diff options
Diffstat (limited to 'include/linux/mm_types.h')
-rw-r--r-- | include/linux/mm_types.h | 398 |
1 files changed, 263 insertions, 135 deletions
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1ae3537c7920..500e536796ca 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -5,9 +5,11 @@ #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> @@ -84,7 +86,21 @@ struct page { * lruvec->lru_lock. Sometimes used as a generic list * by the page owner. */ - struct list_head lru; + union { + struct list_head lru; + + /* Or, for the Unevictable "LRU list" slot */ + struct { + /* Always even, to negate PageTail */ + void *__filler; + /* Count page's or folio's mlocks */ + unsigned int mlock_count; + }; + + /* Or, free page */ + struct list_head buddy_list; + struct list_head pcp_list; + }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ @@ -118,31 +134,6 @@ struct page { atomic_long_t pp_frag_count; }; }; - struct { /* slab, slob and slub */ - union { - struct list_head slab_list; - struct { /* Partial pages */ - struct page *next; -#ifdef CONFIG_64BIT - int pages; /* Nr of pages left */ -#else - short int pages; -#endif - }; - }; - struct kmem_cache *slab_cache; /* not slob */ - /* Double-word boundary */ - void *freelist; /* first free object */ - union { - void *s_mem; /* slab: first object */ - unsigned long counters; /* SLUB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; - }; - }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ @@ -150,11 +141,14 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + atomic_t compound_pincount; +#ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ +#endif }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ - atomic_t hpage_pinned_refcount; + unsigned long _compound_pad_2; /* For both global and memcg */ struct list_head deferred_list; }; @@ -206,9 +200,6 @@ struct page { * which are currently stored here. */ unsigned int page_type; - - unsigned int active; /* SLAB */ - int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ @@ -233,6 +224,18 @@ struct page { not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_KMSAN + /* + * KMSAN metadata for this page: + * - shadow page: every bit indicates whether the corresponding + * bit of the original page is initialized (0) or not (1); + * - origin page: every 4 bytes contain an id of the stack trace + * where the uninitialized value was created. + */ + struct page *kmsan_shadow; + struct page *kmsan_origin; +#endif + #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif @@ -242,6 +245,7 @@ struct page { * 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, @@ -253,6 +257,13 @@ struct page { * @_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. + * @_flags_1: For large folios, additional page flags. + * @__head: Points to the folio. Do not use. + * @_folio_dtor: Which destructor to use for this folio. + * @_folio_order: Do not use directly, call folio_order(). + * @_total_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). + * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * * 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 @@ -268,7 +279,17 @@ struct folio { struct { /* public: */ unsigned long flags; - struct list_head lru; + union { + struct list_head lru; + /* private: avoid cluttering the output */ + struct { + void *__filler; + /* public: */ + unsigned int mlock_count; + /* private: */ + }; + /* public: */ + }; struct address_space *mapping; pgoff_t index; void *private; @@ -281,13 +302,22 @@ struct folio { }; struct page page; }; + unsigned long _flags_1; + unsigned long __head; + unsigned char _folio_dtor; + unsigned char _folio_order; + atomic_t _total_mapcount; + atomic_t _pincount; +#ifdef CONFIG_64BIT + unsigned int _folio_nr_pages; +#endif }; -static_assert(sizeof(struct page) == sizeof(struct folio)); #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); +FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); @@ -297,6 +327,19 @@ FOLIO_MATCH(_refcount, _refcount); FOLIO_MATCH(memcg_data, memcg_data); #endif #undef FOLIO_MATCH +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct folio, fl) == \ + offsetof(struct page, pg) + sizeof(struct page)) +FOLIO_MATCH(flags, _flags_1); +FOLIO_MATCH(compound_head, __head); +FOLIO_MATCH(compound_dtor, _folio_dtor); +FOLIO_MATCH(compound_order, _folio_order); +FOLIO_MATCH(compound_mapcount, _total_mapcount); +FOLIO_MATCH(compound_pincount, _pincount); +#ifdef CONFIG_64BIT +FOLIO_MATCH(compound_nr, _folio_nr_pages); +#endif +#undef FOLIO_MATCH static inline atomic_t *folio_mapcount_ptr(struct folio *folio) { @@ -311,7 +354,7 @@ static inline atomic_t *compound_mapcount_ptr(struct page *page) static inline atomic_t *compound_pincount_ptr(struct page *page) { - return &page[2].hpage_pinned_refcount; + return &page[1].compound_pincount; } /* @@ -386,6 +429,12 @@ struct vm_userfaultfd_ctx { struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ +struct anon_vma_name { + struct kref kref; + /* The name needs to be at the end because it is dynamically sized. */ + char name[]; +}; + /* * 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 @@ -399,21 +448,6 @@ struct vm_area_struct { unsigned long vm_end; /* The first byte after our end address within vm_mm. */ - /* linked list of VM areas per task, sorted by address */ - struct vm_area_struct *vm_next, *vm_prev; - - struct rb_node vm_rb; - - /* - * Largest free memory gap in bytes to the left of this VMA. - * Either between this VMA and vma->vm_prev, or between one of the - * VMAs below us in the VMA rbtree and its ->vm_prev. This helps - * get_unmapped_area find a free area of the right size. - */ - unsigned long rb_subtree_gap; - - /* Second cache line starts here. */ - struct mm_struct *vm_mm; /* The address space we belong to. */ /* @@ -426,11 +460,22 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * containing the name given to the vma, or NULL if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* + * Serialized by mmap_sem. Never use directly because it is + * valid only when vm_file is NULL. Use anon_vma_name instead. + */ + struct anon_vma_name *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -466,9 +511,7 @@ struct vm_area_struct { struct kioctx_table; struct mm_struct { struct { - struct vm_area_struct *mmap; /* list of VMAs */ - struct rb_root mm_rb; - u64 vmacache_seqnum; /* per-thread vmacache */ + struct maple_tree mm_mt; #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, @@ -482,7 +525,6 @@ struct mm_struct { unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER @@ -612,27 +654,27 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and - * migrate pages to new nodes if necessary. + * numa_next_scan is the next time that PTEs will be remapped + * PROT_NONE to trigger NUMA hinting faults; such faults gather + * statistics and migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ + /* Restart point for scanning and remapping PTEs. */ unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ + /* numa_scan_seq prevents two threads remapping PTEs. */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when - * moving a PROT_NONE or PROT_NUMA mapped page. + * moving a PROT_NONE mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT @@ -643,9 +685,37 @@ struct mm_struct { #endif struct work_struct async_put_work; -#ifdef CONFIG_IOMMU_SUPPORT +#ifdef CONFIG_IOMMU_SVA u32 pasid; #endif +#ifdef CONFIG_KSM + /* + * Represent how many pages of this process are involved in KSM + * merging. + */ + unsigned long ksm_merging_pages; + /* + * Represent how many pages are checked for ksm merging + * including merged and not merged. + */ + unsigned long ksm_rmap_items; +#endif +#ifdef CONFIG_LRU_GEN + struct { + /* this mm_struct is on lru_gen_mm_list */ + struct list_head list; + /* + * Set when switching to this mm_struct, as a hint of + * whether it has been used since the last time per-node + * page table walkers cleared the corresponding bits. + */ + unsigned long bitmap; +#ifdef CONFIG_MEMCG + /* points to the memcg of "owner" above */ + struct mem_cgroup *memcg; +#endif + } lru_gen; +#endif /* CONFIG_LRU_GEN */ } __randomize_layout; /* @@ -655,6 +725,7 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ @@ -672,94 +743,91 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return (struct cpumask *)&mm->cpu_bitmap; } -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); +#ifdef CONFIG_LRU_GEN + +struct lru_gen_mm_list { + /* mm_struct list for page table walkers */ + struct list_head fifo; + /* protects the list above */ + spinlock_t lock; +}; + +void lru_gen_add_mm(struct mm_struct *mm); +void lru_gen_del_mm(struct mm_struct *mm); +#ifdef CONFIG_MEMCG +void lru_gen_migrate_mm(struct mm_struct *mm); +#endif -static inline void init_tlb_flush_pending(struct mm_struct *mm) +static inline void lru_gen_init_mm(struct mm_struct *mm) { - atomic_set(&mm->tlb_flush_pending, 0); + INIT_LIST_HEAD(&mm->lru_gen.list); + mm->lru_gen.bitmap = 0; +#ifdef CONFIG_MEMCG + mm->lru_gen.memcg = NULL; +#endif } -static inline void inc_tlb_flush_pending(struct mm_struct *mm) +static inline void lru_gen_use_mm(struct mm_struct *mm) { - atomic_inc(&mm->tlb_flush_pending); /* - * The only time this value is relevant is when there are indeed pages - * to flush. And we'll only flush pages after changing them, which - * requires the PTL. - * - * So the ordering here is: - * - * atomic_inc(&mm->tlb_flush_pending); - * spin_lock(&ptl); - * ... - * set_pte_at(); - * spin_unlock(&ptl); - * - * spin_lock(&ptl) - * mm_tlb_flush_pending(); - * .... - * spin_unlock(&ptl); - * - * flush_tlb_range(); - * atomic_dec(&mm->tlb_flush_pending); - * - * Where the increment if constrained by the PTL unlock, it thus - * ensures that the increment is visible if the PTE modification is - * visible. After all, if there is no PTE modification, nobody cares - * about TLB flushes either. - * - * This very much relies on users (mm_tlb_flush_pending() and - * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and - * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc - * locks (PPC) the unlock of one doesn't order against the lock of - * another PTL. - * - * The decrement is ordered by the flush_tlb_range(), such that - * mm_tlb_flush_pending() will not return false unless all flushes have - * completed. + * When the bitmap is set, page reclaim knows this mm_struct has been + * used since the last time it cleared the bitmap. So it might be worth + * walking the page tables of this mm_struct to clear the accessed bit. */ + WRITE_ONCE(mm->lru_gen.bitmap, -1); } -static inline void dec_tlb_flush_pending(struct mm_struct *mm) +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_add_mm(struct mm_struct *mm) { - /* - * See inc_tlb_flush_pending(). - * - * This cannot be smp_mb__before_atomic() because smp_mb() simply does - * not order against TLB invalidate completion, which is what we need. - * - * Therefore we must rely on tlb_flush_*() to guarantee order. - */ - atomic_dec(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +static inline void lru_gen_del_mm(struct mm_struct *mm) { - /* - * Must be called after having acquired the PTL; orders against that - * PTLs release and therefore ensures that if we observe the modified - * PTE we must also observe the increment from inc_tlb_flush_pending(). - * - * That is, it only guarantees to return true if there is a flush - * pending for _this_ PTL. - */ - return atomic_read(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +#ifdef CONFIG_MEMCG +static inline void lru_gen_migrate_mm(struct mm_struct *mm) { - /* - * Similar to mm_tlb_flush_pending(), we must have acquired the PTL - * for which there is a TLB flush pending in order to guarantee - * we've seen both that PTE modification and the increment. - * - * (no requirement on actually still holding the PTL, that is irrelevant) - */ - return atomic_read(&mm->tlb_flush_pending) > 1; } +#endif + +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 */ + +struct vma_iterator { + struct ma_state mas; +}; + +#define VMA_ITERATOR(name, __mm, __addr) \ + struct vma_iterator name = { \ + .mas = { \ + .tree = &(__mm)->mm_mt, \ + .index = __addr, \ + .node = MAS_START, \ + }, \ + } + +static inline void vma_iter_init(struct vma_iterator *vmi, + struct mm_struct *mm, unsigned long addr) +{ + vmi->mas.tree = &mm->mm_mt; + vmi->mas.index = addr; + vmi->mas.node = MAS_START; +} + +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; @@ -792,6 +860,7 @@ typedef __bitwise unsigned int vm_fault_t; * @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 * */ @@ -809,6 +878,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; @@ -875,4 +945,62 @@ typedef struct { unsigned long val; } swp_entry_t; +/** + * 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 unshare (and mark + * exclusive) a possibly shared anonymous page that is + * mapped R/O. + * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. + * We should only access orig_pte if this flag set. + * + * 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 + * no existing R/O-mapped anonymous page is encountered. + */ +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, + FAULT_FLAG_UNSHARE = 1 << 10, + FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, +}; + +typedef unsigned int __bitwise zap_flags_t; + #endif /* _LINUX_MM_TYPES_H */ |