// SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> #include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/fixmap.h> #include <asm/mtrr.h> #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK phys_addr_t physical_mask __ro_after_init = …; EXPORT_SYMBOL(…); #endif #ifdef CONFIG_HIGHPTE #define PGTABLE_HIGHMEM … #else #define PGTABLE_HIGHMEM … #endif #ifndef CONFIG_PARAVIRT static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) { tlb_remove_page(tlb, table); } #endif gfp_t __userpte_alloc_gfp = …; pgtable_t pte_alloc_one(struct mm_struct *mm) { … } static int __init setup_userpte(char *arg) { … } early_param(…); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { … } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { … } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { … } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { … } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ static inline void pgd_list_add(pgd_t *pgd) { … } static inline void pgd_list_del(pgd_t *pgd) { … } #define UNSHARED_PTRS_PER_PGD … #define MAX_UNSHARED_PTRS_PER_PGD … static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) { … } struct mm_struct *pgd_page_get_mm(struct page *page) { … } static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) { … } static void pgd_dtor(pgd_t *pgd) { … } /* * List of all pgd's needed for non-PAE so it can invalidate entries * in both cached and uncached pgd's; not needed for PAE since the * kernel pmd is shared. If PAE were not to share the pmd a similar * tactic would be needed. This is essentially codepath-based locking * against pageattr.c; it is the unique case in which a valid change * of kernel pagetables can't be lazily synchronized by vmalloc faults. * vmalloc faults work because attached pagetables are never freed. * -- nyc */ #ifdef CONFIG_X86_PAE /* * In PAE mode, we need to do a cr3 reload (=tlb flush) when * updating the top-level pagetable entries to guarantee the * processor notices the update. Since this is expensive, and * all 4 top-level entries are used almost immediately in a * new process's life, we just pre-populate them here. * * Also, if we're in a paravirt environment where the kernel pmd is * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate * and initialize the kernel pmds here. */ #define PREALLOCATED_PMDS … #define MAX_PREALLOCATED_PMDS … /* * We allocate separate PMDs for the kernel part of the user page-table * when PTI is enabled. We need them to map the per-process LDT into the * user-space page-table. */ #define PREALLOCATED_USER_PMDS … #define MAX_PREALLOCATED_USER_PMDS … void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); /* Note: almost everything apart from _PAGE_PRESENT is reserved at the pmd (PDPT) level. */ set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); /* * According to Intel App note "TLBs, Paging-Structure Caches, * and Their Invalidation", April 2007, document 317080-001, * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS … #define MAX_PREALLOCATED_PMDS … #define PREALLOCATED_USER_PMDS … #define MAX_PREALLOCATED_USER_PMDS … #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { … } static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { … } /* * Mop up any pmd pages which may still be attached to the pgd. * Normally they will be freed by munmap/exit_mmap, but any pmd we * preallocate which never got a corresponding vma will need to be * freed manually. */ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) { … } static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { … } static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { … } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { … } #else static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { } #endif /* * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also * assumes that pgd should be in one page. * * But kernel with PAE paging that is not running as a Xen domain * only needs to allocate 32 bytes for pgd instead of one page. */ #ifdef CONFIG_X86_PAE #include <linux/slab.h> #define PGD_SIZE … #define PGD_ALIGN … static struct kmem_cache *pgd_cache; void __init pgtable_cache_init(void) { /* * When PAE kernel is running as a Xen domain, it does not use * shared kernel pmd. And this requires a whole page for pgd. */ if (!SHARED_KERNEL_PMD) return; /* * when PAE kernel is not running as a Xen domain, it uses * shared kernel pmd. Shared kernel pmd does not require a whole * page for pgd. We are able to just allocate a 32-byte for pgd. * During boot time, we create a 32-byte slab for pgd table allocation. */ pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, SLAB_PANIC, NULL); } static inline pgd_t *_pgd_alloc(void) { /* * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate * a 32-byte slab for pgd to save memory space. */ return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } static inline void _pgd_free(pgd_t *pgd) { if (!SHARED_KERNEL_PMD) free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); else kmem_cache_free(pgd_cache, pgd); } #else static inline pgd_t *_pgd_alloc(void) { … } static inline void _pgd_free(pgd_t *pgd) { … } #endif /* CONFIG_X86_PAE */ pgd_t *pgd_alloc(struct mm_struct *mm) { … } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { … } /* * Used to set accessed or dirty bits in the page table entries * on other architectures. On x86, the accessed and dirty bits * are tracked by hardware. However, do_wp_page calls this function * to also make the pte writeable at the same time the dirty bit is * set. In that case we do actually need to write the PTE. */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { … } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { … } int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { … } #endif int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { … } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { … } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp) { … } #endif int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { … } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { … } pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { … } #endif /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve * * Can be used to relocate the fixmap area and poke a hole in the top * of kernel address space to make room for a hypervisor. */ void __init reserve_top_address(unsigned long reserve) { … } int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { … } void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { … } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifdef CONFIG_X86_5LEVEL /** * p4d_set_huge - setup kernel P4D mapping * * No 512GB pages yet -- always return 0 */ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { … } /** * p4d_clear_huge - clear kernel P4D mapping when it is set * * No 512GB pages yet -- always return 0 */ void p4d_clear_huge(p4d_t *p4d) { … } #endif /** * pud_set_huge - setup kernel PUD mapping * * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this * function sets up a huge page only if the complete range has the same MTRR * caching mode. * * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger * page mapping attempt fails. * * Returns 1 on success and 0 on failure. */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { … } /** * pmd_set_huge - setup kernel PMD mapping * * See text over pud_set_huge() above. * * Returns 1 on success and 0 on failure. */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { … } /** * pud_clear_huge - clear kernel PUD mapping when it is set * * Returns 1 on success and 0 on failure (no PUD map is found). */ int pud_clear_huge(pud_t *pud) { … } /** * pmd_clear_huge - clear kernel PMD mapping when it is set * * Returns 1 on success and 0 on failure (no PMD map is found). */ int pmd_clear_huge(pmd_t *pmd) { … } #ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. * @addr: Virtual address associated with pud. * * Context: The pud range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. * * NOTE: Callers must allow a single page allocation. */ int pud_free_pmd_page(pud_t *pud, unsigned long addr) { … } /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. * @addr: Virtual address associated with pmd. * * Context: The pmd range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { … } #else /* !CONFIG_X86_64 */ /* * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd pmd entries. See vmalloc_sync_one(). */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } #endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { … } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { … } void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { … } void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { … }
Codebase Browser
linux