From 6778948f9de86c3cfaf36725a7c87dcff9ba247f Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Mon, 11 Dec 2023 08:20:59 +0000 Subject: [PATCH] kernel_5.10 no rt --- kernel/include/linux/huge_mm.h | 287 +++++++++++++++++++++++++++++++++++++++++---------------- 1 files changed, 205 insertions(+), 82 deletions(-) diff --git a/kernel/include/linux/huge_mm.h b/kernel/include/linux/huge_mm.h index becf9b1..1764571 100644 --- a/kernel/include/linux/huge_mm.h +++ b/kernel/include/linux/huge_mm.h @@ -7,49 +7,78 @@ #include <linux/fs.h> /* only for vma_is_dax() */ -extern vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); -extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma); -extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); -extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pud_t *dst_pud, pud_t *src_pud, unsigned long addr, - struct vm_area_struct *vma); +vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); +int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); +void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); +int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); +void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif -extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); -extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags); -extern bool madvise_free_huge_pmd(struct mmu_gather *tlb, - struct vm_area_struct *vma, - pmd_t *pmd, unsigned long addr, unsigned long next); -extern int zap_huge_pmd(struct mmu_gather *tlb, - struct vm_area_struct *vma, - pmd_t *pmd, unsigned long addr); -extern int zap_huge_pud(struct mmu_gather *tlb, - struct vm_area_struct *vma, - pud_t *pud, unsigned long addr); -extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec); -extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd); -extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot, - int prot_numa); -vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); -vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); +struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags); +bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next); +int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr); +int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, + unsigned long addr); +bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); +int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, + pgprot_t newprot, unsigned long cp_flags); +vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, + pgprot_t pgprot, bool write); + +/** + * vmf_insert_pfn_pmd - insert a pmd size pfn + * @vmf: Structure describing the fault + * @pfn: pfn to insert + * @pgprot: page protection to use + * @write: whether it's a write fault + * + * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. + * + * Return: vm_fault_t value. + */ +static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, + bool write) +{ + return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); +} +vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, + pgprot_t pgprot, bool write); + +/** + * vmf_insert_pfn_pud - insert a pud size pfn + * @vmf: Structure describing the fault + * @pfn: pfn to insert + * @pgprot: page protection to use + * @write: whether it's a write fault + * + * Insert a pud size pfn. See vmf_insert_pfn() for additional info. + * + * Return: vm_fault_t value. + */ +static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, + bool write) +{ + return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); +} + enum transparent_hugepage_flag { + TRANSPARENT_HUGEPAGE_NEVER_DAX, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, @@ -66,13 +95,13 @@ struct kobject; struct kobj_attribute; -extern ssize_t single_hugepage_flag_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count, - enum transparent_hugepage_flag flag); -extern ssize_t single_hugepage_flag_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf, - enum transparent_hugepage_flag flag); +ssize_t single_hugepage_flag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count, + enum transparent_hugepage_flag flag); +ssize_t single_hugepage_flag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf, + enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) @@ -87,23 +116,50 @@ #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) -extern bool is_vma_temporary_stack(struct vm_area_struct *vma); - extern unsigned long transparent_hugepage_flags; + +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + /* Don't have to check pgoff for anonymous vma */ + if (!vma_is_anonymous(vma)) { + if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR)) + return false; + } + + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + return true; +} /* * to be used on vmas which are known to support THP. - * Use transparent_hugepage_enabled otherwise + * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { - if (vma->vm_flags & VM_NOHUGEPAGE) + + /* + * If the hardware/firmware marked hugepage support disabled. + */ + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; - if (is_vma_temporary_stack(vma)) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; - if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (vma_is_temporary_stack(vma)) return false; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) @@ -119,25 +175,18 @@ return false; } -bool transparent_hugepage_enabled(struct vm_area_struct *vma); +bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) -#ifdef CONFIG_DEBUG_VM -#define transparent_hugepage_debug_cow() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG)) -#else /* CONFIG_DEBUG_VM */ -#define transparent_hugepage_debug_cow() 0 -#endif /* CONFIG_DEBUG_VM */ -extern unsigned long thp_get_unmapped_area(struct file *filp, - unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags); +unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags); -extern void prep_transhuge_page(struct page *page); -extern void free_transhuge_page(struct page *page); +void prep_transhuge_page(struct page *page); +void free_transhuge_page(struct page *page); +bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); @@ -174,27 +223,22 @@ __split_huge_pud(__vma, __pud, __address); \ } while (0) -extern int hugepage_madvise(struct vm_area_struct *vma, - unsigned long *vm_flags, int advice); -extern void vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - long adjust_next); -extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, - struct vm_area_struct *vma); -extern spinlock_t *__pud_trans_huge_lock(pud_t *pud, - struct vm_area_struct *vma); +int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, + int advice); +void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, + unsigned long end, long adjust_next); +spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); +spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { return !pmd_none(pmd) && !pmd_present(pmd); } -/* mmap_sem must be held on entry */ +/* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { - VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else @@ -203,25 +247,51 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { - VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } -static inline int hpage_nr_pages(struct page *page) + +/** + * thp_head - Head page of a transparent huge page. + * @page: Any page (tail, head or regular) found in the page cache. + */ +static inline struct page *thp_head(struct page *page) { - if (unlikely(PageTransHuge(page))) + return compound_head(page); +} + +/** + * thp_order - Order of a transparent huge page. + * @page: Head page of a transparent huge page. + */ +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + if (PageHead(page)) + return HPAGE_PMD_ORDER; + return 0; +} + +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + if (PageHead(page)) return HPAGE_PMD_NR; return 1; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); -extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; @@ -251,6 +321,15 @@ return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } +static inline struct list_head *page_deferred_list(struct page *page) +{ + /* + * Global or memcg deferred list in the second tail pages is + * occupied by compound_head. + */ + return &page[2].deferred_list; +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -260,19 +339,52 @@ #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) -#define hpage_nr_pages(x) 1 +static inline struct page *thp_head(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return page; +} + +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return 0; +} + +static inline int thp_nr_pages(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return 1; +} static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; } -static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool transparent_hugepage_active(struct vm_area_struct *vma) +{ + return false; +} + +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + return false; +} + +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) { return false; } static inline void prep_transhuge_page(struct page *page) {} + +static inline bool is_transparent_hugepage(struct page *page) +{ + return false; +} #define transparent_hugepage_flags 0UL @@ -359,13 +471,13 @@ } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } @@ -376,4 +488,15 @@ } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +/** + * thp_size - Size of a transparent huge page. + * @page: Head page of a transparent huge page. + * + * Return: Number of bytes in this page. + */ +static inline unsigned long thp_size(struct page *page) +{ + return PAGE_SIZE << thp_order(page); +} + #endif /* _LINUX_HUGE_MM_H */ -- Gitblit v1.6.2