From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Mon, 11 Dec 2023 02:45:28 +0000 Subject: [PATCH] add boot partition size --- kernel/include/linux/hugetlb.h | 517 +++++++++++++++++++++++++++++++++++++++++++++++---------- 1 files changed, 427 insertions(+), 90 deletions(-) diff --git a/kernel/include/linux/hugetlb.h b/kernel/include/linux/hugetlb.h index cb7dc38..25a24db 100644 --- a/kernel/include/linux/hugetlb.h +++ b/kernel/include/linux/hugetlb.h @@ -9,35 +9,19 @@ #include <linux/cgroup.h> #include <linux/list.h> #include <linux/kref.h> -#include <asm/pgtable.h> +#include <linux/pgtable.h> +#include <linux/gfp.h> +#include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; struct mmu_gather; #ifndef is_hugepd -/* - * Some architectures requires a hugepage directory format that is - * required to support multiple hugepage sizes. For example - * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" - * introduced the same on powerpc. This allows for a more flexible hugepage - * pagetable layout. - */ typedef struct { unsigned long pd; } hugepd_t; #define is_hugepd(hugepd) (0) #define __hugepd(x) ((hugepd_t) { (x) }) -static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr) -{ - return 0; -} -#else -extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr); #endif - #ifdef CONFIG_HUGETLB_PAGE @@ -64,7 +48,52 @@ long adds_in_progress; struct list_head region_cache; long region_cache_count; +#ifdef CONFIG_CGROUP_HUGETLB + /* + * On private mappings, the counter to uncharge reservations is stored + * here. If these fields are 0, then either the mapping is shared, or + * cgroup accounting is disabled for this resv_map. + */ + struct page_counter *reservation_counter; + unsigned long pages_per_hpage; + struct cgroup_subsys_state *css; +#endif }; + +/* + * Region tracking -- allows tracking of reservations and instantiated pages + * across the pages in a mapping. + * + * The region data structures are embedded into a resv_map and protected + * by a resv_map's lock. The set of regions within the resv_map represent + * reservations for huge pages, or huge pages that have already been + * instantiated within the map. The from and to elements are huge page + * indicies into the associated mapping. from indicates the starting index + * of the region. to represents the first index past the end of the region. + * + * For example, a file region structure with from == 0 and to == 4 represents + * four huge pages in a mapping. It is important to note that the to element + * represents the first element past the end of the region. This is used in + * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. + * + * Interval notation of the form [from, to) will be used to indicate that + * the endpoint from is inclusive and to is exclusive. + */ +struct file_region { + struct list_head link; + long from; + long to; +#ifdef CONFIG_CGROUP_HUGETLB + /* + * On shared mappings, each reserved region appears as a struct + * file_region in resv_map. These fields hold the info needed to + * uncharge each reservation. + */ + struct page_counter *reservation_counter; + struct cgroup_subsys_state *css; +#endif +}; + extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -78,14 +107,13 @@ void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); - -#ifdef CONFIG_NUMA -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -#endif +int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, @@ -102,16 +130,19 @@ unsigned long start, unsigned long end, struct page *ref_page); void hugetlb_report_meminfo(struct seq_file *); -int hugetlb_report_node_meminfo(int, char *); +int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); +#ifdef CONFIG_USERFAULTFD int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep); +#endif /* CONFIG_USERFAULTFD */ int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); @@ -123,21 +154,24 @@ void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx); +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud); + +struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages; /* arch callbacks */ -pte_t *huge_pte_alloc(struct mm_struct *mm, +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -145,8 +179,8 @@ struct page *follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags); +struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, + int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, @@ -158,6 +192,7 @@ unsigned long address, unsigned long end, pgprot_t newprot); bool is_hugetlb_entry_migration(pte_t pte); +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -170,8 +205,15 @@ return 0; } -static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, - pte_t *ptep) +static inline struct address_space *hugetlb_page_mapping_lock_write( + struct page *hpage) +{ + return NULL; +} + +static inline int huge_pmd_unshare(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { return 0; } @@ -182,39 +224,133 @@ { } -#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) -#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) -#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) +static inline long follow_hugetlb_page(struct mm_struct *mm, + struct vm_area_struct *vma, struct page **pages, + struct vm_area_struct **vmas, unsigned long *position, + unsigned long *nr_pages, long i, unsigned int