From 07037db5d479f90377c998259a4f9a469c404edf Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Mon, 10 Jul 2017 18:06:09 -0700 Subject: RISC-V: Paging and MMU This patch contains code to manage the RISC-V MMU, including definitions of the page tables and the page walking code. Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/pgtable.h | 430 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 430 insertions(+) create mode 100644 arch/riscv/include/asm/pgtable.h (limited to 'arch/riscv/include/asm/pgtable.h') diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h new file mode 100644 index 000000000000..3399257780b2 --- /dev/null +++ b/arch/riscv/include/asm/pgtable.h @@ -0,0 +1,430 @@ +/* + * Copyright (C) 2012 Regents of the University of California + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ASM_RISCV_PGTABLE_H +#define _ASM_RISCV_PGTABLE_H + +#include + +#include + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_MMU + +/* Page Upper Directory not used in RISC-V */ +#include +#include +#include +#include + +#ifdef CONFIG_64BIT +#include +#else +#include +#endif /* CONFIG_64BIT */ + +/* Number of entries in the page global directory */ +#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t)) +/* Number of entries in the page table */ +#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) + +/* Number of PGD entries that a user-mode program can use */ +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) +#define FIRST_USER_ADDRESS 0 + +/* Page protection bits */ +#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER) + +#define PAGE_NONE __pgprot(0) +#define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ) +#define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE) +#define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC) +#define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) +#define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \ + _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_SHARED PAGE_WRITE +#define PAGE_SHARED_EXEC PAGE_WRITE_EXEC + +#define _PAGE_KERNEL (_PAGE_READ \ + | _PAGE_WRITE \ + | _PAGE_PRESENT \ + | _PAGE_ACCESSED \ + | _PAGE_DIRTY) + +#define PAGE_KERNEL __pgprot(_PAGE_KERNEL) +#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) + +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 + +/* + * ZERO_PAGE is a global shared page that is always zero, + * used for zero-mapped memory areas, etc. + */ +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) + +static inline int pmd_present(pmd_t pmd) +{ + return (pmd_val(pmd) & _PAGE_PRESENT); +} + +static inline int pmd_none(pmd_t pmd) +{ + return (pmd_val(pmd) == 0); +} + +static inline int pmd_bad(pmd_t pmd) +{ + return !pmd_present(pmd); +} + +static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + *pmdp = pmd; +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + set_pmd(pmdp, __pmd(0)); +} + + +static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot) +{ + return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); +} + +#define pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) + +/* Locate an entry in the page global directory */ +static inline pgd_t *pgd_offset(const struct mm_struct *mm, unsigned long addr) +{ + return mm->pgd + pgd_index(addr); +} +/* Locate an entry in the kernel page global directory */ +#define pgd_offset_k(addr) pgd_offset(&init_mm, (addr)) + +static inline struct page *pmd_page(pmd_t pmd) +{ + return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); +} + +static inline unsigned long pmd_page_vaddr(pmd_t pmd) +{ + return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); +} + +/* Yields the page frame number (PFN) of a page table entry */ +static inline unsigned long pte_pfn(pte_t pte) +{ + return (pte_val(pte) >> _PAGE_PFN_SHIFT); +} + +#define pte_page(x) pfn_to_page(pte_pfn(x)) + +/* Constructs a page table entry */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) +{ + return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); +} + +static inline pte_t mk_pte(struct page *page, pgprot_t prot) +{ + return pfn_pte(page_to_pfn(page), prot); +} + +#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + +static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr) +{ + return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(addr); +} + +#define pte_offset_map(dir, addr) pte_offset_kernel((dir), (addr)) +#define pte_unmap(pte) ((void)(pte)) + +/* + * Certain architectures need to do special things when PTEs within + * a page table are directly modified. Thus, the following hook is + * made available. + */ +static inline void set_pte(pte_t *ptep, pte_t pteval) +{ + *ptep = pteval; +} + +static inline void set_pte_at(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pteval) +{ + set_pte(ptep, pteval); +} + +static inline void pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + set_pte_at(mm, addr, ptep, __pte(0)); +} + +static inline int pte_present(pte_t pte) +{ + return (pte_val(pte) & _PAGE_PRESENT); +} + +static inline int pte_none(pte_t pte) +{ + return (pte_val(pte) == 0); +} + +/* static inline int pte_read(pte_t pte) */ + +static inline int pte_write(pte_t pte) +{ + return pte_val(pte) & _PAGE_WRITE; +} + +static inline int pte_huge(pte_t pte) +{ + return pte_present(pte) + && (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)); +} + +/* static inline int pte_exec(pte_t pte) */ + +static inline int pte_dirty(pte_t pte) +{ + return pte_val(pte) & _PAGE_DIRTY; +} + +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + +static inline int pte_special(pte_t pte) +{ + return pte_val(pte) & _PAGE_SPECIAL; +} + +/* static inline pte_t pte_rdprotect(pte_t pte) */ + +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_WRITE)); +} + +/* static inline pte_t pte_mkread(pte_t pte) */ + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_WRITE); +} + +/* static inline pte_t pte_mkexec(pte_t pte) */ + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_DIRTY)); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_ACCESSED)); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPECIAL); +} + +/* Modify page protection bits */ +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); +} + +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e)) + + +/* Commit new configuration to MMU hardware */ +static inline void update_mmu_cache(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + /* + * The kernel assumes that TLBs don't cache invalid entries, but + * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a + * cache flush; it is necessary even after writing invalid entries. + * Relying on flush_tlb_fix_spurious_fault would suffice, but + * the extra traps reduce performance. So, eagerly SFENCE.VMA. + */ + local_flush_tlb_page(address); +} + +#define __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return pte_val(pte_a) == pte_val(pte_b); +} + +#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_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + return __pte(atomic_long_xchg((atomic_long_t *)ptep, 0)); +} + +#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) +{ + atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep); +} + +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +static inline int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + /* + * This comment is borrowed from x86, but applies equally to RISC-V: + * + * Clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); +} + +/* + * Encode and decode a swap entry + * + * Format of swap PTE: + * bit 0: _PAGE_PRESENT (zero) + * bit 1: reserved for future use (zero) + * bits 2 to 6: swap type + * bits 7 to XLEN-1: swap offset + */ +#define __SWP_TYPE_SHIFT 2 +#define __SWP_TYPE_BITS 5 +#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1) +#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) + +#define MAX_SWAPFILES_CHECK() \ + BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) + +#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) }) + +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) + +#ifdef CONFIG_FLATMEM +#define kern_addr_valid(addr) (1) /* FIXME */ +#endif + +extern void paging_init(void); + +static inline void pgtable_cache_init(void) +{ + /* No page table caches to initialize */ +} + +#endif /* CONFIG_MMU */ + +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) +#define VMALLOC_END (PAGE_OFFSET - 1) +#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) + +/* + * Task size is 0x40000000000 for RV64 or 0xb800000 for RV32. + * Note that PGDIR_SIZE must evenly divide TASK_SIZE. + */ +#ifdef CONFIG_64BIT +#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2) +#else +#define TASK_SIZE VMALLOC_START +#endif + +#include + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_RISCV_PGTABLE_H */ -- cgit v1.2.3