diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 615 |
1 files changed, 418 insertions, 197 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 34f9dba17c1a..da5219b48d52 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -319,11 +319,13 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) +#define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS @@ -339,14 +341,27 @@ extern unsigned int kobjsize(const void *objp); #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ +#ifdef CONFIG_X86_USER_SHADOW_STACK +/* + * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of + * support core mm. + * + * These VMAs will get a single end guard page. This helps userspace protect + * itself from attacks. A single page is enough for current shadow stack archs + * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c + * for more details on the guard size. + */ +# define VM_SHADOW_STACK VM_HIGH_ARCH_5 +#else +# define VM_SHADOW_STACK VM_NONE +#endif + #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 -#elif defined(CONFIG_IA64) -# define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI @@ -370,7 +385,7 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -# define VM_UFFD_MINOR_BIT 37 +# define VM_UFFD_MINOR_BIT 38 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE @@ -397,6 +412,8 @@ extern unsigned int kobjsize(const void *objp); #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif +#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) + #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #define VM_STACK_EARLY VM_GROWSDOWN @@ -532,13 +549,6 @@ struct vm_fault { */ }; -/* page entry size for vm->huge_fault() */ -enum page_entry_size { - PE_SIZE_PTE = 0, - PE_SIZE_PMD, - PE_SIZE_PUD, -}; - /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer @@ -562,8 +572,7 @@ struct vm_operations_struct { int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); - vm_fault_t (*huge_fault)(struct vm_fault *vmf, - enum page_entry_size pe_size); + vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); @@ -608,7 +617,7 @@ struct vm_operations_struct { * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, - unsigned long addr); + unsigned long addr, pgoff_t *ilx); #endif /* * Called by vm_normal_page() for special PTEs to find the @@ -679,6 +688,7 @@ static inline void vma_end_read(struct vm_area_struct *vma) rcu_read_unlock(); } +/* WARNING! Can only be used if mmap_lock is expected to be write-locked */ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); @@ -691,6 +701,11 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) return (vma->vm_lock_seq == *mm_lock_seq); } +/* + * Begin writing to a VMA. + * Exclude concurrent readers under the per-VMA lock until the currently + * write-locked mmap_lock is dropped or downgraded. + */ static inline void vma_start_write(struct vm_area_struct *vma) { int mm_lock_seq; @@ -709,26 +724,17 @@ static inline void vma_start_write(struct vm_area_struct *vma) up_write(&vma->vm_lock->lock); } -static inline bool vma_try_start_write(struct vm_area_struct *vma) +static inline void vma_assert_write_locked(struct vm_area_struct *vma) { int mm_lock_seq; - if (__is_vma_write_locked(vma, &mm_lock_seq)) - return true; - - if (!down_write_trylock(&vma->vm_lock->lock)) - return false; - - WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); - up_write(&vma->vm_lock->lock); - return true; + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } -static inline void vma_assert_write_locked(struct vm_area_struct *vma) +static inline void vma_assert_locked(struct vm_area_struct *vma) { - int mm_lock_seq; - - VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); + if (!rwsem_is_locked(&vma->vm_lock->lock)) + vma_assert_write_locked(vma); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) @@ -739,6 +745,22 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) vma->detached = detached; } +static inline void release_fault_lock(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_VMA_LOCK) + vma_end_read(vmf->vma); + else + mmap_read_unlock(vmf->vma->vm_mm); +} + +static inline void assert_fault_locked(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_VMA_LOCK) + vma_assert_locked(vmf->vma); + else + mmap_assert_locked(vmf->vma->vm_mm); +} + struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); @@ -748,25 +770,40 @@ static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} -static inline bool vma_try_start_write(struct vm_area_struct *vma) - { return true; } -static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} +static inline void vma_assert_write_locked(struct vm_area_struct *vma) + { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) {} +static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address) +{ + return NULL; +} + +static inline void release_fault_lock(struct vm_fault *vmf) +{ + mmap_read_unlock(vmf->vma->vm_mm); +} + +static inline void assert_fault_locked(struct vm_fault *vmf) +{ + mmap_assert_locked(vmf->vma->vm_mm); +} + #endif /* CONFIG_PER_VMA_LOCK */ +extern const struct vm_operations_struct vma_dummy_vm_ops; + /* * WARNING: vma_init does not initialize vma->vm_lock. * Use vm_area_alloc()/vm_area_free() if vma needs locking. */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { - static const struct vm_operations_struct dummy_vm_ops = {}; - memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; - vma->vm_ops = &dummy_vm_ops; + vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); vma_numab_state_init(vma); @@ -779,18 +816,22 @@ static inline void vm_flags_init(struct vm_area_struct *vma, ACCESS_PRIVATE(vma, __vm_flags) = flags; } -/* Use when VMA is part of the VMA tree and modifications need coordination */ +/* + * Use when VMA is part of the VMA tree and modifications need coordination + * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and + * it should be locked explicitly beforehand. + */ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { - vma_start_write(vma); + vma_assert_write_locked(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { - vma_start_write(vma); + vma_assert_write_locked(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } @@ -839,6 +880,31 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma) return !vma->vm_ops; } +/* + * Indicate if the VMA is a heap for the given task; for + * /proc/PID/maps that is the heap of the main task. + */ +static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) +{ + return vma->vm_start < vma->vm_mm->brk && + vma->vm_end > vma->vm_mm->start_brk; +} + +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) +{ + /* + * We make no effort to guess what a given thread considers to be + * its "stack". It's not even well-defined for programs written + * languages like Go. + */ + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; +} + static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -869,6 +935,17 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) return vma->vm_flags & VM_ACCESS_FLAGS; } +static inline bool is_shared_maywrite(vm_flags_t vm_flags) +{ + return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == + (VM_SHARED | VM_MAYWRITE); +} + +static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) +{ + return is_shared_maywrite(vma->vm_flags); +} + static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { @@ -976,7 +1053,7 @@ struct inode; * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be * prepared to handle wild return values. For example, PG_head may be - * set before _folio_order is initialised, or this may be a tail page. + * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ static inline unsigned int compound_order(struct page *page) @@ -985,7 +1062,7 @@ static inline unsigned int compound_order(struct page *page) if (!test_bit(PG_head, &folio->flags)) return 0; - return folio->_folio_order; + return folio->_flags_1 & 0xff; } /** @@ -1001,7 +1078,7 @@ static inline unsigned int folio_order(struct folio *folio) { if (!folio_test_large(folio)) return 0; - return folio->_folio_order; + return folio->_flags_1 & 0xff; } #include <linux/huge_mm.h> @@ -1072,11 +1149,6 @@ unsigned long vmalloc_to_pfn(const void *addr); * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ - -#ifndef is_ioremap_addr -#define is_ioremap_addr(x) is_vmalloc_addr(x) -#endif - #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); @@ -1220,33 +1292,6 @@ void folio_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); -/* - * Compound pages have a destructor function. Provide a - * prototype for that function and accessor functions. - * These are _only_ valid on the head of a compound page. - */ -typedef void compound_page_dtor(struct page *); - -/* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */ -enum compound_dtor_id { - NULL_COMPOUND_DTOR, - COMPOUND_PAGE_DTOR, -#ifdef CONFIG_HUGETLB_PAGE - HUGETLB_PAGE_DTOR, -#endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - TRANSHUGE_PAGE_DTOR, -#endif - NR_COMPOUND_DTORS, -}; - -static inline void folio_set_compound_dtor(struct folio *folio, - enum compound_dtor_id compound_dtor) -{ - VM_BUG_ON_FOLIO(compound_dtor >= NR_COMPOUND_DTORS, folio); - folio->_folio_dtor = compound_dtor; -} - void destroy_large_folio(struct folio *folio); /* Returns the number of bytes in this potentially compound page. */ @@ -1282,8 +1327,6 @@ static inline unsigned long thp_size(struct page *page) return PAGE_SIZE << thp_order(page); } -void free_compound_page(struct page *page); - #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when @@ -1294,15 +1337,15 @@ void free_compound_page(struct page *page); static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) - pte = pte_mkwrite(pte); + pte = pte_mkwrite(pte, vma); return