diff options
Diffstat (limited to 'arch/arm64/include/asm/pgtable.h')
| -rw-r--r-- | arch/arm64/include/asm/pgtable.h | 497 |
1 files changed, 356 insertions, 141 deletions
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index f8efbc128446..64d5f1d9cce9 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -30,15 +30,95 @@ #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <asm/cmpxchg.h> #include <asm/fixmap.h> +#include <asm/por.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <linux/page_table_check.h> +static inline void emit_pte_barriers(void) +{ + /* + * These barriers are emitted under certain conditions after a pte entry + * was modified (see e.g. __set_pte_complete()). The dsb makes the store + * visible to the table walker. The isb ensures that any previous + * speculative "invalid translation" marker that is in the CPU's + * pipeline gets cleared, so that any access to that address after + * setting the pte to valid won't cause a spurious fault. If the thread + * gets preempted after storing to the pgtable but before emitting these + * barriers, __switch_to() emits a dsb which ensure the walker gets to + * see the store. There is no guarantee of an isb being issued though. + * This is safe because it will still get issued (albeit on a + * potentially different CPU) when the thread starts running again, + * before any access to the address. + */ + dsb(ishst); + isb(); +} + +static inline void queue_pte_barriers(void) +{ + unsigned long flags; + + if (in_interrupt()) { + emit_pte_barriers(); + return; + } + + flags = read_thread_flags(); + + if (flags & BIT(TIF_LAZY_MMU)) { + /* Avoid the atomic op if already set. */ + if (!(flags & BIT(TIF_LAZY_MMU_PENDING))) + set_thread_flag(TIF_LAZY_MMU_PENDING); + } else { + emit_pte_barriers(); + } +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE +static inline void arch_enter_lazy_mmu_mode(void) +{ + /* + * lazy_mmu_mode is not supposed to permit nesting. But in practice this + * does happen with CONFIG_DEBUG_PAGEALLOC, where a page allocation + * inside a lazy_mmu_mode section (such as zap_pte_range()) will change + * permissions on the linear map with apply_to_page_range(), which + * re-enters lazy_mmu_mode. So we tolerate nesting in our + * implementation. The first call to arch_leave_lazy_mmu_mode() will + * flush and clear the flag such that the remainder of the work in the + * outer nest behaves as if outside of lazy mmu mode. This is safe and + * keeps tracking simple. + */ + + if (in_interrupt()) + return; + + set_thread_flag(TIF_LAZY_MMU); +} + +static inline void arch_flush_lazy_mmu_mode(void) +{ + if (in_interrupt()) + return; + + if (test_and_clear_thread_flag(TIF_LAZY_MMU_PENDING)) + emit_pte_barriers(); +} + +static inline void arch_leave_lazy_mmu_mode(void) +{ + if (in_interrupt()) + return; + + arch_flush_lazy_mmu_mode(); + clear_thread_flag(TIF_LAZY_MMU); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE @@ -50,12 +130,16 @@ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * Outside of a few very special situations (e.g. hibernation), we always - * use broadcast TLB invalidation instructions, therefore a spurious page - * fault on one CPU which has been handled concurrently by another CPU - * does not need to perform additional invalidation. + * We use local TLB invalidation instruction when reusing page in + * write protection fault handler to avoid TLBI broadcast in the hot + * path. This will cause spurious page faults if stale read-only TLB + * entries exist. */ -#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) \ + local_flush_tlb_page_nonotify(vma, address) + +#define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp) \ + local_flush_tlb_page_nonotify(vma, address) /* * ZERO_PAGE is a global shared page that is always zero: used @@ -67,10 +151,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e)) -/* - * Macros to convert between a physical address and its placement in a - * page table entry, taking care of 52-bit addresses. - */ #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { @@ -83,8 +163,15 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else -#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) -#define __phys_to_pte_val(phys) (phys) +static inline phys_addr_t __pte_to_phys(pte_t pte) +{ + return pte_val(pte) & PTE_ADDR_LOW; +} + +static inline pteval_t __phys_to_pte_val(phys_addr_t phys) +{ + return phys; +} #endif #define pte_pfn(pte) (__pte_to_phys(pte) >> PAGE_SHIFT) @@ -107,7 +194,6 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) -#define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) #define pte_tagged(pte) ((pte_val(pte) & PTE_ATTRINDX_MASK) == \ PTE_ATTRINDX(MT_NORMAL_TAGGED)) @@ -149,6 +235,24 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) +static inline bool por_el0_allows_pkey(u8 pkey, bool write, bool execute) +{ + u64 por; + + if (!system_supports_poe()) + return true; + + por = read_sysreg_s(SYS_POR_EL0); + + if (write) + return por_elx_allows_write(por, pkey); + + if (execute) + return por_elx_allows_exec(por, pkey); + + return por_elx_allows_read(por, pkey); +} + /* * p??_access_permitted() is true for valid user mappings (PTE_USER * bit set, subject to the write permission check). For execute-only @@ -156,8 +260,11 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) * not set) must return false. PROT_NONE mappings do not have the * PTE_VALID bit set. */ -#define pte_access_permitted(pte, write) \ +#define pte_access_permitted_no_overlay(pte, write) \ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte))) +#define pte_access_permitted(pte, write) \ + (pte_access_permitted_no_overlay(pte, write) && \ + por_el0_allows_pkey(FIELD_GET(PTE_PO_IDX_MASK, pte_val(pte)), write, false)) #define pmd_access_permitted(pmd, write) \ (pte_access_permitted(pmd_pte(pmd), (write))) #define pud_access_permitted(pud, write) \ @@ -190,7 +297,8 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); + if (pte_sw_dirty(pte)) + pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } @@ -243,8 +351,7 @@ static inline pte_t pte_mkspecial(pte_t pte) static inline pte_t pte_mkcont(pte_t pte) { - pte = set_pte_bit(pte, __pgprot(PTE_CONT)); - return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); + return set_pte_bit(pte, __pgprot(PTE_CONT)); } static inline pte_t pte_mknoncont(pte_t pte) @@ -252,7 +359,7 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } -static inline pte_t pte_mkpresent(pte_t pte) +static inline pte_t pte_mkvalid(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } @@ -269,9 +376,9 @@ static inline pmd_t pmd_mkcont(pmd_t pmd) return __pmd(pmd_val(pmd) | PMD_SECT_CONT); } -static inline pte_t pte_mkdevmap(pte_t pte) +static inline pmd_t pmd_mknoncont(pmd_t pmd) { - return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); + return __pmd(pmd_val(pmd) & ~PMD_SECT_CONT); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP @@ -296,18 +403,20 @@ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte) WRITE_ONCE(*ptep, pte); } -static inline void __set_pte(pte_t *ptep, pte_t pte) +static inline void __set_pte_complete(pte_t pte) { - __set_pte_nosync(ptep, pte); - /* * Only if the new pte is valid and kernel, otherwise TLB maintenance - * or update_mmu_cache() have the necessary barriers. + * has the necessary barriers. */ - if (pte_valid_not_user(pte)) { - dsb(ishst); - isb(); - } + if (pte_valid_not_user(pte)) + queue_pte_barriers(); +} + +static inline void __set_pte(pte_t *ptep, pte_t pte) +{ + __set_pte_nosync(ptep, pte); + __set_pte_complete(pte); } static inline pte_t __ptep_get(pte_t *ptep) @@ -316,7 +425,7 @@ static inline pte_t __ptep_get(pte_t *ptep) } extern void __sync_icache_dcache(pte_t pteval); -bool pgattr_change_is_safe(u64 old, u64 new); +bool pgattr_change_is_safe(pteval_t old, pteval_t new); /* * PTE bits configuration in the presence of hardware Dirty Bit Management @@ -328,7 +437,7 @@ bool pgattr_change_is_safe(u64 old, u64 new); * 1 0 | 1 0 1 * 1 1 | 0 1 x * - * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via + * When hardware DBM is not present, the software PTE_DIRTY bit is updated via * the page fault mechanism. Checking the dirty status of a pte becomes: * * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) @@ -373,10 +482,11 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) /* * If the PTE would provide user space access to the tags associated * with it then ensure that the MTE tags are synchronised. Although - * pte_access_permitted() returns false for exec only mappings, they - * don't expose tags (instruction fetches don't check tags). + * pte_access_permitted_no_overlay() returns false for exec only + * mappings, they don't expose tags (instruction fetches don't check + * tags). */ - if (system_supports_mte() && pte_access_permitted(pte, false) && + if (system_supports_mte() && pte_access_permitted_no_overlay(pte, false) && !pte_special(pte) && pte_tagged(pte)) mte_sync_tags(pte, nr_pages); } @@ -384,6 +494,7 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) /* * Select all bits except the pfn */ +#define pte_pgprot pte_pgprot static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pfn = pte_pfn(pte); @@ -397,28 +508,6 @@ static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte)); } -static inline void __set_ptes(struct mm_struct *mm, - unsigned long __always_unused addr, - pte_t *ptep, pte_t pte, unsigned int nr) -{ - page_table_check_ptes_set(mm, ptep, pte, nr); - __sync_cache_and_tags(pte, nr); - - for (;;) { - __check_safe_pte_update(mm, ptep, pte); - __set_pte(ptep, pte); - if (--nr == 0) - break; - ptep++; - pte = pte_advance_pfn(pte, 1); - } -} - -/* - * Huge pte definitions. - */ -#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) - /* * Hugetlb definitions. */ @@ -465,12 +554,12 @@ static inline pmd_t pte_pmd(pte_t pte) static inline pgprot_t mk_pud_sect_prot(pgprot_t prot) { - return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT); + return __pgprot((pgprot_val(prot) & ~PUD_TYPE_MASK) | PUD_TYPE_SECT); } static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) { - return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); + return __pgprot((pgprot_val(prot) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT); } static inline pte_t pte_swp_mkexclusive(pte_t pte) @@ -478,7 +567,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte) return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } -static inline int pte_swp_exclusive(pte_t pte) +static inline bool pte_swp_exclusive(pte_t pte) { return pte_val(pte) & PTE_SWP_EXCLUSIVE; } @@ -514,7 +603,7 @@ static inline int pte_protnone(pte_t pte) /* * pte_present_invalid() tells us that the pte is invalid from HW * perspective but present from SW perspective, so the fields are to be - * interpretted as per the HW layout. The second 2 checks are the unique + * interpreted as per the HW layout. The second 2 checks are the unique * encoding that we use for PROT_NONE. It is insufficient to only use * the first check because we share the same encoding scheme with pmds * which support pmd_mkinvalid(), so can be present-invalid without @@ -530,18 +619,6 @@ static inline int pmd_protnone(pmd_t pmd) #endif #define pmd_present(pmd) pte_present(pmd_pte(pmd)) - -/* - * THP definitions. - */ - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_huge(pmd_t pmd) -{ - return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); -} -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) @@ -567,57 +644,128 @@ static inline int pmd_trans_huge(pmd_t pmd) #define pmd_write(pmd) pte_write(pmd_pte(pmd)) -#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + /* + * It's possible that the pmd is present-invalid on entry + * and in that case it needs to remain present-invalid on + * exit. So ensure the VALID bit does not get modified. + */ + pmdval_t mask = PMD_TYPE_MASK & ~PTE_VALID; + pmdval_t val = PMD_TYPE_SECT & ~PTE_VALID; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) -#endif -static inline pmd_t pmd_mkdevmap(pmd_t pmd) + return __pmd((pmd_val(pmd) & ~mask) | val); +} + +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +#define pmd_special(pte) (!!((pmd_val(pte) & PTE_SPECIAL))) +static inline pmd_t pmd_mkspecial(pmd_t pmd) { - return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); + return set_pmd_bit(pmd, __pgprot(PTE_SPECIAL)); } +#endif #define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd)) #define __phys_to_pmd_val(phys) __phys_to_pte_val(phys) #define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT) #define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) -#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) #define pud_young(pud) pte_young(pud_pte(pud)) #define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) -#define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT)) +static inline pud_t pud_mkhuge(pud_t pud) +{ + /* + * It's possible that the pud is present-invalid on entry + * and in that case it needs to remain present-invalid on + * exit. So ensure the VALID bit does not get modified. + */ + pudval_t mask = PUD_TYPE_MASK & ~PTE_VALID; + pudval_t val = PUD_TYPE_SECT & ~PTE_VALID; + + return __pud((pud_val(pud) & ~mask) | val); +} #define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud)) #define __phys_to_pud_val(phys) __phys_to_pte_val(phys) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) -static inline void __set_pte_at(struct mm_struct *mm, - unsigned long __always_unused addr, - pte_t *ptep, pte_t pte, unsigned int nr) +#define pmd_pgprot pmd_pgprot +static inline pgprot_t pmd_pgprot(pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + return __pgprot(pmd_val(pfn_pmd(pfn, __pgprot(0))) ^ pmd_val(pmd)); +} + +#define pud_pgprot pud_pgprot +static inline pgprot_t pud_pgprot(pud_t pud) +{ + unsigned long pfn = pud_pfn(pud); + + return __pgprot(pud_val(pfn_pud(pfn, __pgprot(0))) ^ pud_val(pud)); +} + +static inline void __set_ptes_anysz(struct mm_struct *mm, pte_t *ptep, + pte_t pte, unsigned int nr, + unsigned long pgsize) +{ + unsigned long stride = pgsize >> PAGE_SHIFT; + + switch (pgsize) { + case PAGE_SIZE: + page_table_check_ptes_set(mm, ptep, pte, nr); + break; + case PMD_SIZE: + page_table_check_pmds_set(mm, (pmd_t *)ptep, pte_pmd(pte), nr); + break; +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + page_table_check_puds_set(mm, (pud_t *)ptep, pte_pud(pte), nr); + break; +#endif + default: + VM_WARN_ON(1); + } + + __sync_cache_and_tags(pte, nr * stride); + + for (;;) { + __check_safe_pte_update(mm, ptep, pte); + __set_pte_nosync(ptep, pte); + if (--nr == 0) + break; + ptep++; + pte = pte_advance_pfn(pte, stride); + } + + __set_pte_complete(pte); +} + +static inline void __set_ptes(struct mm_struct *mm, + unsigned long __always_unused addr, + pte_t *ptep, pte_t pte, unsigned int nr) { - __sync_cache_and_tags(pte, nr); - __check_safe_pte_update(mm, ptep, pte); - __set_pte(ptep, pte); + __set_ptes_anysz(mm, ptep, pte, nr, PAGE_SIZE); } -static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, pmd_t pmd) +static inline void __set_pmds(struct mm_struct *mm, + unsigned long __always_unused addr, + pmd_t *pmdp, pmd_t pmd, unsigned int nr) { - page_table_check_pmd_set(mm, pmdp, pmd); - return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd), - PMD_SIZE >> PAGE_SHIFT); + __set_ptes_anysz(mm, (pte_t *)pmdp, pmd_pte(pmd), nr, PMD_SIZE); } +#define set_pmd_at(mm, addr, pmdp, pmd) __set_pmds(mm, addr, pmdp, pmd, 1) -static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, - pud_t *pudp, pud_t pud) +static inline void __set_puds(struct mm_struct *mm, + unsigned long __always_unused addr, + pud_t *pudp, pud_t pud, unsigned int nr) { - page_table_check_pud_set(mm, pudp, pud); - return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud), - PUD_SIZE >> PAGE_SHIFT); + __set_ptes_anysz(mm, (pte_t *)pudp, pud_pte(pud), nr, PUD_SIZE); } +#define set_pud_at(mm, addr, pudp, pud) __set_puds(mm, addr, pudp, pud, 1) #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) @@ -631,6 +779,11 @@ static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, #define pgprot_nx(prot) \ __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) +#define pgprot_decrypted(prot) \ + __pgprot_modify(prot, PROT_NS_SHARED, PROT_NS_SHARED) +#define pgprot_encrypted(prot) \ + __pgprot_modify(prot, PROT_NS_SHARED, 0) + /* * Mark the prot value as uncacheable and unbufferable. */ @@ -672,6 +825,17 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) #define pte_leaf_size(pte) (pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + /* + * If pmd is present-invalid, pmd_table() won't detect it + * as a table, so force the valid bit for the comparison. + */ + return pmd_present(pmd) && !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID)); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 static inline bool pud_sect(pud_t pud) { return false; } static inline bool pud_table(pud_t pud) { return true; } @@ -682,8 +846,6 @@ static inline bool pud_table(pud_t pud) { return true; } PUD_TYPE_TABLE) #endif -extern pgd_t init_pg_dir[]; -extern pgd_t init_pg_end[]; extern pgd_t swapper_pg_dir[]; extern pgd_t idmap_pg_dir[]; extern pgd_t tramp_pg_dir[]; @@ -708,10 +870,8 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) WRITE_ONCE(*pmdp, pmd); - if (pmd_valid(pmd)) { - dsb(ishst); - isb(); - } + if (pmd_valid(pmd)) + queue_pte_barriers(); } static inline void pmd_clear(pmd_t *pmdp) @@ -741,19 +901,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) /* use ONLY for statically allocated translation tables */ #define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr)))) -/* - * Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - */ -#define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot) - #if CONFIG_PGTABLE_LEVELS > 2 #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) (!pud_table(pud)) +#define pud_bad(pud) ((pud_val(pud) & PUD_TYPE_MASK) != \ + PUD_TYPE_TABLE) #define pud_present(pud) pte_present(pud_pte(pud)) #ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) @@ -775,10 +930,8 @@ static inline void set_pud(pud_t *pudp, pud_t pud) WRITE_ONCE(*pudp, pud); - if (pud_valid(pud)) { - dsb(ishst); - isb(); - } + if (pud_valid(pud)) + queue_pte_barriers(); } static inline void pud_clear(pud_t *pudp) @@ -844,7 +997,9 @@ static inline bool mm_pud_folded(const struct mm_struct *mm) pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) -#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && \ + ((p4d_val(p4d) & P4D_TYPE_MASK) != \ + P4D_TYPE_TABLE)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) @@ -855,8 +1010,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) } WRITE_ONCE(*p4dp, p4d); - dsb(ishst); - isb(); + queue_pte_barriers(); } static inline void p4d_clear(p4d_t *p4dp) @@ -874,6 +1028,9 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d) static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) { + /* Ensure that 'p4dp' indexes a page table according to 'addr' */ + VM_BUG_ON(((addr >> P4D_SHIFT) ^ ((u64)p4dp >> 3)) % PTRS_PER_P4D); + return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); } @@ -968,7 +1125,9 @@ static inline bool mm_p4d_folded(const struct mm_struct *mm) pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) -#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && \ + ((pgd_val(pgd) & PGD_TYPE_MASK) != \ + PGD_TYPE_TABLE)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) @@ -979,8 +1138,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) } WRITE_ONCE(*pgdp, pgd); - dsb(ishst); - isb(); + queue_pte_barriers(); } static inline void pgd_clear(pgd_t *pgdp) @@ -998,6 +1156,9 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd) static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) { + /* Ensure that 'pgdp' indexes a page table according to 'addr' */ + VM_BUG_ON(((addr >> PGDIR_SHIFT) ^ ((u64)pgdp >> 3)) % PTRS_PER_PGD); + return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); } @@ -1065,6 +1226,28 @@ static inline bool pgtable_l5_enabled(void) { return false; } #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) +static inline +p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr) +{ + /* + * With runtime folding of the pud, pud_offset_lockless() passes + * the 'pgd_t *' we return here to p4d_to_folded_pud(), which + * will offset the pointer assuming that it points into + * a page-table page. However, the fast GUP path passes us a + * pgd_t allocated on the stack and so we must use the original + * pointer in 'pgdp' to construct the p4d pointer instead of + * using the generic p4d_offset_lockless() implementation. + * + * Note: reusing the original pointer means that we may + * dereference the same (live) page-table entry multiple times. + * This is safe because it is still only loaded once in the + * context of each level and the CPU guarantees same-address + * read-after-read ordering. + */ + return p4d_offset(pgdp, addr); +} +#define p4d_offset_lockless p4d_offset_lockless_folded + #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ @@ -1081,7 +1264,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | - PTE_GP | PTE_ATTRINDX_MASK; + PTE_GP | PTE_ATTRINDX_MASK | PTE_PO_IDX_MASK; + /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); @@ -1114,16 +1298,6 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma, return __ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } - -static inline int pud_devmap(pud_t pud) -{ - return 0; -} - -static inline int pgd_devmap(pgd_t pgd) -{ - return 0; -} #endif #ifdef CONFIG_PAGE_TABLE_CHECK @@ -1183,26 +1357,49 @@ static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, return young; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) #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) { + /* Operation applies to PMD table entry only if FEAT_HAFT is enabled */ + VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft()); return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ -static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, - unsigned long address, pte_t *ptep) +static inline pte_t __ptep_get_and_clear_anysz(struct mm_struct *mm, + pte_t *ptep, + unsigned long pgsize) { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); - page_table_check_pte_clear(mm, pte); + switch (pgsize) { + case PAGE_SIZE: + page_table_check_pte_clear(mm, pte); + break; + case PMD_SIZE: + page_table_check_pmd_clear(mm, pte_pmd(pte)); + break; +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + page_table_check_pud_clear(mm, pte_pud(pte)); + break; +#endif + default: + VM_WARN_ON(1); + } return pte; } +static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + return __ptep_get_and_clear_anysz(mm, ptep, PAGE_SIZE); +} + static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { @@ -1239,11 +1436,7 @@ static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm, static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); - - page_table_check_pmd_clear(mm, pmd); - - return pmd; + return pte_pmd(__ptep_get_and_clear_anysz(mm, (pte_t *)pmdp, PMD_SIZE)); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -1262,7 +1455,7 @@ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, } /* - * __ptep_set_wrprotect - mark read-only while trasferring potential hardware + * __ptep_set_wrprotect - mark read-only while transferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, @@ -1426,12 +1619,24 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf, */ #define arch_has_hw_pte_young cpu_has_hw_af +#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG +#define arch_has_hw_nonleaf_pmd_young system_supports_haft +#endif + /* * Experimentally, it's cheap to set the access flag in hardware and we * benefit from prefaulting mappings as 'old' to start with. */ #define arch_wants_old_prefaulted_pte cpu_has_hw_af +/* + * Request exec memory is read into pagecache in at least 64K folios. This size + * can be contpte-mapped when 4K base pages are in use (16 pages into 1 iTLB + * entry), and HPA can coalesce it (4 pages into 1 TLB entry) when 16K base + * pages are in use. + */ +#define exec_folio_order() ilog2(SZ_64K >> PAGE_SHIFT) + static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; @@ -1448,6 +1653,16 @@ extern void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t new_pte); +#define modify_prot_start_ptes modify_prot_start_ptes +extern pte_t modify_prot_start_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr); + +#define modify_prot_commit_ptes modify_prot_commit_ptes +extern void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte, + unsigned int nr); + #ifdef CONFIG_ARM64_CONTPTE /* @@ -1738,6 +1953,6 @@ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, #endif /* CONFIG_ARM64_CONTPTE */ -#endif /* !__ASSEMBLY__ */ +#endif /* !__ASSEMBLER__ */ #endif /* __ASM_PGTABLE_H */ |