flags, + int *nonblocking) +{ + BUG(); + return 0; +} + +static inline struct page *follow_huge_addr(struct mm_struct *mm, + unsigned long address, int write) +{ + return ERR_PTR(-EINVAL); +} + +static inline int copy_hugetlb_page_range(struct mm_struct *dst, + struct mm_struct *src, struct vm_area_struct *vma) +{ + BUG(); + return 0; +} + static inline void hugetlb_report_meminfo(struct seq_file *m) { } -#define hugetlb_report_node_meminfo(n, buf) 0 + +static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) +{ + return 0; +} + static inline void hugetlb_show_meminfo(void) { } -#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL -#define follow_huge_pmd(mm, addr, pmd, flags) NULL -#define follow_huge_pud(mm, addr, pud, flags) NULL -#define follow_huge_pgd(mm, addr, pgd, flags) NULL -#define prepare_hugepage_range(file, addr, len) (-EINVAL) -#define pmd_huge(x) 0 -#define pud_huge(x) 0 -#define is_hugepage_only_range(mm, addr, len) 0 -#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) -#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) -#define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ - src_addr, pagep) ({ BUG(); 0; }) -#define huge_pte_offset(mm, address, sz) 0 + +static inline struct page *follow_huge_pd(struct vm_area_struct *vma, + unsigned long address, hugepd_t hpd, int flags, + int pdshift) +{ + return NULL; +} + +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) +{ + return NULL; +} + +static inline struct page *follow_huge_pud(struct mm_struct *mm, + unsigned long address, pud_t *pud, int flags) +{ + return NULL; +} + +static inline struct page *follow_huge_pgd(struct mm_struct *mm, + unsigned long address, pgd_t *pgd, int flags) +{ + return NULL; +} + +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + return -EINVAL; +} + +static inline int pmd_huge(pmd_t pmd) +{ + return 0; +} + +static inline int pud_huge(pud_t pud) +{ + return 0; +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + BUG(); +} + +#ifdef CONFIG_USERFAULTFD +static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + enum mcopy_atomic_mode mode, + struct page **pagep) +{ + BUG(); + return 0; +} +#endif /* CONFIG_USERFAULTFD */ + +static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, + unsigned long sz) +{ + return NULL; +} static inline bool isolate_huge_page(struct page *page, struct list_head *list) { return false; } -#define putback_active_hugepage(p) do {} while (0) -#define move_hugetlb_state(old, new, reason) do {} while (0) -static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot) +static inline void putback_active_hugepage(struct page *page) +{ +} + +static inline void move_hugetlb_state(struct page *oldpage, + struct page *newpage, int reason) +{ +} + +static inline unsigned long hugetlb_change_protection( + struct vm_area_struct *vma, unsigned long address, + unsigned long end, pgprot_t newprot) { return 0; } @@ -232,6 +368,16 @@ { BUG(); } + +static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + unsigned int flags) +{ + BUG(); + return 0; +} + +static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ /* @@ -310,7 +456,10 @@ return is_file_shm_hugepages(file); } - +static inline struct hstate *hstate_inode(struct inode *i) +{ + return HUGETLBFS_SB(i->i_sb)->hstate; +} #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false @@ -322,6 +471,10 @@ return ERR_PTR(-ENOSYS); } +static inline struct hstate *hstate_inode(struct inode *i) +{ + return NULL; +} #endif /* !CONFIG_HUGETLBFS */ #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA @@ -352,7 +505,8 @@ unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files[5]; + struct cftype cgroup_files_dfl[7]; + struct cftype cgroup_files_legacy[9]; #endif char name[HSTATE_NAME_LEN]; }; @@ -364,9 +518,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); -struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask); + nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, @@ -376,8 +529,8 @@ int __init __alloc_bootmem_huge_page(struct hstate *h); int __init alloc_bootmem_huge_page(struct hstate *h); -void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); +bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE @@ -388,11 +541,6 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) - -static inline struct hstate *hstate_inode(struct inode *i) -{ - return HUGETLBFS_SB(i->i_sb)->hstate; -} static inline struct hstate *hstate_file(struct file *f) { @@ -453,6 +601,20 @@ #include <asm/hugetlb.h> +#ifndef is_hugepage_only_range +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} +#define is_hugepage_only_range is_hugepage_only_range +#endif + +#ifndef arch_clear_hugepage_flags +static inline void arch_clear_hugepage_flags(struct page *page) { } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) @@ -464,7 +626,7 @@ static inline struct hstate *page_hstate(struct page *page) { VM_BUG_ON_PAGE(!PageHuge(page), page); - return size_to_hstate(PAGE_SIZE << compound_order(page)); + return size_to_hstate(page_size(page)); } static inline unsigned hstate_index_to_shift(unsigned index) @@ -480,17 +642,75 @@ extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -static inline bool hugepage_migration_supported(struct hstate *h) -{ + #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +#ifndef arch_hugetlb_migration_supported +static inline bool arch_hugetlb_migration_supported(struct hstate *h) +{ if ((huge_page_shift(h) == PMD_SHIFT) || - (huge_page_shift(h) == PGDIR_SHIFT)) + (huge_page_shift(h) == PUD_SHIFT) || + (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; -#else - return false; +} #endif +#else +static inline bool arch_hugetlb_migration_supported(struct hstate *h) +{ + return false; +} +#endif + +static inline bool hugepage_migration_supported(struct hstate *h) +{ + return arch_hugetlb_migration_supported(h); +} + +/* + * Movability check is different as compared to migration check. + * It determines whether or not a huge page should be placed on + * movable zone or not. Movability of any huge page should be + * required only if huge page size is supported for migration. + * There wont be any reason for the huge page to be movable if + * it is not migratable to start with. Also the size of the huge + * page should be large enough to be placed under a movable zone + * and still feasible enough to be migratable. Just the presence + * in movable zone does not make the migration feasible. + * + * So even though large huge page sizes like the gigantic ones + * are migratable they should not be movable because its not + * feasible to migrate them from movable zone. + */ +static inline bool hugepage_movable_supported(struct hstate *h) +{ + if (!hugepage_migration_supported(h)) + return false; + + if (hstate_is_gigantic(h)) + return false; + return true; +} + +/* Movability of hugepages depends on migration support. */ +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + if (hugepage_movable_supported(h)) + return GFP_HIGHUSER_MOVABLE; + else + return GFP_HIGHUSER; +} + +static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) +{ + gfp_t modified_mask = htlb_alloc_mask(h); + + /* Some callers might want to enforce node */ + modified_mask |= (gfp_mask & __GFP_THISNODE); + + modified_mask |= (gfp_mask & __GFP_NOWARN); + + return modified_mask; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, @@ -536,26 +756,106 @@ } #endif +#ifndef huge_ptep_modify_prot_start +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} +#endif + +#ifndef huge_ptep_modify_prot_commit +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} +#endif + void set_page_huge_active(struct page *page); #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; -#define alloc_huge_page(v, a, r) NULL -#define alloc_huge_page_node(h, nid) NULL -#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL -#define alloc_huge_page_vma(h, vma, address) NULL -#define alloc_bootmem_huge_page(h) NULL -#define hstate_file(f) NULL -#define hstate_sizelog(s) NULL -#define hstate_vma(v) NULL -#define hstate_inode(i) NULL -#define page_hstate(page) NULL -#define huge_page_size(h) PAGE_SIZE -#define huge_page_mask(h) PAGE_MASK -#define vma_kernel_pagesize(v) PAGE_SIZE -#define vma_mmu_pagesize(v) PAGE_SIZE -#define huge_page_order(h) 0 -#define huge_page_shift(h) PAGE_SHIFT + +static inline struct page *alloc_huge_page(struct vm_area_struct *vma, + unsigned long addr, + int avoid_reserve) +{ + return NULL; +} + +static inline struct page * +alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) +{ + return NULL; +} + +static inline struct page *alloc_huge_page_vma(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address) +{ + return NULL; +} + +static inline int __alloc_bootmem_huge_page(struct hstate *h) +{ + return 0; +} + +static inline struct hstate *hstate_file(struct file *f) +{ + return NULL; +} + +static inline struct hstate *hstate_sizelog(int page_size_log) +{ + return NULL; +} + +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline struct hstate *page_hstate(struct page *page) +{ + return NULL; +} + +static inline unsigned long huge_page_size(struct hstate *h) +{ + return PAGE_SIZE; +} + +static inline unsigned long huge_page_mask(struct hstate *h) +{ + return PAGE_MASK; +} + +static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) +{ + return PAGE_SIZE; +} + +static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) +{ + return PAGE_SIZE; +} + +static inline unsigned int huge_page_order(struct hstate *h) +{ + return 0; +} + +static inline unsigned int huge_page_shift(struct hstate *h) +{ + return PAGE_SHIFT; +} + static inline bool hstate_is_gigantic(struct hstate *h) { return false; @@ -592,6 +892,21 @@ return false; } +static inline bool hugepage_movable_supported(struct hstate *h) +{ + return false; +} + +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + return 0; +} + +static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) +{ + return 0; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -626,4 +941,26 @@ return ptl; } +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) +extern void __init hugetlb_cma_reserve(int order); +extern void __init hugetlb_cma_check(void); +#else +static inline __init void hugetlb_cma_reserve(int order) +{ +} +static inline __init void hugetlb_cma_check(void) +{ +} +#endif + +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); + +#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +/* + * ARCHes with special requirements for evicting HUGETLB backing TLB entries can + * implement this. + */ +#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#endif + #endif /* _LINUX_HUGETLB_H */ -- Gitblit v1.6.2