diff options
Diffstat (limited to 'include/linux/hugetlb.h')
| -rw-r--r-- | include/linux/hugetlb.h | 109 |
1 files changed, 89 insertions, 20 deletions
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9ab9d3105d5c..7c977d234aba 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -2,6 +2,7 @@ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H +#include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> @@ -170,11 +171,11 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int isolate_hugetlb(struct page *page, struct list_head *list); -int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison); +bool isolate_hugetlb(struct folio *folio, struct list_head *list); +int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); -void putback_active_hugepage(struct page *page); +void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); @@ -193,6 +194,43 @@ extern struct list_head huge_boot_pages; pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); +/* + * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. + * Returns the pte_t* if found, or NULL if the address is not mapped. + * + * IMPORTANT: we should normally not directly call this function, instead + * this is only a common interface to implement arch-specific + * walker. Please use hugetlb_walk() instead, because that will attempt to + * verify the locking for you. + * + * Since this function will walk all the pgtable pages (including not only + * high-level pgtable page, but also PUD entry that can be unshared + * concurrently for VM_SHARED), the caller of this function should be + * responsible of its thread safety. One can follow this rule: + * + * (1) For private mappings: pmd unsharing is not possible, so holding the + * mmap_lock for either read or write is sufficient. Most callers + * already hold the mmap_lock, so normally, no special action is + * required. + * + * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged + * pgtable page can go away from under us! It can be done by a pmd + * unshare with a follow up munmap() on the other process), then we + * need either: + * + * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare + * won't happen upon the range (it also makes sure the pte_t we + * read is the right and stable one), or, + * + * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make + * sure even if unshare happened the racy unmap() will wait until + * i_mmap_rwsem is released. + * + * Option (2.1) is the safest, which guarantees pte stability from pmd + * sharing pov, until the vma lock released. Option (2.2) doesn't protect + * a concurrent pmd unshare, but it makes sure the pgtable page is safe to + * access. + */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); @@ -211,7 +249,7 @@ 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, +long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); @@ -375,12 +413,12 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline int isolate_hugetlb(struct page *page, struct list_head *list) +static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) { - return -EBUSY; + return false; } -static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison) +static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } @@ -391,7 +429,7 @@ static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, return 0; } -static inline void putback_active_hugepage(struct page *page) +static inline void folio_putback_active_hugetlb(struct folio *folio) { } @@ -400,7 +438,7 @@ static inline void move_hugetlb_state(struct folio *old_folio, { } -static inline unsigned long hugetlb_change_protection( +static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) @@ -679,16 +717,16 @@ struct huge_bootmem_page { }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); -struct page *alloc_huge_page(struct vm_area_struct *vma, +struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); -struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, +struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); -struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, +struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); -int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct folio *folio, 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); + unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); @@ -843,9 +881,9 @@ 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); +extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else -static inline void hugetlb_clear_page_hwpoison(struct page *hpage) +static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif @@ -998,21 +1036,21 @@ static inline int isolate_or_dissolve_huge_page(struct page *page, return -ENOMEM; } -static inline struct page *alloc_huge_page(struct vm_area_struct *vma, +static inline struct folio *alloc_hugetlb_folio(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, +static inline struct folio * +alloc_hugetlb_folio_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, +static inline struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { @@ -1213,4 +1251,35 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif +static inline bool __vma_shareable_lock(struct vm_area_struct *vma) +{ + return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; +} + +/* + * Safe version of huge_pte_offset() to check the locks. See comments + * above huge_pte_offset(). + */ +static inline pte_t * +hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) +{ +#if defined(CONFIG_HUGETLB_PAGE) && \ + defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP) + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + /* + * If pmd sharing possible, locking needed to safely walk the + * hugetlb pgtables. More information can be found at the comment + * above huge_pte_offset() in the same file. + * + * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. + */ + if (__vma_shareable_lock(vma)) + WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && + !lockdep_is_held( + &vma->vm_file->f_mapping->i_mmap_rwsem)); +#endif + return huge_pte_offset(vma->vm_mm, addr, sz); +} + #endif /* _LINUX_HUGETLB_H */ |