diff options
Diffstat (limited to 'include/linux/hugetlb.h')
| -rw-r--r-- | include/linux/hugetlb.h | 561 |
1 files changed, 454 insertions, 107 deletions
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1e897e4168ac..8b4f93e84868 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -9,13 +9,16 @@ #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; +struct node; -#ifndef is_hugepd +#ifndef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; #define is_hugepd(hugepd) (0) #define __hugepd(x) ((hugepd_t) { (x) }) @@ -27,16 +30,36 @@ typedef struct { unsigned long pd; } hugepd_t; #include <linux/shm.h> #include <asm/tlbflush.h> +/* + * For HugeTLB page, there are more metadata to save in the struct page. But + * the head struct page cannot meet our needs, so we have to abuse other tail + * struct page to store the metadata. In order to avoid conflicts caused by + * subsequent use of more tail struct pages, we gather these discrete indexes + * of tail struct page here. + */ +enum { + SUBPAGE_INDEX_SUBPOOL = 1, /* reuse page->private */ +#ifdef CONFIG_CGROUP_HUGETLB + SUBPAGE_INDEX_CGROUP, /* reuse page->private */ + SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */ + __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD, +#endif +#ifdef CONFIG_MEMORY_FAILURE + SUBPAGE_INDEX_HWPOISON, +#endif + __NR_USED_SUBPAGE, +}; + struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ - /* both alloced and reserved pages. */ + /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ - /* sasitfy minimum size. */ + /* satisfy minimum size. */ }; struct resv_map { @@ -46,7 +69,58 @@ struct resv_map { 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 + * indices 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 +}; + +struct hugetlb_vma_lock { + struct kref refs; + struct rw_semaphore rw_sema; + struct vm_area_struct *vma; }; + extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -59,47 +133,56 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); 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 copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); +void hugetlb_dup_vma_private(struct vm_area_struct *vma); +void clear_vma_resv_huge_pages(struct vm_area_struct *vma); +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 move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len); +int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, + struct vm_area_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, unsigned long *, long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); + unsigned long, unsigned long, struct page *, + zap_flags_t); void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page); -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page); + struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); -int hugetlb_report_node_meminfo(int, char *); -void hugetlb_show_meminfo(void); +int hugetlb_report_node_meminfo(char *buf, int len, int nid); +void hugetlb_show_meminfo_node(int nid); 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, - struct page **pagep); -int hugetlb_reserve_pages(struct inode *inode, long from, long to, + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy); +#endif /* CONFIG_USERFAULTFD */ +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -bool isolate_huge_page(struct page *page, struct list_head *list); +int isolate_hugetlb(struct page *page, struct list_head *list); +int get_hwpoison_huge_page(struct page *page, bool *hugetlb); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -107,18 +190,23 @@ void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; 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); +unsigned long hugetlb_mask_last_page(struct hstate *h); +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, @@ -126,23 +214,37 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, 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, pgd_t *pgd, int flags); +void hugetlb_vma_lock_read(struct vm_area_struct *vma); +void hugetlb_vma_unlock_read(struct vm_area_struct *vma); +void hugetlb_vma_lock_write(struct vm_area_struct *vma); +void hugetlb_vma_unlock_write(struct vm_area_struct *vma); +int hugetlb_vma_trylock_write(struct vm_area_struct *vma); +void hugetlb_vma_assert_locked(struct vm_area_struct *vma); +void hugetlb_vma_lock_release(struct kref *kref); + int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot); + unsigned long address, unsigned long end, pgprot_t newprot, + unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ -static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) +{ +} + +static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } @@ -151,8 +253,15 @@ static inline unsigned long hugetlb_total_pages(void) 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; } @@ -180,7 +289,19 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm, } static inline int copy_hugetlb_page_range(struct mm_struct *dst, - struct mm_struct *src, struct vm_area_struct *vma) + struct mm_struct *src, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) +{ + BUG(); + return 0; +} + +static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, + unsigned long len) { BUG(); return 0; @@ -190,12 +311,12 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) { } -static inline int hugetlb_report_node_meminfo(int nid, char *buf) +static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } -static inline void hugetlb_show_meminfo(void) +static inline void hugetlb_show_meminfo_node(int nid) { } @@ -206,8 +327,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_huge_pmd(struct mm_struct *mm, - unsigned long address, pmd_t *pmd, int flags) +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) { return NULL; } @@ -230,6 +351,31 @@ static inline int prepare_hugepage_range(struct file *file, return -EINVAL; } +static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) +{ +} + +static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) +{ + return 