huge_memory.c

// 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/coredump.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/dax.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/pfn_t.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 <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.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 atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;

static inline bool file_thp_enabled(struct vm_area_struct *vma)
{
	return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file &&
	       !inode_is_open_for_write(vma->vm_file->f_inode) &&
	       (vma->vm_flags & VM_EXEC);
}

bool transparent_hugepage_active(struct vm_area_struct *vma)
{
	/* The addr is used to check if the vma size fits */
	unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE;

	if (!transhuge_vma_suitable(vma, addr))
		return false;
	if (vma_is_anonymous(vma))
		return __transparent_hugepage_enabled(vma);
	if (vma_is_shmem(vma))
		return shmem_huge_enabled(vma);
	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
		return file_thp_enabled(vma);

	return false;
}

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

	zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
			HPAGE_PMD_ORDER);
	if (!zero_page) {
		count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
		return false;
	}
	count_vm_event(THP_ZERO_PAGE_ALLOC);
	preempt_disable();
	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
		preempt_enable();
		__free_pages(zero_page, compound_order(zero_page));
		goto retry;
	}
	WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));

	/* We take additional reference here. It will be put back by shrinker */
	atomic_set(&huge_zero_refcount, 2);
	preempt_enable();
	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 page *mm_get_huge_zero_page(struct mm_struct *mm)
{
	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
		return READ_ONCE(huge_zero_page);

	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_page);
}

void mm_put_huge_zero_page(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 page *zero_page = xchg(&huge_zero_page, NULL);
		BUG_ON(zero_page == NULL);
		WRITE_ONCE(huge_zero_pfn, ~0UL);
		__free_pages(zero_page, compound_order(zero_page));
		return HPAGE_PMD_NR;
	}

	return 0;
}

static struct shrinker huge_zero_page_shrinker = {
	.count_objects = shrink_huge_zero_page_count,
	.scan_objects = shrink_huge_zero_page_scan,
	.seeks = DEFAULT_SEEKS,
};

#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(enabled, 0644, enabled_show, enabled_store);

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(defrag, 0644, defrag_show, defrag_store);

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(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);

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 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
	NULL,
};

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

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

	*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;
	}

	return 0;

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

	if (!has_transparent_hugepage()) {
		/*
		 * Hardware doesn't support hugepages, hence disable
		 * DAX PMD support.
		 */
		transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX;
		return -EINVAL;
	}

	/*
	 * hugepages can't be allocated by the buddy allocator
	 */
	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER);
	/*
	 * we use page->mapping and page->index in second tail page
	 * as list_head: assuming THP order >= 2
	 */
	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);

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

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

	err = register_shrinker(&huge_zero_page_shrinker);
	if (err)
		goto err_hzp_shrinker;
	err = register_shrinker(&deferred_split_shrinker);
	if (err)
		goto err_split_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:
	unregister_shrinker(&deferred_split_shrinker);
err_split_shrinker:
	unregister_shrinker(&huge_zero_page_shrinker);
err_hzp_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);

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

#ifdef CONFIG_MEMCG
static inline struct deferred_split *get_deferred_split_queue(struct page *page)
{
	struct mem_cgroup *memcg = page_memcg(compound_head(page));
	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));

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

	return &pgdat->deferred_split_queue;
}
#endif

void prep_transhuge_page(struct page *page)
{
	/*
	 * we use page->mapping and page->indexlru in second tail page
	 * as list_head: assuming THP order >= 2
	 */

	INIT_LIST_HEAD(page_deferred_list(page));
	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}

bool is_transparent_hugepage(struct page *page)
{
	if (!PageCompound(page))
		return false;

	page = compound_head(page);
	return is_huge_zero_page(page) ||
	       page[1].compound_dtor == TRANSHUGE_PAGE_DTOR;
}
EXPORT_SYMBOL_GPL(is_transparent_hugepage);

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)
{
	loff_t off_end = off + len;
	loff_t off_align = round_up(off, size);
	unsigned long len_pad, ret;

	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 = current->mm->get_unmapped_area(filp, addr, len_pad,
					      off >> PAGE_SHIFT, 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;

	ret += (off - ret) & (size - 1);
	return ret;
}

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

	if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
		goto out;

	ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
	if (ret)
		return ret;
out:
	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);

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

	VM_BUG_ON_PAGE(!PageCompound(page), page);

	if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) {
		put_page(page);
		count_vm_event(THP_FAULT_FALLBACK);
		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
		return VM_FAULT_FALLBACK;
	}
	cgroup_throttle_swaprate(page, gfp);

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

	clear_huge_page(page, vmf->address, HPAGE_PMD_NR);
	/*
	 * The memory barrier inside __SetPageUptodate makes sure that
	 * clear_huge_page writes become visible before the set_pmd_at()
	 * write.
	 */
	__SetPageUptodate(page);

