diff options
Diffstat (limited to 'arch/powerpc/include/asm/book3s/64/radix.h')
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/radix.h | 146 |
1 files changed, 112 insertions, 34 deletions
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 7d1a3d1543fc..da954e779744 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -4,7 +4,7 @@ #include <asm/asm-const.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/cmpxchg.h> #endif @@ -14,7 +14,7 @@ #include <asm/book3s/64/radix-4k.h> #endif -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/book3s/64/tlbflush-radix.h> #include <asm/cpu_has_feature.h> #endif @@ -30,11 +30,16 @@ /* Don't have anything in the reserved bits and leaf bits */ #define RADIX_PMD_BAD_BITS 0x60000000000000e0UL #define RADIX_PUD_BAD_BITS 0x60000000000000e0UL -#define RADIX_PGD_BAD_BITS 0x60000000000000e0UL +#define RADIX_P4D_BAD_BITS 0x60000000000000e0UL #define RADIX_PMD_SHIFT (PAGE_SHIFT + RADIX_PTE_INDEX_SIZE) #define RADIX_PUD_SHIFT (RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE) #define RADIX_PGD_SHIFT (RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE) + +#define R_PTRS_PER_PTE (1 << RADIX_PTE_INDEX_SIZE) +#define R_PTRS_PER_PMD (1 << RADIX_PMD_INDEX_SIZE) +#define R_PTRS_PER_PUD (1 << RADIX_PUD_INDEX_SIZE) + /* * Size of EA range mapped by our pagetables. */ @@ -68,23 +73,21 @@ * * * 3rd quadrant expanded: - * +------------------------------+ - * | | - * | | - * | | - * +------------------------------+ Kernel IO map end (0xc010000000000000) + * +------------------------------+ Highest address (0xc010000000000000) + * +------------------------------+ KASAN shadow end (0xc00fc00000000000) * | | * | | - * | 1/2 of virtual map | + * +------------------------------+ Kernel vmemmap end/shadow start (0xc00e000000000000) * | | + * | 512TB | * | | - * +------------------------------+ Kernel IO map start + * +------------------------------+ Kernel IO map end/vmemap start * | | - * | 1/4 of virtual map | + * | 512TB | * | | - * +------------------------------+ Kernel vmemap start + * +------------------------------+ Kernel vmap end/ IO map start * | | - * | 1/4 of virtual map | + * | 512TB | * | | * +------------------------------+ Kernel virt start (0xc008000000000000) * | | @@ -93,26 +96,43 @@ * +------------------------------+ Kernel linear (0xc.....) */ -#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) -#define RADIX_KERN_VIRT_SIZE ASM_CONST(0x0008000000000000) +/* For the sizes of the shadow area, see kasan.h */ /* - * The vmalloc space starts at the beginning of that region, and - * occupies a quarter of it on radix config. - * (we keep a quarter for the virtual memmap) + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 */ -#define RADIX_VMALLOC_START RADIX_KERN_VIRT_START -#define RADIX_VMALLOC_SIZE (RADIX_KERN_VIRT_SIZE >> 2) -#define RADIX_VMALLOC_END (RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE) + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define R_MAX_PHYSMEM_BITS 51 +#else +#define R_MAX_PHYSMEM_BITS 46 +#endif + +#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) /* - * Defines the address of the vmemap area, in its own region on - * hash table CPUs. + * 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick + * the same value as hash. */ -#define RADIX_VMEMMAP_BASE (RADIX_VMALLOC_END) +#define RADIX_KERN_MAP_SIZE (1UL << 49) + +#define RADIX_VMALLOC_START RADIX_KERN_VIRT_START +#define RADIX_VMALLOC_SIZE RADIX_KERN_MAP_SIZE +#define RADIX_VMALLOC_END (RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE) + +#define RADIX_KERN_IO_START RADIX_VMALLOC_END +#define RADIX_KERN_IO_SIZE RADIX_KERN_MAP_SIZE +#define RADIX_KERN_IO_END (RADIX_KERN_IO_START + RADIX_KERN_IO_SIZE) -#define RADIX_KERN_IO_START (RADIX_KERN_VIRT_START + (RADIX_KERN_VIRT_SIZE >> 1)) +#define RADIX_VMEMMAP_START RADIX_KERN_IO_END +#define RADIX_VMEMMAP_SIZE RADIX_KERN_MAP_SIZE +#define RADIX_VMEMMAP_END (RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define RADIX_PTE_TABLE_SIZE (sizeof(pte_t) << RADIX_PTE_INDEX_SIZE) #define RADIX_PMD_TABLE_SIZE (sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE) #define RADIX_PUD_TABLE_SIZE (sizeof(pud_t) << RADIX_PUD_INDEX_SIZE) @@ -127,6 +147,10 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep pte_t entry, unsigned long address, int psize); +extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte); + static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr, unsigned long set) { @@ -204,8 +228,10 @@ static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr, * from ptesync, it should probably go into update_mmu_cache, rather * than set_pte_at (which is used to set ptes unrelated to faults). * - * Spurious faults to vmalloc region are not tolerated, so there is - * a ptesync in flush_cache_vmap. + * Spurious faults from the kernel memory are not tolerated, so there + * is a ptesync in flush_cache_vmap, and __map_kernel_page() follows + * the pte update sequence from ISA Book III 6.10 Translation Table + * Update Synchronization Requirements. */ } @@ -224,17 +250,21 @@ static inline int radix__pud_bad(pud_t pud) return !!(pud_val(pud) & RADIX_PUD_BAD_BITS); } +static inline int radix__pud_same(pud_t pud_a, pud_t pud_b) +{ + return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0); +} -static inline int radix__pgd_bad(pgd_t pgd) +static inline int radix__p4d_bad(p4d_t p4d) { - return !!(pgd_val(pgd) & RADIX_PGD_BAD_BITS); + return !!(p4d_val(p4d) & RADIX_P4D_BAD_BITS); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int radix__pmd_trans_huge(pmd_t pmd) { - return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE; + return (pmd_val(pmd) & _PAGE_PTE) == _PAGE_PTE; } static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) @@ -242,9 +272,22 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) return __pmd(pmd_val(pmd) | _PAGE_PTE); } +static inline int radix__pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & _PAGE_PTE) == _PAGE_PTE; +} + +static inline pud_t radix__pud_mkhuge(pud_t pud) +{ + return __pud(pud_val(pud) | _PAGE_PTE); +} + extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set); +extern unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set); extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, @@ -252,12 +295,35 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); -extern int radix__has_transparent_hugepage(void); +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp); + +static inline int radix__has_transparent_hugepage(void) +{ + /* For radix 2M at PMD level means thp */ + if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT) + return 1; + return 0; +} + +static inline int radix__has_transparent_pud_hugepage(void) +{ + /* For radix 1G at PUD level means pud hugepage support */ + if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_SHIFT) + return 1; + return 0; +} #endif +struct vmem_altmap; +struct dev_pagemap; extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap); extern void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size); @@ -281,8 +347,20 @@ static inline unsigned long radix__get_tree_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int radix__create_section_mapping(unsigned long start, unsigned long end, int nid); +int radix__create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); int radix__remove_section_mapping(unsigned long start, unsigned long end); #endif /* CONFIG_MEMORY_HOTPLUG */ -#endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +#define vmemmap_can_optimize vmemmap_can_optimize +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +#endif + +#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap); +#endif /* __ASSEMBLER__ */ #endif |