/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include #ifdef __KERNEL__ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include struct mempolicy; struct anon_vma; struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; struct bdi_writeback; void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* 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) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } static inline void totalram_pages_set(long val) { atomic_long_set(&_totalram_pages, val); } extern void * high_memory; extern int page_cluster; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern const int mmap_rnd_bits_max; 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 #include #include #include #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within . * 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) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * Those architectures should provide their own implementation of "struct page" * zeroing by defining this macro in . */ #ifndef mm_zero_struct_page #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(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 (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) 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; extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) /* * 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 *); #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 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #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_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) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #ifdef CONFIG_PPC # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #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 #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ # define VM_MPX VM_HIGH_ARCH_4 #else # define VM_MPX VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #else #define VM_STACK VM_GROWSDOWN #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask is used to clear all the VMA flags used by mlock */ #define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ #define FAULT_FLAG_MKWRITE 0x02 /* Fault was mkwrite of existing pte */ #define FAULT_FLAG_ALLOW_RETRY 0x04 /* Retry fault if blocking */ #define FAULT_FLAG_RETRY_NOWAIT 0x08 /* Don't drop mmap_sem and wait when retrying */ #define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */ #define FAULT_FLAG_TRIED 0x20 /* Second try */ #define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ #define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ #define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */ #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" } /* * vm_fault is filled by the 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 { struct vm_area_struct *vma; /* Target VMA */ unsigned int flags; /* FAULT_FLAG_xxx flags */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() calls * alloc_set_pte() from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* 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 * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*split)(struct vm_area_struct * area, unsigned long addr); int (*mremap)(struct vm_area_struct * area); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); void (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; 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; INIT_LIST_HEAD(&vma->anon_vma_chain); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) #if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { return 0; } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) */ #include #include /* * 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) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } /* * 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 int get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; 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. */ static inline bool is_vmalloc_addr(const void *x) { #ifdef CONFIG_MMU unsigned long addr = (unsigned long)x; return addr >= VMALLOC_START && addr < VMALLOC_END; #else return false; #endif } #ifdef CONFIG_MMU extern int is_vmalloc_or_module_addr(const void *x); #else static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif extern void *kvmalloc_node(size_t size, gfp_t flags, int node); static inline void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } static inline void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc(bytes, flags); } static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } extern void kvfree(const void *addr); static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; } static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); return atomic_read(compound_mapcount_ptr(page)) + 1; } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } int __page_mapcount(struct page *page); static inline int page_mapcount(struct page *page) { VM_BUG_ON_PAGE(PageSlab(page), page); if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); int page_trans_huge_mapcount(struct page *page, int *total_mapcount); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } static inline int page_trans_huge_mapcount(struct page *page, int *total_mapcount) { int mapcount = page_mapcount(page); if (total_mapcount) *total_mapcount = mapcount; return mapcount; } #endif static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); /* * 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, }; extern compound_page_dtor * const compound_page_dtors[]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) { VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); page[1].compound_dtor = compound_dtor; } static inline compound_page_dtor *get_compound_page_dtor(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); return compound_page_dtors[page[1].compound_dtor]; } static inline unsigned int compound_order(struct page *page) { if (!PageHead(page)) return 0; return page[1].compound_order; } static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; } 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 * 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) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_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. */ /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #endif #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } #endif #ifdef CONFIG_DEV_PAGEMAP_OPS void dev_pagemap_get_ops(void); void dev_pagemap_put_ops(void); void __put_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool put_devmap_managed_page(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_PUBLIC: case MEMORY_DEVICE_FS_DAX: __put_devmap_managed_page(page); return true; default: break; } return false; } static inline bool is_device_private_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_device_public_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PUBLIC; } #ifdef CONFIG_PCI_P2PDMA static inline bool is_pci_p2pdma_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } #else /* CONFIG_PCI_P2PDMA */ static inline bool is_pci_p2pdma_page(const struct page *page) { return false; } #endif /* CONFIG_PCI_P2PDMA */ #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline void dev_pagemap_get_ops(void) { } static inline void dev_pagemap_put_ops(void) { } static inline bool put_devmap_managed_page(struct page *page) { return false; } static inline bool is_device_private_page(const struct page *page) { return false; } static inline bool is_device_public_page(const struct page *page) { return false; } static inline bool is_pci_p2pdma_page(const struct page *page) { return false; } #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline void get_page(struct page *page) { page = compound_head(page); /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); page_ref_inc(page); } static inline void put_page(struct page *page) { page = compound_head(page); /* * For devmap managed pages we need to catch refcount transition from * 2 to 1, when refcount reach one it means the page is free and we * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ if (put_devmap_managed_page(page)) return; if (put_page_testzero(page)) __put_page(page); } #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) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS extern int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { struct page *p = (struct page *)page; return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif #ifdef CONFIG_NUMA_BALANCING static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(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) { return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) { return page->_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) { return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } extern int page_cpupid_xchg_last(struct page *page, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* 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 1; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_KASAN_SW_TAGS static inline u8 page_kasan_tag(const struct page *page) { return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } static inline void page_kasan_tag_reset(struct page *page) { page_kasan_tag_set(page, 0xff); } #else static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } #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 static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } #ifdef CONFIG_MEMCG static inline struct mem_cgroup *page_memcg(struct page *page) { return page->mem_cgroup; } static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { WARN_ON_ONCE(!rcu_read_lock_held()); return READ_ONCE(page->mem_cgroup); } #else static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { WARN_ON_ONCE(!rcu_read_lock_held()); return NULL; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #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() do { } while(0) #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 #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); extern struct address_space *page_mapping(struct page *page); extern struct address_space *__page_file_mapping(struct page *); static inline struct address_space *page_file_mapping(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_mapping(page); return page->mapping; } extern pgoff_t __page_file_index(struct page *page); /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } bool page_mapped(struct page *page); struct address_space *page_mapping(struct page *page); struct address_space *page_mapping_file(struct page *page); /* * 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(struct page *page) { /* * Page index cannot be this large so this must be * a pfmemalloc page. */ return page->index == -1UL; } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->index = -1UL; } static inline void clear_page_pfmemalloc(struct page *page) { page->index = 0; } /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. */ #define VM_FAULT_OOM 0x0001 #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ #define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ #define VM_FAULT_SIGSEGV 0x0040 #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */ #define VM_FAULT_DONE_COW 0x1000 /* ->fault has fully handled COW */ #define VM_FAULT_NEEDDSYNC 0x2000 /* ->fault did not modify page tables * and needs fsync() to complete (for * synchronous page faults in DAX) */ #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \ VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \ VM_FAULT_FALLBACK) #define VM_FAULT_RESULT_TRACE \ { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ { VM_FAULT_WRITE, "WRITE" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ { VM_FAULT_NOPAGE, "NOPAGE" }, \ { VM_FAULT_LOCKED, "LOCKED" }, \ { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" } /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf) /* * 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) ((unsigned long)(p) & ~PAGE_MASK) /* * 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); extern bool can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ }; struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte, bool with_public_device); #define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false) 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(struct vm_area_struct *vma, unsigned long address, unsigned long size); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); /** * mm_walk - callbacks for walk_page_range * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * this handler should only handle pud_trans_huge() puds. * the pmd_entry or pte_entry callbacks will be used for * regular PUDs. * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 * value means "do page table walk over the current vma," * and a negative one means "abort current page table walk * right now." 1 means "skip the current vma." * @mm: mm_struct representing the target process of page table walk * @vma: vma currently walked (NULL if walking outside vmas) * @private: private data for callbacks' usage * * (see the comment on walk_page_range() for more details) */ struct mm_walk { int (*pud_entry)(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_entry)(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_hole)(unsigned long addr, unsigned long next, struct mm_walk *walk); int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*test_walk)(unsigned long addr, unsigned long next, struct mm_walk *walk); struct mm_struct *mm; struct vm_area_struct *vma; void *private; }; struct mmu_notifier_range; int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk); 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 mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); 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 truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags); extern int fixup_user_fault(struct task_struct *tsk, 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) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct task_struct *tsk, 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) { unmap_mapping_range(mapping, holebegin, holelen, 0); } 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 task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); #ifdef CONFIG_FS_DAX long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); #else static inline long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas) { return get_user_pages(start, nr_pages, gup_flags, pages, vmas); } #endif /* CONFIG_FS_DAX */ int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); /* Container for pinned pfns / pages */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ void *ptrs[0]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, unsigned int gup_flags, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); static inline unsigned int frame_vector_count(struct frame_vector *vec) { return vec->nr_frames; } static inline struct page **frame_vector_pages(struct frame_vector *vec) { if (vec->is_pfns) { int err = frame_vector_to_pages(vec); if (err) return ERR_PTR(err); } return (struct page **)(vec->ptrs); } static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) { if (!vec->is_pfns) frame_vector_to_pfns(vec); return (unsigned long *)(vec->ptrs); } struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); int get_kernel_page(unsigned long start, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_dirtied(struct page *page, struct address_space *mapping); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); void __cancel_dirty_page(struct page *page); static inline void cancel_dirty_page(struct page *page) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (PageDirty(page)) __cancel_dirty_page(page); } int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } #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); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); 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); extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa); extern int mprotect_fixup(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(unsigned long start, int nr_pages, int write, struct page **pages); /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { long val = atomic_long_read(&mm->rss_stat.count[member]); #ifdef SPLIT_RSS_COUNTING /* * counter is updated in asynchronous manner and may go to minus. * But it's never be expected number for users. */ if (val < 0) val = 0; #endif return (unsigned long)val; } static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { atomic_long_add(value, &mm->rss_stat.count[member]); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { atomic_long_inc(&mm->rss_stat.count[member]); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { atomic_long_dec(&mm->rss_stat.count[member]); } /* Optimized variant when page is already known not to be PageAnon */ static inline int mm_counter_file(struct page *page) { if (PageSwapBacked(page)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct page *page) { if (PageAnon(page)) return MM_ANONPAGES; return mm_counter_file(page); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss; } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *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 __HAVE_ARCH_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); 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) { pte_t *ptep; __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); return ptep; } #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) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #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) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #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); /* * The following ifdef needed to get the 4level-fixup.h header to work. * Remove it when 4level-fixup.h has been removed. */ #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) #ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } #endif /* !__ARCH_HAS_5LEVEL_HACK */ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ #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); static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct page *page) { return true; } static inline void ptlock_free(struct page *page) { } static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_page(*pmd)); } static inline bool ptlock_init(struct page *page) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * 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)) return false; spin_lock_init(ptlock_ptr(page)); return true; } #else /* !USE_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 void ptlock_cache_init(void) {} static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ static inline void pgtable_init(void) { ptlock_cache_init(); pgtable_cache_init(); } static inline bool pgtable_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; __SetPageTable(page); inc_zone_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); dec_zone_page_state(page, NR_PAGETABLE); } #define pte_offset_map_lock(mm, pmd, address, ptlp) \ ({ \ spinlock_t *__ptl = pte_lockptr(mm, pmd); \ pte_t *__pte = pte_offset_map(pmd, address); \ *(ptlp) = __ptl; \ spin_lock(__ptl); \ __pte; \ }) #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_to_page(pmd)); } static inline bool pgtable_pmd_page_ctor(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE page->pmd_huge_pte = NULL; #endif return ptlock_init(page); } static inline void pgtable_pmd_page_dtor(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON_PAGE(page->pmd_huge_pte, page); #endif ptlock_free(page); } #define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; } static inline void pgtable_pmd_page_dtor(struct page *page) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } /* * 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) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } extern void __init pagecache_init(void); extern void free_area_init(unsigned long * zones_size); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); 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); #ifdef CONFIG_HIGHMEM /* * Free a highmem page into the buddy system, adjusting totalhigh_pages * and totalram_pages. */ extern void free_highmem_page(struct page *page); #endif extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) { ClearPageReserved(page); init_page_count(page); __free_page(page); } static inline void free_reserved_page(struct page *page) { __free_reserved_page(page); adjust_managed_page_count(page, 1);