mm/hugetlb.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Generic hugetlb support.
 * (C) Nadia Yvette Chambers, April 2004
 */
#include <linux/list.h>
#include <linux/init.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/memblock.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/sched/mm.h>
#include <linux/mmdebug.h>
#include <linux/sched/signal.h>
#include <linux/rmap.h>
#include <linux/string_helpers.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/jhash.h>
#include <linux/numa.h>
#include <linux/llist.h>
#include <linux/cma.h>
#include <linux/migrate.h>

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

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

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

#ifdef CONFIG_CMA
static struct cma *hugetlb_cma[MAX_NUMNODES];
#endif
static unsigned long hugetlb_cma_size __initdata;

/*
 * Minimum page order among possible hugepage sizes, set to a proper value
 * at boot time.
 */
static unsigned int minimum_order __read_mostly = UINT_MAX;

__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 bool __initdata parsed_valid_hugepagesz = true;
static bool __initdata parsed_default_hugepagesz;

/*
 * 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;
struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;

/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);

static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
	if (spool->count)
		return false;
	if (spool->max_hpages != -1)
		return spool->used_hpages == 0;
	if (spool->min_hpages != -1)
		return spool->rsv_hpages == spool->min_hpages;

	return true;
}

static inline void unlock_or_release_subpool(struct hugepage_subpool *spool,
						unsigned long irq_flags)
{
	spin_unlock_irqrestore(&spool->lock, irq_flags);

	/* If no pages are used, and no other handles to the subpool
	 * remain, give up any reservations based on minimum size and
	 * free the subpool */
	if (subpool_is_free(spool)) {
		if (spool->min_hpages != -1)
			hugetlb_acct_memory(spool->hstate,
						-spool->min_hpages);
		kfree(spool);
	}
}

struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
						long min_hpages)
{
	struct hugepage_subpool *spool;

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

	spin_lock_init(&spool->lock);
	spool->count = 1;
	spool->max_hpages = max_hpages;
	spool->hstate = h;
	spool->min_hpages = min_hpages;

	if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
		kfree(spool);
		return NULL;
	}
	spool->rsv_hpages = min_hpages;

	return spool;
}

void hugepage_put_subpool(struct hugepage_subpool *spool)
{
	unsigned long flags;

	spin_lock_irqsave(&spool->lock, flags);
	BUG_ON(!spool->count);
	spool->count--;
	unlock_or_release_subpool(spool, flags);
}

/*
 * Subpool accounting for allocating and reserving pages.
 * Return -ENOMEM if there are not enough resources to satisfy the
 * request.  Otherwise, return the number of pages by which the
 * global pools must be adjusted (upward).  The returned value may
 * only be different than the passed value (delta) in the case where
 * a subpool minimum size must be maintained.
 */
static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
				      long delta)
{
	long ret = delta;

	if (!spool)
		return ret;

	spin_lock_irq(&spool->lock);

	if (spool->max_hpages != -1) {		/* maximum size accounting */
		if ((spool->used_hpages + delta) <= spool->max_hpages)
			spool->used_hpages += delta;
		else {
			ret = -ENOMEM;
			goto unlock_ret;
		}
	}

	/* minimum size accounting */
	if (spool->min_hpages != -1 && spool->rsv_hpages) {
		if (delta > spool->rsv_hpages) {
			/*
			 * Asking for more reserves than those already taken on
			 * behalf of subpool.  Return difference.
			 */
			ret = delta - spool->rsv_hpages;
			spool->rsv_hpages = 0;
		} else {
			ret = 0;	/* reserves already accounted for */
			spool->rsv_hpages -= delta;
		}
	}

unlock_ret:
	spin_unlock_irq(&spool->lock);
	return ret;
}

/*
 * Subpool accounting for freeing and unreserving pages.
 * Return the number of global page reservations that must be dropped.
 * The return value may only be different than the passed value (delta)
 * in the case where a subpool minimum size must be maintained.
 */
static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
				       long delta)
{
	long ret = delta;
	unsigned long flags;

	if (!spool)
		return delta;

	spin_lock_irqsave(&spool->lock, flags);

	if (spool->max_hpages != -1)		/* maximum size accounting */
		spool->used_hpages -= delta;

	 /* minimum size accounting */
	if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) {
		if (spool->rsv_hpages + delta <= spool->min_hpages)
			ret = 0;
		else
			ret = spool->rsv_hpages + delta - spool->min_hpages;

		spool->rsv_hpages += delta;
		if (spool->rsv_hpages > spool->min_hpages)
			spool->rsv_hpages = spool->min_hpages;
	}

	/*
	 * If hugetlbfs_put_super couldn't free spool due to an outstanding
	 * quota reference, free it now.
	 */
	unlock_or_release_subpool(spool, flags);

	return ret;
}

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));
}

/* Helper that removes a struct file_region from the resv_map cache and returns
 * it for use.
 */
static struct file_region *
get_file_region_entry_from_cache(struct resv_map *resv, long from, long to)
{
	struct file_region *nrg = NULL;

	VM_BUG_ON(resv->region_cache_count <= 0);

	resv->region_cache_count--;
	nrg = list_first_entry(&resv->region_cache, struct file_region, link);
	list_del(&nrg->link);

	nrg->from = from;
	nrg->to = to;

	return nrg;
}

static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg,
					      struct file_region *rg)
{
#ifdef CONFIG_CGROUP_HUGETLB
	nrg->reservation_counter = rg->reservation_counter;
	nrg->css = rg->css;
	if (rg->css)
		css_get(rg->css);
#endif
}

/* Helper that records hugetlb_cgroup uncharge info. */
static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
						struct hstate *h,
						struct resv_map *resv,
						struct file_region *nrg)
{
#ifdef CONFIG_CGROUP_HUGETLB
	if (h_cg) {
		nrg->reservation_counter =
			&h_cg->rsvd_hugepage[hstate_index(h)];
		nrg->css = &h_cg->css;
		/*
		 * The caller will hold exactly one h_cg->css reference for the
		 * whole contiguous reservation region. But this area might be
		 * scattered when there are already some file_regions reside in
		 * it. As a result, many file_regions may share only one css
		 * reference. In order to ensure that one file_region must hold
		 * exactly one h_cg->css reference, we should do css_get for
		 * each file_region and leave the reference held by caller
		 * untouched.
		 */
		css_get(&h_cg->css);
		if (!resv->pages_per_hpage)
			resv->pages_per_hpage = pages_per_huge_page(h);
		/* pages_per_hpage should be the same for all entries in
		 * a resv_map.
		 */
		VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h));
	} else {
		nrg->reservation_counter = NULL;
		nrg->css = NULL;
	}
#endif
}

static void put_uncharge_info(struct file_region *rg)
{
#ifdef CONFIG_CGROUP_HUGETLB
	if (rg->css)
		css_put(rg->css);
#endif
}

static bool has_same_uncharge_info(struct file_region *rg,
				   struct file_region *org)
{
#ifdef CONFIG_CGROUP_HUGETLB
	return rg && org &&
	       rg->reservation_counter == org->reservation_counter &&
	       rg->css == org->css;

#else
	return true;
#endif
}

static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
{
	struct file_region *nrg = NULL, *prg = NULL;

	prg = list_prev_entry(rg, link);
	if (&prg->link != &resv->regions && prg->to == rg->from &&
	    has_same_uncharge_info(prg, rg)) {
		prg->to = rg->to;

		list_del(&rg->link);
		put_uncharge_info(rg);
		kfree(rg);

		rg = prg;
	}

	nrg = list_next_entry(rg, link);
	if (&nrg->link != &resv->regions && nrg->from == rg->to &&
	    has_same_uncharge_info(nrg, rg)) {
		nrg->from = rg->from;

		list_del(&rg->link);
		put_uncharge_info(rg);
		kfree(rg);
	}
}

static inline long
hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from,
		     long to, struct hstate *h, struct hugetlb_cgroup *cg,
		     long *regions_needed)
{
	struct file_region *nrg;

	if (!regions_needed) {
		nrg = get_file_region_entry_from_cache(map, from, to);
		record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg);
		list_add(&nrg->link, rg->link.prev);
		coalesce_file_region(map, nrg);
	} else
		*regions_needed += 1;

	return to - from;
}

/*
 * Must be called with resv->lock held.
 *
 * Calling this with regions_needed != NULL will count the number of pages
 * to be added but will not modify the linked list. And regions_needed will
 * indicate the number of file_regions needed in the cache to carry out to add
 * the regions for this range.
 */
static long add_reservation_in_range(struct resv_map *resv, long f, long t,
				     struct hugetlb_cgroup *h_cg,
				     struct hstate *h, long *regions_needed)
{
	long add = 0;
	struct list_head *head = &resv->regions;
	long last_accounted_offset = f;
	struct file_region *rg = NULL, *trg = NULL;

	if (regions_needed)
		*regions_needed = 0;

	/* In this loop, we essentially handle an entry for the range
	 * [last_accounted_offset, rg->from), at every iteration, with some
	 * bounds checking.
	 */
	list_for_each_entry_safe(rg, trg, head, link) {
		/* Skip irrelevant regions that start before our range. */
		if (rg->from < f) {
			/* If this region ends after the last accounted offset,
			 * then we need to update last_accounted_offset.
			 */
			if (rg->to > last_accounted_offset)
				last_accounted_offset = rg->to;
			continue;
		}

