diff options
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/codetag.h | 2 | ||||
| -rw-r--r-- | include/linux/execmem.h | 2 | ||||
| -rw-r--r-- | include/linux/fs.h | 1 | ||||
| -rw-r--r-- | include/linux/lockdep.h | 3 | ||||
| -rw-r--r-- | include/linux/lockdep_types.h | 3 | ||||
| -rw-r--r-- | include/linux/maple_tree.h | 16 | ||||
| -rw-r--r-- | include/linux/memcontrol.h | 21 | ||||
| -rw-r--r-- | include/linux/mm.h | 132 | ||||
| -rw-r--r-- | include/linux/mm_types.h | 40 | ||||
| -rw-r--r-- | include/linux/mmzone.h | 16 | ||||
| -rw-r--r-- | include/linux/nfs_fs.h | 1 | ||||
| -rw-r--r-- | include/linux/page_ext.h | 5 | ||||
| -rw-r--r-- | include/linux/pagemap.h | 40 | ||||
| -rw-r--r-- | include/linux/percpu-defs.h | 7 | ||||
| -rw-r--r-- | include/linux/rmap.h | 11 | ||||
| -rw-r--r-- | include/linux/sched.h | 1 | ||||
| -rw-r--r-- | include/linux/shmem_fs.h | 5 | ||||
| -rw-r--r-- | include/linux/swap.h | 30 | ||||
| -rw-r--r-- | include/linux/swap_ops.h | 44 | ||||
| -rw-r--r-- | include/linux/swapops.h | 7 | ||||
| -rw-r--r-- | include/linux/vm_event_item.h | 4 | ||||
| -rw-r--r-- | include/linux/vmalloc.h | 2 | ||||
| -rw-r--r-- | include/linux/vmstat.h | 17 |
23 files changed, 322 insertions, 88 deletions
diff --git a/include/linux/codetag.h b/include/linux/codetag.h index ddae7484ca45..a25a085c2df1 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -77,6 +77,8 @@ struct codetag_iterator { void codetag_lock_module_list(struct codetag_type *cttype); bool codetag_trylock_module_list(struct codetag_type *cttype); void codetag_unlock_module_list(struct codetag_type *cttype); +unsigned long codetag_get_content_id(struct codetag_type *cttype); +unsigned int codetag_get_count(struct codetag_type *cttype); struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); struct codetag *codetag_next_ct(struct codetag_iterator *iter); diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 7de229134e30..1bd34925d1aa 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -89,7 +89,7 @@ static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; } * @end: address space end (inclusive) * @fallback_start: start of the secondary address space range for fallback * allocations on architectures that require it - * @fallback_end: start of the secondary address space (inclusive) + * @fallback_end: end of the secondary address space (inclusive) * @pgprot: permissions for memory in this address space * @alignment: alignment required for text allocations * @flags: options for memory allocations for this range diff --git a/include/linux/fs.h b/include/linux/fs.h index 072d8cd09a0b..f9d1e05e8ae6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -438,7 +438,6 @@ struct address_space_operations { int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); - int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 621566345406..a6451ecbbe9a 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -273,6 +273,9 @@ extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); +extern u32 lock_sequence(struct lockdep_map *lock); +#define lockdep_sequence(lock) lock_sequence(&(lock)->dep_map) + #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) #define lockdep_assert(cond) \ diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index eae115a26488..55c4b152fedf 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -253,7 +253,8 @@ struct held_lock { unsigned int hardirqs_off:1; unsigned int sync:1; unsigned int references:11; /* 32 bits */ - unsigned int pin_count; + unsigned int pin_count:24; + unsigned int seq_count:8; }; #else /* !CONFIG_LOCKDEP */ diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 4a5631906aff..e595ae5cd0ee 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -11,7 +11,6 @@ #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> -/* #define CONFIG_MAPLE_RCU_DISABLED */ /* * Allocated nodes are mutable until they have been inserted into the tree, @@ -29,13 +28,11 @@ #define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ -#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) #else /* 32bit sizes */ #define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ -#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ #define MAPLE_NODE_MASK 255UL @@ -485,6 +482,12 @@ struct ma_state { unsigned char mas_flags; unsigned char end; /* The end of the node */ enum store_type store_type; /* The type of store needed for this operation */ +#ifdef CONFIG_LOCKDEP + u32 ld_seq; +#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD + unsigned long rcu_gp; +#endif /* CONFIG_RCU_STRICT_GRACE_PERIOD */ +#endif /* CONFIG_LOCKDEP */ }; struct ma_wr_state { @@ -567,12 +570,14 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); +bool mas_nomem_nofail(struct ma_state *mas, unsigned long index, + unsigned long last); void mas_pause(struct ma_state *mas); void maple_tree_init(void); void mas_destroy(struct ma_state *mas); void *mas_prev(struct ma_state *mas, unsigned long min); -void *mas_prev_range(struct ma_state *mas, unsigned long max); +void *mas_prev_range(struct ma_state *mas, unsigned long min); void *mas_next(struct ma_state *mas, unsigned long max); void *mas_next_range(struct ma_state *mas, unsigned long max); @@ -864,9 +869,6 @@ static inline void mt_init(struct maple_tree *mt) static inline bool mt_in_rcu(struct maple_tree *mt) { -#ifdef CONFIG_MAPLE_RCU_DISABLED - return false; -#endif return mt->ma_flags & MT_FLAGS_USE_RCU; } diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 71d045fe127f..7d1c0ce189a8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -239,8 +239,6 @@ struct mem_cgroup { */ bool oom_group; - int swappiness; - /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; @@ -270,10 +268,15 @@ struct mem_cgroup { #endif int kmemcg_id; - struct memcg_vmstats_percpu __percpu *vmstats_percpu; - #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; +#endif + + /* Keep the hot per-CPU stats pointer away from memory event counters. */ + struct memcg_vmstats_percpu __percpu *vmstats_percpu + ____cacheline_aligned_in_smp; + +#ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif @@ -318,6 +321,8 @@ struct mem_cgroup { /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; + + int swappiness; #endif /* CONFIG_MEMCG_V1 */ struct mem_cgroup_per_node *nodeinfo[]; @@ -947,6 +952,8 @@ unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); bool memcg_stat_item_valid(int idx); bool memcg_vm_event_item_valid(enum vm_event_item idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); +unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec, + enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); @@ -1399,6 +1406,12 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); } +static inline unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec, + enum node_stat_item idx) +{ + return node_page_state_monotonic(lruvec_pgdat(lruvec), idx); +} + static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 87feaa5a2b78..dd09c438fa23 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1556,7 +1556,7 @@ static inline void vma_desc_set_anonymous(struct vm_area_desc *desc) desc->vm_ops = NULL; } -static inline bool vma_is_anonymous(struct vm_area_struct *vma) +static inline bool vma_is_anonymous(const struct vm_area_struct *vma) { return !vma->vm_ops; } @@ -2271,17 +2271,76 @@ void unpin_user_pages(struct page **pages, unsigned long npages); void unpin_user_folio(struct folio *folio, unsigned long npages); void unpin_folios(struct folio **folios, unsigned long nfolios); -static inline bool is_cow_mapping(vm_flags_t flags) +/** + * vma_flags_is_cow_mapping() - Do these VMA flags imply a CoW mapping? + * @flags: The VMA flags to check. + * + * Mappings which could be CoW'd (subject to Copy-On-Write faults) are + * described as CoW mappings. + * + * All mappings backed by anonymous folios (all anonymous mappings and most + * MAP_PRIVATE-file backed ranges) are CoW mappings. + * + * All other mappings (including all MAP_SHARED mappings) are non-CoW. + * + * The criteria are !VMA_SHARED_BIT, VMA_MAYWRITE_BIT. + * + * VMA_MAYWRITE_BIT is checked instead of VMA_WRITE_BIT to account for both + * future mprotect() calls which can render a read-only mapping writable, and + * GUP with FOLL_FORCE (e.g. ptrace) which can CoW a read-only mapping. + * + * - No anonymous mapping can ever clear VMA_MAYWRITE_BIT. + * + * - Writes to anonymous mappings do not immediately result in CoW faults but + * may do so after the process is forked or if a read is followed by a + * write. + * + * - Writes to MAP_PRIVATE file-backed mappings result in CoW faults and may + * do so again after fork. + * + * - MAP_SHARED mappings of a file opened read-only are transformed into + * VMA_MAYSHARE_BIT, !VMA_SHARED_BIT, !VMA_MAYWRITE_BIT mappings, so remain + * non-CoW. + * + * - Drivers may clear VMA_MAYWRITE_BIT but do so at mmap() time and cannot + * mark themselves anonymous. Having cleared this flag it is not valid for + * them to leave the VMA_WRITE_BIT flag set. + * + * As a consequence, the anonymous reverse mapping only tracks CoW mappings. + * + * Returns: true if the flags indicate a CoW mapping, otherwise false. + */ +static inline bool vma_flags_is_cow_mapping(const vma_flags_t *flags) { - return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + return vma_flags_test(flags, VMA_MAYWRITE_BIT) && + !vma_flags_test(flags, VMA_SHARED_BIT); } -static inline bool vma_desc_is_cow_mapping(struct vm_area_desc *desc) +/** + * vma_is_cow_mapping() - Is this VMA a CoW mapping? + * @vma: The VMA to check. + * + * See vma_flags_is_cow_mapping() for details. + * + * Returns: true if the VMA is a CoW mapping, otherwise false. + */ +static inline bool vma_is_cow_mapping(const struct vm_area_struct *vma) { - const vma_flags_t *flags = &desc->vma_flags; + return vma_flags_is_cow_mapping(&vma->flags); +} - return vma_flags_test(flags, VMA_MAYWRITE_BIT) && - !vma_flags_test(flags, VMA_SHARED_BIT); +/** + * vma_desc_is_cow_mapping() - Is this VMA descriptor a CoW mapping? + * @desc: The VMA descriptor to check. + * + * See vma_flags_is_cow_mapping() for details. + * + * Returns: true if the VMA descriptor describes a CoW mapping, otherwise + * false. + */ +static inline bool vma_desc_is_cow_mapping(struct vm_area_desc *desc) +{ + return vma_flags_is_cow_mapping(&desc->vma_flags); } #ifndef CONFIG_MMU @@ -4393,6 +4452,65 @@ static inline pgoff_t vma_last_pgoff(const struct vm_area_struct *vma) return vma_end_pgoff(vma) - 1; } +/** + * vma_start_anon_pgoff() - Get the anonymous page offset of the start of @vma + * @vma: The VMA whose anonymous page offset is required. + * + * If unfaulted, then this is vma->vm_start >> PAGE_SHIFT, if faulted then the + * anonymous page offset at the time of first fault. + * + * If the VMA is anonymous, this returns the same value as vma_start_pgoff(). + * + * This value is used for tracking MAP_PRIVATE file-backed mappings by their + * anonymous page offset. + * + * Returns: The anonymous page offset of the start of @vma. + */ +static inline pgoff_t vma_start_anon_pgoff(const struct vm_area_struct *vma) +{ + pgoff_t pgoff = 0; + +#ifdef CONFIG_64BIT + pgoff += vma->__vm_anon_pgoff_hi; + pgoff <<= 32; +#endif + pgoff += vma->__vm_anon_pgoff_lo; + return pgoff; +} + +/** + * vma_end_anon_pgoff() - Get the anonymous page offset of the exclusive end of + * @vma. + * @vma: The VMA whose end anonymous page offset is required. + * + * This returns the anonymous exclusive end page offset of @vma, which is useful + * for expressing page offset ranges. + * + * See the description of vma_start_anon_pgoff() for a description of VMA + * anonymous page offsets. + * + * Returns: The exclusive end anonymous page offset of @vma. + */ +static inline pgoff_t vma_end_anon_pgoff(const struct vm_area_struct *vma) +{ + return vma_start_anon_pgoff(vma) + vma_pages(vma); +} + +/** + * vma_last_anon_pgoff() - Get the anonymous page offset of the last page in + * @vma. + * @vma: The VMA whose last anonymous page offset is required. + * + * See the description of vma_start_anon_pgoff() for a description of VMA + * anonymous page offsets. + * + * Returns: The last anonymous page offset of @vma. + */ +static inline pgoff_t vma_last_anon_pgoff(const struct vm_area_struct *vma) +{ + return vma_end_anon_pgoff(vma) - 1; +} + static inline unsigned long vma_desc_size(const struct vm_area_desc *desc) { return desc->end - desc->start; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 939b5ea8c9e0..6d815f6440c9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -968,6 +968,11 @@ struct vm_area_struct { unsigned int vm_lock_seq; #endif /* + * Low 32-bits of anonymous page offset. + * See vma_start_anon_pgoff() comment for details. + */ + unsigned int __vm_anon_pgoff_lo; + /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack @@ -1042,6 +1047,13 @@ struct vm_area_struct { struct lockdep_map vmlock_dep_map; #endif #endif +#ifdef CONFIG_64BIT + /* + * High 32-bits of anonymous page offset. + * See vma_start_anon_pgoff() comment for details. + */ + unsigned int __vm_anon_pgoff_hi; +#endif /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. @@ -1706,20 +1718,20 @@ enum vm_fault_reason { VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK) -#define VM_FAULT_RESULT_TRACE \ - { VM_FAULT_OOM, "OOM" }, \ - { VM_FAULT_SIGBUS, "SIGBUS" }, \ - { VM_FAULT_MAJOR, "MAJOR" }, \ - { VM_FAULT_HWPOISON, "HWPOISON" }, \ - { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ - { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ - { VM_FAULT_NOPAGE, "NOPAGE" }, \ - { VM_FAULT_LOCKED, "LOCKED" }, \ - { VM_FAULT_RETRY, "RETRY" }, \ - { VM_FAULT_FALLBACK, "FALLBACK" }, \ - { VM_FAULT_DONE_COW, "DONE_COW" }, \ - { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \ - { VM_FAULT_COMPLETED, "COMPLETED" } +#define VM_FAULT_RESULT_TRACE \ + { (__force u32)VM_FAULT_OOM, "OOM" }, \ + { (__force u32)VM_FAULT_SIGBUS, "SIGBUS" }, \ + { (__force u32)VM_FAULT_MAJOR, "MAJOR" }, \ + { (__force u32)VM_FAULT_HWPOISON, "HWPOISON" }, \ + { (__force u32)VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ + { (__force u32)VM_FAULT_SIGSEGV, "SIGSEGV" }, \ + { (__force u32)VM_FAULT_NOPAGE, "NOPAGE" }, \ + { (__force u32)VM_FAULT_LOCKED, "LOCKED" }, \ + { (__force u32)VM_FAULT_RETRY, "RETRY" }, \ + { (__force u32)VM_FAULT_FALLBACK, "FALLBACK" }, \ + { (__force u32)VM_FAULT_DONE_COW, "DONE_COW" }, \ + { (__force u32)VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \ + { (__force u32)VM_FAULT_COMPLETED, "COMPLETED" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0507193b3ae3..94f9c3ff5416 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -323,6 +323,8 @@ enum node_stat_item { PGSCAN_PROACTIVE, PGSCAN_ANON, PGSCAN_FILE, + PGROTATE_ANON, + PGROTATE_FILE, PGREFILL, #ifdef CONFIG_HUGETLB_PAGE NR_HUGETLB, @@ -755,6 +757,12 @@ void lru_gen_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, #endif /* CONFIG_LRU_GEN */ +struct lru_cost { + unsigned long count; + unsigned long last_rotated; + unsigned long last_io; +}; + struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ @@ -763,9 +771,12 @@ struct lruvec { * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. + * Updated and decayed at prepare_scan_control() time; cost_lock + * serialises that update. */ - unsigned long anon_cost; - unsigned long file_cost; + struct lru_cost cost[ANON_AND_FILE]; + /* Protects cost[]. */ + spinlock_t cost_lock; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ @@ -2058,7 +2069,6 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } -extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store a little bit of diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48b806aa3a2f..b85a73ae7919 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -552,7 +552,6 @@ static inline const struct cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, bool swap); ssize_t nfs_file_direct_write(struct kiocb *iocb, diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index f23d4b218da0..79c53ec45dfa 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -55,7 +55,6 @@ struct page_ext { extern bool early_page_ext; extern unsigned long page_ext_size; -extern void pgdat_page_ext_init(struct pglist_data *pgdat); static inline bool early_page_ext_enabled(void) { @@ -202,10 +201,6 @@ static inline bool early_page_ext_enabled(void) return false; } -static inline void pgdat_page_ext_init(struct pglist_data *pgdat) -{ -} - static inline void page_ext_init(void) { } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c6fc783aaee5..0adfa6605653 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1094,10 +1094,44 @@ static inline pgoff_t linear_page_delta(const struct vm_area_struct *vma, static inline pgoff_t linear_page_index(const struct vm_area_struct *vma, const unsigned long address) { - pgoff_t pgoff; + return linear_page_delta(vma, address) + vma_start_pgoff(vma); +} + +static inline pgoff_t __linear_anon_page_index(const struct vm_area_struct *vma, + const unsigned long address) +{ + return linear_page_delta(vma, address) + vma_start_anon_pgoff(vma); +} + +/** + * linear_anon_page_index() - Determine the absolute anonymous page offset of + * @address within @vma. + * @vma: An anonymous or MAP_PRIVATE file-backed VMA in which @address resides. + * @address: The address whose absolute page offset is required. + * + * This returns the anonymous page offset of @address, which is the page offset + * the address possessed at the time the VMA was first faulted. + * + * For anonymous mappings, this returns the same value as linear_page_index(). + * + * For MAP_PRIVATE file-backed mappings, this returns the anonymous page offset + * of @address, which is the page offset the address possessed at the time the + * VMA was first faulted. + * + * It is not valid to call this function for shared file-backed mappings. + * + * Returns: The absolute anonymous page offset of @address within @vma. + */ +static inline pgoff_t linear_anon_page_index(const struct vm_area_struct *vma, + const unsigned long address) +{ + const pgoff_t pgoff = __linear_anon_page_index(vma, address); + + VM_WARN_ON_ONCE(!vma_is_cow_mapping(vma)); + /* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */ + if (vma_is_anonymous(vma) && !vma->vm_file) + VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address)); - pgoff = linear_page_delta(vma, address); - pgoff += vma_start_pgoff(vma); return pgoff; } diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 2cba7cc2b01f..dbe3267a0a13 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -65,13 +65,8 @@ * * Archs which need weak percpu definitions should set * CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU when necessary. - * - * To ensure that the generic code observes the above two - * restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak - * definition is used for all cases. */ -#if (defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE)) || \ - defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU) +#if defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE) /* * __pcpu_scope_* dummy variable is used to enforce scope. It * receives the static modifier when it's used in front of diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8dc0871e5f00..0b332770abee 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -843,7 +843,7 @@ static inline int folio_try_share_anon_rmap_pmd(struct folio *folio, * Called from mm/vmscan.c to handle paging out */ int folio_referenced(struct folio *, int is_locked, - struct mem_cgroup *memcg, vm_flags_t *vm_flags); + struct mem_cgroup *memcg, vma_flags_t *vma_flags); void try_to_migrate(struct folio *folio, enum ttu_flags flags); void try_to_unmap(struct folio *, enum ttu_flags flags); @@ -864,13 +864,14 @@ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, struct page_vma_mapped_walk { unsigned long pfn; unsigned long nr_pages; - pgoff_t pgoff; + pgoff_t pgoff; /* Only meaningful if nr_pages > 1 and not a KSM walk */ struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; unsigned int flags; + bool pgoff_is_anon : 1; }; #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ @@ -881,6 +882,7 @@ struct page_vma_mapped_walk { .vma = _vma, \ .address = _address, \ .flags = _flags, \ + .pgoff_is_anon = folio_test_anon(_folio), \ } static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) @@ -975,10 +977,9 @@ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, #define anon_vma_prepare(vma) (0) static inline int folio_referenced(struct folio *folio, int is_locked, - struct mem_cgroup *memcg, - vm_flags_t *vm_flags) + struct mem_cgroup *memcg, vma_flags_t *vma_flags) { - *vm_flags = 0; + vma_flags_clear_all(vma_flags); return 0; } diff --git a/include/linux/sched.h b/include/linux/sched.h index c7cdbb3e4aa6..8b3d47a325cc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1298,6 +1298,7 @@ struct task_struct { u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; + unsigned int lockdep_seq; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index e729b9b0e38d..5663dff53186 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -12,8 +12,6 @@ #include <linux/userfaultfd_k.h> #include <linux/bits.h> -struct swap_iocb; - /* inode in-kernel data */ #ifdef CONFIG_TMPFS_QUOTA @@ -123,8 +121,7 @@ static inline bool shmem_mapping(const struct address_space *mapping) void shmem_unlock_mapping(struct address_space *mapping); struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -int shmem_writeout(struct folio *folio, struct swap_iocb **plug, - struct list_head *folio_list); +int shmem_write_folio(struct folio *folio); void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end); int shmem_unuse(unsigned int type); diff --git a/include/linux/swap.h b/include/linux/swap.h index 696ed01709c2..5658a1634b85 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -202,7 +202,6 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ - SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ @@ -276,6 +275,7 @@ struct swap_info_struct { struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_list; /* entry in swap_avail_head */ + const struct swap_ops *ops; }; static inline swp_entry_t page_swap_entry(struct page *page) @@ -298,6 +298,14 @@ void folio_add_lru(struct folio *folio); void folio_mark_accessed(struct folio *folio); void lru_add_drain_all(void); +enum lru_cache_drained { + LRU_CACHE_NOT_DRAINED, + LRU_CACHE_DRAINED, + LRU_CACHE_DRAINED_ALL, +}; +void lru_cache_drain_for_folio(const struct folio *folio, + unsigned int extra_refs, enum lru_cache_drained *drained); + /* linux/mm/folio-compat.c */ void mark_page_accessed(struct page *page); @@ -309,7 +317,6 @@ static inline bool lru_cache_disabled(void) } extern unsigned long shrink_all_memory(unsigned long nr_pages); -extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) @@ -334,7 +341,6 @@ extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP - int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, @@ -468,25 +474,7 @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ #ifdef CONFIG_MEMCG -static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) -{ - /* Cgroup2 doesn't have per-cgroup swappiness */ - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return READ_ONCE(vm_swappiness); - - /* root ? */ - if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) - return READ_ONCE(vm_swappiness); - - return READ_ONCE(memcg->swappiness); -} - void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid); -#else -static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) -{ - return READ_ONCE(vm_swappiness); -} #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) diff --git a/include/linux/swap_ops.h b/include/linux/swap_ops.h new file mode 100644 index 000000000000..57ac6c703f68 --- /dev/null +++ b/include/linux/swap_ops.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MM_SWAP_OPS_H +#define _MM_SWAP_OPS_H + +#include <linux/swap.h> /* for SWAP_CLUSTER_MAX */ + +struct swap_iocb { + union { + struct kiocb iocb; + struct bio bio; + }; + struct bio_vec bvecs[SWAP_CLUSTER_MAX]; + int nr_bvecs; + int len; +}; + +struct swap_io_ctx { + struct swap_iocb *sio; + struct swap_info_struct *sis; +}; + +/* + * SWAP_OPS_F_REQUIRE_NOFS: + * When set, all reclaim operations must operated as GFS_NOFS and not + * just GFP_NOIO, as GFP_NOIO allocations could recourse into the + * file system backing this swap file. + */ +#define SWAP_OPS_F_REQUIRE_NOFS (1U << 0) + +struct swap_ops { + unsigned int flags; + + bool (*can_merge)(struct folio *folio, struct folio *prev_folio, + size_t prev_folio_size, int rw); + void (*submit_write)(struct swap_io_ctx *ctx); + void (*submit_read)(struct swap_io_ctx *ctx); +}; + +void swap_fs_prepare_rw(struct swap_io_ctx *ctx, int rw, struct iov_iter *iter); +bool swap_fs_can_merge(struct folio *folio, struct folio *prev_folio, + size_t prev_folio_size, int rw); +int swap_fs_activate(struct swap_info_struct *sis, const struct swap_ops *ops); + +#endif /* _MM_SWAP_OPS_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index c956bc445ee0..e7d0d529f3e0 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -5,6 +5,7 @@ #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> +#include <linux/swap.h> #ifdef CONFIG_MMU @@ -325,8 +326,8 @@ struct page_vma_mapped_walk; extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); -extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, - struct page *new); +void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, + struct folio *folio); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); @@ -346,7 +347,7 @@ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, - struct page *new) + struct folio *folio) { BUILD_BUG(); } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 03fe95f5a020..2628ccda076a 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -175,6 +175,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSTACK_REST, #endif #endif /* CONFIG_DEBUG_STACK_USAGE */ +#ifdef CONFIG_SWAP + NRSWPIN, + NRSWPOUT, +#endif /* CONFIG_SWAP */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index e4d8d0a9f30f..aed121d729b0 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -62,7 +62,7 @@ struct vm_struct { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC unsigned int page_order; #endif - unsigned int nr_pages; + unsigned long nr_pages; phys_addr_t phys_addr; const void *caller; unsigned long requested_size; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3c9c266cf782..5b31d8e7ae40 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -20,7 +20,6 @@ struct reclaim_stat { unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; - unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; @@ -194,6 +193,19 @@ unsigned long global_node_page_state_pages(enum node_stat_item item) return x; } +/* + * Non-clamping variant of global_node_page_state() intended for callers that + * snapshot a monotonically-incremented counter and subtract two samples. + * Returns the raw wrapping value so that unsigned modular subtraction stays + * correct across a signed-long overflow (a real hazard on 32-bit) that the + * clamp in global_node_page_state() would otherwise turn into a huge spurious + * delta. Do NOT use for non-monotonic page-count reads. + */ +static inline unsigned long global_node_page_state_monotonic(enum node_stat_item item) +{ + return (unsigned long)atomic_long_read(&vm_node_stat[item]); +} + static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); @@ -259,11 +271,14 @@ extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); +extern unsigned long node_page_state_monotonic(struct pglist_data *pgdat, + enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) +#define node_page_state_monotonic(node, item) global_node_page_state_monotonic(item) static inline void fold_vm_numa_events(void) { } |