/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; struct folio_batch; extern int sysctl_page_lock_unfairness; void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) { max_mapnr = limit; } #else static inline void set_max_mapnr(unsigned long limit) { … } #endif extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { … } static inline void totalram_pages_inc(void) { … } static inline void totalram_pages_dec(void) { … } static inline void totalram_pages_add(long count) { … } extern void * high_memory; extern int page_cluster; extern const int page_cluster_max; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout … #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #ifndef PHYSMEM_END # ifdef MAX_PHYSMEM_BITS #define PHYSMEM_END … # else #define PHYSMEM_END … # endif #endif #include <asm/page.h> #include <asm/processor.h> #ifndef __pa_symbol #define __pa_symbol … #endif #ifndef page_to_virt #define page_to_virt(x) … #endif #ifndef lm_alias #define lm_alias(x) … #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) … #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) … static inline void __mm_zero_struct_page(struct page *page) { … } #else #define mm_zero_struct_page … #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN … #define DEFAULT_MAX_MAP_COUNT … extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page … #define folio_page_idx … #else #define nth_page(page,n) … #define folio_page_idx(folio, p) … #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) … /* to align the pointer to the (prev) page boundary */ #define PAGE_ALIGN_DOWN(addr) … /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) … static inline struct folio *lru_to_folio(struct list_head *head) { … } void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); /* Use only if VMA has no other users */ void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE … #define VM_READ … #define VM_WRITE … #define VM_EXEC … #define VM_SHARED … /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD … #define VM_MAYWRITE … #define VM_MAYEXEC … #define VM_MAYSHARE … #define VM_GROWSDOWN … #ifdef CONFIG_MMU #define VM_UFFD_MISSING … #else /* CONFIG_MMU */ #define VM_MAYOVERLAY … #define VM_UFFD_MISSING … #endif /* CONFIG_MMU */ #define VM_PFNMAP … #define VM_UFFD_WP … #define VM_LOCKED … #define VM_IO … /* Used by sys_madvise() */ #define VM_SEQ_READ … #define VM_RAND_READ … #define VM_DONTCOPY … #define VM_DONTEXPAND … #define VM_LOCKONFAULT … #define VM_ACCOUNT … #define VM_NORESERVE … #define VM_HUGETLB … #define VM_SYNC … #define VM_ARCH_1 … #define VM_WIPEONFORK … #define VM_DONTDUMP … #ifdef CONFIG_MEM_SOFT_DIRTY #define VM_SOFTDIRTY … #else #define VM_SOFTDIRTY … #endif #define VM_MIXEDMAP … #define VM_HUGEPAGE … #define VM_NOHUGEPAGE … #define VM_MERGEABLE … #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 … #define VM_HIGH_ARCH_BIT_1 … #define VM_HIGH_ARCH_BIT_2 … #define VM_HIGH_ARCH_BIT_3 … #define VM_HIGH_ARCH_BIT_4 … #define VM_HIGH_ARCH_BIT_5 … #define VM_HIGH_ARCH_0 … #define VM_HIGH_ARCH_1 … #define VM_HIGH_ARCH_2 … #define VM_HIGH_ARCH_3 … #define VM_HIGH_ARCH_4 … #define VM_HIGH_ARCH_5 … #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS #define VM_PKEY_SHIFT … #define VM_PKEY_BIT0 … #define VM_PKEY_BIT1 … #define VM_PKEY_BIT2 … #if CONFIG_ARCH_PKEY_BITS > 3 #define VM_PKEY_BIT3 … #else #define VM_PKEY_BIT3 … #endif #if CONFIG_ARCH_PKEY_BITS > 4 #define VM_PKEY_BIT4 … #else #define VM_PKEY_BIT4 … #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 … #else #define VM_SHADOW_STACK … #endif #if defined(CONFIG_X86) #define VM_PAT … #elif defined(CONFIG_PPC64) #define VM_SAO … #elif defined(CONFIG_PARISC) #define VM_GROWSUP … #elif defined(CONFIG_SPARC64) #define VM_SPARC_ADI … #define VM_ARCH_CLEAR … #elif defined(CONFIG_ARM64) #define VM_ARM64_BTI … #define VM_ARCH_CLEAR … #elif !defined(CONFIG_MMU) #define VM_MAPPED_COPY … #endif #if defined(CONFIG_ARM64_MTE) #define VM_MTE … #define VM_MTE_ALLOWED … #else #define VM_MTE … #define VM_MTE_ALLOWED … #endif #ifndef VM_GROWSUP #define VM_GROWSUP … #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR #define VM_UFFD_MINOR_BIT … #define VM_UFFD_MINOR … #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ #define VM_UFFD_MINOR … #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ /* * This flag is used to connect VFIO to arch specific KVM code. It * indicates that the memory under this VMA is safe for use with any * non-cachable memory type inside KVM. Some VFIO devices, on some * platforms, are thought to be unsafe and can cause machine crashes * if KVM does not lock down the memory type. */ #ifdef CONFIG_64BIT #define VM_ALLOW_ANY_UNCACHED_BIT … #define VM_ALLOW_ANY_UNCACHED … #else #define VM_ALLOW_ANY_UNCACHED … #endif #ifdef CONFIG_64BIT #define VM_DROPPABLE_BIT … #define VM_DROPPABLE … #elif defined(CONFIG_PPC32) #define VM_DROPPABLE … #else #define VM_DROPPABLE … #endif #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED … #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP … #define TASK_EXEC … /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC … #define VM_DATA_FLAGS_NON_EXEC … #define VM_DATA_FLAGS_EXEC … #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS … #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS … #endif #define VM_STARTGAP_FLAGS … #ifdef CONFIG_STACK_GROWSUP #define VM_STACK … #define VM_STACK_EARLY … #else #define VM_STACK … #define VM_STACK_EARLY … #endif #define VM_STACK_FLAGS … /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS … /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL … /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED … /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK … /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK … /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR #define VM_ARCH_CLEAR … #endif #define VM_FLAGS_CLEAR … /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT … /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { … } #define FAULT_FLAG_TRACE … /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { … }; /* * 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 * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { … }; #ifdef CONFIG_NUMA_BALANCING static inline void vma_numab_state_init(struct vm_area_struct *vma) { … } static inline void vma_numab_state_free(struct vm_area_struct *vma) { … } #else static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_PER_VMA_LOCK /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. */ static inline bool vma_start_read(struct vm_area_struct *vma) { … } static inline void vma_end_read(struct vm_area_struct *vma) { … } /* 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) { … } /* * 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) { … } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { … } static inline void vma_assert_locked(struct vm_area_struct *vma) { … } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) { … } static inline void release_fault_lock(struct vm_fault *vmf) { … } static inline void assert_fault_locked(struct vm_fault *vmf) { … } struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ 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 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 vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } 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) { … } /* Use when VMA is not part of the VMA tree and needs no locking */ static inline void vm_flags_init(struct vm_area_struct *vma, vm_flags_t flags) { … } /* * 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) { … } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { … } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { … } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { … } /* * Use only if VMA is not part of the VMA tree or has no other users and * therefore needs no locking. */ static inline void __vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { … } /* * Use only when the order of set/clear operations is unimportant, otherwise * use vm_flags_{set|clear} explicitly. */ static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { … } static inline void vma_set_anonymous(struct vm_area_struct *vma) { … } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { … } /* * 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) { … } /* * 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) { … } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { … } static inline bool vma_is_foreign(struct vm_area_struct *vma) { … } static inline bool vma_is_accessible(struct vm_area_struct *vma) { … } static inline bool is_shared_maywrite(vm_flags_t vm_flags) { … } static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) { … } static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { … } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { … } static inline struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) { … } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) { … } static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { … } /* Free any unused preallocations */ static inline void vma_iter_free(struct vma_iterator *vmi) { … } static inline int vma_iter_bulk_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { … } static inline void vma_iter_invalidate(struct vma_iterator *vmi) { … } static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) { … } #define for_each_vma(__vmi, __vma) … /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) … #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); bool vma_is_anon_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) … struct mmu_gather; 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 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) { … } /** * folio_order - The allocation order of a folio. * @folio: The folio. * * A folio is composed of 2^order pages. See get_order() for the definition * of order. * * Return: The order of the folio. */ static inline unsigned int folio_order(const struct folio *folio) { … } #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { … } static inline int folio_put_testzero(struct folio *folio) { … } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline bool get_page_unless_zero(struct page *page) { … } static inline struct folio *folio_get_nontail_page(struct page *page) { … } extern int page_is_ram(unsigned long pfn); enum { … }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for * debugging purposes or implementation of other core folio_*() primitives. */ static inline int folio_entire_mapcount(const struct folio *folio) { … } static inline int folio_large_mapcount(const struct folio *folio) { … } /** * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * * The folio mapcount corresponds to the number of present user page table * entries that reference any part of a folio. Each such present user page * table entry must be paired with exactly on folio reference. * * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts * exactly once. * * For hugetlb folios, each abstracted "hugetlb" user page table entry that * references the entire folio counts exactly once, even when such special * page table entries are comprised of multiple ordinary page table entries. * * Will report 0 for pages which cannot be mapped into userspace, such as * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ static inline int folio_mapcount(const struct folio *folio) { … } /** * folio_mapped - Is this folio mapped into userspace? * @folio: The folio. * * Return: True if any page in this folio is referenced by user page tables. */ static inline bool folio_mapped(const struct folio *folio) { … } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ static inline bool page_mapped(const struct page *page) { … } static inline struct page *virt_to_head_page(const void *x) { … } static inline struct folio *virt_to_folio(const void *x) { … } void __folio_put(struct folio *folio); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { … } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { … } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { … } /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { … } #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { … } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); 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); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { … } #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) … /** * folio_get - Increment the reference count on a folio. * @folio: The folio. * * Context: May be called in any context, as long as you know that * you have a refcount on the folio. If you do not already have one, * folio_try_get() may be the right interface for you to use. */ static inline void folio_get(struct folio *folio) { … } static inline void get_page(struct page *page) { … } static inline __must_check bool try_get_page(struct page *page) { … } /** * folio_put - Decrement the reference count on a folio. * @folio: The folio. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put() unless you can be sure that it wasn't the * last reference. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put(struct folio *folio) { … } /** * folio_put_refs - Reduce the reference count on a folio. * @folio: The folio. * @refs: The amount to subtract from the folio's reference count. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put_refs() unless you can be sure that these weren't * the last references. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put_refs(struct folio *folio, int refs) { … } void folios_put_refs(struct folio_batch *folios, unsigned int *refs); /* * union release_pages_arg - an array of pages or folios * * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. * * The transparent union syntax for this kind of "any of these * argument types" is all kinds of ugly, so look away. */ release_pages_arg __attribute__ ((__transparent_union__ …)); void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need to * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folios_put(struct folio_batch *folios) { … } static inline void put_page(struct page *page) { … } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() * provides safe operation for get_user_pages(), folio_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS … void unpin_user_page(struct page *page); void unpin_folio(struct folio *folio); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); void unpin_user_folio(struct folio *folio, unsigned long npages); void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) { … } #ifndef CONFIG_MMU static inline bool is_nommu_shared_mapping(vm_flags_t flags) { /* * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of * a file mapping. R/O MAP_PRIVATE mappings might still modify * underlying memory if ptrace is active, so this is only possible if * ptrace does not apply. Note that there is no mprotect() to upgrade * write permissions later. */ return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } #endif #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { … } #ifdef NODE_NOT_IN_PAGE_FLAGS int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { … } #endif static inline int folio_nid(const struct folio *folio) { … } #ifdef CONFIG_NUMA_BALANCING /* page access time bits needs to hold at least 4 seconds */ #define PAGE_ACCESS_TIME_MIN_BITS … #if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS #define PAGE_ACCESS_TIME_BUCKETS … #else #define PAGE_ACCESS_TIME_BUCKETS … #endif #define PAGE_ACCESS_TIME_MASK … static inline int cpu_pid_to_cpupid(int cpu, int pid) { … } static inline int cpupid_to_pid(int cpupid) { … } static inline int cpupid_to_cpu(int cpupid) { … } static inline int cpupid_to_nid(int cpupid) { … } static inline bool cpupid_pid_unset(int cpupid) { … } static inline bool cpupid_cpu_unset(int cpupid) { … } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { … } #define cpupid_match_pid(task, cpupid) … #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int folio_last_cpupid(struct folio *folio) { 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 folio_last_cpupid(struct folio *folio) { … } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { … } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ static inline int folio_xchg_access_time(struct folio *folio, int time) { … } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { … } bool folio_use_access_time(struct folio *folio); #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return folio_nid(folio); /* XXX */ } static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } static inline int folio_last_cpupid(struct folio *folio) { return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } static inline bool folio_use_access_time(struct folio *folio) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { unsigned long old_flags, flags; if (!kasan_enabled()) return; tag ^= 0xff; old_flags = READ_ONCE(page->flags); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) { if (kasan_enabled()) page_kasan_tag_set(page, KASAN_TAG_KERNEL); } #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline u8 page_kasan_tag(const struct page *page) { … } static inline void page_kasan_tag_set(struct page *page, u8 tag) { … } static inline void page_kasan_tag_reset(struct page *page) { … } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline struct zone *page_zone(const struct page *page) { … } static inline pg_data_t *page_pgdat(const struct page *page) { … } static