diff options
Diffstat (limited to 'include/linux')
39 files changed, 679 insertions, 464 deletions
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 941deffc590d..7c0786bdf9af 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -30,6 +30,21 @@ struct alloc_tag { struct alloc_tag_counters __percpu *counters; } __aligned(8); +struct alloc_tag_kernel_section { + struct alloc_tag *first_tag; + unsigned long count; +}; + +struct alloc_tag_module_section { + union { + unsigned long start_addr; + struct alloc_tag *first_tag; + }; + unsigned long end_addr; + /* used size */ + unsigned long size; +}; + #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG #define CODETAG_EMPTY ((void *)1) @@ -54,6 +69,8 @@ static inline void set_codetag_empty(union codetag_ref *ref) {} #ifdef CONFIG_MEM_ALLOC_PROFILING +#define ALLOC_TAG_SECTION_NAME "alloc_tags" + struct codetag_bytes { struct codetag *ct; s64 bytes; @@ -76,7 +93,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); #define DEFINE_ALLOC_TAG(_alloc_tag) \ static struct alloc_tag _alloc_tag __used __aligned(8) \ - __section("alloc_tags") = { \ + __section(ALLOC_TAG_SECTION_NAME) = { \ .ct = CODE_TAG_INIT, \ .counters = &_shared_alloc_tag }; @@ -85,7 +102,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); #define DEFINE_ALLOC_TAG(_alloc_tag) \ static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ static struct alloc_tag _alloc_tag __used __aligned(8) \ - __section("alloc_tags") = { \ + __section(ALLOC_TAG_SECTION_NAME) = { \ .ct = CODE_TAG_INIT, \ .counters = &_alloc_tag_cntr }; diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index cffa38a73618..d8a8d245824a 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -6,11 +6,10 @@ #include <linux/kmemleak.h> /* - * Types for free bootmem stored in page->lru.next. These have to be in - * some random range in unsigned long space for debugging purposes. + * Types for free bootmem stored in the low bits of page->private. */ -enum { - MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, +enum bootmem_type { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 1, SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, MIX_SECTION_INFO, NODE_INFO, @@ -21,9 +20,19 @@ enum { void __init register_page_bootmem_info_node(struct pglist_data *pgdat); void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type); + enum bootmem_type type); void put_page_bootmem(struct page *page); +static inline enum bootmem_type bootmem_type(const struct page *page) +{ + return (unsigned long)page->private & 0xf; +} + +static inline unsigned long bootmem_info(const struct page *page) +{ + return (unsigned long)page->private >> 4; +} + /* * Any memory allocated via the memblock allocator and not via the * buddy will be marked reserved already in the memmap. For those @@ -31,7 +40,7 @@ void put_page_bootmem(struct page *page); */ static inline void free_bootmem_page(struct page *page) { - unsigned long magic = page->index; + enum bootmem_type type = bootmem_type(page); /* * The reserve_bootmem_region sets the reserved flag on bootmem @@ -39,7 +48,7 @@ static inline void free_bootmem_page(struct page *page) */ VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); - if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) + if (type == SECTION_INFO || type == MIX_SECTION_INFO) put_page_bootmem(page); else VM_BUG_ON_PAGE(1, page); @@ -53,8 +62,18 @@ static inline void put_page_bootmem(struct page *page) { } +static inline enum bootmem_type bootmem_type(const struct page *page) +{ + return SECTION_INFO; +} + +static inline unsigned long bootmem_info(const struct page *page) +{ + return 0; +} + static inline void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) + enum bootmem_type type) { } diff --git a/include/linux/codetag.h b/include/linux/codetag.h index c2a579ccd455..d14dbd26b370 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -13,6 +13,9 @@ struct codetag_module; struct seq_buf; struct module; +#define CODETAG_SECTION_START_PREFIX "__start_" +#define CODETAG_SECTION_STOP_PREFIX "__stop_" + /* * An instance of this structure is created in a special ELF section at every * code location being tagged. At runtime, the special section is treated as @@ -35,8 +38,15 @@ struct codetag_type_desc { size_t tag_size; void (*module_load)(struct codetag_type *cttype, struct codetag_module *cmod); - bool (*module_unload)(struct codetag_type *cttype, + void (*module_unload)(struct codetag_type *cttype, struct codetag_module *cmod); +#ifdef CONFIG_MODULES + void (*module_replaced)(struct module *mod, struct module *new_mod); + bool (*needs_section_mem)(struct module *mod, unsigned long size); + void *(*alloc_section_mem)(struct module *mod, unsigned long size, + unsigned int prepend, unsigned long align); + void (*free_section_mem)(struct module *mod, bool used); +#endif }; struct codetag_iterator { @@ -71,11 +81,31 @@ struct codetag_type * codetag_register_type(const struct codetag_type_desc *desc); #if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) + +bool codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size); +void *codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align); +void codetag_free_module_sections(struct module *mod); +void codetag_module_replaced(struct module *mod, struct module *new_mod); void codetag_load_module(struct module *mod); -bool codetag_unload_module(struct module *mod); -#else +void codetag_unload_module(struct module *mod); + +#else /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ + +static inline bool +codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size) { return false; } +static inline void * +codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align) { return NULL; } +static inline void codetag_free_module_sections(struct module *mod) {} +static inline void codetag_module_replaced(struct module *mod, struct module *new_mod) {} static inline void codetag_load_module(struct module *mod) {} -static inline bool codetag_unload_module(struct module *mod) { return true; } -#endif +static inline void codetag_unload_module(struct module *mod) {} + +#endif /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ #endif /* _LINUX_CODETAG_H */ diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 32cef1144117..64130ae19690 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -46,11 +46,27 @@ enum execmem_type { /** * enum execmem_range_flags - options for executable memory allocations * @EXECMEM_KASAN_SHADOW: allocate kasan shadow + * @EXECMEM_ROX_CACHE: allocations should use ROX cache of huge pages */ enum execmem_range_flags { EXECMEM_KASAN_SHADOW = (1 << 0), + EXECMEM_ROX_CACHE = (1 << 1), }; +#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +/** + * execmem_fill_trapping_insns - set memory to contain instructions that + * will trap + * @ptr: pointer to memory to fill + * @size: size of the range to fill + * @writable: is the memory poited by @ptr is writable or ROX + * + * A hook for architecures to fill execmem ranges with invalid instructions. + * Architectures that use EXECMEM_ROX_CACHE must implement this. + */ +void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable); +#endif + /** * struct execmem_range - definition of an address space suitable for code and * related data allocations @@ -123,6 +139,39 @@ void *execmem_alloc(enum execmem_type type, size_t size); */ void execmem_free(void *ptr); +#ifdef CONFIG_MMU +/** + * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory + * @size: size of the virtual mapping in bytes + * + * Maps virtually contiguous area in the range suitable for EXECMEM_MODULE_DATA. + * + * Return: the area descriptor on success or %NULL on failure. + */ +struct vm_struct *execmem_vmap(size_t size); +#endif + +/** + * execmem_update_copy - copy an update to executable memory + * @dst: destination address to update + * @src: source address containing the data + * @size: how many bytes of memory shold be copied + * + * Copy @size bytes from @src to @dst using text poking if the memory at + * @dst is read-only. + * + * Return: a pointer to @dst or NULL on error + */ +void *execmem_update_copy(void *dst, const void *src, size_t size); + +/** + * execmem_is_rox - check if execmem is read-only + * @type - the execmem type to check + * + * Return: %true if the @type is read-only, %false if it's writable + */ +bool execmem_is_rox(enum execmem_type type); + #if defined(CONFIG_EXECMEM) && !defined(CONFIG_ARCH_WANTS_EXECMEM_LATE) void execmem_init(void); #else diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a0a6d25f883f..b0fe9f62d15b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -306,7 +306,7 @@ 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); + unsigned long addr); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { @@ -326,7 +326,7 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde { return folio_alloc_noprof(gfp, order); } -#define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ +#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ folio_alloc_noprof(gfp, order) #endif @@ -341,7 +341,7 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { - struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr, false); + struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); return &folio->page; } diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 930a591b9b61..6e452bd8e7e3 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -224,13 +224,7 @@ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { - struct folio *folio; - - folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false); - if (folio) - clear_user_highpage(&folio->page, vaddr); - - return folio; + return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr); } #endif diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ef5b80e48599..b94c2e8ee918 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -2,7 +2,6 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H -#include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ @@ -120,6 +119,8 @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_ZSWPOUT, + MTHP_STAT_SWPIN, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, @@ -253,19 +254,6 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, return orders; } -static inline bool file_thp_enabled(struct vm_area_struct *vma) -{ - struct inode *inode; - - if (!vma->vm_file) - return false; - - inode = vma->vm_file->f_inode; - - return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && - !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); -} - unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e4697539b665..ae4fe8615bb6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -546,16 +546,10 @@ static inline struct hstate *hstate_inode(struct inode *i) } #endif /* !CONFIG_HUGETLBFS */ -#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); -#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ - unsigned long -generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private @@ -1035,9 +1029,19 @@ void hugetlb_unregister_node(struct node *node); */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); +static inline unsigned long huge_page_mask_align(struct file *file) +{ + return PAGE_MASK & ~huge_page_mask(hstate_file(file)); +} + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline unsigned long huge_page_mask_align(struct file *file) +{ + return 0; +} + static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 00a3bf7c0d8f..6bbfc8aa42e8 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -29,6 +29,9 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) +#define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ +#define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> @@ -564,7 +567,8 @@ void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end); + unsigned long free_region_end, + unsigned long flags); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ @@ -579,7 +583,8 @@ static inline int kasan_populate_vmalloc(unsigned long start, static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) { } + unsigned long free_region_end, + unsigned long flags) { } #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ @@ -614,7 +619,8 @@ static inline int kasan_populate_vmalloc(unsigned long start, static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) { } + unsigned long free_region_end, + unsigned long flags) { } static inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 30baae91b225..1f46046080f5 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -2,8 +2,6 @@ #ifndef _LINUX_KHUGEPAGED_H #define _LINUX_KHUGEPAGED_H -#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ - extern unsigned int khugepaged_max_ptes_none __read_mostly; #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 6a3cd1bf4680..93a73c076d16 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -26,6 +26,7 @@ extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; extern void kmemleak_update_trace(const void *ptr) __ref; extern void kmemleak_not_leak(const void *ptr) __ref; +extern void kmemleak_transient_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; @@ -93,6 +94,9 @@ static inline void kmemleak_update_trace(const void *ptr) static inline void kmemleak_not_leak(const void *ptr) { } +static inline void kmemleak_transient_leak(const void *ptr) +{ +} static inline void kmemleak_ignore(const void *ptr) { } diff --git a/include/linux/ksm.h b/include/linux/ksm.h index ec9c05044d4f..6a53ac4885bb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -13,7 +13,6 @@ #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> -#include <linux/sched/coredump.