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.
 */

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

/*
 * By default transparent hugepage support is enabled for all mappings
 * and khugepaged scans all mappings. Defrag is only invoked by
 * khugepaged hugepage allocations and by page faults inside
 * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived
 * 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);

/* 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 mm_slots_hash_init(void);
static int khugepaged_slab_init(void);
static void khugepaged_slab_free(void);

#define MM_SLOTS_HASH_HEADS 1024
static struct hlist_head *mm_slots_hash __read_mostly;
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 int set_recommended_min_free_kbytes(void)
{
	struct zone *zone;
	int nr_zones = 0;
	unsigned long recommended_min;
	extern int min_free_kbytes;

	if (!khugepaged_enabled())
		return 0;

	for_each_populated_zone(zone)
		nr_zones++;

	/* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */
	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)
		min_free_kbytes = recommended_min;
	setup_per_zone_wmarks();
	return 0;
}
late_initcall(set_recommended_min_free_kbytes);

static int start_khugepaged(void)
{
	int err = 0;
	if (khugepaged_enabled()) {
		if (!khugepaged_thread)
			khugepaged_thread = kthread_run(khugepaged, NULL,
							"khugepaged");
		if (unlikely(IS_ERR(khugepaged_thread))) {
			printk(KERN_ERR
			       "khugepaged: kthread_run(khugepaged) failed\n");
			err = PTR_ERR(khugepaged_thread);
			khugepaged_thread = NULL;
		}

		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;
	}

	return err;
}

#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_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);

#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,
#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 = strict_strtoul(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 = strict_strtoul(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 = strict_strtoul(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 = strict_strtoul(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)) {
		printk(KERN_ERR "hugepage: failed kobject create\n");
		return -ENOMEM;
	}

	err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
	if (err) {
		printk(KERN_ERR "hugepage: failed register hugeage group\n");
		goto delete_obj;
	}

	err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
	if (err) {
		printk(KERN_ERR "hugepage: failed register hugeage 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)
		return err;

	err = khugepaged_slab_init();
	if (err)
		goto out;

	err = mm_slots_hash_init();
	if (err) {
		khugepaged_slab_free();
		goto out;
	}

	/*
	 * 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;

	start_khugepaged();

	return 0;
out:
	hugepage_exit_sysfs(hugepage_kobj);
	return err;
}
module_init(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)
		printk(KERN_WARNING
		       "transparent_hugepage= cannot parse, ignored\n");
	return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);

static inline 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, struct vm_area_struct *vma)
{
	pmd_t entry;
	entry = mk_pmd(page, vma->vm_page_prot);
	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
	entry = pmd_mkhuge(entry);
	return entry;
}

static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long haddr, pmd_t *pmd,
					struct page *page)
{
	pgtable_t pgtable;

	VM_BUG_ON(!PageCompound(page));
	pgtable = pte_alloc_one(mm, haddr);
	if (unlikely(!pgtable))
		return VM_FAULT_OOM;

	clear_huge_page(page, haddr, HPAGE_PMD_NR);
	__SetPageUptodate(page);

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_none(*pmd))) {
		spin_unlock(&mm->page_table_lock);
		mem_cgroup_uncharge_page(page);
		put_page(page);
		pte_free(mm, pgtable);
	} else {
		pmd_t entry;
		entry = mk_huge_pmd(page, vma);
		/*
		 * The spinlocking to take the lru_lock inside
		 * page_add_new_anon_rmap() acts as a full memory
		 * barrier to be sure clear_huge_page writes become
		 * visible after the set_pmd_at() write.
		 */
		page_add_new_anon_rmap(page, vma, haddr);
		set_pmd_at(mm, haddr, pmd, entry);
		pgtable_trans_huge_deposit(mm, pgtable);
		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
		mm->nr_ptes++;
		spin_unlock(&mm->page_table_lock);
	}

	return 0;
}

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

static inline struct page *alloc_hugepage_vma(int defrag,
					      struct vm_area_struct *vma,
					      unsigned long haddr, int nd,
					      gfp_t extra_gfp)
{
	return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp),
			       HPAGE_PMD_ORDER, vma, haddr, nd);
}

