linux/mm/swap.h

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

#include <linux/atomic.h> /* for atomic_long_t */
#include <linux/mm.h> /* for PAGE_SHIFT */
#include <linux/memcontrol.h> /* for mem_cgroup_swappiness() */
#include <linux/swap.h> /* for MAX_SWAPFILES_SHIFT, struct swap_info_struct */

struct mempolicy;
struct swap_iocb;
struct swap_memcg_table;
struct swap_io_ctx;

#if defined(MAX_POSSIBLE_PHYSMEM_BITS)
#define SWAP_CACHE_PFN_BITS (MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT)
#elif defined(MAX_PHYSMEM_BITS)
#define SWAP_CACHE_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
#else
#define SWAP_CACHE_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT)
#endif

/* Swap table marker, 0x1 means shadow, 0x2 means PFN (SWP_TB_PFN_MARK) */
#define SWAP_CACHE_PFN_MARK_BITS	2
/* At least 2 bits are needed to distinguish SWP_TB_COUNT_MAX, 1 and 0 */
#define SWAP_COUNT_MIN_BITS		2
/* If there are enough bits besides PFN and marker, store zero flag inline */
#define SWAP_TABLE_HAS_ZEROFLAG		((BITS_PER_LONG - SWAP_CACHE_PFN_MARK_BITS - \
					  SWAP_CACHE_PFN_BITS) > SWAP_COUNT_MIN_BITS)

#ifdef CONFIG_THP_SWAP
#define SWAPFILE_CLUSTER	HPAGE_PMD_NR
#define swap_entry_order(order)	(order)
#else
#define SWAPFILE_CLUSTER	256
#define swap_entry_order(order)	0
#endif

extern struct swap_info_struct *swap_info[];

/*
 * 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 flags field determines if a cluster is free. This is
 * protected by cluster lock.
 */
struct swap_cluster_info {
	spinlock_t lock;	/*
				 * Protect swap_cluster_info fields
				 * other than list, and swap_info_struct->swap_map
				 * elements corresponding to the swap cluster.
				 */
	u16 count;
	u8 flags;
	u8 order;
	atomic_long_t __rcu *table;	/* Swap table entries, see mm/swap_table.h */
	unsigned int *extend_table;	/* For large swap count, protected by ci->lock */
#ifdef CONFIG_MEMCG
	struct swap_memcg_table *memcg_table;	/* Swap table entries' cgroup record */
#endif
#if !SWAP_TABLE_HAS_ZEROFLAG
	unsigned long *zero_bitmap;
#endif
	struct list_head list;
};

/* All on-list cluster must have a non-zero flag. */
enum swap_cluster_flags {
	CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */
	CLUSTER_FLAG_FREE,
	CLUSTER_FLAG_NONFULL,
	CLUSTER_FLAG_FRAG,
	/* Clusters with flags above are allocatable */
	CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG,
	CLUSTER_FLAG_FULL,
	CLUSTER_FLAG_DISCARD,
	CLUSTER_FLAG_MAX,
};

extern int vm_swappiness;

static inline int mem_cgroup_swappiness(const struct mem_cgroup *memcg)
{
#ifdef CONFIG_MEMCG_V1
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
	    !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
		return READ_ONCE(memcg->swappiness);
#endif
	return READ_ONCE(vm_swappiness);
}

#ifdef CONFIG_SWAP
#include <linux/swapops.h> /* for swp_offset */
#include <linux/blk_types.h> /* for bio_end_io_t */

static inline unsigned int swp_cluster_offset(swp_entry_t entry)
{
	return swp_offset(entry) % SWAPFILE_CLUSTER;
}

/*
 * Callers of all helpers below must ensure the entry, type, or offset is
 * valid, and protect the swap device with reference count or locks.
 */
static inline struct swap_info_struct *__swap_type_to_info(int type)
{
	struct swap_info_struct *si;

	si = READ_ONCE(swap_info[type]); /* rcu_dereference() */
	VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */
	return si;
}

static inline struct swap_info_struct *__swap_entry_to_info(swp_entry_t entry)
{
	return __swap_type_to_info(swp_type(entry));
}

static inline struct swap_cluster_info *__swap_offset_to_cluster(
		struct swap_info_struct *si, pgoff_t offset)
{
	VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */
	VM_WARN_ON_ONCE(offset >= roundup(si->max, SWAPFILE_CLUSTER));
	return &si->cluster_info[offset / SWAPFILE_CLUSTER];
}

static inline struct swap_cluster_info *__swap_entry_to_cluster(swp_entry_t entry)
{
	return __swap_offset_to_cluster(__swap_entry_to_info(entry),
					swp_offset(entry));
}

static __always_inline struct swap_cluster_info *__swap_cluster_lock(
		struct swap_info_struct *si, unsigned long offset, bool irq)
{
	struct swap_cluster_info *ci = __swap_offset_to_cluster(si, offset);

	/*
	 * Nothing modifies swap cache in an IRQ context. All access to
	 * swap cache is wrapped by swap_cache_* helpers, and swap cache
	 * writeback is handled outside of IRQs. Swapin or swapout never
	 * occurs in IRQ, and neither does in-place split or replace.
	 *
	 * Besides, modifying swap cache requires synchronization with
	 * swap_map, which was never IRQ safe.
	 */
	VM_WARN_ON_ONCE(!in_task());
	VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */
	if (irq)
		spin_lock_irq(&ci->lock);
	else
		spin_lock(&ci->lock);
	return ci;
}

/**
 * swap_cluster_lock - Lock and return the swap cluster of given offset.
 * @si: swap device the cluster belongs to.
 * @offset: the swap entry offset, pointing to a valid slot.
 *
 * Context: The caller must ensure the offset is in the valid range and
 * protect the swap device with reference count or locks.
 */
static inline struct swap_cluster_info *swap_cluster_lock(
		struct swap_info_struct *si, unsigned long offset)
{
	return __swap_cluster_lock(si, offset, false);
}

static inline struct swap_cluster_info *__swap_cluster_get_and_lock(
		const struct folio *folio, bool irq)
{
	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
	VM_WARN_ON_ONCE_FOLIO(!folio_test_swapcache(folio), folio);
	return __swap_cluster_lock(__swap_entry_to_info(folio->swap),
				   swp_offset(folio->swap), irq);
}

/*
 * swap_cluster_get_and_lock - Locks the cluster that holds a folio's entries.
 * @folio: The folio.
 *
 * This locks and returns the swap cluster that contains a folio's swap
 * entries. The swap entries of a folio are always in one single cluster.
 * The folio has to be locked so its swap entries won't change and the
 * cluster won't be freed.
 *
 * Context: Caller must ensure the folio is locked and in the swap cache.
 * Return: Pointer to the swap cluster.
 */
static inline struct swap_cluster_info *swap_cluster_get_and_lock(
		const struct folio *folio)
{
	return __swap_cluster_get_and_lock(folio, false);
}

/*
 * swap_cluster_get_and_lock_irq - Locks the cluster that holds a folio's entries.
 * @folio: The folio.
 *
 * Same as swap_cluster_get_and_lock but also disable IRQ.
 *
 * Context: Caller must ensure the folio is locked and in the swap cache.
 * Return: Pointer to the swap cluster.
 */
static inline struct swap_cluster_info *swap_cluster_get_and_lock_irq(
		const struct folio *folio)
{
	return __swap_cluster_get_and_lock(folio, true);
}

static inline void swap_cluster_unlock(struct swap_cluster_info *ci)
{
	spin_unlock(&ci->lock);
}

static inline void swap_cluster_unlock_irq(struct swap_cluster_info *ci)
{
	spin_unlock_irq(&ci->lock);
}

extern int swap_retry_table_alloc(swp_entry_t entry, gfp_t gfp);

/*
 * Below are the core routines for doing swap for a folio.
 * All helpers requires the folio to be locked, and a locked folio
 * in the swap cache pins the swap entries / slots allocated to the
 * folio, swap relies heavily on the swap cache and folio lock for
 * synchronization.
 *
 * folio_alloc_swap(): the entry point for a folio to be swapped
 * out. It allocates swap slots and pins the slots with swap cache.
 * The slots start with a swap count of zero. The slots are pinned
 * by swap cache reference which doesn't contribute to swap count.
 *
 * folio_dup_swap(): increases the swap count of a folio, usually
 * during it gets unmapped and a swap entry is installed to replace
 * it (e.g., swap entry in page table). A swap slot with swap
 * count == 0 can only be increased by this helper.
 *
 * folio_put_swap(): does the opposite thing of folio_dup_swap().
 */
int folio_alloc_swap(struct folio *folio);
int folio_dup_swap(struct folio *folio, struct page *page);
void folio_put_swap(struct folio *folio, struct page *page);

/* For internal use */
extern void __swap_cluster_free_entries(struct swap_info_struct *si,
					struct swap_cluster_info *ci,
					unsigned int ci_off, unsigned int nr_pages);

/* linux/mm/page_io.c */
int sio_pool_init(void);
void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio);
void swap_read_submit(struct swap_io_ctx *ctx);
void swap_write_submit(struct swap_io_ctx *ctx);
int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio);
void __swap_writeout(struct swap_io_ctx *ctx, struct folio *folio);

/* linux/mm/swap_state.c */
extern struct address_space swap_space __read_mostly;
static inline struct address_space *swap_address_space(swp_entry_t entry)
{
	return &swap_space;
}

/*
 * Return the swap device position of the swap entry.
 */
static inline loff_t swap_dev_pos(swp_entry_t entry)
{
	return ((loff_t)swp_offset(entry)) << PAGE_SHIFT;
}

/**
 * folio_matches_swap_entry - Check if a folio matches a given swap entry.
 * @folio: The folio.
 * @entry: The swap entry to check against.
 *
 * Context: The caller should have the folio locked to ensure it's stable
 * and nothing will move it in or out of the swap cache.
 * Return: true or false.
 */
static inline bool folio_matches_swap_entry(const struct folio *folio,
					    swp_entry_t entry)
{
	swp_entry_t folio_entry = folio->swap;
	long nr_pages = folio_nr_pages(folio);

	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
	if (!folio_test_swapcache(folio))
		return false;
	VM_WARN_ON_ONCE_FOLIO(!IS_ALIGNED(folio_entry.val, nr_pages), folio);
	return folio_entry.val == round_down(entry.val, nr_pages);
}

/*
 * All swap cache helpers below require the caller to ensure the swap entries
 * used are valid and stabilize the device by any of the following ways:
 * - Hold a reference by get_swap_device(): this ensures a single entry is
 *   valid and increases the swap device's refcount.
 * - Locking a folio in the swap cache: this ensures the folio's swap entries
 *   are valid and pinned, also implies reference to the device.
 * - Locking anything referencing the swap entry: e.g. PTL that protects
 *   swap entries in the page table, similar to locking swap cache folio.
 * - See the comment of get_swap_device() for more complex usage.
 */
bool swap_cache_has_folio(swp_entry_t entry);
struct folio *swap_cache_get_folio(swp_entry_t entry);
void *swap_cache_get_shadow(swp_entry_t entry);
void swap_cache_del_folio(struct folio *folio);
struct folio *__swap_cache_alloc_folio(swp_entry_t target_entry, gfp_t gfp_mask,
				       unsigned long orders, struct vm_fault *vmf,
				       struct mempolicy *mpol, pgoff_t ilx);
/* Below helpers require the caller to lock and pass in the swap cluster. */
void __swap_cache_add_folio(struct swap_cluster_info *ci,
			    struct folio *folio, swp_entry_t entry);
void __swap_cache_del_folio(struct swap_cluster_info *ci,
			    struct folio *folio, swp_entry_t entry, void *shadow,
			    bool swapout);
void __swap_cache_replace_folio(struct swap_cluster_info *ci,
				struct folio *old, struct folio *new);

void show_swap_cache_info(void);
struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
		gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr);
struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
		struct mempolicy *mpol, pgoff_t ilx);
struct folio *swapin_readahead(swp_entry_t entry, gfp_t flag,
		struct vm_fault *vmf);
struct folio *swapin_sync(swp_entry_t entry, gfp_t flag, unsigned long orders,
			   struct vm_fault *vmf, struct mempolicy *mpol, pgoff_t ilx);
void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma,
			   unsigned long addr);

#else /* CONFIG_SWAP */

static inline struct swap_cluster_info *swap_cluster_get_and_lock(
		struct folio *folio)
{
	return NULL;
}

static inline struct swap_cluster_info *swap_cluster_get_and_lock_irq(
		struct folio *folio)
{
	return NULL;
}

static inline void swap_cluster_unlock(struct swap_cluster_info *ci)
{
}

static inline void swap_cluster_unlock_irq(struct swap_cluster_info *ci)
{
}

static inline struct swap_info_struct *__swap_entry_to_info(swp_entry_t entry)
{
	return NULL;
}

static inline int folio_alloc_swap(struct folio *folio)
{
	return -EINVAL;
}

static inline int folio_dup_swap(struct folio *folio, struct page *page)
{
	return -EINVAL;
}

static inline void folio_put_swap(struct folio *folio, struct page *page)
{
}

static inline void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
{
}

static inline void swap_write_submit(struct swap_io_ctx *ctx)
{
}

static inline struct address_space *swap_address_space(swp_entry_t entry)
{
	return NULL;
}

static inline bool folio_matches_swap_entry(const struct folio *folio, swp_entry_t entry)
{
	return false;
}

static inline void show_swap_cache_info(void)
{
}

static inline struct folio *swap_cluster_readahead(swp_entry_t entry,
			gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx)
{
	return NULL;
}

static inline struct folio *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
			struct vm_fault *vmf)
{
	return NULL;
}

static inline struct folio *swapin_sync(
	swp_entry_t entry, gfp_t flag, unsigned long orders,
	struct vm_fault *vmf, struct mempolicy *mpol, pgoff_t ilx)
{
	return NULL;
}

static inline void swap_update_readahead(struct folio *folio,
		struct vm_area_struct *vma, unsigned long addr)
{
}

static inline int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
{
	return 0;
}

static inline int swap_retry_table_alloc(swp_entry_t entry, gfp_t gfp)
{
	return -EINVAL;
}

static inline bool swap_cache_has_folio(swp_entry_t entry)
{
	return false;
}

static inline struct folio *swap_cache_get_folio(swp_entry_t entry)
{
	return NULL;
}

static inline void *swap_cache_get_shadow(swp_entry_t entry)
{
	return NULL;
}

static inline void swap_cache_del_folio(struct folio *folio)
{
}

static inline void __swap_cache_del_folio(struct swap_cluster_info *ci,
		struct folio *folio, swp_entry_t entry, void *shadow,
		bool swapout)
{
}

static inline void __swap_cache_replace_folio(struct swap_cluster_info *ci,
		struct folio *old, struct folio *new)
{
}
#endif /* CONFIG_SWAP */

extern const struct swap_ops swap_bdev_ops;

int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
		struct list_head *folio_list);

#endif /* _MM_SWAP_H */