diff options
Diffstat (limited to 'include/linux/swap.h')
| -rw-r--r-- | include/linux/swap.h | 546 |
1 files changed, 311 insertions, 235 deletions
diff --git a/include/linux/swap.h b/include/linux/swap.h index d83d28e53e62..38ca3df68716 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H @@ -9,17 +10,20 @@ #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> +#include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> +#include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; +struct pagevec; + #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff -#define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ @@ -51,12 +55,49 @@ static inline int current_is_kswapd(void) */ /* - * NUMA node memory migration support + * PTE markers are used to persist information onto PTEs that otherwise + * should be a none pte. As its name "PTE" hints, it should only be + * applied to the leaves of pgtables. + */ +#define SWP_PTE_MARKER_NUM 1 +#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM) + +/* + * Unaddressable device memory support. See include/linux/hmm.h and + * Documentation/mm/hmm.rst. Short description is we need struct pages for + * device memory that is unaddressable (inaccessible) by CPU, so that we can + * migrate part of a process memory to device memory. + * + * When a page is migrated from CPU to device, we set the CPU page table entry + * to a special SWP_DEVICE_{READ|WRITE} entry. + * + * When a page is mapped by the device for exclusive access we set the CPU page + * table entries to a special SWP_DEVICE_EXCLUSIVE entry. + */ +#ifdef CONFIG_DEVICE_PRIVATE +#define SWP_DEVICE_NUM 3 +#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) +#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#define SWP_DEVICE_EXCLUSIVE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) +#else +#define SWP_DEVICE_NUM 0 +#endif + +/* + * Page migration support. + * + * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and + * indicates that the referenced (part of) an anonymous page is exclusive to + * a single process. For SWP_MIGRATION_WRITE, that information is implicit: + * (part of) an anonymous page that are mapped writable are exclusive to a + * single process. */ #ifdef CONFIG_MIGRATION -#define SWP_MIGRATION_NUM 2 -#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_NUM 3 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif @@ -72,7 +113,9 @@ static inline int current_is_kswapd(void) #endif #define MAX_SWAPFILES \ - ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ + SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is @@ -108,9 +151,28 @@ union swap_header { * memory reclaim */ struct reclaim_state { - unsigned long reclaimed_slab; + /* pages reclaimed outside of LRU-based reclaim */ + unsigned long reclaimed; +#ifdef CONFIG_LRU_GEN + /* per-thread mm walk data */ + struct lru_gen_mm_walk *mm_walk; +#endif }; +/* + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based + * reclaim + * @pages: number of pages reclaimed + * + * If the current process is undergoing a reclaim operation, increment the + * number of reclaimed pages by @pages. + */ +static inline void mm_account_reclaimed_pages(unsigned long pages) +{ + if (current->reclaim_state) + current->reclaim_state->reclaimed += pages; +} + #ifdef __KERNEL__ struct address_space; @@ -120,14 +182,14 @@ struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of - * disk blocks. A list of swap extents maps the entire swapfile. (Where the - * term `swapfile' refers to either a blockdevice or an IS_REG file. Apart + * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the + * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { - struct list_head list; + struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; @@ -136,9 +198,9 @@ struct swap_extent { /* * Max bad pages in the new format.. */ -#define __swapoffset(x) ((unsigned long)&((union swap_header *)0)->x) #define MAX_SWAP_BADPAGES \ - ((__swapoffset(magic.magic) - __swapoffset(info.badpages)) / sizeof(int)) + ((offsetof(union swap_header, magic.magic) - \ + offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ @@ -148,233 +210,236 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ + 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 */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 11), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL +#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX -#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */ -#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */ +/* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ -#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */ -#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */ -#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */ +#define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ + +/* Special value in first swap_map */ +#define SWAP_MAP_MAX 0x3e /* Max count */ +#define SWAP_MAP_BAD 0x3f /* Note page is bad */ +#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ + +/* Special value in each swap_map continuation */ +#define SWAP_CONT_MAX 0x7f /* Max count */ /* - * We use this to track usage of a cluster. A cluster is a block of swap disk - * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All - * free clusters are organized into a list. We fetch an entry from the list to - * get a free cluster. - * - * The data field stores next cluster if the cluster is free or cluster usage - * counter otherwise. The flags field determines if a cluster is free. This is - * protected by swap_info_struct.lock. + * The first page in the swap file is the swap header, which is always marked + * bad to prevent it from being allocated as an entry. This also prevents the + * cluster to which it belongs being marked free. Therefore 0 is safe to use as + * a sentinel to indicate an entry is not valid. */ -struct swap_cluster_info { - spinlock_t lock; /* - * Protect swap_cluster_info fields - * and swap_info_struct->swap_map - * elements correspond to the swap - * cluster - */ - unsigned int data:24; - unsigned int flags:8; -}; -#define CLUSTER_FLAG_FREE 1 /* This cluster is free */ -#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ +#define SWAP_ENTRY_INVALID 0 + +#ifdef CONFIG_THP_SWAP +#define SWAP_NR_ORDERS (PMD_ORDER + 1) +#else +#define SWAP_NR_ORDERS 1 +#endif /* - * We assign a cluster to each CPU, so each CPU can allocate swap entry from - * its own cluster and swapout sequentially. The purpose is to optimize swapout - * throughput. + * We keep using same cluster for rotational device so IO will be sequential. + * The purpose is to optimize SWAP throughput on these device. */ -struct percpu_cluster { - struct swap_cluster_info index; /* Current cluster index */ - unsigned int next; /* Likely next allocation offset */ -}; - -struct swap_cluster_list { - struct swap_cluster_info head; - struct swap_cluster_info tail; +struct swap_sequential_cluster { + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { + struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ - struct plist_node avail_list; /* entry in swap_avail_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ + unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ - struct swap_cluster_list free_clusters; /* free clusters list */ - unsigned int lowest_bit; /* index of first free in swap_map */ - unsigned int highest_bit; /* index of last free in swap_map */ + struct list_head free_clusters; /* free clusters list */ + struct list_head full_clusters; /* full clusters list */ + struct list_head nonfull_clusters[SWAP_NR_ORDERS]; + /* list of cluster that contains at least one free slot */ + struct list_head frag_clusters[SWAP_NR_ORDERS]; + /* list of cluster that are fragmented or contented */ unsigned int pages; /* total of usable pages of swap */ - unsigned int inuse_pages; /* number of those currently in use */ - unsigned int cluster_next; /* likely index for next allocation */ - unsigned int cluster_nr; /* countdown to next cluster search */ - struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ - struct swap_extent *curr_swap_extent; - struct swap_extent first_swap_extent; + atomic_long_t inuse_pages; /* number of those currently in use */ + struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */ + spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ + struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ - unsigned int old_block_size; /* seldom referenced */ -#ifdef CONFIG_FRONTSWAP - unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ - atomic_t frontswap_pages; /* frontswap pages in-use counter */ -#endif + struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like - * swap_map, lowest_bit, highest_bit, - * inuse_pages, cluster_next, - * cluster_nr, lowest_alloc, - * highest_alloc, free/discard cluster - * list. other fields are only changed + * swap_map, inuse_pages and all cluster + * lists. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ + spinlock_t cont_lock; /* + * protect swap count continuation page + * list. + */ struct work_struct discard_work; /* discard worker */ - struct swap_cluster_list discard_clusters; /* discard clusters list */ + 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 */ }; +static inline swp_entry_t page_swap_entry(struct page *page) +{ + struct folio *folio = page_folio(page); + swp_entry_t entry = folio->swap; + + entry.val += folio_page_idx(folio, page); + return entry; +} + /* linux/mm/workingset.c */ -void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); -void workingset_activation(struct page *page); -void workingset_update_node(struct radix_tree_node *node, void *private); +bool workingset_test_recent(void *shadow, bool file, bool *workingset, + bool flush); +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); +void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); +void workingset_refault(struct folio *folio, void *shadow); +void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ -extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; -extern unsigned long nr_free_buffer_pages(void); -extern unsigned long nr_free_pagecache_pages(void); -/* Definition of global_page_state not available yet */ -#define nr_free_pages() global_page_state(NR_FREE_PAGES) +/* Definition of global_zone_page_state not available yet */ +#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ -extern void lru_cache_add(struct page *); -extern void lru_cache_add_anon(struct page *page); -extern void lru_cache_add_file(struct page *page); -extern void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec, struct list_head *head); -extern void activate_page(struct page *); -extern void mark_page_accessed(struct page *); +void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, + unsigned int nr_io, unsigned int nr_rotated) + __releases(lruvec->lru_lock); +void lru_note_cost_refault(struct folio *); +void folio_add_lru(struct folio *); +void folio_add_lru_vma(struct folio *, struct vm_area_struct *); +void mark_page_accessed(struct page *); +void folio_mark_accessed(struct folio *); + +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + +extern atomic_t lru_disable_count; + +static inline bool lru_cache_disabled(void) +{ + return atomic_read(&lru_disable_count); +} + +static inline void lru_cache_enable(void) +{ + atomic_dec(&lru_disable_count); +} + +extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); +extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void lru_add_drain_all_cpuslocked(void); -extern void rotate_reclaimable_page(struct page *page); -extern void deactivate_file_page(struct page *page); -extern void mark_page_lazyfree(struct page *page); +void folio_deactivate(struct folio *folio); +void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); -extern void add_page_to_unevictable_list(struct page *page); - -extern void lru_cache_add_active_or_unevictable(struct page *page, - struct vm_area_struct *vma); - /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); -extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern int __isolate_lru_page(struct page *page, isolate_mode_t mode); + +#define MEMCG_RECLAIM_MAY_SWAP (1 << 1) +#define MEMCG_RECLAIM_PROACTIVE (1 << 2) +#define MIN_SWAPPINESS 0 +#define MAX_SWAPPINESS 200 + +/* Just reclaim from anon folios in proactive memory reclaim */ +#define SWAPPINESS_ANON_ONLY (MAX_SWAPPINESS + 1) + extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - bool may_swap); + unsigned int reclaim_options, + int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -extern int remove_mapping(struct address_space *mapping, struct page *page); -extern unsigned long vm_total_pages; +long remove_mapping(struct address_space *mapping, struct folio *folio); + +#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) +extern int reclaim_register_node(struct node *node); +extern void reclaim_unregister_node(struct node *node); -#ifdef CONFIG_NUMA -extern int node_reclaim_mode; -extern int sysctl_min_unmapped_ratio; -extern int sysctl_min_slab_ratio; -extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); #else -#define node_reclaim_mode 0 -static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, - unsigned int order) + +static inline int reclaim_register_node(struct node *node) { return 0; } -#endif -extern int page_evictable(struct page *page); -extern void check_move_unevictable_pages(struct page **, int nr_pages); +static inline void reclaim_unregister_node(struct node *node) +{ +} +#endif /* CONFIG_SYSFS && CONFIG_NUMA */ -extern int kswapd_run(int nid); -extern void kswapd_stop(int nid); +#ifdef CONFIG_NUMA +extern int sysctl_min_unmapped_ratio; +extern int sysctl_min_slab_ratio; +#endif -#ifdef CONFIG_SWAP +void check_move_unevictable_folios(struct folio_batch *fbatch); -#include <linux/blk_types.h> /* for bio_end_io_t */ +extern void __meminit kswapd_run(int nid); +extern void __meminit kswapd_stop(int nid); -/* linux/mm/page_io.c */ -extern int swap_readpage(struct page *page, bool do_poll); -extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern void end_swap_bio_write(struct bio *bio); -extern int __swap_writepage(struct page *page, struct writeback_control *wbc, - bio_end_io_t end_write_func); -extern int swap_set_page_dirty(struct page *page); +#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 *, sector_t *); -/* linux/mm/swap_state.c */ -/* One swap address space for each 64M swap space */ -#define SWAP_ADDRESS_SPACE_SHIFT 14 -#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) -extern struct address_space *swapper_spaces[]; -#define swap_address_space(entry) \ - (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ - >> SWAP_ADDRESS_SPACE_SHIFT]) -extern unsigned long total_swapcache_pages(void); -extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *page); -extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); -extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); -extern void __delete_from_swap_cache(struct page *); -extern void delete_from_swap_cache(struct page *); -extern void free_page_and_swap_cache(struct page *); -extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t); -extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool do_poll); -extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated); -extern struct page *swapin_readahead(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr); +static inline unsigned long total_swapcache_pages(void) +{ + return global_node_page_state(NR_SWAPCACHE); +} +void free_swap_cache(struct folio *folio); +void free_folio_and_swap_cache(struct folio *folio); +void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; -extern bool has_usable_swap(void); +extern atomic_t nr_rotate_swap; /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) @@ -388,34 +453,42 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(struct page *page); -extern void put_swap_page(struct page *page, swp_entry_t entry); +int folio_alloc_swap(struct folio *folio); +bool folio_free_swap(struct folio *folio); +void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, bool cluster, swp_entry_t swp_entries[]); extern int add_swap_count_continuation(swp_entry_t, gfp_t); -extern void swap_shmem_alloc(swp_entry_t); +extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); -extern int swapcache_prepare(swp_entry_t); -extern void swap_free(swp_entry_t); -extern void swapcache_free_entries(swp_entry_t *entries, int n); -extern int free_swap_and_cache(swp_entry_t); -extern int swap_type_of(dev_t, sector_t, struct block_device **); +extern int swapcache_prepare(swp_entry_t entry, int nr); +extern void swap_free_nr(swp_entry_t entry, int nr_pages); +extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); +int swap_type_of(dev_t device, sector_t offset); +int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); -extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); -extern int page_swapcount(struct page *); -extern int __swp_swapcount(swp_entry_t entry); +extern int __swap_count(swp_entry_t entry); +extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); -extern struct swap_info_struct *page_swap_info(struct page *); -extern bool reuse_swap_page(struct page *, int *); -extern int try_to_free_swap(struct page *); struct backing_dev_info; -extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); -extern void exit_swap_address_space(unsigned int type); +extern struct swap_info_struct *get_swap_device(swp_entry_t entry); +sector_t swap_folio_sector(struct folio *folio); + +static inline void put_swap_device(struct swap_info_struct *si) +{ + percpu_ref_put(&si->users); +} #else /* CONFIG_SWAP */ +static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + return NULL; +} + +static inline void put_swap_device(struct swap_info_struct *si) +{ +} -#define swap_address_space(entry) (NULL) #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -423,26 +496,25 @@ extern void exit_swap_address_space(unsigned int type); #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) -/* only sparc can not include linux/pagemap.h in this file - * so leave put_page and release_pages undeclared... */ -#define free_page_and_swap_cache(page) \ - put_page(page) +#define free_folio_and_swap_cache(folio) \ + folio_put(folio) #define free_pages_and_swap_cache(pages, nr) \ - release_pages((pages), (nr), false); + release_pages((pages), (nr)); -static inline void show_swap_cache_info(void) +static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) { } -#define free_swap_and_cache(swp) is_migration_entry(swp) -#define swapcache_prepare(swp) is_migration_entry(swp) +static inline void free_swap_cache(struct folio *folio) +{ +} static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } -static inline void swap_shmem_alloc(swp_entry_t swp) +static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } @@ -451,114 +523,118 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } -static inline void swap_free(swp_entry_t swp) +static inline int swapcache_prepare(swp_entry_t swp, int nr) { + return 0; } -static inline void put_swap_page(struct page *page, swp_entry_t swp) +static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } -static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, - struct vm_area_struct *vma, unsigned long addr) +static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { - return NULL; } -static inline int swap_writepage(struct page *p, struct writeback_control *wbc) +static inline int __swap_count(swp_entry_t entry) { return 0; } -static inline struct page *lookup_swap_cache(swp_entry_t swp) +static inline bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { - return NULL; + return false; } -static inline int add_to_swap(struct page *page) +static inline int swp_swapcount(swp_entry_t entry) { return 0; } -static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp_mask) -{ - return -1; -} - -static inline void __delete_from_swap_cache(struct page *page) -{ -} - -static inline void delete_from_swap_cache(struct page *page) +static inline int folio_alloc_swap(struct folio *folio) { + return -EINVAL; } -static inline int page_swapcount(struct page *page) +static inline bool folio_free_swap(struct folio *folio) { - return 0; -} - -static inline int __swp_swapcount(swp_entry_t entry) -{ - return 0; + return false; } -static inline int swp_swapcount(swp_entry_t entry) +static inline int add_swap_extent(struct swap_info_struct *sis, + unsigned long start_page, + unsigned long nr_pages, sector_t start_block) { - return 0; + return -EINVAL; } +#endif /* CONFIG_SWAP */ -#define reuse_swap_page(page, total_mapcount) \ - (page_trans_huge_mapcount(page, total_mapcount) == 1) - -static inline int try_to_free_swap(struct page *page) +static inline void free_swap_and_cache(swp_entry_t entry) { - return 0; + free_swap_and_cache_nr(entry, 1); } -static inline swp_entry_t get_swap_page(struct page *page) +static inline void swap_free(swp_entry_t entry) { - swp_entry_t entry; - entry.val = 0; - return entry; + swap_free_nr(entry, 1); } -#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 vm_swappiness; + return READ_ONCE(vm_swappiness); /* root ? */ - if (mem_cgroup_disabled() || !memcg->css.parent) - return vm_swappiness; + if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) + return READ_ONCE(vm_swappiness); - return memcg->swappiness; + return READ_ONCE(memcg->swappiness); } - #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { - return vm_swappiness; + return READ_ONCE(vm_swappiness); } #endif -#ifdef CONFIG_MEMCG_SWAP -extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); -extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); -extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); -extern bool mem_cgroup_swap_full(struct page *page); +#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ + if (mem_cgroup_disabled()) + return; + __folio_throttle_swaprate(folio, gfp); +} #else -static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ +} +#endif + +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); +static inline int mem_cgroup_try_charge_swap(struct folio *folio, + swp_entry_t entry) { + if (mem_cgroup_disabled()) + return 0; + return __mem_cgroup_try_charge_swap(folio, entry); } -static inline int mem_cgroup_try_charge_swap(struct page *page, +extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); +static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge_swap(entry, nr_pages); +} + +extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); +extern bool mem_cgroup_swap_full(struct folio *folio); +#else +static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; @@ -574,7 +650,7 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) return get_nr_swap_pages(); } -static inline bool mem_cgroup_swap_full(struct page *page) +static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } |