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

#include <linux/errno.h>
#include <linux/mmdebug.h>
#include <linux/gfp.h>
#include <linux/bug.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/atomic.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
#include <linux/mmap_lock.h>
#include <linux/range.h>
#include <linux/pfn.h>
#include <linux/percpu-refcount.h>
#include <linux/bit_spinlock.h>
#include <linux/shrinker.h>
#include <linux/resource.h>
#include <linux/page_ext.h>
#include <linux/err.h>
#include <linux/page-flags.h>
#include <linux/page_ref.h>
#include <linux/overflow.h>
#include <linux/sizes.h>
#include <linux/sched.h>
#include <linux/pgtable.h>
#include <linux/kasan.h>
#include <linux/memremap.h>
#include <linux/slab.h>

struct mempolicy;
struct anon_vma;
struct anon_vma_chain;
struct user_struct;
struct pt_regs;

extern int sysctl_page_lock_unfairness;

void mm_core_init(void);
void init_mm_internals(void);

#ifndef CONFIG_NUMA             /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;

static inline void set_max_mapnr(unsigned long limit)
{
        max_mapnr = limit;
}
#else
static inline void set_max_mapnr(unsigned long limit) { }
#endif

extern atomic_long_t _totalram_pages;
static inline unsigned long totalram_pages(void)
{
        return (unsigned long)atomic_long_read(&_totalram_pages);
}

static inline void totalram_pages_inc(void)
{
        atomic_long_inc(&_totalram_pages);
}

static inline void totalram_pages_dec(void)
{
        atomic_long_dec(&_totalram_pages);
}

static inline void totalram_pages_add(long count)
{
        atomic_long_add(count, &_totalram_pages);
}

extern void * high_memory;
extern int page_cluster;
extern const int page_cluster_max;

#ifdef CONFIG_SYSCTL
extern int sysctl_legacy_va_layout;
#else
#define sysctl_legacy_va_layout 0
#endif

#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
extern const int mmap_rnd_bits_min;
extern const int mmap_rnd_bits_max;
extern int mmap_rnd_bits __read_mostly;
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
extern const int mmap_rnd_compat_bits_min;
extern const int mmap_rnd_compat_bits_max;
extern int mmap_rnd_compat_bits __read_mostly;
#endif

#include <asm/page.h>
#include <asm/processor.h>

#ifndef __pa_symbol
#define __pa_symbol(x)  __pa(RELOC_HIDE((unsigned long)(x), 0))
#endif

#ifndef page_to_virt
#define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x)))
#endif

#ifndef lm_alias
#define lm_alias(x)     __va(__pa_symbol(x))
#endif

/*
 * To prevent common memory management code establishing
 * a zero page mapping on a read fault.
 * This macro should be defined within <asm/pgtable.h>.
 * s390 does this to prevent multiplexing of hardware bits
 * related to the physical page in case of virtualization.
 */
#ifndef mm_forbids_zeropage
#define mm_forbids_zeropage(X)  (0)
#endif

/*
 * On some architectures it is expensive to call memset() for small sizes.
 * If an architecture decides to implement their own version of
 * mm_zero_struct_page they should wrap the defines below in a #ifndef and
 * define their own version of this macro in <asm/pgtable.h>
 */
#if BITS_PER_LONG == 64
/* This function must be updated when the size of struct page grows above 96
 * or reduces below 56. The idea that compiler optimizes out switch()
 * statement, and only leaves move/store instructions. Also the compiler can
 * combine write statements if they are both assignments and can be reordered,
 * this can result in several of the writes here being dropped.
 */
#define mm_zero_struct_page(pp) __mm_zero_struct_page(pp)
static inline void __mm_zero_struct_page(struct page *page)
{
        unsigned long *_pp = (void *)page;

         /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */
        BUILD_BUG_ON(sizeof(struct page) & 7);
        BUILD_BUG_ON(sizeof(struct page) < 56);
        BUILD_BUG_ON(sizeof(struct page) > 96);

        switch (sizeof(struct page)) {
        case 96:
                _pp[11] = 0;
                fallthrough;
        case 88:
                _pp[10] = 0;
                fallthrough;
        case 80:
                _pp[9] = 0;
                fallthrough;
        case 72:
                _pp[8] = 0;
                fallthrough;
        case 64:
                _pp[7] = 0;
                fallthrough;
        case 56:
                _pp[6] = 0;
                _pp[5] = 0;
                _pp[4] = 0;
                _pp[3] = 0;
                _pp[2] = 0;
                _pp[1] = 0;
                _pp[0] = 0;
        }
}
#else
#define mm_zero_struct_page(pp)  ((void)memset((pp), 0, sizeof(struct page)))
#endif

/*
 * Default maximum number of active map areas, this limits the number of vmas
 * per mm struct. Users can overwrite this number by sysctl but there is a
 * problem.
 *
 * When a program's coredump is generated as ELF format, a section is created
 * per a vma. In ELF, the number of sections is represented in unsigned short.
 * This means the number of sections should be smaller than 65535 at coredump.
 * Because the kernel adds some informative sections to a image of program at
 * generating coredump, we need some margin. The number of extra sections is
 * 1-3 now and depends on arch. We use "5" as safe margin, here.
 *
 * ELF extended numbering allows more than 65535 sections, so 16-bit bound is
 * not a hard limit any more. Although some userspace tools can be surprised by
 * that.
 */
#define MAPCOUNT_ELF_CORE_MARGIN        (5)
#define DEFAULT_MAX_MAP_COUNT   (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)

extern int sysctl_max_map_count;

extern unsigned long sysctl_user_reserve_kbytes;
extern unsigned long sysctl_admin_reserve_kbytes;

extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern unsigned long sysctl_overcommit_kbytes;

int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
                loff_t *);
int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
                loff_t *);
int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
                loff_t *);

#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
#define folio_page_idx(folio, p)        (page_to_pfn(p) - folio_pfn(folio))
#else
#define nth_page(page,n) ((page) + (n))
#define folio_page_idx(folio, p)        ((p) - &(folio)->page)
#endif

/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)

/* to align the pointer to the (prev) page boundary */
#define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE)

/* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */
#define PAGE_ALIGNED(addr)      IS_ALIGNED((unsigned long)(addr), PAGE_SIZE)

#define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
static inline struct folio *lru_to_folio(struct list_head *head)
{
        return list_entry((head)->prev, struct folio, lru);
}

void setup_initial_init_mm(void *start_code, void *end_code,
                           void *end_data, void *brk);

/*
 * Linux kernel virtual memory manager primitives.
 * The idea being to have a "virtual" mm in the same way
 * we have a virtual fs - giving a cleaner interface to the
 * mm details, and allowing different kinds of memory mappings
 * (from shared memory to executable loading to arbitrary
 * mmap() functions).
 */

struct vm_area_struct *vm_area_alloc(struct mm_struct *);
struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
void vm_area_free(struct vm_area_struct *);
/* Use only if VMA has no other users */
void __vm_area_free(struct vm_area_struct *vma);

#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
extern struct rw_semaphore nommu_region_sem;

extern unsigned int kobjsize(const void *objp);
#endif

/*
 * vm_flags in vm_area_struct, see mm_types.h.
 * When changing, update also include/trace/events/mmflags.h
 */
#define VM_NONE         0x00000000

#define VM_READ         0x00000001      /* currently active flags */
#define VM_WRITE        0x00000002
#define VM_EXEC         0x00000004
#define VM_SHARED       0x00000008

/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
#define VM_MAYREAD      0x00000010      /* limits for mprotect() etc */
#define VM_MAYWRITE     0x00000020
#define VM_MAYEXEC      0x00000040
#define VM_MAYSHARE     0x00000080

#define VM_GROWSDOWN    0x00000100      /* general info on the segment */
#ifdef CONFIG_MMU
#define VM_UFFD_MISSING 0x00000200      /* missing pages tracking */
#else /* CONFIG_MMU */
#define VM_MAYOVERLAY   0x00000200      /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */
#define VM_UFFD_MISSING 0
#endif /* CONFIG_MMU */
#define VM_PFNMAP       0x00000400      /* Page-ranges managed without "struct page", just pure PFN */
#define VM_UFFD_WP      0x00001000      /* wrprotect pages tracking */

#define VM_LOCKED       0x00002000
#define VM_IO           0x00004000      /* Memory mapped I/O or similar */

                                        /* Used by sys_madvise() */
#define VM_SEQ_READ     0x00008000      /* App will access data sequentially */
#define VM_RAND_READ    0x00010000      /* App will not benefit from clustered reads */

#define VM_DONTCOPY     0x00020000      /* Do not copy this vma on fork */
#define VM_DONTEXPAND   0x00040000      /* Cannot expand with mremap() */
#define VM_LOCKONFAULT  0x00080000      /* Lock the pages covered when they are faulted in */
#define VM_ACCOUNT      0x00100000      /* Is a VM accounted object */
#define VM_NORESERVE    0x00200000      /* should the VM suppress accounting */
#define VM_HUGETLB      0x00400000      /* Huge TLB Page VM */
#define VM_SYNC         0x00800000      /* Synchronous page faults */
#define VM_ARCH_1       0x01000000      /* Architecture-specific flag */
#define VM_WIPEONFORK   0x02000000      /* Wipe VMA contents in child. */
#define VM_DONTDUMP     0x04000000      /* Do not include in the core dump */

#ifdef CONFIG_MEM_SOFT_DIRTY
# define VM_SOFTDIRTY   0x08000000      /* Not soft dirty clean area */
#else
# define VM_SOFTDIRTY   0
#endif

#define VM_MIXEDMAP     0x10000000      /* Can contain "struct page" and pure PFN pages */
#define VM_HUGEPAGE     0x20000000      /* MADV_HUGEPAGE marked this vma */
#define VM_NOHUGEPAGE   0x40000000      /* MADV_NOHUGEPAGE marked this vma */
#define VM_MERGEABLE    0x80000000      /* KSM may merge identical pages */

#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
#define VM_HIGH_ARCH_BIT_0      32      /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_1      33      /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_2      34      /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_3      35      /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_4      36      /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_5      37      /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_0  BIT(VM_HIGH_ARCH_BIT_0)
#define VM_HIGH_ARCH_1  BIT(VM_HIGH_ARCH_BIT_1)
#define VM_HIGH_ARCH_2  BIT(VM_HIGH_ARCH_BIT_2)
#define VM_HIGH_ARCH_3  BIT(VM_HIGH_ARCH_BIT_3)
#define VM_HIGH_ARCH_4  BIT(VM_HIGH_ARCH_BIT_4)
#define VM_HIGH_ARCH_5  BIT(VM_HIGH_ARCH_BIT_5)
#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */

#ifdef CONFIG_ARCH_HAS_PKEYS
# define VM_PKEY_SHIFT  VM_HIGH_ARCH_BIT_0
# define VM_PKEY_BIT0   VM_HIGH_ARCH_0  /* A protection key is a 4-bit value */
# define VM_PKEY_BIT1   VM_HIGH_ARCH_1  /* on x86 and 5-bit value on ppc64   */
# define VM_PKEY_BIT2   VM_HIGH_ARCH_2
# define VM_PKEY_BIT3   VM_HIGH_ARCH_3
#ifdef CONFIG_PPC
# define VM_PKEY_BIT4  VM_HIGH_ARCH_4
#else
# define VM_PKEY_BIT4  0
#endif
#endif /* CONFIG_ARCH_HAS_PKEYS */

#ifdef CONFIG_X86_USER_SHADOW_STACK
/*
 * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
 * support core mm.
 *
 * These VMAs will get a single end guard page. This helps userspace protect
 * itself from attacks. A single page is enough for current shadow stack archs
 * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c
 * for more details on the guard size.
 */
# define VM_SHADOW_STACK        VM_HIGH_ARCH_5
#else
# define VM_SHADOW_STACK        VM_NONE
#endif

#if defined(CONFIG_X86)
# define VM_PAT         VM_ARCH_1       /* PAT reserves whole VMA at once (x86) */
#elif defined(CONFIG_PPC)
# define VM_SAO         VM_ARCH_1       /* Strong Access Ordering (powerpc) */
#elif defined(CONFIG_PARISC)
# define VM_GROWSUP     VM_ARCH_1
#elif defined(CONFIG_SPARC64)
# define VM_SPARC_ADI   VM_ARCH_1       /* Uses ADI tag for access control */
# define VM_ARCH_CLEAR  VM_SPARC_ADI
#elif defined(CONFIG_ARM64)
# define VM_ARM64_BTI   VM_ARCH_1       /* BTI guarded page, a.k.a. GP bit */
# define VM_ARCH_CLEAR  VM_ARM64_BTI
#elif !defined(CONFIG_MMU)
# define VM_MAPPED_COPY VM_ARCH_1       /* T if mapped copy of data (nommu mmap) */
#endif

#if defined(CONFIG_ARM64_MTE)
# define VM_MTE         VM_HIGH_ARCH_0  /* Use Tagged memory for access control */
# define VM_MTE_ALLOWED VM_HIGH_ARCH_1  /* Tagged memory permitted */
#else
# define VM_MTE         VM_NONE
# define VM_MTE_ALLOWED VM_NONE
#endif

#ifndef VM_GROWSUP
# define VM_GROWSUP     VM_NONE
#endif

#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
# define VM_UFFD_MINOR_BIT      38
# define VM_UFFD_MINOR          BIT(VM_UFFD_MINOR_BIT)  /* UFFD minor faults */
#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
# define VM_UFFD_MINOR          VM_NONE
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */

/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)

#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)

/* Common data flag combinations */
#define VM_DATA_FLAGS_TSK_EXEC  (VM_READ | VM_WRITE | TASK_EXEC | \
                                 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#define VM_DATA_FLAGS_NON_EXEC  (VM_READ | VM_WRITE | VM_MAYREAD | \
                                 VM_MAYWRITE | VM_MAYEXEC)
#define VM_DATA_FLAGS_EXEC      (VM_READ | VM_WRITE | VM_EXEC | \
                                 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)

#ifndef VM_DATA_DEFAULT_FLAGS           /* arch can override this */
#define VM_DATA_DEFAULT_FLAGS  VM_DATA_FLAGS_EXEC
#endif

#ifndef VM_STACK_DEFAULT_FLAGS          /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif

#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)

#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK        VM_GROWSUP
#define VM_STACK_EARLY  VM_GROWSDOWN
#else
#define VM_STACK        VM_GROWSDOWN
#define VM_STACK_EARLY  0
#endif

#define VM_STACK_FLAGS  (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)

/* VMA basic access permission flags */
#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)


/*
 * Special vmas that are non-mergable, non-mlock()able.
 */
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)

/* This mask prevents VMA from being scanned with khugepaged */
#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)

/* This mask defines which mm->def_flags a process can inherit its parent */
#define VM_INIT_DEF_MASK        VM_NOHUGEPAGE

/* This mask represents all the VMA flag bits used by mlock */
#define VM_LOCKED_MASK  (VM_LOCKED | VM_LOCKONFAULT)

/* Arch-specific flags to clear when updating VM flags on protection change */
#ifndef VM_ARCH_CLEAR
# define VM_ARCH_CLEAR  VM_NONE
#endif
#define VM_FLAGS_CLEAR  (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR)

/*
 * mapping from the currently active vm_flags protection bits (the
 * low four bits) to a page protection mask..
 */

/*
 * The default fault flags that should be used by most of the
 * arch-specific page fault handlers.
 */
#define FAULT_FLAG_DEFAULT  (FAULT_FLAG_ALLOW_RETRY | \
                             FAULT_FLAG_KILLABLE | \
                             FAULT_FLAG_INTERRUPTIBLE)

/**
 * fault_flag_allow_retry_first - check ALLOW_RETRY the first time
 * @flags: Fault flags.
 *
 * This is mostly used for places where we want to try to avoid taking
 * the mmap_lock for too long a time when waiting for another condition
 * to change, in which case we can try to be polite to release the
 * mmap_lock in the first round to avoid potential starvation of other
 * processes that would also want the mmap_lock.
 *
 * Return: true if the page fault allows retry and this is the first
 * attempt of the fault handling; false otherwise.
 */
static inline bool fault_flag_allow_retry_first(enum fault_flag flags)
{
        return (flags & FAULT_FLAG_ALLOW_RETRY) &&
            (!(flags & FAULT_FLAG_TRIED));
}

#define FAULT_FLAG_TRACE \
        { FAULT_FLAG_WRITE,             "WRITE" }, \
        { FAULT_FLAG_MKWRITE,           "MKWRITE" }, \
        { FAULT_FLAG_ALLOW_RETRY,       "ALLOW_RETRY" }, \
        { FAULT_FLAG_RETRY_NOWAIT,      "RETRY_NOWAIT" }, \
        { FAULT_FLAG_KILLABLE,          "KILLABLE" }, \
        { FAULT_FLAG_TRIED,             "TRIED" }, \
        { FAULT_FLAG_USER,              "USER" }, \
        { FAULT_FLAG_REMOTE,            "REMOTE" }, \
        { FAULT_FLAG_INSTRUCTION,       "INSTRUCTION" }, \
        { FAULT_FLAG_INTERRUPTIBLE,     "INTERRUPTIBLE" }, \
        { FAULT_FLAG_VMA_LOCK,          "VMA_LOCK" }

/*
 * vm_fault is filled by the pagefault handler and passed to the vma's
 * ->fault function. The vma's ->fault is responsible for returning a bitmask
 * of VM_FAULT_xxx flags that give details about how the fault was handled.
 *
 * MM layer fills up gfp_mask for page allocations but fault handler might
 * alter it if its implementation requires a different allocation context.
 *
 * pgoff should be used in favour of virtual_address, if possible.
 */
struct vm_fault {
        const struct {
                struct vm_area_struct *vma;     /* Target VMA */
                gfp_t gfp_mask;                 /* gfp mask to be used for allocations */
                pgoff_t pgoff;                  /* Logical page offset based on vma */
                unsigned long address;          /* Faulting virtual address - masked */
                unsigned long real_address;     /* Faulting virtual address - unmasked */
        };
        enum fault_flag flags;          /* FAULT_FLAG_xxx flags
                                         * XXX: should really be 'const' */
        pmd_t *pmd;                     /* Pointer to pmd entry matching
                                         * the 'address' */
        pud_t *pud;                     /* Pointer to pud entry matching
                                         * the 'address'
                                         */
        union {
                pte_t orig_pte;         /* Value of PTE at the time of fault */
                pmd_t orig_pmd;         /* Value of PMD at the time of fault,
                                         * used by PMD fault only.
                                         */
        };

        struct page *cow_page;          /* Page handler may use for COW fault */
        struct page *page;              /* ->fault handlers should return a
                                         * page here, unless VM_FAULT_NOPAGE
                                         * is set (which is also implied by
                                         * VM_FAULT_ERROR).
                                         */
        /* These three entries are valid only while holding ptl lock */
        pte_t *pte;                     /* Pointer to pte entry matching
                                         * the 'address'. NULL if the page
                                         * table hasn't been allocated.
                                         */
        spinlock_t *ptl;                /* Page table lock.
                                         * Protects pte page table if 'pte'
                                         * is not NULL, otherwise pmd.
                                         */
        pgtable_t prealloc_pte;         /* Pre-allocated pte page table.
                                         * vm_ops->map_pages() sets up a page
                                         * table from atomic context.
                                         * do_fault_around() pre-allocates
                                         * page table to avoid allocation from
                                         * atomic context.
                                         */
};

/*
 * These are the virtual MM functions - opening of an area, closing and
 * unmapping it (needed to keep files on disk up-to-date etc), pointer
 * to the functions called when a no-page or a wp-page exception occurs.
 */
struct vm_operations_struct {
        void (*open)(struct vm_area_struct * area);
        /**
         * @close: Called when the VMA is being removed from the MM.
         * Context: User context.  May sleep.  Caller holds mmap_lock.
         */
        void (*close)(struct vm_area_struct * area);
        /* Called any time before splitting to check if it's allowed */
        int (*may_split)(struct vm_area_struct *area, unsigned long addr);
        int (*mremap)(struct vm_area_struct *area);
        /*
         * Called by mprotect() to make driver-specific permission
         * checks before mprotect() is finalised.   The VMA must not
         * be modified.  Returns 0 if mprotect() can proceed.
         */
        int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
                        unsigned long end, unsigned long newflags);
        vm_fault_t (*fault)(struct vm_fault *vmf);
        vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
        vm_fault_t (*map_pages)(struct vm_fault *vmf,
                        pgoff_t start_pgoff, pgoff_t end_pgoff);
        unsigned long (*pagesize)(struct vm_area_struct * area);

        /* notification that a previously read-only page is about to become
         * writable, if an error is returned it will cause a SIGBUS */
        vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);

        /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
        vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);

        /* called by access_process_vm when get_user_pages() fails, typically
         * for use by special VMAs. See also generic_access_phys() for a generic
         * implementation useful for any iomem mapping.
         */
        int (*access)(struct vm_area_struct *vma, unsigned long addr,
                      void *buf, int len, int write);

        /* Called by the /proc/PID/maps code to ask the vma whether it
         * has a special name.  Returning non-NULL will also cause this
         * vma to be dumped unconditionally. */
        const char *(*name)(struct vm_area_struct *vma);

#ifdef CONFIG_NUMA
        /*
         * set_policy() op must add a reference to any non-NULL @new mempolicy
         * to hold the policy upon return.  Caller should pass NULL @new to
         * remove a policy and fall back to surrounding context--i.e. do not
         * install a MPOL_DEFAULT policy, nor the task or system default
         * mempolicy.
         */
        int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);

        /*
         * get_policy() op must add reference [mpol_get()] to any policy at
         * (vma,addr) marked as MPOL_SHARED.  The shared policy infrastructure
         * in mm/mempolicy.c will do this automatically.
         * get_policy() must NOT add a ref if the policy at (vma,addr) is not
         * marked as MPOL_SHARED. vma policies are protected by the mmap_lock.
         * If no [shared/vma] mempolicy exists at the addr, get_policy() op
         * must return NULL--i.e., do not "fallback" to task or system default
         * policy.
         */
        struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
                                        unsigned long addr, pgoff_t *ilx);
#endif
        /*
         * Called by vm_normal_page() for special PTEs to find the
         * page for @addr.  This is useful if the default behavior
         * (using pte_page()) would not find the correct page.
         */
        struct page *(*find_special_page)(struct vm_area_struct *vma,
                                          unsigned long addr);
};

#ifdef CONFIG_NUMA_BALANCING
static inline void vma_numab_state_init(struct vm_area_struct *vma)
{
        vma->numab_state = NULL;
}
static inline void vma_numab_state_free(struct vm_area_struct *vma)
{
        kfree(vma->numab_state);
}
#else
static inline void vma_numab_state_init(struct vm_area_struct *vma) {}
static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_PER_VMA_LOCK
/*
 * Try to read-lock a vma. The function is allowed to occasionally yield false
 * locked result to avoid performance overhead, in which case we fall back to
 * using mmap_lock. The function should never yield false unlocked result.
 */
static inline bool vma_start_read(struct vm_area_struct *vma)
{
        /*
         * Check before locking. A race might cause false locked result.
         * We can use READ_ONCE() for the mm_lock_seq here, and don't need
         * ACQUIRE semantics, because this is just a lockless check whose result
         * we don't rely on for anything - the mm_lock_seq read against which we
         * need ordering is below.
         */
        if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq))
                return false;

        if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
                return false;

        /*
         * Overflow might produce false locked result.
         * False unlocked result is impossible because we modify and check
         * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq
         * modification invalidates all existing locks.
         *
         * We must use ACQUIRE semantics for the mm_lock_seq so that if we are
         * racing with vma_end_write_all(), we only start reading from the VMA
         * after it has been unlocked.
         * This pairs with RELEASE semantics in vma_end_write_all().
         */
        if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) {
                up_read(&vma->vm_lock->lock);
                return false;
        }
        return true;
}

static inline void vma_end_read(struct vm_area_struct *vma)
{
        rcu_read_lock(); /* keeps vma alive till the end of up_read */
        up_read(&vma->vm_lock->lock);
        rcu_read_unlock();
}

/* WARNING! Can only be used if mmap_lock is expected to be write-locked */
static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
{
        mmap_assert_write_locked(vma->vm_mm);

        /*
         * current task is holding mmap_write_lock, both vma->vm_lock_seq and
         * mm->mm_lock_seq can't be concurrently modified.
         */
        *mm_lock_seq = vma->vm_mm->mm_lock_seq;
        return (vma->vm_lock_seq == *mm_lock_seq);
}

/*
 * Begin writing to a VMA.
 * Exclude concurrent readers under the per-VMA lock until the currently
 * write-locked mmap_lock is dropped or downgraded.
 */
static inline void vma_start_write(struct vm_area_struct *vma)
{
        int mm_lock_seq;

        if (__is_vma_write_locked(vma, &mm_lock_seq))
                return;

        down_write(&vma->vm_lock->lock);
        /*
         * We should use WRITE_ONCE() here because we can have concurrent reads
         * from the early lockless pessimistic check in vma_start_read().
         * We don't really care about the correctness of that early check, but
         * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
         */
        WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
        up_write(&vma->vm_lock->lock);
}

static inline void vma_assert_write_locked(struct vm_area_struct *vma)
{
        int mm_lock_seq;

        VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
}

static inline void vma_assert_locked(struct vm_area_struct *vma)
{
        if (!rwsem_is_locked(&vma->vm_lock->lock))
                vma_assert_write_locked(vma);
}

static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached)
{
        /* When detaching vma should be write-locked */
        if (detached)
                vma_assert_write_locked(vma);
        vma->detached = detached;
}

static inline void release_fault_lock(struct vm_fault *vmf)
{
        if (vmf->flags & FAULT_FLAG_VMA_LOCK)
                vma_end_read(vmf->vma);
        else
                mmap_read_unlock(vmf->vma->vm_mm);
}

static inline void assert_fault_locked(struct vm_fault *vmf)
{
        if (vmf->flags & FAULT_FLAG_VMA_LOCK)
                vma_assert_locked(vmf->vma);
        else
                mmap_assert_locked(vmf->vma->vm_mm);
}

struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
                                          unsigned long address);

#else /* CONFIG_PER_VMA_LOCK */

static inline bool vma_start_read(struct vm_area_struct *vma)
                { return false; }
static inline void vma_end_read(struct vm_area_struct *vma) {}
static inline void vma_start_write(struct vm_area_struct *vma) {}
static inline void vma_assert_write_locked(struct vm_area_struct *vma)
                { mmap_assert_write_locked(vma->vm_mm); }
static inline void vma_mark_detached(struct vm_area_struct *vma,
                                     bool detached) {}

static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
                unsigned long address)
{
        return NULL;
}

static inline void release_fault_lock(struct vm_fault *vmf)
{
        mmap_read_unlock(vmf->vma->vm_mm);
}

static inline void assert_fault_locked(struct vm_fault *vmf)
{
        mmap_assert_locked(vmf->vma->vm_mm);
}

#endif /* CONFIG_PER_VMA_LOCK */

extern const struct vm_operations_struct vma_dummy_vm_ops;

/*
 * WARNING: vma_init does not initialize vma->vm_lock.
 * Use vm_area_alloc()/vm_area_free() if vma needs locking.
 */
static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
{
        memset(vma, 0, sizeof(*vma));
        vma->vm_mm = mm;
        vma->vm_ops = &vma_dummy_vm_ops;
        INIT_LIST_HEAD(&vma->anon_vma_chain);
        vma_mark_detached(vma, false);
        vma_numab_state_init(vma);
}

/* Use when VMA is not part of the VMA tree and needs no locking */
static inline void vm_flags_init(struct vm_area_struct *vma,
                                 vm_flags_t flags)
{
        ACCESS_PRIVATE(vma, __vm_flags) = flags;
}

/*
 * Use when VMA is part of the VMA tree and modifications need coordination
 * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
 * it should be locked explicitly beforehand.
 */
static inline void vm_flags_reset(struct vm_area_struct *vma,
                                  vm_flags_t flags)
{
        vma_assert_write_locked(vma);
        vm_flags_init(vma, flags);
}

static inline void vm_flags_reset_once(struct vm_area_struct *vma,
                                       vm_flags_t flags)
{
        vma_assert_write_locked(vma);
        WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags);
}

static inline void vm_flags_set(struct vm_area_struct *vma,
                                vm_flags_t flags)
{
        vma_start_write(vma);
        ACCESS_PRIVATE(vma, __vm_flags) |= flags;
}

static inline void vm_flags_clear(struct vm_area_struct *vma,
                                  vm_flags_t flags)
{
        vma_start_write(vma);
        ACCESS_PRIVATE(vma, __vm_flags) &= ~flags;
}

/*
 * Use only if VMA is not part of the VMA tree or has no other users and
 * therefore needs no locking.
 */
static inline void __vm_flags_mod(struct vm_area_struct *vma,
                                  vm_flags_t set, vm_flags_t clear)
{
        vm_flags_init(vma, (vma->vm_flags | set) & ~clear);
}

/*
 * Use only when the order of set/clear operations is unimportant, otherwise
 * use vm_flags_{set|clear} explicitly.
 */
static inline void vm_flags_mod(struct vm_area_struct *vma,
                                vm_flags_t set, vm_flags_t clear)
{
        vma_start_write(vma);
        __vm_flags_mod(vma, set, clear);
}

static inline void vma_set_anonymous(struct vm_area_struct *vma)
{
        vma->vm_ops = NULL;
}

static inline bool vma_is_anonymous(struct vm_area_struct *vma)
{
        return !vma->vm_ops;
}

/*
 * Indicate if the VMA is a heap for the given task; for
 * /proc/PID/maps that is the heap of the main task.
 */
static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
{
        return vma->vm_start < vma->vm_mm->brk &&
                vma->vm_end > vma->vm_mm->start_brk;
}

/*
 * Indicate if the VMA is a stack for the given task; for
 * /proc/PID/maps that is the stack of the main task.
 */
static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
{
        /*
         * We make no effort to guess what a given thread considers to be
         * its "stack".  It's not even well-defined for programs written
         * languages like Go.
         */
        return vma->vm_start <= vma->vm_mm->start_stack &&
                vma->vm_end >= vma->vm_mm->start_stack;
}

static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
{
        int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);

        if (!maybe_stack)
                return false;

        if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
                                                VM_STACK_INCOMPLETE_SETUP)
                return true;

        return false;
}

static inline bool vma_is_foreign(struct vm_area_struct *vma)
{
        if (!current->mm)
                return true;

        if (current->mm != vma->vm_mm)
                return true;

        return false;
}

static inline bool vma_is_accessible(struct vm_area_struct *vma)
{
        return vma->vm_flags & VM_ACCESS_FLAGS;
}

static inline bool is_shared_maywrite(vm_flags_t vm_flags)
{
        return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
                (VM_SHARED | VM_MAYWRITE);
}

static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma)
{
        return is_shared_maywrite(vma->vm_flags);
}

static inline
struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max)
{
        return mas_find(&vmi->mas, max - 1);
}

static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
{
        /*
         * Uses mas_find() to get the first VMA when the iterator starts.
         * Calling mas_next() could skip the first entry.
         */
        return mas_find(&vmi->mas, ULONG_MAX);
}

static inline
struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi)
{
        return mas_next_range(&vmi->mas, ULONG_MAX);
}


static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
{
        return mas_prev(&vmi->mas, 0);
}

static inline
struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi)
{
        return mas_prev_range(&vmi->mas, 0);
}

static inline unsigned long vma_iter_addr(struct vma_iterator *vmi)
{
        return vmi->mas.index;
}

static inline unsigned long vma_iter_end(struct vma_iterator *vmi)
{
        return vmi->mas.last + 1;
}
static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi,
                                      unsigned long count)
{
        return mas_expected_entries(&vmi->mas, count);
}

/* Free any unused preallocations */
static inline void vma_iter_free(struct vma_iterator *vmi)
{
        mas_destroy(&vmi->mas);

}

static inline int vma_iter_bulk_store(struct vma_iterator *vmi,
                                      struct vm_area_struct *vma)
{
        vmi->mas.index = vma->vm_start;
        vmi->mas.last = vma->vm_end - 1;
        mas_store(&vmi->mas, vma);
        if (unlikely(mas_is_err(&vmi->mas)))
                return -ENOMEM;

        return 0;
}

static inline void vma_iter_invalidate(struct vma_iterator *vmi)
{
        mas_pause(&vmi->mas);
}

static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
{
        mas_set(&vmi->mas, addr);
}

#define for_each_vma(__vmi, __vma)                                      \
        while (((__vma) = vma_next(&(__vmi))) != NULL)

/* The MM code likes to work with exclusive end addresses */
#define for_each_vma_range(__vmi, __vma, __end)                         \
        while (((__vma) = vma_find(&(__vmi), (__end))) != NULL)

#ifdef CONFIG_SHMEM
/*
 * The vma_is_shmem is not inline because it is used only by slow
 * paths in userfault.
 */
bool vma_is_shmem(struct vm_area_struct *vma);
bool vma_is_anon_shmem(struct vm_area_struct *vma);
#else
static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; }
static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; }
#endif

int vma_is_stack_for_current(struct vm_area_struct *vma);

/* flush_tlb_range() takes a vma, not a mm, and can care about flags */
#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) }

struct mmu_gather;
struct inode;

/*
 * compound_order() can be called without holding a reference, which means
 * that niceties like page_folio() don't work.  These callers should be
 * prepared to handle wild return values.  For example, PG_head may be
 * set before the order is initialised, or this may be a tail page.
 * See compaction.c for some good examples.
 */
static inline unsigned int compound_order(struct page *page)
{
        struct folio *folio = (struct folio *)page;

        if (!test_bit(PG_head, &folio->flags))
                return 0;
        return folio->_flags_1 & 0xff;
}

/**
 * folio_order - The allocation order of a folio.
 * @folio: The folio.
 *
 * A folio is composed of 2^order pages.  See get_order() for the definition
 * of order.
 *
 * Return: The order of the folio.
 */
static inline unsigned int folio_order(struct folio *folio)
{
        if (!folio_test_large(folio))
                return 0;
        return folio->_flags_1 & 0xff;
}

#include <linux/huge_mm.h>

/*
 * Methods to modify the page usage count.
 *
 * What counts for a page usage:
 * - cache mapping   (page->mapping)
 * - private data    (page->private)
 * - page mapped in a task's page tables, each mapping
 *   is counted separately
 *
 * Also, many kernel routines increase the page count before a critical
 * routine so they can be sure the page doesn't go away from under them.
 */

/*
 * Drop a ref, return true if the refcount fell to zero (the page has no users)
 */
static inline int put_page_testzero(struct page *page)
{
        VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
        return page_ref_dec_and_test(page);
}

static inline int folio_put_testzero(struct folio *folio)
{
        return put_page_testzero(&folio->page);
}

/*
 * Try to grab a ref unless the page has a refcount of zero, return false if
 * that is the case.
 * This can be called when MMU is off so it must not access
 * any of the virtual mappings.
 */
static inline bool get_page_unless_zero(struct page *page)
{
        return page_ref_add_unless(page, 1, 0);
}

static inline struct folio *folio_get_nontail_page(struct page *page)
{
        if (unlikely(!get_page_unless_zero(page)))
                return NULL;
        return (struct folio *)page;
}

extern int page_is_ram(unsigned long pfn);

enum {
        REGION_INTERSECTS,
        REGION_DISJOINT,
        REGION_MIXED,
};

int region_intersects(resource_size_t offset, size_t size, unsigned long flags,
                      unsigned long desc);

/* Support for virtually mapped pages */
struct page *vmalloc_to_page(const void *addr);
unsigned long vmalloc_to_pfn(const void *addr);

/*
 * Determine if an address is within the vmalloc range
 *
 * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
 * is no special casing required.
 */
#ifdef CONFIG_MMU
extern bool is_vmalloc_addr(const void *x);
extern int is_vmalloc_or_module_addr(const void *x);
#else
static inline bool is_vmalloc_addr(const void *x)
{
        return false;
}
static inline int is_vmalloc_or_module_addr(const void *x)
{
        return 0;
}
#endif

/*
 * How many times the entire folio is mapped as a single unit (eg by a
 * PMD or PUD entry).  This is probably not what you want, except for
 * debugging purposes - it does not include PTE-mapped sub-pages; look
 * at folio_mapcount() or page_mapcount() or total_mapcount() instead.
 */
static inline int folio_entire_mapcount(struct folio *folio)
{
        VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
        return atomic_read(&folio->_entire_mapcount) + 1;
}

/*
 * The atomic page->_mapcount, starts from -1: so that transitions
 * both from it and to it can be tracked, using atomic_inc_and_test
 * and atomic_add_negative(-1).
 */
static inline void page_mapcount_reset(struct page *page)
{
        atomic_set(&(page)->_mapcount, -1);
}

/**
 * page_mapcount() - Number of times this precise page is mapped.
 * @page: The page.
 *
 * The number of times this page is mapped.  If this page is part of
 * a large folio, it includes the number of times this page is mapped
 * as part of that folio.
 *
 * The result is undefined for pages which cannot be mapped into userspace.
 * For example SLAB or special types of pages. See function page_has_type().
 * They use this field in struct page differently.
 */
static inline int page_mapcount(struct page *page)
{
        int mapcount = atomic_read(&page->_mapcount) + 1;

        if (unlikely(PageCompound(page)))
                mapcount += folio_entire_mapcount(page_folio(page));

        return mapcount;
}

int folio_total_mapcount(struct folio *folio);

/**
 * folio_mapcount() - Calculate the number of mappings of this folio.
 * @folio: The folio.
 *
 * A large folio tracks both how many times the entire folio is mapped,
 * and how many times each individual page in the folio is mapped.
 * This function calculates the total number of times the folio is
 * mapped.
 *
 * Return: The number of times this folio is mapped.
 */
static inline int folio_mapcount(struct folio *folio)
{
        if (likely(!folio_test_large(folio)))
                return atomic_read(&folio->_mapcount) + 1;
        return folio_total_mapcount(folio);
}

static inline int total_mapcount(struct page *page)
{
        if (likely(!PageCompound(page)))
                return atomic_read(&page->_mapcount) + 1;
        return folio_total_mapcount(page_folio(page));
}

static inline bool folio_large_is_mapped(struct folio *folio)
{
        /*
         * Reading _entire_mapcount below could be omitted if hugetlb
         * participated in incrementing nr_pages_mapped when compound mapped.
         */
        return atomic_read(&folio->_nr_pages_mapped) > 0 ||
                atomic_read(&folio->_entire_mapcount) >= 0;
}

/**
 * folio_mapped - Is this folio mapped into userspace?
 * @folio: The folio.
 *
 * Return: True if any page in this folio is referenced by user page tables.
 */
static inline bool folio_mapped(struct folio *folio)
{
        if (likely(!folio_test_large(folio)))
                return atomic_read(&folio->_mapcount) >= 0;
        return folio_large_is_mapped(folio);
}

/*
 * Return true if this page is mapped into pagetables.
 * For compound page it returns true if any sub-page of compound page is mapped,
 * even if this particular sub-page is not itself mapped by any PTE or PMD.
 */
static inline bool page_mapped(struct page *page)
{
        if (likely(!PageCompound(page)))
                return atomic_read(&page->_mapcount) >= 0;
        return folio_large_is_mapped(page_folio(page));
}

static inline struct page *virt_to_head_page(const void *x)
{
        struct page *page = virt_to_page(x);

        return compound_head(page);
}

static inline struct folio *virt_to_folio(const void *x)
{
        struct page *page = virt_to_page(x);

        return page_folio(page);
}

void __folio_put(struct folio *folio);

void put_pages_list(struct list_head *pages);

void split_page(struct page *page, unsigned int order);
void folio_copy(struct folio *dst, struct folio *src);

unsigned long nr_free_buffer_pages(void);

void destroy_large_folio(struct folio *folio);

/* Returns the number of bytes in this potentially compound page. */
static inline unsigned long page_size(struct page *page)
{
        return PAGE_SIZE << compound_order(page);
}

/* Returns the number of bits needed for the number of bytes in a page */
static inline unsigned int page_shift(struct page *page)
{
        return PAGE_SHIFT + compound_order(page);
}

/**
 * thp_order - Order of a transparent huge page.
 * @page: Head page of a transparent huge page.
 */
static inline unsigned int thp_order(struct page *page)
{
        VM_BUG_ON_PGFLAGS(PageTail(page), page);
        return compound_order(page);
}

/**
 * thp_size - Size of a transparent huge page.
 * @page: Head page of a transparent huge page.
 *
 * Return: Number of bytes in this page.
 */
static inline unsigned long thp_size(struct page *page)
{
        return PAGE_SIZE << thp_order(page);
}

#ifdef CONFIG_MMU
/*
 * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
 * servicing faults for write access.  In the normal case, do always want
 * pte_mkwrite.  But get_user_pages can cause write faults for mappings
 * that do not have writing enabled, when used by access_process_vm.
 */
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
        if (likely(vma->vm_flags & VM_WRITE))
                pte = pte_mkwrite(pte, vma);
        return pte;
}

vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
void set_pte_range(struct vm_fault *vmf, struct folio *folio,
                struct page *page, unsigned int nr, unsigned long addr);

vm_fault_t finish_fault(struct vm_fault *vmf);
#endif

/*
 * Multiple processes may "see" the same page. E.g. for untouched
 * mappings of /dev/null, all processes see the same page full of
 * zeroes, and text pages of executables and shared libraries have
 * only one copy in memory, at most, normally.
 *
 * For the non-reserved pages, page_count(page) denotes a reference count.
 *   page_count() == 0 means the page is free. page->lru is then used for
 *   freelist management in the buddy allocator.
 *   page_count() > 0  means the page has been allocated.
 *
 * Pages are allocated by the slab allocator in order to provide memory
 * to kmalloc and kmem_cache_alloc. In this case, the management of the
 * page, and the fields in 'struct page' are the responsibility of mm/slab.c
 * unless a particular usage is carefully commented. (the responsibility of
 * freeing the kmalloc memory is the caller's, of course).
 *
 * A page may be used by anyone else who does a __get_free_page().
 * In this case, page_count still tracks the references, and should only
 * be used through the normal accessor functions. The top bits of page->flags
 * and page->virtual store page management information, but all other fields
 * are unused and could be used privately, carefully. The management of this
 * page is the responsibility of the one who allocated it, and those who have
 * subsequently been given references to it.
 *
 * The other pages (we may call them "pagecache pages") are completely
 * managed by the Linux memory manager: I/O, buffers, swapping etc.
 * The following discussion applies only to them.
 *
 * A pagecache page contains an opaque `private' member, which belongs to the
 * page's address_space. Usually, this is the address of a circular list of
 * the page's disk buffers. PG_private must be set to tell the VM to call
 * into the filesystem to release these pages.
 *
 * A page may belong to an inode's memory mapping. In this case, page->mapping
 * is the pointer to the inode, and page->index is the file offset of the page,
 * in units of PAGE_SIZE.
 *
 * If pagecache pages are not associated with an inode, they are said to be
 * anonymous pages. These may become associated with the swapcache, and in that
 * case PG_swapcache is set, and page->private is an offset into the swapcache.
 *
 * In either case (swapcache or inode backed), the pagecache itself holds one
 * reference to the page. Setting PG_private should also increment the
 * refcount. The each user mapping also has a reference to the page.
 *
 * The pagecache pages are stored in a per-mapping radix tree, which is
 * rooted at mapping->i_pages, and indexed by offset.
 * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space
 * lists, we instead now tag pages as dirty/writeback in the radix tree.
 *
 * All pagecache pages may be subject to I/O:
 * - inode pages may need to be read from disk,
 * - inode pages which have been modified and are MAP_SHARED may need
 *   to be written back to the inode on disk,
 * - anonymous pages (including MAP_PRIVATE file mappings) which have been
 *   modified may need to be swapped out to swap space and (later) to be read
 *   back into memory.
 */