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, @@ -91,7 +90,7 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); -void collect_procs_ksm(struct folio *folio, struct page *page, +void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); @@ -123,8 +122,9 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } -static inline void collect_procs_ksm(struct folio *folio, struct page *page, - struct list_head *to_kill, int force_early) +static inline void collect_procs_ksm(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + int force_early) { } diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 5099a8ccd5f4..05c166811f6b 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -32,6 +32,8 @@ struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; + /* protects all fields above */ + spinlock_t lock; }; struct list_lru_memcg { @@ -41,11 +43,9 @@ struct list_lru_memcg { }; struct list_lru_node { - /* protects all lists on the node, including per cgroup */ - spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; - long nr_items; + atomic_long_t nr_items; } ____cacheline_aligned_in_smp; struct list_lru { @@ -56,16 +56,28 @@ struct list_lru { bool memcg_aware; struct xarray xa; #endif +#ifdef CONFIG_LOCKDEP + struct lock_class_key *key; +#endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key, struct shrinker *shrinker); + struct shrinker *shrinker); #define list_lru_init(lru) \ - __list_lru_init((lru), false, NULL, NULL) + __list_lru_init((lru), false, NULL) #define list_lru_init_memcg(lru, shrinker) \ - __list_lru_init((lru), true, NULL, shrinker) + __list_lru_init((lru), true, shrinker) + +static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker, + struct lock_class_key *key) +{ +#ifdef CONFIG_LOCKDEP + lru->key = key; +#endif + return list_lru_init_memcg(lru, shrinker); +} int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); @@ -172,7 +184,7 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, - struct list_lru_one *list, spinlock_t *lock, void *cb_arg); + struct list_lru_one *list, void *cb_arg); /** * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index c2c11004085e..cbbcd18d4186 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -224,7 +224,7 @@ typedef struct { /* nothing */ } lockdep_map_p; * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the - * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in + * case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ @@ -592,6 +592,20 @@ static __always_inline void mas_reset(struct ma_state *mas) #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) +/** + * mas_for_each_rev() - Iterate over a range of the maple tree in reverse order. + * @__mas: Maple Tree operation state (maple_state) + * @__entry: Entry retrieved from the tree + * @__min: minimum index to retrieve from the tree + * + * When returned, mas->index and mas->last will hold the entire range for the + * entry. + * + * Note: may return the zero entry. + */ +#define mas_for_each_rev(__mas, __entry, __min) \ + while (((__entry) = mas_find_rev((__mas), (__min))) != NULL) + #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e1b41554a5fb..5502aa8e138e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -299,25 +299,10 @@ struct mem_cgroup { /* 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; @@ -433,9 +418,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * * - the folio lock * - LRU isolation - * - folio_memcg_lock() * - exclusive reference - * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -460,35 +443,6 @@ static inline bool folio_memcg_charged(struct folio *folio) return __folio_memcg(folio) != NULL; } -/** - * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. - * @folio: Pointer to the folio. - * - * This function assumes that the folio is known to have a - * proper memory cgroup pointer. It's not safe to call this function - * against some type of folios, e.g. slab folios or ex-slab folios. - * - * Return: A pointer to the memory cgroup associated with the folio, - * or NULL. - */ -static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) -{ - unsigned long memcg_data = READ_ONCE(folio->memcg_data); - - VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - - if (memcg_data & MEMCG_DATA_KMEM) { - struct obj_cgroup *objcg; - - objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } - - WARN_ON_ONCE(!rcu_read_lock_held()); - - return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); -} - /* * folio_memcg_check - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. @@ -504,9 +458,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * * - the folio lock * - LRU isolation - * - lock_folio_memcg() * - exclusive reference - * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -1103,10 +1055,9 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return NULL; } -static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) +static inline bool folio_memcg_charged(struct folio *folio) { - WARN_ON_ONCE(!rcu_read_lock_held()); - return NULL; + return false; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) @@ -1282,6 +1233,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) return NULL; } +static inline void obj_cgroup_get(struct obj_cgroup *objcg) +{ +} + static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } @@ -1874,26 +1829,6 @@ 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); @@ -1915,26 +1850,6 @@ unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, 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; diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 1add16f21612..ce9885e0178a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -47,7 +47,7 @@ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ - nodemask_t nodes; /* interleave/bind/perfer */ + nodemask_t nodes; /* interleave/bind/preferred/etc */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { diff --git a/include/linux/mm.h b/include/linux/mm.h index 673771f34674..2bbf73eb53e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,11 +97,11 @@ extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif -#ifndef PHYSMEM_END +#ifndef DIRECT_MAP_PHYSMEM_END # ifdef MAX_PHYSMEM_BITS -# define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) +# define DIRECT_MAP_PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) # else -# define PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) +# define DIRECT_MAP_PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) # endif #endif @@ -1298,8 +1298,6 @@ static inline struct folio *virt_to_folio(const void *x) void __folio_put(struct folio *folio); -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); @@ -1907,7 +1905,7 @@ static inline unsigned long page_to_section(const struct page *page) * * Return: The Page Frame Number of the first page in the folio. */ -static inline unsigned long folio_pfn(struct folio *folio) +static inline unsigned long folio_pfn(const struct folio *folio) { return page_to_pfn(&folio->page); } @@ -3028,8 +3026,11 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, return pte; } -pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, spinlock_t **ptlp); +pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp); +pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, pmd_t *pmdvalp, + spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ @@ -3831,9 +3832,6 @@ void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); -void pud_init(void *addr); -void pmd_init(void *addr); -void kernel_pte_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); @@ -4176,63 +4174,6 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla } #endif -#ifdef CONFIG_MEM_ALLOC_PROFILING -static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) -{ - int i; - struct alloc_tag *tag; - unsigned int nr_pages = 1 << new_order; - - if (!mem_alloc_profiling_enabled()) - return; - - tag = pgalloc_tag_get(&folio->page); - if (!tag) - return; - - for (i = nr_pages; i < (1 << old_order); i += nr_pages) { - union codetag_ref *ref = get_page_tag_ref(folio_page(folio, i)); - - if (ref) { - /* Set new reference to point to the original tag */ - alloc_tag_ref_set(ref, tag); - put_page_tag_ref(ref); - } - } -} - -static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) -{ - struct alloc_tag *tag; - union codetag_ref *ref; - - tag = pgalloc_tag_get(&old->page); - if (!tag) - return; - - ref = get_page_tag_ref(&new->page); - if (!ref) - return; - - /* Clear the old ref to the original allocation tag. */ - clear_page_tag_ref(&old->page); - /* Decrement the counters of the tag on get_new_folio. */ - alloc_tag_sub(ref, folio_nr_pages(new)); - - __alloc_tag_ref_set(ref, tag); - - put_page_tag_ref(ref); -} -#else /* !CONFIG_MEM_ALLOC_PROFILING */ -static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) -{ -} - -static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) -{ -} -#endif /* CONFIG_MEM_ALLOC_PROFILING */ - int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f4fe593c1400..1b6a917fffa4 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -155,6 +155,11 @@ static inline int folio_lru_refs(struct folio *folio) return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } +static inline void folio_clear_lru_refs(struct folio *folio) +{ + set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); +} + static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); @@ -222,6 +227,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, { unsigned long seq; unsigned long flags; + unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); @@ -257,7 +263,14 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ - set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + mask = LRU_GEN_MASK; + /* + * Don't clear PG_workingset here because it can affect PSI accounting + * if the activation is due to workingset refault. + */ + if (folio_test_active(folio)) + mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); + set_mask_bits(&folio->flags, mask, flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ @@ -291,6 +304,12 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return true; } +static inline void folio_migrate_refs(struct folio *new, struct folio *old) +{ + unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; + + set_mask_bits(&new->flags, LRU_REFS_MASK, refs); +} #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) @@ -313,6 +332,10 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return false; } +static inline void folio_migrate_refs(struct folio *new, struct folio *old) +{ + +} #endif /* CONFIG_LRU_GEN */ static __always_inline @@ -521,7 +544,7 @@ static inline pte_marker copy_pte_marker( { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ - pte_marker dstm = srcm & PTE_MARKER_POISONED; + pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e85beea1206e..7361a8f3ab68 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1535,4 +1535,88 @@ enum { /* See also internal only FOLL flags in mm/internal.h */ }; +/* mm flags */ + +/* + * The first two bits represent core dump modes for set-user-ID, + * the modes are SUID_DUMP_* defined in linux/sched/coredump.h + */ +#define MMF_DUMPABLE_BITS 2 +#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 +#define MMF_DUMP_DAX_PRIVATE 9 +#define MMF_DUMP_DAX_SHARED 10 + +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 9 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif + /* leave room for more dump flags */ +#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for khugepaged */ + +/* + * This one-shot flag is dropped due to necessity of changing exe once again + * on NFS restore + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ + +#define MMF_HAS_UPROBES 19 /* has uprobes */ +#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) +#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ +/* + * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either + * replaced in the future by mm.pinned_vm when it becomes stable, or grow into + * a counter on its own. We're aggresive on this bit for now: even if the + * pinned pages were unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm, just for simplicity. + */ +#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ + +#define MMF_HAS_MDWE 28 +#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) + + +#define MMF_HAS_MDWE_NO_INHERIT 29 + +#define MMF_VM_MERGE_ANY 30 +#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) + +#define MMF_TOPDOWN 31 /* mm searches top down by default */ +#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) + +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ + MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index d39ebb10caeb..e2dd57ca368b 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -606,6 +606,13 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + return 0; +} + static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 80bc5640bb60..b36124145a16 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,6 +220,9 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, +#ifdef CONFIG_HUGETLB_PAGE + NR_HUGETLB, +#endif NR_VM_NODE_STAT_ITEMS }; @@ -403,6 +406,8 @@ enum { NR_LRU_GEN_CAPS }; +#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) + #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) diff --git a/include/linux/module.h b/include/linux/module.h index 88ecc5e9f523..2a9386cbdf85 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -367,6 +367,8 @@ enum mod_mem_type { struct module_memory { void *base; + void *rw_copy; + bool is_rox; unsigned int size; #ifdef CONFIG_MODULES_TREE_LOOKUP @@ -767,6 +769,15 @@ static inline bool is_livepatch_module(struct module *mod) void set_module_sig_enforced(void); +void *__module_writable_address(struct module *mod, void *loc); + +static inline void *module_writable_address(struct module *mod, void *loc) +{ + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod) + return loc; + return __module_writable_address(mod, loc); +} + #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) @@ -874,6 +885,11 @@ static inline bool module_is_coming(struct module *mod) { return false; } + +static inline void *module_writable_address(struct module *mod, void *loc) +{ + return loc; +} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index e395461d59e5..1f5507ba5a12 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -108,6 +108,10 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +int module_post_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod); + #ifdef CONFIG_MODULES void flush_module_init_free_work(void); #else diff --git a/include/linux/oom.h b/include/linux/oom.h index 7d0c9c48a0c5..1e0fc6931ce9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -7,7 +7,6 @@ #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> -#include <linux/sched/coredump.h> /* MMF_* */ #include <linux/mm.h> /* VM_FAULT* */ struct zonelist; diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 7d79818dc065..4f5c9e979bb9 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -111,5 +111,12 @@ ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \ NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH) +#define NR_NON_PAGEFLAG_BITS (SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH + \ + LAST_CPUPID_SHIFT + KASAN_TAG_WIDTH + \ + LRU_GEN_WIDTH + LRU_REFS_WIDTH) + +#define NR_UNUSED_PAGEFLAG_BITS (BITS_PER_LONG - \ + (NR_NON_PAGEFLAG_BITS + NR_PAGEFLAGS)) + #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 908ee0aad554..2220bfec278e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -689,6 +689,13 @@ static __always_inline bool folio_test_anon(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } +static __always_inline bool PageAnonNotKsm(const struct page *page) +{ + unsigned long flags = (unsigned long)page_folio(page)->mapping; + + return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON; +} + static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); @@ -718,13 +725,8 @@ static __always_inline bool folio_test_ksm(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } - -static __always_inline bool PageKsm(const struct page *page) -{ - return folio_test_ksm(page_folio(page)); -} #else -TESTPAGEFLAG_FALSE(Ksm, ksm) +FOLIO_TEST_FLAG_FALSE(ksm) #endif u64 stable_page_flags(const struct page *page); @@ -1137,14 +1139,14 @@ static __always_inline int PageAnonExclusive(const struct page *page) static __always_inline void SetPageAnonExclusive(struct page *page) { - VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void ClearPageAnonExclusive(struct page *page) { - VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index c16db0067090..73dc2c1841ec 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -3,10 +3,6 @@ #define __LINUX_PAGEISOLATION_H #ifdef CONFIG_MEMORY_ISOLATION -static inline bool has_isolate_pageblock(struct zone *zone) -{ - return zone->nr_isolate_pageblock; -} static inline bool is_migrate_isolate_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; @@ -16,10 +12,6 @@ static inline bool is_migrate_isolate(int migratetype) return migratetype == MIGRATE_ISOLATE; } #else -static inline bool has_isolate_pageblock(struct zone *zone) -{ - return false; -} static inline bool is_migrate_isolate_page(struct page *page) { return false; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 68a5f1ff3301..bcf0865a38ae 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1011,22 +1011,25 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping, return read_cache_folio(mapping, index, NULL, file); } -/* - * Get the offset in PAGE_SIZE (even for hugetlb pages). +/** + * page_pgoff - Calculate the logical page offset of this page. + * @folio: The folio containing this page. + * @page: The page which we need the offset of. + * + * For file pages, this is the offset from the beginning of the file + * in units of PAGE_SIZE. For anonymous pages, this is the offset from + * the beginning of the anon_vma in units of PAGE_SIZE. This will + * return nonsense for KSM pages. + * + * Context: Caller must have a reference on the folio or otherwise + * prevent it from being split or freed. + * + * Return: The offset in units of PAGE_SIZE. */ -static inline pgoff_t page_to_pgoff(struct page *page) +static inline pgoff_t page_pgoff(const struct folio *folio, + const struct page *page) { - struct page *head; - - if (likely(!PageTransTail(page))) - return page->index; - - head = compound_head(page); - /* - * We don't initialize ->index for tail pages: calculate based on - * head page - */ - return head->index + page - head; + return folio->index + folio_page_idx(folio, page); } /* diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index f5eb5a32aeed..9700a29f8afb 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -25,12 +25,15 @@ enum page_walk_lock { * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each PTE (lowest-level) entry, - * including empty ones + * @pte_entry: if set, called for each PTE (lowest-level) entry + * including empty ones, except if @install_pte is set. + * If @install_pte is set, @pte_entry is called only for + * existing PTEs. * @pte_hole: if set, called for each hole at all levels, * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. * Any folded depths (where PTRS_PER_P?D is equal to 1) - * are skipped. + * are skipped. If @install_pte is specified, this will + * not trigger