pte; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); -void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr); +void set_pte_range(struct vm_fault *vmf, struct folio *folio, + struct page *page, unsigned int nr, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); -vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif /* @@ -1651,26 +1694,26 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS -static inline int page_cpupid_xchg_last(struct page *page, int cpupid) +static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { - return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); + return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } -static inline int page_cpupid_last(struct page *page) +static inline int folio_last_cpupid(struct folio *folio) { - return page->_last_cpupid; + return folio->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else -static inline int page_cpupid_last(struct page *page) +static inline int folio_last_cpupid(struct folio *folio) { - return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; + return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } -extern int page_cpupid_xchg_last(struct page *page, int cpupid); +int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { @@ -1678,11 +1721,12 @@ static inline void page_cpupid_reset_last(struct page *page) } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ -static inline int xchg_page_access_time(struct page *page, int time) +static inline int folio_xchg_access_time(struct folio *folio, int time) { int last_time; - last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); + last_time = folio_xchg_last_cpupid(folio, + time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } @@ -1691,24 +1735,24 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) unsigned int pid_bit; pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); - if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { - __set_bit(pid_bit, &vma->numab_state->access_pids[1]); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) { + __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } #else /* !CONFIG_NUMA_BALANCING */ -static inline int page_cpupid_xchg_last(struct page *page, int cpupid) +static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { - return page_to_nid(page); /* XXX */ + return folio_nid(folio); /* XXX */ } -static inline int xchg_page_access_time(struct page *page, int time) +static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } -static inline int page_cpupid_last(struct page *page) +static inline int folio_last_cpupid(struct folio *folio) { - return page_to_nid(page); /* XXX */ + return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) @@ -2006,7 +2050,7 @@ static inline long folio_nr_pages(struct folio *folio) #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else - return 1L << folio->_folio_order; + return 1L << (folio->_flags_1 & 0xff); #endif } @@ -2024,7 +2068,7 @@ static inline unsigned long compound_nr(struct page *page) #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else - return 1L << folio->_folio_order; + return 1L << (folio->_flags_1 & 0xff); #endif } @@ -2170,7 +2214,6 @@ static inline void *folio_address(const struct folio *folio) return page_address(&folio->page); } -extern void *page_rmapping(struct page *page); extern pgoff_t __page_file_index(struct page *page); /* @@ -2238,18 +2281,6 @@ extern void pagefault_out_of_memory(void); #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* - * Flags passed to show_mem() and show_free_areas() to suppress output in - * various contexts. - */ -#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ - -extern void __show_free_areas(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); -static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodemask) -{ - __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); -} - -/* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { @@ -2305,6 +2336,8 @@ struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); @@ -2317,9 +2350,9 @@ static inline void zap_vma_pages(struct vm_area_struct *vma) zap_page_range_single(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL); } -void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, +void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, - unsigned long end, bool mm_wr_locked); + unsigned long end, unsigned long tree_end, bool mm_wr_locked); struct mmu_notifier_range; @@ -2391,8 +2424,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); -extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr, - void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -2403,6 +2434,9 @@ long pin_user_pages_remote(struct mm_struct *mm, unsigned int gup_flags, struct page **pages, int *locked); +/* + * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT. + */ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, unsigned long addr, int gup_flags, @@ -2410,12 +2444,15 @@ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, { struct page *page; struct vm_area_struct *vma; - int got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); + int got; + + if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT))) + return ERR_PTR(-EINVAL); + + got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); if (got < 0) return ERR_PTR(got); - if (got == 0) - return NULL; vma = vma_lookup(mm, addr); if (WARN_ON_ONCE(!vma)) { @@ -2458,7 +2495,7 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, - bool need_rmap_locks); + bool need_rmap_locks, bool for_stack); /* * Flags used by change_protection(). For now we make it a bitmap so @@ -2606,14 +2643,6 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, *maxrss = hiwater_rss; } -#if defined(SPLIT_RSS_COUNTING) -void sync_mm_rss(struct mm_struct *mm); -#else -static inline void sync_mm_rss(struct mm_struct *mm) -{ -} -#endif - #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { @@ -2766,42 +2795,93 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a } #endif /* CONFIG_MMU */ +static inline struct ptdesc *virt_to_ptdesc(const void *x) +{ + return page_ptdesc(virt_to_page(x)); +} + +static inline void *ptdesc_to_virt(const struct ptdesc *pt) +{ + return page_to_virt(ptdesc_page(pt)); +} + +static inline void *ptdesc_address(const struct ptdesc *pt) +{ + return folio_address(ptdesc_folio(pt)); +} + +static inline bool pagetable_is_reserved(struct ptdesc *pt) +{ + return folio_test_reserved(ptdesc_folio(pt)); +} + +/** + * pagetable_alloc - Allocate pagetables + * @gfp: GFP flags + * @order: desired pagetable order + * + * pagetable_alloc allocates memory for page tables as well as a page table + * descriptor to describe that memory. + * + * Return: The ptdesc describing the allocated page tables. + */ +static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order) +{ + struct page *page = alloc_pages(gfp | __GFP_COMP, order); + + return page_ptdesc(page); +} + +/** + * pagetable_free - Free pagetables + * @pt: The page table descriptor + * + * pagetable_free frees the memory of all page tables described by a page + * table descriptor and the memory for the descriptor itself. + */ +static inline void pagetable_free(struct ptdesc *pt) +{ + struct page *page = ptdesc_page(pt); + + __free_pages(page, compound_order(page)); +} + #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); -extern bool ptlock_alloc(struct page *page); -extern void ptlock_free(struct page *page); +bool ptlock_alloc(struct ptdesc *ptdesc); +void ptlock_free(struct ptdesc *ptdesc); -static inline spinlock_t *ptlock_ptr(struct page *page) +static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { - return page->ptl; + return ptdesc->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } -static inline bool ptlock_alloc(struct page *page) +static inline bool ptlock_alloc(struct ptdesc *ptdesc) { return true; } -static inline void ptlock_free(struct page *page) +static inline void ptlock_free(struct ptdesc *ptdesc) { } -static inline spinlock_t *ptlock_ptr(struct page *page) +static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { - return &page->ptl; + return &ptdesc->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { - return ptlock_ptr(pmd_page(*pmd)); + return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } -static inline bool ptlock_init(struct page *page) +static inline bool ptlock_init(struct ptdesc *ptdesc) { /* * prep_new_page() initialize page->private (and therefore page->ptl) @@ -2810,10 +2890,10 @@ static inline bool ptlock_init(struct page *page) * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ - VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page); - if (!ptlock_alloc(page)) + VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc)); + if (!ptlock_alloc(ptdesc)) return false; - spin_lock_init(ptlock_ptr(page)); + spin_lock_init(ptlock_ptr(ptdesc)); return true; } @@ -2826,24 +2906,28 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} -static inline bool ptlock_init(struct page *page) { return true; } -static inline void ptlock_free(struct page *page) {} +static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } +static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline bool pgtable_pte_page_ctor(struct page *page) +static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) { - if (!ptlock_init(page)) + struct folio *folio = ptdesc_folio(ptdesc); + + if (!ptlock_init(ptdesc)) return false; - __SetPageTable(page); - inc_lruvec_page_state(page, NR_PAGETABLE); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } -static inline void pgtable_pte_page_dtor(struct page *page) +static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) { - ptlock_free(page); - __ClearPageTable(page); - dec_lruvec_page_state(page, NR_PAGETABLE); + struct