// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 2009  Red Hat, Inc.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/numa_balancing.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/swapops.h>
#include <linux/backing-dev.h>
#include <linux/dax.h>
#include <linux/mm_types.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/migrate.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
#include <linux/oom.h>
#include <linux/numa.h>
#include <linux/page_owner.h>
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>
#include <linux/compat.h>
#include <linux/pgalloc_tag.h>
#include <linux/pagewalk.h>

#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
#include "swap.h"

#define CREATE_TRACE_POINTS
#include <trace/events/thp.h>

/*
 * By default, transparent hugepage support is disabled in order to avoid
 * risking an increased memory footprint for applications that are not
 * guaranteed to benefit from it. When transparent hugepage support is
 * enabled, it is for all mappings, and khugepaged scans all mappings.
 * Defrag is invoked by khugepaged hugepage allocations and by page faults
 * for all hugepage allocations.
 */
unsigned long transparent_hugepage_flags __read_mostly =
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
        (1<<TRANSPARENT_HUGEPAGE_FLAG)|
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
        (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
        (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
        (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
        (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);

static struct shrinker *deferred_split_shrinker;
static unsigned long deferred_split_count(struct shrinker *shrink,
                                          struct shrink_control *sc);
static unsigned long deferred_split_scan(struct shrinker *shrink,
                                         struct shrink_control *sc);
static bool split_underused_thp = true;

static atomic_t huge_zero_refcount;
struct folio *huge_zero_folio __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;
unsigned long huge_anon_orders_always __read_mostly;
unsigned long huge_anon_orders_madvise __read_mostly;
unsigned long huge_anon_orders_inherit __read_mostly;
static bool anon_orders_configured __initdata;

static inline bool file_thp_enabled(struct vm_area_struct *vma)
{
        struct inode *inode;

        if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
                return false;

        if (!vma->vm_file)
                return false;

        inode = file_inode(vma->vm_file);

        return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
}

unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
                                         vm_flags_t vm_flags,
                                         unsigned long tva_flags,
                                         unsigned long orders)
{
        bool smaps = tva_flags & TVA_SMAPS;
        bool in_pf = tva_flags & TVA_IN_PF;
        bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS;
        unsigned long supported_orders;

        /* Check the intersection of requested and supported orders. */
        if (vma_is_anonymous(vma))
                supported_orders = THP_ORDERS_ALL_ANON;
        else if (vma_is_special_huge(vma))
                supported_orders = THP_ORDERS_ALL_SPECIAL;
        else
                supported_orders = THP_ORDERS_ALL_FILE_DEFAULT;

        orders &= supported_orders;
        if (!orders)
                return 0;

        if (!vma->vm_mm)                /* vdso */
                return 0;

        if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags))
                return 0;

        /* khugepaged doesn't collapse DAX vma, but page fault is fine. */
        if (vma_is_dax(vma))
                return in_pf ? orders : 0;

        /*
         * khugepaged special VMA and hugetlb VMA.
         * Must be checked after dax since some dax mappings may have
         * VM_MIXEDMAP set.
         */
        if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED))
                return 0;

        /*
         * Check alignment for file vma and size for both file and anon vma by
         * filtering out the unsuitable orders.
         *
         * Skip the check for page fault. Huge fault does the check in fault
         * handlers.
         */
        if (!in_pf) {
                int order = highest_order(orders);
                unsigned long addr;

                while (orders) {
                        addr = vma->vm_end - (PAGE_SIZE << order);
                        if (thp_vma_suitable_order(vma, addr, order))
                                break;
                        order = next_order(&orders, order);
                }

                if (!orders)
                        return 0;
        }

        /*
         * Enabled via shmem mount options or sysfs settings.
         * Must be done before hugepage flags check since shmem has its
         * own flags.
         */
        if (!in_pf && shmem_file(vma->vm_file))
                return orders & shmem_allowable_huge_orders(file_inode(vma->vm_file),
                                                   vma, vma->vm_pgoff, 0,
                                                   !enforce_sysfs);

        if (!vma_is_anonymous(vma)) {
                /*
                 * Enforce sysfs THP requirements as necessary. Anonymous vmas
                 * were already handled in thp_vma_allowable_orders().
                 */
                if (enforce_sysfs &&
                    (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
                                                    !hugepage_global_always())))
                        return 0;

                /*
                 * Trust that ->huge_fault() handlers know what they are doing
                 * in fault path.
                 */
                if (((in_pf || smaps)) && vma->vm_ops->huge_fault)
                        return orders;
                /* Only regular file is valid in collapse path */
                if (((!in_pf || smaps)) && file_thp_enabled(vma))
                        return orders;
                return 0;
        }

        if (vma_is_temporary_stack(vma))
                return 0;

        /*
         * THPeligible bit of smaps should show 1 for proper VMAs even
         * though anon_vma is not initialized yet.
         *
         * Allow page fault since anon_vma may be not initialized until
         * the first page fault.
         */
        if (!vma->anon_vma)
                return (smaps || in_pf) ? orders : 0;

        return orders;
}

static bool get_huge_zero_page(void)
{
        struct folio *zero_folio;
retry:
        if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
                return true;

        zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
                        HPAGE_PMD_ORDER);
        if (!zero_folio) {
                count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
                return false;
        }
        /* Ensure zero folio won't have large_rmappable flag set. */
        folio_clear_large_rmappable(zero_folio);
        preempt_disable();
        if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
                preempt_enable();
                folio_put(zero_folio);
                goto retry;
        }
        WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio));

        /* We take additional reference here. It will be put back by shrinker */
        atomic_set(&huge_zero_refcount, 2);
        preempt_enable();
        count_vm_event(THP_ZERO_PAGE_ALLOC);
        return true;
}

static void put_huge_zero_page(void)
{
        /*
         * Counter should never go to zero here. Only shrinker can put
         * last reference.
         */
        BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}

struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
{
        if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
                return READ_ONCE(huge_zero_folio);

        if (!get_huge_zero_page())
                return NULL;

        if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
                put_huge_zero_page();

        return READ_ONCE(huge_zero_folio);
}

void mm_put_huge_zero_folio(struct mm_struct *mm)
{
        if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
                put_huge_zero_page();
}

static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
                                        struct shrink_control *sc)
{
        /* we can free zero page only if last reference remains */
        return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
}

static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
                                       struct shrink_control *sc)
{
        if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
                struct folio *zero_folio = xchg(&huge_zero_folio, NULL);
                BUG_ON(zero_folio == NULL);
                WRITE_ONCE(huge_zero_pfn, ~0UL);
                folio_put(zero_folio);
                return HPAGE_PMD_NR;
        }

        return 0;
}

static struct shrinker *huge_zero_page_shrinker;

#ifdef CONFIG_SYSFS
static ssize_t enabled_show(struct kobject *kobj,
                            struct kobj_attribute *attr, char *buf)
{
        const char *output;

        if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags))
                output = "[always] madvise never";
        else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
                          &transparent_hugepage_flags))
                output = "always [madvise] never";
        else
                output = "always madvise [never]";

        return sysfs_emit(buf, "%s\n", output);
}

static ssize_t enabled_store(struct kobject *kobj,
                             struct kobj_attribute *attr,
                             const char *buf, size_t count)
{
        ssize_t ret = count;

        if (sysfs_streq(buf, "always")) {
                clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
        } else if (sysfs_streq(buf, "madvise")) {
                clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
        } else if (sysfs_streq(buf, "never")) {
                clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
        } else
                ret = -EINVAL;

        if (ret > 0) {
                int err = start_stop_khugepaged();
                if (err)
                        ret = err;
        }
        return ret;
}

static struct kobj_attribute enabled_attr = __ATTR_RW(enabled);

ssize_t single_hugepage_flag_show(struct kobject *kobj,
                                  struct kobj_attribute *attr, char *buf,
                                  enum transparent_hugepage_flag flag)
{
        return sysfs_emit(buf, "%d\n",
                          !!test_bit(flag, &transparent_hugepage_flags));
}

ssize_t single_hugepage_flag_store(struct kobject *kobj,
                                 struct kobj_attribute *attr,
                                 const char *buf, size_t count,
                                 enum transparent_hugepage_flag flag)
{
        unsigned long value;
        int ret;

        ret = kstrtoul(buf, 10, &value);
        if (ret < 0)
                return ret;
        if (value > 1)
                return -EINVAL;

        if (value)
                set_bit(flag, &transparent_hugepage_flags);
        else
                clear_bit(flag, &transparent_hugepage_flags);

        return count;
}

static ssize_t defrag_show(struct kobject *kobj,
                           struct kobj_attribute *attr, char *buf)
{
        const char *output;

        if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
                     &transparent_hugepage_flags))
                output = "[always] defer defer+madvise madvise never";
        else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
                          &transparent_hugepage_flags))
                output = "always [defer] defer+madvise madvise never";
        else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
                          &transparent_hugepage_flags))
                output = "always defer [defer+madvise] madvise never";
        else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
                          &transparent_hugepage_flags))
                output = "always defer defer+madvise [madvise] never";
        else
                output = "always defer defer+madvise madvise [never]";

        return sysfs_emit(buf, "%s\n", output);
}

static ssize_t defrag_store(struct kobject *kobj,
                            struct kobj_attribute *attr,
                            const char *buf, size_t count)
{
        if (sysfs_streq(buf, "always")) {
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
        } else if (sysfs_streq(buf, "defer+madvise")) {
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
        } else if (sysfs_streq(buf, "defer")) {
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
        } else if (sysfs_streq(buf, "madvise")) {
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
        } else if (sysfs_streq(buf, "never")) {
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
        } else
                return -EINVAL;

        return count;
}
static struct kobj_attribute defrag_attr = __ATTR_RW(defrag);

static ssize_t use_zero_page_show(struct kobject *kobj,
                                  struct kobj_attribute *attr, char *buf)
{
        return single_hugepage_flag_show(kobj, attr, buf,
                                         TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static ssize_t use_zero_page_store(struct kobject *kobj,
                struct kobj_attribute *attr, const char *buf, size_t count)
{
        return single_hugepage_flag_store(kobj, attr, buf, count,
                                 TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page);

static ssize_t hpage_pmd_size_show(struct kobject *kobj,
                                   struct kobj_attribute *attr, char *buf)
{
        return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE);
}
static struct kobj_attribute hpage_pmd_size_attr =
        __ATTR_RO(hpage_pmd_size);

static ssize_t split_underused_thp_show(struct kobject *kobj,
                            struct kobj_attribute *attr, char *buf)
{
        return sysfs_emit(buf, "%d\n", split_underused_thp);
}

static ssize_t split_underused_thp_store(struct kobject *kobj,
                             struct kobj_attribute *attr,
                             const char *buf, size_t count)
{
        int err = kstrtobool(buf, &split_underused_thp);

        if (err < 0)
                return err;

        return count;
}

static struct kobj_attribute split_underused_thp_attr = __ATTR(
        shrink_underused, 0644, split_underused_thp_show, split_underused_thp_store);

static struct attribute *hugepage_attr[] = {
        &enabled_attr.attr,
        &defrag_attr.attr,
        &use_zero_page_attr.attr,
        &hpage_pmd_size_attr.attr,
#ifdef CONFIG_SHMEM
        &shmem_enabled_attr.attr,
#endif
        &split_underused_thp_attr.attr,
        NULL,
};

static const struct attribute_group hugepage_attr_group = {
        .attrs = hugepage_attr,
};

static void hugepage_exit_sysfs(struct kobject *hugepage_kobj);
static void thpsize_release(struct kobject *kobj);
static DEFINE_SPINLOCK(huge_anon_orders_lock);
static LIST_HEAD(thpsize_list);

static ssize_t anon_enabled_show(struct kobject *kobj,
                                 struct kobj_attribute *attr, char *buf)
{
        int order = to_thpsize(kobj)->order;
        const char *output;

        if (test_bit(order, &huge_anon_orders_always))
                output = "[always] inherit madvise never";
        else if (test_bit(order, &huge_anon_orders_inherit))
                output = "always [inherit] madvise never";
        else if (test_bit(order, &huge_anon_orders_madvise))
                output = "always inherit [madvise] never";
        else
                output = "always inherit madvise [never]";

        return sysfs_emit(buf, "%s\n", output);
}

static ssize_t anon_enabled_store(struct kobject *kobj,
                                  struct kobj_attribute *attr,
                                  const char *buf, size_t count)
{
        int order = to_thpsize(kobj)->order;
        ssize_t ret = count;

        if (sysfs_streq(buf, "always")) {
                spin_lock(&huge_anon_orders_lock);
                clear_bit(order, &huge_anon_orders_inherit);
                clear_bit(order, &huge_anon_orders_madvise);
                set_bit(order, &huge_anon_orders_always);
                spin_unlock(&huge_anon_orders_lock);
        } else if (sysfs_streq(buf, "inherit")) {
                spin_lock(&huge_anon_orders_lock);
                clear_bit(order, &huge_anon_orders_always);
                clear_bit(order, &huge_anon_orders_madvise);
                set_bit(order, &huge_anon_orders_inherit);
                spin_unlock(&huge_anon_orders_lock);
        } else if (sysfs_streq(buf, "madvise")) {
                spin_lock(&huge_anon_orders_lock);
                clear_bit(order, &huge_anon_orders_always);
                clear_bit(order, &huge_anon_orders_inherit);
                set_bit(order, &huge_anon_orders_madvise);
                spin_unlock(&huge_anon_orders_lock);
        } else if (sysfs_streq(buf, "never")) {
                spin_lock(&huge_anon_orders_lock);
                clear_bit(order, &huge_anon_orders_always);
                clear_bit(order, &huge_anon_orders_inherit);
                clear_bit(order, &huge_anon_orders_madvise);
                spin_unlock(&huge_anon_orders_lock);
        } else
                ret = -EINVAL;

        if (ret > 0) {
                int err;

                err = start_stop_khugepaged();
                if (err)
                        ret = err;
        }
        return ret;
}

static struct kobj_attribute anon_enabled_attr =
        __ATTR(enabled, 0644, anon_enabled_show, anon_enabled_store);

static struct attribute *anon_ctrl_attrs[] = {
        &anon_enabled_attr.attr,
        NULL,
};

static const struct attribute_group anon_ctrl_attr_grp = {
        .attrs = anon_ctrl_attrs,
};

static struct attribute *file_ctrl_attrs[] = {
#ifdef CONFIG_SHMEM
        &thpsize_shmem_enabled_attr.attr,
#endif
        NULL,
};

static const struct attribute_group file_ctrl_attr_grp = {
        .attrs = file_ctrl_attrs,
};

static struct attribute *any_ctrl_attrs[] = {
        NULL,
};

static const struct attribute_group any_ctrl_attr_grp = {
        .attrs = any_ctrl_attrs,
};

static const struct kobj_type thpsize_ktype = {
        .release = &thpsize_release,
        .sysfs_ops = &kobj_sysfs_ops,
};

DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}};

static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item)
{
        unsigned long sum = 0;
        int cpu;

        for_each_possible_cpu(cpu) {
                struct mthp_stat *this = &per_cpu(mthp_stats, cpu);

                sum += this->stats[order][item];
        }

        return sum;
}

#define DEFINE_MTHP_STAT_ATTR(_name, _index)                            \
static ssize_t _name##_show(struct kobject *kobj,                       \
                        struct kobj_attribute *attr, char *buf)         \
{                                                                       \
        int order = to_thpsize(kobj)->order;                            \
                                                                        \
        return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index));  \
}                                                                       \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK);
DEFINE_MTHP_STAT_ATTR(swpin_fallback_charge, MTHP_STAT_SWPIN_FALLBACK_CHARGE);
DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
#ifdef CONFIG_SHMEM
DEFINE_MTHP_STAT_ATTR(shmem_alloc, MTHP_STAT_SHMEM_ALLOC);
DEFINE_MTHP_STAT_ATTR(shmem_fallback, MTHP_STAT_SHMEM_FALLBACK);
DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE);
#endif
DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT);
DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON);
DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);

static struct attribute *anon_stats_attrs[] = {
        &anon_fault_alloc_attr.attr,
        &anon_fault_fallback_attr.attr,
        &anon_fault_fallback_charge_attr.attr,
#ifndef CONFIG_SHMEM
        &zswpout_attr.attr,
        &swpin_attr.attr,
        &swpin_fallback_attr.attr,
        &swpin_fallback_charge_attr.attr,
        &swpout_attr.attr,
        &swpout_fallback_attr.attr,
#endif
        &split_deferred_attr.attr,
        &nr_anon_attr.attr,
        &nr_anon_partially_mapped_attr.attr,
        NULL,
};

static struct attribute_group anon_stats_attr_grp = {
        .name = "stats",
        .attrs = anon_stats_attrs,
};

static struct attribute *file_stats_attrs[] = {
#ifdef CONFIG_SHMEM
        &shmem_alloc_attr.attr,
        &shmem_fallback_attr.attr,
        &shmem_fallback_charge_attr.attr,
#endif
        NULL,
};

static struct attribute_group file_stats_attr_grp = {
        .name = "stats",
        .attrs = file_stats_attrs,
};

static struct attribute *any_stats_attrs[] = {
#ifdef CONFIG_SHMEM
        &zswpout_attr.attr,
        &swpin_attr.attr,
        &swpin_fallback_attr.attr,
        &swpin_fallback_charge_attr.attr,
        &swpout_attr.attr,
        &swpout_fallback_attr.attr,
#endif
        &split_attr.attr,
        &split_failed_attr.attr,
        NULL,
};

static struct attribute_group any_stats_attr_grp = {
        .name = "stats",
        .attrs = any_stats_attrs,
};

static int sysfs_add_group(struct kobject *kobj,
                           const struct attribute_group *grp)
{
        int ret = -ENOENT;

        /*
         * If the group is named, try to merge first, assuming the subdirectory
         * was already created. This avoids the warning emitted by
         * sysfs_create_group() if the directory already exists.
         */
        if (grp->name)
                ret = sysfs_merge_group(kobj, grp);
        if (ret)
                ret = sysfs_create_group(kobj, grp);

        return ret;
}

static struct thpsize *thpsize_create(int order, struct kobject *parent)
{
        unsigned long size = (PAGE_SIZE << order) / SZ_1K;
        struct thpsize *thpsize;
        int ret = -ENOMEM;

        thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL);
        if (!thpsize)
                goto err;

        thpsize->order = order;

        ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent,
                                   "hugepages-%lukB", size);
        if (ret) {
                kfree(thpsize);
                goto err;
        }


        ret = sysfs_add_group(&thpsize->kobj, &any_ctrl_attr_grp);
        if (ret)
                goto err_put;

        ret = sysfs_add_group(&thpsize->kobj, &any_stats_attr_grp);
        if (ret)
                goto err_put;

        if (BIT(order) & THP_ORDERS_ALL_ANON) {
                ret = sysfs_add_group(&thpsize->kobj, &anon_ctrl_attr_grp);
                if (ret)
                        goto err_put;

                ret = sysfs_add_group(&thpsize->kobj, &anon_stats_attr_grp);
                if (ret)
                        goto err_put;
        }

        if (BIT(order) & THP_ORDERS_ALL_FILE_DEFAULT) {
                ret = sysfs_add_group(&thpsize->kobj, &file_ctrl_attr_grp);
                if (ret)
                        goto err_put;

                ret = sysfs_add_group(&thpsize->kobj, &file_stats_attr_grp);
                if (ret)
                        goto err_put;
        }

        return thpsize;
err_put:
        kobject_put(&thpsize->kobj);
err:
        return ERR_PTR(ret);
}

static void thpsize_release(struct kobject *kobj)
{
        kfree(to_thpsize(kobj));
}

static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
        int err;
        struct thpsize *thpsize;
        unsigned long orders;
        int order;

        /*
         * Default to setting PMD-sized THP to inherit the global setting and
         * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time
         * constant so we have to do this here.
         */
        if (!anon_orders_configured)
                huge_anon_orders_inherit = BIT(PMD_ORDER);