for any populated ranges. * @hugetlb_entry: if set, called for each hugetlb entry. This hook * function is called with the vma lock held, in order to * protect against a concurrent freeing of the pte_t* or @@ -51,6 +54,13 @@ enum page_walk_lock { * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. + * @install_pte: if set, missing page table entries are installed and + * thus all levels are always walked in the specified + * range. This callback is then invoked at the PTE level + * (having split any THP pages prior), providing the PTE to + * install. If allocations fail, the walk is aborted. This + * operation is only available for userland memory. Not + * usable for hugetlb ranges. * * p?d_entry callbacks are called even if those levels are folded on a * particular architecture/configuration. @@ -76,6 +86,8 @@ struct mm_walk_ops { int (*pre_vma)(unsigned long start, unsigned long end, struct mm_walk *walk); void (*post_vma)(struct mm_walk *walk); + int (*install_pte)(unsigned long addr, unsigned long next, + pte_t *ptep, struct mm_walk *walk); enum page_walk_lock walk_lock; }; diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 59a3deb792a8..0e43ab653ab6 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -12,45 +12,166 @@ #include <linux/page_ext.h> extern struct page_ext_operations page_alloc_tagging_ops; +extern unsigned long alloc_tag_ref_mask; +extern int alloc_tag_ref_offs; +extern struct alloc_tag_kernel_section kernel_tags; -static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +DECLARE_STATIC_KEY_FALSE(mem_profiling_compressed); + +typedef u16 pgalloc_tag_idx; + +union pgtag_ref_handle { + union codetag_ref *ref; /* reference in page extension */ + struct page *page; /* reference in page flags */ +}; + +/* Reserved indexes */ +#define CODETAG_ID_NULL 0 +#define CODETAG_ID_EMPTY 1 +#define CODETAG_ID_FIRST 2 + +#ifdef CONFIG_MODULES + +extern struct alloc_tag_module_section module_tags; + +static inline struct alloc_tag *module_idx_to_tag(pgalloc_tag_idx idx) { - return (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); + return &module_tags.first_tag[idx - kernel_tags.count]; } -static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +static inline pgalloc_tag_idx module_tag_to_idx(struct alloc_tag *tag) { - return (void *)ref - page_alloc_tagging_ops.offset; + return CODETAG_ID_FIRST + kernel_tags.count + (tag - module_tags.first_tag); } -/* Should be called only if mem_alloc_profiling_enabled() */ -static inline union codetag_ref *get_page_tag_ref(struct page *page) +#else /* CONFIG_MODULES */ + +static inline struct alloc_tag *module_idx_to_tag(pgalloc_tag_idx idx) { - if (page) { - struct page_ext *page_ext = page_ext_get(page); + pr_warn("invalid page tag reference %lu\n", (unsigned long)idx); + return NULL; +} - if (page_ext) - return codetag_ref_from_page_ext(page_ext); +static inline pgalloc_tag_idx module_tag_to_idx(struct alloc_tag *tag) +{ + pr_warn("invalid page tag 0x%lx\n", (unsigned long)tag); + return CODETAG_ID_NULL; +} + +#endif /* CONFIG_MODULES */ + +static inline void idx_to_ref(pgalloc_tag_idx idx, union codetag_ref *ref) +{ + switch (idx) { + case (CODETAG_ID_NULL): + ref->ct = NULL; + break; + case (CODETAG_ID_EMPTY): + set_codetag_empty(ref); + break; + default: + idx -= CODETAG_ID_FIRST; + ref->ct = idx < kernel_tags.count ? + &kernel_tags.first_tag[idx].ct : + &module_idx_to_tag(idx)->ct; + break; } - return NULL; } -static inline void put_page_tag_ref(union codetag_ref *ref) +static inline pgalloc_tag_idx ref_to_idx(union codetag_ref *ref) +{ + struct alloc_tag *tag; + + if (!ref->ct) + return CODETAG_ID_NULL; + + if (is_codetag_empty(ref)) + return CODETAG_ID_EMPTY; + + tag = ct_to_alloc_tag(ref->ct); + if (tag >= kernel_tags.first_tag && tag < kernel_tags.first_tag + kernel_tags.count) + return CODETAG_ID_FIRST + (tag - kernel_tags.first_tag); + + return module_tag_to_idx(tag); +} + + + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline bool get_page_tag_ref(struct page *page, union codetag_ref *ref, + union pgtag_ref_handle *handle) { - if (WARN_ON(!ref)) + if (!page) + return false; + + if (static_key_enabled(&mem_profiling_compressed)) { + pgalloc_tag_idx idx; + + idx = (page->flags >> alloc_tag_ref_offs) & alloc_tag_ref_mask; + idx_to_ref(idx, ref); + handle->page = page; + } else { + struct page_ext *page_ext; + union codetag_ref *tmp; + + page_ext = page_ext_get(page); + if (!page_ext) + return false; + + tmp = (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); + ref->ct = tmp->ct; + handle->ref = tmp; + } + + return true; +} + +static inline void put_page_tag_ref(union pgtag_ref_handle handle) +{ + if (WARN_ON(!handle.ref)) return; - page_ext_put(page_ext_from_codetag_ref(ref)); + if (!static_key_enabled(&mem_profiling_compressed)) + page_ext_put((void *)handle.ref - page_alloc_tagging_ops.offset); +} + +static inline void update_page_tag_ref(union pgtag_ref_handle handle, union codetag_ref *ref) +{ + if (static_key_enabled(&mem_profiling_compressed)) { + struct page *page = handle.page; + unsigned long old_flags; + unsigned long flags; + unsigned long idx; + + if (WARN_ON(!page || !ref)) + return; + + idx = (unsigned long)ref_to_idx(ref); + idx = (idx & alloc_tag_ref_mask) << alloc_tag_ref_offs; + do { + old_flags = READ_ONCE(page->flags); + flags = old_flags; + flags &= ~(alloc_tag_ref_mask << alloc_tag_ref_offs); + flags |= idx; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } else { + if (WARN_ON(!handle.ref || !ref)) + return; + + handle.ref->ct = ref->ct; + } } static inline void clear_page_tag_ref(struct page *page) { if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); + union pgtag_ref_handle handle; + union codetag_ref ref; - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); + if (get_page_tag_ref(page, &ref, &handle)) { + set_codetag_empty(&ref); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } } } @@ -59,11 +180,13 @@ static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); + union pgtag_ref_handle handle; + union codetag_ref ref; - if (ref) { - alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); - put_page_tag_ref(ref); + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_add(&ref, task->alloc_tag, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } } } @@ -71,11 +194,13 @@ static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) { if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); + union pgtag_ref_handle handle; + union codetag_ref ref; - if (ref) { - alloc_tag_sub(ref, PAGE_SIZE * nr); - put_page_tag_ref(ref); + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub(&ref, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } } } @@ -85,13 +210,14 @@ static inline struct alloc_tag *pgalloc_tag_get(struct page *page) struct alloc_tag *tag = NULL; if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - alloc_tag_sub_check(ref); - if (ref) { - if (ref->ct) - tag = ct_to_alloc_tag(ref->ct); - put_page_tag_ref(ref); + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub_check(&ref); + if (ref.ct) + tag = ct_to_alloc_tag(ref.ct); + put_page_tag_ref(handle); } } @@ -104,16 +230,22 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); } +void pgalloc_tag_split(struct folio *folio, int old_order, int new_order); +void pgalloc_tag_copy(struct folio *new, struct folio *old); + +void __init alloc_tag_sec_init(void); + #else /* CONFIG_MEM_ALLOC_PROFILING */ -static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } -static inline void put_page_tag_ref(union codetag_ref *ref) {} static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} +static inline void alloc_tag_sec_init(void) {} +static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {} +static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) {} #endif /* CONFIG_MEM_ALLOC_PROFILING */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8b2ac6bd2ae..adef9d6e9b1b 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -90,6 +90,27 @@ static inline unsigned long pud_index(unsigned long address) #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif +#ifndef kernel_pte_init +static inline void kernel_pte_init(void *addr) +{ +} +#define kernel_pte_init kernel_pte_init +#endif + +#ifndef pmd_init +static inline void pmd_init(void *addr) +{ +} +#define pmd_init pmd_init +#endif + +#ifndef pud_init +static inline void pud_init(void *addr) +{ +} +#define pud_init pud_init +#endif + #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { @@ -1056,44 +1077,6 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) } #endif -/* - * Use set_p*_safe(), and elide TLB flushing, when confident that *no* - * TLB flush will be required as a result of the "set". For example, use - * in scenarios where it is known ahead of time that the routine is - * setting non-present entries, or re-setting an existing entry to the - * same value. Otherwise, use the typical "set" helpers and flush the - * TLB. - */ -#define set_pte_safe(ptep, pte) \ -({ \ - WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ - set_pte(ptep, pte); \ -}) - -#define set_pmd_safe(pmdp, pmd) \ -({ \ - WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ - set_pmd(pmdp, pmd); \ -}) - -#define set_pud_safe(pudp, pud) \ -({ \ - WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ - set_pud(pudp, pud); \ -}) - -#define set_p4d_safe(p4dp, p4d) \ -({ \ - WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ - set_p4d(p4dp, p4d); \ -}) - -#define set_pgd_safe(pgdp, pgd) \ -({ \ - WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ - set_pgd(pgdp, pgd); \ -}) - #ifndef __HAVE_ARCH_DO_SWAP_PAGE static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d5e93e44322e..683a04088f3f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -171,7 +171,7 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, unlink_anon_vmas(next); } -struct anon_vma *folio_get_anon_vma(struct folio *folio); +struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; @@ -194,8 +194,8 @@ enum rmap_level { RMAP_LEVEL_PMD, }; -static inline void __folio_rmap_sanity_checks(struct folio *folio, - struct page *page, int nr_pages, enum rmap_level level) +static inline void __folio_rmap_sanity_checks(const struct folio *folio, + const struct page *page, int nr_pages, enum rmap_level level) { /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); @@ -728,11 +728,8 @@ page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); - -/* - * Used by swapoff to help locate where page is expected in vma. - */ -unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); +unsigned long page_address_in_vma(const struct folio *folio, + const struct page *, const struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. @@ -774,14 +771,14 @@ struct rmap_walk_control { bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); - struct anon_vma *(*anon_lock)(struct folio *folio, + struct anon_vma *(*anon_lock)(const struct folio *folio, struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, +struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index e62ff805cfc9..6eb65ceed213 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,12 +8,6 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ -/* mm flags */ - -/* for SUID_DUMP_* above */ -#define MMF_DUMPABLE_BITS 2 -#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) - extern void set_dumpable(struct mm_struct *mm, int value); /* * This returns the actual value of the suid_dumpable flag. For things @@ -31,80 +25,4 @@ static inline int get_dumpable(struct mm_struct *mm) return __get_dumpable(mm->flags); } -/* coredump filter bits */ -#define MMF_DUMP_ANON_PRIVATE 2 -#define MMF_DUMP_ANON_SHARED 3 -#define MMF_DUMP_MAPPED_PRIVATE 4 -#define MMF_DUMP_MAPPED_SHARED 5 -#define MMF_DUMP_ELF_HEADERS 6 -#define MMF_DUMP_HUGETLB_PRIVATE 7 -#define MMF_DUMP_HUGETLB_SHARED 8 -#define MMF_DUMP_DAX_PRIVATE 9 -#define MMF_DUMP_DAX_SHARED 10 - -#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 9 -#define MMF_DUMP_FILTER_MASK \ - (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) -#define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ - (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) - -#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS -# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) -#else -# define MMF_DUMP_MASK_DEFAULT_ELF 0 -#endif - /* leave room for more dump flags */ -#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when mm is available for - khugepaged */ -/* - * This one-shot flag is dropped due to necessity of changing exe once again - * on NFS restore - */ -//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ - -#define MMF_HAS_UPROBES 19 /* has uprobes */ -#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ -#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ -#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ -#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) -#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ -#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ -/* - * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either - * replaced in the future by mm.pinned_vm when it becomes