123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SWAP_H
#define _LINUX_SWAP_H

#include <linux/spinlock.h>
#include <linux/linkage.h>
#include <linux/mmzone.h>
#include <linux/list.h>
#include <linux/memcontrol.h>
#include <linux/sched.h>
#include <linux/node.h>
#include <linux/fs.h>
#include <linux/atomic.h>
#include <linux/page-flags.h>
#include <asm/page.h>

struct notifier_block;

struct bio;

#define SWAP_FLAG_PREFER	0x8000	/* set if swap priority specified */
#define SWAP_FLAG_PRIO_MASK	0x7fff
#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 */

#define SWAP_BATCH 64

static inline int current_is_kswapd(void)
	return current->flags & PF_KSWAPD;

 * MAX_SWAPFILES defines the maximum number of swaptypes: things which can
 * be swapped to.  The swap type and the offset into that swap type are
 * encoded into pte's and into pgoff_t's in the swapcache.  Using five bits
 * for the type means that the maximum number of swapcache pages is 27 bits
 * on 32-bit-pgoff_t architectures.  And that assumes that the architecture packs
 * the type/offset into the pte as 5/27 as well.

 * Use some of the swap files numbers for other purposes. This
 * is a convenient way to hook into the VM to trigger special
 * actions on faults.

 * Unaddressable device memory support. See include/linux/hmm.h and
 * Documentation/vm/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_* entry.
#define SWP_DEVICE_NUM 2
#define SWP_DEVICE_NUM 0

 * NUMA node memory migration support

 * Handling of hardware poisoned pages with memory corruption.


 * Magic header for a swap area. The first part of the union is
 * what the swap magic looks like for the old (limited to 128MB)
 * swap area format, the second part of the union adds - in the
 * old reserved area - some extra information. Note that the first
 * kilobyte is reserved for boot loader or disk label stuff...
 * Having the magic at the end of the PAGE_SIZE makes detecting swap
 * areas somewhat tricky on machines that support multiple page sizes.
 * For 2.5 we'll probably want to move the magic to just beyond the
 * bootbits...
union swap_header {
	struct {
		char reserved[PAGE_SIZE - 10];
		char magic[10];			/* SWAP-SPACE or SWAPSPACE2 */
	} magic;
	struct {
		char		bootbits[1024];	/* Space for disklabel etc. */
		__u32		version;
		__u32		last_page;
		__u32		nr_badpages;
		unsigned char	sws_uuid[16];
		unsigned char	sws_volume[16];
		__u32		padding[117];
		__u32		badpages[1];
	} info;

 * current->reclaim_state points to one of these when a task is running
 * memory reclaim
struct reclaim_state {
	unsigned long reclaimed_slab;

#ifdef __KERNEL__

struct address_space;
struct sysinfo;
struct writeback_control;
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
 * from setup, they're handled identically.
 * We always assume that blocks are of size PAGE_SIZE.
struct swap_extent {
	struct list_head list;
	pgoff_t start_page;
	pgoff_t nr_pages;
	sector_t start_block;

 * Max bad pages in the new format..
#define __swapoffset(x) ((unsigned long)&((union swap_header *)0)->x)
	((__swapoffset(magic.magic) - __swapoffset(info.badpages)) / sizeof(int))

enum {
	SWP_USED	= (1 << 0),	/* is slot in swap_info[] used? */
	SWP_WRITEOK	= (1 << 1),	/* ok to write to this swap?	*/
	SWP_DISCARDABLE = (1 << 2),	/* blkdev support discard */
	SWP_DISCARDING	= (1 << 3),	/* now discarding a free cluster */
	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_ACTIVATED	= (1 << 7),	/* set after swap_activate success */
	SWP_FS		= (1 << 8),	/* swap file goes 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 << 13),	/* refcount in scan_swap_map */


#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 */
#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 */

 * 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.
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 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
 * its own cluster and swapout sequentially. The purpose is to optimize swapout
 * throughput.
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;

 * The in-memory structure used to track swap areas.
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_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 */
	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 */
	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;
	struct block_device *bdev;	/* swap device or bdev of swap file */
	struct file *swap_file;		/* seldom referenced */
	unsigned int old_block_size;	/* seldom referenced */
	unsigned long *frontswap_map;	/* frontswap in-use, one bit per page */
	atomic_t frontswap_pages;	/* frontswap pages in-use counter */
	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
					 * 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 */

#ifdef CONFIG_64BIT
/* Avoid stack overflow, because we need to save part of page table */

struct vma_swap_readahead {
	unsigned short win;
	unsigned short offset;
	unsigned short nr_pte;
#ifdef CONFIG_64BIT
	pte_t *ptes;
	pte_t ptes[SWAP_RA_PTE_CACHE_SIZE];

/* linux/mm/workingset.c */
void *workingset_eviction(struct address_space *mapping, struct page *page);
void workingset_refault(struct page *page, void *shadow);
void workingset_activation(struct page *page);

/* Only track the nodes of mappings with shadow entries */
void workingset_update_node(struct xa_node *node);
#define mapping_set_update(xas, mapping) do {				\
	if (!dax_mapping(mapping) && !shmem_mapping(mapping))		\
		xas_set_update(xas, workingset_update_node);		\
} while (0)

/* 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_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 *);
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_all(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);
extern void swap_setup(void);

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 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);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
						  unsigned long nr_pages,
						  gfp_t gfp_mask,
						  bool may_swap);
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;

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);
#define node_reclaim_mode 0
static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
				unsigned int order)
	return 0;

extern int page_evictable(struct page *page);
extern void check_move_unevictable_pages(struct page **, int nr_pages);

extern int kswapd_run(int nid);
extern void kswapd_stop(int nid);


#include <linux/blk_types.h> /* for bio_end_io_t */

/* 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);

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 */
extern struct address_space *swapper_spaces[];
#define swap_address_space(entry)			    \
	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
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 *, swp_entry_t entry);
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 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);
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 *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
				struct vm_fault *vmf);
extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
				struct vm_fault *vmf);

/* 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);

/* Swap 50% full? Release swapcache more aggressively.. */
static inline bool vm_swap_full(void)
	return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;

static inline long get_nr_swap_pages(void)
	return atomic_long_read(&nr_swap_pages);

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);
extern swp_entry_t get_swap_page_of_type(int);
extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
extern void swap_shmem_alloc(swp_entry_t);
extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
extern void 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 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;
extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
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
#define total_swapcache_pages()			0UL
#define vm_swap_full()				0

#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) \
#define free_pages_and_swap_cache(pages, nr) \
	release_pages((pages), (nr));

static inline void show_swap_cache_info(void)

#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)
	return 0;

static inline void swap_shmem_alloc(swp_entry_t swp)

static inline int swap_duplicate(swp_entry_t swp)
	return 0;

static inline void swap_free(swp_entry_t swp)

static inline void put_swap_page(struct page *page, swp_entry_t swp)

static inline struct page *swap_cluster_readahead(swp_entry_t entry,
				gfp_t gfp_mask, struct vm_fault *vmf)
	return NULL;

static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
			struct vm_fault *vmf)
	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,
					     struct vm_area_struct *vma,
					     unsigned long addr)
	return NULL;

static inline int add_to_swap(struct page *page)
	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,
							swp_entry_t entry)

static inline void delete_from_swap_cache(struct page *page)

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;

static inline int swp_swapcount(swp_entry_t entry)
	return 0;

#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)
	return 0;

static inline swp_entry_t get_swap_page(struct page *page)
	swp_entry_t entry;
	entry.val = 0;
	return entry;

#endif /* CONFIG_SWAP */

extern int split_swap_cluster(swp_entry_t entry);
static inline int split_swap_cluster(swp_entry_t entry)
	return 0;

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;

	/* root ? */
	if (mem_cgroup_disabled() || !memcg->css.parent)
		return vm_swappiness;

	return memcg->swappiness;
static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
	return vm_swappiness;

#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
					 gfp_t gfp_mask);
static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
						int node, gfp_t gfp_mask)

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);
static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)

static inline int mem_cgroup_try_charge_swap(struct page *page,
					     swp_entry_t entry)
	return 0;

static inline void mem_cgroup_uncharge_swap(swp_entry_t entry,
					    unsigned int nr_pages)

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)
	return vm_swap_full();

#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */