huge_memory.c

/*
 *  Copyright (C) 2009  Red Hat, Inc.
 *
 *  This work is licensed under the terms of the GNU GPL, version 2. See
 *  the COPYING file in the top-level directory.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/sched.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/kthread.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/mman.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 <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"

enum scan_result {
	SCAN_FAIL,
	SCAN_SUCCEED,
	SCAN_PMD_NULL,
	SCAN_EXCEED_NONE_PTE,
	SCAN_PTE_NON_PRESENT,
	SCAN_PAGE_RO,
	SCAN_NO_REFERENCED_PAGE,
	SCAN_PAGE_NULL,
	SCAN_SCAN_ABORT,
	SCAN_PAGE_COUNT,
	SCAN_PAGE_LRU,
	SCAN_PAGE_LOCK,
	SCAN_PAGE_ANON,
	SCAN_PAGE_COMPOUND,
	SCAN_ANY_PROCESS,
	SCAN_VMA_NULL,
	SCAN_VMA_CHECK,
	SCAN_ADDRESS_RANGE,
	SCAN_SWAP_CACHE_PAGE,
	SCAN_DEL_PAGE_LRU,
	SCAN_ALLOC_HUGE_PAGE_FAIL,
	SCAN_CGROUP_CHARGE_FAIL
};

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

/*
 * By default transparent hugepage support is disabled in order that avoid
 * to risk increase the memory footprint of applications without a guaranteed
 * benefit. When transparent hugepage support is enabled, 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_FLAG)|
	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);

/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
/* during fragmentation poll the hugepage allocator once every minute */
static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
static struct task_struct *khugepaged_thread __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
static DEFINE_SPINLOCK(khugepaged_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
/*
 * default collapse hugepages if there is at least one pte mapped like
 * it would have happened if the vma was large enough during page
 * fault.
 */
static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;

static int khugepaged(void *none);
static int khugepaged_slab_init(void);
static void khugepaged_slab_exit(void);

#define MM_SLOTS_HASH_BITS 10
static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);

static struct kmem_cache *mm_slot_cache __read_mostly;

/**
 * struct mm_slot - hash lookup from mm to mm_slot
 * @hash: hash collision list
 * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head
 * @mm: the mm that this information is valid for
 */
struct mm_slot {
	struct hlist_node hash;
	struct list_head mm_node;
	struct mm_struct *mm;
};

/**
 * struct khugepaged_scan - cursor for scanning
 * @mm_head: the head of the mm list to scan
 * @mm_slot: the current mm_slot we are scanning
 * @address: the next address inside that to be scanned
 *
 * There is only the one khugepaged_scan instance of this cursor structure.
 */
struct khugepaged_scan {
	struct list_head mm_head;
	struct mm_slot *mm_slot;
	unsigned long address;
};
static struct khugepaged_scan khugepaged_scan = {
	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
};

static DEFINE_SPINLOCK(split_queue_lock);
static LIST_HEAD(split_queue);
static unsigned long split_queue_len;
static struct shrinker deferred_split_shrinker;

static void set_recommended_min_free_kbytes(void)
{
	struct zone *zone;
	int nr_zones = 0;
	unsigned long recommended_min;

	for_each_populated_zone(zone)
		nr_zones++;

	/* Ensure 2 pageblocks are free to assist fragmentation avoidance */
	recommended_min = pageblock_nr_pages * nr_zones * 2;

	/*
	 * Make sure that on average at least two pageblocks are almost free
	 * of another type, one for a migratetype to fall back to and a
	 * second to avoid subsequent fallbacks of other types There are 3
	 * MIGRATE_TYPES we care about.
	 */
	recommended_min += pageblock_nr_pages * nr_zones *
			   MIGRATE_PCPTYPES * MIGRATE_PCPTYPES;

	/* don't ever allow to reserve more than 5% of the lowmem */
	recommended_min = min(recommended_min,
			      (unsigned long) nr_free_buffer_pages() / 20);
	recommended_min <<= (PAGE_SHIFT-10);

	if (recommended_min > min_free_kbytes) {
		if (user_min_free_kbytes >= 0)
			pr_info("raising min_free_kbytes from %d to %lu "
				"to help transparent hugepage allocations\n",
				min_free_kbytes, recommended_min);

		min_free_kbytes = recommended_min;
	}
	setup_per_zone_wmarks();
}

static int start_stop_khugepaged(void)
{
	int err = 0;
	if (khugepaged_enabled()) {
		if (!khugepaged_thread)
			khugepaged_thread = kthread_run(khugepaged, NULL,
							"khugepaged");
		if (IS_ERR(khugepaged_thread)) {
			pr_err("khugepaged: kthread_run(khugepaged) failed\n");
			err = PTR_ERR(khugepaged_thread);
			khugepaged_thread = NULL;
			goto fail;
		}

		if (!list_empty(&khugepaged_scan.mm_head))
			wake_up_interruptible(&khugepaged_wait);

		set_recommended_min_free_kbytes();
	} else if (khugepaged_thread) {
		kthread_stop(khugepaged_thread);
		khugepaged_thread = NULL;
	}
fail:
	return err;
}

static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;

struct page *get_huge_zero_page(void)
{
	struct page *zero_page;
retry:
	if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
		return READ_ONCE(huge_zero_page);

	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 NULL;
	}
	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;
	}

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

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));
}

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);
		__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 double_flag_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf,
				enum transparent_hugepage_flag enabled,
				enum transparent_hugepage_flag req_madv)
{
	if (test_bit(enabled, &transparent_hugepage_flags)) {
		VM_BUG_ON(test_bit(req_madv, &transparent_hugepage_flags));
		return sprintf(buf, "[always] madvise never\n");
	} else if (test_bit(req_madv, &transparent_hugepage_flags))
		return sprintf(buf, "always [madvise] never\n");
	else
		return sprintf(buf, "always madvise [never]\n");
}
static ssize_t double_flag_store(struct kobject *kobj,
				 struct kobj_attribute *attr,
				 const char *buf, size_t count,
				 enum transparent_hugepage_flag enabled,
				 enum transparent_hugepage_flag req_madv)
{
	if (!memcmp("always", buf,
		    min(sizeof("always")-1, count))) {
		set_bit(enabled, &transparent_hugepage_flags);
		clear_bit(req_madv, &transparent_hugepage_flags);
	} else if (!memcmp("madvise", buf,
			   min(sizeof("madvise")-1, count))) {
		clear_bit(enabled, &transparent_hugepage_flags);
		set_bit(req_madv, &transparent_hugepage_flags);
	} else if (!memcmp("never", buf,
			   min(sizeof("never")-1, count))) {
		clear_bit(enabled, &transparent_hugepage_flags);
		clear_bit(req_madv, &transparent_hugepage_flags);
	} else
		return -EINVAL;

	return count;
}

static ssize_t enabled_show(struct kobject *kobj,
			    struct kobj_attribute *attr, char *buf)
{
	return double_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_FLAG,
				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
}
static ssize_t enabled_store(struct kobject *kobj,
			     struct kobj_attribute *attr,
			     const char *buf, size_t count)
{
	ssize_t ret;

	ret = double_flag_store(kobj, attr, buf, count,
				TRANSPARENT_HUGEPAGE_FLAG,
				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);

	if (ret > 0) {
		int err;

		mutex_lock(&khugepaged_mutex);
		err = start_stop_khugepaged();
		mutex_unlock(&khugepaged_mutex);

		if (err)
			ret = err;
	}

	return ret;
}
static struct kobj_attribute enabled_attr =
	__ATTR(enabled, 0644, enabled_show, enabled_store);

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

static ssize_t single_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;
}

/*
 * Currently defrag only disables __GFP_NOWAIT for allocation. A blind
 * __GFP_REPEAT is too aggressive, it's never worth swapping tons of
 * memory just to allocate one more hugepage.
 */
static ssize_t defrag_show(struct kobject *kobj,
			   struct kobj_attribute *attr, char *buf)
{
	return double_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
				TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
static ssize_t defrag_store(struct kobject *kobj,
			    struct kobj_attribute *attr,
			    const char *buf, size_t count)
{
	return double_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
				 TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
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_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_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);
#ifdef CONFIG_DEBUG_VM
static ssize_t debug_cow_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf)
{
	return single_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
}
static ssize_t debug_cow_store(struct kobject *kobj,
			       struct kobj_attribute *attr,
			       const char *buf, size_t count)
{
	return single_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
}
static struct kobj_attribute debug_cow_attr =
	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
#endif /* CONFIG_DEBUG_VM */

static struct attribute *hugepage_attr[] = {
	&enabled_attr.attr,
	&defrag_attr.attr,
	&use_zero_page_attr.attr,
#ifdef CONFIG_DEBUG_VM
	&debug_cow_attr.attr,
#endif
	NULL,
};

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

static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
					 struct kobj_attribute *attr,
					 char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs);
}

static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
					  struct kobj_attribute *attr,
					  const char *buf, size_t count)
{
	unsigned long msecs;
	int err;

	err = kstrtoul(buf, 10, &msecs);
	if (err || msecs > UINT_MAX)
		return -EINVAL;

	khugepaged_scan_sleep_millisecs = msecs;
	wake_up_interruptible(&khugepaged_wait);

	return count;
}
static struct kobj_attribute scan_sleep_millisecs_attr =
	__ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show,
	       scan_sleep_millisecs_store);

static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
					  struct kobj_attribute *attr,
					  char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs);
}

static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
					   struct kobj_attribute *attr,
					   const char *buf, size_t count)
{
	unsigned long msecs;
	int err;

	err = kstrtoul(buf, 10, &msecs);
	if (err || msecs > UINT_MAX)
		return -EINVAL;

	khugepaged_alloc_sleep_millisecs = msecs;
	wake_up_interruptible(&khugepaged_wait);

	return count;
}
static struct kobj_attribute alloc_sleep_millisecs_attr =
	__ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show,
	       alloc_sleep_millisecs_store);

static ssize_t pages_to_scan_show(struct kobject *kobj,
				  struct kobj_attribute *attr,
				  char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_pages_to_scan);
}
static ssize_t pages_to_scan_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int err;
	unsigned long pages;

	err = kstrtoul(buf, 10, &pages);
	if (err || !pages || pages > UINT_MAX)
		return -EINVAL;

	khugepaged_pages_to_scan = pages;

	return count;
}
static struct kobj_attribute pages_to_scan_attr =
	__ATTR(pages_to_scan, 0644, pages_to_scan_show,
	       pages_to_scan_store);

static ssize_t pages_collapsed_show(struct kobject *kobj,
				    struct kobj_attribute *attr,
				    char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_pages_collapsed);
}
static struct kobj_attribute pages_collapsed_attr =
	__ATTR_RO(pages_collapsed);

static ssize_t full_scans_show(struct kobject *kobj,
			       struct kobj_attribute *attr,
			       char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_full_scans);
}
static struct kobj_attribute full_scans_attr =
	__ATTR_RO(full_scans);

static ssize_t khugepaged_defrag_show(struct kobject *kobj,
				      struct kobj_attribute *attr, char *buf)
{
	return single_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static ssize_t khugepaged_defrag_store(struct kobject *kobj,
				       struct kobj_attribute *attr,
				       const char *buf, size_t count)
{
	return single_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static struct kobj_attribute khugepaged_defrag_attr =
	__ATTR(defrag, 0644, khugepaged_defrag_show,
	       khugepaged_defrag_store);

/*
 * max_ptes_none controls if khugepaged should collapse hugepages over
 * any unmapped ptes in turn potentially increasing the memory
 * footprint of the vmas. When max_ptes_none is 0 khugepaged will not
 * reduce the available free memory in the system as it
 * runs. Increasing max_ptes_none will instead potentially reduce the
 * free memory in the system during the khugepaged scan.
 */
static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj,
					     struct kobj_attribute *attr,
					     char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_max_ptes_none);
}
static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj,
					      struct kobj_attribute *attr,
					      const char *buf, size_t count)
{
	int err;
	unsigned long max_ptes_none;

	err = kstrtoul(buf, 10, &max_ptes_none);
	if (err || max_ptes_none > HPAGE_PMD_NR-1)
		return -EINVAL;

	khugepaged_max_ptes_none = max_ptes_none;

	return count;
}
static struct kobj_attribute khugepaged_max_ptes_none_attr =
	__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
	       khugepaged_max_ptes_none_store);

static struct attribute *khugepaged_attr[] = {
	&khugepaged_defrag_attr.attr,
	&khugepaged_max_ptes_none_attr.attr,
	&pages_to_scan_attr.attr,
	&pages_collapsed_attr.attr,
	&full_scans_attr.attr,
	&scan_sleep_millisecs_attr.attr,
	&alloc_sleep_millisecs_attr.attr,
	NULL,
};

static struct attribute_group khugepaged_attr_group = {
	.attrs = khugepaged_attr,
	.name = "khugepaged",
};

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()) {
		transparent_hugepage_flags = 0;
		return -EINVAL;
	}

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

	err = khugepaged_slab_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_slab_exit();
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;
}

static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
{
	pmd_t entry;
	entry = mk_pmd(page, prot);
	entry = pmd_mkhuge(entry);
	return entry;
}

static inline struct list_head *page_deferred_list(struct page *page)
{
	/*
	 * ->lru in the tail pages is occupied by compound_head.
	 * Let's use ->mapping + ->index in the second tail page as list_head.
	 */
	return (struct list_head *)&page[2].mapping;
}

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
	 */
	BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);

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

static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long address, pmd_t *pmd,
					struct page *page, gfp_t gfp,
					unsigned int flags)
{
	struct mem_cgroup *memcg;
	pgtable_t pgtable;
	spinlock_t *ptl;
	unsigned long haddr = address & HPAGE_PMD_MASK;

	VM_BUG_ON_PAGE(!PageCompound(page), page);

	if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) {
		put_page(page);
		count_vm_event(THP_FAULT_FALLBACK);
		return VM_FAULT_FALLBACK;
	}

	pgtable = pte_alloc_one(mm, haddr);
	if (unlikely(!pgtable)) {
		mem_cgroup_cancel_charge(page, memcg, true);
		put_page(page);
		return VM_FAULT_OOM;
	}

	clear_huge_page(page, haddr, 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);

	ptl = pmd_lock(mm, pmd);
	if (unlikely(!pmd_none(*pmd))) {
		spin_unlock(ptl);
		mem_cgroup_cancel_charge(page, memcg, true);
		put_page(page);
		pte_free(mm, pgtable);
	} else {
		pmd_t entry;

		/* Deliver the page fault to userland */
		if (userfaultfd_missing(vma)) {
			int ret;

			spin_unlock(ptl);
			mem_cgroup_cancel_charge(page, memcg, true);
			put_page(page);
			pte_free(mm, pgtable);
			ret = handle_userfault(vma, address, flags,
					       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);
		mem_cgroup_commit_charge(page, memcg, false, true);
		lru_cache_add_active_or_unevictable(page, vma);
		pgtable_trans_huge_deposit(mm, pmd, pgtable);
		set_pmd_at(mm, haddr, pmd, entry);
		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
		atomic_long_inc(&mm->nr_ptes);
		spin_unlock(ptl);
		count_vm_event(THP_FAULT_ALLOC);
	}

	return 0;
}

static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
{
	return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_RECLAIM)) | extra_gfp;
}

/* Caller must hold page table lock. */
static bool 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 false;
	entry = mk_pmd(zero_page, vma->vm_page_prot);
	entry = pmd_mkhuge(entry);
	pgtable_trans_huge_deposit(mm, pmd, pgtable);
	set_pmd_at(mm, haddr, pmd, entry);
	atomic_long_inc(&mm->nr_ptes);
	return true;
}

int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
			       unsigned long address, pmd_t *pmd,
			       unsigned int flags)
{
	gfp_t gfp;
	struct page *page;
	unsigned long haddr = address & HPAGE_PMD_MASK;

	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
		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 (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm) &&
			transparent_hugepage_use_zero_page()) {
		spinlock_t *ptl;
		pgtable_t pgtable;
		struct page *zero_page;
		bool set;
		int ret;
		pgtable = pte_alloc_one(mm, haddr);
		if (unlikely(!pgtable))
			return VM_FAULT_OOM;
		zero_page = get_huge_zero_page();
		if (unlikely(!zero_page)) {
			pte_free(mm, pgtable);
			count_vm_event(THP_FAULT_FALLBACK);
			return VM_FAULT_FALLBACK;
		}
		ptl = pmd_lock(mm, pmd);
		ret = 0;
		set = false;
		if (pmd_none(*pmd)) {
			if (userfaultfd_missing(vma)) {
				spin_unlock(ptl);
				ret = handle_userfault(vma, address, flags,
						       VM_UFFD_MISSING);
				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
			} else {
				set_huge_zero_page(pgtable, mm, vma,
						   haddr, pmd,
						   zero_page);
				spin_unlock(ptl);
				set = true;
			}
		} else
			spin_unlock(ptl);
		if (!set) {
			pte_free(mm, pgtable);
			put_huge_zero_page();
		}
		return ret;
	}
	gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0);
	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(mm, vma, address, pmd, page, gfp,
					    flags);
}

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

	ptl = pmd_lock(mm, pmd);
	entry = pmd_mkhuge(pfn_pmd(pfn, prot));
	if (write) {
		entry = pmd_mkyoung(pmd_mkdirty(entry));
		entry = maybe_pmd_mkwrite(entry, vma);
	}
	set_pmd_at(mm, addr, pmd, entry);
	update_mmu_cache_pmd(vma, addr, pmd);
	spin_unlock(ptl);
}

int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
			pmd_t *pmd, unsigned long pfn, bool write)
{
	pgprot_t pgprot = vma->vm_page_prot;
	/*
	 * 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));
	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return VM_FAULT_SIGBUS;
	if (track_pfn_insert(vma, &pgprot, pfn))
		return VM_FAULT_SIGBUS;
	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
	return VM_FAULT_NOPAGE;
}

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 *vma)
{
	spinlock_t *dst_ptl, *src_ptl;
	struct page *src_page;
	pmd_t pmd;
	pgtable_t pgtable;
	int ret;

	ret = -ENOMEM;
	pgtable = pte_alloc_one(dst_mm, addr);
	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;
	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