diff options
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/cgroup-defs.h | 15 | ||||
-rw-r--r-- | include/linux/compaction.h | 12 | ||||
-rw-r--r-- | include/linux/fs.h | 2 | ||||
-rw-r--r-- | include/linux/gfp.h | 2 | ||||
-rw-r--r-- | include/linux/highmem.h | 19 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 93 | ||||
-rw-r--r-- | include/linux/memcontrol.h | 148 | ||||
-rw-r--r-- | include/linux/migrate.h | 4 | ||||
-rw-r--r-- | include/linux/mm.h | 114 | ||||
-rw-r--r-- | include/linux/mm_types.h | 8 | ||||
-rw-r--r-- | include/linux/mmap_lock.h | 94 | ||||
-rw-r--r-- | include/linux/mmzone.h | 50 | ||||
-rw-r--r-- | include/linux/page-flags.h | 6 | ||||
-rw-r--r-- | include/linux/page_ext.h | 8 | ||||
-rw-r--r-- | include/linux/pagevec.h | 3 | ||||
-rw-r--r-- | include/linux/poison.h | 4 | ||||
-rw-r--r-- | include/linux/rmap.h | 1 | ||||
-rw-r--r-- | include/linux/sched/mm.h | 16 | ||||
-rw-r--r-- | include/linux/set_memory.h | 5 | ||||
-rw-r--r-- | include/linux/shmem_fs.h | 6 | ||||
-rw-r--r-- | include/linux/slab.h | 18 | ||||
-rw-r--r-- | include/linux/vmalloc.h | 8 | ||||
-rw-r--r-- | include/linux/vmstat.h | 104 |
23 files changed, 397 insertions, 343 deletions
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index fee0b5547cd0..559ee05f86b2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -668,21 +668,6 @@ struct cgroup_subsys { */ bool threaded:1; - /* - * If %false, this subsystem is properly hierarchical - - * configuration, resource accounting and restriction on a parent - * cgroup cover those of its children. If %true, hierarchy support - * is broken in some ways - some subsystems ignore hierarchy - * completely while others are only implemented half-way. - * - * It's now disallowed to create nested cgroups if the subsystem is - * broken and cgroup core will emit a warning message on such - * cases. Eventually, all subsystems will be made properly - * hierarchical and this will go away. - */ - bool broken_hierarchy:1; - bool warned_broken_hierarchy:1; - /* the following two fields are initialized automtically during boot */ int id; const char *name; diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 1de5a1151ee7..ed4070ed41ef 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -98,11 +98,8 @@ extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, int highest_zoneidx); -extern void defer_compaction(struct zone *zone, int order); -extern bool compaction_deferred(struct zone *zone, int order); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); -extern bool compaction_restarting(struct zone *zone, int order); /* Compaction has made some progress and retrying makes sense */ static inline bool compaction_made_progress(enum compact_result result) @@ -194,15 +191,6 @@ static inline enum compact_result compaction_suitable(struct zone *zone, int ord return COMPACT_SKIPPED; } -static inline void defer_compaction(struct zone *zone, int order) -{ -} - -static inline bool compaction_deferred(struct zone *zone, int order) -{ - return true; -} - static inline bool compaction_made_progress(enum compact_result result) { return false; diff --git a/include/linux/fs.h b/include/linux/fs.h index 8667d0cdc71e..1fcc2b00582b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3230,7 +3230,7 @@ static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; - if (!vma->vm_file) + if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c603237e006c..6e479e9c48ce 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -580,8 +580,6 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -extern void free_unref_page(struct page *page); -extern void free_unref_page_list(struct list_head *list); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); diff --git a/include/linux/highmem.h b/include/linux/highmem.h index f597830f26b4..d2c70d3772a3 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -204,13 +204,22 @@ static inline void clear_highpage(struct page *page) kunmap_atomic(kaddr); } +/* + * If we pass in a base or tail page, we can zero up to PAGE_SIZE. + * If we pass in a head page, we can zero up to the size of the compound page. + */ +#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +void zero_user_segments(struct page *page, unsigned start1, unsigned end1, + unsigned start2, unsigned end2); +#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ static inline void zero_user_segments(struct page *page, - unsigned start1, unsigned end1, - unsigned start2, unsigned end2) + unsigned start1, unsigned end1, + unsigned start2, unsigned end2) { void *kaddr = kmap_atomic(page); + unsigned int i; - BUG_ON(end1 > PAGE_SIZE || end2 > PAGE_SIZE); + BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); @@ -219,8 +228,10 @@ static inline void zero_user_segments(struct page *page, memset(kaddr + start2, 0, end2 - start2); kunmap_atomic(kaddr); - flush_dcache_page(page); + for (i = 0; i < compound_nr(page); i++) + flush_dcache_page(page + i); } +#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0365aa97f8e7..6a19f35f836b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -7,43 +7,37 @@ #include <linux/fs.h> /* only for vma_is_dax() */ -extern vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); -extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma); -extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); -extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pud_t *dst_pud, pud_t *src_pud, unsigned long addr, - struct vm_area_struct *vma); +vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); +int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + struct vm_area_struct *vma); +void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); +int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); +void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif -extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); -extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags); -extern bool madvise_free_huge_pmd(struct mmu_gather *tlb, - struct vm_area_struct *vma, - pmd_t *pmd, unsigned long addr, unsigned long next); -extern int zap_huge_pmd(struct mmu_gather *tlb, - struct vm_area_struct *vma, - pmd_t *pmd, unsigned long addr); -extern int zap_huge_pud(struct mmu_gather *tlb, - struct vm_area_struct *vma, - pud_t *pud, unsigned long addr); -extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, - pmd_t *old_pmd, pmd_t *new_pmd); -extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot, - unsigned long cp_flags); +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); +struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags); +bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next); +int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr); +int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, + unsigned long addr); +bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); +int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, + pgprot_t newprot, unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); @@ -100,13 +94,13 @@ enum transparent_hugepage_flag { struct kobject; struct kobj_attribute; -extern ssize_t single_hugepage_flag_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count, - enum transparent_hugepage_flag flag); -extern ssize_t single_hugepage_flag_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf, - enum transparent_hugepage_flag flag); +ssize_t single_hugepage_flag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count, + enum transparent_hugepage_flag flag); +ssize_t single_hugepage_flag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf, + enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) @@ -179,12 +173,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) -extern unsigned long thp_get_unmapped_area(struct file *filp, - unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags); +unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags); -extern void prep_transhuge_page(struct page *page); -extern void free_transhuge_page(struct page *page); +void prep_transhuge_page(struct page *page); +void free_transhuge_page(struct page *page); bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); @@ -222,16 +215,12 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, __split_huge_pud(__vma, __pud, __address); \ } while (0) -extern int hugepage_madvise(struct vm_area_struct *vma, - unsigned long *vm_flags, int advice); -extern void vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - long adjust_next); -extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, - struct vm_area_struct *vma); -extern spinlock_t *__pud_trans_huge_lock(pud_t *pud, - struct vm_area_struct *vma); +int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, + int advice); +void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, + unsigned long end, long adjust_next); +spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); +spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { @@ -294,7 +283,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); -extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 922a7f600465..f530d634f055 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -235,11 +235,6 @@ struct mem_cgroup { struct vmpressure vmpressure; /* - * Should the accounting and control be hierarchical, per subtree? - */ - bool use_hierarchy; - - /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; @@ -296,7 +291,6 @@ struct mem_cgroup { int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM - /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; @@ -589,8 +583,6 @@ static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, { if (root == memcg) return true; - if (!root->use_hierarchy) - return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } @@ -794,19 +786,15 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); -void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, - int val); -void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); - -void mod_memcg_obj_state(void *p, int idx, int val); +void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); -static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, +static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); - __mod_lruvec_slab_state(p, idx, val); + __mod_lruvec_kmem_state(p, idx, val); local_irq_restore(flags); } @@ -820,43 +808,6 @@ static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, local_irq_restore(flags); } -static inline void mod_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_lruvec_state(lruvec, idx, val); - local_irq_restore(flags); -} - -static inline void __mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) -{ - struct page *head = compound_head(page); /* rmap on tail pages */ - pg_data_t *pgdat = page_pgdat(page); - struct lruvec *lruvec; - - /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!head->mem_cgroup) { - __mod_node_page_state(pgdat, idx, val); - return; - } - - lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); - __mod_lruvec_state(lruvec, idx, val); -} - -static inline void mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_lruvec_page_state(page, idx, val); - local_irq_restore(flags); -} - unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); @@ -1215,31 +1166,7 @@ static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, { } -static inline void __mod_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ - __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); -} - -static inline void mod_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ - mod_node_page_state(lruvec_pgdat(lruvec), idx, val); -} - -static inline void __mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) -{ - __mod_node_page_state(page_pgdat(page), idx, val); -} - -static inline void mod_lruvec_page_state(struct page *page, - enum node_stat_item idx, int val) -{ - mod_node_page_state(page_pgdat(page), idx, val); -} - -static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, +static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); @@ -1247,7 +1174,7 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, __mod_node_page_state(page_pgdat(page), idx, val); } -static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, +static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); @@ -1255,10 +1182,6 @@ static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, mod_node_page_state(page_pgdat(page), idx, val); } -static inline void mod_memcg_obj_state(void *p, int idx, int val) -{ -} - static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1322,38 +1245,14 @@ static inline void __dec_memcg_page_state(struct page *page, __mod_memcg_page_state(page, idx, -1); } -static inline void __inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - __mod_lruvec_state(lruvec, idx, 1); -} - -static inline void __dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - __mod_lruvec_state(lruvec, idx, -1); -} - -static inline void __inc_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - __mod_lruvec_page_state(page, idx, 1); -} - -static inline void __dec_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - __mod_lruvec_page_state(page, idx, -1); -} - -static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) +static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { - __mod_lruvec_slab_state(p, idx, 1); + __mod_lruvec_kmem_state(p, idx, 1); } -static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) +static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx) { - __mod_lruvec_slab_state(p, idx, -1); + __mod_lruvec_kmem_state(p, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ @@ -1384,30 +1283,6 @@ static inline void dec_memcg_page_state(struct page *page, mod_memcg_page_state(page, idx, -1); } -static inline void inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, 1); -} - -static inline void dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, -1); -} - -static inline void inc_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - mod_lruvec_page_state(page, idx, 1); -} - -static inline void dec_lruvec_page_state(struct page *page, - enum node_stat_item idx) -{ - mod_lruvec_page_state(page, idx, -1); -} - static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; @@ -1568,9 +1443,8 @@ static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg, } /* - * helper for accessing a memcg's index. It will be used as an index in the - * child cache array in kmem_cache, and also to derive its name. This function - * will return -1 when this is not a kmem-limited memcg. + * A helper for accessing memcg's kmem_id, used for getting + * corresponding LRU lists. */ static inline int memcg_cache_id(struct mem_cgroup *memcg) { diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 0f8d1583fa8e..4594838a0f7c 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -45,8 +45,8 @@ extern struct page *alloc_migration_target(struct page *page, unsigned long priv extern int isolate_movable_page(struct page *page, isolate_mode_t mode); extern void putback_movable_page(struct page *page); -extern int migrate_prep(void); -extern int migrate_prep_local(void); +extern void migrate_prep(void); +extern void migrate_prep_local(void); extern void migrate_page_states(struct page *newpage, struct page *page); extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, diff --git a/include/linux/mm.h b/include/linux/mm.h index 1813fa86b981..e189509323f8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -557,8 +557,9 @@ enum page_entry_size { 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); + /* Called any time before splitting to check if it's allowed */ + int (*may_split)(struct vm_area_struct *area, unsigned long addr); + int (*mremap)(struct vm_area_struct *area, unsigned long flags); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not @@ -1723,8 +1724,8 @@ 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); +extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -2210,7 +2211,7 @@ static inline bool pgtable_pte_page_ctor(struct page *page) if (!ptlock_init(page)) return false; __SetPageTable(page); - inc_zone_page_state(page, NR_PAGETABLE); + inc_lruvec_page_state(page, NR_PAGETABLE); return true; } @@ -2218,7 +2219,7 @@ static inline void pgtable_pte_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); - dec_zone_page_state(page, NR_PAGETABLE); + dec_lruvec_page_state(page, NR_PAGETABLE); } #define pte_offset_map_lock(mm, pmd, address, ptlp) \ @@ -2305,7 +2306,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page) if (!pmd_ptlock_init(page)) return false; __SetPageTable(page); - inc_zone_page_state(page, NR_PAGETABLE); + inc_lruvec_page_state(page, NR_PAGETABLE); return true; } @@ -2313,7 +2314,7 @@ static inline void pgtable_pmd_page_dtor(struct page *page) { pmd_ptlock_free(page); __ClearPageTable(page); - dec_zone_page_state(page, NR_PAGETABLE); + dec_lruvec_page_state(page, NR_PAGETABLE); } /* @@ -2440,9 +2441,6 @@ static inline int early_pfn_to_nid(unsigned long pfn) #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); -/* there is a per-arch backend function. */ -extern int __meminit __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); @@ -2881,44 +2879,56 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); +extern void init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING -extern bool page_poisoning_enabled(void); -extern void kernel_poison_pages(struct page *page, int numpages, int enable); +extern void __kernel_poison_pages(struct page *page, int numpages); +extern void __kernel_unpoison_pages(struct page *page, int numpages); +extern bool _page_poisoning_enabled_early; +DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled); +static inline bool page_poisoning_enabled(void) +{ + return _page_poisoning_enabled_early; +} +/* + * For use in fast paths after init_mem_debugging() has run, or when a + * false negative result is not harmful when called too early. + */ +static inline bool page_poisoning_enabled_static(void) +{ + return static_branch_unlikely(&_page_poisoning_enabled); +} +static inline void kernel_poison_pages(struct page *page, int numpages) +{ + if (page_poisoning_enabled_static()) + __kernel_poison_pages(page, numpages); +} +static inline void kernel_unpoison_pages(struct page *page, int numpages) +{ + if (page_poisoning_enabled_static()) + __kernel_unpoison_pages(page, numpages); +} #else static inline bool page_poisoning_enabled(void) { return false; } -static inline void kernel_poison_pages(struct page *page, int numpages, - int enable) { } +static inline bool page_poisoning_enabled_static(void) { return false; } +static inline void __kernel_poison_pages(struct page *page, int nunmpages) { } +static inline void kernel_poison_pages(struct page *page, int numpages) { } +static inline void kernel_unpoison_pages(struct page *page, int numpages) { } #endif -#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON -DECLARE_STATIC_KEY_TRUE(init_on_alloc); -#else DECLARE_STATIC_KEY_FALSE(init_on_alloc); -#endif static inline bool want_init_on_alloc(gfp_t flags) { - if (static_branch_unlikely(&init_on_alloc) && - !page_poisoning_enabled()) + if (static_branch_unlikely(&init_on_alloc)) return true; return flags & __GFP_ZERO; } -#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON -DECLARE_STATIC_KEY_TRUE(init_on_free); -#else DECLARE_STATIC_KEY_FALSE(init_on_free); -#endif static inline bool want_init_on_free(void) { - return static_branch_unlikely(&init_on_free) && - !page_poisoning_enabled(); + return static_branch_unlikely(&init_on_free); } -#ifdef CONFIG_DEBUG_PAGEALLOC -extern void init_debug_pagealloc(void); -#else -static inline void init_debug_pagealloc(void) {} -#endif extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); @@ -2940,28 +2950,28 @@ static inline bool debug_pagealloc_enabled_static(void) return static_branch_unlikely(&_debug_pagealloc_enabled); } -#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) -extern void __kernel_map_pages(struct page *page, int numpages, int enable); - +#ifdef CONFIG_DEBUG_PAGEALLOC /* - * When called in DEBUG_PAGEALLOC