--- zzzz-none-000/linux-3.10.107/arch/arm64/include/asm/pgtable.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/arm64/include/asm/pgtable.h 2021-02-04 17:41:59.000000000 +0000 @@ -16,6 +16,7 @@ #ifndef __ASM_PGTABLE_H #define __ASM_PGTABLE_H +#include #include #include @@ -25,86 +26,99 @@ * Software defined PTE bits definition. */ #define PTE_VALID (_AT(pteval_t, 1) << 0) -#define PTE_PROT_NONE (_AT(pteval_t, 1) << 1) /* only when !PTE_VALID */ -#define PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !pte_present() */ +#define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) +#define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. - */ -#define VMALLOC_START UL(0xffffff8000000000) -#define VMALLOC_END (PAGE_OFFSET - UL(0x400000000) - SZ_64K) + * + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array + * (rounded up to PUD_SIZE). + * VMALLOC_START: beginning of the kernel VA space + * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, + * fixed mappings and modules + */ +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) + +#ifndef CONFIG_KASAN +#define VMALLOC_START (VA_START) +#else +#include +#define VMALLOC_START (KASAN_SHADOW_END + SZ_64K) +#endif + +#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) -#define FIRST_USER_ADDRESS 0 +#define FIRST_USER_ADDRESS 0UL #ifndef __ASSEMBLY__ + +#include + extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); +extern void __pud_error(const char *file, int line, unsigned long val); extern void __pgd_error(const char *file, int line, unsigned long val); -#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte)) -#ifndef CONFIG_ARM64_64K_PAGES -#define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd_val(pmd)) -#endif -#define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd)) - -/* - * The pgprot_* and protection_map entries will be fixed up at runtime to - * include the cachable and bufferable bits based on memory policy, as well as - * any architecture dependent bits like global/ASID and SMP shared mapping - * bits. - */ -#define _PAGE_DEFAULT PTE_TYPE_PAGE | PTE_AF +#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) +#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -extern pgprot_t pgprot_default; +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) + +#define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) +#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) + +#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) + +#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) + +#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP) +#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) + +#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) +#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) + +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +#define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) +#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) + +#define __P000 PAGE_NONE +#define __P001 PAGE_READONLY +#define __P010 PAGE_COPY +#define __P011 PAGE_COPY +#define __P100 PAGE_READONLY_EXEC +#define __P101 PAGE_READONLY_EXEC +#define __P110 PAGE_COPY_EXEC +#define __P111 PAGE_COPY_EXEC + +#define __S000 PAGE_NONE +#define __S001 PAGE_READONLY +#define __S010 PAGE_SHARED +#define __S011 PAGE_SHARED +#define __S100 PAGE_READONLY_EXEC +#define __S101 PAGE_READONLY_EXEC +#define __S110 PAGE_SHARED_EXEC +#define __S111 PAGE_SHARED_EXEC -#define __pgprot_modify(prot,mask,bits) \ - __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) - -#define _MOD_PROT(p, b) __pgprot_modify(p, 0, b) - -#define PAGE_NONE __pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE) -#define PAGE_SHARED _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN) -#define PAGE_COPY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define PAGE_COPY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) -#define PAGE_READONLY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) -#define PAGE_KERNEL _MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY) -#define PAGE_KERNEL_EXEC _MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY) - -#define __PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE) -#define __PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define __PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) -#define __PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define __PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) -#define __PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define __PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) - -#endif /* __ASSEMBLY__ */ - -#define __P000 __PAGE_NONE -#define __P001 __PAGE_READONLY -#define __P010 __PAGE_COPY -#define __P011 __PAGE_COPY -#define __P100 __PAGE_READONLY_EXEC -#define __P101 __PAGE_READONLY_EXEC -#define __P110 __PAGE_COPY_EXEC -#define __P111 __PAGE_COPY_EXEC - -#define __S000 __PAGE_NONE -#define __S001 __PAGE_READONLY -#define __S010 __PAGE_SHARED -#define __S011 __PAGE_SHARED -#define __S100 __PAGE_READONLY_EXEC -#define __S101 __PAGE_READONLY_EXEC -#define __S110 __PAGE_SHARED_EXEC -#define __S111 __PAGE_SHARED_EXEC - -#ifndef __ASSEMBLY__ /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. @@ -112,6 +126,8 @@ extern struct page *empty_zero_page; #define ZERO_PAGE(vaddr) (empty_zero_page) +#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte)) + #define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) (__pte(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) @@ -119,7 +135,11 @@ #define pte_none(pte) (!pte_val(pte)) #define pte_clear(mm,addr,ptep) set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) -#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + __pte_index(addr)) + +/* Find an entry in the third-level page table. */ +#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + +#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + pte_index(addr)) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) #define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr)) @@ -129,42 +149,142 @@ /* * The following only work if pte_present(). Undefined behaviour otherwise. */ -#define pte_present(pte) (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) -#define pte_dirty(pte) (pte_val(pte) & PTE_DIRTY) -#define pte_young(pte) (pte_val(pte) & PTE_AF) -#define pte_special(pte) (pte_val(pte) & PTE_SPECIAL) -#define pte_write(pte) (!(pte_val(pte) & PTE_RDONLY)) +#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) +#define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) +#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) +#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) +#define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) + +#ifdef CONFIG_ARM64_HW_AFDBM +#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) +#else +#define pte_hw_dirty(pte) (0) +#endif +#define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) +#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) + +#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) +#define pte_valid_not_user(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) + +static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) +{ + pte_val(pte) &= ~pgprot_val(prot); + return pte; +} + +static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) +{ + pte_val(pte) |= pgprot_val(prot); + return pte; +} + +static inline pte_t pte_wrprotect(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_WRITE)); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_WRITE)); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_DIRTY)); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_DIRTY)); +} -#define pte_valid_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) +static inline pte_t pte_mkold(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_AF)); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_AF)); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); +} -#define PTE_BIT_FUNC(fn,op) \ -static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; } +static inline pte_t pte_mkcont(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_CONT)); +} -PTE_BIT_FUNC(wrprotect, |= PTE_RDONLY); -PTE_BIT_FUNC(mkwrite, &= ~PTE_RDONLY); -PTE_BIT_FUNC(mkclean, &= ~PTE_DIRTY); -PTE_BIT_FUNC(mkdirty, |= PTE_DIRTY); -PTE_BIT_FUNC(mkold, &= ~PTE_AF); -PTE_BIT_FUNC(mkyoung, |= PTE_AF); -PTE_BIT_FUNC(mkspecial, |= PTE_SPECIAL); +static inline pte_t pte_mknoncont(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_CONT)); +} static inline void set_pte(pte_t *ptep, pte_t pte) { *ptep = pte; + + /* + * Only if the new pte is valid and kernel, otherwise TLB maintenance + * or update_mmu_cache() have the necessary barriers. + */ + if (pte_valid_not_user(pte)) { + dsb(ishst); + isb(); + } } +struct mm_struct; +struct vm_area_struct; + extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); +/* + * PTE bits configuration in the presence of hardware Dirty Bit Management + * (PTE_WRITE == PTE_DBM): + * + * Dirty Writable | PTE_RDONLY PTE_WRITE PTE_DIRTY (sw) + * 0 0 | 1 0 0 + * 0 1 | 1 1 0 + * 1 0 | 1 0 1 + * 1 1 | 0 1 x + * + * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via + * the page fault mechanism. Checking the dirty status of a pte becomes: + * + * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) + */ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - if (pte_valid_user(pte)) { - if (!pte_special(pte) && pte_exec(pte)) + if (pte_present(pte)) { + if (pte_sw_dirty(pte) && pte_write(pte)) + pte_val(pte) &= ~PTE_RDONLY; + else + pte_val(pte) |= PTE_RDONLY; + if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); - if (!pte_dirty(pte)) - pte = pte_wrprotect(pte); + } + + /* + * If the existing pte is valid, check for potential race with + * hardware updates of the pte (ptep_set_access_flags safely changes + * valid ptes without going through an invalid entry). + */ + if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && + pte_valid(*ptep) && pte_valid(pte)) { + VM_WARN_ONCE(!pte_young(pte), + "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); + VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); } set_pte(ptep, pte); @@ -173,11 +293,93 @@ /* * Huge pte definitions. */ -#define pte_huge(pte) ((pte_val(pte) & PTE_TYPE_MASK) == PTE_TYPE_HUGEPAGE) -#define pte_mkhuge(pte) (__pte((pte_val(pte) & ~PTE_TYPE_MASK) | PTE_TYPE_HUGEPAGE)) +#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT)) +#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) + +/* + * Hugetlb definitions. + */ +#define HUGE_MAX_HSTATE 2 +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define __HAVE_ARCH_PTE_SPECIAL +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +static inline pmd_t pud_pmd(pud_t pud) +{ + return __pmd(pud_val(pud)); +} + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + +static inline pmd_t pte_pmd(pte_t pte) +{ + return __pmd(pte_val(pte)); +} + +static inline pgprot_t mk_sect_prot(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) & ~PTE_TABLE_BIT); +} + +/* + * THP definitions. + */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) +#define pmd_trans_splitting(pmd) pte_special(pmd_pte(pmd)) +#ifdef CONFIG_HAVE_RCU_TABLE_FREE +#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH +struct vm_area_struct; +void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); +#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#define pmd_present(pmd) pte_present(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) +#define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) +#define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd))) +#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) +#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) +#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_SECT_VALID)) + +#define __HAVE_ARCH_PMD_WRITE +#define pmd_write(pmd) pte_write(pmd_pte(pmd)) + +#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) + +#define pmd_pfn(pmd) (((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT) +#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) + +#define pud_write(pud) pte_write(pud_pte(pud)) +#define pud_pfn(pud) (((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT) + +#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) + +static inline int has_transparent_hugepage(void) +{ + return 1; +} + +#define __pgprot_modify(prot,mask,bits) \ + __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) + /* * Mark the prot value as uncacheable and unbufferable. */ @@ -185,22 +387,37 @@ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) -#define pgprot_dmacoherent(prot) \ - __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) +#define pgprot_device(prot) \ + __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) #define pmd_bad(pmd) (!(pmd_val(pmd) & 2)) +#define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ + PMD_TYPE_TABLE) +#define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ + PMD_TYPE_SECT) + +#ifdef CONFIG_ARM64_64K_PAGES +#define pud_sect(pud) (0) +#define pud_table(pud) (1) +#else +#define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ + PUD_TYPE_SECT) +#define pud_table(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ + PUD_TYPE_TABLE) +#endif + static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { *pmdp = pmd; - dsb(); + dsb(ishst); + isb(); } static inline void pmd_clear(pmd_t *pmdp) @@ -221,7 +438,9 @@ */ #define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot) -#ifndef CONFIG_ARM64_64K_PAGES +#if CONFIG_PGTABLE_LEVELS > 2 + +#define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd_val(pmd)) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!(pud_val(pud) & 2)) @@ -230,7 +449,8 @@ static inline void set_pud(pud_t *pudp, pud_t pud) { *pudp = pud; - dsb(); + dsb(ishst); + isb(); } static inline void pud_clear(pud_t *pudp) @@ -243,7 +463,55 @@ return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK); } -#endif /* CONFIG_ARM64_64K_PAGES */ +/* Find an entry in the second-level page table. */ +#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) + +static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) +{ + return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr); +} + +#define pud_page(pud) pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK)) + +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ + +#if CONFIG_PGTABLE_LEVELS > 3 + +#define pud_ERROR(pud) __pud_error(__FILE__, __LINE__, pud_val(pud)) + +#define pgd_none(pgd) (!pgd_val(pgd)) +#define pgd_bad(pgd) (!(pgd_val(pgd) & 2)) +#define pgd_present(pgd) (pgd_val(pgd)) + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + *pgdp = pgd; + dsb(ishst); +} + +static inline void pgd_clear(pgd_t *pgdp) +{ + set_pgd(pgdp, __pgd(0)); +} + +static inline pud_t *pgd_page_vaddr(pgd_t pgd) +{ + return __va(pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK); +} + +/* Find an entry in the frst-level page table. */ +#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) +{ + return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(addr); +} + +#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK)) + +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ + +#define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd)) /* to find an entry in a page-table-directory */ #define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) @@ -253,46 +521,151 @@ /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) -/* Find an entry in the second-level page table.. */ -#ifndef CONFIG_ARM64_64K_PAGES -#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr); + const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | + PTE_PROT_NONE | PTE_VALID | PTE_WRITE; + /* preserve the hardware dirty information */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); + return pte; +} + +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); +} + +#ifdef CONFIG_ARM64_HW_AFDBM +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } #endif -/* Find an entry in the third-level page table.. */ -#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +/* + * Atomic pte/pmd modifications. + */ +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + pteval_t pteval; + unsigned int tmp, res; + + asm volatile("// ptep_test_and_clear_young\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " ubfx %w3, %w0, %5, #1 // extract PTE_AF (young)\n" + " and %0, %0, %4 // clear PTE_AF\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res) + : "L" (~PTE_AF), "I" (ilog2(PTE_AF))); -static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) + return res; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) { - const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID; - pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); - return pte; + return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + pteval_t old_pteval; + unsigned int tmp; + + asm volatile("// ptep_get_and_clear\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " stxr %w1, xzr, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))); + + return __pte(old_pteval); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +/* + * ptep_set_wrprotect - mark read-only while trasferring potential hardware + * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. + */ +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) +{ + pteval_t pteval; + unsigned long tmp; + + asm volatile("// ptep_set_wrprotect\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " tst %0, %4 // check for hw dirty (!PTE_RDONLY)\n" + " csel %1, %3, xzr, eq // set PTE_DIRTY|PTE_RDONLY if dirty\n" + " orr %0, %0, %1 // if !dirty, PTE_RDONLY is already set\n" + " and %0, %0, %5 // clear PTE_WRITE/PTE_DBM\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)) + : "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE) + : "cc"); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + ptep_set_wrprotect(mm, address, (pte_t *)pmdp); +} +#endif +#endif /* CONFIG_ARM64_HW_AFDBM */ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; -#define SWAPPER_DIR_SIZE (3 * PAGE_SIZE) -#define IDMAP_DIR_SIZE (2 * PAGE_SIZE) - /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) - * bit 2: PTE_FILE - * bits 3-8: swap type - * bits 9-63: swap offset + * bits 2-7: swap type + * bits 8-57: swap offset + * bit 58: PTE_PROT_NONE (must be zero) */ -#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_SHIFT 2 #define __SWP_TYPE_BITS 6 +#define __SWP_OFFSET_BITS 50 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) +#define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) -#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT) +#define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK) #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) @@ -300,34 +673,33 @@ /* * Ensure that there are not more swap files than can be encoded in the kernel - * the PTEs. + * PTEs. */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) -/* - * Encode and decode a file entry: - * bits 0-1: present (must be zero) - * bit 2: PTE_FILE - * bits 3-63: file offset / PAGE_SIZE - */ -#define pte_file(pte) (pte_val(pte) & PTE_FILE) -#define pte_to_pgoff(x) (pte_val(x) >> 3) -#define pgoff_to_pte(x) __pte(((x) << 3) | PTE_FILE) - -#define PTE_FILE_MAX_BITS 61 - extern int kern_addr_valid(unsigned long addr); #include +#define pgtable_cache_init() do { } while (0) + /* - * remap a physical page `pfn' of size `size' with page protection `prot' - * into virtual address `from' + * On AArch64, the cache coherency is handled via the set_pte_at() function. */ -#define io_remap_pfn_range(vma,from,pfn,size,prot) \ - remap_pfn_range(vma, from, pfn, size, prot) +static inline void update_mmu_cache(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + /* + * We don't do anything here, so there's a very small chance of + * us retaking a user fault which we just fixed up. The alternative + * is doing a dsb(ishst), but that penalises the fastpath. + */ +} -#define pgtable_cache_init() do { } while (0) +#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) + +#define kc_vaddr_to_offset(v) ((v) & ~VA_START) +#define kc_offset_to_vaddr(o) ((o) | VA_START) #endif /* !__ASSEMBLY__ */