		/* When we find a region that starts beyond our range, we've
		 * finished.
		 */
		if (rg->from >= t)
			break;

		/* Add an entry for last_accounted_offset -> rg->from, and
		 * update last_accounted_offset.
		 */
		if (rg->from > last_accounted_offset)
			add += hugetlb_resv_map_add(resv, rg,
						    last_accounted_offset,
						    rg->from, h, h_cg,
						    regions_needed);

		last_accounted_offset = rg->to;
	}

	/* Handle the case where our range extends beyond
	 * last_accounted_offset.
	 */
	if (last_accounted_offset < t)
		add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
					    t, h, h_cg, regions_needed);

	VM_BUG_ON(add < 0);
	return add;
}

/* Must be called with resv->lock acquired. Will drop lock to allocate entries.
 */
static int allocate_file_region_entries(struct resv_map *resv,
					int regions_needed)
	__must_hold(&resv->lock)
{
	struct list_head allocated_regions;
	int to_allocate = 0, i = 0;
	struct file_region *trg = NULL, *rg = NULL;

	VM_BUG_ON(regions_needed < 0);

	INIT_LIST_HEAD(&allocated_regions);

	/*
	 * Check for sufficient descriptors in the cache to accommodate
	 * the number of in progress add operations plus regions_needed.
	 *
	 * This is a while loop because when we drop the lock, some other call
	 * to region_add or region_del may have consumed some region_entries,
	 * so we keep looping here until we finally have enough entries for
	 * (adds_in_progress + regions_needed).
	 */
	while (resv->region_cache_count <
	       (resv->adds_in_progress + regions_needed)) {
		to_allocate = resv->adds_in_progress + regions_needed -
			      resv->region_cache_count;

		/* At this point, we should have enough entries in the cache
		 * for all the existing adds_in_progress. We should only be
		 * needing to allocate for regions_needed.
		 */
		VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress);

		spin_unlock(&resv->lock);
		for (i = 0; i < to_allocate; i++) {
			trg = kmalloc(sizeof(*trg), GFP_KERNEL);
			if (!trg)
				goto out_of_memory;
			list_add(&trg->link, &allocated_regions);
		}

		spin_lock(&resv->lock);

		list_splice(&allocated_regions, &resv->region_cache);
		resv->region_cache_count += to_allocate;
	}

	return 0;

out_of_memory:
	list_for_each_entry_safe(rg, trg, &allocated_regions, link) {
		list_del(&rg->link);
		kfree(rg);
	}
	return -ENOMEM;
}

/*
 * Add the huge page range represented by [f, t) to the reserve
 * map.  Regions will be taken from the cache to fill in this range.
 * Sufficient regions should exist in the cache due to the previous
 * call to region_chg with the same range, but in some cases the cache will not
 * have sufficient entries due to races with other code doing region_add or
 * region_del.  The extra needed entries will be allocated.
 *
 * regions_needed is the out value provided by a previous call to region_chg.
 *
 * Return the number of new huge pages added to the map.  This number is greater
 * than or equal to zero.  If file_region entries needed to be allocated for
 * this operation and we were not able to allocate, it returns -ENOMEM.
 * region_add of regions of length 1 never allocate file_regions and cannot
 * fail; region_chg will always allocate at least 1 entry and a region_add for
 * 1 page will only require at most 1 entry.
 */
static long region_add(struct resv_map *resv, long f, long t,
		       long in_regions_needed, struct hstate *h,
		       struct hugetlb_cgroup *h_cg)
{
	long add = 0, actual_regions_needed = 0;

	spin_lock(&resv->lock);
retry:

	/* Count how many regions are actually needed to execute this add. */
	add_reservation_in_range(resv, f, t, NULL, NULL,
				 &actual_regions_needed);

	/*
	 * Check for sufficient descriptors in the cache to accommodate
	 * this add operation. Note that actual_regions_needed may be greater
	 * than in_regions_needed, as the resv_map may have been modified since
	 * the region_chg call. In this case, we need to make sure that we
	 * allocate extra entries, such that we have enough for all the
	 * existing adds_in_progress, plus the excess needed for this
	 * operation.
	 */
	if (actual_regions_needed > in_regions_needed &&
	    resv->region_cache_count <
		    resv->adds_in_progress +
			    (actual_regions_needed - in_regions_needed)) {
		/* region_add operation of range 1 should never need to
		 * allocate file_region entries.
		 */
		VM_BUG_ON(t - f <= 1);

		if (allocate_file_region_entries(
			    resv, actual_regions_needed - in_regions_needed)) {
			return -ENOMEM;
		}

		goto retry;
	}

	add = add_reservation_in_range(resv, f, t, h_cg, h, NULL);

	resv->adds_in_progress -= in_regions_needed;

	spin_unlock(&resv->lock);
	return add;
}

/*
 * Examine the existing reserve map and determine how many
 * huge pages in the specified range [f, t) are NOT currently
 * represented.  This routine is called before a subsequent
 * call to region_add that will actually modify the reserve
 * map to add the specified range [f, t).  region_chg does
 * not change the number of huge pages represented by the
 * map.  A number of new file_region structures is added to the cache as a
 * placeholder, for the subsequent region_add call to use. At least 1
 * file_region structure is added.
 *
 * out_regions_needed is the number of regions added to the
 * resv->adds_in_progress.  This value needs to be provided to a follow up call
 * to region_add or region_abort for proper accounting.
 *
 * Returns the number of huge pages that need to be added to the existing
 * reservation map for the range [f, t).  This number is greater or equal to
 * zero.  -ENOMEM is returned if a new file_region structure or cache entry
 * is needed and can not be allocated.
 */
static long region_chg(struct resv_map *resv, long f, long t,
		       long *out_regions_needed)
{
	long chg = 0;

	spin_lock(&resv->lock);

	/* Count how many hugepages in this range are NOT represented. */
	chg = add_reservation_in_range(resv, f, t, NULL, NULL,
				       out_regions_needed);

	if (*out_regions_needed == 0)
		*out_regions_needed = 1;

	if (allocate_file_region_entries(resv, *out_regions_needed))
		return -ENOMEM;

	resv->adds_in_progress += *out_regions_needed;

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

/*
 * Abort the in progress add operation.  The adds_in_progress field
 * of the resv_map keeps track of the operations in progress between
 * calls to region_chg and region_add.  Operations are sometimes
 * aborted after the call to region_chg.  In such cases, region_abort
 * is called to decrement the adds_in_progress counter. regions_needed
 * is the value returned by the region_chg call, it is used to decrement
 * the adds_in_progress counter.
 *
 * NOTE: The range arguments [f, t) are not needed or used in this
 * routine.  They are kept to make reading the calling code easier as
 * arguments will match the associated region_chg call.
 */
static void region_abort(struct resv_map *resv, long f, long t,
			 long regions_needed)
{
	spin_lock(&resv->lock);
	VM_BUG_ON(!resv->region_cache_count);
	resv->adds_in_progress -= regions_needed;
	spin_unlock(&resv->lock);
}

/*
 * Delete the specified range [f, t) from the reserve map.  If the
 * t parameter is LONG_MAX, this indicates that ALL regions after f
 * should be deleted.  Locate the regions which intersect [f, t)
 * and either trim, delete or split the existing regions.
 *
 * Returns the number of huge pages deleted from the reserve map.
 * In the normal case, the return value is zero or more.  In the
 * case where a region must be split, a new region descriptor must
 * be allocated.  If the allocation fails, -ENOMEM will be returned.
 * NOTE: If the parameter t == LONG_MAX, then we will never split
 * a region and possibly return -ENOMEM.  Callers specifying
 * t == LONG_MAX do not need to check for -ENOMEM error.
 */
static long region_del(struct resv_map *resv, long f, long t)
{
	struct list_head *head = &resv->regions;
	struct file_region *rg, *trg;
	struct file_region *nrg = NULL;
	long del = 0;

retry:
	spin_lock(&resv->lock);
	list_for_each_entry_safe(rg, trg, head, link) {
		/*
		 * Skip regions before the range to be deleted.  file_region
		 * ranges are normally of the form [from, to).  However, there
		 * may be a "placeholder" entry in the map which is of the form
		 * (from, to) with from == to.  Check for placeholder entries
		 * at the beginning of the range to be deleted.
		 */
		if (rg->to <= f && (rg->to != rg->from || rg->to != f))
			continue;

		if (rg->from >= t)
			break;

		if (f > rg->from && t < rg->to) { /* Must split region */
			/*
			 * Check for an entry in the cache before dropping
			 * lock and attempting allocation.
			 */
			if (!nrg &&
			    resv->region_cache_count > resv->adds_in_progress) {
				nrg = list_first_entry(&resv->region_cache,
							struct file_region,
							link);
				list_del(&nrg->link);
				resv->region_cache_count--;
			}

			if (!nrg) {
				spin_unlock(&resv->lock);
				nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
				if (!nrg)
					return -ENOMEM;
				goto retry;
			}

			del += t - f;
			hugetlb_cgroup_uncharge_file_region(
				resv, rg, t - f, false);

			/* New entry for end of split region */
			nrg->from = t;
			nrg->to = rg->to;

			copy_hugetlb_cgroup_uncharge_info(nrg, rg);

			INIT_LIST_HEAD(&nrg->link);

			/* Original entry is trimmed */
			rg->to = f;

			list_add(&nrg->link, &rg->link);
			nrg = NULL;
			break;
		}

		if (f <= rg->from && t >= rg->to) { /* Remove entire region */
			del += rg->to - rg->from;
			hugetlb_cgroup_uncharge_file_region(resv, rg,
							    rg->to - rg->from, true);
			list_del(&rg->link);
			kfree(rg);
			continue;
		}

		if (f <= rg->from) {	/* Trim beginning of region */
			hugetlb_cgroup_uncharge_file_region(resv, rg,
							    t - rg->from, false);

			del += t - rg->from;
			rg->from = t;
		} else {		/* Trim end of region */
			hugetlb_cgroup_uncharge_file_region(resv, rg,
							    rg->to - f, false);

			del += rg->to - f;
			rg->to = f;
		}
	}

	spin_unlock(&resv->lock);
	kfree(nrg);
	return del;
}

/*
 * A rare out of memory error was encountered which prevented removal of
 * the reserve map region for a page.  The huge page itself was free'ed
 * and removed from the page cache.  This routine will adjust the subpool
 * usage count, and the global reserve count if needed.  By incrementing
 * these counts, the reserve map entry which could not be deleted will
 * appear as a "reserved" entry instead of simply dangling with incorrect
 * counts.
 */
void hugetlb_fix_reserve_counts(struct inode *inode)
{
	struct hugepage_subpool *spool = subpool_inode(inode);
	long rsv_adjust;
	bool reserved = false;

	rsv_adjust = hugepage_subpool_get_pages(spool, 1);
	if (rsv_adjust > 0) {
		struct hstate *h = hstate_inode(inode);

		if (!hugetlb_acct_memory(h, 1))
			reserved = true;
	} else if (!rsv_adjust) {
		reserved = true;
	}

	if (!reserved)
		pr_warn("hugetlb: Huge Page Reserved count may go negative.\n");
}

/*
 * Count and return the number of huge pages in the reserve map
 * that intersect with the range [f, t).
 */
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);
}
EXPORT_SYMBOL_GPL(linear_hugepage_index);

/*
 * 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)
{
	if (vma->vm_ops && vma->vm_ops->pagesize)
		return vma->vm_ops->pagesize(vma);
	return PAGE_SIZE;
}
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 'strong'
 * version of this symbol is required.
 */
__weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
	return vma_kernel_pagesize(vma);
}

/*
 * 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;
}

static void
resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map,
					  struct hugetlb_cgroup *h_cg,
					  struct hstate *h)
{
#ifdef CONFIG_CGROUP_HUGETLB
	if (!h_cg || !h) {
		resv_map->reservation_counter = NULL;
		resv_map->pages_per_hpage = 0;
		resv_map->css = NULL;
	} else {
		resv_map->reservation_counter =
			&h_cg->rsvd_hugepage[hstate_index(h)];
		resv_map->pages_per_hpage = pages_per_huge_page(h);
		resv_map->css = &h_cg->css;
	}
#endif
}

struct resv_map *resv_map_alloc(void)
{
	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
	struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL);

	if (!resv_map || !rg) {
		kfree(resv_map);
		kfree(rg);
		return NULL;
	}

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

	resv_map->adds_in_progress = 0;
	/*
	 * Initialize these to 0. On shared mappings, 0's here indicate these
	 * fields don't do cgroup accounting. On private mappings, these will be
	 * re-initialized to the proper values, to indicate that hugetlb cgroup
	 * reservations are to be un-charged from here.
	 */
	resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL);

	INIT_LIST_HEAD(&resv_map->region_cache);
	list_add(&rg->link, &resv_map->region_cache);
	resv_map->region_cache_count = 1;

	return resv_map;
}

void resv_map_release(struct kref *ref)
{
	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
	struct list_head *head = &resv_map->region_cache;
	struct file_region *rg, *trg;

	/* Clear out any active regions before we release the map. */
	region_del(resv_map, 0, LONG_MAX);

	/* ... and any entries left in the cache */
	list_for_each_entry_safe(rg, trg, head, link) {
		list_del(&rg->link);
		kfree(rg);
	}

	VM_BUG_ON(resv_map->adds_in_progress);

	kfree(resv_map);
}

static inline struct resv_map *inode_resv_map(struct inode *inode)
{
	/*
	 * At inode evict time, i_mapping may not point to the original
	 * address space within the inode.  This original address space
	 * contains the pointer to the resv_map.  So, always use the
	 * address space embedded within the inode.
	 * The VERY common case is inode->mapping == &inode->i_data but,
	 * this may not be true for device special inodes.
	 */
	return (struct resv_map *)(&inode->i_data)->private_data;
}

static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), 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_VMA(!is_vm_hugetlb_page(vma), vma);
	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);

	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_VMA(!is_vm_hugetlb_page(vma), vma);
	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);

	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_VMA(!is_vm_hugetlb_page(vma), 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_VMA(!is_vm_hugetlb_page(vma), vma);
	if (!(vma->vm_flags & VM_MAYSHARE))
		vma->vm_private_data = (void *)0;
}

/* Returns true if the VMA has associated reserve pages */
static bool 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 true;
		else
			return false;
	}

	/* Shared mappings always use reserves */
	if (vma->vm_flags & VM_MAYSHARE) {
		/*
		 * We know VM_NORESERVE is not set.  Therefore, there SHOULD
		 * be a region map for all pages.  The only situation where
		 * there is no region map is if a hole was punched via
		 * fallocate.  In this case, there really are no reserves to
		 * use.  This situation is indicated if chg != 0.
		 */
		if (chg)
			return false;
		else
			return true;
	}

	/*
	 * Only the process that called mmap() has reserves for
	 * private mappings.
	 */
	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		/*
		 * Like the shared case above, a hole punch or truncate
		 * could have been performed on the private mapping.
		 * Examine the value of chg to determine if reserves
		 * actually exist or were previously consumed.
		 * Very Subtle - The value of chg comes from a previous
		 * call to vma_needs_reserves().  The reserve map for
		 * private mappings has different (opposite) semantics
		 * than that of shared mappings.  vma_needs_reserves()
		 * has already taken this difference in semantics into
		 * account.  Therefore, the meaning of chg is the same
		 * as in the shared case above.  Code could easily be
		 * combined, but keeping it separate draws attention to
		 * subtle differences.
		 */
		if (chg)
			return false;
		else
			return true;
	}

	return false;
}

static void enqueue_huge_page(struct hstate *h, struct page *page)
{
	int nid = page_to_nid(page);

	lockdep_assert_held(&hugetlb_lock);
	list_move(&page->lru, &h->hugepage_freelists[nid]);
	h->free_huge_pages++;
	h->free_huge_pages_node[nid]++;
	SetHPageFreed(page);
}

static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
{
	struct page *page;
	bool pin = !!(current->flags & PF_MEMALLOC_PIN);

	lockdep_assert_held(&hugetlb_lock);
	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
		if (pin && !is_pinnable_page(page))
			continue;

		if (PageHWPoison(page))
			continue;

		list_move(&page->lru, &h->hugepage_activelist);
		set_page_refcounted(page);
		ClearHPageFreed(page);
		h->free_huge_pages--;
		h->free_huge_pages_node[nid]--;
		return page;
	}

	return NULL;
}

static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
		nodemask_t *nmask)
{
	unsigned int cpuset_mems_cookie;
	struct zonelist *zonelist;
	struct zone *zone;
	struct zoneref *z;
	int node = NUMA_NO_NODE;

	zonelist = node_zonelist(nid, gfp_mask);

retry_cpuset:
	cpuset_mems_cookie = read_mems_allowed_begin();
	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) {
		struct page *page;

		if (!cpuset_zone_allowed(zone, gfp_mask))
			continue;
		/*
		 * no need to ask again on the same node. Pool is node rather than
		 * zone aware
		 */
		if (zone_to_nid(zone) == node)
			continue;
		node = zone_to_nid(zone);

		page = dequeue_huge_page_node_exact(h, node);
		if (page)
			return page;
	}
	if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie)))
		goto retry_cpuset;

	return NULL;
}

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;
	struct mempolicy *mpol;
	gfp_t gfp_mask;
	nodemask_t *nodemask;
	int nid;

	/*
	 * 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;

	gfp_mask = htlb_alloc_mask(h);
	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
		SetHPageRestoreReserve(page);
		h->resv_huge_pages--;
	}

	mpol_cond_put(mpol);
	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_in(nid, *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 remove_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--)

#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
static void destroy_compound_gigantic_page(struct page *page,
					unsigned int order)
{
	int i;
	int nr_pages = 1 << order;
	struct page *p = page + 1;

	atomic_set(compound_mapcount_ptr(page), 0);
	atomic_set(compound_pincount_ptr(page), 0);

