X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=include%2Fasm-i386%2Fmach-xen%2Fasm%2Fpgtable.h;h=7268c13477d86250f8d48f7ab3c60ad6d7a708f9;hb=refs%2Fheads%2Fvserver;hp=388a5ba1ec0ca439511c2eaa1b0c14f6e88be4dd;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/include/asm-i386/mach-xen/asm/pgtable.h b/include/asm-i386/mach-xen/asm/pgtable.h index 388a5ba1e..7268c1347 100644 --- a/include/asm-i386/mach-xen/asm/pgtable.h +++ b/include/asm-i386/mach-xen/asm/pgtable.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifndef _I386_BITOPS_H #include @@ -35,14 +36,14 @@ struct vm_area_struct; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) extern unsigned long empty_zero_page[1024]; extern pgd_t *swapper_pg_dir; -extern kmem_cache_t *pgd_cache; -extern kmem_cache_t *pmd_cache; +extern struct kmem_cache *pgd_cache; +extern struct kmem_cache *pmd_cache; extern spinlock_t pgd_lock; extern struct page *pgd_list; -void pmd_ctor(void *, kmem_cache_t *, unsigned long); -void pgd_ctor(void *, kmem_cache_t *, unsigned long); -void pgd_dtor(void *, kmem_cache_t *, unsigned long); +void pmd_ctor(void *, struct kmem_cache *, unsigned long); +void pgd_ctor(void *, struct kmem_cache *, unsigned long); +void pgd_dtor(void *, struct kmem_cache *, unsigned long); void pgtable_cache_init(void); void paging_init(void); @@ -249,20 +250,88 @@ static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return p # include #endif -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - if (!pte_dirty(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low); -} +#ifndef CONFIG_PARAVIRT +/* + * Rules for using pte_update - it must be called after any PTE update which + * has not been done using the set_pte / clear_pte interfaces. It is used by + * shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE + * updates should either be sets, clears, or set_pte_atomic for P->P + * transitions, which means this hook should only be called for user PTEs. + * This hook implies a P->P protection or access change has taken place, which + * requires a subsequent TLB flush. The notification can optionally be delayed + * until the TLB flush event by using the pte_update_defer form of the + * interface, but care must be taken to assure that the flush happens while + * still holding the same page table lock so that the shadow and primary pages + * do not become out of sync on SMP. + */ +#define pte_update(mm, addr, ptep) do { } while (0) +#define pte_update_defer(mm, addr, ptep) do { } while (0) +#endif + +/* + * We only update the dirty/accessed state if we set + * the dirty bit by hand in the kernel, since the hardware + * will do the accessed bit for us, and we don't want to + * race with other CPU's that might be updating the dirty + * bit at the same time. + */ +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ + do { \ + if (__dirty) { \ + if ( likely((__vma)->vm_mm == current->mm) ) { \ + BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \ + pte_update_defer((__vma)->vm_mm, (__address), (__ptep)); \ + } else { \ + xen_l1_entry_update((__ptep), (__entry)); \ + pte_update_defer((__vma)->vm_mm, (__address), (__ptep)); \ + flush_tlb_page((__vma), (__address)); \ + } \ + } \ + } while (0) + +/* + * We don't actually have these, but we want to advertise them so that + * we can encompass the flush here. + */ +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG + +#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH +#define ptep_clear_flush_dirty(vma, address, ptep) \ +({ \ + int __dirty; \ + __dirty = pte_dirty(*(ptep)); \ + if (__dirty) { \ + clear_bit(_PAGE_BIT_DIRTY, &(ptep)->pte_low); \ + pte_update_defer((vma)->vm_mm, (address), (ptep)); \ + flush_tlb_page(vma, address); \ + } \ + __dirty; \ +}) -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young(vma, address, ptep) \ +({ \ + int __young; \ + __young = pte_young(*(ptep)); \ + if (__young) { \ + clear_bit(_PAGE_BIT_ACCESSED, &(ptep)->pte_low); \ + pte_update_defer((vma)->vm_mm, (address), (ptep)); \ + flush_tlb_page(vma, address); \ + } \ + __young; \ +}) + +#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) { - if (!pte_young(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low); + pte_t pte = raw_ptep_get_and_clear(ptep); + pte_update(mm, addr, ptep); + return pte; } +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; @@ -275,10 +344,12 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long return pte; } +#define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { if (pte_write(*ptep)) clear_bit(_PAGE_BIT_RW, &ptep->pte_low); + pte_update(mm, addr, ptep); } /* @@ -368,11 +439,11 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define pte_index(address) \ (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) #define pte_offset_kernel(dir, address) \ - ((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address)) + ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address)) #define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) -#define pmd_page_kernel(pmd) \ +#define pmd_page_vaddr(pmd) \ ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) /* @@ -395,8 +466,6 @@ extern pte_t *lookup_address(unsigned long address); static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;} #endif -extern void noexec_setup(const char *str); - #if defined(CONFIG_HIGHPTE) #define pte_offset_map(dir, address) \ ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + \ @@ -414,29 +483,19 @@ extern void noexec_setup(const char *str); #define pte_unmap_nested(pte) do { } while (0) #endif +/* Clear a kernel PTE and flush it from the TLB */ +#define kpte_clear_flush(ptep, vaddr) \ +do { \ + pte_clear(&init_mm, vaddr, ptep); \ + __flush_tlb_one(vaddr); \ +} while (0) + /* * The i386 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. - * - * Also, we only update the dirty/accessed state if we set - * the dirty bit by hand in the kernel, since the hardware - * will do the accessed bit for us, and we don't want to - * race with other CPU's that might be updating the dirty - * bit at the same time. */ #define update_mmu_cache(vma,address,pte) do { } while (0) #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ - do { \ - if (__dirty) { \ - if ( likely((__vma)->vm_mm == current->mm) ) { \ - BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \ - } else { \ - xen_l1_entry_update((__ptep), (__entry)); \ - flush_tlb_page((__vma), (__address)); \ - } \ - } \ - } while (0) #define __HAVE_ARCH_PTEP_ESTABLISH #define ptep_establish(__vma, __address, __ptep, __entry) \ @@ -490,19 +549,13 @@ int touch_pte_range(struct mm_struct *mm, unsigned long address, unsigned long size); -#define io_remap_pfn_range(vma,from,pfn,size,prot) \ -direct_remap_pfn_range(vma,from,pfn,size,prot,DOMID_IO) +#define io_remap_pfn_range(vma,vaddr,pfn,size,prot) \ + direct_remap_pfn_range(vma,vaddr,pfn,size,prot,DOMID_IO) #define MK_IOSPACE_PFN(space, pfn) (pfn) #define GET_IOSPACE(pfn) 0 #define GET_PFN(pfn) (pfn) -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -#define __HAVE_ARCH_PTE_SAME #include #endif /* _I386_PGTABLE_H */