/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H #include <linux/mm_types_task.h> #include <linux/auxvec.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/maple_tree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/rcupdate.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> #include <linux/percpu_counter.h> #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH … #endif #define AT_VECTOR_SIZE … #define INIT_PASID … struct address_space; struct mem_cgroup; /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. * * If you allocate the page using alloc_pages(), you can use some of the * space in struct page for your own purposes. The five words in the main * union are available, except for bit 0 of the first word which must be * kept clear. Many users use this word to store a pointer to an object * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * * The mapcount field must not be used for own purposes. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the * refcount does not cause problems. On receiving the page from * alloc_pages(), the refcount will be positive. * * If you allocate pages of order > 0, you can use some of the fields * in each subpage, but you may need to restore some of their values * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and counters. * That requires that freelist & counters in struct slab be adjacent and * double-word aligned. Because struct slab currently just reinterprets the * bits of struct page, we align all struct pages to double-word boundaries, * and ensure that 'freelist' is aligned within struct slab. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment … #else #define _struct_page_alignment … #endif struct page { … } _struct_page_alignment; /* * struct encoded_page - a nonexistent type marking this pointer * * An 'encoded_page' pointer is a pointer to a regular 'struct page', but * with the low bits of the pointer indicating extra context-dependent * information. Only used in mmu_gather handling, and this acts as a type * system check on that use. * * We only really have two guaranteed bits in general, although you could * play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE) * for more. * * Use the supplied helper functions to endcode/decode the pointer and bits. */ struct encoded_page; #define ENCODED_PAGE_BITS … /* Perform rmap removal after we have flushed the TLB. */ #define ENCODED_PAGE_BIT_DELAY_RMAP … /* * The next item in an encoded_page array is the "nr_pages" argument, specifying * the number of consecutive pages starting from this page, that all belong to * the same folio. For example, "nr_pages" corresponds to the number of folio * references that must be dropped. If this bit is not set, "nr_pages" is * implicitly 1. */ #define ENCODED_PAGE_BIT_NR_PAGES_NEXT … static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags) { … } static inline unsigned long encoded_page_flags(struct encoded_page *page) { … } static inline struct page *encoded_page_ptr(struct encoded_page *page) { … } static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr) { … } static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page) { … } /* * A swap entry has to fit into a "unsigned long", as the entry is hidden * in the "index" field of the swapper address space. */ swp_entry_t; /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. * @lru: Least Recently Used list; tracks how recently this folio was used. * @mlock_count: Number of times this folio has been pinned by mlock(). * @mapping: The file this page belongs to, or refers to the anon_vma for * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, * this is the index from the beginning of the mmap. * @private: Filesystem per-folio data (see folio_attach_private()). * @swap: Used for swp_entry_t if folio_test_swapcache(). * @_mapcount: Do not access this member directly. Use folio_mapcount() to * find out how many times this folio is mapped by userspace. * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_large_mapcount: Do not use directly, call folio_mapcount(). * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head(). * @_deferred_list: Folios to be split under memory pressure. * @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab. * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that * same power-of-two. It is at least as large as %PAGE_SIZE. If it is * in the page cache, it is at a file offset which is a multiple of that * power-of-two. It may be mapped into userspace at an address which is * at an arbitrary page offset, but its kernel virtual address is aligned * to its size. */ struct folio { … }; #define FOLIO_MATCH … FOLIO_MATCH …; FOLIO_MATCH …; FOLIO_MATCH …; FOLIO_MATCH …; FOLIO_MATCH …; FOLIO_MATCH …; FOLIO_MATCH …; FOLIO_MATCH …; #ifdef CONFIG_MEMCG FOLIO_MATCH …; #endif #if defined(WANT_PAGE_VIRTUAL) FOLIO_MATCH(virtual, virtual); #endif #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS FOLIO_MATCH(_last_cpupid, _last_cpupid); #endif #undef FOLIO_MATCH #define FOLIO_MATCH … FOLIO_MATCH; FOLIO_MATCH; #undef FOLIO_MATCH #define FOLIO_MATCH … FOLIO_MATCH; FOLIO_MATCH; FOLIO_MATCH; FOLIO_MATCH; #undef FOLIO_MATCH /** * struct ptdesc - Memory descriptor for page tables. * @__page_flags: Same as page flags. Powerpc only. * @pt_rcu_head: For freeing page table pages. * @pt_list: List of used page tables. Used for s390 and x86. * @_pt_pad_1: Padding that aliases with page's compound head. * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. * @__page_refcount: Same as page refcount. * @pt_memcg_data: Memcg data. Tracked for page tables here. * * This struct overlays struct page for now. Do not modify without a good * understanding of the issues. */ struct ptdesc { … }; #define TABLE_MATCH … TABLE_MATCH …; TABLE_MATCH …; TABLE_MATCH …; TABLE_MATCH …; TABLE_MATCH …; TABLE_MATCH …; TABLE_MATCH …; TABLE_MATCH …; #ifdef CONFIG_MEMCG TABLE_MATCH …; #endif #undef TABLE_MATCH static_assert(…); #define ptdesc_page(pt) … #define ptdesc_folio(pt) … #define page_ptdesc(p) … /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT … #define PAGE_FRAG_CACHE_MAX_SIZE … #define PAGE_FRAG_CACHE_MAX_ORDER … /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages * should be used for data that's ancillary to the head page (eg attaching * buffer heads to tail pages after attaching buffer heads to the head page) */ #define page_private(page) … static inline void set_page_private(struct page *page, unsigned long private) { … } static inline void *folio_get_private(struct folio *folio) { … } struct page_frag_cache { … }; vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. */ struct vm_region { … }; #ifdef CONFIG_USERFAULTFD #define NULL_VM_UFFD_CTX … struct vm_userfaultfd_ctx { … }; #else /* CONFIG_USERFAULTFD */ #define NULL_VM_UFFD_CTX … struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ struct anon_vma_name { … }; #ifdef CONFIG_ANON_VMA_NAME /* * mmap_lock should be read-locked when calling anon_vma_name(). Caller should * either keep holding the lock while using the returned pointer or it should * raise anon_vma_name refcount before releasing the lock. */ struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); struct anon_vma_name *anon_vma_name_alloc(const char *name); void anon_vma_name_free(struct kref *kref); #else /* CONFIG_ANON_VMA_NAME */ static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { return NULL; } static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) { return NULL; } #endif struct vma_lock { … }; struct vma_numab_state { … }; /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). * * Only explicitly marked struct members may be accessed by RCU readers before * getting a stable reference. */ struct vm_area_struct { … } __randomize_layout; #ifdef CONFIG_NUMA #define vma_policy(vma) … #else #define vma_policy … #endif #ifdef CONFIG_SCHED_MM_CID struct mm_cid { … }; #endif struct kioctx_table; struct iommu_mm_data; struct mm_struct { … }; #define MM_MT_FLAGS … extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { … } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { … } #ifdef CONFIG_LRU_GEN struct lru_gen_mm_list { … }; #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_LRU_GEN_WALKS_MMU void lru_gen_add_mm(struct mm_struct *mm); void lru_gen_del_mm(struct mm_struct *mm); void lru_gen_migrate_mm(struct mm_struct *mm); static inline void lru_gen_init_mm(struct mm_struct *mm) { … } static inline void lru_gen_use_mm(struct mm_struct *mm) { … } #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static inline void lru_gen_add_mm(struct mm_struct *mm) { } static inline void lru_gen_del_mm(struct mm_struct *mm) { } static inline void lru_gen_migrate_mm(struct mm_struct *mm) { } static inline void lru_gen_init_mm(struct mm_struct *mm) { } static inline void lru_gen_use_mm(struct mm_struct *mm) { } #endif /* CONFIG_LRU_GEN_WALKS_MMU */ struct vma_iterator { … }; #define VMA_ITERATOR(name, __mm, __addr) … static inline void vma_iter_init(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long addr) { … } #ifdef CONFIG_SCHED_MM_CID enum mm_cid_state { … }; static inline bool mm_cid_is_unset(int cid) { … } static inline bool mm_cid_is_lazy_put(int cid) { … } static inline bool mm_cid_is_valid(int cid) { … } static inline int mm_cid_set_lazy_put(int cid) { … } static inline int mm_cid_clear_lazy_put(int cid) { … } /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { … } static inline void mm_init_cid(struct mm_struct *mm) { … } static inline int mm_alloc_cid_noprof(struct mm_struct *mm) { … } #define mm_alloc_cid(...) … static inline void mm_destroy_cid(struct mm_struct *mm) { … } static inline unsigned int mm_cid_size(void) { … } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; /** * typedef vm_fault_t - Return type for page fault handlers. * * Page fault handlers return a bitmask of %VM_FAULT values. */ vm_fault_t; /** * enum vm_fault_reason - Page fault handlers return a bitmask of * these values to tell the core VM what happened when handling the * fault. Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. * * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits * @VM_FAULT_SIGSEGV: segmentation fault * @VM_FAULT_NOPAGE: ->fault installed the pte, not return page * @VM_FAULT_LOCKED: ->fault locked the returned page * @VM_FAULT_RETRY: ->fault blocked, must retry * @VM_FAULT_FALLBACK: huge page fault failed, fall back to small * @VM_FAULT_DONE_COW: ->fault has fully handled COW * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ enum vm_fault_reason { … }; /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) … #define VM_FAULT_GET_HINDEX(x) … #define VM_FAULT_ERROR … #define VM_FAULT_RESULT_TRACE … struct vm_special_mapping { … }; enum tlb_flush_reason { … }; /** * enum fault_flag - Fault flag definitions. * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to break COW in a * COW mapping, making sure that an exclusive anon page is * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two * fault flags correctly. Currently there can be three legal combinations: * * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and * this is the first try * * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and * we've already tried at least once * * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry * * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never * be used. Note that page faults can be allowed to retry for multiple times, * in which case we'll have an initial fault with flags (a) then later on * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. * * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when * applied to mappings that are not COW mappings. */ enum fault_flag { … }; zap_flags_t; /* Flags for clear_young_dirty_ptes(). */ cydp_t; /* Clear the access bit */ #define CYDP_CLEAR_YOUNG … /* Clear the dirty bit */ #define CYDP_CLEAR_DIRTY … /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm * users like RDMA and V4L2 only establish mappings which coordinate usage with * the filesystem. Ideas for this coordination include revoking the longterm * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was * added after the problem with filesystems was found FS DAX VMAs are * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. * * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, * but an additional pin counting system) will be invoked. This is intended for * anything that gets a page reference and then touches page data (for example, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has * its own acquire and release mechanisms: * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based * calls applied to them, and that's perfectly OK. This is a constraint on the * callers, not on the pages.) * * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/core-api/pin_user_pages.rst for more information. */ enum { … }; #endif /* _LINUX_MM_TYPES_H */
Codebase Browser
linux