diff options
Diffstat (limited to 'include')
34 files changed, 609 insertions, 357 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); down_read(&mm->mmap_lock); + __mmap_lock_trace_acquire_returned(mm, false, true); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { - return down_read_killable(&mm->mmap_lock); + int ret; + + __mmap_lock_trace_start_locking(mm, false); + ret = down_read_killable(&mm->mmap_lock); + __mmap_lock_trace_acquire_returned(mm, false, ret == 0); + return ret; } static inline bool mmap_read_trylock(struct mm_struct *mm) { - return down_read_trylock(&mm->mmap_lock) != 0; + bool ret; + + __mmap_lock_trace_start_locking(mm, false); + ret = down_read_trylock(&mm->mmap_lock) != 0; + __mmap_lock_trace_acquire_returned(mm, false, ret); + return ret; } static inline void mmap_read_unlock(struct mm_struct *mm) { up_read(&mm->mmap_lock); + __mmap_lock_trace_released(mm, false); } static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) { - if (down_read_trylock(&mm->mmap_lock)) { + if (mmap_read_trylock(mm)) { rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); return true; } @@ -73,6 +156,7 @@ static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { up_read_non_owner(&mm->mmap_lock); + __mmap_lock_trace_released(mm, false); } static inline void mmap_assert_locked(struct mm_struct *mm) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9d0c454d23cd..98a80c01d150 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -152,7 +152,6 @@ enum zone_stat_item { NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_PAGETABLE, /* used for pagetables */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) @@ -207,6 +206,7 @@ enum node_stat_item { #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif + NR_PAGETABLE, /* used for pagetables */ NR_VM_NODE_STAT_ITEMS }; @@ -450,6 +450,12 @@ struct zone { #endif struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; + /* + * the high and batch values are copied to individual pagesets for + * faster access + */ + int pageset_high; + int pageset_batch; #ifndef CONFIG_SPARSEMEM /* @@ -1409,17 +1415,6 @@ void sparse_init(void); #endif /* CONFIG_SPARSEMEM */ /* - * During memory init memblocks map pfns to nids. The search is expensive and - * this caches recent lookups. The implementation of __early_pfn_to_nid - * may treat start/end as pfns or sections. - */ -struct mminit_pfnnid_cache { - unsigned long last_start; - unsigned long last_end; - int last_nid; -}; - -/* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we * need to check pfn validity within that MAX_ORDER_NR_PAGES block. * pfn_valid_within() should be used in this case; we optimise this away @@ -1431,37 +1426,6 @@ struct mminit_pfnnid_cache { #define pfn_valid_within(pfn) (1) #endif -#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL -/* - * pfn_valid() is meant to be able to tell if a given PFN has valid memmap - * associated with it or not. This means that a struct page exists for this - * pfn. The caller cannot assume the page is fully initialized in general. - * Hotplugable pages might not have been onlined yet. pfn_to_online_page() - * will ensure the struct page is fully online and initialized. Special pages - * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly. - * - * In FLATMEM, it is expected that holes always have valid memmap as long as - * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed - * that a valid section has a memmap for the entire section. - * - * However, an ARM, and maybe other embedded architectures in the future - * free memmap backing holes to save memory on the assumption the memmap is - * never used. The page_zone linkages are then broken even though pfn_valid() - * returns true. A walker of the full memmap must then do this additional - * check to ensure the memmap they are looking at is sane by making sure - * the zone and PFN linkages are still valid. This is expensive, but walkers - * of the full memmap are extremely rare. - */ -bool memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone); -#else -static inline bool memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone) -{ - return true; -} -#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ - #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4f6ba9379112..c1368af622c7 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -86,8 +86,7 @@ */ /* - * Don't use the *_dontuse flags. Use the macros. Otherwise you'll break - * locked- and dirty-page accounting. + * Don't use the pageflags directly. Use the PageFoo macros. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which @@ -363,8 +362,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) * for its own purposes. * - PG_private and PG_private_2 cause releasepage() and co to be invoked */ -PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY) - __CLEARPAGEFLAG(Private, private, PF_ANY) +PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index cfce186f0c4e..aff81ba31bd8 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -44,8 +44,12 @@ static inline void page_ext_init_flatmem(void) { } extern void page_ext_init(void); +static inline void page_ext_init_flatmem_late(void) +{ +} #else extern void page_ext_init_flatmem(void); +extern void page_ext_init_flatmem_late(void); static inline void page_ext_init(void) { } @@ -76,6 +80,10 @@ static inline void page_ext_init(void) { } +static inline void page_ext_init_flatmem_late(void) +{ +} + static inline void page_ext_init_flatmem(void) { } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 081d934eda64..ad4ddc17d403 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -43,9 +43,6 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec, unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); -unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, pgoff_t end, - xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { diff --git a/include/linux/poison.h b/include/linux/poison.h index dc8ae5d8db03..aff1c9250c82 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -27,11 +27,7 @@ #define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) /********** mm/page_poison.c **********/ -#ifdef CONFIG_PAGE_POISONING_ZERO -#define PAGE_POISON 0x00 -#else #define PAGE_POISON 0xaa -#endif /********** mm/page_alloc.c ************/ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 3a6adfa70fb0..70085ca1a3fc 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -91,7 +91,6 @@ enum ttu_flags { TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ - TTU_IGNORE_ACCESS = 0x10, /* don't age */ TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a91fb3ad9ec7..1ae08b8462a4 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -181,6 +181,22 @@ static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /** + * might_alloc - Mark possible allocation sites + * @gfp_mask: gfp_t flags that would be used to allocate + * + * Similar to might_sleep() and other annotations, this can be used in functions + * that might allocate, but often don't. Compiles to nothing without + * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. + */ +static inline void might_alloc(gfp_t gfp_mask) +{ + fs_reclaim_acquire(gfp_mask); + fs_reclaim_release(gfp_mask); + + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); +} + +/** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 860e0f843c12..fe1aa4e54680 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -23,6 +23,11 @@ static inline int set_direct_map_default_noflush(struct page *page) { return 0; } + +static inline bool kernel_page_present(struct page *page) +{ + return true; +} #endif #ifndef set_mce_nospec diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a5a5d1d4d7b1..d82b6f396588 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -67,7 +67,11 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); #ifdef CONFIG_SHMEM -extern bool shmem_mapping(struct address_space *mapping); +extern const struct address_space_operations shmem_aops; +static inline bool shmem_mapping(struct address_space *mapping) +{ + return mapping->a_ops == &shmem_aops; +} #else static inline bool shmem_mapping(struct address_space *mapping) { diff --git a/include/linux/slab.h b/include/linux/slab.h index dd6897f62010..be4ba5867ac5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -593,6 +593,24 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) } /** + * krealloc_array - reallocate memory for an array. + * @p: pointer to the memory chunk to reallocate + * @new_n: new number of elements to alloc + * @new_size: new size of a single member of the array + * @flags: the type of memory to allocate (see kmalloc) + */ +static __must_check inline void * +krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) + return NULL; + + return krealloc(p, bytes, flags); +} + +/** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 938eaf9517e2..80c0181c411d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -72,16 +72,14 @@ struct vmap_area { struct list_head list; /* address sorted list */ /* - * The following three variables can be packed, because - * a vmap_area object is always one of the three states: + * The following two variables can be packed, because + * a vmap_area object can be either: * 1) in "free" tree (root is vmap_area_root) - * 2) in "busy" tree (root is free_vmap_area_root) - * 3) in purge list (head is vmap_purge_list) + * 2) or "busy" tree (root is free_vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ - struct llist_node purge_list; /* in purge list */ }; }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 322dcbfcc933..773135fc6e19 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -450,4 +450,108 @@ static inline const char *vm_event_name(enum vm_event_item item) } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ +#ifdef CONFIG_MEMCG + +void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, + int val); + +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); +} + +void __mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int 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); +} + +#else + +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); +} + +#endif /* CONFIG_MEMCG */ + +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_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); +} + #endif /* _LINUX_VMSTAT_H */ diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h new file mode 100644 index 000000000000..0abff67b96f0 --- /dev/null +++ b/include/trace/events/mmap_lock.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mmap_lock + +#if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MMAP_LOCK_H + +#include <linux/tracepoint.h> +#include <linux/types.h> + +struct mm_struct; + +extern int trace_mmap_lock_reg(void); +extern void trace_mmap_lock_unreg(void); + +TRACE_EVENT_FN(mmap_lock_start_locking, + + TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), + + TP_ARGS(mm, memcg_path, write), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __string(memcg_path, memcg_path) + __field(bool, write) + ), + + TP_fast_assign( + __entry->mm = mm; + __assign_str(memcg_path, memcg_path); + __entry->write = write; + ), + + TP_printk( + "mm=%p memcg_path=%s write=%s\n", + __entry->mm, + __get_str(memcg_path), + __entry->write ? "true" : "false" + ), + + trace_mmap_lock_reg, trace_mmap_lock_unreg +); + +TRACE_EVENT_FN(mmap_lock_acquire_returned, + + TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write, + bool success), + + TP_ARGS(mm, memcg_path, write, success), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __string(memcg_path, memcg_path) + __field(bool, write) + __field(bool, success) + ), + + TP_fast_assign( + __entry->mm = mm; + __assign_str(memcg_path, memcg_path); + __entry->write = write; + __entry->success = success; + ), + + TP_printk( + "mm=%p memcg_path=%s write=%s success=%s\n", + __entry->mm, + __get_str(memcg_path), + __entry->write ? "true" : "false", + __entry->success ? "true" : "false" + ), + + trace_mmap_lock_reg, trace_mmap_lock_unreg +); + +TRACE_EVENT_FN(mmap_lock_released, + + TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), + + TP_ARGS(mm, memcg_path, write), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __string(memcg_path, memcg_path) + __field(bool, write) + ), + + TP_fast_assign( + __entry->mm = mm; + __assign_str(memcg_path, memcg_path); + __entry->write = write; + ), + + TP_printk( + "mm=%p memcg_path=%s write=%s\n", + __entry->mm, + __get_str(memcg_path), + __entry->write ? "true" : "false" + ), + + trace_mmap_lock_reg, trace_mmap_lock_unreg +); + +#endif /* _TRACE_MMAP_LOCK_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index c96a4337afe6..5039af667645 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -5,6 +5,7 @@ #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCHED_H +#include <linux/kthread.h> #include <linux/sched/numa_balancing.h> #include <linux/tracepoint.h> #include <linux/binfmts.h> @@ -51,6 +52,89 @@ TRACE_EVENT(sched_kthread_stop_ret, TP_printk("ret=%d", __entry->ret) ); +/** + * sched_kthread_work_queue_work - called when a work gets queued + * @worker: pointer to the kthread_worker + * @work: pointer to struct kthread_work + * + * This event occurs when a work is queued immediately or once a + * delayed work is actually queued (ie: once the delay has been + * reached). + */ +TRACE_EVENT(sched_kthread_work_queue_work, + + TP_PROTO(struct kthread_worker *worker, + struct kthread_work *work), + + TP_ARGS(worker, work), + + TP_STRUCT__entry( + __field( void *, work ) + __field( void *, function) + __field( void *, worker) + ), + + TP_fast_assign( + __entry->work = work; + __entry->function = work->func; + __entry->worker = worker; + ), + + TP_printk("work struct=%p function=%ps worker=%p", + __entry->work, __entry->function, __entry->worker) +); + +/** + * sched_kthread_work_execute_start - called immediately before the work callback + * @work: pointer to struct kthread_work + * + * Allows to track kthread work execution. + */ +TRACE_EVENT(sched_kthread_work_execute_start, + + TP_PROTO(struct kthread_work *work), + + TP_ARGS(work), + + TP_STRUCT__entry( + __field( void *, work ) + __field( void *, function) + ), + + TP_fast_assign( + __entry->work = work; + __entry->function = work->func; + ), + + TP_printk("work struct %p: function %ps", __entry->work, __entry->function) +); + +/** + * sched_kthread_work_execute_end - called immediately after the work callback + * @work: pointer to struct work_struct + * @function: pointer to worker function + * + * Allows to track workqueue execution. + */ +TRACE_EVENT(sched_kthread_work_execute_end, + + TP_PROTO(struct kthread_work *work, kthread_work_func_t function), + + TP_ARGS(work, function), + + TP_STRUCT__entry( + __field( void *, work ) + __field( void *, function) + ), + + TP_fast_assign( + __entry->work = work; + __entry->function = function; + ), + + TP_printk("work struct %p: function %ps", __entry->work, __entry->function) +); + /* * Tracepoint for waking up a task: */ diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index 5ed721ad5b19..af2a44c08683 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,4 +28,9 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) + +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) + #endif /* _UAPI_LINUX_CONST_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 9ca87bc73c44..cde753bb2093 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -14,7 +14,7 @@ #ifndef _UAPI_LINUX_ETHTOOL_H #define _UAPI_LINUX_ETHTOOL_H -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #include <linux/if_ether.h> diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 0ff8f7477847..fadf2db71fe8 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -3,13 +3,6 @@ #define _UAPI_LINUX_KERNEL_H #include <linux/sysinfo.h> - -/* - * 'kernel.h' contains some often-used function prototypes etc - */ -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) -#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) - -#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +#include <linux/const.h> #endif /* _UAPI_LINUX_KERNEL_H */ diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h index f9a1be7fc696..ead2e72e5c88 100644 --- a/include/uapi/linux/lightnvm.h +++ b/include/uapi/linux/lightnvm.h @@ -21,7 +21,7 @@ #define _UAPI_LINUX_LIGHTNVM_H #ifdef __KERNEL__ -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/ioctl.h> #else /* __KERNEL__ */ #include <stdio.h> diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index c36177a86516..a1fd6173e2db 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -2,7 +2,7 @@ #ifndef _UAPI__LINUX_MROUTE6_H #define _UAPI__LINUX_MROUTE6_H -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/in6.h> /* For struct sockaddr_in6. */ diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h index a8283f7dbc51..b8c6bb233ac1 100644 --- a/include/uapi/linux/netfilter/x_tables.h +++ b/include/uapi/linux/netfilter/x_tables.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_X_TABLES_H #define _UAPI_X_TABLES_H -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #define XT_FUNCTION_MAXNAMELEN 30 diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index c3816ff7bfc3..3d94269bbfa8 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -2,7 +2,7 @@ #ifndef _UAPI__LINUX_NETLINK_H #define _UAPI__LINUX_NETLINK_H -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/socket.h> /* for __kernel_sa_family_t */ #include <linux/types.h> diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 27c1ed2822e6..458179df9b27 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -23,7 +23,7 @@ #ifndef _UAPI_LINUX_SYSCTL_H #define _UAPI_LINUX_SYSCTL_H -#include <linux/kernel.h> +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index e7e98bde221f..5f2d88212f7c 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -257,4 +257,13 @@ struct uffdio_writeprotect { __u64 mode; }; +/* + * Flags for the userfaultfd(2) system call itself. + */ + +/* + * Create a userfaultfd that can handle page faults only in user mode. + */ +#define UFFD_USER_MODE_ONLY 1 + #endif /* _LINUX_USERFAULTFD_H */ |