linux/mm/hugetlb.c

/*
 * Generic hugetlb support.
 * (C) Nadia Yvette Chambers, April 2004
 */
#include <linux/list.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/mmu_notifier.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/compiler.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/page-isolation.h>
#include <linux/jhash.h>

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>

#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/node.h>
#include "internal.h"

unsigned long hugepages_treat_as_movable;

int hugetlb_max_hstate __read_mostly;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];

__initdata LIST_HEAD(huge_boot_pages);

/* for command line parsing */
static struct hstate * __initdata parsed_hstate;
static unsigned long __initdata default_hstate_max_huge_pages;
static unsigned long __initdata default_hstate_size;

/*
 * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
 * free_huge_pages, and surplus_huge_pages.
 */
DEFINE_SPINLOCK(hugetlb_lock);

/*
 * Serializes faults on the same logical page.  This is used to
 * prevent spurious OOMs when the hugepage pool is fully utilized.
 */
static int num_fault_mutexes;
static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp;

static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
{
	bool free = (spool->count == 0) && (spool->used_hpages == 0);

	spin_unlock(&spool->lock);

	/* If no pages are used, and no other handles to the subpool
	 * remain, free the subpool the subpool remain */
	if (free)
		kfree(spool);
}

struct hugepage_subpool *hugepage_new_subpool(long nr_blocks)
{
	struct hugepage_subpool *spool;

	spool = kmalloc(sizeof(*spool), GFP_KERNEL);
	if (!spool)
		return NULL;

	spin_lock_init(&spool->lock);
	spool->count = 1;
	spool->max_hpages = nr_blocks;
	spool->used_hpages = 0;

	return spool;
}

void hugepage_put_subpool(struct hugepage_subpool *spool)
{
	spin_lock(&spool->lock);
	BUG_ON(!spool->count);
	spool->count--;
	unlock_or_release_subpool(spool);
}

static int hugepage_subpool_get_pages(struct hugepage_subpool *spool,
				      long delta)
{
	int ret = 0;

	if (!spool)
		return 0;

	spin_lock(&spool->lock);
	if ((spool->used_hpages + delta) <= spool->max_hpages) {
		spool->used_hpages += delta;
	} else {
		ret = -ENOMEM;
	}
	spin_unlock(&spool->lock);

	return ret;
}

static void hugepage_subpool_put_pages(struct hugepage_subpool *spool,
				       long delta)
{
	if (!spool)
		return;

	spin_lock(&spool->lock);
	spool->used_hpages -= delta;
	/* If hugetlbfs_put_super couldn't free spool due to
	* an outstanding quota reference, free it now. */
	unlock_or_release_subpool(spool);
}

static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
{
	return HUGETLBFS_SB(inode->i_sb)->spool;
}

static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
{
	return subpool_inode(file_inode(vma->vm_file));
}

/*
 * Region tracking -- allows tracking of reservations and instantiated pages
 *                    across the pages in a mapping.
 *
 * The region data structures are embedded into a resv_map and
 * protected by a resv_map's lock
 */
struct file_region {
	struct list_head link;
	long from;
	long to;
};

static long region_add(struct resv_map *resv, long f, long t)
{
	struct list_head *head = &resv->regions;
	struct file_region *rg, *nrg, *trg;

	spin_lock(&resv->lock);
	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;

	/* Check for and consume any regions we now overlap with. */
	nrg = rg;
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			break;

		/* If this area reaches higher then extend our area to
		 * include it completely.  If this is not the first area
		 * which we intend to reuse, free it. */
		if (rg->to > t)
			t = rg->to;
		if (rg != nrg) {
			list_del(&rg->link);
			kfree(rg);
		}
	}
	nrg->from = f;
	nrg->to = t;
	spin_unlock(&resv->lock);
	return 0;
}

static long region_chg(struct resv_map *resv, long f, long t)
{
	struct list_head *head = &resv->regions;
	struct file_region *rg, *nrg = NULL;
	long chg = 0;

retry:
	spin_lock(&resv->lock);
	/* Locate the region we are before or in. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* If we are below the current region then a new region is required.
	 * Subtle, allocate a new region at the position but make it zero
	 * size such that we can guarantee to record the reservation. */
	if (&rg->link == head || t < rg->from) {
		if (!nrg) {
			spin_unlock(&resv->lock);
			nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
			if (!nrg)
				return -ENOMEM;

			nrg->from = f;
			nrg->to   = f;
			INIT_LIST_HEAD(&nrg->link);
			goto retry;
		}

		list_add(&nrg->link, rg->link.prev);
		chg = t - f;
		goto out_nrg;
	}

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;
	chg = t - f;

	/* Check for and consume any regions we now overlap with. */
	list_for_each_entry(rg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			goto out;

		/* We overlap with this area, if it extends further than
		 * us then we must extend ourselves.  Account for its
		 * existing reservation. */
		if (rg->to > t) {
			chg += rg->to - t;
			t = rg->to;
		}
		chg -= rg->to - rg->from;
	}

out:
	spin_unlock(&resv->lock);
	/*  We already know we raced and no longer need the new region */
	kfree(nrg);
	return chg;
out_nrg:
	spin_unlock(&resv->lock);
	return chg;
}

static long region_truncate(struct resv_map *resv, long end)
{
	struct list_head *head = &resv->regions;
	struct file_region *rg, *trg;
	long chg = 0;

	spin_lock(&resv->lock);
	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (end <= rg->to)
			break;
	if (&rg->link == head)
		goto out;

	/* If we are in the middle of a region then adjust it. */
	if (end > rg->from) {
		chg = rg->to - end;
		rg->to = end;
		rg = list_entry(rg->link.next, typeof(*rg), link);
	}

	/* Drop any remaining regions. */
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		chg += rg->to - rg->from;
		list_del(&rg->link);
		kfree(rg);
	}

out:
	spin_unlock(&resv->lock);
	return chg;
}

static long region_count(struct resv_map *resv, long f, long t)
{
	struct list_head *head = &resv->regions;
	struct file_region *rg;
	long chg = 0;

	spin_lock(&resv->lock);
	/* Locate each segment we overlap with, and count that overlap. */
	list_for_each_entry(rg, head, link) {
		long seg_from;
		long seg_to;

		if (rg->to <= f)
			continue;
		if (rg->from >= t)
			break;

		seg_from = max(rg->from, f);
		seg_to = min(rg->to, t);

		chg += seg_to - seg_from;
	}
	spin_unlock(&resv->lock);

	return chg;
}

/*
 * Convert the address within this vma to the page offset within
 * the mapping, in pagecache page units; huge pages here.
 */
static pgoff_t vma_hugecache_offset(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	return ((address - vma->vm_start) >> huge_page_shift(h)) +
			(vma->vm_pgoff >> huge_page_order(h));
}

pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
				     unsigned long address)
{
	return vma_hugecache_offset(hstate_vma(vma), vma, address);
}

/*
 * Return the size of the pages allocated when backing a VMA. In the majority
 * cases this will be same size as used by the page table entries.
 */
unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
	struct hstate *hstate;

	if (!is_vm_hugetlb_page(vma))
		return PAGE_SIZE;

	hstate = hstate_vma(vma);

	return 1UL << huge_page_shift(hstate);
}
EXPORT_SYMBOL_GPL(vma_kernel_pagesize);

/*
 * Return the page size being used by the MMU to back a VMA. In the majority
 * of cases, the page size used by the kernel matches the MMU size. On
 * architectures where it differs, an architecture-specific version of this
 * function is required.
 */
#ifndef vma_mmu_pagesize
unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
	return vma_kernel_pagesize(vma);
}
#endif

/*
 * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
 * bits of the reservation map pointer, which are always clear due to
 * alignment.
 */
#define HPAGE_RESV_OWNER    (1UL << 0)
#define HPAGE_RESV_UNMAPPED (1UL << 1)
#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED)

/*
 * These helpers are used to track how many pages are reserved for
 * faults in a MAP_PRIVATE mapping. Only the process that called mmap()
 * is guaranteed to have their future faults succeed.
 *
 * With the exception of reset_vma_resv_huge_pages() which is called at fork(),
 * the reserve counters are updated with the hugetlb_lock held. It is safe
 * to reset the VMA at fork() time as it is not in use yet and there is no
 * chance of the global counters getting corrupted as a result of the values.
 *
 * The private mapping reservation is represented in a subtly different
 * manner to a shared mapping.  A shared mapping has a region map associated
 * with the underlying file, this region map represents the backing file
 * pages which have ever had a reservation assigned which this persists even
 * after the page is instantiated.  A private mapping has a region map
 * associated with the original mmap which is attached to all VMAs which
 * reference it, this region map represents those offsets which have consumed
 * reservation ie. where pages have been instantiated.
 */
static unsigned long get_vma_private_data(struct vm_area_struct *vma)
{
	return (unsigned long)vma->vm_private_data;
}

static void set_vma_private_data(struct vm_area_struct *vma,
							unsigned long value)
{
	vma->vm_private_data = (void *)value;
}

struct resv_map *resv_map_alloc(void)
{
	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
	if (!resv_map)
		return NULL;

	kref_init(&resv_map->refs);
	spin_lock_init(&resv_map->lock);
	INIT_LIST_HEAD(&resv_map->regions);

	return resv_map;
}

void resv_map_release(struct kref *ref)
{
	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);

	/* Clear out any active regions before we release the map. */
	region_truncate(resv_map, 0);
	kfree(resv_map);
}

static inline struct resv_map *inode_resv_map(struct inode *inode)
{
	return inode->i_mapping->private_data;
}

static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (vma->vm_flags & VM_MAYSHARE) {
		struct address_space *mapping = vma->vm_file->f_mapping;
		struct inode *inode = mapping->host;

		return inode_resv_map(inode);

	} else {
		return (struct resv_map *)(get_vma_private_data(vma) &
							~HPAGE_RESV_MASK);
	}
}

static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);

	set_vma_private_data(vma, (get_vma_private_data(vma) &
				HPAGE_RESV_MASK) | (unsigned long)map);
}

static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);

	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
}

static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));

	return (get_vma_private_data(vma) & flag) != 0;
}

/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_MAYSHARE))
		vma->vm_private_data = (void *)0;
}

/* Returns true if the VMA has associated reserve pages */
static int vma_has_reserves(struct vm_area_struct *vma, long chg)
{
	if (vma->vm_flags & VM_NORESERVE) {
		/*
		 * This address is already reserved by other process(chg == 0),
		 * so, we should decrement reserved count. Without decrementing,
		 * reserve count remains after releasing inode, because this
		 * allocated page will go into page cache and is regarded as
		 * coming from reserved pool in releasing step.  Currently, we
		 * don't have any other solution to deal with this situation
		 * properly, so add work-around here.
		 */
		if (vma->vm_flags & VM_MAYSHARE && chg == 0)
			return 1;
		else
			return 0;
	}

	/* Shared mappings always use reserves */
	if (vma->vm_flags & VM_MAYSHARE)
		return 1;

	/*
	 * Only the process that called mmap() has reserves for
	 * private mappings.
	 */
	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		return 1;

	return 0;
}

static void enqueue_huge_page(struct hstate *h, struct page *page)
{
	int nid = page_to_nid(page);
	list_move(&page->lru, &h->hugepage_freelists[nid]);
	h->free_huge_pages++;
	h->free_huge_pages_node[nid]++;
}

static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
		if (!is_migrate_isolate_page(page))
			break;
	/*
	 * if 'non-isolated free hugepage' not found on the list,
	 * the allocation fails.
	 */
	if (&h->hugepage_freelists[nid] == &page->lru)
		return NULL;
	list_move(&page->lru, &h->hugepage_activelist);
	set_page_refcounted(page);
	h->free_huge_pages--;
	h->free_huge_pages_node[nid]--;
	return page;
}

/* Movability of hugepages depends on migration support. */
static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
	if (hugepages_treat_as_movable || hugepage_migration_supported(h))
		return GFP_HIGHUSER_MOVABLE;
	else
		return GFP_HIGHUSER;
}

static struct page *dequeue_huge_page_vma(struct hstate *h,
				struct vm_area_struct *vma,
				unsigned long address, int avoid_reserve,
				long chg)
{
	struct page *page = NULL;
	struct mempolicy *mpol;
	nodemask_t *nodemask;
	struct zonelist *zonelist;
	struct zone *zone;
	struct zoneref *z;
	unsigned int cpuset_mems_cookie;

	/*
	 * A child process with MAP_PRIVATE mappings created by their parent
	 * have no page reserves. This check ensures that reservations are
	 * not "stolen". The child may still get SIGKILLed
	 */
	if (!vma_has_reserves(vma, chg) &&
			h->free_huge_pages - h->resv_huge_pages == 0)
		goto err;

	/* If reserves cannot be used, ensure enough pages are in the pool */
	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
		goto err;

retry_cpuset:
	cpuset_mems_cookie = read_mems_allowed_begin();
	zonelist = huge_zonelist(vma, address,
					htlb_alloc_mask(h), &mpol, &nodemask);

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
						MAX_NR_ZONES - 1, nodemask) {
		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) {
			page = dequeue_huge_page_node(h, zone_to_nid(zone));
			if (page) {
				if (avoid_reserve)
					break;
				if (!vma_has_reserves(vma, chg))
					break;

				SetPagePrivate(page);
				h->resv_huge_pages--;
				break;
			}
		}
	}

	mpol_cond_put(mpol);
	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
		goto retry_cpuset;
	return page;

err:
	return NULL;
}

/*
 * common helper functions for hstate_next_node_to_{alloc|free}.
 * We may have allocated or freed a huge page based on a different
 * nodes_allowed previously, so h->next_node_to_{alloc|free} might
 * be outside of *nodes_allowed.  Ensure that we use an allowed
 * node for alloc or free.
 */
static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
{
	nid = next_node(nid, *nodes_allowed);
	if (nid == MAX_NUMNODES)
		nid = first_node(*nodes_allowed);
	VM_BUG_ON(nid >= MAX_NUMNODES);

	return nid;
}

static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
{
	if (!node_isset(nid, *nodes_allowed))
		nid = next_node_allowed(nid, nodes_allowed);
	return nid;
}

/*
 * returns the previously saved node ["this node"] from which to
 * allocate a persistent huge page for the pool and advance the
 * next node from which to allocate, handling wrap at end of node
 * mask.
 */
static int hstate_next_node_to_alloc(struct hstate *h,
					nodemask_t *nodes_allowed)
{
	int nid;

	VM_BUG_ON(!nodes_allowed);

	nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
	h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);

	return nid;
}

/*
 * helper for free_pool_huge_page() - return the previously saved
 * node ["this node"] from which to free a huge page.  Advance the
 * next node id whether or not we find a free huge page to free so
 * that the next attempt to free addresses the next node.
 */
static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
{
	int nid;

	VM_BUG_ON(!nodes_allowed);

	nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
	h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);

	return nid;
}

#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask)		\
	for (nr_nodes = nodes_weight(*mask);				\
		nr_nodes > 0 &&						\
		((node = hstate_next_node_to_alloc(hs, mask)) || 1);	\
		nr_nodes--)

#define for_each_node_mask_to_free(hs, nr_nodes, node, mask)		\
	for (nr_nodes = nodes_weight(*mask);				\
		nr_nodes > 0 &&						\
		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
		nr_nodes--)

#if defined(CONFIG_CMA) && defined(CONFIG_X86_64)
static void destroy_compound_gigantic_page(struct page *page,
					unsigned long order)
{
	int i;
	int nr_pages = 1 << order;
	struct page *p = page + 1;

	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		__ClearPageTail(p);
		set_page_refcounted(p);
		p->first_page = NULL;
	}

	set_compound_order(page, 0);
	__ClearPageHead(page);
}

static void free_gigantic_page(struct page *page, unsigned order)
{
	free_contig_range(page_to_pfn(page), 1 << order);
}

static int __alloc_gigantic_page(unsigned long start_pfn,
				unsigned long nr_pages)
{
	unsigned long end_pfn = start_pfn + nr_pages;
	return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
}

static bool pfn_range_valid_gigantic(unsigned long start_pfn,
				unsigned long nr_pages)
{
	unsigned long i, end_pfn = start_pfn + nr_pages;
	struct page *page;

	for (i = start_pfn; i < end_pfn; i++) {
		if (!pfn_valid(i))
			return false;

		page = pfn_to_page(i);

		if (PageReserved(page))
			return false;

		if (page_count(page) > 0)
			return false;

		if (PageHuge(page))
			return false;
	}

	return true;
}

static bool zone_spans_last_pfn(const struct zone *zone,
			unsigned long start_pfn, unsigned long nr_pages)
{
	unsigned long last_pfn = start_pfn + nr_pages - 1;
	return zone_spans_pfn(zone, last_pfn);
}

static struct page *alloc_gigantic_page(int nid, unsigned order)
{
	unsigned long nr_pages = 1 << order;
	unsigned long ret, pfn, flags;
	struct zone *z;

	z = NODE_DATA(nid)->node_zones;
	for (; z - NODE_DATA(nid)->node_zones < MAX_NR_ZONES; z++) {
		spin_lock_irqsave(&z->lock, flags);

		pfn = ALIGN(z->zone_start_pfn, nr_pages);
		while (zone_spans_last_pfn(z, pfn, nr_pages)) {
			if (pfn_range_valid_gigantic(pfn, nr_pages)) {
				/*
				 * We release the zone lock here because
				 * alloc_contig_range() will also lock the zone
				 * at some point. If there's an allocation
				 * spinning on this lock, it may win the race
				 * and cause alloc_contig_range() to fail...
				 */
				spin_unlock_irqrestore(&z->lock, flags);
				ret = __alloc_gigantic_page(pfn, nr_pages);
				if (!ret)
					return pfn_to_page(pfn);
				spin_lock_irqsave(&z->lock, flags);
			}
			pfn += nr_pages;
		}

		spin_unlock_irqrestore(&z->lock, flags);
	}

	return NULL;
}

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
static void prep_compound_gigantic_page(struct page *page, unsigned long order);

static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid)
{
	struct page *page;

	page = alloc_gigantic_page(nid, huge_page_order(h));
	if (page) {
		prep_compound_gigantic_page(page, huge_page_order(h));
		prep_new_huge_page(h, page, nid);
	}

	return page;
}

static int alloc_fresh_gigantic_page(struct hstate *h,
				nodemask_t *nodes_allowed)
{
	struct page *page = NULL;
	int nr_nodes, node;

	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
		page = alloc_fresh_gigantic_page_node(h, node);
		if (page)
			return 1;
	}

	return 0;
}

static inline bool gigantic_page_supported(void) { return true; }
#else
static inline bool gigantic_page_supported(void) { return false; }
static inline void free_gigantic_page(struct page *page, unsigned order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
						unsigned long order) { }
static inline int alloc_fresh_gigantic_page(struct hstate *h,
					nodemask_t *nodes_allowed) { return 0; }
#endif

static void update_and_free_page(struct hstate *h, struct page *page)
{
	int i;

	if (hstate_is_gigantic(h) && !gigantic_page_supported())
		return;

	h->nr_huge_pages--;
	h->nr_huge_pages_node[page_to_nid(page)]--;
	for (i = 0; i < pages_per_huge_page(h); i++) {
		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
				1 << PG_referenced | 1 << PG_dirty |
				1 << PG_active | 1 << PG_private |
				1 << PG_writeback);
	}
	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
	set_compound_page_dtor(page, NULL);
	set_page_refcounted(page);
	if (hstate_is_gigantic(h)) {
		destroy_compound_gigantic_page(page, huge_page_order(h));
		free_gigantic_page(page, huge_page_order(h));
	} else {
		arch_release_hugepage(page);
		__free_pages(page, huge_page_order(h));
	}
}

struct hstate *size_to_hstate(unsigned long size)
{
	struct hstate *h;

	for_each_hstate(h) {
		if (huge_page_size(h) == size)
			return h;
	}
	return NULL;
}

void free_huge_page(struct page *page)
{
	/*
	 * Can't pass hstate in here because it is called from the
	 * compound page destructor.
	 */
	struct hstate *h = page_hstate(page);
	int nid = page_to_nid(page);
	struct hugepage_subpool *spool =
		(struct hugepage_subpool *)page_private(page);
	bool restore_reserve;

	set_page_private(page, 0);
	page->mapping = NULL;
	BUG_ON(page_count(page));
	BUG_ON(page_mapcount(page));
	restore_reserve = PagePrivate(page);
	ClearPagePrivate(page);

	spin_lock(&hugetlb_lock);
	hugetlb_cgroup_uncharge_page(hstate_index(h),
				     pages_per_huge_page(h), page);
	if (restore_reserve)
		h->resv_huge_pages++;

	if (h->surplus_huge_pages_node[nid]) {
		/* remove the page from active list */
		list_del(&page->lru);
		update_and_free_page(h, page);
		h->surplus_huge_pages--;
		h->surplus_huge_pages_node[nid]--;
	} else {
		arch_clear_hugepage_flags(page);
		enqueue_huge_page(h, page);
	}
	spin_unlock(&hugetlb_lock);
	hugepage_subpool_put_pages(spool, 1);
}

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
	INIT_LIST_HEAD(&page->lru);
	set_compound_page_dtor(page, free_huge_page);
	spin_lock(&hugetlb_lock);
	set_hugetlb_cgroup(page, NULL);
	h->nr_huge_pages++;
	h->nr_huge_pages_node[nid]++;
	spin_unlock(&hugetlb_lock);
	put_page(page); /* free it into the hugepage allocator */
}

static void prep_compound_gigantic_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;
	struct page *p = page + 1;

	/* we rely on prep_new_huge_page to set the destructor */
	set_compound_order(page, order);
	__SetPageHead(page);
	__ClearPageReserved(page);
	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		__SetPageTail(p);
		/*
		 * For gigantic hugepages allocated through bootmem at
		 * boot, it's safer to be consistent with the not-gigantic
		 * hugepages and clear the PG_reserved bit from all tail pages
		 * too.  Otherwse drivers using get_user_pages() to access tail
		 * pages may get the reference counting wrong if they see
		 * PG_reserved set on a tail page (despite the head page not
		 * having PG_reserved set).  Enforcing this consistency between
		 * head and tail pages allows drivers to optimize away a check
		 * on the head page when they need know if put_page() is needed
		 * after get_user_pages().
		 */
		__ClearPageReserved(p);
		set_page_count(p, 0);
		p->first_page = page;
	}
}

/*
 * PageHuge() only returns true for hugetlbfs pages, but not for normal or
 * transparent huge pages.  See the PageTransHuge() documentation for more
 * details.
 */
int PageHuge(struct page *page)
{
	if (!PageCompound(page))
		return 0;

	page = compound_head(page);
	return get_compound_page_dtor(page) == free_huge_page;
}
EXPORT_SYMBOL_GPL(PageHuge);

/*
 * PageHeadHuge() only returns true for hugetlbfs head page, but not for
 * normal or transparent huge pages.
 */
int PageHeadHuge(struct page *page_head)
{
	if (!PageHead(page_head))
		return 0;

	return get_compound_page_dtor(page_head) == free_huge_page;
}

pgoff_t __basepage_index(struct page *page)
{
	struct page *page_head = compound_head(page);
	pgoff_t index = page_index(page_head);
	unsigned long compound_idx;

	if (!PageHuge(page_head))
		return page_index(page);

	if (compound_order(page_head) >= MAX_ORDER)
		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
	else
		compound_idx = page - page_head;

	return (index << compound_order(page_head)) + compound_idx;
}

static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	page = alloc_pages_exact_node(nid,
		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
						__GFP_REPEAT|__GFP_NOWARN,
		huge_page_order(h));
	if (page) {
		if (arch_prepare_hugepage(page)) {
			__free_pages(page, huge_page_order(h));
			return NULL;
		}
		prep_new_huge_page(h, page, nid);
	}

	return page;
}

static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
{
	struct page *page;
	int nr_nodes, node;
	int ret = 0;

	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
		page = alloc_fresh_huge_page_node(h, node);
		if (page) {
			ret = 1;
			break;
		}
	}

	if (ret)
		count_vm_event(HTLB_BUDDY_PGALLOC);
	else
		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);

	return ret;
}

/*
 * Free huge page from pool from next node to free.
 * Attempt to keep persistent huge pages more or less
 * balanced over allowed nodes.
 * Called with hugetlb_lock locked.
 */
static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
							 bool acct_surplus)
{
	int nr_nodes, node;
	int ret = 0;

	for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
		/*
		 * If we're returning unused surplus pages, only examine
		 * nodes with surplus pages.
		 */
		if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
		    !list_empty(&h->hugepage_freelists[node])) {
			struct page *page =
				list_entry(h->hugepage_freelists[node].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[node]--;
			if (acct_surplus) {
				h->surplus_huge_pages--;
				h->surplus_huge_pages_node[node]--;
			}
			update_and_free_page(h, page);
			ret = 1;
			break;
		}
	}

	return ret;
}

/*
 * Dissolve a given free hugepage into free buddy pages. This function does
 * nothing for in-use (including surplus) hugepages.
 */
static void dissolve_free_huge_page(struct page *page)
{
	spin_lock(&hugetlb_lock);
	if (PageHuge(page) && !page_count(page)) {
		struct hstate *h = page_hstate(page);
		int nid = page_to_nid(page);
		list_del(&page->lru);
		h->free_huge_pages--;
		h->free_huge_pages_node[nid]--;
		update_and_free_page(h, page);
	}
	spin_unlock(&hugetlb_lock);
}

/*
 * Dissolve free hugepages in a given pfn range. Used by memory hotplug to
 * make specified memory blocks removable from the system.
 * Note that start_pfn should aligned with (minimum) hugepage size.
 */
void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned int order = 8 * sizeof(void *);
	unsigned long pfn;
	struct hstate *h;

	/* Set scan step to minimum hugepage size */
	for_each_hstate(h)
		if (order > huge_page_order(h))
			order = huge_page_order(h);
	VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order));
	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order)
		dissolve_free_huge_page(pfn_to_page(pfn));
}

static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
{
	struct page *page;
	unsigned int r_nid;

	if (hstate_is_gigantic(h))
		return NULL;

	/*
	 * Assume we will successfully allocate the surplus page to
	 * prevent racing processes from causing the surplus to exceed
	 * overcommit
	 *
	 * This however introduces a different race, where a process B
	 * tries to grow the static hugepage pool while alloc_pages() is
	 * called by process A. B will only examine the per-node
	 * counters in determining if surplus huge pages can be
	 * converted to normal huge pages in adjust_pool_surplus(). A
	 * won't be able to increment the per-node counter, until the
	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
	 * no more huge pages can be converted from surplus to normal
	 * state (and doesn't try to convert again). Thus, we have a
	 * case where a surplus huge page exists, the pool is grown, and
	 * the surplus huge page still exists after, even though it
	 * should just have been converted to a normal huge page. This
	 * does not leak memory, though, as the hugepage will be freed
	 * once it is out of use. It also does not allow the counters to
	 * go out of whack in adjust_pool_surplus() as we don't modify
	 * the node values until we've gotten the hugepage and only the
	 * per-node value is checked there.
	 */
	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
		spin_unlock(&hugetlb_lock);
		return NULL;
	} else {
		h->nr_huge_pages++;
		h->surplus_huge_pages++;
	}
	spin_unlock(&hugetlb_lock);

	if (nid == NUMA_NO_NODE)
		page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP|
				   __GFP_REPEAT|__GFP_NOWARN,
				   huge_page_order(h));
	else
		page = alloc_pages_exact_node(nid,
			htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));

	if (page && arch_prepare_hugepage(page)) {
		__free_pages(page, huge_page_order(h));
		page = NULL;
	}

	spin_lock(&hugetlb_lock);
	if (page) {
		INIT_LIST_HEAD(&page->lru);
		r_nid = page_to_nid(page);
		set_compound_page_dtor(page, free_huge_page);
		set_hugetlb_cgroup(page, NULL);
		/*
		 * We incremented the global counters already
		 */
		h->nr_huge_pages_node[r_nid]++;
		h->surplus_huge_pages_node[r_nid]++;
		__count_vm_event(HTLB_BUDDY_PGALLOC);
	} else {
		h->nr_huge_pages--;
		h->surplus_huge_pages--;
		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
	}
	spin_unlock(&hugetlb_lock);

	return page;
}

/*
 * This allocation function is useful in the context where vma is irrelevant.
 * E.g. soft-offlining uses this function because it only cares physical
 * address of error page.
 */
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
	struct page *page = NULL;

	spin_lock(&hugetlb_lock);
	if (h->free_huge_pages - h->resv_huge_pages > 0)
		page = dequeue_huge_page_node(h, nid);
	spin_unlock(&hugetlb_lock);

	if (!page)
		page = alloc_buddy_huge_page(h, nid);

	return page;
}

/*
 * Increase the hugetlb pool such that it can accommodate a reservation
 * of size 'delta'.
 */
static int gather_surplus_pages(struct hstate *h, int delta)
{
	struct list_head surplus_list;
	struct page *page, *tmp;
	int ret, i;
	int needed, allocated;
	bool alloc_ok = true;

	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
	if (needed <= 0) {
		h->resv_huge_pages += delta;
		return 0;
	}

	allocated = 0;
	INIT_LIST_HEAD(&surplus_list);

	ret = -ENOMEM;
retry:
	spin_unlock(&hugetlb_lock);
	for (i = 0; i < needed; i++) {
		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
		if (!page) {
			alloc_ok = false;
			break;
		}
		list_add(&page->lru, &surplus_list);
	}
	allocated += i;

	/*
	 * After retaking hugetlb_lock, we need to recalculate 'needed'
	 * because either resv_huge_pages or free_huge_pages may have changed.
	 */
	spin_lock(&hugetlb_lock);
	needed = (h->resv_huge_pages + delta) -
			(h->free_huge_pages + allocated);
	if (needed > 0) {
		if (alloc_ok)
			goto retry;
		/*
		 * We were not able to allocate enough pages to
		 * satisfy the entire reservation so we free what
		 * we've allocated so far.
		 */
		goto free;
	}
	/*
	 * The surplus_list now contains _at_least_ the number of extra pages
	 * needed to accommodate the reservation.  Add the appropriate number
	 * of pages to the hugetlb pool and free the extras back to the buddy
	 * allocator.  Commit the entire reservation here to prevent another
	 * process from stealing the pages as they are added to the pool but
	 * before they are reserved.
	 */
	needed += allocated;
	h->resv_huge_pages += delta;
	ret = 0;

	/* Free the needed pages to the hugetlb pool */
	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
		if ((--needed) < 0)
			break;
		/*
		 * This page is now managed by the hugetlb allocator and has
		 * no users -- drop the buddy allocator's reference.
		 */
		put_page_testzero(page);
		VM_BUG_ON_PAGE(page_count(page), page);
		enqueue_huge_page(h, page);
	}
free:
	spin_unlock(&hugetlb_lock);

	/* Free unnecessary surplus pages to the buddy allocator */
	list_for_each_entry_safe(page, tmp, &surplus_list, lru)
		put_page(page);
	spin_lock(&hugetlb_lock);

	return ret;
}

/*
 * When releasing a hugetlb pool reservation, any surplus pages that were
 * allocated to satisfy the reservation must be explicitly freed if they were
 * never used.
 * Called with hugetlb_lock held.
 */
static void return_unused_surplus_pages(struct hstate *h,
					unsigned long unused_resv_pages)
{
	unsigned long nr_pages;

	/* Uncommit the reservation */
	h->resv_huge_pages -= unused_resv_pages;

	/* Cannot return gigantic pages currently */
	if (hstate_is_gigantic(h))
		return;

	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);

	/*
	 * We want to release as many surplus pages as possible, spread
	 * evenly across all nodes with memory. Iterate across these nodes
	 * until we can no longer free unreserved surplus pages. This occurs
	 * when the nodes with surplus pages have no free pages.
	 * free_pool_huge_page() will balance the the freed pages across the
	 * on-line nodes with memory and will handle the hstate accounting.
	 */
	while (nr_pages--) {
		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
			break;
		cond_resched_lock(&hugetlb_lock);
	}
}

/*
 * Determine if the huge page at addr within the vma has an associated
 * reservation.  Where it does not we will need to logically increase
 * reservation and actually increase subpool usage before an allocation
 * can occur.  Where any new reservation would be required the
 * reservation change is prepared, but not committed.  Once the page
 * has been allocated from the subpool and instantiated the change should
 * be committed via vma_commit_reservation.  No action is required on
 * failure.
 */
static long vma_needs_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct resv_map *resv;
	pgoff_t idx;
	long chg;

	resv = vma_resv_map(vma);
	if (!resv)
		return 1;

	idx = vma_hugecache_offset(h, vma, addr);
	chg = region_chg(resv, idx, idx + 1);

	if (vma->vm_flags & VM_MAYSHARE)
		return chg;
	else
		return chg < 0 ? chg : 0;
}
static void vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct resv_map *resv;
	pgoff_t idx;

	resv = vma_resv_map(vma);
	if (!resv)
		return;

	idx = vma_hugecache_offset(h, vma, addr);
	region_add(resv, idx, idx + 1);
}

static struct page *alloc_huge_page(struct vm_area_struct *vma,
				    unsigned long addr, int avoid_reserve)
{
	struct hugepage_subpool *spool = subpool_vma(vma);
	struct hstate *h = hstate_vma(vma);
	struct page *page;
	long chg;
	int ret, idx;
	struct hugetlb_cgroup *h_cg;

	idx = hstate_index(h);
	/*
	 * Processes that did not create the mapping will have no
	 * reserves and will not have accounted against subpool
	 * limit. Check that the subpool limit can be made before
	 * satisfying the allocation MAP_NORESERVE mappings may also
	 * need pages and subpool limit allocated allocated if no reserve
	 * mapping overlaps.
	 */
	chg = vma_needs_reservation(h, vma, addr);
	if (chg < 0)
		return ERR_PTR(-ENOMEM);
	if (chg || avoid_reserve)
		if (hugepage_subpool_get_pages(spool, 1))
			return ERR_PTR(-ENOSPC);

	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
	if (ret)
		goto out_subpool_put;

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg);
	if (!page) {
		spin_unlock(&hugetlb_lock);
		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
		if (!page)
			goto out_uncharge_cgroup;

		spin_lock(&hugetlb_lock);
		list_move(&page->lru, &h->hugepage_activelist);
		/* Fall through */
	}
	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
	spin_unlock(&hugetlb_lock);

	set_page_private(page, (unsigned long)spool);

	vma_commit_reservation(h, vma, addr);
	return page;

out_uncharge_cgroup:
	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
out_subpool_put:
	if (chg || avoid_reserve)
		hugepage_subpool_put_pages(spool, 1);
	return ERR_PTR(-ENOSPC);
}

/*
 * alloc_huge_page()'s wrapper which simply returns the page if allocation
 * succeeds, otherwise NULL. This function is called from new_vma_page(),
 * where no ERR_VALUE is expected to be returned.
 */
struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
				unsigned long addr, int avoid_reserve)
{
	struct page *page = alloc_huge_page(vma, addr, avoid_reserve);
	if (IS_ERR(page))
		page = NULL;
	return page;
}

int __weak alloc_bootmem_huge_page(struct hstate *h)
{
	struct huge_bootmem_page *m;
	int nr_nodes, node;

	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
		void *addr;

		addr = memblock_virt_alloc_try_nid_nopanic(
				huge_page_size(h), huge_page_size(h),
				0, BOOTMEM_ALLOC_ACCESSIBLE, node);
		if (addr) {
			/*
			 * Use the beginning of the huge page to store the
			 * huge_bootmem_page struct (until gather_bootmem
			 * puts them into the mem_map).
			 */
			m = addr;
			goto found;
		}
	}
	return 0;

found:
	BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
	/* Put them into a private list first because mem_map is not up yet */
	list_add(&m->list, &huge_boot_pages);
	m->hstate = h;
	return 1;
}

static void __init prep_compound_huge_page(struct page *page, int order)
{
	if (unlikely(order > (MAX_ORDER - 1)))
		prep_compound_gigantic_page(page, order);
	else
		prep_compound_page(page, order);
}

/* Put bootmem huge pages into the standard lists after mem_map is up */
static void __init gather_bootmem_prealloc(void)
{
	struct huge_bootmem_page *m;

	list_for_each_entry(m, &huge_boot_pages, list) {
		struct hstate *h = m->hstate;
		struct page *page;

#ifdef CONFIG_HIGHMEM
		page = pfn_to_page(m->phys >> PAGE_SHIFT);
		memblock_free_late(__pa(m),
				   sizeof(struct huge_bootmem_page));
#else
		page = virt_to_page(m);
#endif
		WARN_ON(page_count(page) != 1);
		prep_compound_huge_page(page, h->order);
		WARN_ON(PageReserved(page));
		prep_new_huge_page(h, page, page_to_nid(page));
		/*
		 * If we had gigantic hugepages allocated at boot time, we need
		 * to restore the 'stolen' pages to totalram_pages in order to
		 * fix confusing memory reports from free(1) and another
		 * side-effects, like CommitLimit going negative.
		 */
		if (hstate_is_gigantic(h))
			adjust_managed_page_count(page, 1 << h->order);
	}
}

static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
	unsigned long i;

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (hstate_is_gigantic(h)) {
			if (!alloc_bootmem_huge_page(h))
				break;
		} else if (!alloc_fresh_huge_page(h,
					 &node_states[N_MEMORY]))
			break;
	}
	h->max_huge_pages = i;
}

static void __init hugetlb_init_hstates(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		/* oversize hugepages were init'ed in early boot */
		if (!hstate_is_gigantic(h))
			hugetlb_hstate_alloc_pages(h);
	}
}

static char * __init memfmt(char *buf, unsigned long n)
{
	if (n >= (1UL << 30))
		sprintf(buf, "%lu GB", n >> 30);
	else if (n >= (1UL << 20))
		sprintf(buf, "%lu MB", n >> 20);
	else
		sprintf(buf, "%lu KB", n >> 10);
	return buf;
}

static void __init report_hugepages(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		char buf[32];
		pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
			memfmt(buf, huge_page_size(h)),
			h->free_huge_pages);
	}
}

#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
	int i;

	if (hstate_is_gigantic(h))
		return;

	for_each_node_mask(i, *nodes_allowed) {
		struct page *page, *next;
		struct list_head *freel = &h->hugepage_freelists[i];
		list_for_each_entry_safe(page, next, freel, lru) {
			if (count >= h->nr_huge_pages)
				return;
			if (PageHighMem(page))
				continue;
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[page_to_nid(page)]--;
		}
	}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
}
#endif

/*
 * Increment or decrement surplus_huge_pages.  Keep node-specific counters
 * balanced by operating on them in a round-robin fashion.
 * Returns 1 if an adjustment was made.
 */
static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
				int delta)
{
	int nr_nodes, node;

	VM_BUG_ON(delta != -1 && delta != 1);

	if (delta < 0) {
		for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
			if (h->surplus_huge_pages_node[node])
				goto found;
		}
	} else {
		for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
			if (h->surplus_huge_pages_node[node] <
					h->nr_huge_pages_node[node])
				goto found;
		}
	}
	return 0;

found:
	h->surplus_huge_pages += delta;
	h->surplus_huge_pages_node[node] += delta;
	return 1;
}

#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
	unsigned long min_count, ret;

	if (hstate_is_gigantic(h) && !gigantic_page_supported())
		return h->max_huge_pages;

	/*
	 * Increase the pool size
	 * First take pages out of surplus state.  Then make up the
	 * remaining difference by allocating fresh huge pages.
	 *
	 * We might race with alloc_buddy_huge_page() here and be unable
	 * to convert a surplus huge page to a normal huge page. That is
	 * not critical, though, it just means the overall size of the
	 * pool might be one hugepage larger than it needs to be, but
	 * within all the constraints specified by the sysctls.
	 */
	spin_lock(&hugetlb_lock);
	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, -1))
			break;
	}

	while (count > persistent_huge_pages(h)) {
		/*
		 * If this allocation races such that we no longer need the
		 * page, free_huge_page will handle it by freeing the page
		 * and reducing the surplus.
		 */
		spin_unlock(&hugetlb_lock);
		if (hstate_is_gigantic(h))
			ret = alloc_fresh_gigantic_page(h, nodes_allowed);
		else
			ret = alloc_fresh_huge_page(h, nodes_allowed);
		spin_lock(&hugetlb_lock);
		if (!ret)
			goto out;

		/* Bail for signals. Probably ctrl-c from user */
		if (signal_pending(current))
			goto out;
	}

	/*
	 * Decrease the pool size
	 * First return free pages to the buddy allocator (being careful
	 * to keep enough around to satisfy reservations).  Then place
	 * pages into surplus state as needed so the pool will shrink
	 * to the desired size as pages become free.
	 *
	 * By placing pages into the surplus state independent of the
	 * overcommit value, we are allowing the surplus pool size to
	 * exceed overcommit. There are few sane options here. Since
	 * alloc_buddy_huge_page() is checking the global counter,
	 * though, we'll note that we're not allowed to exceed surplus
	 * and won't grow the pool anywhere else. Not until one of the
	 * sysctls are changed, or the surplus pages go out of use.
	 */
	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
	min_count = max(count, min_count);
	try_to_free_low(h, min_count, nodes_allowed);
	while (min_count < persistent_huge_pages(h)) {
		if (!free_pool_huge_page(h, nodes_allowed, 0))
			break;
		cond_resched_lock(&hugetlb_lock);
	}
	while (count < persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, 1))
			break;
	}
out:
	ret = persistent_huge_pages(h);
	spin_unlock(&hugetlb_lock);
	return ret;
}

#define HSTATE_ATTR_RO(_name) \
	static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

#define HSTATE_ATTR(_name) \
	static struct kobj_attribute _name##_attr = \
		__ATTR(_name, 0644, _name##_show, _name##_store)

static struct kobject *hugepages_kobj;
static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];

static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp);

static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
{
	int i;

	for (i = 0; i < HUGE_MAX_HSTATE; i++)
		if (hstate_kobjs[i] == kobj) {
			if (nidp)
				*nidp = NUMA_NO_NODE;
			return &hstates[i];
		}

	return kobj_to_node_hstate(kobj, nidp);
}

static ssize_t nr_hugepages_show_common(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long nr_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		nr_huge_pages = h->nr_huge_pages;
	else
		nr_huge_pages = h->nr_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", nr_huge_pages);
}

static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
					   struct hstate *h, int nid,
					   unsigned long count, size_t len)
{
	int err;
	NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);

	if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
		err = -EINVAL;
		goto out;
	}

	if (nid == NUMA_NO_NODE) {
		/*
		 * global hstate attribute
		 */
		if (!(obey_mempolicy &&
				init_nodemask_of_mempolicy(nodes_allowed))) {
			NODEMASK_FREE(nodes_allowed);
			nodes_allowed = &node_states[N_MEMORY];
		}
	} else if (nodes_allowed) {
		/*
		 * per node hstate attribute: adjust count to global,
		 * but restrict alloc/free to the specified node.
		 */
		count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
		init_nodemask_of_node(nodes_allowed, nid);
	} else
		nodes_allowed = &node_states[N_MEMORY];

	h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);

	if (nodes_allowed != &node_states[N_MEMORY])
		NODEMASK_FREE(nodes_allowed);

	return len;
out:
	NODEMASK_FREE(nodes_allowed);
	return err;
}

static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
					 struct kobject *kobj, const char *buf,
					 size_t len)
{
	struct hstate *h;
	unsigned long count;
	int nid;
	int err;

	err = kstrtoul(buf, 10, &count);
	if (err)
		return err;

	h = kobj_to_hstate(kobj, &nid);
	return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len);
}

static ssize_t nr_hugepages_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return nr_hugepages_show_common(kobj, attr, buf);
}

static ssize_t nr_hugepages_store(struct kobject *kobj,
	       struct kobj_attribute *attr, const char *buf, size_t len)
{
	return nr_hugepages_store_common(false, kobj, buf, len);
}
HSTATE_ATTR(nr_hugepages);

#ifdef CONFIG_NUMA

/*
 * hstate attribute for optionally mempolicy-based constraint on persistent
 * huge page alloc/free.
 */
static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return nr_hugepages_show_common(kobj, attr, buf);
}

static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
	       struct kobj_attribute *attr, const char *buf, size_t len)
{
	return nr_hugepages_store_common(true, kobj, buf, len);
}
HSTATE_ATTR(nr_hugepages_mempolicy);
#endif


static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj, NULL);
	return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
}

static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
		struct kobj_attribute *attr, const char *buf, size_t count)
{
	int err;
	unsigned long input;
	struct hstate *h = kobj_to_hstate(kobj, NULL);

	if (hstate_is_gigantic(h))
		return -EINVAL;

	err = kstrtoul(buf, 10, &input);
	if (err)
		return err;

	spin_lock(&hugetlb_lock);
	h->nr_overcommit_huge_pages = input;
	spin_unlock(&hugetlb_lock);

	return count;
}
HSTATE_ATTR(nr_overcommit_hugepages);

static ssize_t free_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long free_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		free_huge_pages = h->free_huge_pages;
	else
		free_huge_pages = h->free_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", free_huge_pages);
}
HSTATE_ATTR_RO(free_hugepages);

static ssize_t resv_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj, NULL);
	return sprintf(buf, "%lu\n", h->resv_huge_pages);
}
HSTATE_ATTR_RO(resv_hugepages);

static ssize_t surplus_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long surplus_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		surplus_huge_pages = h->surplus_huge_pages;
	else
		surplus_huge_pages = h->surplus_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", surplus_huge_pages);
}
HSTATE_ATTR_RO(surplus_hugepages);

static struct attribute *hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&nr_overcommit_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&resv_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
#ifdef CONFIG_NUMA
	&nr_hugepages_mempolicy_attr.attr,
#endif
	NULL,
};

static struct attribute_group hstate_attr_group = {
	.attrs = hstate_attrs,
};

static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
				    struct kobject **hstate_kobjs,
				    struct attribute_group *hstate_attr_group)
{
	int retval;
	int hi = hstate_index(h);

	hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
	if (!hstate_kobjs[hi])
		return -ENOMEM;

	retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
	if (retval)
		kobject_put(hstate_kobjs[hi]);

	return retval;
}

static void __init hugetlb_sysfs_init(void)
{
	struct hstate *h;
	int err;

	hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
	if (!hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
					 hstate_kobjs, &hstate_attr_group);
		if (err)
			pr_err("Hugetlb: Unable to add hstate %s", h->name);
	}
}

#ifdef CONFIG_NUMA

/*
 * node_hstate/s - associate per node hstate attributes, via their kobjects,
 * with node devices in node_devices[] using a parallel array.  The array
 * index of a node device or _hstate == node id.
 * This is here to avoid any static dependency of the node device driver, in
 * the base kernel, on the hugetlb module.
 */
struct node_hstate {
	struct kobject		*hugepages_kobj;
	struct kobject		*hstate_kobjs[HUGE_MAX_HSTATE];
};
struct node_hstate node_hstates[MAX_NUMNODES];

/*
 * A subset of global hstate attributes for node devices
 */
static struct attribute *per_node_hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
	NULL,
};

static struct attribute_group per_node_hstate_attr_group = {
	.attrs = per_node_hstate_attrs,
};

/*
 * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj.
 * Returns node id via non-NULL nidp.
 */
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
	int nid;

	for (nid = 0; nid < nr_node_ids; nid++) {
		struct node_hstate *nhs = &node_hstates[nid];
		int i;
		for (i = 0; i < HUGE_MAX_HSTATE; i++)
			if (nhs->hstate_kobjs[i] == kobj) {
				if (nidp)
					*nidp = nid;
				return &hstates[i];
			}
	}

	BUG();
	return NULL;
}

/*
 * Unregister hstate attributes from a single node device.
 * No-op if no hstate attributes attached.
 */
static void hugetlb_unregister_node(struct node *node)
{
	struct hstate *h;
	struct node_hstate *nhs = &node_hstates[node->dev.id];

	if (!nhs->hugepages_kobj)
		return;		/* no hstate attributes */

	for_each_hstate(h) {
		int idx = hstate_index(h);
		if (nhs->hstate_kobjs[idx]) {
			kobject_put(nhs->hstate_kobjs[idx]);
			nhs->hstate_kobjs[idx] = NULL;
		}
	}

	kobject_put(nhs->hugepages_kobj);
	nhs->hugepages_kobj = NULL;
}

/*
 * hugetlb module exit:  unregister hstate attributes from node devices
 * that have them.
 */
static void hugetlb_unregister_all_nodes(void)
{
	int nid;

	/*
	 * disable node device registrations.
	 */
	register_hugetlbfs_with_node(NULL, NULL);

	/*
	 * remove hstate attributes from any nodes that have them.
	 */
	for (nid = 0; nid < nr_node_ids; nid++)
		hugetlb_unregister_node(node_devices[nid]);
}

/*
 * Register hstate attributes for a single node device.
 * No-op if attributes already registered.
 */
static void hugetlb_register_node(struct node *node)
{
	struct hstate *h;
	struct node_hstate *nhs = &node_hstates[node->dev.id];
	int err;

	if (nhs->hugepages_kobj)
		return;		/* already allocated */

	nhs->hugepages_kobj = kobject_create_and_add("hugepages",
							&node->dev.kobj);
	if (!nhs->hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
						nhs->hstate_kobjs,
						&per_node_hstate_attr_group);
		if (err) {
			pr_err("Hugetlb: Unable to add hstate %s for node %d\n",
				h->name, node->dev.id);
			hugetlb_unregister_node(node);
			break;
		}
	}
}

/*
 * hugetlb init time:  register hstate attributes for all registered node
 * devices of nodes that have memory.  All on-line nodes should have
 * registered their associated device by this time.
 */
static void hugetlb_register_all_nodes(void)
{
	int nid;

	for_each_node_state(nid, N_MEMORY) {
		struct node *node = node_devices[nid];
		if (node->dev.id == nid)
			hugetlb_register_node(node);
	}

	/*
	 * Let the node device driver know we're here so it can
	 * [un]register hstate attributes on node hotplug.
	 */
	register_hugetlbfs_with_node(hugetlb_register_node,
				     hugetlb_unregister_node);
}
#else	/* !CONFIG_NUMA */

static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
	BUG();
	if (nidp)
		*nidp = -1;
	return NULL;
}

static void hugetlb_unregister_all_nodes(void) { }

static void hugetlb_register_all_nodes(void) { }

#endif

static void __exit hugetlb_exit(void)
{
	struct hstate *h;

	hugetlb_unregister_all_nodes();

	for_each_hstate(h) {
		kobject_put(hstate_kobjs[hstate_index(h)]);
	}

	kobject_put(hugepages_kobj);
	kfree(htlb_fault_mutex_table);
}
module_exit(hugetlb_exit);

static int __init hugetlb_init(void)
{
	int i;

	if (!hugepages_supported())
		return 0;

	if (!size_to_hstate(default_hstate_size)) {
		default_hstate_size = HPAGE_SIZE;
		if (!size_to_hstate(default_hstate_size))
			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
	}
	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
	if (default_hstate_max_huge_pages)
		default_hstate.max_huge_pages = default_hstate_max_huge_pages;

	hugetlb_init_hstates();
	gather_bootmem_prealloc();
	report_hugepages();

	hugetlb_sysfs_init();
	hugetlb_register_all_nodes();
	hugetlb_cgroup_file_init();

#ifdef CONFIG_SMP
	num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus());
#else
	num_fault_mutexes = 1;
#endif
	htlb_fault_mutex_table =
		kmalloc(sizeof(struct mutex) * num_fault_mutexes, GFP_KERNEL);
	BUG_ON(!htlb_fault_mutex_table);

	for (i = 0; i < num_fault_mutexes; i++)
		mutex_init(&htlb_fault_mutex_table[i]);
	return 0;
}
module_init(hugetlb_init);

/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_add_hstate(unsigned order)
{
	struct hstate *h;
	unsigned long i;

	if (size_to_hstate(PAGE_SIZE << order)) {
		pr_warning("hugepagesz= specified twice, ignoring\n");
		return;
	}
	BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
	BUG_ON(order == 0);
	h = &hstates[hugetlb_max_hstate++];
	h->order = order;
	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
	h->nr_huge_pages = 0;
	h->free_huge_pages = 0;
	for (i = 0; i < MAX_NUMNODES; ++i)
		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
	INIT_LIST_HEAD(&h->hugepage_activelist);
	h->next_nid_to_alloc = first_node(node_states[N_MEMORY]);
	h->next_nid_to_free = first_node(node_states[N_MEMORY]);
	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
					huge_page_size(h)/1024);

	parsed_hstate = h;
}

static int __init hugetlb_nrpages_setup(char *s)
{
	unsigned long *mhp;
	static unsigned long *last_mhp;

	/*
	 * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet,
	 * so this hugepages= parameter goes to the "default hstate".
	 */
	if (!hugetlb_max_hstate)
		mhp = &default_hstate_max_huge_pages;
	else
		mhp = &parsed_hstate->max_huge_pages;

	if (mhp == last_mhp) {
		pr_warning("hugepages= specified twice without "
			   "interleaving hugepagesz=, ignoring\n");
		return 1;
	}

	if (sscanf(s, "%lu", mhp) <= 0)
		*mhp = 0;

	/*
	 * Global state is always initialized later in hugetlb_init.
	 * But we need to allocate >= MAX_ORDER hstates here early to still
	 * use the bootmem allocator.
	 */
	if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER)
		hugetlb_hstate_alloc_pages(parsed_hstate);

	last_mhp = mhp;

	return 1;
}
__setup("hugepages=", hugetlb_nrpages_setup);

static int __init hugetlb_default_setup(char *s)
{
	default_hstate_size = memparse(s, &s);
	return 1;
}
__setup("default_hugepagesz=", hugetlb_default_setup);

static unsigned int cpuset_mems_nr(unsigned int *array)
{
	int node;
	unsigned int nr = 0;

	for_each_node_mask(node, cpuset_current_mems_allowed)
		nr += array[node];

	return nr;
}

#ifdef CONFIG_SYSCTL
static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
			 struct ctl_table *table, int write,
			 void __user *buffer, size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp = h->max_huge_pages;
	int ret;

	if (!hugepages_supported())
		return -ENOTSUPP;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
	if (ret)
		goto out;

	if (write)
		ret = __nr_hugepages_store_common(obey_mempolicy, h,
						  NUMA_NO_NODE, tmp, *length);
out:
	return ret;
}

int hugetlb_sysctl_handler(struct ctl_table *table, int write,
			  void __user *buffer, size_t *length, loff_t *ppos)
{

	return hugetlb_sysctl_handler_common(false, table, write,
							buffer, length, ppos);
}

#ifdef CONFIG_NUMA
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
			  void __user *buffer, size_t *length, loff_t *ppos)
{
	return hugetlb_sysctl_handler_common(true, table, write,
							buffer, length, ppos);
}
#endif /* CONFIG_NUMA */

int hugetlb_overcommit_handler(struct ctl_table *table, int write,
			void __user *buffer,
			size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;
	int ret;

	if (!hugepages_supported())
		return -ENOTSUPP;

	tmp = h->nr_overcommit_huge_pages;

	if (write && hstate_is_gigantic(h))
		return -EINVAL;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
	if (ret)
		goto out;

	if (write) {
		spin_lock(&hugetlb_lock);
		h->nr_overcommit_huge_pages = tmp;
		spin_unlock(&hugetlb_lock);
	}
out:
	return ret;
}

#endif /* CONFIG_SYSCTL */

void hugetlb_report_meminfo(struct seq_file *m)
{
	struct hstate *h = &default_hstate;
	if (!hugepages_supported())
		return;
	seq_printf(m,
			"HugePages_Total:   %5lu\n"
			"HugePages_Free:    %5lu\n"
			"HugePages_Rsvd:    %5lu\n"
			"HugePages_Surp:    %5lu\n"
			"Hugepagesize:   %8lu kB\n",
			h->nr_huge_pages,
			h->free_huge_pages,
			h->resv_huge_pages,
			h->surplus_huge_pages,
			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}

int hugetlb_report_node_meminfo(int nid, char *buf)
{
	struct hstate *h = &default_hstate;
	if (!hugepages_supported())
		return 0;
	return sprintf(buf,
		"Node %d HugePages_Total: %5u\n"
		"Node %d HugePages_Free:  %5u\n"
		"Node %d HugePages_Surp:  %5u\n",
		nid, h->nr_huge_pages_node[nid],
		nid, h->free_huge_pages_node[nid],
		nid, h->surplus_huge_pages_node[nid]);
}

void hugetlb_show_meminfo(void)
{
	struct hstate *h;
	int nid;

	if (!hugepages_supported())
		return;

	for_each_node_state(nid, N_MEMORY)
		for_each_hstate(h)
			pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
				nid,
				h->nr_huge_pages_node[nid],
				h->free_huge_pages_node[nid],
				h->surplus_huge_pages_node[nid],
				1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}

/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
	struct hstate *h;
	unsigned long nr_total_pages = 0;

	for_each_hstate(h)
		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
	return nr_total_pages;
}

static int hugetlb_acct_memory(struct hstate *h, long delta)
{
	int ret = -ENOMEM;

	spin_lock(&hugetlb_lock);
	/*
	 * When cpuset is configured, it breaks the strict hugetlb page
	 * reservation as the accounting is done on a global variable. Such
	 * reservation is completely rubbish in the presence of cpuset because
	 * the reservation is not checked against page availability for the
	 * current cpuset. Application can still potentially OOM'ed by kernel
	 * with lack of free htlb page in cpuset that the task is in.
	 * Attempt to enforce strict accounting with cpuset is almost
	 * impossible (or too ugly) because cpuset is too fluid that
	 * task or memory node can be dynamically moved between cpusets.
	 *
	 * The change of semantics for shared hugetlb mapping with cpuset is
	 * undesirable. However, in order to preserve some of the semantics,
	 * we fall back to check against current free page availability as
	 * a best attempt and hopefully to minimize the impact of changing
	 * semantics that cpuset has.
	 */
	if (delta > 0) {
		if (gather_surplus_pages(h, delta) < 0)
			goto out;

		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
			return_unused_surplus_pages(h, delta);
			goto out;
		}
	}

	ret = 0;
	if (delta < 0)
		return_unused_surplus_pages(h, (unsigned long) -delta);

out:
	spin_unlock(&hugetlb_lock);
	return ret;
}

static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
	struct resv_map *resv = vma_resv_map(vma);

	/*
	 * This new VMA should share its siblings reservation map if present.
	 * The VMA will only ever have a valid reservation map pointer where
	 * it is being copied for another still existing VMA.  As that VMA
	 * has a reference to the reservation map it cannot disappear until
	 * after this open call completes.  It is therefore safe to take a
	 * new reference here without additional locking.
	 */
	if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		kref_get(&resv->refs);
}

static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
	struct hstate *h = hstate_vma(vma);
	struct resv_map *resv = vma_resv_map(vma);
	struct hugepage_subpool *spool = subpool_vma(vma);
	unsigned long reserve, start, end;

	if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		return;

	start = vma_hugecache_offset(h, vma, vma->vm_start);
	end = vma_hugecache_offset(h, vma, vma->vm_end);

	reserve = (end - start) - region_count(resv, start, end);

	kref_put(&resv->refs, resv_map_release);

	if (reserve) {
		hugetlb_acct_memory(h, -reserve);
		hugepage_subpool_put_pages(spool, reserve);
	}
}

/*
 * We cannot handle pagefaults against hugetlb pages at all.  They cause
 * handle_mm_fault() to try to instantiate regular-sized pages in the
 * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
 * this far.
 */
static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	BUG();
	return 0;
}

const struct vm_operations_struct hugetlb_vm_ops = {
	.fault = hugetlb_vm_op_fault,
	.open = hugetlb_vm_op_open,
	.close = hugetlb_vm_op_close,
};

static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
				int writable)
{
	pte_t entry;

	if (writable) {
		entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page,
					 vma->vm_page_prot)));
	} else {
		entry = huge_pte_wrprotect(mk_huge_pte(page,
					   vma->vm_page_prot));
	}
	entry = pte_mkyoung(entry);
	entry = pte_mkhuge(entry);
	entry = arch_make_huge_pte(entry, vma, page, writable);

	return entry;
}

static void set_huge_ptep_writable(struct vm_area_struct *vma,
				   unsigned long address, pte_t *ptep)
{
	pte_t entry;

	entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep)));
	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1))
		update_mmu_cache(vma, address, ptep);
}

static int is_hugetlb_entry_migration(pte_t pte)
{
	swp_entry_t swp;

	if (huge_pte_none(pte) || pte_present(pte))
		return 0;
	swp = pte_to_swp_entry(pte);
	if (non_swap_entry(swp) && is_migration_entry(swp))
		return 1;
	else
		return 0;
}

static int is_hugetlb_entry_hwpoisoned(pte_t pte)
{
	swp_entry_t swp;

	if (huge_pte_none(pte) || pte_present(pte))
		return 0;
	swp = pte_to_swp_entry(pte);
	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
		return 1;
	else
		return 0;
}

int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			    struct vm_area_struct *vma)
{
	pte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr;
	int cow;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */
	int ret = 0;

	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;

	mmun_start = vma->vm_start;
	mmun_end = vma->vm_end;
	if (cow)
		mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end);

	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
		spinlock_t *src_ptl, *dst_ptl;
		src_pte = huge_pte_offset(src, addr);
		if (!src_pte)
			continue;
		dst_pte = huge_pte_alloc(dst, addr, sz);
		if (!dst_pte) {
			ret = -ENOMEM;
			break;
		}

		/* If the pagetables are shared don't copy or take references */
		if (dst_pte == src_pte)
			continue;

		dst_ptl = huge_pte_lock(h, dst, dst_pte);
		src_ptl = huge_pte_lockptr(h, src, src_pte);
		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
		entry = huge_ptep_get(src_pte);
		if (huge_pte_none(entry)) { /* skip none entry */
			;
		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
				    is_hugetlb_entry_hwpoisoned(entry))) {
			swp_entry_t swp_entry = pte_to_swp_entry(entry);

			if (is_write_migration_entry(swp_entry) && cow) {
				/*
				 * COW mappings require pages in both
				 * parent and child to be set to read.
				 */
				make_migration_entry_read(&swp_entry);
				entry = swp_entry_to_pte(swp_entry);
				set_huge_pte_at(src, addr, src_pte, entry);
			}
			set_huge_pte_at(dst, addr, dst_pte, entry);
		} else {
			if (cow)
				huge_ptep_set_wrprotect(src, addr, src_pte);
			entry = huge_ptep_get(src_pte);
			ptepage = pte_page(entry);
			get_page(ptepage);
			page_dup_rmap(ptepage);
			set_huge_pte_at(dst, addr, dst_pte, entry);
		}
		spin_unlock(src_ptl);
		spin_unlock(dst_ptl);
	}

	if (cow)
		mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end);

	return ret;
}

void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
			    unsigned long start, unsigned long end,
			    struct page *ref_page)
{
	int force_flush = 0;
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address;
	pte_t *ptep;
	pte_t pte;
	spinlock_t *ptl;
	struct page *page;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);
	const unsigned long mmun_start = start;	/* For mmu_notifiers */
	const unsigned long mmun_end   = end;	/* For mmu_notifiers */

	WARN_ON(!is_vm_hugetlb_page(vma));
	BUG_ON(start & ~huge_page_mask(h));
	BUG_ON(end & ~huge_page_mask(h));

	tlb_start_vma(tlb, vma);
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
again:
	for (address = start; address < end; address += sz) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;

		ptl = huge_pte_lock(h, mm, ptep);
		if (huge_pmd_unshare(mm, &address, ptep))
			goto unlock;

		pte = huge_ptep_get(ptep);
		if (huge_pte_none(pte))
			goto unlock;

		/*
		 * HWPoisoned hugepage is already unmapped and dropped reference
		 */
		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
			huge_pte_clear(mm, address, ptep);
			goto unlock;
		}

		page = pte_page(pte);
		/*
		 * If a reference page is supplied, it is because a specific
		 * page is being unmapped, not a range. Ensure the page we
		 * are about to unmap is the actual page of interest.
		 */
		if (ref_page) {
			if (page != ref_page)
				goto unlock;

			/*
			 * Mark the VMA as having unmapped its page so that
			 * future faults in this VMA will fail rather than
			 * looking like data was lost
			 */
			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
		}

		pte = huge_ptep_get_and_clear(mm, address, ptep);
		tlb_remove_tlb_entry(tlb, ptep, address);
		if (huge_pte_dirty(pte))
			set_page_dirty(page);

		page_remove_rmap(page);
		force_flush = !__tlb_remove_page(tlb, page);
		if (force_flush) {
			spin_unlock(ptl);
			break;
		}
		/* Bail out after unmapping reference page if supplied */
		if (ref_page) {
			spin_unlock(ptl);
			break;
		}
unlock:
		spin_unlock(ptl);
	}
	/*
	 * mmu_gather ran out of room to batch pages, we break out of
	 * the PTE lock to avoid doing the potential expensive TLB invalidate
	 * and page-free while holding it.
	 */
	if (force_flush) {
		force_flush = 0;
		tlb_flush_mmu(tlb);
		if (address < end && !ref_page)
			goto again;
	}
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	tlb_end_vma(tlb, vma);
}

void __unmap_hugepage_range_final(struct mmu_gather *tlb,
			  struct vm_area_struct *vma, unsigned long start,
			  unsigned long end, struct page *ref_page)
{
	__unmap_hugepage_range(tlb, vma, start, end, ref_page);

	/*
	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
	 * test will fail on a vma being torn down, and not grab a page table
	 * on its way out.  We're lucky that the flag has such an appropriate
	 * name, and can in fact be safely cleared here. We could clear it
	 * before the __unmap_hugepage_range above, but all that's necessary
	 * is to clear it before releasing the i_mmap_mutex. This works
	 * because in the context this is called, the VMA is about to be
	 * destroyed and the i_mmap_mutex is held.
	 */
	vma->vm_flags &= ~VM_MAYSHARE;
}

void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			  unsigned long end, struct page *ref_page)
{
	struct mm_struct *mm;
	struct mmu_gather tlb;

	mm = vma->vm_mm;

	tlb_gather_mmu(&tlb, mm, start, end);
	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
	tlb_finish_mmu(&tlb, start, end);
}

/*
 * This is called when the original mapper is failing to COW a MAP_PRIVATE
 * mappping it owns the reserve page for. The intention is to unmap the page
 * from other VMAs and let the children be SIGKILLed if they are faulting the
 * same region.
 */
static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
			      struct page *page, unsigned long address)
{
	struct hstate *h = hstate_vma(vma);
	struct vm_area_struct *iter_vma;
	struct address_space *mapping;
	pgoff_t pgoff;

	/*
	 * vm_pgoff is in PAGE_SIZE units, hence the different calculation
	 * from page cache lookup which is in HPAGE_SIZE units.
	 */
	address = address & huge_page_mask(h);
	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) +
			vma->vm_pgoff;
	mapping = file_inode(vma->vm_file)->i_mapping;

	/*
	 * Take the mapping lock for the duration of the table walk. As
	 * this mapping should be shared between all the VMAs,
	 * __unmap_hugepage_range() is called as the lock is already held
	 */
	mutex_lock(&mapping->i_mmap_mutex);
	vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) {
		/* Do not unmap the current VMA */
		if (iter_vma == vma)
			continue;

		/*
		 * Unmap the page from other VMAs without their own reserves.
		 * They get marked to be SIGKILLed if they fault in these
		 * areas. This is because a future no-page fault on this VMA
		 * could insert a zeroed page instead of the data existing
		 * from the time of fork. This would look like data corruption
		 */
		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
			unmap_hugepage_range(iter_vma, address,
					     address + huge_page_size(h), page);
	}
	mutex_unlock(&mapping->i_mmap_mutex);
}

/*
 * Hugetlb_cow() should be called with page lock of the original hugepage held.
 * Called with hugetlb_instantiation_mutex held and pte_page locked so we
 * cannot race with other handlers or page migration.
 * Keep the pte_same checks anyway to make transition from the mutex easier.
 */
static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pte_t *ptep, pte_t pte,
			struct page *pagecache_page, spinlock_t *ptl)
{
	struct hstate *h = hstate_vma(vma);
	struct page *old_page, *new_page;
	int ret = 0, outside_reserve = 0;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */

	old_page = pte_page(pte);

retry_avoidcopy:
	/* If no-one else is actually using this page, avoid the copy
	 * and just make the page writable */
	if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
		page_move_anon_rmap(old_page, vma, address);
		set_huge_ptep_writable(vma, address, ptep);
		return 0;
	}

	/*
	 * If the process that created a MAP_PRIVATE mapping is about to
	 * perform a COW due to a shared page count, attempt to satisfy
	 * the allocation without using the existing reserves. The pagecache
	 * page is used to determine if the reserve at this address was
	 * consumed or not. If reserves were used, a partial faulted mapping
	 * at the time of fork() could consume its reserves on COW instead
	 * of the full address range.
	 */
	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
			old_page != pagecache_page)
		outside_reserve = 1;

	page_cache_get(old_page);

	/*
	 * Drop page table lock as buddy allocator may be called. It will
	 * be acquired again before returning to the caller, as expected.
	 */
	spin_unlock(ptl);
	new_page = alloc_huge_page(vma, address, outside_reserve);

	if (IS_ERR(new_page)) {
		/*
		 * If a process owning a MAP_PRIVATE mapping fails to COW,
		 * it is due to references held by a child and an insufficient
		 * huge page pool. To guarantee the original mappers
		 * reliability, unmap the page from child processes. The child
		 * may get SIGKILLed if it later faults.
		 */
		if (outside_reserve) {
			page_cache_release(old_page);
			BUG_ON(huge_pte_none(pte));
			unmap_ref_private(mm, vma, old_page, address);
			BUG_ON(huge_pte_none(pte));
			spin_lock(ptl);
			ptep = huge_pte_offset(mm, address & huge_page_mask(h));
			if (likely(ptep &&
				   pte_same(huge_ptep_get(ptep), pte)))
				goto retry_avoidcopy;
			/*
			 * race occurs while re-acquiring page table
			 * lock, and our job is done.
			 */
			return 0;
		}

		ret = (PTR_ERR(new_page) == -ENOMEM) ?
			VM_FAULT_OOM : VM_FAULT_SIGBUS;
		goto out_release_old;
	}

	/*
	 * When the original hugepage is shared one, it does not have
	 * anon_vma prepared.
	 */
	if (unlikely(anon_vma_prepare(vma))) {
		ret = VM_FAULT_OOM;
		goto out_release_all;
	}

	copy_user_huge_page(new_page, old_page, address, vma,
			    pages_per_huge_page(h));
	__SetPageUptodate(new_page);

	mmun_start = address & huge_page_mask(h);
	mmun_end = mmun_start + huge_page_size(h);
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	/*
	 * Retake the page table lock to check for racing updates
	 * before the page tables are altered
	 */
	spin_lock(ptl);
	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
	if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
		ClearPagePrivate(new_page);

		/* Break COW */
		huge_ptep_clear_flush(vma, address, ptep);
		set_huge_pte_at(mm, address, ptep,
				make_huge_pte(vma, new_page, 1));
		page_remove_rmap(old_page);
		hugepage_add_new_anon_rmap(new_page, vma, address);
		/* Make the old page be freed below */
		new_page = old_page;
	}
	spin_unlock(ptl);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out_release_all:
	page_cache_release(new_page);
out_release_old:
	page_cache_release(old_page);

	spin_lock(ptl); /* Caller expects lock to be held */
	return ret;
}

/* Return the pagecache page at a given address within a VMA */
static struct page *hugetlbfs_pagecache_page(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct address_space *mapping;
	pgoff_t idx;

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	return find_lock_page(mapping, idx);
}

/*
 * Return whether there is a pagecache page to back given address within VMA.
 * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page.
 */
static bool hugetlbfs_pagecache_present(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct address_space *mapping;
	pgoff_t idx;
	struct page *page;

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	page = find_get_page(mapping, idx);
	if (page)
		put_page(page);
	return page != NULL;
}

static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
			   struct address_space *mapping, pgoff_t idx,
			   unsigned long address, pte_t *ptep, unsigned int flags)
{
	struct hstate *h = hstate_vma(vma);
	int ret = VM_FAULT_SIGBUS;
	int anon_rmap = 0;
	unsigned long size;
	struct page *page;
	pte_t new_pte;
	spinlock_t *ptl;

	/*
	 * Currently, we are forced to kill the process in the event the
	 * original mapper has unmapped pages from the child due to a failed
	 * COW. Warn that such a situation has occurred as it may not be obvious
	 */
	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
		pr_warning("PID %d killed due to inadequate hugepage pool\n",
			   current->pid);
		return ret;
	}

	/*
	 * Use page lock to guard against racing truncation
	 * before we get page_table_lock.
	 */
retry:
	page = find_lock_page(mapping, idx);
	if (!page) {
		size = i_size_read(mapping->host) >> huge_page_shift(h);
		if (idx >= size)
			goto out;
		page = alloc_huge_page(vma, address, 0);
		if (IS_ERR(page)) {
			ret = PTR_ERR(page);
			if (ret == -ENOMEM)
				ret = VM_FAULT_OOM;
			else
				ret = VM_FAULT_SIGBUS;
			goto out;
		}
		clear_huge_page(page, address, pages_per_huge_page(h));
		__SetPageUptodate(page);

		if (vma->vm_flags & VM_MAYSHARE) {
			int err;
			struct inode *inode = mapping->host;

			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
			if (err) {
				put_page(page);
				if (err == -EEXIST)
					goto retry;
				goto out;
			}
			ClearPagePrivate(page);

			spin_lock(&inode->i_lock);
			inode->i_blocks += blocks_per_huge_page(h);
			spin_unlock(&inode->i_lock);
		} else {
			lock_page(page);
			if (unlikely(anon_vma_prepare(vma))) {
				ret = VM_FAULT_OOM;
				goto backout_unlocked;
			}
			anon_rmap = 1;
		}
	} else {
		/*
		 * If memory error occurs between mmap() and fault, some process
		 * don't have hwpoisoned swap entry for errored virtual address.
		 * So we need to block hugepage fault by PG_hwpoison bit check.
		 */
		if (unlikely(PageHWPoison(page))) {
			ret = VM_FAULT_HWPOISON |
				VM_FAULT_SET_HINDEX(hstate_index(h));
			goto backout_unlocked;
		}
	}

	/*
	 * If we are going to COW a private mapping later, we examine the
	 * pending reservations for this page now. This will ensure that
	 * any allocations necessary to record that reservation occur outside
	 * the spinlock.
	 */
	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
		if (vma_needs_reservation(h, vma, address) < 0) {
			ret = VM_FAULT_OOM;
			goto backout_unlocked;
		}

	ptl = huge_pte_lockptr(h, mm, ptep);
	spin_lock(ptl);
	size = i_size_read(mapping->host) >> huge_page_shift(h);
	if (idx >= size)
		goto backout;

	ret = 0;
	if (!huge_pte_none(huge_ptep_get(ptep)))
		goto backout;

	if (anon_rmap) {
		ClearPagePrivate(page);
		hugepage_add_new_anon_rmap(page, vma, address);
	} else
		page_dup_rmap(page);
	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
				&& (vma->vm_flags & VM_SHARED)));
	set_huge_pte_at(mm, address, ptep, new_pte);

	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
		/* Optimization, do the COW without a second fault */
		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
	}

	spin_unlock(ptl);
	unlock_page(page);
out:
	return ret;

backout:
	spin_unlock(ptl);
backout_unlocked:
	unlock_page(page);
	put_page(page);
	goto out;
}

#ifdef CONFIG_SMP
static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
			    struct vm_area_struct *vma,
			    struct address_space *mapping,
			    pgoff_t idx, unsigned long address)
{
	unsigned long key[2];
	u32 hash;

	if (vma->vm_flags & VM_SHARED) {
		key[0] = (unsigned long) mapping;
		key[1] = idx;
	} else {
		key[0] = (unsigned long) mm;
		key[1] = address >> huge_page_shift(h);
	}

	hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);

	return hash & (num_fault_mutexes - 1);
}
#else
/*
 * For uniprocesor systems we always use a single mutex, so just
 * return 0 and avoid the hashing overhead.
 */
static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
			    struct vm_area_struct *vma,
			    struct address_space *mapping,
			    pgoff_t idx, unsigned long address)
{
	return 0;
}
#endif

int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, unsigned int flags)
{
	pte_t *ptep, entry;
	spinlock_t *ptl;
	int ret;
	u32 hash;
	pgoff_t idx;
	struct page *page = NULL;
	struct page *pagecache_page = NULL;
	struct hstate *h = hstate_vma(vma);
	struct address_space *mapping;

	address &= huge_page_mask(h);

	ptep = huge_pte_offset(mm, address);
	if (ptep) {
		entry = huge_ptep_get(ptep);
		if (unlikely(is_hugetlb_entry_migration(entry))) {
			migration_entry_wait_huge(vma, mm, ptep);
			return 0;
		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
			return VM_FAULT_HWPOISON_LARGE |
				VM_FAULT_SET_HINDEX(hstate_index(h));
	}

	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
	if (!ptep)
		return VM_FAULT_OOM;

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	/*
	 * Serialize hugepage allocation and instantiation, so that we don't
	 * get spurious allocation failures if two CPUs race to instantiate
	 * the same page in the page cache.
	 */
	hash = fault_mutex_hash(h, mm, vma, mapping, idx, address);
	mutex_lock(&htlb_fault_mutex_table[hash]);

	entry = huge_ptep_get(ptep);
	if (huge_pte_none(entry)) {
		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
		goto out_mutex;
	}

	ret = 0;

	/*
	 * If we are going to COW the mapping later, we examine the pending
	 * reservations for this page now. This will ensure that any
	 * allocations necessary to record that reservation occur outside the
	 * spinlock. For private mappings, we also lookup the pagecache
	 * page now as it is used to determine if a reservation has been
	 * consumed.
	 */
	if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
		if (vma_needs_reservation(h, vma, address) < 0) {
			ret = VM_FAULT_OOM;
			goto out_mutex;
		}

		if (!(vma->vm_flags & VM_MAYSHARE))
			pagecache_page = hugetlbfs_pagecache_page(h,
								vma, address);
	}

	/*
	 * hugetlb_cow() requires page locks of pte_page(entry) and
	 * pagecache_page, so here we need take the former one
	 * when page != pagecache_page or !pagecache_page.
	 * Note that locking order is always pagecache_page -> page,
	 * so no worry about deadlock.
	 */
	page = pte_page(entry);
	get_page(page);
	if (page != pagecache_page)
		lock_page(page);

	ptl = huge_pte_lockptr(h, mm, ptep);
	spin_lock(ptl);
	/* Check for a racing update before calling hugetlb_cow */
	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
		goto out_ptl;


	if (flags & FAULT_FLAG_WRITE) {
		if (!huge_pte_write(entry)) {
			ret = hugetlb_cow(mm, vma, address, ptep, entry,
					pagecache_page, ptl);
			goto out_ptl;
		}
		entry = huge_pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	if (huge_ptep_set_access_flags(vma, address, ptep, entry,
						flags & FAULT_FLAG_WRITE))
		update_mmu_cache(vma, address, ptep);

out_ptl:
	spin_unlock(ptl);

	if (pagecache_page) {
		unlock_page(pagecache_page);
		put_page(pagecache_page);
	}
	if (page != pagecache_page)
		unlock_page(page);
	put_page(page);

out_mutex:
	mutex_unlock(&htlb_fault_mutex_table[hash]);
	return ret;
}

long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
			 struct page **pages, struct vm_area_struct **vmas,
			 unsigned long *position, unsigned long *nr_pages,
			 long i, unsigned int flags)
{
	unsigned long pfn_offset;
	unsigned long vaddr = *position;
	unsigned long remainder = *nr_pages;
	struct hstate *h = hstate_vma(vma);

	while (vaddr < vma->vm_end && remainder) {
		pte_t *pte;
		spinlock_t *ptl = NULL;
		int absent;
		struct page *page;

		/*
		 * Some archs (sparc64, sh*) have multiple pte_ts to
		 * each hugepage.  We have to make sure we get the
		 * first, for the page indexing below to work.
		 *
		 * Note that page table lock is not held when pte is null.
		 */
		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
		if (pte)
			ptl = huge_pte_lock(h, mm, pte);
		absent = !pte || huge_pte_none(huge_ptep_get(pte));

		/*
		 * When coredumping, it suits get_dump_page if we just return
		 * an error where there's an empty slot with no huge pagecache
		 * to back it.  This way, we avoid allocating a hugepage, and
		 * the sparse dumpfile avoids allocating disk blocks, but its
		 * huge holes still show up with zeroes where they need to be.
		 */
		if (absent && (flags & FOLL_DUMP) &&
		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
			if (pte)
				spin_unlock(ptl);
			remainder = 0;
			break;
		}

		/*
		 * We need call hugetlb_fault for both hugepages under migration
		 * (in which case hugetlb_fault waits for the migration,) and
		 * hwpoisoned hugepages (in which case we need to prevent the
		 * caller from accessing to them.) In order to do this, we use
		 * here is_swap_pte instead of is_hugetlb_entry_migration and
		 * is_hugetlb_entry_hwpoisoned. This is because it simply covers
		 * both cases, and because we can't follow correct pages
		 * directly from any kind of swap entries.
		 */
		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
		    ((flags & FOLL_WRITE) &&
		      !huge_pte_write(huge_ptep_get(pte)))) {
			int ret;

			if (pte)
				spin_unlock(ptl);
			ret = hugetlb_fault(mm, vma, vaddr,
				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
			if (!(ret & VM_FAULT_ERROR))
				continue;

			remainder = 0;
			break;
		}

		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
		page = pte_page(huge_ptep_get(pte));
same_page:
		if (pages) {
			pages[i] = mem_map_offset(page, pfn_offset);
			get_page_foll(pages[i]);
		}

		if (vmas)
			vmas[i] = vma;

		vaddr += PAGE_SIZE;
		++pfn_offset;
		--remainder;
		++i;
		if (vaddr < vma->vm_end && remainder &&
				pfn_offset < pages_per_huge_page(h)) {
			/*
			 * We use pfn_offset to avoid touching the pageframes
			 * of this compound page.
			 */
			goto same_page;
		}
		spin_unlock(ptl);
	}
	*nr_pages = remainder;
	*position = vaddr;

	return i ? i : -EFAULT;
}

unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
		unsigned long address, unsigned long end, pgprot_t newprot)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long start = address;
	pte_t *ptep;
	pte_t pte;
	struct hstate *h = hstate_vma(vma);
	unsigned long pages = 0;

	BUG_ON(address >= end);
	flush_cache_range(vma, address, end);

	mmu_notifier_invalidate_range_start(mm, start, end);
	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
	for (; address < end; address += huge_page_size(h)) {
		spinlock_t *ptl;
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;
		ptl = huge_pte_lock(h, mm, ptep);
		if (huge_pmd_unshare(mm, &address, ptep)) {
			pages++;
			spin_unlock(ptl);
			continue;
		}
		if (!huge_pte_none(huge_ptep_get(ptep))) {
			pte = huge_ptep_get_and_clear(mm, address, ptep);
			pte = pte_mkhuge(huge_pte_modify(pte, newprot));
			pte = arch_make_huge_pte(pte, vma, NULL, 0);
			set_huge_pte_at(mm, address, ptep, pte);
			pages++;
		}
		spin_unlock(ptl);
	}
	/*
	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
	 * may have cleared our pud entry and done put_page on the page table:
	 * once we release i_mmap_mutex, another task can do the final put_page
	 * and that page table be reused and filled with junk.
	 */
	flush_tlb_range(vma, start, end);
	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
	mmu_notifier_invalidate_range_end(mm, start, end);

	return pages << h->order;
}

int hugetlb_reserve_pages(struct inode *inode,
					long from, long to,
					struct vm_area_struct *vma,
					vm_flags_t vm_flags)
{
	long ret, chg;
	struct hstate *h = hstate_inode(inode);
	struct hugepage_subpool *spool = subpool_inode(inode);
	struct resv_map *resv_map;

	/*
	 * Only apply hugepage reservation if asked. At fault time, an
	 * attempt will be made for VM_NORESERVE to allocate a page
	 * without using reserves
	 */
	if (vm_flags & VM_NORESERVE)
		return 0;

	/*
	 * Shared mappings base their reservation on the number of pages that
	 * are already allocated on behalf of the file. Private mappings need
	 * to reserve the full area even if read-only as mprotect() may be
	 * called to make the mapping read-write. Assume !vma is a shm mapping
	 */
	if (!vma || vma->vm_flags & VM_MAYSHARE) {
		resv_map = inode_resv_map(inode);

		chg = region_chg(resv_map, from, to);

	} else {
		resv_map = resv_map_alloc();
		if (!resv_map)
			return -ENOMEM;

		chg = to - from;

		set_vma_resv_map(vma, resv_map);
		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
	}

	if (chg < 0) {
		ret = chg;
		goto out_err;
	}

	/* There must be enough pages in the subpool for the mapping */
	if (hugepage_subpool_get_pages(spool, chg)) {
		ret = -ENOSPC;
		goto out_err;
	}

	/*
	 * Check enough hugepages are available for the reservation.
	 * Hand the pages back to the subpool if there are not
	 */
	ret = hugetlb_acct_memory(h, chg);
	if (ret < 0) {
		hugepage_subpool_put_pages(spool, chg);
		goto out_err;
	}

	/*
	 * Account for the reservations made. Shared mappings record regions
	 * that have reservations as they are shared by multiple VMAs.
	 * When the last VMA disappears, the region map says how much
	 * the reservation was and the page cache tells how much of
	 * the reservation was consumed. Private mappings are per-VMA and
	 * only the consumed reservations are tracked. When the VMA
	 * disappears, the original reservation is the VMA size and the
	 * consumed reservations are stored in the map. Hence, nothing
	 * else has to be done for private mappings here
	 */
	if (!vma || vma->vm_flags & VM_MAYSHARE)
		region_add(resv_map, from, to);
	return 0;
out_err:
	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		kref_put(&resv_map->refs, resv_map_release);
	return ret;
}

void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
{
	struct hstate *h = hstate_inode(inode);
	struct resv_map *resv_map = inode_resv_map(inode);
	long chg = 0;
	struct hugepage_subpool *spool = subpool_inode(inode);

	if (resv_map)
		chg = region_truncate(resv_map, offset);
	spin_lock(&inode->i_lock);
	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
	spin_unlock(&inode->i_lock);

	hugepage_subpool_put_pages(spool, (chg - freed));
	hugetlb_acct_memory(h, -(chg - freed));
}

#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
static unsigned long page_table_shareable(struct vm_area_struct *svma,
				struct vm_area_struct *vma,
				unsigned long addr, pgoff_t idx)
{
	unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
				svma->vm_start;
	unsigned long sbase = saddr & PUD_MASK;
	unsigned long s_end = sbase + PUD_SIZE;

	/* Allow segments to share if only one is marked locked */
	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;

	/*
	 * match the virtual addresses, permission and the alignment of the
	 * page table page.
	 */
	if (pmd_index(addr) != pmd_index(saddr) ||
	    vm_flags != svm_flags ||
	    sbase < svma->vm_start || svma->vm_end < s_end)
		return 0;

	return saddr;
}

static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
{
	unsigned long base = addr & PUD_MASK;
	unsigned long end = base + PUD_SIZE;

	/*
	 * check on proper vm_flags and page table alignment
	 */
	if (vma->vm_flags & VM_MAYSHARE &&
	    vma->vm_start <= base && end <= vma->vm_end)
		return 1;
	return 0;
}

/*
 * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
 * and returns the corresponding pte. While this is not necessary for the
 * !shared pmd case because we can allocate the pmd later as well, it makes the
 * code much cleaner. pmd allocation is essential for the shared case because
 * pud has to be populated inside the same i_mmap_mutex section - otherwise
 * racing tasks could either miss the sharing (see huge_pte_offset) or select a
 * bad pmd for sharing.
 */
pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
{
	struct vm_area_struct *vma = find_vma(mm, addr);
	struct address_space *mapping = vma->vm_file->f_mapping;
	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
			vma->vm_pgoff;
	struct vm_area_struct *svma;
	unsigned long saddr;
	pte_t *spte = NULL;
	pte_t *pte;
	spinlock_t *ptl;

	if (!vma_shareable(vma, addr))
		return (pte_t *)pmd_alloc(mm, pud, addr);

	mutex_lock(&mapping->i_mmap_mutex);
	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
		if (svma == vma)
			continue;

		saddr = page_table_shareable(svma, vma, addr, idx);
		if (saddr) {
			spte = huge_pte_offset(svma->vm_mm, saddr);
			if (spte) {
				get_page(virt_to_page(spte));
				break;
			}
		}
	}

	if (!spte)
		goto out;

	ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte);
	spin_lock(ptl);
	if (pud_none(*pud))
		pud_populate(mm, pud,
				(pmd_t *)((unsigned long)spte & PAGE_MASK));
	else
		put_page(virt_to_page(spte));
	spin_unlock(ptl);
out:
	pte = (pte_t *)pmd_alloc(mm, pud, addr);
	mutex_unlock(&mapping->i_mmap_mutex);
	return pte;
}

/*
 * unmap huge page backed by shared pte.
 *
 * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
 * indicated by page_count > 1, unmap is achieved by clearing pud and
 * decrementing the ref count. If count == 1, the pte page is not shared.
 *
 * called with page table lock held.
 *
 * returns: 1 successfully unmapped a shared pte page
 *	    0 the underlying pte page is not shared, or it is the last user
 */
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
{
	pgd_t *pgd = pgd_offset(mm, *addr);
	pud_t *pud = pud_offset(pgd, *addr);

	BUG_ON(page_count(virt_to_page(ptep)) == 0);
	if (page_count(virt_to_page(ptep)) == 1)
		return 0;

	pud_clear(pud);
	put_page(virt_to_page(ptep));
	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
	return 1;
}
#define want_pmd_share()	(1)
#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
{
	return NULL;
}
#define want_pmd_share()	(0)
#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */

#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
pte_t *huge_pte_alloc(struct mm_struct *mm,
			unsigned long addr, unsigned long sz)
{
	pgd_t *pgd;
	pud_t *pud;
	pte_t *pte = NULL;

	pgd = pgd_offset(mm, addr);
	pud = pud_alloc(mm, pgd, addr);
	if (pud) {
		if (sz == PUD_SIZE) {
			pte = (pte_t *)pud;
		} else {
			BUG_ON(sz != PMD_SIZE);
			if (want_pmd_share() && pud_none(*pud))
				pte = huge_pmd_share(mm, addr, pud);
			else
				pte = (pte_t *)pmd_alloc(mm, pud, addr);
		}
	}
	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));

	return pte;
}

pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd = NULL;

	pgd = pgd_offset(mm, addr);
	if (pgd_present(*pgd)) {
		pud = pud_offset(pgd, addr);
		if (pud_present(*pud)) {
			if (pud_huge(*pud))
				return (pte_t *)pud;
			pmd = pmd_offset(pud, addr);
		}
	}
	return (pte_t *) pmd;
}

struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
		pmd_t *pmd, int write)
{
	struct page *page;

	page = pte_page(*(pte_t *)pmd);
	if (page)
		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
	return page;
}

struct page *
follow_huge_pud(struct mm_struct *mm, unsigned long address,
		pud_t *pud, int write)
{
	struct page *page;

	page = pte_page(*(pte_t *)pud);
	if (page)
		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
	return page;
}

#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */

/* Can be overriden by architectures */
struct page * __weak
follow_huge_pud(struct mm_struct *mm, unsigned long address,
	       pud_t *pud, int write)
{
	BUG();
	return NULL;
}

#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */

#ifdef CONFIG_MEMORY_FAILURE

/* Should be called in hugetlb_lock */
static int is_hugepage_on_freelist(struct page *hpage)
{
	struct page *page;
	struct page *tmp;
	struct hstate *h = page_hstate(hpage);
	int nid = page_to_nid(hpage);

	list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru)
		if (page == hpage)
			return 1;
	return 0;
}

/*
 * This function is called from memory failure code.
 * Assume the caller holds page lock of the head page.
 */
int dequeue_hwpoisoned_huge_page(struct page *hpage)
{
	struct hstate *h = page_hstate(hpage);
	int nid = page_to_nid(hpage);
	int ret = -EBUSY;

	spin_lock(&hugetlb_lock);
	if (is_hugepage_on_freelist(hpage)) {
		/*
		 * Hwpoisoned hugepage isn't linked to activelist or freelist,
		 * but dangling hpage->lru can trigger list-debug warnings
		 * (this happens when we call unpoison_memory() on it),
		 * so let it point to itself with list_del_init().
		 */
		list_del_init(&hpage->lru);
		set_page_refcounted(hpage);
		h->free_huge_pages--;
		h->free_huge_pages_node[nid]--;
		ret = 0;
	}
	spin_unlock(&hugetlb_lock);
	return ret;
}
#endif

bool isolate_huge_page(struct page *page, struct list_head *list)
{
	VM_BUG_ON_PAGE(!PageHead(page), page);
	if (!get_page_unless_zero(page))
		return false;
	spin_lock(&hugetlb_lock);
	list_move_tail(&page->lru, list);
	spin_unlock(&hugetlb_lock);
	return true;
}

void putback_active_hugepage(struct page *page)
{
	VM_BUG_ON_PAGE(!PageHead(page), page);
	spin_lock(&hugetlb_lock);
	list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist);
	spin_unlock(&hugetlb_lock);
	put_page(page);
}

bool is_hugepage_active(struct page *page)
{
	VM_BUG_ON_PAGE(!PageHuge(page), page);
	/*
	 * This function can be called for a tail page because the caller,
	 * scan_movable_pages, scans through a given pfn-range which typically
	 * covers one memory block. In systems using gigantic hugepage (1GB
	 * for x86_64,) a hugepage is larger than a memory block, and we don't
	 * support migrating such large hugepages for now, so return false
	 * when called for tail pages.
	 */
	if (PageTail(page))
		return false;
	/*
	 * Refcount of a hwpoisoned hugepages is 1, but they are not active,
	 * so we should return false for them.
	 */
	if (unlikely(PageHWPoison(page)))
		return false;
	return page_count(page) > 0;
}