hugetlb multi size, giant hugetlb support, etc

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -331,6 +331,16 @@ static int adjust_pool_surplus(int delta
 	return ret;
 }
 
+static void prep_new_huge_page(struct page *page, int nid)
+{
+	set_compound_page_dtor(page, free_huge_page);
+	spin_lock(&hugetlb_lock);
+	nr_huge_pages++;
+	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(int nid)
 {
 	struct page *page;

@@ -344,12 +354,7 @@ static struct page *alloc_fresh_huge_pag
 			__free_pages(page, HUGETLB_PAGE_ORDER);
 			return NULL;
 		}
-		set_compound_page_dtor(page, free_huge_page);
-		spin_lock(&hugetlb_lock);
-		nr_huge_pages++;
-		nr_huge_pages_node[nid]++;
-		spin_unlock(&hugetlb_lock);
-		put_page(page); /* free it into the hugepage allocator */
+		prep_new_huge_page(page, nid);
 	}
 
 	return page;

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -22,18 +22,12 @@
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
-static unsigned long surplus_huge_pages;
-static unsigned long nr_overcommit_huge_pages;
 unsigned long max_huge_pages;
 unsigned long sysctl_overcommit_huge_pages;
-static struct list_head hugepage_freelists[MAX_NUMNODES];
-static unsigned int nr_huge_pages_node[MAX_NUMNODES];
-static unsigned int free_huge_pages_node[MAX_NUMNODES];
-static unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
-static int hugetlb_next_nid;
+
+struct hstate default_hstate;
 
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages

@@ -55,11 +49,11 @@ static pgoff_t vma_page_offset(struct vm
  * Convert the address within this vma to the page offset within
  * the mapping, in pagecache page units; huge pages here.
  */
-static pgoff_t vma_pagecache_offset(struct vm_area_struct *vma,
-					unsigned long address)
+static pgoff_t vma_pagecache_offset(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long address)
 {
-	return ((address - vma->vm_start) >> HPAGE_SHIFT) +
-			(vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+	return ((address - vma->vm_start) >> huge_page_shift(h)) +
+			(vma->vm_pgoff >> huge_page_order(h));
 }
 
 #define HPAGE_RESV_OWNER    (1UL << (BITS_PER_LONG - 1))

@@ -120,14 +114,15 @@ static int is_vma_resv_set(struct vm_are
 }
 
 /* Decrement the reserved pages in the hugepage pool by one */
-static void decrement_hugepage_resv_vma(struct vm_area_struct *vma)
+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 */
-		resv_huge_pages--;
+		h->resv_huge_pages--;
 	} else {
 		/*
 		 * Only the process that called mmap() has reserves for

@@ -135,7 +130,7 @@ static void decrement_hugepage_resv_vma(
 		 */
 		if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
 			unsigned long flags, reserve;
-			resv_huge_pages--;
+			h->resv_huge_pages--;
 			flags = (unsigned long)vma->vm_private_data &
 							HPAGE_RESV_MASK;
 			reserve = (unsigned long)vma->vm_private_data - 1;

@@ -162,12 +157,13 @@ static int vma_has_private_reserves(stru
 	return 1;
 }
 
-static void clear_huge_page(struct page *page, unsigned long addr)
+static void clear_huge_page(struct page *page,
+			unsigned long addr, unsigned long sz)
 {
 	int i;
 
 	might_sleep();
-	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
+	for (i = 0; i < sz/PAGE_SIZE; i++) {
 		cond_resched();
 		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
 	}

@@ -177,41 +173,43 @@ static void copy_huge_page(struct page *
 			   unsigned long addr, struct vm_area_struct *vma)
 {
 	int i;
+	struct hstate *h = hstate_vma(vma);
 
 	might_sleep();
-	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
+	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 page *page)
+static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
-	list_add(&page->lru, &hugepage_freelists[nid]);
-	free_huge_pages++;
-	free_huge_pages_node[nid]++;
+	list_add(&page->lru, &h->hugepage_freelists[nid]);
+	h->free_huge_pages++;
+	h->free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(void)
+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(&hugepage_freelists[nid])) {
-			page = list_entry(hugepage_freelists[nid].next,
+		if (!list_empty(&h->hugepage_freelists[nid])) {
+			page = list_entry(h->hugepage_freelists[nid].next,
 					  struct page, lru);
 			list_del(&page->lru);
-			free_huge_pages--;
-			free_huge_pages_node[nid]--;
+			h->free_huge_pages--;
+			h->free_huge_pages_node[nid]--;
 			break;
 		}
 	}
 	return page;
 }
 
-static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
+static struct page *dequeue_huge_page_vma(struct hstate *h,
+				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve)
 {
 	int nid;

@@ -229,26 +227,26 @@ static struct page *dequeue_huge_page_vm
 	 * not "stolen". The child may still get SIGKILLed
 	 */
 	if (!vma_has_private_reserves(vma) &&
-			free_huge_pages - resv_huge_pages == 0)
+			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 && free_huge_pages - resv_huge_pages == 0)
+	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(&hugepage_freelists[nid])) {
-			page = list_entry(hugepage_freelists[nid].next,
+		    !list_empty(&h->hugepage_freelists[nid])) {
+			page = list_entry(h->hugepage_freelists[nid].next,
 					  struct page, lru);
 			list_del(&page->lru);
-			free_huge_pages--;
-			free_huge_pages_node[nid]--;
+			h->free_huge_pages--;
+			h->free_huge_pages_node[nid]--;
 
 			if (!avoid_reserve)
-				decrement_hugepage_resv_vma(vma);
+				decrement_hugepage_resv_vma(h, vma);
 
 			break;
 		}

@@ -257,12 +255,13 @@ static struct page *dequeue_huge_page_vm
 	return page;
 }
 
-static void update_and_free_page(struct page *page)
+static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
-	nr_huge_pages--;
-	nr_huge_pages_node[page_to_nid(page)]--;
-	for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) {
+
+	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);

@@ -270,11 +269,16 @@ static void update_and_free_page(struct 
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
 	arch_release_hugepage(page);
-	__free_pages(page, HUGETLB_PAGE_ORDER);
+	__free_pages(page, huge_page_order(h));
 }
 
 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 = &default_hstate;
 	int nid = page_to_nid(page);
 	struct address_space *mapping;
 

@@ -284,12 +288,12 @@ static void free_huge_page(struct page *
 	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
-	if (surplus_huge_pages_node[nid]) {
-		update_and_free_page(page);
-		surplus_huge_pages--;
-		surplus_huge_pages_node[nid]--;
+	if (h->surplus_huge_pages_node[nid]) {
+		update_and_free_page(h, page);
+		h->surplus_huge_pages--;
+		h->surplus_huge_pages_node[nid]--;
 	} else {
-		enqueue_huge_page(page);
+		enqueue_huge_page(h, page);
 	}
 	spin_unlock(&hugetlb_lock);
 	if (mapping)

@@ -301,7 +305,7 @@ static void free_huge_page(struct page *
  * balanced by operating on them in a round-robin fashion.
  * Returns 1 if an adjustment was made.
  */
-static int adjust_pool_surplus(int delta)
+static int adjust_pool_surplus(struct hstate *h, int delta)
 {
 	static int prev_nid;
 	int nid = prev_nid;

@@ -314,15 +318,15 @@ static int adjust_pool_surplus(int delta
 			nid = first_node(node_online_map);
 
 		/* To shrink on this node, there must be a surplus page */
-		if (delta < 0 && !surplus_huge_pages_node[nid])
+		if (delta < 0 && !h->surplus_huge_pages_node[nid])
 			continue;
 		/* Surplus cannot exceed the total number of pages */
-		if (delta > 0 && surplus_huge_pages_node[nid] >=
-						nr_huge_pages_node[nid])
+		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+						h->nr_huge_pages_node[nid])
 			continue;
 
-		surplus_huge_pages += delta;
-		surplus_huge_pages_node[nid] += delta;
+		h->surplus_huge_pages += delta;
+		h->surplus_huge_pages_node[nid] += delta;
 		ret = 1;
 		break;
 	} while (nid != prev_nid);

@@ -331,46 +335,46 @@ static int adjust_pool_surplus(int delta
 	return ret;
 }
 
-static void prep_new_huge_page(struct page *page, int nid)
+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);
-	nr_huge_pages++;
-	nr_huge_pages_node[nid]++;
+	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(int nid)
+static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
 
 	page = alloc_pages_node(nid,
 		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
 						__GFP_REPEAT|__GFP_NOWARN,
-		HUGETLB_PAGE_ORDER);
+		huge_page_order(h));
 	if (page) {
 		if (arch_prepare_hugepage(page)) {
 			__free_pages(page, HUGETLB_PAGE_ORDER);
 			return NULL;
 		}
-		prep_new_huge_page(page, nid);
+		prep_new_huge_page(h, page, nid);
 	}
 
 	return page;
 }
 
-static int alloc_fresh_huge_page(void)
+static int alloc_fresh_huge_page(struct hstate *h)
 {
 	struct page *page;
 	int start_nid;
 	int next_nid;
 	int ret = 0;
 
-	start_nid = hugetlb_next_nid;
+	start_nid = h->hugetlb_next_nid;
 
 	do {
-		page = alloc_fresh_huge_page_node(hugetlb_next_nid);
+		page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
 		if (page)
 			ret = 1;
 		/*

@@ -384,11 +388,11 @@ static int alloc_fresh_huge_page(void)
 		 * if we just successfully allocated a hugepage so that
 		 * the next caller gets hugepages on the next node.
 		 */
-		next_nid = next_node(hugetlb_next_nid, node_online_map);
+		next_nid = next_node(h->hugetlb_next_nid, node_online_map);
 		if (next_nid == MAX_NUMNODES)
 			next_nid = first_node(node_online_map);
-		hugetlb_next_nid = next_nid;
-	} while (!page && hugetlb_next_nid != start_nid);
+		h->hugetlb_next_nid = next_nid;
+	} while (!page && h->hugetlb_next_nid != start_nid);
 
 	if (ret)
 		count_vm_event(HTLB_BUDDY_PGALLOC);

@@ -398,8 +402,8 @@ static int alloc_fresh_huge_page(void)
 	return ret;
 }
 
-static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
-						unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long address)
 {
 	struct page *page;
 	unsigned int nid;

@@ -428,18 +432,18 @@ static struct page *alloc_buddy_huge_pag
 	 * per-node value is checked there.
 	 */
 	spin_lock(&hugetlb_lock);
-	if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
 		spin_unlock(&hugetlb_lock);
 		return NULL;
 	} else {
-		nr_huge_pages++;
-		surplus_huge_pages++;
+		h->nr_huge_pages++;
+		h->surplus_huge_pages++;
 	}
 	spin_unlock(&hugetlb_lock);
 
 	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
 					__GFP_REPEAT|__GFP_NOWARN,
-					HUGETLB_PAGE_ORDER);
+					huge_page_order(h));
 
 	spin_lock(&hugetlb_lock);
 	if (page) {

@@ -454,12 +458,12 @@ static struct page *alloc_buddy_huge_pag
 		/*
 		 * We incremented the global counters already
 		 */
-		nr_huge_pages_node[nid]++;
-		surplus_huge_pages_node[nid]++;
+		h->nr_huge_pages_node[nid]++;
+		h->surplus_huge_pages_node[nid]++;
 		__count_vm_event(HTLB_BUDDY_PGALLOC);
 	} else {
-		nr_huge_pages--;
-		surplus_huge_pages--;
+		h->nr_huge_pages--;
+		h->surplus_huge_pages--;
 		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
 	}
 	spin_unlock(&hugetlb_lock);

@@ -471,16 +475,16 @@ static struct page *alloc_buddy_huge_pag
  * Increase the hugetlb pool such that it can accomodate a reservation
  * of size 'delta'.
  */
-static int gather_surplus_pages(int 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 = (resv_huge_pages + delta) - free_huge_pages;
+	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
 	if (needed <= 0) {
-		resv_huge_pages += delta;
+		h->resv_huge_pages += delta;
 		return 0;
 	}
 

@@ -491,7 +495,7 @@ static int gather_surplus_pages(int delt
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = alloc_buddy_huge_page(NULL, 0);
+		page = alloc_buddy_huge_page(h, NULL, 0);
 		if (!page) {
 			/*
 			 * We were not able to allocate enough pages to

@@ -512,7 +516,8 @@ retry:
 	 * because either resv_huge_pages or free_huge_pages may have changed.
 	 */
 	spin_lock(&hugetlb_lock);
-	needed = (resv_huge_pages + delta) - (free_huge_pages + allocated);
+	needed = (h->resv_huge_pages + delta) -
+			(h->free_huge_pages + allocated);
 	if (needed > 0)
 		goto retry;
 

@@ -525,7 +530,7 @@ retry:
 	 * before they are reserved.
 	 */
 	needed += allocated;
-	resv_huge_pages += delta;
+	h->resv_huge_pages += delta;
 	ret = 0;
 free:
 	/* Free the needed pages to the hugetlb pool */

@@ -533,7 +538,7 @@ free:
 		if ((--needed) < 0)
 			break;
 		list_del(&page->lru);
-		enqueue_huge_page(page);
+		enqueue_huge_page(h, page);
 	}
 
 	/* Free unnecessary surplus pages to the buddy allocator */

@@ -561,7 +566,8 @@ free:
  * allocated to satisfy the reservation must be explicitly freed if they were
  * never used.
  */
-static void return_unused_surplus_pages(unsigned long unused_resv_pages)
+static void return_unused_surplus_pages(struct hstate *h,
+					unsigned long unused_resv_pages)
 {
 	static int nid = -1;
 	struct page *page;

@@ -576,27 +582,27 @@ static void return_unused_surplus_pages(
 	unsigned long remaining_iterations = num_online_nodes();
 
 	/* Uncommit the reservation */
-	resv_huge_pages -= unused_resv_pages;
+	h->resv_huge_pages -= unused_resv_pages;
 
-	nr_pages = min(unused_resv_pages, surplus_huge_pages);
+	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 (!surplus_huge_pages_node[nid])
+		if (!h->surplus_huge_pages_node[nid])
 			continue;
 
-		if (!list_empty(&hugepage_freelists[nid])) {
-			page = list_entry(hugepage_freelists[nid].next,
+		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(page);
-			free_huge_pages--;
-			free_huge_pages_node[nid]--;
-			surplus_huge_pages--;
-			surplus_huge_pages_node[nid]--;
+			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();
 		}

@@ -733,13 +739,14 @@ static long region_truncate(struct list_
  * an instantiated the change should be committed via vma_commit_reservation.
  * No action is required on failure.
  */
-static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr)
+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_pagecache_offset(vma, addr);
+		pgoff_t idx = vma_pagecache_offset(h, vma, addr);
 		return region_chg(&inode->i_mapping->private_list,
 							idx, idx + 1);
 

@@ -750,14 +757,14 @@ static int vma_needs_reservation(struct 
 
 	return 0;
 }
-static void vma_commit_reservation(struct vm_area_struct *vma,
-							unsigned long addr)
+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_pagecache_offset(vma, addr);
+		pgoff_t idx = vma_pagecache_offset(h, vma, addr);
 		region_add(&inode->i_mapping->private_list, idx, idx + 1);
 	}
 }

@@ -765,6 +772,7 @@ static void vma_commit_reservation(struc
 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;

@@ -777,7 +785,7 @@ static struct page *alloc_huge_page(stru
 	 * MAP_NORESERVE mappings may also need pages and quota allocated
 	 * if no reserve mapping overlaps.
 	 */
-	chg = vma_needs_reservation(vma, addr);
+	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
 		return ERR_PTR(chg);
 	if (chg)

@@ -785,11 +793,11 @@ static struct page *alloc_huge_page(stru
 			return ERR_PTR(-ENOSPC);
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page_vma(vma, addr, avoid_reserve);
+	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page) {
-		page = alloc_buddy_huge_page(vma, addr);
+		page = alloc_buddy_huge_page(h, vma, addr);
 		if (!page) {
 			hugetlb_put_quota(inode->i_mapping, chg);
 			return ERR_PTR(-VM_FAULT_OOM);

@@ -799,7 +807,7 @@ static struct page *alloc_huge_page(stru
 	set_page_refcounted(page);
 	set_page_private(page, (unsigned long) mapping);
 
-	vma_commit_reservation(vma, addr);
+	vma_commit_reservation(h, vma, addr);
 
 	return page;
 }

@@ -807,21 +815,28 @@ static struct page *alloc_huge_page(stru
 static int __init hugetlb_init(void)
 {
 	unsigned long i;
+	struct hstate *h = &default_hstate;
 
 	if (HPAGE_SHIFT == 0)
 		return 0;
 
+	if (!h->order) {
+		h->order = HPAGE_SHIFT - PAGE_SHIFT;
+		h->mask = HPAGE_MASK;
+	}
+
 	for (i = 0; i < MAX_NUMNODES; ++i)
-		INIT_LIST_HEAD(&hugepage_freelists[i]);
+		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
 
-	hugetlb_next_nid = first_node(node_online_map);
+	h->hugetlb_next_nid = first_node(node_online_map);
 
 	for (i = 0; i < max_huge_pages; ++i) {
-		if (!alloc_fresh_huge_page())
+		if (!alloc_fresh_huge_page(h))
 			break;
 	}
-	max_huge_pages = free_huge_pages = nr_huge_pages = i;
-	printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages);
+	max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
+	printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n",
+			h->free_huge_pages);
 	return 0;
 }
 module_init(hugetlb_init);

@@ -847,34 +862,36 @@ static unsigned int cpuset_mems_nr(unsig
 
 #ifdef CONFIG_SYSCTL
 #ifdef CONFIG_HIGHMEM
-static void try_to_free_low(unsigned long count)
+static void try_to_free_low(struct hstate *h, unsigned long count)
 {
 	int i;
 
 	for (i = 0; i < MAX_NUMNODES; ++i) {
 		struct page *page, *next;
-		list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) {
-			if (count >= nr_huge_pages)
+		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(page);
-			free_huge_pages--;
-			free_huge_pages_node[page_to_nid(page)]--;
+			h->free_huge_pages--;
+			h->free_huge_pages_node[page_to_nid(page)]--;
 		}
 	}
 }
 #else
-static inline void try_to_free_low(unsigned long count)
+static inline void try_to_free_low(struct hstate *h, unsigned long count)
 {
 }
 #endif
 
-#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages)
+#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
 static unsigned long set_max_huge_pages(unsigned long count)
 {
 	unsigned long min_count, ret;
+	struct hstate *h = &default_hstate;
 
 	/*
 	 * Increase the pool size

@@ -888,19 +905,19 @@ static unsigned long set_max_huge_pages(
 	 * within all the constraints specified by the sysctls.
 	 */
 	spin_lock(&hugetlb_lock);
-	while (surplus_huge_pages && count > persistent_huge_pages) {
-		if (!adjust_pool_surplus(-1))
+	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
+		if (!adjust_pool_surplus(h, -1))
 			break;
 	}
 
-	while (count > persistent_huge_pages) {
+	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();
+		ret = alloc_fresh_huge_page(h);
 		spin_lock(&hugetlb_lock);
 		if (!ret)
 			goto out;

@@ -922,21 +939,21 @@ static unsigned long set_max_huge_pages(
 	 * 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 = resv_huge_pages + nr_huge_pages - free_huge_pages;
+	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
 	min_count = max(count, min_count);
-	try_to_free_low(min_count);
-	while (min_count < persistent_huge_pages) {
-		struct page *page = dequeue_huge_page();
+	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(page);
+		update_and_free_page(h, page);
 	}
-	while (count < persistent_huge_pages) {
-		if (!adjust_pool_surplus(1))
+	while (count < persistent_huge_pages(h)) {
+		if (!adjust_pool_surplus(h, 1))
 			break;
 	}
 out:
-	ret = persistent_huge_pages;
+	ret = persistent_huge_pages(h);
 	spin_unlock(&hugetlb_lock);
 	return ret;
 }

@@ -966,9 +983,10 @@ int hugetlb_overcommit_handler(struct ct
 			struct file *file, void __user *buffer,
 			size_t *length, loff_t *ppos)
 {
+	struct hstate *h = &default_hstate;
 	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
 	spin_lock(&hugetlb_lock);
-	nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
+	h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
 	spin_unlock(&hugetlb_lock);
 	return 0;
 }

@@ -977,37 +995,40 @@ int hugetlb_overcommit_handler(struct ct
 
 int hugetlb_report_meminfo(char *buf)
 {
+	struct hstate *h = &default_hstate;
 	return sprintf(buf,
 			"HugePages_Total: %5lu\n"
 			"HugePages_Free:  %5lu\n"
 			"HugePages_Rsvd:  %5lu\n"
 			"HugePages_Surp:  %5lu\n"
 			"Hugepagesize:    %5lu kB\n",
-			nr_huge_pages,
-			free_huge_pages,
-			resv_huge_pages,
-			surplus_huge_pages,
-			HPAGE_SIZE/1024);
+			h->nr_huge_pages,
+			h->free_huge_pages,
+			h->resv_huge_pages,
+			h->surplus_huge_pages,
+			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
 }
 
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
+	struct hstate *h = &default_hstate;
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
 		"Node %d HugePages_Free:  %5u\n"
 		"Node %d HugePages_Surp:  %5u\n",
-		nid, nr_huge_pages_node[nid],
-		nid, free_huge_pages_node[nid],
-		nid, surplus_huge_pages_node[nid]);
+		nid, h->nr_huge_pages_node[nid],
+		nid, h->free_huge_pages_node[nid],
+		nid, h->surplus_huge_pages_node[nid]);
 }
 
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE);
+	struct hstate *h = &default_hstate;
+	return h->nr_huge_pages * pages_per_huge_page(h);
 }
 
-static int hugetlb_acct_memory(long delta)
+static int hugetlb_acct_memory(struct hstate *h, long delta)
 {
 	int ret = -ENOMEM;
 

@@ -1030,18 +1051,18 @@ static int hugetlb_acct_memory(long delt
 	 * semantics that cpuset has.
 	 */
 	if (delta > 0) {
-		if (gather_surplus_pages(delta) < 0)
+		if (gather_surplus_pages(h, delta) < 0)
 			goto out;
 
-		if (delta > cpuset_mems_nr(free_huge_pages_node)) {
-			return_unused_surplus_pages(delta);
+		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+			return_unused_surplus_pages(h, delta);
 			goto out;
 		}
 	}
 
 	ret = 0;
 	if (delta < 0)
-		return_unused_surplus_pages((unsigned long) -delta);
+		return_unused_surplus_pages(h, (unsigned long) -delta);
 
 out:
 	spin_unlock(&hugetlb_lock);

@@ -1050,9 +1071,11 @@ out:
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
+	struct hstate *h = hstate_vma(vma);
 	unsigned long reserve = vma_resv_huge_pages(vma);
+
 	if (reserve)
-		hugetlb_acct_memory(-reserve);
+		hugetlb_acct_memory(h, -reserve);
 }
 
 /*

@@ -1108,14 +1131,16 @@ int copy_hugetlb_page_range(struct mm_st
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
 
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, addr);
+		dst_pte = huge_pte_alloc(dst, addr, sz);
 		if (!dst_pte)
 			goto nomem;
 

@@ -1151,6 +1176,9 @@ void __unmap_hugepage_range(struct vm_ar
 	pte_t pte;
 	struct page *page;
 	struct page *tmp;
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
+
 	/*
 	 * A page gathering list, protected by per file i_mmap_lock. The
 	 * lock is used to avoid list corruption from multiple unmapping

@@ -1159,11 +1187,11 @@ void __unmap_hugepage_range(struct vm_ar
 	LIST_HEAD(page_list);
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
-	BUG_ON(start & ~HPAGE_MASK);
-	BUG_ON(end & ~HPAGE_MASK);
+	BUG_ON(start & ~huge_page_mask(h));
+	BUG_ON(end & ~huge_page_mask(h));
 
 	spin_lock(&mm->page_table_lock);
-	for (address = start; address < end; address += HPAGE_SIZE) {
+	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;

@@ -1276,6 +1304,7 @@ static int hugetlb_cow(struct mm_struct 
 			unsigned long address, pte_t *ptep, pte_t pte,
 			struct page *pagecache_page)
 {
+	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
 	int avoidcopy;
 	int outside_reserve = 0;

@@ -1336,7 +1365,7 @@ retry_avoidcopy:
 	__SetPageUptodate(new_page);
 	spin_lock(&mm->page_table_lock);
 
-	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
+	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		/* Break COW */
 		huge_ptep_clear_flush(vma, address, ptep);

@@ -1351,14 +1380,14 @@ retry_avoidcopy:
 }
 
 /* Return the pagecache page at a given address within a VMA */
-static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma,
-			unsigned long address)
+static struct page *hugetlbfs_pagecache_page(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long address)
 {
 	struct address_space *mapping;
 	pgoff_t idx;
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_pagecache_offset(vma, address);
+	idx = vma_pagecache_offset(h, vma, address);
 
 	return find_lock_page(mapping, idx);
 }

@@ -1366,6 +1395,7 @@ static struct page *hugetlbfs_pagecache_
 static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, int write_access)
 {
+	struct hstate *h = hstate_vma(vma);
 	int ret = VM_FAULT_SIGBUS;
 	pgoff_t idx;
 	unsigned long size;

@@ -1386,7 +1416,7 @@ static int hugetlb_no_page(struct mm_str
 	}
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_pagecache_offset(vma, address);
+	idx = vma_pagecache_offset(h, vma, address);
 
 	/*
 	 * Use page lock to guard against racing truncation

@@ -1395,7 +1425,7 @@ static int hugetlb_no_page(struct mm_str
 retry:
 	page = find_lock_page(mapping, idx);
 	if (!page) {
-		size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+		size = i_size_read(mapping->host) >> huge_page_shift(h);
 		if (idx >= size)
 			goto out;
 		page = alloc_huge_page(vma, address, 0);

@@ -1403,7 +1433,7 @@ retry:
 			ret = -PTR_ERR(page);
 			goto out;
 		}
-		clear_huge_page(page, address);
+		clear_huge_page(page, address, huge_page_size(h));
 		__SetPageUptodate(page);
 
 		if (vma->vm_flags & VM_SHARED) {

@@ -1419,14 +1449,14 @@ retry:
 			}
 
 			spin_lock(&inode->i_lock);
-			inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+			inode->i_blocks += blocks_per_huge_page(h);
 			spin_unlock(&inode->i_lock);
 		} else
 			lock_page(page);
 	}
 
 	spin_lock(&mm->page_table_lock);
-	size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
 		goto backout;
 

@@ -1462,8 +1492,9 @@ int hugetlb_fault(struct mm_struct *mm, 
 	pte_t entry;
 	int ret;
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
+	struct hstate *h = hstate_vma(vma);
 
-	ptep = huge_pte_alloc(mm, address);
+	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
 	if (!ptep)
 		return VM_FAULT_OOM;
 

@@ -1487,7 +1518,7 @@ int hugetlb_fault(struct mm_struct *mm, 
 	if (likely(pte_same(entry, huge_ptep_get(ptep))))
 		if (write_access && !pte_write(entry)) {
 			struct page *page;
-			page = hugetlbfs_pagecache_page(vma, address);
+			page = hugetlbfs_pagecache_page(h, vma, address);
 			ret = hugetlb_cow(mm, vma, address, ptep, entry, page);
 			if (page) {
 				unlock_page(page);

@@ -1508,6 +1539,7 @@ int follow_hugetlb_page(struct mm_struct
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
 	int remainder = *length;
+	struct hstate *h = hstate_vma(vma);
 
 	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {

@@ -1519,7 +1551,7 @@ int follow_hugetlb_page(struct mm_struct
 		 * each hugepage.  We have to make * sure we get the
 		 * first, for the page indexing below to work.
 		 */
-		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
+		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
 
 		if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
 		    (write && !pte_write(huge_ptep_get(pte)))) {

@@ -1537,7 +1569,7 @@ int follow_hugetlb_page(struct mm_struct
 			break;
 		}
 
-		pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
 		page = pte_page(huge_ptep_get(pte));
 same_page:
 		if (pages) {

@@ -1553,7 +1585,7 @@ same_page:
 		--remainder;
 		++i;
 		if (vaddr < vma->vm_end && remainder &&
-				pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+				pfn_offset < pages_per_huge_page(h)) {
 			/*
 			 * We use pfn_offset to avoid touching the pageframes
 			 * of this compound page.

@@ -1575,13 +1607,14 @@ void hugetlb_change_protection(struct vm
 	unsigned long start = address;
 	pte_t *ptep;
 	pte_t pte;
+	struct hstate *h = hstate_vma(vma);
 
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
 	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
 	spin_lock(&mm->page_table_lock);
-	for (; address < end; address += HPAGE_SIZE) {
+	for (; address < end; address += huge_page_size(h)) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;

@@ -1604,6 +1637,7 @@ int hugetlb_reserve_pages(struct inode *
 					struct vm_area_struct *vma)
 {
 	long ret, chg;
+	struct hstate *h = hstate_inode(inode);
 
 	if (vma && vma->vm_flags & VM_NORESERVE)
 		return 0;

@@ -1627,7 +1661,7 @@ int hugetlb_reserve_pages(struct inode *
 
 	if (hugetlb_get_quota(inode->i_mapping, chg))
 		return -ENOSPC;
-	ret = hugetlb_acct_memory(chg);
+	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
 		return ret;

@@ -1639,12 +1673,13 @@ int hugetlb_reserve_pages(struct inode *
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
+	struct hstate *h = hstate_inode(inode);
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
 
 	spin_lock(&inode->i_lock);
-	inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed;
+	inode->i_blocks -= blocks_per_huge_page(h);
 	spin_unlock(&inode->i_lock);
 
 	hugetlb_put_quota(inode->i_mapping, (chg - freed));
-	hugetlb_acct_memory(-(chg - freed));
+	hugetlb_acct_memory(h, -(chg - freed));
 }

Index: linux-2.6/arch/powerpc/mm/hugetlbpage.c
===================================================================
@@ -128,7 +128,8 @@ pte_t *huge_pte_offset(struct mm_struct 
 	return NULL;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pg;
 	pud_t *pu;

Index: linux-2.6/arch/sparc64/mm/hugetlbpage.c
===================================================================
@@ -175,7 +175,7 @@ hugetlb_get_unmapped_area(struct file *f
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}

@@ -195,7 +195,8 @@ hugetlb_get_unmapped_area(struct file *f
 				pgoff, flags);
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

Index: linux-2.6/arch/sh/mm/hugetlbpage.c
===================================================================
@@ -22,7 +22,8 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

Index: linux-2.6/arch/ia64/mm/hugetlbpage.c
===================================================================
@@ -24,7 +24,7 @@
 unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT;
 
 pte_t *
-huge_pte_alloc (struct mm_struct *mm, unsigned long addr)
+huge_pte_alloc (struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;

@@ -75,7 +75,8 @@ int huge_pmd_unshare(struct mm_struct *m
  * Don't actually need to do any preparation, but need to make sure
  * the address is in the right region.
  */
-int prepare_hugepage_range(unsigned long addr, unsigned long len)
+int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

@@ -149,7 +150,7 @@ unsigned long hugetlb_get_unmapped_area(
 
 	/* Handle MAP_FIXED */
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *m
 	return 1;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

@@ -368,7 +369,7 @@ hugetlb_get_unmapped_area(struct file *f
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}

