hugetlb.c

/*
 * Generic hugetlb support.
 * (C) William Irwin, April 2004
 */
#include <linux/gfp.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/mmu_notifier.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
#include <linux/bootmem.h>
#include <linux/sysfs.h>

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

#include <linux/hugetlb.h>
#include "internal.h"

const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;

static int max_hstate;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];

__initdata LIST_HEAD(huge_boot_pages);

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

#define for_each_hstate(h) \
	for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)

/*
 * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
 */
static DEFINE_SPINLOCK(hugetlb_lock);

/*
 * Region tracking -- allows tracking of reservations and instantiated pages
 *                    across the pages in a mapping.
 *
 * The region data structures are protected by a combination of the mmap_sem
 * and the hugetlb_instantion_mutex.  To access or modify a region the caller
 * must either hold the mmap_sem for write, or the mmap_sem for read and
 * the hugetlb_instantiation mutex:
 *
 * 	down_write(&mm->mmap_sem);
 * or
 * 	down_read(&mm->mmap_sem);
 * 	mutex_lock(&hugetlb_instantiation_mutex);
 */
struct file_region {
	struct list_head link;
	long from;
	long to;
};

static long region_add(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg, *trg;

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

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

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

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

static long region_chg(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg;
	long chg = 0;

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

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

		return t - f;
	}

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

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

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

static long region_truncate(struct list_head *head, long end)
{
	struct file_region *rg, *trg;
	long chg = 0;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (end <= rg->to)
			break;
	if (&rg->link == head)
		return 0;

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

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

static long region_count(struct list_head *head, long f, long t)
{
	struct file_region *rg;
	long chg = 0;

	/* Locate each segment we overlap with, and count that overlap. */
	list_for_each_entry(rg, head, link) {
		int seg_from;
		int 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;
	}

	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));
}

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

	if (!is_vm_hugetlb_page(vma))
		return PAGE_SIZE;

	hstate = hstate_vma(vma);

	return 1UL << (hstate->order + PAGE_SHIFT);
}

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

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

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

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

struct resv_map {
	struct kref refs;
	struct list_head regions;
};

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

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

	return resv_map;
}

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

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

static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_SHARED))
		return (struct resv_map *)(get_vma_private_data(vma) &
							~HPAGE_RESV_MASK);
	return NULL;
}

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

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

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

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

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

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

/* Decrement the reserved pages in the hugepage pool by one */
static void decrement_hugepage_resv_vma(struct hstate *h,
			struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_NORESERVE)
		return;

	if (vma->vm_flags & VM_SHARED) {
		/* Shared mappings always use reserves */
		h->resv_huge_pages--;
	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		/*
		 * Only the process that called mmap() has reserves for
		 * private mappings.
		 */
		h->resv_huge_pages--;
	}
}

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

/* Returns true if the VMA has associated reserve pages */
static int vma_has_reserves(struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_SHARED)
		return 1;
	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		return 1;
	return 0;
}

static void clear_gigantic_page(struct page *page,
			unsigned long addr, unsigned long sz)
{
	int i;
	struct page *p = page;

	might_sleep();
	for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
		cond_resched();
		clear_user_highpage(p, addr + i * PAGE_SIZE);
	}
}
static void clear_huge_page(struct page *page,
			unsigned long addr, unsigned long sz)
{
	int i;

	if (unlikely(sz > MAX_ORDER_NR_PAGES)) {
		clear_gigantic_page(page, addr, sz);
		return;
	}

	might_sleep();
	for (i = 0; i < sz/PAGE_SIZE; i++) {
		cond_resched();
		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
	}
}

static void copy_gigantic_page(struct page *dst, struct page *src,
			   unsigned long addr, struct vm_area_struct *vma)
{
	int i;
	struct hstate *h = hstate_vma(vma);
	struct page *dst_base = dst;
	struct page *src_base = src;
	might_sleep();
	for (i = 0; i < pages_per_huge_page(h); ) {
		cond_resched();
		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}
static void copy_huge_page(struct page *dst, struct page *src,
			   unsigned long addr, struct vm_area_struct *vma)
{
	int i;
	struct hstate *h = hstate_vma(vma);

	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
		copy_gigantic_page(dst, src, addr, vma);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page(h); i++) {
		cond_resched();
		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
	}
}

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

static struct page *dequeue_huge_page(struct hstate *h)
{
	int nid;
	struct page *page = NULL;

	for (nid = 0; nid < MAX_NUMNODES; ++nid) {
		if (!list_empty(&h->hugepage_freelists[nid])) {
			page = list_entry(h->hugepage_freelists[nid].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[nid]--;
			break;
		}
	}
	return page;
}

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

	/*
	 * 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) &&
			h->free_huge_pages - h->resv_huge_pages == 0)
		return NULL;

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

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
						MAX_NR_ZONES - 1, nodemask) {
		nid = zone_to_nid(zone);
		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
		    !list_empty(&h->hugepage_freelists[nid])) {
			page = list_entry(h->hugepage_freelists[nid].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[nid]--;

			if (!avoid_reserve)
				decrement_hugepage_resv_vma(h, vma);

			break;
		}
	}
	mpol_cond_put(mpol);
	return page;
}

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

	VM_BUG_ON(h->order >= MAX_ORDER);

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

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

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

static 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 address_space *mapping;

	mapping = (struct address_space *) page_private(page);
	set_page_private(page, 0);
	BUG_ON(page_count(page));
	INIT_LIST_HEAD(&page->lru);

	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
		update_and_free_page(h, page);
		h->surplus_huge_pages--;
		h->surplus_huge_pages_node[nid]--;
	} else {
		enqueue_huge_page(h, page);
	}
	spin_unlock(&hugetlb_lock);
	if (mapping)
		hugetlb_put_quota(mapping, 1);
}

/*
 * 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, int delta)
{
	static int prev_nid;
	int nid = prev_nid;
	int ret = 0;

	VM_BUG_ON(delta != -1 && delta != 1);
	do {
		nid = next_node(nid, node_online_map);
		if (nid == MAX_NUMNODES)
			nid = first_node(node_online_map);

		/* To shrink on this node, there must be a surplus page */
		if (delta < 0 && !h->surplus_huge_pages_node[nid])
			continue;
		/* Surplus cannot exceed the total number of pages */
		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
						h->nr_huge_pages_node[nid])
			continue;

		h->surplus_huge_pages += delta;
		h->surplus_huge_pages_node[nid] += delta;
		ret = 1;
		break;
	} while (nid != prev_nid);

	prev_nid = nid;
	return ret;
}

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

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

	if (h->order >= MAX_ORDER)
		return NULL;

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

	return page;
}

/*
 * Use a helper variable to find the next node and then
 * copy it back to hugetlb_next_nid afterwards:
 * otherwise there's a window in which a racer might
 * pass invalid nid MAX_NUMNODES to alloc_pages_node.
 * But we don't need to use a spin_lock here: it really
 * doesn't matter if occasionally a racer chooses the
 * same nid as we do.  Move nid forward in the mask even
 * if we just successfully allocated a hugepage so that
 * the next caller gets hugepages on the next node.
 */
static int hstate_next_node(struct hstate *h)
{
	int next_nid;
	next_nid = next_node(h->hugetlb_next_nid, node_online_map);
	if (next_nid == MAX_NUMNODES)
		next_nid = first_node(node_online_map);
	h->hugetlb_next_nid = next_nid;
	return next_nid;
}

static int alloc_fresh_huge_page(struct hstate *h)
{
	struct page *page;
	int start_nid;
	int next_nid;
	int ret = 0;

	start_nid = h->hugetlb_next_nid;

	do {
		page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
		if (page)
			ret = 1;
		next_nid = hstate_next_node(h);
	} while (!page && h->hugetlb_next_nid != start_nid);

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

	return ret;
}

static struct page *alloc_buddy_huge_page(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct page *page;
	unsigned int nid;

	if (h->order >= MAX_ORDER)
		return NULL;

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

	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
					__GFP_REPEAT|__GFP_NOWARN,
					huge_page_order(h));

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

	spin_lock(&hugetlb_lock);
	if (page) {
		/*
		 * This page is now managed by the hugetlb allocator and has
		 * no users -- drop the buddy allocator's reference.
		 */
		put_page_testzero(page);
		VM_BUG_ON(page_count(page));
		nid = page_to_nid(page);
		set_compound_page_dtor(page, free_huge_page);
		/*
		 * We incremented the global counters already
		 */
		h->nr_huge_pages_node[nid]++;
		h->surplus_huge_pages_node[nid]++;
		__count_vm_event(HTLB_BUDDY_PGALLOC);
	} else {
		h->nr_huge_pages--;
		h->surplus_huge_pages--;
		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
	}
	spin_unlock(&hugetlb_lock);

	return page;
}

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

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

	allocated = 0;
	INIT_LIST_HEAD(&surplus_list);

	ret = -ENOMEM;
retry:
	spin_unlock(&hugetlb_lock);
	for (i = 0; i < needed; i++) {
		page = alloc_buddy_huge_page(h, NULL, 0);
		if (!page) {
			/*
			 * We were not able to allocate enough pages to
			 * satisfy the entire reservation so we free what
			 * we've allocated so far.
			 */
			spin_lock(&hugetlb_lock);
			needed = 0;
			goto free;
		}

		list_add(&page->lru, &surplus_list);
	}
	allocated += needed;

	/*
	 * After retaking hugetlb_lock, we need to recalculate 'needed'
	 * because either resv_huge_pages or free_huge_pages may have changed.
	 */
	spin_lock(&hugetlb_lock);
	needed = (h->resv_huge_pages + delta) -
			(h->free_huge_pages + allocated);
	if (needed > 0)
		goto retry;

	/*
	 * The surplus_list now contains _at_least_ the number of extra pages
	 * needed to accomodate 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:
	/* Free the needed pages to the hugetlb pool */
	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
		if ((--needed) < 0)
			break;
		list_del(&page->lru);
		enqueue_huge_page(h, page);
	}

	/* Free unnecessary surplus pages to the buddy allocator */
	if (!list_empty(&surplus_list)) {
		spin_unlock(&hugetlb_lock);
		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
			list_del(&page->lru);
			/*
			 * The page has a reference count of zero already, so
			 * call free_huge_page directly instead of using
			 * put_page.  This must be done with hugetlb_lock
			 * unlocked which is safe because free_huge_page takes
			 * hugetlb_lock before deciding how to free the page.
			 */
			free_huge_page(page);
		}
		spin_lock(&hugetlb_lock);
	}

	return ret;
}

/*
 * When releasing a hugetlb pool reservation, any surplus pages that were
 * allocated to satisfy the reservation must be explicitly freed if they were
 * never used.
 */
static void return_unused_surplus_pages(struct hstate *h,
					unsigned long unused_resv_pages)
{
	static int nid = -1;
	struct page *page;
	unsigned long nr_pages;

	/*
	 * We want to release as many surplus pages as possible, spread
	 * evenly across all nodes. Iterate across all nodes until we
	 * can no longer free unreserved surplus pages. This occurs when
	 * the nodes with surplus pages have no free pages.
	 */
	unsigned long remaining_iterations = num_online_nodes();

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

	/* Cannot return gigantic pages currently */
	if (h->order >= MAX_ORDER)
		return;

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

	while (remaining_iterations-- && nr_pages) {
		nid = next_node(nid, node_online_map);
		if (nid == MAX_NUMNODES)
			nid = first_node(node_online_map);

		if (!h->surplus_huge_pages_node[nid])
			continue;

		if (!list_empty(&h->hugepage_freelists[nid])) {
			page = list_entry(h->hugepage_freelists[nid].next,
					  struct page, lru);
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[nid]--;
			h->surplus_huge_pages--;
			h->surplus_huge_pages_node[nid]--;
			nr_pages--;
			remaining_iterations = num_online_nodes();
		}
	}
}

/*
 * Determine if the huge page at addr within the vma has an associated
 * reservation.  Where it does not we will need to logically increase
 * reservation and actually increase quota before an allocation can occur.
 * Where any new reservation would be required the reservation change is
 * prepared, but not committed.  Once the page has been quota'd allocated
 * an instantiated the change should be committed via vma_commit_reservation.
 * No action is required on failure.
 */
static int vma_needs_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_SHARED) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		return region_chg(&inode->i_mapping->private_list,
							idx, idx + 1);

	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		return 1;

	} else  {
		int err;
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		err = region_chg(&reservations->regions, idx, idx + 1);
		if (err < 0)
			return err;
		return 0;
	}
}
static void vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_SHARED) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		region_add(&inode->i_mapping->private_list, idx, idx + 1);

	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		/* Mark this page used in the map. */
		region_add(&reservations->regions, idx, idx + 1);
	}
}

static struct page *alloc_huge_page(struct vm_area_struct *vma,
				    unsigned long addr, int avoid_reserve)
{
	struct hstate *h = hstate_vma(vma);
	struct page *page;
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned int chg;

	/*
	 * Processes that did not create the mapping will have no reserves and
	 * will not have accounted against quota. Check that the quota can be
	 * made before satisfying the allocation
	 * MAP_NORESERVE mappings may also need pages and quota allocated
	 * if no reserve mapping overlaps.
	 */
	chg = vma_needs_reservation(h, vma, addr);
	if (chg < 0)
		return ERR_PTR(chg);
	if (chg)
		if (hugetlb_get_quota(inode->i_mapping, chg))
			return ERR_PTR(-ENOSPC);

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
	spin_unlock(&hugetlb_lock);

	if (!page) {
		page = alloc_buddy_huge_page(h, vma, addr);
		if (!page) {
			hugetlb_put_quota(inode->i_mapping, chg);
			return ERR_PTR(-VM_FAULT_OOM);
		}
	}

	set_page_refcounted(page);
	set_page_private(page, (unsigned long) mapping);

	vma_commit_reservation(h, vma, addr);

	return page;
}

int __weak alloc_bootmem_huge_page(struct hstate *h)
{
	struct huge_bootmem_page *m;
	int nr_nodes = nodes_weight(node_online_map);

	while (nr_nodes) {
		void *addr;

		addr = __alloc_bootmem_node_nopanic(
				NODE_DATA(h->hugetlb_next_nid),
				huge_page_size(h), huge_page_size(h), 0);

		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;
		}
		hstate_next_node(h);
		nr_nodes--;
	}
	return 0;

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

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

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

	list_for_each_entry(m, &huge_boot_pages, list) {
		struct page *page = virt_to_page(m);
		struct hstate *h = m->hstate;
		__ClearPageReserved(page);
		WARN_ON(page_count(page) != 1);
		prep_compound_huge_page(page, h->order);
		prep_new_huge_page(h, page, page_to_nid(page));
	}
}

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

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (h->order >= MAX_ORDER) {
			if (!alloc_bootmem_huge_page(h))
				break;
		} else if (!alloc_fresh_huge_page(h))
			break;
	}
	h->max_huge_pages = i;
}

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

	for_each_hstate(h) {
		/* oversize hugepages were init'ed in early boot */
		if (h->order < MAX_ORDER)
			hugetlb_hstate_alloc_pages(h);
	}
}

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

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

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

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

	if (h->order >= MAX_ORDER)
		return;

	for (i = 0; i < MAX_NUMNODES; ++i) {
		struct page *page, *next;
		struct list_head *freel = &h->hugepage_freelists[i];
		list_for_each_entry_safe(page, next, freel, lru) {
			if (count >= h->nr_huge_pages)
				return;
			if (PageHighMem(page))
				continue;
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[page_to_nid(page)]--;
		}
	}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count)
{
}
#endif

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

	if (h->order >= MAX_ORDER)
		return h->max_huge_pages;

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

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

	}

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