        *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
        if (unlikely(!*hugepage_kobj)) {
                pr_err("failed to create transparent hugepage kobject\n");
                return -ENOMEM;
        }

        err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
        if (err) {
                pr_err("failed to register transparent hugepage group\n");
                goto delete_obj;
        }

        err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
        if (err) {
                pr_err("failed to register transparent hugepage group\n");
                goto remove_hp_group;
        }

        orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT;
        order = highest_order(orders);
        while (orders) {
                thpsize = thpsize_create(order, *hugepage_kobj);
                if (IS_ERR(thpsize)) {
                        pr_err("failed to create thpsize for order %d\n", order);
                        err = PTR_ERR(thpsize);
                        goto remove_all;
                }
                list_add(&thpsize->node, &thpsize_list);
                order = next_order(&orders, order);
        }

        return 0;

remove_all:
        hugepage_exit_sysfs(*hugepage_kobj);
        return err;
remove_hp_group:
        sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
delete_obj:
        kobject_put(*hugepage_kobj);
        return err;
}

static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
        struct thpsize *thpsize, *tmp;

        list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) {
                list_del(&thpsize->node);
                kobject_put(&thpsize->kobj);
        }

        sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
        sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
        kobject_put(hugepage_kobj);
}
#else
static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
        return 0;
}

static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
}
#endif /* CONFIG_SYSFS */

static int __init thp_shrinker_init(void)
{
        huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero");
        if (!huge_zero_page_shrinker)
                return -ENOMEM;

        deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE |
                                                 SHRINKER_MEMCG_AWARE |
                                                 SHRINKER_NONSLAB,
                                                 "thp-deferred_split");
        if (!deferred_split_shrinker) {
                shrinker_free(huge_zero_page_shrinker);
                return -ENOMEM;
        }

        huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count;
        huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan;
        shrinker_register(huge_zero_page_shrinker);

        deferred_split_shrinker->count_objects = deferred_split_count;
        deferred_split_shrinker->scan_objects = deferred_split_scan;
        shrinker_register(deferred_split_shrinker);

        return 0;
}

static void __init thp_shrinker_exit(void)
{
        shrinker_free(huge_zero_page_shrinker);
        shrinker_free(deferred_split_shrinker);
}

static int __init hugepage_init(void)
{
        int err;
        struct kobject *hugepage_kobj;

        if (!has_transparent_hugepage()) {
                transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED;
                return -EINVAL;
        }

        /*
         * hugepages can't be allocated by the buddy allocator
         */
        MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER);

        err = hugepage_init_sysfs(&hugepage_kobj);
        if (err)
                goto err_sysfs;

        err = khugepaged_init();
        if (err)
                goto err_slab;

        err = thp_shrinker_init();
        if (err)
                goto err_shrinker;

        /*
         * By default disable transparent hugepages on smaller systems,
         * where the extra memory used could hurt more than TLB overhead
         * is likely to save.  The admin can still enable it through /sys.
         */
        if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) {
                transparent_hugepage_flags = 0;
                return 0;
        }

        err = start_stop_khugepaged();
        if (err)
                goto err_khugepaged;

        return 0;
err_khugepaged:
        thp_shrinker_exit();
err_shrinker:
        khugepaged_destroy();
err_slab:
        hugepage_exit_sysfs(hugepage_kobj);
err_sysfs:
        return err;
}
subsys_initcall(hugepage_init);

static int __init setup_transparent_hugepage(char *str)
{
        int ret = 0;
        if (!str)
                goto out;
        if (!strcmp(str, "always")) {
                set_bit(TRANSPARENT_HUGEPAGE_FLAG,
                        &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
                          &transparent_hugepage_flags);
                ret = 1;
        } else if (!strcmp(str, "madvise")) {
                clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
                          &transparent_hugepage_flags);
                set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
                        &transparent_hugepage_flags);
                ret = 1;
        } else if (!strcmp(str, "never")) {
                clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
                          &transparent_hugepage_flags);
                clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
                          &transparent_hugepage_flags);
                ret = 1;
        }
out:
        if (!ret)
                pr_warn("transparent_hugepage= cannot parse, ignored\n");
        return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);

static char str_dup[PAGE_SIZE] __initdata;
static int __init setup_thp_anon(char *str)
{
        char *token, *range, *policy, *subtoken;
        unsigned long always, inherit, madvise;
        char *start_size, *end_size;
        int start, end, nr;
        char *p;

        if (!str || strlen(str) + 1 > PAGE_SIZE)
                goto err;
        strscpy(str_dup, str);

        always = huge_anon_orders_always;
        madvise = huge_anon_orders_madvise;
        inherit = huge_anon_orders_inherit;
        p = str_dup;
        while ((token = strsep(&p, ";")) != NULL) {
                range = strsep(&token, ":");
                policy = token;

                if (!policy)
                        goto err;

                while ((subtoken = strsep(&range, ",")) != NULL) {
                        if (strchr(subtoken, '-')) {
                                start_size = strsep(&subtoken, "-");
                                end_size = subtoken;

                                start = get_order_from_str(start_size, THP_ORDERS_ALL_ANON);
                                end = get_order_from_str(end_size, THP_ORDERS_ALL_ANON);
                        } else {
                                start_size = end_size = subtoken;
                                start = end = get_order_from_str(subtoken,
                                                                 THP_ORDERS_ALL_ANON);

                        }

                        if (start == -EINVAL) {
                                pr_err("invalid size %s in thp_anon boot parameter\n", start_size);
                                goto err;
                        }

                        if (end == -EINVAL) {
                                pr_err("invalid size %s in thp_anon boot parameter\n", end_size);
                                goto err;
                        }

                        if (start < 0 || end < 0 || start > end)
                                goto err;

                        nr = end - start + 1;
                        if (!strcmp(policy, "always")) {
                                bitmap_set(&always, start, nr);
                                bitmap_clear(&inherit, start, nr);
                                bitmap_clear(&madvise, start, nr);
                        } else if (!strcmp(policy, "madvise")) {
                                bitmap_set(&madvise, start, nr);
                                bitmap_clear(&inherit, start, nr);
                                bitmap_clear(&always, start, nr);
                        } else if (!strcmp(policy, "inherit")) {
                                bitmap_set(&inherit, start, nr);
                                bitmap_clear(&madvise, start, nr);
                                bitmap_clear(&always, start, nr);
                        } else if (!strcmp(policy, "never")) {
                                bitmap_clear(&inherit, start, nr);
                                bitmap_clear(&madvise, start, nr);
                                bitmap_clear(&always, start, nr);
                        } else {
                                pr_err("invalid policy %s in thp_anon boot parameter\n", policy);
                                goto err;
                        }
                }
        }

        huge_anon_orders_always = always;
        huge_anon_orders_madvise = madvise;
        huge_anon_orders_inherit = inherit;
        anon_orders_configured = true;
        return 1;

err:
        pr_warn("thp_anon=%s: error parsing string, ignoring setting\n", str);
        return 0;
}
__setup("thp_anon=", setup_thp_anon);

pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
        if (likely(vma->vm_flags & VM_WRITE))
                pmd = pmd_mkwrite(pmd, vma);
        return pmd;
}

#ifdef CONFIG_MEMCG
static inline
struct deferred_split *get_deferred_split_queue(struct folio *folio)
{
        struct mem_cgroup *memcg = folio_memcg(folio);
        struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));

        if (memcg)
                return &memcg->deferred_split_queue;
        else
                return &pgdat->deferred_split_queue;
}
#else
static inline
struct deferred_split *get_deferred_split_queue(struct folio *folio)
{
        struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));

        return &pgdat->deferred_split_queue;
}
#endif

static inline bool is_transparent_hugepage(const struct folio *folio)
{
        if (!folio_test_large(folio))
                return false;

        return is_huge_zero_folio(folio) ||
                folio_test_large_rmappable(folio);
}

static unsigned long __thp_get_unmapped_area(struct file *filp,
                unsigned long addr, unsigned long len,
                loff_t off, unsigned long flags, unsigned long size,
                vm_flags_t vm_flags)
{
        loff_t off_end = off + len;
        loff_t off_align = round_up(off, size);
        unsigned long len_pad, ret, off_sub;

        if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall())
                return 0;

        if (off_end <= off_align || (off_end - off_align) < size)
                return 0;

        len_pad = len + size;
        if (len_pad < len || (off + len_pad) < off)
                return 0;

        ret = mm_get_unmapped_area_vmflags(current->mm, filp, addr, len_pad,
                                           off >> PAGE_SHIFT, flags, vm_flags);

        /*
         * The failure might be due to length padding. The caller will retry
         * without the padding.
         */
        if (IS_ERR_VALUE(ret))
                return 0;

        /*
         * Do not try to align to THP boundary if allocation at the address
         * hint succeeds.
         */
        if (ret == addr)
                return addr;

        off_sub = (off - ret) & (size - 1);

        if (test_bit(MMF_TOPDOWN, &current->mm->flags) && !off_sub)
                return ret + size;

        ret += off_sub;
        return ret;
}

unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
                unsigned long len, unsigned long pgoff, unsigned long flags,
                vm_flags_t vm_flags)
{
        unsigned long ret;
        loff_t off = (loff_t)pgoff << PAGE_SHIFT;

        ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags);
        if (ret)
                return ret;

        return mm_get_unmapped_area_vmflags(current->mm, filp, addr, len, pgoff, flags,
                                            vm_flags);
}

unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
                unsigned long len, unsigned long pgoff, unsigned long flags)
{
        return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);

static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
                unsigned long addr)
{
        gfp_t gfp = vma_thp_gfp_mask(vma);
        const int order = HPAGE_PMD_ORDER;
        struct folio *folio;

        folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK);

        if (unlikely(!folio)) {
                count_vm_event(THP_FAULT_FALLBACK);
                count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
                return NULL;
        }

        VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
        if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
                folio_put(folio);
                count_vm_event(THP_FAULT_FALLBACK);
                count_vm_event(THP_FAULT_FALLBACK_CHARGE);
                count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
                count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
                return NULL;
        }
        folio_throttle_swaprate(folio, gfp);

       /*
        * When a folio is not zeroed during allocation (__GFP_ZERO not used)
        * or user folios require special handling, folio_zero_user() is used to
        * make sure that the page corresponding to the faulting address will be
        * hot in the cache after zeroing.
        */
        if (user_alloc_needs_zeroing())
                folio_zero_user(folio, addr);
        /*
         * The memory barrier inside __folio_mark_uptodate makes sure that
         * folio_zero_user writes become visible before the set_pmd_at()
         * write.
         */
        __folio_mark_uptodate(folio);
        return folio;
}

static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd,
                struct vm_area_struct *vma, unsigned long haddr)
{
        pmd_t entry;

        entry = folio_mk_pmd(folio, vma->vm_page_prot);
        entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
        folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
        folio_add_lru_vma(folio, vma);
        set_pmd_at(vma->vm_mm, haddr, pmd, entry);
        update_mmu_cache_pmd(vma, haddr, pmd);
        add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
        count_vm_event(THP_FAULT_ALLOC);
        count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
        count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
}

static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf)
{
        unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
        struct vm_area_struct *vma = vmf->vma;
        struct folio *folio;
        pgtable_t pgtable;
        vm_fault_t ret = 0;

        folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
        if (unlikely(!folio))
                return VM_FAULT_FALLBACK;

        pgtable = pte_alloc_one(vma->vm_mm);
        if (unlikely(!pgtable)) {
                ret = VM_FAULT_OOM;
                goto release;
        }

        vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
        if (unlikely(!pmd_none(*vmf->pmd))) {
                goto unlock_release;
        } else {
                ret = check_stable_address_space(vma->vm_mm);
                if (ret)
                        goto unlock_release;

                /* Deliver the page fault to userland */
                if (userfaultfd_missing(vma)) {
                        spin_unlock(vmf->ptl);
                        folio_put(folio);
                        pte_free(vma->vm_mm, pgtable);
                        ret = handle_userfault(vmf, VM_UFFD_MISSING);
                        VM_BUG_ON(ret & VM_FAULT_FALLBACK);
                        return ret;
                }
                pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
                map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
                mm_inc_nr_ptes(vma->vm_mm);
                deferred_split_folio(folio, false);
                spin_unlock(vmf->ptl);
        }

        return 0;
unlock_release:
        spin_unlock(vmf->ptl);
release:
        if (pgtable)
                pte_free(vma->vm_mm, pgtable);
        folio_put(folio);
        return ret;

}

/*
 * always: directly stall for all thp allocations
 * defer: wake kswapd and fail if not immediately available
 * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise
 *                fail if not immediately available
 * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately
 *          available
 * never: never stall for any thp allocation
 */
gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma)
{
        const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE);

        /* Always do synchronous compaction */
        if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
                return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);

        /* Kick kcompactd and fail quickly */
        if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
                return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;

        /* Synchronous compaction if madvised, otherwise kick kcompactd */
        if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
                return GFP_TRANSHUGE_LIGHT |
                        (vma_madvised ? __GFP_DIRECT_RECLAIM :
                                        __GFP_KSWAPD_RECLAIM);

        /* Only do synchronous compaction if madvised */
        if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
                return GFP_TRANSHUGE_LIGHT |
                       (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);

        return GFP_TRANSHUGE_LIGHT;
}

/* Caller must hold page table lock. */
static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm,
                struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
                struct folio *zero_folio)
{
        pmd_t entry;
        entry = folio_mk_pmd(zero_folio, vma->vm_page_prot);
        pgtable_trans_huge_deposit(mm, pmd, pgtable);
        set_pmd_at(mm, haddr, pmd, entry);
        mm_inc_nr_ptes(mm);
}

vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
{
        struct vm_area_struct *vma = vmf->vma;
        unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
        vm_fault_t ret;

        if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
                return VM_FAULT_FALLBACK;
        ret = vmf_anon_prepare(vmf);
        if (ret)
                return ret;
        khugepaged_enter_vma(vma, vma->vm_flags);

        if (!(vmf->flags & FAULT_FLAG_WRITE) &&
                        !mm_forbids_zeropage(vma->vm_mm) &&
                        transparent_hugepage_use_zero_page()) {
                pgtable_t pgtable;
                struct folio *zero_folio;
                vm_fault_t ret;

                pgtable = pte_alloc_one(vma->vm_mm);
                if (unlikely(!pgtable))
                        return VM_FAULT_OOM;
                zero_folio = mm_get_huge_zero_folio(vma->vm_mm);
                if (unlikely(!zero_folio)) {
                        pte_free(vma->vm_mm, pgtable);
                        count_vm_event(THP_FAULT_FALLBACK);
                        return VM_FAULT_FALLBACK;
                }
                vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
                ret = 0;
                if (pmd_none(*vmf->pmd)) {
                        ret = check_stable_address_space(vma->vm_mm);
                        if (ret) {
                                spin_unlock(vmf->ptl);
                                pte_free(vma->vm_mm, pgtable);
                        } else if (userfaultfd_missing(vma)) {
                                spin_unlock(vmf->ptl);
                                pte_free(vma->vm_mm, pgtable);
                                ret = handle_userfault(vmf, VM_UFFD_MISSING);
                                VM_BUG_ON(ret & VM_FAULT_FALLBACK);
                        } else {
                                set_huge_zero_folio(pgtable, vma->vm_mm, vma,
                                                   haddr, vmf->pmd, zero_folio);
                                update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
                                spin_unlock(vmf->ptl);
                        }
                } else {
                        spin_unlock(vmf->ptl);
                        pte_free(vma->vm_mm, pgtable);
                }
                return ret;
        }

        return __do_huge_pmd_anonymous_page(vmf);
}

struct folio_or_pfn {
        union {
                struct folio *folio;
                unsigned long pfn;
        };
        bool is_folio;
};

static int insert_pmd(struct vm_area_struct *vma, unsigned long addr,
                pmd_t *pmd, struct folio_or_pfn fop, pgprot_t prot,
                bool write, pgtable_t pgtable)
{
        struct mm_struct *mm = vma->vm_mm;
        pmd_t entry;

        lockdep_assert_held(pmd_lockptr(mm, pmd));

        if (!pmd_none(*pmd)) {
                const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) :
                                          fop.pfn;

                if (write) {
                        if (pmd_pfn(*pmd) != pfn) {
                                WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
                                return -EEXIST;
                        }
                        entry = pmd_mkyoung(*pmd);
                        entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
                        if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
                                update_mmu_cache_pmd(vma, addr, pmd);
                }

                return -EEXIST;
        }

        if (fop.is_folio) {
                entry = folio_mk_pmd(fop.folio, vma->vm_page_prot);

                folio_get(fop.folio);
                folio_add_file_rmap_pmd(fop.folio, &fop.folio->page, vma);
                add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PMD_NR);
        } else {
                entry = pmd_mkhuge(pfn_pmd(fop.pfn, prot));
                entry = pmd_mkspecial(entry);
        }
        if (write) {
                entry = pmd_mkyoung(pmd_mkdirty(entry));
                entry = maybe_pmd_mkwrite(entry, vma);
        }

        if (pgtable) {
                pgtable_trans_huge_deposit(mm, pmd, pgtable);
                mm_inc_nr_ptes(mm);
        }

        set_pmd_at(mm, addr, pmd, entry);
        update_mmu_cache_pmd(vma, addr, pmd);
        return 0;
}

/**
 * vmf_insert_pfn_pmd - insert a pmd size pfn
 * @vmf: Structure describing the fault
 * @pfn: pfn to insert
 * @write: whether it's a write fault
 *
 * Insert a pmd size pfn. See vmf_insert_pfn() for additional info.
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn,
                              bool write)
{
        unsigned long addr = vmf->address & PMD_MASK;
        struct vm_area_struct *vma = vmf->vma;
        pgprot_t pgprot = vma->vm_page_prot;
        struct folio_or_pfn fop = {
                .pfn = pfn,
        };
        pgtable_t pgtable = NULL;
        spinlock_t *ptl;
        int error;

        /*
         * If we had pmd_special, we could avoid all these restrictions,
         * but we need to be consistent with PTEs and architectures that
         * can't support a 'special' bit.
         */
        BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
        BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
                                                (VM_PFNMAP|VM_MIXEDMAP));
        BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));

        if (addr < vma->vm_start || addr >= vma->vm_end)
                return VM_FAULT_SIGBUS;

        if (arch_needs_pgtable_deposit()) {
                pgtable = pte_alloc_one(vma->vm_mm);
                if (!pgtable)
                        return VM_FAULT_OOM;
        }

        pfnmap_setup_cachemode_pfn(pfn, &pgprot);

        ptl = pmd_lock(vma->vm_mm, vmf->pmd);
        error = insert_pmd(vma, addr, vmf->pmd, fop, pgprot, write,
                           pgtable);
        spin_unlock(ptl);
        if (error && pgtable)
                pte_free(vma->vm_mm, pgtable);

        return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);

vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
                                bool write)
{
        struct vm_area_struct *vma = vmf->vma;
        unsigned long addr = vmf->address & PMD_MASK;
        struct mm_struct *mm = vma->vm_mm;
        struct folio_or_pfn fop = {
                .folio = folio,
                .is_folio = true,
        };
        spinlock_t *ptl;
        pgtable_t pgtable = NULL;
        int error;

        if (addr < vma->vm_start || addr >= vma->vm_end)
                return VM_FAULT_SIGBUS;

        if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER))
                return VM_FAULT_SIGBUS;

        if (arch_needs_pgtable_deposit()) {
                pgtable = pte_alloc_one(vma->vm_mm);
                if (!pgtable)
                        return VM_FAULT_OOM;
        }

        ptl = pmd_lock(mm, vmf->pmd);
        error = insert_pmd(vma, addr, vmf->pmd, fop, vma->vm_page_prot,
                           write, pgtable);
        spin_unlock(ptl);
        if (error && pgtable)
                pte_free(mm, pgtable);

        return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_folio_pmd);

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
{
        if (likely(vma->vm_flags & VM_WRITE))
                pud = pud_mkwrite(pud);
        return pud;
}

static void insert_pud(struct vm_area_struct *vma, unsigned long addr,
                pud_t *pud, struct folio_or_pfn fop, pgprot_t prot, bool write)
{
        struct mm_struct *mm = vma->vm_mm;
        pud_t entry;

        if (!pud_none(*pud)) {
                const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) :
                                          fop.pfn;

                if (write) {
                        if (WARN_ON_ONCE(pud_pfn(*pud) != pfn))
                                return;
                        entry = pud_mkyoung(*pud);
                        entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
                        if (pudp_set_access_flags(vma, addr, pud, entry, 1))
                                update_mmu_cache_pud(vma, addr, pud);
                }
                return;
        }

        if (fop.is_folio) {
                entry = folio_mk_pud(fop.folio, vma->vm_page_prot);

                folio_get(fop.folio);
                folio_add_file_rmap_pud(fop.folio, &fop.folio->page, vma);
                add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PUD_NR);
        } else {
                entry = pud_mkhuge(pfn_pud(fop.pfn, prot));
                entry = pud_mkspecial(entry);
        }
        if (write) {
                entry = pud_mkyoung(pud_mkdirty(entry));
                entry = maybe_pud_mkwrite(entry, vma);
        }
        set_pud_at(mm, addr, pud, entry);
        update_mmu_cache_pud(vma, addr, pud);
}