115 lines not on this page · raw message

172 lines not on this page · raw message

Index: linux-2.6/ipc/shm.c
===================================================================
@@ -562,7 +562,8 @@ static void shm_get_stat(struct ipc_name
 
 		if (is_file_hugepages(shp->shm_file)) {
 			struct address_space *mapping = inode->i_mapping;
-			*rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages;
+			struct hstate *h = hstate_file(shp->shm_file);
+			*rss += pages_per_huge_page(h) * mapping->nrpages;
 		} else {
 			struct shmem_inode_info *info = SHMEM_I(inode);
 			spin_lock(&info->lock);

Index: linux-2.6/mm/memory.c
===================================================================
@@ -904,7 +904,7 @@ unsigned long unmap_vmas(struct mmu_gath
 			if (unlikely(is_vm_hugetlb_page(vma))) {
 				unmap_hugepage_range(vma, start, end, NULL);
 				zap_work -= (end - start) /
-						(HPAGE_SIZE / PAGE_SIZE);
+					pages_per_huge_page(hstate_vma(vma));
 				start = end;
 			} else
 				start = unmap_page_range(*tlbp, vma,

Index: linux-2.6/mm/mempolicy.c
===================================================================
@@ -1477,7 +1477,7 @@ struct zonelist *huge_zonelist(struct vm
 
 	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
 		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
-						HPAGE_SHIFT), gfp_flags);
+				huge_page_shift(hstate_vma(vma))), gfp_flags);
 	} else {
 		zl = policy_zonelist(gfp_flags, *mpol);
 		if ((*mpol)->mode == MPOL_BIND)

@@ -2216,9 +2216,12 @@ static void check_huge_range(struct vm_a
 {
 	unsigned long addr;
 	struct page *page;
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
 
-	for (addr = start; addr < end; addr += HPAGE_SIZE) {
-		pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK);
+	for (addr = start; addr < end; addr += sz) {
+		pte_t *ptep = huge_pte_offset(vma->vm_mm,
+						addr & huge_page_mask(h));
 		pte_t pte;
 
 		if (!ptep)

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -1808,7 +1808,8 @@ int split_vma(struct mm_struct * mm, str
 	struct mempolicy *pol;
 	struct vm_area_struct *new;
 
-	if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK))
+	if (is_vm_hugetlb_page(vma) && (addr &
+					~(huge_page_mask(hstate_vma(vma)))))
 		return -EINVAL;
 
 	if (mm->map_count >= sysctl_max_map_count)

Index: linux-2.6/include/asm-ia64/hugetlb.h
===================================================================
@@ -8,7 +8,8 @@ void hugetlb_free_pgd_range(struct mmu_g
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-int prepare_hugepage_range(unsigned long addr, unsigned long len);
+int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len);
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,

Index: linux-2.6/include/asm-powerpc/hugetlb.h
===================================================================
@@ -21,7 +21,8 @@ pte_t huge_ptep_get_and_clear(struct mm_
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-s390/hugetlb.h
===================================================================
@@ -22,7 +22,8 @@ void set_huge_pte_at(struct mm_struct *m
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-sh/hugetlb.h
===================================================================
@@ -14,7 +14,8 @@ static inline int is_hugepage_only_range
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-sparc64/hugetlb.h
===================================================================
@@ -22,7 +22,8 @@ static inline int is_hugepage_only_range
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-x86/hugetlb.h
===================================================================
@@ -14,11 +14,13 @@ static inline int is_hugepage_only_range
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }

Index: linux-2.6/arch/s390/mm/hugetlbpage.c
===================================================================
@@ -72,7 +72,8 @@ void arch_release_hugepage(struct page *
 	page[1].index = 0;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -22,18 +22,12 @@
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
-static unsigned long surplus_huge_pages;
-static unsigned long nr_overcommit_huge_pages;
 unsigned long max_huge_pages;
 unsigned long sysctl_overcommit_huge_pages;
-static struct list_head hugepage_freelists[MAX_NUMNODES];
-static unsigned int nr_huge_pages_node[MAX_NUMNODES];
-static unsigned int free_huge_pages_node[MAX_NUMNODES];
-static unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
-static int hugetlb_next_nid;
+
+struct hstate default_hstate;
 
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages

@@ -55,11 +49,11 @@ static pgoff_t vma_page_offset(struct vm
  * Convert the address within this vma to the page offset within
  * the mapping, in pagecache page units; huge pages here.
  */
-static pgoff_t vma_pagecache_offset(struct vm_area_struct *vma,
-					unsigned long address)
+static pgoff_t vma_pagecache_offset(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long address)
 {
-	return ((address - vma->vm_start) >> HPAGE_SHIFT) +
-			(vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+	return ((address - vma->vm_start) >> huge_page_shift(h)) +
+			(vma->vm_pgoff >> huge_page_order(h));
 }
 
 #define HPAGE_RESV_OWNER    (1UL << (BITS_PER_LONG - 1))

@@ -120,14 +114,15 @@ static int is_vma_resv_set(struct vm_are
 }
 
 /* Decrement the reserved pages in the hugepage pool by one */
-static void decrement_hugepage_resv_vma(struct vm_area_struct *vma)
+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 */
-		resv_huge_pages--;
+		h->resv_huge_pages--;
 	} else {
 		/*
 		 * Only the process that called mmap() has reserves for

@@ -135,7 +130,7 @@ static void decrement_hugepage_resv_vma(
 		 */
 		if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
 			unsigned long flags, reserve;
-			resv_huge_pages--;
+			h->resv_huge_pages--;
 			flags = (unsigned long)vma->vm_private_data &
 							HPAGE_RESV_MASK;
 			reserve = (unsigned long)vma->vm_private_data - 1;

@@ -162,12 +157,13 @@ static int vma_has_private_reserves(stru
 	return 1;
 }
 
-static void clear_huge_page(struct page *page, unsigned long addr)
+static void clear_huge_page(struct page *page,
+			unsigned long addr, unsigned long sz)
 {
 	int i;
 
 	might_sleep();
-	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
+	for (i = 0; i < sz/PAGE_SIZE; i++) {
 		cond_resched();
 		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
 	}

@@ -177,41 +173,43 @@ static void copy_huge_page(struct page *
 			   unsigned long addr, struct vm_area_struct *vma)
 {
 	int i;
+	struct hstate *h = hstate_vma(vma);
 
 	might_sleep();
-	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
+	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 page *page)
+static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
-	list_add(&page->lru, &hugepage_freelists[nid]);
-	free_huge_pages++;
-	free_huge_pages_node[nid]++;
+	list_add(&page->lru, &h->hugepage_freelists[nid]);
+	h->free_huge_pages++;
+	h->free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(void)
+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(&hugepage_freelists[nid])) {
-			page = list_entry(hugepage_freelists[nid].next,
+		if (!list_empty(&h->hugepage_freelists[nid])) {
+			page = list_entry(h->hugepage_freelists[nid].next,
 					  struct page, lru);
 			list_del(&page->lru);
-			free_huge_pages--;
-			free_huge_pages_node[nid]--;
+			h->free_huge_pages--;
+			h->free_huge_pages_node[nid]--;
 			break;
 		}
 	}
 	return page;
 }
 
-static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
+static struct page *dequeue_huge_page_vma(struct hstate *h,
+				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve)
 {
 	int nid;

@@ -229,26 +227,26 @@ static struct page *dequeue_huge_page_vm
 	 * not "stolen". The child may still get SIGKILLed
 	 */
 	if (!vma_has_private_reserves(vma) &&
-			free_huge_pages - resv_huge_pages == 0)
+			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 && free_huge_pages - resv_huge_pages == 0)
+	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(&hugepage_freelists[nid])) {
-			page = list_entry(hugepage_freelists[nid].next,
+		    !list_empty(&h->hugepage_freelists[nid])) {
+			page = list_entry(h->hugepage_freelists[nid].next,
 					  struct page, lru);
 			list_del(&page->lru);
-			free_huge_pages--;
-			free_huge_pages_node[nid]--;
+			h->free_huge_pages--;
+			h->free_huge_pages_node[nid]--;
 
 			if (!avoid_reserve)
-				decrement_hugepage_resv_vma(vma);
+				decrement_hugepage_resv_vma(h, vma);
 
 			break;
 		}

@@ -257,12 +255,13 @@ static struct page *dequeue_huge_page_vm
 	return page;
 }
 
-static void update_and_free_page(struct page *page)
+static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
-	nr_huge_pages--;
-	nr_huge_pages_node[page_to_nid(page)]--;
-	for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) {
+
+	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);

@@ -270,11 +269,16 @@ static void update_and_free_page(struct 
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
 	arch_release_hugepage(page);
-	__free_pages(page, HUGETLB_PAGE_ORDER);
+	__free_pages(page, huge_page_order(h));
 }
 
 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 = &default_hstate;
 	int nid = page_to_nid(page);
 	struct address_space *mapping;
 

@@ -284,12 +288,12 @@ static void free_huge_page(struct page *
 	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
-	if (surplus_huge_pages_node[nid]) {
-		update_and_free_page(page);
-		surplus_huge_pages--;
-		surplus_huge_pages_node[nid]--;
+	if (h->surplus_huge_pages_node[nid]) {
+		update_and_free_page(h, page);
+		h->surplus_huge_pages--;
+		h->surplus_huge_pages_node[nid]--;
 	} else {
-		enqueue_huge_page(page);
+		enqueue_huge_page(h, page);
 	}
 	spin_unlock(&hugetlb_lock);
 	if (mapping)

@@ -301,7 +305,7 @@ static void free_huge_page(struct page *
  * balanced by operating on them in a round-robin fashion.
  * Returns 1 if an adjustment was made.
  */
-static int adjust_pool_surplus(int delta)
+static int adjust_pool_surplus(struct hstate *h, int delta)
 {
 	static int prev_nid;
 	int nid = prev_nid;

@@ -314,15 +318,15 @@ static int adjust_pool_surplus(int delta
 			nid = first_node(node_online_map);
 
 		/* To shrink on this node, there must be a surplus page */
-		if (delta < 0 && !surplus_huge_pages_node[nid])
+		if (delta < 0 && !h->surplus_huge_pages_node[nid])
 			continue;
 		/* Surplus cannot exceed the total number of pages */
-		if (delta > 0 && surplus_huge_pages_node[nid] >=
-						nr_huge_pages_node[nid])
+		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+						h->nr_huge_pages_node[nid])
 			continue;
 
-		surplus_huge_pages += delta;
-		surplus_huge_pages_node[nid] += delta;
+		h->surplus_huge_pages += delta;
+		h->surplus_huge_pages_node[nid] += delta;
 		ret = 1;
 		break;
 	} while (nid != prev_nid);

@@ -331,46 +335,46 @@ static int adjust_pool_surplus(int delta
 	return ret;
 }
 
-static void prep_new_huge_page(struct page *page, int nid)
+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);
-	nr_huge_pages++;
-	nr_huge_pages_node[nid]++;
+	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(int nid)
+static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
 
 	page = alloc_pages_node(nid,
 		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
 						__GFP_REPEAT|__GFP_NOWARN,
-		HUGETLB_PAGE_ORDER);
+		huge_page_order(h));
 	if (page) {
 		if (arch_prepare_hugepage(page)) {
 			__free_pages(page, HUGETLB_PAGE_ORDER);
 			return NULL;
 		}
-		prep_new_huge_page(page, nid);
+		prep_new_huge_page(h, page, nid);
 	}
 
 	return page;
 }
 
-static int alloc_fresh_huge_page(void)
+static int alloc_fresh_huge_page(struct hstate *h)
 {
 	struct page *page;
 	int start_nid;
 	int next_nid;
 	int ret = 0;
 
-	start_nid = hugetlb_next_nid;
+	start_nid = h->hugetlb_next_nid;
 
 	do {
-		page = alloc_fresh_huge_page_node(hugetlb_next_nid);
+		page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
 		if (page)
 			ret = 1;
 		/*

@@ -384,11 +388,11 @@ static int alloc_fresh_huge_page(void)
 		 * if we just successfully allocated a hugepage so that
 		 * the next caller gets hugepages on the next node.
 		 */
-		next_nid = next_node(hugetlb_next_nid, node_online_map);
+		next_nid = next_node(h->hugetlb_next_nid, node_online_map);
 		if (next_nid == MAX_NUMNODES)
 			next_nid = first_node(node_online_map);
-		hugetlb_next_nid = next_nid;
-	} while (!page && hugetlb_next_nid != start_nid);
+		h->hugetlb_next_nid = next_nid;
+	} while (!page && h->hugetlb_next_nid != start_nid);
 
 	if (ret)
 		count_vm_event(HTLB_BUDDY_PGALLOC);

@@ -398,8 +402,8 @@ static int alloc_fresh_huge_page(void)
 	return ret;
 }
 
-static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
-						unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long address)
 {
 	struct page *page;
 	unsigned int nid;

@@ -428,18 +432,18 @@ static struct page *alloc_buddy_huge_pag
 	 * per-node value is checked there.
 	 */
 	spin_lock(&hugetlb_lock);
-	if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
 		spin_unlock(&hugetlb_lock);
 		return NULL;
 	} else {
-		nr_huge_pages++;
-		surplus_huge_pages++;
+		h->nr_huge_pages++;
+		h->surplus_huge_pages++;
 	}
 	spin_unlock(&hugetlb_lock);
 
 	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
 					__GFP_REPEAT|__GFP_NOWARN,
-					HUGETLB_PAGE_ORDER);
+					huge_page_order(h));
 
 	spin_lock(&hugetlb_lock);
 	if (page) {

@@ -454,12 +458,12 @@ static struct page *alloc_buddy_huge_pag
 		/*
 		 * We incremented the global counters already
 		 */
-		nr_huge_pages_node[nid]++;
-		surplus_huge_pages_node[nid]++;
+		h->nr_huge_pages_node[nid]++;
+		h->surplus_huge_pages_node[nid]++;
 		__count_vm_event(HTLB_BUDDY_PGALLOC);
 	} else {
-		nr_huge_pages--;
-		surplus_huge_pages--;
+		h->nr_huge_pages--;
+		h->surplus_huge_pages--;
 		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
 	}
 	spin_unlock(&hugetlb_lock);

@@ -471,16 +475,16 @@ static struct page *alloc_buddy_huge_pag
  * Increase the hugetlb pool such that it can accomodate a reservation
  * of size 'delta'.
  */
-static int gather_surplus_pages(int 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 = (resv_huge_pages + delta) - free_huge_pages;
+	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
 	if (needed <= 0) {
-		resv_huge_pages += delta;
+		h->resv_huge_pages += delta;
 		return 0;
 	}
 

@@ -491,7 +495,7 @@ static int gather_surplus_pages(int delt
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = alloc_buddy_huge_page(NULL, 0);
+		page = alloc_buddy_huge_page(h, NULL, 0);
 		if (!page) {
 			/*
 			 * We were not able to allocate enough pages to

@@ -512,7 +516,8 @@ retry:
 	 * because either resv_huge_pages or free_huge_pages may have changed.
 	 */
 	spin_lock(&hugetlb_lock);
-	needed = (resv_huge_pages + delta) - (free_huge_pages + allocated);
+	needed = (h->resv_huge_pages + delta) -
+			(h->free_huge_pages + allocated);
 	if (needed > 0)
 		goto retry;
 

@@ -525,7 +530,7 @@ retry:
 	 * before they are reserved.
 	 */
 	needed += allocated;
-	resv_huge_pages += delta;
+	h->resv_huge_pages += delta;
 	ret = 0;
 free:
 	/* Free the needed pages to the hugetlb pool */

@@ -533,7 +538,7 @@ free:
 		if ((--needed) < 0)
 			break;
 		list_del(&page->lru);
-		enqueue_huge_page(page);
+		enqueue_huge_page(h, page);
 	}
 
 	/* Free unnecessary surplus pages to the buddy allocator */

@@ -561,7 +566,8 @@ free:
  * allocated to satisfy the reservation must be explicitly freed if they were
  * never used.
  */
-static void return_unused_surplus_pages(unsigned long unused_resv_pages)
+static void return_unused_surplus_pages(struct hstate *h,
+					unsigned long unused_resv_pages)
 {
 	static int nid = -1;
 	struct page *page;

@@ -576,27 +582,27 @@ static void return_unused_surplus_pages(
 	unsigned long remaining_iterations = num_online_nodes();
 
 	/* Uncommit the reservation */
-	resv_huge_pages -= unused_resv_pages;
+	h->resv_huge_pages -= unused_resv_pages;
 
-	nr_pages = min(unused_resv_pages, surplus_huge_pages);
+	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 (!surplus_huge_pages_node[nid])
+		if (!h->surplus_huge_pages_node[nid])
 			continue;
 
-		if (!list_empty(&hugepage_freelists[nid])) {
-			page = list_entry(hugepage_freelists[nid].next,
+		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(page);
-			free_huge_pages--;
-			free_huge_pages_node[nid]--;
-			surplus_huge_pages--;
-			surplus_huge_pages_node[nid]--;
+			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();
 		}

@@ -733,13 +739,14 @@ static long region_truncate(struct list_
  * an instantiated the change should be committed via vma_commit_reservation.
  * No action is required on failure.
  */
-static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr)
+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_pagecache_offset(vma, addr);
+		pgoff_t idx = vma_pagecache_offset(h, vma, addr);
 		return region_chg(&inode->i_mapping->private_list,
 							idx, idx + 1);
 

@@ -750,14 +757,14 @@ static int vma_needs_reservation(struct 
 
 	return 0;
 }
-static void vma_commit_reservation(struct vm_area_struct *vma,
-							unsigned long addr)
+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_pagecache_offset(vma, addr);
+		pgoff_t idx = vma_pagecache_offset(h, vma, addr);
 		region_add(&inode->i_mapping->private_list, idx, idx + 1);
 	}
 }

@@ -765,6 +772,7 @@ static void vma_commit_reservation(struc
 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;

@@ -777,7 +785,7 @@ static struct page *alloc_huge_page(stru
 	 * MAP_NORESERVE mappings may also need pages and quota allocated
 	 * if no reserve mapping overlaps.
 	 */
-	chg = vma_needs_reservation(vma, addr);
+	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
 		return ERR_PTR(chg);
 	if (chg)

@@ -785,11 +793,11 @@ static struct page *alloc_huge_page(stru
 			return ERR_PTR(-ENOSPC);
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page_vma(vma, addr, avoid_reserve);
+	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page) {
-		page = alloc_buddy_huge_page(vma, addr);
+		page = alloc_buddy_huge_page(h, vma, addr);
 		if (!page) {
 			hugetlb_put_quota(inode->i_mapping, chg);
 			return ERR_PTR(-VM_FAULT_OOM);

@@ -799,7 +807,7 @@ static struct page *alloc_huge_page(stru
 	set_page_refcounted(page);
 	set_page_private(page, (unsigned long) mapping);
 
-	vma_commit_reservation(vma, addr);
+	vma_commit_reservation(h, vma, addr);
 
 	return page;
 }

@@ -807,21 +815,28 @@ static struct page *alloc_huge_page(stru
 static int __init hugetlb_init(void)
 {
 	unsigned long i;
+	struct hstate *h = &default_hstate;
 
 	if (HPAGE_SHIFT == 0)
 		return 0;
 
+	if (!h->order) {
+		h->order = HPAGE_SHIFT - PAGE_SHIFT;
+		h->mask = HPAGE_MASK;
+	}
+
 	for (i = 0; i < MAX_NUMNODES; ++i)
-		INIT_LIST_HEAD(&hugepage_freelists[i]);
+		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
 
-	hugetlb_next_nid = first_node(node_online_map);
+	h->hugetlb_next_nid = first_node(node_online_map);
 
 	for (i = 0; i < max_huge_pages; ++i) {
-		if (!alloc_fresh_huge_page())
+		if (!alloc_fresh_huge_page(h))
 			break;
 	}
-	max_huge_pages = free_huge_pages = nr_huge_pages = i;
-	printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages);
+	max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
+	printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n",
+			h->free_huge_pages);
 	return 0;
 }
 module_init(hugetlb_init);

@@ -847,34 +862,36 @@ static unsigned int cpuset_mems_nr(unsig
 
 #ifdef CONFIG_SYSCTL
 #ifdef CONFIG_HIGHMEM
-static void try_to_free_low(unsigned long count)
+static void try_to_free_low(struct hstate *h, unsigned long count)
 {
 	int i;
 
 	for (i = 0; i < MAX_NUMNODES; ++i) {
 		struct page *page, *next;
-		list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) {
-			if (count >= nr_huge_pages)
+		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(page);
-			free_huge_pages--;
-			free_huge_pages_node[page_to_nid(page)]--;
+			h->free_huge_pages--;
+			h->free_huge_pages_node[page_to_nid(page)]--;
 		}
 	}
 }
 #else
-static inline void try_to_free_low(unsigned long count)
+static inline void try_to_free_low(struct hstate *h, unsigned long count)
 {
 }
 #endif
 
-#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages)
+#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
 static unsigned long set_max_huge_pages(unsigned long count)
 {
 	unsigned long min_count, ret;
+	struct hstate *h = &default_hstate;
 
 	/*
 	 * Increase the pool size

@@ -888,19 +905,19 @@ static unsigned long set_max_huge_pages(
 	 * within all the constraints specified by the sysctls.
 	 */
 	spin_lock(&hugetlb_lock);
-	while (surplus_huge_pages && count > persistent_huge_pages) {
-		if (!adjust_pool_surplus(-1))
+	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
+		if (!adjust_pool_surplus(h, -1))
 			break;
 	}
 
-	while (count > persistent_huge_pages) {
+	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();
+		ret = alloc_fresh_huge_page(h);
 		spin_lock(&hugetlb_lock);
 		if (!ret)
 			goto out;

@@ -922,21 +939,21 @@ static unsigned long set_max_huge_pages(
 	 * 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 = resv_huge_pages + nr_huge_pages - free_huge_pages;
+	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
 	min_count = max(count, min_count);
-	try_to_free_low(min_count);
-	while (min_count < persistent_huge_pages) {
-		struct page *page = dequeue_huge_page();
+	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(page);
+		update_and_free_page(h, page);
 	}
-	while (count < persistent_huge_pages) {
-		if (!adjust_pool_surplus(1))
+	while (count < persistent_huge_pages(h)) {
+		if (!adjust_pool_surplus(h, 1))
 			break;
 	}
 out:
-	ret = persistent_huge_pages;
+	ret = persistent_huge_pages(h);
 	spin_unlock(&hugetlb_lock);
 	return ret;
 }

@@ -966,9 +983,10 @@ int hugetlb_overcommit_handler(struct ct
 			struct file *file, void __user *buffer,
 			size_t *length, loff_t *ppos)
 {
+	struct hstate *h = &default_hstate;
 	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
 	spin_lock(&hugetlb_lock);
-	nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
+	h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
 	spin_unlock(&hugetlb_lock);
 	return 0;
 }

@@ -977,37 +995,40 @@ int hugetlb_overcommit_handler(struct ct
 
 int hugetlb_report_meminfo(char *buf)
 {
+	struct hstate *h = &default_hstate;
 	return sprintf(buf,
 			"HugePages_Total: %5lu\n"
 			"HugePages_Free:  %5lu\n"
 			"HugePages_Rsvd:  %5lu\n"
 			"HugePages_Surp:  %5lu\n"
 			"Hugepagesize:    %5lu kB\n",
-			nr_huge_pages,
-			free_huge_pages,
-			resv_huge_pages,
-			surplus_huge_pages,
-			HPAGE_SIZE/1024);
+			h->nr_huge_pages,
+			h->free_huge_pages,
+			h->resv_huge_pages,
+			h->surplus_huge_pages,
+			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
 }
 
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
+	struct hstate *h = &default_hstate;
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
 		"Node %d HugePages_Free:  %5u\n"
 		"Node %d HugePages_Surp:  %5u\n",
-		nid, nr_huge_pages_node[nid],
-		nid, free_huge_pages_node[nid],
-		nid, surplus_huge_pages_node[nid]);
+		nid, h->nr_huge_pages_node[nid],
+		nid, h->free_huge_pages_node[nid],
+		nid, h->surplus_huge_pages_node[nid]);
 }
 
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE);
+	struct hstate *h = &default_hstate;
+	return h->nr_huge_pages * pages_per_huge_page(h);
 }
 
-static int hugetlb_acct_memory(long delta)
+static int hugetlb_acct_memory(struct hstate *h, long delta)
 {
 	int ret = -ENOMEM;
 

@@ -1030,18 +1051,18 @@ static int hugetlb_acct_memory(long delt
 	 * semantics that cpuset has.
 	 */
 	if (delta > 0) {
-		if (gather_surplus_pages(delta) < 0)
+		if (gather_surplus_pages(h, delta) < 0)
 			goto out;
 
-		if (delta > cpuset_mems_nr(free_huge_pages_node)) {
-			return_unused_surplus_pages(delta);
+		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+			return_unused_surplus_pages(h, delta);
 			goto out;
 		}
 	}
 
 	ret = 0;
 	if (delta < 0)
-		return_unused_surplus_pages((unsigned long) -delta);
+		return_unused_surplus_pages(h, (unsigned long) -delta);
 
 out:
 	spin_unlock(&hugetlb_lock);

@@ -1050,9 +1071,11 @@ out:
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
+	struct hstate *h = hstate_vma(vma);
 	unsigned long reserve = vma_resv_huge_pages(vma);
+
 	if (reserve)
-		hugetlb_acct_memory(-reserve);
+		hugetlb_acct_memory(h, -reserve);
 }
 
 /*

@@ -1108,14 +1131,16 @@ int copy_hugetlb_page_range(struct mm_st
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
 
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, addr);
+		dst_pte = huge_pte_alloc(dst, addr, sz);
 		if (!dst_pte)
 			goto nomem;
 

@@ -1151,6 +1176,9 @@ void __unmap_hugepage_range(struct vm_ar
 	pte_t pte;
 	struct page *page;
 	struct page *tmp;
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
+
 	/*
 	 * A page gathering list, protected by per file i_mmap_lock. The
 	 * lock is used to avoid list corruption from multiple unmapping

@@ -1159,11 +1187,11 @@ void __unmap_hugepage_range(struct vm_ar
 	LIST_HEAD(page_list);
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
-	BUG_ON(start & ~HPAGE_MASK);
-	BUG_ON(end & ~HPAGE_MASK);
+	BUG_ON(start & ~huge_page_mask(h));
+	BUG_ON(end & ~huge_page_mask(h));
 
 	spin_lock(&mm->page_table_lock);
-	for (address = start; address < end; address += HPAGE_SIZE) {
+	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;

@@ -1276,6 +1304,7 @@ static int hugetlb_cow(struct mm_struct 
 			unsigned long address, pte_t *ptep, pte_t pte,
 			struct page *pagecache_page)
 {
+	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
 	int avoidcopy;
 	int outside_reserve = 0;

@@ -1336,7 +1365,7 @@ retry_avoidcopy:
 	__SetPageUptodate(new_page);
 	spin_lock(&mm->page_table_lock);
 
-	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
+	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		/* Break COW */
 		huge_ptep_clear_flush(vma, address, ptep);

@@ -1351,14 +1380,14 @@ retry_avoidcopy:
 }
 
 /* Return the pagecache page at a given address within a VMA */
-static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma,
-			unsigned long address)
+static struct page *hugetlbfs_pagecache_page(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long address)
 {
 	struct address_space *mapping;
 	pgoff_t idx;
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_pagecache_offset(vma, address);
+	idx = vma_pagecache_offset(h, vma, address);
 
 	return find_lock_page(mapping, idx);
 }

@@ -1366,6 +1395,7 @@ static struct page *hugetlbfs_pagecache_
 static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, int write_access)
 {
+	struct hstate *h = hstate_vma(vma);
 	int ret = VM_FAULT_SIGBUS;
 	pgoff_t idx;
 	unsigned long size;

@@ -1386,7 +1416,7 @@ static int hugetlb_no_page(struct mm_str
 	}
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_pagecache_offset(vma, address);
+	idx = vma_pagecache_offset(h, vma, address);
 
 	/*
 	 * Use page lock to guard against racing truncation

@@ -1395,7 +1425,7 @@ static int hugetlb_no_page(struct mm_str
 retry:
 	page = find_lock_page(mapping, idx);
 	if (!page) {
-		size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+		size = i_size_read(mapping->host) >> huge_page_shift(h);
 		if (idx >= size)
 			goto out;
 		page = alloc_huge_page(vma, address, 0);

@@ -1403,7 +1433,7 @@ retry:
 			ret = -PTR_ERR(page);
 			goto out;
 		}
-		clear_huge_page(page, address);
+		clear_huge_page(page, address, huge_page_size(h));
 		__SetPageUptodate(page);
 
 		if (vma->vm_flags & VM_SHARED) {

@@ -1419,14 +1449,14 @@ retry:
 			}
 
 			spin_lock(&inode->i_lock);
-			inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+			inode->i_blocks += blocks_per_huge_page(h);
 			spin_unlock(&inode->i_lock);
 		} else
 			lock_page(page);
 	}
 
 	spin_lock(&mm->page_table_lock);
-	size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
 		goto backout;
 

@@ -1462,8 +1492,9 @@ int hugetlb_fault(struct mm_struct *mm, 
 	pte_t entry;
 	int ret;
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
+	struct hstate *h = hstate_vma(vma);
 
-	ptep = huge_pte_alloc(mm, address);
+	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
 	if (!ptep)
 		return VM_FAULT_OOM;
 

@@ -1487,7 +1518,7 @@ int hugetlb_fault(struct mm_struct *mm, 
 	if (likely(pte_same(entry, huge_ptep_get(ptep))))
 		if (write_access && !pte_write(entry)) {
 			struct page *page;
-			page = hugetlbfs_pagecache_page(vma, address);
+			page = hugetlbfs_pagecache_page(h, vma, address);
 			ret = hugetlb_cow(mm, vma, address, ptep, entry, page);
 			if (page) {
 				unlock_page(page);

@@ -1508,6 +1539,7 @@ int follow_hugetlb_page(struct mm_struct
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
 	int remainder = *length;
+	struct hstate *h = hstate_vma(vma);
 
 	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {

@@ -1519,7 +1551,7 @@ int follow_hugetlb_page(struct mm_struct
 		 * each hugepage.  We have to make * sure we get the
 		 * first, for the page indexing below to work.
 		 */
-		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
+		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
 
 		if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
 		    (write && !pte_write(huge_ptep_get(pte)))) {

@@ -1537,7 +1569,7 @@ int follow_hugetlb_page(struct mm_struct
 			break;
 		}
 
-		pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
 		page = pte_page(huge_ptep_get(pte));
 same_page:
 		if (pages) {

@@ -1553,7 +1585,7 @@ same_page:
 		--remainder;
 		++i;
 		if (vaddr < vma->vm_end && remainder &&
-				pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+				pfn_offset < pages_per_huge_page(h)) {
 			/*
 			 * We use pfn_offset to avoid touching the pageframes
 			 * of this compound page.