#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);

bool __put_devmap_managed_page_refs(struct page *page, int refs);
static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
{
        if (!static_branch_unlikely(&devmap_managed_key))
                return false;
        if (!is_zone_device_page(page))
                return false;
        return __put_devmap_managed_page_refs(page, refs);
}
#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
{
        return false;
}
#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */

static inline bool put_devmap_managed_page(struct page *page)
{
        return put_devmap_managed_page_refs(page, 1);
}

/* 127: arbitrary random number, small enough to assemble well */
#define folio_ref_zero_or_close_to_overflow(folio) \
        ((unsigned int) folio_ref_count(folio) + 127u <= 127u)

/**
 * folio_get - Increment the reference count on a folio.
 * @folio: The folio.
 *
 * Context: May be called in any context, as long as you know that
 * you have a refcount on the folio.  If you do not already have one,
 * folio_try_get() may be the right interface for you to use.
 */
static inline void folio_get(struct folio *folio)
{
        VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio);
        folio_ref_inc(folio);
}

static inline void get_page(struct page *page)
{
        folio_get(page_folio(page));
}

static inline __must_check bool try_get_page(struct page *page)
{
        page = compound_head(page);
        if (WARN_ON_ONCE(page_ref_count(page) <= 0))
                return false;
        page_ref_inc(page);
        return true;
}

/**
 * folio_put - Decrement the reference count on a folio.
 * @folio: The folio.
 *
 * If the folio's reference count reaches zero, the memory will be
 * released back to the page allocator and may be used by another
 * allocation immediately.  Do not access the memory or the struct folio
 * after calling folio_put() unless you can be sure that it wasn't the
 * last reference.
 *
 * Context: May be called in process or interrupt context, but not in NMI
 * context.  May be called while holding a spinlock.
 */
static inline void folio_put(struct folio *folio)
{
        if (folio_put_testzero(folio))
                __folio_put(folio);
}

/**
 * folio_put_refs - Reduce the reference count on a folio.
 * @folio: The folio.
 * @refs: The amount to subtract from the folio's reference count.
 *
 * If the folio's reference count reaches zero, the memory will be
 * released back to the page allocator and may be used by another
 * allocation immediately.  Do not access the memory or the struct folio
 * after calling folio_put_refs() unless you can be sure that these weren't
 * the last references.
 *
 * Context: May be called in process or interrupt context, but not in NMI
 * context.  May be called while holding a spinlock.
 */
static inline void folio_put_refs(struct folio *folio, int refs)
{
        if (folio_ref_sub_and_test(folio, refs))
                __folio_put(folio);
}

/*
 * union release_pages_arg - an array of pages or folios
 *
 * release_pages() releases a simple array of multiple pages, and
 * accepts various different forms of said page array: either
 * a regular old boring array of pages, an array of folios, or
 * an array of encoded page pointers.
 *
 * The transparent union syntax for this kind of "any of these
 * argument types" is all kinds of ugly, so look away.
 */
typedef union {
        struct page **pages;
        struct folio **folios;
        struct encoded_page **encoded_pages;
} release_pages_arg __attribute__ ((__transparent_union__));

void release_pages(release_pages_arg, int nr);

/**
 * folios_put - Decrement the reference count on an array of folios.
 * @folios: The folios.
 * @nr: How many folios there are.
 *
 * Like folio_put(), but for an array of folios.  This is more efficient
 * than writing the loop yourself as it will optimise the locks which
 * need to be taken if the folios are freed.
 *
 * Context: May be called in process or interrupt context, but not in NMI
 * context.  May be called while holding a spinlock.
 */
static inline void folios_put(struct folio **folios, unsigned int nr)
{
        release_pages(folios, nr);
}

static inline void put_page(struct page *page)
{
        struct folio *folio = page_folio(page);

        /*
         * For some devmap managed pages we need to catch refcount transition
         * from 2 to 1:
         */
        if (put_devmap_managed_page(&folio->page))
                return;
        folio_put(folio);
}

/*
 * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
 * the page's refcount so that two separate items are tracked: the original page
 * reference count, and also a new count of how many pin_user_pages() calls were
 * made against the page. ("gup-pinned" is another term for the latter).
 *
 * With this scheme, pin_user_pages() becomes special: such pages are marked as
 * distinct from normal pages. As such, the unpin_user_page() call (and its
 * variants) must be used in order to release gup-pinned pages.
 *
 * Choice of value:
 *
 * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
 * counts with respect to pin_user_pages() and unpin_user_page() becomes
 * simpler, due to the fact that adding an even power of two to the page
 * refcount has the effect of using only the upper N bits, for the code that
 * counts up using the bias value. This means that the lower bits are left for
 * the exclusive use of the original code that increments and decrements by one
 * (or at least, by much smaller values than the bias value).
 *
 * Of course, once the lower bits overflow into the upper bits (and this is
 * OK, because subtraction recovers the original values), then visual inspection
 * no longer suffices to directly view the separate counts. However, for normal
 * applications that don't have huge page reference counts, this won't be an
 * issue.
 *
 * Locking: the lockless algorithm described in folio_try_get_rcu()
 * provides safe operation for get_user_pages(), page_mkclean() and
 * other calls that race to set up page table entries.
 */
#define GUP_PIN_COUNTING_BIAS (1U << 10)

void unpin_user_page(struct page *page);
void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
                                 bool make_dirty);
void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
                                      bool make_dirty);
void unpin_user_pages(struct page **pages, unsigned long npages);

static inline bool is_cow_mapping(vm_flags_t flags)
{
        return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}

#ifndef CONFIG_MMU
static inline bool is_nommu_shared_mapping(vm_flags_t flags)
{
        /*
         * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected
         * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of
         * a file mapping. R/O MAP_PRIVATE mappings might still modify
         * underlying memory if ptrace is active, so this is only possible if
         * ptrace does not apply. Note that there is no mprotect() to upgrade
         * write permissions later.
         */
        return flags & (VM_MAYSHARE | VM_MAYOVERLAY);
}
#endif

#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif

/*
 * The identification function is mainly used by the buddy allocator for
 * determining if two pages could be buddies. We are not really identifying
 * the zone since we could be using the section number id if we do not have
 * node id available in page flags.
 * We only guarantee that it will return the same value for two combinable
 * pages in a zone.
 */
static inline int page_zone_id(struct page *page)
{
        return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
}

#ifdef NODE_NOT_IN_PAGE_FLAGS
extern int page_to_nid(const struct page *page);
#else
static inline int page_to_nid(const struct page *page)
{
        struct page *p = (struct page *)page;

        return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK;
}
#endif

static inline int folio_nid(const struct folio *folio)
{
        return page_to_nid(&folio->page);
}

#ifdef CONFIG_NUMA_BALANCING
/* page access time bits needs to hold at least 4 seconds */
#define PAGE_ACCESS_TIME_MIN_BITS       12
#if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS
#define PAGE_ACCESS_TIME_BUCKETS                                \
        (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT)
#else
#define PAGE_ACCESS_TIME_BUCKETS        0
#endif