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

		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);
			put_page(page);
			pte_free(vma->vm_mm, pgtable);
			ret = handle_userfault(vmf, VM_UFFD_MISSING);
			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
			return ret;
		}

		entry = mk_huge_pmd(page, vma->vm_page_prot);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		page_add_new_anon_rmap(page, vma, haddr, true);
		lru_cache_add_inactive_or_unevictable(page, vma);
		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
		mm_inc_nr_ptes(vma->vm_mm);
		spin_unlock(vmf->ptl);
		count_vm_event(THP_FAULT_ALLOC);
		count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
	}

	return 0;
unlock_release:
	spin_unlock(vmf->ptl);
release:
	if (pgtable)
		pte_free(vma->vm_mm, pgtable);
	put_page(page);
	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_page(pgtable_t pgtable, struct mm_struct *mm,
		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
		struct page *zero_page)
{
	pmd_t entry;
	if (!pmd_none(*pmd))
		return;
	entry = mk_pmd(zero_page, vma->vm_page_prot);
	entry = pmd_mkhuge(entry);
	if (pgtable)
		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;
	gfp_t gfp;
	struct page *page;
	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

	if (!transhuge_vma_suitable(vma, haddr))
		return VM_FAULT_FALLBACK;
	if (unlikely(anon_vma_prepare(vma)))
		return VM_FAULT_OOM;
	if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
		return VM_FAULT_OOM;
	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
			!mm_forbids_zeropage(vma->vm_mm) &&
			transparent_hugepage_use_zero_page()) {
		pgtable_t pgtable;
		struct page *zero_page;
		vm_fault_t ret;
		pgtable = pte_alloc_one(vma->vm_mm);
		if (unlikely(!pgtable))
			return VM_FAULT_OOM;
		zero_page = mm_get_huge_zero_page(vma->vm_mm);
		if (unlikely(!zero_page)) {
			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_page(pgtable, vma->vm_mm, vma,
						   haddr, vmf->pmd, zero_page);
				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;
	}
	gfp = vma_thp_gfp_mask(vma);
	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
	if (unlikely(!page)) {
		count_vm_event(THP_FAULT_FALLBACK);
		return VM_FAULT_FALLBACK;
	}
	prep_transhuge_page(page);
	return __do_huge_pmd_anonymous_page(vmf, page, gfp);
}

static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
		pgtable_t pgtable)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t entry;
	spinlock_t *ptl;

	ptl = pmd_lock(mm, pmd);
	if (!pmd_none(*pmd)) {
		if (write) {
			if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
				WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
				goto out_unlock;
			}
			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);
		}

		goto out_unlock;
	}

	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
	if (pfn_t_devmap(pfn))
		entry = pmd_mkdevmap(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);
		pgtable = NULL;
	}

	set_pmd_at(mm, addr, pmd, entry);
	update_mmu_cache_pmd(vma, addr, pmd);

out_unlock:
	spin_unlock(ptl);
	if (pgtable)
		pte_free(mm, pgtable);
}

/**
 * vmf_insert_pfn_pmd_prot - insert a pmd size pfn
 * @vmf: Structure describing the fault
 * @pfn: pfn to insert
 * @pgprot: page protection to use
 * @write: whether it's a write fault
 *
 * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and
 * also consult the vmf_insert_mixed_prot() documentation when
 * @pgprot != @vmf->vma->vm_page_prot.
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
				   pgprot_t pgprot, bool write)
{
	unsigned long addr = vmf->address & PMD_MASK;
	struct vm_area_struct *vma = vmf->vma;
	pgtable_t pgtable = NULL;

	/*
	 * 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)) &&
			!pfn_t_devmap(pfn));
	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;
	}

	track_pfn_insert(vma, &pgprot, pfn);

	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
	return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot);

#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_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
{
	struct mm_struct *mm = vma->vm_mm;
	pud_t entry;
	spinlock_t *ptl;

	ptl = pud_lock(mm, pud);
	if (!pud_none(*pud)) {
		if (write) {
			if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
				WARN_ON_ONCE(!is_huge_zero_pud(*pud));
				goto out_unlock;
			}
			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);
		}
		goto out_unlock;
	}

	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
	if (pfn_t_devmap(pfn))
		entry = pud_mkdevmap(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);

out_unlock:
	spin_unlock(ptl);
}

/**
 * vmf_insert_pfn_pud_prot - insert a pud size pfn
 * @vmf: Structure describing the fault
 * @pfn: pfn to insert
 * @pgprot: page protection to use
 * @write: whether it's a write fault
 *
 * Insert a pud size pfn. See vmf_insert_pfn() for additional info and
 * also consult the vmf_insert_mixed_prot() documentation when
 * @pgprot != @vmf->vma->vm_page_prot.
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn,
				   pgprot_t pgprot, bool write)
{
	unsigned long addr = vmf->address & PUD_MASK;
	struct vm_area_struct *vma = vmf->vma;

	/*
	 * 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)) &&
			!pfn_t_devmap(pfn));
	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;

	track_pfn_insert(vma, &pgprot, pfn);

	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
	return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
		pmd_t *pmd, int flags)
{
	pmd_t _pmd;

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

struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
		pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
{
	unsigned long pfn = pmd_pfn(*pmd);
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;

	assert_spin_locked(pmd_lockptr(mm, pmd));

	/*
	 * When we COW a devmap PMD entry, we split it into PTEs, so we should
	 * not be in this function with `flags & FOLL_COW` set.
	 */
	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");

	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
			 (FOLL_PIN | FOLL_GET)))
		return NULL;

	if (flags & FOLL_WRITE && !pmd_write(*pmd))
		return NULL;