diff options
Diffstat (limited to 'arch/x86/include')
| -rw-r--r-- | arch/x86/include/asm/kvm_host.h | 1 | ||||
| -rw-r--r-- | arch/x86/include/asm/paravirt.h | 25 | ||||
| -rw-r--r-- | arch/x86/include/asm/paravirt_types.h | 6 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable-2level.h | 9 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable-3level.h | 23 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable.h | 143 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable_64.h | 28 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable_types.h | 3 | ||||
| -rw-r--r-- | arch/x86/include/asm/xen/page.h | 16 |
9 files changed, 243 insertions, 11 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index aa75f21a9fba..ffd7f8d29187 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -822,6 +822,7 @@ extern bool kvm_rebooting; #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_age_hva(struct kvm *kvm, unsigned long hva); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7709c12431b8..2071a8b2b32f 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -435,6 +435,11 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr, { PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep); } +static inline void pmd_update(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp); +} static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -442,6 +447,12 @@ static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep); } +static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp); +} + static inline pte_t __pte(pteval_t val) { pteval_t ret; @@ -543,6 +554,20 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ +#if PAGETABLE_LEVELS >= 3 + if (sizeof(pmdval_t) > sizeof(long)) + /* 5 arg words */ + pv_mmu_ops.set_pmd_at(mm, addr, pmdp, pmd); + else + PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp, pmd.pmd); +#endif +} +#endif + static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { pmdval_t val = native_pmd_val(pmd); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b82bac975250..82885099c869 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -265,10 +265,16 @@ struct pv_mmu_ops { 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 (*set_pmd_at)(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmdval); 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); + void (*pmd_update)(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp); + void (*pmd_update_defer)(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp); pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 2334982b339e..98391db840c6 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -46,6 +46,15 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) #endif +#ifdef CONFIG_SMP +static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) +{ + return __pmd(xchg((pmdval_t *)xp, 0)); +} +#else +#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) +#endif + /* * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken, * split up the 29 bits of offset into this range: diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 177b0165ea01..94b979d1b58d 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -104,6 +104,29 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep) #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) #endif +#ifdef CONFIG_SMP +union split_pmd { + struct { + u32 pmd_low; + u32 pmd_high; + }; + pmd_t pmd; +}; +static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) +{ + union split_pmd res, *orig = (union split_pmd *)pmdp; + + /* xchg acts as a barrier before setting of the high bits */ + res.pmd_low = xchg(&orig->pmd_low, 0); + res.pmd_high = orig->pmd_high; + orig->pmd_high = 0; + + return res.pmd; +} +#else +#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) +#endif + /* * Bits 0, 6 and 7 are taken in the low part of the pte, * put the 32 bits of offset into the high part. diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index ada823a13c7c..18601c86fab1 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -35,6 +35,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #else /* !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_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) @@ -59,6 +60,8 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pte_update(mm, addr, ptep) do { } while (0) #define pte_update_defer(mm, addr, ptep) do { } while (0) +#define pmd_update(mm, addr, ptep) do { } while (0) +#define pmd_update_defer(mm, addr, ptep) do { } while (0) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) @@ -94,6 +97,11 @@ static inline int pte_young(pte_t pte) return pte_flags(pte) & _PAGE_ACCESSED; } +static inline int pmd_young(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_ACCESSED; +} + static inline int pte_write(pte_t pte) { return pte_flags(pte) & _PAGE_RW; @@ -142,6 +150,23 @@ static inline int pmd_large(pmd_t pte) (_PAGE_PSE | _PAGE_PRESENT); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_splitting(pmd_t pmd) +{ + return pmd_val(pmd) & _PAGE_SPLITTING; +} + +static inline int pmd_trans_huge(pmd_t pmd) +{ + return pmd_val(pmd) & _PAGE_PSE; +} + +static inline int has_transparent_hugepage(void) +{ + return cpu_has_pse; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); @@ -216,6 +241,55 @@ static inline pte_t pte_mkspecial(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL); } +static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) +{ + pmdval_t v = native_pmd_val(pmd); + + return __pmd(v | set); +} + +static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) +{ + pmdval_t v = native_pmd_val(pmd); + + return __pmd(v & ~clear); +} + +static inline pmd_t pmd_mkold(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_ACCESSED); +} + +static inline pmd_t pmd_wrprotect(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_RW); +} + +static inline pmd_t pmd_mkdirty(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_DIRTY); +} + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_PSE); +} + +static inline pmd_t pmd_mkyoung(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_ACCESSED); +} + +static inline pmd_t pmd_mkwrite(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_RW); +} + +static inline pmd_t pmd_mknotpresent(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_PRESENT); +} + /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. @@ -256,6 +330,16 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) return __pte(val); } +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + pmdval_t val = pmd_val(pmd); + + val &= _HPAGE_CHG_MASK; + val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK; + + return __pmd(val); +} + /* mprotect needs to preserve PAT bits when updating vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) @@ -350,7 +434,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pmd_page(pmd) pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) +#define pmd_page(pmd) pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT) /* * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] @@ -524,12 +608,26 @@ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) return res; } +static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) +{ + pmd_t res = *pmdp; + + native_pmd_clear(pmdp); + return res; +} + 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_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp , pmd_t pmd) +{ + native_set_pmd(pmdp, pmd); +} + #ifndef CONFIG_PARAVIRT /* * Rules for using pte_update - it must be called after any PTE update which @@ -607,6 +705,49 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, #define flush_tlb_fix_spurious_fault(vma, address) +#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) + +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); + +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +extern int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + + +#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH +extern void pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp); + +#define __HAVE_ARCH_PMD_WRITE +static inline int pmd_write(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_RW; +} + +#define __HAVE_ARCH_PMDP_GET_AND_CLEAR +static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = native_pmdp_get_and_clear(pmdp); + pmd_update(mm, addr, pmdp); + return pmd; +} + +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); + pmd_update(mm, addr, pmdp); +} + /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f86da20347f2..975f709e09ae 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -59,6 +59,16 @@ static inline void native_set_pte_atomic(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; +} + +static inline void native_pmd_clear(pmd_t *pmd) +{ + native_set_pmd(pmd, native_make_pmd(0)); +} + static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP @@ -72,14 +82,17 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #endif } -static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) +static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { - *pmdp = pmd; -} - -static inline void native_pmd_clear(pmd_t *pmd) -{ - native_set_pmd(pmd, native_make_pmd(0)); +#ifdef CONFIG_SMP + return native_make_pmd(xchg(&xp->pmd, 0)); +#else + /* native_local_pmdp_get_and_clear, + but duplicated because of cyclic dependency */ + pmd_t ret = *xp; + native_pmd_clear(xp); + return ret; +#endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) @@ -168,6 +181,7 @@ extern void cleanup_highmap(void); #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index d1f4a760be23..7db7723d1f32 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,6 +22,7 @@ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1 +#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ /* If _PAGE_BIT_PRESENT is clear, we use these: */ @@ -45,6 +46,7 @@ #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) +#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) #define __HAVE_ARCH_PTE_SPECIAL #ifdef CONFIG_KMEMCHECK @@ -70,6 +72,7 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY) +#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) #define _PAGE_CACHE_WB (0) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 8760cc60a21c..f25bdf238a33 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -42,6 +42,11 @@ extern unsigned int machine_to_phys_order; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern int m2p_add_override(unsigned long mfn, struct page *page); +extern int m2p_remove_override(struct page *page); +extern struct page *m2p_find_override(unsigned long mfn); +extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); + static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; @@ -72,9 +77,6 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely((mfn >> machine_to_phys_order) != 0)) - return ~0; - pfn = 0; /* * The array access can fail (e.g., device space beyond end of RAM). @@ -83,6 +85,14 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) */ __get_user(pfn, &machine_to_phys_mapping[mfn]); + /* + * If this appears to be a foreign mfn (because the pfn + * doesn't map back to the mfn), then check the local override + * table to see if there's a better pfn to use. + */ + if (get_phys_to_machine(pfn) != mfn) + pfn = m2p_find_override_pfn(mfn, pfn); + return pfn; } |