#define PAGE_ACCESS_TIME_MASK                           \
        (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS)

static inline int cpu_pid_to_cpupid(int cpu, int pid)
{
        return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK);
}

static inline int cpupid_to_pid(int cpupid)
{
        return cpupid & LAST__PID_MASK;
}

static inline int cpupid_to_cpu(int cpupid)
{
        return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK;
}

static inline int cpupid_to_nid(int cpupid)
{
        return cpu_to_node(cpupid_to_cpu(cpupid));
}

static inline bool cpupid_pid_unset(int cpupid)
{
        return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK);
}

static inline bool cpupid_cpu_unset(int cpupid)
{
        return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK);
}

static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
{
        return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid);
}

#define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid)
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
{
        return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK);
}

static inline int folio_last_cpupid(struct folio *folio)
{
        return folio->_last_cpupid;
}
static inline void page_cpupid_reset_last(struct page *page)
{
        page->_last_cpupid = -1 & LAST_CPUPID_MASK;
}
#else
static inline int folio_last_cpupid(struct folio *folio)
{
        return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
}

int folio_xchg_last_cpupid(struct folio *folio, int cpupid);

static inline void page_cpupid_reset_last(struct page *page)
{
        page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT;
}
#endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */

static inline int folio_xchg_access_time(struct folio *folio, int time)
{
        int last_time;

        last_time = folio_xchg_last_cpupid(folio,
                                           time >> PAGE_ACCESS_TIME_BUCKETS);
        return last_time << PAGE_ACCESS_TIME_BUCKETS;
}

static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
{
        unsigned int pid_bit;

        pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG));
        if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) {
                __set_bit(pid_bit, &vma->numab_state->pids_active[1]);
        }
}
#else /* !CONFIG_NUMA_BALANCING */
static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
{
        return folio_nid(folio); /* XXX */
}

static inline int folio_xchg_access_time(struct folio *folio, int time)
{
        return 0;
}

static inline int folio_last_cpupid(struct folio *folio)
{
        return folio_nid(folio); /* XXX */
}

static inline int cpupid_to_nid(int cpupid)
{
        return -1;
}

static inline int cpupid_to_pid(int cpupid)
{
        return -1;
}

static inline int cpupid_to_cpu(int cpupid)
{
        return -1;
}

static inline int cpu_pid_to_cpupid(int nid, int pid)
{
        return -1;
}

static inline bool cpupid_pid_unset(int cpupid)
{
        return true;
}

static inline void page_cpupid_reset_last(struct page *page)
{
}

static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
{
        return false;
}

static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
{
}
#endif /* CONFIG_NUMA_BALANCING */

#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)

/*
 * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid
 * setting tags for all pages to native kernel tag value 0xff, as the default
 * value 0x00 maps to 0xff.
 */

static inline u8 page_kasan_tag(const struct page *page)
{
        u8 tag = 0xff;

        if (kasan_enabled()) {
                tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
                tag ^= 0xff;
        }

        return tag;
}

static inline void page_kasan_tag_set(struct page *page, u8 tag)
{
        unsigned long old_flags, flags;

        if (!kasan_enabled())
                return;

        tag ^= 0xff;
        old_flags = READ_ONCE(page->flags);
        do {
                flags = old_flags;
                flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
                flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
        } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags)));
}

static inline void page_kasan_tag_reset(struct page *page)
{
        if (kasan_enabled())
                page_kasan_tag_set(page, 0xff);
}

#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */

static inline u8 page_kasan_tag(const struct page *page)
{
        return 0xff;
}

static inline void page_kasan_tag_set(struct page *page, u8 tag) { }
static inline void page_kasan_tag_reset(struct page *page) { }

#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */

static inline struct zone *page_zone(const struct page *page)
{
        return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}

static inline pg_data_t *page_pgdat(const struct page *page)
{
        return NODE_DATA(page_to_nid(page));
}

static inline struct zone *folio_zone(const struct folio *folio)
{
        return page_zone(&folio->page);
}

static inline pg_data_t *folio_pgdat(const struct folio *folio)
{
        return page_pgdat(&folio->page);
}

#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
        page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
        page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}

static inline unsigned long page_to_section(const struct page *page)
{
        return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
#endif

/**
 * folio_pfn - Return the Page Frame Number of a folio.
 * @folio: The folio.
 *
 * A folio may contain multiple pages.  The pages have consecutive
 * Page Frame Numbers.
 *
 * Return: The Page Frame Number of the first page in the folio.
 */
static inline unsigned long folio_pfn(struct folio *folio)
{
        return page_to_pfn(&folio->page);
}

static inline struct folio *pfn_folio(unsigned long pfn)
{
        return page_folio(pfn_to_page(pfn));
}

/**
 * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA.
 * @folio: The folio.
 *
 * This function checks if a folio has been pinned via a call to
 * a function in the pin_user_pages() family.
 *
 * For small folios, the return value is partially fuzzy: false is not fuzzy,
 * because it means "definitely not pinned for DMA", but true means "probably
 * pinned for DMA, but possibly a false positive due to having at least
 * GUP_PIN_COUNTING_BIAS worth of normal folio references".
 *
 * False positives are OK, because: a) it's unlikely for a folio to
 * get that many refcounts, and b) all the callers of this routine are
 * expected to be able to deal gracefully with a false positive.
 *
 * For large folios, the result will be exactly correct. That's because
 * we have more tracking data available: the _pincount field is used
 * instead of the GUP_PIN_COUNTING_BIAS scheme.
 *
 * For more information, please see Documentation/core-api/pin_user_pages.rst.
 *
 * Return: True, if it is likely that the page has been "dma-pinned".
 * False, if the page is definitely not dma-pinned.
 */
static inline bool folio_maybe_dma_pinned(struct folio *folio)
{
        if (folio_test_large(folio))
                return atomic_read(&folio->_pincount) > 0;

        /*
         * folio_ref_count() is signed. If that refcount overflows, then
         * folio_ref_count() returns a negative value, and callers will avoid
         * further incrementing the refcount.
         *
         * Here, for that overflow case, use the sign bit to count a little
         * bit higher via unsigned math, and thus still get an accurate result.
         */
        return ((unsigned int)folio_ref_count(folio)) >=
                GUP_PIN_COUNTING_BIAS;
}

static inline bool page_maybe_dma_pinned(struct page *page)
{
        return folio_maybe_dma_pinned(page_folio(page));
}

/*
 * This should most likely only be called during fork() to see whether we
 * should break the cow immediately for an anon page on the src mm.
 *
 * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
 */
static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
                                          struct page *page)
{
        VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));

        if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
                return false;

        return page_maybe_dma_pinned(page);
}

/**
 * is_zero_page - Query if a page is a zero page
 * @page: The page to query
 *
 * This returns true if @page is one of the permanent zero pages.
 */
static inline bool is_zero_page(const struct page *page)
{
        return is_zero_pfn(page_to_pfn(page));
}

/**
 * is_zero_folio - Query if a folio is a zero page
 * @folio: The folio to query
 *
 * This returns true if @folio is one of the permanent zero pages.
 */
static inline bool is_zero_folio(const struct folio *folio)
{
        return is_zero_page(&folio->page);
}

/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */
#ifdef CONFIG_MIGRATION
static inline bool folio_is_longterm_pinnable(struct folio *folio)
{
#ifdef CONFIG_CMA
        int mt = folio_migratetype(folio);

        if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
                return false;
#endif
        /* The zero page can be "pinned" but gets special handling. */
        if (is_zero_folio(folio))