linux/include/linux/rmap.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RMAP_H
#define _LINUX_RMAP_H
/*
 * Declarations for Reverse Mapping functions in mm/rmap.c
 */

#include <linux/list.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/rwsem.h>
#include <linux/memcontrol.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/memremap.h>

/*
 * The anon_vma heads a list of private "related" vmas, to scan if
 * an anonymous page pointing to this anon_vma needs to be unmapped:
 * the vmas on the list will be related by forking, or by splitting.
 *
 * Since vmas come and go as they are split and merged (particularly
 * in mprotect), the mapping field of an anonymous page cannot point
 * directly to a vma: instead it points to an anon_vma, on whose list
 * the related vmas can be easily linked or unlinked.
 *
 * After unlinking the last vma on the list, we must garbage collect
 * the anon_vma object itself: we're guaranteed no page can be
 * pointing to this anon_vma once its vma list is empty.
 */
struct anon_vma { … };

/*
 * The copy-on-write semantics of fork mean that an anon_vma
 * can become associated with multiple processes. Furthermore,
 * each child process will have its own anon_vma, where new
 * pages for that process are instantiated.
 *
 * This structure allows us to find the anon_vmas associated
 * with a VMA, or the VMAs associated with an anon_vma.
 * The "same_vma" list contains the anon_vma_chains linking
 * all the anon_vmas associated with this VMA.
 * The "rb" field indexes on an interval tree the anon_vma_chains
 * which link all the VMAs associated with this anon_vma.
 */
struct anon_vma_chain { … };

enum ttu_flags { … };

#ifdef CONFIG_MMU
static inline void get_anon_vma(struct anon_vma *anon_vma)
{ … }

void __put_anon_vma(struct anon_vma *anon_vma);

static inline void put_anon_vma(struct anon_vma *anon_vma)
{ … }

static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
{ … }

static inline int anon_vma_trylock_write(struct anon_vma *anon_vma)
{ … }

static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
{ … }

static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
{ … }

static inline int anon_vma_trylock_read(struct anon_vma *anon_vma)
{ … }

static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
{ … }


/*
 * anon_vma helper functions.
 */
void anon_vma_init(void);	/* create anon_vma_cachep */
int  __anon_vma_prepare(struct vm_area_struct *);
void unlink_anon_vmas(struct vm_area_struct *);
int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);

static inline int anon_vma_prepare(struct vm_area_struct *vma)
{ … }

static inline void anon_vma_merge(struct vm_area_struct *vma,
				  struct vm_area_struct *next)
{ … }

struct anon_vma *folio_get_anon_vma(struct folio *folio);

/* RMAP flags, currently only relevant for some anon rmap operations. */
rmap_t;

/*
 * No special request: A mapped anonymous (sub)page is possibly shared between
 * processes.
 */
#define RMAP_NONE …

/* The anonymous (sub)page is exclusive to a single process. */
#define RMAP_EXCLUSIVE …

/*
 * Internally, we're using an enum to specify the granularity. We make the
 * compiler emit specialized code for each granularity.
 */
enum rmap_level { … };

static inline void __folio_rmap_sanity_checks(struct folio *folio,
		struct page *page, int nr_pages, enum rmap_level level)
{ … }

/*
 * rmap interfaces called when adding or removing pte of page
 */
void folio_move_anon_rmap(struct folio *, struct vm_area_struct *);
void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages,
		struct vm_area_struct *, unsigned long address, rmap_t flags);
#define folio_add_anon_rmap_pte(folio, page, vma, address, flags) …
void folio_add_anon_rmap_pmd(struct folio *, struct page *,
		struct vm_area_struct *, unsigned long address, rmap_t flags);
void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
		unsigned long address, rmap_t flags);
void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
		struct vm_area_struct *);
#define folio_add_file_rmap_pte(folio, page, vma) …
void folio_add_file_rmap_pmd(struct folio *, struct page *,
		struct vm_area_struct *);
void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages,
		struct vm_area_struct *);
#define folio_remove_rmap_pte(folio, page, vma) …
void folio_remove_rmap_pmd(struct folio *, struct page *,
		struct vm_area_struct *);

void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
		unsigned long address, rmap_t flags);
void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
		unsigned long address);

/* See folio_try_dup_anon_rmap_*() */
static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
		struct vm_area_struct *vma)
{ … }

/* See folio_try_share_anon_rmap_*() */
static inline int hugetlb_try_share_anon_rmap(struct folio *folio)
{ … }

static inline void hugetlb_add_file_rmap(struct folio *folio)
{ … }

static inline void hugetlb_remove_rmap(struct folio *folio)
{ … }

static __always_inline void __folio_dup_file_rmap(struct folio *folio,
		struct page *page, int nr_pages, enum rmap_level level)
{ … }

/**
 * folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio
 * @folio:	The folio to duplicate the mappings of
 * @page:	The first page to duplicate the mappings of
 * @nr_pages:	The number of pages of which the mapping will be duplicated
 *
 * The page range of the folio is defined by [page, page + nr_pages)
 *
 * The caller needs to hold the page table lock.
 */
static inline void folio_dup_file_rmap_ptes(struct folio *folio,
		struct page *page, int nr_pages)
{ … }

static __always_inline void folio_dup_file_rmap_pte(struct folio *folio,
		struct page *page)
{ … }

/**
 * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio
 * @folio:	The folio to duplicate the mapping of
 * @page:	The first page to duplicate the mapping of
 *
 * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock.
 */
static inline void folio_dup_file_rmap_pmd(struct folio *folio,
		struct page *page)
{ … }

static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *src_vma,
		enum rmap_level level)
{ … }