stable, or grow into - * a counter on its own. We're aggresive on this bit for now: even if the - * pinned pages were unpinned later on, we'll still keep this bit set for the - * lifecycle of this mm, just for simplicity. - */ -#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ - -#define MMF_HAS_MDWE 28 -#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) - - -#define MMF_HAS_MDWE_NO_INHERIT 29 - -#define MMF_VM_MERGE_ANY 30 -#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) - -#define MMF_TOPDOWN 31 /* mm searches top down by default */ -#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) - -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ - MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) - -static inline unsigned long mmf_init_flags(unsigned long flags) -{ - if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) - flags &= ~((1UL << MMF_HAS_MDWE) | - (1UL << MMF_HAS_MDWE_NO_INHERIT)); - return flags & MMF_INIT_MASK; -} - #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index e7aec20fb44f..3030d9245f5a 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -34,6 +34,12 @@ static inline int set_direct_map_default_noflush(struct page *page) return 0; } +static inline int set_direct_map_valid_noflush(struct page *page, + unsigned nr, bool valid) +{ + return 0; +} + static inline bool kernel_page_present(struct page *page) { return true; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 018da28c01e7..0b273a7b9f01 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -114,6 +114,7 @@ int shmem_unuse(unsigned int type); unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force); +bool shmem_hpage_pmd_enabled(void); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, @@ -121,6 +122,11 @@ static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, { return 0; } + +static inline bool shmem_hpage_pmd_enabled(void) +{ + return false; +} #endif #ifdef CONFIG_SHMEM diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cb468e418ea1..96f26e29fefe 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -426,9 +426,19 @@ typedef unsigned long pte_marker; * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. + * + * Note that, when encountered by the faulting logic, PTEs with this marker will + * result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error + * logic. */ #define PTE_MARKER_POISONED BIT(1) -#define PTE_MARKER_MASK (BIT(2) - 1) +/* + * Indicates that, on fault, this PTE will case a SIGSEGV signal to be + * sent. This means guard markers behave in effect as if the region were mapped + * PROT_NONE, rather than if they were a memory hole or equivalent. + */ +#define PTE_MARKER_GUARD BIT(2) +#define PTE_MARKER_MASK (BIT(3) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { @@ -464,6 +474,18 @@ static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); + +} + +static inline swp_entry_t make_guard_swp_entry(void) +{ + return make_pte_marker_entry(PTE_MARKER_GUARD); +} + +static inline int is_guard_swp_entry(swp_entry_t entry) +{ + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_GUARD); } /* diff --git a/include/linux/text-patching.h b/include/linux/text-patching.h new file mode 100644 index 000000000000..ad5877ab0855 --- /dev/null +++ b/include/linux/text-patching.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TEXT_PATCHING_H +#define _LINUX_TEXT_PATCHING_H + +#include <asm/text-patching.h> + +#ifndef text_poke_copy +static inline void *text_poke_copy(void *dst, const void *src, size_t len) +{ + return memcpy(dst, src, len); +} +#define text_poke_copy text_poke_copy +#endif + +#endif /* _LINUX_TEXT_PATCHING_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ad2ce7a6ab7a..31e9ffd936e3 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -134,12 +134,6 @@ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); -#ifdef CONFIG_MMU -extern unsigned long vmalloc_nr_pages(void); -#else -static inline unsigned long vmalloc_nr_pages(void) { return 0; } -#endif - extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); #define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) @@ -208,6 +202,9 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); +int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift); + /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() @@ -266,12 +263,29 @@ static inline bool is_vm_area_hugepages(const void *addr) #endif } +/* for /proc/kcore */ +long vread_iter(struct iov_iter *iter, const char *addr, size_t count); + +/* + * Internals. Don't use.. + */ +__init void vm_area_add_early(struct vm_struct *vm); +__init void vm_area_register_early(struct vm_struct *vm, size_t align); + +int register_vmap_purge_notifier(struct notifier_block *nb); +int unregister_vmap_purge_notifier(struct notifier_block *nb); + #ifdef CONFIG_MMU +#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) + +unsigned long vmalloc_nr_pages(void); + int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); + static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); @@ -279,24 +293,14 @@ static inline void set_vm_flush_reset_perms(void *addr) if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } +#else /* !CONFIG_MMU */ +#define VMALLOC_TOTAL 0UL -#else -static inline void set_vm_flush_reset_perms(void *addr) -{ -} -#endif - -/* for /proc/kcore */ -extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); - -/* - * Internals. Don't use.. - */ -extern __init void vm_area_add_early(struct vm_struct *vm); -extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); +static inline unsigned long vmalloc_nr_pages(void) { return 0; } +static inline void set_vm_flush_reset_perms(void *addr) {} +#endif /* CONFIG_MMU */ -#ifdef CONFIG_SMP -# ifdef CONFIG_MMU +#if defined(CONFIG_MMU) && defined(CONFIG_SMP) struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); @@ -311,22 +315,9 @@ pcpu_get_vm_areas(const unsigned long *offsets, return NULL; } -static inline void -pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) -{ -} -# endif -#endif - -#ifdef CONFIG_MMU -#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) -#else -#define VMALLOC_TOTAL 0UL +static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) {} #endif -int register_vmap_purge_notifier(struct notifier_block *nb); -int unregister_vmap_purge_notifier(struct notifier_block *nb); - #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 9cd1beef0654..d961ead91bf1 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,7 +7,7 @@ struct lruvec; -extern atomic_t zswap_stored_pages; +extern atomic_long_t zswap_stored_pages; #ifdef CONFIG_ZSWAP |