@@ -1575,13 +1607,14 @@ void hugetlb_change_protection(struct vm
 	unsigned long start = address;
 	pte_t *ptep;
 	pte_t pte;
+	struct hstate *h = hstate_vma(vma);
 
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
 	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
 	spin_lock(&mm->page_table_lock);
-	for (; address < end; address += HPAGE_SIZE) {
+	for (; address < end; address += huge_page_size(h)) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;

@@ -1604,6 +1637,7 @@ int hugetlb_reserve_pages(struct inode *
 					struct vm_area_struct *vma)
 {
 	long ret, chg;
+	struct hstate *h = hstate_inode(inode);
 
 	if (vma && vma->vm_flags & VM_NORESERVE)
 		return 0;

@@ -1627,7 +1661,7 @@ int hugetlb_reserve_pages(struct inode *
 
 	if (hugetlb_get_quota(inode->i_mapping, chg))
 		return -ENOSPC;
-	ret = hugetlb_acct_memory(chg);
+	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
 		return ret;

@@ -1639,12 +1673,13 @@ int hugetlb_reserve_pages(struct inode *
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
+	struct hstate *h = hstate_inode(inode);
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
 
 	spin_lock(&inode->i_lock);
-	inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed;
+	inode->i_blocks -= blocks_per_huge_page(h);
 	spin_unlock(&inode->i_lock);
 
 	hugetlb_put_quota(inode->i_mapping, (chg - freed));
-	hugetlb_acct_memory(-(chg - freed));
+	hugetlb_acct_memory(h, -(chg - freed));
 }

Index: linux-2.6/arch/powerpc/mm/hugetlbpage.c
===================================================================
@@ -128,7 +128,8 @@ pte_t *huge_pte_offset(struct mm_struct 
 	return NULL;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pg;
 	pud_t *pu;

Index: linux-2.6/arch/sparc64/mm/hugetlbpage.c
===================================================================
@@ -175,7 +175,7 @@ hugetlb_get_unmapped_area(struct file *f
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}

@@ -195,7 +195,8 @@ hugetlb_get_unmapped_area(struct file *f
 				pgoff, flags);
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

Index: linux-2.6/arch/sh/mm/hugetlbpage.c
===================================================================
@@ -22,7 +22,8 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

Index: linux-2.6/arch/ia64/mm/hugetlbpage.c
===================================================================
@@ -24,7 +24,7 @@
 unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT;
 
 pte_t *
-huge_pte_alloc (struct mm_struct *mm, unsigned long addr)
+huge_pte_alloc (struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;

@@ -75,7 +75,8 @@ int huge_pmd_unshare(struct mm_struct *m
  * Don't actually need to do any preparation, but need to make sure
  * the address is in the right region.
  */
-int prepare_hugepage_range(unsigned long addr, unsigned long len)
+int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

@@ -149,7 +150,7 @@ unsigned long hugetlb_get_unmapped_area(
 
 	/* Handle MAP_FIXED */
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *m
 	return 1;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

@@ -368,7 +369,7 @@ hugetlb_get_unmapped_area(struct file *f
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}

116 lines not on this page · raw message

172 lines not on this page · raw message

Index: linux-2.6/ipc/shm.c
===================================================================
@@ -562,7 +562,8 @@ static void shm_get_stat(struct ipc_name
 
 		if (is_file_hugepages(shp->shm_file)) {
 			struct address_space *mapping = inode->i_mapping;
-			*rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages;
+			struct hstate *h = hstate_file(shp->shm_file);
+			*rss += pages_per_huge_page(h) * mapping->nrpages;
 		} else {
 			struct shmem_inode_info *info = SHMEM_I(inode);
 			spin_lock(&info->lock);

Index: linux-2.6/mm/memory.c
===================================================================
@@ -904,7 +904,7 @@ unsigned long unmap_vmas(struct mmu_gath
 			if (unlikely(is_vm_hugetlb_page(vma))) {
 				unmap_hugepage_range(vma, start, end, NULL);
 				zap_work -= (end - start) /
-						(HPAGE_SIZE / PAGE_SIZE);
+					pages_per_huge_page(hstate_vma(vma));
 				start = end;
 			} else
 				start = unmap_page_range(*tlbp, vma,

Index: linux-2.6/mm/mempolicy.c
===================================================================
@@ -1477,7 +1477,7 @@ struct zonelist *huge_zonelist(struct vm
 
 	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
 		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
-						HPAGE_SHIFT), gfp_flags);
+				huge_page_shift(hstate_vma(vma))), gfp_flags);
 	} else {
 		zl = policy_zonelist(gfp_flags, *mpol);
 		if ((*mpol)->mode == MPOL_BIND)

@@ -2216,9 +2216,12 @@ static void check_huge_range(struct vm_a
 {
 	unsigned long addr;
 	struct page *page;
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
 
-	for (addr = start; addr < end; addr += HPAGE_SIZE) {
-		pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK);
+	for (addr = start; addr < end; addr += sz) {
+		pte_t *ptep = huge_pte_offset(vma->vm_mm,
+						addr & huge_page_mask(h));
 		pte_t pte;
 
 		if (!ptep)

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -1808,7 +1808,8 @@ int split_vma(struct mm_struct * mm, str
 	struct mempolicy *pol;
 	struct vm_area_struct *new;
 
-	if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK))
+	if (is_vm_hugetlb_page(vma) && (addr &
+					~(huge_page_mask(hstate_vma(vma)))))
 		return -EINVAL;
 
 	if (mm->map_count >= sysctl_max_map_count)

Index: linux-2.6/include/asm-ia64/hugetlb.h
===================================================================
@@ -8,7 +8,8 @@ void hugetlb_free_pgd_range(struct mmu_g
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-int prepare_hugepage_range(unsigned long addr, unsigned long len);
+int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len);
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,

Index: linux-2.6/include/asm-powerpc/hugetlb.h
===================================================================
@@ -21,7 +21,8 @@ pte_t huge_ptep_get_and_clear(struct mm_
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-s390/hugetlb.h
===================================================================
@@ -22,7 +22,8 @@ void set_huge_pte_at(struct mm_struct *m
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-sh/hugetlb.h
===================================================================
@@ -14,7 +14,8 @@ static inline int is_hugepage_only_range
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-sparc64/hugetlb.h
===================================================================
@@ -22,7 +22,8 @@ static inline int is_hugepage_only_range
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
 	if (len & ~HPAGE_MASK)
 		return -EINVAL;

Index: linux-2.6/include/asm-x86/hugetlb.h
===================================================================
@@ -14,11 +14,13 @@ static inline int is_hugepage_only_range
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }

Index: linux-2.6/arch/s390/mm/hugetlbpage.c
===================================================================
@@ -72,7 +72,8 @@ void arch_release_hugepage(struct page *
 	page[1].index = 0;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -22,12 +22,19 @@
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-unsigned long max_huge_pages;
-unsigned long sysctl_overcommit_huge_pages;
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
 
-struct hstate default_hstate;
+static int max_hstate = 0;
+unsigned int default_hstate_idx;
+struct hstate hstates[HUGE_MAX_HSTATE];
+
+/* for command line parsing */
+static struct hstate * __initdata parsed_hstate = NULL;
+static unsigned long __initdata default_hstate_max_huge_pages = 0;
+
+#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

@@ -272,13 +279,24 @@ static void update_and_free_page(struct 
 	__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 = &default_hstate;
+	struct hstate *h = page_hstate(page);
 	int nid = page_to_nid(page);
 	struct address_space *mapping;
 

@@ -812,39 +830,94 @@ static struct page *alloc_huge_page(stru
 	return page;
 }
 
-static int __init hugetlb_init(void)
+static void __init hugetlb_init_one_hstate(struct hstate *h)
 {
 	unsigned long i;
-	struct hstate *h = &default_hstate;
-
-	if (HPAGE_SHIFT == 0)
-		return 0;
-
-	if (!h->order) {
-		h->order = HPAGE_SHIFT - PAGE_SHIFT;
-		h->mask = HPAGE_MASK;
-	}
 
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
 
 	h->hugetlb_next_nid = first_node(node_online_map);
 
-	for (i = 0; i < max_huge_pages; ++i) {
+	for (i = 0; i < h->max_huge_pages; ++i) {
 		if (!alloc_fresh_huge_page(h))
 			break;
 	}
-	max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
-	printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n",
-			h->free_huge_pages);
+	h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
+}
+
+static void __init hugetlb_init_hstates(void)
+{
+	struct hstate *h;
+
+	for_each_hstate(h) {
+		hugetlb_init_one_hstate(h);
+	}
+}
+
+static void __init report_hugepages(void)
+{
+	struct hstate *h;
+
+	for_each_hstate(h) {
+		printk(KERN_INFO "Total HugeTLB memory allocated, "
+				"%ld %dMB pages\n",
+				h->free_huge_pages,
+				1 << (h->order + PAGE_SHIFT - 20));
+	}
+}
+
+static int __init hugetlb_init(void)
+{
+	BUILD_BUG_ON(HPAGE_SHIFT == 0);
+
+	if (!size_to_hstate(HPAGE_SIZE)) {
+		hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
+		parsed_hstate->max_huge_pages = default_hstate_max_huge_pages;
+	}
+	default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates;
+
+	hugetlb_init_hstates();
+
+	report_hugepages();
+
 	return 0;
 }
 module_init(hugetlb_init);
 
+/* Should be called on processing a hugepagesz=... option */
+void __init hugetlb_add_hstate(unsigned order)
+{
+	struct hstate *h;
+	if (size_to_hstate(PAGE_SIZE << order)) {
+		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
+		return;
+	}
+	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
+	BUG_ON(order == 0);
+	h = &hstates[max_hstate++];
+	h->order = order;
+	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
+	hugetlb_init_one_hstate(h);
+	parsed_hstate = h;
+}
+
 static int __init hugetlb_setup(char *s)
 {
-	if (sscanf(s, "%lu", &max_huge_pages) <= 0)
-		max_huge_pages = 0;
+	unsigned long *mhp;
+
+	/*
+	 * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
+	 * so this hugepages= parameter goes to the "default hstate".
+	 */
+	if (!max_hstate)
+		mhp = &default_hstate_max_huge_pages;
+	else
+		mhp = &parsed_hstate->max_huge_pages;
+
+	if (sscanf(s, "%lu", mhp) <= 0)
+		*mhp = 0;
+
 	return 1;
 }
 __setup("hugepages=", hugetlb_setup);

@@ -875,7 +948,7 @@ static void try_to_free_low(struct hstat
 			if (PageHighMem(page))
 				continue;
 			list_del(&page->lru);
-			update_and_free_page(page);
+			update_and_free_page(h, page);
 			h->free_huge_pages--;
 			h->free_huge_pages_node[page_to_nid(page)]--;
 		}

@@ -888,10 +961,9 @@ static inline void try_to_free_low(struc
 #endif
 
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
-static unsigned long set_max_huge_pages(unsigned long count)
+static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 {
 	unsigned long min_count, ret;
-	struct hstate *h = &default_hstate;
 
 	/*
 	 * Increase the pool size

@@ -962,8 +1034,19 @@ int hugetlb_sysctl_handler(struct ctl_ta
 			   struct file *file, void __user *buffer,
 			   size_t *length, loff_t *ppos)
 {
+	struct hstate *h = &default_hstate;
+	unsigned long tmp;
+
+	if (!write)
+		tmp = h->max_huge_pages;
+
+	table->data = &tmp;
+	table->maxlen = sizeof(unsigned long);
 	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
-	max_huge_pages = set_max_huge_pages(max_huge_pages);
+
+	if (write)
+		h->max_huge_pages = set_max_huge_pages(h, tmp);
+
 	return 0;
 }
 

@@ -984,10 +1067,21 @@ int hugetlb_overcommit_handler(struct ct
 			size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
+	unsigned long tmp;
+
+	if (!write)
+		tmp = h->nr_overcommit_huge_pages;
+
+	table->data = &tmp;
+	table->maxlen = sizeof(unsigned long);
 	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
-	spin_lock(&hugetlb_lock);
-	h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
-	spin_unlock(&hugetlb_lock);
+
+	if (write) {
+		spin_lock(&hugetlb_lock);
+		h->nr_overcommit_huge_pages = tmp;
+		spin_unlock(&hugetlb_lock);
+	}
+
 	return 0;
 }
 

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -36,8 +36,6 @@ int hugetlb_reserve_pages(struct inode *
 						struct vm_area_struct *vma);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
 
-extern unsigned long max_huge_pages;
-extern unsigned long sysctl_overcommit_huge_pages;
 extern unsigned long hugepages_treat_as_movable;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;

@@ -181,7 +179,17 @@ struct hstate {
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 };
 
-extern struct hstate default_hstate;
+void __init hugetlb_add_hstate(unsigned order);
+struct hstate *size_to_hstate(unsigned long size);
+
+#ifndef HUGE_MAX_HSTATE
+#define HUGE_MAX_HSTATE 1
+#endif
+
+extern struct hstate hstates[HUGE_MAX_HSTATE];
+extern unsigned int default_hstate_idx;
+
+#define default_hstate (hstates[default_hstate_idx])
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 {

@@ -228,6 +236,11 @@ static inline unsigned int blocks_per_hu
 	return huge_page_size(h) / 512;
 }
 
+static inline struct hstate *page_hstate(struct page *page)
+{
+	return size_to_hstate(PAGE_SIZE << compound_order(page));
+}
+
 #else
 struct hstate {};
 #define hstate_file(f) NULL

Index: linux-2.6/kernel/sysctl.c
===================================================================
@@ -915,7 +915,7 @@ static struct ctl_table vm_table[] = {
 #ifdef CONFIG_HUGETLB_PAGE
 	 {
 		.procname	= "nr_hugepages",
-		.data		= &max_huge_pages,
+		.data		= NULL,
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= &hugetlb_sysctl_handler,

@@ -941,10 +941,12 @@ static struct ctl_table vm_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nr_overcommit_hugepages",
-		.data		= &sysctl_overcommit_huge_pages,
-		.maxlen		= sizeof(sysctl_overcommit_huge_pages),
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= &hugetlb_overcommit_handler,
+		.extra1		= (void *)&hugetlb_zero,
+		.extra2		= (void *)&hugetlb_infinity,
 	},
 #endif
 	{

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -100,6 +100,7 @@ struct hugetlbfs_config {
 	umode_t mode;
 	long	nr_blocks;
 	long	nr_inodes;
+	struct hstate *hstate;
 };
 
 struct hugetlbfs_sb_info {

@@ -108,6 +109,7 @@ struct hugetlbfs_sb_info {
 	long	max_inodes;   /* inodes allowed */
 	long	free_inodes;  /* inodes free */
 	spinlock_t	stat_lock;
+	struct hstate *hstate;
 };
 
 

@@ -191,19 +193,21 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
-static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
+static inline struct hstate *hstate_inode(struct inode *i)
 {
-	return &default_hstate;
+	struct hugetlbfs_sb_info *hsb;
+	hsb = HUGETLBFS_SB(i->i_sb);
+	return hsb->hstate;
 }
 
 static inline struct hstate *hstate_file(struct file *f)
 {
-	return &default_hstate;
+	return hstate_inode(f->f_dentry->d_inode);
 }
 
-static inline struct hstate *hstate_inode(struct inode *i)
+static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 {
-	return &default_hstate;
+	return hstate_file(vma->vm_file);
 }
 
 static inline unsigned long huge_page_size(struct hstate *h)

103 lines not on this page · raw message

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -1334,19 +1334,9 @@ void __unmap_hugepage_range(struct vm_ar
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			  unsigned long end, struct page *ref_page)
 {
-	/*
-	 * It is undesirable to test vma->vm_file as it should be non-null
-	 * for valid hugetlb area. However, vm_file will be NULL in the error
-	 * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails,
-	 * do_mmap_pgoff() nullifies vma->vm_file before calling this function
-	 * to clean up. Since no pte has actually been setup, it is safe to
-	 * do nothing in this case.
-	 */
-	if (vma->vm_file) {
-		spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
-		__unmap_hugepage_range(vma, start, end, ref_page);
-		spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
-	}
+	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+	__unmap_hugepage_range(vma, start, end, ref_page);
+	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 }
 
 /*

Index: linux-2.6/mm/memory.c
===================================================================
@@ -902,9 +902,23 @@ unsigned long unmap_vmas(struct mmu_gath
 			}
 
 			if (unlikely(is_vm_hugetlb_page(vma))) {
-				unmap_hugepage_range(vma, start, end, NULL);
-				zap_work -= (end - start) /
+				/*
+				 * It is undesirable to test vma->vm_file as it
+				 * should be non-null for valid hugetlb area.
+				 * However, vm_file will be NULL in the error
+				 * cleanup path of do_mmap_pgoff. When
+				 * hugetlbfs ->mmap method fails,
+				 * do_mmap_pgoff() nullifies vma->vm_file
+				 * before calling this function to clean up.
+				 * Since no pte has actually been setup, it is
+				 * safe to do nothing in this case.
+				 */
+				if (vma->vm_file) {
+					unmap_hugepage_range(vma, start, end, NULL);
+					zap_work -= (end - start) /
 					pages_per_huge_page(hstate_vma(vma));
+				}
+
 				start = end;
 			} else
 				start = unmap_page_range(*tlbp, vma,

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -164,6 +164,7 @@ unsigned long hugetlb_get_unmapped_area(
 
 #ifdef CONFIG_HUGETLB_PAGE
 
+#define HSTATE_NAME_LEN 32
 /* Defines one hugetlb page size */
 struct hstate {
 	int hugetlb_next_nid;

@@ -179,6 +180,7 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+	char name[HSTATE_NAME_LEN];
 };
 
 void __init hugetlb_add_hstate(unsigned order);

312 lines not on this page · raw message

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -383,6 +383,27 @@ static struct page *alloc_fresh_huge_pag
 	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;

@@ -396,21 +417,7 @@ static int alloc_fresh_huge_page(struct 
 		page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
 		if (page)
 			ret = 1;
-		/*
-		 * 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.
-		 */
-		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;
+		next_nid = hstate_next_node(h);
 	} while (!page && h->hugetlb_next_nid != start_nid);
 
 	if (ret)

Index: linux-2.6/mm/bootmem.c
===================================================================
@@ -576,6 +576,18 @@ void * __init alloc_bootmem_section(unsi
 }
 #endif
 
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	void *ptr;
+
+	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
+	if (ptr)
+		return ptr;
+
+	return __alloc_bootmem_nopanic(size, align, goal);
+}
+
 #ifndef ARCH_LOW_ADDRESS_LIMIT
 #define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
 #endif

Index: linux-2.6/include/linux/bootmem.h
===================================================================
@@ -87,6 +87,10 @@ extern void *__alloc_bootmem_node(pg_dat
 				  unsigned long size,
 				  unsigned long align,
 				  unsigned long goal);
+extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal);
 extern unsigned long init_bootmem_node(pg_data_t *pgdat,
 				       unsigned long freepfn,
 				       unsigned long startpfn,

Index: linux-2.6/mm/internal.h
===================================================================
@@ -16,6 +16,8 @@
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
+extern void prep_compound_page(struct page *page, unsigned long order);
+
 static inline void set_page_count(struct page *page, int v)
 {
 	atomic_set(&page->_count, v);

Index: linux-2.6/mm/page_alloc.c
===================================================================
@@ -288,7 +288,7 @@ static void free_compound_page(struct pa
 	__free_pages_ok(page, compound_order(page));
 }
 
-static void prep_compound_page(struct page *page, unsigned long order)
+void prep_compound_page(struct page *page, unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -14,6 +14,7 @@
 #include <linux/mempolicy.h>
 #include <linux/cpuset.h>
 #include <linux/mutex.h>
+#include <linux/bootmem.h>
 #include <linux/sysfs.h>
 
 #include <asm/page.h>

@@ -307,7 +308,7 @@ static void free_huge_page(struct page *
 	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
-	if (h->surplus_huge_pages_node[nid]) {
+	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]--;

@@ -368,6 +369,9 @@ static struct page *alloc_fresh_huge_pag
 {
 	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,

@@ -434,6 +438,9 @@ static struct page *alloc_buddy_huge_pag
 	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

@@ -610,6 +617,10 @@ static void return_unused_surplus_pages(
 	/* 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) {

@@ -838,6 +849,63 @@ static struct page *alloc_huge_page(stru
 	return page;
 }
 
+static __initdata LIST_HEAD(huge_boot_pages);
+
+struct huge_bootmem_page {
+	struct list_head list;
+	struct hstate *hstate;
+};
+
+static int __init 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;
+			if (m)
+				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;
+}
+
+/* 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_page(page, h->order);
+		prep_new_huge_page(h, page, page_to_nid(page));
+	}
+}
+
 static void __init hugetlb_init_one_hstate(struct hstate *h)
 {
 	unsigned long i;

@@ -848,7 +916,10 @@ static void __init hugetlb_init_one_hsta
 	h->hugetlb_next_nid = first_node(node_online_map);
 
 	for (i = 0; i < h->max_huge_pages; ++i) {
-		if (!alloc_fresh_huge_page(h))
+		if (h->order >= MAX_ORDER) {
+			if (!alloc_bootmem_huge_page(h))
+				break;
+		} else if (!alloc_fresh_huge_page(h))
 			break;
 	}
 	h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;

@@ -881,6 +952,9 @@ static void try_to_free_low(struct hstat
 {
 	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];