/**
 * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range
 *				  of a folio
 * @folio:	The folio to duplicate the mappings of
 * @page:	The first page to duplicate the mappings of
 * @nr_pages:	The number of pages of which the mapping will be duplicated
 * @src_vma:	The vm area from which the mappings are duplicated
 *
 * The page range of the folio is defined by [page, page + nr_pages)
 *
 * The caller needs to hold the page table lock and the
 * vma->vma_mm->write_protect_seq.
 *
 * Duplicating the mappings can only fail if the folio may be pinned; device
 * private folios cannot get pinned and consequently this function cannot fail
 * for them.
 *
 * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in
 * the parent and the child. They must *not* be writable after this call
 * succeeded.
 *
 * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise.
 */
static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *src_vma)
{ … }

static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio,
		struct page *page, struct vm_area_struct *src_vma)
{ … }

/**
 * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range
 *				 of a folio
 * @folio:	The folio to duplicate the mapping of
 * @page:	The first page to duplicate the mapping of
 * @src_vma:	The vm area from which the mapping is duplicated
 *
 * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock and the
 * vma->vma_mm->write_protect_seq.
 *
 * Duplicating the mapping can only fail if the folio may be pinned; device
 * private folios cannot get pinned and consequently this function cannot fail
 * for them.
 *
 * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in
 * the parent and the child. They must *not* be writable after this call
 * succeeded.
 *
 * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
 */
static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
		struct page *page, struct vm_area_struct *src_vma)
{ … }

static __always_inline int __folio_try_share_anon_rmap(struct folio *folio,
		struct page *page, int nr_pages, enum rmap_level level)
{ … }

/**
 * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page
 *				   mapped by a PTE possibly shared to prepare
 *				   for KSM or temporary unmapping
 * @folio:	The folio to share a mapping of
 * @page:	The mapped exclusive page
 *
 * The caller needs to hold the page table lock and has to have the page table
 * entries cleared/invalidated.
 *
 * This is similar to folio_try_dup_anon_rmap_pte(), however, not used during
 * fork() to duplicate mappings, but instead to prepare for KSM or temporarily
 * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte().
 *
 * Marking the mapped page shared can only fail if the folio maybe pinned;
 * device private folios cannot get pinned and consequently this function cannot
 * fail.
 *
 * Returns 0 if marking the mapped page possibly shared succeeded. Returns
 * -EBUSY otherwise.
 */
static inline int folio_try_share_anon_rmap_pte(struct folio *folio,
		struct page *page)
{ … }

/**
 * folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page
 *				   range mapped by a PMD possibly shared to
 *				   prepare for temporary unmapping
 * @folio:	The folio to share the mapping of
 * @page:	The first page to share the mapping of
 *
 * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock and has to have the page table
 * entries cleared/invalidated.
 *
 * This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during
 * fork() to duplicate a mapping, but instead to prepare for temporarily
 * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd().
 *
 * Marking the mapped pages shared can only fail if the folio maybe pinned;
 * device private folios cannot get pinned and consequently this function cannot
 * fail.
 *
 * Returns 0 if marking the mapped pages possibly shared succeeded. Returns
 * -EBUSY otherwise.
 */
static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
		struct page *page)
{ … }

/*
 * Called from mm/vmscan.c to handle paging out
 */
int folio_referenced(struct folio *, int is_locked,
			struct mem_cgroup *memcg, unsigned long *vm_flags);

void try_to_migrate(struct folio *folio, enum ttu_flags flags);
void try_to_unmap(struct folio *, enum ttu_flags flags);

int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
				unsigned long end, struct page **pages,
				void *arg);

/* Avoid racy checks */
#define PVMW_SYNC …
/* Look for migration entries rather than present PTEs */
#define PVMW_MIGRATION …

struct page_vma_mapped_walk { … };

#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) …

static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
{ … }

/**
 * page_vma_mapped_walk_restart - Restart the page table walk.
 * @pvmw: Pointer to struct page_vma_mapped_walk.
 *
 * It restarts the page table walk when changes occur in the page
 * table, such as splitting a PMD. Ensures that the PTL held during
 * the previous walk is released and resets the state to allow for
 * a new walk starting at the current address stored in pvmw->address.
 */
static inline void
page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw)
{ … }

bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);

/*
 * Used by swapoff to help locate where page is expected in vma.
 */
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);

/*
 * Cleans the PTEs of shared mappings.
 * (and since clean PTEs should also be readonly, write protects them too)
 *
 * returns the number of cleaned PTEs.
 */
int folio_mkclean(struct folio *);

int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
		      struct vm_area_struct *vma);

void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);

/*
 * rmap_walk_control: To control rmap traversing for specific needs
 *
 * arg: passed to rmap_one() and invalid_vma()
 * try_lock: bail out if the rmap lock is contended
 * contended: indicate the rmap traversal bailed out due to lock contention
 * rmap_one: executed on each vma where page is mapped
 * done: for checking traversing termination condition
 * anon_lock: for getting anon_lock by optimized way rather than default
 * invalid_vma: for skipping uninterested vma
 */
struct rmap_walk_control { … };

void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc);
void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc);
struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
					  struct rmap_walk_control *rwc);

#else	/* !CONFIG_MMU */

#define anon_vma_init …
#define anon_vma_prepare …

static inline int folio_referenced(struct folio *folio, int is_locked,
				  struct mem_cgroup *memcg,
				  unsigned long *vm_flags)
{
	*vm_flags = 0;
	return 0;
}

static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags)
{
}

static inline int folio_mkclean(struct folio *folio)
{
	return 0;
}
#endif	/* CONFIG_MMU */

#endif	/* _LINUX_RMAP_H */