTO 0x00000020 +#define PNX8XXX_UART_INT_RX 0x00000010 +#define PNX8XXX_UART_INT_RXOVRN 0x00000008 +#define PNX8XXX_UART_INT_FRERR 0x00000004 +#define PNX8XXX_UART_INT_BREAK 0x00000002 +#define PNX8XXX_UART_INT_PARITY 0x00000001 +#define PNX8XXX_UART_INT_ALLRX 0x0000003F +#define PNX8XXX_UART_INT_ALLTX 0x000000C0 + +#define PNX8XXX_UART_FIFO_TXFIFO 0x001F0000 +#define PNX8XXX_UART_FIFO_TXFIFO_STA (0x1f<<16) +#define PNX8XXX_UART_FIFO_RXBRK 0x00008000 +#define PNX8XXX_UART_FIFO_RXFE 0x00004000 +#define PNX8XXX_UART_FIFO_RXPAR 0x00002000 +#define PNX8XXX_UART_FIFO_RXFIFO 0x00001F00 +#define PNX8XXX_UART_FIFO_RBRTHR 0x000000FF + +#endif diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index 60fce3c92857..b7c7307ceec6 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -78,7 +78,6 @@ void rpc_unregister_sysctl(void); * module currently registers its sysctl table dynamically, the sysctl path * for module FOO is <CTL_SUNRPC, CTL_FOODEBUG>. */ -#define CTL_SUNRPC 7249 /* arbitrary and hopefully unused */ enum { CTL_RPCDEBUG = 1, diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 665412c4f4b9..2c5fb38d9392 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -53,7 +53,6 @@ struct __sysctl_args { /* For internal pattern-matching use only: */ #ifdef __KERNEL__ -#define CTL_ANY -1 /* Matches any name */ #define CTL_NONE 0 #define CTL_UNNUMBERED CTL_NONE /* sysctl without a binary number */ #endif @@ -69,7 +68,13 @@ enum CTL_DEV=7, /* Devices */ CTL_BUS=8, /* Busses */ CTL_ABI=9, /* Binary emulation */ - CTL_CPU=10 /* CPU stuff (speed scaling, etc) */ + CTL_CPU=10, /* CPU stuff (speed scaling, etc) */ + CTL_ARLAN=254, /* arlan wireless driver */ + CTL_APPLDATA=2120, /* s390 appldata */ + CTL_S390DBF=5677, /* s390 debug */ + CTL_SUNRPC=7249, /* sunrpc debug */ + CTL_PM=9899, /* frv power management */ + CTL_FRV=9898, /* frv specific sysctls */ }; /* CTL_BUS names: */ @@ -202,6 +207,11 @@ enum VM_PANIC_ON_OOM=33, /* panic at out-of-memory */ VM_VDSO_ENABLED=34, /* map VDSO into new processes? */ VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */ + + /* s390 vm cmm sysctls */ + VM_CMM_PAGES=1111, + VM_CMM_TIMED_PAGES=1112, + VM_CMM_TIMEOUT=1113, }; @@ -803,6 +813,7 @@ enum FS_AIO_NR=18, /* current system-wide number of aio requests */ FS_AIO_MAX_NR=19, /* system-wide maximum number of aio requests */ FS_INOTIFY=20, /* inotify submenu */ + FS_OCFS2=988, /* ocfs2 */ }; /* /proc/sys/fs/quota/ */ @@ -913,7 +924,11 @@ enum #ifdef __KERNEL__ #include <linux/list.h> -extern void sysctl_init(void); +/* For the /proc/sys support */ +struct ctl_table; +extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev); +extern void sysctl_head_finish(struct ctl_table_header *prev); +extern int sysctl_perm(struct ctl_table *table, int op); typedef struct ctl_table ctl_table; @@ -1007,9 +1022,9 @@ struct ctl_table int maxlen; mode_t mode; ctl_table *child; + ctl_table *parent; /* Automatically set */ proc_handler *proc_handler; /* Callback for text formatting */ ctl_handler *strategy; /* Callback function for all r/w */ - struct proc_dir_entry *de; /* /proc control block */ void *extra1; void *extra2; }; @@ -1024,8 +1039,8 @@ struct ctl_table_header struct completion *unregistering; }; -struct ctl_table_header * register_sysctl_table(ctl_table * table, - int insert_at_head); +struct ctl_table_header * register_sysctl_table(ctl_table * table); + void unregister_sysctl_table(struct ctl_table_header * table); #else /* __KERNEL__ */ diff --git a/include/linux/time.h b/include/linux/time.h index 55cee172d723..eceb1a59b078 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -90,7 +90,7 @@ static inline struct timespec timespec_sub(struct timespec lhs, extern struct timespec xtime; extern struct timespec wall_to_monotonic; -extern seqlock_t xtime_lock; +extern seqlock_t xtime_lock __attribute__((weak)); void timekeeping_init(void); |