#ifndef CONFIG_NUMA
static inline struct page *alloc_hugepage(int defrag)
{
	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
			   HPAGE_PMD_ORDER);
}
#endif

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

	if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
		if (unlikely(anon_vma_prepare(vma)))
			return VM_FAULT_OOM;
		if (unlikely(khugepaged_enter(vma)))
			return VM_FAULT_OOM;
		page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
					  vma, haddr, numa_node_id(), 0);
		if (unlikely(!page)) {
			count_vm_event(THP_FAULT_FALLBACK);
			goto out;
		}
		count_vm_event(THP_FAULT_ALLOC);
		if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
			put_page(page);
			goto out;
		}
		if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd,
							  page))) {
			mem_cgroup_uncharge_page(page);
			put_page(page);
			goto out;
		}

		return 0;
	}
out:
	/*
	 * Use __pte_alloc instead of pte_alloc_map, because we can't
	 * run pte_offset_map on the pmd, if an huge pmd could
	 * materialize from under us from a different thread.
	 */
	if (unlikely(__pte_alloc(mm, vma, pmd, address)))
		return VM_FAULT_OOM;
	/* if an huge pmd materialized from under us just retry later */
	if (unlikely(pmd_trans_huge(*pmd)))
		return 0;
	/*
	 * A regular pmd is established and it can't morph into a huge pmd
	 * from under us anymore at this point because we hold the mmap_sem
	 * read mode and khugepaged takes it in write mode. So now it's
	 * safe to run pte_offset_map().
	 */
	pte = pte_offset_map(pmd, address);
	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}

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)
{
	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;

	spin_lock(&dst_mm->page_table_lock);
	spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING);

	ret = -EAGAIN;
	pmd = *src_pmd;
	if (unlikely(!pmd_trans_huge(pmd))) {
		pte_free(dst_mm, pgtable);
		goto out_unlock;
	}
	if (unlikely(pmd_trans_splitting(pmd))) {
		/* split huge page running from under us */
		spin_unlock(&src_mm->page_table_lock);
		spin_unlock(&dst_mm->page_table_lock);
		pte_free(dst_mm, pgtable);

		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
		goto out;
	}
	src_page = pmd_page(pmd);
	VM_BUG_ON(!PageHead(src_page));
	get_page(src_page);
	page_dup_rmap(src_page);
	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);

	pmdp_set_wrprotect(src_mm, addr, src_pmd);
	pmd = pmd_mkold(pmd_wrprotect(pmd));
	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
	pgtable_trans_huge_deposit(dst_mm, pgtable);
	dst_mm->nr_ptes++;

	ret = 0;
out_unlock:
	spin_unlock(&src_mm->page_table_lock);
	spin_unlock(&dst_mm->page_table_lock);
out:
	return ret;
}

void huge_pmd_set_accessed(struct mm_struct *mm,
			   struct vm_area_struct *vma,
			   unsigned long address,
			   pmd_t *pmd, pmd_t orig_pmd,
			   int dirty)
{
	pmd_t entry;
	unsigned long haddr;

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto unlock;

	entry = pmd_mkyoung(orig_pmd);
	haddr = address & HPAGE_PMD_MASK;
	if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
		update_mmu_cache_pmd(vma, address, pmd);

unlock:
	spin_unlock(&mm->page_table_lock);
}

static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long address,
					pmd_t *pmd, pmd_t orig_pmd,
					struct page *page,
					unsigned long haddr)
{
	pgtable_t pgtable;
	pmd_t _pmd;
	int ret = 0, i;
	struct page **pages;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */

	pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR,
			GFP_KERNEL);
	if (unlikely(!pages)) {
		ret |= VM_FAULT_OOM;
		goto out;
	}

	for (i = 0; i < HPAGE_PMD_NR; i++) {
		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
					       __GFP_OTHER_NODE,
					       vma, address, page_to_nid(page));
		if (unlikely(!pages[i] ||
			     mem_cgroup_newpage_charge(pages[i], mm,
						       GFP_KERNEL))) {
			if (pages[i])
				put_page(pages[i]);
			mem_cgroup_uncharge_start();
			while (--i >= 0) {
				mem_cgroup_uncharge_page(pages[i]);
				put_page(pages[i]);
			}
			mem_cgroup_uncharge_end();
			kfree(pages);
			ret |= VM_FAULT_OOM;
			goto out;
		}
	}

	for (i = 0; i < HPAGE_PMD_NR; i++) {
		copy_user_highpage(pages[i], page + i,
				   haddr + PAGE_SIZE * i, vma);
		__SetPageUptodate(pages[i]);
		cond_resched();
	}

	mmun_start = haddr;
	mmun_end   = haddr + HPAGE_PMD_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto out_free_pages;
	VM_BUG_ON(!PageHead(page));

	pmdp_clear_flush(vma, haddr, pmd);
	/* leave pmd empty until pte is filled */

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

	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
		pte_t *pte, entry;
		entry = mk_pte(pages[i], vma->vm_page_prot);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		page_add_new_anon_rmap(pages[i], vma, haddr);
		pte = pte_offset_map(&_pmd, haddr);
		VM_BUG_ON(!pte_none(*pte));
		set_pte_at(mm, haddr, pte, entry);
		pte_unmap(pte);
	}
	kfree(pages);

	smp_wmb(); /* make pte visible before pmd */
	pmd_populate(mm, pmd, pgtable);
	page_remove_rmap(page);
	spin_unlock(&mm->page_table_lock);

	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

	ret |= VM_FAULT_WRITE;
	put_page(page);

out:
	return ret;

out_free_pages:
	spin_unlock(&mm->page_table_lock);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	mem_cgroup_uncharge_start();
	for (i = 0; i < HPAGE_PMD_NR; i++) {
		mem_cgroup_uncharge_page(pages[i]);
		put_page(pages[i]);
	}
	mem_cgroup_uncharge_end();
	kfree(pages);
	goto out;
}

int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
{
	int ret = 0;
	struct page *page, *new_page;
	unsigned long haddr;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */

	VM_BUG_ON(!vma->anon_vma);
	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto out_unlock;

	page = pmd_page(orig_pmd);
	VM_BUG_ON(!PageCompound(page) || !PageHead(page));
	haddr = address & HPAGE_PMD_MASK;
	if (page_mapcount(page) == 1) {
		pmd_t entry;
		entry = pmd_mkyoung(orig_pmd);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		if (pmdp_set_access_flags(vma, haddr, pmd, entry,  1))
			update_mmu_cache_pmd(vma, address, pmd);
		ret |= VM_FAULT_WRITE;
		goto out_unlock;
	}
	get_page(page);
	spin_unlock(&mm->page_table_lock);

	if (transparent_hugepage_enabled(vma) &&
	    !transparent_hugepage_debug_cow())
		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
					      vma, haddr, numa_node_id(), 0);
	else
		new_page = NULL;

	if (unlikely(!new_page)) {
		count_vm_event(THP_FAULT_FALLBACK);
		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
						   pmd, orig_pmd, page, haddr);
		if (ret & VM_FAULT_OOM)
			split_huge_page(page);
		put_page(page);
		goto out;
	}
	count_vm_event(THP_FAULT_ALLOC);

	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
		put_page(new_page);
		split_huge_page(page);
		put_page(page);
		ret |= VM_FAULT_OOM;
		goto out;
	}

	copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
	__SetPageUptodate(new_page);

	mmun_start = haddr;
	mmun_end   = haddr + HPAGE_PMD_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	spin_lock(&mm->page_table_lock);
	put_page(page);
	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
		spin_unlock(&mm->page_table_lock);
		mem_cgroup_uncharge_page(new_page);
		put_page(new_page);
		goto out_mn;
	} else {
		pmd_t entry;
		VM_BUG_ON(!PageHead(page));
		entry = mk_huge_pmd(new_page, vma);
		pmdp_clear_flush(vma, haddr, pmd);
		page_add_new_anon_rmap(new_page, vma, haddr);
		set_pmd_at(mm, haddr, pmd, entry);
		update_mmu_cache_pmd(vma, address, pmd);
		page_remove_rmap(page);
		put_page(page);
		ret |= VM_FAULT_WRITE;
	}
	spin_unlock(&mm->page_table_lock);
out_mn:
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
	return ret;
out_unlock:
	spin_unlock(&mm->page_table_lock);
	return ret;
}