	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		clear_compound_head(p);
		set_page_refcounted(p);
	}

	set_compound_order(page, 0);
	page[1].compound_nr = 0;
	__ClearPageHead(page);
}

static void free_gigantic_page(struct page *page, unsigned int order)
{
	/*
	 * If the page isn't allocated using the cma allocator,
	 * cma_release() returns false.
	 */
#ifdef CONFIG_CMA
	if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order))
		return;
#endif

	free_contig_range(page_to_pfn(page), 1 << order);
}

#ifdef CONFIG_CONTIG_ALLOC
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
		int nid, nodemask_t *nodemask)
{
	unsigned long nr_pages = pages_per_huge_page(h);
	if (nid == NUMA_NO_NODE)
		nid = numa_mem_id();

#ifdef CONFIG_CMA
	{
		struct page *page;
		int node;

		if (hugetlb_cma[nid]) {
			page = cma_alloc(hugetlb_cma[nid], nr_pages,
					huge_page_order(h), true);
			if (page)
				return page;
		}

		if (!(gfp_mask & __GFP_THISNODE)) {
			for_each_node_mask(node, *nodemask) {
				if (node == nid || !hugetlb_cma[node])
					continue;

				page = cma_alloc(hugetlb_cma[node], nr_pages,
						huge_page_order(h), true);
				if (page)
					return page;
			}
		}
	}
#endif

	return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask);
}

#else /* !CONFIG_CONTIG_ALLOC */
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
					int nid, nodemask_t *nodemask)
{
	return NULL;
}
#endif /* CONFIG_CONTIG_ALLOC */

#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
					int nid, nodemask_t *nodemask)
{
	return NULL;
}
static inline void free_gigantic_page(struct page *page, unsigned int order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
						unsigned int order) { }
#endif

/*
 * Remove hugetlb page from lists, and update dtor so that page appears
 * as just a compound page.  A reference is held on the page.
 *
 * Must be called with hugetlb lock held.
 */
static void remove_hugetlb_page(struct hstate *h, struct page *page,
							bool adjust_surplus)
{
	int nid = page_to_nid(page);

	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page);

	lockdep_assert_held(&hugetlb_lock);
	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
		return;

	list_del(&page->lru);

	if (HPageFreed(page)) {
		h->free_huge_pages--;
		h->free_huge_pages_node[nid]--;
	}
	if (adjust_surplus) {
		h->surplus_huge_pages--;
		h->surplus_huge_pages_node[nid]--;
	}

	set_page_refcounted(page);
	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);

	h->nr_huge_pages--;
	h->nr_huge_pages_node[nid]--;
}

static void add_hugetlb_page(struct hstate *h, struct page *page,
			     bool adjust_surplus)
{
	int zeroed;
	int nid = page_to_nid(page);

	VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page);

	lockdep_assert_held(&hugetlb_lock);

	INIT_LIST_HEAD(&page->lru);
	h->nr_huge_pages++;
	h->nr_huge_pages_node[nid]++;

	if (adjust_surplus) {
		h->surplus_huge_pages++;
		h->surplus_huge_pages_node[nid]++;
	}

	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
	set_page_private(page, 0);
	SetHPageVmemmapOptimized(page);

	/*
	 * This page is now managed by the hugetlb allocator and has
	 * no users -- drop the last reference.
	 */
	zeroed = put_page_testzero(page);
	VM_BUG_ON_PAGE(!zeroed, page);
	arch_clear_hugepage_flags(page);
	enqueue_huge_page(h, page);
}

static void __update_and_free_page(struct hstate *h, struct page *page)
{
	int i;
	struct page *subpage = page;

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

	if (alloc_huge_page_vmemmap(h, page)) {
		spin_lock_irq(&hugetlb_lock);
		/*
		 * If we cannot allocate vmemmap pages, just refuse to free the
		 * page and put the page back on the hugetlb free list and treat
		 * as a surplus page.
		 */
		add_hugetlb_page(h, page, true);
		spin_unlock_irq(&hugetlb_lock);
		return;
	}

	for (i = 0; i < pages_per_huge_page(h);
	     i++, subpage = mem_map_next(subpage, page, i)) {
		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
				1 << PG_referenced | 1 << PG_dirty |
				1 << PG_active | 1 << PG_private |
				1 << PG_writeback);
	}
	if (hstate_is_gigantic(h)) {
		destroy_compound_gigantic_page(page, huge_page_order(h));
		free_gigantic_page(page, huge_page_order(h));
	} else {
		__free_pages(page, huge_page_order(h));
	}
}

/*
 * As update_and_free_page() can be called under any context, so we cannot
 * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the
 * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate
 * the vmemmap pages.
 *
 * free_hpage_workfn() locklessly retrieves the linked list of pages to be
 * freed and frees them one-by-one. As the page->mapping pointer is going
 * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node
 * structure of a lockless linked list of huge pages to be freed.
 */
static LLIST_HEAD(hpage_freelist);

static void free_hpage_workfn(struct work_struct *work)
{
	struct llist_node *node;

	node = llist_del_all(&hpage_freelist);

	while (node) {
		struct page *page;
		struct hstate *h;

		page = container_of((struct address_space **)node,
				     struct page, mapping);
		node = node->next;
		page->mapping = NULL;
		/*
		 * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate()
		 * is going to trigger because a previous call to
		 * remove_hugetlb_page() will set_compound_page_dtor(page,
		 * NULL_COMPOUND_DTOR), so do not use page_hstate() directly.
		 */
		h = size_to_hstate(page_size(page));

		__update_and_free_page(h, page);

		cond_resched();
	}
}
static DECLARE_WORK(free_hpage_work, free_hpage_workfn);

static inline void flush_free_hpage_work(struct hstate *h)
{
	if (free_vmemmap_pages_per_hpage(h))
		flush_work(&free_hpage_work);
}

static void update_and_free_page(struct hstate *h, struct page *page,
				 bool atomic)
{
	if (!HPageVmemmapOptimized(page) || !atomic) {
		__update_and_free_page(h, page);
		return;
	}

	/*
	 * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages.
	 *
	 * Only call schedule_work() if hpage_freelist is previously
	 * empty. Otherwise, schedule_work() had been called but the workfn
	 * hasn't retrieved the list yet.
	 */
	if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist))
		schedule_work(&free_hpage_work);
}

static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
{
	struct page *page, *t_page;

	list_for_each_entry_safe(page, t_page, list, lru) {
		update_and_free_page(h, page, false);
		cond_resched();
	}
}

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 = hugetlb_page_subpool(page);
	bool restore_reserve;
	unsigned long flags;

	VM_BUG_ON_PAGE(page_count(page), page);
	VM_BUG_ON_PAGE(page_mapcount(page), page);

	hugetlb_set_page_subpool(page, NULL);
	page->mapping = NULL;
	restore_reserve = HPageRestoreReserve(page);
	ClearHPageRestoreReserve(page);

	/*
	 * If HPageRestoreReserve was set on page, page allocation consumed a
	 * reservation.  If the page was associated with a subpool, there
	 * would have been a page reserved in the subpool before allocation
	 * via hugepage_subpool_get_pages().  Since we are 'restoring' the
	 * reservation, do not call hugepage_subpool_put_pages() as this will
	 * remove the reserved page from the subpool.
	 */
	if (!restore_reserve) {
		/*
		 * A return code of zero implies that the subpool will be
		 * under its minimum size if the reservation is not restored
		 * after page is free.  Therefore, force restore_reserve
		 * operation.
		 */
		if (hugepage_subpool_put_pages(spool, 1) == 0)
			restore_reserve = true;
	}

	spin_lock_irqsave(&hugetlb_lock, flags);
	ClearHPageMigratable(page);
	hugetlb_cgroup_uncharge_page(hstate_index(h),
				     pages_per_huge_page(h), page);
	hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
					  pages_per_huge_page(h), page);
	if (restore_reserve)
		h->resv_huge_pages++;

	if (HPageTemporary(page)) {
		remove_hugetlb_page(h, page, false);
		spin_unlock_irqrestore(&hugetlb_lock, flags);
		update_and_free_page(h, page, true);
	} else if (h->surplus_huge_pages_node[nid]) {
		/* remove the page from active list */
		remove_hugetlb_page(h, page, true);
		spin_unlock_irqrestore(&hugetlb_lock, flags);
		update_and_free_page(h, page, true);
	} else {
		arch_clear_hugepage_flags(page);
		enqueue_huge_page(h, page);
		spin_unlock_irqrestore(&hugetlb_lock, flags);
	}
}

/*
 * Must be called with the hugetlb lock held
 */
static void __prep_account_new_huge_page(struct hstate *h, int nid)
{
	lockdep_assert_held(&hugetlb_lock);
	h->nr_huge_pages++;
	h->nr_huge_pages_node[nid]++;
}

static void __prep_new_huge_page(struct hstate *h, struct page *page)
{
	free_huge_page_vmemmap(h, page);
	INIT_LIST_HEAD(&page->lru);
	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
	hugetlb_set_page_subpool(page, NULL);
	set_hugetlb_cgroup(page, NULL);
	set_hugetlb_cgroup_rsvd(page, NULL);
}

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
	__prep_new_huge_page(h, page);
	spin_lock_irq(&hugetlb_lock);
	__prep_account_new_huge_page(h, nid);
	spin_unlock_irq(&hugetlb_lock);
}

static bool prep_compound_gigantic_page(struct page *page, unsigned int order)
{
	int i, j;
	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);
	__ClearPageReserved(page);
	__SetPageHead(page);
	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		/*
		 * 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.  Otherwise 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);
		/*
		 * Subtle and very unlikely
		 *
		 * Gigantic 'page allocators' such as memblock or cma will
		 * return a set of pages with each page ref counted.  We need
		 * to turn this set of pages into a compound page with tail
		 * page ref counts set to zero.  Code such as speculative page
		 * cache adding could take a ref on a 'to be' tail page.
		 * We need to respect any increased ref count, and only set
		 * the ref count to zero if count is currently 1.  If count
		 * is not 1, we call synchronize_rcu in the hope that a rcu
		 * grace period will cause ref count to drop and then retry.
		 * If count is still inflated on retry we return an error and
		 * must discard the pages.
		 */
		if (!page_ref_freeze(p, 1)) {
			pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n");
			synchronize_rcu();
			if (!page_ref_freeze(p, 1))
				goto out_error;
		}
		set_page_count(p, 0);
		set_compound_head(p, page);
	}
	atomic_set(compound_mapcount_ptr(page), -1);
	atomic_set(compound_pincount_ptr(page), 0);
	return true;

out_error:
	/* undo tail page modifications made above */
	p = page + 1;
	for (j = 1; j < i; j++, p = mem_map_next(p, page, j)) {
		clear_compound_head(p);
		set_page_refcounted(p);
	}
	/* need to clear PG_reserved on remaining tail pages  */
	for (; j < nr_pages; j++, p = mem_map_next(p, page, j))
		__ClearPageReserved(p);
	set_compound_order(page, 0);
	page[1].compound_nr = 0;
	__ClearPageHead(page);
	return false;
}

/*
 * 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 page[1].compound_dtor == HUGETLB_PAGE_DTOR;
}
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 page_head[1].compound_dtor == HUGETLB_PAGE_DTOR;
}

/*
 * Find and lock address space (mapping) in write mode.
 *
 * Upon entry, the page is locked which means that page_mapping() is
 * stable.  Due to locking order, we can only trylock_write.  If we can
 * not get the lock, simply return NULL to caller.
 */
struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
{
	struct address_space *mapping = page_mapping(hpage);

	if (!mapping)
		return mapping;

	if (i_mmap_trylock_write(mapping))
		return mapping;

	return NULL;
}

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

	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_buddy_huge_page(struct hstate *h,
		gfp_t gfp_mask, int nid, nodemask_t *nmask,
		nodemask_t *node_alloc_noretry)
{
	int order = huge_page_order(h);
	struct page *page;
	bool alloc_try_hard = true;

	/*
	 * By default we always try hard to allocate the page with
	 * __GFP_RETRY_MAYFAIL flag.  However, if we are allocating pages in
	 * a loop (to adjust global huge page counts) and previous allocation
	 * failed, do not continue to try hard on the same node.  Use the
	 * node_alloc_noretry bitmap to manage this state information.
	 */
	if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry))
		alloc_try_hard = false;
	gfp_mask |= __GFP_COMP|__GFP_NOWARN;
	if (alloc_try_hard)
		gfp_mask |= __GFP_RETRY_MAYFAIL;
	if (nid == NUMA_NO_NODE)
		nid = numa_mem_id();
	page = __alloc_pages(gfp_mask, order, nid, nmask);
	if (page)
		__count_vm_event(HTLB_BUDDY_PGALLOC);
	else
		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);

	/*
	 * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this
	 * indicates an overall state change.  Clear bit so that we resume
	 * normal 'try hard' allocations.
	 */
	if (node_alloc_noretry && page && !alloc_try_hard)
		node_clear(nid, *node_alloc_noretry);

	/*
	 * If we tried hard to get a page but failed, set bit so that
	 * subsequent attempts will not try as hard until there is an
	 * overall state change.
	 */
	if (node_alloc_noretry && !page && alloc_try_hard)
		node_set(nid, *node_alloc_noretry);

	return page;
}

/*
 * Common helper to allocate a fresh hugetlb page. All specific allocators
 * should use this function to get new hugetlb pages
 */
static struct page *alloc_fresh_huge_page(struct hstate *h,
		gfp_t gfp_mask, int nid, nodemask_t *nmask,
		nodemask_t *node_alloc_noretry)
{
	struct page *page;
	bool retry = false;

retry:
	if (hstate_is_gigantic(h))
		page = alloc_gigantic_page(h, gfp_mask, nid, nmask);
	else
		page = alloc_buddy_huge_page(h, gfp_mask,
				nid, nmask, node_alloc_noretry);
	if (!page)
		return NULL;

	if (hstate_is_gigantic(h)) {
		if (!prep_compound_gigantic_page(page, huge_page_order(h))) {
			/*
			 * Rare failure to convert pages to compound page.
			 * Free pages and try again - ONCE!
			 */
			free_gigantic_page(page, huge_page_order(h));
			if (!retry) {
				retry = true;
				goto retry;
			}
			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
			return NULL;
		}
	}
	prep_new_huge_page(h, page, page_to_nid(page));

	return page;
}

/*
 * Allocates a fresh page to the hugetlb allocator pool in the node interleaved
 * manner.
 */
static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
				nodemask_t *node_alloc_noretry)
{
	struct page *page;
	int nr_nodes, node;
	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;

	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
		page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed,
						node_alloc_noretry);
		if (page)
			break;
	}

	if (!page)
		return 0;

	put_page(page); /* free it into the hugepage allocator */

	return 1;
}

/*
 * Remove huge page from pool from next node to free.  Attempt to keep
 * persistent huge pages more or less balanced over allowed nodes.
 * This routine only 'removes' the hugetlb page.  The caller must make
 * an additional call to free the page to low level allocators.
 * Called with hugetlb_lock locked.
 */
static struct page *remove_pool_huge_page(struct hstate *h,
						nodemask_t *nodes_allowed,
						 bool acct_surplus)
{
	int nr_nodes, node;
	struct page *page = NULL;

	lockdep_assert_held(&hugetlb_lock);
	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])) {
			page = list_entry(h->hugepage_freelists[node].next,
					  struct page, lru);
			remove_hugetlb_page(h, page, acct_surplus);
			break;
		}
	}

	return page;
}

/*
 * Dissolve a given free hugepage into free buddy pages. This function does
 * nothing for in-use hugepages and non-hugepages.
 * This function returns values like below:
 *
 *  -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages
 *           when the system is under memory pressure and the feature of
 *           freeing unused vmemmap pages associated with each hugetlb page
 *           is enabled.
 *  -EBUSY:  failed to dissolved free hugepages or the hugepage is in-use
 *           (allocated or reserved.)
 *       0:  successfully dissolved free hugepages or the page is not a
 *           hugepage (considered as already dissolved)
 */
int dissolve_free_huge_page(struct page *page)
{
	int rc = -EBUSY;

retry:
	/* Not to disrupt normal path by vainly holding hugetlb_lock */
	if (!PageHuge(page))
		return 0;

	spin_lock_irq(&hugetlb_lock);
	if (!PageHuge(page)) {
		rc = 0;
		goto out;
	}

	if (!page_count(page)) {
		struct page *head = compound_head(page);
		struct hstate *h = page_hstate(head);
		if (h->free_huge_pages - h->resv_huge_pages == 0)
			goto out;

		/*
		 * We should make sure that the page is already on the free list
		 * when it is dissolved.
		 */
		if (unlikely(!HPageFreed(head))) {
			spin_unlock_irq(&hugetlb_lock);
			cond_resched();

			/*
			 * Theoretically, we should return -EBUSY when we
			 * encounter this race. In fact, we have a chance
			 * to successfully dissolve the page if we do a
			 * retry. Because the race window is quite small.
			 * If we seize this opportunity, it is an optimization
			 * for increasing the success rate of dissolving page.
			 */
			goto retry;
		}

		remove_hugetlb_page(h, head, false);
		h->max_huge_pages--;
		spin_unlock_irq(&hugetlb_lock);

		/*
		 * Normally update_and_free_page will allocate required vmemmmap
		 * before freeing the page.  update_and_free_page will fail to
		 * free the page if it can not allocate required vmemmap.  We
		 * need to adjust max_huge_pages if the page is not freed.
		 * Attempt to allocate vmemmmap here so that we can take
		 * appropriate action on failure.
		 */
		rc = alloc_huge_page_vmemmap(h, head);
		if (!rc) {
			/*
			 * Move PageHWPoison flag from head page to the raw
			 * error page, which makes any subpages rather than
			 * the error page reusable.
			 */
			if (PageHWPoison(head) && page != head) {
				SetPageHWPoison(page);
				ClearPageHWPoison(head);
			}
			update_and_free_page(h, head, false);
		} else {
			spin_lock_irq(&hugetlb_lock);
			add_hugetlb_page(h, head, false);
			h->max_huge_pages++;
			spin_unlock_irq(&hugetlb_lock);
		}

		return rc;
	}
out:
	spin_unlock_irq(&hugetlb_lock);
	return rc;
}

/*
 * Dissolve free hugepages in a given pfn range. Used by memory hotplug to
 * make specified memory blocks removable from the system.
 * Note that this will dissolve a free gigantic hugepage completely, if any
 * part of it lies within the given range.
 * Also note that if dissolve_free_huge_page() returns with an error, all
 * free hugepages that were dissolved before that error are lost.
 */
int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pfn;
	struct page *page;
	int rc = 0;

	if (!hugepages_supported())
		return rc;

	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
		page = pfn_to_page(pfn);
		rc = dissolve_free_huge_page(page);
		if (rc)
			break;
	}

	return rc;
}

/*
 * Allocates a fresh surplus page from the page allocator.
 */
static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
		int nid, nodemask_t *nmask)
{
	struct page *page = NULL;

	if (hstate_is_gigantic(h))
		return NULL;

	spin_lock_irq(&hugetlb_lock);
	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages)
		goto out_unlock;
	spin_unlock_irq(&hugetlb_lock);

	page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL);
	if (!page)
		return NULL;

	spin_lock_irq(&hugetlb_lock);
	/*
	 * We could have raced with the pool size change.
	 * Double check that and simply deallocate the new page
	 * if we would end up overcommiting the surpluses. Abuse
	 * temporary page to workaround the nasty free_huge_page
	 * codeflow
	 */
	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
		SetHPageTemporary(page);
		spin_unlock_irq(&hugetlb_lock);
		put_page(page);
		return NULL;
	} else {
		h->surplus_huge_pages++;
		h->surplus_huge_pages_node[page_to_nid(page)]++;
	}

out_unlock:
	spin_unlock_irq(&hugetlb_lock);

	return page;
}

static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
				     int nid, nodemask_t *nmask)
{
	struct page *page;

	if (hstate_is_gigantic(h))
		return NULL;

	page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL);
	if (!page)
		return NULL;

	/*
	 * We do not account these pages as surplus because they are only
	 * temporary and will be released properly on the last reference
	 */
	SetHPageTemporary(page);

	return page;
}

/*
 * Use the VMA's mpolicy to allocate a huge page from the buddy.
 */
static
struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct page *page;
	struct mempolicy *mpol;
	gfp_t gfp_mask = htlb_alloc_mask(h);
	int nid;
	nodemask_t *nodemask;

	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
	page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
	mpol_cond_put(mpol);

	return page;
}

/* page migration callback function */
struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
		nodemask_t *nmask, gfp_t gfp_mask)
{
	spin_lock_irq(&hugetlb_lock);
	if (h->free_huge_pages - h->resv_huge_pages > 0) {
		struct page *page;

		page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
		if (page) {
			spin_unlock_irq(&hugetlb_lock);
			return page;
		}
	}
	spin_unlock_irq(&hugetlb_lock);

	return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
}

/* mempolicy aware migration callback */
struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
		unsigned long address)
{
	struct mempolicy *mpol;
	nodemask_t *nodemask;
	struct page *page;
	gfp_t gfp_mask;
	int node;

	gfp_mask = htlb_alloc_mask(h);
	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask);
	mpol_cond_put(mpol);

	return page;
}

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

	lockdep_assert_held(&hugetlb_lock);
	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_irq(&hugetlb_lock);
	for (i = 0; i < needed; i++) {
		page = alloc_surplus_huge_page(h, htlb_alloc_mask(h),
				NUMA_NO_NODE, NULL);
		if (!page) {
			alloc_ok = false;
			break;
		}
		list_add(&page->lru, &surplus_list);
		cond_resched();
	}
	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_irq(&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) {
		int zeroed;

		if ((--needed) < 0)
			break;
		/*
		 * This page is now managed by the hugetlb allocator and has
		 * no users -- drop the buddy allocator's reference.
		 */
		zeroed = put_page_testzero(page);
		VM_BUG_ON_PAGE(!zeroed, page);
		enqueue_huge_page(h, page);
	}
free:
	spin_unlock_irq(&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_irq(&hugetlb_lock);

	return ret;
}

/*
 * This routine has two main purposes:
 * 1) Decrement the reservation count (resv_huge_pages) by the value passed
 *    in unused_resv_pages.  This corresponds to the prior adjustments made
 *    to the associated reservation map.
 * 2) Free any unused surplus pages that may have been allocated to satisfy
 *    the reservation.  As many as unused_resv_pages may be freed.
 */
static void return_unused_surplus_pages(struct hstate *h,
					unsigned long unused_resv_pages)
{
	unsigned long nr_pages;
	struct page *page;
	LIST_HEAD(page_list);

	lockdep_assert_held(&hugetlb_lock);
	/* Uncommit the reservation */
	h->resv_huge_pages -= unused_resv_pages;

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

	/*
	 * Part (or even all) of the reservation could have been backed
	 * by pre-allocated pages. Only free surplus pages.
	 */
	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.
	 * remove_pool_huge_page() will balance the freed pages across the
	 * on-line nodes with memory and will handle the hstate accounting.
	 */
	while (nr_pages--) {
		page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1);
		if (!page)
			goto out;

		list_add(&page->lru, &page_list);
	}

out:
	spin_unlock_irq(&hugetlb_lock);
	update_and_free_pages_bulk(h, &page_list);
	spin_lock_irq(&hugetlb_lock);
}


/*
 * vma_needs_reservation, vma_commit_reservation and vma_end_reservation
 * are used by the huge page allocation routines to manage reservations.
 *
 * vma_needs_reservation is called to determine if the huge page at addr
 * within the vma has an associated reservation.  If a reservation is
 * needed, the value 1 is returned.  The caller is then responsible for
 * managing the global reservation and subpool usage counts.  After
 * the huge page has been allocated, vma_commit_reservation is called
 * to add the page to the reservation map.  If the page allocation fails,
 * the reservation must be ended instead of committed.  vma_end_reservation
 * is called in such cases.
 *
 * In the normal case, vma_commit_reservation returns the same value
 * as the preceding vma_needs_reservation call.  The only time this
 * is not the case is if a reserve map was changed between calls.  It
 * is the responsibility of the caller to notice the difference and
 * take appropriate action.
 *
 * vma_add_reservation is used in error paths where a reservation must
 * be restored when a newly allocated huge page must be freed.  It is
 * to be called after calling vma_needs_reservation to determine if a
 * reservation exists.
 *
 * vma_del_reservation is used in error paths where an entry in the reserve
 * map was created during huge page allocation and must be removed.  It is to
 * be called after calling vma_needs_reservation to determine if a reservation
 * exists.
 */
enum vma_resv_mode {
	VMA_NEEDS_RESV,
	VMA_COMMIT_RESV,
	VMA_END_RESV,
	VMA_ADD_RESV,
	VMA_DEL_RESV,
};
static long __vma_reservation_common(struct hstate *h,
				struct vm_area_struct *vma, unsigned long addr,
				enum vma_resv_mode mode)
{
	struct resv_map *resv;
	pgoff_t idx;
	long ret;
	long dummy_out_regions_needed;

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

	idx = vma_hugecache_offset(h, vma, addr);
	switch (mode) {
	case VMA_NEEDS_RESV:
		ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed);
		/* We assume that vma_reservation_* routines always operate on
		 * 1 page, and that adding to resv map a 1 page entry can only
		 * ever require 1 region.
		 */
		VM_BUG_ON(dummy_out_regions_needed != 1);
		break;
	case VMA_COMMIT_RESV:
		ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
		/* region_add calls of range 1 should never fail. */
		VM_BUG_ON(ret < 0);
		break;
	case VMA_END_RESV:
		region_abort(resv, idx, idx + 1, 1);
		ret = 0;
		break;
	case VMA_ADD_RESV:
		if (vma->vm_flags & VM_MAYSHARE) {
			ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
			/* region_add calls of range 1 should never fail. */
			VM_BUG_ON(ret < 0);
		} else {
			region_abort(resv, idx, idx + 1, 1);
			ret = region_del(resv, idx, idx + 1);
		}
		break;
	case VMA_DEL_RESV:
		if (vma->vm_flags & VM_MAYSHARE) {
			region_abort(resv, idx, idx + 1, 1);
			ret = region_del(resv, idx, idx + 1);
		} else {
			ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
			/* region_add calls of range 1 should never fail. */
			VM_BUG_ON(ret < 0);
		}
		break;
	default:
		BUG();
	}

	if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV)
		return ret;
	/*
	 * We know private mapping must have HPAGE_RESV_OWNER set.
	 *
	 * In most cases, reserves always exist for private mappings.
	 * However, a file associated with mapping could have been
	 * hole punched or truncated after reserves were consumed.
	 * As subsequent fault on such a range will not use reserves.
	 * Subtle - The reserve map for private mappings has the
	 * opposite meaning than that of shared mappings.  If NO
	 * entry is in the reserve map, it means a reservation exists.
	 * If an entry exists in the reserve map, it means the
	 * reservation has already been consumed.  As a result, the
	 * return value of this routine is the opposite of the
	 * value returned from reserve map manipulation routines above.
	 */
	if (ret > 0)
		return 0;
	if (ret == 0)
		return 1;
	return ret;
}

static long vma_needs_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV);
}

static long vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV);
}

static void vma_end_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	(void)__vma_reservation_common(h, vma, addr, VMA_END_RESV);
}

static long vma_add_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
}

static long vma_del_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV);
}

/*
 * This routine is called to restore reservation information on error paths.
 * It should ONLY be called for pages allocated via alloc_huge_page(), and
 * the hugetlb mutex should remain held when calling this routine.
 *
 * It handles two specific cases:
 * 1) A reservation was in place and the page consumed the reservation.
 *    HPageRestoreReserve is set in the page.
 * 2) No reservation was in place for the page, so HPageRestoreReserve is
 *    not set.  However, alloc_huge_page always updates the reserve map.
 *
 * In case 1, free_huge_page later in the error path will increment the
 * global reserve count.  But, free_huge_page does not have enough context
 * to adjust the reservation map.  This case deals primarily with private
 * mappings.  Adjust the reserve map here to be consistent with global
 * reserve count adjustments to be made by free_huge_page.  Make sure the
 * reserve map indicates there is a reservation present.
 *
 * In case 2, simply undo reserve map modifications done by alloc_huge_page.
 */
void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
			unsigned long address, struct page *page)
{
	long rc = vma_needs_reservation(h, vma, address);

	if (HPageRestoreReserve(page)) {
		if (unlikely(rc < 0))
			/*
			 * Rare out of memory condition in reserve map
			 * manipulation.  Clear HPageRestoreReserve so that
			 * global reserve count will not be incremented
			 * by free_huge_page.  This will make it appear
			 * as though the reservation for this page was
			 * consumed.  This may prevent the task from
			 * faulting in the page at a later time.  This
			 * is better than inconsistent global huge page
			 * accounting of reserve counts.
			 */
			ClearHPageRestoreReserve(page);
		else if (rc)
			(void)vma_add_reservation(h, vma, address);
		else
			vma_end_reservation(h, vma, address);
	} else {
		if (!rc) {
			/*
			 * This indicates there is an entry in the reserve map
			 * not added by alloc_huge_page.  We know it was added
			 * before the alloc_huge_page call, otherwise
			 * HPageRestoreReserve would be set on the page.
			 * Remove the entry so that a subsequent allocation
			 * does not consume a reservation.
			 */
			rc = vma_del_reservation(h, vma, address);
			if (rc < 0)
				/*
				 * VERY rare out of memory condition.  Since
				 * we can not delete the entry, set
				 * HPageRestoreReserve so that the reserve
				 * count will be incremented when the page
				 * is freed.  This reserve will be consumed
				 * on a subsequent allocation.
				 */
				SetHPageRestoreReserve(page);
		} else if (rc < 0) {
			/*
			 * Rare out of memory condition from
			 * vma_needs_reservation call.  Memory allocation is
			 * only attempted if a new entry is needed.  Therefore,
			 * this implies there is not an entry in the
			 * reserve map.
			 *
			 * For shared mappings, no entry in the map indicates
			 * no reservation.  We are done.
			 */
			if (!(vma->vm_flags & VM_MAYSHARE))
				/*
				 * For private mappings, no entry indicates
				 * a reservation is present.  Since we can
				 * not add an entry, set SetHPageRestoreReserve
				 * on the page so reserve count will be
				 * incremented when freed.  This reserve will
				 * be consumed on a subsequent allocation.
				 */
				SetHPageRestoreReserve(page);
		} else
			/*
			 * No reservation present, do nothing
			 */
			 vma_end_reservation(h, vma, address);
	}
}

/*
 * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one
 * @h: struct hstate old page belongs to
 * @old_page: Old page to dissolve
 * @list: List to isolate the page in case we need to
 * Returns 0 on success, otherwise negated error.
 */
static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
					struct list_head *list)
{
	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
	int nid = page_to_nid(old_page);
	struct page *new_page;
	int ret = 0;

	/*
	 * Before dissolving the page, we need to allocate a new one for the
	 * pool to remain stable.  Here, we allocate the page and 'prep' it
	 * by doing everything but actually updating counters and adding to
	 * the pool.  This simplifies and let us do most of the processing
	 * under the lock.
	 */
	new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL);
	if (!new_page)
		return -ENOMEM;
	__prep_new_huge_page(h, new_page);

retry:
	spin_lock_irq(&hugetlb_lock);
	if (!PageHuge(old_page)) {
		/*
		 * Freed from under us. Drop new_page too.
		 */
		goto free_new;
	} else if (page_count(old_page)) {
		/*
		 * Someone has grabbed the page, try to isolate it here.
		 * Fail with -EBUSY if not possible.
		 */
		spin_unlock_irq(&hugetlb_lock);
		if (!isolate_huge_page(old_page, list))
			ret = -EBUSY;
		spin_lock_irq(&hugetlb_lock);
		goto free_new;
	} else if (!HPageFreed(old_page)) {
		/*
		 * Page's refcount is 0 but it has not been enqueued in the
		 * freelist yet. Race window is small, so we can succeed here if
		 * we retry.
		 */
		spin_unlock_irq(&hugetlb_lock);
		cond_resched();
		goto retry;
	} else {
		/*
		 * Ok, old_page is still a genuine free hugepage. Remove it from
		 * the freelist and decrease the counters. These will be
		 * incremented again when calling __prep_account_new_huge_page()
		 * and enqueue_huge_page() for new_page. The counters will remain
		 * stable since this happens under the lock.
		 */
		remove_hugetlb_page(h, old_page, false);

		/*
		 * Reference count trick is needed because allocator gives us
		 * referenced page but the pool requires pages with 0 refcount.
		 */
		__prep_account_new_huge_page(h, nid);
		page_ref_dec(new_page);
		enqueue_huge_page(h, new_page);

		/*
		 * Pages have been replaced, we can safely free the old one.
		 */
		spin_unlock_irq(&hugetlb_lock);
		update_and_free_page(h, old_page, false);
	}

	return ret;

free_new:
	spin_unlock_irq(&hugetlb_lock);
	update_and_free_page(h, new_page, false);

	return ret;
}

int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
{
	struct hstate *h;
	struct page *head;
	int ret = -EBUSY;

	/*
	 * The page might have been dissolved from under our feet, so make sure
	 * to carefully check the state under the lock.
	 * Return success when racing as if we dissolved the page ourselves.
	 */
	spin_lock_irq(&hugetlb_lock);
	if (PageHuge(page)) {
		head = compound_head(page);
		h = page_hstate(head);
	} else {
		spin_unlock_irq(&hugetlb_lock);
		return 0;
	}
	spin_unlock_irq(&hugetlb_lock);

	/*
	 * Fence off gigantic pages as there is a cyclic dependency between
	 * alloc_contig_range and them. Return -ENOMEM as this has the effect
	 * of bailing out right away without further retrying.
	 */
	if (hstate_is_gigantic(h))
		return -ENOMEM;

	if (page_count(head) && isolate_huge_page(head, list))
		ret = 0;
	else if (!page_count(head))
		ret = alloc_and_dissolve_huge_page(h, head, list);

	return ret;
}

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 map_chg, map_commit;
	long gbl_chg;
	int ret, idx;
	struct hugetlb_cgroup *h_cg;
	bool deferred_reserve;

	idx = hstate_index(h);
	/*
	 * Examine the region/reserve map to determine if the process
	 * has a reservation for the page to be allocated.  A return
	 * code of zero indicates a reservation exists (no change).
	 */
	map_chg = gbl_chg = vma_needs_reservation(h, vma, addr);
	if (map_chg < 0)
		return ERR_PTR(-ENOMEM);

	/*
	 * Processes that did not create the mapping will have no
	 * reserves as indicated by the region/reserve map. Check
	 * that the allocation will not exceed the subpool limit.
	 * Allocations for MAP_NORESERVE mappings also need to be
	 * checked against any subpool limit.
	 */
	if (map_chg || avoid_reserve) {
		gbl_chg = hugepage_subpool_get_pages(spool, 1);
		if (gbl_chg < 0) {
			vma_end_reservation(h, vma, addr);
			return ERR_PTR(-ENOSPC);
		}

		/*
		 * Even though there was no reservation in the region/reserve
		 * map, there could be reservations associated with the
		 * subpool that can be used.  This would be indicated if the
		 * return value of hugepage_subpool_get_pages() is zero.
		 * However, if avoid_reserve is specified we still avoid even
		 * the subpool reservations.
		 */
		if (avoid_reserve)
			gbl_chg = 1;
	}

	/* If this allocation is not consuming a reservation, charge it now.
	 */
	deferred_reserve = map_chg || avoid_reserve;
	if (deferred_reserve) {
		ret = hugetlb_cgroup_charge_cgroup_rsvd(
			idx, pages_per_huge_page(h), &h_cg);
		if (ret)
			goto out_subpool_put;
	}

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

	spin_lock_irq(&hugetlb_lock);
	/*
	 * glb_chg is passed to indicate whether or not a page must be taken
	 * from the global free pool (global change).  gbl_chg == 0 indicates
	 * a reservation exists for the allocation.
	 */
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg);
	if (!page) {
		spin_unlock_irq(&hugetlb_lock);
		page = alloc_buddy_huge_page_with_mpol(h, vma, addr);
		if (!page)
			goto out_uncharge_cgroup;
		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
			SetHPageRestoreReserve(page);
			h->resv_huge_pages--;
		}
		spin_lock_irq(&hugetlb_lock);
		list_add(&page->lru, &h->hugepage_activelist);
		/* Fall through */
	}
	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
	/* If allocation is not consuming a reservation, also store the
	 * hugetlb_cgroup pointer on the page.
	 */
	if (deferred_reserve) {
		hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h),
						  h_cg, page);
	}

	spin_unlock_irq(&hugetlb_lock);

	hugetlb_set_page_subpool(page, spool);

	map_commit = vma_commit_reservation(h, vma, addr);
	if (unlikely(map_chg > map_commit)) {
		/*
		 * The page was added to the reservation map between
		 * vma_needs_reservation and vma_commit_reservation.
		 * This indicates a race with hugetlb_reserve_pages.
		 * Adjust for the subpool count incremented above AND
		 * in hugetlb_reserve_pages for the same page.  Also,
		 * the reservation count added in hugetlb_reserve_pages
		 * no longer applies.
		 */
		long rsv_adjust;

		rsv_adjust = hugepage_subpool_put_pages(spool, 1);
		hugetlb_acct_memory(h, -rsv_adjust);
		if (deferred_reserve)
			hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
					pages_per_huge_page(h), page);
	}
	return page;

out_uncharge_cgroup:
	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
out_uncharge_cgroup_reservation:
	if (deferred_reserve)
		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
						    h_cg);
out_subpool_put:
	if (map_chg || avoid_reserve)
		hugepage_subpool_put_pages(spool, 1);
	vma_end_reservation(h, vma, addr);
	return ERR_PTR(-ENOSPC);
}

int alloc_bootmem_huge_page(struct hstate *h)
	__attribute__ ((weak, alias("__alloc_bootmem_huge_page")));
int __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_alloc_try_nid_raw(
				huge_page_size(h), huge_page_size(h),
				0, MEMBLOCK_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(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
	/* Put them into a private list first because mem_map is not up yet */
	INIT_LIST_HEAD(&m->list);
	list_add(&m->list, &huge_boot_pages);
	m->hstate = h;
	return 1;
}

/*
 * Put bootmem huge pages into the standard lists after mem_map is up.
 * Note: This only applies to gigantic (order > MAX_ORDER) pages.
 */
static void __init gather_bootmem_prealloc(void)
{
	struct huge_bootmem_page *m;

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

		VM_BUG_ON(!hstate_is_gigantic(h));
		WARN_ON(page_count(page) != 1);
		if (prep_compound_gigantic_page(page, huge_page_order(h))) {
			WARN_ON(PageReserved(page));
			prep_new_huge_page(h, page, page_to_nid(page));
			put_page(page); /* add to the hugepage allocator */
		} else {
			free_gigantic_page(page, huge_page_order(h));
			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
		}

		/*
		 * We need to restore the 'stolen' pages to totalram_pages
		 * in order to fix confusing memory reports from free(1) and
		 * other side-effects, like CommitLimit going negative.
		 */
		adjust_managed_page_count(page, pages_per_huge_page(h));
		cond_resched();
	}
}

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

	if (!hstate_is_gigantic(h)) {
		/*
		 * Bit mask controlling how hard we retry per-node allocations.
		 * Ignore errors as lower level routines can deal with
		 * node_alloc_noretry == NULL.  If this kmalloc fails at boot
		 * time, we are likely in bigger trouble.
		 */
		node_alloc_noretry = kmalloc(sizeof(*node_alloc_noretry),
						GFP_KERNEL);
	} else {
		/* allocations done at boot time */
		node_alloc_noretry = NULL;
	}

	/* bit mask controlling how hard we retry per-node allocations */
	if (node_alloc_noretry)
		nodes_clear(*node_alloc_noretry);

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (hstate_is_gigantic(h)) {
			if (hugetlb_cma_size) {
				pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
				goto free;
			}
			if (!alloc_bootmem_huge_page(h))
				break;
		} else if (!alloc_pool_huge_page(h,
					 &node_states[N_MEMORY],
					 node_alloc_noretry))
			break;
		cond_resched();
	}
	if (i < h->max_huge_pages) {
		char buf[32];

		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
		pr_warn("HugeTLB: allocating %lu of page size %s failed.  Only allocated %lu hugepages.\n",
			h->max_huge_pages, buf, i);
		h->max_huge_pages = i;
	}
free:
	kfree(node_alloc_noretry);
}

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

	for_each_hstate(h) {
		if (minimum_order > huge_page_order(h))
			minimum_order = huge_page_order(h);

		/* oversize hugepages were init'ed in early boot */
		if (!hstate_is_gigantic(h))
			hugetlb_hstate_alloc_pages(h);
	}
	VM_BUG_ON(minimum_order == UINT_MAX);
}

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

	for_each_hstate(h) {
		char buf[32];

		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
		pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
			buf, 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;
	LIST_HEAD(page_list);

	lockdep_assert_held(&hugetlb_lock);
	if (hstate_is_gigantic(h))
		return;

	/*
	 * Collect pages to be freed on a list, and free after dropping lock
	 */
	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)
				goto out;
			if (PageHighMem(page))
				continue;
			remove_hugetlb_page(h, page, false);
			list_add(&page->lru, &page_list);
		}
	}

out:
	spin_unlock_irq(&hugetlb_lock);
	update_and_free_pages_bulk(h, &page_list);
	spin_lock_irq(&hugetlb_lock);
}
#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;

	lockdep_assert_held(&hugetlb_lock);
	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 int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
			      nodemask_t *nodes_allowed)
{
	unsigned long min_count, ret;
	struct page *page;
	LIST_HEAD(page_list);
	NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);

	/*
	 * Bit mask controlling how hard we retry per-node allocations.
	 * If we can not allocate the bit mask, do not attempt to allocate
	 * the requested huge pages.
	 */
	if (node_alloc_noretry)
		nodes_clear(*node_alloc_noretry);
	else
		return -ENOMEM;

	/*
	 * resize_lock mutex prevents concurrent adjustments to number of
	 * pages in hstate via the proc/sysfs interfaces.
	 */
	mutex_lock(&h->resize_lock);
	flush_free_hpage_work(h);
	spin_lock_irq(&hugetlb_lock);

	/*
	 * Check for a node specific request.
	 * Changing node specific huge page count may require a corresponding
	 * change to the global count.  In any case, the passed node mask
	 * (nodes_allowed) will restrict alloc/free to the specified node.
	 */
	if (nid != NUMA_NO_NODE) {
		unsigned long old_count = count;

		count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
		/*
		 * User may have specified a large count value which caused the
		 * above calculation to overflow.  In this case, they wanted
		 * to allocate as many huge pages as possible.  Set count to
		 * largest possible value to align with their intention.
		 */
		if (count < old_count)
			count = ULONG_MAX;
	}

	/*
	 * Gigantic pages runtime allocation depend on the capability for large
	 * page range allocation.
	 * If the system does not provide this feature, return an error when
	 * the user tries to allocate gigantic pages but let the user free the
	 * boottime allocated gigantic pages.
	 */
	if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
		if (count > persistent_huge_pages(h)) {
			spin_unlock_irq(&hugetlb_lock);
			mutex_unlock(&h->resize_lock);
			NODEMASK_FREE(node_alloc_noretry);
			return -EINVAL;
		}
		/* Fall through to decrease pool */
	}

	/*
	 * 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_surplus_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.
	 */
	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_irq(&hugetlb_lock);

		/* yield cpu to avoid soft lockup */
		cond_resched();

		ret = alloc_pool_huge_page(h, nodes_allowed,
						node_alloc_noretry);
		spin_lock_irq(&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_surplus_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);

	/*
	 * Collect pages to be removed on list without dropping lock
	 */
	while (min_count < persistent_huge_pages(h)) {
		page = remove_pool_huge_page(h, nodes_allowed, 0);
		if (!page)
			break;

		list_add(&page->lru, &page_list);
	}
	/* free the pages after dropping lock */
	spin_unlock_irq(&hugetlb_lock);
	update_and_free_pages_bulk(h, &page_list);
	flush_free_hpage_work(h);
	spin_lock_irq(&hugetlb_lock);

	while (count < persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, 1))
			break;
	}
out:
	h->max_huge_pages = persistent_huge_pages(h);
	spin_unlock_irq(&hugetlb_lock);
	mutex_unlock(&h->resize_lock);

	NODEMASK_FREE(node_alloc_noretry);

	return 0;
}

#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 sysfs_emit(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_t nodes_allowed, *n_mask;

	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
		return -EINVAL;

	if (nid == NUMA_NO_NODE) {
		/*
		 * global hstate attribute
		 */
		if (!(obey_mempolicy &&
				init_nodemask_of_mempolicy(&nodes_allowed)))
			n_mask = &node_states[N_MEMORY];
		else
			n_mask = &nodes_allowed;
	} else {
		/*
		 * Node specific request.  count adjustment happens in
		 * set_max_huge_pages() after acquiring hugetlb_lock.
		 */
		init_nodemask_of_node(&nodes_allowed, nid);
		n_mask = &nodes_allowed;
	}

	err = set_max_huge_pages(h, count, nid, n_mask);

	return err ? err : len;
}

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)
{