inline struct zone *folio_zone(const struct folio *folio) { … } static inline pg_data_t *folio_pgdat(const struct folio *folio) { … } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif /** * folio_pfn - Return the Page Frame Number of a folio. * @folio: The folio. * * A folio may contain multiple pages. The pages have consecutive * Page Frame Numbers. * * Return: The Page Frame Number of the first page in the folio. */ static inline unsigned long folio_pfn(struct folio *folio) { … } static inline struct folio *pfn_folio(unsigned long pfn) { … } /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. * * This function checks if a folio has been pinned via a call to * a function in the pin_user_pages() family. * * For small folios, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal folio references". * * False positives are OK, because: a) it's unlikely for a folio to * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * * For large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * Return: True, if it is likely that the folio has been "dma-pinned". * False, if the folio is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { … } /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, struct folio *folio) { … } /** * is_zero_page - Query if a page is a zero page * @page: The page to query * * This returns true if @page is one of the permanent zero pages. */ static inline bool is_zero_page(const struct page *page) { … } /** * is_zero_folio - Query if a folio is a zero page * @folio: The folio to query * * This returns true if @folio is one of the permanent zero pages. */ static inline bool is_zero_folio(const struct folio *folio) { … } /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */ #ifdef CONFIG_MIGRATION static inline bool folio_is_longterm_pinnable(struct folio *folio) { … } #else static inline bool folio_is_longterm_pinnable(struct folio *folio) { return true; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { … } static inline void set_page_node(struct page *page, unsigned long node) { … } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { … } /** * folio_nr_pages - The number of pages in the folio. * @folio: The folio. * * Return: A positive power of two. */ static inline long folio_nr_pages(const struct folio *folio) { … } /* Only hugetlbfs can allocate folios larger than MAX_ORDER */ #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #define MAX_FOLIO_NR_PAGES … #else #define MAX_FOLIO_NR_PAGES … #endif /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ static inline unsigned long compound_nr(struct page *page) { … } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline int thp_nr_pages(struct page *page) { … } /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. * * If you have physically contiguous memory which may span more than * one folio (eg a &struct bio_vec), use this function to move from one * folio to the next. Do not use it if the memory is only virtually * contiguous as the folios are almost certainly not adjacent to each * other. This is the folio equivalent to writing ``page++``. * * Context: We assume that the folios are refcounted and/or locked at a * higher level and do not adjust the reference counts. * Return: The next struct folio. */ static inline struct folio *folio_next(struct folio *folio) { … } /** * folio_shift - The size of the memory described by this folio. * @folio: The folio. * * A folio represents a number of bytes which is a power-of-two in size. * This function tells you which power-of-two the folio is. See also * folio_size() and folio_order(). * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ static inline unsigned int folio_shift(const struct folio *folio) { … } /** * folio_size - The number of bytes in a folio. * @folio: The folio. * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ static inline size_t folio_size(const struct folio *folio) { … } /** * folio_likely_mapped_shared - Estimate if the folio is mapped into the page * tables of more than one MM * @folio: The folio. * * This function checks if the folio is currently mapped into more than one * MM ("mapped shared"), or if the folio is only mapped into a single MM * ("mapped exclusively"). * * For KSM folios, this function also returns "mapped shared" when a folio is * mapped multiple times into the same MM, because the individual page mappings * are independent. * * As precise information is not easily available for all folios, this function * estimates the number of MMs ("sharers") that are currently mapping a folio * using the number of times the first page of the folio is currently mapped * into page tables. * * For small anonymous folios and anonymous hugetlb folios, the return * value will be exactly correct: non-KSM folios can only be mapped at most once * into an MM, and they cannot be partially mapped. KSM folios are * considered shared even if mapped multiple times into the same MM. * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly * indicate "mapped exclusively" (false negative) when the folio is * only partially mapped into at least one MM. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. * * Further, this function only considers current page table mappings that * are tracked using the folio mapcount(s). * * This function does not consider: * #. If the folio might get mapped in the (near) future (e.g., swapcache, * pagecache, temporary unmapping for migration). * #. If the folio is mapped differently (VM_PFNMAP). * #. If hugetlb page table sharing applies. Callers might want to check * hugetlb_pmd_shared(). * * Return: Whether the folio is estimated to be mapped into more than one MM. */ static inline bool folio_likely_mapped_shared(struct folio *folio) { … } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { … } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init … #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif static __always_inline void *lowmem_page_address(const struct page *page) { … } #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) … #define set_page_address(page, address) … #define page_address_init() … #endif static inline void *folio_address(const struct folio *folio) { … } /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(const struct page *page) { … } /* * Return true only if the folio has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool folio_is_pfmemalloc(const struct folio *folio) { … } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { … } static inline void clear_page_pfmemalloc(struct page *page) { … } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) … #define offset_in_thp(page, p) … #define offset_in_folio(folio, p) … /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { … }; /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely * drop the page in the mm, either by truncation or unmapping of the vma. By * default, the flag is not set. */ #define ZAP_FLAG_DROP_MARKER … /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP … #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit_signals(struct task_struct *t); static inline int task_mm_cid(struct task_struct *t) { … } #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } static inline int task_mm_cid(struct task_struct *t) { /* * Use the processor id as a fall-back when the mm cid feature is * disabled. This provides functional per-cpu data structure accesses * in user-space, althrough it won't provide the memory usage benefits. */ return raw_smp_processor_id(); } #endif #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); 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); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details); static inline void zap_vma_pages(struct vm_area_struct *vma) { … } void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); struct follow_pfnmap_args { … }; int follow_pfnmap_start(struct follow_pfnmap_args *args); void follow_pfnmap_end(struct follow_pfnmap_args *args); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int generic_error_remove_folio(struct address_space *mapping, struct folio *folio); struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long address, struct pt_regs *regs); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { … } static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr); 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); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, 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, struct vm_area_struct **vmap) { … } long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; struct page *get_dump_page(unsigned long addr); bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* * Whether we should manually check if we can map individual PTEs writable, * because something (e.g., COW, uffd-wp) blocks that from happening for all * PTEs automatically in a writable mapping. */ #define MM_CP_TRY_CHANGE_WRITABLE … /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA … /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP … #define MM_CP_UFFD_WP_RESOLVE … #define MM_CP_UFFD_WP_ALL … bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { … } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { … } void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { … } static inline void inc_mm_counter(struct mm_struct *mm, int member) { … } static inline void dec_mm_counter(struct mm_struct *mm, int member) { … } /* Optimized variant when folio is already known not to be anon */ static inline int mm_counter_file(struct folio *folio) { … } static inline int mm_counter(struct folio *folio) { … } static inline unsigned long get_mm_rss(struct mm_struct *mm) { … } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { … } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { … } static inline void update_hiwater_rss(struct mm_struct *mm) { … } static inline void update_hiwater_vm(struct mm_struct *mm) { … } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { … } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { … } #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP static inline bool pmd_special(pmd_t pmd) { return false; } static inline pmd_t pmd_mkspecial(pmd_t pmd) { return pmd; } #endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ #ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP static inline bool pud_special(pud_t pud) { return false; } static inline pud_t pud_mkspecial(pud_t pud) { return pud; } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { … } #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { … } static inline void mm_dec_nr_puds(struct mm_struct *mm) { … } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { … } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { … } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { … } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { … } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { … } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { … } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { … } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { … } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { … } #endif /* CONFIG_MMU */ static inline struct ptdesc *virt_to_ptdesc(const void *x) { … } static inline void *ptdesc_to_virt(const struct ptdesc *pt) { … } static inline void *ptdesc_address(const struct ptdesc *pt) { … } static inline bool pagetable_is_reserved(struct ptdesc *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_noprof(gfp_t gfp, unsigned int order) { … } #define pagetable_alloc(...) … /** * 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) { … } #if defined(CONFIG_SPLIT_PTE_PTLOCKS) #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); bool ptlock_alloc(struct ptdesc *ptdesc); void ptlock_free(struct ptdesc *ptdesc); static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { … } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) { } static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return &ptdesc->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { … } static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) { … } static inline bool ptlock_init(struct ptdesc *ptdesc) { … } #else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) { … } static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) { … } pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { … } pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { … } pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) … #define pte_alloc(mm, pmd) … #define pte_alloc_map(mm, pmd, address) … #define pte_alloc_map_lock(mm, pmd, address, ptlp) … #define pte_alloc_kernel(pmd, address) … #if defined(CONFIG_SPLIT_PMD_PTLOCKS) static inline struct page *pmd_pgtable_page(pmd_t *pmd) { … } static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd) { … } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { … } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { … } static inline void pmd_ptlock_free(struct ptdesc *ptdesc) { … } #define pmd_huge_pte(mm, pmd) … #else 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 ptdesc *ptdesc) { return true; } static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte … #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { … } static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { … } static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) { … } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { … } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { … } static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { … } static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) { … } extern void __init pagecache_init(void); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ void free_reserved_page(struct page *page); #define free_highmem_page(page) … static inline void mark_page_reserved(struct page *page) { … } static inline void free_reserved_ptdesc(struct ptdesc *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 * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { … } static inline unsigned long get_num_physpages(void) { … } /* * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif 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(void) { … } extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) … void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) … /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { … } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); static inline unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { … } extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, 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); int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { … } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* 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, unsigned long, unsigned long, unsigned long, unsigned long); struct vm_unmapped_area_info { … }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); /* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ int expand_downwards(struct vm_area_struct *vma, unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /* * Look up the first VMA which intersects the interval [start_addr, end_addr) * NULL if none. Assume start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address * @mm: The process address space. * @addr: The user address. * * Return: The vm_area_struct at the given address, %NULL otherwise. */ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { … } static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) { … } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { … } static inline unsigned long vm_end_gap(struct vm_area_struct *vma) { … } static inline unsigned long vma_pages(struct vm_area_struct *vma) { … } /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { … } static inline bool range_in_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { … } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif void vma_set_file(struct vm_area_struct *vma, struct file *file); #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { … } #ifndef io_remap_pfn_range static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { … } #endif static inline vm_fault_t vmf_error(int err) { … } /* * 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) { … } static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { … } /* * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ static inline bool gup_can_follow_protnone(struct vm_area_struct *vma, unsigned int flags) { … } pte_fn_t; extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); extern bool _page_poisoning_enabled_early; DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled); static inline bool page_poisoning_enabled(void) { … } /* * For use in fast paths after init_mem_debugging() has run, or when a * false negative result is not harmful when called too early. */ static inline bool page_poisoning_enabled_static(void) { … } static inline void kernel_poison_pages(struct page *page, int numpages) { … } static inline void kernel_unpoison_pages(struct page *page, int numpages) { … } #else static inline bool page_poisoning_enabled(void) { return false; } static inline bool page_poisoning_enabled_static(void) { return false; } static inline void __kernel_poison_pages(struct page *page, int nunmpages) { } static inline void kernel_poison_pages(struct page *page, int numpages) { } static inline void kernel_unpoison_pages(struct page *page, int numpages) { } #endif DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); static inline bool want_init_on_alloc(gfp_t flags) { … } DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { … } extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { … } /* * 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) { … } /* * To support DEBUG_PAGEALLOC architecture must ensure that * __kernel_map_pages() never fails */ extern void __kernel_map_pages(struct page *page, int numpages, int enable); #ifdef CONFIG_DEBUG_PAGEALLOC static inline void debug_pagealloc_map_pages(struct page *page, int numpages) { … } static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) { … } extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { … } static inline bool debug_guardpage_enabled(void) { … } static inline bool page_is_guard(struct page *page) { … } bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { … } void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) { … } #else /* CONFIG_DEBUG_PAGEALLOC */ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); #endif void drop_slab(void); #ifndef CONFIG_MMU #define randomize_va_space … #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); void pud_init(void *addr); void pmd_init(void *addr); void kernel_pte_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap, struct page *reuse); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, unsigned long addr, unsigned long next); int vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { … } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { … } #else static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { } #endif #define VMEMMAP_RESERVE_NR … #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { … } /* * If we don't have an architecture override, use the generic rule */ #ifndef vmemmap_can_optimize #define vmemmap_can_optimize … #endif #else static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { return false; } #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); enum mf_flags { … }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE /* * Sysfs entries for memory failure handling statistics. */ extern const struct attribute_group memory_failure_attr_group; extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { } static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void num_poisoned_pages_inc(unsigned long pfn) { } static inline void num_poisoned_pages_sub(unsigned long pfn, long i) { } #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); #else static inline void memblk_nr_poison_inc(unsigned long pfn) { } static inline void memblk_nr_poison_sub(unsigned long pfn, long i) { } #endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) { return -ENXIO; } #endif #ifndef arch_is_platform_page static inline bool arch_is_platform_page(u64 paddr) { return false; } #endif /* * Error handlers for various types of pages. */ enum mf_result { … }; enum mf_action_page_type { … }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) void folio_zero_user(struct folio *folio, unsigned long addr_hint); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? * @vma: Pointer to the struct vm_area_struct to consider * * Whether transhuge page-table entries are considered "special" following * the definition in vm_normal_page(). * * Return: true if transhuge page-table entries should be considered special, * false otherwise. */ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) { … } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { … } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif extern int sysctl_nr_trim_pages; #ifdef CONFIG_PRINTK void mem_dump_obj(void *object); #else static inline void mem_dump_obj(void *object) {} #endif /** * 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_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_write(int seals, struct vm_area_struct *vma) { … } #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name); #else static inline int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { return 0; } #endif #ifdef CONFIG_UNACCEPTED_MEMORY bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size); void accept_memory(phys_addr_t start, unsigned long size); #else static inline bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size) { return false; } static inline void accept_memory(phys_addr_t start, unsigned long size) { } #endif static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { … } void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); #ifdef CONFIG_64BIT int do_mseal(unsigned long start, size_t len_in, unsigned long flags); #else static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags) { /* noop on 32 bit */ return 0; } #endif #ifdef CONFIG_MEM_ALLOC_PROFILING static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) { int i; struct alloc_tag *tag; unsigned int nr_pages = 1 << new_order; if (!mem_alloc_profiling_enabled()) return; tag = pgalloc_tag_get(&folio->page); if (!tag) return; for (i = nr_pages; i < (1 << old_order); i += nr_pages) { union codetag_ref *ref = get_page_tag_ref(folio_page(folio, i)); if (ref) { /* Set new reference to point to the original tag */ alloc_tag_ref_set(ref, tag); put_page_tag_ref(ref); } } } static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) { struct alloc_tag *tag; union codetag_ref *ref; tag = pgalloc_tag_get(&old->page); if (!tag) return; ref = get_page_tag_ref(&new->page); if (!ref) return; /* Clear the old ref to the original allocation tag. */ clear_page_tag_ref(&old->page); /* Decrement the counters of the tag on get_new_folio. */ alloc_tag_sub(ref, folio_nr_pages(new)); __alloc_tag_ref_set(ref, tag); put_page_tag_ref(ref); } #else /* !CONFIG_MEM_ALLOC_PROFILING */ static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) { … } static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) { … } #endif /* CONFIG_MEM_ALLOC_PROFILING */ #endif /* _LINUX_MM_H */
Codebase Browser
linux