folio *folio = ptdesc_folio(ptdesc); + + ptlock_free(ptdesc); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); @@ -2892,28 +2976,33 @@ static inline struct page *pmd_pgtable_page(pmd_t *pmd) return virt_to_page((void *)((unsigned long) pmd & mask)); } +static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd) +{ + return page_ptdesc(pmd_pgtable_page(pmd)); +} + static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { - return ptlock_ptr(pmd_pgtable_page(pmd)); + return ptlock_ptr(pmd_ptdesc(pmd)); } -static inline bool pmd_ptlock_init(struct page *page) +static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - page->pmd_huge_pte = NULL; + ptdesc->pmd_huge_pte = NULL; #endif - return ptlock_init(page); + return ptlock_init(ptdesc); } -static inline void pmd_ptlock_free(struct page *page) +static inline void pmd_ptlock_free(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(page->pmd_huge_pte, page); + VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); #endif - ptlock_free(page); + ptlock_free(ptdesc); } -#define pmd_huge_pte(mm, pmd) (pmd_pgtable_page(pmd)->pmd_huge_pte) +#define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else @@ -2922,8 +3011,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) return &mm->page_table_lock; } -static inline bool pmd_ptlock_init(struct page *page) { return true; } -static inline void pmd_ptlock_free(struct page *page) {} +static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } +static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -2936,20 +3025,24 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -static inline bool pgtable_pmd_page_ctor(struct page *page) +static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { - if (!pmd_ptlock_init(page)) + struct folio *folio = ptdesc_folio(ptdesc); + + if (!pmd_ptlock_init(ptdesc)) return false; - __SetPageTable(page); - inc_lruvec_page_state(page, NR_PAGETABLE); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } -static inline void pgtable_pmd_page_dtor(struct page *page) +static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) { - pmd_ptlock_free(page); - __ClearPageTable(page); - dec_lruvec_page_state(page, NR_PAGETABLE); + struct folio *folio = ptdesc_folio(ptdesc); + + pmd_ptlock_free(ptdesc); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } /* @@ -2971,6 +3064,22 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) return ptl; } +static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) +{ + struct folio *folio = ptdesc_folio(ptdesc); + + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); +} + +static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +{ + struct folio *folio = ptdesc_folio(ptdesc); + + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); +} + extern void __init pagecache_init(void); extern void free_initmem(void); @@ -3004,6 +3113,11 @@ static inline void mark_page_reserved(struct page *page) adjust_managed_page_count(page, -1); } +static inline void free_reserved_ptdesc(struct ptdesc *pt) +{ + free_reserved_page(ptdesc_page(pt)); +} + /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within @@ -3069,9 +3183,9 @@ extern void mem_init(void); extern void __init mmap_init(void); extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); -static inline void show_mem(unsigned int flags, nodemask_t *nodemask) +static inline void show_mem(void) { - __show_mem(flags, nodemask, MAX_NR_ZONES - 1); + __show_mem(0, NULL, MAX_NR_ZONES - 1); } extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); @@ -3130,22 +3244,73 @@ extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct *next); extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff); -extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, - struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, - unsigned long end, unsigned long vm_flags, struct anon_vma *, - struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx, - struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); -extern int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *, - unsigned long addr, int new_below); -extern int split_vma(struct vma_iterator *vmi, struct vm_area_struct *, - unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name); + +/* We are about to modify the VMA's flags. */ +static inline struct vm_area_struct +*vma_modify_flags(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or anon_name. */ +static inline struct vm_area_struct +*vma_modify_flags_name(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long new_flags, + struct anon_vma_name *new_name) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); +} + +/* We are about to modify the VMA's memory policy. */ +static inline struct vm_area_struct +*vma_modify_policy(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct mempolicy *new_pol) +{ + return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, + new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or uffd context. */ +static inline struct vm_area_struct +*vma_modify_flags_uffd(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags, + struct vm_userfaultfd_ctx new_ctx) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), new_ctx, anon_vma_name(vma)); +} static inline int check_data_rlimit(unsigned long rlim, unsigned long new, @@ -3193,7 +3358,8 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate, struct list_head *uf); + vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, + struct list_head *uf); extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); @@ -3216,8 +3382,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif -/* These take the mm semaphore themselves */ -extern int __must_check vm_brk(unsigned long, unsigned long); +/* This takes the mm semaphore itself */ extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, @@ -3281,15 +3446,26 @@ struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) return mtree_load(&mm->mm_mt, addr); } +static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_GROWSDOWN) + return stack_guard_gap; + + /* See reasoning around the VM_SHADOW_STACK definition */ + if (vma->vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { + unsigned long gap = stack_guard_start_gap(vma); unsigned long vm_start = vma->vm_start; - if (vma->vm_flags & VM_GROWSDOWN) { - vm_start -= stack_guard_gap; - if (vm_start > vma->vm_start) - vm_start = 0; - } + vm_start -= gap; + if (vm_start > vma->vm_start) + vm_start = 0; return vm_start; } @@ -3403,6 +3579,24 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } +/* + * Convert errno to return value for ->page_mkwrite() calls. + * + * This should eventually be merged with vmf_error() above, but will need a + * careful audit of all vmf_error() callers. + */ +static inline vm_fault_t vmf_fs_error(int err) +{ + if (err == 0) + return VM_FAULT_LOCKED; + if (err == -EFAULT || err == -EAGAIN) + return VM_FAULT_NOPAGE; + if (err == -ENOMEM) + return VM_FAULT_OOM; + /* -ENOSPC, -EDQUOT, -EIO ... */ + return VM_FAULT_SIGBUS; +} + struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); @@ -3509,8 +3703,8 @@ static inline bool debug_pagealloc_enabled(void) } /* - * For use in fast paths after init_debug_pagealloc() has run, or when a - * false negative result is not harmful when called too early. + * For use in fast paths after mem_debugging_and_hardening_init() has run, + * or when a false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { @@ -3665,13 +3859,32 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif -#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP -static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, - struct dev_pagemap *pgmap) +#define VMEMMAP_RESERVE_NR 2 +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { - return is_power_of_2(sizeof(struct page)) && - pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap; + unsigned long nr_pages; + unsigned long nr_vmemmap_pages; + + if (!pgmap || !is_power_of_2(sizeof(struct page))) + return false; + + nr_pages = pgmap_vmemmap_nr(pgmap); + nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT); + /* + * For vmemmap optimization with DAX we need minimum 2 vmemmap + * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst + */ + return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR); } +/* + * If we don't have an architecture override, use the generic rule + */ +#ifndef vmemmap_can_optimize +#define vmemmap_can_optimize __vmemmap_can_optimize +#endif + #else static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) @@ -3860,25 +4073,26 @@ static inline void mem_dump_obj(void *object) {} #endif /** - * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and + * handle them. * @seals: the seals to check * @vma: the vma to operate on * - * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on - * the vma flags. Return 0 if check pass, or <0 for errors. + * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper + * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. */ -static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & F_SEAL_FUTURE_WRITE) { + if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. + * write seals are active. */ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) return -EPERM; /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as * MAP_SHARED and read-only, take care to not allow mprotect to * revert protections on such mappings. Do this only for shared * mappings. For private mappings, don't need to mask @@ -3922,4 +4136,11 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end) #endif +static inline bool pfn_is_unaccepted_memory(unsigned long pfn) +{ + phys_addr_t paddr = pfn << PAGE_SHIFT; + + return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); +} + #endif /* _LINUX_MM_H */ |