diff options
Diffstat (limited to 'arch/arm64/include/asm/pgtable.h')
| -rw-r--r-- | arch/arm64/include/asm/pgtable.h | 384 |
1 files changed, 298 insertions, 86 deletions
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index afdd56d26ad7..d3b538be1500 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,6 +34,7 @@ #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> @@ -49,12 +50,6 @@ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline bool arch_thp_swp_supported(void) -{ - return !system_supports_mte(); -} -#define arch_thp_swp_supported arch_thp_swp_supported - /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page @@ -73,10 +68,6 @@ 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) { @@ -89,8 +80,15 @@ 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) @@ -105,7 +103,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) /* * The following only work if pte_present(). Undefined behaviour otherwise. */ -#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) +#define pte_present(pte) (pte_valid(pte) || pte_present_invalid(pte)) #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)) @@ -132,6 +130,8 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) +#define pte_present_invalid(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID) /* * Execute-only user mappings do not have the PTE_USER bit set. All valid * kernel mappings have the PTE_UXN bit set. @@ -153,6 +153,24 @@ 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 @@ -160,8 +178,11 @@ 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) \ @@ -247,8 +268,7 @@ 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) @@ -256,11 +276,18 @@ 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)); } +static inline pte_t pte_mkinvalid(pte_t pte) +{ + pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID)); + pte = clear_pte_bit(pte, __pgprot(PTE_VALID)); + return pte; +} + static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); @@ -271,9 +298,31 @@ static inline pte_t pte_mkdevmap(pte_t pte) return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); } -static inline void __set_pte(pte_t *ptep, pte_t pte) +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline int pte_uffd_wp(pte_t pte) +{ + return !!(pte_val(pte) & PTE_UFFD_WP); +} + +static inline pte_t pte_mkuffd_wp(pte_t pte) +{ + return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP))); +} + +static inline pte_t pte_clear_uffd_wp(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP)); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +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) +{ + __set_pte_nosync(ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance @@ -291,7 +340,7 @@ 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 @@ -348,10 +397,11 @@ 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); } @@ -359,6 +409,7 @@ 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); @@ -390,11 +441,6 @@ static inline void __set_ptes(struct mm_struct *mm, } /* - * Huge pte definitions. - */ -#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) - -/* * Hugetlb definitions. */ #define HUGE_MAX_HSTATE 4 @@ -440,12 +486,12 @@ 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) @@ -463,39 +509,48 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } -#ifdef CONFIG_NUMA_BALANCING -/* - * See the comment in include/linux/pgtable.h - */ -static inline int pte_protnone(pte_t pte) +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { - return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE; + return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } -static inline int pmd_protnone(pmd_t pmd) +static inline int pte_swp_uffd_wp(pte_t pte) { - return pte_protnone(pmd_pte(pmd)); + return !!(pte_val(pte) & PTE_SWP_UFFD_WP); } -#endif - -#define pmd_present_invalid(pmd) (!!(pmd_val(pmd) & PMD_PRESENT_INVALID)) -static inline int pmd_present(pmd_t pmd) +static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { - return pte_present(pmd_pte(pmd)) || pmd_present_invalid(pmd); + return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ +#ifdef CONFIG_NUMA_BALANCING /* - * THP definitions. + * See the comment in include/linux/pgtable.h */ +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 + * 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 + * being PROT_NONE. + */ + return pte_present_invalid(pte) && !pte_user(pte) && !pte_user_exec(pte); +} -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_huge(pmd_t pmd) +static inline int pmd_protnone(pmd_t pmd) { - return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); + return pte_protnone(pmd_pte(pmd)); } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif +#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_valid(pmd) pte_valid(pmd_pte(pmd)) @@ -508,21 +563,32 @@ static inline int pmd_trans_huge(pmd_t pmd) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(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_mkinvalid(pmd) pte_pmd(pte_mkinvalid(pmd_pte(pmd))) +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +#define pmd_uffd_wp(pmd) pte_uffd_wp(pmd_pte(pmd)) +#define pmd_mkuffd_wp(pmd) pte_pmd(pte_mkuffd_wp(pmd_pte(pmd))) +#define pmd_clear_uffd_wp(pmd) pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd))) +#define pmd_swp_uffd_wp(pmd) pte_swp_uffd_wp(pmd_pte(pmd)) +#define pmd_swp_mkuffd_wp(pmd) pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd))) +#define pmd_swp_clear_uffd_wp(pmd) \ + pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +#define pmd_write(pmd) pte_write(pmd_pte(pmd)) -static inline pmd_t pmd_mkinvalid(pmd_t pmd) +static inline pmd_t pmd_mkhuge(pmd_t pmd) { - pmd = set_pmd_bit(pmd, __pgprot(PMD_PRESENT_INVALID)); - pmd = clear_pmd_bit(pmd, __pgprot(PMD_SECT_VALID)); + /* + * 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; - return pmd; + return __pmd((pmd_val(pmd) & ~mask) | val); } -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) - -#define pmd_write(pmd) pte_write(pmd_pte(pmd)) - -#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) - #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) #endif @@ -531,6 +597,14 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); } +#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 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) @@ -541,13 +615,40 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) #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)) +#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_pte_at(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) @@ -585,6 +686,11 @@ 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. */ @@ -626,6 +732,18 @@ 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_val(pmd) && 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; } @@ -707,9 +825,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) 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)) +#else +#define pud_leaf(pud) false +#endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) @@ -760,6 +883,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #else +#define pud_valid(pud) false #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) #define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ @@ -793,7 +917,9 @@ 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) @@ -823,6 +949,9 @@ 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); } @@ -917,7 +1046,9 @@ 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) @@ -947,6 +1078,9 @@ 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); } @@ -1005,6 +1139,8 @@ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) static inline bool pgtable_l5_enabled(void) { return false; } +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + /* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ #define p4d_set_fixmap(addr) NULL #define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) @@ -1012,6 +1148,28 @@ 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) \ @@ -1027,8 +1185,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK. */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP | - PTE_ATTRINDX_MASK; + PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | + 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)); @@ -1076,17 +1235,17 @@ static inline int pgd_devmap(pgd_t pgd) #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { - return pte_present(pte) && (pte_user(pte) || pte_user_exec(pte)); + return pte_valid(pte) && (pte_user(pte) || pte_user_exec(pte)); } static inline bool pmd_user_accessible_page(pmd_t pmd) { - return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); + return pmd_valid(pmd) && !pmd_table(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { - return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud)); + return pud_valid(pud) && !pud_table(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif @@ -1130,15 +1289,17 @@ 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) @@ -1209,7 +1370,7 @@ 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, @@ -1227,6 +1388,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, __ptep_set_wrprotect(mm, address, ptep); } +static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, cydp_t flags) +{ + pte_t old_pte; + + do { + old_pte = pte; + + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + + pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), + pte_val(old_pte), pte_val(pte)); + } while (pte_val(pte) != pte_val(old_pte)); +} + +static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + pte = __ptep_get(ptep); + + if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) + __set_pte(ptep, pte_mkclean(pte_mkold(pte))); + else + __clear_young_dirty_pte(vma, addr, ptep, pte, flags); + + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, @@ -1248,15 +1449,16 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, * Encode and decode a swap entry: * bits 0-1: present (must be zero) * bits 2: remember PG_anon_exclusive - * bits 3-7: swap type - * bits 8-57: swap offset - * bit 58: PTE_PROT_NONE (must be zero) + * bit 3: remember uffd-wp state + * bits 6-10: swap type + * bit 11: PTE_PRESENT_INVALID (must be zero) + * bits 12-61: swap offset */ -#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_SHIFT 6 #define __SWP_TYPE_BITS 5 -#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_SHIFT 12 +#define __SWP_OFFSET_BITS 50 #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) @@ -1280,12 +1482,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) -{ - if (system_supports_mte()) - return mte_save_tags(page); - return 0; -} +extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) @@ -1301,11 +1498,7 @@ static inline void arch_swap_invalidate_area(int type) } #define __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) -{ - if (system_supports_mte()) - mte_restore_tags(entry, &folio->page); -} +extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ @@ -1341,6 +1534,10 @@ 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. @@ -1392,6 +1589,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); +extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -1616,6 +1816,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } +#define clear_young_dirty_ptes clear_young_dirty_ptes +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); + else + contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); +} + #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get @@ -1635,6 +1846,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags +#define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ |