diff options
Diffstat (limited to 'include')
49 files changed, 771 insertions, 466 deletions
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 62cac266a1c8..eeff40295b4b 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -46,6 +46,9 @@ acpi_status acpi_os_terminate(void); * Interrupts are off during resume, just like they are for boot. * However, boot has (system_state != SYSTEM_RUNNING) * to quiet __might_sleep() in kmalloc() and resume does not. + * + * These specialized allocators have to be macros for their allocations to be + * accounted separately (to have separate alloc_tag). */ #define acpi_os_allocate(_size) \ kmalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) @@ -53,14 +56,14 @@ acpi_status acpi_os_terminate(void); #define acpi_os_allocate_zeroed(_size) \ kzalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) +#define acpi_os_acquire_object(_cache) \ + kmem_cache_zalloc(_cache, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) + static inline void acpi_os_free(void *memory) { kfree(memory); } -#define acpi_os_acquire_object(_cache) \ - kmem_cache_zalloc(_cache, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) - static inline acpi_thread_id acpi_os_get_thread_id(void) { return (acpi_thread_id) (unsigned long)current; diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 6dcf4d576970..594d5905f615 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -144,7 +144,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, #endif #ifndef __HAVE_ARCH_HUGE_PTEP_GET -static inline pte_t huge_ptep_get(pte_t *ptep) +static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { return ptep_get(ptep); } diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index abd24016a900..8c61ccd161ba 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -122,7 +122,7 @@ static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag "alloc_tag was not cleared (got tag for %s:%u)\n", ref->ct->filename, ref->ct->lineno); - WARN_ONCE(!tag, "current->alloc_tag not set"); + WARN_ONCE(!tag, "current->alloc_tag not set\n"); } static inline void alloc_tag_sub_check(union codetag_ref *ref) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f1d4a97b9d1..3b94ec161e8c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -275,7 +275,7 @@ struct bpf_map { u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; @@ -2253,7 +2253,7 @@ struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array); -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); @@ -2262,6 +2262,10 @@ void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else +/* + * These specialized allocators have to be macros for their allocations to be + * accounted separately (to have separate alloc_tag). + */ #define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ kmalloc_node(_size, _flags, _node) #define bpf_map_kzalloc(_map, _size, _flags) \ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index e022e40b099e..14acf1bbe0ce 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -53,7 +53,7 @@ typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within - * a page (via a page_mapping) and for wrapping bio submission + * a folio (via a folio_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index b36690ca0d3f..293af7f8a694 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -681,9 +681,7 @@ struct cftype { __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); -#ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; -#endif }; /* diff --git a/include/linux/damon.h b/include/linux/damon.h index f7da65e1ac04..27c546bfc6d4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -105,6 +105,8 @@ struct damon_target { * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. + * @DAMOS_MIGRATE_HOT: Migrate the regions prioritizing warmer regions. + * @DAMOS_MIGRATE_COLD: Migrate the regions prioritizing colder regions. * @DAMOS_STAT: Do nothing but count the stat. * @NR_DAMOS_ACTIONS: Total number of DAMOS actions * @@ -122,6 +124,8 @@ enum damos_action { DAMOS_NOHUGEPAGE, DAMOS_LRU_PRIO, DAMOS_LRU_DEPRIO, + DAMOS_MIGRATE_HOT, + DAMOS_MIGRATE_COLD, DAMOS_STAT, /* Do nothing but only record the stat */ NR_DAMOS_ACTIONS, }; @@ -374,6 +378,7 @@ struct damos_access_pattern { * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. + * @target_nid: Destination node if @action is "migrate_{hot,cold}". * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. @@ -389,6 +394,10 @@ struct damos_access_pattern { * monitoring context are inactive, DAMON stops monitoring either, and just * repeatedly checks the watermarks. * + * @target_nid is used to set the migration target node for migrate_hot or + * migrate_cold actions, which means it's only meaningful when @action is either + * "migrate_hot" or "migrate_cold". + * * Before applying the &action to a memory region, &struct damon_operations * implementation could check pages of the region and skip &action to respect * &filters @@ -410,6 +419,9 @@ struct damos { /* public: */ struct damos_quota quota; struct damos_watermarks wmarks; + union { + int target_nid; + }; struct list_head filters; struct damos_stat stat; struct list_head list; @@ -726,9 +738,11 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, enum damos_action action, unsigned long apply_interval_us, struct damos_quota *quota, - struct damos_watermarks *wmarks); + struct damos_watermarks *wmarks, + int target_nid); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); +int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src); struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); @@ -742,6 +756,7 @@ void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); +int damon_commit_ctx(struct damon_ctx *old_ctx, struct damon_ctx *new_ctx); int damon_nr_running_ctxs(void); bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index ad9e2506c2f4..68c3c1e41014 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -85,6 +85,10 @@ dma_fence_chain_contained(struct dma_fence *fence) * dma_fence_chain_alloc * * Returns a new struct dma_fence_chain object or NULL on failure. + * + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. */ #define dma_fence_chain_alloc() \ ((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL)) diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 6d5edef09d45..354413950d34 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -91,22 +91,19 @@ static inline void fault_config_init(struct fault_config *config, struct kmem_cache; -bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); - #ifdef CONFIG_FAIL_PAGE_ALLOC -bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); +bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); #else -static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return false; } #endif /* CONFIG_FAIL_PAGE_ALLOC */ -int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB -extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); +int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #else -static inline bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) +static inline int should_failslab(struct kmem_cache *s, gfp_t gfpflags) { return false; } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7f9691d375f0..f53f76e0b17e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -303,6 +303,8 @@ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); +struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #else @@ -319,6 +321,11 @@ static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } +static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid) +{ + return folio_alloc_noprof(gfp, order); +} #define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ folio_alloc_noprof(gfp, order) #endif @@ -326,6 +333,7 @@ static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) #define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) +#define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 9ca96fc90449..d4d063cf63b5 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -228,6 +228,11 @@ static inline int hid_bpf_connect_device(struct hid_device *hdev) { return 0; } static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {} static inline void hid_bpf_destroy_device(struct hid_device *hid) {} static inline int hid_bpf_device_init(struct hid_device *hid) { return 0; } +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ #define call_hid_bpf_rdesc_fixup(_hdev, _rdesc, _size) \ ((u8 *)kmemdup(_rdesc, *(_size), GFP_KERNEL)) diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a3028e400a9c..dd100e849f5e 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -131,22 +131,17 @@ static inline void __kunmap_atomic(const void *addr) preempt_enable(); } -unsigned int __nr_free_highpages(void); -extern atomic_long_t _totalhigh_pages; +unsigned long __nr_free_highpages(void); +unsigned long __totalhigh_pages(void); -static inline unsigned int nr_free_highpages(void) +static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { - return (unsigned long)atomic_long_read(&_totalhigh_pages); -} - -static inline void totalhigh_pages_add(long count) -{ - atomic_long_add(count, &_totalhigh_pages); + return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) @@ -239,8 +234,8 @@ static inline void __kunmap_atomic(const void *addr) preempt_enable(); } -static inline unsigned int nr_free_highpages(void) { return 0; } -static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline unsigned long nr_free_highpages(void) { return 0; } +static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 00341b56d291..930a591b9b61 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -179,7 +179,7 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ -static inline unsigned int nr_free_highpages(void); +static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE @@ -352,6 +352,9 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, kunmap_local(vto); kunmap_local(vfrom); + if (ret) + memory_failure_queue(page_to_pfn(from), 0); + return ret; } @@ -368,6 +371,9 @@ static inline int copy_mc_highpage(struct page *to, struct page *from) kunmap_local(vto); kunmap_local(vfrom); + if (ret) + memory_failure_queue(page_to_pfn(from), 0); + return ret; } #else diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2aa986a5cd1b..cff002be83eb 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -6,6 +6,7 @@ #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ +#include <linux/kobject.h> 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, @@ -63,6 +64,7 @@ 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; +extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for anonymous THP; all orders up to @@ -126,18 +128,6 @@ static inline bool hugepage_global_always(void) (1<<TRANSPARENT_HUGEPAGE_FLAG); } -static inline bool hugepage_flags_enabled(void) -{ - /* - * We cover both the anon and the file-backed case here; we must return - * true if globally enabled, even when all anon sizes are set to never. - * So we don't need to look at huge_anon_orders_inherit. - */ - return hugepage_global_enabled() || - huge_anon_orders_always || - huge_anon_orders_madvise; -} - static inline int highest_order(unsigned long orders) { return fls_long(orders) - 1; @@ -265,12 +255,26 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); } +struct thpsize { + struct kobject kobj; + struct list_head node; + int order; +}; + +#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) + enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, + MTHP_STAT_SHMEM_ALLOC, + MTHP_STAT_SHMEM_FALLBACK, + MTHP_STAT_SHMEM_FALLBACK_CHARGE, + MTHP_STAT_SPLIT, + MTHP_STAT_SPLIT_FAILED, + MTHP_STAT_SPLIT_DEFERRED, __MTHP_STAT_COUNT }; @@ -415,6 +419,11 @@ static inline bool thp_migration_supported(void) return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } +void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, bool freeze, struct folio *folio); +bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmdp, struct folio *folio); + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool folio_test_pmd_mappable(struct folio *folio) @@ -477,6 +486,16 @@ static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) {} +static inline void split_huge_pmd_locked(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + bool freeze, struct folio *folio) {} + +static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp, + struct folio *folio) +{ + return false; +} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) @@ -550,6 +569,16 @@ static inline bool thp_migration_supported(void) { return false; } + +static inline int highest_order(unsigned long orders) +{ + return 0; +} + +static inline int next_order(unsigned long *orders, int prev) +{ + return 0; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int split_folio_to_list_to_order(struct folio *folio, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2b3c3a404769..c9bf68c239a0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,12 +20,6 @@ struct user_struct; struct mmu_gather; struct node; -#ifndef CONFIG_ARCH_HAS_HUGEPD -typedef struct { unsigned long pd; } hugepd_t; -#define is_hugepd(hugepd) (0) -#define __hugepd(x) ((hugepd_t) { (x) }) -#endif - void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE @@ -616,47 +610,35 @@ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ - } \ -static inline int HPage##uname(struct page *page) \ - { return test_bit(HPG_##flname, &(page->private)); } + } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ - } \ -static inline void SetHPage##uname(struct page *page) \ - { set_bit(HPG_##flname, &(page->private)); } + } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ - } \ -static inline void ClearHPage##uname(struct page *page) \ - { clear_bit(HPG_##flname, &(page->private)); } + } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ - { return 0; } \ -static inline int HPage##uname(struct page *page) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ - { } \ -static inline void SetHPage##uname(struct page *page) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ - { } \ -static inline void ClearHPage##uname(struct page *page) \ { } #endif @@ -681,6 +663,7 @@ HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; + struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; @@ -698,11 +681,6 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_CGROUP_HUGETLB - /* cgroup control files */ - struct cftype cgroup_files_dfl[8]; - struct cftype cgroup_files_legacy[10]; -#endif char name[HSTATE_NAME_LEN]; }; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index b900c642210c..5157d92b6f23 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1595,6 +1595,11 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); */ extern struct kmem_cache *jbd2_handle_cache; +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ #define jbd2_alloc_handle(_gfp_flags) \ ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) @@ -1609,6 +1614,11 @@ static inline void jbd2_free_handle(handle_t *handle) */ extern struct kmem_cache *jbd2_inode_cache; +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ #define jbd2_alloc_inode(_gfp_flags) \ ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e0c23a32cdf0..2b1432cc16d5 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -230,6 +230,67 @@ void kmsan_handle_urb(const struct urb *urb, bool is_out); */ void kmsan_unpoison_entry_regs(const struct pt_regs *regs); +/** + * kmsan_get_metadata() - Return a pointer to KMSAN shadow or origins. + * @addr: kernel address. + * @is_origin: whether to return origins or shadow. + * + * Return NULL if metadata cannot be found. + */ +void *kmsan_get_metadata(void *addr, bool is_origin); + +/** + * kmsan_enable_current(): Enable KMSAN for the current task. + * + * Each kmsan_enable_current() current call must be preceded by a + * kmsan_disable_current() call. These call pairs may be nested. + */ +void kmsan_enable_current(void); + +/** + * kmsan_disable_current(): Disable KMSAN for the current task. + * + * Each kmsan_disable_current() current call must be followed by a + * kmsan_enable_current() call. These call pairs may be nested. + */ +void kmsan_disable_current(void); + +/** + * memset_no_sanitize_memory(): Fill memory without KMSAN instrumentation. + * @s: address of kernel memory to fill. + * @c: constant byte to fill the memory with. + * @n: number of bytes to fill. + * + * This is like memset(), but without KMSAN instrumentation. + */ +static inline void *memset_no_sanitize_memory(void *s, int c, size_t n) +{ + return __memset(s, c, n); +} + +extern bool kmsan_enabled; +extern int panic_on_kmsan; + +/* + * KMSAN performs a lot of consistency checks that are currently enabled by + * default. BUG_ON is normally discouraged in the kernel, unless used for + * debugging, but KMSAN itself is a debugging tool, so it makes little sense to + * recover if something goes wrong. + */ +#define KMSAN_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) { \ + WRITE_ONCE(kmsan_enabled, false); \ + if (panic_on_kmsan) { \ + /* Can't call panic() here because */ \ + /* of uaccess checks. */ \ + BUG(); \ + } \ + } \ + __cond; \ + }) + #else static inline void kmsan_init_shadow(void) @@ -329,6 +390,21 @@ static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs) { } +static inline void kmsan_enable_current(void) +{ +} + +static inline void kmsan_disable_current(void) +{ +} + +static inline void *memset_no_sanitize_memory(void *s, int c, size_t n) +{ + return memset(s, c, n); +} + +#define KMSAN_WARN_ON WARN_ON + #endif #endif /* _LINUX_KMSAN_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h index 929287981afe..dfc59918b3c0 100644 --- a/include/linux/kmsan_types.h +++ b/include/linux/kmsan_types.h @@ -31,7 +31,7 @@ struct kmsan_context_state { struct kmsan_ctx { struct kmsan_context_state cstate; int kmsan_in_runtime; - bool allow_reporting; + unsigned int depth; }; #endif /* _LINUX_KMSAN_TYPES_H */ diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 792b67ceb631..5099a8ccd5f4 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -50,7 +50,7 @@ struct list_lru_node { struct list_lru { struct list_lru_node *node; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct list_head list; int shrinker_id; bool memcg_aware; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 45cac33334c8..fc4d75c6cec3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -316,8 +316,6 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, for (; i != U64_MAX; \ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) -int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); - #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 030d34e9d117..7e2eb091049a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -69,18 +69,6 @@ struct mem_cgroup_id { refcount_t ref; }; -/* - * Per memcg event counter is incremented at every pagein/pageout. With THP, - * it will be incremented by the number of pages. This counter is used - * to trigger some periodic events. This is straightforward and better - * than using jiffies etc. to handle periodic memcg event. - */ -enum mem_cgroup_events_target { - MEM_CGROUP_TARGET_THRESH, - MEM_CGROUP_TARGET_SOFTLIMIT, - MEM_CGROUP_NTARGETS, -}; - struct memcg_vmstats_percpu; struct memcg_vmstats; struct lruvec_stats_percpu; @@ -96,23 +84,33 @@ struct mem_cgroup_reclaim_iter { * per-node information in memory controller. */ struct mem_cgroup_per_node { - struct lruvec lruvec; + /* Keep the read-only fields at the start */ + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; struct lruvec_stats *lruvec_stats; - - unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; - - struct mem_cgroup_reclaim_iter iter; - struct shrinker_info __rcu *shrinker_info; +#ifdef CONFIG_MEMCG_V1 + /* + * Memcg-v1 only stuff in middle as buffer between read mostly fields + * and update often fields to avoid false sharing. If v1 stuff is + * not present, an explicit padding is needed. + */ + struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; - struct mem_cgroup *memcg; /* Back pointer, we cannot */ - /* use container_of */ +#else + CACHELINE_PADDING(_pad1_); +#endif + + /* Fields which get updated often at the end. */ + struct lruvec lruvec; + unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; + struct mem_cgroup_reclaim_iter iter; }; struct mem_cgroup_threshold { @@ -194,14 +192,10 @@ struct mem_cgroup { struct page_counter memsw; /* v1 only */ }; - /* Legacy consumer-oriented counters */ - struct page_counter kmem; /* v1 only */ - struct page_counter tcpmem; /* v1 only */ - /* Range enforcement for interrupt charges */ struct work_struct high_work; -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +#ifdef CONFIG_ZSWAP unsigned long zswap_max; /* @@ -211,8 +205,6 @@ struct mem_cgroup { bool zswap_writeback; #endif - unsigned long soft_limit; - /* vmpressure notifications */ struct vmpressure vmpressure; @@ -221,13 +213,7 @@ struct mem_cgroup { */ bool oom_group; - /* protected by memcg_oom_lock */ - bool oom_lock; - int under_oom; - - int swappiness; - /* OOM-Killer disable */ - int oom_kill_disable; + int swappiness; /* memory.events and memory.events.local */ struct cgroup_file events_file; @@ -236,29 +222,6 @@ struct mem_cgroup { /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; - /* protect arrays of thresholds */ - struct mutex thresholds_lock; - - /* thresholds for memory usage. RCU-protected */ - struct mem_cgroup_thresholds thresholds; - - /* thresholds for mem+swap usage. RCU-protected */ - struct mem_cgroup_thresholds memsw_thresholds; - - /* For oom notifier event fd */ - struct list_head oom_notify; - - /* - * Should we move charges of a task when a task is moved into this - * mem_cgroup ? And what type of charges should we move ? - */ - unsigned long move_charge_at_immigrate; - /* taken only while moving_account > 0 */ - spinlock_t move_lock; - unsigned long move_lock_flags; - - CACHELINE_PADDING(_pad1_); - /* memory.stat */ struct memcg_vmstats *vmstats; @@ -273,11 +236,6 @@ struct mem_cgroup { */ unsigned long socket_pressure; - /* Legacy tcp memory accounting */ - bool tcpmem_active; - int tcpmem_pressure; - -#ifdef CONFIG_MEMCG_KMEM int kmemcg_id; /* * memcg->objcg is wiped out as a part of the objcg repaprenting @@ -288,15 +246,6 @@ struct mem_cgroup { struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; -#endif - - CACHELINE_PADDING(_pad2_); - - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; struct memcg_vmstats_percpu __percpu *vmstats_percpu; @@ -306,10 +255,6 @@ struct mem_cgroup { struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif - /* List of events which userspace want to receive */ - struct list_head event_list; - spinlock_t event_list_lock; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif @@ -319,6 +264,56 @@ struct mem_cgroup { struct lru_gen_mm_list mm_list; #endif +#ifdef CONFIG_MEMCG_V1 + /* Legacy consumer-oriented counters */ + struct page_counter kmem; /* v1 only */ + struct page_counter tcpmem; /* v1 only */ + + unsigned long soft_limit; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + /* OOM-Killer disable */ + int oom_kill_disable; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + unsigned long move_lock_flags; + + /* Legacy tcp memory accounting */ + bool tcpmem_active; + int tcpmem_pressure; + + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + struct task_struct *move_lock_task; + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; +#endif /* CONFIG_MEMCG_V1 */ + struct mem_cgroup_per_node *nodeinfo[]; }; @@ -443,11 +438,6 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return __folio_memcg(folio); } -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return folio_memcg(page_folio(page)); -} - /** * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. * @folio: Pointer to the folio. @@ -540,7 +530,6 @@ retry: return memcg; } -#ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. @@ -556,15 +545,6 @@ static inline bool folio_memcg_kmem(struct folio *folio) return folio->memcg_data & MEMCG_DATA_KMEM; } - -#else -static inline bool folio_memcg_kmem(struct folio *folio) -{ - return false; -} - -#endif - static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); @@ -949,51 +929,13 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); -static inline void mem_cgroup_enter_user_fault(void) -{ - WARN_ON(current->in_user_fault); - current->in_user_fault = 1; -} - -static inline void mem_cgroup_exit_user_fault(void) -{ - WARN_ON(!current->in_user_fault); - current->in_user_fault = 0; -} - -static inline bool task_in_memcg_oom(struct task_struct *p) -{ - return p->memcg_in_oom; -} - -bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -void folio_memcg_lock(struct folio *folio); -void folio_memcg_unlock(struct folio *folio); - void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val); -/* try to stablize folio_memcg() for all the pages in a memcg */ -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - rcu_read_lock(); - - if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) - return true; - - rcu_read_unlock(); - return false; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} - /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val) @@ -1014,7 +956,7 @@ static inline void mod_memcg_page_state(struct page *page, return; rcu_read_lock(); - memcg = page_memcg(page); + memcg = folio_memcg(page_folio(page)); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); @@ -1120,10 +1062,6 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, void split_page_memcg(struct page *head, int old_order, int new_order); -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); - #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 @@ -1133,11 +1071,6 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return NULL; } -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return NULL; -} - static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { WARN_ON_ONCE(!rcu_read_lock_held()); @@ -1439,48 +1372,10 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } -static inline void folio_memcg_lock(struct folio *folio) -{ -} - -static inline void folio_memcg_unlock(struct folio *folio) -{ -} - -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - /* to match folio_memcg_rcu() */ - rcu_read_lock(); - return true; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} - static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } -static inline void mem_cgroup_enter_user_fault(void) -{ -} - -static inline void mem_cgroup_exit_user_fault(void) -{ -} - -static inline bool task_in_memcg_oom(struct task_struct *p) -{ - return false; -} - -static inline bool mem_cgroup_oom_synchronize(bool wait) -{ - return false; -} - static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { @@ -1574,14 +1469,6 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) static inline void split_page_memcg(struct page *head, int old_order, int new_order) { } - -static inline -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) -{ - return 0; -} #endif /* CONFIG_MEMCG */ /* @@ -1589,7 +1476,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, * if MEMCG_DATA_OBJEXTS is set. */ struct slabobj_ext { -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING @@ -1636,7 +1523,7 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } -/* Test requires a stable page->memcg binding, see page_memcg() */ +/* Test requires a stable folio->memcg binding, see folio_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { @@ -1734,8 +1621,10 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { +#ifdef CONFIG_MEMCG_V1 if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return !!memcg->tcpmem_pressure; +#endif /* CONFIG_MEMCG_V1 */ do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; @@ -1762,7 +1651,7 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg, } #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); @@ -1905,9 +1794,9 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG */ -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +#if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); @@ -1932,4 +1821,100 @@ static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) } #endif + +/* Cgroup v1-related declarations */ + +#ifdef CONFIG_MEMCG_V1 +unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); + +bool mem_cgroup_oom_synchronize(bool wait); + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return p->memcg_in_oom; +} + +void folio_memcg_lock(struct folio *folio); +void folio_memcg_unlock(struct folio *folio); + +/* try to stablize folio_memcg() for all the pages in a memcg */ +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + rcu_read_lock(); + + if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) + return true; + + rcu_read_unlock(); + return false; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + +static inline void mem_cgroup_enter_user_fault(void) +{ + WARN_ON(current->in_user_fault); + current->in_user_fault = 1; +} + +static inline void mem_cgroup_exit_user_fault(void) +{ + WARN_ON(!current->in_user_fault); + current->in_user_fault = 0; +} + +#else /* CONFIG_MEMCG_V1 */ +static inline +unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + return 0; +} + +static inline void folio_memcg_lock(struct folio *folio) +{ +} + +static inline void folio_memcg_unlock(struct folio *folio) +{ +} + +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + /* to match folio_memcg_rcu() */ + rcu_read_lock(); + return true; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return false; +} + +static inline bool mem_cgroup_oom_synchronize(bool wait) +{ + return false; +} + +static inline void mem_cgroup_enter_user_fault(void) +{ +} + +static inline void mem_cgroup_exit_user_fault(void) +{ +} + +#endif /* CONFIG_MEMCG_V1 */ + #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memfd.h b/include/linux/memfd.h index e7abf6fa4c52..3f2cf339ceaf 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -6,11 +6,16 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); +struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } +static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) +{ + return ERR_PTR(-EINVAL); +} #endif #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 0d70788558f4..0dc0cf2863e2 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -38,6 +38,7 @@ struct access_coordinate; #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; extern struct memory_dev_type *default_dram_type; +extern nodemask_t default_dram_nodes; struct memory_dev_type *alloc_memory_type(int adistance); void put_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); @@ -76,6 +77,7 @@ static inline bool node_is_toptier(int node) #define numa_demotion_enabled false #define default_dram_type NULL +#define default_dram_nodes NODE_MASK_NONE /* * CONFIG_NUMA implementation returns non NULL error. */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7a9ff464608d..ebe876930e78 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -175,8 +175,8 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern void __offline_isolated_pages(unsigned long start_pfn, - unsigned long end_pfn); +extern unsigned long __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn); typedef void (*online_page_callback_t)(struct page *page, unsigned int order); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 2ce13e8a309b..644be30b69c8 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -63,8 +63,6 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION void putback_movable_pages(struct list_head *l); -int migrate_folio_extra(struct address_space *mapping, struct folio *dst, - struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free, @@ -78,7 +76,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); -void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); @@ -142,9 +139,16 @@ const struct movable_operations *page_movable_ops(struct page *page) } #ifdef CONFIG_NUMA_BALANCING +int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node); int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node); #else +static inline int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node) +{ + return -EAGAIN; /* can't migrate now */ +} static inline int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node) { diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index f37cc03f9369..265c4328b36a 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -7,16 +7,11 @@ * on most operations but not ->writepage as the potential stall time * is too significant * MIGRATE_SYNC will block when migrating pages - * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages - * with the CPU. Instead, page copy happens outside the migratepage() - * callback and is likely using a DMA engine. See migrate_vma() and HMM - * (mm/hmm.c) for users of this mode. */ enum migrate_mode { MIGRATE_ASYNC, MIGRATE_SYNC_LIGHT, MIGRATE_SYNC, - MIGRATE_SYNC_NO_COPY, }; enum migrate_reason { @@ -29,6 +24,7 @@ enum migrate_reason { MR_CONTIG_RANGE, MR_LONGTERM_PIN, MR_DEMOTION, + MR_DAMON, MR_TYPES }; diff --git a/include/linux/mm.h b/include/linux/mm.h index ab3d78116043..7d044e737dba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1202,8 +1202,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for - * debugging purposes - it does not include PTE-mapped sub-pages; look - * at folio_mapcount() or page_mapcount() instead. + * debugging purposes or implementation of other core folio_*() primitives. */ static inline int folio_entire_mapcount(const struct folio *folio) { @@ -1211,40 +1210,6 @@ static inline int folio_entire_mapcount(const struct folio *folio) return atomic_read(&folio->_entire_mapcount) + 1; } -/* - * The atomic page->_mapcount, starts from -1: so that transitions - * both from it and to it can be tracked, using atomic_inc_and_test - * and atomic_add_negative(-1). - */ -static inline void page_mapcount_reset(struct page *page) -{ - atomic_set(&(page)->_mapcount, -1); -} - -/** - * page_mapcount() - Number of times this precise page is mapped. - * @page: The page. - * - * The number of times this page is mapped. If this page is part of - * a large folio, it includes the number of times this page is mapped - * as part of that folio. - * - * Will report 0 for pages which cannot be mapped into userspace, eg - * slab, page tables and similar. - */ -static inline int page_mapcount(struct page *page) -{ - int mapcount = atomic_read(&page->_mapcount) + 1; - - /* Handle page_has_type() pages */ - if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) - mapcount = 0; - if (unlikely(PageCompound(page))) - mapcount += folio_entire_mapcount(page_folio(page)); - - return mapcount; -} - static inline int folio_large_mapcount(const struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); @@ -1326,6 +1291,7 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); +int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); @@ -1612,17 +1578,19 @@ static inline void put_page(struct page *page) * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() - * provides safe operation for get_user_pages(), page_mkclean() and + * provides safe operation for get_user_pages(), folio_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); +void unpin_folio(struct folio *folio); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); +void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) { @@ -1953,8 +1921,8 @@ static inline struct folio *pfn_folio(unsigned long pfn) * * For more information, please see Documentation/core-api/pin_user_pages.rst. * - * Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. + * Return: True, if it is likely that the folio has been "dma-pinned". + * False, if the folio is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { @@ -1973,11 +1941,6 @@ static inline bool folio_maybe_dma_pinned(struct folio *folio) GUP_PIN_COUNTING_BIAS; } -static inline bool page_maybe_dma_pinned(struct page *page) -{ - return folio_maybe_dma_pinned(page_folio(page)); -} - /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. @@ -2295,19 +2258,6 @@ static inline void *folio_address(const struct folio *folio) return page_address(&folio->page); } -extern pgoff_t __page_file_index(struct page *page); - -/* - * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use swp_offset(->private) - */ -static inline pgoff_t page_index(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return __page_file_index(page); - return page->index; -} - /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not @@ -2550,6 +2500,9 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, + struct folio **folios, unsigned int max_folios, + pgoff_t *offset); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); @@ -4038,7 +3991,6 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); -struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { @@ -4059,12 +4011,6 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i) } #endif -#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) -void add_to_kill_ksm(struct task_struct *tsk, struct page *p, - struct vm_area_struct *vma, struct list_head *to_kill, - unsigned long ksm_addr); -#endif - #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); @@ -4105,10 +4051,10 @@ enum mf_result { enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, - MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, + MF_MSG_GET_HWPOISON, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, @@ -4122,13 +4068,12 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, + MF_MSG_ALREADY_POISONED, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) -extern void clear_huge_page(struct page *page, - unsigned long addr_hint, - unsigned int pages_per_huge_page); +void folio_zero_user(struct folio *folio, unsigned long addr_hint); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a199c48bc462..485424979254 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -46,9 +46,7 @@ struct mem_cgroup; * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * - * If your page will not be mapped to userspace, you can also use the four - * bytes in the mapcount union, but you must call page_mapcount_reset() - * before freeing it. + * The mapcount field must not be used for own purposes. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the @@ -152,18 +150,31 @@ struct page { union { /* This union is 4 bytes in size. */ /* - * If the page can be mapped to userspace, encodes the number - * of times this page is referenced by a page table. + * For head pages of typed folios, the value stored here + * allows for determining what this page is used for. The + * tail pages of typed folios will not store a type + * (page_type == _mapcount == -1). + * + * See page-flags.h for a list of page types which are currently + * stored here. + * + * Owners of typed folios may reuse the lower 16 bit of the + * head page page_type field after setting the page type, + * but must reset these 16 bit to -1 before clearing the + * page type. */ - atomic_t _mapcount; + unsigned int page_type; /* - * If the page is neither PageSlab nor mappable to userspace, - * the value stored here may help determine what this page - * is used for. See page-flags.h for a list of page types - * which are currently stored here. + * For pages that are part of non-typed folios for which mappings + * are tracked via the RMAP, encodes the number of times this page + * is directly referenced by a page table. + * + * Note that the mapcount is always initialized to -1, so that + * transitions both from it and to it can be tracked, using + * atomic_inc_and_test() and atomic_add_negative(-1). */ - unsigned int page_type; + atomic_t _mapcount; }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1dc6248feb83..41458892bc8a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,6 +220,8 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, + NR_MEMMAP, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b9e914e1face..5769fe6e4950 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -30,16 +30,11 @@ * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) - * - Pages not added to the page allocator when onlining a section because - * they were excluded via the online_page_callback() or because they are - * PG_hwpoison. * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). - * - Pages part of an offline section (struct pages of offline sections should - * not be trusted as they will be initialized when first onlined). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) @@ -616,11 +611,6 @@ PAGEFLAG_FALSE(Uncached, uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) -#define MAGIC_HWPOISON 0x48575053U /* HWPS */ -extern void SetPageHWPoisonTakenOff(struct page *page); -extern void ClearPageHWPoisonTakenOff(struct page *page); -extern bool take_page_off_buddy(struct page *page); -extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 @@ -655,27 +645,28 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* - * On an anonymous page mapped into a user virtual memory area, - * page->mapping points to its anon_vma, not to a struct address_space; + * On an anonymous folio mapped into a user virtual memory area, + * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON - * bit; and then page->mapping points, not to an anon_vma, but to a private + * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable - * page and then page->mapping points to a struct movable_operations. + * page and then folio->mapping points to a struct movable_operations. * - * Please note that, confusingly, "page_mapping" refers to the inode - * address_space which maps the page from disk; whereas "page_mapped" - * refers to user virtual address space into which the page is mapped. + * Please note that, confusingly, "folio_mapping" refers to the inode + * address_space which maps the folio from disk; whereas "folio_mapped" + * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its - * internal states, the page->mapping does not exist as such, nor do these - * flags below. So in order to avoid testing non-existent bits, please - * make sure that PageSlab(page) actually evaluates to false before calling - * the following functions (e.g., PageAnon). See mm/slab.h. + * internal states, the folio->mapping does not exist as such, nor do + * these flags below. So in order to avoid testing non-existent bits, + * please make sure that folio_test_slab(folio) actually evaluates to + * false before calling the following functions (e.g., folio_test_anon). + * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 @@ -945,22 +936,28 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) */ enum pagetype { - PG_buddy = 0x00000080, - PG_offline = 0x00000100, - PG_table = 0x00000200, - PG_guard = 0x00000400, - PG_hugetlb = 0x00000800, - PG_slab = 0x00001000, - - PAGE_TYPE_BASE = 0xf0000000, - /* Reserve 0x0000007f to catch underflows of _mapcount */ - PAGE_MAPCOUNT_RESERVE = -128, + PG_buddy = 0x40000000, + PG_offline = 0x20000000, + PG_table = 0x10000000, + PG_guard = 0x08000000, + PG_hugetlb = 0x04000000, + PG_slab = 0x02000000, + PG_zsmalloc = 0x01000000, + + PAGE_TYPE_BASE = 0x80000000, + + /* + * Reserve 0xffff0000 - 0xfffffffe to catch _mapcount underflows and + * allow owners that set a type to reuse the lower 16 bit for their own + * purposes. + */ + PAGE_MAPCOUNT_RESERVE = ~0x0000ffff, }; #define PageType(page, flag) \ - ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) + ((READ_ONCE(page->page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) #define folio_test_type(folio, flag) \ - ((folio->page.page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) + ((READ_ONCE(folio->page.page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) static inline int page_type_has_type(unsigned int page_type) { @@ -969,7 +966,7 @@ static inline int page_type_has_type(unsigned int page_type) static inline int page_has_type(const struct page *page) { - return page_type_has_type(page->page_type); + return page_type_has_type(READ_ONCE(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ @@ -1018,15 +1015,22 @@ PAGE_TYPE_OPS(Buddy, buddy, buddy) * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * + * When a memory block gets onlined, all pages are initialized with a + * refcount of 1 and PageOffline(). generic_online_page() will + * take care of clearing PageOffline(). + * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() - * pages (now with a reference count of zero) are treated like free pages, - * allowing the containing memory block to get offlined. A driver that + * pages (now with a reference count of zero) are treated like free (unmanaged) + * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will - * require to re-set the pages PageOffline() and not giving them to the - * buddy via online_page_callback_t. + * require not giving them to the buddy via generic_online_page(). + * + * Memory offlining code will not adjust the managed page count for any + * PageOffline() pages, treating them like they were never exposed to the + * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random @@ -1070,6 +1074,8 @@ FOLIO_TYPE_OPS(hugetlb, hugetlb) FOLIO_TEST_FLAG_FALSE(hugetlb) #endif +PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) + /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 8cd858d912c4..904c52f97284 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -81,4 +81,8 @@ static inline void page_counter_reset_watermark(struct page_counter *counter) counter->watermark = page_counter_read(counter); } +void page_counter_calculate_protection(struct page_counter *root, + struct page_counter *counter, + bool recursive_protection); + #endif /* _LINUX_PAGE_COUNTER_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2d72bd89bf7b..483a191bb4df 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -434,7 +434,6 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); @@ -800,7 +799,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -#define swapcache_index(folio) __page_file_index(&(folio)->page) +extern pgoff_t __folio_swap_cache_index(struct folio *folio); /** * folio_index - File index of a folio. @@ -815,9 +814,9 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, */ static inline pgoff_t folio_index(struct folio *folio) { - if (unlikely(folio_test_swapcache(folio))) - return swapcache_index(folio); - return folio->index; + if (unlikely(folio_test_swapcache(folio))) + return __folio_swap_cache_index(folio); + return folio->index; } /** @@ -940,11 +939,6 @@ static inline loff_t page_offset(struct page *page) return ((loff_t)page->index) << PAGE_SHIFT; } -static inline loff_t page_file_offset(struct page *page) -{ - return ((loff_t)page_index(page)) << PAGE_SHIFT; -} - /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. @@ -954,18 +948,6 @@ static inline loff_t folio_pos(struct folio *folio) return page_offset(&folio->page); } -/** - * folio_file_pos - Returns the byte position of this folio in its file. - * @folio: The folio. - * - * This differs from folio_pos() for folios which belong to a swap file. - * NFS is the only filesystem today which needs to use folio_file_pos(). - */ -static inline loff_t folio_file_pos(struct folio *folio) -{ - return page_file_offset(&folio->page); -} - /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ @@ -1319,8 +1301,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @folio: The folio at @index which triggered the readahead call. - * @index: Index of first page to be read. + * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which @@ -1331,9 +1312,9 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct folio *folio, pgoff_t index, unsigned long req_count) + struct folio *folio, unsigned long req_count) { - DEFINE_READAHEAD(ractl, file, ra, mapping, index); + DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index ec3573119923..8efce7414fad 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -475,6 +475,12 @@ do { \ raw_cpu_cmpxchg(pcp, oval, nval); \ }) +#define __this_cpu_try_cmpxchg(pcp, ovalp, nval) \ +({ \ + __this_cpu_preempt_check("try_cmpxchg"); \ + raw_cpu_try_cmpxchg(pcp, ovalp, nval); \ +}) + #define __this_cpu_sub(pcp, val) __this_cpu_add(pcp, -(typeof(pcp))(val)) #define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) #define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 9cacadbd61f8..18cd0c0c73d9 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -15,7 +15,7 @@ extern struct page_ext_operations page_alloc_tagging_ops; static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) { - return (void *)page_ext + page_alloc_tagging_ops.offset; + return (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); } static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) @@ -71,6 +71,7 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) static inline void pgalloc_tag_split(struct page *page, unsigned int nr) { int i; + struct page_ext *first_page_ext; struct page_ext *page_ext; union codetag_ref *ref; struct alloc_tag *tag; @@ -78,7 +79,7 @@ static inline void pgalloc_tag_split(struct page *page, unsigned int nr) if (!mem_alloc_profiling_enabled()) return; - page_ext = page_ext_get(page); + first_page_ext = page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; @@ -94,7 +95,7 @@ static inline void pgalloc_tag_split(struct page *page, unsigned int nr) page_ext = page_ext_next(page_ext); } out: - page_ext_put(page_ext); + page_ext_put(first_page_ext); } static inline struct alloc_tag *pgalloc_tag_get(struct page *page) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 18019f037bae..2a6a3cccfc36 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -729,13 +729,18 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ -#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +#ifndef update_mmu_tlb_range +static inline void update_mmu_tlb_range(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) +{ +} +#endif + static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + update_mmu_tlb_range(vma, address, ptep, 1); } -#define __HAVE_ARCH_UPDATE_MMU_TLB -#endif /* * Some architectures may be able to avoid expensive synchronization @@ -1084,6 +1089,15 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) }) #ifndef __HAVE_ARCH_DO_SWAP_PAGE +static inline void arch_do_swap_page_nr(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte, + int nr) +{ + +} +#else /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be @@ -1092,12 +1106,17 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ -static inline void arch_do_swap_page(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, - pte_t pte, pte_t oldpte) -{ - +static inline void arch_do_swap_page_nr(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte, + int nr) +{ + for (int i = 0; i < nr; i++) { + arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE, + pte_advance_pfn(pte, i), + pte_advance_pfn(oldpte, i)); + } } #endif @@ -1888,9 +1907,12 @@ typedef unsigned int pgtbl_mod_mask; #ifndef pmd_leaf_size #define pmd_leaf_size(x) PMD_SIZE #endif +#ifndef __pte_leaf_size #ifndef pte_leaf_size #define pte_leaf_size(x) PAGE_SIZE #endif +#define __pte_leaf_size(x,y) pte_leaf_size(y) +#endif /* * We always define pmd_pfn for all archs as it's used in lots of generic diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 7229b9baf20d..0978c64f49d8 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -200,6 +200,9 @@ static inline void __folio_rmap_sanity_checks(struct folio *folio, /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); + /* When (un)mapping zeropages, we should never touch ref+mapcount. */ + VM_WARN_ON_FOLIO(is_zero_folio(folio), folio); + /* * TODO: we get driver-allocated folios that have nothing to do with * the rmap using vm_insert_page(); therefore, we cannot assume that @@ -241,7 +244,7 @@ void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages, void folio_add_anon_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_add_file_rmap_pte(folio, page, vma) \ @@ -681,16 +684,6 @@ struct page_vma_mapped_walk { unsigned int flags; }; -#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ - struct page_vma_mapped_walk name = { \ - .pfn = page_to_pfn(_page), \ - .nr_pages = compound_nr(_page), \ - .pgoff = page_to_pgoff(_page), \ - .vma = _vma, \ - .address = _address, \ - .flags = _flags, \ - } - #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ .pfn = folio_pfn(_folio), \ @@ -710,6 +703,30 @@ static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) spin_unlock(pvmw->ptl); } +/** + * page_vma_mapped_walk_restart - Restart the page table walk. + * @pvmw: Pointer to struct page_vma_mapped_walk. + * + * It restarts the page table walk when changes occur in the page + * table, such as splitting a PMD. Ensures that the PTL held during + * the previous walk is released and resets the state to allow for + * a new walk starting at the current address stored in pvmw->address. + */ +static inline void +page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) +{ + WARN_ON_ONCE(!pvmw->pmd && !pvmw->pte); + + if (likely(pvmw->ptl)) + spin_unlock(pvmw->ptl); + else + WARN_ON_ONCE(1); + + pvmw->ptl = NULL; + pvmw->pmd = NULL; + pvmw->pte = NULL; +} + bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); /* @@ -730,8 +747,6 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); - /* * rmap_walk_control: To control rmap traversing for specific needs * @@ -787,8 +802,4 @@ static inline int folio_mkclean(struct folio *folio) } #endif /* CONFIG_MMU */ -static inline int page_mkclean(struct page *page) -{ - return folio_mkclean(page_folio(page)); -} #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index e330ee0205c0..a898d9bde8ca 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -942,7 +942,7 @@ struct task_struct { #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN @@ -1458,17 +1458,18 @@ struct task_struct { unsigned int kcov_softirq; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; +#endif +#ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; -#endif -#ifdef CONFIG_MEMCG_KMEM + /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3fb18f7eb73e..1d06b1e5408a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -113,12 +113,21 @@ int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge); #else static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags) { return false; } +static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge) +{ + return 0; +} #endif #ifdef CONFIG_SHMEM diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9c29bdd5596d..29c3ea5b6e93 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3429,6 +3429,10 @@ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** @@ -3445,6 +3449,10 @@ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ #define dev_alloc_page() dev_alloc_pages(0) /** diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c9efda9df285..d9b03e0746e7 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -414,6 +414,11 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ #define sk_psock_init_link() \ ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ GFP_ATOMIC | __GFP_NOWARN)) diff --git a/include/linux/slab.h b/include/linux/slab.h index d99afce36098..eb2bf4629157 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -41,7 +41,7 @@ enum _slab_flag_bits { #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC @@ -171,7 +171,7 @@ enum _slab_flag_bits { # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /* Account to memcg */ -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED @@ -407,7 +407,7 @@ enum kmalloc_cache_type { #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif -#ifndef CONFIG_MEMCG_KMEM +#ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, @@ -420,7 +420,7 @@ enum kmalloc_cache_type { #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES @@ -436,7 +436,7 @@ extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ - (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) + (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; @@ -464,7 +464,7 @@ static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigne */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; - if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) + if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; diff --git a/include/linux/swap.h b/include/linux/swap.h index e685e93ba354..ba7ea95d1c57 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -405,10 +405,13 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) +#define MIN_SWAPPINESS 0 +#define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options); + unsigned int reclaim_options, + int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, @@ -478,7 +481,7 @@ extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); -extern void swap_free(swp_entry_t); +extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); @@ -556,7 +559,7 @@ static inline int swapcache_prepare(swp_entry_t swp) return 0; } -static inline void swap_free(swp_entry_t swp) +static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } @@ -604,6 +607,11 @@ static inline void free_swap_and_cache(swp_entry_t entry) free_swap_and_cache_nr(entry, 1); } +static inline void swap_free(swp_entry_t entry) +{ + swap_free_nr(entry, 1); +} + #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { diff --git a/include/linux/swapops.h b/include/linux/swapops.h index a5c560a2f8c2..cb468e418ea1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -334,7 +334,7 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); -extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); +extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { @@ -359,7 +359,7 @@ static inline int is_migration_entry(swp_entry_t swp) static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, - pte_t *pte) { } + unsigned long addr, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 735eae6e272c..16b0cfa80502 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -624,4 +624,8 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } + +void __meminit mod_node_early_perpage_metadata(int nid, long delta); +void __meminit store_early_perpage_metadata(void); + #endif /* _LINUX_VMSTAT_H */ diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 2a85b941db97..6cecb4a4f68b 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -35,7 +35,8 @@ void zswap_swapoff(int type); void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); void zswap_lruvec_state_init(struct lruvec *lruvec); void zswap_folio_swapin(struct folio *folio); -bool is_zswap_enabled(void); +bool zswap_is_enabled(void); +bool zswap_never_enabled(void); #else struct zswap_lruvec_state {}; @@ -60,11 +61,16 @@ static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} static inline void zswap_folio_swapin(struct folio *folio) {} -static inline bool is_zswap_enabled(void) +static inline bool zswap_is_enabled(void) { return false; } +static inline bool zswap_never_enabled(void) +{ + return true; +} + #endif #endif /* _LINUX_ZSWAP_H */ diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 7c47151d5c72..e5f7ee0864e7 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -356,10 +356,9 @@ TRACE_EVENT(aer_event, #define MF_PAGE_TYPE \ EM ( MF_MSG_KERNEL, "reserved kernel page" ) \ EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" ) \ - EM ( MF_MSG_SLAB, "kernel slab page" ) \ - EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \ EM ( MF_MSG_HUGE, "huge page" ) \ EM ( MF_MSG_FREE_HUGE, "free huge page" ) \ + EM ( MF_MSG_GET_HWPOISON, "get hwpoison page" ) \ EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \ EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \ EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \ @@ -373,6 +372,7 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_BUDDY, "free buddy page" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ + EM ( MF_MSG_ALREADY_POISONED, "already poisoned" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 8a829e0f6e55..b37eb0a7060f 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -36,7 +36,7 @@ TRACE_EVENT(kmem_cache_alloc, __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; - __entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ? + __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), @@ -87,7 +87,7 @@ TRACE_EVENT(kmalloc, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, - (IS_ENABLED(CONFIG_MEMCG_KMEM) && + (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 0190ef725b43..cd01dd7b3640 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -22,7 +22,8 @@ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ EM( MR_CONTIG_RANGE, "contig_range") \ EM( MR_LONGTERM_PIN, "longterm_pin") \ - EMe(MR_DEMOTION, "demotion") + EM( MR_DEMOTION, "demotion") \ + EMe(MR_DAMON, "damon") /* * First define the enums in the above macros to be exported to userspace diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 191a7e88a8ab..753971770733 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -336,8 +336,10 @@ typedef int __bitwise __kernel_rwf_t; #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) +#define PROCFS_IOCTL_MAGIC 'f' + /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -396,4 +398,158 @@ struct pm_scan_arg { __u64 return_mask; }; +/* /proc/<pid>/maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc/<pid>/maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + #endif /* _UAPI_LINUX_FS_H */ |