/**
 * vmf_insert_pfn_pud - insert a pud size pfn
 * @vmf: Structure describing the fault
 * @pfn: pfn to insert
 * @write: whether it's a write fault
 *
 * Insert a pud size pfn. See vmf_insert_pfn() for additional info.
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn,
                              bool write)
{
        unsigned long addr = vmf->address & PUD_MASK;
        struct vm_area_struct *vma = vmf->vma;
        pgprot_t pgprot = vma->vm_page_prot;
        struct folio_or_pfn fop = {
                .pfn = pfn,
        };
        spinlock_t *ptl;

        /*
         * If we had pud_special, we could avoid all these restrictions,
         * but we need to be consistent with PTEs and architectures that
         * can't support a 'special' bit.
         */
        BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
        BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
                                                (VM_PFNMAP|VM_MIXEDMAP));
        BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));

        if (addr < vma->vm_start || addr >= vma->vm_end)
                return VM_FAULT_SIGBUS;

        pfnmap_setup_cachemode_pfn(pfn, &pgprot);

        ptl = pud_lock(vma->vm_mm, vmf->pud);
        insert_pud(vma, addr, vmf->pud, fop, pgprot, write);
        spin_unlock(ptl);

        return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);

/**
 * vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry
 * @vmf: Structure describing the fault
 * @folio: folio to insert
 * @write: whether it's a write fault
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
                                bool write)
{
        struct vm_area_struct *vma = vmf->vma;
        unsigned long addr = vmf->address & PUD_MASK;
        pud_t *pud = vmf->pud;
        struct mm_struct *mm = vma->vm_mm;
        struct folio_or_pfn fop = {
                .folio = folio,
                .is_folio = true,
        };
        spinlock_t *ptl;

        if (addr < vma->vm_start || addr >= vma->vm_end)
                return VM_FAULT_SIGBUS;

        if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER))
                return VM_FAULT_SIGBUS;

        ptl = pud_lock(mm, pud);
        insert_pud(vma, addr, vmf->pud, fop, vma->vm_page_prot, write);
        spin_unlock(ptl);

        return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_folio_pud);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
               pmd_t *pmd, bool write)
{
        pmd_t _pmd;

        _pmd = pmd_mkyoung(*pmd);
        if (write)
                _pmd = pmd_mkdirty(_pmd);
        if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
                                  pmd, _pmd, write))
                update_mmu_cache_pmd(vma, addr, pmd);
}

int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
                  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
        spinlock_t *dst_ptl, *src_ptl;
        struct page *src_page;
        struct folio *src_folio;
        pmd_t pmd;
        pgtable_t pgtable = NULL;
        int ret = -ENOMEM;

        pmd = pmdp_get_lockless(src_pmd);
        if (unlikely(pmd_present(pmd) && pmd_special(pmd))) {
                dst_ptl = pmd_lock(dst_mm, dst_pmd);
                src_ptl = pmd_lockptr(src_mm, src_pmd);
                spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
                /*
                 * No need to recheck the pmd, it can't change with write
                 * mmap lock held here.
                 *
                 * Meanwhile, making sure it's not a CoW VMA with writable
                 * mapping, otherwise it means either the anon page wrongly
                 * applied special bit, or we made the PRIVATE mapping be
                 * able to wrongly write to the backend MMIO.
                 */
                VM_WARN_ON_ONCE(is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd));
                goto set_pmd;
        }

        /* Skip if can be re-fill on fault */
        if (!vma_is_anonymous(dst_vma))
                return 0;

        pgtable = pte_alloc_one(dst_mm);
        if (unlikely(!pgtable))
                goto out;

        dst_ptl = pmd_lock(dst_mm, dst_pmd);
        src_ptl = pmd_lockptr(src_mm, src_pmd);
        spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);

        ret = -EAGAIN;
        pmd = *src_pmd;

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
        if (unlikely(is_swap_pmd(pmd))) {
                swp_entry_t entry = pmd_to_swp_entry(pmd);

                VM_BUG_ON(!is_pmd_migration_entry(pmd));
                if (!is_readable_migration_entry(entry)) {
                        entry = make_readable_migration_entry(
                                                        swp_offset(entry));
                        pmd = swp_entry_to_pmd(entry);
                        if (pmd_swp_soft_dirty(*src_pmd))
                                pmd = pmd_swp_mksoft_dirty(pmd);
                        if (pmd_swp_uffd_wp(*src_pmd))
                                pmd = pmd_swp_mkuffd_wp(pmd);
                        set_pmd_at(src_mm, addr, src_pmd, pmd);
                }
                add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
                mm_inc_nr_ptes(dst_mm);
                pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
                if (!userfaultfd_wp(dst_vma))
                        pmd = pmd_swp_clear_uffd_wp(pmd);
                set_pmd_at(dst_mm, addr, dst_pmd, pmd);
                ret = 0;
                goto out_unlock;
        }
#endif

        if (unlikely(!pmd_trans_huge(pmd))) {
                pte_free(dst_mm, pgtable);
                goto out_unlock;
        }
        /*
         * When page table lock is held, the huge zero pmd should not be
         * under splitting since we don't split the page itself, only pmd to
         * a page table.
         */
        if (is_huge_zero_pmd(pmd)) {
                /*
                 * mm_get_huge_zero_folio() will never allocate a new
                 * folio here, since we already have a zero page to
                 * copy. It just takes a reference.
                 */
                mm_get_huge_zero_folio(dst_mm);
                goto out_zero_page;
        }

        src_page = pmd_page(pmd);
        VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
        src_folio = page_folio(src_page);

        folio_get(src_folio);
        if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, dst_vma, src_vma))) {
                /* Page maybe pinned: split and retry the fault on PTEs. */
                folio_put(src_folio);
                pte_free(dst_mm, pgtable);
                spin_unlock(src_ptl);
                spin_unlock(dst_ptl);
                __split_huge_pmd(src_vma, src_pmd, addr, false);
                return -EAGAIN;
        }
        add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
out_zero_page:
        mm_inc_nr_ptes(dst_mm);
        pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
        pmdp_set_wrprotect(src_mm, addr, src_pmd);
        if (!userfaultfd_wp(dst_vma))
                pmd = pmd_clear_uffd_wp(pmd);
        pmd = pmd_wrprotect(pmd);
set_pmd:
        pmd = pmd_mkold(pmd);
        set_pmd_at(dst_mm, addr, dst_pmd, pmd);

        ret = 0;
out_unlock:
        spin_unlock(src_ptl);
        spin_unlock(dst_ptl);
out:
        return ret;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
void touch_pud(struct vm_area_struct *vma, unsigned long addr,
               pud_t *pud, bool write)
{
        pud_t _pud;

        _pud = pud_mkyoung(*pud);
        if (write)
                _pud = pud_mkdirty(_pud);
        if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
                                  pud, _pud, write))
                update_mmu_cache_pud(vma, addr, pud);
}

int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
                  struct vm_area_struct *vma)
{
        spinlock_t *dst_ptl, *src_ptl;
        pud_t pud;
        int ret;

        dst_ptl = pud_lock(dst_mm, dst_pud);
        src_ptl = pud_lockptr(src_mm, src_pud);
        spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);

        ret = -EAGAIN;
        pud = *src_pud;
        if (unlikely(!pud_trans_huge(pud)))
                goto out_unlock;

        /*
         * TODO: once we support anonymous pages, use
         * folio_try_dup_anon_rmap_*() and split if duplicating fails.
         */
        if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) {
                pudp_set_wrprotect(src_mm, addr, src_pud);
                pud = pud_wrprotect(pud);
        }
        pud = pud_mkold(pud);
        set_pud_at(dst_mm, addr, dst_pud, pud);

        ret = 0;
out_unlock:
        spin_unlock(src_ptl);
        spin_unlock(dst_ptl);
        return ret;
}

void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
{
        bool write = vmf->flags & FAULT_FLAG_WRITE;

        vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud);
        if (unlikely(!pud_same(*vmf->pud, orig_pud)))
                goto unlock;

        touch_pud(vmf->vma, vmf->address, vmf->pud, write);
unlock:
        spin_unlock(vmf->ptl);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

void huge_pmd_set_accessed(struct vm_fault *vmf)
{
        bool write = vmf->flags & FAULT_FLAG_WRITE;

        vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
        if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd)))
                goto unlock;

        touch_pmd(vmf->vma, vmf->address, vmf->pmd, write);

unlock:
        spin_unlock(vmf->ptl);
}

static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf)
{
        unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
        struct vm_area_struct *vma = vmf->vma;
        struct mmu_notifier_range range;
        struct folio *folio;
        vm_fault_t ret = 0;

        folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
        if (unlikely(!folio))
                return VM_FAULT_FALLBACK;

        mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr,
                                haddr + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
        vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
        if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd)))
                goto release;
        ret = check_stable_address_space(vma->vm_mm);
        if (ret)
                goto release;
        (void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd);
        map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
        goto unlock;
release:
        folio_put(folio);
unlock:
        spin_unlock(vmf->ptl);
        mmu_notifier_invalidate_range_end(&range);
        return ret;
}

vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
{
        const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
        struct vm_area_struct *vma = vmf->vma;
        struct folio *folio;
        struct page *page;
        unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
        pmd_t orig_pmd = vmf->orig_pmd;

        vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
        VM_BUG_ON_VMA(!vma->anon_vma, vma);

        if (is_huge_zero_pmd(orig_pmd)) {
                vm_fault_t ret = do_huge_zero_wp_pmd(vmf);

                if (!(ret & VM_FAULT_FALLBACK))
                        return ret;

                /* Fallback to splitting PMD if THP cannot be allocated */
                goto fallback;
        }

        spin_lock(vmf->ptl);

        if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
                spin_unlock(vmf->ptl);
                return 0;
        }

        page = pmd_page(orig_pmd);
        folio = page_folio(page);
        VM_BUG_ON_PAGE(!PageHead(page), page);

        /* Early check when only holding the PT lock. */
        if (PageAnonExclusive(page))
                goto reuse;

        if (!folio_trylock(folio)) {
                folio_get(folio);
                spin_unlock(vmf->ptl);
                folio_lock(folio);
                spin_lock(vmf->ptl);
                if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
                        spin_unlock(vmf->ptl);
                        folio_unlock(folio);
                        folio_put(folio);
                        return 0;
                }
                folio_put(folio);
        }

        /* Recheck after temporarily dropping the PT lock. */
        if (PageAnonExclusive(page)) {
                folio_unlock(folio);
                goto reuse;
        }

        /*
         * See do_wp_page(): we can only reuse the folio exclusively if
         * there are no additional references. Note that we always drain
         * the LRU cache immediately after adding a THP.
         */
        if (folio_ref_count(folio) >
                        1 + folio_test_swapcache(folio) * folio_nr_pages(folio))
                goto unlock_fallback;
        if (folio_test_swapcache(folio))
                folio_free_swap(folio);
        if (folio_ref_count(folio) == 1) {
                pmd_t entry;

                folio_move_anon_rmap(folio, vma);
                SetPageAnonExclusive(page);
                folio_unlock(folio);
reuse:
                if (unlikely(unshare)) {
                        spin_unlock(vmf->ptl);
                        return 0;
                }
                entry = pmd_mkyoung(orig_pmd);
                entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
                if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
                        update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
                spin_unlock(vmf->ptl);
                return 0;
        }

unlock_fallback:
        folio_unlock(folio);
        spin_unlock(vmf->ptl);
fallback:
        __split_huge_pmd(vma, vmf->pmd, vmf->address, false);
        return VM_FAULT_FALLBACK;
}

static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
                                           unsigned long addr, pmd_t pmd)
{
        struct page *page;

        if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE)))
                return false;

        /* Don't touch entries that are not even readable (NUMA hinting). */

        if (pmd_protnone(pmd))
                return false;

        /* Do we need write faults for softdirty tracking? */
        if (pmd_needs_soft_dirty_wp(vma, pmd))
                return false;

        /* Do we need write faults for uffd-wp tracking? */
        if (userfaultfd_huge_pmd_wp(vma, pmd))
                return false;

        if (!(vma->vm_flags & VM_SHARED)) {
                /* See can_change_pte_writable(). */
                page = vm_normal_page_pmd(vma, addr, pmd);
                return page && PageAnon(page) && PageAnonExclusive(page);
        }

        /* See can_change_pte_writable(). */
        return pmd_dirty(pmd);
}

/* NUMA hinting page fault entry point for trans huge pmds */
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
        struct vm_area_struct *vma = vmf->vma;
        struct folio *folio;
        unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
        int nid = NUMA_NO_NODE;
        int target_nid, last_cpupid;
        pmd_t pmd, old_pmd;
        bool writable = false;
        int flags = 0;

        vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
        old_pmd = pmdp_get(vmf->pmd);

        if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) {
                spin_unlock(vmf->ptl);
                return 0;
        }

        pmd = pmd_modify(old_pmd, vma->vm_page_prot);

        /*
         * Detect now whether the PMD could be writable; this information
         * is only valid while holding the PT lock.
         */
        writable = pmd_write(pmd);
        if (!writable && vma_wants_manual_pte_write_upgrade(vma) &&
            can_change_pmd_writable(vma, vmf->address, pmd))
                writable = true;

        folio = vm_normal_folio_pmd(vma, haddr, pmd);
        if (!folio)
                goto out_map;

        nid = folio_nid(folio);

        target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable,
                                        &last_cpupid);
        if (target_nid == NUMA_NO_NODE)
                goto out_map;
        if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
                flags |= TNF_MIGRATE_FAIL;
                goto out_map;
        }
        /* The folio is isolated and isolation code holds a folio reference. */
        spin_unlock(vmf->ptl);
        writable = false;

        if (!migrate_misplaced_folio(folio, target_nid)) {
                flags |= TNF_MIGRATED;
                nid = target_nid;
                task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
                return 0;
        }

        flags |= TNF_MIGRATE_FAIL;
        vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
        if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) {
                spin_unlock(vmf->ptl);
                return 0;
        }
out_map:
        /* Restore the PMD */
        pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot);
        pmd = pmd_mkyoung(pmd);
        if (writable)
                pmd = pmd_mkwrite(pmd, vma);
        set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
        update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
        spin_unlock(vmf->ptl);

        if (nid != NUMA_NO_NODE)
                task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
        return 0;
}

/*
 * Return true if we do MADV_FREE successfully on entire pmd page.
 * Otherwise, return false.
 */
bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
                pmd_t *pmd, unsigned long addr, unsigned long next)
{
        spinlock_t *ptl;
        pmd_t orig_pmd;
        struct folio *folio;
        struct mm_struct *mm = tlb->mm;
        bool ret = false;

        tlb_change_page_size(tlb, HPAGE_PMD_SIZE);

        ptl = pmd_trans_huge_lock(pmd, vma);
        if (!ptl)
                goto out_unlocked;

        orig_pmd = *pmd;
        if (is_huge_zero_pmd(orig_pmd))
                goto out;

        if (unlikely(!pmd_present(orig_pmd))) {
                VM_BUG_ON(thp_migration_supported() &&
                                  !is_pmd_migration_entry(orig_pmd));
                goto out;
        }

        folio = pmd_folio(orig_pmd);
        /*
         * If other processes are mapping this folio, we couldn't discard
         * the folio unless they all do MADV_FREE so let's skip the folio.
         */
        if (folio_maybe_mapped_shared(folio))
                goto out;

        if (!folio_trylock(folio))
                goto out;

        /*
         * If user want to discard part-pages of THP, split it so MADV_FREE
         * will deactivate only them.
         */
        if (next - addr != HPAGE_PMD_SIZE) {
                folio_get(folio);
                spin_unlock(ptl);
                split_folio(folio);
                folio_unlock(folio);
                folio_put(folio);
                goto out_unlocked;
        }

        if (folio_test_dirty(folio))
                folio_clear_dirty(folio);
        folio_unlock(folio);

        if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
                pmdp_invalidate(vma, addr, pmd);
                orig_pmd = pmd_mkold(orig_pmd);
                orig_pmd = pmd_mkclean(orig_pmd);

                set_pmd_at(mm, addr, pmd, orig_pmd);
                tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
        }

        folio_mark_lazyfree(folio);
        ret = true;
out:
        spin_unlock(ptl);
out_unlocked:
        return ret;
}

static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
{
        pgtable_t pgtable;

        pgtable = pgtable_trans_huge_withdraw(mm, pmd);
        pte_free(mm, pgtable);
        mm_dec_nr_ptes(mm);
}

int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
                 pmd_t *pmd, unsigned long addr)
{
        pmd_t orig_pmd;
        spinlock_t *ptl;

        tlb_change_page_size(tlb, HPAGE_PMD_SIZE);

        ptl = __pmd_trans_huge_lock(pmd, vma);
        if (!ptl)
                return 0;
        /*
         * For architectures like ppc64 we look at deposited pgtable
         * when calling pmdp_huge_get_and_clear. So do the
         * pgtable_trans_huge_withdraw after finishing pmdp related
         * operations.
         */
        orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd,
                                                tlb->fullmm);
        arch_check_zapped_pmd(vma, orig_pmd);
        tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
        if (!vma_is_dax(vma) && vma_is_special_huge(vma)) {
                if (arch_needs_pgtable_deposit())
                        zap_deposited_table(tlb->mm, pmd);
                spin_unlock(ptl);
        } else if (is_huge_zero_pmd(orig_pmd)) {
                if (!vma_is_dax(vma) || arch_needs_pgtable_deposit())
                        zap_deposited_table(tlb->mm, pmd);
                spin_unlock(ptl);
        } else {
                struct folio *folio = NULL;
                int flush_needed = 1;

                if (pmd_present(orig_pmd)) {
                        struct page *page = pmd_page(orig_pmd);

                        folio = page_folio(page);
                        folio_remove_rmap_pmd(folio, page, vma);
                        WARN_ON_ONCE(folio_mapcount(folio) < 0);
                        VM_BUG_ON_PAGE(!PageHead(page), page);
                } else if (thp_migration_supported()) {
                        swp_entry_t entry;

                        VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
                        entry = pmd_to_swp_entry(orig_pmd);
                        folio = pfn_swap_entry_folio(entry);
                        flush_needed = 0;
                } else
                        WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");

                if (folio_test_anon(folio)) {
                        zap_deposited_table(tlb->mm, pmd);
                        add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
                } else {
                        if (arch_needs_pgtable_deposit())
                                zap_deposited_table(tlb->mm, pmd);
                        add_mm_counter(tlb->mm, mm_counter_file(folio),
                                       -HPAGE_PMD_NR);

                        /*
                         * Use flush_needed to indicate whether the PMD entry
                         * is present, instead of checking pmd_present() again.
                         */
                        if (flush_needed && pmd_young(orig_pmd) &&
                            likely(vma_has_recency(vma)))
                                folio_mark_accessed(folio);
                }

                spin_unlock(ptl);
                if (flush_needed)
                        tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE);
        }
        return 1;
}

#ifndef pmd_move_must_withdraw
static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
                                         spinlock_t *old_pmd_ptl,
                                         struct vm_area_struct *vma)
{
        /*
         * With split pmd lock we also need to move preallocated
         * PTE page table if new_pmd is on different PMD page table.
         *
         * We also don't deposit and withdraw tables for file pages.
         */
        return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
}
#endif

static pmd_t move_soft_dirty_pmd(pmd_t pmd)
{
#ifdef CONFIG_MEM_SOFT_DIRTY
        if (unlikely(is_pmd_migration_entry(pmd)))
                pmd = pmd_swp_mksoft_dirty(pmd);
        else if (pmd_present(pmd))
                pmd = pmd_mksoft_dirty(pmd);
#endif
        return pmd;
}

static pmd_t clear_uffd_wp_pmd(pmd_t pmd)
{
        if (pmd_present(pmd))
                pmd = pmd_clear_uffd_wp(pmd);
        else if (is_swap_pmd(pmd))
                pmd = pmd_swp_clear_uffd_wp(pmd);

        return pmd;
}

bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
                  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
{
        spinlock_t *old_ptl, *new_ptl;
        pmd_t pmd;
        struct mm_struct *mm = vma->vm_mm;
        bool force_flush = false;

        /*
         * The destination pmd shouldn't be established, free_pgtables()
         * should have released it; but move_page_tables() might have already
         * inserted a page table, if racing against shmem/file collapse.
         */
        if (!pmd_none(*new_pmd)) {
                VM_BUG_ON(pmd_trans_huge(*new_pmd));
                return false;
        }

        /*
         * We don't have to worry about the ordering of src and dst
         * ptlocks because exclusive mmap_lock prevents deadlock.
         */
        old_ptl = __pmd_trans_huge_lock(old_pmd, vma);
        if (old_ptl) {
                new_ptl = pmd_lockptr(mm, new_pmd);
                if (new_ptl != old_ptl)
                        spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
                pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
                if (pmd_present(pmd))
                        force_flush = true;
                VM_BUG_ON(!pmd_none(*new_pmd));

                if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) {
                        pgtable_t pgtable;
                        pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
                        pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
                }
                pmd = move_soft_dirty_pmd(pmd);
                if (vma_has_uffd_without_event_remap(vma))
                        pmd = clear_uffd_wp_pmd(pmd);
                set_pmd_at(mm, new_addr, new_pmd, pmd);
                if (force_flush)
                        flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
                if (new_ptl != old_ptl)
                        spin_unlock(new_ptl);
                spin_unlock(old_ptl);
                return true;
        }
        return false;
}

/*
 * Returns
 *  - 0 if PMD could not be locked
 *  - 1 if PMD was locked but protections unchanged and TLB flush unnecessary
 *      or if prot_numa but THP migration is not supported
 *  - HPAGE_PMD_NR if protections changed and TLB flush necessary
 */
int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
                    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
                    unsigned long cp_flags)
{
        struct mm_struct *mm = vma->vm_mm;
        spinlock_t *ptl;
        pmd_t oldpmd, entry;
        bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
        bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
        bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
        int ret = 1;

        tlb_change_page_size(tlb, HPAGE_PMD_SIZE);

        if (prot_numa && !thp_migration_supported())
                return 1;

        ptl = __pmd_trans_huge_lock(pmd, vma);
        if (!ptl)
                return 0;

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
        if (is_swap_pmd(*pmd)) {
                swp_entry_t entry = pmd_to_swp_entry(*pmd);
                struct folio *folio = pfn_swap_entry_folio(entry);
                pmd_t newpmd;

                VM_BUG_ON(!is_pmd_migration_entry(*pmd));
                if (is_writable_migration_entry(entry)) {
                        /*
                         * A protection check is difficult so
                         * just be safe and disable write
                         */
                        if (folio_test_anon(folio))
                                entry = make_readable_exclusive_migration_entry(swp_offset(entry));
                        else
                                entry = make_readable_migration_entry(swp_offset(entry));
                        newpmd = swp_entry_to_pmd(entry);
                        if (pmd_swp_soft_dirty(*pmd))
                                newpmd = pmd_swp_mksoft_dirty(newpmd);
                } else {
                        newpmd = *pmd;
                }

                if (uffd_wp)
                        newpmd = pmd_swp_mkuffd_wp(newpmd);
                else if (uffd_wp_resolve)
                        newpmd = pmd_swp_clear_uffd_wp(newpmd);
                if (!pmd_same(*pmd, newpmd))
                        set_pmd_at(mm, addr, pmd, newpmd);
                goto unlock;
        }
#endif

        if (prot_numa) {
                struct folio *folio;
                bool toptier;
                /*
                 * Avoid trapping faults against the zero page. The read-only
                 * data is likely to be read-cached on the local CPU and
                 * local/remote hits to the zero page are not interesting.
                 */
                if (is_huge_zero_pmd(*pmd))
                        goto unlock;

                if (pmd_protnone(*pmd))
                        goto unlock;

                folio = pmd_folio(*pmd);
                toptier = node_is_toptier(folio_nid(folio));
                /*
                 * Skip scanning top tier node if normal numa
                 * balancing is disabled
                 */
                if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
                    toptier)
                        goto unlock;

                if (folio_use_access_time(folio))
                        folio_xchg_access_time(folio,
                                               jiffies_to_msecs(jiffies));
        }
        /*
         * In case prot_numa, we are under mmap_read_lock(mm). It's critical
         * to not clear pmd intermittently to avoid race with MADV_DONTNEED
         * which is also under mmap_read_lock(mm):
         *
         *      CPU0:                           CPU1:
         *                              change_huge_pmd(prot_numa=1)
         *                               pmdp_huge_get_and_clear_notify()
         * madvise_dontneed()
         *  zap_pmd_range()
         *   pmd_trans_huge(*pmd) == 0 (without ptl)
         *   // skip the pmd
         *                               set_pmd_at();
         *                               // pmd is re-established
         *
         * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
         * which may break userspace.
         *
         * pmdp_invalidate_ad() is required to make sure we don't miss
         * dirty/young flags set by hardware.
         */
        oldpmd = pmdp_invalidate_ad(vma, addr, pmd);

        entry = pmd_modify(oldpmd, newprot);
        if (uffd_wp)
                entry = pmd_mkuffd_wp(entry);
        else if (uffd_wp_resolve)
                /*
                 * Leave the write bit to be handled by PF interrupt
                 * handler, then things like COW could be properly
                 * handled.
                 */
                entry = pmd_clear_uffd_wp(entry);

        /* See change_pte_range(). */
        if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) &&
            can_change_pmd_writable(vma, addr, entry))
                entry = pmd_mkwrite(entry, vma);

        ret = HPAGE_PMD_NR;
        set_pmd_at(mm, addr, pmd, entry);

        if (huge_pmd_needs_flush(oldpmd, entry))
                tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
unlock:
        spin_unlock(ptl);
        return ret;
}

/*
 * Returns:
 *
 * - 0: if pud leaf changed from under us
 * - 1: if pud can be skipped
 * - HPAGE_PUD_NR: if pud was successfully processed
 */
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
                    pud_t *pudp, unsigned long addr, pgprot_t newprot,
                    unsigned long cp_flags)
{
        struct mm_struct *mm = vma->vm_mm;
        pud_t oldpud, entry;
        spinlock_t *ptl;

        tlb_change_page_size(tlb, HPAGE_PUD_SIZE);

        /* NUMA balancing doesn't apply to dax */
        if (cp_flags & MM_CP_PROT_NUMA)
                return 1;

        /*
         * Huge entries on userfault-wp only works with anonymous, while we
         * don't have anonymous PUDs yet.
         */
        if (WARN_ON_ONCE(cp_flags & MM_CP_UFFD_WP_ALL))
                return 1;

        ptl = __pud_trans_huge_lock(pudp, vma);
        if (!ptl)
                return 0;

        /*
         * Can't clear PUD or it can race with concurrent zapping.  See
         * change_huge_pmd().
         */
        oldpud = pudp_invalidate(vma, addr, pudp);
        entry = pud_modify(oldpud, newprot);
        set_pud_at(mm, addr, pudp, entry);
        tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE);

        spin_unlock(ptl);
        return HPAGE_PUD_NR;
}
#endif

#ifdef CONFIG_USERFAULTFD
/*
 * The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by
 * the caller, but it must return after releasing the page_table_lock.
 * Just move the page from src_pmd to dst_pmd if possible.
 * Return zero if succeeded in moving the page, -EAGAIN if it needs to be
 * repeated by the caller, or other errors in case of failure.
 */
int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
                        struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
                        unsigned long dst_addr, unsigned long src_addr)
{
        pmd_t _dst_pmd, src_pmdval;
        struct page *src_page;
        struct folio *src_folio;
        struct anon_vma *src_anon_vma;
        spinlock_t *src_ptl, *dst_ptl;
        pgtable_t src_pgtable;
        struct mmu_notifier_range range;
        int err = 0;

        src_pmdval = *src_pmd;
        src_ptl = pmd_lockptr(mm, src_pmd);

        lockdep_assert_held(src_ptl);
        vma_assert_locked(src_vma);
        vma_assert_locked(dst_vma);

        /* Sanity checks before the operation */
        if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) ||
            WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) {
                spin_unlock(src_ptl);
                return -EINVAL;
        }

        if (!pmd_trans_huge(src_pmdval)) {
                spin_unlock(src_ptl);
                if (is_pmd_migration_entry(src_pmdval)) {
                        pmd_migration_entry_wait(mm, &src_pmdval);
                        return -EAGAIN;
                }
                return -ENOENT;
        }

        src_page = pmd_page(src_pmdval);

        if (!is_huge_zero_pmd(src_pmdval)) {
                if (unlikely(!PageAnonExclusive(src_page))) {
                        spin_unlock(src_ptl);
                        return -EBUSY;
                }

                src_folio = page_folio(src_page);
                folio_get(src_folio);
        } else
                src_folio = NULL;

        spin_unlock(src_ptl);

        flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE);
        mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr,
                                src_addr + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);

        if (src_folio) {
                folio_lock(src_folio);

                /*
                 * split_huge_page walks the anon_vma chain without the page
                 * lock. Serialize against it with the anon_vma lock, the page
                 * lock is not enough.
                 */
                src_anon_vma = folio_get_anon_vma(src_folio);
                if (!src_anon_vma) {
                        err = -EAGAIN;
                        goto unlock_folio;
                }
                anon_vma_lock_write(src_anon_vma);
        } else
                src_anon_vma = NULL;

        dst_ptl = pmd_lockptr(mm, dst_pmd);
        double_pt_lock(src_ptl, dst_ptl);
        if (unlikely(!pmd_same(*src_pmd, src_pmdval) ||
                     !pmd_same(*dst_pmd, dst_pmdval))) {
                err = -EAGAIN;
                goto unlock_ptls;
        }
        if (src_folio) {
                if (folio_maybe_dma_pinned(src_folio) ||
                    !PageAnonExclusive(&src_folio->page)) {
                        err = -EBUSY;
                        goto unlock_ptls;
                }

                if (WARN_ON_ONCE(!folio_test_head(src_folio)) ||
                    WARN_ON_ONCE(!folio_test_anon(src_folio))) {
                        err = -EBUSY;
                        goto unlock_ptls;
                }

                src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
                /* Folio got pinned from under us. Put it back and fail the move. */
                if (folio_maybe_dma_pinned(src_folio)) {
                        set_pmd_at(mm, src_addr, src_pmd, src_pmdval);
                        err = -EBUSY;
                        goto unlock_ptls;
                }

                folio_move_anon_rmap(src_folio, dst_vma);
                src_folio->index = linear_page_index(dst_vma, dst_addr);

                _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot);
                /* Follow mremap() behavior and treat the entry dirty after the move */
                _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);
        } else {
                src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
                _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot);
        }
        set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd);

        src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd);
        pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable);
unlock_ptls:
        double_pt_unlock(src_ptl, dst_ptl);
        if (src_anon_vma) {
                anon_vma_unlock_write(src_anon_vma);
                put_anon_vma(src_anon_vma);
        }
unlock_folio:
        /* unblock rmap walks */
        if (src_folio)
                folio_unlock(src_folio);
        mmu_notifier_invalidate_range_end(&range);
        if (src_folio)
                folio_put(src_folio);
        return err;
}
#endif /* CONFIG_USERFAULTFD */

/*
 * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise.
 *
 * Note that if it returns page table lock pointer, this routine returns without
 * unlocking page table lock. So callers must unlock it.
 */
spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
{
        spinlock_t *ptl;
        ptl = pmd_lock(vma->vm_mm, pmd);
        if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd)))
                return ptl;
        spin_unlock(ptl);
        return NULL;
}

/*
 * Returns page table lock pointer if a given pud maps a thp, NULL otherwise.
 *
 * Note that if it returns page table lock pointer, this routine returns without
 * unlocking page table lock. So callers must unlock it.
 */
spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
{
        spinlock_t *ptl;

        ptl = pud_lock(vma->vm_mm, pud);
        if (likely(pud_trans_huge(*pud)))
                return ptl;
        spin_unlock(ptl);
        return NULL;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
                 pud_t *pud, unsigned long addr)
{
        spinlock_t *ptl;
        pud_t orig_pud;

        ptl = __pud_trans_huge_lock(pud, vma);
        if (!ptl)
                return 0;

        orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
        arch_check_zapped_pud(vma, orig_pud);
        tlb_remove_pud_tlb_entry(tlb, pud, addr);
        if (!vma_is_dax(vma) && vma_is_special_huge(vma)) {
                spin_unlock(ptl);
                /* No zero page support yet */
        } else {
                struct page *page = NULL;
                struct folio *folio;

                /* No support for anonymous PUD pages or migration yet */
                VM_WARN_ON_ONCE(vma_is_anonymous(vma) ||
                                !pud_present(orig_pud));

                page = pud_page(orig_pud);
                folio = page_folio(page);
                folio_remove_rmap_pud(folio, page, vma);
                add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PUD_NR);

                spin_unlock(ptl);
                tlb_remove_page_size(tlb, page, HPAGE_PUD_SIZE);
        }
        return 1;
}

static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
                unsigned long haddr)
{
        struct folio *folio;
        struct page *page;
        pud_t old_pud;

        VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
        VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
        VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
        VM_BUG_ON(!pud_trans_huge(*pud));

        count_vm_event(THP_SPLIT_PUD);

        old_pud = pudp_huge_clear_flush(vma, haddr, pud);

        if (!vma_is_dax(vma))
                return;

        page = pud_page(old_pud);
        folio = page_folio(page);

        if (!folio_test_dirty(folio) && pud_dirty(old_pud))
                folio_mark_dirty(folio);
        if (!folio_test_referenced(folio) && pud_young(old_pud))
                folio_set_referenced(folio);
        folio_remove_rmap_pud(folio, page, vma);
        folio_put(folio);
        add_mm_counter(vma->vm_mm, mm_counter_file(folio),
                -HPAGE_PUD_NR);
}

void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
                unsigned long address)
{
        spinlock_t *ptl;
        struct mmu_notifier_range range;

        mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
                                address & HPAGE_PUD_MASK,
                                (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
        ptl = pud_lock(vma->vm_mm, pud);
        if (unlikely(!pud_trans_huge(*pud)))
                goto out;
        __split_huge_pud_locked(vma, pud, range.start);

out:
        spin_unlock(ptl);
        mmu_notifier_invalidate_range_end(&range);
}
#else
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
                unsigned long address)
{
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
                unsigned long haddr, pmd_t *pmd)
{
        struct mm_struct *mm = vma->vm_mm;
        pgtable_t pgtable;
        pmd_t _pmd, old_pmd;
        unsigned long addr;
        pte_t *pte;
        int i;

        /*
         * Leave pmd empty until pte is filled note that it is fine to delay
         * notification until mmu_notifier_invalidate_range_end() as we are
         * replacing a zero pmd write protected page with a zero pte write
         * protected page.
         *
         * See Documentation/mm/mmu_notifier.rst
         */
        old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd);

        pgtable = pgtable_trans_huge_withdraw(mm, pmd);
        pmd_populate(mm, &_pmd, pgtable);

        pte = pte_offset_map(&_pmd, haddr);
        VM_BUG_ON(!pte);
        for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
                pte_t entry;

                entry = pfn_pte(my_zero_pfn(addr), vma->vm_page_prot);
                entry = pte_mkspecial(entry);
                if (pmd_uffd_wp(old_pmd))
                        entry = pte_mkuffd_wp(entry);
                VM_BUG_ON(!pte_none(ptep_get(pte)));
                set_pte_at(mm, addr, pte, entry);
                pte++;
        }
        pte_unmap(pte - 1);
        smp_wmb(); /* make pte visible before pmd */
        pmd_populate(mm, pmd, pgtable);
}

static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
                unsigned long haddr, bool freeze)
{
        struct mm_struct *mm = vma->vm_mm;
        struct folio *folio;
        struct page *page;
        pgtable_t pgtable;
        pmd_t old_pmd, _pmd;
        bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
        bool anon_exclusive = false, dirty = false;
        unsigned long addr;
        pte_t *pte;
        int i;

        VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
        VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
        VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
        VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd));

        count_vm_event(THP_SPLIT_PMD);

        if (!vma_is_anonymous(vma)) {
                old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd);
                /*
                 * We are going to unmap this huge page. So
                 * just go ahead and zap it
                 */
                if (arch_needs_pgtable_deposit())
                        zap_deposited_table(mm, pmd);
                if (!vma_is_dax(vma) && vma_is_special_huge(vma))
                        return;
                if (unlikely(is_pmd_migration_entry(old_pmd))) {
                        swp_entry_t entry;

                        entry = pmd_to_swp_entry(old_pmd);
                        folio = pfn_swap_entry_folio(entry);
                } else if (is_huge_zero_pmd(old_pmd)) {
                        return;
                } else {
                        page = pmd_page(old_pmd);
                        folio = page_folio(page);
                        if (!folio_test_dirty(folio) && pmd_dirty(old_pmd))
                                folio_mark_dirty(folio);
                        if (!folio_test_referenced(folio) && pmd_young(old_pmd))
                                folio_set_referenced(folio);
                        folio_remove_rmap_pmd(folio, page, vma);
                        folio_put(folio);
                }
                add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR);
                return;
        }

        if (is_huge_zero_pmd(*pmd)) {
                /*
                 * FIXME: Do we want to invalidate secondary mmu by calling
                 * mmu_notifier_arch_invalidate_secondary_tlbs() see comments below
                 * inside __split_huge_pmd() ?
                 *
                 * We are going from a zero huge page write protected to zero
                 * small page also write protected so it does not seems useful
                 * to invalidate secondary mmu at this time.
                 */
                return __split_huge_zero_page_pmd(vma, haddr, pmd);
        }

        pmd_migration = is_pmd_migration_entry(*pmd);
        if (unlikely(pmd_migration)) {
                swp_entry_t entry;

                old_pmd = *pmd;
                entry = pmd_to_swp_entry(old_pmd);
                page = pfn_swap_entry_to_page(entry);
                write = is_writable_migration_entry(entry);
                if (PageAnon(page))
                        anon_exclusive = is_readable_exclusive_migration_entry(entry);
                young = is_migration_entry_young(entry);
                dirty = is_migration_entry_dirty(entry);
                soft_dirty = pmd_swp_soft_dirty(old_pmd);
                uffd_wp = pmd_swp_uffd_wp(old_pmd);
        } else {
                /*
                 * Up to this point the pmd is present and huge and userland has
                 * the whole access to the hugepage during the split (which
                 * happens in place). If we overwrite the pmd with the not-huge
                 * version pointing to the pte here (which of course we could if
                 * all CPUs were bug free), userland could trigger a small page
                 * size TLB miss on the small sized TLB while the hugepage TLB
                 * entry is still established in the huge TLB. Some CPU doesn't
                 * like that. See
                 * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum
                 * 383 on page 105. Intel should be safe but is also warns that
                 * it's only safe if the permission and cache attributes of the
                 * two entries loaded in the two TLB is identical (which should
                 * be the case here). But it is generally safer to never allow
                 * small and huge TLB entries for the same virtual address to be
                 * loaded simultaneously. So instead of doing "pmd_populate();
                 * flush_pmd_tlb_range();" we first mark the current pmd
                 * notpresent (atomically because here the pmd_trans_huge must
                 * remain set at all times on the pmd until the split is
                 * complete for this pmd), then we flush the SMP TLB and finally
                 * we write the non-huge version of the pmd entry with
                 * pmd_populate.
                 */
                old_pmd = pmdp_invalidate(vma, haddr, pmd);
                page = pmd_page(old_pmd);
                folio = page_folio(page);
                if (pmd_dirty(old_pmd)) {
                        dirty = true;
                        folio_set_dirty(folio);
                }
                write = pmd_write(old_pmd);
                young = pmd_young(old_pmd);
                soft_dirty = pmd_soft_dirty(old_pmd);
                uffd_wp = pmd_uffd_wp(old_pmd);

                VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio);
                VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);

                /*
                 * Without "freeze", we'll simply split the PMD, propagating the
                 * PageAnonExclusive() flag for each PTE by setting it for
                 * each subpage -- no need to (temporarily) clear.
                 *
                 * With "freeze" we want to replace mapped pages by
                 * migration entries right away. This is only possible if we
                 * managed to clear PageAnonExclusive() -- see
                 * set_pmd_migration_entry().
                 *
                 * In case we cannot clear PageAnonExclusive(), split the PMD
                 * only and let try_to_migrate_one() fail later.
                 *
                 * See folio_try_share_anon_rmap_pmd(): invalidate PMD first.
                 */
                anon_exclusive = PageAnonExclusive(page);
                if (freeze && anon_exclusive &&
                    folio_try_share_anon_rmap_pmd(folio, page))
                        freeze = false;
                if (!freeze) {
                        rmap_t rmap_flags = RMAP_NONE;

                        folio_ref_add(folio, HPAGE_PMD_NR - 1);
                        if (anon_exclusive)
                                rmap_flags |= RMAP_EXCLUSIVE;
                        folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
                                                 vma, haddr, rmap_flags);
                }
        }

        /*
         * Withdraw the table only after we mark the pmd entry invalid.
         * This's critical for some architectures (Power).
         */
        pgtable = pgtable_trans_huge_withdraw(mm, pmd);
        pmd_populate(mm, &_pmd, pgtable);

        pte = pte_offset_map(&_pmd, haddr);
        VM_BUG_ON(!pte);

        /*
         * Note that NUMA hinting access restrictions are not transferred to
         * avoid any possibility of altering permissions across VMAs.
         */
        if (freeze || pmd_migration) {
                for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {