diff options
Diffstat (limited to 'include/linux/swap.h')
| -rw-r--r-- | include/linux/swap.h | 142 |
1 files changed, 129 insertions, 13 deletions
diff --git a/include/linux/swap.h b/include/linux/swap.h index d83d28e53e62..c2b8128799c1 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 @@ -51,6 +52,23 @@ static inline int current_is_kswapd(void) */ /* + * Unaddressable device memory support. See include/linux/hmm.h and + * Documentation/vm/hmm.txt. 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_* entry. + */ +#ifdef CONFIG_DEVICE_PRIVATE +#define SWP_DEVICE_NUM 2 +#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) +#else +#define SWP_DEVICE_NUM 0 +#endif + +/* * NUMA node memory migration support */ #ifdef CONFIG_MIGRATION @@ -72,7 +90,8 @@ 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) /* * Magic header for a swap area. The first part of the union is @@ -152,8 +171,9 @@ enum { 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_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 11), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL @@ -188,6 +208,7 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ +#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from @@ -211,7 +232,7 @@ struct swap_info_struct { 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 */ + struct plist_node avail_lists[MAX_NUMNODES];/* entry in swap_avail_heads */ 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 */ @@ -246,15 +267,49 @@ struct swap_info_struct { * 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 */ }; +#ifdef CONFIG_64BIT +#define SWAP_RA_ORDER_CEILING 5 +#else +/* Avoid stack overflow, because we need to save part of page table */ +#define SWAP_RA_ORDER_CEILING 3 +#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) +#endif + +struct vma_swap_readahead { + unsigned short win; + unsigned short offset; + unsigned short nr_pte; +#ifdef CONFIG_64BIT + pte_t *ptes; +#else + pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; +#endif +}; + /* 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); + +/* Do not use directly, use workingset_lookup_update */ +void workingset_update_node(struct radix_tree_node *node); + +/* Returns workingset_update_node() if the mapping has shadow entries. */ +#define workingset_lookup_update(mapping) \ +({ \ + radix_tree_update_node_t __helper = workingset_update_node; \ + if (dax_mapping(mapping) || shmem_mapping(mapping)) \ + __helper = NULL; \ + __helper; \ +}) /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; @@ -262,8 +317,8 @@ 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 */ @@ -349,6 +404,7 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, #define SWAP_ADDRESS_SPACE_SHIFT 14 #define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) extern struct address_space *swapper_spaces[]; +extern bool swap_vma_readahead; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) @@ -361,7 +417,9 @@ 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 *lookup_swap_cache(swp_entry_t entry, + struct vm_area_struct *vma, + unsigned long addr); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool do_poll); @@ -371,11 +429,23 @@ extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); +extern struct page *swap_readahead_detect(struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); +extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); + /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap); +} + /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { @@ -404,9 +474,11 @@ 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 __swap_count(struct swap_info_struct *si, swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); +extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); struct backing_dev_info; @@ -415,6 +487,16 @@ extern void exit_swap_address_space(unsigned int type); #else /* CONFIG_SWAP */ +static inline int swap_readpage(struct page *page, bool do_poll) +{ + return 0; +} + +static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) +{ + return NULL; +} + #define swap_address_space(entry) (NULL) #define get_nr_swap_pages() 0L #define total_swap_pages 0L @@ -428,14 +510,14 @@ extern void exit_swap_address_space(unsigned int type); #define free_page_and_swap_cache(page) \ put_page(page) #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) { } -#define free_swap_and_cache(swp) is_migration_entry(swp) -#define swapcache_prepare(swp) is_migration_entry(swp) +#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { @@ -465,12 +547,32 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, return NULL; } +static inline bool swap_use_vma_readahead(void) +{ + return false; +} + +static inline struct page *swap_readahead_detect( + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + +static inline struct page *do_swap_page_readahead( + swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + static inline int swap_writepage(struct page *p, struct writeback_control *wbc) { return 0; } -static inline struct page *lookup_swap_cache(swp_entry_t swp) +static inline struct page *lookup_swap_cache(swp_entry_t swp, + struct vm_area_struct *vma, + unsigned long addr) { return NULL; } @@ -499,6 +601,11 @@ static inline int page_swapcount(struct page *page) return 0; } +static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry) +{ + return 0; +} + static inline int __swp_swapcount(swp_entry_t entry) { return 0; @@ -509,8 +616,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_mapcount) \ - (page_trans_huge_mapcount(page, total_mapcount) == 1) +#define reuse_swap_page(page, total_map_swapcount) \ + (page_trans_huge_mapcount(page, total_map_swapcount) == 1) static inline int try_to_free_swap(struct page *page) { @@ -526,6 +633,15 @@ static inline swp_entry_t get_swap_page(struct page *page) #endif /* CONFIG_SWAP */ +#ifdef CONFIG_THP_SWAP +extern int split_swap_cluster(swp_entry_t entry); +#else +static inline int split_swap_cluster(swp_entry_t entry) +{ + return 0; +} +#endif + #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { |