diff options
Diffstat (limited to 'arch/riscv/include/asm/pgtable.h')
| -rw-r--r-- | arch/riscv/include/asm/pgtable.h | 246 |
1 files changed, 158 insertions, 88 deletions
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 5dbd6610729b..20242402fc11 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -31,7 +31,7 @@ #define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) /* - * Half of the kernel address space (half of the entries of the page global + * Half of the kernel address space (1/4 of the entries of the page global * directory) is for the direct mapping. */ #define KERN_VIRT_SIZE ((PTRS_PER_PGD / 2 * PGDIR_SIZE) / 2) @@ -62,11 +62,16 @@ * struct pages to map half the virtual address space. Then * position vmemmap directly below the VMALLOC region. */ +#define VA_BITS_SV32 32 #ifdef CONFIG_64BIT +#define VA_BITS_SV39 39 +#define VA_BITS_SV48 48 +#define VA_BITS_SV57 57 + #define VA_BITS (pgtable_l5_enabled ? \ - 57 : (pgtable_l4_enabled ? 48 : 39)) + VA_BITS_SV57 : (pgtable_l4_enabled ? VA_BITS_SV48 : VA_BITS_SV39)) #else -#define VA_BITS 32 +#define VA_BITS VA_BITS_SV32 #endif #define VMEMMAP_SHIFT \ @@ -79,7 +84,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -87,9 +92,13 @@ #define FIXADDR_TOP PCI_IO_START #ifdef CONFIG_64BIT -#define FIXADDR_SIZE PMD_SIZE +#define MAX_FDT_SIZE PMD_SIZE +#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M) +#define FIXADDR_SIZE (PMD_SIZE + FIX_FDT_SIZE) #else -#define FIXADDR_SIZE PGDIR_SIZE +#define MAX_FDT_SIZE PGDIR_SIZE +#define FIX_FDT_SIZE MAX_FDT_SIZE +#define FIXADDR_SIZE (PGDIR_SIZE + FIX_FDT_SIZE) #endif #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) @@ -107,11 +116,27 @@ #include <asm/page.h> #include <asm/tlbflush.h> #include <linux/mm_types.h> +#include <asm/compat.h> #define __page_val_to_pfn(_val) (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT) #ifdef CONFIG_64BIT #include <asm/pgtable-64.h> + +#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1)) +#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1)) +#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1)) + +#ifdef CONFIG_COMPAT +#define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) +#define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39) +#define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64) +#define MMAP_MIN_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_MIN_VA_BITS_64) +#else +#define MMAP_VA_BITS ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) +#define MMAP_MIN_VA_BITS (VA_BITS_SV39) +#endif /* CONFIG_COMPAT */ + #else #include <asm/pgtable-32.h> #endif /* CONFIG_64BIT */ @@ -161,8 +186,7 @@ extern struct pt_alloc_ops pt_ops __initdata; _PAGE_EXEC | _PAGE_WRITE) #define PAGE_COPY PAGE_READ -#define PAGE_COPY_EXEC PAGE_EXEC -#define PAGE_COPY_READ_EXEC PAGE_READ_EXEC +#define PAGE_COPY_EXEC PAGE_READ_EXEC #define PAGE_SHARED PAGE_WRITE #define PAGE_SHARED_EXEC PAGE_WRITE_EXEC @@ -185,26 +209,8 @@ extern struct pt_alloc_ops pt_ops __initdata; #define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) extern pgd_t swapper_pg_dir[]; - -/* MAP_PRIVATE permissions: xwr (copy-on-write) */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READ -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_EXEC -#define __P101 PAGE_READ_EXEC -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_READ_EXEC - -/* MAP_SHARED permissions: xwr */ -#define __S000 PAGE_NONE -#define __S001 PAGE_READ -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_EXEC -#define __S101 PAGE_READ_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC +extern pgd_t trampoline_pg_dir[]; +extern pgd_t early_pg_dir[]; #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_present(pmd_t pmd) @@ -235,14 +241,14 @@ static inline int pmd_bad(pmd_t pmd) } #define pmd_leaf pmd_leaf -static inline int pmd_leaf(pmd_t pmd) +static inline bool pmd_leaf(pmd_t pmd) { return pmd_present(pmd) && (pmd_val(pmd) & _PAGE_LEAF); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void pmd_clear(pmd_t *pmdp) @@ -284,10 +290,48 @@ static inline pte_t pud_pte(pud_t pud) return __pte(pud_val(pud)); } +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#include <asm/cpufeature.h> + +static __always_inline bool has_svnapot(void) +{ + return riscv_has_extension_likely(RISCV_ISA_EXT_SVNAPOT); +} + +static inline unsigned long pte_napot(pte_t pte) +{ + return pte_val(pte) & _PAGE_NAPOT; +} + +static inline pte_t pte_mknapot(pte_t pte, unsigned int order) +{ + int pos = order - 1 + _PAGE_PFN_SHIFT; + unsigned long napot_bit = BIT(pos); + unsigned long napot_mask = ~GENMASK(pos, _PAGE_PFN_SHIFT); + + return __pte((pte_val(pte) & napot_mask) | napot_bit | _PAGE_NAPOT); +} + +#else + +static __always_inline bool has_svnapot(void) { return false; } + +static inline unsigned long pte_napot(pte_t pte) +{ + return 0; +} + +#endif /* CONFIG_RISCV_ISA_SVNAPOT */ + /* Yields the page frame number (PFN) of a page table entry */ static inline unsigned long pte_pfn(pte_t pte) { - return __page_val_to_pfn(pte_val(pte)); + unsigned long res = __page_val_to_pfn(pte_val(pte)); + + if (has_svnapot() && pte_napot(pte)) + res = res & (res - 1UL); + + return res; } #define pte_page(x) pfn_to_page(pte_pfn(x)) @@ -358,7 +402,7 @@ static inline pte_t pte_wrprotect(pte_t pte) /* static inline pte_t pte_mkread(pte_t pte) */ -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) | _PAGE_WRITE); } @@ -395,6 +439,10 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#define pte_leaf_size(pte) (pte_napot(pte) ? \ + napot_cont_size(napot_cont_order(pte)) :\ + PAGE_SIZE) + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/asm-generic/pgtable.h @@ -425,8 +473,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* Commit new configuration to MMU hardware */ -static inline void update_mmu_cache(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) { /* * The kernel assumes that TLBs don't cache invalid entries, but @@ -435,8 +484,14 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, * Relying on flush_tlb_fix_spurious_fault would suffice, but * the extra traps reduce performance. So, eagerly SFENCE.VMA. */ - local_flush_tlb_page(address); + while (nr--) + local_flush_tlb_page(address + nr * PAGE_SIZE); } +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) + +#define __HAVE_ARCH_UPDATE_MMU_TLB +#define update_mmu_tlb update_mmu_cache static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) @@ -459,13 +514,12 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) */ static inline void set_pte(pte_t *ptep, pte_t pteval) { - *ptep = pteval; + WRITE_ONCE(*ptep, pteval); } void flush_icache_pte(pte_t pte); -static inline void __set_pte_at(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pte_t pteval) +static inline void __set_pte_at(pte_t *ptep, pte_t pteval) { if (pte_present(pteval) && pte_exec(pteval)) flush_icache_pte(pteval); @@ -473,32 +527,35 @@ static inline void __set_pte_at(struct mm_struct *mm, set_pte(ptep, pteval); } -static inline void set_pte_at(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pte_t pteval) +#define PFN_PTE_SHIFT _PAGE_PFN_SHIFT + +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval, unsigned int nr) { - page_table_check_pte_set(mm, addr, ptep, pteval); - __set_pte_at(mm, addr, ptep, pteval); + page_table_check_ptes_set(mm, ptep, pteval, nr); + + for (;;) { + __set_pte_at(ptep, pteval); + if (--nr == 0) + break; + ptep++; + pte_val(pteval) += 1 << _PAGE_PFN_SHIFT; + } } +#define set_ptes set_ptes static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - __set_pte_at(mm, addr, ptep, __pte(0)); + __set_pte_at(ptep, __pte(0)); } -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -static inline int ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, - pte_t entry, int dirty) -{ - if (!pte_same(*ptep, entry)) - set_pte_at(vma->vm_mm, address, ptep, entry); - /* - * update_mmu_cache will unconditionally execute, handling both - * the case that the PTE changed and the spurious fault case. - */ - return true; -} +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* defined in mm/pgtable.c */ +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG /* defined in mm/pgtable.c */ +extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, @@ -506,21 +563,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0)); - page_table_check_pte_clear(mm, address, pte); + page_table_check_pte_clear(mm, pte); return pte; } -#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) -{ - if (!pte_young(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); -} - #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) @@ -615,11 +662,13 @@ static inline int pmd_write(pmd_t pmd) return pte_write(pmd_pte(pmd)); } +#define pmd_dirty pmd_dirty static inline int pmd_dirty(pmd_t pmd) { return pte_dirty(pmd_pte(pmd)); } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pte_young(pmd_pte(pmd)); @@ -640,9 +689,9 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pte_pmd(pte_mkyoung(pmd_pte(pmd))); } -static inline pmd_t pmd_mkwrite(pmd_t pmd) +static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { - return pte_pmd(pte_mkwrite(pmd_pte(pmd))); + return pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))); } static inline pmd_t pmd_wrprotect(pmd_t pmd) @@ -663,15 +712,15 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(mm, addr, pmdp, pmd); - return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); + page_table_check_pmd_set(mm, pmdp, pmd); + return __set_pte_at((pte_t *)pmdp, pmd_pte(pmd)); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - page_table_check_pud_set(mm, addr, pudp, pud); - return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); + page_table_check_pud_set(mm, pudp, pud); + return __set_pte_at((pte_t *)pudp, pud_pte(pud)); } #ifdef CONFIG_PAGE_TABLE_CHECK @@ -718,7 +767,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, { pmd_t pmd = __pmd(atomic_long_xchg((atomic_long_t *)pmdp, 0)); - page_table_check_pmd_clear(mm, address, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -734,22 +783,28 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd))); } + +#define pmdp_collapse_flush pmdp_collapse_flush +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * Encode and decode a swap entry + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). * * Format of swap PTE: * bit 0: _PAGE_PRESENT (zero) * bit 1 to 3: _PAGE_LEAF (zero) * bit 5: _PAGE_PROT_NONE (zero) - * bits 6 to 10: swap type - * bits 10 to XLEN-1: swap offset + * bit 6: exclusive marker + * bits 7 to 11: swap type + * bits 12 to XLEN-1: swap offset */ -#define __SWP_TYPE_SHIFT 6 +#define __SWP_TYPE_SHIFT 7 #define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) @@ -760,11 +815,27 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) #define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) \ - { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) + { (((type) & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT) | \ + ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE); +} + #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) #define __swp_entry_to_pmd(swp) __pmd((swp).val) @@ -784,21 +855,23 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32. * Note that PGDIR_SIZE must evenly divide TASK_SIZE. * Task size is: - * - 0x9fc00000 (~2.5GB) for RV32. - * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu - * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu + * - 0x9fc00000 (~2.5GB) for RV32. + * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu + * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu + * - 0x100000000000000 ( 64PB) for RV64 using SV57 mmu * * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V * Instruction Set Manual Volume II: Privileged Architecture" states that * "load and store effective addresses, which are 64bits, must have bits * 63–48 all equal to bit 47, or else a page-fault exception will occur." + * Similarly for SV57, bits 63–57 must be equal to bit 56. */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) #define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2) #ifdef CONFIG_COMPAT -#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) +#define TASK_SIZE_32 (_AC(0x80000000, UL)) #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #else @@ -816,13 +889,11 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL #define TASK_SIZE 0xffffffffUL -#define VMALLOC_START 0 +#define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE #endif /* !CONFIG_MMU */ -#define kern_addr_valid(addr) (1) /* FIXME */ - extern char _start[]; extern void *_dtb_early_va; extern uintptr_t _dtb_early_pa; @@ -834,7 +905,6 @@ extern uintptr_t _dtb_early_pa; #define dtb_early_pa _dtb_early_pa #endif /* CONFIG_XIP_KERNEL */ extern u64 satp_mode; -extern bool pgtable_l4_enabled; void paging_init(void); void misc_mem_init(void); |