1; +} + +static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) +{ +} + static inline int pmd_huge(pmd_t pmd) { return 0; @@ -253,16 +399,20 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, 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, - struct page **pagep) + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy) { BUG(); return 0; } +#endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) @@ -270,9 +420,19 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline bool isolate_huge_page(struct page *page, struct list_head *list) +static inline int isolate_hugetlb(struct page *page, struct list_head *list) { - return false; + return -EBUSY; +} + +static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + return 0; +} + +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; } static inline void putback_active_hugepage(struct page *page) @@ -286,21 +446,16 @@ static inline void move_hugetlb_state(struct page *oldpage, static inline unsigned long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, - unsigned long end, pgprot_t newprot) + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) -{ - BUG(); -} - -static inline void __unmap_hugepage_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { BUG(); } @@ -313,6 +468,8 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, return 0; } +static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } + #endif /* !CONFIG_HUGETLB_PAGE */ /* * hugepages at page global directory. If arch support @@ -379,8 +536,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, - struct user_struct **user, int creat_flags, - int page_size_log); + int creat_flags, int page_size_log); static inline bool is_file_hugepages(struct file *file) { @@ -390,18 +546,24 @@ static inline bool is_file_hugepages(struct file *file) 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 static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, - struct user_struct **user, int creat_flags, - int page_size_log) + int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } +static inline struct hstate *hstate_inode(struct inode *i) +{ + return NULL; +} #endif /* !CONFIG_HUGETLBFS */ #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA @@ -410,14 +572,106 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +unsigned long +generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); + +/* + * huegtlb page specific state flags. These flags are located in page.private + * of the hugetlb head page. Functions created via the below macros should be + * used to manipulate these flags. + * + * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at + * allocation time. Cleared when page is fully instantiated. Free + * routine checks flag to restore a reservation on error paths. + * Synchronization: Examined or modified by code that knows it has + * the only reference to page. i.e. After allocation but before use + * or when the page is being freed. + * HPG_migratable - Set after a newly allocated page is added to the page + * cache and/or page tables. Indicates the page is a candidate for + * migration. + * Synchronization: Initially set after new page allocation with no + * locking. When examined and modified during migration processing + * (isolate, migrate, putback) the hugetlb_lock is held. + * HPG_temporary - Set on a page that is temporarily allocated from the buddy + * allocator. Typically used for migration target pages when no pages + * are available in the pool. The hugetlb free page path will + * immediately free pages with this flag set to the buddy allocator. + * Synchronization: Can be set after huge page allocation from buddy when + * code knows it has only reference. All other examinations and + * modifications require hugetlb_lock. + * HPG_freed - Set when page is on the free lists. + * Synchronization: hugetlb_lock held for examination and modification. + * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. + * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page + * that is not tracked by raw_hwp_page list. + */ +enum hugetlb_page_flags { + HPG_restore_reserve = 0, + HPG_migratable, + HPG_temporary, + HPG_freed, + HPG_vmemmap_optimized, + HPG_raw_hwp_unreliable, + __NR_HPAGEFLAGS, +}; + +/* + * Macros to create test, set and clear function definitions for + * hugetlb specific page flags. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define TESTHPAGEFLAG(uname, flname) \ +static inline int HPage##uname(struct page *page) \ + { return test_bit(HPG_##flname, &(page->private)); } + +#define SETHPAGEFLAG(uname, flname) \ +static inline void SetHPage##uname(struct page *page) \ + { set_bit(HPG_##flname, &(page->private)); } + +#define CLEARHPAGEFLAG(uname, flname) \ +static inline void ClearHPage##uname(struct page *page) \ + { clear_bit(HPG_##flname, &(page->private)); } +#else +#define TESTHPAGEFLAG(uname, flname) \ +static inline int HPage##uname(struct page *page) \ + { return 0; } + +#define SETHPAGEFLAG(uname, flname) \ +static inline void SetHPage##uname(struct page *page) \ + { } + +#define CLEARHPAGEFLAG(uname, flname) \ +static inline void ClearHPage##uname(struct page *page) \ + { } +#endif + +#define HPAGEFLAG(uname, flname) \ + TESTHPAGEFLAG(uname, flname) \ + SETHPAGEFLAG(uname, flname) \ + CLEARHPAGEFLAG(uname, flname) \ + +/* + * Create functions associated with hugetlb page flags + */ +HPAGEFLAG(RestoreReserve, restore_reserve) +HPAGEFLAG(Migratable, migratable) +HPAGEFLAG(Temporary, temporary) +HPAGEFLAG(Freed, freed) +HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) +HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) + #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { + struct mutex resize_lock; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; + unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; @@ -427,13 +681,14 @@ struct hstate { unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[5]; - struct cftype cgroup_files_legacy[5]; + struct cftype cgroup_files_dfl[8]; + struct cftype cgroup_files_legacy[10]; #endif char name[HSTATE_NAME_LEN]; }; @@ -443,24 +698,25 @@ struct huge_bootmem_page { struct hstate *hstate; }; +int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); 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); -struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, - int nid, nodemask_t *nmask); -int huge_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page); /* arch callback */ -int __init __alloc_bootmem_huge_page(struct hstate *h); -int __init alloc_bootmem_huge_page(struct hstate *h); +int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); +int __init alloc_bootmem_huge_page(struct hstate *h, int nid); +bool __init hugetlb_node_alloc_supported(void); -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 @@ -472,9 +728,18 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) -static inline struct hstate *hstate_inode(struct inode *i) +/* + * hugetlb page subpool pointer located in hpage[1].private + */ +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { - return HUGETLBFS_SB(i->i_sb)->hstate; + return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL); +} + +static inline void hugetlb_set_page_subpool(struct page *hpage, + struct hugepage_subpool *subpool) +{ + set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool); } static inline struct hstate *hstate_file(struct file *f) @@ -495,7 +760,7 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma) return hstate_file(vma->vm_file); } -static inline unsigned long huge_page_size(struct hstate *h) +static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } @@ -524,7 +789,7 @@ static inline bool hstate_is_gigantic(struct hstate *h) return huge_page_order(h) >= MAX_ORDER; } -static inline unsigned int pages_per_huge_page(struct hstate *h) +static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } @@ -536,11 +801,25 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) #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) +static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, + vm_flags_t flags) { - return entry; + return pte_mkhuge(entry); } #endif @@ -560,21 +839,18 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -pgoff_t __basepage_index(struct page *page); - -/* Return page->index in PAGE_SIZE units */ -static inline pgoff_t basepage_index(struct page *page) -{ - if (!PageCompound(page)) - return page->index; - - return __basepage_index(page); -} - extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); +#ifdef CONFIG_MEMORY_FAILURE +extern void hugetlb_clear_page_hwpoison(struct page *hpage); +#else +static inline void hugetlb_clear_page_hwpoison(struct page *hpage) +{ +} +#endif + #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) @@ -604,7 +880,7 @@ static inline bool hugepage_migration_supported(struct hstate *h) * 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 + * There won't 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 @@ -624,6 +900,27 @@ static inline bool hugepage_movable_supported(struct hstate *h) 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, struct mm_struct *mm, pte_t *pte) { @@ -644,6 +941,11 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); +static inline void hugetlb_count_init(struct mm_struct *mm) +{ + atomic_long_set(&mm->hugetlb_usage, 0); +} + static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); @@ -654,14 +956,6 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) atomic_long_sub(l, &mm->hugetlb_usage); } -#ifndef set_huge_swap_pte_at -static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) -{ - set_huge_pte_at(mm, addr, ptep, pte); -} -#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, @@ -681,23 +975,35 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif +#ifdef CONFIG_NUMA +void hugetlb_register_node(struct node *node); +void hugetlb_unregister_node(struct node *node); +#endif + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; -static inline struct page *alloc_huge_page(struct vm_area_struct *vma, - unsigned long addr, - int avoid_reserve) +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { return NULL; } -static inline struct page *alloc_huge_page_node(struct hstate *h, int nid) +static inline int isolate_or_dissolve_huge_page(struct page *page, + struct list_head *list) +{ + return -ENOMEM; +} + +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) +alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } @@ -729,12 +1035,12 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma) return NULL; } -static inline struct hstate *hstate_inode(struct inode *i) +static inline struct hstate *page_hstate(struct page *page) { return NULL; } -static inline struct hstate *page_hstate(struct page *page) +static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } @@ -789,11 +1095,6 @@ static inline int hstate_index(struct hstate *h) return 0; } -static inline pgoff_t basepage_index(struct page *page) -{ - return page->index; -} - static inline int dissolve_free_huge_page(struct page *page) { return 0; @@ -815,12 +1116,26 @@ 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) { return &mm->page_table_lock; } +static inline void hugetlb_count_init(struct mm_struct *mm) +{ +} + static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } @@ -829,8 +1144,22 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } -static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + return *ptep; +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ +} + +static inline void hugetlb_register_node(struct node *node) +{ +} + +static inline void hugetlb_unregister_node(struct node *node) { } #endif /* CONFIG_HUGETLB_PAGE */ @@ -845,4 +1174,22 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, return ptl; } +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) +extern void __init hugetlb_cma_reserve(int order); +#else +static inline __init void hugetlb_cma_reserve(int order) +{ +} +#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 */ |