context, the call should most likely be - * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static() + * To support DEBUG_PAGEALLOC architecture must ensure that + * __kernel_map_pages() never fails */ -static inline void -kernel_map_pages(struct page *page, int numpages, int enable) -{ - __kernel_map_pages(page, numpages, enable); -} -#ifdef CONFIG_HIBERNATION -extern bool kernel_page_present(struct page *page); -#endif /* CONFIG_HIBERNATION */ -#else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ -static inline void -kernel_map_pages(struct page *page, int numpages, int enable) {} -#ifdef CONFIG_HIBERNATION -static inline bool kernel_page_present(struct page *page) { return true; } -#endif /* CONFIG_HIBERNATION */ -#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ +extern void __kernel_map_pages(struct page *page, int numpages, int enable); + +static inline void debug_pagealloc_map_pages(struct page *page, int numpages) +{ + if (debug_pagealloc_enabled_static()) + __kernel_map_pages(page, numpages, 1); +} + +static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) +{ + if (debug_pagealloc_enabled_static()) + __kernel_map_pages(page, numpages, 0); +} +#else /* CONFIG_DEBUG_PAGEALLOC */ +static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} +static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} +#endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5a9238f6caad..915f4f100383 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -14,6 +14,7 @@ #include <linux/uprobes.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> +#include <linux/seqlock.h> #include <asm/mmu.h> @@ -446,6 +447,13 @@ struct mm_struct { */ atomic_t has_pinned; + /** + * @write_protect_seq: Locked when any thread is write + * protecting pages mapped by this mm to enforce a later COW, + * for instance during page table copying for fork(). + */ + seqcount_t write_protect_seq; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 18e7eae9b5ba..0540f0156f58 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -1,11 +1,65 @@ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H +#include <linux/lockdep.h> +#include <linux/mm_types.h> #include <linux/mmdebug.h> +#include <linux/rwsem.h> +#include <linux/tracepoint-defs.h> +#include <linux/types.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), +DECLARE_TRACEPOINT(mmap_lock_start_locking); +DECLARE_TRACEPOINT(mmap_lock_acquire_returned); +DECLARE_TRACEPOINT(mmap_lock_released); + +#ifdef CONFIG_TRACING + +void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write); +void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, + bool success); +void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write); + +static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, + bool write) +{ + if (tracepoint_enabled(mmap_lock_start_locking)) + __mmap_lock_do_trace_start_locking(mm, write); +} + +static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, + bool write, bool success) +{ + if (tracepoint_enabled(mmap_lock_acquire_returned)) + __mmap_lock_do_trace_acquire_returned(mm, write, success); +} + +static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) +{ + if (tracepoint_enabled(mmap_lock_released)) + __mmap_lock_do_trace_released(mm, write); +} + +#else /* !CONFIG_TRACING */ + +static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, + bool write) +{ +} + +static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, + bool write, bool success) +{ +} + +static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) +{ +} + +#endif /* CONFIG_TRACING */ + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -13,57 +67,86 @@ static inline void mmap_init_lock(struct mm_struct *mm) static inline void mmap_write_lock(struct mm_struct *mm) { + __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); + __mmap_lock_trace_acquire_returned(mm, true, true); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { + __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); + __mmap_lock_trace_acquire_returned(mm, true, true); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { - return down_write_killable(&mm->mmap_lock); + int ret; + + __mmap_lock_trace_start_locking(mm, true); + ret = down_write_killable(&mm->mmap_lock); + __mmap_lock_trace_acquire_returned(mm, true, ret == 0); + return ret; } static inline bool mmap_write_trylock(struct mm_struct *mm) { - return down_write_trylock(&mm->mmap_lock) != 0; + bool ret; + + __mmap_lock_trace_start_locking(mm, true); + ret = down_write_trylock(&mm->mmap_lock) != 0; + __mmap_lock_trace_acquire_returned(mm, true, ret); + return ret; } static inline void mmap_write_unlock(struct mm_struct *mm) { up_write(&mm->mmap_lock); + __mmap_lock_trace_released(mm, true); } static inline void mmap_write_downgrade(struct mm_struct *mm) { downgrade_write(&mm->mmap_lock); + __mmap_lock_trace_acquire_returned(mm, false, true); } static inline void mmap_read_lock(struct mm_struct *mm) { + __mmap_lock_trace_start_locking(mm, false); |